Initial import

83 files changed, 29298 insertions, 0 deletions

diff --git a/arch/s390/kernel/.gitignore b/arch/s390/kernel/.gitignore
new file mode 100644
index 000000000..c5f676c3c
--- /dev/null
+++ b/arch/s390/kernel/.gitignore
@@ -0,0 +1 @@
+vmlinux.lds
diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile
new file mode 100644
index 000000000..ffb87617a
--- /dev/null
+++ b/arch/s390/kernel/Makefile
@@ -0,0 +1,60 @@
+#
+# Makefile for the linux kernel.
+#
+
+ifdef CONFIG_FUNCTION_TRACER
+# Don't trace early setup code and tracing code
+CFLAGS_REMOVE_early.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_ftrace.o = $(CC_FLAGS_FTRACE)
+endif
+
+#
+# Passing null pointers is ok for smp code, since we access the lowcore here.
+#
+CFLAGS_smp.o	:= -Wno-nonnull
+
+#
+# Disable tailcall optimizations for stack / callchain walking functions
+# since this might generate broken code when accessing register 15 and
+# passing its content to other functions.
+#
+CFLAGS_stacktrace.o	+= -fno-optimize-sibling-calls
+CFLAGS_dumpstack.o	+= -fno-optimize-sibling-calls
+
+#
+# Pass UTS_MACHINE for user_regset definition
+#
+CFLAGS_ptrace.o		+= -DUTS_MACHINE='"$(UTS_MACHINE)"'
+
+CFLAGS_sysinfo.o += -w
+
+obj-y	:= traps.o time.o process.o base.o early.o setup.o idle.o vtime.o
+obj-y	+= processor.o sys_s390.o ptrace.o signal.o cpcmd.o ebcdic.o nmi.o
+obj-y	+= debug.o irq.o ipl.o dis.o diag.o sclp.o vdso.o
+obj-y	+= sysinfo.o jump_label.o lgr.o os_info.o machine_kexec.o pgm_check.o
+obj-y	+= runtime_instr.o cache.o dumpstack.o
+obj-y	+= entry.o reipl.o relocate_kernel.o
+
+extra-y				+= head.o head64.o vmlinux.lds
+
+obj-$(CONFIG_MODULES)		+= s390_ksyms.o module.o
+obj-$(CONFIG_SMP)		+= smp.o
+obj-$(CONFIG_SCHED_BOOK)	+= topology.o
+obj-$(CONFIG_HIBERNATION)	+= suspend.o swsusp.o
+obj-$(CONFIG_AUDIT)		+= audit.o
+compat-obj-$(CONFIG_AUDIT)	+= compat_audit.o
+obj-$(CONFIG_COMPAT)		+= compat_linux.o compat_signal.o
+obj-$(CONFIG_COMPAT)		+= compat_wrapper.o $(compat-obj-y)
+
+obj-$(CONFIG_STACKTRACE)	+= stacktrace.o
+obj-$(CONFIG_KPROBES)		+= kprobes.o
+obj-$(CONFIG_FUNCTION_TRACER)	+= mcount.o ftrace.o
+obj-$(CONFIG_CRASH_DUMP)	+= crash_dump.o
+obj-$(CONFIG_UPROBES)		+= uprobes.o
+
+obj-$(CONFIG_PERF_EVENTS)	+= perf_event.o perf_cpum_cf.o perf_cpum_sf.o
+obj-$(CONFIG_PERF_EVENTS)	+= perf_cpum_cf_events.o
+
+# vdso
+obj-y				+= vdso64/
+obj-$(CONFIG_COMPAT)		+= vdso32/
diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c
new file mode 100644
index 000000000..c7d1b9d09
--- /dev/null
+++ b/arch/s390/kernel/asm-offsets.c
@@ -0,0 +1,184 @@
+/*
+ * Generate definitions needed by assembly language modules.
+ * This code generates raw asm output which is post-processed to extract
+ * and format the required data.
+ */
+
+#define ASM_OFFSETS_C
+
+#include <linux/kbuild.h>
+#include <linux/kvm_host.h>
+#include <linux/sched.h>
+#include <asm/idle.h>
+#include <asm/vdso.h>
+#include <asm/pgtable.h>
+
+/*
+ * Make sure that the compiler is new enough. We want a compiler that
+ * is known to work with the "Q" assembler constraint.
+ */
+#if __GNUC__ < 4 || (__GNUC__ == 4 && __GNUC_MINOR__ < 3)
+#error Your compiler is too old; please use version 4.3 or newer
+#endif
+
+int main(void)
+{
+	DEFINE(__THREAD_info, offsetof(struct task_struct, stack));
+	DEFINE(__THREAD_ksp, offsetof(struct task_struct, thread.ksp));
+	DEFINE(__THREAD_mm_segment, offsetof(struct task_struct, thread.mm_segment));
+	BLANK();
+	DEFINE(__TASK_pid, offsetof(struct task_struct, pid));
+	BLANK();
+	DEFINE(__THREAD_per_cause, offsetof(struct task_struct, thread.per_event.cause));
+	DEFINE(__THREAD_per_address, offsetof(struct task_struct, thread.per_event.address));
+	DEFINE(__THREAD_per_paid, offsetof(struct task_struct, thread.per_event.paid));
+	BLANK();
+	DEFINE(__TI_task, offsetof(struct thread_info, task));
+	DEFINE(__TI_flags, offsetof(struct thread_info, flags));
+	DEFINE(__TI_sysc_table, offsetof(struct thread_info, sys_call_table));
+	DEFINE(__TI_cpu, offsetof(struct thread_info, cpu));
+	DEFINE(__TI_precount, offsetof(struct thread_info, preempt_count));
+	DEFINE(__TI_user_timer, offsetof(struct thread_info, user_timer));
+	DEFINE(__TI_system_timer, offsetof(struct thread_info, system_timer));
+	DEFINE(__TI_last_break, offsetof(struct thread_info, last_break));
+	BLANK();
+	DEFINE(__PT_ARGS, offsetof(struct pt_regs, args));
+	DEFINE(__PT_PSW, offsetof(struct pt_regs, psw));
+	DEFINE(__PT_GPRS, offsetof(struct pt_regs, gprs));
+	DEFINE(__PT_ORIG_GPR2, offsetof(struct pt_regs, orig_gpr2));
+	DEFINE(__PT_INT_CODE, offsetof(struct pt_regs, int_code));
+	DEFINE(__PT_INT_PARM, offsetof(struct pt_regs, int_parm));
+	DEFINE(__PT_INT_PARM_LONG, offsetof(struct pt_regs, int_parm_long));
+	DEFINE(__PT_FLAGS, offsetof(struct pt_regs, flags));
+	DEFINE(__PT_SIZE, sizeof(struct pt_regs));
+	BLANK();
+	DEFINE(__SF_BACKCHAIN, offsetof(struct stack_frame, back_chain));
+	DEFINE(__SF_GPRS, offsetof(struct stack_frame, gprs));
+	DEFINE(__SF_EMPTY, offsetof(struct stack_frame, empty1));
+	BLANK();
+	/* timeval/timezone offsets for use by vdso */
+	DEFINE(__VDSO_UPD_COUNT, offsetof(struct vdso_data, tb_update_count));
+	DEFINE(__VDSO_XTIME_STAMP, offsetof(struct vdso_data, xtime_tod_stamp));
+	DEFINE(__VDSO_XTIME_SEC, offsetof(struct vdso_data, xtime_clock_sec));
+	DEFINE(__VDSO_XTIME_NSEC, offsetof(struct vdso_data, xtime_clock_nsec));
+	DEFINE(__VDSO_XTIME_CRS_SEC, offsetof(struct vdso_data, xtime_coarse_sec));
+	DEFINE(__VDSO_XTIME_CRS_NSEC, offsetof(struct vdso_data, xtime_coarse_nsec));
+	DEFINE(__VDSO_WTOM_SEC, offsetof(struct vdso_data, wtom_clock_sec));
+	DEFINE(__VDSO_WTOM_NSEC, offsetof(struct vdso_data, wtom_clock_nsec));
+	DEFINE(__VDSO_WTOM_CRS_SEC, offsetof(struct vdso_data, wtom_coarse_sec));
+	DEFINE(__VDSO_WTOM_CRS_NSEC, offsetof(struct vdso_data, wtom_coarse_nsec));
+	DEFINE(__VDSO_TIMEZONE, offsetof(struct vdso_data, tz_minuteswest));
+	DEFINE(__VDSO_ECTG_OK, offsetof(struct vdso_data, ectg_available));
+	DEFINE(__VDSO_TK_MULT, offsetof(struct vdso_data, tk_mult));
+	DEFINE(__VDSO_TK_SHIFT, offsetof(struct vdso_data, tk_shift));
+	DEFINE(__VDSO_ECTG_BASE, offsetof(struct vdso_per_cpu_data, ectg_timer_base));
+	DEFINE(__VDSO_ECTG_USER, offsetof(struct vdso_per_cpu_data, ectg_user_time));
+	/* constants used by the vdso */
+	DEFINE(__CLOCK_REALTIME, CLOCK_REALTIME);
+	DEFINE(__CLOCK_MONOTONIC, CLOCK_MONOTONIC);
+	DEFINE(__CLOCK_REALTIME_COARSE, CLOCK_REALTIME_COARSE);
+	DEFINE(__CLOCK_MONOTONIC_COARSE, CLOCK_MONOTONIC_COARSE);
+	DEFINE(__CLOCK_THREAD_CPUTIME_ID, CLOCK_THREAD_CPUTIME_ID);
+	DEFINE(__CLOCK_REALTIME_RES, MONOTONIC_RES_NSEC);
+	DEFINE(__CLOCK_COARSE_RES, LOW_RES_NSEC);
+	BLANK();
+	/* idle data offsets */
+	DEFINE(__CLOCK_IDLE_ENTER, offsetof(struct s390_idle_data, clock_idle_enter));
+	DEFINE(__CLOCK_IDLE_EXIT, offsetof(struct s390_idle_data, clock_idle_exit));
+	DEFINE(__TIMER_IDLE_ENTER, offsetof(struct s390_idle_data, timer_idle_enter));
+	DEFINE(__TIMER_IDLE_EXIT, offsetof(struct s390_idle_data, timer_idle_exit));
+	/* lowcore offsets */
+	DEFINE(__LC_EXT_PARAMS, offsetof(struct _lowcore, ext_params));
+	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));
+	DEFINE(__LC_PGM_ILC, offsetof(struct _lowcore, pgm_ilc));
+	DEFINE(__LC_PGM_INT_CODE, offsetof(struct _lowcore, pgm_code));
+	DEFINE(__LC_TRANS_EXC_CODE, offsetof(struct _lowcore, trans_exc_code));
+	DEFINE(__LC_MON_CLASS_NR, offsetof(struct _lowcore, mon_class_num));
+	DEFINE(__LC_PER_CODE, offsetof(struct _lowcore, per_code));
+	DEFINE(__LC_PER_ATMID, offsetof(struct _lowcore, per_atmid));
+	DEFINE(__LC_PER_ADDRESS, offsetof(struct _lowcore, per_address));
+	DEFINE(__LC_EXC_ACCESS_ID, offsetof(struct _lowcore, exc_access_id));
+	DEFINE(__LC_PER_ACCESS_ID, offsetof(struct _lowcore, per_access_id));
+	DEFINE(__LC_OP_ACCESS_ID, offsetof(struct _lowcore, op_access_id));
+	DEFINE(__LC_AR_MODE_ID, offsetof(struct _lowcore, ar_mode_id));
+	DEFINE(__LC_MON_CODE, offsetof(struct _lowcore, monitor_code));
+	DEFINE(__LC_SUBCHANNEL_ID, offsetof(struct _lowcore, subchannel_id));
+	DEFINE(__LC_SUBCHANNEL_NR, offsetof(struct _lowcore, subchannel_nr));
+	DEFINE(__LC_IO_INT_PARM, offsetof(struct _lowcore, io_int_parm));
+	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_MCCK_EXT_DAM_CODE, offsetof(struct _lowcore, external_damage_code));
+	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));
+	DEFINE(__LC_CPU_FLAGS, offsetof(struct _lowcore, cpu_flags));
+	DEFINE(__LC_RETURN_PSW, offsetof(struct _lowcore, return_psw));
+	DEFINE(__LC_RETURN_MCCK_PSW, offsetof(struct _lowcore, return_mcck_psw));
+	DEFINE(__LC_SYNC_ENTER_TIMER, offsetof(struct _lowcore, sync_enter_timer));
+	DEFINE(__LC_ASYNC_ENTER_TIMER, offsetof(struct _lowcore, async_enter_timer));
+	DEFINE(__LC_MCCK_ENTER_TIMER, offsetof(struct _lowcore, mcck_enter_timer));
+	DEFINE(__LC_EXIT_TIMER, offsetof(struct _lowcore, exit_timer));
+	DEFINE(__LC_USER_TIMER, offsetof(struct _lowcore, user_timer));
+	DEFINE(__LC_SYSTEM_TIMER, offsetof(struct _lowcore, system_timer));
+	DEFINE(__LC_STEAL_TIMER, offsetof(struct _lowcore, steal_timer));
+	DEFINE(__LC_LAST_UPDATE_TIMER, offsetof(struct _lowcore, last_update_timer));
+	DEFINE(__LC_LAST_UPDATE_CLOCK, offsetof(struct _lowcore, last_update_clock));
+	DEFINE(__LC_CURRENT, offsetof(struct _lowcore, current_task));
+	DEFINE(__LC_CURRENT_PID, offsetof(struct _lowcore, current_pid));
+	DEFINE(__LC_THREAD_INFO, offsetof(struct _lowcore, thread_info));
+	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_RESTART_DATA, offsetof(struct _lowcore, restart_data));
+	DEFINE(__LC_RESTART_SOURCE, offsetof(struct _lowcore, restart_source));
+	DEFINE(__LC_KERNEL_ASCE, offsetof(struct _lowcore, kernel_asce));
+	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_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));
+	DEFINE(__LC_PREFIX_SAVE_AREA, offsetof(struct _lowcore, prefixreg_save_area));
+	DEFINE(__LC_AREGS_SAVE_AREA, offsetof(struct _lowcore, access_regs_save_area));
+	DEFINE(__LC_FPREGS_SAVE_AREA, offsetof(struct _lowcore, floating_pt_save_area));
+	DEFINE(__LC_GPREGS_SAVE_AREA, offsetof(struct _lowcore, gpregs_save_area));
+	DEFINE(__LC_CREGS_SAVE_AREA, offsetof(struct _lowcore, cregs_save_area));
+	DEFINE(__LC_DATA_EXC_CODE, offsetof(struct _lowcore, data_exc_code));
+	DEFINE(__LC_MCCK_FAIL_STOR_ADDR, offsetof(struct _lowcore, failing_storage_address));
+	DEFINE(__LC_VX_SAVE_AREA_ADDR, offsetof(struct _lowcore, vector_save_area_addr));
+	DEFINE(__LC_EXT_PARAMS2, offsetof(struct _lowcore, ext_params2));
+	DEFINE(SAVE_AREA_BASE, offsetof(struct _lowcore, floating_pt_save_area));
+	DEFINE(__LC_PASTE, offsetof(struct _lowcore, paste));
+	DEFINE(__LC_FP_CREG_SAVE_AREA, offsetof(struct _lowcore, fpt_creg_save_area));
+	DEFINE(__LC_LAST_BREAK, offsetof(struct _lowcore, breaking_event_addr));
+	DEFINE(__LC_VDSO_PER_CPU, offsetof(struct _lowcore, vdso_per_cpu_data));
+	DEFINE(__LC_GMAP, offsetof(struct _lowcore, gmap));
+	DEFINE(__LC_PGM_TDB, offsetof(struct _lowcore, pgm_tdb));
+	DEFINE(__THREAD_trap_tdb, offsetof(struct task_struct, thread.trap_tdb));
+	DEFINE(__GMAP_ASCE, offsetof(struct gmap, asce));
+	DEFINE(__SIE_PROG0C, offsetof(struct kvm_s390_sie_block, prog0c));
+	DEFINE(__SIE_PROG20, offsetof(struct kvm_s390_sie_block, prog20));
+	return 0;
+}
diff --git a/arch/s390/kernel/audit.c b/arch/s390/kernel/audit.c
new file mode 100644
index 000000000..f4932c22e
--- /dev/null
+++ b/arch/s390/kernel/audit.c
@@ -0,0 +1,78 @@
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/audit.h>
+#include <asm/unistd.h>
+#include "audit.h"
+
+static unsigned dir_class[] = {
+#include <asm-generic/audit_dir_write.h>
+~0U
+};
+
+static unsigned read_class[] = {
+#include <asm-generic/audit_read.h>
+~0U
+};
+
+static unsigned write_class[] = {
+#include <asm-generic/audit_write.h>
+~0U
+};
+
+static unsigned chattr_class[] = {
+#include <asm-generic/audit_change_attr.h>
+~0U
+};
+
+static unsigned signal_class[] = {
+#include <asm-generic/audit_signal.h>
+~0U
+};
+
+int audit_classify_arch(int arch)
+{
+#ifdef CONFIG_COMPAT
+	if (arch == AUDIT_ARCH_S390)
+		return 1;
+#endif
+	return 0;
+}
+
+int audit_classify_syscall(int abi, unsigned syscall)
+{
+#ifdef CONFIG_COMPAT
+	if (abi == AUDIT_ARCH_S390)
+		return s390_classify_syscall(syscall);
+#endif
+	switch(syscall) {
+	case __NR_open:
+		return 2;
+	case __NR_openat:
+		return 3;
+	case __NR_socketcall:
+		return 4;
+	case __NR_execve:
+		return 5;
+	default:
+		return 0;
+	}
+}
+
+static int __init audit_classes_init(void)
+{
+#ifdef CONFIG_COMPAT
+	audit_register_class(AUDIT_CLASS_WRITE_32, s390_write_class);
+	audit_register_class(AUDIT_CLASS_READ_32, s390_read_class);
+	audit_register_class(AUDIT_CLASS_DIR_WRITE_32, s390_dir_class);
+	audit_register_class(AUDIT_CLASS_CHATTR_32, s390_chattr_class);
+	audit_register_class(AUDIT_CLASS_SIGNAL_32, s390_signal_class);
+#endif
+	audit_register_class(AUDIT_CLASS_WRITE, write_class);
+	audit_register_class(AUDIT_CLASS_READ, read_class);
+	audit_register_class(AUDIT_CLASS_DIR_WRITE, dir_class);
+	audit_register_class(AUDIT_CLASS_CHATTR, chattr_class);
+	audit_register_class(AUDIT_CLASS_SIGNAL, signal_class);
+	return 0;
+}
+
+__initcall(audit_classes_init);
diff --git a/arch/s390/kernel/audit.h b/arch/s390/kernel/audit.h
new file mode 100644
index 000000000..12b56f4b5
--- /dev/null
+++ b/arch/s390/kernel/audit.h
@@ -0,0 +1,15 @@
+#ifndef __ARCH_S390_KERNEL_AUDIT_H
+#define __ARCH_S390_KERNEL_AUDIT_H
+
+#include <linux/types.h>
+
+#ifdef CONFIG_COMPAT
+extern int s390_classify_syscall(unsigned);
+extern __u32 s390_dir_class[];
+extern __u32 s390_write_class[];
+extern __u32 s390_read_class[];
+extern __u32 s390_chattr_class[];
+extern __u32 s390_signal_class[];
+#endif /* CONFIG_COMPAT */
+
+#endif /* __ARCH_S390_KERNEL_AUDIT_H */
diff --git a/arch/s390/kernel/base.S b/arch/s390/kernel/base.S
new file mode 100644
index 000000000..daed3fde4
--- /dev/null
+++ b/arch/s390/kernel/base.S
@@ -0,0 +1,131 @@
+/*
+ *  arch/s390/kernel/base.S
+ *
+ *    Copyright IBM Corp. 2006, 2007
+ *    Author(s): Heiko Carstens <heiko.carstens@de.ibm.com>
+ *		 Michael Holzheu <holzheu@de.ibm.com>
+ */
+
+#include <linux/linkage.h>
+#include <asm/asm-offsets.h>
+#include <asm/ptrace.h>
+#include <asm/sigp.h>
+
+ENTRY(s390_base_mcck_handler)
+	basr	%r13,0
+0:	lg	%r15,__LC_PANIC_STACK	# load panic stack
+	aghi	%r15,-STACK_FRAME_OVERHEAD
+	larl	%r1,s390_base_mcck_handler_fn
+	lg	%r1,0(%r1)
+	ltgr	%r1,%r1
+	jz	1f
+	basr	%r14,%r1
+1:	la	%r1,4095
+	lmg	%r0,%r15,__LC_GPREGS_SAVE_AREA-4095(%r1)
+	lpswe	__LC_MCK_OLD_PSW
+
+	.section .bss
+	.align 8
+	.globl	s390_base_mcck_handler_fn
+s390_base_mcck_handler_fn:
+	.quad	0
+	.previous
+
+ENTRY(s390_base_ext_handler)
+	stmg	%r0,%r15,__LC_SAVE_AREA_ASYNC
+	basr	%r13,0
+0:	aghi	%r15,-STACK_FRAME_OVERHEAD
+	larl	%r1,s390_base_ext_handler_fn
+	lg	%r1,0(%r1)
+	ltgr	%r1,%r1
+	jz	1f
+	basr	%r14,%r1
+1:	lmg	%r0,%r15,__LC_SAVE_AREA_ASYNC
+	ni	__LC_EXT_OLD_PSW+1,0xfd	# clear wait state bit
+	lpswe	__LC_EXT_OLD_PSW
+
+	.section .bss
+	.align 8
+	.globl s390_base_ext_handler_fn
+s390_base_ext_handler_fn:
+	.quad	0
+	.previous
+
+ENTRY(s390_base_pgm_handler)
+	stmg	%r0,%r15,__LC_SAVE_AREA_SYNC
+	basr	%r13,0
+0:	aghi	%r15,-STACK_FRAME_OVERHEAD
+	larl	%r1,s390_base_pgm_handler_fn
+	lg	%r1,0(%r1)
+	ltgr	%r1,%r1
+	jz	1f
+	basr	%r14,%r1
+	lmg	%r0,%r15,__LC_SAVE_AREA_SYNC
+	lpswe	__LC_PGM_OLD_PSW
+1:	lpswe	disabled_wait_psw-0b(%r13)
+
+	.align	8
+disabled_wait_psw:
+	.quad	0x0002000180000000,0x0000000000000000 + s390_base_pgm_handler
+
+	.section .bss
+	.align 8
+	.globl s390_base_pgm_handler_fn
+s390_base_pgm_handler_fn:
+	.quad	0
+	.previous
+
+#
+# Calls diag 308 subcode 1 and continues execution
+#
+# The following conditions must be ensured before calling this function:
+# * Prefix register = 0
+# * Lowcore protection is disabled
+#
+ENTRY(diag308_reset)
+	larl	%r4,.Lctlregs		# Save control registers
+	stctg	%c0,%c15,0(%r4)
+	larl	%r4,.Lfpctl		# Floating point control register
+	stfpc	0(%r4)
+	larl	%r4,.Lcontinue_psw	# Save PSW flags
+	epsw	%r2,%r3
+	stm	%r2,%r3,0(%r4)
+	larl	%r4,.Lrestart_psw	# Setup restart PSW at absolute 0
+	lghi	%r3,0
+	lg	%r4,0(%r4)		# Save PSW
+	sturg	%r4,%r3			# Use sturg, because of large pages
+	lghi	%r1,1
+	lghi	%r0,0
+	diag	%r0,%r1,0x308
+.Lrestart_part2:
+	lhi	%r0,0			# Load r0 with zero
+	lhi	%r1,2			# Use mode 2 = ESAME (dump)
+	sigp	%r1,%r0,SIGP_SET_ARCHITECTURE	# Switch to ESAME mode
+	sam64				# Switch to 64 bit addressing mode
+	larl	%r4,.Lctlregs		# Restore control registers
+	lctlg	%c0,%c15,0(%r4)
+	larl	%r4,.Lfpctl		# Restore floating point ctl register
+	lfpc	0(%r4)
+	larl	%r4,.Lcontinue_psw	# Restore PSW flags
+	lpswe	0(%r4)
+.Lcontinue:
+	br	%r14
+.align 16
+.Lrestart_psw:
+	.long	0x00080000,0x80000000 + .Lrestart_part2
+
+	.section .data..nosave,"aw",@progbits
+.align 8
+.Lcontinue_psw:
+	.quad	0,.Lcontinue
+	.previous
+
+	.section .bss
+.align 8
+.Lctlregs:
+	.rept	16
+	.quad	0
+	.endr
+.Lfpctl:
+	.long	0
+	.previous
diff --git a/arch/s390/kernel/cache.c b/arch/s390/kernel/cache.c
new file mode 100644
index 000000000..bff5e3b6d
--- /dev/null
+++ b/arch/s390/kernel/cache.c
@@ -0,0 +1,181 @@
+/*
+ * Extract CPU cache information and expose them via sysfs.
+ *
+ *    Copyright IBM Corp. 2012
+ *    Author(s): Heiko Carstens <heiko.carstens@de.ibm.com>
+ */
+
+#include <linux/seq_file.h>
+#include <linux/cpu.h>
+#include <linux/cacheinfo.h>
+#include <asm/facility.h>
+
+enum {
+	CACHE_SCOPE_NOTEXISTS,
+	CACHE_SCOPE_PRIVATE,
+	CACHE_SCOPE_SHARED,
+	CACHE_SCOPE_RESERVED,
+};
+
+enum {
+	CTYPE_SEPARATE,
+	CTYPE_DATA,
+	CTYPE_INSTRUCTION,
+	CTYPE_UNIFIED,
+};
+
+enum {
+	EXTRACT_TOPOLOGY,
+	EXTRACT_LINE_SIZE,
+	EXTRACT_SIZE,
+	EXTRACT_ASSOCIATIVITY,
+};
+
+enum {
+	CACHE_TI_UNIFIED = 0,
+	CACHE_TI_DATA = 0,
+	CACHE_TI_INSTRUCTION,
+};
+
+struct cache_info {
+	unsigned char	    : 4;
+	unsigned char scope : 2;
+	unsigned char type  : 2;
+};
+
+#define CACHE_MAX_LEVEL 8
+union cache_topology {
+	struct cache_info ci[CACHE_MAX_LEVEL];
+	unsigned long long raw;
+};
+
+static const char * const cache_type_string[] = {
+	"",
+	"Instruction",
+	"Data",
+	"",
+	"Unified",
+};
+
+static const enum cache_type cache_type_map[] = {
+	[CTYPE_SEPARATE] = CACHE_TYPE_SEPARATE,
+	[CTYPE_DATA] = CACHE_TYPE_DATA,
+	[CTYPE_INSTRUCTION] = CACHE_TYPE_INST,
+	[CTYPE_UNIFIED] = CACHE_TYPE_UNIFIED,
+};
+
+void show_cacheinfo(struct seq_file *m)
+{
+	struct cpu_cacheinfo *this_cpu_ci;
+	struct cacheinfo *cache;
+	int idx;
+
+	if (!test_facility(34))
+		return;
+	get_online_cpus();
+	this_cpu_ci = get_cpu_cacheinfo(cpumask_any(cpu_online_mask));
+	for (idx = 0; idx < this_cpu_ci->num_leaves; idx++) {
+		cache = this_cpu_ci->info_list + idx;
+		seq_printf(m, "cache%-11d: ", idx);
+		seq_printf(m, "level=%d ", cache->level);
+		seq_printf(m, "type=%s ", cache_type_string[cache->type]);
+		seq_printf(m, "scope=%s ",
+			   cache->disable_sysfs ? "Shared" : "Private");
+		seq_printf(m, "size=%dK ", cache->size >> 10);
+		seq_printf(m, "line_size=%u ", cache->coherency_line_size);
+		seq_printf(m, "associativity=%d", cache->ways_of_associativity);
+		seq_puts(m, "\n");
+	}
+	put_online_cpus();
+}
+
+static inline enum cache_type get_cache_type(struct cache_info *ci, int level)
+{
+	if (level >= CACHE_MAX_LEVEL)
+		return CACHE_TYPE_NOCACHE;
+	ci += level;
+	if (ci->scope != CACHE_SCOPE_SHARED && ci->scope != CACHE_SCOPE_PRIVATE)
+		return CACHE_TYPE_NOCACHE;
+	return cache_type_map[ci->type];
+}
+
+static inline unsigned long ecag(int ai, int li, int ti)
+{
+	unsigned long cmd, val;
+
+	cmd = ai << 4 | li << 1 | ti;
+	asm volatile(".insn	rsy,0xeb000000004c,%0,0,0(%1)" /* ecag */
+		     : "=d" (val) : "a" (cmd));
+	return val;
+}
+
+static void ci_leaf_init(struct cacheinfo *this_leaf, int private,
+			 enum cache_type type, unsigned int level, int cpu)
+{
+	int ti, num_sets;
+
+	if (type == CACHE_TYPE_INST)
+		ti = CACHE_TI_INSTRUCTION;
+	else
+		ti = CACHE_TI_UNIFIED;
+	this_leaf->level = level + 1;
+	this_leaf->type = type;
+	this_leaf->coherency_line_size = ecag(EXTRACT_LINE_SIZE, level, ti);
+	this_leaf->ways_of_associativity = ecag(EXTRACT_ASSOCIATIVITY, level, ti);
+	this_leaf->size = ecag(EXTRACT_SIZE, level, ti);
+	num_sets = this_leaf->size / this_leaf->coherency_line_size;
+	num_sets /= this_leaf->ways_of_associativity;
+	this_leaf->number_of_sets = num_sets;
+	cpumask_set_cpu(cpu, &this_leaf->shared_cpu_map);
+	if (!private)
+		this_leaf->disable_sysfs = true;
+}
+
+int init_cache_level(unsigned int cpu)
+{
+	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
+	unsigned int level = 0, leaves = 0;
+	union cache_topology ct;
+	enum cache_type ctype;
+
+	if (!this_cpu_ci)
+		return -EINVAL;
+	ct.raw = ecag(EXTRACT_TOPOLOGY, 0, 0);
+	do {
+		ctype = get_cache_type(&ct.ci[0], level);
+		if (ctype == CACHE_TYPE_NOCACHE)
+			break;
+		/* Separate instruction and data caches */
+		leaves += (ctype == CACHE_TYPE_SEPARATE) ? 2 : 1;
+	} while (++level < CACHE_MAX_LEVEL);
+	this_cpu_ci->num_levels = level;
+	this_cpu_ci->num_leaves = leaves;
+	return 0;
+}
+
+int populate_cache_leaves(unsigned int cpu)
+{
+	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
+	struct cacheinfo *this_leaf = this_cpu_ci->info_list;
+	unsigned int level, idx, pvt;
+	union cache_topology ct;
+	enum cache_type ctype;
+
+	if (!test_facility(34))
+		return -EOPNOTSUPP;
+	ct.raw = ecag(EXTRACT_TOPOLOGY, 0, 0);
+	for (idx = 0, level = 0; level < this_cpu_ci->num_levels &&
+	     idx < this_cpu_ci->num_leaves; idx++, level++) {
+		if (!this_leaf)
+			return -EINVAL;
+		pvt = (ct.ci[level].scope == CACHE_SCOPE_PRIVATE) ? 1 : 0;
+		ctype = get_cache_type(&ct.ci[0], level);
+		if (ctype == CACHE_TYPE_SEPARATE) {
+			ci_leaf_init(this_leaf++, pvt, CACHE_TYPE_DATA, level, cpu);
+			ci_leaf_init(this_leaf++, pvt, CACHE_TYPE_INST, level, cpu);
+		} else {
+			ci_leaf_init(this_leaf++, pvt, ctype, level, cpu);
+		}
+	}
+	return 0;
+}
diff --git a/arch/s390/kernel/compat_audit.c b/arch/s390/kernel/compat_audit.c
new file mode 100644
index 000000000..d6487bf87
--- /dev/null
+++ b/arch/s390/kernel/compat_audit.c
@@ -0,0 +1,44 @@
+#undef __s390x__
+#include <asm/unistd.h>
+#include "audit.h"
+
+unsigned s390_dir_class[] = {
+#include <asm-generic/audit_dir_write.h>
+~0U
+};
+
+unsigned s390_chattr_class[] = {
+#include <asm-generic/audit_change_attr.h>
+~0U
+};
+
+unsigned s390_write_class[] = {
+#include <asm-generic/audit_write.h>
+~0U
+};
+
+unsigned s390_read_class[] = {
+#include <asm-generic/audit_read.h>
+~0U
+};
+
+unsigned s390_signal_class[] = {
+#include <asm-generic/audit_signal.h>
+~0U
+};
+
+int s390_classify_syscall(unsigned syscall)
+{
+	switch(syscall) {
+	case __NR_open:
+		return 2;
+	case __NR_openat:
+		return 3;
+	case __NR_socketcall:
+		return 4;
+	case __NR_execve:
+		return 5;
+	default:
+		return 1;
+	}
+}
diff --git a/arch/s390/kernel/compat_linux.c b/arch/s390/kernel/compat_linux.c
new file mode 100644
index 000000000..437e61159
--- /dev/null
+++ b/arch/s390/kernel/compat_linux.c
@@ -0,0 +1,520 @@
+/*
+ *  S390 version
+ *    Copyright IBM Corp. 2000
+ *    Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com),
+ *               Gerhard Tonn (ton@de.ibm.com)   
+ *               Thomas Spatzier (tspat@de.ibm.com)
+ *
+ *  Conversion between 31bit and 64bit native syscalls.
+ *
+ * Heavily inspired by the 32-bit Sparc compat code which is 
+ * Copyright (C) 1997,1998 Jakub Jelinek (jj@sunsite.mff.cuni.cz)
+ * Copyright (C) 1997 David S. Miller (davem@caip.rutgers.edu)
+ *
+ */
+
+
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/fs.h> 
+#include <linux/mm.h> 
+#include <linux/file.h> 
+#include <linux/signal.h>
+#include <linux/resource.h>
+#include <linux/times.h>
+#include <linux/smp.h>
+#include <linux/sem.h>
+#include <linux/msg.h>
+#include <linux/shm.h>
+#include <linux/uio.h>
+#include <linux/quota.h>
+#include <linux/module.h>
+#include <linux/poll.h>
+#include <linux/personality.h>
+#include <linux/stat.h>
+#include <linux/filter.h>
+#include <linux/highmem.h>
+#include <linux/highuid.h>
+#include <linux/mman.h>
+#include <linux/ipv6.h>
+#include <linux/in.h>
+#include <linux/icmpv6.h>
+#include <linux/syscalls.h>
+#include <linux/sysctl.h>
+#include <linux/binfmts.h>
+#include <linux/capability.h>
+#include <linux/compat.h>
+#include <linux/vfs.h>
+#include <linux/ptrace.h>
+#include <linux/fadvise.h>
+#include <linux/ipc.h>
+#include <linux/slab.h>
+
+#include <asm/types.h>
+#include <asm/uaccess.h>
+
+#include <net/scm.h>
+#include <net/sock.h>
+
+#include "compat_linux.h"
+
+/* For this source file, we want overflow handling. */
+
+#undef high2lowuid
+#undef high2lowgid
+#undef low2highuid
+#undef low2highgid
+#undef SET_UID16
+#undef SET_GID16
+#undef NEW_TO_OLD_UID
+#undef NEW_TO_OLD_GID
+#undef SET_OLDSTAT_UID
+#undef SET_OLDSTAT_GID
+#undef SET_STAT_UID
+#undef SET_STAT_GID
+
+#define high2lowuid(uid) ((uid) > 65535) ? (u16)overflowuid : (u16)(uid)
+#define high2lowgid(gid) ((gid) > 65535) ? (u16)overflowgid : (u16)(gid)
+#define low2highuid(uid) ((uid) == (u16)-1) ? (uid_t)-1 : (uid_t)(uid)
+#define low2highgid(gid) ((gid) == (u16)-1) ? (gid_t)-1 : (gid_t)(gid)
+#define SET_UID16(var, uid)	var = high2lowuid(uid)
+#define SET_GID16(var, gid)	var = high2lowgid(gid)
+#define NEW_TO_OLD_UID(uid)	high2lowuid(uid)
+#define NEW_TO_OLD_GID(gid)	high2lowgid(gid)
+#define SET_OLDSTAT_UID(stat, uid)	(stat).st_uid = high2lowuid(uid)
+#define SET_OLDSTAT_GID(stat, gid)	(stat).st_gid = high2lowgid(gid)
+#define SET_STAT_UID(stat, uid)		(stat).st_uid = high2lowuid(uid)
+#define SET_STAT_GID(stat, gid)		(stat).st_gid = high2lowgid(gid)
+
+COMPAT_SYSCALL_DEFINE3(s390_chown16, const char __user *, filename,
+		       u16, user, u16, group)
+{
+	return sys_chown(filename, low2highuid(user), low2highgid(group));
+}
+
+COMPAT_SYSCALL_DEFINE3(s390_lchown16, const char __user *,
+		       filename, u16, user, u16, group)
+{
+	return sys_lchown(filename, low2highuid(user), low2highgid(group));
+}
+
+COMPAT_SYSCALL_DEFINE3(s390_fchown16, unsigned int, fd, u16, user, u16, group)
+{
+	return sys_fchown(fd, low2highuid(user), low2highgid(group));
+}
+
+COMPAT_SYSCALL_DEFINE2(s390_setregid16, u16, rgid, u16, egid)
+{
+	return sys_setregid(low2highgid(rgid), low2highgid(egid));
+}
+
+COMPAT_SYSCALL_DEFINE1(s390_setgid16, u16, gid)
+{
+	return sys_setgid((gid_t)gid);
+}
+
+COMPAT_SYSCALL_DEFINE2(s390_setreuid16, u16, ruid, u16, euid)
+{
+	return sys_setreuid(low2highuid(ruid), low2highuid(euid));
+}
+
+COMPAT_SYSCALL_DEFINE1(s390_setuid16, u16, uid)
+{
+	return sys_setuid((uid_t)uid);
+}
+
+COMPAT_SYSCALL_DEFINE3(s390_setresuid16, u16, ruid, u16, euid, u16, suid)
+{
+	return sys_setresuid(low2highuid(ruid), low2highuid(euid),
+			     low2highuid(suid));
+}
+
+COMPAT_SYSCALL_DEFINE3(s390_getresuid16, u16 __user *, ruidp,
+		       u16 __user *, euidp, u16 __user *, suidp)
+{
+	const struct cred *cred = current_cred();
+	int retval;
+	u16 ruid, euid, suid;
+
+	ruid = high2lowuid(from_kuid_munged(cred->user_ns, cred->uid));
+	euid = high2lowuid(from_kuid_munged(cred->user_ns, cred->euid));
+	suid = high2lowuid(from_kuid_munged(cred->user_ns, cred->suid));
+
+	if (!(retval   = put_user(ruid, ruidp)) &&
+	    !(retval   = put_user(euid, euidp)))
+		retval = put_user(suid, suidp);
+
+	return retval;
+}
+
+COMPAT_SYSCALL_DEFINE3(s390_setresgid16, u16, rgid, u16, egid, u16, sgid)
+{
+	return sys_setresgid(low2highgid(rgid), low2highgid(egid),
+			     low2highgid(sgid));
+}
+
+COMPAT_SYSCALL_DEFINE3(s390_getresgid16, u16 __user *, rgidp,
+		       u16 __user *, egidp, u16 __user *, sgidp)
+{
+	const struct cred *cred = current_cred();
+	int retval;
+	u16 rgid, egid, sgid;
+
+	rgid = high2lowgid(from_kgid_munged(cred->user_ns, cred->gid));
+	egid = high2lowgid(from_kgid_munged(cred->user_ns, cred->egid));
+	sgid = high2lowgid(from_kgid_munged(cred->user_ns, cred->sgid));
+
+	if (!(retval   = put_user(rgid, rgidp)) &&
+	    !(retval   = put_user(egid, egidp)))
+		retval = put_user(sgid, sgidp);
+
+	return retval;
+}
+
+COMPAT_SYSCALL_DEFINE1(s390_setfsuid16, u16, uid)
+{
+	return sys_setfsuid((uid_t)uid);
+}
+
+COMPAT_SYSCALL_DEFINE1(s390_setfsgid16, u16, gid)
+{
+	return sys_setfsgid((gid_t)gid);
+}
+
+static int groups16_to_user(u16 __user *grouplist, struct group_info *group_info)
+{
+	struct user_namespace *user_ns = current_user_ns();
+	int i;
+	u16 group;
+	kgid_t kgid;
+
+	for (i = 0; i < group_info->ngroups; i++) {
+		kgid = GROUP_AT(group_info, i);
+		group = (u16)from_kgid_munged(user_ns, kgid);
+		if (put_user(group, grouplist+i))
+			return -EFAULT;
+	}
+
+	return 0;
+}
+
+static int groups16_from_user(struct group_info *group_info, u16 __user *grouplist)
+{
+	struct user_namespace *user_ns = current_user_ns();
+	int i;
+	u16 group;
+	kgid_t kgid;
+
+	for (i = 0; i < group_info->ngroups; i++) {
+		if (get_user(group, grouplist+i))
+			return  -EFAULT;
+
+		kgid = make_kgid(user_ns, (gid_t)group);
+		if (!gid_valid(kgid))
+			return -EINVAL;
+
+		GROUP_AT(group_info, i) = kgid;
+	}
+
+	return 0;
+}
+
+COMPAT_SYSCALL_DEFINE2(s390_getgroups16, int, gidsetsize, u16 __user *, grouplist)
+{
+	const struct cred *cred = current_cred();
+	int i;
+
+	if (gidsetsize < 0)
+		return -EINVAL;
+
+	get_group_info(cred->group_info);
+	i = cred->group_info->ngroups;
+	if (gidsetsize) {
+		if (i > gidsetsize) {
+			i = -EINVAL;
+			goto out;
+		}
+		if (groups16_to_user(grouplist, cred->group_info)) {
+			i = -EFAULT;
+			goto out;
+		}
+	}
+out:
+	put_group_info(cred->group_info);
+	return i;
+}
+
+COMPAT_SYSCALL_DEFINE2(s390_setgroups16, int, gidsetsize, u16 __user *, grouplist)
+{
+	struct group_info *group_info;
+	int retval;
+
+	if (!may_setgroups())
+		return -EPERM;
+	if ((unsigned)gidsetsize > NGROUPS_MAX)
+		return -EINVAL;
+
+	group_info = groups_alloc(gidsetsize);
+	if (!group_info)
+		return -ENOMEM;
+	retval = groups16_from_user(group_info, grouplist);
+	if (retval) {
+		put_group_info(group_info);
+		return retval;
+	}
+
+	retval = set_current_groups(group_info);
+	put_group_info(group_info);
+
+	return retval;
+}
+
+COMPAT_SYSCALL_DEFINE0(s390_getuid16)
+{
+	return high2lowuid(from_kuid_munged(current_user_ns(), current_uid()));
+}
+
+COMPAT_SYSCALL_DEFINE0(s390_geteuid16)
+{
+	return high2lowuid(from_kuid_munged(current_user_ns(), current_euid()));
+}
+
+COMPAT_SYSCALL_DEFINE0(s390_getgid16)
+{
+	return high2lowgid(from_kgid_munged(current_user_ns(), current_gid()));
+}
+
+COMPAT_SYSCALL_DEFINE0(s390_getegid16)
+{
+	return high2lowgid(from_kgid_munged(current_user_ns(), current_egid()));
+}
+
+#ifdef CONFIG_SYSVIPC
+COMPAT_SYSCALL_DEFINE5(s390_ipc, uint, call, int, first, compat_ulong_t, second,
+		compat_ulong_t, third, compat_uptr_t, ptr)
+{
+	if (call >> 16)		/* hack for backward compatibility */
+		return -EINVAL;
+	return compat_sys_ipc(call, first, second, third, ptr, third);
+}
+#endif
+
+COMPAT_SYSCALL_DEFINE3(s390_truncate64, const char __user *, path, u32, high, u32, low)
+{
+	return sys_truncate(path, (unsigned long)high << 32 | low);
+}
+
+COMPAT_SYSCALL_DEFINE3(s390_ftruncate64, unsigned int, fd, u32, high, u32, low)
+{
+	return sys_ftruncate(fd, (unsigned long)high << 32 | low);
+}
+
+COMPAT_SYSCALL_DEFINE5(s390_pread64, unsigned int, fd, char __user *, ubuf,
+		       compat_size_t, count, u32, high, u32, low)
+{
+	if ((compat_ssize_t) count < 0)
+		return -EINVAL;
+	return sys_pread64(fd, ubuf, count, (unsigned long)high << 32 | low);
+}
+
+COMPAT_SYSCALL_DEFINE5(s390_pwrite64, unsigned int, fd, const char __user *, ubuf,
+		       compat_size_t, count, u32, high, u32, low)
+{
+	if ((compat_ssize_t) count < 0)
+		return -EINVAL;
+	return sys_pwrite64(fd, ubuf, count, (unsigned long)high << 32 | low);
+}
+
+COMPAT_SYSCALL_DEFINE4(s390_readahead, int, fd, u32, high, u32, low, s32, count)
+{
+	return sys_readahead(fd, (unsigned long)high << 32 | low, count);
+}
+
+struct stat64_emu31 {
+	unsigned long long  st_dev;
+	unsigned int    __pad1;
+#define STAT64_HAS_BROKEN_ST_INO        1
+	u32             __st_ino;
+	unsigned int    st_mode;
+	unsigned int    st_nlink;
+	u32             st_uid;
+	u32             st_gid;
+	unsigned long long  st_rdev;
+	unsigned int    __pad3;
+	long            st_size;
+	u32             st_blksize;
+	unsigned char   __pad4[4];
+	u32             __pad5;     /* future possible st_blocks high bits */
+	u32             st_blocks;  /* Number 512-byte blocks allocated. */
+	u32             st_atime;
+	u32             __pad6;
+	u32             st_mtime;
+	u32             __pad7;
+	u32             st_ctime;
+	u32             __pad8;     /* will be high 32 bits of ctime someday */
+	unsigned long   st_ino;
+};	
+
+static int cp_stat64(struct stat64_emu31 __user *ubuf, struct kstat *stat)
+{
+	struct stat64_emu31 tmp;
+
+	memset(&tmp, 0, sizeof(tmp));
+
+	tmp.st_dev = huge_encode_dev(stat->dev);
+	tmp.st_ino = stat->ino;
+	tmp.__st_ino = (u32)stat->ino;
+	tmp.st_mode = stat->mode;
+	tmp.st_nlink = (unsigned int)stat->nlink;
+	tmp.st_uid = from_kuid_munged(current_user_ns(), stat->uid);
+	tmp.st_gid = from_kgid_munged(current_user_ns(), stat->gid);
+	tmp.st_rdev = huge_encode_dev(stat->rdev);
+	tmp.st_size = stat->size;
+	tmp.st_blksize = (u32)stat->blksize;
+	tmp.st_blocks = (u32)stat->blocks;
+	tmp.st_atime = (u32)stat->atime.tv_sec;
+	tmp.st_mtime = (u32)stat->mtime.tv_sec;
+	tmp.st_ctime = (u32)stat->ctime.tv_sec;
+
+	return copy_to_user(ubuf,&tmp,sizeof(tmp)) ? -EFAULT : 0; 
+}
+
+COMPAT_SYSCALL_DEFINE2(s390_stat64, const char __user *, filename, struct stat64_emu31 __user *, statbuf)
+{
+	struct kstat stat;
+	int ret = vfs_stat(filename, &stat);
+	if (!ret)
+		ret = cp_stat64(statbuf, &stat);
+	return ret;
+}
+
+COMPAT_SYSCALL_DEFINE2(s390_lstat64, const char __user *, filename, struct stat64_emu31 __user *, statbuf)
+{
+	struct kstat stat;
+	int ret = vfs_lstat(filename, &stat);
+	if (!ret)
+		ret = cp_stat64(statbuf, &stat);
+	return ret;
+}
+
+COMPAT_SYSCALL_DEFINE2(s390_fstat64, unsigned int, fd, struct stat64_emu31 __user *, statbuf)
+{
+	struct kstat stat;
+	int ret = vfs_fstat(fd, &stat);
+	if (!ret)
+		ret = cp_stat64(statbuf, &stat);
+	return ret;
+}
+
+COMPAT_SYSCALL_DEFINE4(s390_fstatat64, unsigned int, dfd, const char __user *, filename,
+		       struct stat64_emu31 __user *, statbuf, int, flag)
+{
+	struct kstat stat;
+	int error;
+
+	error = vfs_fstatat(dfd, filename, &stat, flag);
+	if (error)
+		return error;
+	return cp_stat64(statbuf, &stat);
+}
+
+/*
+ * Linux/i386 didn't use to be able to handle more than
+ * 4 system call parameters, so these system calls used a memory
+ * block for parameter passing..
+ */
+
+struct mmap_arg_struct_emu31 {
+	compat_ulong_t addr;
+	compat_ulong_t len;
+	compat_ulong_t prot;
+	compat_ulong_t flags;
+	compat_ulong_t fd;
+	compat_ulong_t offset;
+};
+
+COMPAT_SYSCALL_DEFINE1(s390_old_mmap, struct mmap_arg_struct_emu31 __user *, arg)
+{
+	struct mmap_arg_struct_emu31 a;
+
+	if (copy_from_user(&a, arg, sizeof(a)))
+		return -EFAULT;
+	if (a.offset & ~PAGE_MASK)
+		return -EINVAL;
+	return sys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, a.fd,
+			      a.offset >> PAGE_SHIFT);
+}
+
+COMPAT_SYSCALL_DEFINE1(s390_mmap2, struct mmap_arg_struct_emu31 __user *, arg)
+{
+	struct mmap_arg_struct_emu31 a;
+
+	if (copy_from_user(&a, arg, sizeof(a)))
+		return -EFAULT;
+	return sys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, a.fd, a.offset);
+}
+
+COMPAT_SYSCALL_DEFINE3(s390_read, unsigned int, fd, char __user *, buf, compat_size_t, count)
+{
+	if ((compat_ssize_t) count < 0)
+		return -EINVAL; 
+
+	return sys_read(fd, buf, count);
+}
+
+COMPAT_SYSCALL_DEFINE3(s390_write, unsigned int, fd, const char __user *, buf, compat_size_t, count)
+{
+	if ((compat_ssize_t) count < 0)
+		return -EINVAL; 
+
+	return sys_write(fd, buf, count);
+}
+
+/*
+ * 31 bit emulation wrapper functions for sys_fadvise64/fadvise64_64.
