Merge branch 'for-3.5' of ../cgroup into block/for-3.5/core-merged

cgroup/for-3.5 contains the following changes which blk-cgroup needs
to proceed with the on-going cleanup.

* Dynamic addition and removal of cftypes to make config/stat file
  handling modular for policies.

* cgroup removal update to not wait for css references to drain to fix
  blkcg removal hang caused by cfq caching cfqgs.

Pull in cgroup/for-3.5 into block/for-3.5/core.  This causes the
following conflicts in block/blk-cgroup.c.

* 761b3ef50e "cgroup: remove cgroup_subsys argument from callbacks"
  conflicts with blkiocg_pre_destroy() addition and blkiocg_attach()
  removal.  Resolved by removing @subsys from all subsys methods.

* 676f7c8f84 "cgroup: relocate cftype and cgroup_subsys definitions in
  controllers" conflicts with ->pre_destroy() and ->attach() updates
  and removal of modular config.  Resolved by dropping forward
  declarations of the methods and applying updates to the relocated
  blkio_subsys.

* 4baf6e3325 "cgroup: convert all non-memcg controllers to the new
  cftype interface" builds upon the previous item.  Resolved by adding
  ->base_cftypes to the relocated blkio_subsys.

Signed-off-by: Tejun Heo <tj@kernel.org>

86 files changed, 3266 insertions, 1985 deletions

diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index d1727584230a..2b7c0fbe578e 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -64,6 +64,7 @@ config ARCH_SUPPORTS_DEBUG_PAGEALLOC
 config S390
 	def_bool y
 	select USE_GENERIC_SMP_HELPERS if SMP
+	select GENERIC_CPU_DEVICES if !SMP
 	select HAVE_SYSCALL_WRAPPERS
 	select HAVE_FUNCTION_TRACER
 	select HAVE_FUNCTION_TRACE_MCOUNT_TEST
@@ -218,6 +219,7 @@ config COMPAT
 	prompt "Kernel support for 31 bit emulation"
 	depends on 64BIT
 	select COMPAT_BINFMT_ELF
+	select ARCH_WANT_OLD_COMPAT_IPC
 	help
 	  Select this option if you want to enable your system kernel to
 	  handle system-calls from ELF binaries for 31 bit ESA.  This option
@@ -227,6 +229,9 @@ config COMPAT
 config SYSVIPC_COMPAT
 	def_bool y if COMPAT && SYSVIPC
 
+config KEYS_COMPAT
+	def_bool y if COMPAT && KEYS
+
 config AUDIT_ARCH
 	def_bool y
 
diff --git a/arch/s390/crypto/crypt_s390.h b/arch/s390/crypto/crypt_s390.h
index ffd1ac255f19..9178db6db0a5 100644
--- a/arch/s390/crypto/crypt_s390.h
+++ b/arch/s390/crypto/crypt_s390.h
@@ -17,6 +17,7 @@
 #define _CRYPTO_ARCH_S390_CRYPT_S390_H
 
 #include <asm/errno.h>
+#include <asm/facility.h>
 
 #define CRYPT_S390_OP_MASK 0xFF00
 #define CRYPT_S390_FUNC_MASK 0x00FF
diff --git a/arch/s390/hypfs/inode.c b/arch/s390/hypfs/inode.c
index 8a2a887478cc..6a2cb560e968 100644
--- a/arch/s390/hypfs/inode.c
+++ b/arch/s390/hypfs/inode.c
@@ -293,11 +293,9 @@ static int hypfs_fill_super(struct super_block *sb, void *data, int silent)
 		return -ENOMEM;
 	root_inode->i_op = &simple_dir_inode_operations;
 	root_inode->i_fop = &simple_dir_operations;
-	sb->s_root = root_dentry = d_alloc_root(root_inode);
-	if (!root_dentry) {
-		iput(root_inode);
+	sb->s_root = root_dentry = d_make_root(root_inode);
+	if (!root_dentry)
 		return -ENOMEM;
-	}
 	if (MACHINE_IS_VM)
 		rc = hypfs_vm_create_files(sb, root_dentry);
 	else
diff --git a/arch/s390/include/asm/atomic.h b/arch/s390/include/asm/atomic.h
index 8517d2ae3b5c..748347baecb8 100644
--- a/arch/s390/include/asm/atomic.h
+++ b/arch/s390/include/asm/atomic.h
@@ -15,7 +15,7 @@
 
 #include <linux/compiler.h>
 #include <linux/types.h>
-#include <asm/system.h>
+#include <asm/cmpxchg.h>
 
 #define ATOMIC_INIT(i)  { (i) }
 
diff --git a/arch/s390/include/asm/barrier.h b/arch/s390/include/asm/barrier.h
new file mode 100644
index 000000000000..451273ad4d34
--- /dev/null
+++ b/arch/s390/include/asm/barrier.h
@@ -0,0 +1,35 @@
+/*
+ * Copyright IBM Corp. 1999, 2009
+ *
+ * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
+ */
+
+#ifndef __ASM_BARRIER_H
+#define __ASM_BARRIER_H
+
+/*
+ * Force strict CPU ordering.
+ * And yes, this is required on UP too when we're talking
+ * to devices.
+ *
+ * This is very similar to the ppc eieio/sync instruction in that is
+ * does a checkpoint syncronisation & makes sure that 
+ * all memory ops have completed wrt other CPU's ( see 7-15 POP  DJB ).
+ */
+
+#define eieio()	asm volatile("bcr 15,0" : : : "memory")
+#define SYNC_OTHER_CORES(x)   eieio()
+#define mb()    eieio()
+#define rmb()   eieio()
+#define wmb()   eieio()
+#define read_barrier_depends() do { } while(0)
+#define smp_mb()       mb()
+#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 set_mb(var, value)      do { var = value; mb(); } while (0)
+
+#endif /* __ASM_BARRIER_H */
diff --git a/arch/s390/include/asm/compat.h b/arch/s390/include/asm/compat.h
index 2e49748b27da..234f1d859cea 100644
--- a/arch/s390/include/asm/compat.h
+++ b/arch/s390/include/asm/compat.h
@@ -172,13 +172,6 @@ static inline int is_compat_task(void)
 	return is_32bit_task();
 }
 
-#else
-
-static inline int is_compat_task(void)
-{
-	return 0;
-}
-
 #endif
 
 static inline void __user *arch_compat_alloc_user_space(long len)
diff --git a/arch/s390/include/asm/cpu_mf.h b/arch/s390/include/asm/cpu_mf.h
new file mode 100644
index 000000000000..a3afecdae145
--- /dev/null
+++ b/arch/s390/include/asm/cpu_mf.h
@@ -0,0 +1,97 @@
+/*
+ * CPU-measurement facilities
+ *
+ *  Copyright IBM Corp. 2012
+ *  Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
+ *	       Jan Glauber <jang@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ */
+#ifndef _ASM_S390_CPU_MF_H
+#define _ASM_S390_CPU_MF_H
+
+#include <asm/facility.h>
+
+#define CPU_MF_INT_SF_IAE	(1 << 31)	/* invalid entry address */
+#define CPU_MF_INT_SF_ISE	(1 << 30)	/* incorrect SDBT entry */
+#define CPU_MF_INT_SF_PRA	(1 << 29)	/* program request alert */
+#define CPU_MF_INT_SF_SACA	(1 << 23)	/* sampler auth. change alert */
+#define CPU_MF_INT_SF_LSDA	(1 << 22)	/* loss of sample data alert */
+#define CPU_MF_INT_CF_CACA	(1 <<  7)	/* counter auth. change alert */
+#define CPU_MF_INT_CF_LCDA	(1 <<  6)	/* loss of counter data alert */
+
+#define CPU_MF_INT_CF_MASK	(CPU_MF_INT_CF_CACA|CPU_MF_INT_CF_LCDA)
+#define CPU_MF_INT_SF_MASK	(CPU_MF_INT_SF_IAE|CPU_MF_INT_SF_ISE|	\
+				 CPU_MF_INT_SF_PRA|CPU_MF_INT_SF_SACA|	\
+				 CPU_MF_INT_SF_LSDA)
+
+/* CPU measurement facility support */
+static inline int cpum_cf_avail(void)
+{
+	return MACHINE_HAS_SPP && test_facility(67);
+}
+
+static inline int cpum_sf_avail(void)
+{
+	return MACHINE_HAS_SPP && test_facility(68);
+}
+
+
+struct cpumf_ctr_info {
+	u16   cfvn;
+	u16   auth_ctl;
+	u16   enable_ctl;
+	u16   act_ctl;
+	u16   max_cpu;
+	u16   csvn;
+	u16   max_cg;
+	u16   reserved1;
+	u32   reserved2[12];
+} __packed;
+
+/* Query counter information */
+static inline int qctri(struct cpumf_ctr_info *info)
+{
+	int rc = -EINVAL;
+
+	asm volatile (
+		"0:	.insn	s,0xb28e0000,%1\n"
+		"1:	lhi	%0,0\n"
+		"2:\n"
+		EX_TABLE(1b, 2b)
+		: "+d" (rc), "=Q" (*info));
+	return rc;
+}
+
+/* Load CPU-counter-set controls */
+static inline int lcctl(u64 ctl)
+{
+	int cc;
+
+	asm volatile (
+		"	.insn	s,0xb2840000,%1\n"
+		"	ipm	%0\n"
+		"	srl	%0,28\n"
+		: "=d" (cc) : "m" (ctl) : "cc");
+	return cc;
+}
+
+/* Extract CPU counter */
+static inline int ecctr(u64 ctr, u64 *val)
+{
+	register u64 content asm("4") = 0;
+	int cc;
+
+	asm volatile (
+		"	.insn	rre,0xb2e40000,%0,%2\n"
+		"	ipm	%1\n"
+		"	srl	%1,28\n"
+		: "=d" (content), "=d" (cc) : "d" (ctr) : "cc");
+	if (!cc)
+		*val = content;
+	return cc;
+}
+
+#endif /* _ASM_S390_CPU_MF_H */
diff --git a/arch/s390/include/asm/cputime.h b/arch/s390/include/asm/cputime.h
index c23c3900c304..24ef186a1c4f 100644
--- a/arch/s390/include/asm/cputime.h
+++ b/arch/s390/include/asm/cputime.h
@@ -170,24 +170,17 @@ struct s390_idle_data {
 	unsigned int sequence;
 	unsigned long long idle_count;
 	unsigned long long idle_enter;
+	unsigned long long idle_exit;
 	unsigned long long idle_time;
 	int nohz_delay;
 };
 
 DECLARE_PER_CPU(struct s390_idle_data, s390_idle);
 
-void vtime_start_cpu(__u64 int_clock, __u64 enter_timer);
 cputime64_t s390_get_idle_time(int cpu);
 
 #define arch_idle_time(cpu) s390_get_idle_time(cpu)
 
-static inline void s390_idle_check(struct pt_regs *regs, __u64 int_clock,
-				   __u64 enter_timer)
-{
-	if (regs->psw.mask & PSW_MASK_WAIT)
-		vtime_start_cpu(int_clock, enter_timer);
-}
-
 static inline int s390_nohz_delay(int cpu)
 {
 	return __get_cpu_var(s390_idle).nohz_delay != 0;
diff --git a/arch/s390/include/asm/ctl_reg.h b/arch/s390/include/asm/ctl_reg.h
new file mode 100644
index 000000000000..ecde9417d669
--- /dev/null
+++ b/arch/s390/include/asm/ctl_reg.h
@@ -0,0 +1,76 @@
+/*
+ * Copyright IBM Corp. 1999, 2009
+ *
+ * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
+ */
+
+#ifndef __ASM_CTL_REG_H
+#define __ASM_CTL_REG_H
+
+#ifdef __s390x__
+
+#define __ctl_load(array, low, high) ({				\
+	typedef struct { char _[sizeof(array)]; } addrtype;	\
+	asm volatile(						\
+		"	lctlg	%1,%2,%0\n"			\
+		: : "Q" (*(addrtype *)(&array)),		\
+		    "i" (low), "i" (high));			\
+	})
+
+#define __ctl_store(array, low, high) ({			\
+	typedef struct { char _[sizeof(array)]; } addrtype;	\
+	asm volatile(						\
+		"	stctg	%1,%2,%0\n"			\
+		: "=Q" (*(addrtype *)(&array))			\
+		: "i" (low), "i" (high));			\
+	})
+
+#else /* __s390x__ */
+
+#define __ctl_load(array, low, high) ({				\
+	typedef struct { char _[sizeof(array)]; } addrtype;	\
+	asm volatile(						\
+		"	lctl	%1,%2,%0\n"			\
+		: : "Q" (*(addrtype *)(&array)),		\
+		    "i" (low), "i" (high));			\
+})
+
+#define __ctl_store(array, low, high) ({			\
+	typedef struct { char _[sizeof(array)]; } addrtype;	\
+	asm volatile(						\
+		"	stctl	%1,%2,%0\n"			\
+		: "=Q" (*(addrtype *)(&array))			\
+		: "i" (low), "i" (high));			\
+	})
+
+#endif /* __s390x__ */
+
+#define __ctl_set_bit(cr, bit) ({	\
+	unsigned long __dummy;		\
+	__ctl_store(__dummy, cr, cr);	\
+	__dummy |= 1UL << (bit);	\
+	__ctl_load(__dummy, cr, cr);	\
+})
+
+#define __ctl_clear_bit(cr, bit) ({	\
+	unsigned long __dummy;		\
+	__ctl_store(__dummy, cr, cr);	\
+	__dummy &= ~(1UL << (bit));	\
+	__ctl_load(__dummy, cr, cr);	\
+})
+
+#ifdef CONFIG_SMP
+
+extern void smp_ctl_set_bit(int cr, int bit);
+extern void smp_ctl_clear_bit(int cr, int bit);
+#define ctl_set_bit(cr, bit) smp_ctl_set_bit(cr, bit)
+#define ctl_clear_bit(cr, bit) smp_ctl_clear_bit(cr, bit)
+
+#else
+
+#define ctl_set_bit(cr, bit) __ctl_set_bit(cr, bit)
+#define ctl_clear_bit(cr, bit) __ctl_clear_bit(cr, bit)
+
+#endif /* CONFIG_SMP */
+
+#endif /* __ASM_CTL_REG_H */
diff --git a/arch/s390/include/asm/debug.h b/arch/s390/include/asm/debug.h
index 9d88db1f55d0..8a8245ed14d2 100644
--- a/arch/s390/include/asm/debug.h
+++ b/arch/s390/include/asm/debug.h
@@ -131,6 +131,7 @@ void debug_unregister(debug_info_t* id);
 
 void debug_set_level(debug_info_t* id, int new_level);
 
+void debug_set_critical(void);
 void debug_stop_all(void);
 
 static inline debug_entry_t*
diff --git a/arch/s390/include/asm/elf.h b/arch/s390/include/asm/elf.h
index 547f1a6a35d4..c4ee39f7a4d6 100644
--- a/arch/s390/include/asm/elf.h
+++ b/arch/s390/include/asm/elf.h
@@ -129,7 +129,6 @@ typedef s390_fp_regs compat_elf_fpregset_t;
 typedef s390_compat_regs compat_elf_gregset_t;
 
 #include <linux/sched.h>	/* for task_struct */
-#include <asm/system.h>		/* for save_access_regs */
 #include <asm/mmu_context.h>
 
 #include <asm/vdso.h>
diff --git a/arch/s390/include/asm/exec.h b/arch/s390/include/asm/exec.h
new file mode 100644
index 000000000000..c4a93d6327fa
--- /dev/null
+++ b/arch/s390/include/asm/exec.h
@@ -0,0 +1,12 @@
+/*
+ * Copyright IBM Corp. 1999, 2009
+ *
+ * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
+ */
+
+#ifndef __ASM_EXEC_H
+#define __ASM_EXEC_H
+
+extern unsigned long arch_align_stack(unsigned long sp);
+
+#endif /* __ASM_EXEC_H */
diff --git a/arch/s390/include/asm/facility.h b/arch/s390/include/asm/facility.h
new file mode 100644
index 000000000000..1e5b27edc0c9
--- /dev/null
+++ b/arch/s390/include/asm/facility.h
@@ -0,0 +1,63 @@
+/*
+ * Copyright IBM Corp. 1999, 2009
+ *
+ * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
+ */
+
+#ifndef __ASM_FACILITY_H
+#define __ASM_FACILITY_H
+
+#include <linux/string.h>
+#include <linux/preempt.h>
+#include <asm/lowcore.h>
+
+#define MAX_FACILITY_BIT (256*8)	/* stfle_fac_list has 256 bytes */
+
+/*
+ * The test_facility function uses the bit odering where the MSB is bit 0.
+ * That makes it easier to query facility bits with the bit number as
+ * documented in the Principles of Operation.
+ */
+static inline int test_facility(unsigned long nr)
+{
+	unsigned char *ptr;
+
+	if (nr >= MAX_FACILITY_BIT)
+		return 0;
+	ptr = (unsigned char *) &S390_lowcore.stfle_fac_list + (nr >> 3);
+	return (*ptr & (0x80 >> (nr & 7))) != 0;
+}
+
+/**
+ * stfle - Store facility list extended
+ * @stfle_fac_list: array where facility list can be stored
+ * @size: size of passed in array in double words
+ */
+static inline void stfle(u64 *stfle_fac_list, int size)
+{
+	unsigned long nr;
+
+	preempt_disable();
+	S390_lowcore.stfl_fac_list = 0;
+	asm volatile(
+		"	.insn s,0xb2b10000,0(0)\n" /* stfl */
+		"0:\n"
+		EX_TABLE(0b, 0b)
+		: "=m" (S390_lowcore.stfl_fac_list));
+	nr = 4; /* bytes stored by stfl */
+	memcpy(stfle_fac_list, &S390_lowcore.stfl_fac_list, 4);
+	if (S390_lowcore.stfl_fac_list & 0x01000000) {
+		/* More facility bits available with stfle */
+		register unsigned long reg0 asm("0") = size - 1;
+
+		asm volatile(".insn s,0xb2b00000,0(%1)" /* stfle */
+			     : "+d" (reg0)
+			     : "a" (stfle_fac_list)
+			     : "memory", "cc");
+		nr = (reg0 + 1) * 8; /* # bytes stored by stfle */
+	}
+	memset((char *) stfle_fac_list + nr, 0, size * 8 - nr);
+	preempt_enable();
+}
+
+#endif /* __ASM_FACILITY_H */
diff --git a/arch/s390/include/asm/hardirq.h b/arch/s390/include/asm/hardirq.h
index e4155d3eb2cb..510ba9ef4248 100644
--- a/arch/s390/include/asm/hardirq.h
+++ b/arch/s390/include/asm/hardirq.h
@@ -18,6 +18,7 @@
 
 #define __ARCH_IRQ_STAT
 #define __ARCH_HAS_DO_SOFTIRQ
+#define __ARCH_IRQ_EXIT_IRQS_DISABLED
 
 #define HARDIRQ_BITS	8
 
diff --git a/arch/s390/include/asm/ipl.h b/arch/s390/include/asm/ipl.h
index 6940abfbe1d9..2bd6cb897b90 100644
--- a/arch/s390/include/asm/ipl.h
+++ b/arch/s390/include/asm/ipl.h
@@ -169,5 +169,6 @@ enum diag308_rc {
 extern int diag308(unsigned long subcode, void *addr);
 extern void diag308_reset(void);
 extern void store_status(void);
+extern void lgr_info_log(void);
 
 #endif /* _ASM_S390_IPL_H */
diff --git a/arch/s390/include/asm/irq.h b/arch/s390/include/asm/irq.h
index ba6d85f88d50..5289cacd4861 100644
--- a/arch/s390/include/asm/irq.h
+++ b/arch/s390/include/asm/irq.h
@@ -34,11 +34,18 @@ enum interruption_class {
 	NR_IRQS,
 };
 
-typedef void (*ext_int_handler_t)(unsigned int, unsigned int, unsigned long);
+struct ext_code {
+	unsigned short subcode;
+	unsigned short code;
+};
+
+typedef void (*ext_int_handler_t)(struct ext_code, unsigned int, unsigned long);
 
 int register_external_interrupt(u16 code, ext_int_handler_t handler);
 int unregister_external_interrupt(u16 code, ext_int_handler_t handler);
 void service_subclass_irq_register(void);
 void service_subclass_irq_unregister(void);
+void measurement_alert_subclass_register(void);
+void measurement_alert_subclass_unregister(void);
 
 #endif /* _ASM_IRQ_H */
diff --git a/arch/s390/include/asm/jump_label.h b/arch/s390/include/asm/jump_label.h
index 95a6cf2b5b67..6c32190dc73e 100644
--- a/arch/s390/include/asm/jump_label.h
+++ b/arch/s390/include/asm/jump_label.h
@@ -13,7 +13,7 @@
 #define ASM_ALIGN ".balign 4"
 #endif
 
-static __always_inline bool arch_static_branch(struct jump_label_key *key)
+static __always_inline bool arch_static_branch(struct static_key *key)
 {
 	asm goto("0:	brcl 0,0\n"
 		".pushsection __jump_table, \"aw\"\n"
diff --git a/arch/s390/include/asm/kvm.h b/arch/s390/include/asm/kvm.h
index 82b32a100c7d..96076676e224 100644
--- a/arch/s390/include/asm/kvm.h
+++ b/arch/s390/include/asm/kvm.h
@@ -41,4 +41,15 @@ struct kvm_debug_exit_arch {
 struct kvm_guest_debug_arch {
 };
 
+#define KVM_SYNC_PREFIX (1UL << 0)
+#define KVM_SYNC_GPRS   (1UL << 1)
+#define KVM_SYNC_ACRS   (1UL << 2)
+#define KVM_SYNC_CRS    (1UL << 3)
+/* definition of registers in kvm_run */
+struct kvm_sync_regs {
+	__u64 prefix;	/* prefix register */
+	__u64 gprs[16];	/* general purpose registers */
+	__u32 acrs[16];	/* access registers */
+	__u64 crs[16];	/* control registers */
+};
 #endif
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index b0c235cb6ad5..7343872890a2 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -220,18 +220,17 @@ struct kvm_s390_float_interrupt {
 	struct list_head list;
 	atomic_t active;
 	int next_rr_cpu;
-	unsigned long idle_mask [(64 + sizeof(long) - 1) / sizeof(long)];
-	struct kvm_s390_local_interrupt *local_int[64];
+	unsigned long idle_mask[(KVM_MAX_VCPUS + sizeof(long) - 1)
+				/ sizeof(long)];
+	struct kvm_s390_local_interrupt *local_int[KVM_MAX_VCPUS];
 };
 
 
 struct kvm_vcpu_arch {
 	struct kvm_s390_sie_block *sie_block;
-	unsigned long	  guest_gprs[16];
 	s390_fp_regs      host_fpregs;
 	unsigned int      host_acrs[NUM_ACRS];
 	s390_fp_regs      guest_fpregs;
-	unsigned int      guest_acrs[NUM_ACRS];
 	struct kvm_s390_local_interrupt local_int;
 	struct hrtimer    ckc_timer;
 	struct tasklet_struct tasklet;
@@ -246,6 +245,9 @@ struct kvm_vm_stat {
 	u32 remote_tlb_flush;
 };
 
+struct kvm_arch_memory_slot {
+};
+
 struct kvm_arch{
 	struct sca_block *sca;
 	debug_info_t *dbf;
@@ -253,5 +255,5 @@ struct kvm_arch{
 	struct gmap *gmap;
 };
 
-extern int sie64a(struct kvm_s390_sie_block *, unsigned long *);
+extern int sie64a(struct kvm_s390_sie_block *, u64 *);
 #endif
diff --git a/arch/s390/include/asm/lowcore.h b/arch/s390/include/asm/lowcore.h
index 707f2306725b..47853debb3b9 100644
--- a/arch/s390/include/asm/lowcore.h
+++ b/arch/s390/include/asm/lowcore.h
@@ -1,5 +1,5 @@
 /*
- *    Copyright IBM Corp. 1999,2010
+ *    Copyright IBM Corp. 1999,2012
  *    Author(s): Hartmut Penner <hp@de.ibm.com>,
  *		 Martin Schwidefsky <schwidefsky@de.ibm.com>,
  *		 Denis Joseph Barrow,
@@ -12,14 +12,6 @@
 #include <asm/ptrace.h>
 #include <asm/cpu.h>
 
-void restart_int_handler(void);
-void ext_int_handler(void);
-void system_call(void);
-void pgm_check_handler(void);
-void mcck_int_handler(void);
-void io_int_handler(void);
-void psw_restart_int_handler(void);
-
 #ifdef CONFIG_32BIT
 
 #define LC_ORDER 0
@@ -56,7 +48,7 @@ struct _lowcore {
 	psw_t	mcck_new_psw;			/* 0x0070 */
 	psw_t	io_new_psw;			/* 0x0078 */
 	__u32	ext_params;			/* 0x0080 */
-	__u16	cpu_addr;			/* 0x0084 */
+	__u16	ext_cpu_addr;			/* 0x0084 */
 	__u16	ext_int_code;			/* 0x0086 */
 	__u16	svc_ilc;			/* 0x0088 */
 	__u16	svc_code;			/* 0x008a */
@@ -117,32 +109,37 @@ struct _lowcore {
 	__u64	steal_timer;			/* 0x0288 */
 	__u64	last_update_timer;		/* 0x0290 */
 	__u64	last_update_clock;		/* 0x0298 */
+	__u64	int_clock;			/* 0x02a0 */
+	__u64	mcck_clock;			/* 0x02a8 */
+	__u64	clock_comparator;		/* 0x02b0 */
 
 	/* Current process. */
-	__u32	current_task;			/* 0x02a0 */
-	__u32	thread_info;			/* 0x02a4 */
-	__u32	kernel_stack;			/* 0x02a8 */
+	__u32	current_task;			/* 0x02b8 */
+	__u32	thread_info;			/* 0x02bc */
+	__u32	kernel_stack;			/* 0x02c0 */
+
+	/* Interrupt, panic and restart stack. */
+	__u32	async_stack;			/* 0x02c4 */
+	__u32	panic_stack;			/* 0x02c8 */
+	__u32	restart_stack;			/* 0x02cc */
 
-	/* Interrupt and panic stack. */
-	__u32	async_stack;			/* 0x02ac */
-	__u32	panic_stack;			/* 0x02b0 */
+	/* Restart function and parameter. */
+	__u32	restart_fn;			/* 0x02d0 */
+	__u32	restart_data;			/* 0x02d4 */
+	__u32	restart_source;			/* 0x02d8 */
 
 	/* Address space pointer. */
-	__u32	kernel_asce;			/* 0x02b4 */
-	__u32	user_asce;			/* 0x02b8 */
-	__u32	current_pid;			/* 0x02bc */
+	__u32	kernel_asce;			/* 0x02dc */
+	__u32	user_asce;			/* 0x02e0 */
+	__u32	current_pid;			/* 0x02e4 */
 
 	/* SMP info area */
-	__u32	cpu_nr;				/* 0x02c0 */
-	__u32	softirq_pending;		/* 0x02c4 */
-	__u32	percpu_offset;			/* 0x02c8 */
-	__u32	ext_call_fast;			/* 0x02cc */
-	__u64	int_clock;			/* 0x02d0 */
-	__u64	mcck_clock;			/* 0x02d8 */
-	__u64	clock_comparator;		/* 0x02e0 */
-	__u32	machine_flags;			/* 0x02e8 */
-	__u32	ftrace_func;			/* 0x02ec */
-	__u8	pad_0x02f8[0x0300-0x02f0];	/* 0x02f0 */
+	__u32	cpu_nr;				/* 0x02e8 */
+	__u32	softirq_pending;		/* 0x02ec */
+	__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 */
@@ -157,7 +154,9 @@ struct _lowcore {
 	__u32	ipib;				/* 0x0e00 */
 	__u32	ipib_checksum;			/* 0x0e04 */
 	__u32	vmcore_info;			/* 0x0e08 */
-	__u8	pad_0x0e0c[0x0f00-0x0e0c];	/* 0x0e0c */
+	__u8	pad_0x0e0c[0x0e18-0x0e0c];	/* 0x0e0c */
+	__u32	os_info;			/* 0x0e18 */
+	__u8	pad_0x0e1c[0x0f00-0x0e1c];	/* 0x0e1c */
 
 	/* Extended facility list */
 	__u64	stfle_fac_list[32];		/* 0x0f00 */
@@ -189,7 +188,7 @@ struct _lowcore {
 	__u32	ipl_parmblock_ptr;		/* 0x0014 */
 	__u8	pad_0x0018[0x0080-0x0018];	/* 0x0018 */
 	__u32	ext_params;			/* 0x0080 */
-	__u16	cpu_addr;			/* 0x0084 */
+	__u16	ext_cpu_addr;			/* 0x0084 */
 	__u16	ext_int_code;			/* 0x0086 */
 	__u16	svc_ilc;			/* 0x0088 */
 	__u16	svc_code;			/* 0x008a */
@@ -254,34 +253,39 @@ struct _lowcore {
 	__u64	steal_timer;			/* 0x02e0 */
 	__u64	last_update_timer;		/* 0x02e8 */
 	__u64	last_update_clock;		/* 0x02f0 */
+	__u64	int_clock;			/* 0x02f8 */
+	__u64	mcck_clock;			/* 0x0300 */
+	__u64	clock_comparator;		/* 0x0308 */
 
 	/* Current process. */
-	__u64	current_task;			/* 0x02f8 */
-	__u64	thread_info;			/* 0x0300 */
-	__u64	kernel_stack;			/* 0x0308 */
+	__u64	current_task;			/* 0x0310 */
+	__u64	thread_info;			/* 0x0318 */
+	__u64	kernel_stack;			/* 0x0320 */
+
+	/* Interrupt, panic and restart stack. */
+	__u64	async_stack;			/* 0x0328 */
+	__u64	panic_stack;			/* 0x0330 */
+	__u64	restart_stack;			/* 0x0338 */
 
-	/* Interrupt and panic stack. */
-	__u64	async_stack;			/* 0x0310 */
-	__u64	panic_stack;			/* 0x0318 */
+	/* Restart function and parameter. */
+	__u64	restart_fn;			/* 0x0340 */
+	__u64	restart_data;			/* 0x0348 */
+	__u64	restart_source;			/* 0x0350 */
 
 	/* Address space pointer. */
-	__u64	kernel_asce;			/* 0x0320 */
-	__u64	user_asce;			/* 0x0328 */
-	__u64	current_pid;			/* 0x0330 */
+	__u64	kernel_asce;			/* 0x0358 */
+	__u64	user_asce;			/* 0x0360 */
+	__u64	current_pid;			/* 0x0368 */
 
 	/* SMP info area */
-	__u32	cpu_nr;				/* 0x0338 */
-	__u32	softirq_pending;		/* 0x033c */
-	__u64	percpu_offset;			/* 0x0340 */
-	__u64	ext_call_fast;			/* 0x0348 */
-	__u64	int_clock;			/* 0x0350 */
-	__u64	mcck_clock;			/* 0x0358 */
-	__u64	clock_comparator;		/* 0x0360 */
-	__u64	vdso_per_cpu_data;		/* 0x0368 */
-	__u64	machine_flags;			/* 0x0370 */
-	__u64	ftrace_func;			/* 0x0378 */
-	__u64	gmap;				/* 0x0380 */
-	__u8	pad_0x0388[0x0400-0x0388];	/* 0x0388 */
+	__u32	cpu_nr;				/* 0x0370 */
+	__u32	softirq_pending;		/* 0x0374 */
+	__u64	percpu_offset;			/* 0x0378 */
+	__u64	vdso_per_cpu_data;		/* 0x0380 */
+	__u64	machine_flags;			/* 0x0388 */
+	__u64	ftrace_func;			/* 0x0390 */
+	__u64	gmap;				/* 0x0398 */
+	__u8	pad_0x03a0[0x0400-0x03a0];	/* 0x03a0 */
 
 	/* Interrupt response block. */
 	__u8	irb[64];			/* 0x0400 */
@@ -298,8 +302,15 @@ struct _lowcore {
 	 */
 	__u64	ipib;				/* 0x0e00 */
 	__u32	ipib_checksum;			/* 0x0e08 */
-	__u64	vmcore_info;			/* 0x0e0c */
-	__u8	pad_0x0e14[0x0f00-0x0e14];	/* 0x0e14 */
+	/*
+	 * Because the vmcore_info pointer is not 8 byte aligned it never
+	 * should not be accessed directly. For accessing the pointer, first
+	 * copy it to a local pointer variable.
+	 */
+	__u8	vmcore_info[8];			/* 0x0e0c */
+	__u8	pad_0x0e14[0x0e18-0x0e14];	/* 0x0e14 */
+	__u64	os_info;			/* 0x0e18 */
+	__u8	pad_0x0e20[0x0f00-0x0e20];	/* 0x0e20 */
 
 	/* Extended facility list */
 	__u64	stfle_fac_list[32];		/* 0x0f00 */
diff --git a/arch/s390/include/asm/mmu.h b/arch/s390/include/asm/mmu.h
index 4506791adcd5..6340178748bf 100644
--- a/arch/s390/include/asm/mmu.h
+++ b/arch/s390/include/asm/mmu.h
@@ -1,6 +1,8 @@
 #ifndef __MMU_H
 #define __MMU_H
 
+#include <linux/errno.h>
+
 typedef struct {
 	atomic_t attach_count;
 	unsigned int flush_mm;
@@ -21,4 +23,18 @@ typedef struct {
 	.context.pgtable_list = LIST_HEAD_INIT(name.context.pgtable_list),    \
 	.context.gmap_list = LIST_HEAD_INIT(name.context.gmap_list),
 
+static inline int tprot(unsigned long addr)
+{
+	int rc = -EFAULT;
+
+	asm volatile(
+		"	tprot	0(%1),0\n"
+		"0:	ipm	%0\n"
+		"	srl	%0,28\n"
+		"1:\n"
+		EX_TABLE(0b,1b)
+		: "+d" (rc) : "a" (addr) : "cc");
+	return rc;
+}
+
 #endif
diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h
index 5682f160ff82..5d09e405c54d 100644
--- a/arch/s390/include/asm/mmu_context.h
+++ b/arch/s390/include/asm/mmu_context.h
@@ -12,6 +12,7 @@
 #include <asm/pgalloc.h>
 #include <asm/uaccess.h>
 #include <asm/tlbflush.h>
+#include <asm/ctl_reg.h>
 #include <asm-generic/mm_hooks.h>
 
 static inline int init_new_context(struct task_struct *tsk,
diff --git a/arch/s390/include/asm/os_info.h b/arch/s390/include/asm/os_info.h
new file mode 100644
index 000000000000..d07518af09ea
--- /dev/null
+++ b/arch/s390/include/asm/os_info.h
@@ -0,0 +1,50 @@
+/*
+ * OS info memory interface
+ *
+ * Copyright IBM Corp. 2012
+ * Author(s): Michael Holzheu <holzheu@linux.vnet.ibm.com>
+ */
+#ifndef _ASM_S390_OS_INFO_H
+#define _ASM_S390_OS_INFO_H
+
+#define OS_INFO_VERSION_MAJOR	1
+#define OS_INFO_VERSION_MINOR	1
+#define OS_INFO_MAGIC		0x4f53494e464f535aULL /* OSINFOSZ */
+
+#define OS_INFO_VMCOREINFO	0
+#define OS_INFO_REIPL_BLOCK	1
+#define OS_INFO_INIT_FN		2
+
+struct os_info_entry {
+	u64	addr;
+	u64	size;
+	u32	csum;
+} __packed;
+
+struct os_info {
+	u64	magic;
+	u32	csum;
+	u16	version_major;
+	u16	version_minor;
+	u64	crashkernel_addr;
+	u64	crashkernel_size;
+	struct os_info_entry entry[3];
+	u8	reserved[4004];
+} __packed;
+
+void os_info_init(void);
+void os_info_entry_add(int nr, void *ptr, u64 len);
+void os_info_crashkernel_add(unsigned long base, unsigned long size);
+u32 os_info_csum(struct os_info *os_info);
+
+#ifdef CONFIG_CRASH_DUMP
+void *os_info_old_entry(int nr, unsigned long *size);
+int copy_from_oldmem(void *dest, void *src, size_t count);
+#else
+static inline void *os_info_old_entry(int nr, unsigned long *size)
+{
+	return NULL;
+}
+#endif
+
+#endif /* _ASM_S390_OS_INFO_H */
diff --git a/arch/s390/include/asm/perf_event.h b/arch/s390/include/asm/perf_event.h
index a75f168d2718..7941968e12b4 100644
--- a/arch/s390/include/asm/perf_event.h
+++ b/arch/s390/include/asm/perf_event.h
@@ -1,9 +1,16 @@
 /*
  * Performance event support - s390 specific definitions.
  *
- * Copyright 2009 Martin Schwidefsky, IBM Corporation.
+ * Copyright IBM Corp. 2009, 2012
+ * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
+ *	      Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
  */
 
-/* Empty, just to avoid compiling error */
+#include <asm/cpu_mf.h>
 
-#define PERF_EVENT_INDEX_OFFSET 0
+/* CPU-measurement counter facility */
+#define PERF_CPUM_CF_MAX_CTR		160
+
+/* Per-CPU flags for PMU states */
+#define PMU_F_RESERVED			0x1000
+#define PMU_F_ENABLED			0x2000
diff --git a/arch/s390/include/asm/posix_types.h b/arch/s390/include/asm/posix_types.h
index 8cc113f92523..edf8527ff08d 100644
--- a/arch/s390/include/asm/posix_types.h
+++ b/arch/s390/include/asm/posix_types.h
@@ -3,7 +3,6 @@
  *
  *  S390 version
  *
- *  Derived from "include/asm-i386/posix_types.h"
  */
 
 #ifndef __ARCH_S390_POSIX_TYPES_H
@@ -15,22 +14,11 @@
  * assume GCC is being used.
  */
 
-typedef long            __kernel_off_t;
-typedef int             __kernel_pid_t;
 typedef unsigned long   __kernel_size_t;
-typedef long            __kernel_time_t;
-typedef long            __kernel_suseconds_t;
-typedef long            __kernel_clock_t;
-typedef int		__kernel_timer_t;
-typedef int		__kernel_clockid_t;
-typedef int             __kernel_daddr_t;
-typedef char *          __kernel_caddr_t;
-typedef unsigned short	__kernel_uid16_t;
-typedef unsigned short	__kernel_gid16_t;
+#define __kernel_size_t __kernel_size_t
 
-#ifdef __GNUC__
-typedef long long       __kernel_loff_t;
-#endif
+typedef unsigned short	__kernel_old_dev_t;
+#define __kernel_old_dev_t __kernel_old_dev_t
 
 #ifndef __s390x__
 
@@ -42,11 +30,6 @@ typedef unsigned short  __kernel_uid_t;
 typedef unsigned short  __kernel_gid_t;
 typedef int             __kernel_ssize_t;
 typedef int             __kernel_ptrdiff_t;
-typedef unsigned int	__kernel_uid32_t;
-typedef unsigned int	__kernel_gid32_t;
-typedef unsigned short	__kernel_old_uid_t;
-typedef unsigned short	__kernel_old_gid_t;
-typedef unsigned short	__kernel_old_dev_t;
 
 #else /* __s390x__ */
 
@@ -59,49 +42,16 @@ typedef unsigned int    __kernel_gid_t;
 typedef long            __kernel_ssize_t;
 typedef long            __kernel_ptrdiff_t;
 typedef unsigned long   __kernel_sigset_t;      /* at least 32 bits */
-typedef __kernel_uid_t __kernel_old_uid_t;
-typedef __kernel_gid_t __kernel_old_gid_t;
-typedef __kernel_uid_t __kernel_uid32_t;
-typedef __kernel_gid_t __kernel_gid32_t;
-typedef unsigned short __kernel_old_dev_t;
 