+ * These need to rewrite the advise values for POSIX_FADV_{DONTNEED,NOREUSE}
+ * because the 31 bit values differ from the 64 bit values.
+ */
+
+COMPAT_SYSCALL_DEFINE5(s390_fadvise64, int, fd, u32, high, u32, low, compat_size_t, len, int, advise)
+{
+	if (advise == 4)
+		advise = POSIX_FADV_DONTNEED;
+	else if (advise == 5)
+		advise = POSIX_FADV_NOREUSE;
+	return sys_fadvise64(fd, (unsigned long)high << 32 | low, len, advise);
+}
+
+struct fadvise64_64_args {
+	int fd;
+	long long offset;
+	long long len;
+	int advice;
+};
+
+COMPAT_SYSCALL_DEFINE1(s390_fadvise64_64, struct fadvise64_64_args __user *, args)
+{
+	struct fadvise64_64_args a;
+
+	if ( copy_from_user(&a, args, sizeof(a)) )
+		return -EFAULT;
+	if (a.advice == 4)
+		a.advice = POSIX_FADV_DONTNEED;
+	else if (a.advice == 5)
+		a.advice = POSIX_FADV_NOREUSE;
+	return sys_fadvise64_64(a.fd, a.offset, a.len, a.advice);
+}
+
+COMPAT_SYSCALL_DEFINE6(s390_sync_file_range, int, fd, u32, offhigh, u32, offlow,
+		       u32, nhigh, u32, nlow, unsigned int, flags)
+{
+	return sys_sync_file_range(fd, ((loff_t)offhigh << 32) + offlow,
+				   ((u64)nhigh << 32) + nlow, flags);
+}
+
+COMPAT_SYSCALL_DEFINE6(s390_fallocate, int, fd, int, mode, u32, offhigh, u32, offlow,
+		       u32, lenhigh, u32, lenlow)
+{
+	return sys_fallocate(fd, mode, ((loff_t)offhigh << 32) + offlow,
+			     ((u64)lenhigh << 32) + lenlow);
+}
diff --git a/arch/s390/kernel/compat_linux.h b/arch/s390/kernel/compat_linux.h
new file mode 100644
index 000000000..a0a886c04
--- /dev/null
+++ b/arch/s390/kernel/compat_linux.h
@@ -0,0 +1,129 @@
+#ifndef _ASM_S390X_S390_H
+#define _ASM_S390X_S390_H
+
+#include <linux/compat.h>
+#include <linux/socket.h>
+#include <linux/syscalls.h>
+
+/* Macro that masks the high order bit of an 32 bit pointer and converts it*/
+/*       to a 64 bit pointer */
+#define A(__x) ((unsigned long)((__x) & 0x7FFFFFFFUL))
+#define AA(__x)				\
+	((unsigned long)(__x))
+
+/* Now 32bit compatibility types */
+struct ipc_kludge_32 {
+        __u32   msgp;                           /* pointer              */
+        __s32   msgtyp;
+};
+
+/* asm/sigcontext.h */
+typedef union
+{
+	__u64   d;
+	__u32   f; 
+} freg_t32;
+
+typedef struct
+{
+	unsigned int	fpc;
+	unsigned int	pad;
+	freg_t32	fprs[__NUM_FPRS];              
+} _s390_fp_regs32;
+
+typedef struct 
+{
+        __u32   mask;
+        __u32	addr;
+} _psw_t32 __attribute__ ((aligned(8)));
+
+typedef struct
+{
+	_psw_t32	psw;
+	__u32		gprs[__NUM_GPRS];
+	__u32		acrs[__NUM_ACRS];
+} _s390_regs_common32;
+
+typedef struct
+{
+	_s390_regs_common32 regs;
+	_s390_fp_regs32     fpregs;
+} _sigregs32;
+
+typedef struct
+{
+	__u32 gprs_high[__NUM_GPRS];
+	__u64 vxrs_low[__NUM_VXRS_LOW];
+	__vector128 vxrs_high[__NUM_VXRS_HIGH];
+	__u8 __reserved[128];
+} _sigregs_ext32;
+
+#define _SIGCONTEXT_NSIG32	64
+#define _SIGCONTEXT_NSIG_BPW32	32
+#define __SIGNAL_FRAMESIZE32	96
+#define _SIGMASK_COPY_SIZE32	(sizeof(u32)*2)
+
+struct sigcontext32
+{
+	__u32	oldmask[_COMPAT_NSIG_WORDS];
+	__u32	sregs;				/* pointer */
+};
+
+/* asm/signal.h */
+
+/* asm/ucontext.h */
+struct ucontext32 {
+	__u32			uc_flags;
+	__u32			uc_link;	/* pointer */	
+	compat_stack_t		uc_stack;
+	_sigregs32		uc_mcontext;
+	compat_sigset_t		uc_sigmask;
+	/* Allow for uc_sigmask growth.  Glibc uses a 1024-bit sigset_t.  */
+	unsigned char		__unused[128 - sizeof(compat_sigset_t)];
+	_sigregs_ext32		uc_mcontext_ext;
+};
+
+struct stat64_emu31;
+struct mmap_arg_struct_emu31;
+struct fadvise64_64_args;
+
+long compat_sys_s390_chown16(const char __user *filename, u16 user, u16 group);
+long compat_sys_s390_lchown16(const char __user *filename, u16 user, u16 group);
+long compat_sys_s390_fchown16(unsigned int fd, u16 user, u16 group);
+long compat_sys_s390_setregid16(u16 rgid, u16 egid);
+long compat_sys_s390_setgid16(u16 gid);
+long compat_sys_s390_setreuid16(u16 ruid, u16 euid);
+long compat_sys_s390_setuid16(u16 uid);
+long compat_sys_s390_setresuid16(u16 ruid, u16 euid, u16 suid);
+long compat_sys_s390_getresuid16(u16 __user *ruid, u16 __user *euid, u16 __user *suid);
+long compat_sys_s390_setresgid16(u16 rgid, u16 egid, u16 sgid);
+long compat_sys_s390_getresgid16(u16 __user *rgid, u16 __user *egid, u16 __user *sgid);
+long compat_sys_s390_setfsuid16(u16 uid);
+long compat_sys_s390_setfsgid16(u16 gid);
+long compat_sys_s390_getgroups16(int gidsetsize, u16 __user *grouplist);
+long compat_sys_s390_setgroups16(int gidsetsize, u16 __user *grouplist);
+long compat_sys_s390_getuid16(void);
+long compat_sys_s390_geteuid16(void);
+long compat_sys_s390_getgid16(void);
+long compat_sys_s390_getegid16(void);
+long compat_sys_s390_truncate64(const char __user *path, u32 high, u32 low);
+long compat_sys_s390_ftruncate64(unsigned int fd, u32 high, u32 low);
+long compat_sys_s390_pread64(unsigned int fd, char __user *ubuf, compat_size_t count, u32 high, u32 low);
+long compat_sys_s390_pwrite64(unsigned int fd, const char __user *ubuf, compat_size_t count, u32 high, u32 low);
+long compat_sys_s390_readahead(int fd, u32 high, u32 low, s32 count);
+long compat_sys_s390_stat64(const char __user *filename, struct stat64_emu31 __user *statbuf);
+long compat_sys_s390_lstat64(const char __user *filename, struct stat64_emu31 __user *statbuf);
+long compat_sys_s390_fstat64(unsigned int fd, struct stat64_emu31 __user *statbuf);
+long compat_sys_s390_fstatat64(unsigned int dfd, const char __user *filename, struct stat64_emu31 __user *statbuf, int flag);
+long compat_sys_s390_old_mmap(struct mmap_arg_struct_emu31 __user *arg);
+long compat_sys_s390_mmap2(struct mmap_arg_struct_emu31 __user *arg);
+long compat_sys_s390_read(unsigned int fd, char __user * buf, compat_size_t count);
+long compat_sys_s390_write(unsigned int fd, const char __user * buf, compat_size_t count);
+long compat_sys_s390_fadvise64(int fd, u32 high, u32 low, compat_size_t len, int advise);
+long compat_sys_s390_fadvise64_64(struct fadvise64_64_args __user *args);
+long compat_sys_s390_sync_file_range(int fd, u32 offhigh, u32 offlow, u32 nhigh, u32 nlow, unsigned int flags);
+long compat_sys_s390_fallocate(int fd, int mode, u32 offhigh, u32 offlow, u32 lenhigh, u32 lenlow);
+long compat_sys_sigreturn(void);
+long compat_sys_rt_sigreturn(void);
+
+#endif /* _ASM_S390X_S390_H */
diff --git a/arch/s390/kernel/compat_ptrace.h b/arch/s390/kernel/compat_ptrace.h
new file mode 100644
index 000000000..12b823833
--- /dev/null
+++ b/arch/s390/kernel/compat_ptrace.h
@@ -0,0 +1,63 @@
+#ifndef _PTRACE32_H
+#define _PTRACE32_H
+
+#include <asm/ptrace.h>    /* needed for NUM_CR_WORDS */
+#include "compat_linux.h"  /* needed for psw_compat_t */
+
+struct compat_per_struct_kernel {
+	__u32 cr9;		/* PER control bits */
+	__u32 cr10;		/* PER starting address */
+	__u32 cr11;		/* PER ending address */
+	__u32 bits;		/* Obsolete software bits */
+	__u32 starting_addr;	/* User specified start address */
+	__u32 ending_addr;	/* User specified end address */
+	__u16 perc_atmid;	/* PER trap ATMID */
+	__u32 address;		/* PER trap instruction address */
+	__u8  access_id;	/* PER trap access identification */
+};
+
+struct compat_user_regs_struct
+{
+	psw_compat_t psw;
+	u32 gprs[NUM_GPRS];
+	u32 acrs[NUM_ACRS];
+	u32 orig_gpr2;
+	/* nb: there's a 4-byte hole here */
+	s390_fp_regs fp_regs;
+	/*
+	 * These per registers are in here so that gdb can modify them
+	 * itself as there is no "official" ptrace interface for hardware
+	 * watchpoints. This is the way intel does it.
+	 */
+	struct compat_per_struct_kernel per_info;
+	u32  ieee_instruction_pointer;	/* obsolete, always 0 */
+};
+
+struct compat_user {
+	/* We start with the registers, to mimic the way that "memory"
+	   is returned from the ptrace(3,...) function.  */
+	struct compat_user_regs_struct regs;
+	/* The rest of this junk is to help gdb figure out what goes where */
+	u32 u_tsize;		/* Text segment size (pages). */
+	u32 u_dsize;	        /* Data segment size (pages). */
+	u32 u_ssize;	        /* Stack segment size (pages). */
+	u32 start_code;         /* Starting virtual address of text. */
+	u32 start_stack;	/* Starting virtual address of stack area.
+				   This is actually the bottom of the stack,
+				   the top of the stack is always found in the
+				   esp register.  */
+	s32 signal;     	 /* Signal that caused the core dump. */
+	u32 u_ar0;               /* Used by gdb to help find the values for */
+	                         /* the registers. */
+	u32 magic;		 /* To uniquely identify a core file */
+	char u_comm[32];	 /* User command that was responsible */
+};
+
+typedef struct
+{
+	__u32   len;
+	__u32   kernel_addr;
+	__u32   process_addr;
+} compat_ptrace_area;
+
+#endif /* _PTRACE32_H */
diff --git a/arch/s390/kernel/compat_signal.c b/arch/s390/kernel/compat_signal.c
new file mode 100644
index 000000000..fe8d6924e
--- /dev/null
+++ b/arch/s390/kernel/compat_signal.c
@@ -0,0 +1,549 @@
+/*
+ *    Copyright IBM Corp. 2000, 2006
+ *    Author(s): Denis Joseph Barrow (djbarrow@de.ibm.com,barrow_dj@yahoo.com)
+ *               Gerhard Tonn (ton@de.ibm.com)                  
+ *
+ *  Copyright (C) 1991, 1992  Linus Torvalds
+ *
+ *  1997-11-28  Modified for POSIX.1b signals by Richard Henderson
+ */
+
+#include <linux/compat.h>
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/smp.h>
+#include <linux/kernel.h>
+#include <linux/signal.h>
+#include <linux/errno.h>
+#include <linux/wait.h>
+#include <linux/ptrace.h>
+#include <linux/unistd.h>
+#include <linux/stddef.h>
+#include <linux/tty.h>
+#include <linux/personality.h>
+#include <linux/binfmts.h>
+#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"
+
+typedef struct 
+{
+	__u8 callee_used_stack[__SIGNAL_FRAMESIZE32];
+	struct sigcontext32 sc;
+	_sigregs32 sregs;
+	int signo;
+	_sigregs_ext32 sregs_ext;
+	__u16 svc_insn;		/* Offset of svc_insn is NOT fixed! */
+} sigframe32;
+
+typedef struct 
+{
+	__u8 callee_used_stack[__SIGNAL_FRAMESIZE32];
+	__u16 svc_insn;
+	compat_siginfo_t info;
+	struct ucontext32 uc;
+} rt_sigframe32;
+
+int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from)
+{
+	int err;
+
+	/* If you change siginfo_t structure, please be sure
+	   this code is fixed accordingly.
+	   It should never copy any pad contained in the structure
+	   to avoid security leaks, but must copy the generic
+	   3 ints plus the relevant union member.  
+	   This routine must convert siginfo from 64bit to 32bit as well
+	   at the same time.  */
+	err = __put_user(from->si_signo, &to->si_signo);
+	err |= __put_user(from->si_errno, &to->si_errno);
+	err |= __put_user((short)from->si_code, &to->si_code);
+	if (from->si_code < 0)
+		err |= __copy_to_user(&to->_sifields._pad, &from->_sifields._pad, SI_PAD_SIZE);
+	else {
+		switch (from->si_code >> 16) {
+		case __SI_RT >> 16: /* This is not generated by the kernel as of now.  */
+		case __SI_MESGQ >> 16:
+			err |= __put_user(from->si_int, &to->si_int);
+			/* fallthrough */
+		case __SI_KILL >> 16:
+			err |= __put_user(from->si_pid, &to->si_pid);
+			err |= __put_user(from->si_uid, &to->si_uid);
+			break;
+		case __SI_CHLD >> 16:
+			err |= __put_user(from->si_pid, &to->si_pid);
+			err |= __put_user(from->si_uid, &to->si_uid);
+			err |= __put_user(from->si_utime, &to->si_utime);
+			err |= __put_user(from->si_stime, &to->si_stime);
+			err |= __put_user(from->si_status, &to->si_status);
+			break;
+		case __SI_FAULT >> 16:
+			err |= __put_user((unsigned long) from->si_addr,
+					  &to->si_addr);
+			break;
+		case __SI_POLL >> 16:
+			err |= __put_user(from->si_band, &to->si_band);
+			err |= __put_user(from->si_fd, &to->si_fd);
+			break;
+		case __SI_TIMER >> 16:
+			err |= __put_user(from->si_tid, &to->si_tid);
+			err |= __put_user(from->si_overrun, &to->si_overrun);
+			err |= __put_user(from->si_int, &to->si_int);
+			break;
+		default:
+			break;
+		}
+	}
+	return err ? -EFAULT : 0;
+}
+
+int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from)
+{
+	int err;
+	u32 tmp;
+
+	err = __get_user(to->si_signo, &from->si_signo);
+	err |= __get_user(to->si_errno, &from->si_errno);
+	err |= __get_user(to->si_code, &from->si_code);
+
+	if (to->si_code < 0)
+		err |= __copy_from_user(&to->_sifields._pad, &from->_sifields._pad, SI_PAD_SIZE);
+	else {
+		switch (to->si_code >> 16) {
+		case __SI_RT >> 16: /* This is not generated by the kernel as of now.  */
+		case __SI_MESGQ >> 16:
+			err |= __get_user(to->si_int, &from->si_int);
+			/* fallthrough */
+		case __SI_KILL >> 16:
+			err |= __get_user(to->si_pid, &from->si_pid);
+			err |= __get_user(to->si_uid, &from->si_uid);
+			break;
+		case __SI_CHLD >> 16:
+			err |= __get_user(to->si_pid, &from->si_pid);
+			err |= __get_user(to->si_uid, &from->si_uid);
+			err |= __get_user(to->si_utime, &from->si_utime);
+			err |= __get_user(to->si_stime, &from->si_stime);
+			err |= __get_user(to->si_status, &from->si_status);
+			break;
+		case __SI_FAULT >> 16:
+			err |= __get_user(tmp, &from->si_addr);
+			to->si_addr = (void __force __user *)
+				(u64) (tmp & PSW32_ADDR_INSN);
+			break;
+		case __SI_POLL >> 16:
+			err |= __get_user(to->si_band, &from->si_band);
+			err |= __get_user(to->si_fd, &from->si_fd);
+			break;
+		case __SI_TIMER >> 16:
+			err |= __get_user(to->si_tid, &from->si_tid);
+			err |= __get_user(to->si_overrun, &from->si_overrun);
+			err |= __get_user(to->si_int, &from->si_int);
+			break;
+		default:
+			break;
+		}
+	}
+	return err ? -EFAULT : 0;
+}
+
+/* Store registers needed to create the signal frame */
+static void store_sigregs(void)
+{
+	int i;
+
+	save_access_regs(current->thread.acrs);
+	save_fp_ctl(&current->thread.fp_regs.fpc);
+	if (current->thread.vxrs) {
+		save_vx_regs(current->thread.vxrs);
+		for (i = 0; i < __NUM_FPRS; i++)
+			current->thread.fp_regs.fprs[i] =
+				*(freg_t *)(current->thread.vxrs + i);
+	} else
+		save_fp_regs(current->thread.fp_regs.fprs);
+}
+
+/* Load registers after signal return */
+static void load_sigregs(void)
+{
+	int i;
+
+	restore_access_regs(current->thread.acrs);
+	/* restore_fp_ctl is done in restore_sigregs */
+	if (current->thread.vxrs) {
+		for (i = 0; i < __NUM_FPRS; i++)
+			*(freg_t *)(current->thread.vxrs + i) =
+				current->thread.fp_regs.fprs[i];
+		restore_vx_regs(current->thread.vxrs);
+	} else
+		restore_fp_regs(current->thread.fp_regs.fprs);
+}
+
+static int save_sigregs32(struct pt_regs *regs, _sigregs32 __user *sregs)
+{
+	_sigregs32 user_sregs;
+	int i;
+
+	user_sregs.regs.psw.mask = (__u32)(regs->psw.mask >> 32);
+	user_sregs.regs.psw.mask &= PSW32_MASK_USER | PSW32_MASK_RI;
+	user_sregs.regs.psw.mask |= PSW32_USER_BITS;
+	user_sregs.regs.psw.addr = (__u32) regs->psw.addr |
+		(__u32)(regs->psw.mask & PSW_MASK_BA);
+	for (i = 0; i < NUM_GPRS; i++)
+		user_sregs.regs.gprs[i] = (__u32) regs->gprs[i];
+	memcpy(&user_sregs.regs.acrs, current->thread.acrs,
+	       sizeof(user_sregs.regs.acrs));
+	memcpy(&user_sregs.fpregs, &current->thread.fp_regs,
+	       sizeof(user_sregs.fpregs));
+	if (__copy_to_user(sregs, &user_sregs, sizeof(_sigregs32)))
+		return -EFAULT;
+	return 0;
+}
+
+static int restore_sigregs32(struct pt_regs *regs,_sigregs32 __user *sregs)
+{
+	_sigregs32 user_sregs;
+	int i;
+
+	/* Alwys make any pending restarted system call return -EINTR */
+	current->restart_block.fn = do_no_restart_syscall;
+
+	if (__copy_from_user(&user_sregs, &sregs->regs, sizeof(user_sregs)))
+		return -EFAULT;
+
+	if (!is_ri_task(current) && (user_sregs.regs.psw.mask & PSW32_MASK_RI))
+		return -EINVAL;
+
+	/* Loading the floating-point-control word can fail. Do that first. */
+	if (restore_fp_ctl(&user_sregs.fpregs.fpc))
+		return -EINVAL;
+
+	/* Use regs->psw.mask instead of PSW_USER_BITS to preserve PER bit. */
+	regs->psw.mask = (regs->psw.mask & ~(PSW_MASK_USER | PSW_MASK_RI)) |
+		(__u64)(user_sregs.regs.psw.mask & PSW32_MASK_USER) << 32 |
+		(__u64)(user_sregs.regs.psw.mask & PSW32_MASK_RI) << 32 |
+		(__u64)(user_sregs.regs.psw.addr & PSW32_ADDR_AMODE);
+	/* Check for invalid user address space control. */
+	if ((regs->psw.mask & PSW_MASK_ASC) == PSW_ASC_HOME)
+		regs->psw.mask = PSW_ASC_PRIMARY |
+			(regs->psw.mask & ~PSW_MASK_ASC);
+	regs->psw.addr = (__u64)(user_sregs.regs.psw.addr & PSW32_ADDR_INSN);
+	for (i = 0; i < NUM_GPRS; i++)
+		regs->gprs[i] = (__u64) user_sregs.regs.gprs[i];
+	memcpy(&current->thread.acrs, &user_sregs.regs.acrs,
+	       sizeof(current->thread.acrs));
+
+	memcpy(&current->thread.fp_regs, &user_sregs.fpregs,
+	       sizeof(current->thread.fp_regs));
+
+	clear_pt_regs_flag(regs, PIF_SYSCALL); /* No longer in a system call */
+	return 0;
+}
+
+static int save_sigregs_ext32(struct pt_regs *regs,
+			      _sigregs_ext32 __user *sregs_ext)
+{
+	__u32 gprs_high[NUM_GPRS];
+	__u64 vxrs[__NUM_VXRS_LOW];
+	int i;
+
+	/* Save high gprs to signal stack */
+	for (i = 0; i < NUM_GPRS; i++)
+		gprs_high[i] = regs->gprs[i] >> 32;
+	if (__copy_to_user(&sregs_ext->gprs_high, &gprs_high,
+			   sizeof(sregs_ext->gprs_high)))
+		return -EFAULT;
+
+	/* Save vector registers to signal stack */
+	if (current->thread.vxrs) {
+		for (i = 0; i < __NUM_VXRS_LOW; i++)
+			vxrs[i] = *((__u64 *)(current->thread.vxrs + i) + 1);
+		if (__copy_to_user(&sregs_ext->vxrs_low, vxrs,
+				   sizeof(sregs_ext->vxrs_low)) ||
+		    __copy_to_user(&sregs_ext->vxrs_high,
+				   current->thread.vxrs + __NUM_VXRS_LOW,
+				   sizeof(sregs_ext->vxrs_high)))
+			return -EFAULT;
+	}
+	return 0;
+}
+
+static int restore_sigregs_ext32(struct pt_regs *regs,
+				 _sigregs_ext32 __user *sregs_ext)
+{
+	__u32 gprs_high[NUM_GPRS];
+	__u64 vxrs[__NUM_VXRS_LOW];
+	int i;
+
+	/* Restore high gprs from signal stack */
+	if (__copy_from_user(&gprs_high, &sregs_ext->gprs_high,
+			     sizeof(&sregs_ext->gprs_high)))
+		return -EFAULT;
+	for (i = 0; i < NUM_GPRS; i++)
+		*(__u32 *)&regs->gprs[i] = gprs_high[i];
+
+	/* Restore vector registers from signal stack */
+	if (current->thread.vxrs) {
+		if (__copy_from_user(vxrs, &sregs_ext->vxrs_low,
+				     sizeof(sregs_ext->vxrs_low)) ||
+		    __copy_from_user(current->thread.vxrs + __NUM_VXRS_LOW,
+				     &sregs_ext->vxrs_high,
+				     sizeof(sregs_ext->vxrs_high)))
+			return -EFAULT;
+		for (i = 0; i < __NUM_VXRS_LOW; i++)
+			*((__u64 *)(current->thread.vxrs + i) + 1) = vxrs[i];
+	}
+	return 0;
+}
+
+COMPAT_SYSCALL_DEFINE0(sigreturn)
+{
+	struct pt_regs *regs = task_pt_regs(current);
+	sigframe32 __user *frame = (sigframe32 __user *)regs->gprs[15];
+	sigset_t set;
+
+	if (__copy_from_user(&set.sig, &frame->sc.oldmask, _SIGMASK_COPY_SIZE32))
+		goto badframe;
+	set_current_blocked(&set);
+	if (restore_sigregs32(regs, &frame->sregs))
+		goto badframe;
+	if (restore_sigregs_ext32(regs, &frame->sregs_ext))
+		goto badframe;
+	load_sigregs();
+	return regs->gprs[2];
+badframe:
+	force_sig(SIGSEGV, current);
+	return 0;
+}
+
+COMPAT_SYSCALL_DEFINE0(rt_sigreturn)
+{
+	struct pt_regs *regs = task_pt_regs(current);
+	rt_sigframe32 __user *frame = (rt_sigframe32 __user *)regs->gprs[15];
+	sigset_t set;
+
+	if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set)))
+		goto badframe;
+	set_current_blocked(&set);
+	if (compat_restore_altstack(&frame->uc.uc_stack))
+		goto badframe;
+	if (restore_sigregs32(regs, &frame->uc.uc_mcontext))
+		goto badframe;
+	if (restore_sigregs_ext32(regs, &frame->uc.uc_mcontext_ext))
+		goto badframe;
+	load_sigregs();
+	return regs->gprs[2];
+badframe:
+	force_sig(SIGSEGV, current);
+	return 0;
+}	
+
+/*
+ * Set up a signal frame.
+ */
+
+
+/*
+ * Determine which stack to use..
+ */
+static inline void __user *
+get_sigframe(struct k_sigaction *ka, struct pt_regs * regs, size_t frame_size)
+{
+	unsigned long sp;
+
+	/* Default to using normal stack */
+	sp = (unsigned long) A(regs->gprs[15]);
+
+	/* Overflow on alternate signal stack gives SIGSEGV. */
+	if (on_sig_stack(sp) && !on_sig_stack((sp - frame_size) & -8UL))
+		return (void __user *) -1UL;
+
+	/* This is the X/Open sanctioned signal stack switching.  */
+	if (ka->sa.sa_flags & SA_ONSTACK) {
+		if (! sas_ss_flags(sp))
+			sp = current->sas_ss_sp + current->sas_ss_size;
+	}
+
+	return (void __user *)((sp - frame_size) & -8ul);
+}
+
+static int setup_frame32(struct ksignal *ksig, sigset_t *set,
+			 struct pt_regs *regs)
+{
+	int sig = ksig->sig;
+	sigframe32 __user *frame;
+	struct sigcontext32 sc;
+	unsigned long restorer;
+	size_t frame_size;
+
+	/*
+	 * gprs_high are always present for 31-bit compat tasks.
+	 * The space for vector registers is only allocated if
+	 * the machine supports it
+	 */
+	frame_size = sizeof(*frame) - sizeof(frame->sregs_ext.__reserved);
+	if (!MACHINE_HAS_VX)
+		frame_size -= sizeof(frame->sregs_ext.vxrs_low) +
+			      sizeof(frame->sregs_ext.vxrs_high);
+	frame = get_sigframe(&ksig->ka, regs, frame_size);
+	if (frame == (void __user *) -1UL)
+		return -EFAULT;
+
+	/* Set up backchain. */
+	if (__put_user(regs->gprs[15], (unsigned int __user *) frame))
+		return -EFAULT;
+
+	/* Create struct sigcontext32 on the signal stack */
+	memcpy(&sc.oldmask, &set->sig, _SIGMASK_COPY_SIZE32);
+	sc.sregs = (__u32)(unsigned long __force) &frame->sregs;
+	if (__copy_to_user(&frame->sc, &sc, sizeof(frame->sc)))
+		return -EFAULT;
+
+	/* Store registers needed to create the signal frame */
+	store_sigregs();
+
+	/* Create _sigregs32 on the signal stack */
+	if (save_sigregs32(regs, &frame->sregs))
+		return -EFAULT;
+
+	/* Place signal number on stack to allow backtrace from handler.  */
+	if (__put_user(regs->gprs[2], (int __force __user *) &frame->signo))
+		return -EFAULT;
+
+	/* Create _sigregs_ext32 on the signal stack */
+	if (save_sigregs_ext32(regs, &frame->sregs_ext))
+		return -EFAULT;
+
+	/* Set up to return from userspace.  If provided, use a stub
+	   already in userspace.  */
+	if (ksig->ka.sa.sa_flags & SA_RESTORER) {
+		restorer = (unsigned long __force)
+			ksig->ka.sa.sa_restorer | PSW32_ADDR_AMODE;
+	} else {
+		/* Signal frames without vectors registers are short ! */
+		__u16 __user *svc = (void __user *) frame + frame_size - 2;
+		if (__put_user(S390_SYSCALL_OPCODE | __NR_sigreturn, svc))
+			return -EFAULT;
+		restorer = (unsigned long __force) svc | PSW32_ADDR_AMODE;
+        }
+
+	/* Set up registers for signal handler */
+	regs->gprs[14] = restorer;
+	regs->gprs[15] = (__force __u64) frame;
+	/* Force 31 bit amode and default user address space control. */
+	regs->psw.mask = PSW_MASK_BA |
+		(PSW_USER_BITS & PSW_MASK_ASC) |
+		(regs->psw.mask & ~PSW_MASK_ASC);
+	regs->psw.addr = (__force __u64) ksig->ka.sa.sa_handler;
+
+	regs->gprs[2] = sig;
+	regs->gprs[3] = (__force __u64) &frame->sc;
+
+	/* We forgot to include these in the sigcontext.
+	   To avoid breaking binary compatibility, they are passed as args. */
+	if (sig == SIGSEGV || sig == SIGBUS || sig == SIGILL ||
+	    sig == SIGTRAP || sig == SIGFPE) {
+		/* set extra registers only for synchronous signals */
+		regs->gprs[4] = regs->int_code & 127;
+		regs->gprs[5] = regs->int_parm_long;
+		regs->gprs[6] = task_thread_info(current)->last_break;
+	}
+
+	return 0;
+}
+
+static int setup_rt_frame32(struct ksignal *ksig, sigset_t *set,
+			    struct pt_regs *regs)
+{
+	rt_sigframe32 __user *frame;
+	unsigned long restorer;
+	size_t frame_size;
+	u32 uc_flags;
+
+	frame_size = sizeof(*frame) -
+		     sizeof(frame->uc.uc_mcontext_ext.__reserved);
+	/*
+	 * gprs_high are always present for 31-bit compat tasks.
+	 * The space for vector registers is only allocated if
+	 * the machine supports it
+	 */
+	uc_flags = UC_GPRS_HIGH;
+	if (MACHINE_HAS_VX) {
+		if (current->thread.vxrs)
+			uc_flags |= UC_VXRS;
+	} else
+		frame_size -= sizeof(frame->uc.uc_mcontext_ext.vxrs_low) +
+			      sizeof(frame->uc.uc_mcontext_ext.vxrs_high);
+	frame = get_sigframe(&ksig->ka, regs, frame_size);
+	if (frame == (void __user *) -1UL)
+		return -EFAULT;
+
+	/* Set up backchain. */
+	if (__put_user(regs->gprs[15], (unsigned int __force __user *) frame))
+		return -EFAULT;
+
+	/* Set up to return from userspace.  If provided, use a stub
+	   already in userspace.  */
+	if (ksig->ka.sa.sa_flags & SA_RESTORER) {
+		restorer = (unsigned long __force)
+			ksig->ka.sa.sa_restorer | PSW32_ADDR_AMODE;
+	} else {
+		__u16 __user *svc = &frame->svc_insn;
+		if (__put_user(S390_SYSCALL_OPCODE | __NR_rt_sigreturn, svc))
+			return -EFAULT;
+		restorer = (unsigned long __force) svc | PSW32_ADDR_AMODE;
+	}
+
+	/* Create siginfo on the signal stack */
+	if (copy_siginfo_to_user32(&frame->info, &ksig->info))
+		return -EFAULT;
+
+	/* Store registers needed to create the signal frame */
+	store_sigregs();
+
+	/* Create ucontext on the signal stack. */
+	if (__put_user(uc_flags, &frame->uc.uc_flags) ||
+	    __put_user(0, &frame->uc.uc_link) ||
+	    __compat_save_altstack(&frame->uc.uc_stack, regs->gprs[15]) ||
+	    save_sigregs32(regs, &frame->uc.uc_mcontext) ||
+	    __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set)) ||
+	    save_sigregs_ext32(regs, &frame->uc.uc_mcontext_ext))
+		return -EFAULT;
+
+	/* Set up registers for signal handler */
+	regs->gprs[14] = restorer;
+	regs->gprs[15] = (__force __u64) frame;
+	/* Force 31 bit amode and default user address space control. */
+	regs->psw.mask = PSW_MASK_BA |
+		(PSW_USER_BITS & PSW_MASK_ASC) |
+		(regs->psw.mask & ~PSW_MASK_ASC);
+	regs->psw.addr = (__u64 __force) ksig->ka.sa.sa_handler;
+
+	regs->gprs[2] = ksig->sig;
+	regs->gprs[3] = (__force __u64) &frame->info;
+	regs->gprs[4] = (__force __u64) &frame->uc;
+	regs->gprs[5] = task_thread_info(current)->last_break;
+	return 0;
+}
+
+/*
+ * OK, we're invoking a handler
+ */	
+
+void handle_signal32(struct ksignal *ksig, sigset_t *oldset,
+		     struct pt_regs *regs)
+{
+	int ret;
+
+	/* Set up the stack frame */
+	if (ksig->ka.sa.sa_flags & SA_SIGINFO)
+		ret = setup_rt_frame32(ksig, oldset, regs);
+	else
+		ret = setup_frame32(ksig, oldset, regs);
+
+	signal_setup_done(ret, ksig, test_thread_flag(TIF_SINGLE_STEP));
+}
+
diff --git a/arch/s390/kernel/compat_wrapper.c b/arch/s390/kernel/compat_wrapper.c
new file mode 100644
index 000000000..d7fa2f0f1
--- /dev/null
+++ b/arch/s390/kernel/compat_wrapper.c
@@ -0,0 +1,222 @@
+/*
+ *  Compat system call wrappers.
+ *
+ *    Copyright IBM Corp. 2014
+ */
+
+#include <linux/syscalls.h>
+#include <linux/compat.h>
+#include "entry.h"
+
+#define COMPAT_SYSCALL_WRAP1(name, ...) \
+	COMPAT_SYSCALL_WRAPx(1, _##name, __VA_ARGS__)
+#define COMPAT_SYSCALL_WRAP2(name, ...) \
+	COMPAT_SYSCALL_WRAPx(2, _##name, __VA_ARGS__)
+#define COMPAT_SYSCALL_WRAP3(name, ...) \
+	COMPAT_SYSCALL_WRAPx(3, _##name, __VA_ARGS__)
+#define COMPAT_SYSCALL_WRAP4(name, ...) \
+	COMPAT_SYSCALL_WRAPx(4, _##name, __VA_ARGS__)
+#define COMPAT_SYSCALL_WRAP5(name, ...) \
+	COMPAT_SYSCALL_WRAPx(5, _##name, __VA_ARGS__)
+#define COMPAT_SYSCALL_WRAP6(name, ...) \
+	COMPAT_SYSCALL_WRAPx(6, _##name, __VA_ARGS__)
+
+#define __SC_COMPAT_TYPE(t, a) \
+	__typeof(__builtin_choose_expr(sizeof(t) > 4, 0L, (t)0)) a
+
+#define __SC_COMPAT_CAST(t, a)						\
+({									\
+	long __ReS = a;							\
+									\
+	BUILD_BUG_ON((sizeof(t) > 4) && !__TYPE_IS_L(t) &&		\
+		     !__TYPE_IS_UL(t) && !__TYPE_IS_PTR(t));		\
+	if (__TYPE_IS_L(t))						\
+		__ReS = (s32)a;						\
+	if (__TYPE_IS_UL(t))						\
+		__ReS = (u32)a;						\
+	if (__TYPE_IS_PTR(t))						\
+		__ReS = a & 0x7fffffff;					\
+	(t)__ReS;							\
+})
+
+/*
+ * The COMPAT_SYSCALL_WRAP macro generates system call wrappers to be used by
+ * compat tasks. These wrappers will only be used for system calls where only
+ * the system call arguments need sign or zero extension or zeroing of the upper
+ * 33 bits of pointers.
+ * Note: since the wrapper function will afterwards call a system call which
+ * again performs zero and sign extension for all system call arguments with
+ * a size of less than eight bytes, these compat wrappers only touch those
+ * system call arguments with a size of eight bytes ((unsigned) long and
+ * pointers). Zero and sign extension for e.g. int parameters will be done by
+ * the regular system call wrappers.
+ */
+#define COMPAT_SYSCALL_WRAPx(x, name, ...)					\
+	asmlinkage long sys##name(__MAP(x,__SC_DECL,__VA_ARGS__));		\
+	asmlinkage long compat_sys##name(__MAP(x,__SC_COMPAT_TYPE,__VA_ARGS__));\
+	asmlinkage long compat_sys##name(__MAP(x,__SC_COMPAT_TYPE,__VA_ARGS__))	\
+	{									\
+		return sys##name(__MAP(x,__SC_COMPAT_CAST,__VA_ARGS__));	\
+	}
+
+COMPAT_SYSCALL_WRAP1(exit, int, error_code);
+COMPAT_SYSCALL_WRAP1(close, unsigned int, fd);
+COMPAT_SYSCALL_WRAP2(creat, const char __user *, pathname, umode_t, mode);
+COMPAT_SYSCALL_WRAP2(link, const char __user *, oldname, const char __user *, newname);
+COMPAT_SYSCALL_WRAP1(unlink, const char __user *, pathname);
+COMPAT_SYSCALL_WRAP1(chdir, const char __user *, filename);
+COMPAT_SYSCALL_WRAP3(mknod, const char __user *, filename, umode_t, mode, unsigned, dev);
+COMPAT_SYSCALL_WRAP2(chmod, const char __user *, filename, umode_t, mode);
+COMPAT_SYSCALL_WRAP1(oldumount, char __user *, name);
+COMPAT_SYSCALL_WRAP1(alarm, unsigned int, seconds);
+COMPAT_SYSCALL_WRAP2(access, const char __user *, filename, int, mode);
+COMPAT_SYSCALL_WRAP1(nice, int, increment);
+COMPAT_SYSCALL_WRAP2(kill, int, pid, int, sig);
+COMPAT_SYSCALL_WRAP2(rename, const char __user *, oldname, const char __user *, newname);
+COMPAT_SYSCALL_WRAP2(mkdir, const char __user *, pathname, umode_t, mode);
+COMPAT_SYSCALL_WRAP1(rmdir, const char __user *, pathname);
+COMPAT_SYSCALL_WRAP1(dup, unsigned int, fildes);
+COMPAT_SYSCALL_WRAP1(pipe, int __user *, fildes);
+COMPAT_SYSCALL_WRAP1(brk, unsigned long, brk);
+COMPAT_SYSCALL_WRAP2(signal, int, sig, __sighandler_t, handler);
+COMPAT_SYSCALL_WRAP1(acct, const char __user *, name);
+COMPAT_SYSCALL_WRAP2(umount, char __user *, name, int, flags);
+COMPAT_SYSCALL_WRAP2(setpgid, pid_t, pid, pid_t, pgid);
+COMPAT_SYSCALL_WRAP1(umask, int, mask);
+COMPAT_SYSCALL_WRAP1(chroot, const char __user *, filename);
+COMPAT_SYSCALL_WRAP2(dup2, unsigned int, oldfd, unsigned int, newfd);
+COMPAT_SYSCALL_WRAP3(sigsuspend, int, unused1, int, unused2, old_sigset_t, mask);
+COMPAT_SYSCALL_WRAP2(sethostname, char __user *, name, int, len);
+COMPAT_SYSCALL_WRAP2(symlink, const char __user *, old, const char __user *, new);
+COMPAT_SYSCALL_WRAP3(readlink, const char __user *, path, char __user *, buf, int, bufsiz);
+COMPAT_SYSCALL_WRAP1(uselib, const char __user *, library);
+COMPAT_SYSCALL_WRAP2(swapon, const char __user *, specialfile, int, swap_flags);
+COMPAT_SYSCALL_WRAP4(reboot, int, magic1, int, magic2, unsigned int, cmd, void __user *, arg);
+COMPAT_SYSCALL_WRAP2(munmap, unsigned long, addr, size_t, len);
+COMPAT_SYSCALL_WRAP2(fchmod, unsigned int, fd, umode_t, mode);
+COMPAT_SYSCALL_WRAP2(getpriority, int, which, int, who);
+COMPAT_SYSCALL_WRAP3(setpriority, int, which, int, who, int, niceval);
+COMPAT_SYSCALL_WRAP3(syslog, int, type, char __user *, buf, int, len);
+COMPAT_SYSCALL_WRAP1(swapoff, const char __user *, specialfile);
+COMPAT_SYSCALL_WRAP1(fsync, unsigned int, fd);
+COMPAT_SYSCALL_WRAP2(setdomainname, char __user *, name, int, len);
+COMPAT_SYSCALL_WRAP1(newuname, struct new_utsname __user *, name);
+COMPAT_SYSCALL_WRAP3(mprotect, unsigned long, start, size_t, len, unsigned long, prot);
+COMPAT_SYSCALL_WRAP3(init_module, void __user *, umod, unsigned long, len, const char __user *, uargs);
+COMPAT_SYSCALL_WRAP2(delete_module, const char __user *, name_user, unsigned int, flags);
+COMPAT_SYSCALL_WRAP4(quotactl, unsigned int, cmd, const char __user *, special, qid_t, id, void __user *, addr);
+COMPAT_SYSCALL_WRAP1(getpgid, pid_t, pid);
+COMPAT_SYSCALL_WRAP1(fchdir, unsigned int, fd);
+COMPAT_SYSCALL_WRAP2(bdflush, int, func, long, data);
+COMPAT_SYSCALL_WRAP3(sysfs, int, option, unsigned long, arg1, unsigned long, arg2);
+COMPAT_SYSCALL_WRAP1(s390_personality, unsigned int, personality);
+COMPAT_SYSCALL_WRAP5(llseek, unsigned int, fd, unsigned long, high, unsigned long, low, loff_t __user *, result, unsigned int, whence);
+COMPAT_SYSCALL_WRAP2(flock, unsigned int, fd, unsigned int, cmd);
+COMPAT_SYSCALL_WRAP3(msync, unsigned long, start, size_t, len, int, flags);
+COMPAT_SYSCALL_WRAP1(getsid, pid_t, pid);
+COMPAT_SYSCALL_WRAP1(fdatasync, unsigned int, fd);
+COMPAT_SYSCALL_WRAP2(mlock, unsigned long, start, size_t, len);
+COMPAT_SYSCALL_WRAP2(munlock, unsigned long, start, size_t, len);
+COMPAT_SYSCALL_WRAP1(mlockall, int, flags);
+COMPAT_SYSCALL_WRAP2(sched_setparam, pid_t, pid, struct sched_param __user *, param);
+COMPAT_SYSCALL_WRAP2(sched_getparam, pid_t, pid, struct sched_param __user *, param);
+COMPAT_SYSCALL_WRAP3(sched_setscheduler, pid_t, pid, int, policy, struct sched_param __user *, param);
+COMPAT_SYSCALL_WRAP1(sched_getscheduler, pid_t, pid);
+COMPAT_SYSCALL_WRAP1(sched_get_priority_max, int, policy);
+COMPAT_SYSCALL_WRAP1(sched_get_priority_min, int, policy);
+COMPAT_SYSCALL_WRAP5(mremap, unsigned long, addr, unsigned long, old_len, unsigned long, new_len, unsigned long, flags, unsigned long, new_addr);
+COMPAT_SYSCALL_WRAP3(poll, struct pollfd __user *, ufds, unsigned int, nfds, int, timeout);
+COMPAT_SYSCALL_WRAP5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, unsigned long, arg4, unsigned long, arg5);
+COMPAT_SYSCALL_WRAP2(getcwd, char __user *, buf, unsigned long, size);
+COMPAT_SYSCALL_WRAP2(capget, cap_user_header_t, header, cap_user_data_t, dataptr);
+COMPAT_SYSCALL_WRAP2(capset, cap_user_header_t, header, const cap_user_data_t, data);
+COMPAT_SYSCALL_WRAP3(lchown, const char __user *, filename, uid_t, user, gid_t, group);
+COMPAT_SYSCALL_WRAP2(setreuid, uid_t, ruid, uid_t, euid);
+COMPAT_SYSCALL_WRAP2(setregid, gid_t, rgid, gid_t, egid);
+COMPAT_SYSCALL_WRAP2(getgroups, int, gidsetsize, gid_t __user *, grouplist);
+COMPAT_SYSCALL_WRAP2(setgroups, int, gidsetsize, gid_t __user *, grouplist);
+COMPAT_SYSCALL_WRAP3(fchown, unsigned int, fd, uid_t, user, gid_t, group);
+COMPAT_SYSCALL_WRAP3(setresuid, uid_t, ruid, uid_t, euid, uid_t, suid);
+COMPAT_SYSCALL_WRAP3(getresuid, uid_t __user *, ruid, uid_t __user *, euid, uid_t __user *, suid);
+COMPAT_SYSCALL_WRAP3(setresgid, gid_t, rgid, gid_t, egid, gid_t, sgid);
+COMPAT_SYSCALL_WRAP3(getresgid, gid_t __user *, rgid, gid_t __user *, egid, gid_t __user *, sgid);
+COMPAT_SYSCALL_WRAP3(chown, const char __user *, filename, uid_t, user, gid_t, group);
+COMPAT_SYSCALL_WRAP1(setuid, uid_t, uid);
+COMPAT_SYSCALL_WRAP1(setgid, gid_t, gid);
+COMPAT_SYSCALL_WRAP1(setfsuid, uid_t, uid);
+COMPAT_SYSCALL_WRAP1(setfsgid, gid_t, gid);
+COMPAT_SYSCALL_WRAP2(pivot_root, const char __user *, new_root, const char __user *, put_old);
+COMPAT_SYSCALL_WRAP3(mincore, unsigned long, start, size_t, len, unsigned char __user *, vec);
+COMPAT_SYSCALL_WRAP3(madvise, unsigned long, start, size_t, len, int, behavior);
+COMPAT_SYSCALL_WRAP5(setxattr, const char __user *, path, const char __user *, name, const void __user *, value, size_t, size, int, flags);
+COMPAT_SYSCALL_WRAP5(lsetxattr, const char __user *, path, const char __user *, name, const void __user *, value, size_t, size, int, flags);
+COMPAT_SYSCALL_WRAP5(fsetxattr, int, fd, const char __user *, name, const void __user *, value, size_t, size, int, flags);
+COMPAT_SYSCALL_WRAP3(getdents64, unsigned int, fd, struct linux_dirent64 __user *, dirent, unsigned int, count);
+COMPAT_SYSCALL_WRAP4(getxattr, const char __user *, path, const char __user *, name, void __user *, value, size_t, size);
+COMPAT_SYSCALL_WRAP4(lgetxattr, const char __user *, path, const char __user *, name, void __user *, value, size_t, size);
+COMPAT_SYSCALL_WRAP4(fgetxattr, int, fd, const char __user *, name, void __user *, value, size_t, size);
+COMPAT_SYSCALL_WRAP3(listxattr, const char __user *, path, char __user *, list, size_t, size);
+COMPAT_SYSCALL_WRAP3(llistxattr, const char __user *, path, char __user *, list, size_t, size);
+COMPAT_SYSCALL_WRAP3(flistxattr, int, fd, char __user *, list, size_t, size);
+COMPAT_SYSCALL_WRAP2(removexattr, const char __user *, path, const char __user *, name);
+COMPAT_SYSCALL_WRAP2(lremovexattr, const char __user *, path, const char __user *, name);
+COMPAT_SYSCALL_WRAP2(fremovexattr, int, fd, const char __user *, name);
+COMPAT_SYSCALL_WRAP1(exit_group, int, error_code);
+COMPAT_SYSCALL_WRAP1(set_tid_address, int __user *, tidptr);
+COMPAT_SYSCALL_WRAP1(epoll_create, int, size);
+COMPAT_SYSCALL_WRAP4(epoll_ctl, int, epfd, int, op, int, fd, struct epoll_event __user *, event);
+COMPAT_SYSCALL_WRAP4(epoll_wait, int, epfd, struct epoll_event __user *, events, int, maxevents, int, timeout);
+COMPAT_SYSCALL_WRAP1(timer_getoverrun, timer_t, timer_id);
+COMPAT_SYSCALL_WRAP1(timer_delete, compat_timer_t, compat_timer_id);
+COMPAT_SYSCALL_WRAP1(io_destroy, aio_context_t, ctx);
+COMPAT_SYSCALL_WRAP3(io_cancel, aio_context_t, ctx_id, struct iocb __user *, iocb, struct io_event __user *, result);
+COMPAT_SYSCALL_WRAP1(mq_unlink, const char __user *, name);
+COMPAT_SYSCALL_WRAP5(add_key, const char __user *, tp, const char __user *, dsc, const void __user *, pld, size_t, len, key_serial_t, id);
+COMPAT_SYSCALL_WRAP4(request_key, const char __user *, tp, const char __user *, dsc, const char __user *, info, key_serial_t, id);
+COMPAT_SYSCALL_WRAP5(remap_file_pages, unsigned long, start, unsigned long, size, unsigned long, prot, unsigned long, pgoff, unsigned long, flags);
+COMPAT_SYSCALL_WRAP3(ioprio_set, int, which, int, who, int, ioprio);
+COMPAT_SYSCALL_WRAP2(ioprio_get, int, which, int, who);
+COMPAT_SYSCALL_WRAP3(inotify_add_watch, int, fd, const char __user *, path, u32, mask);
+COMPAT_SYSCALL_WRAP2(inotify_rm_watch, int, fd, __s32, wd);
+COMPAT_SYSCALL_WRAP3(mkdirat, int, dfd, const char __user *, pathname, umode_t, mode);
+COMPAT_SYSCALL_WRAP4(mknodat, int, dfd, const char __user *, filename, umode_t, mode, unsigned, dev);
+COMPAT_SYSCALL_WRAP5(fchownat, int, dfd, const char __user *, filename, uid_t, user, gid_t, group, int, flag);
+COMPAT_SYSCALL_WRAP3(unlinkat, int, dfd, const char __user *, pathname, int, flag);
+COMPAT_SYSCALL_WRAP4(renameat, int, olddfd, const char __user *, oldname, int, newdfd, const char __user *, newname);
+COMPAT_SYSCALL_WRAP5(linkat, int, olddfd, const char __user *, oldname, int, newdfd, const char __user *, newname, int, flags);
+COMPAT_SYSCALL_WRAP3(symlinkat, const char __user *, oldname, int, newdfd, const char __user *, newname);
+COMPAT_SYSCALL_WRAP4(readlinkat, int, dfd, const char __user *, path, char __user *, buf, int, bufsiz);
+COMPAT_SYSCALL_WRAP3(fchmodat, int, dfd, const char __user *, filename, umode_t, mode);
+COMPAT_SYSCALL_WRAP3(faccessat, int, dfd, const char __user *, filename, int, mode);
+COMPAT_SYSCALL_WRAP1(unshare, unsigned long, unshare_flags);
+COMPAT_SYSCALL_WRAP6(splice, int, fd_in, loff_t __user *, off_in, int, fd_out, loff_t __user *, off_out, size_t, len, unsigned int, flags);
+COMPAT_SYSCALL_WRAP4(tee, int, fdin, int, fdout, size_t, len, unsigned int, flags);
+COMPAT_SYSCALL_WRAP3(getcpu, unsigned __user *, cpu, unsigned __user *, node, struct getcpu_cache __user *, cache);
+COMPAT_SYSCALL_WRAP1(eventfd, unsigned int, count);
+COMPAT_SYSCALL_WRAP2(timerfd_create, int, clockid, int, flags);
+COMPAT_SYSCALL_WRAP2(eventfd2, unsigned int, count, int, flags);
+COMPAT_SYSCALL_WRAP1(inotify_init1, int, flags);
+COMPAT_SYSCALL_WRAP2(pipe2, int __user *, fildes, int, flags);
+COMPAT_SYSCALL_WRAP3(dup3, unsigned int, oldfd, unsigned int, newfd, int, flags);
+COMPAT_SYSCALL_WRAP1(epoll_create1, int, flags);
+COMPAT_SYSCALL_WRAP2(tkill, int, pid, int, sig);
+COMPAT_SYSCALL_WRAP3(tgkill, int, tgid, int, pid, int, sig);
+COMPAT_SYSCALL_WRAP5(perf_event_open, struct perf_event_attr __user *, attr_uptr, pid_t, pid, int, cpu, int, group_fd, unsigned long, flags);
+COMPAT_SYSCALL_WRAP5(clone, unsigned long, newsp, unsigned long, clone_flags, int __user *, parent_tidptr, int __user *, child_tidptr, int, tls_val);
+COMPAT_SYSCALL_WRAP2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags);
+COMPAT_SYSCALL_WRAP4(prlimit64, pid_t, pid, unsigned int, resource, const struct rlimit64 __user *, new_rlim, struct rlimit64 __user *, old_rlim);
+COMPAT_SYSCALL_WRAP5(name_to_handle_at, int, dfd, const char __user *, name, struct file_handle __user *, handle, int __user *, mnt_id, int, flag);
+COMPAT_SYSCALL_WRAP1(syncfs, int, fd);
+COMPAT_SYSCALL_WRAP2(setns, int, fd, int, nstype);
+COMPAT_SYSCALL_WRAP2(s390_runtime_instr, int, command, int, signum);
+COMPAT_SYSCALL_WRAP5(kcmp, pid_t, pid1, pid_t, pid2, int, type, unsigned long, idx1, unsigned long, idx2);
+COMPAT_SYSCALL_WRAP3(finit_module, int, fd, const char __user *, uargs, int, flags);
+COMPAT_SYSCALL_WRAP3(sched_setattr, pid_t, pid, struct sched_attr __user *, attr, unsigned int, flags);
+COMPAT_SYSCALL_WRAP4(sched_getattr, pid_t, pid, struct sched_attr __user *, attr, unsigned int, size, unsigned int, flags);
+COMPAT_SYSCALL_WRAP5(renameat2, int, olddfd, const char __user *, oldname, int, newdfd, const char __user *, newname, unsigned int, flags);
+COMPAT_SYSCALL_WRAP3(seccomp, unsigned int, op, unsigned int, flags, const char __user *, uargs)
+COMPAT_SYSCALL_WRAP3(getrandom, char __user *, buf, size_t, count, unsigned int, flags)
+COMPAT_SYSCALL_WRAP2(memfd_create, const char __user *, uname, unsigned int, flags)
+COMPAT_SYSCALL_WRAP3(bpf, int, cmd, union bpf_attr *, attr, unsigned int, size);
+COMPAT_SYSCALL_WRAP3(s390_pci_mmio_write, const unsigned long, mmio_addr, const void __user *, user_buffer, const size_t, length);
+COMPAT_SYSCALL_WRAP3(s390_pci_mmio_read, const unsigned long, mmio_addr, void __user *, user_buffer, const size_t, length);
diff --git a/arch/s390/kernel/cpcmd.c b/arch/s390/kernel/cpcmd.c
new file mode 100644
index 000000000..199ec92ef
--- /dev/null
+++ b/arch/s390/kernel/cpcmd.c
@@ -0,0 +1,113 @@
+/*
+ *  S390 version
+ *    Copyright IBM Corp. 1999, 2007
+ *    Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com),
+ *               Christian Borntraeger (cborntra@de.ibm.com),
+ */
+
+#define KMSG_COMPONENT "cpcmd"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/stddef.h>
+#include <linux/string.h>
+#include <asm/ebcdic.h>
+#include <asm/cpcmd.h>
+#include <asm/io.h>
+
+static DEFINE_SPINLOCK(cpcmd_lock);
+static char cpcmd_buf[241];
+
+static int diag8_noresponse(int cmdlen)
+{
+	register unsigned long reg2 asm ("2") = (addr_t) cpcmd_buf;
+	register unsigned long reg3 asm ("3") = cmdlen;
+
+	asm volatile(
+		"	sam31\n"
+		"	diag	%1,%0,0x8\n"
+		"	sam64\n"
+		: "+d" (reg3) : "d" (reg2) : "cc");
+	return reg3;
+}
+
+static int diag8_response(int cmdlen, char *response, int *rlen)
+{
+	register unsigned long reg2 asm ("2") = (addr_t) cpcmd_buf;
+	register unsigned long reg3 asm ("3") = (addr_t) response;
+	register unsigned long reg4 asm ("4") = cmdlen | 0x40000000L;
+	register unsigned long reg5 asm ("5") = *rlen;
+
+	asm volatile(
+		"	sam31\n"
+		"	diag	%2,%0,0x8\n"
+		"	sam64\n"
+		"	brc	8,1f\n"
+		"	agr	%1,%4\n"
+		"1:\n"
+		: "+d" (reg4), "+d" (reg5)
+		: "d" (reg2), "d" (reg3), "d" (*rlen) : "cc");
+	*rlen = reg5;
+	return reg4;
+}
+
+/*
+ * __cpcmd has some restrictions over cpcmd
+ *  - the response buffer must reside below 2GB (if any)
+ *  - __cpcmd is unlocked and therefore not SMP-safe
+ */
+int  __cpcmd(const char *cmd, char *response, int rlen, int *response_code)
+{
+	int cmdlen;
+	int rc;
+	int response_len;
+
+	cmdlen = strlen(cmd);
+	BUG_ON(cmdlen > 240);
+	memcpy(cpcmd_buf, cmd, cmdlen);
+	ASCEBC(cpcmd_buf, cmdlen);
+
+	if (response) {
+		memset(response, 0, rlen);
+		response_len = rlen;
+		rc = diag8_response(cmdlen, response, &rlen);
+		EBCASC(response, response_len);
+        } else {
+		rc = diag8_noresponse(cmdlen);
+        }
+	if (response_code)
+		*response_code = rc;
+	return rlen;
+}
+EXPORT_SYMBOL(__cpcmd);
+
+int cpcmd(const char *cmd, char *response, int rlen, int *response_code)
+{
+	char *lowbuf;
+	int len;
+	unsigned long flags;
+
+	if ((virt_to_phys(response) != (unsigned long) response) ||
+			(((unsigned long)response + rlen) >> 31)) {
+		lowbuf = kmalloc(rlen, GFP_KERNEL | GFP_DMA);
+		if (!lowbuf) {
+			pr_warning("The cpcmd kernel function failed to "
+				   "allocate a response buffer\n");
+			return -ENOMEM;
+		}
+		spin_lock_irqsave(&cpcmd_lock, flags);
+		len = __cpcmd(cmd, lowbuf, rlen, response_code);
+		spin_unlock_irqrestore(&cpcmd_lock, flags);
+		memcpy(response, lowbuf, rlen);
+		kfree(lowbuf);
+	} else {
+		spin_lock_irqsave(&cpcmd_lock, flags);
+		len = __cpcmd(cmd, response, rlen, response_code);
+		spin_unlock_irqrestore(&cpcmd_lock, flags);
+	}
+	return len;
+}
+EXPORT_SYMBOL(cpcmd);
diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c
new file mode 100644
index 000000000..49b74454d
--- /dev/null
+++ b/arch/s390/kernel/crash_dump.c
@@ -0,0 +1,687 @@
+/*
+ * S390 kdump implementation
+ *
+ * Copyright IBM Corp. 2011
+ * Author(s): Michael Holzheu <holzheu@linux.vnet.ibm.com>
+ */
+
+#include <linux/crash_dump.h>
+#include <asm/lowcore.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/gfp.h>
+#include <linux/slab.h>
+#include <linux/bootmem.h>
+#include <linux/elf.h>
+#include <linux/memblock.h>
+#include <asm/os_info.h>
+#include <asm/elf.h>
+#include <asm/ipl.h>
+#include <asm/sclp.h>
+
+#define PTR_ADD(x, y) (((char *) (x)) + ((unsigned long) (y)))
+#define PTR_SUB(x, y) (((char *) (x)) - ((unsigned long) (y)))
+#define PTR_DIFF(x, y) ((unsigned long)(((char *) (x)) - ((unsigned long) (y))))
+
+static struct memblock_region oldmem_region;
+
+static struct memblock_type oldmem_type = {
+	.cnt = 1,
+	.max = 1,
+	.total_size = 0,
+	.regions = &oldmem_region,
+};
+
+#define for_each_dump_mem_range(i, nid, p_start, p_end, p_nid)		\
+	for (i = 0, __next_mem_range(&i, nid, &memblock.physmem,	\
+				     &oldmem_type, p_start,		\
+				     p_end, p_nid);			\
+	     i != (u64)ULLONG_MAX;					\
+	     __next_mem_range(&i, nid, &memblock.physmem,		\
+			      &oldmem_type,				\
+			      p_start, p_end, p_nid))
+
+struct dump_save_areas dump_save_areas;
+
+/*
+ * Allocate and add a save area for a CPU
+ */
+struct save_area_ext *dump_save_area_create(int cpu)
+{
+	struct save_area_ext **save_areas, *save_area;
+
+	save_area = kmalloc(sizeof(*save_area), GFP_KERNEL);
+	if (!save_area)
+		return NULL;
+	if (cpu + 1 > dump_save_areas.count) {
+		dump_save_areas.count = cpu + 1;
+		save_areas = krealloc(dump_save_areas.areas,
+				      dump_save_areas.count * sizeof(void *),
+				      GFP_KERNEL | __GFP_ZERO);
+		if (!save_areas) {
+			kfree(save_area);
+			return NULL;
+		}
+		dump_save_areas.areas = save_areas;
+	}
+	dump_save_areas.areas[cpu] = save_area;
+	return save_area;
+}
+
+/*
+ * Return physical address for virtual address
+ */
+static inline void *load_real_addr(void *addr)
+{
+	unsigned long real_addr;
+
+	asm volatile(
+		   "	lra     %0,0(%1)\n"
+		   "	jz	0f\n"
+		   "	la	%0,0\n"
+		   "0:"
+		   : "=a" (real_addr) : "a" (addr) : "cc");
+	return (void *)real_addr;
+}
+
+/*
+ * Copy real to virtual or real memory
+ */
+static int copy_from_realmem(void *dest, void *src, size_t count)
+{
+	unsigned long size;
+
+	if (!count)
+		return 0;
+	if (!is_vmalloc_or_module_addr(dest))
+		return memcpy_real(dest, src, count);
+	do {
+		size = min(count, PAGE_SIZE - (__pa(dest) & ~PAGE_MASK));
+		if (memcpy_real(load_real_addr(dest), src, size))
+			return -EFAULT;
+		count -= size;
+		dest += size;
+		src += size;
+	} while (count);
+	return 0;
+}
+
+/*
+ * Pointer to ELF header in new kernel
+ */
+static void *elfcorehdr_newmem;
+
+/*
+ * Copy one page from zfcpdump "oldmem"
+ *
+ * For pages below HSA size memory from the HSA is copied. Otherwise
+ * real memory copy is used.
+ */
+static ssize_t copy_oldmem_page_zfcpdump(char *buf, size_t csize,
+					 unsigned long src, int userbuf)
+{
+	int rc;
+
+	if (src < sclp_get_hsa_size()) {
+		rc = memcpy_hsa(buf, src, csize, userbuf);
+	} else {
+		if (userbuf)
+			rc = copy_to_user_real((void __force __user *) buf,
+					       (void *) src, csize);
+		else
+			rc = memcpy_real(buf, (void *) src, csize);
+	}
+	return rc ? rc : csize;
+}
+
+/*
+ * Copy one page from kdump "oldmem"
+ *
+ * For the kdump reserved memory this functions performs a swap operation:
+ *  - [OLDMEM_BASE - OLDMEM_BASE + OLDMEM_SIZE] is mapped to [0 - OLDMEM_SIZE].
+ *  - [0 - OLDMEM_SIZE] is mapped to [OLDMEM_BASE - OLDMEM_BASE + OLDMEM_SIZE]
+ */
+static ssize_t copy_oldmem_page_kdump(char *buf, size_t csize,
+				      unsigned long src, int userbuf)
+
+{
+	int rc;
+
+	if (src < OLDMEM_SIZE)
+		src += OLDMEM_BASE;
+	else if (src > OLDMEM_BASE &&
+		 src < OLDMEM_BASE + OLDMEM_SIZE)
+		src -= OLDMEM_BASE;
+	if (userbuf)
+		rc = copy_to_user_real((void __force __user *) buf,
+				       (void *) src, csize);
+	else
+		rc = copy_from_realmem(buf, (void *) src, csize);
+	return (rc == 0) ? rc : csize;
+}
+
+/*
+ * Copy one page from "oldmem"
+ */
+ssize_t copy_oldmem_page(unsigned long pfn, char *buf, size_t csize,
+			 unsigned long offset, int userbuf)
+{
+	unsigned long src;
+
+	if (!csize)
+		return 0;
+	src = (pfn << PAGE_SHIFT) + offset;
+	if (OLDMEM_BASE)
+		return copy_oldmem_page_kdump(buf, csize, src, userbuf);
+	else
+		return copy_oldmem_page_zfcpdump(buf, csize, src, userbuf);
+}
+
+/*
+ * Remap "oldmem" for kdump
+ *
+ * For the kdump reserved memory this functions performs a swap operation:
+ * [0 - OLDMEM_SIZE] is mapped to [OLDMEM_BASE - OLDMEM_BASE + OLDMEM_SIZE]
+ */
+static int remap_oldmem_pfn_range_kdump(struct vm_area_struct *vma,
+					unsigned long from, unsigned long pfn,
+					unsigned long size, pgprot_t prot)
+{
+	unsigned long size_old;
+	int rc;
+
+	if (pfn < OLDMEM_SIZE >> PAGE_SHIFT) {
+		size_old = min(size, OLDMEM_SIZE - (pfn << PAGE_SHIFT));
+		rc = remap_pfn_range(vma, from,
+				     pfn + (OLDMEM_BASE >> PAGE_SHIFT),
+				     size_old, prot);
+		if (rc || size == size_old)
+			return rc;
+		size -= size_old;
+		from += size_old;
+		pfn += size_old >> PAGE_SHIFT;
+	}
+	return remap_pfn_range(vma, from, pfn, size, prot);
+}
+
+/*
+ * Remap "oldmem" for zfcpdump
+ *
+ * We only map available memory above HSA size. Memory below HSA size
+ * is read on demand using the copy_oldmem_page() function.
+ */
+static int remap_oldmem_pfn_range_zfcpdump(struct vm_area_struct *vma,
+					   unsigned long from,
+					   unsigned long pfn,
+					   unsigned long size, pgprot_t prot)
+{
+	unsigned long hsa_end = sclp_get_hsa_size();
+	unsigned long size_hsa;
+
+	if (pfn < hsa_end >> PAGE_SHIFT) {
+		size_hsa = min(size, hsa_end - (pfn << PAGE_SHIFT));
+		if (size == size_hsa)
+			return 0;
+		size -= size_hsa;
+		from += size_hsa;
+		pfn += size_hsa >> PAGE_SHIFT;
+	}
+	return remap_pfn_range(vma, from, pfn, size, prot);
+}
+
+/*
+ * Remap "oldmem" for kdump or zfcpdump
+ */
+int remap_oldmem_pfn_range(struct vm_area_struct *vma, unsigned long from,
+			   unsigned long pfn, unsigned long size, pgprot_t prot)
+{
+	if (OLDMEM_BASE)
+		return remap_oldmem_pfn_range_kdump(vma, from, pfn, size, prot);
+	else
+		return remap_oldmem_pfn_range_zfcpdump(vma, from, pfn, size,
+						       prot);
+}
+
+/*
+ * Copy memory from old kernel
+ */
+int copy_from_oldmem(void *dest, void *src, size_t count)
+{
+	unsigned long copied = 0;
+	int rc;
+
+	if (OLDMEM_BASE) {
+		if ((unsigned long) src < OLDMEM_SIZE) {
+			copied = min(count, OLDMEM_SIZE - (unsigned long) src);
+			rc = copy_from_realmem(dest, src + OLDMEM_BASE, copied);
+			if (rc)
+				return rc;
+		}
+	} else {
+		unsigned long hsa_end = sclp_get_hsa_size();
+		if ((unsigned long) src < hsa_end) {
+			copied = min(count, hsa_end - (unsigned long) src);
+			rc = memcpy_hsa(dest, (unsigned long) src, copied, 0);
+			if (rc)
+				return rc;
+		}
+	}
+	return copy_from_realmem(dest + copied, src + copied, count - copied);
+}
+
+/*
+ * Alloc memory and panic in case of ENOMEM
+ */
+static void *kzalloc_panic(int len)
+{
+	void *rc;
+
+	rc = kzalloc(len, GFP_KERNEL);
+	if (!rc)
+		panic("s390 kdump kzalloc (%d) failed", len);
+	return rc;
+}
+
+/*
+ * Initialize ELF note
+ */
+static void *nt_init(void *buf, Elf64_Word type, void *desc, int d_len,
+		     const char *name)
+{
+	Elf64_Nhdr *note;
+	u64 len;
+
+	note = (Elf64_Nhdr *)buf;
+	note->n_namesz = strlen(name) + 1;
+	note->n_descsz = d_len;
+	note->n_type = type;
+	len = sizeof(Elf64_Nhdr);
+
+	memcpy(buf + len, name, note->n_namesz);
+	len = roundup(len + note->n_namesz, 4);
+
+	memcpy(buf + len, desc, note->n_descsz);
+	len = roundup(len + note->n_descsz, 4);
+
+	return PTR_ADD(buf, len);
+}
+
+/*
+ * Initialize prstatus note
+ */
+static void *nt_prstatus(void *ptr, struct save_area *sa)
+{
+	struct elf_prstatus nt_prstatus;
+	static int cpu_nr = 1;
+
+	memset(&nt_prstatus, 0, sizeof(nt_prstatus));
+	memcpy(&nt_prstatus.pr_reg.gprs, sa->gp_regs, sizeof(sa->gp_regs));
+	memcpy(&nt_prstatus.pr_reg.psw, sa->psw, sizeof(sa->psw));
+	memcpy(&nt_prstatus.pr_reg.acrs, sa->acc_regs, sizeof(sa->acc_regs));
+	nt_prstatus.pr_pid = cpu_nr;
+	cpu_nr++;
+
+	return nt_init(ptr, NT_PRSTATUS, &nt_prstatus, sizeof(nt_prstatus),
+			 "CORE");
+}
+
+/*
+ * Initialize fpregset (floating point) note
+ */
+static void *nt_fpregset(void *ptr, struct save_area *sa)
+{
+	elf_fpregset_t nt_fpregset;
+
+	memset(&nt_fpregset, 0, sizeof(nt_fpregset));
+	memcpy(&nt_fpregset.fpc, &sa->fp_ctrl_reg, sizeof(sa->fp_ctrl_reg));
+	memcpy(&nt_fpregset.fprs, &sa->fp_regs, sizeof(sa->fp_regs));
+
+	return nt_init(ptr, NT_PRFPREG, &nt_fpregset, sizeof(nt_fpregset),
+		       "CORE");
+}
+
+/*
+ * Initialize timer note
+ */
+static void *nt_s390_timer(void *ptr, struct save_area *sa)
+{
+	return nt_init(ptr, NT_S390_TIMER, &sa->timer, sizeof(sa->timer),
+			 KEXEC_CORE_NOTE_NAME);
+}
+
+/*
+ * Initialize TOD clock comparator note
+ */
+static void *nt_s390_tod_cmp(void *ptr, struct save_area *sa)
+{
+	return nt_init(ptr, NT_S390_TODCMP, &sa->clk_cmp,
+		       sizeof(sa->clk_cmp), KEXEC_CORE_NOTE_NAME);
+}
+
+/*
+ * Initialize TOD programmable register note
+ */
+static void *nt_s390_tod_preg(void *ptr, struct save_area *sa)
+{
+	return nt_init(ptr, NT_S390_TODPREG, &sa->tod_reg,
+		       sizeof(sa->tod_reg), KEXEC_CORE_NOTE_NAME);
+}
+
+/*
+ * Initialize control register note
+ */
+static void *nt_s390_ctrs(void *ptr, struct save_area *sa)
+{
+	return nt_init(ptr, NT_S390_CTRS, &sa->ctrl_regs,
+		       sizeof(sa->ctrl_regs), KEXEC_CORE_NOTE_NAME);
+}
+
+/*
+ * Initialize prefix register note
+ */
+static void *nt_s390_prefix(void *ptr, struct save_area *sa)
+{
+	return nt_init(ptr, NT_S390_PREFIX, &sa->pref_reg,
+			 sizeof(sa->pref_reg), KEXEC_CORE_NOTE_NAME);
+}
+
+/*
+ * Initialize vxrs high note (full 128 bit VX registers 16-31)
+ */
+static void *nt_s390_vx_high(void *ptr, __vector128 *vx_regs)
+{
+	return nt_init(ptr, NT_S390_VXRS_HIGH, &vx_regs[16],
+		       16 * sizeof(__vector128), KEXEC_CORE_NOTE_NAME);
+}
+
+/*
+ * Initialize vxrs low note (lower halves of VX registers 0-15)
+ */
+static void *nt_s390_vx_low(void *ptr, __vector128 *vx_regs)
+{
+	Elf64_Nhdr *note;
+	u64 len;
+	int i;
+
+	note = (Elf64_Nhdr *)ptr;
+	note->n_namesz = strlen(KEXEC_CORE_NOTE_NAME) + 1;
+	note->n_descsz = 16 * 8;
+	note->n_type = NT_S390_VXRS_LOW;
+	len = sizeof(Elf64_Nhdr);
+
+	memcpy(ptr + len, KEXEC_CORE_NOTE_NAME, note->n_namesz);
+	len = roundup(len + note->n_namesz, 4);
+
+	ptr += len;
+	/* Copy lower halves of SIMD registers 0-15 */
+	for (i = 0; i < 16; i++) {
+		memcpy(ptr, &vx_regs[i].u[2], 8);
+		ptr += 8;
+	}
+	return ptr;
+}
+
+/*
+ * Fill ELF notes for one CPU with save area registers
+ */
+void *fill_cpu_elf_notes(void *ptr, struct save_area *sa, __vector128 *vx_regs)
+{
+	ptr = nt_prstatus(ptr, sa);
+	ptr = nt_fpregset(ptr, sa);
+	ptr = nt_s390_timer(ptr, sa);
+	ptr = nt_s390_tod_cmp(ptr, sa);
+	ptr = nt_s390_tod_preg(ptr, sa);
+	ptr = nt_s390_ctrs(ptr, sa);
+	ptr = nt_s390_prefix(ptr, sa);
+	if (MACHINE_HAS_VX && vx_regs) {
+		ptr = nt_s390_vx_low(ptr, vx_regs);
+		ptr = nt_s390_vx_high(ptr, vx_regs);
+	}
+	return ptr;
+}
+
+/*
+ * Initialize prpsinfo note (new kernel)
+ */
+static void *nt_prpsinfo(void *ptr)
+{
+	struct elf_prpsinfo prpsinfo;
+
+	memset(&prpsinfo, 0, sizeof(prpsinfo));
+	prpsinfo.pr_sname = 'R';
+	strcpy(prpsinfo.pr_fname, "vmlinux");
+	return nt_init(ptr, NT_PRPSINFO, &prpsinfo, sizeof(prpsinfo),
+		       KEXEC_CORE_NOTE_NAME);
+}
+
+/*
+ * Get vmcoreinfo using lowcore->vmcore_info (new kernel)
+ */
+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 NULL;
+	memset(nt_name, 0, sizeof(nt_name));
+	if (copy_from_oldmem(&note, addr, sizeof(note)))
+		return NULL;
+	if (copy_from_oldmem(nt_name, addr + sizeof(note), sizeof(nt_name) - 1))
+		return NULL;
+	if (strcmp(nt_name, "VMCOREINFO") != 0)
+		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;
+	return nt_init(ptr, 0, vmcoreinfo, size, "VMCOREINFO");
+}
+
+/*
+ * Initialize ELF header (new kernel)
+ */
+static void *ehdr_init(Elf64_Ehdr *ehdr, int mem_chunk_cnt)
+{
+	memset(ehdr, 0, sizeof(*ehdr));
+	memcpy(ehdr->e_ident, ELFMAG, SELFMAG);
+	ehdr->e_ident[EI_CLASS] = ELFCLASS64;
+	ehdr->e_ident[EI_DATA] = ELFDATA2MSB;
+	ehdr->e_ident[EI_VERSION] = EV_CURRENT;
+	memset(ehdr->e_ident + EI_PAD, 0, EI_NIDENT - EI_PAD);
+	ehdr->e_type = ET_CORE;
+	ehdr->e_machine = EM_S390;
+	ehdr->e_version = EV_CURRENT;
+	ehdr->e_phoff = sizeof(Elf64_Ehdr);
+	ehdr->e_ehsize = sizeof(Elf64_Ehdr);
+	ehdr->e_phentsize = sizeof(Elf64_Phdr);
+	ehdr->e_phnum = mem_chunk_cnt + 1;
+	return ehdr + 1;
+}
+
+/*
+ * Return CPU count for ELF header (new kernel)
+ */
+static int get_cpu_cnt(void)
+{
+	int i, cpus = 0;
+
+	for (i = 0; i < dump_save_areas.count; i++) {
+		if (dump_save_areas.areas[i]->sa.pref_reg == 0)
+			continue;
+		cpus++;
+	}
+	return cpus;
+}
+
+/*
+ * Return memory chunk count for ELF header (new kernel)
+ */
+static int get_mem_chunk_cnt(void)
+{
+	int cnt = 0;
+	u64 idx;
+
+	for_each_dump_mem_range(idx, NUMA_NO_NODE, NULL, NULL, NULL)
+		cnt++;
+	return cnt;
+}
+
+/*
+ * Initialize ELF loads (new kernel)
+ */
+static void loads_init(Elf64_Phdr *phdr, u64 loads_offset)
+{
+	phys_addr_t start, end;
+	u64 idx;
+
+	for_each_dump_mem_range(idx, NUMA_NO_NODE, &start, &end, NULL) {
+		phdr->p_filesz = end - start;
+		phdr->p_type = PT_LOAD;
+		phdr->p_offset = start;
+		phdr->p_vaddr = start;
+		phdr->p_paddr = start;
+		phdr->p_memsz = end - start;
+		phdr->p_flags = PF_R | PF_W | PF_X;
+		phdr->p_align = PAGE_SIZE;
+		phdr++;
+	}
+}
+
+/*
+ * Initialize notes (new kernel)
+ */
+static void *notes_init(Elf64_Phdr *phdr, void *ptr, u64 notes_offset)
+{
+	struct save_area_ext *sa_ext;
+	void *ptr_start = ptr;
+	int i;
+
+	ptr = nt_prpsinfo(ptr);
+
+	for (i = 0; i < dump_save_areas.count; i++) {
+		sa_ext = dump_save_areas.areas[i];
+		if (sa_ext->sa.pref_reg == 0)
+			continue;
+		ptr = fill_cpu_elf_notes(ptr, &sa_ext->sa, sa_ext->vx_regs);
+	}
+	ptr = nt_vmcoreinfo(ptr);
+	memset(phdr, 0, sizeof(*phdr));
+	phdr->p_type = PT_NOTE;
+	phdr->p_offset = notes_offset;
+	phdr->p_filesz = (unsigned long) PTR_SUB(ptr, ptr_start);
+	phdr->p_memsz = phdr->p_filesz;
+	return ptr;
+}
+
+/*
+ * Create ELF core header (new kernel)
+ */
+int elfcorehdr_alloc(unsigned long long *addr, unsigned long long *size)
+{
+	Elf64_Phdr *phdr_notes, *phdr_loads;
+	int mem_chunk_cnt;
+	void *ptr, *hdr;
+	u32 alloc_size;
+	u64 hdr_off;
+
+	/* If we are not in kdump or zfcpdump mode return */
+	if (!OLDMEM_BASE && ipl_info.type != IPL_TYPE_FCP_DUMP)
+		return 0;
+	/* If elfcorehdr= has been passed via cmdline, we use that one */
+	if (elfcorehdr_addr != ELFCORE_ADDR_MAX)
+		return 0;
+	/* If we cannot get HSA size for zfcpdump return error */
+	if (ipl_info.type == IPL_TYPE_FCP_DUMP && !sclp_get_hsa_size())
+		return -ENODEV;
+
+	/* For kdump, exclude previous crashkernel memory */
+	if (OLDMEM_BASE) {
+		oldmem_region.base = OLDMEM_BASE;
+		oldmem_region.size = OLDMEM_SIZE;
+		oldmem_type.total_size = OLDMEM_SIZE;
+	}
+
+	mem_chunk_cnt = get_mem_chunk_cnt();
+
+	alloc_size = 0x1000 + get_cpu_cnt() * 0x4a0 +
+		mem_chunk_cnt * sizeof(Elf64_Phdr);
+	hdr = kzalloc_panic(alloc_size);
+	/* Init elf header */
+	ptr = ehdr_init(hdr, mem_chunk_cnt);
+	/* Init program headers */
+	phdr_notes = ptr;
+	ptr = PTR_ADD(ptr, sizeof(Elf64_Phdr));
+	phdr_loads = ptr;
+	ptr = PTR_ADD(ptr, sizeof(Elf64_Phdr) * mem_chunk_cnt);
+	/* Init notes */
+	hdr_off = PTR_DIFF(ptr, hdr);
+	ptr = notes_init(phdr_notes, ptr, ((unsigned long) hdr) + hdr_off);
+	/* Init loads */
+	hdr_off = PTR_DIFF(ptr, hdr);
+	loads_init(phdr_loads, hdr_off);
+	*addr = (unsigned long long) hdr;
+	elfcorehdr_newmem = hdr;
+	*size = (unsigned long long) hdr_off;
+	BUG_ON(elfcorehdr_size > alloc_size);
+	return 0;
+}
+
+/*
+ * Free ELF core header (new kernel)
+ */
+void elfcorehdr_free(unsigned long long addr)
+{
+	if (!elfcorehdr_newmem)
+		return;
+	kfree((void *)(unsigned long)addr);
+}
+
+/*
+ * Read from ELF header
+ */
+ssize_t elfcorehdr_read(char *buf, size_t count, u64 *ppos)
+{
+	void *src = (void *)(unsigned long)*ppos;
+
+	src = elfcorehdr_newmem ? src : src - OLDMEM_BASE;
+	memcpy(buf, src, count);
+	*ppos += count;
+	return count;
+}
+
+/*
+ * Read from ELF notes data
+ */
+ssize_t elfcorehdr_read_notes(char *buf, size_t count, u64 *ppos)
+{
+	void *src = (void *)(unsigned long)*ppos;
+	int rc;
+
+	if (elfcorehdr_newmem) {
+		memcpy(buf, src, count);
+	} else {
+		rc = copy_from_oldmem(buf, src, count);
+		if (rc)
+			return rc;
+	}
+	*ppos += count;
+	return count;
+}
diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c
new file mode 100644
index 000000000..c1f21aca7
--- /dev/null
+++ b/arch/s390/kernel/debug.c
@@ -0,0 +1,1540 @@
+/*
+ *   S/390 debug facility
+ *
+ *    Copyright IBM Corp. 1999, 2012
+ *
+ *    Author(s): Michael Holzheu (holzheu@de.ibm.com),
+ *               Holger Smolinski (Holger.Smolinski@de.ibm.com)
+ *
+ *    Bugreports to: <Linux390@de.ibm.com>
+ */
+
+#define KMSG_COMPONENT "s390dbf"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
+#include <linux/stddef.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/slab.h>
+#include <linux/ctype.h>
+#include <linux/string.h>
+#include <linux/sysctl.h>
+#include <asm/uaccess.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/fs.h>
+#include <linux/debugfs.h>
+
+#include <asm/debug.h>
+
+#define DEBUG_PROLOG_ENTRY -1
+
+#define ALL_AREAS 0 /* copy all debug areas */
+#define NO_AREAS  1 /* copy no debug areas */
+
+/* typedefs */
+
+typedef struct file_private_info {
+	loff_t offset;			/* offset of last read in file */
+	int    act_area;                /* number of last formated area */
+	int    act_page;                /* act page in given area */
+	int    act_entry;               /* last formated entry (offset */
+                                        /* relative to beginning of last */
+                                        /* formated page) */
+	size_t act_entry_offset;        /* up to this offset we copied */
+					/* in last read the last formated */
+					/* entry to userland */
+	char   temp_buf[2048];		/* buffer for output */
+	debug_info_t *debug_info_org;   /* original debug information */
+	debug_info_t *debug_info_snap;	/* snapshot of debug information */
+	struct debug_view *view;	/* used view of debug info */
+} file_private_info_t;
+
+typedef struct
+{
+	char *string;
+	/* 
+	 * This assumes that all args are converted into longs 
+	 * on L/390 this is the case for all types of parameter 
+	 * except of floats, and long long (32 bit) 
+	 *
+	 */
+	long args[0];
+} debug_sprintf_entry_t;
+
+
+/* internal function prototyes */
+
+static int debug_init(void);
+static ssize_t debug_output(struct file *file, char __user *user_buf,
+			size_t user_len, loff_t * offset);
+static ssize_t debug_input(struct file *file, const char __user *user_buf,
+			size_t user_len, loff_t * offset);
+static int debug_open(struct inode *inode, struct file *file);
+static int debug_close(struct inode *inode, struct file *file);
+static debug_info_t *debug_info_create(const char *name, int pages_per_area,
+			int nr_areas, int buf_size, umode_t mode);
+static void debug_info_get(debug_info_t *);
+static void debug_info_put(debug_info_t *);
+static int debug_prolog_level_fn(debug_info_t * id,
+			struct debug_view *view, char *out_buf);
+static int debug_input_level_fn(debug_info_t * id, struct debug_view *view,
+			struct file *file, const char __user *user_buf,
+			size_t user_buf_size, loff_t * offset);
+static int debug_prolog_pages_fn(debug_info_t * id,
+			struct debug_view *view, char *out_buf);
+static int debug_input_pages_fn(debug_info_t * id, struct debug_view *view,
+			struct file *file, const char __user *user_buf,
+			size_t user_buf_size, loff_t * offset);
+static int debug_input_flush_fn(debug_info_t * id, struct debug_view *view,
+			struct file *file, const char __user *user_buf,
+			size_t user_buf_size, loff_t * offset);
+static int debug_hex_ascii_format_fn(debug_info_t * id, struct debug_view *view,
+			char *out_buf, const char *in_buf);
+static int debug_raw_format_fn(debug_info_t * id,
+			struct debug_view *view, char *out_buf,
+			const char *in_buf);
+static int debug_raw_header_fn(debug_info_t * id, struct debug_view *view,
+			int area, debug_entry_t * entry, char *out_buf);
+
+static int debug_sprintf_format_fn(debug_info_t * id, struct debug_view *view,
+			char *out_buf, debug_sprintf_entry_t *curr_event);
+
+/* globals */
+
+struct debug_view debug_raw_view = {
+	"raw",
+	NULL,
+	&debug_raw_header_fn,
+	&debug_raw_format_fn,
+	NULL,
+	NULL
+};
+EXPORT_SYMBOL(debug_raw_view);
+
+struct debug_view debug_hex_ascii_view = {
+	"hex_ascii",
+	NULL,
+	&debug_dflt_header_fn,
+	&debug_hex_ascii_format_fn,
+	NULL,
+	NULL
+};
+EXPORT_SYMBOL(debug_hex_ascii_view);
+
+static struct debug_view debug_level_view = {
+	"level",
+	&debug_prolog_level_fn,
+	NULL,
+	NULL,
+	&debug_input_level_fn,
+	NULL
+};
+
+static struct debug_view debug_pages_view = {
+	"pages",
+	&debug_prolog_pages_fn,
+	NULL,
+	NULL,
+	&debug_input_pages_fn,
+	NULL
+};
+
+static struct debug_view debug_flush_view = {
+        "flush",
+        NULL,
+        NULL,
+        NULL,
+        &debug_input_flush_fn,
+        NULL
+};
+
+struct debug_view debug_sprintf_view = {
+	"sprintf",
+	NULL,
+	&debug_dflt_header_fn,
+	(debug_format_proc_t*)&debug_sprintf_format_fn,
+	NULL,
+	NULL
+};
+EXPORT_SYMBOL(debug_sprintf_view);
+
+/* used by dump analysis tools to determine version of debug feature */
+static unsigned int __used debug_feature_version = __DEBUG_FEATURE_VERSION;
+
+/* static globals */
+
+static debug_info_t *debug_area_first = NULL;
+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,
+	.read    = debug_output,
+	.write   = debug_input,
+	.open    = debug_open,
+	.release = debug_close,
+	.llseek  = no_llseek,
+};
+
+static struct dentry *debug_debugfs_root_entry;
+
+/* functions */
+
+/*
+ * debug_areas_alloc
+ * - Debug areas are implemented as a threedimensonal array:
+ *   areas[areanumber][pagenumber][pageoffset]
+ */
+
+static debug_entry_t***
+debug_areas_alloc(int pages_per_area, int nr_areas)
+{
+	debug_entry_t*** areas;
+	int i,j;
+
+	areas = kmalloc(nr_areas *
+					sizeof(debug_entry_t**),
+					GFP_KERNEL);
+	if (!areas)
+		goto fail_malloc_areas;
+	for (i = 0; i < nr_areas; i++) {
+		areas[i] = kmalloc(pages_per_area *
+				sizeof(debug_entry_t*),GFP_KERNEL);
+		if (!areas[i]) {
+			goto fail_malloc_areas2;
+		}
+		for(j = 0; j < pages_per_area; j++) {
+			areas[i][j] = kzalloc(PAGE_SIZE, GFP_KERNEL);
+			if(!areas[i][j]) {
+				for(j--; j >=0 ; j--) {
+					kfree(areas[i][j]);
+				}
+				kfree(areas[i]);
+				goto fail_malloc_areas2;
+			}
+		}
+	}
+	return areas;
+
+fail_malloc_areas2:
+	for(i--; i >= 0; i--){
+		for(j=0; j < pages_per_area;j++){
+			kfree(areas[i][j]);
+		}
+		kfree(areas[i]);
+	}
+	kfree(areas);
+fail_malloc_areas:
+	return NULL;
+
+}
+
+
+/*
+ * debug_info_alloc
+ * - alloc new debug-info
+ */
+
+static debug_info_t*
+debug_info_alloc(const char *name, int pages_per_area, int nr_areas,
+		 int buf_size, int level, int mode)
+{
+	debug_info_t* rc;
+
+	/* alloc everything */
+
+	rc = kmalloc(sizeof(debug_info_t), GFP_KERNEL);
+	if(!rc)
+		goto fail_malloc_rc;
+	rc->active_entries = kcalloc(nr_areas, sizeof(int), GFP_KERNEL);
+	if(!rc->active_entries)
+		goto fail_malloc_active_entries;
+	rc->active_pages = kcalloc(nr_areas, sizeof(int), GFP_KERNEL);
+	if(!rc->active_pages)
+		goto fail_malloc_active_pages;
+	if((mode == ALL_AREAS) && (pages_per_area != 0)){
+		rc->areas = debug_areas_alloc(pages_per_area, nr_areas);
+		if(!rc->areas)
+			goto fail_malloc_areas;
+	} else {
+		rc->areas = NULL;
+	}
+
+	/* initialize members */
+
+	spin_lock_init(&rc->lock);
+	rc->pages_per_area = pages_per_area;
+	rc->nr_areas       = nr_areas;
+	rc->active_area    = 0;
+	rc->level          = level;
+	rc->buf_size       = buf_size;
+	rc->entry_size     = sizeof(debug_entry_t) + buf_size;
+	strlcpy(rc->name, name, sizeof(rc->name));
+	memset(rc->views, 0, DEBUG_MAX_VIEWS * sizeof(struct debug_view *));
+	memset(rc->debugfs_entries, 0 ,DEBUG_MAX_VIEWS *
+		sizeof(struct dentry*));
+	atomic_set(&(rc->ref_count), 0);
+
+	return rc;
+
+fail_malloc_areas:
+	kfree(rc->active_pages);
+fail_malloc_active_pages:
+	kfree(rc->active_entries);
+fail_malloc_active_entries:
+	kfree(rc);
+fail_malloc_rc:
+	return NULL;
+}
+
+/*
+ * debug_areas_free
+ * - free all debug areas
+ */
+
+static void
+debug_areas_free(debug_info_t* db_info)
+{
+	int i,j;
+
+	if(!db_info->areas)
+		return;
+	for (i = 0; i < db_info->nr_areas; i++) {
+		for(j = 0; j < db_info->pages_per_area; j++) {
+			kfree(db_info->areas[i][j]);
+		}
+		kfree(db_info->areas[i]);
+	}
+	kfree(db_info->areas);
+	db_info->areas = NULL;
+}
+
+/*
+ * debug_info_free
+ * - free memory debug-info
+ */
+
+static void
+debug_info_free(debug_info_t* db_info){
+	debug_areas_free(db_info);
+	kfree(db_info->active_entries);
+	kfree(db_info->active_pages);
+	kfree(db_info);
+}
+
+/*
+ * debug_info_create
+ * - create new debug-info
+ */
+
+static debug_info_t*
+debug_info_create(const char *name, int pages_per_area, int nr_areas,
+		  int buf_size, umode_t mode)
+{
+	debug_info_t* rc;
+
+        rc = debug_info_alloc(name, pages_per_area, nr_areas, buf_size,
+				DEBUG_DEFAULT_LEVEL, ALL_AREAS);
+        if(!rc) 
+		goto out;
+
+	rc->mode = mode & ~S_IFMT;
+
+	/* create root directory */
+        rc->debugfs_root_entry = debugfs_create_dir(rc->name,
+					debug_debugfs_root_entry);
+
+	/* append new element to linked list */
+        if (!debug_area_first) {
+                /* first element in list */
+                debug_area_first = rc;
+                rc->prev = NULL;
+        } else {
+                /* append element to end of list */
+                debug_area_last->next = rc;
+                rc->prev = debug_area_last;
+        }
+        debug_area_last = rc;
+        rc->next = NULL;
+
+	debug_info_get(rc);
+out:
+	return rc;
+}
+
+/*
+ * debug_info_copy
+ * - copy debug-info
+ */
+
+static debug_info_t*
+debug_info_copy(debug_info_t* in, int mode)
+{
+        int i,j;
+        debug_info_t* rc;
+        unsigned long flags;
+
+	/* get a consistent copy of the debug areas */
+	do {
+		rc = debug_info_alloc(in->name, in->pages_per_area,
+			in->nr_areas, in->buf_size, in->level, mode);
+		spin_lock_irqsave(&in->lock, flags);
+		if(!rc)
+			goto out;
+		/* has something changed in the meantime ? */
+		if((rc->pages_per_area == in->pages_per_area) &&
+		   (rc->nr_areas == in->nr_areas)) {
+			break;
+		}
+		spin_unlock_irqrestore(&in->lock, flags);
+		debug_info_free(rc);
+	} while (1);
+
+	if (mode == NO_AREAS)
+                goto out;
+
+        for(i = 0; i < in->nr_areas; i++){
+		for(j = 0; j < in->pages_per_area; j++) {
+			memcpy(rc->areas[i][j], in->areas[i][j],PAGE_SIZE);
+		}
+        }
+out:
+        spin_unlock_irqrestore(&in->lock, flags);
+        return rc;
+}
+
+/*
+ * debug_info_get
+ * - increments reference count for debug-info
+ */
+
+static void
+debug_info_get(debug_info_t * db_info)
+{
+	if (db_info)
+		atomic_inc(&db_info->ref_count);
+}
+
+/*
+ * debug_info_put:
+ * - decreases reference count for debug-info and frees it if necessary
+ */
+
+static void
+debug_info_put(debug_info_t *db_info)
+{
+	int i;
+
+	if (!db_info)
+		return;
+	if (atomic_dec_and_test(&db_info->ref_count)) {
+		for (i = 0; i < DEBUG_MAX_VIEWS; i++) {
+			if (!db_info->views[i])
+				continue;
+			debugfs_remove(db_info->debugfs_entries[i]);
+		}
+		debugfs_remove(db_info->debugfs_root_entry);
+		if(db_info == debug_area_first)
+			debug_area_first = db_info->next;
+		if(db_info == debug_area_last)
+			debug_area_last = db_info->prev;
+		if(db_info->prev) db_info->prev->next = db_info->next;
+		if(db_info->next) db_info->next->prev = db_info->prev;
+		debug_info_free(db_info);
+	}
+}
+
+/*
+ * debug_format_entry:
+ * - format one debug entry and return size of formated data
+ */
+
+static int
+debug_format_entry(file_private_info_t *p_info)
+{
+	debug_info_t *id_snap   = p_info->debug_info_snap;
+	struct debug_view *view = p_info->view;
+	debug_entry_t *act_entry;
+	size_t len = 0;
+	if(p_info->act_entry == DEBUG_PROLOG_ENTRY){
+		/* print prolog */
+        	if (view->prolog_proc)
+                	len += view->prolog_proc(id_snap,view,p_info->temp_buf);
+		goto out;
+	}
+	if (!id_snap->areas) /* this is true, if we have a prolog only view */
+		goto out;    /* or if 'pages_per_area' is 0 */
+	act_entry = (debug_entry_t *) ((char*)id_snap->areas[p_info->act_area]
+				[p_info->act_page] + p_info->act_entry);
+                        
+	if (act_entry->id.stck == 0LL)
+			goto out;  /* empty entry */
+	if (view->header_proc)
+		len += view->header_proc(id_snap, view, p_info->act_area,
+					act_entry, p_info->temp_buf + len);
+	if (view->format_proc)
+		len += view->format_proc(id_snap, view, p_info->temp_buf + len,
+						DEBUG_DATA(act_entry));
+out:
+        return len;
+}
+
+/*
+ * debug_next_entry:
+ * - goto next entry in p_info
+ */
+
+static inline int
+debug_next_entry(file_private_info_t *p_info)
+{
+	debug_info_t *id;
+
+	id = p_info->debug_info_snap;
+	if(p_info->act_entry == DEBUG_PROLOG_ENTRY){
+		p_info->act_entry = 0;
+		p_info->act_page  = 0;
+		goto out;
+	}
+	if(!id->areas)
+		return 1;
+	p_info->act_entry += id->entry_size;
+	/* switch to next page, if we reached the end of the page  */
+	if (p_info->act_entry > (PAGE_SIZE - id->entry_size)){
+		/* next page */
+		p_info->act_entry = 0;
+		p_info->act_page += 1;
+		if((p_info->act_page % id->pages_per_area) == 0) {
+			/* next area */
+        		p_info->act_area++;
+			p_info->act_page=0;
+		}
+        	if(p_info->act_area >= id->nr_areas)
+			return 1;
+	}
+out:
+	return 0;	
+}
+
+/*
+ * debug_output:
+ * - called for user read()
+ * - copies formated debug entries to the user buffer
+ */
+
+static ssize_t
+debug_output(struct file *file,		/* file descriptor */
+	    char __user *user_buf,	/* user buffer */
+	    size_t  len,		/* length of buffer */
+	    loff_t *offset)		/* offset in the file */
+{
+	size_t count = 0;
+	size_t entry_offset;
+	file_private_info_t *p_info;
+
+	p_info = ((file_private_info_t *) file->private_data);
+	if (*offset != p_info->offset) 
+		return -EPIPE;
+	if(p_info->act_area >= p_info->debug_info_snap->nr_areas)
+		return 0;
+	entry_offset = p_info->act_entry_offset;
+	while(count < len){
+		int formatted_line_size;
+		int formatted_line_residue;
+		int user_buf_residue;
+		size_t copy_size;
+
+		formatted_line_size = debug_format_entry(p_info);
+		formatted_line_residue = formatted_line_size - entry_offset;
+		user_buf_residue = len-count;
+		copy_size = min(user_buf_residue, formatted_line_residue);
+		if(copy_size){
+			if (copy_to_user(user_buf + count, p_info->temp_buf
+					+ entry_offset, copy_size))
+				return -EFAULT;
+			count += copy_size;
+			entry_offset += copy_size;
+		}
+		if(copy_size == formatted_line_residue){
+			entry_offset = 0;
+			if(debug_next_entry(p_info))
+				goto out;
+		}
+	}
+out:
+	p_info->offset           = *offset + count;
+	p_info->act_entry_offset = entry_offset;
+	*offset = p_info->offset;
+	return count;
+}
+
+/*
+ * debug_input:
+ * - called for user write()
+ * - calls input function of view
+ */
+
+static ssize_t
+debug_input(struct file *file, const char __user *user_buf, size_t length,
+		loff_t *offset)
+{
+	int rc = 0;
+	file_private_info_t *p_info;
+
+	mutex_lock(&debug_mutex);
+	p_info = ((file_private_info_t *) file->private_data);
+	if (p_info->view->input_proc)
+		rc = p_info->view->input_proc(p_info->debug_info_org,
+					      p_info->view, file, user_buf,
+					      length, offset);
+	else
+		rc = -EPERM;
+	mutex_unlock(&debug_mutex);
+	return rc;		/* number of input characters */
+}
+
+/*
+ * debug_open:
+ * - called for user open()
+ * - copies formated output to private_data area of the file
+ *   handle
+ */
+
+static int
+debug_open(struct inode *inode, struct file *file)
+{
+	int i, rc = 0;
+	file_private_info_t *p_info;
+	debug_info_t *debug_info, *debug_info_snapshot;
+
+	mutex_lock(&debug_mutex);
+	debug_info = file_inode(file)->i_private;
+	/* find debug view */
+	for (i = 0; i < DEBUG_MAX_VIEWS; i++) {
+		if (!debug_info->views[i])
+			continue;
+		else if (debug_info->debugfs_entries[i] ==
+			 file->f_path.dentry) {
+			goto found;	/* found view ! */
+		}
+	}
+	/* no entry found */
+	rc = -EINVAL;
+	goto out;
+
+found:
+
+	/* Make snapshot of current debug areas to get it consistent.     */
+	/* To copy all the areas is only needed, if we have a view which  */
+	/* formats the debug areas. */
+
+	if(!debug_info->views[i]->format_proc &&
+		!debug_info->views[i]->header_proc){
+		debug_info_snapshot = debug_info_copy(debug_info, NO_AREAS);
+	} else {
+		debug_info_snapshot = debug_info_copy(debug_info, ALL_AREAS);
+	}
+
+	if(!debug_info_snapshot){
+		rc = -ENOMEM;
+		goto out;
+	}
+	p_info = kmalloc(sizeof(file_private_info_t),
+						GFP_KERNEL);
+	if(!p_info){
+		debug_info_free(debug_info_snapshot);
+		rc = -ENOMEM;
+		goto out;
+	}
+	p_info->offset = 0;
+	p_info->debug_info_snap = debug_info_snapshot;
+	p_info->debug_info_org  = debug_info;
+	p_info->view = debug_info->views[i];
+	p_info->act_area = 0;
+	p_info->act_page = 0;
+	p_info->act_entry = DEBUG_PROLOG_ENTRY;
+	p_info->act_entry_offset = 0;
+	file->private_data = p_info;
+	debug_info_get(debug_info);
+	nonseekable_open(inode, file);
+out:
+	mutex_unlock(&debug_mutex);
+	return rc;
+}
+
+/*
+ * debug_close:
+ * - called for user close()
+ * - deletes  private_data area of the file handle
+ */
+
+static int
+debug_close(struct inode *inode, struct file *file)
+{
+	file_private_info_t *p_info;
+	p_info = (file_private_info_t *) file->private_data;
+	if(p_info->debug_info_snap)
+		debug_info_free(p_info->debug_info_snap);
+	debug_info_put(p_info->debug_info_org);
+	kfree(file->private_data);
+	return 0;		/* success */
+}
+
+/*
+ * debug_register_mode:
+ * - Creates and initializes debug area for the caller
+ *   The mode parameter allows to specify access rights for the s390dbf files
+ * - Returns handle for debug area
+ */
+
+debug_info_t *debug_register_mode(const char *name, int pages_per_area,
+				  int nr_areas, int buf_size, umode_t mode,
+				  uid_t uid, gid_t gid)
+{
+	debug_info_t *rc = NULL;
+
+	/* Since debugfs currently does not support uid/gid other than root, */
+	/* we do not allow gid/uid != 0 until we get support for that. */
+	if ((uid != 0) || (gid != 0))
+		pr_warning("Root becomes the owner of all s390dbf files "
+			   "in sysfs\n");
+	BUG_ON(!initialized);
+	mutex_lock(&debug_mutex);
+
+        /* create new debug_info */
+
+	rc = debug_info_create(name, pages_per_area, nr_areas, buf_size, mode);
+	if(!rc) 
+		goto out;
+	debug_register_view(rc, &debug_level_view);
+        debug_register_view(rc, &debug_flush_view);
+	debug_register_view(rc, &debug_pages_view);
+out:
+        if (!rc){
+		pr_err("Registering debug feature %s failed\n", name);
+        }
+	mutex_unlock(&debug_mutex);
+	return rc;
+}
+EXPORT_SYMBOL(debug_register_mode);
+
+/*
+ * debug_register:
+ * - creates and initializes debug area for the caller
+ * - returns handle for debug area
+ */
+
+debug_info_t *debug_register(const char *name, int pages_per_area,
+			     int nr_areas, int buf_size)
+{
+	return debug_register_mode(name, pages_per_area, nr_areas, buf_size,
+				   S_IRUSR | S_IWUSR, 0, 0);
+}
+EXPORT_SYMBOL(debug_register);
+
+/*
+ * debug_unregister:
+ * - give back debug area
+ */
+
+void
+debug_unregister(debug_info_t * id)
+{
+	if (!id)
+		goto out;
+	mutex_lock(&debug_mutex);
+	debug_info_put(id);
+	mutex_unlock(&debug_mutex);
+
+out:
+	return;
+}
+EXPORT_SYMBOL(debug_unregister);
+
+/*
+ * debug_set_size:
+ * - set area size (number of pages) and number of areas
+ */
+static int
+debug_set_size(debug_info_t* id, int nr_areas, int pages_per_area)
+{
+	unsigned long flags;
+	debug_entry_t *** new_areas;
+	int rc=0;
+
+	if(!id || (nr_areas <= 0) || (pages_per_area < 0))
+		return -EINVAL;
+	if(pages_per_area > 0){
+		new_areas = debug_areas_alloc(pages_per_area, nr_areas);
+		if(!new_areas) {
+			pr_info("Allocating memory for %i pages failed\n",
+				pages_per_area);
+			rc = -ENOMEM;
+			goto out;
+		}
+	} else {
+		new_areas = NULL;
+	}
+	spin_lock_irqsave(&id->lock,flags);
+	debug_areas_free(id);
+	id->areas = new_areas;
+	id->nr_areas = nr_areas;
+	id->pages_per_area = pages_per_area;
+	id->active_area = 0;
+	memset(id->active_entries,0,sizeof(int)*id->nr_areas);
+	memset(id->active_pages, 0, sizeof(int)*id->nr_areas);
+	spin_unlock_irqrestore(&id->lock,flags);
+	pr_info("%s: set new size (%i pages)\n" ,id->name, pages_per_area);
+out:
+	return rc;
+}
+
+/*
+ * debug_set_level:
+ * - set actual debug level
+ */
+
+void
+debug_set_level(debug_info_t* id, int new_level)
+{
+	unsigned long flags;
+	if(!id)
+		return;	
+	spin_lock_irqsave(&id->lock,flags);
+        if(new_level == DEBUG_OFF_LEVEL){
+                id->level = DEBUG_OFF_LEVEL;
+		pr_info("%s: switched off\n",id->name);
+        } else if ((new_level > DEBUG_MAX_LEVEL) || (new_level < 0)) {
+		pr_info("%s: level %i is out of range (%i - %i)\n",
+                        id->name, new_level, 0, DEBUG_MAX_LEVEL);
+        } else {
+                id->level = new_level;
+        }
+	spin_unlock_irqrestore(&id->lock,flags);
+}
+EXPORT_SYMBOL(debug_set_level);
+
+/*
+ * proceed_active_entry:
+ * - set active entry to next in the ring buffer
+ */
+
+static inline void
+proceed_active_entry(debug_info_t * id)
+{
+	if ((id->active_entries[id->active_area] += id->entry_size)
+	    > (PAGE_SIZE - id->entry_size)){
+		id->active_entries[id->active_area] = 0;
+		id->active_pages[id->active_area] =
+			(id->active_pages[id->active_area] + 1) %
+			id->pages_per_area;
+	}
+}
+
+/*
+ * proceed_active_area:
+ * - set active area to next in the ring buffer
+ */
+
+static inline void
+proceed_active_area(debug_info_t * id)
+{
+	id->active_area++;
+	id->active_area = id->active_area % id->nr_areas;
+}
+
+/*
+ * get_active_entry:
+ */
+
+static inline debug_entry_t*
+get_active_entry(debug_info_t * id)
+{
+	return (debug_entry_t *) (((char *) id->areas[id->active_area]
+					[id->active_pages[id->active_area]]) +
+					id->active_entries[id->active_area]);
+}
+
+/*
+ * debug_finish_entry:
+ * - set timestamp, caller address, cpu number etc.