 #endif /* __s390x__ */
 
-typedef struct {
-        int     val[2];
-} __kernel_fsid_t;
-
-
-#ifdef __KERNEL__
-
-#undef __FD_SET
-static inline void __FD_SET(unsigned long fd, __kernel_fd_set *fdsetp)
-{
-	unsigned long _tmp = fd / __NFDBITS;
-	unsigned long _rem = fd % __NFDBITS;
-	fdsetp->fds_bits[_tmp] |= (1UL<<_rem);
-}
-
-#undef __FD_CLR
-static inline void __FD_CLR(unsigned long fd, __kernel_fd_set *fdsetp)
-{
-	unsigned long _tmp = fd / __NFDBITS;
-	unsigned long _rem = fd % __NFDBITS;
-	fdsetp->fds_bits[_tmp] &= ~(1UL<<_rem);
-}
-
-#undef __FD_ISSET
-static inline int __FD_ISSET(unsigned long fd, const __kernel_fd_set *fdsetp)
-{
-	unsigned long _tmp = fd / __NFDBITS;
-	unsigned long _rem = fd % __NFDBITS;
-	return (fdsetp->fds_bits[_tmp] & (1UL<<_rem)) != 0;
-}
-
-#undef  __FD_ZERO
-#define __FD_ZERO(fdsetp) \
-	((void) memset ((void *) (fdsetp), 0, sizeof (__kernel_fd_set)))
+#define __kernel_ino_t  __kernel_ino_t
+#define __kernel_mode_t __kernel_mode_t
+#define __kernel_nlink_t __kernel_nlink_t
+#define __kernel_ipc_pid_t __kernel_ipc_pid_t
+#define __kernel_uid_t __kernel_uid_t
+#define __kernel_gid_t __kernel_gid_t
 
-#endif     /* __KERNEL__ */
+#include <asm-generic/posix_types.h>
 
 #endif
diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index d25843a6a915..d499b30ea487 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -14,6 +14,7 @@
 #define __ASM_S390_PROCESSOR_H
 
 #include <linux/linkage.h>
+#include <linux/irqflags.h>
 #include <asm/cpu.h>
 #include <asm/page.h>
 #include <asm/ptrace.h>
@@ -156,6 +157,14 @@ unsigned long get_wchan(struct task_struct *p);
 #define KSTK_EIP(tsk)	(task_pt_regs(tsk)->psw.addr)
 #define KSTK_ESP(tsk)	(task_pt_regs(tsk)->gprs[15])
 
+static inline unsigned short stap(void)
+{
+	unsigned short cpu_address;
+
+	asm volatile("stap %0" : "=m" (cpu_address));
+	return cpu_address;
+}
+
 /*
  * Give up the time slice of the virtual PU.
  */
@@ -304,6 +313,21 @@ static inline void __noreturn disabled_wait(unsigned long code)
 }
 
 /*
+ * Use to set psw mask except for the first byte which
+ * won't be changed by this function.
+ */
+static inline void
+__set_psw_mask(unsigned long mask)
+{
+	__load_psw_mask(mask | (arch_local_save_flags() & ~(-1UL >> 8)));
+}
+
+#define local_mcck_enable() \
+	__set_psw_mask(psw_kernel_bits | PSW_MASK_DAT | PSW_MASK_MCHECK)
+#define local_mcck_disable() \
+	__set_psw_mask(psw_kernel_bits | PSW_MASK_DAT)
+
+/*
  * Basic Machine Check/Program Check Handler.
  */
 
diff --git a/arch/s390/include/asm/qeth.h b/arch/s390/include/asm/qeth.h
index 90efda0b137d..2c7c898c03e4 100644
--- a/arch/s390/include/asm/qeth.h
+++ b/arch/s390/include/asm/qeth.h
@@ -20,6 +20,7 @@
 #define SIOC_QETH_ARP_FLUSH_CACHE       (SIOCDEVPRIVATE + 4)
 #define SIOC_QETH_ADP_SET_SNMP_CONTROL  (SIOCDEVPRIVATE + 5)
 #define SIOC_QETH_GET_CARD_TYPE         (SIOCDEVPRIVATE + 6)
+#define SIOC_QETH_QUERY_OAT		(SIOCDEVPRIVATE + 7)
 
 struct qeth_arp_cache_entry {
 	__u8  macaddr[6];
@@ -107,4 +108,10 @@ struct qeth_arp_query_user_data {
 	char *entries;
 } __attribute__((packed));
 
+struct qeth_query_oat_data {
+	__u32 command;
+	__u32 buffer_len;
+	__u32 response_len;
+	__u64 ptr;
+};
 #endif /* __ASM_S390_QETH_IOCTL_H__ */
diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h
index 097183c70407..b21e46e5d4b8 100644
--- a/arch/s390/include/asm/setup.h
+++ b/arch/s390/include/asm/setup.h
@@ -140,6 +140,20 @@ extern char vmpoff_cmd[];
 #define NSS_NAME_SIZE	8
 extern char kernel_nss_name[];
 
+#ifdef CONFIG_PFAULT
+extern int pfault_init(void);
+extern void pfault_fini(void);
+#else /* CONFIG_PFAULT */
+#define pfault_init()		({-1;})
+#define pfault_fini()		do { } while (0)
+#endif /* CONFIG_PFAULT */
+
+extern void cmma_init(void);
+
+extern void (*_machine_restart)(char *command);
+extern void (*_machine_halt)(void);
+extern void (*_machine_power_off)(void);
+
 #else /* __ASSEMBLY__ */
 
 #ifndef __s390x__
diff --git a/arch/s390/include/asm/sigp.h b/arch/s390/include/asm/sigp.h
deleted file mode 100644
index 7040b8567cd0..000000000000
--- a/arch/s390/include/asm/sigp.h
+++ /dev/null
@@ -1,132 +0,0 @@
-/*
- *  Routines and structures for signalling other processors.
- *
- *    Copyright IBM Corp. 1999,2010
- *    Author(s): Denis Joseph Barrow,
- *		 Martin Schwidefsky <schwidefsky@de.ibm.com>,
- *		 Heiko Carstens <heiko.carstens@de.ibm.com>,
- */
-
-#ifndef __ASM_SIGP_H
-#define __ASM_SIGP_H
-
-#include <asm/system.h>
-
-/* Get real cpu address from logical cpu number. */
-extern unsigned short __cpu_logical_map[];
-
-static inline int cpu_logical_map(int cpu)
-{
-#ifdef CONFIG_SMP
-	return __cpu_logical_map[cpu];
-#else
-	return stap();
-#endif
-}
-
-enum {
-	sigp_sense = 1,
-	sigp_external_call = 2,
-	sigp_emergency_signal = 3,
-	sigp_start = 4,
-	sigp_stop = 5,
-	sigp_restart = 6,
-	sigp_stop_and_store_status = 9,
-	sigp_initial_cpu_reset = 11,
-	sigp_cpu_reset = 12,
-	sigp_set_prefix = 13,
-	sigp_store_status_at_address = 14,
-	sigp_store_extended_status_at_address = 15,
-	sigp_set_architecture = 18,
-	sigp_conditional_emergency_signal = 19,
-	sigp_sense_running = 21,
-};
-
-enum {
-	sigp_order_code_accepted = 0,
-	sigp_status_stored = 1,
-	sigp_busy = 2,
-	sigp_not_operational = 3,
-};
-
-/*
- * Definitions for external call.
- */
-enum {
-	ec_schedule = 0,
-	ec_call_function,
-	ec_call_function_single,
-	ec_stop_cpu,
-};
-
-/*
- * Signal processor.
- */
-static inline int raw_sigp(u16 cpu, int order)
-{
-	register unsigned long reg1 asm ("1") = 0;
-	int ccode;
-
-	asm volatile(
-		"	sigp	%1,%2,0(%3)\n"
-		"	ipm	%0\n"
-		"	srl	%0,28\n"
-		:	"=d"	(ccode)
-		: "d" (reg1), "d" (cpu),
-		  "a" (order) : "cc" , "memory");
-	return ccode;
-}
-
-/*
- * Signal processor with parameter.
- */
-static inline int raw_sigp_p(u32 parameter, u16 cpu, int order)
-{
-	register unsigned int reg1 asm ("1") = parameter;
-	int ccode;
-
-	asm volatile(
-		"	sigp	%1,%2,0(%3)\n"
-		"	ipm	%0\n"
-		"	srl	%0,28\n"
-		: "=d" (ccode)
-		: "d" (reg1), "d" (cpu),
-		  "a" (order) : "cc" , "memory");
-	return ccode;
-}
-
-/*
- * Signal processor with parameter and return status.
- */
-static inline int raw_sigp_ps(u32 *status, u32 parm, u16 cpu, int order)
-{
-	register unsigned int reg1 asm ("1") = parm;
-	int ccode;
-
-	asm volatile(
-		"	sigp	%1,%2,0(%3)\n"
-		"	ipm	%0\n"
-		"	srl	%0,28\n"
-		: "=d" (ccode), "+d" (reg1)
-		: "d" (cpu), "a" (order)
-		: "cc" , "memory");
-	*status = reg1;
-	return ccode;
-}
-
-static inline int sigp(int cpu, int order)
-{
-	return raw_sigp(cpu_logical_map(cpu), order);
-}
-
-static inline int sigp_p(u32 parameter, int cpu, int order)
-{
-	return raw_sigp_p(parameter, cpu_logical_map(cpu), order);
-}
-
-static inline int sigp_ps(u32 *status, u32 parm, int cpu, int order)
-{
-	return raw_sigp_ps(status, parm, cpu_logical_map(cpu), order);
-}
-
-#endif /* __ASM_SIGP_H */
diff --git a/arch/s390/include/asm/smp.h b/arch/s390/include/asm/smp.h
index c32e9123b40c..c77c6de6f6c0 100644
--- a/arch/s390/include/asm/smp.h
+++ b/arch/s390/include/asm/smp.h
@@ -1,5 +1,5 @@
 /*
- *    Copyright IBM Corp. 1999,2009
+ *    Copyright IBM Corp. 1999,2012
  *    Author(s): Denis Joseph Barrow,
  *		 Martin Schwidefsky <schwidefsky@de.ibm.com>,
  *		 Heiko Carstens <heiko.carstens@de.ibm.com>,
@@ -9,72 +9,53 @@
 
 #ifdef CONFIG_SMP
 
-#include <asm/system.h>
-#include <asm/sigp.h>
-
-extern void machine_restart_smp(char *);
-extern void machine_halt_smp(void);
-extern void machine_power_off_smp(void);
+#include <asm/lowcore.h>
 
 #define raw_smp_processor_id()	(S390_lowcore.cpu_nr)
 
-extern int __cpu_disable (void);
-extern void __cpu_die (unsigned int cpu);
-extern int __cpu_up (unsigned int cpu);
-
 extern struct mutex smp_cpu_state_mutex;
+extern struct save_area *zfcpdump_save_areas[NR_CPUS + 1];
+
+extern int __cpu_up(unsigned int cpu);
 
 extern void arch_send_call_function_single_ipi(int cpu);
 extern void arch_send_call_function_ipi_mask(const struct cpumask *mask);
 
-extern struct save_area *zfcpdump_save_areas[NR_CPUS + 1];
-
-extern void smp_switch_to_ipl_cpu(void (*func)(void *), void *);
-extern void smp_switch_to_cpu(void (*)(void *), void *, unsigned long sp,
-			      int from, int to);
-extern void smp_restart_with_online_cpu(void);
-extern void smp_restart_cpu(void);
+extern void smp_call_online_cpu(void (*func)(void *), void *);
+extern void smp_call_ipl_cpu(void (*func)(void *), void *);
 
-/*
- * returns 1 if (virtual) cpu is scheduled
- * returns 0 otherwise
- */
-static inline int smp_vcpu_scheduled(int cpu)
-{
-	u32 status;
-
-	switch (sigp_ps(&status, 0, cpu, sigp_sense_running)) {
-	case sigp_status_stored:
-		/* Check for running status */
-		if (status & 0x400)
-			return 0;
-		break;
-	case sigp_not_operational:
-		return 0;
-	default:
-		break;
-	}
-	return 1;
-}
+extern int smp_find_processor_id(u16 address);
+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);
 
 #else /* CONFIG_SMP */
 
-static inline void smp_switch_to_ipl_cpu(void (*func)(void *), void *data)
+static inline void smp_call_ipl_cpu(void (*func)(void *), void *data)
 {
 	func(data);
 }
 
-static inline void smp_restart_with_online_cpu(void)
+static inline void smp_call_online_cpu(void (*func)(void *), void *data)
 {
+	func(data);
 }
 
-#define smp_vcpu_scheduled	(1)
+static inline int smp_find_processor_id(int address) { return 0; }
+static inline int smp_vcpu_scheduled(int cpu) { return 1; }
+static inline void smp_yield_cpu(int cpu) { }
+static inline void smp_yield(void) { }
+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);
+extern void __cpu_die(unsigned int cpu);
+extern int __cpu_disable(void);
 #else
 static inline int smp_rescan_cpus(void) { return 0; }
 static inline void cpu_die(void) { }
diff --git a/arch/s390/include/asm/socket.h b/arch/s390/include/asm/socket.h
index 67b5c1b14b51..c91b720965c0 100644
--- a/arch/s390/include/asm/socket.h
+++ b/arch/s390/include/asm/socket.h
@@ -72,5 +72,9 @@
 
 #define SO_WIFI_STATUS		41
 #define SCM_WIFI_STATUS		SO_WIFI_STATUS
+#define SO_PEEK_OFF		42
+
+/* Instruct lower device to use last 4-bytes of skb data as FCS */
+#define SO_NOFCS		43
 
 #endif /* _ASM_SOCKET_H */
diff --git a/arch/s390/include/asm/switch_to.h b/arch/s390/include/asm/switch_to.h
new file mode 100644
index 000000000000..f223068b7822
--- /dev/null
+++ b/arch/s390/include/asm/switch_to.h
@@ -0,0 +1,100 @@
+/*
+ * Copyright IBM Corp. 1999, 2009
+ *
+ * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
+ */
+
+#ifndef __ASM_SWITCH_TO_H
+#define __ASM_SWITCH_TO_H
+
+#include <linux/thread_info.h>
+
+extern struct task_struct *__switch_to(void *, void *);
+extern void update_per_regs(struct task_struct *task);
+
+static inline void save_fp_regs(s390_fp_regs *fpregs)
+{
+	asm volatile(
+		"	std	0,%O0+8(%R0)\n"
+		"	std	2,%O0+24(%R0)\n"
+		"	std	4,%O0+40(%R0)\n"
+		"	std	6,%O0+56(%R0)"
+		: "=Q" (*fpregs) : "Q" (*fpregs));
+	if (!MACHINE_HAS_IEEE)
+		return;
+	asm volatile(
+		"	stfpc	%0\n"
+		"	std	1,%O0+16(%R0)\n"
+		"	std	3,%O0+32(%R0)\n"
+		"	std	5,%O0+48(%R0)\n"
+		"	std	7,%O0+64(%R0)\n"
+		"	std	8,%O0+72(%R0)\n"
+		"	std	9,%O0+80(%R0)\n"
+		"	std	10,%O0+88(%R0)\n"
+		"	std	11,%O0+96(%R0)\n"
+		"	std	12,%O0+104(%R0)\n"
+		"	std	13,%O0+112(%R0)\n"
+		"	std	14,%O0+120(%R0)\n"
+		"	std	15,%O0+128(%R0)\n"
+		: "=Q" (*fpregs) : "Q" (*fpregs));
+}
+
+static inline void restore_fp_regs(s390_fp_regs *fpregs)
+{
+	asm volatile(
+		"	ld	0,%O0+8(%R0)\n"
+		"	ld	2,%O0+24(%R0)\n"
+		"	ld	4,%O0+40(%R0)\n"
+		"	ld	6,%O0+56(%R0)"
+		: : "Q" (*fpregs));
+	if (!MACHINE_HAS_IEEE)
+		return;
+	asm volatile(
+		"	lfpc	%0\n"
+		"	ld	1,%O0+16(%R0)\n"
+		"	ld	3,%O0+32(%R0)\n"
+		"	ld	5,%O0+48(%R0)\n"
+		"	ld	7,%O0+64(%R0)\n"
+		"	ld	8,%O0+72(%R0)\n"
+		"	ld	9,%O0+80(%R0)\n"
+		"	ld	10,%O0+88(%R0)\n"
+		"	ld	11,%O0+96(%R0)\n"
+		"	ld	12,%O0+104(%R0)\n"
+		"	ld	13,%O0+112(%R0)\n"
+		"	ld	14,%O0+120(%R0)\n"
+		"	ld	15,%O0+128(%R0)\n"
+		: : "Q" (*fpregs));
+}
+
+static inline void save_access_regs(unsigned int *acrs)
+{
+	asm volatile("stam 0,15,%0" : "=Q" (*acrs));
+}
+
+static inline void restore_access_regs(unsigned int *acrs)
+{
+	asm volatile("lam 0,15,%0" : : "Q" (*acrs));
+}
+
+#define switch_to(prev,next,last) do {					\
+	if (prev->mm) {							\
+		save_fp_regs(&prev->thread.fp_regs);			\
+		save_access_regs(&prev->thread.acrs[0]);		\
+	}								\
+	if (next->mm) {							\
+		restore_fp_regs(&next->thread.fp_regs);			\
+		restore_access_regs(&next->thread.acrs[0]);		\
+		update_per_regs(next);					\
+	}								\
+	prev = __switch_to(prev,next);					\
+} while (0)
+
+extern void account_vtime(struct task_struct *, struct task_struct *);
+extern void account_tick_vtime(struct task_struct *);
+
+#define finish_arch_switch(prev) do {					     \
+	set_fs(current->thread.mm_segment);				     \
+	account_vtime(prev, current);					     \
+} while (0)
+
+#endif /* __ASM_SWITCH_TO_H */
diff --git a/arch/s390/include/asm/system.h b/arch/s390/include/asm/system.h
deleted file mode 100644
index d73cc6b60000..000000000000
--- a/arch/s390/include/asm/system.h
+++ /dev/null
@@ -1,281 +0,0 @@
-/*
- * Copyright IBM Corp. 1999, 2009
- *
- * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
- */
-
-#ifndef __ASM_SYSTEM_H
-#define __ASM_SYSTEM_H
-
-#include <linux/kernel.h>
-#include <linux/errno.h>
-#include <asm/types.h>
-#include <asm/ptrace.h>
-#include <asm/setup.h>
-#include <asm/processor.h>
-#include <asm/lowcore.h>
-#include <asm/cmpxchg.h>
-
-#ifdef __KERNEL__
-
-struct task_struct;
-
-extern struct task_struct *__switch_to(void *, void *);
-extern void update_per_regs(struct task_struct *task);
-
-static inline void save_fp_regs(s390_fp_regs *fpregs)
-{
-	asm volatile(
-		"	std	0,%O0+8(%R0)\n"
-		"	std	2,%O0+24(%R0)\n"
-		"	std	4,%O0+40(%R0)\n"
-		"	std	6,%O0+56(%R0)"
-		: "=Q" (*fpregs) : "Q" (*fpregs));
-	if (!MACHINE_HAS_IEEE)
-		return;
-	asm volatile(
-		"	stfpc	%0\n"
-		"	std	1,%O0+16(%R0)\n"
-		"	std	3,%O0+32(%R0)\n"
-		"	std	5,%O0+48(%R0)\n"
-		"	std	7,%O0+64(%R0)\n"
-		"	std	8,%O0+72(%R0)\n"
-		"	std	9,%O0+80(%R0)\n"
-		"	std	10,%O0+88(%R0)\n"
-		"	std	11,%O0+96(%R0)\n"
-		"	std	12,%O0+104(%R0)\n"
-		"	std	13,%O0+112(%R0)\n"
-		"	std	14,%O0+120(%R0)\n"
-		"	std	15,%O0+128(%R0)\n"
-		: "=Q" (*fpregs) : "Q" (*fpregs));
-}
-
-static inline void restore_fp_regs(s390_fp_regs *fpregs)
-{
-	asm volatile(
-		"	ld	0,%O0+8(%R0)\n"
-		"	ld	2,%O0+24(%R0)\n"
-		"	ld	4,%O0+40(%R0)\n"
-		"	ld	6,%O0+56(%R0)"
-		: : "Q" (*fpregs));
-	if (!MACHINE_HAS_IEEE)
-		return;
-	asm volatile(
-		"	lfpc	%0\n"
-		"	ld	1,%O0+16(%R0)\n"
-		"	ld	3,%O0+32(%R0)\n"
-		"	ld	5,%O0+48(%R0)\n"
-		"	ld	7,%O0+64(%R0)\n"
-		"	ld	8,%O0+72(%R0)\n"
-		"	ld	9,%O0+80(%R0)\n"
-		"	ld	10,%O0+88(%R0)\n"
-		"	ld	11,%O0+96(%R0)\n"
-		"	ld	12,%O0+104(%R0)\n"
-		"	ld	13,%O0+112(%R0)\n"
-		"	ld	14,%O0+120(%R0)\n"
-		"	ld	15,%O0+128(%R0)\n"
-		: : "Q" (*fpregs));
-}
-
-static inline void save_access_regs(unsigned int *acrs)
-{
-	asm volatile("stam 0,15,%0" : "=Q" (*acrs));
-}
-
-static inline void restore_access_regs(unsigned int *acrs)
-{
-	asm volatile("lam 0,15,%0" : : "Q" (*acrs));
-}
-
-#define switch_to(prev,next,last) do {					\
-	if (prev->mm) {							\
-		save_fp_regs(&prev->thread.fp_regs);			\
-		save_access_regs(&prev->thread.acrs[0]);		\
-	}								\
-	if (next->mm) {							\
-		restore_fp_regs(&next->thread.fp_regs);			\
-		restore_access_regs(&next->thread.acrs[0]);		\
-		update_per_regs(next);					\
-	}								\
-	prev = __switch_to(prev,next);					\
-} while (0)
-
-extern void account_vtime(struct task_struct *, struct task_struct *);
-extern void account_tick_vtime(struct task_struct *);
-
-#ifdef CONFIG_PFAULT
-extern int pfault_init(void);
-extern void pfault_fini(void);
-#else /* CONFIG_PFAULT */
-#define pfault_init()		({-1;})
-#define pfault_fini()		do { } while (0)
-#endif /* CONFIG_PFAULT */
-
-extern void cmma_init(void);
-extern int memcpy_real(void *, void *, size_t);
-extern void copy_to_absolute_zero(void *dest, void *src, size_t count);
-extern int copy_to_user_real(void __user *dest, void *src, size_t count);
-extern int copy_from_user_real(void *dest, void __user *src, size_t count);
-
-#define finish_arch_switch(prev) do {					     \
-	set_fs(current->thread.mm_segment);				     \
-	account_vtime(prev, current);					     \
-} while (0)
-
-#define nop() asm volatile("nop")
-
-/*
- * Force strict CPU ordering.
- * And yes, this is required on UP too when we're talking
- * to devices.
- *
- * This is very similar to the ppc eieio/sync instruction in that is
- * does a checkpoint syncronisation & makes sure that 
- * all memory ops have completed wrt other CPU's ( see 7-15 POP  DJB ).
- */
-
-#define eieio()	asm volatile("bcr 15,0" : : : "memory")
-#define SYNC_OTHER_CORES(x)   eieio()
-#define mb()    eieio()
-#define rmb()   eieio()
-#define wmb()   eieio()
-#define read_barrier_depends() do { } while(0)
-#define smp_mb()       mb()
-#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 set_mb(var, value)      do { var = value; mb(); } while (0)
-
-#ifdef __s390x__
-
-#define __ctl_load(array, low, high) ({				\
-	typedef struct { char _[sizeof(array)]; } addrtype;	\
-	asm volatile(						\
-		"	lctlg	%1,%2,%0\n"			\
-		: : "Q" (*(addrtype *)(&array)),		\
-		    "i" (low), "i" (high));			\
-	})
-
-#define __ctl_store(array, low, high) ({			\
-	typedef struct { char _[sizeof(array)]; } addrtype;	\
-	asm volatile(						\
-		"	stctg	%1,%2,%0\n"			\
-		: "=Q" (*(addrtype *)(&array))			\
-		: "i" (low), "i" (high));			\
-	})
-
-#else /* __s390x__ */
-
-#define __ctl_load(array, low, high) ({				\
-	typedef struct { char _[sizeof(array)]; } addrtype;	\
-	asm volatile(						\
-		"	lctl	%1,%2,%0\n"			\
-		: : "Q" (*(addrtype *)(&array)),		\
-		    "i" (low), "i" (high));			\
-})
-
-#define __ctl_store(array, low, high) ({			\
-	typedef struct { char _[sizeof(array)]; } addrtype;	\
-	asm volatile(						\
-		"	stctl	%1,%2,%0\n"			\
-		: "=Q" (*(addrtype *)(&array))			\
-		: "i" (low), "i" (high));			\
-	})
-
-#endif /* __s390x__ */
-
-#define __ctl_set_bit(cr, bit) ({	\
-	unsigned long __dummy;		\
-	__ctl_store(__dummy, cr, cr);	\
-	__dummy |= 1UL << (bit);	\
-	__ctl_load(__dummy, cr, cr);	\
-})
-
-#define __ctl_clear_bit(cr, bit) ({	\
-	unsigned long __dummy;		\
-	__ctl_store(__dummy, cr, cr);	\
-	__dummy &= ~(1UL << (bit));	\
-	__ctl_load(__dummy, cr, cr);	\
-})
-
-/*
- * Use to set psw mask except for the first byte which
- * won't be changed by this function.
- */
-static inline void
-__set_psw_mask(unsigned long mask)
-{
-	__load_psw_mask(mask | (arch_local_save_flags() & ~(-1UL >> 8)));
-}
-
-#define local_mcck_enable() \
-	__set_psw_mask(psw_kernel_bits | PSW_MASK_DAT | PSW_MASK_MCHECK)
-#define local_mcck_disable() \
-	__set_psw_mask(psw_kernel_bits | PSW_MASK_DAT)
-
-#ifdef CONFIG_SMP
-
-extern void smp_ctl_set_bit(int cr, int bit);
-extern void smp_ctl_clear_bit(int cr, int bit);
-#define ctl_set_bit(cr, bit) smp_ctl_set_bit(cr, bit)
-#define ctl_clear_bit(cr, bit) smp_ctl_clear_bit(cr, bit)
-
-#else
-
-#define ctl_set_bit(cr, bit) __ctl_set_bit(cr, bit)
-#define ctl_clear_bit(cr, bit) __ctl_clear_bit(cr, bit)
-
-#endif /* CONFIG_SMP */
-
-#define MAX_FACILITY_BIT (256*8)	/* stfle_fac_list has 256 bytes */
-
-/*
- * The test_facility function uses the bit odering where the MSB is bit 0.
- * That makes it easier to query facility bits with the bit number as
- * documented in the Principles of Operation.
- */
-static inline int test_facility(unsigned long nr)
-{
-	unsigned char *ptr;
-
-	if (nr >= MAX_FACILITY_BIT)
-		return 0;
-	ptr = (unsigned char *) &S390_lowcore.stfle_fac_list + (nr >> 3);
-	return (*ptr & (0x80 >> (nr & 7))) != 0;
-}
-
-static inline unsigned short stap(void)
-{
-	unsigned short cpu_address;
-
-	asm volatile("stap %0" : "=m" (cpu_address));
-	return cpu_address;
-}
-
-extern void (*_machine_restart)(char *command);
-extern void (*_machine_halt)(void);
-extern void (*_machine_power_off)(void);
-
-extern unsigned long arch_align_stack(unsigned long sp);
-
-static inline int tprot(unsigned long addr)
-{
-	int rc = -EFAULT;
-
-	asm volatile(
-		"	tprot	0(%1),0\n"
-		"0:	ipm	%0\n"
-		"	srl	%0,28\n"
-		"1:\n"
-		EX_TABLE(0b,1b)
-		: "+d" (rc) : "a" (addr) : "cc");
-	return rc;
-}
-
-#endif /* __KERNEL__ */
-
-#endif
diff --git a/arch/s390/include/asm/timer.h b/arch/s390/include/asm/timer.h
index 814243cafdfe..e63069ba39e3 100644
--- a/arch/s390/include/asm/timer.h
+++ b/arch/s390/include/asm/timer.h
@@ -33,8 +33,8 @@ struct vtimer_queue {
 	spinlock_t lock;
 	__u64 timer;		/* last programmed timer */
 	__u64 elapsed;		/* elapsed time of timer expire values */
-	__u64 idle;		/* temp var for idle */
-	int do_spt;		/* =1: reprogram cpu timer in idle */
+	__u64 idle_enter;	/* cpu timer on idle enter */
+	__u64 idle_exit;	/* cpu timer on idle exit */
 };
 
 extern void init_virt_timer(struct vtimer_list *timer);
diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h
index 2b23885e81e9..8f2cada4f7c9 100644
--- a/arch/s390/include/asm/uaccess.h
+++ b/arch/s390/include/asm/uaccess.h
@@ -16,6 +16,7 @@
  */
 #include <linux/sched.h>
 #include <linux/errno.h>
+#include <asm/ctl_reg.h>
 
 #define VERIFY_READ     0
 #define VERIFY_WRITE    1
@@ -375,4 +376,9 @@ clear_user(void __user *to, unsigned long n)
 	return n;
 }
 
+extern int memcpy_real(void *, void *, size_t);
+extern void copy_to_absolute_zero(void *dest, void *src, size_t count);
+extern int copy_to_user_real(void __user *dest, void *src, size_t count);
+extern int copy_from_user_real(void *dest, void __user *src, size_t count);
+
 #endif /* __S390_UACCESS_H */
diff --git a/arch/s390/include/asm/vdso.h b/arch/s390/include/asm/vdso.h
index 533f35751aeb..c4a11cfad3c8 100644
--- a/arch/s390/include/asm/vdso.h
+++ b/arch/s390/include/asm/vdso.h
@@ -40,8 +40,8 @@ struct vdso_per_cpu_data {
 extern struct vdso_data *vdso_data;
 
 #ifdef CONFIG_64BIT
-int vdso_alloc_per_cpu(int cpu, struct _lowcore *lowcore);
-void vdso_free_per_cpu(int cpu, struct _lowcore *lowcore);
+int vdso_alloc_per_cpu(struct _lowcore *lowcore);
+void vdso_free_per_cpu(struct _lowcore *lowcore);
 #endif
 
 #endif /* __ASSEMBLY__ */
diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile
index 7d9ec924e7e7..884b18afc864 100644
--- a/arch/s390/kernel/Makefile
+++ b/arch/s390/kernel/Makefile
@@ -23,7 +23,7 @@ CFLAGS_sysinfo.o += -Iinclude/math-emu -Iarch/s390/math-emu -w
 obj-y	:=  bitmap.o traps.o time.o process.o base.o early.o setup.o vtime.o \
 	    processor.o sys_s390.o ptrace.o signal.o cpcmd.o ebcdic.o nmi.o \
 	    debug.o irq.o ipl.o dis.o diag.o mem_detect.o sclp.o vdso.o \
-	    sysinfo.o jump_label.o
+	    sysinfo.o jump_label.o lgr.o os_info.o
 
 obj-y	+= $(if $(CONFIG_64BIT),entry64.o,entry.o)
 obj-y	+= $(if $(CONFIG_64BIT),reipl64.o,reipl.o)
@@ -34,8 +34,6 @@ extra-y				+= $(if $(CONFIG_64BIT),head64.o,head31.o)
 obj-$(CONFIG_MODULES)		+= s390_ksyms.o module.o
 obj-$(CONFIG_SMP)		+= smp.o
 obj-$(CONFIG_SCHED_BOOK)	+= topology.o
-obj-$(CONFIG_SMP)		+= $(if $(CONFIG_64BIT),switch_cpu64.o, \
-							switch_cpu.o)
 obj-$(CONFIG_HIBERNATION)	+= suspend.o swsusp_asm64.o
 obj-$(CONFIG_AUDIT)		+= audit.o
 compat-obj-$(CONFIG_AUDIT)	+= compat_audit.o
@@ -50,6 +48,7 @@ obj-$(CONFIG_DYNAMIC_FTRACE)	+= ftrace.o
 obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o
 obj-$(CONFIG_FTRACE_SYSCALLS)  += ftrace.o
 obj-$(CONFIG_CRASH_DUMP)	+= crash_dump.o
+obj-$(CONFIG_PERF_EVENTS)	+= perf_event.o perf_cpum_cf.o
 
 # Kexec part
 S390_KEXEC_OBJS := machine_kexec.o crash.o
diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c
index 6e6a72e66d60..83e6edf5cf17 100644
--- a/arch/s390/kernel/asm-offsets.c
+++ b/arch/s390/kernel/asm-offsets.c
@@ -8,8 +8,9 @@
 
 #include <linux/kbuild.h>
 #include <linux/sched.h>
+#include <asm/cputime.h>
+#include <asm/timer.h>
 #include <asm/vdso.h>
-#include <asm/sigp.h>
 #include <asm/pgtable.h>
 
 /*
@@ -70,15 +71,15 @@ int main(void)
 	DEFINE(__CLOCK_MONOTONIC, CLOCK_MONOTONIC);
 	DEFINE(__CLOCK_REALTIME_RES, MONOTONIC_RES_NSEC);
 	BLANK();
-	/* constants for SIGP */
-	DEFINE(__SIGP_STOP, sigp_stop);
-	DEFINE(__SIGP_RESTART, sigp_restart);
-	DEFINE(__SIGP_SENSE, sigp_sense);
-	DEFINE(__SIGP_INITIAL_CPU_RESET, sigp_initial_cpu_reset);
-	BLANK();
+	/* idle data offsets */
+	DEFINE(__IDLE_ENTER, offsetof(struct s390_idle_data, idle_enter));
+	DEFINE(__IDLE_EXIT, offsetof(struct s390_idle_data, idle_exit));
+	/* vtimer queue offsets */
+	DEFINE(__VQ_IDLE_ENTER, offsetof(struct vtimer_queue, idle_enter));
+	DEFINE(__VQ_IDLE_EXIT, offsetof(struct vtimer_queue, idle_exit));
 	/* lowcore offsets */
 	DEFINE(__LC_EXT_PARAMS, offsetof(struct _lowcore, ext_params));
-	DEFINE(__LC_CPU_ADDRESS, offsetof(struct _lowcore, cpu_addr));
+	DEFINE(__LC_EXT_CPU_ADDR, offsetof(struct _lowcore, ext_cpu_addr));
 	DEFINE(__LC_EXT_INT_CODE, offsetof(struct _lowcore, ext_int_code));
 	DEFINE(__LC_SVC_ILC, offsetof(struct _lowcore, svc_ilc));
 	DEFINE(__LC_SVC_INT_CODE, offsetof(struct _lowcore, svc_code));
@@ -95,20 +96,19 @@ int main(void)
 	DEFINE(__LC_IO_INT_WORD, offsetof(struct _lowcore, io_int_word));
 	DEFINE(__LC_STFL_FAC_LIST, offsetof(struct _lowcore, stfl_fac_list));
 	DEFINE(__LC_MCCK_CODE, offsetof(struct _lowcore, mcck_interruption_code));
-	DEFINE(__LC_DUMP_REIPL, offsetof(struct _lowcore, ipib));
-	BLANK();
-	DEFINE(__LC_RST_NEW_PSW, offsetof(struct _lowcore, restart_psw));
 	DEFINE(__LC_RST_OLD_PSW, offsetof(struct _lowcore, restart_old_psw));
 	DEFINE(__LC_EXT_OLD_PSW, offsetof(struct _lowcore, external_old_psw));
 	DEFINE(__LC_SVC_OLD_PSW, offsetof(struct _lowcore, svc_old_psw));
 	DEFINE(__LC_PGM_OLD_PSW, offsetof(struct _lowcore, program_old_psw));
 	DEFINE(__LC_MCK_OLD_PSW, offsetof(struct _lowcore, mcck_old_psw));
 	DEFINE(__LC_IO_OLD_PSW, offsetof(struct _lowcore, io_old_psw));
+	DEFINE(__LC_RST_NEW_PSW, offsetof(struct _lowcore, restart_psw));
 	DEFINE(__LC_EXT_NEW_PSW, offsetof(struct _lowcore, external_new_psw));
 	DEFINE(__LC_SVC_NEW_PSW, offsetof(struct _lowcore, svc_new_psw));
 	DEFINE(__LC_PGM_NEW_PSW, offsetof(struct _lowcore, program_new_psw));
 	DEFINE(__LC_MCK_NEW_PSW, offsetof(struct _lowcore, mcck_new_psw));
 	DEFINE(__LC_IO_NEW_PSW, offsetof(struct _lowcore, io_new_psw));
+	BLANK();
 	DEFINE(__LC_SAVE_AREA_SYNC, offsetof(struct _lowcore, save_area_sync));
 	DEFINE(__LC_SAVE_AREA_ASYNC, offsetof(struct _lowcore, save_area_async));
 	DEFINE(__LC_SAVE_AREA_RESTART, offsetof(struct _lowcore, save_area_restart));
@@ -129,12 +129,16 @@ int main(void)
 	DEFINE(__LC_KERNEL_STACK, offsetof(struct _lowcore, kernel_stack));
 	DEFINE(__LC_ASYNC_STACK, offsetof(struct _lowcore, async_stack));
 	DEFINE(__LC_PANIC_STACK, offsetof(struct _lowcore, panic_stack));
+	DEFINE(__LC_RESTART_STACK, offsetof(struct _lowcore, restart_stack));
+	DEFINE(__LC_RESTART_FN, offsetof(struct _lowcore, restart_fn));
 	DEFINE(__LC_USER_ASCE, offsetof(struct _lowcore, user_asce));
 	DEFINE(__LC_INT_CLOCK, offsetof(struct _lowcore, int_clock));
 	DEFINE(__LC_MCCK_CLOCK, offsetof(struct _lowcore, mcck_clock));
 	DEFINE(__LC_MACHINE_FLAGS, offsetof(struct _lowcore, machine_flags));
 	DEFINE(__LC_FTRACE_FUNC, offsetof(struct _lowcore, ftrace_func));
 	DEFINE(__LC_IRB, offsetof(struct _lowcore, irb));
+	DEFINE(__LC_DUMP_REIPL, offsetof(struct _lowcore, ipib));
+	BLANK();
 	DEFINE(__LC_CPU_TIMER_SAVE_AREA, offsetof(struct _lowcore, cpu_timer_save_area));
 	DEFINE(__LC_CLOCK_COMP_SAVE_AREA, offsetof(struct _lowcore, clock_comp_save_area));
 	DEFINE(__LC_PSW_SAVE_AREA, offsetof(struct _lowcore, psw_save_area));
diff --git a/arch/s390/kernel/compat_signal.c b/arch/s390/kernel/compat_signal.c
index 6fe78c2f95d9..28040fd5e8a2 100644
--- a/arch/s390/kernel/compat_signal.c
+++ b/arch/s390/kernel/compat_signal.c
@@ -27,6 +27,7 @@
 #include <asm/ucontext.h>
 #include <asm/uaccess.h>
 #include <asm/lowcore.h>
+#include <asm/switch_to.h>
 #include "compat_linux.h"
 #include "compat_ptrace.h"
 #include "entry.h"
@@ -581,7 +582,6 @@ give_sigsegv:
 int handle_signal32(unsigned long sig, struct k_sigaction *ka,
 		    siginfo_t *info, sigset_t *oldset, struct pt_regs *regs)
 {
-	sigset_t blocked;
 	int ret;
 
 	/* Set up the stack frame */
@@ -591,10 +591,7 @@ int handle_signal32(unsigned long sig, struct k_sigaction *ka,
 		ret = setup_frame32(sig, ka, oldset, regs);
 	if (ret)
 		return ret;
-	sigorsets(&blocked, &current->blocked, &ka->sa.sa_mask);
-	if (!(ka->sa.sa_flags & SA_NODEFER))
-		sigaddset(&blocked, sig);
-	set_current_blocked(&blocked);
+	block_sigmask(ka, sig);
 	return 0;
 }
 
diff --git a/arch/s390/kernel/compat_wrapper.S b/arch/s390/kernel/compat_wrapper.S
index 18c51df9fe06..ff605a39cf43 100644
--- a/arch/s390/kernel/compat_wrapper.S
+++ b/arch/s390/kernel/compat_wrapper.S
@@ -662,7 +662,7 @@ ENTRY(sys32_getresuid16_wrapper)
 ENTRY(sys32_poll_wrapper)
 	llgtr	%r2,%r2			# struct pollfd *
 	llgfr	%r3,%r3			# unsigned int
-	lgfr	%r4,%r4			# long
+	lgfr	%r4,%r4			# int
 	jg	sys_poll		# branch to system call
 