+ */
+
+static inline void
+debug_finish_entry(debug_info_t * id, debug_entry_t* active, int level,
+			int exception)
+{
+	active->id.stck = get_tod_clock_fast();
+	active->id.fields.cpuid = smp_processor_id();
+	active->caller = __builtin_return_address(0);
+	active->id.fields.exception = exception;
+	active->id.fields.level     = level;
+	proceed_active_entry(id);
+	if(exception)
+		proceed_active_area(id);
+}
+
+static int debug_stoppable=1;
+static int debug_active=1;
+
+#define CTL_S390DBF_STOPPABLE 5678
+#define CTL_S390DBF_ACTIVE 5679
+
+/*
+ * proc handler for the running debug_active sysctl
+ * always allow read, allow write only if debug_stoppable is set or
+ * if debug_active is already off
+ */
+static int
+s390dbf_procactive(struct ctl_table *table, int write,
+                     void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	if (!write || debug_stoppable || !debug_active)
+		return proc_dointvec(table, write, buffer, lenp, ppos);
+	else
+		return 0;
+}
+
+
+static struct ctl_table s390dbf_table[] = {
+	{
+		.procname       = "debug_stoppable",
+		.data		= &debug_stoppable,
+		.maxlen		= sizeof(int),
+		.mode           = S_IRUGO | S_IWUSR,
+		.proc_handler   = proc_dointvec,
+	},
+	 {
+		.procname       = "debug_active",
+		.data		= &debug_active,
+		.maxlen		= sizeof(int),
+		.mode           = S_IRUGO | S_IWUSR,
+		.proc_handler   = s390dbf_procactive,
+	},
+	{ }
+};
+
+static struct ctl_table s390dbf_dir_table[] = {
+	{
+		.procname       = "s390dbf",
+		.maxlen         = 0,
+		.mode           = S_IRUGO | S_IXUGO,
+		.child          = s390dbf_table,
+	},
+	{ }
+};
+
+static struct ctl_table_header *s390dbf_sysctl_header;
+
+void
+debug_stop_all(void)
+{
+	if (debug_stoppable)
+		debug_active = 0;
+}
+EXPORT_SYMBOL(debug_stop_all);
+
+void debug_set_critical(void)
+{
+	debug_critical = 1;
+}
+
+/*
+ * debug_event_common:
+ * - write debug entry with given size
+ */
+
+debug_entry_t*
+debug_event_common(debug_info_t * id, int level, const void *buf, int len)
+{
+	unsigned long flags;
+	debug_entry_t *active;
+
+	if (!debug_active || !id->areas)
+		return NULL;
+	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));
+	debug_finish_entry(id, active, level, 0);
+	spin_unlock_irqrestore(&id->lock, flags);
+
+	return active;
+}
+EXPORT_SYMBOL(debug_event_common);
+
+/*
+ * debug_exception_common:
+ * - write debug entry with given size and switch to next debug area
+ */
+
+debug_entry_t
+*debug_exception_common(debug_info_t * id, int level, const void *buf, int len)
+{
+	unsigned long flags;
+	debug_entry_t *active;
+
+	if (!debug_active || !id->areas)
+		return NULL;
+	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));
+	debug_finish_entry(id, active, level, 1);
+	spin_unlock_irqrestore(&id->lock, flags);
+
+	return active;
+}
+EXPORT_SYMBOL(debug_exception_common);
+
+/*
+ * counts arguments in format string for sprintf view
+ */
+
+static inline int
+debug_count_numargs(char *string)
+{
+	int numargs=0;
+
+	while(*string) {
+		if(*string++=='%')
+			numargs++;
+	}
+	return(numargs);
+}
+
+/*
+ * debug_sprintf_event:
+ */
+
+debug_entry_t*
+__debug_sprintf_event(debug_info_t *id, int level, char *string, ...)
+{
+	va_list   ap;
+	int numargs,idx;
+	unsigned long flags;
+	debug_sprintf_entry_t *curr_event;
+	debug_entry_t *active;
+
+	if (!debug_active || !id->areas)
+		return NULL;
+	numargs=debug_count_numargs(string);
+
+	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);
+	curr_event->string=string;
+	for(idx=0;idx<min(numargs,(int)(id->buf_size / sizeof(long))-1);idx++)
+		curr_event->args[idx]=va_arg(ap,long);
+	va_end(ap);
+	debug_finish_entry(id, active, level, 0);
+	spin_unlock_irqrestore(&id->lock, flags);
+
+	return active;
+}
+EXPORT_SYMBOL(__debug_sprintf_event);
+
+/*
+ * debug_sprintf_exception:
+ */
+
+debug_entry_t*
+__debug_sprintf_exception(debug_info_t *id, int level, char *string, ...)
+{
+	va_list   ap;
+	int numargs,idx;
+	unsigned long flags;
+	debug_sprintf_entry_t *curr_event;
+	debug_entry_t *active;
+
+	if (!debug_active || !id->areas)
+		return NULL;
+
+	numargs=debug_count_numargs(string);
+
+	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);
+	curr_event->string=string;
+	for(idx=0;idx<min(numargs,(int)(id->buf_size / sizeof(long))-1);idx++)
+		curr_event->args[idx]=va_arg(ap,long);
+	va_end(ap);
+	debug_finish_entry(id, active, level, 1);
+	spin_unlock_irqrestore(&id->lock, flags);
+
+	return active;
+}
+EXPORT_SYMBOL(__debug_sprintf_exception);
+
+/*
+ * debug_register_view:
+ */
+
+int
+debug_register_view(debug_info_t * id, struct debug_view *view)
+{
+	int rc = 0;
+	int i;
+	unsigned long flags;
+	umode_t mode;
+	struct dentry *pde;
+
+	if (!id)
+		goto out;
+	mode = (id->mode | S_IFREG) & ~S_IXUGO;
+	if (!(view->prolog_proc || view->format_proc || view->header_proc))
+		mode &= ~(S_IRUSR | S_IRGRP | S_IROTH);
+	if (!view->input_proc)
+		mode &= ~(S_IWUSR | S_IWGRP | S_IWOTH);
+	pde = debugfs_create_file(view->name, mode, id->debugfs_root_entry,
+				id , &debug_file_ops);
+	if (!pde){
+		pr_err("Registering view %s/%s failed due to out of "
+		       "memory\n", id->name,view->name);
+		rc = -1;
+		goto out;
+	}
+	spin_lock_irqsave(&id->lock, flags);
+	for (i = 0; i < DEBUG_MAX_VIEWS; i++) {
+		if (!id->views[i])
+			break;
+	}
+	if (i == DEBUG_MAX_VIEWS) {
+		pr_err("Registering view %s/%s would exceed the maximum "
+		       "number of views %i\n", id->name, view->name, i);
+		rc = -1;
+	} else {
+		id->views[i] = view;
+		id->debugfs_entries[i] = pde;
+	}
+	spin_unlock_irqrestore(&id->lock, flags);
+	if (rc)
+		debugfs_remove(pde);
+out:
+	return rc;
+}
+EXPORT_SYMBOL(debug_register_view);
+
+/*
+ * debug_unregister_view:
+ */
+
+int
+debug_unregister_view(debug_info_t * id, struct debug_view *view)
+{
+	struct dentry *dentry = NULL;
+	unsigned long flags;
+	int i, rc = 0;
+
+	if (!id)
+		goto out;
+	spin_lock_irqsave(&id->lock, flags);
+	for (i = 0; i < DEBUG_MAX_VIEWS; i++) {
+		if (id->views[i] == view)
+			break;
+	}
+	if (i == DEBUG_MAX_VIEWS)
+		rc = -1;
+	else {
+		dentry = id->debugfs_entries[i];
+		id->views[i] = NULL;
+		id->debugfs_entries[i] = NULL;
+	}
+	spin_unlock_irqrestore(&id->lock, flags);
+	debugfs_remove(dentry);
+out:
+	return rc;
+}
+EXPORT_SYMBOL(debug_unregister_view);
+
+static inline char *
+debug_get_user_string(const char __user *user_buf, size_t user_len)
+{
+	char* buffer;
+
+	buffer = kmalloc(user_len + 1, GFP_KERNEL);
+	if (!buffer)
+		return ERR_PTR(-ENOMEM);
+	if (copy_from_user(buffer, user_buf, user_len) != 0) {
+		kfree(buffer);
+		return ERR_PTR(-EFAULT);
+	}
+	/* got the string, now strip linefeed. */
+	if (buffer[user_len - 1] == '\n')
+		buffer[user_len - 1] = 0;
+	else
+		buffer[user_len] = 0;
+        return buffer;
+}
+
+static inline int
+debug_get_uint(char *buf)
+{
+	int rc;
+
+	buf = skip_spaces(buf);
+	rc = simple_strtoul(buf, &buf, 10);
+	if(*buf){
+		rc = -EINVAL;
+	}
+	return rc;
+}
+
+/*
+ * functions for debug-views
+ ***********************************
+*/
+
+/*
+ * prints out actual debug level
+ */
+
+static int
+debug_prolog_pages_fn(debug_info_t * id,
+				 struct debug_view *view, char *out_buf)
+{
+	return sprintf(out_buf, "%i\n", id->pages_per_area);
+}
+
+/*
+ * reads new size (number of pages per debug area)
+ */
+
+static int
+debug_input_pages_fn(debug_info_t * id, struct debug_view *view,
+			struct file *file, const char __user *user_buf,
+			size_t user_len, loff_t * offset)
+{
+	char *str;
+	int rc,new_pages;
+
+	if (user_len > 0x10000)
+                user_len = 0x10000;
+	if (*offset != 0){
+		rc = -EPIPE;
+		goto out;
+	}
+	str = debug_get_user_string(user_buf,user_len);
+	if(IS_ERR(str)){
+		rc = PTR_ERR(str);
+		goto out;
+	}
+	new_pages = debug_get_uint(str);
+	if(new_pages < 0){
+		rc = -EINVAL;
+		goto free_str;
+	}
+	rc = debug_set_size(id,id->nr_areas, new_pages);
+	if(rc != 0){
+		rc = -EINVAL;
+		goto free_str;
+	}
+	rc = user_len;
+free_str:
+	kfree(str);
+out:
+	*offset += user_len;
+	return rc;		/* number of input characters */
+}
+
+/*
+ * prints out actual debug level
+ */
+
+static int
+debug_prolog_level_fn(debug_info_t * id, struct debug_view *view, char *out_buf)
+{
+	int rc = 0;
+
+	if(id->level == DEBUG_OFF_LEVEL) {
+		rc = sprintf(out_buf,"-\n");
+	}
+	else {
+		rc = sprintf(out_buf, "%i\n", id->level);
+	}
+	return rc;
+}
+
+/*
+ * reads new debug level
+ */
+
+static int
+debug_input_level_fn(debug_info_t * id, struct debug_view *view,
+			struct file *file, const char __user *user_buf,
+			size_t user_len, loff_t * offset)
+{
+	char *str;
+	int rc,new_level;
+
+	if (user_len > 0x10000)
+                user_len = 0x10000;
+	if (*offset != 0){
+		rc = -EPIPE;
+		goto out;
+	}
+	str = debug_get_user_string(user_buf,user_len);
+	if(IS_ERR(str)){
+		rc = PTR_ERR(str);
+		goto out;
+	}
+	if(str[0] == '-'){
+		debug_set_level(id, DEBUG_OFF_LEVEL);
+		rc = user_len;
+		goto free_str;
+	} else {
+		new_level = debug_get_uint(str);
+	}
+	if(new_level < 0) {
+		pr_warning("%s is not a valid level for a debug "
+			   "feature\n", str);
+		rc = -EINVAL;
+	} else {
+		debug_set_level(id, new_level);
+		rc = user_len;
+	}
+free_str:
+	kfree(str);
+out:
+	*offset += user_len;
+	return rc;		/* number of input characters */
+}
+
+
+/*
+ * flushes debug areas
+ */
+ 
+static void debug_flush(debug_info_t* id, int area)
+{
+        unsigned long flags;
+        int i,j;
+
+        if(!id || !id->areas)
+                return;
+        spin_lock_irqsave(&id->lock,flags);
+        if(area == DEBUG_FLUSH_ALL){
+                id->active_area = 0;
+                memset(id->active_entries, 0, id->nr_areas * sizeof(int));
+                for (i = 0; i < id->nr_areas; i++) {
+			id->active_pages[i] = 0;
+			for(j = 0; j < id->pages_per_area; j++) {
+                        	memset(id->areas[i][j], 0, PAGE_SIZE);
+			}
+		}
+        } else if(area >= 0 && area < id->nr_areas) {
+                id->active_entries[area] = 0;
+		id->active_pages[area] = 0;
+		for(i = 0; i < id->pages_per_area; i++) {
+                	memset(id->areas[area][i],0,PAGE_SIZE);
+		}
+        }
+        spin_unlock_irqrestore(&id->lock,flags);
+}
+
+/*
+ * view function: flushes debug areas 
+ */
+
+static int
+debug_input_flush_fn(debug_info_t * id, struct debug_view *view,
+			struct file *file, const char __user *user_buf,
+			size_t user_len, loff_t * offset)
+{
+        char input_buf[1];
+        int rc = user_len;
+
+	if (user_len > 0x10000)
+                user_len = 0x10000;
+        if (*offset != 0){
+		rc = -EPIPE;
+                goto out;
+	}
+        if (copy_from_user(input_buf, user_buf, 1)){
+                rc = -EFAULT;
+                goto out;
+        }
+        if(input_buf[0] == '-') { 
+                debug_flush(id, DEBUG_FLUSH_ALL);
+                goto out;
+        }
+        if (isdigit(input_buf[0])) {
+                int area = ((int) input_buf[0] - (int) '0');
+                debug_flush(id, area);
+                goto out;
+        }
+
+	pr_info("Flushing debug data failed because %c is not a valid "
+		 "area\n", input_buf[0]);
+
+out:
+        *offset += user_len;
+        return rc;              /* number of input characters */
+}
+
+/*
+ * prints debug header in raw format
+ */
+
+static int
+debug_raw_header_fn(debug_info_t * id, struct debug_view *view,
+			int area, debug_entry_t * entry, char *out_buf)
+{
+        int rc;
+
+	rc = sizeof(debug_entry_t);
+	memcpy(out_buf,entry,sizeof(debug_entry_t));
+        return rc;
+}
+
+/*
+ * prints debug data in raw format
+ */
+
+static int
+debug_raw_format_fn(debug_info_t * id, struct debug_view *view,
+			       char *out_buf, const char *in_buf)
+{
+	int rc;
+
+	rc = id->buf_size;
+	memcpy(out_buf, in_buf, id->buf_size);
+	return rc;
+}
+
+/*
+ * prints debug data in hex/ascii format
+ */
+
+static int
+debug_hex_ascii_format_fn(debug_info_t * id, struct debug_view *view,
+	    		  char *out_buf, const char *in_buf)
+{
+	int i, rc = 0;
+
+	for (i = 0; i < id->buf_size; i++) {
+                rc += sprintf(out_buf + rc, "%02x ",
+                              ((unsigned char *) in_buf)[i]);
+        }
+	rc += sprintf(out_buf + rc, "| ");
+	for (i = 0; i < id->buf_size; i++) {
+		unsigned char c = in_buf[i];
+		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;
+}
+
+/*
+ * prints header for debug entry
+ */
+
+int
+debug_dflt_header_fn(debug_info_t * id, struct debug_view *view,
+			 int area, debug_entry_t * entry, char *out_buf)
+{
+	struct timespec time_spec;
+	char *except_str;
+	unsigned long caller;
+	int rc = 0;
+	unsigned int level;
+
+	level = entry->id.fields.level;
+	stck_to_timespec(entry->id.stck, &time_spec);
+
+	if (entry->id.fields.exception)
+		except_str = "*";
+	else
+		except_str = "-";
+	caller = ((unsigned long) entry->caller) & PSW_ADDR_INSN;
+	rc += sprintf(out_buf, "%02i %011lu:%06lu %1u %1s %02i %p  ",
+		      area, time_spec.tv_sec, time_spec.tv_nsec / 1000, level,
+		      except_str, entry->id.fields.cpuid, (void *) caller);
+	return rc;
+}
+EXPORT_SYMBOL(debug_dflt_header_fn);
+
+/*
+ * prints debug data sprintf-formated:
+ * debug_sprinf_event/exception calls must be used together with this view
+ */
+
+#define DEBUG_SPRINTF_MAX_ARGS 10
+
+static int
+debug_sprintf_format_fn(debug_info_t * id, struct debug_view *view,
+                        char *out_buf, debug_sprintf_entry_t *curr_event)
+{
+	int num_longs, num_used_args = 0,i, rc = 0;
+	int index[DEBUG_SPRINTF_MAX_ARGS];
+
+	/* count of longs fit into one entry */
+	num_longs = id->buf_size /  sizeof(long); 
+
+	if(num_longs < 1)
+		goto out; /* bufsize of entry too small */
+	if(num_longs == 1) {
+		/* no args, we use only the string */
+		strcpy(out_buf, curr_event->string);
+		rc = strlen(curr_event->string);
+		goto out;
+	}
+
+	/* number of arguments used for sprintf (without the format string) */
+	num_used_args   = min(DEBUG_SPRINTF_MAX_ARGS, (num_longs - 1));
+
+	memset(index,0, DEBUG_SPRINTF_MAX_ARGS * sizeof(int));
+
+	for(i = 0; i < num_used_args; i++)
+		index[i] = i;
+
+	rc =  sprintf(out_buf, curr_event->string, curr_event->args[index[0]],
+		curr_event->args[index[1]], curr_event->args[index[2]],
+		curr_event->args[index[3]], curr_event->args[index[4]],
+		curr_event->args[index[5]], curr_event->args[index[6]],
+		curr_event->args[index[7]], curr_event->args[index[8]],
+		curr_event->args[index[9]]);
+
+out:
+
+	return rc;
+}
+
+/*
+ * debug_init:
+ * - is called exactly once to initialize the debug feature
+ */
+static int __init debug_init(void)
+{
+	s390dbf_sysctl_header = register_sysctl_table(s390dbf_dir_table);
+	mutex_lock(&debug_mutex);
+	debug_debugfs_root_entry = debugfs_create_dir(DEBUG_DIR_ROOT, NULL);
+	initialized = 1;
+	mutex_unlock(&debug_mutex);
+	return 0;
+}
+postcore_initcall(debug_init);
diff --git a/arch/s390/kernel/diag.c b/arch/s390/kernel/diag.c
new file mode 100644
index 000000000..2f69243bf
--- /dev/null
+++ b/arch/s390/kernel/diag.c
@@ -0,0 +1,66 @@
+/*
+ * Implementation of s390 diagnose codes
+ *
+ * Copyright IBM Corp. 2007
+ * Author(s): Michael Holzheu <holzheu@de.ibm.com>
+ */
+
+#include <linux/module.h>
+#include <asm/diag.h>
+
+/*
+ * Diagnose 14: Input spool file manipulation
+ */
+int diag14(unsigned long rx, unsigned long ry1, unsigned long subcode)
+{
+	register unsigned long _ry1 asm("2") = ry1;
+	register unsigned long _ry2 asm("3") = subcode;
+	int rc = 0;
+
+	asm volatile(
+		"   sam31\n"
+		"   diag    %2,2,0x14\n"
+		"   sam64\n"
+		"   ipm     %0\n"
+		"   srl     %0,28\n"
+		: "=d" (rc), "+d" (_ry2)
+		: "d" (rx), "d" (_ry1)
+		: "cc");
+
+	return rc;
+}
+EXPORT_SYMBOL(diag14);
+
+/*
+ * Diagnose 210: Get information about a virtual device
+ */
+int diag210(struct diag210 *addr)
+{
+	/*
+	 * diag 210 needs its data below the 2GB border, so we
+	 * use a static data area to be sure
+	 */
+	static struct diag210 diag210_tmp;
+	static DEFINE_SPINLOCK(diag210_lock);
+	unsigned long flags;
+	int ccode;
+
+	spin_lock_irqsave(&diag210_lock, flags);
+	diag210_tmp = *addr;
+
+	asm volatile(
+		"	lhi	%0,-1\n"
+		"	sam31\n"
+		"	diag	%1,0,0x210\n"
+		"0:	ipm	%0\n"
+		"	srl	%0,28\n"
+		"1:	sam64\n"
+		EX_TABLE(0b, 1b)
+		: "=&d" (ccode) : "a" (&diag210_tmp) : "cc", "memory");
+
+	*addr = diag210_tmp;
+	spin_unlock_irqrestore(&diag210_lock, flags);
+
+	return ccode;
+}
+EXPORT_SYMBOL(diag210);
diff --git a/arch/s390/kernel/dis.c b/arch/s390/kernel/dis.c
new file mode 100644
index 000000000..8140d10c6
--- /dev/null
+++ b/arch/s390/kernel/dis.c
@@ -0,0 +1,2049 @@
+/*
+ * Disassemble s390 instructions.
+ *
+ * Copyright IBM Corp. 2007
+ * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com),
+ */
+
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+#include <linux/ptrace.h>
+#include <linux/timer.h>
+#include <linux/mm.h>
+#include <linux/smp.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/delay.h>
+#include <linux/module.h>
+#include <linux/kallsyms.h>
+#include <linux/reboot.h>
+#include <linux/kprobes.h>
+#include <linux/kdebug.h>
+
+#include <asm/uaccess.h>
+#include <asm/dis.h>
+#include <asm/io.h>
+#include <linux/atomic.h>
+#include <asm/mathemu.h>
+#include <asm/cpcmd.h>
+#include <asm/lowcore.h>
+#include <asm/debug.h>
+#include <asm/irq.h>
+
+enum {
+	UNUSED,	/* Indicates the end of the operand list */
+	R_8,	/* GPR starting at position 8 */
+	R_12,	/* GPR starting at position 12 */
+	R_16,	/* GPR starting at position 16 */
+	R_20,	/* GPR starting at position 20 */
+	R_24,	/* GPR starting at position 24 */
+	R_28,	/* GPR starting at position 28 */
+	R_32,	/* GPR starting at position 32 */
+	F_8,	/* FPR starting at position 8 */
+	F_12,	/* FPR starting at position 12 */
+	F_16,	/* FPR starting at position 16 */
+	F_20,	/* FPR starting at position 16 */
+	F_24,	/* FPR starting at position 24 */
+	F_28,	/* FPR starting at position 28 */
+	F_32,	/* FPR starting at position 32 */
+	A_8,	/* Access reg. starting at position 8 */
+	A_12,	/* Access reg. starting at position 12 */
+	A_24,	/* Access reg. starting at position 24 */
+	A_28,	/* Access reg. starting at position 28 */
+	C_8,	/* Control reg. starting at position 8 */
+	C_12,	/* Control reg. starting at position 12 */
+	V_8,	/* Vector reg. starting at position 8, extension bit at 36 */
+	V_12,	/* Vector reg. starting at position 12, extension bit at 37 */
+	V_16,	/* Vector reg. starting at position 16, extension bit at 38 */
+	V_32,	/* Vector reg. starting at position 32, extension bit at 39 */
+	W_12,	/* Vector reg. at bit 12, extension at bit 37, used as index */
+	B_16,	/* Base register starting at position 16 */
+	B_32,	/* Base register starting at position 32 */
+	X_12,	/* Index register starting at position 12 */
+	D_20,	/* Displacement starting at position 20 */
+	D_36,	/* Displacement starting at position 36 */
+	D20_20,	/* 20 bit displacement starting at 20 */
+	L4_8,	/* 4 bit length starting at position 8 */
+	L4_12,	/* 4 bit length starting at position 12 */
+	L8_8,	/* 8 bit length starting at position 8 */
+	U4_8,	/* 4 bit unsigned value starting at 8 */
+	U4_12,	/* 4 bit unsigned value starting at 12 */
+	U4_16,	/* 4 bit unsigned value starting at 16 */
+	U4_20,	/* 4 bit unsigned value starting at 20 */
+	U4_24,	/* 4 bit unsigned value starting at 24 */
+	U4_28,	/* 4 bit unsigned value starting at 28 */
+	U4_32,	/* 4 bit unsigned value starting at 32 */
+	U4_36,	/* 4 bit unsigned value starting at 36 */
+	U8_8,	/* 8 bit unsigned value starting at 8 */
+	U8_16,	/* 8 bit unsigned value starting at 16 */
+	U8_24,	/* 8 bit unsigned value starting at 24 */
+	U8_32,	/* 8 bit unsigned value starting at 32 */
+	I8_8,	/* 8 bit signed value starting at 8 */
+	I8_16,	/* 8 bit signed value starting at 16 */
+	I8_24,	/* 8 bit signed value starting at 24 */
+	I8_32,	/* 8 bit signed value starting at 32 */
+	J12_12, /* PC relative offset at 12 */
+	I16_16,	/* 16 bit signed value starting at 16 */
+	I16_32,	/* 32 bit signed value starting at 16 */
+	U16_16,	/* 16 bit unsigned value starting at 16 */
+	U16_32,	/* 32 bit unsigned value starting at 16 */
+	J16_16,	/* PC relative jump offset at 16 */
+	J16_32, /* PC relative offset at 16 */
+	I24_24, /* 24 bit signed value starting at 24 */
+	J32_16,	/* PC relative long offset at 16 */
+	I32_16,	/* 32 bit signed value starting at 16 */
+	U32_16,	/* 32 bit unsigned value starting at 16 */
+	M_16,	/* 4 bit optional mask starting at 16 */
+	M_20,	/* 4 bit optional mask starting at 20 */
+	M_24,	/* 4 bit optional mask starting at 24 */
+	M_28,	/* 4 bit optional mask starting at 28 */
+	M_32,	/* 4 bit optional mask starting at 32 */
+	RO_28,	/* optional GPR starting at position 28 */
+};
+
+/*
+ * Enumeration of the different instruction formats.
+ * For details consult the principles of operation.
+ */
+enum {
+	INSTR_INVALID,
+	INSTR_E,
+	INSTR_IE_UU,
+	INSTR_MII_UPI,
+	INSTR_RIE_R0IU, INSTR_RIE_R0UU, INSTR_RIE_RRP, INSTR_RIE_RRPU,
+	INSTR_RIE_RRUUU, INSTR_RIE_RUPI, INSTR_RIE_RUPU, INSTR_RIE_RRI0,
+	INSTR_RIL_RI, INSTR_RIL_RP, INSTR_RIL_RU, INSTR_RIL_UP,
+	INSTR_RIS_R0RDU, INSTR_RIS_R0UU, INSTR_RIS_RURDI, INSTR_RIS_RURDU,
+	INSTR_RI_RI, INSTR_RI_RP, INSTR_RI_RU, INSTR_RI_UP,
+	INSTR_RRE_00, INSTR_RRE_0R, INSTR_RRE_AA, INSTR_RRE_AR, INSTR_RRE_F0,
+	INSTR_RRE_FF, INSTR_RRE_FR, INSTR_RRE_R0, INSTR_RRE_RA, INSTR_RRE_RF,
+	INSTR_RRE_RR, INSTR_RRE_RR_OPT,
+	INSTR_RRF_0UFF, INSTR_RRF_F0FF, INSTR_RRF_F0FF2, INSTR_RRF_F0FR,
+	INSTR_RRF_FFRU, INSTR_RRF_FUFF, INSTR_RRF_FUFF2, INSTR_RRF_M0RR,
+	INSTR_RRF_R0RR,	INSTR_RRF_R0RR2, INSTR_RRF_RMRR, INSTR_RRF_RURR,
+	INSTR_RRF_U0FF,	INSTR_RRF_U0RF, INSTR_RRF_U0RR, INSTR_RRF_UUFF,
+	INSTR_RRF_UUFR, INSTR_RRF_UURF,
+	INSTR_RRR_F0FF, INSTR_RRS_RRRDU,
+	INSTR_RR_FF, INSTR_RR_R0, INSTR_RR_RR, INSTR_RR_U0, INSTR_RR_UR,
+	INSTR_RSE_CCRD, INSTR_RSE_RRRD, INSTR_RSE_RURD,
+	INSTR_RSI_RRP,
+	INSTR_RSL_LRDFU, INSTR_RSL_R0RD,
+	INSTR_RSY_AARD, INSTR_RSY_CCRD, INSTR_RSY_RRRD, INSTR_RSY_RURD,
+	INSTR_RSY_RDRM, INSTR_RSY_RMRD,
+	INSTR_RS_AARD, INSTR_RS_CCRD, INSTR_RS_R0RD, INSTR_RS_RRRD,
+	INSTR_RS_RURD,
+	INSTR_RXE_FRRD, INSTR_RXE_RRRD, INSTR_RXE_RRRDM,
+	INSTR_RXF_FRRDF,
+	INSTR_RXY_FRRD, INSTR_RXY_RRRD, INSTR_RXY_URRD,
+	INSTR_RX_FRRD, INSTR_RX_RRRD, INSTR_RX_URRD,
+	INSTR_SIL_RDI, INSTR_SIL_RDU,
+	INSTR_SIY_IRD, INSTR_SIY_URD,
+	INSTR_SI_URD,
+	INSTR_SMI_U0RDP,
+	INSTR_SSE_RDRD,
+	INSTR_SSF_RRDRD, INSTR_SSF_RRDRD2,
+	INSTR_SS_L0RDRD, INSTR_SS_LIRDRD, INSTR_SS_LLRDRD, INSTR_SS_RRRDRD,
+	INSTR_SS_RRRDRD2, INSTR_SS_RRRDRD3,
+	INSTR_S_00, INSTR_S_RD,
+	INSTR_VRI_V0IM, INSTR_VRI_V0I0, INSTR_VRI_V0IIM, INSTR_VRI_VVIM,
+	INSTR_VRI_VVV0IM, INSTR_VRI_VVV0I0, INSTR_VRI_VVIMM,
+	INSTR_VRR_VV00MMM, INSTR_VRR_VV000MM, INSTR_VRR_VV0000M,
+	INSTR_VRR_VV00000, INSTR_VRR_VVV0M0M, INSTR_VRR_VV00M0M,
+	INSTR_VRR_VVV000M, INSTR_VRR_VVV000V, INSTR_VRR_VVV0000,
+	INSTR_VRR_VVV0MMM, INSTR_VRR_VVV00MM, INSTR_VRR_VVVMM0V,
+	INSTR_VRR_VVVM0MV, INSTR_VRR_VVVM00V, INSTR_VRR_VRR0000,
+	INSTR_VRS_VVRDM, INSTR_VRS_VVRD0, INSTR_VRS_VRRDM, INSTR_VRS_VRRD0,
+	INSTR_VRS_RVRDM,
+	INSTR_VRV_VVRDM, INSTR_VRV_VWRDM,
+	INSTR_VRX_VRRDM, INSTR_VRX_VRRD0,
+};
+
+static const struct s390_operand operands[] =
+{
+	[UNUSED]  = { 0, 0, 0 },
+	[R_8]	 = {  4,  8, OPERAND_GPR },
+	[R_12]	 = {  4, 12, OPERAND_GPR },
+	[R_16]	 = {  4, 16, OPERAND_GPR },
+	[R_20]	 = {  4, 20, OPERAND_GPR },
+	[R_24]	 = {  4, 24, OPERAND_GPR },
+	[R_28]	 = {  4, 28, OPERAND_GPR },
+	[R_32]	 = {  4, 32, OPERAND_GPR },
+	[F_8]	 = {  4,  8, OPERAND_FPR },
+	[F_12]	 = {  4, 12, OPERAND_FPR },
+	[F_16]	 = {  4, 16, OPERAND_FPR },
+	[F_20]	 = {  4, 16, OPERAND_FPR },
+	[F_24]	 = {  4, 24, OPERAND_FPR },
+	[F_28]	 = {  4, 28, OPERAND_FPR },
+	[F_32]	 = {  4, 32, OPERAND_FPR },
+	[A_8]	 = {  4,  8, OPERAND_AR },
+	[A_12]	 = {  4, 12, OPERAND_AR },
+	[A_24]	 = {  4, 24, OPERAND_AR },
+	[A_28]	 = {  4, 28, OPERAND_AR },
+	[C_8]	 = {  4,  8, OPERAND_CR },
+	[C_12]	 = {  4, 12, OPERAND_CR },
+	[V_8]	 = {  4,  8, OPERAND_VR },
+	[V_12]	 = {  4, 12, OPERAND_VR },
+	[V_16]	 = {  4, 16, OPERAND_VR },
+	[V_32]	 = {  4, 32, OPERAND_VR },
+	[W_12]	 = {  4, 12, OPERAND_INDEX | OPERAND_VR },
+	[B_16]	 = {  4, 16, OPERAND_BASE | OPERAND_GPR },
+	[B_32]	 = {  4, 32, OPERAND_BASE | OPERAND_GPR },
+	[X_12]	 = {  4, 12, OPERAND_INDEX | OPERAND_GPR },
+	[D_20]	 = { 12, 20, OPERAND_DISP },
+	[D_36]	 = { 12, 36, OPERAND_DISP },
+	[D20_20] = { 20, 20, OPERAND_DISP | OPERAND_SIGNED },
+	[L4_8]	 = {  4,  8, OPERAND_LENGTH },
+	[L4_12]  = {  4, 12, OPERAND_LENGTH },
+	[L8_8]	 = {  8,  8, OPERAND_LENGTH },
+	[U4_8]	 = {  4,  8, 0 },
+	[U4_12]  = {  4, 12, 0 },
+	[U4_16]  = {  4, 16, 0 },
+	[U4_20]  = {  4, 20, 0 },
+	[U4_24]  = {  4, 24, 0 },
+	[U4_28]  = {  4, 28, 0 },
+	[U4_32]  = {  4, 32, 0 },
+	[U4_36]  = {  4, 36, 0 },
+	[U8_8]	 = {  8,  8, 0 },
+	[U8_16]  = {  8, 16, 0 },
+	[U8_24]  = {  8, 24, 0 },
+	[U8_32]  = {  8, 32, 0 },
+	[J12_12] = { 12, 12, OPERAND_PCREL },
+	[I8_8]	 = {  8,  8, OPERAND_SIGNED },
+	[I8_16]  = {  8, 16, OPERAND_SIGNED },
+	[I8_24]  = {  8, 24, OPERAND_SIGNED },
+	[I8_32]  = {  8, 32, OPERAND_SIGNED },
+	[I16_32] = { 16, 32, OPERAND_SIGNED },
+	[I16_16] = { 16, 16, OPERAND_SIGNED },
+	[U16_16] = { 16, 16, 0 },
+	[U16_32] = { 16, 32, 0 },
+	[J16_16] = { 16, 16, OPERAND_PCREL },
+	[J16_32] = { 16, 32, OPERAND_PCREL },
+	[I24_24] = { 24, 24, OPERAND_SIGNED },
+	[J32_16] = { 32, 16, OPERAND_PCREL },
+	[I32_16] = { 32, 16, OPERAND_SIGNED },
+	[U32_16] = { 32, 16, 0 },
+	[M_16]	 = {  4, 16, 0 },
+	[M_20]	 = {  4, 20, 0 },
+	[M_24]	 = {  4, 24, 0 },
+	[M_28]	 = {  4, 28, 0 },
+	[M_32]	 = {  4, 32, 0 },
+	[RO_28]  = {  4, 28, OPERAND_GPR }
+};
+
+static const unsigned char formats[][7] = {
+	[INSTR_E]	  = { 0xff, 0,0,0,0,0,0 },
+	[INSTR_IE_UU]	  = { 0xff, U4_24,U4_28,0,0,0,0 },
+	[INSTR_MII_UPI]	  = { 0xff, U4_8,J12_12,I24_24 },
+	[INSTR_RIE_R0IU]  = { 0xff, R_8,I16_16,U4_32,0,0,0 },
+	[INSTR_RIE_R0UU]  = { 0xff, R_8,U16_16,U4_32,0,0,0 },
+	[INSTR_RIE_RRI0]  = { 0xff, R_8,R_12,I16_16,0,0,0 },
+	[INSTR_RIE_RRPU]  = { 0xff, R_8,R_12,U4_32,J16_16,0,0 },
+	[INSTR_RIE_RRP]	  = { 0xff, R_8,R_12,J16_16,0,0,0 },
+	[INSTR_RIE_RRUUU] = { 0xff, R_8,R_12,U8_16,U8_24,U8_32,0 },
+	[INSTR_RIE_RUPI]  = { 0xff, R_8,I8_32,U4_12,J16_16,0,0 },
+	[INSTR_RIE_RUPU]  = { 0xff, R_8,U8_32,U4_12,J16_16,0,0 },
+	[INSTR_RIL_RI]	  = { 0x0f, R_8,I32_16,0,0,0,0 },
+	[INSTR_RIL_RP]	  = { 0x0f, R_8,J32_16,0,0,0,0 },
+	[INSTR_RIL_RU]	  = { 0x0f, R_8,U32_16,0,0,0,0 },
+	[INSTR_RIL_UP]	  = { 0x0f, U4_8,J32_16,0,0,0,0 },
+	[INSTR_RIS_R0RDU] = { 0xff, R_8,U8_32,D_20,B_16,0,0 },
+	[INSTR_RIS_RURDI] = { 0xff, R_8,I8_32,U4_12,D_20,B_16,0 },
+	[INSTR_RIS_RURDU] = { 0xff, R_8,U8_32,U4_12,D_20,B_16,0 },
+	[INSTR_RI_RI]	  = { 0x0f, R_8,I16_16,0,0,0,0 },
+	[INSTR_RI_RP]	  = { 0x0f, R_8,J16_16,0,0,0,0 },
+	[INSTR_RI_RU]	  = { 0x0f, R_8,U16_16,0,0,0,0 },
+	[INSTR_RI_UP]	  = { 0x0f, U4_8,J16_16,0,0,0,0 },
+	[INSTR_RRE_00]	  = { 0xff, 0,0,0,0,0,0 },
+	[INSTR_RRE_0R]	  = { 0xff, R_28,0,0,0,0,0 },
+	[INSTR_RRE_AA]	  = { 0xff, A_24,A_28,0,0,0,0 },
+	[INSTR_RRE_AR]	  = { 0xff, A_24,R_28,0,0,0,0 },
+	[INSTR_RRE_F0]	  = { 0xff, F_24,0,0,0,0,0 },
+	[INSTR_RRE_FF]	  = { 0xff, F_24,F_28,0,0,0,0 },
+	[INSTR_RRE_FR]	  = { 0xff, F_24,R_28,0,0,0,0 },
+	[INSTR_RRE_R0]	  = { 0xff, R_24,0,0,0,0,0 },
+	[INSTR_RRE_RA]	  = { 0xff, R_24,A_28,0,0,0,0 },
+	[INSTR_RRE_RF]	  = { 0xff, R_24,F_28,0,0,0,0 },
+	[INSTR_RRE_RR]	  = { 0xff, R_24,R_28,0,0,0,0 },
+	[INSTR_RRE_RR_OPT]= { 0xff, R_24,RO_28,0,0,0,0 },
+	[INSTR_RRF_0UFF]  = { 0xff, F_24,F_28,U4_20,0,0,0 },
+	[INSTR_RRF_F0FF2] = { 0xff, F_24,F_16,F_28,0,0,0 },
+	[INSTR_RRF_F0FF]  = { 0xff, F_16,F_24,F_28,0,0,0 },
+	[INSTR_RRF_F0FR]  = { 0xff, F_24,F_16,R_28,0,0,0 },
+	[INSTR_RRF_FFRU]  = { 0xff, F_24,F_16,R_28,U4_20,0,0 },
+	[INSTR_RRF_FUFF]  = { 0xff, F_24,F_16,F_28,U4_20,0,0 },
+	[INSTR_RRF_FUFF2] = { 0xff, F_24,F_28,F_16,U4_20,0,0 },
+	[INSTR_RRF_M0RR]  = { 0xff, R_24,R_28,M_16,0,0,0 },
+	[INSTR_RRF_R0RR]  = { 0xff, R_24,R_16,R_28,0,0,0 },
+	[INSTR_RRF_R0RR2] = { 0xff, R_24,R_28,R_16,0,0,0 },
+	[INSTR_RRF_RMRR]  = { 0xff, R_24,R_16,R_28,M_20,0,0 },
+	[INSTR_RRF_RURR]  = { 0xff, R_24,R_28,R_16,U4_20,0,0 },
+	[INSTR_RRF_U0FF]  = { 0xff, F_24,U4_16,F_28,0,0,0 },
+	[INSTR_RRF_U0RF]  = { 0xff, R_24,U4_16,F_28,0,0,0 },
+	[INSTR_RRF_U0RR]  = { 0xff, R_24,R_28,U4_16,0,0,0 },
+	[INSTR_RRF_UUFF]  = { 0xff, F_24,U4_16,F_28,U4_20,0,0 },
+	[INSTR_RRF_UUFR]  = { 0xff, F_24,U4_16,R_28,U4_20,0,0 },
+	[INSTR_RRF_UURF]  = { 0xff, R_24,U4_16,F_28,U4_20,0,0 },
+	[INSTR_RRR_F0FF]  = { 0xff, F_24,F_28,F_16,0,0,0 },
+	[INSTR_RRS_RRRDU] = { 0xff, R_8,R_12,U4_32,D_20,B_16,0 },
+	[INSTR_RR_FF]	  = { 0xff, F_8,F_12,0,0,0,0 },
+	[INSTR_RR_R0]	  = { 0xff, R_8, 0,0,0,0,0 },
+	[INSTR_RR_RR]	  = { 0xff, R_8,R_12,0,0,0,0 },
+	[INSTR_RR_U0]	  = { 0xff, U8_8, 0,0,0,0,0 },
+	[INSTR_RR_UR]	  = { 0xff, U4_8,R_12,0,0,0,0 },
+	[INSTR_RSE_CCRD]  = { 0xff, C_8,C_12,D_20,B_16,0,0 },
+	[INSTR_RSE_RRRD]  = { 0xff, R_8,R_12,D_20,B_16,0,0 },
+	[INSTR_RSE_RURD]  = { 0xff, R_8,U4_12,D_20,B_16,0,0 },
+	[INSTR_RSI_RRP]	  = { 0xff, R_8,R_12,J16_16,0,0,0 },
+	[INSTR_RSL_LRDFU] = { 0xff, F_32,D_20,L4_8,B_16,U4_36,0 },
+	[INSTR_RSL_R0RD]  = { 0xff, D_20,L4_8,B_16,0,0,0 },
+	[INSTR_RSY_AARD]  = { 0xff, A_8,A_12,D20_20,B_16,0,0 },
+	[INSTR_RSY_CCRD]  = { 0xff, C_8,C_12,D20_20,B_16,0,0 },
+	[INSTR_RSY_RDRM]  = { 0xff, R_8,D20_20,B_16,U4_12,0,0 },
+	[INSTR_RSY_RMRD]  = { 0xff, R_8,U4_12,D20_20,B_16,0,0 },
+	[INSTR_RSY_RRRD]  = { 0xff, R_8,R_12,D20_20,B_16,0,0 },
+	[INSTR_RSY_RURD]  = { 0xff, R_8,U4_12,D20_20,B_16,0,0 },
+	[INSTR_RS_AARD]	  = { 0xff, A_8,A_12,D_20,B_16,0,0 },
+	[INSTR_RS_CCRD]	  = { 0xff, C_8,C_12,D_20,B_16,0,0 },
+	[INSTR_RS_R0RD]	  = { 0xff, R_8,D_20,B_16,0,0,0 },
+	[INSTR_RS_RRRD]	  = { 0xff, R_8,R_12,D_20,B_16,0,0 },
+	[INSTR_RS_RURD]	  = { 0xff, R_8,U4_12,D_20,B_16,0,0 },
+	[INSTR_RXE_FRRD]  = { 0xff, F_8,D_20,X_12,B_16,0,0 },
+	[INSTR_RXE_RRRD]  = { 0xff, R_8,D_20,X_12,B_16,0,0 },
+	[INSTR_RXE_RRRDM] = { 0xff, R_8,D_20,X_12,B_16,M_32,0 },
+	[INSTR_RXF_FRRDF] = { 0xff, F_32,F_8,D_20,X_12,B_16,0 },
+	[INSTR_RXY_FRRD]  = { 0xff, F_8,D20_20,X_12,B_16,0,0 },
+	[INSTR_RXY_RRRD]  = { 0xff, R_8,D20_20,X_12,B_16,0,0 },
+	[INSTR_RXY_URRD]  = { 0xff, U4_8,D20_20,X_12,B_16,0,0 },
+	[INSTR_RX_FRRD]	  = { 0xff, F_8,D_20,X_12,B_16,0,0 },
+	[INSTR_RX_RRRD]	  = { 0xff, R_8,D_20,X_12,B_16,0,0 },
+	[INSTR_RX_URRD]	  = { 0xff, U4_8,D_20,X_12,B_16,0,0 },
+	[INSTR_SIL_RDI]   = { 0xff, D_20,B_16,I16_32,0,0,0 },
+	[INSTR_SIL_RDU]   = { 0xff, D_20,B_16,U16_32,0,0,0 },
+	[INSTR_SIY_IRD]   = { 0xff, D20_20,B_16,I8_8,0,0,0 },
+	[INSTR_SIY_URD]	  = { 0xff, D20_20,B_16,U8_8,0,0,0 },
+	[INSTR_SI_URD]	  = { 0xff, D_20,B_16,U8_8,0,0,0 },
+	[INSTR_SMI_U0RDP] = { 0xff, U4_8,J16_32,D_20,B_16,0,0 },
+	[INSTR_SSE_RDRD]  = { 0xff, D_20,B_16,D_36,B_32,0,0 },
+	[INSTR_SSF_RRDRD] = { 0x0f, D_20,B_16,D_36,B_32,R_8,0 },
+	[INSTR_SSF_RRDRD2]= { 0x0f, R_8,D_20,B_16,D_36,B_32,0 },
+	[INSTR_SS_L0RDRD] = { 0xff, D_20,L8_8,B_16,D_36,B_32,0 },
+	[INSTR_SS_LIRDRD] = { 0xff, D_20,L4_8,B_16,D_36,B_32,U4_12 },
+	[INSTR_SS_LLRDRD] = { 0xff, D_20,L4_8,B_16,D_36,L4_12,B_32 },
+	[INSTR_SS_RRRDRD2]= { 0xff, R_8,D_20,B_16,R_12,D_36,B_32 },
+	[INSTR_SS_RRRDRD3]= { 0xff, R_8,R_12,D_20,B_16,D_36,B_32 },
+	[INSTR_SS_RRRDRD] = { 0xff, D_20,R_8,B_16,D_36,B_32,R_12 },
+	[INSTR_S_00]	  = { 0xff, 0,0,0,0,0,0 },
+	[INSTR_S_RD]	  = { 0xff, D_20,B_16,0,0,0,0 },
+	[INSTR_VRI_V0IM]  = { 0xff, V_8,I16_16,M_32,0,0,0 },
+	[INSTR_VRI_V0I0]  = { 0xff, V_8,I16_16,0,0,0,0 },
+	[INSTR_VRI_V0IIM] = { 0xff, V_8,I8_16,I8_24,M_32,0,0 },
+	[INSTR_VRI_VVIM]  = { 0xff, V_8,I16_16,V_12,M_32,0,0 },
+	[INSTR_VRI_VVV0IM]= { 0xff, V_8,V_12,V_16,I8_24,M_32,0 },
+	[INSTR_VRI_VVV0I0]= { 0xff, V_8,V_12,V_16,I8_24,0,0 },
+	[INSTR_VRI_VVIMM] = { 0xff, V_8,V_12,I16_16,M_32,M_28,0 },
+	[INSTR_VRR_VV00MMM]={ 0xff, V_8,V_12,M_32,M_28,M_24,0 },
+	[INSTR_VRR_VV000MM]={ 0xff, V_8,V_12,M_32,M_28,0,0 },
+	[INSTR_VRR_VV0000M]={ 0xff, V_8,V_12,M_32,0,0,0 },
+	[INSTR_VRR_VV00000]={ 0xff, V_8,V_12,0,0,0,0 },
+	[INSTR_VRR_VVV0M0M]={ 0xff, V_8,V_12,V_16,M_32,M_24,0 },
+	[INSTR_VRR_VV00M0M]={ 0xff, V_8,V_12,M_32,M_24,0,0 },
+	[INSTR_VRR_VVV000M]={ 0xff, V_8,V_12,V_16,M_32,0,0 },
+	[INSTR_VRR_VVV000V]={ 0xff, V_8,V_12,V_16,V_32,0,0 },
+	[INSTR_VRR_VVV0000]={ 0xff, V_8,V_12,V_16,0,0,0 },
+	[INSTR_VRR_VVV0MMM]={ 0xff, V_8,V_12,V_16,M_32,M_28,M_24 },
+	[INSTR_VRR_VVV00MM]={ 0xff, V_8,V_12,V_16,M_32,M_28,0 },
+	[INSTR_VRR_VVVMM0V]={ 0xff, V_8,V_12,V_16,V_32,M_20,M_24 },
+	[INSTR_VRR_VVVM0MV]={ 0xff, V_8,V_12,V_16,V_32,M_28,M_20 },
+	[INSTR_VRR_VVVM00V]={ 0xff, V_8,V_12,V_16,V_32,M_20,0 },
+	[INSTR_VRR_VRR0000]={ 0xff, V_8,R_12,R_16,0,0,0 },
+	[INSTR_VRS_VVRDM] = { 0xff, V_8,V_12,D_20,B_16,M_32,0 },
+	[INSTR_VRS_VVRD0] = { 0xff, V_8,V_12,D_20,B_16,0,0 },
+	[INSTR_VRS_VRRDM] = { 0xff, V_8,R_12,D_20,B_16,M_32,0 },
+	[INSTR_VRS_VRRD0] = { 0xff, V_8,R_12,D_20,B_16,0,0 },
+	[INSTR_VRS_RVRDM] = { 0xff, R_8,V_12,D_20,B_16,M_32,0 },
+	[INSTR_VRV_VVRDM] = { 0xff, V_8,V_12,D_20,B_16,M_32,0 },
+	[INSTR_VRV_VWRDM] = { 0xff, V_8,D_20,W_12,B_16,M_32,0 },
+	[INSTR_VRX_VRRDM] = { 0xff, V_8,D_20,X_12,B_16,M_32,0 },
+	[INSTR_VRX_VRRD0] = { 0xff, V_8,D_20,X_12,B_16,0,0 },
+};
+
+enum {
+	LONG_INSN_ALGHSIK,
+	LONG_INSN_ALHHHR,
+	LONG_INSN_ALHHLR,
+	LONG_INSN_ALHSIK,
+	LONG_INSN_ALSIHN,
+	LONG_INSN_CDFBRA,
+	LONG_INSN_CDGBRA,
+	LONG_INSN_CDGTRA,
+	LONG_INSN_CDLFBR,
+	LONG_INSN_CDLFTR,
+	LONG_INSN_CDLGBR,
+	LONG_INSN_CDLGTR,
+	LONG_INSN_CEFBRA,
+	LONG_INSN_CEGBRA,
+	LONG_INSN_CELFBR,
+	LONG_INSN_CELGBR,
+	LONG_INSN_CFDBRA,
+	LONG_INSN_CFEBRA,
+	LONG_INSN_CFXBRA,
+	LONG_INSN_CGDBRA,
+	LONG_INSN_CGDTRA,
+	LONG_INSN_CGEBRA,
+	LONG_INSN_CGXBRA,
+	LONG_INSN_CGXTRA,
+	LONG_INSN_CLFDBR,
+	LONG_INSN_CLFDTR,
+	LONG_INSN_CLFEBR,
+	LONG_INSN_CLFHSI,
+	LONG_INSN_CLFXBR,
+	LONG_INSN_CLFXTR,
+	LONG_INSN_CLGDBR,
+	LONG_INSN_CLGDTR,
+	LONG_INSN_CLGEBR,
+	LONG_INSN_CLGFRL,
+	LONG_INSN_CLGHRL,
+	LONG_INSN_CLGHSI,
+	LONG_INSN_CLGXBR,
+	LONG_INSN_CLGXTR,
+	LONG_INSN_CLHHSI,
+	LONG_INSN_CXFBRA,
+	LONG_INSN_CXGBRA,
+	LONG_INSN_CXGTRA,
+	LONG_INSN_CXLFBR,
+	LONG_INSN_CXLFTR,
+	LONG_INSN_CXLGBR,
+	LONG_INSN_CXLGTR,
+	LONG_INSN_FIDBRA,
+	LONG_INSN_FIEBRA,
+	LONG_INSN_FIXBRA,
+	LONG_INSN_LDXBRA,
+	LONG_INSN_LEDBRA,
+	LONG_INSN_LEXBRA,
+	LONG_INSN_LLGFAT,
+	LONG_INSN_LLGFRL,
+	LONG_INSN_LLGHRL,
+	LONG_INSN_LLGTAT,
+	LONG_INSN_POPCNT,
+	LONG_INSN_RIEMIT,
+	LONG_INSN_RINEXT,
+	LONG_INSN_RISBGN,
+	LONG_INSN_RISBHG,
+	LONG_INSN_RISBLG,
+	LONG_INSN_SLHHHR,
+	LONG_INSN_SLHHLR,
+	LONG_INSN_TABORT,
+	LONG_INSN_TBEGIN,
+	LONG_INSN_TBEGINC,
+	LONG_INSN_PCISTG,
+	LONG_INSN_MPCIFC,
+	LONG_INSN_STPCIFC,
+	LONG_INSN_PCISTB,
+	LONG_INSN_VPOPCT,
+	LONG_INSN_VERLLV,
+	LONG_INSN_VESRAV,
+	LONG_INSN_VESRLV,
+	LONG_INSN_VSBCBI,
+	LONG_INSN_STCCTM
+};
+
+static char *long_insn_name[] = {
+	[LONG_INSN_ALGHSIK] = "alghsik",
+	[LONG_INSN_ALHHHR] = "alhhhr",
+	[LONG_INSN_ALHHLR] = "alhhlr",
+	[LONG_INSN_ALHSIK] = "alhsik",
+	[LONG_INSN_ALSIHN] = "alsihn",
+	[LONG_INSN_CDFBRA] = "cdfbra",
+	[LONG_INSN_CDGBRA] = "cdgbra",
+	[LONG_INSN_CDGTRA] = "cdgtra",
+	[LONG_INSN_CDLFBR] = "cdlfbr",
+	[LONG_INSN_CDLFTR] = "cdlftr",
+	[LONG_INSN_CDLGBR] = "cdlgbr",
+	[LONG_INSN_CDLGTR] = "cdlgtr",
+	[LONG_INSN_CEFBRA] = "cefbra",
+	[LONG_INSN_CEGBRA] = "cegbra",
+	[LONG_INSN_CELFBR] = "celfbr",
+	[LONG_INSN_CELGBR] = "celgbr",
+	[LONG_INSN_CFDBRA] = "cfdbra",
+	[LONG_INSN_CFEBRA] = "cfebra",
+	[LONG_INSN_CFXBRA] = "cfxbra",
+	[LONG_INSN_CGDBRA] = "cgdbra",
+	[LONG_INSN_CGDTRA] = "cgdtra",
+	[LONG_INSN_CGEBRA] = "cgebra",
+	[LONG_INSN_CGXBRA] = "cgxbra",
+	[LONG_INSN_CGXTRA] = "cgxtra",
+	[LONG_INSN_CLFDBR] = "clfdbr",
+	[LONG_INSN_CLFDTR] = "clfdtr",
+	[LONG_INSN_CLFEBR] = "clfebr",
+	[LONG_INSN_CLFHSI] = "clfhsi",
+	[LONG_INSN_CLFXBR] = "clfxbr",
+	[LONG_INSN_CLFXTR] = "clfxtr",
+	[LONG_INSN_CLGDBR] = "clgdbr",
+	[LONG_INSN_CLGDTR] = "clgdtr",
+	[LONG_INSN_CLGEBR] = "clgebr",
+	[LONG_INSN_CLGFRL] = "clgfrl",
+	[LONG_INSN_CLGHRL] = "clghrl",
+	[LONG_INSN_CLGHSI] = "clghsi",
+	[LONG_INSN_CLGXBR] = "clgxbr",
+	[LONG_INSN_CLGXTR] = "clgxtr",
+	[LONG_INSN_CLHHSI] = "clhhsi",
+	[LONG_INSN_CXFBRA] = "cxfbra",
+	[LONG_INSN_CXGBRA] = "cxgbra",
+	[LONG_INSN_CXGTRA] = "cxgtra",
+	[LONG_INSN_CXLFBR] = "cxlfbr",
+	[LONG_INSN_CXLFTR] = "cxlftr",
+	[LONG_INSN_CXLGBR] = "cxlgbr",
+	[LONG_INSN_CXLGTR] = "cxlgtr",
+	[LONG_INSN_FIDBRA] = "fidbra",
+	[LONG_INSN_FIEBRA] = "fiebra",
+	[LONG_INSN_FIXBRA] = "fixbra",
+	[LONG_INSN_LDXBRA] = "ldxbra",
+	[LONG_INSN_LEDBRA] = "ledbra",
+	[LONG_INSN_LEXBRA] = "lexbra",
+	[LONG_INSN_LLGFAT] = "llgfat",
+	[LONG_INSN_LLGFRL] = "llgfrl",
+	[LONG_INSN_LLGHRL] = "llghrl",
+	[LONG_INSN_LLGTAT] = "llgtat",
+	[LONG_INSN_POPCNT] = "popcnt",
+	[LONG_INSN_RIEMIT] = "riemit",
+	[LONG_INSN_RINEXT] = "rinext",
+	[LONG_INSN_RISBGN] = "risbgn",
+	[LONG_INSN_RISBHG] = "risbhg",
+	[LONG_INSN_RISBLG] = "risblg",
+	[LONG_INSN_SLHHHR] = "slhhhr",
+	[LONG_INSN_SLHHLR] = "slhhlr",
+	[LONG_INSN_TABORT] = "tabort",
+	[LONG_INSN_TBEGIN] = "tbegin",
+	[LONG_INSN_TBEGINC] = "tbeginc",
+	[LONG_INSN_PCISTG] = "pcistg",
+	[LONG_INSN_MPCIFC] = "mpcifc",
+	[LONG_INSN_STPCIFC] = "stpcifc",
+	[LONG_INSN_PCISTB] = "pcistb",
+	[LONG_INSN_VPOPCT] = "vpopct",
+	[LONG_INSN_VERLLV] = "verllv",
+	[LONG_INSN_VESRAV] = "vesrav",
+	[LONG_INSN_VESRLV] = "vesrlv",
+	[LONG_INSN_VSBCBI] = "vsbcbi",
+	[LONG_INSN_STCCTM] = "stcctm",
+};
+
+static struct s390_insn opcode[] = {
+	{ "bprp", 0xc5, INSTR_MII_UPI },
+	{ "bpp", 0xc7, INSTR_SMI_U0RDP },
+	{ "trtr", 0xd0, INSTR_SS_L0RDRD },
+	{ "lmd", 0xef, INSTR_SS_RRRDRD3 },
+	{ "spm", 0x04, INSTR_RR_R0 },
+	{ "balr", 0x05, INSTR_RR_RR },
+	{ "bctr", 0x06, INSTR_RR_RR },
+	{ "bcr", 0x07, INSTR_RR_UR },
+	{ "svc", 0x0a, INSTR_RR_U0 },
+	{ "bsm", 0x0b, INSTR_RR_RR },
+	{ "bassm", 0x0c, INSTR_RR_RR },
+	{ "basr", 0x0d, INSTR_RR_RR },
+	{ "mvcl", 0x0e, INSTR_RR_RR },
+	{ "clcl", 0x0f, INSTR_RR_RR },
+	{ "lpr", 0x10, INSTR_RR_RR },
+	{ "lnr", 0x11, INSTR_RR_RR },
+	{ "ltr", 0x12, INSTR_RR_RR },
+	{ "lcr", 0x13, INSTR_RR_RR },
+	{ "nr", 0x14, INSTR_RR_RR },
+	{ "clr", 0x15, INSTR_RR_RR },
+	{ "or", 0x16, INSTR_RR_RR },
+	{ "xr", 0x17, INSTR_RR_RR },
+	{ "lr", 0x18, INSTR_RR_RR },
+	{ "cr", 0x19, INSTR_RR_RR },
+	{ "ar", 0x1a, INSTR_RR_RR },
+	{ "sr", 0x1b, INSTR_RR_RR },
+	{ "mr", 0x1c, INSTR_RR_RR },
+	{ "dr", 0x1d, INSTR_RR_RR },
+	{ "alr", 0x1e, INSTR_RR_RR },
+	{ "slr", 0x1f, INSTR_RR_RR },
+	{ "lpdr", 0x20, INSTR_RR_FF },
+	{ "lndr", 0x21, INSTR_RR_FF },
+	{ "ltdr", 0x22, INSTR_RR_FF },
+	{ "lcdr", 0x23, INSTR_RR_FF },
+	{ "hdr", 0x24, INSTR_RR_FF },
+	{ "ldxr", 0x25, INSTR_RR_FF },
+	{ "mxr", 0x26, INSTR_RR_FF },
+	{ "mxdr", 0x27, INSTR_RR_FF },
+	{ "ldr", 0x28, INSTR_RR_FF },
+	{ "cdr", 0x29, INSTR_RR_FF },
+	{ "adr", 0x2a, INSTR_RR_FF },
+	{ "sdr", 0x2b, INSTR_RR_FF },
+	{ "mdr", 0x2c, INSTR_RR_FF },
+	{ "ddr", 0x2d, INSTR_RR_FF },
+	{ "awr", 0x2e, INSTR_RR_FF },
+	{ "swr", 0x2f, INSTR_RR_FF },
+	{ "lper", 0x30, INSTR_RR_FF },
+	{ "lner", 0x31, INSTR_RR_FF },
+	{ "lter", 0x32, INSTR_RR_FF },
+	{ "lcer", 0x33, INSTR_RR_FF },
+	{ "her", 0x34, INSTR_RR_FF },
+	{ "ledr", 0x35, INSTR_RR_FF },
+	{ "axr", 0x36, INSTR_RR_FF },
+	{ "sxr", 0x37, INSTR_RR_FF },
+	{ "ler", 0x38, INSTR_RR_FF },
+	{ "cer", 0x39, INSTR_RR_FF },
+	{ "aer", 0x3a, INSTR_RR_FF },
+	{ "ser", 0x3b, INSTR_RR_FF },
+	{ "mder", 0x3c, INSTR_RR_FF },
+	{ "der", 0x3d, INSTR_RR_FF },
+	{ "aur", 0x3e, INSTR_RR_FF },
+	{ "sur", 0x3f, INSTR_RR_FF },
+	{ "sth", 0x40, INSTR_RX_RRRD },
+	{ "la", 0x41, INSTR_RX_RRRD },
+	{ "stc", 0x42, INSTR_RX_RRRD },
+	{ "ic", 0x43, INSTR_RX_RRRD },
+	{ "ex", 0x44, INSTR_RX_RRRD },
+	{ "bal", 0x45, INSTR_RX_RRRD },
+	{ "bct", 0x46, INSTR_RX_RRRD },
+	{ "bc", 0x47, INSTR_RX_URRD },
+	{ "lh", 0x48, INSTR_RX_RRRD },
+	{ "ch", 0x49, INSTR_RX_RRRD },
+	{ "ah", 0x4a, INSTR_RX_RRRD },
+	{ "sh", 0x4b, INSTR_RX_RRRD },
+	{ "mh", 0x4c, INSTR_RX_RRRD },
+	{ "bas", 0x4d, INSTR_RX_RRRD },
+	{ "cvd", 0x4e, INSTR_RX_RRRD },
+	{ "cvb", 0x4f, INSTR_RX_RRRD },
+	{ "st", 0x50, INSTR_RX_RRRD },
+	{ "lae", 0x51, INSTR_RX_RRRD },
+	{ "n", 0x54, INSTR_RX_RRRD },
+	{ "cl", 0x55, INSTR_RX_RRRD },
+	{ "o", 0x56, INSTR_RX_RRRD },
+	{ "x", 0x57, INSTR_RX_RRRD },
+	{ "l", 0x58, INSTR_RX_RRRD },
+	{ "c", 0x59, INSTR_RX_RRRD },
+	{ "a", 0x5a, INSTR_RX_RRRD },
+	{ "s", 0x5b, INSTR_RX_RRRD },
+	{ "m", 0x5c, INSTR_RX_RRRD },
+	{ "d", 0x5d, INSTR_RX_RRRD },
+	{ "al", 0x5e, INSTR_RX_RRRD },
+	{ "sl", 0x5f, INSTR_RX_RRRD },
+	{ "std", 0x60, INSTR_RX_FRRD },
+	{ "mxd", 0x67, INSTR_RX_FRRD },
+	{ "ld", 0x68, INSTR_RX_FRRD },
+	{ "cd", 0x69, INSTR_RX_FRRD },
+	{ "ad", 0x6a, INSTR_RX_FRRD },
+	{ "sd", 0x6b, INSTR_RX_FRRD },
+	{ "md", 0x6c, INSTR_RX_FRRD },
+	{ "dd", 0x6d, INSTR_RX_FRRD },
+	{ "aw", 0x6e, INSTR_RX_FRRD },
+	{ "sw", 0x6f, INSTR_RX_FRRD },
+	{ "ste", 0x70, INSTR_RX_FRRD },
+	{ "ms", 0x71, INSTR_RX_RRRD },
+	{ "le", 0x78, INSTR_RX_FRRD },
+	{ "ce", 0x79, INSTR_RX_FRRD },
+	{ "ae", 0x7a, INSTR_RX_FRRD },
+	{ "se", 0x7b, INSTR_RX_FRRD },
+	{ "mde", 0x7c, INSTR_RX_FRRD },
+	{ "de", 0x7d, INSTR_RX_FRRD },
+	{ "au", 0x7e, INSTR_RX_FRRD },
+	{ "su", 0x7f, INSTR_RX_FRRD },
+	{ "ssm", 0x80, INSTR_S_RD },
+	{ "lpsw", 0x82, INSTR_S_RD },
+	{ "diag", 0x83, INSTR_RS_RRRD },
+	{ "brxh", 0x84, INSTR_RSI_RRP },
+	{ "brxle", 0x85, INSTR_RSI_RRP },
+	{ "bxh", 0x86, INSTR_RS_RRRD },
+	{ "bxle", 0x87, INSTR_RS_RRRD },
+	{ "srl", 0x88, INSTR_RS_R0RD },
+	{ "sll", 0x89, INSTR_RS_R0RD },
+	{ "sra", 0x8a, INSTR_RS_R0RD },
+	{ "sla", 0x8b, INSTR_RS_R0RD },
+	{ "srdl", 0x8c, INSTR_RS_R0RD },
+	{ "sldl", 0x8d, INSTR_RS_R0RD },
+	{ "srda", 0x8e, INSTR_RS_R0RD },
+	{ "slda", 0x8f, INSTR_RS_R0RD },
+	{ "stm", 0x90, INSTR_RS_RRRD },
+	{ "tm", 0x91, INSTR_SI_URD },
+	{ "mvi", 0x92, INSTR_SI_URD },
+	{ "ts", 0x93, INSTR_S_RD },
+	{ "ni", 0x94, INSTR_SI_URD },
+	{ "cli", 0x95, INSTR_SI_URD },
+	{ "oi", 0x96, INSTR_SI_URD },
+	{ "xi", 0x97, INSTR_SI_URD },
+	{ "lm", 0x98, INSTR_RS_RRRD },
+	{ "trace", 0x99, INSTR_RS_RRRD },
+	{ "lam", 0x9a, INSTR_RS_AARD },
+	{ "stam", 0x9b, INSTR_RS_AARD },
+	{ "mvcle", 0xa8, INSTR_RS_RRRD },
+	{ "clcle", 0xa9, INSTR_RS_RRRD },
+	{ "stnsm", 0xac, INSTR_SI_URD },
+	{ "stosm", 0xad, INSTR_SI_URD },
+	{ "sigp", 0xae, INSTR_RS_RRRD },
+	{ "mc", 0xaf, INSTR_SI_URD },
+	{ "lra", 0xb1, INSTR_RX_RRRD },
+	{ "stctl", 0xb6, INSTR_RS_CCRD },
+	{ "lctl", 0xb7, INSTR_RS_CCRD },
+	{ "cs", 0xba, INSTR_RS_RRRD },
+	{ "cds", 0xbb, INSTR_RS_RRRD },
+	{ "clm", 0xbd, INSTR_RS_RURD },
+	{ "stcm", 0xbe, INSTR_RS_RURD },
+	{ "icm", 0xbf, INSTR_RS_RURD },
+	{ "mvn", 0xd1, INSTR_SS_L0RDRD },
+	{ "mvc", 0xd2, INSTR_SS_L0RDRD },
+	{ "mvz", 0xd3, INSTR_SS_L0RDRD },
+	{ "nc", 0xd4, INSTR_SS_L0RDRD },
+	{ "clc", 0xd5, INSTR_SS_L0RDRD },
+	{ "oc", 0xd6, INSTR_SS_L0RDRD },
+	{ "xc", 0xd7, INSTR_SS_L0RDRD },
+	{ "mvck", 0xd9, INSTR_SS_RRRDRD },
+	{ "mvcp", 0xda, INSTR_SS_RRRDRD },
+	{ "mvcs", 0xdb, INSTR_SS_RRRDRD },
+	{ "tr", 0xdc, INSTR_SS_L0RDRD },
+	{ "trt", 0xdd, INSTR_SS_L0RDRD },
+	{ "ed", 0xde, INSTR_SS_L0RDRD },
+	{ "edmk", 0xdf, INSTR_SS_L0RDRD },
+	{ "pku", 0xe1, INSTR_SS_L0RDRD },
+	{ "unpku", 0xe2, INSTR_SS_L0RDRD },
+	{ "mvcin", 0xe8, INSTR_SS_L0RDRD },
+	{ "pka", 0xe9, INSTR_SS_L0RDRD },
+	{ "unpka", 0xea, INSTR_SS_L0RDRD },
+	{ "plo", 0xee, INSTR_SS_RRRDRD2 },
+	{ "srp", 0xf0, INSTR_SS_LIRDRD },
+	{ "mvo", 0xf1, INSTR_SS_LLRDRD },
+	{ "pack", 0xf2, INSTR_SS_LLRDRD },
+	{ "unpk", 0xf3, INSTR_SS_LLRDRD },
+	{ "zap", 0xf8, INSTR_SS_LLRDRD },
+	{ "cp", 0xf9, INSTR_SS_LLRDRD },
+	{ "ap", 0xfa, INSTR_SS_LLRDRD },
+	{ "sp", 0xfb, INSTR_SS_LLRDRD },
+	{ "mp", 0xfc, INSTR_SS_LLRDRD },
+	{ "dp", 0xfd, INSTR_SS_LLRDRD },
+	{ "", 0, INSTR_INVALID }
+};
+
+static struct s390_insn opcode_01[] = {
+	{ "ptff", 0x04, INSTR_E },
+	{ "pfpo", 0x0a, INSTR_E },
+	{ "sam64", 0x0e, INSTR_E },
+	{ "pr", 0x01, INSTR_E },
+	{ "upt", 0x02, INSTR_E },
+	{ "sckpf", 0x07, INSTR_E },
+	{ "tam", 0x0b, INSTR_E },
+	{ "sam24", 0x0c, INSTR_E },
+	{ "sam31", 0x0d, INSTR_E },
+	{ "trap2", 0xff, INSTR_E },
+	{ "", 0, INSTR_INVALID }
+};
+
+static struct s390_insn opcode_a5[] = {
+	{ "iihh", 0x00, INSTR_RI_RU },
+	{ "iihl", 0x01, INSTR_RI_RU },
+	{ "iilh", 0x02, INSTR_RI_RU },
+	{ "iill", 0x03, INSTR_RI_RU },
+	{ "nihh", 0x04, INSTR_RI_RU },
+	{ "nihl", 0x05, INSTR_RI_RU },
+	{ "nilh", 0x06, INSTR_RI_RU },
+	{ "nill", 0x07, INSTR_RI_RU },
+	{ "oihh", 0x08, INSTR_RI_RU },
+	{ "oihl", 0x09, INSTR_RI_RU },
+	{ "oilh", 0x0a, INSTR_RI_RU },
+	{ "oill", 0x0b, INSTR_RI_RU },
+	{ "llihh", 0x0c, INSTR_RI_RU },
+	{ "llihl", 0x0d, INSTR_RI_RU },
+	{ "llilh", 0x0e, INSTR_RI_RU },
+	{ "llill", 0x0f, INSTR_RI_RU },
+	{ "", 0, INSTR_INVALID }
+};
+
+static struct s390_insn opcode_a7[] = {
+	{ "tmhh", 0x02, INSTR_RI_RU },
+	{ "tmhl", 0x03, INSTR_RI_RU },
+	{ "brctg", 0x07, INSTR_RI_RP },
+	{ "lghi", 0x09, INSTR_RI_RI },
+	{ "aghi", 0x0b, INSTR_RI_RI },
+	{ "mghi", 0x0d, INSTR_RI_RI },
+	{ "cghi", 0x0f, INSTR_RI_RI },
+	{ "tmlh", 0x00, INSTR_RI_RU },
+	{ "tmll", 0x01, INSTR_RI_RU },
+	{ "brc", 0x04, INSTR_RI_UP },
+	{ "bras", 0x05, INSTR_RI_RP },
+	{ "brct", 0x06, INSTR_RI_RP },
+	{ "lhi", 0x08, INSTR_RI_RI },
+	{ "ahi", 0x0a, INSTR_RI_RI },
+	{ "mhi", 0x0c, INSTR_RI_RI },
+	{ "chi", 0x0e, INSTR_RI_RI },
+	{ "", 0, INSTR_INVALID }
+};
+
+static struct s390_insn opcode_aa[] = {
+	{ { 0, LONG_INSN_RINEXT }, 0x00, INSTR_RI_RI },
+	{ "rion", 0x01, INSTR_RI_RI },
+	{ "tric", 0x02, INSTR_RI_RI },
+	{ "rioff", 0x03, INSTR_RI_RI },
+	{ { 0, LONG_INSN_RIEMIT }, 0x04, INSTR_RI_RI },
+	{ "", 0, INSTR_INVALID }
+};
+
+static struct s390_insn opcode_b2[] = {
+	{ "stckf", 0x7c, INSTR_S_RD },
+	{ "lpp", 0x80, INSTR_S_RD },
+	{ "lcctl", 0x84, INSTR_S_RD },
+	{ "lpctl", 0x85, INSTR_S_RD },
+	{ "qsi", 0x86, INSTR_S_RD },
+	{ "lsctl", 0x87, INSTR_S_RD },
+	{ "qctri", 0x8e, INSTR_S_RD },
+	{ "stfle", 0xb0, INSTR_S_RD },
+	{ "lpswe", 0xb2, INSTR_S_RD },
+	{ "srnmb", 0xb8, INSTR_S_RD },
+	{ "srnmt", 0xb9, INSTR_S_RD },
+	{ "lfas", 0xbd, INSTR_S_RD },
+	{ "scctr", 0xe0, INSTR_RRE_RR },
+	{ "spctr", 0xe1, INSTR_RRE_RR },
+	{ "ecctr", 0xe4, INSTR_RRE_RR },
+	{ "epctr", 0xe5, INSTR_RRE_RR },
+	{ "ppa", 0xe8, INSTR_RRF_U0RR },
+	{ "etnd", 0xec, INSTR_RRE_R0 },
+	{ "ecpga", 0xed, INSTR_RRE_RR },
+	{ "tend", 0xf8, INSTR_S_00 },
+	{ "niai", 0xfa, INSTR_IE_UU },
+	{ { 0, LONG_INSN_TABORT }, 0xfc, INSTR_S_RD },
+	{ "stidp", 0x02, INSTR_S_RD },
+	{ "sck", 0x04, INSTR_S_RD },
+	{ "stck", 0x05, INSTR_S_RD },
+	{ "sckc", 0x06, INSTR_S_RD },
+	{ "stckc", 0x07, INSTR_S_RD },
+	{ "spt", 0x08, INSTR_S_RD },
+	{ "stpt", 0x09, INSTR_S_RD },
+	{ "spka", 0x0a, INSTR_S_RD },
+	{ "ipk", 0x0b, INSTR_S_00 },
+	{ "ptlb", 0x0d, INSTR_S_00 },
+	{ "spx", 0x10, INSTR_S_RD },
+	{ "stpx", 0x11, INSTR_S_RD },
+	{ "stap", 0x12, INSTR_S_RD },
+	{ "sie", 0x14, INSTR_S_RD },
+	{ "pc", 0x18, INSTR_S_RD },
+	{ "sac", 0x19, INSTR_S_RD },
+	{ "cfc", 0x1a, INSTR_S_RD },
+	{ "servc", 0x20, INSTR_RRE_RR },
+	{ "ipte", 0x21, INSTR_RRE_RR },
+	{ "ipm", 0x22, INSTR_RRE_R0 },
+	{ "ivsk", 0x23, INSTR_RRE_RR },
+	{ "iac", 0x24, INSTR_RRE_R0 },
+	{ "ssar", 0x25, INSTR_RRE_R0 },
+	{ "epar", 0x26, INSTR_RRE_R0 },
+	{ "esar", 0x27, INSTR_RRE_R0 },
+	{ "pt", 0x28, INSTR_RRE_RR },
+	{ "iske", 0x29, INSTR_RRE_RR },
+	{ "rrbe", 0x2a, INSTR_RRE_RR },
+	{ "sske", 0x2b, INSTR_RRF_M0RR },
+	{ "tb", 0x2c, INSTR_RRE_0R },
+	{ "dxr", 0x2d, INSTR_RRE_FF },
+	{ "pgin", 0x2e, INSTR_RRE_RR },
+	{ "pgout", 0x2f, INSTR_RRE_RR },
+	{ "csch", 0x30, INSTR_S_00 },
+	{ "hsch", 0x31, INSTR_S_00 },
+	{ "msch", 0x32, INSTR_S_RD },
+	{ "ssch", 0x33, INSTR_S_RD },
+	{ "stsch", 0x34, INSTR_S_RD },
+	{ "tsch", 0x35, INSTR_S_RD },
+	{ "tpi", 0x36, INSTR_S_RD },
+	{ "sal", 0x37, INSTR_S_00 },
+	{ "rsch", 0x38, INSTR_S_00 },
+	{ "stcrw", 0x39, INSTR_S_RD },
+	{ "stcps", 0x3a, INSTR_S_RD },
+	{ "rchp", 0x3b, INSTR_S_00 },
+	{ "schm", 0x3c, INSTR_S_00 },
+	{ "bakr", 0x40, INSTR_RRE_RR },
+	{ "cksm", 0x41, INSTR_RRE_RR },
+	{ "sqdr", 0x44, INSTR_RRE_FF },
+	{ "sqer", 0x45, INSTR_RRE_FF },
+	{ "stura", 0x46, INSTR_RRE_RR },
+	{ "msta", 0x47, INSTR_RRE_R0 },
+	{ "palb", 0x48, INSTR_RRE_00 },
+	{ "ereg", 0x49, INSTR_RRE_RR },
+	{ "esta", 0x4a, INSTR_RRE_RR },
+	{ "lura", 0x4b, INSTR_RRE_RR },
+	{ "tar", 0x4c, INSTR_RRE_AR },
+	{ "cpya", 0x4d, INSTR_RRE_AA },
+	{ "sar", 0x4e, INSTR_RRE_AR },
+	{ "ear", 0x4f, INSTR_RRE_RA },
+	{ "csp", 0x50, INSTR_RRE_RR },
+	{ "msr", 0x52, INSTR_RRE_RR },
+	{ "mvpg", 0x54, INSTR_RRE_RR },
+	{ "mvst", 0x55, INSTR_RRE_RR },
+	{ "cuse", 0x57, INSTR_RRE_RR },
+	{ "bsg", 0x58, INSTR_RRE_RR },
+	{ "bsa", 0x5a, INSTR_RRE_RR },
+	{ "clst", 0x5d, INSTR_RRE_RR },
+	{ "srst", 0x5e, INSTR_RRE_RR },
+	{ "cmpsc", 0x63, INSTR_RRE_RR },
+	{ "siga", 0x74, INSTR_S_RD },
+	{ "xsch", 0x76, INSTR_S_00 },
+	{ "rp", 0x77, INSTR_S_RD },
+	{ "stcke", 0x78, INSTR_S_RD },
+	{ "sacf", 0x79, INSTR_S_RD },
+	{ "stsi", 0x7d, INSTR_S_RD },
+	{ "srnm", 0x99, INSTR_S_RD },
+	{ "stfpc", 0x9c, INSTR_S_RD },
+	{ "lfpc", 0x9d, INSTR_S_RD },
+	{ "tre", 0xa5, INSTR_RRE_RR },
+	{ "cuutf", 0xa6, INSTR_RRF_M0RR },
+	{ "cutfu", 0xa7, INSTR_RRF_M0RR },
+	{ "stfl", 0xb1, INSTR_S_RD },
+	{ "trap4", 0xff, INSTR_S_RD },
+	{ "", 0, INSTR_INVALID }
+};
+
+static struct s390_insn opcode_b3[] = {
+	{ "maylr", 0x38, INSTR_RRF_F0FF },
+	{ "mylr", 0x39, INSTR_RRF_F0FF },
+	{ "mayr", 0x3a, INSTR_RRF_F0FF },
+	{ "myr", 0x3b, INSTR_RRF_F0FF },
+	{ "mayhr", 0x3c, INSTR_RRF_F0FF },
+	{ "myhr", 0x3d, INSTR_RRF_F0FF },
+	{ "lpdfr", 0x70, INSTR_RRE_FF },
+	{ "lndfr", 0x71, INSTR_RRE_FF },
+	{ "cpsdr", 0x72, INSTR_RRF_F0FF2 },
+	{ "lcdfr", 0x73, INSTR_RRE_FF },
+	{ "sfasr", 0x85, INSTR_RRE_R0 },
+	{ { 0, LONG_INSN_CELFBR }, 0x90, INSTR_RRF_UUFR },
+	{ { 0, LONG_INSN_CDLFBR }, 0x91, INSTR_RRF_UUFR },
+	{ { 0, LONG_INSN_CXLFBR }, 0x92, INSTR_RRF_UURF },
+	{ { 0, LONG_INSN_CEFBRA }, 0x94, INSTR_RRF_UUFR },
+	{ { 0, LONG_INSN_CDFBRA }, 0x95, INSTR_RRF_UUFR },
+	{ { 0, LONG_INSN_CXFBRA }, 0x96, INSTR_RRF_UURF },
+	{ { 0, LONG_INSN_CFEBRA }, 0x98, INSTR_RRF_UURF },
+	{ { 0, LONG_INSN_CFDBRA }, 0x99, INSTR_RRF_UURF },
+	{ { 0, LONG_INSN_CFXBRA }, 0x9a, INSTR_RRF_UUFR },
+	{ { 0, LONG_INSN_CLFEBR }, 0x9c, INSTR_RRF_UURF },
+	{ { 0, LONG_INSN_CLFDBR }, 0x9d, INSTR_RRF_UURF },
+	{ { 0, LONG_INSN_CLFXBR }, 0x9e, INSTR_RRF_UUFR },
+	{ { 0, LONG_INSN_CELGBR }, 0xa0, INSTR_RRF_UUFR },
+	{ { 0, LONG_INSN_CDLGBR }, 0xa1, INSTR_RRF_UUFR },
+	{ { 0, LONG_INSN_CXLGBR }, 0xa2, INSTR_RRF_UURF },
+	{ { 0, LONG_INSN_CEGBRA }, 0xa4, INSTR_RRF_UUFR },
+	{ { 0, LONG_INSN_CDGBRA }, 0xa5, INSTR_RRF_UUFR },
+	{ { 0, LONG_INSN_CXGBRA }, 0xa6, INSTR_RRF_UURF },
+	{ { 0, LONG_INSN_CGEBRA }, 0xa8, INSTR_RRF_UURF },
+	{ { 0, LONG_INSN_CGDBRA }, 0xa9, INSTR_RRF_UURF },
+	{ { 0, LONG_INSN_CGXBRA }, 0xaa, INSTR_RRF_UUFR },
+	{ { 0, LONG_INSN_CLGEBR }, 0xac, INSTR_RRF_UURF },
+	{ { 0, LONG_INSN_CLGDBR }, 0xad, INSTR_RRF_UURF },
+	{ { 0, LONG_INSN_CLGXBR }, 0xae, INSTR_RRF_UUFR },
+	{ "ldgr", 0xc1, INSTR_RRE_FR },
+	{ "cegr", 0xc4, INSTR_RRE_FR },
+	{ "cdgr", 0xc5, INSTR_RRE_FR },
+	{ "cxgr", 0xc6, INSTR_RRE_FR },
+	{ "cger", 0xc8, INSTR_RRF_U0RF },
+	{ "cgdr", 0xc9, INSTR_RRF_U0RF },
+	{ "cgxr", 0xca, INSTR_RRF_U0RF },
+	{ "lgdr", 0xcd, INSTR_RRE_RF },
+	{ "mdtra", 0xd0, INSTR_RRF_FUFF2 },
+	{ "ddtra", 0xd1, INSTR_RRF_FUFF2 },
+	{ "adtra", 0xd2, INSTR_RRF_FUFF2 },
+	{ "sdtra", 0xd3, INSTR_RRF_FUFF2 },
+	{ "ldetr", 0xd4, INSTR_RRF_0UFF },
+	{ "ledtr", 0xd5, INSTR_RRF_UUFF },
+	{ "ltdtr", 0xd6, INSTR_RRE_FF },
+	{ "fidtr", 0xd7, INSTR_RRF_UUFF },
+	{ "mxtra", 0xd8, INSTR_RRF_FUFF2 },
+	{ "dxtra", 0xd9, INSTR_RRF_FUFF2 },
+	{ "axtra", 0xda, INSTR_RRF_FUFF2 },
+	{ "sxtra", 0xdb, INSTR_RRF_FUFF2 },
+	{ "lxdtr", 0xdc, INSTR_RRF_0UFF },
+	{ "ldxtr", 0xdd, INSTR_RRF_UUFF },
+	{ "ltxtr", 0xde, INSTR_RRE_FF },
+	{ "fixtr", 0xdf, INSTR_RRF_UUFF },
+	{ "kdtr", 0xe0, INSTR_RRE_FF },
+	{ { 0, LONG_INSN_CGDTRA }, 0xe1, INSTR_RRF_UURF },
+	{ "cudtr", 0xe2, INSTR_RRE_RF },