 ENTRY(sys32_setresgid16_wrapper)
diff --git a/arch/s390/kernel/cpcmd.c b/arch/s390/kernel/cpcmd.c
index 3e8b8816f309..e3dd886e1b32 100644
--- a/arch/s390/kernel/cpcmd.c
+++ b/arch/s390/kernel/cpcmd.c
@@ -18,7 +18,6 @@
 #include <linux/string.h>
 #include <asm/ebcdic.h>
 #include <asm/cpcmd.h>
-#include <asm/system.h>
 #include <asm/io.h>
 
 static DEFINE_SPINLOCK(cpcmd_lock);
diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c
index 39f8fd4438fc..cc1172b26873 100644
--- a/arch/s390/kernel/crash_dump.c
+++ b/arch/s390/kernel/crash_dump.c
@@ -11,10 +11,10 @@
 #include <linux/module.h>
 #include <linux/gfp.h>
 #include <linux/slab.h>
-#include <linux/crash_dump.h>
 #include <linux/bootmem.h>
 #include <linux/elf.h>
 #include <asm/ipl.h>
+#include <asm/os_info.h>
 
 #define PTR_ADD(x, y) (((char *) (x)) + ((unsigned long) (y)))
 #define PTR_SUB(x, y) (((char *) (x)) - ((unsigned long) (y)))
@@ -52,7 +52,7 @@ ssize_t copy_oldmem_page(unsigned long pfn, char *buf,
 /*
  * Copy memory from old kernel
  */
-static int copy_from_oldmem(void *dest, void *src, size_t count)
+int copy_from_oldmem(void *dest, void *src, size_t count)
 {
 	unsigned long copied = 0;
 	int rc;
@@ -225,28 +225,44 @@ static void *nt_prpsinfo(void *ptr)
 }
 
 /*
- * Initialize vmcoreinfo note (new kernel)
+ * Get vmcoreinfo using lowcore->vmcore_info (new kernel)
  */
-static void *nt_vmcoreinfo(void *ptr)
+static void *get_vmcoreinfo_old(unsigned long *size)
 {
 	char nt_name[11], *vmcoreinfo;
 	Elf64_Nhdr note;
 	void *addr;
 
 	if (copy_from_oldmem(&addr, &S390_lowcore.vmcore_info, sizeof(addr)))
-		return ptr;
+		return NULL;
 	memset(nt_name, 0, sizeof(nt_name));
 	if (copy_from_oldmem(&note, addr, sizeof(note)))
-		return ptr;
+		return NULL;
 	if (copy_from_oldmem(nt_name, addr + sizeof(note), sizeof(nt_name) - 1))
-		return ptr;
+		return NULL;
 	if (strcmp(nt_name, "VMCOREINFO") != 0)
-		return ptr;
-	vmcoreinfo = kzalloc_panic(note.n_descsz + 1);
+		return NULL;
+	vmcoreinfo = kzalloc_panic(note.n_descsz);
 	if (copy_from_oldmem(vmcoreinfo, addr + 24, note.n_descsz))
+		return NULL;
+	*size = note.n_descsz;
+	return vmcoreinfo;
+}
+
+/*
+ * Initialize vmcoreinfo note (new kernel)
+ */
+static void *nt_vmcoreinfo(void *ptr)
+{
+	unsigned long size;
+	void *vmcoreinfo;
+
+	vmcoreinfo = os_info_old_entry(OS_INFO_VMCOREINFO, &size);
+	if (!vmcoreinfo)
+		vmcoreinfo = get_vmcoreinfo_old(&size);
+	if (!vmcoreinfo)
 		return ptr;
-	vmcoreinfo[note.n_descsz + 1] = 0;
-	return nt_init(ptr, 0, vmcoreinfo, note.n_descsz, "VMCOREINFO");
+	return nt_init(ptr, 0, vmcoreinfo, size, "VMCOREINFO");
 }
 
 /*
diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c
index 6848828b962e..19e5e9eba546 100644
--- a/arch/s390/kernel/debug.c
+++ b/arch/s390/kernel/debug.c
@@ -2,8 +2,8 @@
  *  arch/s390/kernel/debug.c
  *   S/390 debug facility
  *
- *    Copyright (C) 1999, 2000 IBM Deutschland Entwicklung GmbH,
- *                             IBM Corporation
+ *    Copyright IBM Corp. 1999, 2012
+ *
  *    Author(s): Michael Holzheu (holzheu@de.ibm.com),
  *               Holger Smolinski (Holger.Smolinski@de.ibm.com)
  *
@@ -167,6 +167,7 @@ static debug_info_t *debug_area_last = NULL;
 static DEFINE_MUTEX(debug_mutex);
 
 static int initialized;
+static int debug_critical;
 
 static const struct file_operations debug_file_ops = {
 	.owner   = THIS_MODULE,
@@ -932,6 +933,11 @@ debug_stop_all(void)
 }
 
 
+void debug_set_critical(void)
+{
+	debug_critical = 1;
+}
+
 /*
  * debug_event_common:
  * - write debug entry with given size
@@ -945,7 +951,11 @@ debug_event_common(debug_info_t * id, int level, const void *buf, int len)
 
 	if (!debug_active || !id->areas)
 		return NULL;
-	spin_lock_irqsave(&id->lock, flags);
+	if (debug_critical) {
+		if (!spin_trylock_irqsave(&id->lock, flags))
+			return NULL;
+	} else
+		spin_lock_irqsave(&id->lock, flags);
 	active = get_active_entry(id);
 	memset(DEBUG_DATA(active), 0, id->buf_size);
 	memcpy(DEBUG_DATA(active), buf, min(len, id->buf_size));
@@ -968,7 +978,11 @@ debug_entry_t
 
 	if (!debug_active || !id->areas)
 		return NULL;
-	spin_lock_irqsave(&id->lock, flags);
+	if (debug_critical) {
+		if (!spin_trylock_irqsave(&id->lock, flags))
+			return NULL;
+	} else
+		spin_lock_irqsave(&id->lock, flags);
 	active = get_active_entry(id);
 	memset(DEBUG_DATA(active), 0, id->buf_size);
 	memcpy(DEBUG_DATA(active), buf, min(len, id->buf_size));
@@ -1013,7 +1027,11 @@ debug_sprintf_event(debug_info_t* id, int level,char *string,...)
 		return NULL;
 	numargs=debug_count_numargs(string);
 
-	spin_lock_irqsave(&id->lock, flags);
+	if (debug_critical) {
+		if (!spin_trylock_irqsave(&id->lock, flags))
+			return NULL;
+	} else
+		spin_lock_irqsave(&id->lock, flags);
 	active = get_active_entry(id);
 	curr_event=(debug_sprintf_entry_t *) DEBUG_DATA(active);
 	va_start(ap,string);
@@ -1047,7 +1065,11 @@ debug_sprintf_exception(debug_info_t* id, int level,char *string,...)
 
 	numargs=debug_count_numargs(string);
 
-	spin_lock_irqsave(&id->lock, flags);
+	if (debug_critical) {
+		if (!spin_trylock_irqsave(&id->lock, flags))
+			return NULL;
+	} else
+		spin_lock_irqsave(&id->lock, flags);
 	active = get_active_entry(id);
 	curr_event=(debug_sprintf_entry_t *)DEBUG_DATA(active);
 	va_start(ap,string);
@@ -1428,10 +1450,10 @@ debug_hex_ascii_format_fn(debug_info_t * id, struct debug_view *view,
 	rc += sprintf(out_buf + rc, "| ");
 	for (i = 0; i < id->buf_size; i++) {
 		unsigned char c = in_buf[i];
-		if (!isprint(c))
-			rc += sprintf(out_buf + rc, ".");
-		else
+		if (isascii(c) && isprint(c))
 			rc += sprintf(out_buf + rc, "%c", c);
+		else
+			rc += sprintf(out_buf + rc, ".");
 	}
 	rc += sprintf(out_buf + rc, "\n");
 	return rc;
diff --git a/arch/s390/kernel/dis.c b/arch/s390/kernel/dis.c
index e2f847599c8e..3221c6fca8bb 100644
--- a/arch/s390/kernel/dis.c
+++ b/arch/s390/kernel/dis.c
@@ -24,7 +24,6 @@
 #include <linux/kprobes.h>
 #include <linux/kdebug.h>
 
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include <asm/io.h>
 #include <linux/atomic.h>
diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c
index 52098d6dfaa7..9475e682727f 100644
--- a/arch/s390/kernel/early.c
+++ b/arch/s390/kernel/early.c
@@ -29,6 +29,7 @@
 #include <asm/sysinfo.h>
 #include <asm/cpcmd.h>
 #include <asm/sclp.h>
+#include <asm/facility.h>
 #include "entry.h"
 
 /*
@@ -262,25 +263,8 @@ static noinline __init void setup_lowcore_early(void)
 
 static noinline __init void setup_facility_list(void)
 {
-	unsigned long nr;
-
-	S390_lowcore.stfl_fac_list = 0;
-	asm volatile(
-		"	.insn	s,0xb2b10000,0(0)\n" /* stfl */
-		"0:\n"
-		EX_TABLE(0b,0b) : "=m" (S390_lowcore.stfl_fac_list));
-	memcpy(&S390_lowcore.stfle_fac_list, &S390_lowcore.stfl_fac_list, 4);
-	nr = 4;				/* # bytes stored by stfl */
-	if (test_facility(7)) {
-		/* More facility bits available with stfle */
-		register unsigned long reg0 asm("0") = MAX_FACILITY_BIT/64 - 1;
-		asm volatile(".insn s,0xb2b00000,%0" /* stfle */
-			     : "=m" (S390_lowcore.stfle_fac_list), "+d" (reg0)
-			     : : "cc");
-		nr = (reg0 + 1) * 8;	/* # bytes stored by stfle */
-	}
-	memset((char *) S390_lowcore.stfle_fac_list + nr, 0,
-	       MAX_FACILITY_BIT/8 - nr);
+	stfle(S390_lowcore.stfle_fac_list,
+	      ARRAY_SIZE(S390_lowcore.stfle_fac_list));
 }
 
 static noinline __init void setup_hpage(void)
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index 3705700ed374..74ee563fe62b 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -2,7 +2,7 @@
  *  arch/s390/kernel/entry.S
  *    S390 low-level entry points.
  *
- *    Copyright (C) IBM Corp. 1999,2006
+ *    Copyright (C) IBM Corp. 1999,2012
  *    Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com),
  *		 Hartmut Penner (hp@de.ibm.com),
  *		 Denis Joseph Barrow (djbarrow@de.ibm.com,barrow_dj@yahoo.com),
@@ -105,14 +105,14 @@ STACK_SIZE  = 1 << STACK_SHIFT
 
 	.macro	ADD64 high,low,timer
 	al	\high,\timer
-	al	\low,\timer+4
+	al	\low,4+\timer
 	brc	12,.+8
 	ahi	\high,1
 	.endm
 
 	.macro	SUB64 high,low,timer
 	sl	\high,\timer
-	sl	\low,\timer+4
+	sl	\low,4+\timer
 	brc	3,.+8
 	ahi	\high,-1
 	.endm
@@ -471,7 +471,6 @@ io_tif:
 	jnz	io_work			# there is work to do (signals etc.)
 io_restore:
 	mvc	__LC_RETURN_PSW(8),__PT_PSW(%r11)
-	ni	__LC_RETURN_PSW+1,0xfd	# clean wait state bit
 	stpt	__LC_EXIT_TIMER
 	lm	%r0,%r15,__PT_R0(%r11)
 	lpsw	__LC_RETURN_PSW
@@ -606,12 +605,32 @@ ext_skip:
 	stm	%r8,%r9,__PT_PSW(%r11)
 	TRACE_IRQS_OFF
 	lr	%r2,%r11		# pass pointer to pt_regs
-	l	%r3,__LC_CPU_ADDRESS	# get cpu address + interruption code
+	l	%r3,__LC_EXT_CPU_ADDR	# get cpu address + interruption code
 	l	%r4,__LC_EXT_PARAMS	# get external parameters
 	l	%r1,BASED(.Ldo_extint)
 	basr	%r14,%r1		# call do_extint
 	j	io_return
 
+/*
+ * Load idle PSW. The second "half" of this function is in cleanup_idle.
+ */
+ENTRY(psw_idle)
+	st	%r4,__SF_EMPTY(%r15)
+	basr	%r1,0
+	la	%r1,psw_idle_lpsw+4-.(%r1)
+	st	%r1,__SF_EMPTY+4(%r15)
+	oi	__SF_EMPTY+4(%r15),0x80
+	la	%r1,.Lvtimer_max-psw_idle_lpsw-4(%r1)
+	stck	__IDLE_ENTER(%r2)
+	ltr	%r5,%r5
+	stpt	__VQ_IDLE_ENTER(%r3)
+	jz	psw_idle_lpsw
+	spt	0(%r1)
+psw_idle_lpsw:
+	lpsw	__SF_EMPTY(%r15)
+	br	%r14
+psw_idle_end:
+
 __critical_end:
 
 /*
@@ -673,7 +692,6 @@ mcck_skip:
 	TRACE_IRQS_ON
 mcck_return:
 	mvc	__LC_RETURN_MCCK_PSW(8),__PT_PSW(%r11) # move return PSW
-	ni	__LC_RETURN_MCCK_PSW+1,0xfd # clear wait state bit
 	tm	__LC_RETURN_MCCK_PSW+1,0x01 # returning to user ?
 	jno	0f
 	lm	%r0,%r15,__PT_R0(%r11)
@@ -691,77 +709,30 @@ mcck_panic:
 0:	ahi	%r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
 	j	mcck_skip
 
-/*
- * Restart interruption handler, kick starter for additional CPUs
- */
-#ifdef CONFIG_SMP
-	__CPUINIT
-ENTRY(restart_int_handler)
-	basr	%r1,0
-restart_base:
-	spt	restart_vtime-restart_base(%r1)
-	stck	__LC_LAST_UPDATE_CLOCK
-	mvc	__LC_LAST_UPDATE_TIMER(8),restart_vtime-restart_base(%r1)
-	mvc	__LC_EXIT_TIMER(8),restart_vtime-restart_base(%r1)
-	l	%r15,__LC_GPREGS_SAVE_AREA+60 # load ksp
-	lctl	%c0,%c15,__LC_CREGS_SAVE_AREA # get new ctl regs
-	lam	%a0,%a15,__LC_AREGS_SAVE_AREA
-	lm	%r6,%r15,__SF_GPRS(%r15)# load registers from clone
-	l	%r1,__LC_THREAD_INFO
-	mvc	__LC_USER_TIMER(8),__TI_user_timer(%r1)
-	mvc	__LC_SYSTEM_TIMER(8),__TI_system_timer(%r1)
-	xc	__LC_STEAL_TIMER(8),__LC_STEAL_TIMER
-	ssm	__LC_PGM_NEW_PSW	# turn dat on, keep irqs off
-	basr	%r14,0
-	l	%r14,restart_addr-.(%r14)
-	basr	%r14,%r14		# call start_secondary
-restart_addr:
-	.long	start_secondary
-	.align	8
-restart_vtime:
-	.long	0x7fffffff,0xffffffff
-	.previous
-#else
-/*
- * If we do not run with SMP enabled, let the new CPU crash ...
- */
-ENTRY(restart_int_handler)
-	basr	%r1,0
-restart_base:
-	lpsw	restart_crash-restart_base(%r1)
-	.align	8
-restart_crash:
-	.long	0x000a0000,0x00000000
-restart_go:
-#endif
-
 #
 # PSW restart interrupt handler
 #
-ENTRY(psw_restart_int_handler)
+ENTRY(restart_int_handler)
 	st	%r15,__LC_SAVE_AREA_RESTART
-	basr	%r15,0
-0:	l	%r15,.Lrestart_stack-0b(%r15)	# load restart stack
-	l	%r15,0(%r15)
+	l	%r15,__LC_RESTART_STACK
 	ahi	%r15,-__PT_SIZE			# create pt_regs on stack
+	xc	0(__PT_SIZE,%r15),0(%r15)
 	stm	%r0,%r14,__PT_R0(%r15)
 	mvc	__PT_R15(4,%r15),__LC_SAVE_AREA_RESTART
 	mvc	__PT_PSW(8,%r15),__LC_RST_OLD_PSW # store restart old psw
-	ahi	%r15,-STACK_FRAME_OVERHEAD
-	xc	__SF_BACKCHAIN(4,%r15),__SF_BACKCHAIN(%r15)
-	basr	%r14,0
-1:	l	%r14,.Ldo_restart-1b(%r14)
-	basr	%r14,%r14
-	basr	%r14,0				# load disabled wait PSW if
-2:	lpsw	restart_psw_crash-2b(%r14)	# do_restart returns
-	.align 4
-.Ldo_restart:
-	.long	do_restart
-.Lrestart_stack:
-	.long	restart_stack
-	.align 8
-restart_psw_crash:
-	.long	0x000a0000,0x00000000 + restart_psw_crash
+	ahi	%r15,-STACK_FRAME_OVERHEAD	# create stack frame on stack
+	xc	0(STACK_FRAME_OVERHEAD,%r15),0(%r15)
+	lm	%r1,%r3,__LC_RESTART_FN		# load fn, parm & source cpu
+	ltr	%r3,%r3				# test source cpu address
+	jm	1f				# negative -> skip source stop
+0:	sigp	%r4,%r3,1			# sigp sense to source cpu
+	brc	10,0b				# wait for status stored
+1:	basr	%r14,%r1			# call function
+	stap	__SF_EMPTY(%r15)		# store cpu address
+	lh	%r3,__SF_EMPTY(%r15)
+2:	sigp	%r4,%r3,5			# sigp stop to current cpu
+	brc	2,2b
+3:	j	3b
 
 	.section .kprobes.text, "ax"
 
@@ -795,6 +766,8 @@ cleanup_table:
 	.long	io_tif + 0x80000000
 	.long	io_restore + 0x80000000
 	.long	io_done + 0x80000000
+	.long	psw_idle + 0x80000000
+	.long	psw_idle_end + 0x80000000
 
 cleanup_critical:
 	cl	%r9,BASED(cleanup_table)	# system_call
@@ -813,6 +786,10 @@ cleanup_critical:
 	jl	cleanup_io_tif
 	cl	%r9,BASED(cleanup_table+28)	# io_done
 	jl	cleanup_io_restore
+	cl	%r9,BASED(cleanup_table+32)	# psw_idle
+	jl	0f
+	cl	%r9,BASED(cleanup_table+36)	# psw_idle_end
+	jl	cleanup_idle
 0:	br	%r14
 
 cleanup_system_call:
@@ -896,7 +873,6 @@ cleanup_io_restore:
 	jhe	0f
 	l	%r9,12(%r11)		# get saved r11 pointer to pt_regs
 	mvc	__LC_RETURN_PSW(8),__PT_PSW(%r9)
-	ni	__LC_RETURN_PSW+1,0xfd	# clear wait state bit
 	mvc	0(32,%r11),__PT_R8(%r9)
 	lm	%r0,%r7,__PT_R0(%r9)
 0:	lm	%r8,%r9,__LC_RETURN_PSW
@@ -904,11 +880,52 @@ cleanup_io_restore:
 cleanup_io_restore_insn:
 	.long	io_done - 4 + 0x80000000
 
+cleanup_idle:
+	# copy interrupt clock & cpu timer
+	mvc	__IDLE_EXIT(8,%r2),__LC_INT_CLOCK
+	mvc	__VQ_IDLE_EXIT(8,%r3),__LC_ASYNC_ENTER_TIMER
+	chi	%r11,__LC_SAVE_AREA_ASYNC
+	je	0f
+	mvc	__IDLE_EXIT(8,%r2),__LC_MCCK_CLOCK
+	mvc	__VQ_IDLE_EXIT(8,%r3),__LC_MCCK_ENTER_TIMER
+0:	# check if stck has been executed
+	cl	%r9,BASED(cleanup_idle_insn)
+	jhe	1f
+	mvc	__IDLE_ENTER(8,%r2),__IDLE_EXIT(%r2)
+	mvc	__VQ_IDLE_ENTER(8,%r3),__VQ_IDLE_EXIT(%r3)
+	j	2f
+1:	# check if the cpu timer has been reprogrammed
+	ltr	%r5,%r5
+	jz	2f
+	spt	__VQ_IDLE_ENTER(%r3)
+2:	# account system time going idle
+	lm	%r9,%r10,__LC_STEAL_TIMER
+	ADD64	%r9,%r10,__IDLE_ENTER(%r2)
+	SUB64	%r9,%r10,__LC_LAST_UPDATE_CLOCK
+	stm	%r9,%r10,__LC_STEAL_TIMER
+	mvc	__LC_LAST_UPDATE_CLOCK(8),__IDLE_EXIT(%r2)
+	lm	%r9,%r10,__LC_SYSTEM_TIMER
+	ADD64	%r9,%r10,__LC_LAST_UPDATE_TIMER
+	SUB64	%r9,%r10,__VQ_IDLE_ENTER(%r3)
+	stm	%r9,%r10,__LC_SYSTEM_TIMER
+	mvc	__LC_LAST_UPDATE_TIMER(8),__VQ_IDLE_EXIT(%r3)
+	# prepare return psw
+	n	%r8,BASED(cleanup_idle_wait)	# clear wait state bit
+	l	%r9,24(%r11)			# return from psw_idle
+	br	%r14
+cleanup_idle_insn:
+	.long	psw_idle_lpsw + 0x80000000
+cleanup_idle_wait:
+	.long	0xfffdffff
+
 /*
  * Integer constants
  */
 	.align	4
-.Lnr_syscalls:		.long	NR_syscalls
+.Lnr_syscalls:
+	.long	NR_syscalls
+.Lvtimer_max:
+	.quad	0x7fffffffffffffff
 
 /*
  * Symbol constants
diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h
index bf538aaf407d..6cdddac93a2e 100644
--- a/arch/s390/kernel/entry.h
+++ b/arch/s390/kernel/entry.h
@@ -4,11 +4,22 @@
 #include <linux/types.h>
 #include <linux/signal.h>
 #include <asm/ptrace.h>
-
+#include <asm/cputime.h>
+#include <asm/timer.h>
 
 extern void (*pgm_check_table[128])(struct pt_regs *);
 extern void *restart_stack;
 
+void system_call(void);
+void pgm_check_handler(void);
+void ext_int_handler(void);
+void io_int_handler(void);
+void mcck_int_handler(void);
+void restart_int_handler(void);
+void restart_call_handler(void);
+void psw_idle(struct s390_idle_data *, struct vtimer_queue *,
+	      unsigned long, int);
+
 asmlinkage long do_syscall_trace_enter(struct pt_regs *regs);
 asmlinkage void do_syscall_trace_exit(struct pt_regs *regs);
 
@@ -24,9 +35,9 @@ int handle_signal32(unsigned long sig, struct k_sigaction *ka,
 		    siginfo_t *info, sigset_t *oldset, struct pt_regs *regs);
 void do_notify_resume(struct pt_regs *regs);
 
-void do_extint(struct pt_regs *regs, unsigned int, unsigned int, unsigned long);
+struct ext_code;
+void do_extint(struct pt_regs *regs, struct ext_code, unsigned int, unsigned long);
 void do_restart(void);
-int __cpuinit start_secondary(void *cpuvoid);
 void __init startup_init(void);
 void die(struct pt_regs *regs, const char *str);
 
diff --git a/arch/s390/kernel/entry64.S b/arch/s390/kernel/entry64.S
index 412a7b8783d7..4e1c292fa7e3 100644
--- a/arch/s390/kernel/entry64.S
+++ b/arch/s390/kernel/entry64.S
@@ -2,7 +2,7 @@
  *  arch/s390/kernel/entry64.S
  *    S390 low-level entry points.
  *
- *    Copyright (C) IBM Corp. 1999,2010
+ *    Copyright (C) IBM Corp. 1999,2012
  *    Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com),
  *		 Hartmut Penner (hp@de.ibm.com),
  *		 Denis Joseph Barrow (djbarrow@de.ibm.com,barrow_dj@yahoo.com),
@@ -489,7 +489,6 @@ io_restore:
 	lg	%r14,__LC_VDSO_PER_CPU
 	lmg	%r0,%r10,__PT_R0(%r11)
 	mvc	__LC_RETURN_PSW(16),__PT_PSW(%r11)
-	ni	__LC_RETURN_PSW+1,0xfd	# clear wait state bit
 	stpt	__LC_EXIT_TIMER
 	mvc	__VDSO_ECTG_BASE(16,%r14),__LC_EXIT_TIMER
 	lmg	%r11,%r15,__PT_R11(%r11)
@@ -625,12 +624,30 @@ ext_skip:
 	TRACE_IRQS_OFF
 	lghi	%r1,4096
 	lgr	%r2,%r11		# pass pointer to pt_regs
-	llgf	%r3,__LC_CPU_ADDRESS	# get cpu address + interruption code
+	llgf	%r3,__LC_EXT_CPU_ADDR	# get cpu address + interruption code
 	llgf	%r4,__LC_EXT_PARAMS	# get external parameter
 	lg	%r5,__LC_EXT_PARAMS2-4096(%r1)	# get 64 bit external parameter
 	brasl	%r14,do_extint
 	j	io_return
 
+/*
+ * Load idle PSW. The second "half" of this function is in cleanup_idle.
+ */
+ENTRY(psw_idle)
+	stg	%r4,__SF_EMPTY(%r15)
+	larl	%r1,psw_idle_lpsw+4
+	stg	%r1,__SF_EMPTY+8(%r15)
+	larl	%r1,.Lvtimer_max
+	stck	__IDLE_ENTER(%r2)
+	ltr	%r5,%r5
+	stpt	__VQ_IDLE_ENTER(%r3)
+	jz	psw_idle_lpsw
+	spt	0(%r1)
+psw_idle_lpsw:
+	lpswe	__SF_EMPTY(%r15)
+	br	%r14
+psw_idle_end:
+
 __critical_end:
 
 /*
@@ -696,7 +713,6 @@ mcck_return:
 	lg	%r14,__LC_VDSO_PER_CPU
 	lmg	%r0,%r10,__PT_R0(%r11)
 	mvc	__LC_RETURN_MCCK_PSW(16),__PT_PSW(%r11) # move return PSW
-	ni	__LC_RETURN_MCCK_PSW+1,0xfd # clear wait state bit
 	tm	__LC_RETURN_MCCK_PSW+1,0x01 # returning to user ?
 	jno	0f
 	stpt	__LC_EXIT_TIMER
@@ -713,68 +729,30 @@ mcck_panic:
 0:	aghi	%r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
 	j	mcck_skip
 
-/*
- * Restart interruption handler, kick starter for additional CPUs
- */
-#ifdef CONFIG_SMP
-	__CPUINIT
-ENTRY(restart_int_handler)
-	basr	%r1,0
-restart_base:
-	spt	restart_vtime-restart_base(%r1)
-	stck	__LC_LAST_UPDATE_CLOCK
-	mvc	__LC_LAST_UPDATE_TIMER(8),restart_vtime-restart_base(%r1)
-	mvc	__LC_EXIT_TIMER(8),restart_vtime-restart_base(%r1)
-	lghi	%r10,__LC_GPREGS_SAVE_AREA
-	lg	%r15,120(%r10)		# load ksp
-	lghi	%r10,__LC_CREGS_SAVE_AREA
-	lctlg	%c0,%c15,0(%r10)	# get new ctl regs
-	lghi	%r10,__LC_AREGS_SAVE_AREA
-	lam	%a0,%a15,0(%r10)
-	lmg	%r6,%r15,__SF_GPRS(%r15)# load registers from clone
-	lg	%r1,__LC_THREAD_INFO
-	mvc	__LC_USER_TIMER(8),__TI_user_timer(%r1)
-	mvc	__LC_SYSTEM_TIMER(8),__TI_system_timer(%r1)
-	xc	__LC_STEAL_TIMER(8),__LC_STEAL_TIMER
-	ssm	__LC_PGM_NEW_PSW	# turn dat on, keep irqs off
-	brasl	%r14,start_secondary
-	.align	8
-restart_vtime:
-	.long	0x7fffffff,0xffffffff
-	.previous
-#else
-/*
- * If we do not run with SMP enabled, let the new CPU crash ...
- */
-ENTRY(restart_int_handler)
-	basr	%r1,0
-restart_base:
-	lpswe	restart_crash-restart_base(%r1)
-	.align 8
-restart_crash:
-	.long  0x000a0000,0x00000000,0x00000000,0x00000000
-restart_go:
-#endif
-
 #
 # PSW restart interrupt handler
 #
-ENTRY(psw_restart_int_handler)
+ENTRY(restart_int_handler)
 	stg	%r15,__LC_SAVE_AREA_RESTART
-	larl	%r15,restart_stack		# load restart stack
-	lg	%r15,0(%r15)
+	lg	%r15,__LC_RESTART_STACK
 	aghi	%r15,-__PT_SIZE			# create pt_regs on stack
+	xc	0(__PT_SIZE,%r15),0(%r15)
 	stmg	%r0,%r14,__PT_R0(%r15)
 	mvc	__PT_R15(8,%r15),__LC_SAVE_AREA_RESTART
 	mvc	__PT_PSW(16,%r15),__LC_RST_OLD_PSW # store restart old psw
-	aghi	%r15,-STACK_FRAME_OVERHEAD
-	xc	__SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
-	brasl	%r14,do_restart
-	larl	%r14,restart_psw_crash		# load disabled wait PSW if
-	lpswe	0(%r14)				# do_restart returns
-	.align 8
-restart_psw_crash:
-	.quad	0x0002000080000000,0x0000000000000000 + restart_psw_crash
+	aghi	%r15,-STACK_FRAME_OVERHEAD	# create stack frame on stack
+	xc	0(STACK_FRAME_OVERHEAD,%r15),0(%r15)
+	lmg	%r1,%r3,__LC_RESTART_FN		# load fn, parm & source cpu
+	ltgr	%r3,%r3				# test source cpu address
+	jm	1f				# negative -> skip source stop
+0:	sigp	%r4,%r3,1			# sigp sense to source cpu
+	brc	10,0b				# wait for status stored
+1:	basr	%r14,%r1			# call function
+	stap	__SF_EMPTY(%r15)		# store cpu address
+	llgh	%r3,__SF_EMPTY(%r15)
+2:	sigp	%r4,%r3,5			# sigp stop to current cpu
+	brc	2,2b
+3:	j	3b
 
 	.section .kprobes.text, "ax"
 
@@ -808,6 +786,8 @@ cleanup_table:
 	.quad	io_tif
 	.quad	io_restore
 	.quad	io_done
+	.quad	psw_idle
+	.quad	psw_idle_end
 
 cleanup_critical:
 	clg	%r9,BASED(cleanup_table)	# system_call
@@ -826,6 +806,10 @@ cleanup_critical:
 	jl	cleanup_io_tif
 	clg	%r9,BASED(cleanup_table+56)	# io_done
 	jl	cleanup_io_restore
+	clg	%r9,BASED(cleanup_table+64)	# psw_idle
+	jl	0f
+	clg	%r9,BASED(cleanup_table+72)	# psw_idle_end
+	jl	cleanup_idle
 0:	br	%r14
 
 
@@ -915,7 +899,6 @@ cleanup_io_restore:
 	je	0f
 	lg	%r9,24(%r11)		# get saved r11 pointer to pt_regs
 	mvc	__LC_RETURN_PSW(16),__PT_PSW(%r9)
-	ni	__LC_RETURN_PSW+1,0xfd	# clear wait state bit
 	mvc	0(64,%r11),__PT_R8(%r9)
 	lmg	%r0,%r7,__PT_R0(%r9)
 0:	lmg	%r8,%r9,__LC_RETURN_PSW
@@ -923,6 +906,42 @@ cleanup_io_restore:
 cleanup_io_restore_insn:
 	.quad	io_done - 4
 
+cleanup_idle:
+	# copy interrupt clock & cpu timer
+	mvc	__IDLE_EXIT(8,%r2),__LC_INT_CLOCK
+	mvc	__VQ_IDLE_EXIT(8,%r3),__LC_ASYNC_ENTER_TIMER
+	cghi	%r11,__LC_SAVE_AREA_ASYNC
+	je	0f
+	mvc	__IDLE_EXIT(8,%r2),__LC_MCCK_CLOCK
+	mvc	__VQ_IDLE_EXIT(8,%r3),__LC_MCCK_ENTER_TIMER
+0:	# check if stck & stpt have been executed
+	clg	%r9,BASED(cleanup_idle_insn)
+	jhe	1f
+	mvc	__IDLE_ENTER(8,%r2),__IDLE_EXIT(%r2)
+	mvc	__VQ_IDLE_ENTER(8,%r3),__VQ_IDLE_EXIT(%r3)
+	j	2f
+1:	# check if the cpu timer has been reprogrammed
+	ltr	%r5,%r5
+	jz	2f
+	spt	__VQ_IDLE_ENTER(%r3)
+2:	# account system time going idle
+	lg	%r9,__LC_STEAL_TIMER
+	alg	%r9,__IDLE_ENTER(%r2)
+	slg	%r9,__LC_LAST_UPDATE_CLOCK
+	stg	%r9,__LC_STEAL_TIMER
+	mvc	__LC_LAST_UPDATE_CLOCK(8),__IDLE_EXIT(%r2)
+	lg	%r9,__LC_SYSTEM_TIMER
+	alg	%r9,__LC_LAST_UPDATE_TIMER
+	slg	%r9,__VQ_IDLE_ENTER(%r3)
+	stg	%r9,__LC_SYSTEM_TIMER
+	mvc	__LC_LAST_UPDATE_TIMER(8),__VQ_IDLE_EXIT(%r3)
+	# prepare return psw
+	nihh	%r8,0xfffd		# clear wait state bit
+	lg	%r9,48(%r11)		# return from psw_idle
+	br	%r14
+cleanup_idle_insn:
+	.quad	psw_idle_lpsw
+
 /*
  * Integer constants
  */
@@ -931,6 +950,8 @@ cleanup_io_restore_insn:
 	.quad	__critical_start
 .Lcritical_length:
 	.quad	__critical_end - __critical_start
+.Lvtimer_max:
+	.quad	0x7fffffffffffffff
 
 
 #if defined(CONFIG_KVM) || defined(CONFIG_KVM_MODULE)
diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c
index affa8e68124a..8342e65a140d 100644
--- a/arch/s390/kernel/ipl.c
+++ b/arch/s390/kernel/ipl.c
@@ -2,7 +2,7 @@
  *  arch/s390/kernel/ipl.c
  *    ipl/reipl/dump support for Linux on s390.
  *
- *    Copyright IBM Corp. 2005,2007
+ *    Copyright IBM Corp. 2005,2012
  *    Author(s): Michael Holzheu <holzheu@de.ibm.com>
  *		 Heiko Carstens <heiko.carstens@de.ibm.com>
  *		 Volker Sameske <sameske@de.ibm.com>
@@ -17,6 +17,7 @@
 #include <linux/fs.h>
 #include <linux/gfp.h>
 #include <linux/crash_dump.h>
+#include <linux/debug_locks.h>
 #include <asm/ipl.h>
 #include <asm/smp.h>
 #include <asm/setup.h>
@@ -25,8 +26,9 @@
 #include <asm/ebcdic.h>
 #include <asm/reset.h>
 #include <asm/sclp.h>
-#include <asm/sigp.h>
 #include <asm/checksum.h>
+#include <asm/debug.h>
+#include <asm/os_info.h>
 #include "entry.h"
 
 #define IPL_PARM_BLOCK_VERSION 0
@@ -571,7 +573,7 @@ static void __ipl_run(void *unused)
 
 static void ipl_run(struct shutdown_trigger *trigger)
 {
-	smp_switch_to_ipl_cpu(__ipl_run, NULL);
+	smp_call_ipl_cpu(__ipl_run, NULL);
 }
 
 static int __init ipl_init(void)
@@ -950,6 +952,13 @@ static struct attribute_group reipl_nss_attr_group = {
 	.attrs = reipl_nss_attrs,
 };
 
+static void set_reipl_block_actual(struct ipl_parameter_block *reipl_block)
+{
+	reipl_block_actual = reipl_block;
+	os_info_entry_add(OS_INFO_REIPL_BLOCK, reipl_block_actual,
+			  reipl_block->hdr.len);
+}
+
 /* reipl type */
 
 static int reipl_set_type(enum ipl_type type)
@@ -965,7 +974,7 @@ static int reipl_set_type(enum ipl_type type)
 			reipl_method = REIPL_METHOD_CCW_VM;
 		else
 			reipl_method = REIPL_METHOD_CCW_CIO;
-		reipl_block_actual = reipl_block_ccw;
+		set_reipl_block_actual(reipl_block_ccw);
 		break;
 	case IPL_TYPE_FCP:
 		if (diag308_set_works)
@@ -974,7 +983,7 @@ static int reipl_set_type(enum ipl_type type)
 			reipl_method = REIPL_METHOD_FCP_RO_VM;
 		else
 			reipl_method = REIPL_METHOD_FCP_RO_DIAG;
-		reipl_block_actual = reipl_block_fcp;
+		set_reipl_block_actual(reipl_block_fcp);
 		break;
 	case IPL_TYPE_FCP_DUMP:
 		reipl_method = REIPL_METHOD_FCP_DUMP;
@@ -984,7 +993,7 @@ static int reipl_set_type(enum ipl_type type)
 			reipl_method = REIPL_METHOD_NSS_DIAG;
 		else
 			reipl_method = REIPL_METHOD_NSS;
-		reipl_block_actual = reipl_block_nss;
+		set_reipl_block_actual(reipl_block_nss);
 		break;
 	case IPL_TYPE_UNKNOWN:
 		reipl_method = REIPL_METHOD_DEFAULT;
@@ -1101,7 +1110,7 @@ static void __reipl_run(void *unused)
 
 static void reipl_run(struct shutdown_trigger *trigger)
 {
-	smp_switch_to_ipl_cpu(__reipl_run, NULL);
+	smp_call_ipl_cpu(__reipl_run, NULL);
 }
 
 static void reipl_block_ccw_init(struct ipl_parameter_block *ipb)
@@ -1256,6 +1265,29 @@ static int __init reipl_fcp_init(void)
 	return 0;
 }
 
+static int __init reipl_type_init(void)
+{
+	enum ipl_type reipl_type = ipl_info.type;
+	struct ipl_parameter_block *reipl_block;
+	unsigned long size;
+
+	reipl_block = os_info_old_entry(OS_INFO_REIPL_BLOCK, &size);
+	if (!reipl_block)
+		goto out;
+	/*
+	 * If we have an OS info reipl block, this will be used
+	 */
+	if (reipl_block->hdr.pbt == DIAG308_IPL_TYPE_FCP) {
+		memcpy(reipl_block_fcp, reipl_block, size);
+		reipl_type = IPL_TYPE_FCP;
+	} else if (reipl_block->hdr.pbt == DIAG308_IPL_TYPE_CCW) {
+		memcpy(reipl_block_ccw, reipl_block, size);
+		reipl_type = IPL_TYPE_CCW;
+	}
+out:
+	return reipl_set_type(reipl_type);
+}
+
 static int __init reipl_init(void)
 {
 	int rc;
@@ -1277,10 +1309,7 @@ static int __init reipl_init(void)
 	rc = reipl_nss_init();
 	if (rc)
 		return rc;
-	rc = reipl_set_type(ipl_info.type);
-	if (rc)
-		return rc;
-	return 0;
+	return reipl_type_init();
 }
 
 static struct shutdown_action __refdata reipl_action = {
@@ -1421,7 +1450,7 @@ static void dump_run(struct shutdown_trigger *trigger)
 	if (dump_method == DUMP_METHOD_NONE)
 		return;
 	smp_send_stop();
-	smp_switch_to_ipl_cpu(__dump_run, NULL);
+	smp_call_ipl_cpu(__dump_run, NULL);
 }
 
 static int __init dump_ccw_init(void)
@@ -1499,30 +1528,12 @@ static struct shutdown_action __refdata dump_action = {
 
 static void dump_reipl_run(struct shutdown_trigger *trigger)
 {
-	preempt_disable();
-	/*
-	 * Bypass dynamic address translation (DAT) when storing IPL parameter
-	 * information block address and checksum into the prefix area
-	 * (corresponding to absolute addresses 0-8191).
-	 * When enhanced DAT applies and the STE format control in one,
-	 * the absolute address is formed without prefixing. In this case a
-	 * normal store (stg/st) into the prefix area would no more match to
-	 * absolute addresses 0-8191.
-	 */
-#ifdef CONFIG_64BIT
-	asm volatile("sturg %0,%1"
-		:: "a" ((unsigned long) reipl_block_actual),
-		"a" (&lowcore_ptr[smp_processor_id()]->ipib));
-#else
-	asm volatile("stura %0,%1"
-		:: "a" ((unsigned long) reipl_block_actual),
-		"a" (&lowcore_ptr[smp_processor_id()]->ipib));
-#endif
-	asm volatile("stura %0,%1"
-		:: "a" (csum_partial(reipl_block_actual,
-				     reipl_block_actual->hdr.len, 0)),
-		"a" (&lowcore_ptr[smp_processor_id()]->ipib_checksum));
-	preempt_enable();
+	u32 csum;
+
+	csum = csum_partial(reipl_block_actual, reipl_block_actual->hdr.len, 0);
+	copy_to_absolute_zero(&S390_lowcore.ipib_checksum, &csum, sizeof(csum));
+	copy_to_absolute_zero(&S390_lowcore.ipib, &reipl_block_actual,
+			      sizeof(reipl_block_actual));
 	dump_run(trigger);
 }
 
@@ -1623,9 +1634,7 @@ static void stop_run(struct shutdown_trigger *trigger)
 	if (strcmp(trigger->name, ON_PANIC_STR) == 0 ||
 	    strcmp(trigger->name, ON_RESTART_STR) == 0)
 		disabled_wait((unsigned long) __builtin_return_address(0));
-	while (sigp(smp_processor_id(), sigp_stop) == sigp_busy)
-		cpu_relax();
-	for (;;);
+	smp_stop_cpu();
 }
 
 static struct shutdown_action stop_action = {SHUTDOWN_ACTION_STOP_STR,
@@ -1713,6 +1722,7 @@ static struct kobj_attribute on_panic_attr =
 
 static void do_panic(void)
 {
+	lgr_info_log();
 	on_panic_trigger.action->fn(&on_panic_trigger);
 	stop_run(&on_panic_trigger);
 }
@@ -1738,9 +1748,8 @@ static ssize_t on_restart_store(struct kobject *kobj,
 static struct kobj_attribute on_restart_attr =
 	__ATTR(on_restart, 0644, on_restart_show, on_restart_store);
 
-void do_restart(void)
+static void __do_restart(void *ignore)
 {
-	smp_restart_with_online_cpu();
 	smp_send_stop();
 #ifdef CONFIG_CRASH_DUMP
 	crash_kexec(NULL);
@@ -1749,6 +1758,14 @@ void do_restart(void)
 	stop_run(&on_restart_trigger);
 }
 
+void do_restart(void)
+{
+	tracing_off();
+	debug_locks_off();
+	lgr_info_log();
+	smp_call_online_cpu(__do_restart, NULL);
+}
+
 /* on halt */
 
 static struct shutdown_trigger on_halt_trigger = {ON_HALT_STR, &stop_action};
diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c
index b9a7fdd9c814..1c2cdd59ccd0 100644
--- a/arch/s390/kernel/irq.c
+++ b/arch/s390/kernel/irq.c
@@ -165,13 +165,6 @@ static inline int ext_hash(u16 code)
 	return (code + (code >> 9)) & 0xff;
 }
 
-static void ext_int_hash_update(struct rcu_head *head)
-{
-	struct ext_int_info *p = container_of(head, struct ext_int_info, rcu);
-
-	kfree(p);
-}
-
 int register_external_interrupt(u16 code, ext_int_handler_t handler)
 {
 	struct ext_int_info *p;
@@ -202,38 +195,34 @@ int unregister_external_interrupt(u16 code, ext_int_handler_t handler)
 	list_for_each_entry_rcu(p, &ext_int_hash[index], entry)
 		if (p->code == code && p->handler == handler) {
 			list_del_rcu(&p->entry);
-			call_rcu(&p->rcu, ext_int_hash_update);
+			kfree_rcu(p, rcu);
 		}
 	spin_unlock_irqrestore(&ext_int_hash_lock, flags);
 	return 0;
 }
 EXPORT_SYMBOL(unregister_external_interrupt);
 
-void __irq_entry do_extint(struct pt_regs *regs, unsigned int ext_int_code,
+void __irq_entry do_extint(struct pt_regs *regs, struct ext_code ext_code,
 			   unsigned int param32, unsigned long param64)
 {
 	struct pt_regs *old_regs;
-	unsigned short code;
 	struct ext_int_info *p;
 	int index;
 
-	code = (unsigned short) ext_int_code;
 	old_regs = set_irq_regs(regs);
-	s390_idle_check(regs, S390_lowcore.int_clock,
-			S390_lowcore.async_enter_timer);
 	irq_enter();
 	if (S390_lowcore.int_clock >= S390_lowcore.clock_comparator)
 		/* Serve timer interrupts first. */
 		clock_comparator_work();
 	kstat_cpu(smp_processor_id()).irqs[EXTERNAL_INTERRUPT]++;
-	if (code != 0x1004)
+	if (ext_code.code != 0x1004)
 		__get_cpu_var(s390_idle).nohz_delay = 1;
 
-	index = ext_hash(code);
+	index = ext_hash(ext_code.code);
 	rcu_read_lock();
 	list_for_each_entry_rcu(p, &ext_int_hash[index], entry)
-		if (likely(p->code == code))
-			p->handler(ext_int_code, param32, param64);
+		if (likely(p->code == ext_code.code))
+			p->handler(ext_code, param32, param64);
 	rcu_read_unlock();
 	irq_exit();
 	set_irq_regs(old_regs);
@@ -266,3 +255,26 @@ void service_subclass_irq_unregister(void)
 	spin_unlock(&sc_irq_lock);
 }
 EXPORT_SYMBOL(service_subclass_irq_unregister);
+
+static DEFINE_SPINLOCK(ma_subclass_lock);
+static int ma_subclass_refcount;
+
+void measurement_alert_subclass_register(void)
+{
+	spin_lock(&ma_subclass_lock);
+	if (!ma_subclass_refcount)
+		ctl_set_bit(0, 5);
+	ma_subclass_refcount++;
+	spin_unlock(&ma_subclass_lock);
+}
+EXPORT_SYMBOL(measurement_alert_subclass_register);
+
+void measurement_alert_subclass_unregister(void)
+{
+	spin_lock(&ma_subclass_lock);
+	ma_subclass_refcount--;
+	if (!ma_subclass_refcount)
+		ctl_clear_bit(0, 5);
+	spin_unlock(&ma_subclass_lock);
+}
+EXPORT_SYMBOL(measurement_alert_subclass_unregister);
diff --git a/arch/s390/kernel/lgr.c b/arch/s390/kernel/lgr.c
new file mode 100644
index 000000000000..87f080b17af1
--- /dev/null
+++ b/arch/s390/kernel/lgr.c
@@ -0,0 +1,200 @@
+/*
+ * Linux Guest Relocation (LGR) detection
+ *
+ * Copyright IBM Corp. 2012
+ * Author(s): Michael Holzheu <holzheu@linux.vnet.ibm.com>
+ */
+
+#include <linux/module.h>
+#include <linux/timer.h>
+#include <linux/slab.h>
+#include <asm/facility.h>
+#include <asm/sysinfo.h>
+#include <asm/ebcdic.h>
+#include <asm/debug.h>
+#include <asm/ipl.h>
+
+#define LGR_TIMER_INTERVAL_SECS (30 * 60)
+#define VM_LEVEL_MAX 2 /* Maximum is 8, but we only record two levels */
+
+/*
+ * LGR info: Contains stfle and stsi data
+ */
+struct lgr_info {
+	/* Bit field with facility information: 4 DWORDs are stored */
+	u64 stfle_fac_list[4];
+	/* Level of system (1 = CEC, 2 = LPAR, 3 = z/VM */
+	u32 level;
+	/* Level 1: CEC info (stsi 1.1.1) */
+	char manufacturer[16];
+	char type[4];
+	char sequence[16];
+	char plant[4];
+	char model[16];
+	/* Level 2: LPAR info (stsi 2.2.2) */
+	u16 lpar_number;
+	char name[8];
+	/* Level 3: VM info (stsi 3.2.2) */
+	u8 vm_count;
+	struct {
+		char name[8];
+		char cpi[16];
+	} vm[VM_LEVEL_MAX];
+} __packed __aligned(8);
+
+/*
+ * LGR globals
+ */
+static void *lgr_page;
+static struct lgr_info lgr_info_last;
+static struct lgr_info lgr_info_cur;
+static struct debug_info *lgr_dbf;
+
+/*
+ * Return number of valid stsi levels
+ */
+static inline int stsi_0(void)
+{
+	int rc = stsi(NULL, 0, 0, 0);
+
+	return rc == -ENOSYS ? rc : (((unsigned int) rc) >> 28);
+}
+
+/*
+ * Copy buffer and then convert it to ASCII
+ */
+static void cpascii(char *dst, char *src, int size)
+{
+	memcpy(dst, src, size);
+	EBCASC(dst, size);
+}
+
+/*
+ * Fill LGR info with 1.1.1 stsi data
+ */
+static void lgr_stsi_1_1_1(struct lgr_info *lgr_info)
+{
+	struct sysinfo_1_1_1 *si = lgr_page;
+
+	if (stsi(si, 1, 1, 1) == -ENOSYS)
+		return;
+	cpascii(lgr_info->manufacturer, si->manufacturer,
+		sizeof(si->manufacturer));
+	cpascii(lgr_info->type, si->type, sizeof(si->type));
+	cpascii(lgr_info->model, si->model, sizeof(si->model));
+	cpascii(lgr_info->sequence, si->sequence, sizeof(si->sequence));
+	cpascii(lgr_info->plant, si->plant, sizeof(si->plant));
+}
+
+/*
+ * Fill LGR info with 2.2.2 stsi data
+ */
+static void lgr_stsi_2_2_2(struct lgr_info *lgr_info)
+{
+	struct sysinfo_2_2_2 *si = lgr_page;
+
+	if (stsi(si, 2, 2, 2) == -ENOSYS)
+		return;
+	cpascii(lgr_info->name, si->name, sizeof(si->name));
+	memcpy(&lgr_info->lpar_number, &si->lpar_number,
+	       sizeof(lgr_info->lpar_number));
+}
+
+/*
+ * Fill LGR info with 3.2.2 stsi data
+ */
+static void lgr_stsi_3_2_2(struct lgr_info *lgr_info)
+{
+	struct sysinfo_3_2_2 *si = lgr_page;
+	int i;
+
+	if (stsi(si, 3, 2, 2) == -ENOSYS)
+		return;
+	for (i = 0; i < min_t(u8, si->count, VM_LEVEL_MAX); i++) {
+		cpascii(lgr_info->vm[i].name, si->vm[i].name,
+			sizeof(si->vm[i].name));
+		cpascii(lgr_info->vm[i].cpi, si->vm[i].cpi,
+			sizeof(si->vm[i].cpi));
+	}
+	lgr_info->vm_count = si->count;
+}
+
+/*
+ * Fill LGR info with current data
+ */
+static void lgr_info_get(struct lgr_info *lgr_info)
+{
+	memset(lgr_info, 0, sizeof(*lgr_info));
+	stfle(lgr_info->stfle_fac_list, ARRAY_SIZE(lgr_info->stfle_fac_list));
+	lgr_info->level = stsi_0();
+	if (lgr_info->level == -ENOSYS)
+		return;
+	if (lgr_info->level >= 1)
+		lgr_stsi_1_1_1(lgr_info);
+	if (lgr_info->level >= 2)
+		lgr_stsi_2_2_2(lgr_info);
+	if (lgr_info->level >= 3)
+		lgr_stsi_3_2_2(lgr_info);
+}
+
+/*
+ * Check if LGR info has changed and if yes log new LGR info to s390dbf
+ */
+void lgr_info_log(void)
+{
+	static DEFINE_SPINLOCK(lgr_info_lock);
+	unsigned long flags;
+
+	if (!spin_trylock_irqsave(&lgr_info_lock, flags))
+		return;
+	lgr_info_get(&lgr_info_cur);
+	if (memcmp(&lgr_info_last, &lgr_info_cur, sizeof(lgr_info_cur)) != 0) {
+		debug_event(lgr_dbf, 1, &lgr_info_cur, sizeof(lgr_info_cur));
+		lgr_info_last = lgr_info_cur;
+	}
+	spin_unlock_irqrestore(&lgr_info_lock, flags);
+}
+EXPORT_SYMBOL_GPL(lgr_info_log);
+
+static void lgr_timer_set(void);
+
+/*
+ * LGR timer callback
+ */
+static void lgr_timer_fn(unsigned long ignored)
+{
+	lgr_info_log();
+	lgr_timer_set();
+}
+
+static struct timer_list lgr_timer =
+	TIMER_DEFERRED_INITIALIZER(lgr_timer_fn, 0, 0);
+
+/*
+ * Setup next LGR timer
+ */
+static void lgr_timer_set(void)
+{
+	mod_timer(&lgr_timer, jiffies + LGR_TIMER_INTERVAL_SECS * HZ);
+}
+
+/*
+ * Initialize LGR: Add s390dbf, write initial lgr_info and setup timer
+ */
+static int __init lgr_init(void)
+{
+	lgr_page = (void *) __get_free_pages(GFP_KERNEL, 0);
+	if (!lgr_page)
+		return -ENOMEM;
+	lgr_dbf = debug_register("lgr", 1, 1, sizeof(struct lgr_info));
+	if (!lgr_dbf) {
+		free_page((unsigned long) lgr_page);
+		return -ENOMEM;
+	}
+	debug_register_view(lgr_dbf, &debug_hex_ascii_view);
+	lgr_info_get(&lgr_info_last);
+	debug_event(lgr_dbf, 1, &lgr_info_last, sizeof(lgr_info_last));
+	lgr_timer_set();
+	return 0;
+}
+module_init(lgr_init);
diff --git a/arch/s390/kernel/machine_kexec.c b/arch/s390/kernel/machine_kexec.c
index 47b168fb29c4..bdad47d54478 100644
--- a/arch/s390/kernel/machine_kexec.c
+++ b/arch/s390/kernel/machine_kexec.c
@@ -14,11 +14,11 @@
 #include <linux/delay.h>
 #include <linux/reboot.h>
 #include <linux/ftrace.h>
+#include <linux/debug_locks.h>
 #include <asm/cio.h>
 #include <asm/setup.h>
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
-#include <asm/system.h>
 #include <asm/smp.h>
 #include <asm/reset.h>
 #include <asm/ipl.h>
@@ -49,50 +49,21 @@ static void add_elf_notes(int cpu)
 }
 
 /*
- * Store status of next available physical CPU
- */
-static int store_status_next(int start_cpu, int this_cpu)
-{
-	struct save_area *sa = (void *) 4608 + store_prefix();
-	int cpu, rc;
-
-	for (cpu = start_cpu; cpu < 65536; cpu++) {
-		if (cpu == this_cpu)
-			continue;
-		do {
-			rc = raw_sigp(cpu, sigp_stop_and_store_status);
-		} while (rc == sigp_busy);
-		if (rc != sigp_order_code_accepted)
-			continue;
-		if (sa->pref_reg)
-			return cpu;
-	}
-	return -1;
-}
-
-/*
  * Initialize CPU ELF notes
  */
 void setup_regs(void)
 {
 	unsigned long sa = S390_lowcore.prefixreg_save_area + SAVE_AREA_BASE;
-	int cpu, this_cpu, phys_cpu = 0, first = 1;
+	int cpu, this_cpu;
 
-	this_cpu = stap();
-
-	if (!S390_lowcore.prefixreg_save_area)
-		first = 0;
+	this_cpu = smp_find_processor_id(stap());
+	add_elf_notes(this_cpu);
 	for_each_online_cpu(cpu) {
-		if (first) {
-			add_elf_notes(cpu);
-			first = 0;
+		if (cpu == this_cpu)
+			continue;
+		if (smp_store_status(cpu))
 			continue;
-		}
-		phys_cpu = store_status_next(phys_cpu, this_cpu);
-		if (phys_cpu == -1)
-			break;
 		add_elf_notes(cpu);
-		phys_cpu++;
 	}
 	/* Copy dump CPU store status info to absolute zero */
 	memcpy((void *) SAVE_AREA_BASE, (void *) sa, sizeof(struct save_area));
@@ -238,10 +209,14 @@ static void __machine_kexec(void *data)
 	struct kimage *image = data;
 
 	pfault_fini();
-	if (image->type == KEXEC_TYPE_CRASH)
+	tracing_off();
+	debug_locks_off();
+	if (image->type == KEXEC_TYPE_CRASH) {
+		lgr_info_log();
 		s390_reset_system(__do_machine_kdump, data);
-	else
+	} else {
 		s390_reset_system(__do_machine_kexec, data);
+	}
 	disabled_wait((unsigned long) __builtin_return_address(0));
 }
 
@@ -255,5 +230,5 @@ void machine_kexec(struct kimage *image)
 		return;
 	tracer_disable();
 	smp_send_stop();
-	smp_switch_to_ipl_cpu(__machine_kexec, image);
+	smp_call_ipl_cpu(__machine_kexec, image);
 }
diff --git a/arch/s390/kernel/nmi.c b/arch/s390/kernel/nmi.c
index 0fd2e863e114..8c372ca61350 100644
--- a/arch/s390/kernel/nmi.c
+++ b/arch/s390/kernel/nmi.c
@@ -254,8 +254,6 @@ void notrace s390_do_machine_check(struct pt_regs *regs)
 	int umode;
 
 	nmi_enter();
-	s390_idle_check(regs, S390_lowcore.mcck_clock,
-			S390_lowcore.mcck_enter_timer);
 	kstat_cpu(smp_processor_id()).irqs[NMI_NMI]++;
 	mci = (struct mci *) &S390_lowcore.mcck_interruption_code;
 	mcck = &__get_cpu_var(cpu_mcck);
diff --git a/arch/s390/kernel/os_info.c b/arch/s390/kernel/os_info.c
new file mode 100644
index 000000000000..e8d6c214d498
--- /dev/null
+++ b/arch/s390/kernel/os_info.c
@@ -0,0 +1,168 @@
+/*
+ * OS info memory interface
+ *
+ * Copyright IBM Corp. 2012
+ * Author(s): Michael Holzheu <holzheu@linux.vnet.ibm.com>
+ */
+
+#define KMSG_COMPONENT "os_info"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
+#include <linux/crash_dump.h>
+#include <linux/kernel.h>
+#include <asm/checksum.h>
+#include <asm/lowcore.h>
+#include <asm/os_info.h>
+
+/*
+ * OS info structure has to be page aligned
+ */
+static struct os_info os_info __page_aligned_data;
+
+/*
+ * Compute checksum over OS info structure
+ */
+u32 os_info_csum(struct os_info *os_info)
+{
+	int size = sizeof(*os_info) - offsetof(struct os_info, version_major);
+	return csum_partial(&os_info->version_major, size, 0);
+}
+
+/*
+ * Add crashkernel info to OS info and update checksum
+ */
+void os_info_crashkernel_add(unsigned long base, unsigned long size)
+{
+	os_info.crashkernel_addr = (u64)(unsigned long)base;
+	os_info.crashkernel_size = (u64)(unsigned long)size;
+	os_info.csum = os_info_csum(&os_info);
+}
+
+/*
+ * Add OS info entry and update checksum
+ */
+void os_info_entry_add(int nr, void *ptr, u64 size)
+{
+	os_info.entry[nr].addr = (u64)(unsigned long)ptr;
+	os_info.entry[nr].size = size;
+	os_info.entry[nr].csum = csum_partial(ptr, size, 0);
+	os_info.csum = os_info_csum(&os_info);
+}
+
+/*
+ * Initialize OS info struture and set lowcore pointer
+ */
+void __init os_info_init(void)
+{
+	void *ptr = &os_info;
+
+	os_info.version_major = OS_INFO_VERSION_MAJOR;
+	os_info.version_minor = OS_INFO_VERSION_MINOR;
+	os_info.magic = OS_INFO_MAGIC;
+	os_info.csum = os_info_csum(&os_info);
+	copy_to_absolute_zero(&S390_lowcore.os_info, &ptr, sizeof(ptr));
+}
+
+#ifdef CONFIG_CRASH_DUMP
+
+static struct os_info *os_info_old;
+
+/*
+ * Allocate and copy OS info entry from oldmem
+ */
+static void os_info_old_alloc(int nr, int align)
+{
+	unsigned long addr, size = 0;
+	char *buf, *buf_align, *msg;
+	u32 csum;
+
+	addr = os_info_old->entry[nr].addr;
+	if (!addr) {
+		msg = "not available";
+		goto fail;
+	}
+	size = os_info_old->entry[nr].size;
+	buf = kmalloc(size + align - 1, GFP_KERNEL);
+	if (!buf) {
+		msg = "alloc failed";
+		goto fail;
+	}
+	buf_align = PTR_ALIGN(buf, align);
+	if (copy_from_oldmem(buf_align, (void *) addr, size)) {
+		msg = "copy failed";
+		goto fail_free;
+	}
+	csum = csum_partial(buf_align, size, 0);
+	if (csum != os_info_old->entry[nr].csum) {
+		msg = "checksum failed";
+		goto fail_free;
+	}
+	os_info_old->entry[nr].addr = (u64)(unsigned long)buf_align;
+	msg = "copied";
+	goto out;
+fail_free:
+	kfree(buf);
+fail:
+	os_info_old->entry[nr].addr = 0;
+out:
+	pr_info("entry %i: %s (addr=0x%lx size=%lu)\n",
+		nr, msg, addr, size);
+}
+
+/*
+ * Initialize os info and os info entries from oldmem
+ */
+static void os_info_old_init(void)
+{
+	static int os_info_init;
+	unsigned long addr;
+
+	if (os_info_init)
+		return;
+	if (!OLDMEM_BASE)
+		goto fail;
+	if (copy_from_oldmem(&addr, &S390_lowcore.os_info, sizeof(addr)))
+		goto fail;
+	if (addr == 0 || addr % PAGE_SIZE)
+		goto fail;
+	os_info_old = kzalloc(sizeof(*os_info_old), GFP_KERNEL);
+	if (!os_info_old)
+		goto fail;
+	if (copy_from_oldmem(os_info_old, (void *) addr, sizeof(*os_info_old)))
+		goto fail_free;
+	if (os_info_old->magic != OS_INFO_MAGIC)
+		goto fail_free;
+	if (os_info_old->csum != os_info_csum(os_info_old))
+		goto fail_free;
+	if (os_info_old->version_major > OS_INFO_VERSION_MAJOR)
+		goto fail_free;
+	os_info_old_alloc(OS_INFO_VMCOREINFO, 1);
+	os_info_old_alloc(OS_INFO_REIPL_BLOCK, 1);
+	os_info_old_alloc(OS_INFO_INIT_FN, PAGE_SIZE);
+	pr_info("crashkernel: addr=0x%lx size=%lu\n",
+		(unsigned long) os_info_old->crashkernel_addr,
+		(unsigned long) os_info_old->crashkernel_size);
+	os_info_init = 1;
+	return;
+fail_free:
+	kfree(os_info_old);
+fail:
+	os_info_init = 1;
+	os_info_old = NULL;
+}
+
+/*
+ * Return pointer to os infor entry and its size
+ */
+void *os_info_old_entry(int nr, unsigned long *size)
+{
+	os_info_old_init();
+
+	if (!os_info_old)
+		return NULL;
+	if (!os_info_old->entry[nr].addr)
+		return NULL;
+	*size = (unsigned long) os_info_old->entry[nr].size;
+	return (void *)(unsigned long)os_info_old->entry[nr].addr;
+}
+#endif
diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c
new file mode 100644
index 000000000000..46405086479c
--- /dev/null
+++ b/arch/s390/kernel/perf_cpum_cf.c
@@ -0,0 +1,690 @@
+/*
+ * Performance event support for s390x - CPU-measurement Counter Facility
+ *
+ *  Copyright IBM Corp. 2012
+ *  Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ */
+#define KMSG_COMPONENT	"cpum_cf"
+#define pr_fmt(fmt)	KMSG_COMPONENT ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/kernel_stat.h>
+#include <linux/perf_event.h>
+#include <linux/percpu.h>
+#include <linux/notifier.h>
+#include <linux/init.h>
+#include <linux/export.h>
+#include <asm/ctl_reg.h>
+#include <asm/irq.h>
+#include <asm/cpu_mf.h>
+
+/* CPU-measurement counter facility supports these CPU counter sets:
+ * For CPU counter sets:
+ *    Basic counter set:	     0-31
+ *    Problem-state counter set:    32-63
+ *    Crypto-activity counter set:  64-127
+ *    Extented counter set:	   128-159
+ */
+enum cpumf_ctr_set {
+	/* CPU counter sets */
+	CPUMF_CTR_SET_BASIC   = 0,
+	CPUMF_CTR_SET_USER    = 1,
+	CPUMF_CTR_SET_CRYPTO  = 2,
+	CPUMF_CTR_SET_EXT     = 3,
+
+	/* Maximum number of counter sets */
+	CPUMF_CTR_SET_MAX,
+};
+
+#define CPUMF_LCCTL_ENABLE_SHIFT    16
+#define CPUMF_LCCTL_ACTCTL_SHIFT     0
+static const u64 cpumf_state_ctl[CPUMF_CTR_SET_MAX] = {
+	[CPUMF_CTR_SET_BASIC]	= 0x02,
+	[CPUMF_CTR_SET_USER]	= 0x04,
+	[CPUMF_CTR_SET_CRYPTO]	= 0x08,
+	[CPUMF_CTR_SET_EXT]	= 0x01,
+};
+
+static void ctr_set_enable(u64 *state, int ctr_set)
+{
+	*state |= cpumf_state_ctl[ctr_set] << CPUMF_LCCTL_ENABLE_SHIFT;
+}
+static void ctr_set_disable(u64 *state, int ctr_set)
+{
+	*state &= ~(cpumf_state_ctl[ctr_set] << CPUMF_LCCTL_ENABLE_SHIFT);
+}
+static void ctr_set_start(u64 *state, int ctr_set)
+{
+	*state |= cpumf_state_ctl[ctr_set] << CPUMF_LCCTL_ACTCTL_SHIFT;
+}
+static void ctr_set_stop(u64 *state, int ctr_set)
+{
+	*state &= ~(cpumf_state_ctl[ctr_set] << CPUMF_LCCTL_ACTCTL_SHIFT);
+}
+
+/* Local CPUMF event structure */
+struct cpu_hw_events {
+	struct cpumf_ctr_info	info;
+	atomic_t		ctr_set[CPUMF_CTR_SET_MAX];
+	u64			state, tx_state;
+	unsigned int		flags;
+};
+static DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events) = {
+	.ctr_set = {
+		[CPUMF_CTR_SET_BASIC]  = ATOMIC_INIT(0),
+		[CPUMF_CTR_SET_USER]   = ATOMIC_INIT(0),
+		[CPUMF_CTR_SET_CRYPTO] = ATOMIC_INIT(0),
+		[CPUMF_CTR_SET_EXT]    = ATOMIC_INIT(0),
+	},
+	.state = 0,
+	.flags = 0,
+};
+
+static int get_counter_set(u64 event)
+{
+	int set = -1;
+
+	if (event < 32)
+		set = CPUMF_CTR_SET_BASIC;
+	else if (event < 64)
+		set = CPUMF_CTR_SET_USER;
+	else if (event < 128)
+		set = CPUMF_CTR_SET_CRYPTO;
+	else if (event < 160)
+		set = CPUMF_CTR_SET_EXT;
+
+	return set;
+}
+
+static int validate_event(const struct hw_perf_event *hwc)
+{
+	switch (hwc->config_base) {
+	case CPUMF_CTR_SET_BASIC:
+	case CPUMF_CTR_SET_USER:
+	case CPUMF_CTR_SET_CRYPTO:
+	case CPUMF_CTR_SET_EXT:
+		/* check for reserved counters */
+		if ((hwc->config >=  6 && hwc->config <=  31) ||
+		    (hwc->config >= 38 && hwc->config <=  63) ||
+		    (hwc->config >= 80 && hwc->config <= 127))
+			return -EOPNOTSUPP;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int validate_ctr_version(const struct hw_perf_event *hwc)
+{
+	struct cpu_hw_events *cpuhw;
+	int err = 0;
+
+	cpuhw = &get_cpu_var(cpu_hw_events);
+
+	/* check required version for counter sets */
+	switch (hwc->config_base) {
+	case CPUMF_CTR_SET_BASIC:
+	case CPUMF_CTR_SET_USER:
+		if (cpuhw->info.cfvn < 1)
+			err = -EOPNOTSUPP;
+		break;
+	case CPUMF_CTR_SET_CRYPTO:
+	case CPUMF_CTR_SET_EXT:
+		if (cpuhw->info.csvn < 1)
+			err = -EOPNOTSUPP;
+		break;
+	}
+
+	put_cpu_var(cpu_hw_events);
+	return err;
+}
+
+static int validate_ctr_auth(const struct hw_perf_event *hwc)
+{
+	struct cpu_hw_events *cpuhw;
+	u64 ctrs_state;
+	int err = 0;
+
+	cpuhw = &get_cpu_var(cpu_hw_events);
+
+	/* check authorization for cpu counter sets */
+	ctrs_state = cpumf_state_ctl[hwc->config_base];
+	if (!(ctrs_state & cpuhw->info.auth_ctl))
+		err = -EPERM;
+
+	put_cpu_var(cpu_hw_events);
+	return err;
+}
+
+/*
+ * Change the CPUMF state to active.
+ * Enable and activate the CPU-counter sets according
+ * to the per-cpu control state.
+ */
+static void cpumf_pmu_enable(struct pmu *pmu)
+{
+	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+	int err;
+
+	if (cpuhw->flags & PMU_F_ENABLED)
+		return;
+
+	err = lcctl(cpuhw->state);
+	if (err) {
+		pr_err("Enabling the performance measuring unit "
+		       "failed with rc=%lx\n", err);
+		return;
+	}
+
+	cpuhw->flags |= PMU_F_ENABLED;
+}
+
+/*
+ * Change the CPUMF state to inactive.
+ * Disable and enable (inactive) the CPU-counter sets according
+ * to the per-cpu control state.
+ */
+static void cpumf_pmu_disable(struct pmu *pmu)
+{
+	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+	int err;
+	u64 inactive;
+
+	if (!(cpuhw->flags & PMU_F_ENABLED))
+		return;
+
+	inactive = cpuhw->state & ~((1 << CPUMF_LCCTL_ENABLE_SHIFT) - 1);
+	err = lcctl(inactive);
+	if (err) {
+		pr_err("Disabling the performance measuring unit "
+		       "failed with rc=%lx\n", err);
+		return;
+	}
+
+	cpuhw->flags &= ~PMU_F_ENABLED;
+}
+
+
+/* Number of perf events counting hardware events */
+static atomic_t num_events = ATOMIC_INIT(0);
+/* Used to avoid races in calling reserve/release_cpumf_hardware */
+static DEFINE_MUTEX(pmc_reserve_mutex);
+
+/* CPU-measurement alerts for the counter facility */
+static void cpumf_measurement_alert(struct ext_code ext_code,
+				    unsigned int alert, unsigned long unused)
+{
+	struct cpu_hw_events *cpuhw;
+
+	if (!(alert & CPU_MF_INT_CF_MASK))
+		return;
+
+	kstat_cpu(smp_processor_id()).irqs[EXTINT_CPM]++;
+	cpuhw = &__get_cpu_var(cpu_hw_events);
+
+	/* Measurement alerts are shared and might happen when the PMU
+	 * is not reserved.  Ignore these alerts in this case. */
+	if (!(cpuhw->flags & PMU_F_RESERVED))
+		return;
+
+	/* counter authorization change alert */
+	if (alert & CPU_MF_INT_CF_CACA)
+		qctri(&cpuhw->info);
+
+	/* loss of counter data alert */
+	if (alert & CPU_MF_INT_CF_LCDA)
+		pr_err("CPU[%i] Counter data was lost\n", smp_processor_id());
+}
+
+#define PMC_INIT      0
+#define PMC_RELEASE   1
+static void setup_pmc_cpu(void *flags)
+{
+	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+
+	switch (*((int *) flags)) {
+	case PMC_INIT:
+		memset(&cpuhw->info, 0, sizeof(cpuhw->info));
+		qctri(&cpuhw->info);
+		cpuhw->flags |= PMU_F_RESERVED;
+		break;
+
+	case PMC_RELEASE:
+		cpuhw->flags &= ~PMU_F_RESERVED;
+		break;
+	}
+
+	/* Disable CPU counter sets */
+	lcctl(0);
+}
+
+/* Initialize the CPU-measurement facility */
+static int reserve_pmc_hardware(void)
+{
+	int flags = PMC_INIT;
+
+	on_each_cpu(setup_pmc_cpu, &flags, 1);
+	measurement_alert_subclass_register();
+
+	return 0;
+}
+
+/* Release the CPU-measurement facility */
+static void release_pmc_hardware(void)
+{
+	int flags = PMC_RELEASE;
+
+	on_each_cpu(setup_pmc_cpu, &flags, 1);
+	measurement_alert_subclass_unregister();
+}
+
+/* Release the PMU if event is the last perf event */
+static void hw_perf_event_destroy(struct perf_event *event)
+{
+	if (!atomic_add_unless(&num_events, -1, 1)) {
+		mutex_lock(&pmc_reserve_mutex);
+		if (atomic_dec_return(&num_events) == 0)
+			release_pmc_hardware();
+		mutex_unlock(&pmc_reserve_mutex);
+	}
+}
+
+/* CPUMF <-> perf event mappings for kernel+userspace (basic set) */
+static const int cpumf_generic_events_basic[] = {
+	[PERF_COUNT_HW_CPU_CYCLES]	    = 0,
+	[PERF_COUNT_HW_INSTRUCTIONS]	    = 1,
+	[PERF_COUNT_HW_CACHE_REFERENCES]    = -1,
+	[PERF_COUNT_HW_CACHE_MISSES]	    = -1,
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = -1,
+	[PERF_COUNT_HW_BRANCH_MISSES]	    = -1,
+	[PERF_COUNT_HW_BUS_CYCLES]	    = -1,
+};
+/* CPUMF <-> perf event mappings for userspace (problem-state set) */
+static const int cpumf_generic_events_user[] = {
+	[PERF_COUNT_HW_CPU_CYCLES]	    = 32,
+	[PERF_COUNT_HW_INSTRUCTIONS]	    = 33,
+	[PERF_COUNT_HW_CACHE_REFERENCES]    = -1,
+	[PERF_COUNT_HW_CACHE_MISSES]	    = -1,
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = -1,
+	[PERF_COUNT_HW_BRANCH_MISSES]	    = -1,
+	[PERF_COUNT_HW_BUS_CYCLES]	    = -1,
+};
+
+static int __hw_perf_event_init(struct perf_event *event)
+{
+	struct perf_event_attr *attr = &event->attr;
+	struct hw_perf_event *hwc = &event->hw;
+	int err;
+	u64 ev;
+
+	switch (attr->type) {
+	case PERF_TYPE_RAW:
+		/* Raw events are used to access counters directly,
+		 * hence do not permit excludes */
+		if (attr->exclude_kernel || attr->exclude_user ||
+		    attr->exclude_hv)
+			return -EOPNOTSUPP;
+		ev = attr->config;
+		break;
+
+	case PERF_TYPE_HARDWARE:
+		ev = attr->config;
+		/* Count user space (problem-state) only */
+		if (!attr->exclude_user && attr->exclude_kernel) {
+			if (ev >= ARRAY_SIZE(cpumf_generic_events_user))
+				return -EOPNOTSUPP;
+			ev = cpumf_generic_events_user[ev];
+
+		/* No support for kernel space counters only */
+		} else if (!attr->exclude_kernel && attr->exclude_user) {
+			return -EOPNOTSUPP;
+
+		/* Count user and kernel space */
+		} else {
+			if (ev >= ARRAY_SIZE(cpumf_generic_events_basic))
+				return -EOPNOTSUPP;
+			ev = cpumf_generic_events_basic[ev];
+		}
+		break;
+
+	default:
+		return -ENOENT;
+	}
+
+	if (ev == -1)
+		return -ENOENT;
+
+	if (ev >= PERF_CPUM_CF_MAX_CTR)
+		return -EINVAL;
+
+	/* The CPU measurement counter facility does not have any interrupts
+	 * to do sampling.  Sampling must be provided by external means,
+	 * for example, by timers.
+	 */
+	if (hwc->sample_period)
+		return -EINVAL;
+
+	/* Use the hardware perf event structure to store the counter number
+	 * in 'config' member and the counter set to which the counter belongs
+	 * in the 'config_base'.  The counter set (config_base) is then used
+	 * to enable/disable the counters.
+	 */
+	hwc->config = ev;
+	hwc->config_base = get_counter_set(ev);
+
+	/* Validate the counter that is assigned to this event.
+	 * Because the counter facility can use numerous counters at the
+	 * same time without constraints, it is not necessary to explicity
+	 * validate event groups (event->group_leader != event).
+	 */
+	err = validate_event(hwc);
+	if (err)
+		return err;
+
+	/* Initialize for using the CPU-measurement counter facility */
+	if (!atomic_inc_not_zero(&num_events)) {
+		mutex_lock(&pmc_reserve_mutex);
+		if (atomic_read(&num_events) == 0 && reserve_pmc_hardware())
+			err = -EBUSY;
+		else
+			atomic_inc(&num_events);
+		mutex_unlock(&pmc_reserve_mutex);
+	}
+	event->destroy = hw_perf_event_destroy;
+
+	/* Finally, validate version and authorization of the counter set */
+	err = validate_ctr_auth(hwc);
+	if (!err)
+		err = validate_ctr_version(hwc);
+
+	return err;
+}
+
+static int cpumf_pmu_event_init(struct perf_event *event)
+{
+	int err;
+
+	switch (event->attr.type) {
+	case PERF_TYPE_HARDWARE:
+	case PERF_TYPE_HW_CACHE:
+	case PERF_TYPE_RAW:
+		err = __hw_perf_event_init(event);
+		break;
+	default:
+		return -ENOENT;
+	}
+
+	if (unlikely(err) && event->destroy)
+		event->destroy(event);
+
+	return err;
+}
+
+static int hw_perf_event_reset(struct perf_event *event)
+{
+	u64 prev, new;
+	int err;
+
+	do {
+		prev = local64_read(&event->hw.prev_count);
+		err = ecctr(event->hw.config, &new);
+		if (err) {
+			if (err != 3)
+				break;
+			/* The counter is not (yet) available. This
+			 * might happen if the counter set to which
+			 * this counter belongs is in the disabled
+			 * state.
+			 */
+			new = 0;
+		}
+	} while (local64_cmpxchg(&event->hw.prev_count, prev, new) != prev);
+
+	return err;
+}
+
+static int hw_perf_event_update(struct perf_event *event)
+{
+	u64 prev, new, delta;
+	int err;
+
+	do {
+		prev = local64_read(&event->hw.prev_count);
+		err = ecctr(event->hw.config, &new);
+		if (err)
+			goto out;
+	} while (local64_cmpxchg(&event->hw.prev_count, prev, new) != prev);
+
+	delta = (prev <= new) ? new - prev
+			      : (-1ULL - prev) + new + 1;	 /* overflow */
+	local64_add(delta, &event->count);
+out:
+	return err;
+}
+
+static void cpumf_pmu_read(struct perf_event *event)
+{
+	if (event->hw.state & PERF_HES_STOPPED)
+		return;
+
+	hw_perf_event_update(event);
+}
+
+static void cpumf_pmu_start(struct perf_event *event, int flags)
+{
+	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+	struct hw_perf_event *hwc = &event->hw;
+
+	if (WARN_ON_ONCE(!(hwc->state & PERF_HES_STOPPED)))
+		return;
+
+	if (WARN_ON_ONCE(hwc->config == -1))
+		return;
+
+	if (flags & PERF_EF_RELOAD)
+		WARN_ON_ONCE(!(hwc->state & PERF_HES_UPTODATE));
+
+	hwc->state = 0;
+
+	/* (Re-)enable and activate the counter set */
+	ctr_set_enable(&cpuhw->state, hwc->config_base);
+	ctr_set_start(&cpuhw->state, hwc->config_base);
+
+	/* The counter set to which this counter belongs can be already active.
+	 * Because all counters in a set are active, the event->hw.prev_count
+	 * needs to be synchronized.  At this point, the counter set can be in
+	 * the inactive or disabled state.
+	 */
+	hw_perf_event_reset(event);
+
+	/* increment refcount for this counter set */
+	atomic_inc(&cpuhw->ctr_set[hwc->config_base]);
+}
+
+static void cpumf_pmu_stop(struct perf_event *event, int flags)
+{
+	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+	struct hw_perf_event *hwc = &event->hw;
+
+	if (!(hwc->state & PERF_HES_STOPPED)) {
+		/* Decrement reference count for this counter set and if this
+		 * is the last used counter in the set, clear activation
+		 * control and set the counter set state to inactive.
+		 */
+		if (!atomic_dec_return(&cpuhw->ctr_set[hwc->config_base]))
+			ctr_set_stop(&cpuhw->state, hwc->config_base);
+		event->hw.state |= PERF_HES_STOPPED;
+	}
+
+	if ((flags & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) {
+		hw_perf_event_update(event);
+		event->hw.state |= PERF_HES_UPTODATE;
+	}
+}
+
+static int cpumf_pmu_add(struct perf_event *event, int flags)
+{
+	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+
+	/* Check authorization for the counter set to which this
+	 * counter belongs.
+	 * For group events transaction, the authorization check is
+	 * done in cpumf_pmu_commit_txn().
+	 */
+	if (!(cpuhw->flags & PERF_EVENT_TXN))
+		if (validate_ctr_auth(&event->hw))
+			return -EPERM;
+
+	ctr_set_enable(&cpuhw->state, event->hw.config_base);
+	event->hw.state = PERF_HES_UPTODATE | PERF_HES_STOPPED;
+
+	if (flags & PERF_EF_START)
+		cpumf_pmu_start(event, PERF_EF_RELOAD);
+
+	perf_event_update_userpage(event);
+
+	return 0;
+}
+
+static void cpumf_pmu_del(struct perf_event *event, int flags)
+{
+	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+
+	cpumf_pmu_stop(event, PERF_EF_UPDATE);
+
+	/* Check if any counter in the counter set is still used.  If not used,
+	 * change the counter set to the disabled state.  This also clears the
+	 * content of all counters in the set.
+	 *
+	 * When a new perf event has been added but not yet started, this can
+	 * clear enable control and resets all counters in a set.  Therefore,
+	 * cpumf_pmu_start() always has to reenable a counter set.
+	 */
+	if (!atomic_read(&cpuhw->ctr_set[event->hw.config_base]))
+		ctr_set_disable(&cpuhw->state, event->hw.config_base);
+
+	perf_event_update_userpage(event);
+}
+
+/*
+ * Start group events scheduling transaction.
+ * Set flags to perform a single test at commit time.
+ */
+static void cpumf_pmu_start_txn(struct pmu *pmu)
+{
+	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+
+	perf_pmu_disable(pmu);
+	cpuhw->flags |= PERF_EVENT_TXN;
+	cpuhw->tx_state = cpuhw->state;
+}
+
+/*
+ * Stop and cancel a group events scheduling tranctions.
+ * Assumes cpumf_pmu_del() is called for each successful added
+ * cpumf_pmu_add() during the transaction.
+ */
+static void cpumf_pmu_cancel_txn(struct pmu *pmu)
+{
+	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+
+	WARN_ON(cpuhw->tx_state != cpuhw->state);
+
+	cpuhw->flags &= ~PERF_EVENT_TXN;
+	perf_pmu_enable(pmu);
+}
+
+/*
+ * Commit the group events scheduling transaction.  On success, the
+ * transaction is closed.   On error, the transaction is kept open
+ * until cpumf_pmu_cancel_txn() is called.
+ */
+static int cpumf_pmu_commit_txn(struct pmu *pmu)
+{
+	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+	u64 state;
+
+	/* check if the updated state can be scheduled */
+	state = cpuhw->state & ~((1 << CPUMF_LCCTL_ENABLE_SHIFT) - 1);
+	state >>= CPUMF_LCCTL_ENABLE_SHIFT;
+	if ((state & cpuhw->info.auth_ctl) != state)
+		return -EPERM;
+
+	cpuhw->flags &= ~PERF_EVENT_TXN;
+	perf_pmu_enable(pmu);
+	return 0;
+}
+
+/* Performance monitoring unit for s390x */
+static struct pmu cpumf_pmu = {
+	.pmu_enable   = cpumf_pmu_enable,
+	.pmu_disable  = cpumf_pmu_disable,
+	.event_init   = cpumf_pmu_event_init,
+	.add	      = cpumf_pmu_add,
+	.del	      = cpumf_pmu_del,
+	.start	      = cpumf_pmu_start,
+	.stop	      = cpumf_pmu_stop,
+	.read	      = cpumf_pmu_read,
+	.start_txn    = cpumf_pmu_start_txn,
+	.commit_txn   = cpumf_pmu_commit_txn,
+	.cancel_txn   = cpumf_pmu_cancel_txn,
+};
+
+static int __cpuinit cpumf_pmu_notifier(struct notifier_block *self,
+					unsigned long action, void *hcpu)
+{
+	unsigned int cpu = (long) hcpu;
+	int flags;
+
+	switch (action & ~CPU_TASKS_FROZEN) {
+	case CPU_ONLINE:
+		flags = PMC_INIT;
+		smp_call_function_single(cpu, setup_pmc_cpu, &flags, 1);
+		break;
+	case CPU_DOWN_PREPARE:
+		flags = PMC_RELEASE;
+		smp_call_function_single(cpu, setup_pmc_cpu, &flags, 1);
+		break;
+	default:
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
+static int __init cpumf_pmu_init(void)
+{
+	int rc;
+
+	if (!cpum_cf_avail())
+		return -ENODEV;
+
+	/* clear bit 15 of cr0 to unauthorize problem-state to
+	 * extract measurement counters */
+	ctl_clear_bit(0, 48);
+
+	/* register handler for measurement-alert interruptions */
+	rc = register_external_interrupt(0x1407, cpumf_measurement_alert);
+	if (rc) {
+		pr_err("Registering for CPU-measurement alerts "
+		       "failed with rc=%i\n", rc);
+		goto out;
+	}
+
+	rc = perf_pmu_register(&cpumf_pmu, "cpum_cf", PERF_TYPE_RAW);
+	if (rc) {
+		pr_err("Registering the cpum_cf PMU failed with rc=%i\n", rc);
+		unregister_external_interrupt(0x1407, cpumf_measurement_alert);
+		goto out;
+	}
+	perf_cpu_notifier(cpumf_pmu_notifier);
+out:
+	return rc;
+}
+early_initcall(cpumf_pmu_init);
diff --git a/arch/s390/kernel/perf_event.c b/arch/s390/kernel/perf_event.c
new file mode 100644
index 000000000000..f58f37f66824
--- /dev/null
+++ b/arch/s390/kernel/perf_event.c
@@ -0,0 +1,124 @@
+/*
+ * Performance event support for s390x
+ *
+ *  Copyright IBM Corp. 2012
+ *  Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ */
+#define KMSG_COMPONENT	"perf"
+#define pr_fmt(fmt)	KMSG_COMPONENT ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/perf_event.h>
+#include <linux/percpu.h>
+#include <linux/export.h>
+#include <asm/irq.h>
+#include <asm/cpu_mf.h>
+#include <asm/lowcore.h>
+#include <asm/processor.h>
+
+const char *perf_pmu_name(void)
+{
+	if (cpum_cf_avail() || cpum_sf_avail())
+		return "CPU-measurement facilities (CPUMF)";
+	return "pmu";
+}
+EXPORT_SYMBOL(perf_pmu_name);
+
+int perf_num_counters(void)
+{
+	int num = 0;
+
+	if (cpum_cf_avail())
+		num += PERF_CPUM_CF_MAX_CTR;
+
+	return num;
+}
+EXPORT_SYMBOL(perf_num_counters);
+
+void perf_event_print_debug(void)
+{
+	struct cpumf_ctr_info cf_info;
+	unsigned long flags;
+	int cpu;
+
+	if (!cpum_cf_avail())
+		return;
+
+	local_irq_save(flags);
+
+	cpu = smp_processor_id();
+	memset(&cf_info, 0, sizeof(cf_info));
+	if (!qctri(&cf_info)) {
+		pr_info("CPU[%i] CPUM_CF: ver=%u.%u A=%04x E=%04x C=%04x\n",
+			cpu, cf_info.cfvn, cf_info.csvn,
+			cf_info.auth_ctl, cf_info.enable_ctl, cf_info.act_ctl);
+		print_hex_dump_bytes("CPUMF Query: ", DUMP_PREFIX_OFFSET,
+				     &cf_info, sizeof(cf_info));
+	}
+
+	local_irq_restore(flags);
+}
+
+/* See also arch/s390/kernel/traps.c */
+static unsigned long __store_trace(struct perf_callchain_entry *entry,
+				   unsigned long sp,
+				   unsigned long low, unsigned long high)
+{
+	struct stack_frame *sf;
+	struct pt_regs *regs;
+
+	while (1) {
+		sp = sp & PSW_ADDR_INSN;
+		if (sp < low || sp > high - sizeof(*sf))
+			return sp;
+		sf = (struct stack_frame *) sp;
+		perf_callchain_store(entry, sf->gprs[8] & PSW_ADDR_INSN);
+		/* Follow the backchain. */
+		while (1) {
+			low = sp;
+			sp = sf->back_chain & PSW_ADDR_INSN;
+			if (!sp)
+				break;
+			if (sp <= low || sp > high - sizeof(*sf))
+				return sp;
+			sf = (struct stack_frame *) sp;
+			perf_callchain_store(entry,
+					     sf->gprs[8] & PSW_ADDR_INSN);
+		}
+		/* Zero backchain detected, check for interrupt frame. */
+		sp = (unsigned long) (sf + 1);
+		if (sp <= low || sp > high - sizeof(*regs))
+			return sp;
+		regs = (struct pt_regs *) sp;
+		perf_callchain_store(entry, sf->gprs[8] & PSW_ADDR_INSN);
+		low = sp;
+		sp = regs->gprs[15];
+	}
+}
+
+void perf_callchain_kernel(struct perf_callchain_entry *entry,
+			   struct pt_regs *regs)
+{
+	unsigned long head;
+	struct stack_frame *head_sf;
+
+	if (user_mode(regs))
+		return;
+
+	head = regs->gprs[15];
+	head_sf = (struct stack_frame *) head;
+
+	if (!head_sf || !head_sf->back_chain)
+		return;
+
+	head = head_sf->back_chain;
+	head = __store_trace(entry, head, S390_lowcore.async_stack - ASYNC_SIZE,
+			     S390_lowcore.async_stack);
+
+	__store_trace(entry, head, S390_lowcore.thread_info,
+		      S390_lowcore.thread_info + THREAD_SIZE);
+}
diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c
index 3201ae447990..60055cefdd04 100644
--- a/arch/s390/kernel/process.c
+++ b/arch/s390/kernel/process.c
@@ -23,14 +23,13 @@
 #include <linux/kprobes.h>
 #include <linux/random.h>
 #include <linux/module.h>
-#include <asm/system.h>
 #include <asm/io.h>
 #include <asm/processor.h>
 #include <asm/irq.h>
 #include <asm/timer.h>
 #include <asm/nmi.h>
-#include <asm/compat.h>
 #include <asm/smp.h>
+#include <asm/switch_to.h>
 #include "entry.h"
 