+	{ "csdtr", 0xe3, INSTR_RRE_RF },
+	{ "cdtr", 0xe4, INSTR_RRE_FF },
+	{ "eedtr", 0xe5, INSTR_RRE_RF },
+	{ "esdtr", 0xe7, INSTR_RRE_RF },
+	{ "kxtr", 0xe8, INSTR_RRE_FF },
+	{ { 0, LONG_INSN_CGXTRA }, 0xe9, INSTR_RRF_UUFR },
+	{ "cuxtr", 0xea, INSTR_RRE_RF },
+	{ "csxtr", 0xeb, INSTR_RRE_RF },
+	{ "cxtr", 0xec, INSTR_RRE_FF },
+	{ "eextr", 0xed, INSTR_RRE_RF },
+	{ "esxtr", 0xef, INSTR_RRE_RF },
+	{ { 0, LONG_INSN_CDGTRA }, 0xf1, INSTR_RRF_UUFR },
+	{ "cdutr", 0xf2, INSTR_RRE_FR },
+	{ "cdstr", 0xf3, INSTR_RRE_FR },
+	{ "cedtr", 0xf4, INSTR_RRE_FF },
+	{ "qadtr", 0xf5, INSTR_RRF_FUFF },
+	{ "iedtr", 0xf6, INSTR_RRF_F0FR },
+	{ "rrdtr", 0xf7, INSTR_RRF_FFRU },
+	{ { 0, LONG_INSN_CXGTRA }, 0xf9, INSTR_RRF_UURF },
+	{ "cxutr", 0xfa, INSTR_RRE_FR },
+	{ "cxstr", 0xfb, INSTR_RRE_FR },
+	{ "cextr", 0xfc, INSTR_RRE_FF },
+	{ "qaxtr", 0xfd, INSTR_RRF_FUFF },
+	{ "iextr", 0xfe, INSTR_RRF_F0FR },
+	{ "rrxtr", 0xff, INSTR_RRF_FFRU },
+	{ "lpebr", 0x00, INSTR_RRE_FF },
+	{ "lnebr", 0x01, INSTR_RRE_FF },
+	{ "ltebr", 0x02, INSTR_RRE_FF },
+	{ "lcebr", 0x03, INSTR_RRE_FF },
+	{ "ldebr", 0x04, INSTR_RRE_FF },
+	{ "lxdbr", 0x05, INSTR_RRE_FF },
+	{ "lxebr", 0x06, INSTR_RRE_FF },
+	{ "mxdbr", 0x07, INSTR_RRE_FF },
+	{ "kebr", 0x08, INSTR_RRE_FF },
+	{ "cebr", 0x09, INSTR_RRE_FF },
+	{ "aebr", 0x0a, INSTR_RRE_FF },
+	{ "sebr", 0x0b, INSTR_RRE_FF },
+	{ "mdebr", 0x0c, INSTR_RRE_FF },
+	{ "debr", 0x0d, INSTR_RRE_FF },
+	{ "maebr", 0x0e, INSTR_RRF_F0FF },
+	{ "msebr", 0x0f, INSTR_RRF_F0FF },
+	{ "lpdbr", 0x10, INSTR_RRE_FF },
+	{ "lndbr", 0x11, INSTR_RRE_FF },
+	{ "ltdbr", 0x12, INSTR_RRE_FF },
+	{ "lcdbr", 0x13, INSTR_RRE_FF },
+	{ "sqebr", 0x14, INSTR_RRE_FF },
+	{ "sqdbr", 0x15, INSTR_RRE_FF },
+	{ "sqxbr", 0x16, INSTR_RRE_FF },
+	{ "meebr", 0x17, INSTR_RRE_FF },
+	{ "kdbr", 0x18, INSTR_RRE_FF },
+	{ "cdbr", 0x19, INSTR_RRE_FF },
+	{ "adbr", 0x1a, INSTR_RRE_FF },
+	{ "sdbr", 0x1b, INSTR_RRE_FF },
+	{ "mdbr", 0x1c, INSTR_RRE_FF },
+	{ "ddbr", 0x1d, INSTR_RRE_FF },
+	{ "madbr", 0x1e, INSTR_RRF_F0FF },
+	{ "msdbr", 0x1f, INSTR_RRF_F0FF },
+	{ "lder", 0x24, INSTR_RRE_FF },
+	{ "lxdr", 0x25, INSTR_RRE_FF },
+	{ "lxer", 0x26, INSTR_RRE_FF },
+	{ "maer", 0x2e, INSTR_RRF_F0FF },
+	{ "mser", 0x2f, INSTR_RRF_F0FF },
+	{ "sqxr", 0x36, INSTR_RRE_FF },
+	{ "meer", 0x37, INSTR_RRE_FF },
+	{ "madr", 0x3e, INSTR_RRF_F0FF },
+	{ "msdr", 0x3f, INSTR_RRF_F0FF },
+	{ "lpxbr", 0x40, INSTR_RRE_FF },
+	{ "lnxbr", 0x41, INSTR_RRE_FF },
+	{ "ltxbr", 0x42, INSTR_RRE_FF },
+	{ "lcxbr", 0x43, INSTR_RRE_FF },
+	{ { 0, LONG_INSN_LEDBRA }, 0x44, INSTR_RRF_UUFF },
+	{ { 0, LONG_INSN_LDXBRA }, 0x45, INSTR_RRF_UUFF },
+	{ { 0, LONG_INSN_LEXBRA }, 0x46, INSTR_RRF_UUFF },
+	{ { 0, LONG_INSN_FIXBRA }, 0x47, INSTR_RRF_UUFF },
+	{ "kxbr", 0x48, INSTR_RRE_FF },
+	{ "cxbr", 0x49, INSTR_RRE_FF },
+	{ "axbr", 0x4a, INSTR_RRE_FF },
+	{ "sxbr", 0x4b, INSTR_RRE_FF },
+	{ "mxbr", 0x4c, INSTR_RRE_FF },
+	{ "dxbr", 0x4d, INSTR_RRE_FF },
+	{ "tbedr", 0x50, INSTR_RRF_U0FF },
+	{ "tbdr", 0x51, INSTR_RRF_U0FF },
+	{ "diebr", 0x53, INSTR_RRF_FUFF },
+	{ { 0, LONG_INSN_FIEBRA }, 0x57, INSTR_RRF_UUFF },
+	{ "thder", 0x58, INSTR_RRE_FF },
+	{ "thdr", 0x59, INSTR_RRE_FF },
+	{ "didbr", 0x5b, INSTR_RRF_FUFF },
+	{ { 0, LONG_INSN_FIDBRA }, 0x5f, INSTR_RRF_UUFF },
+	{ "lpxr", 0x60, INSTR_RRE_FF },
+	{ "lnxr", 0x61, INSTR_RRE_FF },
+	{ "ltxr", 0x62, INSTR_RRE_FF },
+	{ "lcxr", 0x63, INSTR_RRE_FF },
+	{ "lxr", 0x65, INSTR_RRE_FF },
+	{ "lexr", 0x66, INSTR_RRE_FF },
+	{ "fixr", 0x67, INSTR_RRE_FF },
+	{ "cxr", 0x69, INSTR_RRE_FF },
+	{ "lzer", 0x74, INSTR_RRE_F0 },
+	{ "lzdr", 0x75, INSTR_RRE_F0 },
+	{ "lzxr", 0x76, INSTR_RRE_F0 },
+	{ "fier", 0x77, INSTR_RRE_FF },
+	{ "fidr", 0x7f, INSTR_RRE_FF },
+	{ "sfpc", 0x84, INSTR_RRE_RR_OPT },
+	{ "efpc", 0x8c, INSTR_RRE_RR_OPT },
+	{ "cefbr", 0x94, INSTR_RRE_RF },
+	{ "cdfbr", 0x95, INSTR_RRE_RF },
+	{ "cxfbr", 0x96, INSTR_RRE_RF },
+	{ "cfebr", 0x98, INSTR_RRF_U0RF },
+	{ "cfdbr", 0x99, INSTR_RRF_U0RF },
+	{ "cfxbr", 0x9a, INSTR_RRF_U0RF },
+	{ "cefr", 0xb4, INSTR_RRE_FR },
+	{ "cdfr", 0xb5, INSTR_RRE_FR },
+	{ "cxfr", 0xb6, INSTR_RRE_FR },
+	{ "cfer", 0xb8, INSTR_RRF_U0RF },
+	{ "cfdr", 0xb9, INSTR_RRF_U0RF },
+	{ "cfxr", 0xba, INSTR_RRF_U0RF },
+	{ "", 0, INSTR_INVALID }
+};
+
+static struct s390_insn opcode_b9[] = {
+	{ "lpgr", 0x00, INSTR_RRE_RR },
+	{ "lngr", 0x01, INSTR_RRE_RR },
+	{ "ltgr", 0x02, INSTR_RRE_RR },
+	{ "lcgr", 0x03, INSTR_RRE_RR },
+	{ "lgr", 0x04, INSTR_RRE_RR },
+	{ "lurag", 0x05, INSTR_RRE_RR },
+	{ "lgbr", 0x06, INSTR_RRE_RR },
+	{ "lghr", 0x07, INSTR_RRE_RR },
+	{ "agr", 0x08, INSTR_RRE_RR },
+	{ "sgr", 0x09, INSTR_RRE_RR },
+	{ "algr", 0x0a, INSTR_RRE_RR },
+	{ "slgr", 0x0b, INSTR_RRE_RR },
+	{ "msgr", 0x0c, INSTR_RRE_RR },
+	{ "dsgr", 0x0d, INSTR_RRE_RR },
+	{ "eregg", 0x0e, INSTR_RRE_RR },
+	{ "lrvgr", 0x0f, INSTR_RRE_RR },
+	{ "lpgfr", 0x10, INSTR_RRE_RR },
+	{ "lngfr", 0x11, INSTR_RRE_RR },
+	{ "ltgfr", 0x12, INSTR_RRE_RR },
+	{ "lcgfr", 0x13, INSTR_RRE_RR },
+	{ "lgfr", 0x14, INSTR_RRE_RR },
+	{ "llgfr", 0x16, INSTR_RRE_RR },
+	{ "llgtr", 0x17, INSTR_RRE_RR },
+	{ "agfr", 0x18, INSTR_RRE_RR },
+	{ "sgfr", 0x19, INSTR_RRE_RR },
+	{ "algfr", 0x1a, INSTR_RRE_RR },
+	{ "slgfr", 0x1b, INSTR_RRE_RR },
+	{ "msgfr", 0x1c, INSTR_RRE_RR },
+	{ "dsgfr", 0x1d, INSTR_RRE_RR },
+	{ "cgr", 0x20, INSTR_RRE_RR },
+	{ "clgr", 0x21, INSTR_RRE_RR },
+	{ "sturg", 0x25, INSTR_RRE_RR },
+	{ "lbr", 0x26, INSTR_RRE_RR },
+	{ "lhr", 0x27, INSTR_RRE_RR },
+	{ "cgfr", 0x30, INSTR_RRE_RR },
+	{ "clgfr", 0x31, INSTR_RRE_RR },
+	{ "cfdtr", 0x41, INSTR_RRF_UURF },
+	{ { 0, LONG_INSN_CLGDTR }, 0x42, INSTR_RRF_UURF },
+	{ { 0, LONG_INSN_CLFDTR }, 0x43, INSTR_RRF_UURF },
+	{ "bctgr", 0x46, INSTR_RRE_RR },
+	{ "cfxtr", 0x49, INSTR_RRF_UURF },
+	{ { 0, LONG_INSN_CLGXTR }, 0x4a, INSTR_RRF_UUFR },
+	{ { 0, LONG_INSN_CLFXTR }, 0x4b, INSTR_RRF_UUFR },
+	{ "cdftr", 0x51, INSTR_RRF_UUFR },
+	{ { 0, LONG_INSN_CDLGTR }, 0x52, INSTR_RRF_UUFR },
+	{ { 0, LONG_INSN_CDLFTR }, 0x53, INSTR_RRF_UUFR },
+	{ "cxftr", 0x59, INSTR_RRF_UURF },
+	{ { 0, LONG_INSN_CXLGTR }, 0x5a, INSTR_RRF_UURF },
+	{ { 0, LONG_INSN_CXLFTR }, 0x5b, INSTR_RRF_UUFR },
+	{ "cgrt", 0x60, INSTR_RRF_U0RR },
+	{ "clgrt", 0x61, INSTR_RRF_U0RR },
+	{ "crt", 0x72, INSTR_RRF_U0RR },
+	{ "clrt", 0x73, INSTR_RRF_U0RR },
+	{ "ngr", 0x80, INSTR_RRE_RR },
+	{ "ogr", 0x81, INSTR_RRE_RR },
+	{ "xgr", 0x82, INSTR_RRE_RR },
+	{ "flogr", 0x83, INSTR_RRE_RR },
+	{ "llgcr", 0x84, INSTR_RRE_RR },
+	{ "llghr", 0x85, INSTR_RRE_RR },
+	{ "mlgr", 0x86, INSTR_RRE_RR },
+	{ "dlgr", 0x87, INSTR_RRE_RR },
+	{ "alcgr", 0x88, INSTR_RRE_RR },
+	{ "slbgr", 0x89, INSTR_RRE_RR },
+	{ "cspg", 0x8a, INSTR_RRE_RR },
+	{ "idte", 0x8e, INSTR_RRF_R0RR },
+	{ "crdte", 0x8f, INSTR_RRF_RMRR },
+	{ "llcr", 0x94, INSTR_RRE_RR },
+	{ "llhr", 0x95, INSTR_RRE_RR },
+	{ "esea", 0x9d, INSTR_RRE_R0 },
+	{ "ptf", 0xa2, INSTR_RRE_R0 },
+	{ "lptea", 0xaa, INSTR_RRF_RURR },
+	{ "rrbm", 0xae, INSTR_RRE_RR },
+	{ "pfmf", 0xaf, INSTR_RRE_RR },
+	{ "cu14", 0xb0, INSTR_RRF_M0RR },
+	{ "cu24", 0xb1, INSTR_RRF_M0RR },
+	{ "cu41", 0xb2, INSTR_RRE_RR },
+	{ "cu42", 0xb3, INSTR_RRE_RR },
+	{ "trtre", 0xbd, INSTR_RRF_M0RR },
+	{ "srstu", 0xbe, INSTR_RRE_RR },
+	{ "trte", 0xbf, INSTR_RRF_M0RR },
+	{ "ahhhr", 0xc8, INSTR_RRF_R0RR2 },
+	{ "shhhr", 0xc9, INSTR_RRF_R0RR2 },
+	{ { 0, LONG_INSN_ALHHHR }, 0xca, INSTR_RRF_R0RR2 },
+	{ { 0, LONG_INSN_SLHHHR }, 0xcb, INSTR_RRF_R0RR2 },
+	{ "chhr", 0xcd, INSTR_RRE_RR },
+	{ "clhhr", 0xcf, INSTR_RRE_RR },
+	{ { 0, LONG_INSN_PCISTG }, 0xd0, INSTR_RRE_RR },
+	{ "pcilg", 0xd2, INSTR_RRE_RR },
+	{ "rpcit", 0xd3, INSTR_RRE_RR },
+	{ "ahhlr", 0xd8, INSTR_RRF_R0RR2 },
+	{ "shhlr", 0xd9, INSTR_RRF_R0RR2 },
+	{ { 0, LONG_INSN_ALHHLR }, 0xda, INSTR_RRF_R0RR2 },
+	{ { 0, LONG_INSN_SLHHLR }, 0xdb, INSTR_RRF_R0RR2 },
+	{ "chlr", 0xdd, INSTR_RRE_RR },
+	{ "clhlr", 0xdf, INSTR_RRE_RR },
+	{ { 0, LONG_INSN_POPCNT }, 0xe1, INSTR_RRE_RR },
+	{ "locgr", 0xe2, INSTR_RRF_M0RR },
+	{ "ngrk", 0xe4, INSTR_RRF_R0RR2 },
+	{ "ogrk", 0xe6, INSTR_RRF_R0RR2 },
+	{ "xgrk", 0xe7, INSTR_RRF_R0RR2 },
+	{ "agrk", 0xe8, INSTR_RRF_R0RR2 },
+	{ "sgrk", 0xe9, INSTR_RRF_R0RR2 },
+	{ "algrk", 0xea, INSTR_RRF_R0RR2 },
+	{ "slgrk", 0xeb, INSTR_RRF_R0RR2 },
+	{ "locr", 0xf2, INSTR_RRF_M0RR },
+	{ "nrk", 0xf4, INSTR_RRF_R0RR2 },
+	{ "ork", 0xf6, INSTR_RRF_R0RR2 },
+	{ "xrk", 0xf7, INSTR_RRF_R0RR2 },
+	{ "ark", 0xf8, INSTR_RRF_R0RR2 },
+	{ "srk", 0xf9, INSTR_RRF_R0RR2 },
+	{ "alrk", 0xfa, INSTR_RRF_R0RR2 },
+	{ "slrk", 0xfb, INSTR_RRF_R0RR2 },
+	{ "kmac", 0x1e, INSTR_RRE_RR },
+	{ "lrvr", 0x1f, INSTR_RRE_RR },
+	{ "km", 0x2e, INSTR_RRE_RR },
+	{ "kmc", 0x2f, INSTR_RRE_RR },
+	{ "kimd", 0x3e, INSTR_RRE_RR },
+	{ "klmd", 0x3f, INSTR_RRE_RR },
+	{ "epsw", 0x8d, INSTR_RRE_RR },
+	{ "trtt", 0x90, INSTR_RRF_M0RR },
+	{ "trto", 0x91, INSTR_RRF_M0RR },
+	{ "trot", 0x92, INSTR_RRF_M0RR },
+	{ "troo", 0x93, INSTR_RRF_M0RR },
+	{ "mlr", 0x96, INSTR_RRE_RR },
+	{ "dlr", 0x97, INSTR_RRE_RR },
+	{ "alcr", 0x98, INSTR_RRE_RR },
+	{ "slbr", 0x99, INSTR_RRE_RR },
+	{ "", 0, INSTR_INVALID }
+};
+
+static struct s390_insn opcode_c0[] = {
+	{ "lgfi", 0x01, INSTR_RIL_RI },
+	{ "xihf", 0x06, INSTR_RIL_RU },
+	{ "xilf", 0x07, INSTR_RIL_RU },
+	{ "iihf", 0x08, INSTR_RIL_RU },
+	{ "iilf", 0x09, INSTR_RIL_RU },
+	{ "nihf", 0x0a, INSTR_RIL_RU },
+	{ "nilf", 0x0b, INSTR_RIL_RU },
+	{ "oihf", 0x0c, INSTR_RIL_RU },
+	{ "oilf", 0x0d, INSTR_RIL_RU },
+	{ "llihf", 0x0e, INSTR_RIL_RU },
+	{ "llilf", 0x0f, INSTR_RIL_RU },
+	{ "larl", 0x00, INSTR_RIL_RP },
+	{ "brcl", 0x04, INSTR_RIL_UP },
+	{ "brasl", 0x05, INSTR_RIL_RP },
+	{ "", 0, INSTR_INVALID }
+};
+
+static struct s390_insn opcode_c2[] = {
+	{ "msgfi", 0x00, INSTR_RIL_RI },
+	{ "msfi", 0x01, INSTR_RIL_RI },
+	{ "slgfi", 0x04, INSTR_RIL_RU },
+	{ "slfi", 0x05, INSTR_RIL_RU },
+	{ "agfi", 0x08, INSTR_RIL_RI },
+	{ "afi", 0x09, INSTR_RIL_RI },
+	{ "algfi", 0x0a, INSTR_RIL_RU },
+	{ "alfi", 0x0b, INSTR_RIL_RU },
+	{ "cgfi", 0x0c, INSTR_RIL_RI },
+	{ "cfi", 0x0d, INSTR_RIL_RI },
+	{ "clgfi", 0x0e, INSTR_RIL_RU },
+	{ "clfi", 0x0f, INSTR_RIL_RU },
+	{ "", 0, INSTR_INVALID }
+};
+
+static struct s390_insn opcode_c4[] = {
+	{ "llhrl", 0x02, INSTR_RIL_RP },
+	{ "lghrl", 0x04, INSTR_RIL_RP },
+	{ "lhrl", 0x05, INSTR_RIL_RP },
+	{ { 0, LONG_INSN_LLGHRL }, 0x06, INSTR_RIL_RP },
+	{ "sthrl", 0x07, INSTR_RIL_RP },
+	{ "lgrl", 0x08, INSTR_RIL_RP },
+	{ "stgrl", 0x0b, INSTR_RIL_RP },
+	{ "lgfrl", 0x0c, INSTR_RIL_RP },
+	{ "lrl", 0x0d, INSTR_RIL_RP },
+	{ { 0, LONG_INSN_LLGFRL }, 0x0e, INSTR_RIL_RP },
+	{ "strl", 0x0f, INSTR_RIL_RP },
+	{ "", 0, INSTR_INVALID }
+};
+
+static struct s390_insn opcode_c6[] = {
+	{ "exrl", 0x00, INSTR_RIL_RP },
+	{ "pfdrl", 0x02, INSTR_RIL_UP },
+	{ "cghrl", 0x04, INSTR_RIL_RP },
+	{ "chrl", 0x05, INSTR_RIL_RP },
+	{ { 0, LONG_INSN_CLGHRL }, 0x06, INSTR_RIL_RP },
+	{ "clhrl", 0x07, INSTR_RIL_RP },
+	{ "cgrl", 0x08, INSTR_RIL_RP },
+	{ "clgrl", 0x0a, INSTR_RIL_RP },
+	{ "cgfrl", 0x0c, INSTR_RIL_RP },
+	{ "crl", 0x0d, INSTR_RIL_RP },
+	{ { 0, LONG_INSN_CLGFRL }, 0x0e, INSTR_RIL_RP },
+	{ "clrl", 0x0f, INSTR_RIL_RP },
+	{ "", 0, INSTR_INVALID }
+};
+
+static struct s390_insn opcode_c8[] = {
+	{ "mvcos", 0x00, INSTR_SSF_RRDRD },
+	{ "ectg", 0x01, INSTR_SSF_RRDRD },
+	{ "csst", 0x02, INSTR_SSF_RRDRD },
+	{ "lpd", 0x04, INSTR_SSF_RRDRD2 },
+	{ "lpdg", 0x05, INSTR_SSF_RRDRD2 },
+	{ "", 0, INSTR_INVALID }
+};
+
+static struct s390_insn opcode_cc[] = {
+	{ "brcth", 0x06, INSTR_RIL_RP },
+	{ "aih", 0x08, INSTR_RIL_RI },
+	{ "alsih", 0x0a, INSTR_RIL_RI },
+	{ { 0, LONG_INSN_ALSIHN }, 0x0b, INSTR_RIL_RI },
+	{ "cih", 0x0d, INSTR_RIL_RI },
+	{ "clih", 0x0f, INSTR_RIL_RI },
+	{ "", 0, INSTR_INVALID }
+};
+
+static struct s390_insn opcode_e3[] = {
+	{ "ltg", 0x02, INSTR_RXY_RRRD },
+	{ "lrag", 0x03, INSTR_RXY_RRRD },
+	{ "lg", 0x04, INSTR_RXY_RRRD },
+	{ "cvby", 0x06, INSTR_RXY_RRRD },
+	{ "ag", 0x08, INSTR_RXY_RRRD },
+	{ "sg", 0x09, INSTR_RXY_RRRD },
+	{ "alg", 0x0a, INSTR_RXY_RRRD },
+	{ "slg", 0x0b, INSTR_RXY_RRRD },
+	{ "msg", 0x0c, INSTR_RXY_RRRD },
+	{ "dsg", 0x0d, INSTR_RXY_RRRD },
+	{ "cvbg", 0x0e, INSTR_RXY_RRRD },
+	{ "lrvg", 0x0f, INSTR_RXY_RRRD },
+	{ "lt", 0x12, INSTR_RXY_RRRD },
+	{ "lray", 0x13, INSTR_RXY_RRRD },
+	{ "lgf", 0x14, INSTR_RXY_RRRD },
+	{ "lgh", 0x15, INSTR_RXY_RRRD },
+	{ "llgf", 0x16, INSTR_RXY_RRRD },
+	{ "llgt", 0x17, INSTR_RXY_RRRD },
+	{ "agf", 0x18, INSTR_RXY_RRRD },
+	{ "sgf", 0x19, INSTR_RXY_RRRD },
+	{ "algf", 0x1a, INSTR_RXY_RRRD },
+	{ "slgf", 0x1b, INSTR_RXY_RRRD },
+	{ "msgf", 0x1c, INSTR_RXY_RRRD },
+	{ "dsgf", 0x1d, INSTR_RXY_RRRD },
+	{ "cg", 0x20, INSTR_RXY_RRRD },
+	{ "clg", 0x21, INSTR_RXY_RRRD },
+	{ "stg", 0x24, INSTR_RXY_RRRD },
+	{ "ntstg", 0x25, INSTR_RXY_RRRD },
+	{ "cvdy", 0x26, INSTR_RXY_RRRD },
+	{ "cvdg", 0x2e, INSTR_RXY_RRRD },
+	{ "strvg", 0x2f, INSTR_RXY_RRRD },
+	{ "cgf", 0x30, INSTR_RXY_RRRD },
+	{ "clgf", 0x31, INSTR_RXY_RRRD },
+	{ "ltgf", 0x32, INSTR_RXY_RRRD },
+	{ "cgh", 0x34, INSTR_RXY_RRRD },
+	{ "pfd", 0x36, INSTR_RXY_URRD },
+	{ "strvh", 0x3f, INSTR_RXY_RRRD },
+	{ "bctg", 0x46, INSTR_RXY_RRRD },
+	{ "sty", 0x50, INSTR_RXY_RRRD },
+	{ "msy", 0x51, INSTR_RXY_RRRD },
+	{ "ny", 0x54, INSTR_RXY_RRRD },
+	{ "cly", 0x55, INSTR_RXY_RRRD },
+	{ "oy", 0x56, INSTR_RXY_RRRD },
+	{ "xy", 0x57, INSTR_RXY_RRRD },
+	{ "ly", 0x58, INSTR_RXY_RRRD },
+	{ "cy", 0x59, INSTR_RXY_RRRD },
+	{ "ay", 0x5a, INSTR_RXY_RRRD },
+	{ "sy", 0x5b, INSTR_RXY_RRRD },
+	{ "mfy", 0x5c, INSTR_RXY_RRRD },
+	{ "aly", 0x5e, INSTR_RXY_RRRD },
+	{ "sly", 0x5f, INSTR_RXY_RRRD },
+	{ "sthy", 0x70, INSTR_RXY_RRRD },
+	{ "lay", 0x71, INSTR_RXY_RRRD },
+	{ "stcy", 0x72, INSTR_RXY_RRRD },
+	{ "icy", 0x73, INSTR_RXY_RRRD },
+	{ "laey", 0x75, INSTR_RXY_RRRD },
+	{ "lb", 0x76, INSTR_RXY_RRRD },
+	{ "lgb", 0x77, INSTR_RXY_RRRD },
+	{ "lhy", 0x78, INSTR_RXY_RRRD },
+	{ "chy", 0x79, INSTR_RXY_RRRD },
+	{ "ahy", 0x7a, INSTR_RXY_RRRD },
+	{ "shy", 0x7b, INSTR_RXY_RRRD },
+	{ "mhy", 0x7c, INSTR_RXY_RRRD },
+	{ "ng", 0x80, INSTR_RXY_RRRD },
+	{ "og", 0x81, INSTR_RXY_RRRD },
+	{ "xg", 0x82, INSTR_RXY_RRRD },
+	{ "lgat", 0x85, INSTR_RXY_RRRD },
+	{ "mlg", 0x86, INSTR_RXY_RRRD },
+	{ "dlg", 0x87, INSTR_RXY_RRRD },
+	{ "alcg", 0x88, INSTR_RXY_RRRD },
+	{ "slbg", 0x89, INSTR_RXY_RRRD },
+	{ "stpq", 0x8e, INSTR_RXY_RRRD },
+	{ "lpq", 0x8f, INSTR_RXY_RRRD },
+	{ "llgc", 0x90, INSTR_RXY_RRRD },
+	{ "llgh", 0x91, INSTR_RXY_RRRD },
+	{ "llc", 0x94, INSTR_RXY_RRRD },
+	{ "llh", 0x95, INSTR_RXY_RRRD },
+	{ { 0, LONG_INSN_LLGTAT }, 0x9c, INSTR_RXY_RRRD },
+	{ { 0, LONG_INSN_LLGFAT }, 0x9d, INSTR_RXY_RRRD },
+	{ "lat", 0x9f, INSTR_RXY_RRRD },
+	{ "lbh", 0xc0, INSTR_RXY_RRRD },
+	{ "llch", 0xc2, INSTR_RXY_RRRD },
+	{ "stch", 0xc3, INSTR_RXY_RRRD },
+	{ "lhh", 0xc4, INSTR_RXY_RRRD },
+	{ "llhh", 0xc6, INSTR_RXY_RRRD },
+	{ "sthh", 0xc7, INSTR_RXY_RRRD },
+	{ "lfhat", 0xc8, INSTR_RXY_RRRD },
+	{ "lfh", 0xca, INSTR_RXY_RRRD },
+	{ "stfh", 0xcb, INSTR_RXY_RRRD },
+	{ "chf", 0xcd, INSTR_RXY_RRRD },
+	{ "clhf", 0xcf, INSTR_RXY_RRRD },
+	{ { 0, LONG_INSN_MPCIFC }, 0xd0, INSTR_RXY_RRRD },
+	{ { 0, LONG_INSN_STPCIFC }, 0xd4, INSTR_RXY_RRRD },
+	{ "lrv", 0x1e, INSTR_RXY_RRRD },
+	{ "lrvh", 0x1f, INSTR_RXY_RRRD },
+	{ "strv", 0x3e, INSTR_RXY_RRRD },
+	{ "ml", 0x96, INSTR_RXY_RRRD },
+	{ "dl", 0x97, INSTR_RXY_RRRD },
+	{ "alc", 0x98, INSTR_RXY_RRRD },
+	{ "slb", 0x99, INSTR_RXY_RRRD },
+	{ "", 0, INSTR_INVALID }
+};
+
+static struct s390_insn opcode_e5[] = {
+	{ "strag", 0x02, INSTR_SSE_RDRD },
+	{ "mvhhi", 0x44, INSTR_SIL_RDI },
+	{ "mvghi", 0x48, INSTR_SIL_RDI },
+	{ "mvhi", 0x4c, INSTR_SIL_RDI },
+	{ "chhsi", 0x54, INSTR_SIL_RDI },
+	{ { 0, LONG_INSN_CLHHSI }, 0x55, INSTR_SIL_RDU },
+	{ "cghsi", 0x58, INSTR_SIL_RDI },
+	{ { 0, LONG_INSN_CLGHSI }, 0x59, INSTR_SIL_RDU },
+	{ "chsi", 0x5c, INSTR_SIL_RDI },
+	{ { 0, LONG_INSN_CLFHSI }, 0x5d, INSTR_SIL_RDU },
+	{ { 0, LONG_INSN_TBEGIN }, 0x60, INSTR_SIL_RDU },
+	{ { 0, LONG_INSN_TBEGINC }, 0x61, INSTR_SIL_RDU },
+	{ "lasp", 0x00, INSTR_SSE_RDRD },
+	{ "tprot", 0x01, INSTR_SSE_RDRD },
+	{ "mvcsk", 0x0e, INSTR_SSE_RDRD },
+	{ "mvcdk", 0x0f, INSTR_SSE_RDRD },
+	{ "", 0, INSTR_INVALID }
+};
+
+static struct s390_insn opcode_e7[] = {
+	{ "lcbb", 0x27, INSTR_RXE_RRRDM },
+	{ "vgef", 0x13, INSTR_VRV_VVRDM },
+	{ "vgeg", 0x12, INSTR_VRV_VVRDM },
+	{ "vgbm", 0x44, INSTR_VRI_V0I0 },
+	{ "vgm", 0x46, INSTR_VRI_V0IIM },
+	{ "vl", 0x06, INSTR_VRX_VRRD0 },
+	{ "vlr", 0x56, INSTR_VRR_VV00000 },
+	{ "vlrp", 0x05, INSTR_VRX_VRRDM },
+	{ "vleb", 0x00, INSTR_VRX_VRRDM },
+	{ "vleh", 0x01, INSTR_VRX_VRRDM },
+	{ "vlef", 0x03, INSTR_VRX_VRRDM },
+	{ "vleg", 0x02, INSTR_VRX_VRRDM },
+	{ "vleib", 0x40, INSTR_VRI_V0IM },
+	{ "vleih", 0x41, INSTR_VRI_V0IM },
+	{ "vleif", 0x43, INSTR_VRI_V0IM },
+	{ "vleig", 0x42, INSTR_VRI_V0IM },
+	{ "vlgv", 0x21, INSTR_VRS_RVRDM },
+	{ "vllez", 0x04, INSTR_VRX_VRRDM },
+	{ "vlm", 0x36, INSTR_VRS_VVRD0 },
+	{ "vlbb", 0x07, INSTR_VRX_VRRDM },
+	{ "vlvg", 0x22, INSTR_VRS_VRRDM },
+	{ "vlvgp", 0x62, INSTR_VRR_VRR0000 },
+	{ "vll", 0x37, INSTR_VRS_VRRD0 },
+	{ "vmrh", 0x61, INSTR_VRR_VVV000M },
+	{ "vmrl", 0x60, INSTR_VRR_VVV000M },
+	{ "vpk", 0x94, INSTR_VRR_VVV000M },
+	{ "vpks", 0x97, INSTR_VRR_VVV0M0M },
+	{ "vpkls", 0x95, INSTR_VRR_VVV0M0M },
+	{ "vperm", 0x8c, INSTR_VRR_VVV000V },
+	{ "vpdi", 0x84, INSTR_VRR_VVV000M },
+	{ "vrep", 0x4d, INSTR_VRI_VVIM },
+	{ "vrepi", 0x45, INSTR_VRI_V0IM },
+	{ "vscef", 0x1b, INSTR_VRV_VWRDM },
+	{ "vsceg", 0x1a, INSTR_VRV_VWRDM },
+	{ "vsel", 0x8d, INSTR_VRR_VVV000V },
+	{ "vseg", 0x5f, INSTR_VRR_VV0000M },
+	{ "vst", 0x0e, INSTR_VRX_VRRD0 },
+	{ "vsteb", 0x08, INSTR_VRX_VRRDM },
+	{ "vsteh", 0x09, INSTR_VRX_VRRDM },
+	{ "vstef", 0x0b, INSTR_VRX_VRRDM },
+	{ "vsteg", 0x0a, INSTR_VRX_VRRDM },
+	{ "vstm", 0x3e, INSTR_VRS_VVRD0 },
+	{ "vstl", 0x3f, INSTR_VRS_VRRD0 },
+	{ "vuph", 0xd7, INSTR_VRR_VV0000M },
+	{ "vuplh", 0xd5, INSTR_VRR_VV0000M },
+	{ "vupl", 0xd6, INSTR_VRR_VV0000M },
+	{ "vupll", 0xd4, INSTR_VRR_VV0000M },
+	{ "va", 0xf3, INSTR_VRR_VVV000M },
+	{ "vacc", 0xf1, INSTR_VRR_VVV000M },
+	{ "vac", 0xbb, INSTR_VRR_VVVM00V },
+	{ "vaccc", 0xb9, INSTR_VRR_VVVM00V },
+	{ "vn", 0x68, INSTR_VRR_VVV0000 },
+	{ "vnc", 0x69, INSTR_VRR_VVV0000 },
+	{ "vavg", 0xf2, INSTR_VRR_VVV000M },
+	{ "vavgl", 0xf0, INSTR_VRR_VVV000M },
+	{ "vcksm", 0x66, INSTR_VRR_VVV0000 },
+	{ "vec", 0xdb, INSTR_VRR_VV0000M },
+	{ "vecl", 0xd9, INSTR_VRR_VV0000M },
+	{ "vceq", 0xf8, INSTR_VRR_VVV0M0M },
+	{ "vch", 0xfb, INSTR_VRR_VVV0M0M },
+	{ "vchl", 0xf9, INSTR_VRR_VVV0M0M },
+	{ "vclz", 0x53, INSTR_VRR_VV0000M },
+	{ "vctz", 0x52, INSTR_VRR_VV0000M },
+	{ "vx", 0x6d, INSTR_VRR_VVV0000 },
+	{ "vgfm", 0xb4, INSTR_VRR_VVV000M },
+	{ "vgfma", 0xbc, INSTR_VRR_VVVM00V },
+	{ "vlc", 0xde, INSTR_VRR_VV0000M },
+	{ "vlp", 0xdf, INSTR_VRR_VV0000M },
+	{ "vmx", 0xff, INSTR_VRR_VVV000M },
+	{ "vmxl", 0xfd, INSTR_VRR_VVV000M },
+	{ "vmn", 0xfe, INSTR_VRR_VVV000M },
+	{ "vmnl", 0xfc, INSTR_VRR_VVV000M },
+	{ "vmal", 0xaa, INSTR_VRR_VVVM00V },
+	{ "vmae", 0xae, INSTR_VRR_VVVM00V },
+	{ "vmale", 0xac, INSTR_VRR_VVVM00V },
+	{ "vmah", 0xab, INSTR_VRR_VVVM00V },
+	{ "vmalh", 0xa9, INSTR_VRR_VVVM00V },
+	{ "vmao", 0xaf, INSTR_VRR_VVVM00V },
+	{ "vmalo", 0xad, INSTR_VRR_VVVM00V },
+	{ "vmh", 0xa3, INSTR_VRR_VVV000M },
+	{ "vmlh", 0xa1, INSTR_VRR_VVV000M },
+	{ "vml", 0xa2, INSTR_VRR_VVV000M },
+	{ "vme", 0xa6, INSTR_VRR_VVV000M },
+	{ "vmle", 0xa4, INSTR_VRR_VVV000M },
+	{ "vmo", 0xa7, INSTR_VRR_VVV000M },
+	{ "vmlo", 0xa5, INSTR_VRR_VVV000M },
+	{ "vno", 0x6b, INSTR_VRR_VVV0000 },
+	{ "vo", 0x6a, INSTR_VRR_VVV0000 },
+	{ { 0, LONG_INSN_VPOPCT }, 0x50, INSTR_VRR_VV0000M },
+	{ { 0, LONG_INSN_VERLLV }, 0x73, INSTR_VRR_VVV000M },
+	{ "verll", 0x33, INSTR_VRS_VVRDM },
+	{ "verim", 0x72, INSTR_VRI_VVV0IM },
+	{ "veslv", 0x70, INSTR_VRR_VVV000M },
+	{ "vesl", 0x30, INSTR_VRS_VVRDM },
+	{ { 0, LONG_INSN_VESRAV }, 0x7a, INSTR_VRR_VVV000M },
+	{ "vesra", 0x3a, INSTR_VRS_VVRDM },
+	{ { 0, LONG_INSN_VESRLV }, 0x78, INSTR_VRR_VVV000M },
+	{ "vesrl", 0x38, INSTR_VRS_VVRDM },
+	{ "vsl", 0x74, INSTR_VRR_VVV0000 },
+	{ "vslb", 0x75, INSTR_VRR_VVV0000 },
+	{ "vsldb", 0x77, INSTR_VRI_VVV0I0 },
+	{ "vsra", 0x7e, INSTR_VRR_VVV0000 },
+	{ "vsrab", 0x7f, INSTR_VRR_VVV0000 },
+	{ "vsrl", 0x7c, INSTR_VRR_VVV0000 },
+	{ "vsrlb", 0x7d, INSTR_VRR_VVV0000 },
+	{ "vs", 0xf7, INSTR_VRR_VVV000M },
+	{ "vscb", 0xf5, INSTR_VRR_VVV000M },
+	{ "vsb", 0xbf, INSTR_VRR_VVVM00V },
+	{ { 0, LONG_INSN_VSBCBI }, 0xbd, INSTR_VRR_VVVM00V },
+	{ "vsumg", 0x65, INSTR_VRR_VVV000M },
+	{ "vsumq", 0x67, INSTR_VRR_VVV000M },
+	{ "vsum", 0x64, INSTR_VRR_VVV000M },
+	{ "vtm", 0xd8, INSTR_VRR_VV00000 },
+	{ "vfae", 0x82, INSTR_VRR_VVV0M0M },
+	{ "vfee", 0x80, INSTR_VRR_VVV0M0M },
+	{ "vfene", 0x81, INSTR_VRR_VVV0M0M },
+	{ "vistr", 0x5c, INSTR_VRR_VV00M0M },
+	{ "vstrc", 0x8a, INSTR_VRR_VVVMM0V },
+	{ "vfa", 0xe3, INSTR_VRR_VVV00MM },
+	{ "wfc", 0xcb, INSTR_VRR_VV000MM },
+	{ "wfk", 0xca, INSTR_VRR_VV000MM },
+	{ "vfce", 0xe8, INSTR_VRR_VVV0MMM },
+	{ "vfch", 0xeb, INSTR_VRR_VVV0MMM },
+	{ "vfche", 0xea, INSTR_VRR_VVV0MMM },
+	{ "vcdg", 0xc3, INSTR_VRR_VV00MMM },
+	{ "vcdlg", 0xc1, INSTR_VRR_VV00MMM },
+	{ "vcgd", 0xc2, INSTR_VRR_VV00MMM },
+	{ "vclgd", 0xc0, INSTR_VRR_VV00MMM },
+	{ "vfd", 0xe5, INSTR_VRR_VVV00MM },
+	{ "vfi", 0xc7, INSTR_VRR_VV00MMM },
+	{ "vlde", 0xc4, INSTR_VRR_VV000MM },
+	{ "vled", 0xc5, INSTR_VRR_VV00MMM },
+	{ "vfm", 0xe7, INSTR_VRR_VVV00MM },
+	{ "vfma", 0x8f, INSTR_VRR_VVVM0MV },
+	{ "vfms", 0x8e, INSTR_VRR_VVVM0MV },
+	{ "vfpso", 0xcc, INSTR_VRR_VV00MMM },
+	{ "vfsq", 0xce, INSTR_VRR_VV000MM },
+	{ "vfs", 0xe2, INSTR_VRR_VVV00MM },
+	{ "vftci", 0x4a, INSTR_VRI_VVIMM },
+};
+
+static struct s390_insn opcode_eb[] = {
+	{ "lmg", 0x04, INSTR_RSY_RRRD },
+	{ "srag", 0x0a, INSTR_RSY_RRRD },
+	{ "slag", 0x0b, INSTR_RSY_RRRD },
+	{ "srlg", 0x0c, INSTR_RSY_RRRD },
+	{ "sllg", 0x0d, INSTR_RSY_RRRD },
+	{ "tracg", 0x0f, INSTR_RSY_RRRD },
+	{ "csy", 0x14, INSTR_RSY_RRRD },
+	{ "rllg", 0x1c, INSTR_RSY_RRRD },
+	{ "clmh", 0x20, INSTR_RSY_RURD },
+	{ "clmy", 0x21, INSTR_RSY_RURD },
+	{ "clt", 0x23, INSTR_RSY_RURD },
+	{ "stmg", 0x24, INSTR_RSY_RRRD },
+	{ "stctg", 0x25, INSTR_RSY_CCRD },
+	{ "stmh", 0x26, INSTR_RSY_RRRD },
+	{ "clgt", 0x2b, INSTR_RSY_RURD },
+	{ "stcmh", 0x2c, INSTR_RSY_RURD },
+	{ "stcmy", 0x2d, INSTR_RSY_RURD },
+	{ "lctlg", 0x2f, INSTR_RSY_CCRD },
+	{ "csg", 0x30, INSTR_RSY_RRRD },
+	{ "cdsy", 0x31, INSTR_RSY_RRRD },
+	{ "cdsg", 0x3e, INSTR_RSY_RRRD },
+	{ "bxhg", 0x44, INSTR_RSY_RRRD },
+	{ "bxleg", 0x45, INSTR_RSY_RRRD },
+	{ "ecag", 0x4c, INSTR_RSY_RRRD },
+	{ "tmy", 0x51, INSTR_SIY_URD },
+	{ "mviy", 0x52, INSTR_SIY_URD },
+	{ "niy", 0x54, INSTR_SIY_URD },
+	{ "cliy", 0x55, INSTR_SIY_URD },
+	{ "oiy", 0x56, INSTR_SIY_URD },
+	{ "xiy", 0x57, INSTR_SIY_URD },
+	{ "asi", 0x6a, INSTR_SIY_IRD },
+	{ "alsi", 0x6e, INSTR_SIY_IRD },
+	{ "agsi", 0x7a, INSTR_SIY_IRD },
+	{ "algsi", 0x7e, INSTR_SIY_IRD },
+	{ "icmh", 0x80, INSTR_RSY_RURD },
+	{ "icmy", 0x81, INSTR_RSY_RURD },
+	{ "clclu", 0x8f, INSTR_RSY_RRRD },
+	{ "stmy", 0x90, INSTR_RSY_RRRD },
+	{ "lmh", 0x96, INSTR_RSY_RRRD },
+	{ "lmy", 0x98, INSTR_RSY_RRRD },
+	{ "lamy", 0x9a, INSTR_RSY_AARD },
+	{ "stamy", 0x9b, INSTR_RSY_AARD },
+	{ { 0, LONG_INSN_PCISTB }, 0xd0, INSTR_RSY_RRRD },
+	{ "sic", 0xd1, INSTR_RSY_RRRD },
+	{ "srak", 0xdc, INSTR_RSY_RRRD },
+	{ "slak", 0xdd, INSTR_RSY_RRRD },
+	{ "srlk", 0xde, INSTR_RSY_RRRD },
+	{ "sllk", 0xdf, INSTR_RSY_RRRD },
+	{ "locg", 0xe2, INSTR_RSY_RDRM },
+	{ "stocg", 0xe3, INSTR_RSY_RDRM },
+	{ "lang", 0xe4, INSTR_RSY_RRRD },
+	{ "laog", 0xe6, INSTR_RSY_RRRD },
+	{ "laxg", 0xe7, INSTR_RSY_RRRD },
+	{ "laag", 0xe8, INSTR_RSY_RRRD },
+	{ "laalg", 0xea, INSTR_RSY_RRRD },
+	{ "loc", 0xf2, INSTR_RSY_RDRM },
+	{ "stoc", 0xf3, INSTR_RSY_RDRM },
+	{ "lan", 0xf4, INSTR_RSY_RRRD },
+	{ "lao", 0xf6, INSTR_RSY_RRRD },
+	{ "lax", 0xf7, INSTR_RSY_RRRD },
+	{ "laa", 0xf8, INSTR_RSY_RRRD },
+	{ "laal", 0xfa, INSTR_RSY_RRRD },
+	{ "lric", 0x60, INSTR_RSY_RDRM },
+	{ "stric", 0x61, INSTR_RSY_RDRM },
+	{ "mric", 0x62, INSTR_RSY_RDRM },
+	{ { 0, LONG_INSN_STCCTM }, 0x17, INSTR_RSY_RMRD },
+	{ "rll", 0x1d, INSTR_RSY_RRRD },
+	{ "mvclu", 0x8e, INSTR_RSY_RRRD },
+	{ "tp", 0xc0, INSTR_RSL_R0RD },
+	{ "", 0, INSTR_INVALID }
+};
+
+static struct s390_insn opcode_ec[] = {
+	{ "brxhg", 0x44, INSTR_RIE_RRP },
+	{ "brxlg", 0x45, INSTR_RIE_RRP },
+	{ { 0, LONG_INSN_RISBLG }, 0x51, INSTR_RIE_RRUUU },
+	{ "rnsbg", 0x54, INSTR_RIE_RRUUU },
+	{ "risbg", 0x55, INSTR_RIE_RRUUU },
+	{ "rosbg", 0x56, INSTR_RIE_RRUUU },
+	{ "rxsbg", 0x57, INSTR_RIE_RRUUU },
+	{ { 0, LONG_INSN_RISBGN }, 0x59, INSTR_RIE_RRUUU },
+	{ { 0, LONG_INSN_RISBHG }, 0x5D, INSTR_RIE_RRUUU },
+	{ "cgrj", 0x64, INSTR_RIE_RRPU },
+	{ "clgrj", 0x65, INSTR_RIE_RRPU },
+	{ "cgit", 0x70, INSTR_RIE_R0IU },
+	{ "clgit", 0x71, INSTR_RIE_R0UU },
+	{ "cit", 0x72, INSTR_RIE_R0IU },
+	{ "clfit", 0x73, INSTR_RIE_R0UU },
+	{ "crj", 0x76, INSTR_RIE_RRPU },
+	{ "clrj", 0x77, INSTR_RIE_RRPU },
+	{ "cgij", 0x7c, INSTR_RIE_RUPI },
+	{ "clgij", 0x7d, INSTR_RIE_RUPU },
+	{ "cij", 0x7e, INSTR_RIE_RUPI },
+	{ "clij", 0x7f, INSTR_RIE_RUPU },
+	{ "ahik", 0xd8, INSTR_RIE_RRI0 },
+	{ "aghik", 0xd9, INSTR_RIE_RRI0 },
+	{ { 0, LONG_INSN_ALHSIK }, 0xda, INSTR_RIE_RRI0 },
+	{ { 0, LONG_INSN_ALGHSIK }, 0xdb, INSTR_RIE_RRI0 },
+	{ "cgrb", 0xe4, INSTR_RRS_RRRDU },
+	{ "clgrb", 0xe5, INSTR_RRS_RRRDU },
+	{ "crb", 0xf6, INSTR_RRS_RRRDU },
+	{ "clrb", 0xf7, INSTR_RRS_RRRDU },
+	{ "cgib", 0xfc, INSTR_RIS_RURDI },
+	{ "clgib", 0xfd, INSTR_RIS_RURDU },
+	{ "cib", 0xfe, INSTR_RIS_RURDI },
+	{ "clib", 0xff, INSTR_RIS_RURDU },
+	{ "", 0, INSTR_INVALID }
+};
+
+static struct s390_insn opcode_ed[] = {
+	{ "mayl", 0x38, INSTR_RXF_FRRDF },
+	{ "myl", 0x39, INSTR_RXF_FRRDF },
+	{ "may", 0x3a, INSTR_RXF_FRRDF },
+	{ "my", 0x3b, INSTR_RXF_FRRDF },
+	{ "mayh", 0x3c, INSTR_RXF_FRRDF },
+	{ "myh", 0x3d, INSTR_RXF_FRRDF },
+	{ "sldt", 0x40, INSTR_RXF_FRRDF },
+	{ "srdt", 0x41, INSTR_RXF_FRRDF },
+	{ "slxt", 0x48, INSTR_RXF_FRRDF },
+	{ "srxt", 0x49, INSTR_RXF_FRRDF },
+	{ "tdcet", 0x50, INSTR_RXE_FRRD },
+	{ "tdget", 0x51, INSTR_RXE_FRRD },
+	{ "tdcdt", 0x54, INSTR_RXE_FRRD },
+	{ "tdgdt", 0x55, INSTR_RXE_FRRD },
+	{ "tdcxt", 0x58, INSTR_RXE_FRRD },
+	{ "tdgxt", 0x59, INSTR_RXE_FRRD },
+	{ "ley", 0x64, INSTR_RXY_FRRD },
+	{ "ldy", 0x65, INSTR_RXY_FRRD },
+	{ "stey", 0x66, INSTR_RXY_FRRD },
+	{ "stdy", 0x67, INSTR_RXY_FRRD },
+	{ "czdt", 0xa8, INSTR_RSL_LRDFU },
+	{ "czxt", 0xa9, INSTR_RSL_LRDFU },
+	{ "cdzt", 0xaa, INSTR_RSL_LRDFU },
+	{ "cxzt", 0xab, INSTR_RSL_LRDFU },
+	{ "ldeb", 0x04, INSTR_RXE_FRRD },
+	{ "lxdb", 0x05, INSTR_RXE_FRRD },
+	{ "lxeb", 0x06, INSTR_RXE_FRRD },
+	{ "mxdb", 0x07, INSTR_RXE_FRRD },
+	{ "keb", 0x08, INSTR_RXE_FRRD },
+	{ "ceb", 0x09, INSTR_RXE_FRRD },
+	{ "aeb", 0x0a, INSTR_RXE_FRRD },
+	{ "seb", 0x0b, INSTR_RXE_FRRD },
+	{ "mdeb", 0x0c, INSTR_RXE_FRRD },
+	{ "deb", 0x0d, INSTR_RXE_FRRD },
+	{ "maeb", 0x0e, INSTR_RXF_FRRDF },
+	{ "mseb", 0x0f, INSTR_RXF_FRRDF },
+	{ "tceb", 0x10, INSTR_RXE_FRRD },
+	{ "tcdb", 0x11, INSTR_RXE_FRRD },
+	{ "tcxb", 0x12, INSTR_RXE_FRRD },
+	{ "sqeb", 0x14, INSTR_RXE_FRRD },
+	{ "sqdb", 0x15, INSTR_RXE_FRRD },
+	{ "meeb", 0x17, INSTR_RXE_FRRD },
+	{ "kdb", 0x18, INSTR_RXE_FRRD },
+	{ "cdb", 0x19, INSTR_RXE_FRRD },
+	{ "adb", 0x1a, INSTR_RXE_FRRD },
+	{ "sdb", 0x1b, INSTR_RXE_FRRD },
+	{ "mdb", 0x1c, INSTR_RXE_FRRD },
+	{ "ddb", 0x1d, INSTR_RXE_FRRD },
+	{ "madb", 0x1e, INSTR_RXF_FRRDF },
+	{ "msdb", 0x1f, INSTR_RXF_FRRDF },
+	{ "lde", 0x24, INSTR_RXE_FRRD },
+	{ "lxd", 0x25, INSTR_RXE_FRRD },
+	{ "lxe", 0x26, INSTR_RXE_FRRD },
+	{ "mae", 0x2e, INSTR_RXF_FRRDF },
+	{ "mse", 0x2f, INSTR_RXF_FRRDF },
+	{ "sqe", 0x34, INSTR_RXE_FRRD },
+	{ "sqd", 0x35, INSTR_RXE_FRRD },
+	{ "mee", 0x37, INSTR_RXE_FRRD },
+	{ "mad", 0x3e, INSTR_RXF_FRRDF },
+	{ "msd", 0x3f, INSTR_RXF_FRRDF },
+	{ "", 0, INSTR_INVALID }
+};
+
+/* Extracts an operand value from an instruction.  */
+static unsigned int extract_operand(unsigned char *code,
+				    const struct s390_operand *operand)
+{
+	unsigned char *cp;
+	unsigned int val;
+	int bits;
+
+	/* Extract fragments of the operand byte for byte.  */
+	cp = code + operand->shift / 8;
+	bits = (operand->shift & 7) + operand->bits;
+	val = 0;
+	do {
+		val <<= 8;
+		val |= (unsigned int) *cp++;
+		bits -= 8;
+	} while (bits > 0);
+	val >>= -bits;
+	val &= ((1U << (operand->bits - 1)) << 1) - 1;
+
+	/* Check for special long displacement case.  */
+	if (operand->bits == 20 && operand->shift == 20)
+		val = (val & 0xff) << 12 | (val & 0xfff00) >> 8;
+
+	/* Check for register extensions bits for vector registers. */
+	if (operand->flags & OPERAND_VR) {
+		if (operand->shift == 8)
+			val |= (code[4] & 8) << 1;
+		else if (operand->shift == 12)
+			val |= (code[4] & 4) << 2;
+		else if (operand->shift == 16)
+			val |= (code[4] & 2) << 3;
+		else if (operand->shift == 32)
+			val |= (code[4] & 1) << 4;
+	}
+
+	/* Sign extend value if the operand is signed or pc relative.  */
+	if ((operand->flags & (OPERAND_SIGNED | OPERAND_PCREL)) &&
+	    (val & (1U << (operand->bits - 1))))
+		val |= (-1U << (operand->bits - 1)) << 1;
+
+	/* Double value if the operand is pc relative.	*/
+	if (operand->flags & OPERAND_PCREL)
+		val <<= 1;
+
+	/* Length x in an instructions has real length x + 1.  */
+	if (operand->flags & OPERAND_LENGTH)
+		val++;
+	return val;
+}
+
+struct s390_insn *find_insn(unsigned char *code)
+{
+	unsigned char opfrag = code[1];
+	unsigned char opmask;
+	struct s390_insn *table;
+
+	switch (code[0]) {
+	case 0x01:
+		table = opcode_01;
+		break;
+	case 0xa5:
+		table = opcode_a5;
+		break;
+	case 0xa7:
+		table = opcode_a7;
+		break;
+	case 0xaa:
+		table = opcode_aa;
+		break;
+	case 0xb2:
+		table = opcode_b2;
+		break;
+	case 0xb3:
+		table = opcode_b3;
+		break;
+	case 0xb9:
+		table = opcode_b9;
+		break;
+	case 0xc0:
+		table = opcode_c0;
+		break;
+	case 0xc2:
+		table = opcode_c2;
+		break;
+	case 0xc4:
+		table = opcode_c4;
+		break;
+	case 0xc6:
+		table = opcode_c6;
+		break;
+	case 0xc8:
+		table = opcode_c8;
+		break;
+	case 0xcc:
+		table = opcode_cc;
+		break;
+	case 0xe3:
+		table = opcode_e3;
+		opfrag = code[5];
+		break;
+	case 0xe5:
+		table = opcode_e5;
+		break;
+	case 0xe7:
+		table = opcode_e7;
+		opfrag = code[5];
+		break;
+	case 0xeb:
+		table = opcode_eb;
+		opfrag = code[5];
+		break;
+	case 0xec:
+		table = opcode_ec;
+		opfrag = code[5];
+		break;
+	case 0xed:
+		table = opcode_ed;
+		opfrag = code[5];
+		break;
+	default:
+		table = opcode;
+		opfrag = code[0];
+		break;
+	}
+	while (table->format != INSTR_INVALID) {
+		opmask = formats[table->format][0];
+		if (table->opfrag == (opfrag & opmask))
+			return table;
+		table++;
+	}
+	return NULL;
+}
+
+/**
+ * insn_to_mnemonic - decode an s390 instruction
+ * @instruction: instruction to decode
+ * @buf: buffer to fill with mnemonic
+ * @len: length of buffer
+ *
+ * Decode the instruction at @instruction and store the corresponding
+ * mnemonic into @buf of length @len.
+ * @buf is left unchanged if the instruction could not be decoded.
+ * Returns:
+ *  %0 on success, %-ENOENT if the instruction was not found.
+ */
+int insn_to_mnemonic(unsigned char *instruction, char *buf, unsigned int len)
+{
+	struct s390_insn *insn;
+
+	insn = find_insn(instruction);
+	if (!insn)
+		return -ENOENT;
+	if (insn->name[0] == '\0')
+		snprintf(buf, len, "%s",
+			 long_insn_name[(int) insn->name[1]]);
+	else
+		snprintf(buf, len, "%.5s", insn->name);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(insn_to_mnemonic);
+
+static int print_insn(char *buffer, unsigned char *code, unsigned long addr)
+{
+	struct s390_insn *insn;
+	const unsigned char *ops;
+	const struct s390_operand *operand;
+	unsigned int value;
+	char separator;
+	char *ptr;
+	int i;
+
+	ptr = buffer;
+	insn = find_insn(code);
+	if (insn) {
+		if (insn->name[0] == '\0')
+			ptr += sprintf(ptr, "%s\t",
+				       long_insn_name[(int) insn->name[1]]);
+		else
+			ptr += sprintf(ptr, "%.5s\t", insn->name);
+		/* Extract the operands. */
+		separator = 0;
+		for (ops = formats[insn->format] + 1, i = 0;
+		     *ops != 0 && i < 6; ops++, i++) {
+			operand = operands + *ops;
+			value = extract_operand(code, operand);
+			if ((operand->flags & OPERAND_INDEX)  && value == 0)
+				continue;
+			if ((operand->flags & OPERAND_BASE) &&
+			    value == 0 && separator == '(') {
+				separator = ',';
+				continue;
+			}
+			if (separator)
+				ptr += sprintf(ptr, "%c", separator);
+			if (operand->flags & OPERAND_GPR)
+				ptr += sprintf(ptr, "%%r%i", value);
+			else if (operand->flags & OPERAND_FPR)
+				ptr += sprintf(ptr, "%%f%i", value);
+			else if (operand->flags & OPERAND_AR)
+				ptr += sprintf(ptr, "%%a%i", value);
+			else if (operand->flags & OPERAND_CR)
+				ptr += sprintf(ptr, "%%c%i", value);
+			else if (operand->flags & OPERAND_VR)
+				ptr += sprintf(ptr, "%%v%i", value);
+			else if (operand->flags & OPERAND_PCREL)
+				ptr += sprintf(ptr, "%lx", (signed int) value
+								      + addr);
+			else if (operand->flags & OPERAND_SIGNED)
+				ptr += sprintf(ptr, "%i", value);
+			else
+				ptr += sprintf(ptr, "%u", value);
+			if (operand->flags & OPERAND_DISP)
+				separator = '(';
+			else if (operand->flags & OPERAND_BASE) {
+				ptr += sprintf(ptr, ")");
+				separator = ',';
+			} else
+				separator = ',';
+		}
+	} else
+		ptr += sprintf(ptr, "unknown");
+	return (int) (ptr - buffer);
+}
+
+void show_code(struct pt_regs *regs)
+{
+	char *mode = user_mode(regs) ? "User" : "Krnl";
+	unsigned char code[64];
+	char buffer[64], *ptr;
+	mm_segment_t old_fs;
+	unsigned long addr;
+	int start, end, opsize, hops, i;
+
+	/* Get a snapshot of the 64 bytes surrounding the fault address. */
+	old_fs = get_fs();
+	set_fs(user_mode(regs) ? USER_DS : KERNEL_DS);
+	for (start = 32; start && regs->psw.addr >= 34 - start; start -= 2) {
+		addr = regs->psw.addr - 34 + start;
+		if (__copy_from_user(code + start - 2,
+				     (char __user *) addr, 2))
+			break;
+	}
+	for (end = 32; end < 64; end += 2) {
+		addr = regs->psw.addr + end - 32;
+		if (__copy_from_user(code + end,
+				     (char __user *) addr, 2))
+			break;
+	}
+	set_fs(old_fs);
+	/* Code snapshot useable ? */
+	if ((regs->psw.addr & 1) || start >= end) {
+		printk("%s Code: Bad PSW.\n", mode);
+		return;
+	}
+	/* Find a starting point for the disassembly. */
+	while (start < 32) {
+		for (i = 0, hops = 0; start + i < 32 && hops < 3; hops++) {
+			if (!find_insn(code + start + i))
+				break;
+			i += insn_length(code[start + i]);
+		}
+		if (start + i == 32)
+			/* Looks good, sequence ends at PSW. */
+			break;
+		start += 2;
+	}
+	/* Decode the instructions. */
+	ptr = buffer;
+	ptr += sprintf(ptr, "%s Code:", mode);
+	hops = 0;
+	while (start < end && hops < 8) {
+		opsize = insn_length(code[start]);
+		if  (start + opsize == 32)
+			*ptr++ = '#';
+		else if (start == 32)
+			*ptr++ = '>';
+		else
+			*ptr++ = ' ';
+		addr = regs->psw.addr + start - 32;
+		ptr += sprintf(ptr, "%016lx: ", addr);
+		if (start + opsize >= end)
+			break;
+		for (i = 0; i < opsize; i++)
+			ptr += sprintf(ptr, "%02x", code[start + i]);
+		*ptr++ = '\t';
+		if (i < 6)
+			*ptr++ = '\t';
+		ptr += print_insn(ptr, code + start, addr);
+		start += opsize;
+		printk(buffer);
+		ptr = buffer;
+		ptr += sprintf(ptr, "\n          ");
+		hops++;
+	}
+	printk("\n");
+}
+
+void print_fn_code(unsigned char *code, unsigned long len)
+{
+	char buffer[64], *ptr;
+	int opsize, i;
+
+	while (len) {
+		ptr = buffer;
+		opsize = insn_length(*code);
+		if (opsize > len)
+			break;
+		ptr += sprintf(ptr, "%p: ", code);
+		for (i = 0; i < opsize; i++)
+			ptr += sprintf(ptr, "%02x", code[i]);
+		*ptr++ = '\t';
+		if (i < 4)
+			*ptr++ = '\t';
+		ptr += print_insn(ptr, code, (unsigned long) code);
+		*ptr++ = '\n';
+		*ptr++ = 0;
+		printk(buffer);
+		code += opsize;
+		len -= opsize;
+	}
+}
diff --git a/arch/s390/kernel/dumpstack.c b/arch/s390/kernel/dumpstack.c
new file mode 100644
index 000000000..dc8e20473
--- /dev/null
+++ b/arch/s390/kernel/dumpstack.c
@@ -0,0 +1,204 @@
+/*
+ * Stack dumping functions
+ *
+ *  Copyright IBM Corp. 1999, 2013
+ */
+
+#include <linux/kallsyms.h>
+#include <linux/hardirq.h>
+#include <linux/kprobes.h>
+#include <linux/utsname.h>
+#include <linux/export.h>
+#include <linux/kdebug.h>
+#include <linux/ptrace.h>
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <asm/processor.h>
+#include <asm/debug.h>
+#include <asm/dis.h>
+#include <asm/ipl.h>
+
+/*
+ * For show_trace we have tree different stack to consider:
+ *   - the panic stack which is used if the kernel stack has overflown
+ *   - the asynchronous interrupt stack (cpu related)
+ *   - the synchronous kernel stack (process related)
+ * The stack trace can start at any of the three stack and can potentially
+ * touch all of them. The order is: panic stack, async stack, sync stack.
+ */
+static unsigned long
+__show_trace(unsigned long sp, unsigned long low, unsigned long high)
+{
+	struct stack_frame *sf;
+	struct pt_regs *regs;
+	unsigned long addr;
+
+	while (1) {
+		sp = sp & PSW_ADDR_INSN;
+		if (sp < low || sp > high - sizeof(*sf))
+			return sp;
+		sf = (struct stack_frame *) sp;
+		addr = sf->gprs[8] & PSW_ADDR_INSN;
+		printk("([<%016lx>] %pSR)\n", addr, (void *)addr);
+		/* 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;
+			addr = sf->gprs[8] & PSW_ADDR_INSN;
+			printk(" [<%016lx>] %pSR\n", addr, (void *)addr);
+		}
+		/* 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;
+		addr = regs->psw.addr & PSW_ADDR_INSN;
+		printk(" [<%016lx>] %pSR\n", addr, (void *)addr);
+		low = sp;
+		sp = regs->gprs[15];
+	}
+}
+
+static void show_trace(struct task_struct *task, unsigned long *stack)
+{
+	const unsigned long frame_size =
+		STACK_FRAME_OVERHEAD + sizeof(struct pt_regs);
+	register unsigned long __r15 asm ("15");
+	unsigned long sp;
+
+	sp = (unsigned long) stack;
+	if (!sp)
+		sp = task ? task->thread.ksp : __r15;
+	printk("Call Trace:\n");
+#ifdef CONFIG_CHECK_STACK
+	sp = __show_trace(sp,
+			  S390_lowcore.panic_stack + frame_size - 4096,
+			  S390_lowcore.panic_stack + frame_size);
+#endif
+	sp = __show_trace(sp,
+			  S390_lowcore.async_stack + frame_size - ASYNC_SIZE,
+			  S390_lowcore.async_stack + frame_size);
+	if (task)
+		__show_trace(sp, (unsigned long) task_stack_page(task),
+			     (unsigned long) task_stack_page(task) + THREAD_SIZE);
+	else
+		__show_trace(sp, S390_lowcore.thread_info,
+			     S390_lowcore.thread_info + THREAD_SIZE);
+	if (!task)
+		task = current;
+	debug_show_held_locks(task);
+}
+
+void show_stack(struct task_struct *task, unsigned long *sp)
+{
+	register unsigned long *__r15 asm ("15");
+	unsigned long *stack;
+	int i;
+
+	if (!sp)
+		stack = task ? (unsigned long *) task->thread.ksp : __r15;
+	else
+		stack = sp;
+
+	for (i = 0; i < 20; i++) {
+		if (((addr_t) stack & (THREAD_SIZE-1)) == 0)
+			break;
+		if ((i * sizeof(long) % 32) == 0)
+			printk("%s       ", i == 0 ? "" : "\n");
+		printk("%016lx ", *stack++);
+	}
+	printk("\n");
+	show_trace(task, sp);
+}
+
+static void show_last_breaking_event(struct pt_regs *regs)
+{
+	printk("Last Breaking-Event-Address:\n");
+	printk(" [<%016lx>] %pSR\n", regs->args[0], (void *)regs->args[0]);
+}
+
+static inline int mask_bits(struct pt_regs *regs, unsigned long bits)
+{
+	return (regs->psw.mask & bits) / ((~bits + 1) & bits);
+}
+
+void show_registers(struct pt_regs *regs)
+{
+	char *mode;
+
+	mode = user_mode(regs) ? "User" : "Krnl";
+	printk("%s PSW : %p %p", mode, (void *)regs->psw.mask, (void *)regs->psw.addr);
+	if (!user_mode(regs))
+		printk(" (%pSR)", (void *)regs->psw.addr);
+	printk("\n");
+	printk("           R:%x T:%x IO:%x EX:%x Key:%x M:%x W:%x "
+	       "P:%x AS:%x CC:%x PM:%x", mask_bits(regs, PSW_MASK_PER),
+	       mask_bits(regs, PSW_MASK_DAT), mask_bits(regs, PSW_MASK_IO),
+	       mask_bits(regs, PSW_MASK_EXT), mask_bits(regs, PSW_MASK_KEY),
+	       mask_bits(regs, PSW_MASK_MCHECK), mask_bits(regs, PSW_MASK_WAIT),
+	       mask_bits(regs, PSW_MASK_PSTATE), mask_bits(regs, PSW_MASK_ASC),
+	       mask_bits(regs, PSW_MASK_CC), mask_bits(regs, PSW_MASK_PM));
+	printk(" EA:%x", mask_bits(regs, PSW_MASK_EA | PSW_MASK_BA));
+	printk("\n%s GPRS: %016lx %016lx %016lx %016lx\n", mode,
+	       regs->gprs[0], regs->gprs[1], regs->gprs[2], regs->gprs[3]);
+	printk("           %016lx %016lx %016lx %016lx\n",
+	       regs->gprs[4], regs->gprs[5], regs->gprs[6], regs->gprs[7]);
+	printk("           %016lx %016lx %016lx %016lx\n",
+	       regs->gprs[8], regs->gprs[9], regs->gprs[10], regs->gprs[11]);
+	printk("           %016lx %016lx %016lx %016lx\n",
+	       regs->gprs[12], regs->gprs[13], regs->gprs[14], regs->gprs[15]);
+	show_code(regs);
+}
+
+void show_regs(struct pt_regs *regs)
+{
+	show_regs_print_info(KERN_DEFAULT);
+	show_registers(regs);
+	/* Show stack backtrace if pt_regs is from kernel mode */
+	if (!user_mode(regs))
+		show_trace(NULL, (unsigned long *) regs->gprs[15]);
+	show_last_breaking_event(regs);
+}
+
+static DEFINE_SPINLOCK(die_lock);
+
+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);
+	bust_spinlocks(1);
+	printk("%s: %04x ilc:%d [#%d] ", str, regs->int_code & 0xffff,
+	       regs->int_code >> 17, ++die_counter);
+#ifdef CONFIG_PREEMPT
+	printk("PREEMPT ");
+#endif
+#ifdef CONFIG_SMP
+	printk("SMP ");
+#endif
+#ifdef CONFIG_DEBUG_PAGEALLOC
+	printk("DEBUG_PAGEALLOC");
+#endif
+	printk("\n");
+	notify_die(DIE_OOPS, str, regs, 0, regs->int_code & 0xffff, SIGSEGV);
+	print_modules();
+	show_regs(regs);
+	bust_spinlocks(0);
+	add_taint(TAINT_DIE, LOCKDEP_NOW_UNRELIABLE);
+	spin_unlock_irq(&die_lock);
+	if (in_interrupt())
+		panic("Fatal exception in interrupt");
+	if (panic_on_oops)
+		panic("Fatal exception: panic_on_oops");
+	oops_exit();
+	do_exit(SIGSEGV);
+}
diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c
new file mode 100644
index 000000000..549a73a4b
--- /dev/null
+++ b/arch/s390/kernel/early.c
@@ -0,0 +1,444 @@
+/*
+ *    Copyright IBM Corp. 2007, 2009
+ *    Author(s): Hongjie Yang <hongjie@us.ibm.com>,
+ *		 Heiko Carstens <heiko.carstens@de.ibm.com>
+ */
+
+#define KMSG_COMPONENT "setup"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
+#include <linux/compiler.h>
+#include <linux/init.h>
+#include <linux/errno.h>
+#include <linux/string.h>
+#include <linux/ctype.h>
+#include <linux/lockdep.h>
+#include <linux/module.h>
+#include <linux/pfn.h>
+#include <linux/uaccess.h>
+#include <linux/kernel.h>
+#include <asm/ebcdic.h>
+#include <asm/ipl.h>
+#include <asm/lowcore.h>
+#include <asm/processor.h>
+#include <asm/sections.h>
+#include <asm/setup.h>
+#include <asm/sysinfo.h>
+#include <asm/cpcmd.h>
+#include <asm/sclp.h>
+#include <asm/facility.h>
+#include "entry.h"
+
+/*
+ * Create a Kernel NSS if the SAVESYS= parameter is defined
+ */
+#define DEFSYS_CMD_SIZE		128
+#define SAVESYS_CMD_SIZE	32
+
+char kernel_nss_name[NSS_NAME_SIZE + 1];
+
+static void __init setup_boot_command_line(void);
+
+/*
+ * Get the TOD clock running.
+ */
+static void __init reset_tod_clock(void)
+{
+	u64 time;
+
+	if (store_tod_clock(&time) == 0)
+		return;
+	/* TOD clock not running. Set the clock to Unix Epoch. */
+	if (set_tod_clock(TOD_UNIX_EPOCH) != 0 || store_tod_clock(&time) != 0)
+		disabled_wait(0);
+
+	sched_clock_base_cc = TOD_UNIX_EPOCH;
+	S390_lowcore.last_update_clock = sched_clock_base_cc;
+}
+
+#ifdef CONFIG_SHARED_KERNEL
+int __init savesys_ipl_nss(char *cmd, const int cmdlen);
+
+asm(
+	"	.section .init.text,\"ax\",@progbits\n"
+	"	.align	4\n"
+	"	.type	savesys_ipl_nss, @function\n"
+	"savesys_ipl_nss:\n"
+	"	stmg	6,15,48(15)\n"
+	"	lgr	14,3\n"
+	"	sam31\n"
+	"	diag	2,14,0x8\n"
+	"	sam64\n"
+	"	lgr	2,14\n"
+	"	lmg	6,15,48(15)\n"
+	"	br	14\n"
+	"	.size	savesys_ipl_nss, .-savesys_ipl_nss\n"
+	"	.previous\n");
+
+static __initdata char upper_command_line[COMMAND_LINE_SIZE];
+
+static noinline __init void create_kernel_nss(void)
+{
+	unsigned int i, stext_pfn, eshared_pfn, end_pfn, min_size;
+#ifdef CONFIG_BLK_DEV_INITRD
+	unsigned int sinitrd_pfn, einitrd_pfn;
+#endif
+	int response;
+	int hlen;
+	size_t len;
+	char *savesys_ptr;
+	char defsys_cmd[DEFSYS_CMD_SIZE];
+	char savesys_cmd[SAVESYS_CMD_SIZE];
+
+	/* Do nothing if we are not running under VM */
+	if (!MACHINE_IS_VM)
+		return;
+
+	/* Convert COMMAND_LINE to upper case */
+	for (i = 0; i < strlen(boot_command_line); i++)
+		upper_command_line[i] = toupper(boot_command_line[i]);
+
+	savesys_ptr = strstr(upper_command_line, "SAVESYS=");
+
+	if (!savesys_ptr)
+		return;
+
+	savesys_ptr += 8;    /* Point to the beginning of the NSS name */
+	for (i = 0; i < NSS_NAME_SIZE; i++) {
+		if (savesys_ptr[i] == ' ' || savesys_ptr[i] == '\0')
+			break;
+		kernel_nss_name[i] = savesys_ptr[i];
+	}
+
+	stext_pfn = PFN_DOWN(__pa(&_stext));
+	eshared_pfn = PFN_DOWN(__pa(&_eshared));
+	end_pfn = PFN_UP(__pa(&_end));
+	min_size = end_pfn << 2;
+
+	hlen = snprintf(defsys_cmd, DEFSYS_CMD_SIZE,
+			"DEFSYS %s 00000-%.5X EW %.5X-%.5X SR %.5X-%.5X",
+			kernel_nss_name, stext_pfn - 1, stext_pfn,
+			eshared_pfn - 1, eshared_pfn, end_pfn);
+
+#ifdef CONFIG_BLK_DEV_INITRD
+	if (INITRD_START && INITRD_SIZE) {
+		sinitrd_pfn = PFN_DOWN(__pa(INITRD_START));
+		einitrd_pfn = PFN_UP(__pa(INITRD_START + INITRD_SIZE));
+		min_size = einitrd_pfn << 2;
+		hlen += snprintf(defsys_cmd + hlen, DEFSYS_CMD_SIZE - hlen,
+				 " EW %.5X-%.5X", sinitrd_pfn, einitrd_pfn);
+	}
+#endif
+
+	snprintf(defsys_cmd + hlen, DEFSYS_CMD_SIZE - hlen,
+		 " EW MINSIZE=%.7iK PARMREGS=0-13", min_size);
+	defsys_cmd[DEFSYS_CMD_SIZE - 1] = '\0';
+	snprintf(savesys_cmd, SAVESYS_CMD_SIZE, "SAVESYS %s \n IPL %s",
+		 kernel_nss_name, kernel_nss_name);
+	savesys_cmd[SAVESYS_CMD_SIZE - 1] = '\0';
+
+	__cpcmd(defsys_cmd, NULL, 0, &response);
+
+	if (response != 0) {
+		pr_err("Defining the Linux kernel NSS failed with rc=%d\n",
+			response);
+		kernel_nss_name[0] = '\0';
+		return;
+	}
+
+	len = strlen(savesys_cmd);
+	ASCEBC(savesys_cmd, len);
+	response = savesys_ipl_nss(savesys_cmd, len);
+
+	/* On success: response is equal to the command size,
+	 *	       max SAVESYS_CMD_SIZE
+	 * On error: response contains the numeric portion of cp error message.
+	 *	     for SAVESYS it will be >= 263
+	 *	     for missing privilege class, it will be 1
+	 */
+	if (response > SAVESYS_CMD_SIZE || response == 1) {
+		pr_err("Saving the Linux kernel NSS failed with rc=%d\n",
+			response);
+		kernel_nss_name[0] = '\0';
+		return;
+	}
+
+	/* re-initialize cputime accounting. */
+	sched_clock_base_cc = get_tod_clock();
+	S390_lowcore.last_update_clock = sched_clock_base_cc;
+	S390_lowcore.last_update_timer = 0x7fffffffffffffffULL;
+	S390_lowcore.user_timer = 0;
+	S390_lowcore.system_timer = 0;
+	asm volatile("SPT 0(%0)" : : "a" (&S390_lowcore.last_update_timer));
+
+	/* re-setup boot command line with new ipl vm parms */
+	ipl_update_parameters();
+	setup_boot_command_line();
+
+	ipl_flags = IPL_NSS_VALID;
+}
+
+#else /* CONFIG_SHARED_KERNEL */
+
+static inline void create_kernel_nss(void) { }
+
+#endif /* CONFIG_SHARED_KERNEL */
+
+/*
+ * Clear bss memory
+ */
+static noinline __init void clear_bss_section(void)
+{
+	memset(__bss_start, 0, __bss_stop - __bss_start);
+}
+
+/*
+ * Initialize storage key for kernel pages
+ */
+static noinline __init void init_kernel_storage_key(void)
+{
+#if PAGE_DEFAULT_KEY
+	unsigned long end_pfn, init_pfn;
+
+	end_pfn = PFN_UP(__pa(&_end));
+
+	for (init_pfn = 0 ; init_pfn < end_pfn; init_pfn++)
+		page_set_storage_key(init_pfn << PAGE_SHIFT,
+				     PAGE_DEFAULT_KEY, 0);
+#endif
+}
+
+static __initdata char sysinfo_page[PAGE_SIZE] __aligned(PAGE_SIZE);
+
+static noinline __init void detect_machine_type(void)
+{
+	struct sysinfo_3_2_2 *vmms = (struct sysinfo_3_2_2 *)&sysinfo_page;
+
+	/* Check current-configuration-level */
+	if (stsi(NULL, 0, 0, 0) <= 2) {
+		S390_lowcore.machine_flags |= MACHINE_FLAG_LPAR;
+		return;
+	}
+	/* Get virtual-machine cpu information. */
+	if (stsi(vmms, 3, 2, 2) || !vmms->count)
+		return;
+
+	/* Running under KVM? If not we assume z/VM */
+	if (!memcmp(vmms->vm[0].cpi, "\xd2\xe5\xd4", 3))
+		S390_lowcore.machine_flags |= MACHINE_FLAG_KVM;
+	else
+		S390_lowcore.machine_flags |= MACHINE_FLAG_VM;
+}
+
+static __init void setup_topology(void)
+{
+	int max_mnest;
+
+	if (!test_facility(11))
+		return;
+	S390_lowcore.machine_flags |= MACHINE_FLAG_TOPOLOGY;
+	for (max_mnest = 6; max_mnest > 1; max_mnest--) {
+		if (stsi(&sysinfo_page, 15, 1, max_mnest) == 0)
+			break;
+	}
+	topology_max_mnest = max_mnest;
+}
+
+static void early_pgm_check_handler(void)
+{
+	const struct exception_table_entry *fixup;
+	unsigned long cr0, cr0_new;
+	unsigned long addr;
+
+	addr = S390_lowcore.program_old_psw.addr;
+	fixup = search_exception_tables(addr & PSW_ADDR_INSN);
+	if (!fixup)
+		disabled_wait(0);
+	/* Disable low address protection before storing into lowcore. */
+	__ctl_store(cr0, 0, 0);
+	cr0_new = cr0 & ~(1UL << 28);
+	__ctl_load(cr0_new, 0, 0);
+	S390_lowcore.program_old_psw.addr = extable_fixup(fixup)|PSW_ADDR_AMODE;
+	__ctl_load(cr0, 0, 0);
+}
+
+static noinline __init void setup_lowcore_early(void)
+{
+	psw_t psw;
+
+	psw.mask = PSW_MASK_BASE | PSW_DEFAULT_KEY | PSW_MASK_EA | PSW_MASK_BA;
+	psw.addr = PSW_ADDR_AMODE | (unsigned long) s390_base_ext_handler;
+	S390_lowcore.external_new_psw = psw;
+	psw.addr = PSW_ADDR_AMODE | (unsigned long) s390_base_pgm_handler;
+	S390_lowcore.program_new_psw = psw;
+	s390_base_pgm_handler_fn = early_pgm_check_handler;
+}
+
+static noinline __init void setup_facility_list(void)
+{
+	stfle(S390_lowcore.stfle_fac_list,
+	      ARRAY_SIZE(S390_lowcore.stfle_fac_list));
+}
+
+static __init void detect_diag9c(void)
+{
+	unsigned int cpu_address;
+	int rc;
+
+	cpu_address = stap();
+	asm volatile(
+		"	diag	%2,0,0x9c\n"
+		"0:	la	%0,0\n"
+		"1:\n"
+		EX_TABLE(0b,1b)
+		: "=d" (rc) : "0" (-EOPNOTSUPP), "d" (cpu_address) : "cc");
+	if (!rc)
+		S390_lowcore.machine_flags |= MACHINE_FLAG_DIAG9C;
+}
+
+static __init void detect_diag44(void)
+{
+	int rc;
+
+	asm volatile(
+		"	diag	0,0,0x44\n"
+		"0:	la	%0,0\n"
+		"1:\n"
+		EX_TABLE(0b,1b)
+		: "=d" (rc) : "0" (-EOPNOTSUPP) : "cc");
+	if (!rc)
+		S390_lowcore.machine_flags |= MACHINE_FLAG_DIAG44;
+}
+
+static __init void detect_machine_facilities(void)
+{
+	if (test_facility(8)) {
+		S390_lowcore.machine_flags |= MACHINE_FLAG_EDAT1;
+		__ctl_set_bit(0, 23);
+	}
+	if (test_facility(78))
+		S390_lowcore.machine_flags |= MACHINE_FLAG_EDAT2;
+	if (test_facility(3))
+		S390_lowcore.machine_flags |= MACHINE_FLAG_IDTE;
+	if (test_facility(40))
+		S390_lowcore.machine_flags |= MACHINE_FLAG_LPP;
+	if (test_facility(50) && test_facility(73))
+		S390_lowcore.machine_flags |= MACHINE_FLAG_TE;
+	if (test_facility(51))
+		S390_lowcore.machine_flags |= MACHINE_FLAG_TLB_LC;
+	if (test_facility(129))
+		S390_lowcore.machine_flags |= MACHINE_FLAG_VX;
+}
+
+static int __init cad_setup(char *str)
+{
+	int val;
+
+	get_option(&str, &val);
+	if (val && test_facility(128))
+		S390_lowcore.machine_flags |= MACHINE_FLAG_CAD;
+	return 0;
+}
+early_param("cad", cad_setup);
+
+static int __init cad_init(void)
+{
+	if (MACHINE_HAS_CAD)
+		/* Enable problem state CAD. */
+		__ctl_set_bit(2, 3);
+	return 0;
+}
+early_initcall(cad_init);
+
+static __init void rescue_initrd(void)
+{
+#ifdef CONFIG_BLK_DEV_INITRD
+	unsigned long min_initrd_addr = (unsigned long) _end + (4UL << 20);
+	/*
+	 * Just like in case of IPL from VM reader we make sure there is a
+	 * gap of 4MB between end of kernel and start of initrd.
+	 * That way we can also be sure that saving an NSS will succeed,
+	 * which however only requires different segments.
+	 */
+	if (!INITRD_START || !INITRD_SIZE)
+		return;
+	if (INITRD_START >= min_initrd_addr)
+		return;
+	memmove((void *) min_initrd_addr, (void *) INITRD_START, INITRD_SIZE);
+	INITRD_START = min_initrd_addr;
+#endif
+}
+
+/* Set up boot command line */
+static void __init append_to_cmdline(size_t (*ipl_data)(char *, size_t))
+{
+	char *parm, *delim;
+	size_t rc, len;
+
+	len = strlen(boot_command_line);
+
+	delim = boot_command_line + len;	/* '\0' character position */
+	parm  = boot_command_line + len + 1;	/* append right after '\0' */
+
+	rc = ipl_data(parm, COMMAND_LINE_SIZE - len - 1);
+	if (rc) {
+		if (*parm == '=')
+			memmove(boot_command_line, parm + 1, rc);
+		else
+			*delim = ' ';		/* replace '\0' with space */
+	}
+}
+
+static inline int has_ebcdic_char(const char *str)
+{
+	int i;
+
+	for (i = 0; str[i]; i++)
+		if (str[i] & 0x80)
+			return 1;
+	return 0;
+}
+
+static void __init setup_boot_command_line(void)
+{
+	COMMAND_LINE[ARCH_COMMAND_LINE_SIZE - 1] = 0;
+	/* convert arch command line to ascii if necessary */
+	if (has_ebcdic_char(COMMAND_LINE))
+		EBCASC(COMMAND_LINE, ARCH_COMMAND_LINE_SIZE);
+	/* copy arch command line */
+	strlcpy(boot_command_line, strstrip(COMMAND_LINE),
+		ARCH_COMMAND_LINE_SIZE);
+
+	/* append IPL PARM data to the boot command line */
+	if (MACHINE_IS_VM)
+		append_to_cmdline(append_ipl_vmparm);
+
+	append_to_cmdline(append_ipl_scpdata);
+}
+
+/*
+ * Save ipl parameters, clear bss memory, initialize storage keys
+ * and create a kernel NSS at startup if the SAVESYS= parm is defined
+ */
+void __init startup_init(void)
+{
+	reset_tod_clock();
+	ipl_save_parameters();
+	rescue_initrd();
+	clear_bss_section();
+	init_kernel_storage_key();
+	lockdep_init();
+	lockdep_off();
+	setup_lowcore_early();
+	setup_facility_list();
+	detect_machine_type();
+	ipl_update_parameters();
+	setup_boot_command_line();
+	create_kernel_nss();
+	detect_diag9c();
+	detect_diag44();
+	detect_machine_facilities();
+	setup_topology();
+	sclp_early_detect();
+	lockdep_on();
+}
diff --git a/arch/s390/kernel/ebcdic.c b/arch/s390/kernel/ebcdic.c
new file mode 100644
index 000000000..b971c6be6
--- /dev/null
+++ b/arch/s390/kernel/ebcdic.c
@@ -0,0 +1,400 @@
+/*
+ *    ECBDIC -> ASCII, ASCII -> ECBDIC,
+ *    upper to lower case (EBCDIC) conversion tables.
+ *
+ *  S390 version
+ *    Copyright IBM Corp. 1999
+ *    Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
+ *               Martin Peschke <peschke@fh-brandenburg.de>
+ */
+
+#include <linux/module.h>
+#include <asm/types.h>
+#include <asm/ebcdic.h>
+
+/*
+ * ASCII (IBM PC 437)  -> EBCDIC 037
+ */
+__u8 _ascebc[256] =
+{
+ /*00 NUL   SOH   STX   ETX   EOT   ENQ   ACK   BEL */
+     0x00, 0x01, 0x02, 0x03, 0x37, 0x2D, 0x2E, 0x2F,
+ /*08  BS    HT    LF    VT    FF    CR    SO    SI */
+ /*              ->NL                               */
+     0x16, 0x05, 0x15, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F,
+ /*10 DLE   DC1   DC2   DC3   DC4   NAK   SYN   ETB */
+     0x10, 0x11, 0x12, 0x13, 0x3C, 0x3D, 0x32, 0x26,
+ /*18 CAN    EM   SUB   ESC    FS    GS    RS    US */
+ /*                               ->IGS ->IRS ->IUS */
+     0x18, 0x19, 0x3F, 0x27, 0x22, 0x1D, 0x1E, 0x1F,
+ /*20  SP     !     "     #     $     %     &     ' */
+     0x40, 0x5A, 0x7F, 0x7B, 0x5B, 0x6C, 0x50, 0x7D,
+ /*28   (     )     *     +     ,     -    .      / */
+     0x4D, 0x5D, 0x5C, 0x4E, 0x6B, 0x60, 0x4B, 0x61,
+ /*30   0     1     2     3     4     5     6     7 */
+     0xF0, 0xF1, 0xF2, 0xF3, 0xF4, 0xF5, 0xF6, 0xF7,
+ /*38   8     9     :     ;     <     =     >     ? */
+     0xF8, 0xF9, 0x7A, 0x5E, 0x4C, 0x7E, 0x6E, 0x6F,
+ /*40   @     A     B     C     D     E     F     G */
+     0x7C, 0xC1, 0xC2, 0xC3, 0xC4, 0xC5, 0xC6, 0xC7,
+ /*48   H     I     J     K     L     M     N     O */
+     0xC8, 0xC9, 0xD1, 0xD2, 0xD3, 0xD4, 0xD5, 0xD6,
+ /*50   P     Q     R     S     T     U     V     W */
+     0xD7, 0xD8, 0xD9, 0xE2, 0xE3, 0xE4, 0xE5, 0xE6,
+ /*58   X     Y     Z     [     \     ]     ^     _ */
+     0xE7, 0xE8, 0xE9, 0xBA, 0xE0, 0xBB, 0xB0, 0x6D,
+ /*60   `     a     b     c     d     e     f     g */
+     0x79, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87,
+ /*68   h     i     j     k     l     m     n     o */
+     0x88, 0x89, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96,
+ /*70   p     q     r     s     t     u     v     w */
+     0x97, 0x98, 0x99, 0xA2, 0xA3, 0xA4, 0xA5, 0xA6,
+ /*78   x     y     z     {     |     }     ~    DL */
+     0xA7, 0xA8, 0xA9, 0xC0, 0x4F, 0xD0, 0xA1, 0x07,
+ /*80*/
+     0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F,
+ /*88*/
+     0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F,
+ /*90*/
+     0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F,
+ /*98*/
+     0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F,
+ /*A0*/
+     0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F,
+ /*A8*/
+     0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F,
+ /*B0*/
+     0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F,
+ /*B8*/
+     0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F,
+ /*C0*/
+     0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F,
+ /*C8*/
+     0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F,
+ /*D0*/
+     0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F,
+ /*D8*/
+     0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F,
+ /*E0        sz						*/
+     0x3F, 0x59, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F,
+ /*E8*/
+     0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F,
+ /*F0*/
+     0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F,
+ /*F8*/
+     0x90, 0x3F, 0x3F, 0x3F, 0x3F, 0xEA, 0x3F, 0xFF
+};
+
+/*
+ * EBCDIC 037 -> ASCII (IBM PC 437)
+ */
+__u8 _ebcasc[256] =
+{
+ /* 0x00   NUL   SOH   STX   ETX  *SEL    HT  *RNL   DEL */
+          0x00, 0x01, 0x02, 0x03, 0x07, 0x09, 0x07, 0x7F,
+ /* 0x08   -GE  -SPS  -RPT    VT    FF    CR    SO    SI */
+          0x07, 0x07, 0x07, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F,
+ /* 0x10   DLE   DC1   DC2   DC3  -RES   -NL    BS  -POC
+                                  -ENP  ->LF             */
+          0x10, 0x11, 0x12, 0x13, 0x07, 0x0A, 0x08, 0x07,
+ /* 0x18   CAN    EM  -UBS  -CU1  -IFS  -IGS  -IRS  -ITB
+                                                    -IUS */
+          0x18, 0x19, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07,
+ /* 0x20   -DS  -SOS    FS  -WUS  -BYP    LF   ETB   ESC
+                                  -INP                   */
+          0x07, 0x07, 0x1C, 0x07, 0x07, 0x0A, 0x17, 0x1B,
+ /* 0x28   -SA  -SFE   -SM  -CSP  -MFA   ENQ   ACK   BEL
+                       -SW                               */ 
+          0x07, 0x07, 0x07, 0x07, 0x07, 0x05, 0x06, 0x07,
+ /* 0x30  ----  ----   SYN   -IR   -PP  -TRN  -NBS   EOT */
+          0x07, 0x07, 0x16, 0x07, 0x07, 0x07, 0x07, 0x04,
+ /* 0x38  -SBS   -IT  -RFF  -CU3   DC4   NAK  ----   SUB */
+          0x07, 0x07, 0x07, 0x07, 0x14, 0x15, 0x07, 0x1A,
+ /* 0x40    SP   RSP           �ä              ----       */
+          0x20, 0xFF, 0x83, 0x84, 0x85, 0xA0, 0x07, 0x86,
+ /* 0x48                       .     <     (     +     | */
+          0x87, 0xA4, 0x9B, 0x2E, 0x3C, 0x28, 0x2B, 0x7C,
+ /* 0x50     &                                      ---- */
+          0x26, 0x82, 0x88, 0x89, 0x8A, 0xA1, 0x8C, 0x07,
+ /* 0x58           �ß     !     $     *     )     ;       */
+          0x8D, 0xE1, 0x21, 0x24, 0x2A, 0x29, 0x3B, 0xAA,
+ /* 0x60     -     /  ----     �Ä  ----  ----  ----       */
+          0x2D, 0x2F, 0x07, 0x8E, 0x07, 0x07, 0x07, 0x8F,
+ /* 0x68              ----     ,     %     _     >     ? */ 
+          0x80, 0xA5, 0x07, 0x2C, 0x25, 0x5F, 0x3E, 0x3F,
+ /* 0x70  ----        ----  ----  ----  ----  ----  ---- */
+          0x07, 0x90, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07,
+ /* 0x78     *     `     :     #     @     '     =     " */
+          0x70, 0x60, 0x3A, 0x23, 0x40, 0x27, 0x3D, 0x22,
+ /* 0x80     *     a     b     c     d     e     f     g */
+          0x07, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67,
+ /* 0x88     h     i              ----  ----  ----       */
+          0x68, 0x69, 0xAE, 0xAF, 0x07, 0x07, 0x07, 0xF1,
+ /* 0x90     �°     j     k     l     m     n     o     p */
+          0xF8, 0x6A, 0x6B, 0x6C, 0x6D, 0x6E, 0x6F, 0x70,
+ /* 0x98     q     r                    ----        ---- */
+          0x71, 0x72, 0xA6, 0xA7, 0x91, 0x07, 0x92, 0x07,
+ /* 0xA0           ~     s     t     u     v     w     x */
+          0xE6, 0x7E, 0x73, 0x74, 0x75, 0x76, 0x77, 0x78,
+ /* 0xA8     y     z              ----  ----  ----  ---- */
+          0x79, 0x7A, 0xAD, 0xAB, 0x07, 0x07, 0x07, 0x07,
+ /* 0xB0     ^                    ----     �§  ----       */
+          0x5E, 0x9C, 0x9D, 0xFA, 0x07, 0x07, 0x07, 0xAC,
+ /* 0xB8        ----     [     ]  ----  ----  ----  ---- */
+          0xAB, 0x07, 0x5B, 0x5D, 0x07, 0x07, 0x07, 0x07,
+ /* 0xC0     {     A     B     C     D     E     F     G */
+          0x7B, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47,
+ /* 0xC8     H     I  ----           �ö              ---- */
+          0x48, 0x49, 0x07, 0x93, 0x94, 0x95, 0xA2, 0x07,
+ /* 0xD0     }     J     K     L     M     N     O     P */
+          0x7D, 0x4A, 0x4B, 0x4C, 0x4D, 0x4E, 0x4F, 0x50,
+ /* 0xD8     Q     R  ----           �ü                   */
+          0x51, 0x52, 0x07, 0x96, 0x81, 0x97, 0xA3, 0x98,
+ /* 0xE0     \           S     T     U     V     W     X */
+          0x5C, 0xF6, 0x53, 0x54, 0x55, 0x56, 0x57, 0x58,
+ /* 0xE8     Y     Z        ----     �Ö  ----  ----  ---- */
+          0x59, 0x5A, 0xFD, 0x07, 0x99, 0x07, 0x07, 0x07,
+ /* 0xF0     0     1     2     3     4     5     6     7 */
+          0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37,
+ /* 0xF8     8     9  ----  ----     �Ü  ----  ----  ---- */
+          0x38, 0x39, 0x07, 0x07, 0x9A, 0x07, 0x07, 0x07
+};
+
+
+/*
+ * ASCII (IBM PC 437)  -> EBCDIC 500
+ */
+__u8 _ascebc_500[256] =
+{
+ /*00 NUL   SOH   STX   ETX   EOT   ENQ   ACK   BEL */
+     0x00, 0x01, 0x02, 0x03, 0x37, 0x2D, 0x2E, 0x2F,
+ /*08  BS    HT    LF    VT    FF    CR    SO    SI */
+ /*              ->NL                               */
+     0x16, 0x05, 0x15, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F,
+ /*10 DLE   DC1   DC2   DC3   DC4   NAK   SYN   ETB */
+     0x10, 0x11, 0x12, 0x13, 0x3C, 0x3D, 0x32, 0x26,
+ /*18 CAN    EM   SUB   ESC    FS    GS    RS    US */
+ /*                               ->IGS ->IRS ->IUS */
+     0x18, 0x19, 0x3F, 0x27, 0x22, 0x1D, 0x1E, 0x1F,
+ /*20  SP     !     "     #     $     %     &     ' */
+     0x40, 0x4F, 0x7F, 0x7B, 0x5B, 0x6C, 0x50, 0x7D,
+ /*28   (     )     *     +     ,     -    .      / */
+     0x4D, 0x5D, 0x5C, 0x4E, 0x6B, 0x60, 0x4B, 0x61,
+ /*30   0     1     2     3     4     5     6     7 */
+     0xF0, 0xF1, 0xF2, 0xF3, 0xF4, 0xF5, 0xF6, 0xF7,
+ /*38   8     9     :     ;     <     =     >     ? */
+     0xF8, 0xF9, 0x7A, 0x5E, 0x4C, 0x7E, 0x6E, 0x6F,
+ /*40   @     A     B     C     D     E     F     G */
+     0x7C, 0xC1, 0xC2, 0xC3, 0xC4, 0xC5, 0xC6, 0xC7,
+ /*48   H     I     J     K     L     M     N     O */
+     0xC8, 0xC9, 0xD1, 0xD2, 0xD3, 0xD4, 0xD5, 0xD6,
+ /*50   P     Q     R     S     T     U     V     W */
+     0xD7, 0xD8, 0xD9, 0xE2, 0xE3, 0xE4, 0xE5, 0xE6,
+ /*58   X     Y     Z     [     \     ]     ^     _ */
+     0xE7, 0xE8, 0xE9, 0x4A, 0xE0, 0x5A, 0x5F, 0x6D,
+ /*60   `     a     b     c     d     e     f     g */
+     0x79, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87,
+ /*68   h     i     j     k     l     m     n     o */
+     0x88, 0x89, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96,
+ /*70   p     q     r     s     t     u     v     w */
+     0x97, 0x98, 0x99, 0xA2, 0xA3, 0xA4, 0xA5, 0xA6,
+ /*78   x     y     z     {     |     }     ~    DL */
+     0xA7, 0xA8, 0xA9, 0xC0, 0xBB, 0xD0, 0xA1, 0x07,
+ /*80*/
+     0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F,
+ /*88*/
+     0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F,
+ /*90*/
+     0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F,
+ /*98*/
+     0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F,
+ /*A0*/
+     0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F,
+ /*A8*/
+     0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F,
+ /*B0*/
+     0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F,
+ /*B8*/
+     0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F,
+ /*C0*/
+     0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F,
+ /*C8*/
+     0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F,
+ /*D0*/
+     0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F,
+ /*D8*/
+     0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F,
+ /*E0        sz						*/
+     0x3F, 0x59, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F,
+ /*E8*/
+     0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F,
+ /*F0*/
+     0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F, 0x3F,
+ /*F8*/
+     0x90, 0x3F, 0x3F, 0x3F, 0x3F, 0xEA, 0x3F, 0xFF
+};
+
+/*
+ * EBCDIC 500 -> ASCII (IBM PC 437)
+ */
+__u8 _ebcasc_500[256] =
+{
+ /* 0x00   NUL   SOH   STX   ETX  *SEL    HT  *RNL   DEL */
+          0x00, 0x01, 0x02, 0x03, 0x07, 0x09, 0x07, 0x7F,
+ /* 0x08   -GE  -SPS  -RPT    VT    FF    CR    SO    SI */
+          0x07, 0x07, 0x07, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F,
+ /* 0x10   DLE   DC1   DC2   DC3  -RES   -NL    BS  -POC
+                                  -ENP  ->LF             */
+          0x10, 0x11, 0x12, 0x13, 0x07, 0x0A, 0x08, 0x07,
+ /* 0x18   CAN    EM  -UBS  -CU1  -IFS  -IGS  -IRS  -ITB
+                                                    -IUS */
+          0x18, 0x19, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07,
+ /* 0x20   -DS  -SOS    FS  -WUS  -BYP    LF   ETB   ESC
+                                  -INP                   */
+          0x07, 0x07, 0x1C, 0x07, 0x07, 0x0A, 0x17, 0x1B,
+ /* 0x28   -SA  -SFE   -SM  -CSP  -MFA   ENQ   ACK   BEL
+                       -SW                               */ 
+          0x07, 0x07, 0x07, 0x07, 0x07, 0x05, 0x06, 0x07,
+ /* 0x30  ----  ----   SYN   -IR   -PP  -TRN  -NBS   EOT */
+          0x07, 0x07, 0x16, 0x07, 0x07, 0x07, 0x07, 0x04,
+ /* 0x38  -SBS   -IT  -RFF  -CU3   DC4   NAK  ----   SUB */
+          0x07, 0x07, 0x07, 0x07, 0x14, 0x15, 0x07, 0x1A,
+ /* 0x40    SP   RSP           �ä              ----       */
+          0x20, 0xFF, 0x83, 0x84, 0x85, 0xA0, 0x07, 0x86,
+ /* 0x48                 [     .     <     (     +     ! */
+          0x87, 0xA4, 0x5B, 0x2E, 0x3C, 0x28, 0x2B, 0x21,
+ /* 0x50     &                                      ---- */
+          0x26, 0x82, 0x88, 0x89, 0x8A, 0xA1, 0x8C, 0x07,
+ /* 0x58           �ß     ]     $     *     )     ;     ^ */
+          0x8D, 0xE1, 0x5D, 0x24, 0x2A, 0x29, 0x3B, 0x5E,
+ /* 0x60     -     /  ----     �Ä  ----  ----  ----       */
+          0x2D, 0x2F, 0x07, 0x8E, 0x07, 0x07, 0x07, 0x8F,
+ /* 0x68              ----     ,     %     _     >     ? */ 
+          0x80, 0xA5, 0x07, 0x2C, 0x25, 0x5F, 0x3E, 0x3F,
+ /* 0x70  ----        ----  ----  ----  ----  ----  ---- */
+          0x07, 0x90, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07,
+ /* 0x78     *     `     :     #     @     '     =     " */
+          0x70, 0x60, 0x3A, 0x23, 0x40, 0x27, 0x3D, 0x22,
+ /* 0x80     *     a     b     c     d     e     f     g */
+          0x07, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67,
+ /* 0x88     h     i              ----  ----  ----       */
+          0x68, 0x69, 0xAE, 0xAF, 0x07, 0x07, 0x07, 0xF1,
+ /* 0x90     �°     j     k     l     m     n     o     p */
+          0xF8, 0x6A, 0x6B, 0x6C, 0x6D, 0x6E, 0x6F, 0x70,
+ /* 0x98     q     r                    ----        ---- */
+          0x71, 0x72, 0xA6, 0xA7, 0x91, 0x07, 0x92, 0x07,
+ /* 0xA0           ~     s     t     u     v     w     x */
+          0xE6, 0x7E, 0x73, 0x74, 0x75, 0x76, 0x77, 0x78,
+ /* 0xA8     y     z              ----  ----  ----  ---- */
+          0x79, 0x7A, 0xAD, 0xAB, 0x07, 0x07, 0x07, 0x07,
+ /* 0xB0                          ----     �§  ----       */
+          0x9B, 0x9C, 0x9D, 0xFA, 0x07, 0x07, 0x07, 0xAC,
+ /* 0xB8        ----           |  ----  ----  ----  ---- */
+          0xAB, 0x07, 0xAA, 0x7C, 0x07, 0x07, 0x07, 0x07,
+ /* 0xC0     {     A     B     C     D     E     F     G */
+          0x7B, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47,
+ /* 0xC8     H     I  ----           �ö              ---- */
+          0x48, 0x49, 0x07, 0x93, 0x94, 0x95, 0xA2, 0x07,
+ /* 0xD0     }     J     K     L     M     N     O     P */
+          0x7D, 0x4A, 0x4B, 0x4C, 0x4D, 0x4E, 0x4F, 0x50,
+ /* 0xD8     Q     R  ----           �ü                   */
+          0x51, 0x52, 0x07, 0x96, 0x81, 0x97, 0xA3, 0x98,
+ /* 0xE0     \           S     T     U     V     W     X */
+          0x5C, 0xF6, 0x53, 0x54, 0x55, 0x56, 0x57, 0x58,
+ /* 0xE8     Y     Z        ----     �Ö  ----  ----  ---- */
+          0x59, 0x5A, 0xFD, 0x07, 0x99, 0x07, 0x07, 0x07,
+ /* 0xF0     0     1     2     3     4     5     6     7 */
+          0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37,
+ /* 0xF8     8     9  ----  ----     �Ü  ----  ----  ---- */
+          0x38, 0x39, 0x07, 0x07, 0x9A, 0x07, 0x07, 0x07
+};
+
+
+/*
+ * EBCDIC 037/500 conversion table:
+ * from upper to lower case
+ */
+__u8 _ebc_tolower[256] =
+{
+	0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07,
+	0x08, 0x09, 0x0A, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F,
+	0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17,
+	0x18, 0x19, 0x1A, 0x1B, 0x1C, 0x1D, 0x1E, 0x1F,
+	0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27,
+	0x28, 0x29, 0x2A, 0x2B, 0x2C, 0x2D, 0x2E, 0x2F,
+	0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37,
+	0x38, 0x39, 0x3A, 0x3B, 0x3C, 0x3D, 0x3E, 0x3F,
+	0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47,
+	0x48, 0x49, 0x4A, 0x4B, 0x4C, 0x4D, 0x4E, 0x4F,
+	0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57,
+	0x58, 0x59, 0x5A, 0x5B, 0x5C, 0x5D, 0x5E, 0x5F,
+	0x60, 0x61, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47,
+	0x48, 0x49, 0x6A, 0x6B, 0x6C, 0x6D, 0x6E, 0x6F,
+	0x70, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57,
+	0x58, 0x79, 0x7A, 0x7B, 0x7C, 0x7D, 0x7E, 0x7F,
+	0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87,
+	0x88, 0x89, 0x8A, 0x8B, 0x8C, 0x8D, 0x8E, 0x8F,
+	0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97,
+	0x98, 0x99, 0x9A, 0x9B, 0x9C, 0x9D, 0x9C, 0x9F,
+	0xA0, 0xA1, 0xA2, 0xA3, 0xA4, 0xA5, 0xA6, 0xA7,
+	0xA8, 0xA9, 0xAA, 0xAB, 0x8C, 0x8D, 0x8E, 0xAF,
+	0xB0, 0xB1, 0xB2, 0xB3, 0xB4, 0xB5, 0xB6, 0xB7,
+	0xB8, 0xB9, 0xBA, 0xBB, 0xBC, 0xBD, 0xBE, 0xBF,
+	0xC0, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87,
+	0x88, 0x89, 0xCA, 0xCB, 0xCC, 0xCD, 0xCE, 0xCF,
+	0xD0, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97,
+	0x98, 0x99, 0xDA, 0xDB, 0xDC, 0xDD, 0xDE, 0xDF,
+	0xE0, 0xE1, 0xA2, 0xA3, 0xA4, 0xA5, 0xA6, 0xA7,
+	0xA8, 0xA9, 0xEA, 0xCB, 0xCC, 0xCD, 0xCE, 0xCF,
+	0xF0, 0xF1, 0xF2, 0xF3, 0xF4, 0xF5, 0xF6, 0xF7,
+	0xF8, 0xF9, 0xFA, 0xDB, 0xDC, 0xDD, 0xDE, 0xFF
+};
+
+
+/*
+ * EBCDIC 037/500 conversion table:
+ * from lower to upper case
+ */
+__u8 _ebc_toupper[256] =
+{
+	0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07,
+	0x08, 0x09, 0x0A, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F,
+	0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17,
+	0x18, 0x19, 0x1A, 0x1B, 0x1C, 0x1D, 0x1E, 0x1F,
+	0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27,
+	0x28, 0x29, 0x2A, 0x2B, 0x2C, 0x2D, 0x2E, 0x2F,
+	0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37,
+	0x38, 0x39, 0x3A, 0x3B, 0x3C, 0x3D, 0x3E, 0x3F,
+	0x40, 0x41, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67,
+	0x68, 0x69, 0x4A, 0x4B, 0x4C, 0x4D, 0x4E, 0x4F,
+	0x50, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77,
+	0x78, 0x59, 0x5A, 0x5B, 0x5C, 0x5D, 0x5E, 0x5F,
+	0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67,
+	0x68, 0x69, 0x6A, 0x6B, 0x6C, 0x6D, 0x6E, 0x6F,
+	0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77,
+	0x78, 0x79, 0x7A, 0x7B, 0x7C, 0x7D, 0x7E, 0x7F,
+	0x80, 0xC1, 0xC2, 0xC3, 0xC4, 0xC5, 0xC6, 0xC7,
+	0xC8, 0xC9, 0x8A, 0x8B, 0xAC, 0xAD, 0xAE, 0x8F,
+	0x90, 0xD1, 0xD2, 0xD3, 0xD4, 0xD5, 0xD6, 0xD7,
+	0xD8, 0xD9, 0x9A, 0x9B, 0x9E, 0x9D, 0x9E, 0x9F,
+	0xA0, 0xA1, 0xE2, 0xE3, 0xE4, 0xE5, 0xE6, 0xE7,
+	0xE8, 0xE9, 0xAA, 0xAB, 0xAC, 0xAD, 0xAE, 0xAF,
+	0xB0, 0xB1, 0xB2, 0xB3, 0xB4, 0xB5, 0xB6, 0xB7,
+	0xB8, 0xB9, 0xBA, 0xBB, 0xBC, 0xBD, 0xBE, 0xBF,
+	0xC0, 0xC1, 0xC2, 0xC3, 0xC4, 0xC5, 0xC6, 0xC7,
+	0xC8, 0xC9, 0xCA, 0xEB, 0xEC, 0xED, 0xEE, 0xEF,
+	0xD0, 0xD1, 0xD2, 0xD3, 0xD4, 0xD5, 0xD6, 0xD7,
+	0xD8, 0xD9, 0xDA, 0xFB, 0xFC, 0xFD, 0xFE, 0xDF,
+	0xE0, 0xE1, 0xE2, 0xE3, 0xE4, 0xE5, 0xE6, 0xE7,
+	0xE8, 0xE9, 0xEA, 0xEB, 0xEC, 0xED, 0xEE, 0xEF,
+	0xF0, 0xF1, 0xF2, 0xF3, 0xF4, 0xF5, 0xF6, 0xF7,
+	0xF8, 0xF9, 0xFA, 0xFB, 0xFC, 0xFD, 0xFE, 0xFF
+};
+
+EXPORT_SYMBOL(_ascebc_500);
+EXPORT_SYMBOL(_ebcasc_500);
+EXPORT_SYMBOL(_ascebc);
+EXPORT_SYMBOL(_ebcasc);
+EXPORT_SYMBOL(_ebc_tolower);
+EXPORT_SYMBOL(_ebc_toupper);
+
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
new file mode 100644
index 000000000..99b44acbf
--- /dev/null
+++ b/arch/s390/kernel/entry.S
@@ -0,0 +1,1059 @@
+/*
+ *    S390 low-level entry points.