 asmlinkage void ret_from_fork(void) asm ("ret_from_fork");
@@ -76,16 +75,10 @@ static void default_idle(void)
 	if (test_thread_flag(TIF_MCCK_PENDING)) {
 		local_mcck_enable();
 		local_irq_enable();
-		s390_handle_mcck();
 		return;
 	}
-	trace_hardirqs_on();
-	/* Don't trace preempt off for idle. */
-	stop_critical_timings();
-	/* Stop virtual timer and halt the cpu. */
+	/* Halt the cpu and keep track of cpu time accounting. */
 	vtime_stop_cpu();
-	/* Reenable preemption tracer. */
-	start_critical_timings();
 }
 
 void cpu_idle(void)
@@ -93,13 +86,13 @@ void cpu_idle(void)
 	for (;;) {
 		tick_nohz_idle_enter();
 		rcu_idle_enter();
-		while (!need_resched())
+		while (!need_resched() && !test_thread_flag(TIF_MCCK_PENDING))
 			default_idle();
 		rcu_idle_exit();
 		tick_nohz_idle_exit();
-		preempt_enable_no_resched();
-		schedule();
-		preempt_disable();
+		if (test_thread_flag(TIF_MCCK_PENDING))
+			s390_handle_mcck();
+		schedule_preempt_disabled();
 	}
 }
 
diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c
index 9d82ed4bcb27..02f300fbf070 100644
--- a/arch/s390/kernel/ptrace.c
+++ b/arch/s390/kernel/ptrace.c
@@ -20,15 +20,15 @@
 #include <linux/regset.h>
 #include <linux/tracehook.h>
 #include <linux/seccomp.h>
+#include <linux/compat.h>
 #include <trace/syscall.h>
-#include <asm/compat.h>
 #include <asm/segment.h>
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include <asm/unistd.h>
+#include <asm/switch_to.h>
 #include "entry.h"
 
 #ifdef CONFIG_COMPAT
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index 354de0763eff..06264ae8ccd9 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -2,7 +2,7 @@
  *  arch/s390/kernel/setup.c
  *
  *  S390 version
- *    Copyright (C) IBM Corp. 1999,2010
+ *    Copyright (C) IBM Corp. 1999,2012
  *    Author(s): Hartmut Penner (hp@de.ibm.com),
  *               Martin Schwidefsky (schwidefsky@de.ibm.com)
  *
@@ -46,10 +46,11 @@
 #include <linux/kexec.h>
 #include <linux/crash_dump.h>
 #include <linux/memory.h>
+#include <linux/compat.h>
 
 #include <asm/ipl.h>
 #include <asm/uaccess.h>
-#include <asm/system.h>
+#include <asm/facility.h>
 #include <asm/smp.h>
 #include <asm/mmu_context.h>
 #include <asm/cpcmd.h>
@@ -59,9 +60,10 @@
 #include <asm/ptrace.h>
 #include <asm/sections.h>
 #include <asm/ebcdic.h>
-#include <asm/compat.h>
 #include <asm/kvm_virtio.h>
 #include <asm/diag.h>
+#include <asm/os_info.h>
+#include "entry.h"
 
 long psw_kernel_bits	= PSW_DEFAULT_KEY | PSW_MASK_BASE | PSW_ASC_PRIMARY |
 			  PSW_MASK_EA | PSW_MASK_BA;
@@ -351,8 +353,9 @@ static void setup_addressing_mode(void)
 	}
 }
 
-static void __init
-setup_lowcore(void)
+void *restart_stack __attribute__((__section__(".data")));
+
+static void __init setup_lowcore(void)
 {
 	struct _lowcore *lc;
 
@@ -363,7 +366,7 @@ setup_lowcore(void)
 	lc = __alloc_bootmem_low(LC_PAGES * PAGE_SIZE, LC_PAGES * PAGE_SIZE, 0);
 	lc->restart_psw.mask = psw_kernel_bits;
 	lc->restart_psw.addr =
-		PSW_ADDR_AMODE | (unsigned long) psw_restart_int_handler;
+		PSW_ADDR_AMODE | (unsigned long) restart_int_handler;
 	lc->external_new_psw.mask = psw_kernel_bits |
 		PSW_MASK_DAT | PSW_MASK_MCHECK;
 	lc->external_new_psw.addr =
@@ -412,6 +415,24 @@ setup_lowcore(void)
 	lc->last_update_timer = S390_lowcore.last_update_timer;
 	lc->last_update_clock = S390_lowcore.last_update_clock;
 	lc->ftrace_func = S390_lowcore.ftrace_func;
+
+	restart_stack = __alloc_bootmem(ASYNC_SIZE, ASYNC_SIZE, 0);
+	restart_stack += ASYNC_SIZE;
+
+	/*
+	 * Set up PSW restart to call ipl.c:do_restart(). Copy the relevant
+	 * restart data to the absolute zero lowcore. This is necesary if
+	 * PSW restart is done on an offline CPU that has lowcore zero.
+	 */
+	lc->restart_stack = (unsigned long) restart_stack;
+	lc->restart_fn = (unsigned long) do_restart;
+	lc->restart_data = 0;
+	lc->restart_source = -1UL;
+	memcpy(&S390_lowcore.restart_stack, &lc->restart_stack,
+	       4*sizeof(unsigned long));
+	copy_to_absolute_zero(&S390_lowcore.restart_psw,
+			      &lc->restart_psw, sizeof(psw_t));
+
 	set_prefix((u32)(unsigned long) lc);
 	lowcore_ptr[0] = lc;
 }
@@ -572,27 +593,6 @@ static void __init setup_memory_end(void)
 	}
 }
 
-void *restart_stack __attribute__((__section__(".data")));
-
-/*
- * Setup new PSW and allocate stack for PSW restart interrupt
- */
-static void __init setup_restart_psw(void)
-{
-	psw_t psw;
-
-	restart_stack = __alloc_bootmem(ASYNC_SIZE, ASYNC_SIZE, 0);
-	restart_stack += ASYNC_SIZE;
-
-	/*
-	 * Setup restart PSW for absolute zero lowcore. This is necesary
-	 * if PSW restart is done on an offline CPU that has lowcore zero
-	 */
-	psw.mask = PSW_DEFAULT_KEY | PSW_MASK_BASE | PSW_MASK_EA | PSW_MASK_BA;
-	psw.addr = PSW_ADDR_AMODE | (unsigned long) psw_restart_int_handler;
-	copy_to_absolute_zero(&S390_lowcore.restart_psw, &psw, sizeof(psw));
-}
-
 static void __init setup_vmcoreinfo(void)
 {
 #ifdef CONFIG_KEXEC
@@ -747,7 +747,7 @@ static void __init reserve_crashkernel(void)
 {
 #ifdef CONFIG_CRASH_DUMP
 	unsigned long long crash_base, crash_size;
-	char *msg;
+	char *msg = NULL;
 	int rc;
 
 	rc = parse_crashkernel(boot_command_line, memory_end, &crash_size,
@@ -779,11 +779,11 @@ static void __init reserve_crashkernel(void)
 	pr_info("Reserving %lluMB of memory at %lluMB "
 		"for crashkernel (System RAM: %luMB)\n",
 		crash_size >> 20, crash_base >> 20, memory_end >> 20);
+	os_info_crashkernel_add(crash_base, crash_size);
 #endif
 }
 
-static void __init
-setup_memory(void)
+static void __init setup_memory(void)
 {
         unsigned long bootmap_size;
 	unsigned long start_pfn, end_pfn;
@@ -1014,8 +1014,7 @@ static void __init setup_hwcaps(void)
  * was printed.
  */
 
-void __init
-setup_arch(char **cmdline_p)
+void __init setup_arch(char **cmdline_p)
 {
         /*
          * print what head.S has found out about the machine
@@ -1060,6 +1059,7 @@ setup_arch(char **cmdline_p)
 
 	parse_early_param();
 
+	os_info_init();
 	setup_ipl();
 	setup_memory_end();
 	setup_addressing_mode();
@@ -1068,7 +1068,6 @@ setup_arch(char **cmdline_p)
 	setup_memory();
 	setup_resources();
 	setup_vmcoreinfo();
-	setup_restart_psw();
 	setup_lowcore();
 
         cpu_init();
diff --git a/arch/s390/kernel/signal.c b/arch/s390/kernel/signal.c
index a8ba840294ff..f7582b27f600 100644
--- a/arch/s390/kernel/signal.c
+++ b/arch/s390/kernel/signal.c
@@ -30,7 +30,7 @@
 #include <asm/ucontext.h>
 #include <asm/uaccess.h>
 #include <asm/lowcore.h>
-#include <asm/compat.h>
+#include <asm/switch_to.h>
 #include "entry.h"
 
 #define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP)))
@@ -385,7 +385,6 @@ static int handle_signal(unsigned long sig, struct k_sigaction *ka,
 			 siginfo_t *info, sigset_t *oldset,
 			 struct pt_regs *regs)
 {
-	sigset_t blocked;
 	int ret;
 
 	/* Set up the stack frame */
@@ -395,10 +394,7 @@ static int handle_signal(unsigned long sig, struct k_sigaction *ka,
 		ret = setup_frame(sig, ka, oldset, regs);
 	if (ret)
 		return ret;
-	sigorsets(&blocked, &current->blocked, &ka->sa.sa_mask);
-	if (!(ka->sa.sa_flags & SA_NODEFER))
-		sigaddset(&blocked, sig);
-	set_current_blocked(&blocked);
+	block_sigmask(ka, sig);
 	return 0;
 }
 
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index 2398ce6b15ae..1f77227669e8 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -1,23 +1,18 @@
 /*
- *  arch/s390/kernel/smp.c
+ *  SMP related functions
  *
- *    Copyright IBM Corp. 1999, 2009
- *    Author(s): Denis Joseph Barrow (djbarrow@de.ibm.com,barrow_dj@yahoo.com),
- *		 Martin Schwidefsky (schwidefsky@de.ibm.com)
- *		 Heiko Carstens (heiko.carstens@de.ibm.com)
+ *    Copyright IBM Corp. 1999,2012
+ *    Author(s): Denis Joseph Barrow,
+ *		 Martin Schwidefsky <schwidefsky@de.ibm.com>,
+ *		 Heiko Carstens <heiko.carstens@de.ibm.com>,
  *
  *  based on other smp stuff by
  *    (c) 1995 Alan Cox, CymruNET Ltd  <alan@cymru.net>
  *    (c) 1998 Ingo Molnar
  *
- * We work with logical cpu numbering everywhere we can. The only
- * functions using the real cpu address (got from STAP) are the sigp
- * functions. For all other functions we use the identity mapping.
- * That means that cpu_number_map[i] == i for every cpu. cpu_number_map is
- * used e.g. to find the idle task belonging to a logical cpu. Every array
- * in the kernel is sorted by the logical cpu number and not by the physical
- * one which is causing all the confusion with __cpu_logical_map and
- * cpu_number_map in other architectures.
+ * The code outside of smp.c uses logical cpu numbers, only smp.c does
+ * the translation of logical to physical cpu ids. All new code that
+ * operates on physical cpu numbers needs to go into smp.c.
  */
 
 #define KMSG_COMPONENT "cpu"
@@ -31,198 +26,435 @@
 #include <linux/spinlock.h>
 #include <linux/kernel_stat.h>
 #include <linux/delay.h>
-#include <linux/cache.h>
 #include <linux/interrupt.h>
 #include <linux/irqflags.h>
 #include <linux/cpu.h>
-#include <linux/timex.h>
-#include <linux/bootmem.h>
 #include <linux/slab.h>
 #include <linux/crash_dump.h>
 #include <asm/asm-offsets.h>
+#include <asm/switch_to.h>
+#include <asm/facility.h>
 #include <asm/ipl.h>
 #include <asm/setup.h>
-#include <asm/sigp.h>
-#include <asm/pgalloc.h>
 #include <asm/irq.h>
-#include <asm/cpcmd.h>
 #include <asm/tlbflush.h>
 #include <asm/timer.h>
 #include <asm/lowcore.h>
 #include <asm/sclp.h>
-#include <asm/cputime.h>
 #include <asm/vdso.h>
-#include <asm/cpu.h>
+#include <asm/debug.h>
+#include <asm/os_info.h>
 #include "entry.h"
 
-/* logical cpu to cpu address */
-unsigned short __cpu_logical_map[NR_CPUS];
+enum {
+	sigp_sense = 1,
+	sigp_external_call = 2,
+	sigp_emergency_signal = 3,
+	sigp_start = 4,
+	sigp_stop = 5,
+	sigp_restart = 6,
+	sigp_stop_and_store_status = 9,
+	sigp_initial_cpu_reset = 11,
+	sigp_cpu_reset = 12,
+	sigp_set_prefix = 13,
+	sigp_store_status_at_address = 14,
+	sigp_store_extended_status_at_address = 15,
+	sigp_set_architecture = 18,
+	sigp_conditional_emergency_signal = 19,
+	sigp_sense_running = 21,
+};
 
-static struct task_struct *current_set[NR_CPUS];
+enum {
+	sigp_order_code_accepted = 0,
+	sigp_status_stored = 1,
+	sigp_busy = 2,
+	sigp_not_operational = 3,
+};
 
-static u8 smp_cpu_type;
-static int smp_use_sigp_detection;
+enum {
+	ec_schedule = 0,
+	ec_call_function,
+	ec_call_function_single,
+	ec_stop_cpu,
+};
 
-enum s390_cpu_state {
+enum {
 	CPU_STATE_STANDBY,
 	CPU_STATE_CONFIGURED,
 };
 
+struct pcpu {
+	struct cpu cpu;
+	struct task_struct *idle;	/* idle process for the cpu */
+	struct _lowcore *lowcore;	/* lowcore page(s) for the cpu */
+	unsigned long async_stack;	/* async stack for the cpu */
+	unsigned long panic_stack;	/* panic stack for the cpu */
+	unsigned long ec_mask;		/* bit mask for ec_xxx functions */
+	int state;			/* physical cpu state */
+	u32 status;			/* last status received via sigp */
+	u16 address;			/* physical cpu address */
+};
+
+static u8 boot_cpu_type;
+static u16 boot_cpu_address;
+static struct pcpu pcpu_devices[NR_CPUS];
+
 DEFINE_MUTEX(smp_cpu_state_mutex);
-static int smp_cpu_state[NR_CPUS];
 
-static DEFINE_PER_CPU(struct cpu, cpu_devices);
+/*
+ * Signal processor helper functions.
+ */
+static inline int __pcpu_sigp(u16 addr, u8 order, u32 parm, u32 *status)
+{
+	register unsigned int reg1 asm ("1") = parm;
+	int cc;
 
-static void smp_ext_bitcall(int, int);
+	asm volatile(
+		"	sigp	%1,%2,0(%3)\n"
+		"	ipm	%0\n"
+		"	srl	%0,28\n"
+		: "=d" (cc), "+d" (reg1) : "d" (addr), "a" (order) : "cc");
+	if (status && cc == 1)
+		*status = reg1;
+	return cc;
+}
 
-static int raw_cpu_stopped(int cpu)
+static inline int __pcpu_sigp_relax(u16 addr, u8 order, u32 parm, u32 *status)
 {
-	u32 status;
+	int cc;
 
-	switch (raw_sigp_ps(&status, 0, cpu, sigp_sense)) {
-	case sigp_status_stored:
-		/* Check for stopped and check stop state */
-		if (status & 0x50)
-			return 1;
-		break;
-	default:
-		break;
+	while (1) {
+		cc = __pcpu_sigp(addr, order, parm, status);
+		if (cc != sigp_busy)
+			return cc;
+		cpu_relax();
 	}
-	return 0;
 }
 
-static inline int cpu_stopped(int cpu)
+static int pcpu_sigp_retry(struct pcpu *pcpu, u8 order, u32 parm)
 {
-	return raw_cpu_stopped(cpu_logical_map(cpu));
+	int cc, retry;
+
+	for (retry = 0; ; retry++) {
+		cc = __pcpu_sigp(pcpu->address, order, parm, &pcpu->status);
+		if (cc != sigp_busy)
+			break;
+		if (retry >= 3)
+			udelay(10);
+	}
+	return cc;
+}
+
+static inline int pcpu_stopped(struct pcpu *pcpu)
+{
+	if (__pcpu_sigp(pcpu->address, sigp_sense,
+			0, &pcpu->status) != sigp_status_stored)
+		return 0;
+	/* Check for stopped and check stop state */
+	return !!(pcpu->status & 0x50);
+}
+
+static inline int pcpu_running(struct pcpu *pcpu)
+{
+	if (__pcpu_sigp(pcpu->address, sigp_sense_running,
+			0, &pcpu->status) != sigp_status_stored)
+		return 1;
+	/* Check for running status */
+	return !(pcpu->status & 0x400);
 }
 
 /*
- * Ensure that PSW restart is done on an online CPU
+ * Find struct pcpu by cpu address.
  */
-void smp_restart_with_online_cpu(void)
+static struct pcpu *pcpu_find_address(const struct cpumask *mask, int address)
 {
 	int cpu;
 
-	for_each_online_cpu(cpu) {
-		if (stap() == __cpu_logical_map[cpu]) {
-			/* We are online: Enable DAT again and return */
-			__load_psw_mask(psw_kernel_bits | PSW_MASK_DAT);
-			return;
-		}
+	for_each_cpu(cpu, mask)
+		if (pcpu_devices[cpu].address == address)
+			return pcpu_devices + cpu;
+	return NULL;
+}
+
+static void pcpu_ec_call(struct pcpu *pcpu, int ec_bit)
+{
+	int order;
+
+	set_bit(ec_bit, &pcpu->ec_mask);
+	order = pcpu_running(pcpu) ?
+		sigp_external_call : sigp_emergency_signal;
+	pcpu_sigp_retry(pcpu, order, 0);
+}
+
+static int __cpuinit pcpu_alloc_lowcore(struct pcpu *pcpu, int cpu)
+{
+	struct _lowcore *lc;
+
+	if (pcpu != &pcpu_devices[0]) {
+		pcpu->lowcore =	(struct _lowcore *)
+			__get_free_pages(GFP_KERNEL | GFP_DMA, LC_ORDER);
+		pcpu->async_stack = __get_free_pages(GFP_KERNEL, ASYNC_ORDER);
+		pcpu->panic_stack = __get_free_page(GFP_KERNEL);
+		if (!pcpu->lowcore || !pcpu->panic_stack || !pcpu->async_stack)
+			goto out;
 	}
-	/* We are not online: Do PSW restart on an online CPU */
-	while (sigp(cpu, sigp_restart) == sigp_busy)
-		cpu_relax();
-	/* And stop ourself */
-	while (raw_sigp(stap(), sigp_stop) == sigp_busy)
-		cpu_relax();
-	for (;;);
+	lc = pcpu->lowcore;
+	memcpy(lc, &S390_lowcore, 512);
+	memset((char *) lc + 512, 0, sizeof(*lc) - 512);
+	lc->async_stack = pcpu->async_stack + ASYNC_SIZE;
+	lc->panic_stack = pcpu->panic_stack + PAGE_SIZE;
+	lc->cpu_nr = cpu;
+#ifndef CONFIG_64BIT
+	if (MACHINE_HAS_IEEE) {
+		lc->extended_save_area_addr = get_zeroed_page(GFP_KERNEL);
+		if (!lc->extended_save_area_addr)
+			goto out;
+	}
+#else
+	if (vdso_alloc_per_cpu(lc))
+		goto out;
+#endif
+	lowcore_ptr[cpu] = lc;
+	pcpu_sigp_retry(pcpu, sigp_set_prefix, (u32)(unsigned long) lc);
+	return 0;
+out:
+	if (pcpu != &pcpu_devices[0]) {
+		free_page(pcpu->panic_stack);
+		free_pages(pcpu->async_stack, ASYNC_ORDER);
+		free_pages((unsigned long) pcpu->lowcore, LC_ORDER);
+	}
+	return -ENOMEM;
 }
 
-void smp_switch_to_ipl_cpu(void (*func)(void *), void *data)
+static void pcpu_free_lowcore(struct pcpu *pcpu)
 {
-	struct _lowcore *lc, *current_lc;
-	struct stack_frame *sf;
-	struct pt_regs *regs;
-	unsigned long sp;
-
-	if (smp_processor_id() == 0)
-		func(data);
-	__load_psw_mask(PSW_DEFAULT_KEY | PSW_MASK_BASE |
-			PSW_MASK_EA | PSW_MASK_BA);
-	/* Disable lowcore protection */
-	__ctl_clear_bit(0, 28);
-	current_lc = lowcore_ptr[smp_processor_id()];
-	lc = lowcore_ptr[0];
-	if (!lc)
-		lc = current_lc;
-	lc->restart_psw.mask =
-		PSW_DEFAULT_KEY | PSW_MASK_BASE | PSW_MASK_EA | PSW_MASK_BA;
-	lc->restart_psw.addr = PSW_ADDR_AMODE | (unsigned long) smp_restart_cpu;
-	if (!cpu_online(0))
-		smp_switch_to_cpu(func, data, 0, stap(), __cpu_logical_map[0]);
-	while (sigp(0, sigp_stop_and_store_status) == sigp_busy)
-		cpu_relax();
-	sp = lc->panic_stack;
-	sp -= sizeof(struct pt_regs);
-	regs = (struct pt_regs *) sp;
-	memcpy(&regs->gprs, &current_lc->gpregs_save_area, sizeof(regs->gprs));
-	regs->psw = current_lc->psw_save_area;
-	sp -= STACK_FRAME_OVERHEAD;
-	sf = (struct stack_frame *) sp;
-	sf->back_chain = 0;
-	smp_switch_to_cpu(func, data, sp, stap(), __cpu_logical_map[0]);
+	pcpu_sigp_retry(pcpu, sigp_set_prefix, 0);
+	lowcore_ptr[pcpu - pcpu_devices] = NULL;
+#ifndef CONFIG_64BIT
+	if (MACHINE_HAS_IEEE) {
+		struct _lowcore *lc = pcpu->lowcore;
+
+		free_page((unsigned long) lc->extended_save_area_addr);
+		lc->extended_save_area_addr = 0;
+	}
+#else
+	vdso_free_per_cpu(pcpu->lowcore);
+#endif
+	if (pcpu != &pcpu_devices[0]) {
+		free_page(pcpu->panic_stack);
+		free_pages(pcpu->async_stack, ASYNC_ORDER);
+		free_pages((unsigned long) pcpu->lowcore, LC_ORDER);
+	}
+}
+
+static void pcpu_prepare_secondary(struct pcpu *pcpu, int cpu)
+{
+	struct _lowcore *lc = pcpu->lowcore;
+
+	atomic_inc(&init_mm.context.attach_count);
+	lc->cpu_nr = cpu;
+	lc->percpu_offset = __per_cpu_offset[cpu];
+	lc->kernel_asce = S390_lowcore.kernel_asce;
+	lc->machine_flags = S390_lowcore.machine_flags;
+	lc->ftrace_func = S390_lowcore.ftrace_func;
+	lc->user_timer = lc->system_timer = lc->steal_timer = 0;
+	__ctl_store(lc->cregs_save_area, 0, 15);
+	save_access_regs((unsigned int *) lc->access_regs_save_area);
+	memcpy(lc->stfle_fac_list, S390_lowcore.stfle_fac_list,
+	       MAX_FACILITY_BIT/8);
+}
+
+static void pcpu_attach_task(struct pcpu *pcpu, struct task_struct *tsk)
+{
+	struct _lowcore *lc = pcpu->lowcore;
+	struct thread_info *ti = task_thread_info(tsk);
+
+	lc->kernel_stack = (unsigned long) task_stack_page(tsk) + THREAD_SIZE;
+	lc->thread_info = (unsigned long) task_thread_info(tsk);
+	lc->current_task = (unsigned long) tsk;
+	lc->user_timer = ti->user_timer;
+	lc->system_timer = ti->system_timer;
+	lc->steal_timer = 0;
+}
+
+static void pcpu_start_fn(struct pcpu *pcpu, void (*func)(void *), void *data)
+{
+	struct _lowcore *lc = pcpu->lowcore;
+
+	lc->restart_stack = lc->kernel_stack;
+	lc->restart_fn = (unsigned long) func;
+	lc->restart_data = (unsigned long) data;
+	lc->restart_source = -1UL;
+	pcpu_sigp_retry(pcpu, sigp_restart, 0);
+}
+
+/*
+ * Call function via PSW restart on pcpu and stop the current cpu.
+ */
+static void pcpu_delegate(struct pcpu *pcpu, void (*func)(void *),
+			  void *data, unsigned long stack)
+{
+	struct _lowcore *lc = pcpu->lowcore;
+	unsigned short this_cpu;
+
+	__load_psw_mask(psw_kernel_bits);
+	this_cpu = stap();
+	if (pcpu->address == this_cpu)
+		func(data);	/* should not return */
+	/* Stop target cpu (if func returns this stops the current cpu). */
+	pcpu_sigp_retry(pcpu, sigp_stop, 0);
+	/* Restart func on the target cpu and stop the current cpu. */
+	lc->restart_stack = stack;
+	lc->restart_fn = (unsigned long) func;
+	lc->restart_data = (unsigned long) data;
+	lc->restart_source = (unsigned long) this_cpu;
+	asm volatile(
+		"0:	sigp	0,%0,6	# sigp restart to target cpu\n"
+		"	brc	2,0b	# busy, try again\n"
+		"1:	sigp	0,%1,5	# sigp stop to current cpu\n"
+		"	brc	2,1b	# busy, try again\n"
+		: : "d" (pcpu->address), "d" (this_cpu) : "0", "1", "cc");
+	for (;;) ;
+}
+
+/*
+ * Call function on an online CPU.
+ */
+void smp_call_online_cpu(void (*func)(void *), void *data)
+{
+	struct pcpu *pcpu;
+
+	/* Use the current cpu if it is online. */
+	pcpu = pcpu_find_address(cpu_online_mask, stap());
+	if (!pcpu)
+		/* Use the first online cpu. */
+		pcpu = pcpu_devices + cpumask_first(cpu_online_mask);
+	pcpu_delegate(pcpu, func, data, (unsigned long) restart_stack);
 }
 
-static void smp_stop_cpu(void)
+/*
+ * Call function on the ipl CPU.
+ */
+void smp_call_ipl_cpu(void (*func)(void *), void *data)
 {
-	while (sigp(smp_processor_id(), sigp_stop) == sigp_busy)
+	pcpu_delegate(&pcpu_devices[0], func, data,
+		      pcpu_devices->panic_stack + PAGE_SIZE);
+}
+
+int smp_find_processor_id(u16 address)
+{
+	int cpu;
+
+	for_each_present_cpu(cpu)
+		if (pcpu_devices[cpu].address == address)
+			return cpu;
+	return -1;
+}
+
+int smp_vcpu_scheduled(int cpu)
+{
+	return pcpu_running(pcpu_devices + cpu);
+}
+
+void smp_yield(void)
+{
+	if (MACHINE_HAS_DIAG44)
+		asm volatile("diag 0,0,0x44");
+}
+
+void smp_yield_cpu(int cpu)
+{
+	if (MACHINE_HAS_DIAG9C)
+		asm volatile("diag %0,0,0x9c"
+			     : : "d" (pcpu_devices[cpu].address));
+	else if (MACHINE_HAS_DIAG44)
+		asm volatile("diag 0,0,0x44");
+}
+
+/*
+ * Send cpus emergency shutdown signal. This gives the cpus the
+ * opportunity to complete outstanding interrupts.
+ */
+void smp_emergency_stop(cpumask_t *cpumask)
+{
+	u64 end;
+	int cpu;
+
+	end = get_clock() + (1000000UL << 12);
+	for_each_cpu(cpu, cpumask) {
+		struct pcpu *pcpu = pcpu_devices + cpu;
+		set_bit(ec_stop_cpu, &pcpu->ec_mask);
+		while (__pcpu_sigp(pcpu->address, sigp_emergency_signal,
+				   0, NULL) == sigp_busy &&
+		       get_clock() < end)
+			cpu_relax();
+	}
+	while (get_clock() < end) {
+		for_each_cpu(cpu, cpumask)
+			if (pcpu_stopped(pcpu_devices + cpu))
+				cpumask_clear_cpu(cpu, cpumask);
+		if (cpumask_empty(cpumask))
+			break;
 		cpu_relax();
+	}
 }
 
+/*
+ * Stop all cpus but the current one.
+ */
 void smp_send_stop(void)
 {
 	cpumask_t cpumask;
 	int cpu;
-	u64 end;
 
 	/* Disable all interrupts/machine checks */
 	__load_psw_mask(psw_kernel_bits | PSW_MASK_DAT);
 	trace_hardirqs_off();
 
+	debug_set_critical();
 	cpumask_copy(&cpumask, cpu_online_mask);
 	cpumask_clear_cpu(smp_processor_id(), &cpumask);
 
-	if (oops_in_progress) {
-		/*
-		 * Give the other cpus the opportunity to complete
-		 * outstanding interrupts before stopping them.
-		 */
-		end = get_clock() + (1000000UL << 12);
-		for_each_cpu(cpu, &cpumask) {
-			set_bit(ec_stop_cpu, (unsigned long *)
-				&lowcore_ptr[cpu]->ext_call_fast);
-			while (sigp(cpu, sigp_emergency_signal) == sigp_busy &&
-			       get_clock() < end)
-				cpu_relax();
-		}
-		while (get_clock() < end) {
-			for_each_cpu(cpu, &cpumask)
-				if (cpu_stopped(cpu))
-					cpumask_clear_cpu(cpu, &cpumask);
-			if (cpumask_empty(&cpumask))
-				break;
-			cpu_relax();
-		}
-	}
+	if (oops_in_progress)
+		smp_emergency_stop(&cpumask);
 
 	/* stop all processors */
 	for_each_cpu(cpu, &cpumask) {
-		while (sigp(cpu, sigp_stop) == sigp_busy)
-			cpu_relax();
-		while (!cpu_stopped(cpu))
+		struct pcpu *pcpu = pcpu_devices + cpu;
+		pcpu_sigp_retry(pcpu, sigp_stop, 0);
+		while (!pcpu_stopped(pcpu))
 			cpu_relax();
 	}
 }
 
 /*
+ * Stop the current cpu.
+ */
+void smp_stop_cpu(void)
+{
+	pcpu_sigp_retry(pcpu_devices + smp_processor_id(), sigp_stop, 0);
+	for (;;) ;
+}
+
+/*
  * This is the main routine where commands issued by other
  * cpus are handled.
  */
-
-static void do_ext_call_interrupt(unsigned int ext_int_code,
+static void do_ext_call_interrupt(struct ext_code ext_code,
 				  unsigned int param32, unsigned long param64)
 {
 	unsigned long bits;
+	int cpu;
 
-	if ((ext_int_code & 0xffff) == 0x1202)
-		kstat_cpu(smp_processor_id()).irqs[EXTINT_EXC]++;
+	cpu = smp_processor_id();
+	if (ext_code.code == 0x1202)
+		kstat_cpu(cpu).irqs[EXTINT_EXC]++;
 	else
-		kstat_cpu(smp_processor_id()).irqs[EXTINT_EMS]++;
+		kstat_cpu(cpu).irqs[EXTINT_EMS]++;
 	/*
 	 * handle bit signal external calls
 	 */
-	bits = xchg(&S390_lowcore.ext_call_fast, 0);
+	bits = xchg(&pcpu_devices[cpu].ec_mask, 0);
 
 	if (test_bit(ec_stop_cpu, &bits))
 		smp_stop_cpu();
@@ -238,38 +470,17 @@ static void do_ext_call_interrupt(unsigned int ext_int_code,
 
 }
 
-/*
- * Send an external call sigp to another cpu and return without waiting
- * for its completion.
- */
-static void smp_ext_bitcall(int cpu, int sig)
-{
-	int order;
-
-	/*
-	 * Set signaling bit in lowcore of target cpu and kick it
-	 */
-	set_bit(sig, (unsigned long *) &lowcore_ptr[cpu]->ext_call_fast);
-	while (1) {
-		order = smp_vcpu_scheduled(cpu) ?
-			sigp_external_call : sigp_emergency_signal;
-		if (sigp(cpu, order) != sigp_busy)
-			break;
-		udelay(10);
-	}
-}
-
 void arch_send_call_function_ipi_mask(const struct cpumask *mask)
 {
 	int cpu;
 
 	for_each_cpu(cpu, mask)
-		smp_ext_bitcall(cpu, ec_call_function);
+		pcpu_ec_call(pcpu_devices + cpu, ec_call_function);
 }
 
 void arch_send_call_function_single_ipi(int cpu)
 {
-	smp_ext_bitcall(cpu, ec_call_function_single);
+	pcpu_ec_call(pcpu_devices + cpu, ec_call_function_single);
 }
 
 #ifndef CONFIG_64BIT
@@ -295,15 +506,16 @@ EXPORT_SYMBOL(smp_ptlb_all);
  */
 void smp_send_reschedule(int cpu)
 {
-	smp_ext_bitcall(cpu, ec_schedule);
+	pcpu_ec_call(pcpu_devices + cpu, ec_schedule);
 }
 
 /*
  * parameter area for the set/clear control bit callbacks
  */
 struct ec_creg_mask_parms {
-	unsigned long orvals[16];
-	unsigned long andvals[16];
+	unsigned long orval;
+	unsigned long andval;
+	int cr;
 };
 
 /*
@@ -313,11 +525,9 @@ static void smp_ctl_bit_callback(void *info)
 {
 	struct ec_creg_mask_parms *pp = info;
 	unsigned long cregs[16];
-	int i;
 
 	__ctl_store(cregs, 0, 15);
-	for (i = 0; i <= 15; i++)
-		cregs[i] = (cregs[i] & pp->andvals[i]) | pp->orvals[i];
+	cregs[pp->cr] = (cregs[pp->cr] & pp->andval) | pp->orval;
 	__ctl_load(cregs, 0, 15);
 }
 
@@ -326,11 +536,8 @@ static void smp_ctl_bit_callback(void *info)
  */
 void smp_ctl_set_bit(int cr, int bit)
 {
-	struct ec_creg_mask_parms parms;
+	struct ec_creg_mask_parms parms = { 1UL << bit, -1UL, cr };
 
-	memset(&parms.orvals, 0, sizeof(parms.orvals));
-	memset(&parms.andvals, 0xff, sizeof(parms.andvals));
-	parms.orvals[cr] = 1UL << bit;
 	on_each_cpu(smp_ctl_bit_callback, &parms, 1);
 }
 EXPORT_SYMBOL(smp_ctl_set_bit);
@@ -340,226 +547,178 @@ EXPORT_SYMBOL(smp_ctl_set_bit);
  */
 void smp_ctl_clear_bit(int cr, int bit)
 {
-	struct ec_creg_mask_parms parms;
+	struct ec_creg_mask_parms parms = { 0, ~(1UL << bit), cr };
 
-	memset(&parms.orvals, 0, sizeof(parms.orvals));
-	memset(&parms.andvals, 0xff, sizeof(parms.andvals));
-	parms.andvals[cr] = ~(1UL << bit);
 	on_each_cpu(smp_ctl_bit_callback, &parms, 1);
 }
 EXPORT_SYMBOL(smp_ctl_clear_bit);
 
 #if defined(CONFIG_ZFCPDUMP) || defined(CONFIG_CRASH_DUMP)
 
-static void __init smp_get_save_area(unsigned int cpu, unsigned int phy_cpu)
+struct save_area *zfcpdump_save_areas[NR_CPUS + 1];
+EXPORT_SYMBOL_GPL(zfcpdump_save_areas);
+
+static void __init smp_get_save_area(int cpu, u16 address)
 {
-	if (ipl_info.type != IPL_TYPE_FCP_DUMP && !OLDMEM_BASE)
-		return;
+	void *lc = pcpu_devices[0].lowcore;
+	struct save_area *save_area;
+
 	if (is_kdump_kernel())
 		return;
+	if (!OLDMEM_BASE && (address == boot_cpu_address ||
+			     ipl_info.type != IPL_TYPE_FCP_DUMP))
+		return;
 	if (cpu >= NR_CPUS) {
-		pr_warning("CPU %i exceeds the maximum %i and is excluded from "
-			   "the dump\n", cpu, NR_CPUS - 1);
+		pr_warning("CPU %i exceeds the maximum %i and is excluded "
+			   "from the dump\n", cpu, NR_CPUS - 1);
 		return;
 	}
-	zfcpdump_save_areas[cpu] = kmalloc(sizeof(struct save_area), GFP_KERNEL);
-	while (raw_sigp(phy_cpu, sigp_stop_and_store_status) == sigp_busy)
-		cpu_relax();
-	memcpy_real(zfcpdump_save_areas[cpu],
-		    (void *)(unsigned long) store_prefix() + SAVE_AREA_BASE,
-		    sizeof(struct save_area));
+	save_area = kmalloc(sizeof(struct save_area), GFP_KERNEL);
+	if (!save_area)
+		panic("could not allocate memory for save area\n");
+	zfcpdump_save_areas[cpu] = save_area;
+#ifdef CONFIG_CRASH_DUMP
+	if (address == boot_cpu_address) {
+		/* Copy the registers of the boot cpu. */
+		copy_oldmem_page(1, (void *) save_area, sizeof(*save_area),
+				 SAVE_AREA_BASE - PAGE_SIZE, 0);
+		return;
+	}
+#endif
+	/* Get the registers of a non-boot cpu. */
+	__pcpu_sigp_relax(address, sigp_stop_and_store_status, 0, NULL);
+	memcpy_real(save_area, lc + SAVE_AREA_BASE, sizeof(*save_area));
 }
 
-struct save_area *zfcpdump_save_areas[NR_CPUS + 1];
-EXPORT_SYMBOL_GPL(zfcpdump_save_areas);
-
-#else
-
-static inline void smp_get_save_area(unsigned int cpu, unsigned int phy_cpu) { }
-
-#endif /* CONFIG_ZFCPDUMP */
-
-static int cpu_known(int cpu_id)
+int smp_store_status(int cpu)
 {
-	int cpu;
+	struct pcpu *pcpu;
 
-	for_each_present_cpu(cpu) {
-		if (__cpu_logical_map[cpu] == cpu_id)
-			return 1;
-	}
+	pcpu = pcpu_devices + cpu;
+	if (__pcpu_sigp_relax(pcpu->address, sigp_stop_and_store_status,
+			      0, NULL) != sigp_order_code_accepted)
+		return -EIO;
 	return 0;
 }
 
-static int smp_rescan_cpus_sigp(cpumask_t avail)
-{
-	int cpu_id, logical_cpu;
+#else /* CONFIG_ZFCPDUMP || CONFIG_CRASH_DUMP */
 
-	logical_cpu = cpumask_first(&avail);
-	if (logical_cpu >= nr_cpu_ids)
-		return 0;
-	for (cpu_id = 0; cpu_id <= MAX_CPU_ADDRESS; cpu_id++) {
-		if (cpu_known(cpu_id))
-			continue;
-		__cpu_logical_map[logical_cpu] = cpu_id;
-		cpu_set_polarization(logical_cpu, POLARIZATION_UNKNOWN);
-		if (!cpu_stopped(logical_cpu))
-			continue;
-		set_cpu_present(logical_cpu, true);
-		smp_cpu_state[logical_cpu] = CPU_STATE_CONFIGURED;
-		logical_cpu = cpumask_next(logical_cpu, &avail);
-		if (logical_cpu >= nr_cpu_ids)
-			break;
-	}
-	return 0;
-}
+static inline void smp_get_save_area(int cpu, u16 address) { }
+
+#endif /* CONFIG_ZFCPDUMP || CONFIG_CRASH_DUMP */
 
-static int smp_rescan_cpus_sclp(cpumask_t avail)
+static struct sclp_cpu_info *smp_get_cpu_info(void)
 {
+	static int use_sigp_detection;
 	struct sclp_cpu_info *info;
-	int cpu_id, logical_cpu, cpu;
-	int rc;
-
-	logical_cpu = cpumask_first(&avail);
-	if (logical_cpu >= nr_cpu_ids)
-		return 0;
-	info = kmalloc(sizeof(*info), GFP_KERNEL);
-	if (!info)
-		return -ENOMEM;
-	rc = sclp_get_cpu_info(info);
-	if (rc)
-		goto out;
-	for (cpu = 0; cpu < info->combined; cpu++) {
-		if (info->has_cpu_type && info->cpu[cpu].type != smp_cpu_type)
-			continue;
-		cpu_id = info->cpu[cpu].address;
-		if (cpu_known(cpu_id))
-			continue;
-		__cpu_logical_map[logical_cpu] = cpu_id;
-		cpu_set_polarization(logical_cpu, POLARIZATION_UNKNOWN);
-		set_cpu_present(logical_cpu, true);
-		if (cpu >= info->configured)
-			smp_cpu_state[logical_cpu] = CPU_STATE_STANDBY;
-		else
-			smp_cpu_state[logical_cpu] = CPU_STATE_CONFIGURED;
-		logical_cpu = cpumask_next(logical_cpu, &avail);
-		if (logical_cpu >= nr_cpu_ids)
-			break;
+	int address;
+
+	info = kzalloc(sizeof(*info), GFP_KERNEL);
+	if (info && (use_sigp_detection || sclp_get_cpu_info(info))) {
+		use_sigp_detection = 1;
+		for (address = 0; address <= MAX_CPU_ADDRESS; address++) {
+			if (__pcpu_sigp_relax(address, sigp_sense, 0, NULL) ==
+			    sigp_not_operational)
+				continue;
+			info->cpu[info->configured].address = address;
+			info->configured++;
+		}
+		info->combined = info->configured;
 	}
-out:
-	kfree(info);
-	return rc;
+	return info;
 }
 
-static int __smp_rescan_cpus(void)
+static int __devinit smp_add_present_cpu(int cpu);
+
+static int __devinit __smp_rescan_cpus(struct sclp_cpu_info *info,
+				       int sysfs_add)
 {
+	struct pcpu *pcpu;
 	cpumask_t avail;
+	int cpu, nr, i;
 
+	nr = 0;
 	cpumask_xor(&avail, cpu_possible_mask, cpu_present_mask);
-	if (smp_use_sigp_detection)
-		return smp_rescan_cpus_sigp(avail);
-	else
-		return smp_rescan_cpus_sclp(avail);
+	cpu = cpumask_first(&avail);
+	for (i = 0; (i < info->combined) && (cpu < nr_cpu_ids); i++) {
+		if (info->has_cpu_type && info->cpu[i].type != boot_cpu_type)
+			continue;
+		if (pcpu_find_address(cpu_present_mask, info->cpu[i].address))
+			continue;
+		pcpu = pcpu_devices + cpu;
+		pcpu->address = info->cpu[i].address;
+		pcpu->state = (cpu >= info->configured) ?
+			CPU_STATE_STANDBY : CPU_STATE_CONFIGURED;
+		cpu_set_polarization(cpu, POLARIZATION_UNKNOWN);
+		set_cpu_present(cpu, true);
+		if (sysfs_add && smp_add_present_cpu(cpu) != 0)
+			set_cpu_present(cpu, false);
+		else
+			nr++;
+		cpu = cpumask_next(cpu, &avail);
+	}
+	return nr;
 }
 
 static void __init smp_detect_cpus(void)
 {
 	unsigned int cpu, c_cpus, s_cpus;
 	struct sclp_cpu_info *info;
-	u16 boot_cpu_addr, cpu_addr;
 
-	c_cpus = 1;
-	s_cpus = 0;
-	boot_cpu_addr = __cpu_logical_map[0];
-	info = kmalloc(sizeof(*info), GFP_KERNEL);
+	info = smp_get_cpu_info();
 	if (!info)
 		panic("smp_detect_cpus failed to allocate memory\n");
-#ifdef CONFIG_CRASH_DUMP
-	if (OLDMEM_BASE && !is_kdump_kernel()) {
-		struct save_area *save_area;
-
-		save_area = kmalloc(sizeof(*save_area), GFP_KERNEL);
-		if (!save_area)
-			panic("could not allocate memory for save area\n");
-		copy_oldmem_page(1, (void *) save_area, sizeof(*save_area),
-				 0x200, 0);
-		zfcpdump_save_areas[0] = save_area;
-	}
-#endif
-	/* Use sigp detection algorithm if sclp doesn't work. */
-	if (sclp_get_cpu_info(info)) {
-		smp_use_sigp_detection = 1;
-		for (cpu = 0; cpu <= MAX_CPU_ADDRESS; cpu++) {
-			if (cpu == boot_cpu_addr)
-				continue;
-			if (!raw_cpu_stopped(cpu))
-				continue;
-			smp_get_save_area(c_cpus, cpu);
-			c_cpus++;
-		}
-		goto out;
-	}
-
 	if (info->has_cpu_type) {
 		for (cpu = 0; cpu < info->combined; cpu++) {
-			if (info->cpu[cpu].address == boot_cpu_addr) {
-				smp_cpu_type = info->cpu[cpu].type;
-				break;
-			}
+			if (info->cpu[cpu].address != boot_cpu_address)
+				continue;
+			/* The boot cpu dictates the cpu type. */
+			boot_cpu_type = info->cpu[cpu].type;
+			break;
 		}
 	}
-
+	c_cpus = s_cpus = 0;
 	for (cpu = 0; cpu < info->combined; cpu++) {
-		if (info->has_cpu_type && info->cpu[cpu].type != smp_cpu_type)
-			continue;
-		cpu_addr = info->cpu[cpu].address;
-		if (cpu_addr == boot_cpu_addr)
+		if (info->has_cpu_type && info->cpu[cpu].type != boot_cpu_type)
 			continue;
-		if (!raw_cpu_stopped(cpu_addr)) {
+		if (cpu < info->configured) {
+			smp_get_save_area(c_cpus, info->cpu[cpu].address);
+			c_cpus++;
+		} else
 			s_cpus++;
-			continue;
-		}
-		smp_get_save_area(c_cpus, cpu_addr);
-		c_cpus++;
 	}
-out:
-	kfree(info);
 	pr_info("%d configured CPUs, %d standby CPUs\n", c_cpus, s_cpus);
 	get_online_cpus();
-	__smp_rescan_cpus();
+	__smp_rescan_cpus(info, 0);
 	put_online_cpus();
+	kfree(info);
 }
 
 /*
  *	Activate a secondary processor.
  */
-int __cpuinit start_secondary(void *cpuvoid)
+static void __cpuinit smp_start_secondary(void *cpuvoid)
 {
+	S390_lowcore.last_update_clock = get_clock();
+	S390_lowcore.restart_stack = (unsigned long) restart_stack;
+	S390_lowcore.restart_fn = (unsigned long) do_restart;
+	S390_lowcore.restart_data = 0;
+	S390_lowcore.restart_source = -1UL;
+	restore_access_regs(S390_lowcore.access_regs_save_area);
+	__ctl_load(S390_lowcore.cregs_save_area, 0, 15);
+	__load_psw_mask(psw_kernel_bits | PSW_MASK_DAT);
 	cpu_init();
 	preempt_disable();
 	init_cpu_timer();
 	init_cpu_vtimer();
 	pfault_init();
-
 	notify_cpu_starting(smp_processor_id());
 	ipi_call_lock();
 	set_cpu_online(smp_processor_id(), true);
 	ipi_call_unlock();
-	__ctl_clear_bit(0, 28); /* Disable lowcore protection */
-	S390_lowcore.restart_psw.mask =
-		PSW_DEFAULT_KEY | PSW_MASK_BASE | PSW_MASK_EA | PSW_MASK_BA;
-	S390_lowcore.restart_psw.addr =
-		PSW_ADDR_AMODE | (unsigned long) psw_restart_int_handler;
-	__ctl_set_bit(0, 28); /* Enable lowcore protection */
-	/*
-	 * Wait until the cpu which brought this one up marked it
-	 * active before enabling interrupts.
-	 */
-	while (!cpumask_test_cpu(smp_processor_id(), cpu_active_mask))
-		cpu_relax();
 	local_irq_enable();
 	/* cpu_idle will call schedule for us */
 	cpu_idle();
-	return 0;
 }
 
 struct create_idle {
@@ -578,82 +737,20 @@ static void __cpuinit smp_fork_idle(struct work_struct *work)
 	complete(&c_idle->done);
 }
 
-static int __cpuinit smp_alloc_lowcore(int cpu)
-{
-	unsigned long async_stack, panic_stack;
-	struct _lowcore *lowcore;
-
-	lowcore = (void *) __get_free_pages(GFP_KERNEL | GFP_DMA, LC_ORDER);
-	if (!lowcore)
-		return -ENOMEM;
-	async_stack = __get_free_pages(GFP_KERNEL, ASYNC_ORDER);
-	panic_stack = __get_free_page(GFP_KERNEL);
-	if (!panic_stack || !async_stack)
-		goto out;
-	memcpy(lowcore, &S390_lowcore, 512);
-	memset((char *)lowcore + 512, 0, sizeof(*lowcore) - 512);
-	lowcore->async_stack = async_stack + ASYNC_SIZE;
-	lowcore->panic_stack = panic_stack + PAGE_SIZE;
-	lowcore->restart_psw.mask =
-		PSW_DEFAULT_KEY | PSW_MASK_BASE | PSW_MASK_EA | PSW_MASK_BA;
-	lowcore->restart_psw.addr =
-		PSW_ADDR_AMODE | (unsigned long) restart_int_handler;
-	if (user_mode != HOME_SPACE_MODE)
-		lowcore->restart_psw.mask |= PSW_ASC_HOME;
-#ifndef CONFIG_64BIT
-	if (MACHINE_HAS_IEEE) {
-		unsigned long save_area;
-
-		save_area = get_zeroed_page(GFP_KERNEL);
-		if (!save_area)
-			goto out;
-		lowcore->extended_save_area_addr = (u32) save_area;
-	}
-#else
-	if (vdso_alloc_per_cpu(cpu, lowcore))
-		goto out;
-#endif
-	lowcore_ptr[cpu] = lowcore;
-	return 0;
-
-out:
-	free_page(panic_stack);
-	free_pages(async_stack, ASYNC_ORDER);
-	free_pages((unsigned long) lowcore, LC_ORDER);
-	return -ENOMEM;
-}
-
-static void smp_free_lowcore(int cpu)
-{
-	struct _lowcore *lowcore;
-
-	lowcore = lowcore_ptr[cpu];
-#ifndef CONFIG_64BIT
-	if (MACHINE_HAS_IEEE)
-		free_page((unsigned long) lowcore->extended_save_area_addr);
-#else
-	vdso_free_per_cpu(cpu, lowcore);
-#endif
-	free_page(lowcore->panic_stack - PAGE_SIZE);
-	free_pages(lowcore->async_stack - ASYNC_SIZE, ASYNC_ORDER);
-	free_pages((unsigned long) lowcore, LC_ORDER);
-	lowcore_ptr[cpu] = NULL;
-}
-
 /* Upping and downing of CPUs */
 int __cpuinit __cpu_up(unsigned int cpu)
 {
-	struct _lowcore *cpu_lowcore;
 	struct create_idle c_idle;
-	struct task_struct *idle;
-	struct stack_frame *sf;
-	u32 lowcore;
-	int ccode;
+	struct pcpu *pcpu;
+	int rc;
 
-	if (smp_cpu_state[cpu] != CPU_STATE_CONFIGURED)
+	pcpu = pcpu_devices + cpu;
+	if (pcpu->state != CPU_STATE_CONFIGURED)
+		return -EIO;
+	if (pcpu_sigp_retry(pcpu, sigp_initial_cpu_reset, 0) !=
+	    sigp_order_code_accepted)
 		return -EIO;
-	idle = current_set[cpu];
-	if (!idle) {
+	if (!pcpu->idle) {
 		c_idle.done = COMPLETION_INITIALIZER_ONSTACK(c_idle.done);
 		INIT_WORK_ONSTACK(&c_idle.work, smp_fork_idle);
 		c_idle.cpu = cpu;
@@ -661,68 +758,28 @@ int __cpuinit __cpu_up(unsigned int cpu)
 		wait_for_completion(&c_idle.done);
 		if (IS_ERR(c_idle.idle))
 			return PTR_ERR(c_idle.idle);
-		idle = c_idle.idle;
-		current_set[cpu] = c_idle.idle;
+		pcpu->idle = c_idle.idle;
 	}
-	init_idle(idle, cpu);
-	if (smp_alloc_lowcore(cpu))
-		return -ENOMEM;
-	do {
-		ccode = sigp(cpu, sigp_initial_cpu_reset);
-		if (ccode == sigp_busy)
-			udelay(10);
-		if (ccode == sigp_not_operational)
-			goto err_out;
-	} while (ccode == sigp_busy);
-
-	lowcore = (u32)(unsigned long)lowcore_ptr[cpu];
-	while (sigp_p(lowcore, cpu, sigp_set_prefix) == sigp_busy)
-		udelay(10);
-
-	cpu_lowcore = lowcore_ptr[cpu];
-	cpu_lowcore->kernel_stack = (unsigned long)
-		task_stack_page(idle) + THREAD_SIZE;
-	cpu_lowcore->thread_info = (unsigned long) task_thread_info(idle);
-	sf = (struct stack_frame *) (cpu_lowcore->kernel_stack
-				     - sizeof(struct pt_regs)
-				     - sizeof(struct stack_frame));
-	memset(sf, 0, sizeof(struct stack_frame));
-	sf->gprs[9] = (unsigned long) sf;
-	cpu_lowcore->gpregs_save_area[15] = (unsigned long) sf;
-	__ctl_store(cpu_lowcore->cregs_save_area, 0, 15);
-	atomic_inc(&init_mm.context.attach_count);
-	asm volatile(
-		"	stam	0,15,0(%0)"
-		: : "a" (&cpu_lowcore->access_regs_save_area) : "memory");
-	cpu_lowcore->percpu_offset = __per_cpu_offset[cpu];
-	cpu_lowcore->current_task = (unsigned long) idle;
-	cpu_lowcore->cpu_nr = cpu;
-	cpu_lowcore->kernel_asce = S390_lowcore.kernel_asce;
-	cpu_lowcore->machine_flags = S390_lowcore.machine_flags;
-	cpu_lowcore->ftrace_func = S390_lowcore.ftrace_func;
-	memcpy(cpu_lowcore->stfle_fac_list, S390_lowcore.stfle_fac_list,
-	       MAX_FACILITY_BIT/8);
-	eieio();
-
-	while (sigp(cpu, sigp_restart) == sigp_busy)
-		udelay(10);
-
+	init_idle(pcpu->idle, cpu);
+	rc = pcpu_alloc_lowcore(pcpu, cpu);
+	if (rc)
+		return rc;
+	pcpu_prepare_secondary(pcpu, cpu);
+	pcpu_attach_task(pcpu, pcpu->idle);
+	pcpu_start_fn(pcpu, smp_start_secondary, NULL);
 	while (!cpu_online(cpu))
 		cpu_relax();
 	return 0;
-
-err_out:
-	smp_free_lowcore(cpu);
-	return -EIO;
 }
 
 static int __init setup_possible_cpus(char *s)
 {
-	int pcpus, cpu;
+	int max, cpu;
 
-	pcpus = simple_strtoul(s, NULL, 0);
+	if (kstrtoint(s, 0, &max) < 0)
+		return 0;
 	init_cpu_possible(cpumask_of(0));
-	for (cpu = 1; cpu < pcpus && cpu < nr_cpu_ids; cpu++)
+	for (cpu = 1; cpu < max && cpu < nr_cpu_ids; cpu++)
 		set_cpu_possible(cpu, true);
 	return 0;
 }
@@ -732,113 +789,79 @@ early_param("possible_cpus", setup_possible_cpus);
 
 int __cpu_disable(void)
 {
-	struct ec_creg_mask_parms cr_parms;
-	int cpu = smp_processor_id();
-
-	set_cpu_online(cpu, false);
+	unsigned long cregs[16];
 
-	/* Disable pfault pseudo page faults on this cpu. */
+	set_cpu_online(smp_processor_id(), false);
+	/* Disable pseudo page faults on this cpu. */
 	pfault_fini();
-
-	memset(&cr_parms.orvals, 0, sizeof(cr_parms.orvals));
-	memset(&cr_parms.andvals, 0xff, sizeof(cr_parms.andvals));
-
-	/* disable all external interrupts */
-	cr_parms.orvals[0] = 0;
-	cr_parms.andvals[0] = ~(1 << 15 | 1 << 14 | 1 << 13 | 1 << 11 |
-				1 << 10 | 1 <<	9 | 1 <<  6 | 1 <<  5 |
-				1 <<  4);
-	/* disable all I/O interrupts */
-	cr_parms.orvals[6] = 0;
-	cr_parms.andvals[6] = ~(1 << 31 | 1 << 30 | 1 << 29 | 1 << 28 |
-				1 << 27 | 1 << 26 | 1 << 25 | 1 << 24);
-	/* disable most machine checks */
-	cr_parms.orvals[14] = 0;
-	cr_parms.andvals[14] = ~(1 << 28 | 1 << 27 | 1 << 26 |
-				 1 << 25 | 1 << 24);
-
-	smp_ctl_bit_callback(&cr_parms);
-
+	/* Disable interrupt sources via control register. */
+	__ctl_store(cregs, 0, 15);
+	cregs[0]  &= ~0x0000ee70UL;	/* disable all external interrupts */
+	cregs[6]  &= ~0xff000000UL;	/* disable all I/O interrupts */
+	cregs[14] &= ~0x1f000000UL;	/* disable most machine checks */
+	__ctl_load(cregs, 0, 15);
 	return 0;
 }
 
 void __cpu_die(unsigned int cpu)
 {
+	struct pcpu *pcpu;
+
 	/* Wait until target cpu is down */
-	while (!cpu_stopped(cpu))
+	pcpu = pcpu_devices + cpu;
+	while (!pcpu_stopped(pcpu))
 		cpu_relax();
-	while (sigp_p(0, cpu, sigp_set_prefix) == sigp_busy)
-		udelay(10);
-	smp_free_lowcore(cpu);
+	pcpu_free_lowcore(pcpu);
 	atomic_dec(&init_mm.context.attach_count);
 }
 
 void __noreturn cpu_die(void)
 {
 	idle_task_exit();
-	while (sigp(smp_processor_id(), sigp_stop) == sigp_busy)
-		cpu_relax();
-	for (;;);
+	pcpu_sigp_retry(pcpu_devices + smp_processor_id(), sigp_stop, 0);
+	for (;;) ;
 }
 
 #endif /* CONFIG_HOTPLUG_CPU */
 
-void __init smp_prepare_cpus(unsigned int max_cpus)
+static void smp_call_os_info_init_fn(void)
 {
-#ifndef CONFIG_64BIT
-	unsigned long save_area = 0;
-#endif
-	unsigned long async_stack, panic_stack;
-	struct _lowcore *lowcore;
+	int (*init_fn)(void);
+	unsigned long size;
 
-	smp_detect_cpus();
+	init_fn = os_info_old_entry(OS_INFO_INIT_FN, &size);
+	if (!init_fn)
+		return;
+	init_fn();
+}
 
+void __init smp_prepare_cpus(unsigned int max_cpus)
+{
 	/* request the 0x1201 emergency signal external interrupt */
 	if (register_external_interrupt(0x1201, do_ext_call_interrupt) != 0)
 		panic("Couldn't request external interrupt 0x1201");
 	/* request the 0x1202 external call external interrupt */
 	if (register_external_interrupt(0x1202, do_ext_call_interrupt) != 0)
 		panic("Couldn't request external interrupt 0x1202");
-
-	/* Reallocate current lowcore, but keep its contents. */
-	lowcore = (void *) __get_free_pages(GFP_KERNEL | GFP_DMA, LC_ORDER);
-	panic_stack = __get_free_page(GFP_KERNEL);
-	async_stack = __get_free_pages(GFP_KERNEL, ASYNC_ORDER);
-	BUG_ON(!lowcore || !panic_stack || !async_stack);
-#ifndef CONFIG_64BIT
-	if (MACHINE_HAS_IEEE)
-		save_area = get_zeroed_page(GFP_KERNEL);
-#endif
-	local_irq_disable();
-	local_mcck_disable();
-	lowcore_ptr[smp_processor_id()] = lowcore;
-	*lowcore = S390_lowcore;
-	lowcore->panic_stack = panic_stack + PAGE_SIZE;
-	lowcore->async_stack = async_stack + ASYNC_SIZE;
-#ifndef CONFIG_64BIT
-	if (MACHINE_HAS_IEEE)
-		lowcore->extended_save_area_addr = (u32) save_area;
-#endif
-	set_prefix((u32)(unsigned long) lowcore);
-	local_mcck_enable();
-	local_irq_enable();
-#ifdef CONFIG_64BIT
-	if (vdso_alloc_per_cpu(smp_processor_id(), &S390_lowcore))
-		BUG();
-#endif
+	smp_call_os_info_init_fn();
+	smp_detect_cpus();
 }
 
 void __init smp_prepare_boot_cpu(void)
 {
-	BUG_ON(smp_processor_id() != 0);
-
-	current_thread_info()->cpu = 0;
-	set_cpu_present(0, true);
-	set_cpu_online(0, true);
+	struct pcpu *pcpu = pcpu_devices;
+
+	boot_cpu_address = stap();
+	pcpu->idle = current;
+	pcpu->state = CPU_STATE_CONFIGURED;
+	pcpu->address = boot_cpu_address;
+	pcpu->lowcore = (struct _lowcore *)(unsigned long) store_prefix();
+	pcpu->async_stack = S390_lowcore.async_stack - ASYNC_SIZE;
+	pcpu->panic_stack = S390_lowcore.panic_stack - PAGE_SIZE;
 	S390_lowcore.percpu_offset = __per_cpu_offset[0];
-	current_set[0] = current;
-	smp_cpu_state[0] = CPU_STATE_CONFIGURED;
 	cpu_set_polarization(0, POLARIZATION_UNKNOWN);
+	set_cpu_present(0, true);
+	set_cpu_online(0, true);
 }
 
 void __init smp_cpus_done(unsigned int max_cpus)
@@ -848,7 +871,6 @@ void __init smp_cpus_done(unsigned int max_cpus)
 void __init smp_setup_processor_id(void)
 {
 	S390_lowcore.cpu_nr = 0;
-	__cpu_logical_map[0] = stap();
 }
 
 /*
@@ -864,56 +886,57 @@ int setup_profiling_timer(unsigned int multiplier)
 
 #ifdef CONFIG_HOTPLUG_CPU
 static ssize_t cpu_configure_show(struct device *dev,
-				struct device_attribute *attr, char *buf)
+				  struct device_attribute *attr, char *buf)
 {
 	ssize_t count;
 
 	mutex_lock(&smp_cpu_state_mutex);
-	count = sprintf(buf, "%d\n", smp_cpu_state[dev->id]);
+	count = sprintf(buf, "%d\n", pcpu_devices[dev->id].state);
 	mutex_unlock(&smp_cpu_state_mutex);
 	return count;
 }
 
 static ssize_t cpu_configure_store(struct device *dev,
-				  struct device_attribute *attr,
-				  const char *buf, size_t count)
+				   struct device_attribute *attr,
+				   const char *buf, size_t count)
 {
-	int cpu = dev->id;
-	int val, rc;
+	struct pcpu *pcpu;
+	int cpu, val, rc;
 	char delim;
 
 	if (sscanf(buf, "%d %c", &val, &delim) != 1)
 		return -EINVAL;
 	if (val != 0 && val != 1)
 		return -EINVAL;
-
 	get_online_cpus();
 	mutex_lock(&smp_cpu_state_mutex);
 	rc = -EBUSY;
 	/* disallow configuration changes of online cpus and cpu 0 */
+	cpu = dev->id;
 	if (cpu_online(cpu) || cpu == 0)
 		goto out;
+	pcpu = pcpu_devices + cpu;
 	rc = 0;
 	switch (val) {
 	case 0:
-		if (smp_cpu_state[cpu] == CPU_STATE_CONFIGURED) {
-			rc = sclp_cpu_deconfigure(__cpu_logical_map[cpu]);
-			if (!rc) {
-				smp_cpu_state[cpu] = CPU_STATE_STANDBY;
-				cpu_set_polarization(cpu, POLARIZATION_UNKNOWN);
-				topology_expect_change();
-			}
-		}
+		if (pcpu->state != CPU_STATE_CONFIGURED)
+			break;
+		rc = sclp_cpu_deconfigure(pcpu->address);
+		if (rc)
+			break;
+		pcpu->state = CPU_STATE_STANDBY;
+		cpu_set_polarization(cpu, POLARIZATION_UNKNOWN);
+		topology_expect_change();
 		break;
 	case 1:
-		if (smp_cpu_state[cpu] == CPU_STATE_STANDBY) {
-			rc = sclp_cpu_configure(__cpu_logical_map[cpu]);
-			if (!rc) {
-				smp_cpu_state[cpu] = CPU_STATE_CONFIGURED;
-				cpu_set_polarization(cpu, POLARIZATION_UNKNOWN);
-				topology_expect_change();
-			}
-		}
+		if (pcpu->state != CPU_STATE_STANDBY)
+			break;
+		rc = sclp_cpu_configure(pcpu->address);
+		if (rc)
+			break;
+		pcpu->state = CPU_STATE_CONFIGURED;
+		cpu_set_polarization(cpu, POLARIZATION_UNKNOWN);
+		topology_expect_change();
 		break;
 	default:
 		break;
@@ -929,7 +952,7 @@ static DEVICE_ATTR(configure, 0644, cpu_configure_show, cpu_configure_store);
 static ssize_t show_cpu_address(struct device *dev,
 				struct device_attribute *attr, char *buf)
 {
-	return sprintf(buf, "%d\n", __cpu_logical_map[dev->id]);
+	return sprintf(buf, "%d\n", pcpu_devices[dev->id].address);
 }
 static DEVICE_ATTR(address, 0444, show_cpu_address, NULL);
 
@@ -961,22 +984,16 @@ static DEVICE_ATTR(capability, 0444, show_capability, NULL);
 static ssize_t show_idle_count(struct device *dev,
 				struct device_attribute *attr, char *buf)
 {
-	struct s390_idle_data *idle;
+	struct s390_idle_data *idle = &per_cpu(s390_idle, dev->id);
 	unsigned long long idle_count;
 	unsigned int sequence;
 
-	idle = &per_cpu(s390_idle, dev->id);
-repeat:
-	sequence = idle->sequence;
-	smp_rmb();
-	if (sequence & 1)
-		goto repeat;
-	idle_count = idle->idle_count;
-	if (idle->idle_enter)
-		idle_count++;
-	smp_rmb();
-	if (idle->sequence != sequence)
-		goto repeat;
+	do {
+		sequence = ACCESS_ONCE(idle->sequence);
+		idle_count = ACCESS_ONCE(idle->idle_count);
+		if (ACCESS_ONCE(idle->idle_enter))
+			idle_count++;
+	} while ((sequence & 1) || (idle->sequence != sequence));
 	return sprintf(buf, "%llu\n", idle_count);
 }
 static DEVICE_ATTR(idle_count, 0444, show_idle_count, NULL);
@@ -984,24 +1001,18 @@ static DEVICE_ATTR(idle_count, 0444, show_idle_count, NULL);
 static ssize_t show_idle_time(struct device *dev,
 				struct device_attribute *attr, char *buf)
 {
-	struct s390_idle_data *idle;
-	unsigned long long now, idle_time, idle_enter;
+	struct s390_idle_data *idle = &per_cpu(s390_idle, dev->id);
+	unsigned long long now, idle_time, idle_enter, idle_exit;
 	unsigned int sequence;
 
-	idle = &per_cpu(s390_idle, dev->id);
-	now = get_clock();
-repeat:
-	sequence = idle->sequence;
-	smp_rmb();
-	if (sequence & 1)
-		goto repeat;
-	idle_time = idle->idle_time;
-	idle_enter = idle->idle_enter;
-	if (idle_enter != 0ULL && idle_enter < now)
-		idle_time += now - idle_enter;
-	smp_rmb();
-	if (idle->sequence != sequence)
-		goto repeat;
+	do {
+		now = get_clock();
+		sequence = ACCESS_ONCE(idle->sequence);
+		idle_time = ACCESS_ONCE(idle->idle_time);
+		idle_enter = ACCESS_ONCE(idle->idle_enter);
+		idle_exit = ACCESS_ONCE(idle->idle_exit);
+	} while ((sequence & 1) || (idle->sequence != sequence));
+	idle_time += idle_enter ? ((idle_exit ? : now) - idle_enter) : 0;
 	return sprintf(buf, "%llu\n", idle_time >> 12);
 }
 static DEVICE_ATTR(idle_time_us, 0444, show_idle_time, NULL);
@@ -1021,7 +1032,7 @@ static int __cpuinit smp_cpu_notify(struct notifier_block *self,
 				    unsigned long action, void *hcpu)
 {
 	unsigned int cpu = (unsigned int)(long)hcpu;
-	struct cpu *c = &per_cpu(cpu_devices, cpu);
+	struct cpu *c = &pcpu_devices[cpu].cpu;
 	struct device *s = &c->dev;
 	struct s390_idle_data *idle;
 	int err = 0;
@@ -1047,7 +1058,7 @@ static struct notifier_block __cpuinitdata smp_cpu_nb = {
 
 static int __devinit smp_add_present_cpu(int cpu)
 {
-	struct cpu *c = &per_cpu(cpu_devices, cpu);
+	struct cpu *c = &pcpu_devices[cpu].cpu;
 	struct device *s = &c->dev;
 	int rc;
 
@@ -1085,29 +1096,21 @@ out:
 
 int __ref smp_rescan_cpus(void)
 {
-	cpumask_t newcpus;
-	int cpu;
-	int rc;
+	struct sclp_cpu_info *info;
+	int nr;
 
+	info = smp_get_cpu_info();
+	if (!info)
+		return -ENOMEM;
 	get_online_cpus();
 	mutex_lock(&smp_cpu_state_mutex);
-	cpumask_copy(&newcpus, cpu_present_mask);
-	rc = __smp_rescan_cpus();
-	if (rc)
-		goto out;
-	cpumask_andnot(&newcpus, cpu_present_mask, &newcpus);
-	for_each_cpu(cpu, &newcpus) {
-		rc = smp_add_present_cpu(cpu);
-		if (rc)
-			set_cpu_present(cpu, false);
-	}
-	rc = 0;
-out:
+	nr = __smp_rescan_cpus(info, 1);
 	mutex_unlock(&smp_cpu_state_mutex);
 	put_online_cpus();
-	if (!cpumask_empty(&newcpus))
+	kfree(info);
+	if (nr)
 		topology_schedule_update();
-	return rc;
+	return 0;
 }
 
 static ssize_t __ref rescan_store(struct device *dev,
diff --git a/arch/s390/kernel/suspend.c b/arch/s390/kernel/suspend.c
index 47df775c844d..aa1494d0e380 100644
--- a/arch/s390/kernel/suspend.c
+++ b/arch/s390/kernel/suspend.c
@@ -9,7 +9,7 @@
 #include <linux/pfn.h>
 #include <linux/suspend.h>
 #include <linux/mm.h>
-#include <asm/system.h>
+#include <asm/ctl_reg.h>
 
 /*
  * References to section boundaries
diff --git a/arch/s390/kernel/switch_cpu.S b/arch/s390/kernel/switch_cpu.S
deleted file mode 100644
index bfe070bc7659..000000000000
--- a/arch/s390/kernel/switch_cpu.S
+++ /dev/null
@@ -1,58 +0,0 @@
-/*
- * 31-bit switch cpu code
- *
- * Copyright IBM Corp. 2009
- *
- */
-
-#include <linux/linkage.h>
-#include <asm/asm-offsets.h>
-#include <asm/ptrace.h>
-
-# smp_switch_to_cpu switches to destination cpu and executes the passed function
-# Parameter: %r2 - function to call
-#	     %r3 - function parameter
-#	     %r4 - stack poiner
-#	     %r5 - current cpu
-#	     %r6 - destination cpu
-
-	.section .text
-ENTRY(smp_switch_to_cpu)
-	stm	%r6,%r15,__SF_GPRS(%r15)
-	lr	%r1,%r15
-	ahi	%r15,-STACK_FRAME_OVERHEAD
-	st	%r1,__SF_BACKCHAIN(%r15)
-	basr	%r13,0
-0:	la	%r1,.gprregs_addr-0b(%r13)
-	l	%r1,0(%r1)
-	stm	%r0,%r15,0(%r1)
-1:	sigp	%r0,%r6,__SIGP_RESTART	/* start destination CPU */
-	brc	2,1b			/* busy, try again */
-2:	sigp	%r0,%r5,__SIGP_STOP	/* stop current CPU */
-	brc	2,2b			/* busy, try again */
-3:	j	3b
-
-ENTRY(smp_restart_cpu)
-	basr	%r13,0
-0:	la	%r1,.gprregs_addr-0b(%r13)
-	l	%r1,0(%r1)
-	lm	%r0,%r15,0(%r1)
-1:	sigp	%r0,%r5,__SIGP_SENSE	/* Wait for calling CPU */
-	brc	10,1b			/* busy, accepted (status 0), running */
-	tmll	%r0,0x40		/* Test if calling CPU is stopped */
-	jz	1b
-	ltr	%r4,%r4			/* New stack ? */
-	jz	1f
-	lr	%r15,%r4
-1:	lr	%r14,%r2		/* r14: Function to call */
-	lr	%r2,%r3			/* r2 : Parameter for function*/
-	basr	%r14,%r14		/* Call function */
-
-.gprregs_addr:
-	.long	.gprregs
-
-	.section .data,"aw",@progbits
-.gprregs:
-	.rept	16
-	.long	0
-	.endr
diff --git a/arch/s390/kernel/switch_cpu64.S b/arch/s390/kernel/switch_cpu64.S
deleted file mode 100644
index fcc42d799e41..000000000000
--- a/arch/s390/kernel/switch_cpu64.S
+++ /dev/null
@@ -1,51 +0,0 @@
-/*
- * 64-bit switch cpu code
- *
- * Copyright IBM Corp. 2009
- *
- */
-
-#include <linux/linkage.h>
-#include <asm/asm-offsets.h>
-#include <asm/ptrace.h>
-
-# smp_switch_to_cpu switches to destination cpu and executes the passed function
-# Parameter: %r2 - function to call
-#	     %r3 - function parameter
-#	     %r4 - stack poiner
-#	     %r5 - current cpu
-#	     %r6 - destination cpu
-
-	.section .text
-ENTRY(smp_switch_to_cpu)
-	stmg	%r6,%r15,__SF_GPRS(%r15)
-	lgr	%r1,%r15
-	aghi	%r15,-STACK_FRAME_OVERHEAD
-	stg	%r1,__SF_BACKCHAIN(%r15)
-	larl	%r1,.gprregs
-	stmg	%r0,%r15,0(%r1)
-1:	sigp	%r0,%r6,__SIGP_RESTART	/* start destination CPU */
-	brc	2,1b			/* busy, try again */
-2:	sigp	%r0,%r5,__SIGP_STOP	/* stop current CPU */
-	brc	2,2b			/* busy, try again */
-3:	j	3b
-
-ENTRY(smp_restart_cpu)
-	larl	%r1,.gprregs
-	lmg	%r0,%r15,0(%r1)
-1:	sigp	%r0,%r5,__SIGP_SENSE	/* Wait for calling CPU */
-	brc	10,1b			/* busy, accepted (status 0), running */
-	tmll	%r0,0x40		/* Test if calling CPU is stopped */
-	jz	1b
-	ltgr	%r4,%r4			/* New stack ? */
-	jz	1f
-	lgr	%r15,%r4
-1:	lgr	%r14,%r2		/* r14: Function to call */
-	lgr	%r2,%r3			/* r2 : Parameter for function*/
-	basr	%r14,%r14		/* Call function */
-
-	.section .data,"aw",@progbits
-.gprregs:
-	.rept	16
-	.quad	0
-	.endr
diff --git a/arch/s390/kernel/swsusp_asm64.S b/arch/s390/kernel/swsusp_asm64.S
index acb78cdee896..dd70ef046058 100644
--- a/arch/s390/kernel/swsusp_asm64.S
+++ b/arch/s390/kernel/swsusp_asm64.S
@@ -42,7 +42,7 @@ ENTRY(swsusp_arch_suspend)
 	lghi	%r1,0x1000
 
 	/* Save CPU address */
-	stap	__LC_CPU_ADDRESS(%r0)
+	stap	__LC_EXT_CPU_ADDR(%r0)
 
 	/* Store registers */
 	mvc	0x318(4,%r1),__SF_EMPTY(%r15)	/* move prefix to lowcore */
@@ -173,15 +173,15 @@ pgm_check_entry:
 	larl	%r1,.Lresume_cpu		/* Resume CPU address: r2 */
 	stap	0(%r1)
 	llgh	%r2,0(%r1)
-	llgh	%r1,__LC_CPU_ADDRESS(%r0)	/* Suspend CPU address: r1 */
+	llgh	%r1,__LC_EXT_CPU_ADDR(%r0)	/* Suspend CPU address: r1 */
 	cgr	%r1,%r2
 	je	restore_registers		/* r1 = r2 -> nothing to do */
 	larl	%r4,.Lrestart_suspend_psw	/* Set new restart PSW */
 	mvc	__LC_RST_NEW_PSW(16,%r0),0(%r4)
 3:
-	sigp	%r9,%r1,__SIGP_INITIAL_CPU_RESET
-	brc	8,4f	/* accepted */
-	brc	2,3b	/* busy, try again */
+	sigp	%r9,%r1,11			/* sigp initial cpu reset */
+	brc	8,4f				/* accepted */
+	brc	2,3b				/* busy, try again */
 
 	/* Suspend CPU not available -> panic */
 	larl	%r15,init_thread_union
@@ -196,10 +196,10 @@ pgm_check_entry:
 	lpsw	0(%r3)
 4:
 	/* Switch to suspend CPU */
-	sigp	%r9,%r1,__SIGP_RESTART	/* start suspend CPU */
+	sigp	%r9,%r1,6		/* sigp restart to suspend CPU */
 	brc	2,4b			/* busy, try again */
 5:
-	sigp	%r9,%r2,__SIGP_STOP	/* stop resume (current) CPU */
+	sigp	%r9,%r2,5		/* sigp stop to current resume CPU */
 	brc	2,5b			/* busy, try again */
 6:	j	6b
 
@@ -207,7 +207,7 @@ restart_suspend:
 	larl	%r1,.Lresume_cpu
 	llgh	%r2,0(%r1)
 7:
-	sigp	%r9,%r2,__SIGP_SENSE	/* Wait for resume CPU */
+	sigp	%r9,%r2,1		/* sigp sense, wait for resume CPU */
 	brc	8,7b			/* accepted, status 0, still running */
 	brc	2,7b			/* busy, try again */
 	tmll	%r9,0x40		/* Test if resume CPU is stopped */
@@ -257,6 +257,9 @@ restore_registers:
 	lghi	%r2,0
 	brasl	%r14,arch_set_page_states
 
+	/* Log potential guest relocation */
+	brasl	%r14,lgr_info_log
+
 	/* Reinitialize the channel subsystem */
 	brasl	%r14,channel_subsystem_reinit
 
diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c
index fa02f443f5f6..d4e1cb1dbcd1 100644
--- a/arch/s390/kernel/time.c
+++ b/arch/s390/kernel/time.c
@@ -113,11 +113,14 @@ static void fixup_clock_comparator(unsigned long long delta)
 static int s390_next_ktime(ktime_t expires,
 			   struct clock_event_device *evt)
 {
+	struct timespec ts;
 	u64 nsecs;
 
-	nsecs = ktime_to_ns(ktime_sub(expires, ktime_get_monotonic_offset()));
+	ts.tv_sec = ts.tv_nsec = 0;
+	monotonic_to_bootbased(&ts);
+	nsecs = ktime_to_ns(ktime_add(timespec_to_ktime(ts), expires));
 	do_div(nsecs, 125);
-	S390_lowcore.clock_comparator = TOD_UNIX_EPOCH + (nsecs << 9);
+	S390_lowcore.clock_comparator = sched_clock_base_cc + (nsecs << 9);
 	set_clock_comparator(S390_lowcore.clock_comparator);
 	return 0;
 }
@@ -162,7 +165,7 @@ void init_cpu_timer(void)
 	__ctl_set_bit(0, 4);
 }
 
-static void clock_comparator_interrupt(unsigned int ext_int_code,
+static void clock_comparator_interrupt(struct ext_code ext_code,
 				       unsigned int param32,
 				       unsigned long param64)
 {
@@ -174,7 +177,7 @@ static void clock_comparator_interrupt(unsigned int ext_int_code,
 static void etr_timing_alert(struct etr_irq_parm *);
 static void stp_timing_alert(struct stp_irq_parm *);
 
-static void timing_alert_interrupt(unsigned int ext_int_code,
+static void timing_alert_interrupt(struct ext_code ext_code,
 				   unsigned int param32, unsigned long param64)
 {
 	kstat_cpu(smp_processor_id()).irqs[EXTINT_TLA]++;
diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c
index 7370a41948ca..4f8dc942257c 100644
--- a/arch/s390/kernel/topology.c
+++ b/arch/s390/kernel/topology.c
@@ -79,12 +79,12 @@ static struct mask_info *add_cpus_to_mask(struct topology_cpu *tl_cpu,
 	     cpu < TOPOLOGY_CPU_BITS;
 	     cpu = find_next_bit(&tl_cpu->mask[0], TOPOLOGY_CPU_BITS, cpu + 1))
 	{
-		unsigned int rcpu, lcpu;
+		unsigned int rcpu;
+		int lcpu;
 
 		rcpu = TOPOLOGY_CPU_BITS - 1 - cpu + tl_cpu->origin;
-		for_each_present_cpu(lcpu) {
-			if (cpu_logical_map(lcpu) != rcpu)
-				continue;
+		lcpu = smp_find_processor_id(rcpu);
+		if (lcpu >= 0) {
 			cpumask_set_cpu(lcpu, &book->mask);
 			cpu_book_id[lcpu] = book->id;
 			cpumask_set_cpu(lcpu, &core->mask);
diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c
index 5ce3750b181f..77cdf4234ebc 100644
--- a/arch/s390/kernel/traps.c
+++ b/arch/s390/kernel/traps.c
@@ -33,7 +33,6 @@
 #include <linux/kprobes.h>
 #include <linux/bug.h>
 #include <linux/utsname.h>
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include <asm/io.h>
 #include <linux/atomic.h>
@@ -41,6 +40,7 @@
 #include <asm/cpcmd.h>
 #include <asm/lowcore.h>
 #include <asm/debug.h>
+#include <asm/ipl.h>
 #include "entry.h"
 
 void (*pgm_check_table[128])(struct pt_regs *regs);
@@ -144,8 +144,8 @@ void show_stack(struct task_struct *task, unsigned long *sp)
 	for (i = 0; i < kstack_depth_to_print; i++) {
 		if (((addr_t) stack & (THREAD_SIZE-1)) == 0)
 			break;
-		if (i && ((i * sizeof (long) % 32) == 0))
-			printk("\n       ");
+		if ((i * sizeof(long) % 32) == 0)
+			printk("%s       ", i == 0 ? "" : "\n");
 		printk(LONG, *stack++);
 	}
 	printk("\n");
@@ -239,6 +239,7 @@ void die(struct pt_regs *regs, const char *str)
 	static int die_counter;
 
 	oops_enter();
+	lgr_info_log();
 	debug_stop_all();
 	console_verbose();
 	spin_lock_irq(&die_lock);
diff --git a/arch/s390/kernel/vdso.c b/arch/s390/kernel/vdso.c
index d73630b4fe1d..ea5590fdca3b 100644
--- a/arch/s390/kernel/vdso.c
+++ b/arch/s390/kernel/vdso.c
@@ -25,12 +25,12 @@
 #include <linux/compat.h>
 #include <asm/asm-offsets.h>
 #include <asm/pgtable.h>
-#include <asm/system.h>
 #include <asm/processor.h>
 #include <asm/mmu.h>
 #include <asm/mmu_context.h>
 #include <asm/sections.h>
 #include <asm/vdso.h>
+#include <asm/facility.h>
 
 #if defined(CONFIG_32BIT) || defined(CONFIG_COMPAT)
 extern char vdso32_start, vdso32_end;
@@ -89,18 +89,11 @@ static void vdso_init_data(struct vdso_data *vd)
 
 #ifdef CONFIG_64BIT
 /*
- * Setup per cpu vdso data page.
- */
-static void vdso_init_per_cpu_data(int cpu, struct vdso_per_cpu_data *vpcd)
-{
-}
-
-/*
  * Allocate/free per cpu vdso data.
  */
 #define SEGMENT_ORDER	2
 
-int vdso_alloc_per_cpu(int cpu, struct _lowcore *lowcore)
+int vdso_alloc_per_cpu(struct _lowcore *lowcore)
 {
 	unsigned long segment_table, page_table, page_frame;
 	u32 *psal, *aste;
@@ -139,7 +132,6 @@ int vdso_alloc_per_cpu(int cpu, struct _lowcore *lowcore)
 	aste[4] = (u32)(addr_t) psal;
 	lowcore->vdso_per_cpu_data = page_frame;
 
-	vdso_init_per_cpu_data(cpu, (struct vdso_per_cpu_data *) page_frame);
 	return 0;
 
 out:
@@ -149,7 +141,7 @@ out:
 	return -ENOMEM;
 }
 
-void vdso_free_per_cpu(int cpu, struct _lowcore *lowcore)
+void vdso_free_per_cpu(struct _lowcore *lowcore)
 {
 	unsigned long segment_table, page_table, page_frame;
 	u32 *psal, *aste;
@@ -168,19 +160,15 @@ void vdso_free_per_cpu(int cpu, struct _lowcore *lowcore)
 	free_pages(segment_table, SEGMENT_ORDER);
 }
 
-static void __vdso_init_cr5(void *dummy)
+static void vdso_init_cr5(void)
 {
 	unsigned long cr5;
 
+	if (user_mode == HOME_SPACE_MODE || !vdso_enabled)
+		return;
 	cr5 = offsetof(struct _lowcore, paste);
 	__ctl_load(cr5, 5, 5);
 }
-
-static void vdso_init_cr5(void)
-{
-	if (user_mode != HOME_SPACE_MODE && vdso_enabled)
-		on_each_cpu(__vdso_init_cr5, NULL, 1);
-}
 #endif /* CONFIG_64BIT */
 
 /*
@@ -253,17 +241,11 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 	 * on the "data" page of the vDSO or you'll stop getting kernel
 	 * updates and your nice userland gettimeofday will be totally dead.
 	 * It's fine to use that for setting breakpoints in the vDSO code
-	 * pages though
-	 *
-	 * Make sure the vDSO gets into every core dump.
-	 * Dumping its contents makes post-mortem fully interpretable later
-	 * without matching up the same kernel and hardware config to see
-	 * what PC values meant.
+	 * pages though.
 	 */
 	rc = install_special_mapping(mm, vdso_base, vdso_pages << PAGE_SHIFT,
 				     VM_READ|VM_EXEC|
-				     VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC|
-				     VM_ALWAYSDUMP,
+				     VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
 				     vdso_pagelist);
 	if (rc)
 		current->mm->context.vdso_base = 0;
@@ -322,10 +304,8 @@ static int __init vdso_init(void)
 	}
 	vdso64_pagelist[vdso64_pages - 1] = virt_to_page(vdso_data);
 	vdso64_pagelist[vdso64_pages] = NULL;
-#ifndef CONFIG_SMP
-	if (vdso_alloc_per_cpu(0, &S390_lowcore))
+	if (vdso_alloc_per_cpu(&S390_lowcore))
 		BUG();
-#endif
 	vdso_init_cr5();
 #endif /* CONFIG_64BIT */
 
@@ -335,7 +315,7 @@ static int __init vdso_init(void)
 
 	return 0;
 }
-arch_initcall(vdso_init);
+early_initcall(vdso_init);
 
 int in_gate_area_no_mm(unsigned long addr)
 {
diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c
index bb48977f5469..39ebff506946 100644
--- a/arch/s390/kernel/vtime.c
+++ b/arch/s390/kernel/vtime.c
@@ -26,6 +26,7 @@
 #include <asm/irq_regs.h>
 #include <asm/cputime.h>
 #include <asm/irq.h>
+#include "entry.h"
 
 static DEFINE_PER_CPU(struct vtimer_queue, virt_cpu_timer);
 
@@ -123,153 +124,53 @@ void account_system_vtime(struct task_struct *tsk)
 }
 EXPORT_SYMBOL_GPL(account_system_vtime);
 
-void __kprobes vtime_start_cpu(__u64 int_clock, __u64 enter_timer)
+void __kprobes vtime_stop_cpu(void)
 {
 	struct s390_idle_data *idle = &__get_cpu_var(s390_idle);
 	struct vtimer_queue *vq = &__get_cpu_var(virt_cpu_timer);
-	__u64 idle_time, expires;
+	unsigned long long idle_time;
+	unsigned long psw_mask;
 
-	if (idle->idle_enter == 0ULL)
-		return;
+	trace_hardirqs_on();
+	/* Don't trace preempt off for idle. */
+	stop_critical_timings();
 
-	/* Account time spent with enabled wait psw loaded as idle time. */
-	idle_time = int_clock - idle->idle_enter;
-	account_idle_time(idle_time);
-	S390_lowcore.steal_timer +=
-		idle->idle_enter - S390_lowcore.last_update_clock;
-	S390_lowcore.last_update_clock = int_clock;
-
-	/* Account system time spent going idle. */
-	S390_lowcore.system_timer += S390_lowcore.last_update_timer - vq->idle;
-	S390_lowcore.last_update_timer = enter_timer;
-
-	/* Restart vtime CPU timer */
-	if (vq->do_spt) {
-		/* Program old expire value but first save progress. */
-		expires = vq->idle - enter_timer;
-		expires += get_vtimer();
-		set_vtimer(expires);
-	} else {
-		/* Don't account the CPU timer delta while the cpu was idle. */
-		vq->elapsed -= vq->idle - enter_timer;
-	}
+	/* Wait for external, I/O or machine check interrupt. */
+	psw_mask = psw_kernel_bits | PSW_MASK_WAIT | PSW_MASK_DAT |
+		PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK;
+	idle->nohz_delay = 0;
 
+	/* Call the assembler magic in entry.S */
+	psw_idle(idle, vq, psw_mask, !list_empty(&vq->list));
+
+	/* Reenable preemption tracer. */
+	start_critical_timings();
+
+	/* Account time spent with enabled wait psw loaded as idle time. */
 	idle->sequence++;
 	smp_wmb();
+	idle_time = idle->idle_exit - idle->idle_enter;
 	idle->idle_time += idle_time;
-	idle->idle_enter = 0ULL;
+	idle->idle_enter = idle->idle_exit = 0ULL;
 	idle->idle_count++;
+	account_idle_time(idle_time);
 	smp_wmb();
 	idle->sequence++;
 }
 
-void __kprobes vtime_stop_cpu(void)
-{
-	struct s390_idle_data *idle = &__get_cpu_var(s390_idle);
-	struct vtimer_queue *vq = &__get_cpu_var(virt_cpu_timer);
-	psw_t psw;
-
-	/* Wait for external, I/O or machine check interrupt. */
-	psw.mask = psw_kernel_bits | PSW_MASK_WAIT |
-		PSW_MASK_DAT | PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK;
-
-	idle->nohz_delay = 0;
-
-	/* Check if the CPU timer needs to be reprogrammed. */
-	if (vq->do_spt) {
-		__u64 vmax = VTIMER_MAX_SLICE;
-		/*
-		 * The inline assembly is equivalent to
-		 *	vq->idle = get_cpu_timer();
-		 *	set_cpu_timer(VTIMER_MAX_SLICE);
-		 *	idle->idle_enter = get_clock();
-		 *	__load_psw_mask(psw_kernel_bits | PSW_MASK_WAIT |
-		 *			   PSW_MASK_DAT | PSW_MASK_IO |
-		 *			   PSW_MASK_EXT | PSW_MASK_MCHECK);
-		 * The difference is that the inline assembly makes sure that
-		 * the last three instruction are stpt, stck and lpsw in that
-		 * order. This is done to increase the precision.
-		 */
-		asm volatile(
-#ifndef CONFIG_64BIT
-			"	basr	1,0\n"
-			"0:	ahi	1,1f-0b\n"
-			"	st	1,4(%2)\n"
-#else /* CONFIG_64BIT */
-			"	larl	1,1f\n"
-			"	stg	1,8(%2)\n"
-#endif /* CONFIG_64BIT */
-			"	stpt	0(%4)\n"
-			"	spt	0(%5)\n"
-			"	stck	0(%3)\n"
-#ifndef CONFIG_64BIT
-			"	lpsw	0(%2)\n"
-#else /* CONFIG_64BIT */
-			"	lpswe	0(%2)\n"
-#endif /* CONFIG_64BIT */
-			"1:"
-			: "=m" (idle->idle_enter), "=m" (vq->idle)
-			: "a" (&psw), "a" (&idle->idle_enter),
-			  "a" (&vq->idle), "a" (&vmax), "m" (vmax), "m" (psw)
-			: "memory", "cc", "1");
-	} else {
-		/*
-		 * The inline assembly is equivalent to
-		 *	vq->idle = get_cpu_timer();
-		 *	idle->idle_enter = get_clock();
-		 *	__load_psw_mask(psw_kernel_bits | PSW_MASK_WAIT |
-		 *			   PSW_MASK_DAT | PSW_MASK_IO |
-		 *			   PSW_MASK_EXT | PSW_MASK_MCHECK);
-		 * The difference is that the inline assembly makes sure that
-		 * the last three instruction are stpt, stck and lpsw in that
-		 * order. This is done to increase the precision.
-		 */
-		asm volatile(
-#ifndef CONFIG_64BIT
-			"	basr	1,0\n"
-			"0:	ahi	1,1f-0b\n"
-			"	st	1,4(%2)\n"
-#else /* CONFIG_64BIT */
-			"	larl	1,1f\n"
-			"	stg	1,8(%2)\n"
-#endif /* CONFIG_64BIT */
-			"	stpt	0(%4)\n"
-			"	stck	0(%3)\n"
-#ifndef CONFIG_64BIT
-			"	lpsw	0(%2)\n"
-#else /* CONFIG_64BIT */
-			"	lpswe	0(%2)\n"
-#endif /* CONFIG_64BIT */
-			"1:"
-			: "=m" (idle->idle_enter), "=m" (vq->idle)
-			: "a" (&psw), "a" (&idle->idle_enter),
-			  "a" (&vq->idle), "m" (psw)
-			: "memory", "cc", "1");
-	}
-}
-
 cputime64_t s390_get_idle_time(int cpu)
 {
-	struct s390_idle_data *idle;
-	unsigned long long now, idle_time, idle_enter;
+	struct s390_idle_data *idle = &per_cpu(s390_idle, cpu);
+	unsigned long long now, idle_enter, idle_exit;
 	unsigned int sequence;
 
-	idle = &per_cpu(s390_idle, cpu);
-
-	now = get_clock();
-repeat:
-	sequence = idle->sequence;
-	smp_rmb();
-	if (sequence & 1)
-		goto repeat;
-	idle_time = 0;
-	idle_enter = idle->idle_enter;
-	if (idle_enter != 0ULL && idle_enter < now)
-		idle_time = now - idle_enter;
-	smp_rmb();
-	if (idle->sequence != sequence)
-		goto repeat;
-	return idle_time;
+	do {
+		now = get_clock();
+		sequence = ACCESS_ONCE(idle->sequence);
+		idle_enter = ACCESS_ONCE(idle->idle_enter);
+		idle_exit = ACCESS_ONCE(idle->idle_exit);
+	} while ((sequence & 1) || (idle->sequence != sequence));
+	return idle_enter ? ((idle_exit ? : now) - idle_enter) : 0;
 }
 
 /*
@@ -319,7 +220,7 @@ static void do_callbacks(struct list_head *cb_list)
 /*
  * Handler for the virtual CPU timer.
  */
-static void do_cpu_timer_interrupt(unsigned int ext_int_code,
+static void do_cpu_timer_interrupt(struct ext_code ext_code,
 				   unsigned int param32, unsigned long param64)
 {
 	struct vtimer_queue *vq;
@@ -346,7 +247,6 @@ static void do_cpu_timer_interrupt(unsigned int ext_int_code,
 	}
 	spin_unlock(&vq->lock);
 
-	vq->do_spt = list_empty(&cb_list);
 	do_callbacks(&cb_list);
 
 	/* next event is first in list */
@@ -355,8 +255,7 @@ static void do_cpu_timer_interrupt(unsigned int ext_int_code,
 	if (!list_empty(&vq->list)) {
 		event = list_first_entry(&vq->list, struct vtimer_list, entry);
 		next = event->expires;
-	} else
-		vq->do_spt = 0;
+	}
 	spin_unlock(&vq->lock);
 	/*
 	 * To improve precision add the time spent by the
@@ -570,6 +469,9 @@ void init_cpu_vtimer(void)
 
 	/* enable cpu timer interrupts */
 	__ctl_set_bit(0,10);
+
+	/* set initial cpu timer */
+	set_vtimer(0x7fffffffffffffffULL);
 }
 
 static int __cpuinit s390_nohz_notify(struct notifier_block *self,
diff --git a/arch/s390/kvm/Kconfig b/arch/s390/kvm/Kconfig
index a21634173a66..78eb9847008f 100644
--- a/arch/s390/kvm/Kconfig
+++ b/arch/s390/kvm/Kconfig
@@ -34,6 +34,15 @@ config KVM
 
 	  If unsure, say N.
 
+config KVM_S390_UCONTROL
+	bool "Userspace controlled virtual machines"
+	depends on KVM
+	---help---
+	  Allow CAP_SYS_ADMIN users to create KVM virtual machines that are
+	  controlled by userspace.
+
+	  If unsure, say N.
+
 # OK, it's a little counter-intuitive to do this, but it puts it neatly under
 # the virtualization menu.
 source drivers/vhost/Kconfig
diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c
index 8943e82cd4d9..a353f0ea45c2 100644
--- a/arch/s390/kvm/diag.c
+++ b/arch/s390/kvm/diag.c
@@ -20,8 +20,8 @@ static int diag_release_pages(struct kvm_vcpu *vcpu)
 	unsigned long start, end;
 	unsigned long prefix  = vcpu->arch.sie_block->prefix;
 
-	start = vcpu->arch.guest_gprs[(vcpu->arch.sie_block->ipa & 0xf0) >> 4];
-	end = vcpu->arch.guest_gprs[vcpu->arch.sie_block->ipa & 0xf] + 4096;
+	start = vcpu->run->s.regs.gprs[(vcpu->arch.sie_block->ipa & 0xf0) >> 4];
+	end = vcpu->run->s.regs.gprs[vcpu->arch.sie_block->ipa & 0xf] + 4096;
 
 	if (start & ~PAGE_MASK || end & ~PAGE_MASK || start > end
 	    || start < 2 * PAGE_SIZE)
@@ -56,7 +56,7 @@ static int __diag_time_slice_end(struct kvm_vcpu *vcpu)
 static int __diag_ipl_functions(struct kvm_vcpu *vcpu)
 {
 	unsigned int reg = vcpu->arch.sie_block->ipa & 0xf;
-	unsigned long subcode = vcpu->arch.guest_gprs[reg] & 0xffff;
+	unsigned long subcode = vcpu->run->s.regs.gprs[reg] & 0xffff;
 
 	VCPU_EVENT(vcpu, 5, "diag ipl functions, subcode %lx", subcode);
 	switch (subcode) {
diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c
index 02434543eabb..361456577c6f 100644
--- a/arch/s390/kvm/intercept.c
+++ b/arch/s390/kvm/intercept.c
@@ -36,7 +36,7 @@ static int handle_lctlg(struct kvm_vcpu *vcpu)
 
 	useraddr = disp2;
 	if (base2)
-		useraddr += vcpu->arch.guest_gprs[base2];
+		useraddr += vcpu->run->s.regs.gprs[base2];
 
 	if (useraddr & 7)
 		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
@@ -75,7 +75,7 @@ static int handle_lctl(struct kvm_vcpu *vcpu)
 
 	useraddr = disp2;
 	if (base2)
-		useraddr += vcpu->arch.guest_gprs[base2];
+		useraddr += vcpu->run->s.regs.gprs[base2];
 
 	if (useraddr & 3)
 		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
@@ -133,13 +133,6 @@ static int handle_stop(struct kvm_vcpu *vcpu)
 
 	vcpu->stat.exit_stop_request++;
 	spin_lock_bh(&vcpu->arch.local_int.lock);
-	if (vcpu->arch.local_int.action_bits & ACTION_STORE_ON_STOP) {
-		vcpu->arch.local_int.action_bits &= ~ACTION_STORE_ON_STOP;
-		rc = kvm_s390_vcpu_store_status(vcpu,
-						  KVM_S390_STORE_STATUS_NOADDR);
-		if (rc >= 0)
-			rc = -EOPNOTSUPP;
-	}
 
 	if (vcpu->arch.local_int.action_bits & ACTION_RELOADVCPU_ON_STOP) {
 		vcpu->arch.local_int.action_bits &= ~ACTION_RELOADVCPU_ON_STOP;
@@ -155,7 +148,18 @@ static int handle_stop(struct kvm_vcpu *vcpu)
 		rc = -EOPNOTSUPP;
 	}
 
-	spin_unlock_bh(&vcpu->arch.local_int.lock);
+	if (vcpu->arch.local_int.action_bits & ACTION_STORE_ON_STOP) {
+		vcpu->arch.local_int.action_bits &= ~ACTION_STORE_ON_STOP;
+		/* store status must be called unlocked. Since local_int.lock
+		 * only protects local_int.* and not guest memory we can give
+		 * up the lock here */
+		spin_unlock_bh(&vcpu->arch.local_int.lock);
+		rc = kvm_s390_vcpu_store_status(vcpu,
+						KVM_S390_STORE_STATUS_NOADDR);
+		if (rc >= 0)
+			rc = -EOPNOTSUPP;
+	} else
+		spin_unlock_bh(&vcpu->arch.local_int.lock);
 	return rc;
 }
 
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 278ee009ce65..2d9f9a72bb81 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -134,7 +134,7 @@ static void __do_deliver_interrupt(struct kvm_vcpu *vcpu,
 		if (rc == -EFAULT)
 			exception = 1;
 
-		rc = put_guest_u16(vcpu, __LC_CPU_ADDRESS, inti->emerg.code);
+		rc = put_guest_u16(vcpu, __LC_EXT_CPU_ADDR, inti->emerg.code);
 		if (rc == -EFAULT)
 			exception = 1;
 
@@ -156,7 +156,7 @@ static void __do_deliver_interrupt(struct kvm_vcpu *vcpu,
 		if (rc == -EFAULT)
 			exception = 1;
 
-		rc = put_guest_u16(vcpu, __LC_CPU_ADDRESS, inti->extcall.code);
+		rc = put_guest_u16(vcpu, __LC_EXT_CPU_ADDR, inti->extcall.code);
 		if (rc == -EFAULT)
 			exception = 1;
 
@@ -202,7 +202,7 @@ static void __do_deliver_interrupt(struct kvm_vcpu *vcpu,
 		if (rc == -EFAULT)
 			exception = 1;
 
-		rc = put_guest_u16(vcpu, __LC_CPU_ADDRESS, 0x0d00);
+		rc = put_guest_u16(vcpu, __LC_EXT_CPU_ADDR, 0x0d00);
 		if (rc == -EFAULT)
 			exception = 1;
 
@@ -236,8 +236,7 @@ static void __do_deliver_interrupt(struct kvm_vcpu *vcpu,
 		VCPU_EVENT(vcpu, 4, "interrupt: set prefix to %x",
 			   inti->prefix.address);
 		vcpu->stat.deliver_prefix_signal++;
-		vcpu->arch.sie_block->prefix = inti->prefix.address;
-		vcpu->arch.sie_block->ihcpu = 0xffff;
+		kvm_s390_set_prefix(vcpu, inti->prefix.address);
 		break;
 
 	case KVM_S390_RESTART:
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index d1c445732451..217ce44395a4 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -27,7 +27,7 @@
 #include <asm/lowcore.h>
 #include <asm/pgtable.h>
 #include <asm/nmi.h>
-#include <asm/system.h>
+#include <asm/switch_to.h>
 #include "kvm-s390.h"
 #include "gaccess.h"
 
@@ -129,6 +129,10 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_S390_PSW:
 	case KVM_CAP_S390_GMAP:
 	case KVM_CAP_SYNC_MMU:
+#ifdef CONFIG_KVM_S390_UCONTROL
+	case KVM_CAP_S390_UCONTROL:
+#endif
+	case KVM_CAP_SYNC_REGS:
 		r = 1;
 		break;
 	default:
@@ -171,11 +175,22 @@ long kvm_arch_vm_ioctl(struct file *filp,
 	return r;
 }
 
-int kvm_arch_init_vm(struct kvm *kvm)
+int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 {
 	int rc;
 	char debug_name[16];
 
+	rc = -EINVAL;
+#ifdef CONFIG_KVM_S390_UCONTROL
+	if (type & ~KVM_VM_S390_UCONTROL)
+		goto out_err;
+	if ((type & KVM_VM_S390_UCONTROL) && (!capable(CAP_SYS_ADMIN)))
+		goto out_err;
+#else
+	if (type)
+		goto out_err;
+#endif
+
 	rc = s390_enable_sie();
 	if (rc)
 		goto out_err;
@@ -198,10 +213,13 @@ int kvm_arch_init_vm(struct kvm *kvm)
 	debug_register_view(kvm->arch.dbf, &debug_sprintf_view);
 	VM_EVENT(kvm, 3, "%s", "vm created");
 
-	kvm->arch.gmap = gmap_alloc(current->mm);
-	if (!kvm->arch.gmap)
-		goto out_nogmap;
-
+	if (type & KVM_VM_S390_UCONTROL) {
+		kvm->arch.gmap = NULL;
+	} else {
+		kvm->arch.gmap = gmap_alloc(current->mm);
+		if (!kvm->arch.gmap)
+			goto out_nogmap;
+	}
 	return 0;
 out_nogmap:
 	debug_unregister(kvm->arch.dbf);
@@ -214,11 +232,18 @@ out_err:
 void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 {
 	VCPU_EVENT(vcpu, 3, "%s", "free cpu");
-	clear_bit(63 - vcpu->vcpu_id, (unsigned long *) &vcpu->kvm->arch.sca->mcn);
-	if (vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sda ==
-		(__u64) vcpu->arch.sie_block)
-		vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sda = 0;
+	if (!kvm_is_ucontrol(vcpu->kvm)) {
+		clear_bit(63 - vcpu->vcpu_id,
+			  (unsigned long *) &vcpu->kvm->arch.sca->mcn);
+		if (vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sda ==
+		    (__u64) vcpu->arch.sie_block)
+			vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sda = 0;
+	}
 	smp_mb();
+
+	if (kvm_is_ucontrol(vcpu->kvm))
+		gmap_free(vcpu->arch.gmap);
+
 	free_page((unsigned long)(vcpu->arch.sie_block));
 	kvm_vcpu_uninit(vcpu);
 	kfree(vcpu);
@@ -249,13 +274,25 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 	kvm_free_vcpus(kvm);
 	free_page((unsigned long)(kvm->arch.sca));
 	debug_unregister(kvm->arch.dbf);
-	gmap_free(kvm->arch.gmap);
+	if (!kvm_is_ucontrol(kvm))
+		gmap_free(kvm->arch.gmap);
 }
 
 /* Section: vcpu related */
 int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 {
+	if (kvm_is_ucontrol(vcpu->kvm)) {
+		vcpu->arch.gmap = gmap_alloc(current->mm);
+		if (!vcpu->arch.gmap)
+			return -ENOMEM;
+		return 0;
+	}
+
 	vcpu->arch.gmap = vcpu->kvm->arch.gmap;
+	vcpu->run->kvm_valid_regs = KVM_SYNC_PREFIX |
+				    KVM_SYNC_GPRS |
+				    KVM_SYNC_ACRS |
+				    KVM_SYNC_CRS;
 	return 0;
 }
 
@@ -270,7 +307,7 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	save_access_regs(vcpu->arch.host_acrs);
 	vcpu->arch.guest_fpregs.fpc &= FPC_VALID_MASK;
 	restore_fp_regs(&vcpu->arch.guest_fpregs);
-	restore_access_regs(vcpu->arch.guest_acrs);
+	restore_access_regs(vcpu->run->s.regs.acrs);
 	gmap_enable(vcpu->arch.gmap);
 	atomic_set_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
 }
@@ -280,7 +317,7 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 	atomic_clear_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
 	gmap_disable(vcpu->arch.gmap);
 	save_fp_regs(&vcpu->arch.guest_fpregs);
-	save_access_regs(vcpu->arch.guest_acrs);
+	save_access_regs(vcpu->run->s.regs.acrs);
 	restore_fp_regs(&vcpu->arch.host_fpregs);
 	restore_access_regs(vcpu->arch.host_acrs);
 }
@@ -290,8 +327,7 @@ static void kvm_s390_vcpu_initial_reset(struct kvm_vcpu *vcpu)
 	/* this equals initial cpu reset in pop, but we don't switch to ESA */
 	vcpu->arch.sie_block->gpsw.mask = 0UL;
 	vcpu->arch.sie_block->gpsw.addr = 0UL;
-	vcpu->arch.sie_block->prefix    = 0UL;
-	vcpu->arch.sie_block->ihcpu     = 0xffff;
+	kvm_s390_set_prefix(vcpu, 0);
 	vcpu->arch.sie_block->cputm     = 0UL;
 	vcpu->arch.sie_block->ckc       = 0UL;
 	vcpu->arch.sie_block->todpr     = 0;
@@ -342,12 +378,19 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
 		goto out_free_cpu;
 
 	vcpu->arch.sie_block->icpua = id;
-	BUG_ON(!kvm->arch.sca);
-	if (!kvm->arch.sca->cpu[id].sda)
-		kvm->arch.sca->cpu[id].sda = (__u64) vcpu->arch.sie_block;
-	vcpu->arch.sie_block->scaoh = (__u32)(((__u64)kvm->arch.sca) >> 32);
-	vcpu->arch.sie_block->scaol = (__u32)(__u64)kvm->arch.sca;
-	set_bit(63 - id, (unsigned long *) &kvm->arch.sca->mcn);
+	if (!kvm_is_ucontrol(kvm)) {
+		if (!kvm->arch.sca) {
+			WARN_ON_ONCE(1);
+			goto out_free_cpu;
+		}
+		if (!kvm->arch.sca->cpu[id].sda)
+			kvm->arch.sca->cpu[id].sda =
+				(__u64) vcpu->arch.sie_block;
+		vcpu->arch.sie_block->scaoh =
+			(__u32)(((__u64)kvm->arch.sca) >> 32);
+		vcpu->arch.sie_block->scaol = (__u32)(__u64)kvm->arch.sca;
+		set_bit(63 - id, (unsigned long *) &kvm->arch.sca->mcn);
+	}
 
 	spin_lock_init(&vcpu->arch.local_int.lock);
 	INIT_LIST_HEAD(&vcpu->arch.local_int.list);
@@ -388,29 +431,29 @@ static int kvm_arch_vcpu_ioctl_initial_reset(struct kvm_vcpu *vcpu)
 
 int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 {
-	memcpy(&vcpu->arch.guest_gprs, &regs->gprs, sizeof(regs->gprs));
+	memcpy(&vcpu->run->s.regs.gprs, &regs->gprs, sizeof(regs->gprs));
 	return 0;
 }
 
 int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 {
-	memcpy(&regs->gprs, &vcpu->arch.guest_gprs, sizeof(regs->gprs));
+	memcpy(&regs->gprs, &vcpu->run->s.regs.gprs, sizeof(regs->gprs));
 	return 0;
 }
 
 int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 				  struct kvm_sregs *sregs)
 {
-	memcpy(&vcpu->arch.guest_acrs, &sregs->acrs, sizeof(sregs->acrs));
+	memcpy(&vcpu->run->s.regs.acrs, &sregs->acrs, sizeof(sregs->acrs));
 	memcpy(&vcpu->arch.sie_block->gcr, &sregs->crs, sizeof(sregs->crs));
-	restore_access_regs(vcpu->arch.guest_acrs);
+	restore_access_regs(vcpu->run->s.regs.acrs);
 	return 0;
 }
 
 int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
 				  struct kvm_sregs *sregs)
 {
-	memcpy(&sregs->acrs, &vcpu->arch.guest_acrs, sizeof(sregs->acrs));
+	memcpy(&sregs->acrs, &vcpu->run->s.regs.acrs, sizeof(sregs->acrs));
 	memcpy(&sregs->crs, &vcpu->arch.sie_block->gcr, sizeof(sregs->crs));
 	return 0;
 }
@@ -418,7 +461,7 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
 int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
 {
 	memcpy(&vcpu->arch.guest_fpregs.fprs, &fpu->fprs, sizeof(fpu->fprs));
-	vcpu->arch.guest_fpregs.fpc = fpu->fpc;
+	vcpu->arch.guest_fpregs.fpc = fpu->fpc & FPC_VALID_MASK;
 	restore_fp_regs(&vcpu->arch.guest_fpregs);
 	return 0;
 }
@@ -467,9 +510,11 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
 	return -EINVAL; /* not implemented yet */
 }
 
-static void __vcpu_run(struct kvm_vcpu *vcpu)
+static int __vcpu_run(struct kvm_vcpu *vcpu)
 {
-	memcpy(&vcpu->arch.sie_block->gg14, &vcpu->arch.guest_gprs[14], 16);
+	int rc;
+
+	memcpy(&vcpu->arch.sie_block->gg14, &vcpu->run->s.regs.gprs[14], 16);
 
 	if (need_resched())
 		schedule();
@@ -477,7 +522,8 @@ static void __vcpu_run(struct kvm_vcpu *vcpu)
 	if (test_thread_flag(TIF_MCCK_PENDING))
 		s390_handle_mcck();
 
-	kvm_s390_deliver_pending_interrupts(vcpu);
+	if (!kvm_is_ucontrol(vcpu->kvm))
+		kvm_s390_deliver_pending_interrupts(vcpu);
 
 	vcpu->arch.sie_block->icptcode = 0;
 	local_irq_disable();
@@ -485,9 +531,15 @@ static void __vcpu_run(struct kvm_vcpu *vcpu)
 	local_irq_enable();
 	VCPU_EVENT(vcpu, 6, "entering sie flags %x",
 		   atomic_read(&vcpu->arch.sie_block->cpuflags));
-	if (sie64a(vcpu->arch.sie_block, vcpu->arch.guest_gprs)) {
-		VCPU_EVENT(vcpu, 3, "%s", "fault in sie instruction");
-		kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+	rc = sie64a(vcpu->arch.sie_block, vcpu->run->s.regs.gprs);
+	if (rc) {
+		if (kvm_is_ucontrol(vcpu->kvm)) {
+			rc = SIE_INTERCEPT_UCONTROL;
+		} else {
+			VCPU_EVENT(vcpu, 3, "%s", "fault in sie instruction");
+			kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+			rc = 0;
+		}
 	}
 	VCPU_EVENT(vcpu, 6, "exit sie icptcode %d",
 		   vcpu->arch.sie_block->icptcode);
@@ -495,7 +547,8 @@ static void __vcpu_run(struct kvm_vcpu *vcpu)
 	kvm_guest_exit();
 	local_irq_enable();
 
-	memcpy(&vcpu->arch.guest_gprs[14], &vcpu->arch.sie_block->gg14, 16);
+	memcpy(&vcpu->run->s.regs.gprs[14], &vcpu->arch.sie_block->gg14, 16);
+	return rc;
 }
 
 int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
@@ -516,6 +569,7 @@ rerun_vcpu:
 	case KVM_EXIT_UNKNOWN:
 	case KVM_EXIT_INTR:
 	case KVM_EXIT_S390_RESET:
+	case KVM_EXIT_S390_UCONTROL:
 		break;
 	default:
 		BUG();
@@ -523,12 +577,26 @@ rerun_vcpu:
 
 	vcpu->arch.sie_block->gpsw.mask = kvm_run->psw_mask;
 	vcpu->arch.sie_block->gpsw.addr = kvm_run->psw_addr;
+	if (kvm_run->kvm_dirty_regs & KVM_SYNC_PREFIX) {
+		kvm_run->kvm_dirty_regs &= ~KVM_SYNC_PREFIX;
+		kvm_s390_set_prefix(vcpu, kvm_run->s.regs.prefix);
+	}
+	if (kvm_run->kvm_dirty_regs & KVM_SYNC_CRS) {
+		kvm_run->kvm_dirty_regs &= ~KVM_SYNC_CRS;
+		memcpy(&vcpu->arch.sie_block->gcr, &kvm_run->s.regs.crs, 128);
+		kvm_s390_set_prefix(vcpu, kvm_run->s.regs.prefix);
+	}
 
 	might_fault();
 
 	do {
-		__vcpu_run(vcpu);
-		rc = kvm_handle_sie_intercept(vcpu);
+		rc = __vcpu_run(vcpu);
+		if (rc)
+			break;
+		if (kvm_is_ucontrol(vcpu->kvm))
+			rc = -EOPNOTSUPP;
+		else
+			rc = kvm_handle_sie_intercept(vcpu);
 	} while (!signal_pending(current) && !rc);
 
 	if (rc == SIE_INTERCEPT_RERUNVCPU)
@@ -539,6 +607,16 @@ rerun_vcpu:
 		rc = -EINTR;
 	}
 
+#ifdef CONFIG_KVM_S390_UCONTROL
+	if (rc == SIE_INTERCEPT_UCONTROL) {
+		kvm_run->exit_reason = KVM_EXIT_S390_UCONTROL;
+		kvm_run->s390_ucontrol.trans_exc_code =
+			current->thread.gmap_addr;
+		kvm_run->s390_ucontrol.pgm_code = 0x10;
+		rc = 0;
+	}
+#endif
+
 	if (rc == -EOPNOTSUPP) {
 		/* intercept cannot be handled in-kernel, prepare kvm-run */
 		kvm_run->exit_reason         = KVM_EXIT_S390_SIEIC;
@@ -556,6 +634,8 @@ rerun_vcpu:
 
 	kvm_run->psw_mask     = vcpu->arch.sie_block->gpsw.mask;
 	kvm_run->psw_addr     = vcpu->arch.sie_block->gpsw.addr;
+	kvm_run->s.regs.prefix = vcpu->arch.sie_block->prefix;
+	memcpy(&kvm_run->s.regs.crs, &vcpu->arch.sie_block->gcr, 128);
 
 	if (vcpu->sigset_active)
 		sigprocmask(SIG_SETMASK, &sigsaved, NULL);
@@ -602,7 +682,7 @@ int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr)
 		return -EFAULT;
 
 	if (__guestcopy(vcpu, addr + offsetof(struct save_area, gp_regs),
-			vcpu->arch.guest_gprs, 128, prefix))
+			vcpu->run->s.regs.gprs, 128, prefix))
 		return -EFAULT;
 
 	if (__guestcopy(vcpu, addr + offsetof(struct save_area, psw),
@@ -631,7 +711,7 @@ int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr)
 		return -EFAULT;
 
 	if (__guestcopy(vcpu, addr + offsetof(struct save_area, acc_regs),
-			&vcpu->arch.guest_acrs, 64, prefix))
+			&vcpu->run->s.regs.acrs, 64, prefix))
 		return -EFAULT;
 
 	if (__guestcopy(vcpu,
@@ -673,12 +753,77 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 	case KVM_S390_INITIAL_RESET:
 		r = kvm_arch_vcpu_ioctl_initial_reset(vcpu);
 		break;
+#ifdef CONFIG_KVM_S390_UCONTROL
+	case KVM_S390_UCAS_MAP: {
+		struct kvm_s390_ucas_mapping ucasmap;
+
+		if (copy_from_user(&ucasmap, argp, sizeof(ucasmap))) {
+			r = -EFAULT;
+			break;
+		}
+
+		if (!kvm_is_ucontrol(vcpu->kvm)) {
+			r = -EINVAL;
+			break;
+		}
+
+		r = gmap_map_segment(vcpu->arch.gmap, ucasmap.user_addr,
+				     ucasmap.vcpu_addr, ucasmap.length);
+		break;
+	}
+	case KVM_S390_UCAS_UNMAP: {
+		struct kvm_s390_ucas_mapping ucasmap;
+
+		if (copy_from_user(&ucasmap, argp, sizeof(ucasmap))) {
+			r = -EFAULT;
+			break;
+		}
+
+		if (!kvm_is_ucontrol(vcpu->kvm)) {
+			r = -EINVAL;
+			break;
+		}
+
+		r = gmap_unmap_segment(vcpu->arch.gmap, ucasmap.vcpu_addr,
+			ucasmap.length);
+		break;
+	}
+#endif
+	case KVM_S390_VCPU_FAULT: {
+		r = gmap_fault(arg, vcpu->arch.gmap);
+		if (!IS_ERR_VALUE(r))
+			r = 0;
+		break;
+	}
 	default:
-		r = -EINVAL;
+		r = -ENOTTY;
 	}
 	return r;
 }
 
+int kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf)
+{
+#ifdef CONFIG_KVM_S390_UCONTROL
+	if ((vmf->pgoff == KVM_S390_SIE_PAGE_OFFSET)
+		 && (kvm_is_ucontrol(vcpu->kvm))) {
+		vmf->page = virt_to_page(vcpu->arch.sie_block);
+		get_page(vmf->page);
+		return 0;
+	}
+#endif
+	return VM_FAULT_SIGBUS;
+}
+
+void kvm_arch_free_memslot(struct kvm_memory_slot *free,
+			   struct kvm_memory_slot *dont)
+{
+}
+
+int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages)
+{
+	return 0;
+}
+
 /* Section: memory related */
 int kvm_arch_prepare_memory_region(struct kvm *kvm,
 				   struct kvm_memory_slot *memslot,
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index 99b0b7597115..ff28f9d1c9eb 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -26,6 +26,7 @@ typedef int (*intercept_handler_t)(struct kvm_vcpu *vcpu);
 
 /* negativ values are error codes, positive values for internal conditions */
 #define SIE_INTERCEPT_RERUNVCPU		(1<<0)
+#define SIE_INTERCEPT_UCONTROL		(1<<1)
 int kvm_handle_sie_intercept(struct kvm_vcpu *vcpu);
 
 #define VM_EVENT(d_kvm, d_loglevel, d_string, d_args...)\
@@ -47,6 +48,23 @@ static inline int __cpu_is_stopped(struct kvm_vcpu *vcpu)
 	return atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_STOP_INT;
 }
 
+static inline int kvm_is_ucontrol(struct kvm *kvm)
+{
+#ifdef CONFIG_KVM_S390_UCONTROL
+	if (kvm->arch.gmap)
+		return 0;
+	return 1;
+#else
+	return 0;
+#endif
+}
+
+static inline void kvm_s390_set_prefix(struct kvm_vcpu *vcpu, u32 prefix)
+{
+	vcpu->arch.sie_block->prefix = prefix & 0x7fffe000u;
+	vcpu->arch.sie_block->ihcpu  = 0xffff;
+}
+
 int kvm_s390_handle_wait(struct kvm_vcpu *vcpu);
 enum hrtimer_restart kvm_s390_idle_wakeup(struct hrtimer *timer);
 void kvm_s390_tasklet(unsigned long parm);
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index d02638959922..e5a45dbd26ac 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -33,7 +33,7 @@ static int handle_set_prefix(struct kvm_vcpu *vcpu)
 
 	operand2 = disp2;
 	if (base2)
-		operand2 += vcpu->arch.guest_gprs[base2];
+		operand2 += vcpu->run->s.regs.gprs[base2];
 
 	/* must be word boundary */
 	if (operand2 & 3) {
@@ -56,8 +56,7 @@ static int handle_set_prefix(struct kvm_vcpu *vcpu)
 		goto out;
 	}
 
-	vcpu->arch.sie_block->prefix = address;
-	vcpu->arch.sie_block->ihcpu = 0xffff;
+	kvm_s390_set_prefix(vcpu, address);
 
 	VCPU_EVENT(vcpu, 5, "setting prefix to %x", address);
 out:
@@ -74,7 +73,7 @@ static int handle_store_prefix(struct kvm_vcpu *vcpu)
 	vcpu->stat.instruction_stpx++;
 	operand2 = disp2;
 	if (base2)
-		operand2 += vcpu->arch.guest_gprs[base2];
+		operand2 += vcpu->run->s.regs.gprs[base2];
 
 	/* must be word boundary */
 	if (operand2 & 3) {
@@ -106,7 +105,7 @@ static int handle_store_cpu_address(struct kvm_vcpu *vcpu)
 	vcpu->stat.instruction_stap++;
 	useraddr = disp2;
 	if (base2)
-		useraddr += vcpu->arch.guest_gprs[base2];
+		useraddr += vcpu->run->s.regs.gprs[base2];
 
 	if (useraddr & 1) {
 		kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
@@ -181,7 +180,7 @@ static int handle_stidp(struct kvm_vcpu *vcpu)
 	vcpu->stat.instruction_stidp++;
 	operand2 = disp2;
 	if (base2)
-		operand2 += vcpu->arch.guest_gprs[base2];
+		operand2 += vcpu->run->s.regs.gprs[base2];
 
 	if (operand2 & 7) {
 		kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
@@ -232,9 +231,9 @@ static void handle_stsi_3_2_2(struct kvm_vcpu *vcpu, struct sysinfo_3_2_2 *mem)
 
 static int handle_stsi(struct kvm_vcpu *vcpu)
 {
-	int fc = (vcpu->arch.guest_gprs[0] & 0xf0000000) >> 28;
-	int sel1 = vcpu->arch.guest_gprs[0] & 0xff;
-	int sel2 = vcpu->arch.guest_gprs[1] & 0xffff;
+	int fc = (vcpu->run->s.regs.gprs[0] & 0xf0000000) >> 28;
+	int sel1 = vcpu->run->s.regs.gprs[0] & 0xff;
+	int sel2 = vcpu->run->s.regs.gprs[1] & 0xffff;
 	int base2 = vcpu->arch.sie_block->ipb >> 28;
 	int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16);
 	u64 operand2;
@@ -245,14 +244,14 @@ static int handle_stsi(struct kvm_vcpu *vcpu)
 
 	operand2 = disp2;
 	if (base2)
-		operand2 += vcpu->arch.guest_gprs[base2];
+		operand2 += vcpu->run->s.regs.gprs[base2];
 
 	if (operand2 & 0xfff && fc > 0)
 		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
 
 	switch (fc) {
 	case 0:
-		vcpu->arch.guest_gprs[0] = 3 << 28;
+		vcpu->run->s.regs.gprs[0] = 3 << 28;
 		vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44);
 		return 0;
 	case 1: /* same handling for 1 and 2 */
@@ -281,7 +280,7 @@ static int handle_stsi(struct kvm_vcpu *vcpu)
 	}
 	free_page(mem);
 	vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44);
-	vcpu->arch.guest_gprs[0] = 0;
+	vcpu->run->s.regs.gprs[0] = 0;
 	return 0;
 out_mem:
 	free_page(mem);
@@ -333,8 +332,8 @@ static int handle_tprot(struct kvm_vcpu *vcpu)
 	int disp1 = (vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16;
 	int base2 = (vcpu->arch.sie_block->ipb & 0xf000) >> 12;
 	int disp2 = vcpu->arch.sie_block->ipb & 0x0fff;
-	u64 address1 = disp1 + base1 ? vcpu->arch.guest_gprs[base1] : 0;
-	u64 address2 = disp2 + base2 ? vcpu->arch.guest_gprs[base2] : 0;
+	u64 address1 = disp1 + base1 ? vcpu->run->s.regs.gprs[base1] : 0;
+	u64 address2 = disp2 + base2 ? vcpu->run->s.regs.gprs[base2] : 0;
 	struct vm_area_struct *vma;
 	unsigned long user_address;
 
diff --git a/arch/s390/kvm/sigp.c b/arch/s390/kvm/sigp.c
index 0a7941d74bc6..0ad4cf238391 100644
--- a/arch/s390/kvm/sigp.c
+++ b/arch/s390/kvm/sigp.c
@@ -48,7 +48,7 @@
 
 
 static int __sigp_sense(struct kvm_vcpu *vcpu, u16 cpu_addr,
-			unsigned long *reg)
+			u64 *reg)
 {
 	struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int;
 	int rc;
@@ -160,12 +160,15 @@ static int __inject_sigp_stop(struct kvm_s390_local_interrupt *li, int action)
 	inti->type = KVM_S390_SIGP_STOP;
 
 	spin_lock_bh(&li->lock);
+	if ((atomic_read(li->cpuflags) & CPUSTAT_STOPPED))
+		goto out;
 	list_add_tail(&inti->list, &li->list);
 	atomic_set(&li->active, 1);
 	atomic_set_mask(CPUSTAT_STOP_INT, li->cpuflags);
 	li->action_bits |= action;
 	if (waitqueue_active(&li->wq))
 		wake_up_interruptible(&li->wq);
+out:
 	spin_unlock_bh(&li->lock);
 
 	return 0; /* order accepted */
@@ -220,7 +223,7 @@ static int __sigp_set_arch(struct kvm_vcpu *vcpu, u32 parameter)
 }
 
 static int __sigp_set_prefix(struct kvm_vcpu *vcpu, u16 cpu_addr, u32 address,
-			     unsigned long *reg)
+			     u64 *reg)
 {
 	struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int;
 	struct kvm_s390_local_interrupt *li = NULL;
@@ -278,7 +281,7 @@ out_fi:
 }
 
 static int __sigp_sense_running(struct kvm_vcpu *vcpu, u16 cpu_addr,
-				unsigned long *reg)
+				u64 *reg)
 {
 	int rc;
 	struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int;
@@ -309,6 +312,34 @@ static int __sigp_sense_running(struct kvm_vcpu *vcpu, u16 cpu_addr,
 	return rc;
 }
 
+static int __sigp_restart(struct kvm_vcpu *vcpu, u16 cpu_addr)
+{
+	int rc = 0;
+	struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int;
+	struct kvm_s390_local_interrupt *li;
+
+	if (cpu_addr >= KVM_MAX_VCPUS)
+		return 3; /* not operational */
+
+	spin_lock(&fi->lock);
+	li = fi->local_int[cpu_addr];
+	if (li == NULL) {
+		rc = 3; /* not operational */
+		goto out;
+	}
+
+	spin_lock_bh(&li->lock);
+	if (li->action_bits & ACTION_STOP_ON_STOP)
+		rc = 2; /* busy */
+	else
+		VCPU_EVENT(vcpu, 4, "sigp restart %x to handle userspace",
+			cpu_addr);
+	spin_unlock_bh(&li->lock);
+out:
+	spin_unlock(&fi->lock);
+	return rc;
+}
+
 int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu)
 {
 	int r1 = (vcpu->arch.sie_block->ipa & 0x00f0) >> 4;
@@ -316,7 +347,7 @@ int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu)
 	int base2 = vcpu->arch.sie_block->ipb >> 28;
 	int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16);
 	u32 parameter;
-	u16 cpu_addr = vcpu->arch.guest_gprs[r3];
+	u16 cpu_addr = vcpu->run->s.regs.gprs[r3];
 	u8 order_code;
 	int rc;
 
@@ -327,18 +358,18 @@ int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu)
 
 	order_code = disp2;
 	if (base2)
-		order_code += vcpu->arch.guest_gprs[base2];
+		order_code += vcpu->run->s.regs.gprs[base2];
 
 	if (r1 % 2)
-		parameter = vcpu->arch.guest_gprs[r1];
+		parameter = vcpu->run->s.regs.gprs[r1];
 	else
-		parameter = vcpu->arch.guest_gprs[r1 + 1];
+		parameter = vcpu->run->s.regs.gprs[r1 + 1];
 
 	switch (order_code) {
 	case SIGP_SENSE:
 		vcpu->stat.instruction_sigp_sense++;
 		rc = __sigp_sense(vcpu, cpu_addr,
-				  &vcpu->arch.guest_gprs[r1]);
+				  &vcpu->run->s.regs.gprs[r1]);
 		break;
 	case SIGP_EXTERNAL_CALL:
 		vcpu->stat.instruction_sigp_external_call++;
@@ -354,7 +385,8 @@ int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu)
 		break;
 	case SIGP_STOP_STORE_STATUS:
 		vcpu->stat.instruction_sigp_stop++;
-		rc = __sigp_stop(vcpu, cpu_addr, ACTION_STORE_ON_STOP);
+		rc = __sigp_stop(vcpu, cpu_addr, ACTION_STORE_ON_STOP |
+						 ACTION_STOP_ON_STOP);
 		break;
 	case SIGP_SET_ARCH:
 		vcpu->stat.instruction_sigp_arch++;
@@ -363,15 +395,18 @@ int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu)
 	case SIGP_SET_PREFIX:
 		vcpu->stat.instruction_sigp_prefix++;
 		rc = __sigp_set_prefix(vcpu, cpu_addr, parameter,
-				       &vcpu->arch.guest_gprs[r1]);
+				       &vcpu->run->s.regs.gprs[r1]);
 		break;
 	case SIGP_SENSE_RUNNING:
 		vcpu->stat.instruction_sigp_sense_running++;
 		rc = __sigp_sense_running(vcpu, cpu_addr,
-					  &vcpu->arch.guest_gprs[r1]);
+					  &vcpu->run->s.regs.gprs[r1]);
 		break;
 	case SIGP_RESTART:
 		vcpu->stat.instruction_sigp_restart++;
+		rc = __sigp_restart(vcpu, cpu_addr);
+		if (rc == 2) /* busy */
+			break;
 		/* user space must know about restart */
 	default:
 		return -EOPNOTSUPP;
diff --git a/arch/s390/lib/delay.c b/arch/s390/lib/delay.c
index db92f044024c..9f1f71e85778 100644
--- a/arch/s390/lib/delay.c
+++ b/arch/s390/lib/delay.c
@@ -13,6 +13,7 @@
 #include <linux/irqflags.h>
 #include <linux/interrupt.h>
 #include <asm/div64.h>
+#include <asm/timer.h>
 
 void __delay(unsigned long loops)
 {
@@ -28,36 +29,33 @@ void __delay(unsigned long loops)
 
 static void __udelay_disabled(unsigned long long usecs)
 {
-	unsigned long mask, cr0, cr0_saved;
-	u64 clock_saved;
-	u64 end;
+	unsigned long cr0, cr6, new;
+	u64 clock_saved, end;
 
-	mask = psw_kernel_bits | PSW_MASK_DAT | PSW_MASK_WAIT |
-		PSW_MASK_EXT | PSW_MASK_MCHECK;
 	end = get_clock() + (usecs << 12);
 	clock_saved = local_tick_disable();
-	__ctl_store(cr0_saved, 0, 0);
-	cr0 = (cr0_saved & 0xffff00e0) | 0x00000800;
-	__ctl_load(cr0 , 0, 0);
+	__ctl_store(cr0, 0, 0);
+	__ctl_store(cr6, 6, 6);
+	new = (cr0 &  0xffff00e0) | 0x00000800;
+	__ctl_load(new , 0, 0);
+	new = 0;
+	__ctl_load(new, 6, 6);
 	lockdep_off();
 	do {
 		set_clock_comparator(end);
-		trace_hardirqs_on();
-		__load_psw_mask(mask);
+		vtime_stop_cpu();
 		local_irq_disable();
 	} while (get_clock() < end);
 	lockdep_on();
-	__ctl_load(cr0_saved, 0, 0);
+	__ctl_load(cr0, 0, 0);
+	__ctl_load(cr6, 6, 6);
 	local_tick_enable(clock_saved);
 }
 
 static void __udelay_enabled(unsigned long long usecs)
 {
-	unsigned long mask;
-	u64 clock_saved;
-	u64 end;
+	u64 clock_saved, end;
 
-	mask = psw_kernel_bits | PSW_MASK_WAIT | PSW_MASK_EXT | PSW_MASK_IO;
 	end = get_clock() + (usecs << 12);
 	do {
 		clock_saved = 0;
@@ -65,8 +63,7 @@ static void __udelay_enabled(unsigned long long usecs)
 			clock_saved = local_tick_disable();
 			set_clock_comparator(end);
 		}
-		trace_hardirqs_on();
-		__load_psw_mask(mask);
+		vtime_stop_cpu();
 		local_irq_disable();
 		if (clock_saved)
 			local_tick_enable(clock_saved);
diff --git a/arch/s390/lib/spinlock.c b/arch/s390/lib/spinlock.c
index 91754ffb9203..093eb694d9c1 100644
--- a/arch/s390/lib/spinlock.c
+++ b/arch/s390/lib/spinlock.c
@@ -10,6 +10,7 @@
 #include <linux/module.h>
 #include <linux/spinlock.h>
 #include <linux/init.h>
+#include <linux/smp.h>
 #include <asm/io.h>
 
 int spin_retry = 1000;
@@ -24,21 +25,6 @@ static int __init spin_retry_setup(char *str)
 }
 __setup("spin_retry=", spin_retry_setup);
 
-static inline void _raw_yield(void)
-{
-	if (MACHINE_HAS_DIAG44)
-		asm volatile("diag 0,0,0x44");
-}
-
-static inline void _raw_yield_cpu(int cpu)
-{
-	if (MACHINE_HAS_DIAG9C)
-		asm volatile("diag %0,0,0x9c"
-			     : : "d" (cpu_logical_map(cpu)));
-	else
-		_raw_yield();
-}
-
 void arch_spin_lock_wait(arch_spinlock_t *lp)
 {
 	int count = spin_retry;
@@ -60,7 +46,7 @@ void arch_spin_lock_wait(arch_spinlock_t *lp)
 		}
 		owner = lp->owner_cpu;
 		if (owner)
-			_raw_yield_cpu(~owner);
+			smp_yield_cpu(~owner);
 		if (_raw_compare_and_swap(&lp->owner_cpu, 0, cpu) == 0)
 			return;
 	}
@@ -91,7 +77,7 @@ void arch_spin_lock_wait_flags(arch_spinlock_t *lp, unsigned long flags)
 		}
 		owner = lp->owner_cpu;
 		if (owner)
-			_raw_yield_cpu(~owner);
+			smp_yield_cpu(~owner);
 		local_irq_disable();
 		if (_raw_compare_and_swap(&lp->owner_cpu, 0, cpu) == 0)
 			return;
@@ -121,7 +107,7 @@ void arch_spin_relax(arch_spinlock_t *lock)
 	if (cpu != 0) {
 		if (MACHINE_IS_VM || MACHINE_IS_KVM ||
 		    !smp_vcpu_scheduled(~cpu))
-			_raw_yield_cpu(~cpu);
+			smp_yield_cpu(~cpu);
 	}
 }
 EXPORT_SYMBOL(arch_spin_relax);
@@ -133,7 +119,7 @@ void _raw_read_lock_wait(arch_rwlock_t *rw)
 
 	while (1) {
 		if (count-- <= 0) {
-			_raw_yield();
+			smp_yield();
 			count = spin_retry;
 		}
 		if (!arch_read_can_lock(rw))
@@ -153,7 +139,7 @@ void _raw_read_lock_wait_flags(arch_rwlock_t *rw, unsigned long flags)
 	local_irq_restore(flags);
 	while (1) {
 		if (count-- <= 0) {
-			_raw_yield();
+			smp_yield();
 			count = spin_retry;
 		}
 		if (!arch_read_can_lock(rw))
@@ -188,7 +174,7 @@ void _raw_write_lock_wait(arch_rwlock_t *rw)
 
 	while (1) {
 		if (count-- <= 0) {
-			_raw_yield();
+			smp_yield();
 			count = spin_retry;
 		}
 		if (!arch_write_can_lock(rw))
@@ -206,7 +192,7 @@ void _raw_write_lock_wait_flags(arch_rwlock_t *rw, unsigned long flags)
 	local_irq_restore(flags);
 	while (1) {
 		if (count-- <= 0) {
-			_raw_yield();
+			smp_yield();
 			count = spin_retry;
 		}
 		if (!arch_write_can_lock(rw))
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index 354dd39073ef..46ef3fd0663b 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -32,11 +32,10 @@
 #include <linux/uaccess.h>
 #include <linux/hugetlb.h>
 #include <asm/asm-offsets.h>
-#include <asm/system.h>
 #include <asm/pgtable.h>
 #include <asm/irq.h>
 #include <asm/mmu_context.h>
-#include <asm/compat.h>
+#include <asm/facility.h>
 #include "../kernel/entry.h"
 
 #ifndef CONFIG_64BIT
@@ -533,7 +532,7 @@ void pfault_fini(void)
 static DEFINE_SPINLOCK(pfault_lock);
 static LIST_HEAD(pfault_list);
 
-static void pfault_interrupt(unsigned int ext_int_code,
+static void pfault_interrupt(struct ext_code ext_code,
 			     unsigned int param32, unsigned long param64)
 {
 	struct task_struct *tsk;
@@ -546,7 +545,7 @@ static void pfault_interrupt(unsigned int ext_int_code,
 	 * in the 'cpu address' field associated with the
          * external interrupt. 
 	 */
-	subcode = ext_int_code >> 16;
+	subcode = ext_code.subcode;
 	if ((subcode & 0xff00) != __SUBCODE_MASK)
 		return;
 	kstat_cpu(smp_processor_id()).irqs[EXTINT_PFL]++;
diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index 5d633019d8f3..2bea0605856e 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -29,7 +29,6 @@
 #include <linux/export.h>
 #include <linux/gfp.h>
 #include <asm/processor.h>
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
@@ -38,6 +37,7 @@
 #include <asm/tlb.h>
 #include <asm/tlbflush.h>
 #include <asm/sections.h>
+#include <asm/ctl_reg.h>
 
 pgd_t swapper_pg_dir[PTRS_PER_PGD] __attribute__((__aligned__(PAGE_SIZE)));
 
@@ -223,16 +223,38 @@ void free_initrd_mem(unsigned long start, unsigned long end)
 #ifdef CONFIG_MEMORY_HOTPLUG
 int arch_add_memory(int nid, u64 start, u64 size)
 {
-	struct pglist_data *pgdat;
+	unsigned long zone_start_pfn, zone_end_pfn, nr_pages;
+	unsigned long start_pfn = PFN_DOWN(start);
+	unsigned long size_pages = PFN_DOWN(size);
 	struct zone *zone;
 	int rc;
 
-	pgdat = NODE_DATA(nid);
-	zone = pgdat->node_zones + ZONE_MOVABLE;
 	rc = vmem_add_mapping(start, size);
 	if (rc)
 		return rc;
-	rc = __add_pages(nid, zone, PFN_DOWN(start), PFN_DOWN(size));
+	for_each_zone(zone) {
+		if (zone_idx(zone) != ZONE_MOVABLE) {
+			/* Add range within existing zone limits */
+			zone_start_pfn = zone->zone_start_pfn;
+			zone_end_pfn = zone->zone_start_pfn +
+				       zone->spanned_pages;
+		} else {
+			/* Add remaining range to ZONE_MOVABLE */
+			zone_start_pfn = start_pfn;
+			zone_end_pfn = start_pfn + size_pages;
+		}
+		if (start_pfn < zone_start_pfn || start_pfn >= zone_end_pfn)
+			continue;
+		nr_pages = (start_pfn + size_pages > zone_end_pfn) ?
+			   zone_end_pfn - start_pfn : size_pages;
+		rc = __add_pages(nid, zone, start_pfn, nr_pages);
+		if (rc)
+			break;
+		start_pfn += nr_pages;
+		size_pages -= nr_pages;
+		if (!size_pages)
+			break;
+	}
 	if (rc)
 		vmem_remove_mapping(start, size);
 	return rc;
diff --git a/arch/s390/mm/maccess.c b/arch/s390/mm/maccess.c
index 1cb8427bedfb..7bb15fcca75e 100644
--- a/arch/s390/mm/maccess.c
+++ b/arch/s390/mm/maccess.c
@@ -12,7 +12,7 @@
 #include <linux/types.h>
 #include <linux/errno.h>
 #include <linux/gfp.h>
-#include <asm/system.h>
+#include <asm/ctl_reg.h>
 
 /*
  * This function writes to kernel memory bypassing DAT and possible
diff --git a/arch/s390/mm/mmap.c b/arch/s390/mm/mmap.c
index f09c74881b7e..2857c48486ea 100644
--- a/arch/s390/mm/mmap.c
+++ b/arch/s390/mm/mmap.c
@@ -29,8 +29,8 @@
 #include <linux/mman.h>
 #include <linux/module.h>
 #include <linux/random.h>
+#include <linux/compat.h>
 #include <asm/pgalloc.h>
-#include <asm/compat.h>
 
 static unsigned long stack_maxrandom_size(void)
 {
@@ -100,7 +100,6 @@ void arch_pick_mmap_layout(struct mm_struct *mm)
 		mm->unmap_area = arch_unmap_area_topdown;
 	}
 }
-EXPORT_SYMBOL_GPL(arch_pick_mmap_layout);
 
 #else
 
@@ -175,6 +174,5 @@ void arch_pick_mmap_layout(struct mm_struct *mm)
 		mm->unmap_area = arch_unmap_area_topdown;
 	}
 }
-EXPORT_SYMBOL_GPL(arch_pick_mmap_layout);
 
 #endif
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 9a4d02f64f16..373adf69b01c 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -18,7 +18,6 @@
 #include <linux/rcupdate.h>
 #include <linux/slab.h>
 
-#include <asm/system.h>
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
 #include <asm/tlb.h>
@@ -574,7 +573,7 @@ static inline void page_table_free_pgste(unsigned long *table)
 	page = pfn_to_page(__pa(table) >> PAGE_SHIFT);
 	mp = (struct gmap_pgtable *) page->index;
 	BUG_ON(!list_empty(&mp->mapper));
-	pgtable_page_ctor(page);
+	pgtable_page_dtor(page);
 	atomic_set(&page->_mapcount, -1);
 	kfree(mp);
 	__free_page(page);
diff --git a/arch/s390/oprofile/hwsampler.c b/arch/s390/oprofile/hwsampler.c
index 9daee91e6c3f..c6646de07bf4 100644
--- a/arch/s390/oprofile/hwsampler.c
+++ b/arch/s390/oprofile/hwsampler.c
@@ -18,7 +18,8 @@
 #include <linux/oom.h>
 #include <linux/oprofile.h>
 
-#include <asm/lowcore.h>
+#include <asm/facility.h>
+#include <asm/cpu_mf.h>
 #include <asm/irq.h>
 
 #include "hwsampler.h"
@@ -30,12 +31,6 @@
 #define ALERT_REQ_MASK   0x4000000000000000ul
 #define BUFFER_FULL_MASK 0x8000000000000000ul
 
-#define EI_IEA      (1 << 31)	/* invalid entry address              */
-#define EI_ISE      (1 << 30)	/* incorrect SDBT entry               */
-#define EI_PRA      (1 << 29)	/* program request alert              */
-#define EI_SACA     (1 << 23)	/* sampler authorization change alert */
-#define EI_LSDA     (1 << 22)	/* loss of sample data alert          */
-
 DECLARE_PER_CPU(struct hws_cpu_buffer, sampler_cpu_buffer);
 
 struct hws_execute_parms {
@@ -232,9 +227,20 @@ static inline unsigned long *trailer_entry_ptr(unsigned long v)
 	return (unsigned long *) ret;
 }
 
-/* prototypes for external interrupt handler and worker */
-static void hws_ext_handler(unsigned int ext_int_code,
-				unsigned int param32, unsigned long param64);
+static void hws_ext_handler(struct ext_code ext_code,
+			    unsigned int param32, unsigned long param64)
+{
+	struct hws_cpu_buffer *cb = &__get_cpu_var(sampler_cpu_buffer);
+
+	if (!(param32 & CPU_MF_INT_SF_MASK))
+		return;
+
+	kstat_cpu(smp_processor_id()).irqs[EXTINT_CPM]++;
+	atomic_xchg(&cb->ext_params, atomic_read(&cb->ext_params) | param32);
+
+	if (hws_wq)
+		queue_work(hws_wq, &cb->worker);
+}
 
 static void worker(struct work_struct *work);
 
@@ -673,18 +679,6 @@ int hwsampler_activate(unsigned int cpu)
 	return rc;
 }
 
-static void hws_ext_handler(unsigned int ext_int_code,
-			    unsigned int param32, unsigned long param64)
-{
-	struct hws_cpu_buffer *cb;
-
-	kstat_cpu(smp_processor_id()).irqs[EXTINT_CPM]++;
-	cb = &__get_cpu_var(sampler_cpu_buffer);
-	atomic_xchg(&cb->ext_params, atomic_read(&cb->ext_params) | param32);
-	if (hws_wq)
-		queue_work(hws_wq, &cb->worker);
-}
-
 static int check_qsi_on_setup(void)
 {
 	int rc;
@@ -760,23 +754,23 @@ static int worker_check_error(unsigned int cpu, int ext_params)
 	if (!sdbt || !*sdbt)
 		return -EINVAL;
 
-	if (ext_params & EI_PRA)
+	if (ext_params & CPU_MF_INT_SF_PRA)
 		cb->req_alert++;
 
-	if (ext_params & EI_LSDA)
+	if (ext_params & CPU_MF_INT_SF_LSDA)
 		cb->loss_of_sample_data++;
 
-	if (ext_params & EI_IEA) {
+	if (ext_params & CPU_MF_INT_SF_IAE) {
 		cb->invalid_entry_address++;
 		rc = -EINVAL;
 	}
 
-	if (ext_params & EI_ISE) {
+	if (ext_params & CPU_MF_INT_SF_ISE) {
 		cb->incorrect_sdbt_entry++;
 		rc = -EINVAL;
 	}
 
-	if (ext_params & EI_SACA) {
+	if (ext_params & CPU_MF_INT_SF_SACA) {
 		cb->sample_auth_change_alert++;
 		rc = -EINVAL;
 	}
@@ -1009,7 +1003,7 @@ int hwsampler_deallocate(void)
 	if (hws_state != HWS_STOPPED)
 		goto deallocate_exit;
 
-	ctl_clear_bit(0, 5); /* set bit 58 CR0 off */
+	measurement_alert_subclass_unregister();
 	deallocate_sdbt();
 
 	hws_state = HWS_DEALLOCATED;
@@ -1123,7 +1117,7 @@ int hwsampler_shutdown(void)
 		mutex_lock(&hws_sem);
 
 		if (hws_state == HWS_STOPPED) {
-			ctl_clear_bit(0, 5); /* set bit 58 CR0 off */
+			measurement_alert_subclass_unregister();
 			deallocate_sdbt();
 		}
 		if (hws_wq) {
@@ -1198,7 +1192,7 @@ start_all_exit:
 	hws_oom = 1;
 	hws_flush_all = 0;
 	/* now let them in, 1407 CPUMF external interrupts */
-	ctl_set_bit(0, 5); /* set CR0 bit 58 */
+	measurement_alert_subclass_register();
 
 	return 0;
 }