+ *
+ *    Copyright 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),
+ *		 Heiko Carstens <heiko.carstens@de.ibm.com>
+ */
+
+#include <linux/init.h>
+#include <linux/linkage.h>
+#include <asm/processor.h>
+#include <asm/cache.h>
+#include <asm/errno.h>
+#include <asm/ptrace.h>
+#include <asm/thread_info.h>
+#include <asm/asm-offsets.h>
+#include <asm/unistd.h>
+#include <asm/page.h>
+#include <asm/sigp.h>
+#include <asm/irq.h>
+
+__PT_R0      =	__PT_GPRS
+__PT_R1      =	__PT_GPRS + 8
+__PT_R2      =	__PT_GPRS + 16
+__PT_R3      =	__PT_GPRS + 24
+__PT_R4      =	__PT_GPRS + 32
+__PT_R5      =	__PT_GPRS + 40
+__PT_R6      =	__PT_GPRS + 48
+__PT_R7      =	__PT_GPRS + 56
+__PT_R8      =	__PT_GPRS + 64
+__PT_R9      =	__PT_GPRS + 72
+__PT_R10     =	__PT_GPRS + 80
+__PT_R11     =	__PT_GPRS + 88
+__PT_R12     =	__PT_GPRS + 96
+__PT_R13     =	__PT_GPRS + 104
+__PT_R14     =	__PT_GPRS + 112
+__PT_R15     =	__PT_GPRS + 120
+
+STACK_SHIFT = PAGE_SHIFT + THREAD_ORDER
+STACK_SIZE  = 1 << STACK_SHIFT
+STACK_INIT = STACK_SIZE - STACK_FRAME_OVERHEAD - __PT_SIZE
+
+_TIF_WORK	= (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED | \
+		   _TIF_UPROBE)
+_TIF_TRACE	= (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SECCOMP | \
+		   _TIF_SYSCALL_TRACEPOINT)
+_CIF_WORK	= (_CIF_MCCK_PENDING | _CIF_ASCE)
+_PIF_WORK	= (_PIF_PER_TRAP)
+
+#define BASED(name) name-system_call(%r13)
+
+	.macro	TRACE_IRQS_ON
+#ifdef CONFIG_TRACE_IRQFLAGS
+	basr	%r2,%r0
+	brasl	%r14,trace_hardirqs_on_caller
+#endif
+	.endm
+
+	.macro	TRACE_IRQS_OFF
+#ifdef CONFIG_TRACE_IRQFLAGS
+	basr	%r2,%r0
+	brasl	%r14,trace_hardirqs_off_caller
+#endif
+	.endm
+
+	.macro	LOCKDEP_SYS_EXIT
+#ifdef CONFIG_LOCKDEP
+	tm	__PT_PSW+1(%r11),0x01	# returning to user ?
+	jz	.+10
+	brasl	%r14,lockdep_sys_exit
+#endif
+	.endm
+
+	.macro LPP newpp
+#if IS_ENABLED(CONFIG_KVM)
+	tm	__LC_MACHINE_FLAGS+6,0x20	# MACHINE_FLAG_LPP
+	jz	.+8
+	.insn	s,0xb2800000,\newpp
+#endif
+	.endm
+
+	.macro	HANDLE_SIE_INTERCEPT scratch,reason
+#if IS_ENABLED(CONFIG_KVM)
+	tmhh	%r8,0x0001		# interrupting from user ?
+	jnz	.+62
+	lgr	\scratch,%r9
+	slg	\scratch,BASED(.Lsie_critical)
+	clg	\scratch,BASED(.Lsie_critical_length)
+	.if	\reason==1
+	# Some program interrupts are suppressing (e.g. protection).
+	# We must also check the instruction after SIE in that case.
+	# do_protection_exception will rewind to .Lrewind_pad
+	jh	.+42
+	.else
+	jhe	.+42
+	.endif
+	lg	%r14,__SF_EMPTY(%r15)		# get control block pointer
+	LPP	__SF_EMPTY+16(%r15)		# set host id
+	ni	__SIE_PROG0C+3(%r14),0xfe	# no longer in SIE
+	lctlg	%c1,%c1,__LC_USER_ASCE		# load primary asce
+	larl	%r9,sie_exit			# skip forward to sie_exit
+	mvi	__SF_EMPTY+31(%r15),\reason	# set exit reason
+#endif
+	.endm
+
+	.macro	CHECK_STACK stacksize,savearea
+#ifdef CONFIG_CHECK_STACK
+	tml	%r15,\stacksize - CONFIG_STACK_GUARD
+	lghi	%r14,\savearea
+	jz	stack_overflow
+#endif
+	.endm
+
+	.macro	SWITCH_ASYNC savearea,stack,shift
+	tmhh	%r8,0x0001		# interrupting from user ?
+	jnz	1f
+	lgr	%r14,%r9
+	slg	%r14,BASED(.Lcritical_start)
+	clg	%r14,BASED(.Lcritical_length)
+	jhe	0f
+	lghi	%r11,\savearea		# inside critical section, do cleanup
+	brasl	%r14,cleanup_critical
+	tmhh	%r8,0x0001		# retest problem state after cleanup
+	jnz	1f
+0:	lg	%r14,\stack		# are we already on the target stack?
+	slgr	%r14,%r15
+	srag	%r14,%r14,\shift
+	jnz	1f
+	CHECK_STACK 1<<\shift,\savearea
+	aghi	%r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
+	j	2f
+1:	lg	%r15,\stack		# load target stack
+2:	la	%r11,STACK_FRAME_OVERHEAD(%r15)
+	.endm
+
+	.macro UPDATE_VTIME scratch,enter_timer
+	lg	\scratch,__LC_EXIT_TIMER
+	slg	\scratch,\enter_timer
+	alg	\scratch,__LC_USER_TIMER
+	stg	\scratch,__LC_USER_TIMER
+	lg	\scratch,__LC_LAST_UPDATE_TIMER
+	slg	\scratch,__LC_EXIT_TIMER
+	alg	\scratch,__LC_SYSTEM_TIMER
+	stg	\scratch,__LC_SYSTEM_TIMER
+	mvc	__LC_LAST_UPDATE_TIMER(8),\enter_timer
+	.endm
+
+	.macro	LAST_BREAK scratch
+	srag	\scratch,%r10,23
+	jz	.+10
+	stg	%r10,__TI_last_break(%r12)
+	.endm
+
+	.macro REENABLE_IRQS
+	stg	%r8,__LC_RETURN_PSW
+	ni	__LC_RETURN_PSW,0xbf
+	ssm	__LC_RETURN_PSW
+	.endm
+
+	.macro STCK savearea
+#ifdef CONFIG_HAVE_MARCH_Z9_109_FEATURES
+	.insn	s,0xb27c0000,\savearea		# store clock fast
+#else
+	.insn	s,0xb2050000,\savearea		# store clock
+#endif
+	.endm
+
+	.section .kprobes.text, "ax"
+
+/*
+ * Scheduler resume function, called by switch_to
+ *  gpr2 = (task_struct *) prev
+ *  gpr3 = (task_struct *) next
+ * Returns:
+ *  gpr2 = prev
+ */
+ENTRY(__switch_to)
+	stmg	%r6,%r15,__SF_GPRS(%r15)	# store gprs of prev task
+	stg	%r15,__THREAD_ksp(%r2)		# store kernel stack of prev
+	lg	%r4,__THREAD_info(%r2)		# get thread_info of prev
+	lg	%r5,__THREAD_info(%r3)		# get thread_info of next
+	lgr	%r15,%r5
+	aghi	%r15,STACK_INIT			# end of kernel stack of next
+	stg	%r3,__LC_CURRENT		# store task struct of next
+	stg	%r5,__LC_THREAD_INFO		# store thread info of next
+	stg	%r15,__LC_KERNEL_STACK		# store end of kernel stack
+	lctl	%c4,%c4,__TASK_pid(%r3)		# load pid to control reg. 4
+	mvc	__LC_CURRENT_PID+4(4,%r0),__TASK_pid(%r3) # store pid of next
+	lg	%r15,__THREAD_ksp(%r3)		# load kernel stack of next
+	lmg	%r6,%r15,__SF_GPRS(%r15)	# load gprs of next task
+	br	%r14
+
+.L__critical_start:
+/*
+ * SVC interrupt handler routine. System calls are synchronous events and
+ * are executed with interrupts enabled.
+ */
+
+ENTRY(system_call)
+	stpt	__LC_SYNC_ENTER_TIMER
+.Lsysc_stmg:
+	stmg	%r8,%r15,__LC_SAVE_AREA_SYNC
+	lg	%r10,__LC_LAST_BREAK
+	lg	%r12,__LC_THREAD_INFO
+	lghi	%r14,_PIF_SYSCALL
+.Lsysc_per:
+	lg	%r15,__LC_KERNEL_STACK
+	la	%r11,STACK_FRAME_OVERHEAD(%r15)	# pointer to pt_regs
+.Lsysc_vtime:
+	UPDATE_VTIME %r13,__LC_SYNC_ENTER_TIMER
+	LAST_BREAK %r13
+	stmg	%r0,%r7,__PT_R0(%r11)
+	mvc	__PT_R8(64,%r11),__LC_SAVE_AREA_SYNC
+	mvc	__PT_PSW(16,%r11),__LC_SVC_OLD_PSW
+	mvc	__PT_INT_CODE(4,%r11),__LC_SVC_ILC
+	stg	%r14,__PT_FLAGS(%r11)
+.Lsysc_do_svc:
+	lg	%r10,__TI_sysc_table(%r12)	# address of system call table
+	llgh	%r8,__PT_INT_CODE+2(%r11)
+	slag	%r8,%r8,2			# shift and test for svc 0
+	jnz	.Lsysc_nr_ok
+	# svc 0: system call number in %r1
+	llgfr	%r1,%r1				# clear high word in r1
+	cghi	%r1,NR_syscalls
+	jnl	.Lsysc_nr_ok
+	sth	%r1,__PT_INT_CODE+2(%r11)
+	slag	%r8,%r1,2
+.Lsysc_nr_ok:
+	xc	__SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
+	stg	%r2,__PT_ORIG_GPR2(%r11)
+	stg	%r7,STACK_FRAME_OVERHEAD(%r15)
+	lgf	%r9,0(%r8,%r10)			# get system call add.
+	tm	__TI_flags+7(%r12),_TIF_TRACE
+	jnz	.Lsysc_tracesys
+	basr	%r14,%r9			# call sys_xxxx
+	stg	%r2,__PT_R2(%r11)		# store return value
+
+.Lsysc_return:
+	LOCKDEP_SYS_EXIT
+.Lsysc_tif:
+	tm	__PT_PSW+1(%r11),0x01		# returning to user ?
+	jno	.Lsysc_restore
+	tm	__PT_FLAGS+7(%r11),_PIF_WORK
+	jnz	.Lsysc_work
+	tm	__TI_flags+7(%r12),_TIF_WORK
+	jnz	.Lsysc_work			# check for work
+	tm	__LC_CPU_FLAGS+7,_CIF_WORK
+	jnz	.Lsysc_work
+.Lsysc_restore:
+	lg	%r14,__LC_VDSO_PER_CPU
+	lmg	%r0,%r10,__PT_R0(%r11)
+	mvc	__LC_RETURN_PSW(16),__PT_PSW(%r11)
+	stpt	__LC_EXIT_TIMER
+	mvc	__VDSO_ECTG_BASE(16,%r14),__LC_EXIT_TIMER
+	lmg	%r11,%r15,__PT_R11(%r11)
+	lpswe	__LC_RETURN_PSW
+.Lsysc_done:
+
+#
+# One of the work bits is on. Find out which one.
+#
+.Lsysc_work:
+	tm	__LC_CPU_FLAGS+7,_CIF_MCCK_PENDING
+	jo	.Lsysc_mcck_pending
+	tm	__TI_flags+7(%r12),_TIF_NEED_RESCHED
+	jo	.Lsysc_reschedule
+#ifdef CONFIG_UPROBES
+	tm	__TI_flags+7(%r12),_TIF_UPROBE
+	jo	.Lsysc_uprobe_notify
+#endif
+	tm	__PT_FLAGS+7(%r11),_PIF_PER_TRAP
+	jo	.Lsysc_singlestep
+	tm	__TI_flags+7(%r12),_TIF_SIGPENDING
+	jo	.Lsysc_sigpending
+	tm	__TI_flags+7(%r12),_TIF_NOTIFY_RESUME
+	jo	.Lsysc_notify_resume
+	tm	__LC_CPU_FLAGS+7,_CIF_ASCE
+	jo	.Lsysc_uaccess
+	j	.Lsysc_return		# beware of critical section cleanup
+
+#
+# _TIF_NEED_RESCHED is set, call schedule
+#
+.Lsysc_reschedule:
+	larl	%r14,.Lsysc_return
+	jg	schedule
+
+#
+# _CIF_MCCK_PENDING is set, call handler
+#
+.Lsysc_mcck_pending:
+	larl	%r14,.Lsysc_return
+	jg	s390_handle_mcck	# TIF bit will be cleared by handler
+
+#
+# _CIF_ASCE is set, load user space asce
+#
+.Lsysc_uaccess:
+	ni	__LC_CPU_FLAGS+7,255-_CIF_ASCE
+	lctlg	%c1,%c1,__LC_USER_ASCE		# load primary asce
+	j	.Lsysc_return
+
+#
+# _TIF_SIGPENDING is set, call do_signal
+#
+.Lsysc_sigpending:
+	lgr	%r2,%r11		# pass pointer to pt_regs
+	brasl	%r14,do_signal
+	tm	__PT_FLAGS+7(%r11),_PIF_SYSCALL
+	jno	.Lsysc_return
+	lmg	%r2,%r7,__PT_R2(%r11)	# load svc arguments
+	lg	%r10,__TI_sysc_table(%r12)	# address of system call table
+	lghi	%r8,0			# svc 0 returns -ENOSYS
+	llgh	%r1,__PT_INT_CODE+2(%r11)	# load new svc number
+	cghi	%r1,NR_syscalls
+	jnl	.Lsysc_nr_ok		# invalid svc number -> do svc 0
+	slag	%r8,%r1,2
+	j	.Lsysc_nr_ok		# restart svc
+
+#
+# _TIF_NOTIFY_RESUME is set, call do_notify_resume
+#
+.Lsysc_notify_resume:
+	lgr	%r2,%r11		# pass pointer to pt_regs
+	larl	%r14,.Lsysc_return
+	jg	do_notify_resume
+
+#
+# _TIF_UPROBE is set, call uprobe_notify_resume
+#
+#ifdef CONFIG_UPROBES
+.Lsysc_uprobe_notify:
+	lgr	%r2,%r11		# pass pointer to pt_regs
+	larl	%r14,.Lsysc_return
+	jg	uprobe_notify_resume
+#endif
+
+#
+# _PIF_PER_TRAP is set, call do_per_trap
+#
+.Lsysc_singlestep:
+	ni	__PT_FLAGS+7(%r11),255-_PIF_PER_TRAP
+	lgr	%r2,%r11		# pass pointer to pt_regs
+	larl	%r14,.Lsysc_return
+	jg	do_per_trap
+
+#
+# call tracehook_report_syscall_entry/tracehook_report_syscall_exit before
+# and after the system call
+#
+.Lsysc_tracesys:
+	lgr	%r2,%r11		# pass pointer to pt_regs
+	la	%r3,0
+	llgh	%r0,__PT_INT_CODE+2(%r11)
+	stg	%r0,__PT_R2(%r11)
+	brasl	%r14,do_syscall_trace_enter
+	lghi	%r0,NR_syscalls
+	clgr	%r0,%r2
+	jnh	.Lsysc_tracenogo
+	sllg	%r8,%r2,2
+	lgf	%r9,0(%r8,%r10)
+.Lsysc_tracego:
+	lmg	%r3,%r7,__PT_R3(%r11)
+	stg	%r7,STACK_FRAME_OVERHEAD(%r15)
+	lg	%r2,__PT_ORIG_GPR2(%r11)
+	basr	%r14,%r9		# call sys_xxx
+	stg	%r2,__PT_R2(%r11)	# store return value
+.Lsysc_tracenogo:
+	tm	__TI_flags+7(%r12),_TIF_TRACE
+	jz	.Lsysc_return
+	lgr	%r2,%r11		# pass pointer to pt_regs
+	larl	%r14,.Lsysc_return
+	jg	do_syscall_trace_exit
+
+#
+# a new process exits the kernel with ret_from_fork
+#
+ENTRY(ret_from_fork)
+	la	%r11,STACK_FRAME_OVERHEAD(%r15)
+	lg	%r12,__LC_THREAD_INFO
+	brasl	%r14,schedule_tail
+	TRACE_IRQS_ON
+	ssm	__LC_SVC_NEW_PSW	# reenable interrupts
+	tm	__PT_PSW+1(%r11),0x01	# forking a kernel thread ?
+	jne	.Lsysc_tracenogo
+	# it's a kernel thread
+	lmg	%r9,%r10,__PT_R9(%r11)	# load gprs
+ENTRY(kernel_thread_starter)
+	la	%r2,0(%r10)
+	basr	%r14,%r9
+	j	.Lsysc_tracenogo
+
+/*
+ * Program check handler routine
+ */
+
+ENTRY(pgm_check_handler)
+	stpt	__LC_SYNC_ENTER_TIMER
+	stmg	%r8,%r15,__LC_SAVE_AREA_SYNC
+	lg	%r10,__LC_LAST_BREAK
+	lg	%r12,__LC_THREAD_INFO
+	larl	%r13,system_call
+	lmg	%r8,%r9,__LC_PGM_OLD_PSW
+	HANDLE_SIE_INTERCEPT %r14,1
+	tmhh	%r8,0x0001		# test problem state bit
+	jnz	1f			# -> fault in user space
+	tmhh	%r8,0x4000		# PER bit set in old PSW ?
+	jnz	0f			# -> enabled, can't be a double fault
+	tm	__LC_PGM_ILC+3,0x80	# check for per exception
+	jnz	.Lpgm_svcper		# -> single stepped svc
+0:	CHECK_STACK STACK_SIZE,__LC_SAVE_AREA_SYNC
+	aghi	%r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
+	j	2f
+1:	UPDATE_VTIME %r14,__LC_SYNC_ENTER_TIMER
+	LAST_BREAK %r14
+	lg	%r15,__LC_KERNEL_STACK
+	lg	%r14,__TI_task(%r12)
+	lghi	%r13,__LC_PGM_TDB
+	tm	__LC_PGM_ILC+2,0x02	# check for transaction abort
+	jz	2f
+	mvc	__THREAD_trap_tdb(256,%r14),0(%r13)
+2:	la	%r11,STACK_FRAME_OVERHEAD(%r15)
+	stmg	%r0,%r7,__PT_R0(%r11)
+	mvc	__PT_R8(64,%r11),__LC_SAVE_AREA_SYNC
+	stmg	%r8,%r9,__PT_PSW(%r11)
+	mvc	__PT_INT_CODE(4,%r11),__LC_PGM_ILC
+	mvc	__PT_INT_PARM_LONG(8,%r11),__LC_TRANS_EXC_CODE
+	xc	__PT_FLAGS(8,%r11),__PT_FLAGS(%r11)
+	stg	%r10,__PT_ARGS(%r11)
+	tm	__LC_PGM_ILC+3,0x80	# check for per exception
+	jz	0f
+	tmhh	%r8,0x0001		# kernel per event ?
+	jz	.Lpgm_kprobe
+	oi	__PT_FLAGS+7(%r11),_PIF_PER_TRAP
+	mvc	__THREAD_per_address(8,%r14),__LC_PER_ADDRESS
+	mvc	__THREAD_per_cause(2,%r14),__LC_PER_CODE
+	mvc	__THREAD_per_paid(1,%r14),__LC_PER_ACCESS_ID
+0:	REENABLE_IRQS
+	xc	__SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
+	larl	%r1,pgm_check_table
+	llgh	%r10,__PT_INT_CODE+2(%r11)
+	nill	%r10,0x007f
+	sll	%r10,2
+	je	.Lsysc_return
+	lgf	%r1,0(%r10,%r1)		# load address of handler routine
+	lgr	%r2,%r11		# pass pointer to pt_regs
+	basr	%r14,%r1		# branch to interrupt-handler
+	j	.Lsysc_return
+
+#
+# PER event in supervisor state, must be kprobes
+#
+.Lpgm_kprobe:
+	REENABLE_IRQS
+	xc	__SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
+	lgr	%r2,%r11		# pass pointer to pt_regs
+	brasl	%r14,do_per_trap
+	j	.Lsysc_return
+
+#
+# single stepped system call
+#
+.Lpgm_svcper:
+	mvc	__LC_RETURN_PSW(8),__LC_SVC_NEW_PSW
+	larl	%r14,.Lsysc_per
+	stg	%r14,__LC_RETURN_PSW+8
+	lghi	%r14,_PIF_SYSCALL | _PIF_PER_TRAP
+	lpswe	__LC_RETURN_PSW		# branch to .Lsysc_per and enable irqs
+
+/*
+ * IO interrupt handler routine
+ */
+ENTRY(io_int_handler)
+	STCK	__LC_INT_CLOCK
+	stpt	__LC_ASYNC_ENTER_TIMER
+	stmg	%r8,%r15,__LC_SAVE_AREA_ASYNC
+	lg	%r10,__LC_LAST_BREAK
+	lg	%r12,__LC_THREAD_INFO
+	larl	%r13,system_call
+	lmg	%r8,%r9,__LC_IO_OLD_PSW
+	HANDLE_SIE_INTERCEPT %r14,2
+	SWITCH_ASYNC __LC_SAVE_AREA_ASYNC,__LC_ASYNC_STACK,STACK_SHIFT
+	tmhh	%r8,0x0001		# interrupting from user?
+	jz	.Lio_skip
+	UPDATE_VTIME %r14,__LC_ASYNC_ENTER_TIMER
+	LAST_BREAK %r14
+.Lio_skip:
+	stmg	%r0,%r7,__PT_R0(%r11)
+	mvc	__PT_R8(64,%r11),__LC_SAVE_AREA_ASYNC
+	stmg	%r8,%r9,__PT_PSW(%r11)
+	mvc	__PT_INT_CODE(12,%r11),__LC_SUBCHANNEL_ID
+	xc	__PT_FLAGS(8,%r11),__PT_FLAGS(%r11)
+	TRACE_IRQS_OFF
+	xc	__SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
+.Lio_loop:
+	lgr	%r2,%r11		# pass pointer to pt_regs
+	lghi	%r3,IO_INTERRUPT
+	tm	__PT_INT_CODE+8(%r11),0x80	# adapter interrupt ?
+	jz	.Lio_call
+	lghi	%r3,THIN_INTERRUPT
+.Lio_call:
+	brasl	%r14,do_IRQ
+	tm	__LC_MACHINE_FLAGS+6,0x10	# MACHINE_FLAG_LPAR
+	jz	.Lio_return
+	tpi	0
+	jz	.Lio_return
+	mvc	__PT_INT_CODE(12,%r11),__LC_SUBCHANNEL_ID
+	j	.Lio_loop
+.Lio_return:
+	LOCKDEP_SYS_EXIT
+	TRACE_IRQS_ON
+.Lio_tif:
+	tm	__TI_flags+7(%r12),_TIF_WORK
+	jnz	.Lio_work		# there is work to do (signals etc.)
+	tm	__LC_CPU_FLAGS+7,_CIF_WORK
+	jnz	.Lio_work
+.Lio_restore:
+	lg	%r14,__LC_VDSO_PER_CPU
+	lmg	%r0,%r10,__PT_R0(%r11)
+	mvc	__LC_RETURN_PSW(16),__PT_PSW(%r11)
+	stpt	__LC_EXIT_TIMER
+	mvc	__VDSO_ECTG_BASE(16,%r14),__LC_EXIT_TIMER
+	lmg	%r11,%r15,__PT_R11(%r11)
+	lpswe	__LC_RETURN_PSW
+.Lio_done:
+
+#
+# There is work todo, find out in which context we have been interrupted:
+# 1) if we return to user space we can do all _TIF_WORK work
+# 2) if we return to kernel code and kvm is enabled check if we need to
+#    modify the psw to leave SIE
+# 3) if we return to kernel code and preemptive scheduling is enabled check
+#    the preemption counter and if it is zero call preempt_schedule_irq
+# Before any work can be done, a switch to the kernel stack is required.
+#
+.Lio_work:
+	tm	__PT_PSW+1(%r11),0x01	# returning to user ?
+	jo	.Lio_work_user		# yes -> do resched & signal
+#ifdef CONFIG_PREEMPT
+	# check for preemptive scheduling
+	icm	%r0,15,__TI_precount(%r12)
+	jnz	.Lio_restore		# preemption is disabled
+	tm	__TI_flags+7(%r12),_TIF_NEED_RESCHED
+	jno	.Lio_restore
+	# switch to kernel stack
+	lg	%r1,__PT_R15(%r11)
+	aghi	%r1,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
+	mvc	STACK_FRAME_OVERHEAD(__PT_SIZE,%r1),0(%r11)
+	xc	__SF_BACKCHAIN(8,%r1),__SF_BACKCHAIN(%r1)
+	la	%r11,STACK_FRAME_OVERHEAD(%r1)
+	lgr	%r15,%r1
+	# TRACE_IRQS_ON already done at .Lio_return, call
+	# TRACE_IRQS_OFF to keep things symmetrical
+	TRACE_IRQS_OFF
+	brasl	%r14,preempt_schedule_irq
+	j	.Lio_return
+#else
+	j	.Lio_restore
+#endif
+
+#
+# Need to do work before returning to userspace, switch to kernel stack
+#
+.Lio_work_user:
+	lg	%r1,__LC_KERNEL_STACK
+	mvc	STACK_FRAME_OVERHEAD(__PT_SIZE,%r1),0(%r11)
+	xc	__SF_BACKCHAIN(8,%r1),__SF_BACKCHAIN(%r1)
+	la	%r11,STACK_FRAME_OVERHEAD(%r1)
+	lgr	%r15,%r1
+
+#
+# One of the work bits is on. Find out which one.
+#
+.Lio_work_tif:
+	tm	__LC_CPU_FLAGS+7,_CIF_MCCK_PENDING
+	jo	.Lio_mcck_pending
+	tm	__TI_flags+7(%r12),_TIF_NEED_RESCHED
+	jo	.Lio_reschedule
+	tm	__TI_flags+7(%r12),_TIF_SIGPENDING
+	jo	.Lio_sigpending
+	tm	__TI_flags+7(%r12),_TIF_NOTIFY_RESUME
+	jo	.Lio_notify_resume
+	tm	__LC_CPU_FLAGS+7,_CIF_ASCE
+	jo	.Lio_uaccess
+	j	.Lio_return		# beware of critical section cleanup
+
+#
+# _CIF_MCCK_PENDING is set, call handler
+#
+.Lio_mcck_pending:
+	# TRACE_IRQS_ON already done at .Lio_return
+	brasl	%r14,s390_handle_mcck	# TIF bit will be cleared by handler
+	TRACE_IRQS_OFF
+	j	.Lio_return
+
+#
+# _CIF_ASCE is set, load user space asce
+#
+.Lio_uaccess:
+	ni	__LC_CPU_FLAGS+7,255-_CIF_ASCE
+	lctlg	%c1,%c1,__LC_USER_ASCE		# load primary asce
+	j	.Lio_return
+
+#
+# _TIF_NEED_RESCHED is set, call schedule
+#
+.Lio_reschedule:
+	# TRACE_IRQS_ON already done at .Lio_return
+	ssm	__LC_SVC_NEW_PSW	# reenable interrupts
+	brasl	%r14,schedule		# call scheduler
+	ssm	__LC_PGM_NEW_PSW	# disable I/O and ext. interrupts
+	TRACE_IRQS_OFF
+	j	.Lio_return
+
+#
+# _TIF_SIGPENDING or is set, call do_signal
+#
+.Lio_sigpending:
+	# TRACE_IRQS_ON already done at .Lio_return
+	ssm	__LC_SVC_NEW_PSW	# reenable interrupts
+	lgr	%r2,%r11		# pass pointer to pt_regs
+	brasl	%r14,do_signal
+	ssm	__LC_PGM_NEW_PSW	# disable I/O and ext. interrupts
+	TRACE_IRQS_OFF
+	j	.Lio_return
+
+#
+# _TIF_NOTIFY_RESUME or is set, call do_notify_resume
+#
+.Lio_notify_resume:
+	# TRACE_IRQS_ON already done at .Lio_return
+	ssm	__LC_SVC_NEW_PSW	# reenable interrupts
+	lgr	%r2,%r11		# pass pointer to pt_regs
+	brasl	%r14,do_notify_resume
+	ssm	__LC_PGM_NEW_PSW	# disable I/O and ext. interrupts
+	TRACE_IRQS_OFF
+	j	.Lio_return
+
+/*
+ * External interrupt handler routine
+ */
+ENTRY(ext_int_handler)
+	STCK	__LC_INT_CLOCK
+	stpt	__LC_ASYNC_ENTER_TIMER
+	stmg	%r8,%r15,__LC_SAVE_AREA_ASYNC
+	lg	%r10,__LC_LAST_BREAK
+	lg	%r12,__LC_THREAD_INFO
+	larl	%r13,system_call
+	lmg	%r8,%r9,__LC_EXT_OLD_PSW
+	HANDLE_SIE_INTERCEPT %r14,3
+	SWITCH_ASYNC __LC_SAVE_AREA_ASYNC,__LC_ASYNC_STACK,STACK_SHIFT
+	tmhh	%r8,0x0001		# interrupting from user ?
+	jz	.Lext_skip
+	UPDATE_VTIME %r14,__LC_ASYNC_ENTER_TIMER
+	LAST_BREAK %r14
+.Lext_skip:
+	stmg	%r0,%r7,__PT_R0(%r11)
+	mvc	__PT_R8(64,%r11),__LC_SAVE_AREA_ASYNC
+	stmg	%r8,%r9,__PT_PSW(%r11)
+	lghi	%r1,__LC_EXT_PARAMS2
+	mvc	__PT_INT_CODE(4,%r11),__LC_EXT_CPU_ADDR
+	mvc	__PT_INT_PARM(4,%r11),__LC_EXT_PARAMS
+	mvc	__PT_INT_PARM_LONG(8,%r11),0(%r1)
+	xc	__PT_FLAGS(8,%r11),__PT_FLAGS(%r11)
+	TRACE_IRQS_OFF
+	xc	__SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
+	lgr	%r2,%r11		# pass pointer to pt_regs
+	lghi	%r3,EXT_INTERRUPT
+	brasl	%r14,do_IRQ
+	j	.Lio_return
+
+/*
+ * Load idle PSW. The second "half" of this function is in .Lcleanup_idle.
+ */
+ENTRY(psw_idle)
+	stg	%r3,__SF_EMPTY(%r15)
+	larl	%r1,.Lpsw_idle_lpsw+4
+	stg	%r1,__SF_EMPTY+8(%r15)
+	STCK	__CLOCK_IDLE_ENTER(%r2)
+	stpt	__TIMER_IDLE_ENTER(%r2)
+.Lpsw_idle_lpsw:
+	lpswe	__SF_EMPTY(%r15)
+	br	%r14
+.Lpsw_idle_end:
+
+.L__critical_end:
+
+/*
+ * Machine check handler routines
+ */
+ENTRY(mcck_int_handler)
+	STCK	__LC_MCCK_CLOCK
+	la	%r1,4095		# revalidate r1
+	spt	__LC_CPU_TIMER_SAVE_AREA-4095(%r1)	# revalidate cpu timer
+	lmg	%r0,%r15,__LC_GPREGS_SAVE_AREA-4095(%r1)# revalidate gprs
+	lg	%r10,__LC_LAST_BREAK
+	lg	%r12,__LC_THREAD_INFO
+	larl	%r13,system_call
+	lmg	%r8,%r9,__LC_MCK_OLD_PSW
+	HANDLE_SIE_INTERCEPT %r14,4
+	tm	__LC_MCCK_CODE,0x80	# system damage?
+	jo	.Lmcck_panic		# yes -> rest of mcck code invalid
+	lghi	%r14,__LC_CPU_TIMER_SAVE_AREA
+	mvc	__LC_MCCK_ENTER_TIMER(8),0(%r14)
+	tm	__LC_MCCK_CODE+5,0x02	# stored cpu timer value valid?
+	jo	3f
+	la	%r14,__LC_SYNC_ENTER_TIMER
+	clc	0(8,%r14),__LC_ASYNC_ENTER_TIMER
+	jl	0f
+	la	%r14,__LC_ASYNC_ENTER_TIMER
+0:	clc	0(8,%r14),__LC_EXIT_TIMER
+	jl	1f
+	la	%r14,__LC_EXIT_TIMER
+1:	clc	0(8,%r14),__LC_LAST_UPDATE_TIMER
+	jl	2f
+	la	%r14,__LC_LAST_UPDATE_TIMER
+2:	spt	0(%r14)
+	mvc	__LC_MCCK_ENTER_TIMER(8),0(%r14)
+3:	tm	__LC_MCCK_CODE+2,0x09	# mwp + ia of old psw valid?
+	jno	.Lmcck_panic		# no -> skip cleanup critical
+	SWITCH_ASYNC __LC_GPREGS_SAVE_AREA+64,__LC_PANIC_STACK,PAGE_SHIFT
+	tm	%r8,0x0001		# interrupting from user ?
+	jz	.Lmcck_skip
+	UPDATE_VTIME %r14,__LC_MCCK_ENTER_TIMER
+	LAST_BREAK %r14
+.Lmcck_skip:
+	lghi	%r14,__LC_GPREGS_SAVE_AREA+64
+	stmg	%r0,%r7,__PT_R0(%r11)
+	mvc	__PT_R8(64,%r11),0(%r14)
+	stmg	%r8,%r9,__PT_PSW(%r11)
+	xc	__PT_FLAGS(8,%r11),__PT_FLAGS(%r11)
+	xc	__SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
+	lgr	%r2,%r11		# pass pointer to pt_regs
+	brasl	%r14,s390_do_machine_check
+	tm	__PT_PSW+1(%r11),0x01	# returning to user ?
+	jno	.Lmcck_return
+	lg	%r1,__LC_KERNEL_STACK	# switch to kernel stack
+	mvc	STACK_FRAME_OVERHEAD(__PT_SIZE,%r1),0(%r11)
+	xc	__SF_BACKCHAIN(8,%r1),__SF_BACKCHAIN(%r1)
+	la	%r11,STACK_FRAME_OVERHEAD(%r1)
+	lgr	%r15,%r1
+	ssm	__LC_PGM_NEW_PSW	# turn dat on, keep irqs off
+	tm	__LC_CPU_FLAGS+7,_CIF_MCCK_PENDING
+	jno	.Lmcck_return
+	TRACE_IRQS_OFF
+	brasl	%r14,s390_handle_mcck
+	TRACE_IRQS_ON
+.Lmcck_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
+	tm	__LC_RETURN_MCCK_PSW+1,0x01 # returning to user ?
+	jno	0f
+	stpt	__LC_EXIT_TIMER
+	mvc	__VDSO_ECTG_BASE(16,%r14),__LC_EXIT_TIMER
+0:	lmg	%r11,%r15,__PT_R11(%r11)
+	lpswe	__LC_RETURN_MCCK_PSW
+
+.Lmcck_panic:
+	lg	%r14,__LC_PANIC_STACK
+	slgr	%r14,%r15
+	srag	%r14,%r14,PAGE_SHIFT
+	jz	0f
+	lg	%r15,__LC_PANIC_STACK
+0:	aghi	%r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
+	j	.Lmcck_skip
+
+#
+# PSW restart interrupt handler
+#
+ENTRY(restart_int_handler)
+	stg	%r15,__LC_SAVE_AREA_RESTART
+	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	# create stack frame on stack
+	xc	0(STACK_FRAME_OVERHEAD,%r15),0(%r15)
+	lg	%r1,__LC_RESTART_FN		# load fn, parm & source cpu
+	lg	%r2,__LC_RESTART_DATA
+	lg	%r3,__LC_RESTART_SOURCE
+	ltgr	%r3,%r3				# test source cpu address
+	jm	1f				# negative -> skip source stop
+0:	sigp	%r4,%r3,SIGP_SENSE		# 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,SIGP_STOP		# sigp stop to current cpu
+	brc	2,2b
+3:	j	3b
+
+	.section .kprobes.text, "ax"
+
+#ifdef CONFIG_CHECK_STACK
+/*
+ * The synchronous or the asynchronous stack overflowed. We are dead.
+ * No need to properly save the registers, we are going to panic anyway.
+ * Setup a pt_regs so that show_trace can provide a good call trace.
+ */
+stack_overflow:
+	lg	%r15,__LC_PANIC_STACK	# change to panic stack
+	la	%r11,STACK_FRAME_OVERHEAD(%r15)
+	stmg	%r0,%r7,__PT_R0(%r11)
+	stmg	%r8,%r9,__PT_PSW(%r11)
+	mvc	__PT_R8(64,%r11),0(%r14)
+	stg	%r10,__PT_ORIG_GPR2(%r11) # store last break to orig_gpr2
+	xc	__SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
+	lgr	%r2,%r11		# pass pointer to pt_regs
+	jg	kernel_stack_overflow
+#endif
+
+	.align	8
+.Lcleanup_table:
+	.quad	system_call
+	.quad	.Lsysc_do_svc
+	.quad	.Lsysc_tif
+	.quad	.Lsysc_restore
+	.quad	.Lsysc_done
+	.quad	.Lio_tif
+	.quad	.Lio_restore
+	.quad	.Lio_done
+	.quad	psw_idle
+	.quad	.Lpsw_idle_end
+
+cleanup_critical:
+	clg	%r9,BASED(.Lcleanup_table)	# system_call
+	jl	0f
+	clg	%r9,BASED(.Lcleanup_table+8)	# .Lsysc_do_svc
+	jl	.Lcleanup_system_call
+	clg	%r9,BASED(.Lcleanup_table+16)	# .Lsysc_tif
+	jl	0f
+	clg	%r9,BASED(.Lcleanup_table+24)	# .Lsysc_restore
+	jl	.Lcleanup_sysc_tif
+	clg	%r9,BASED(.Lcleanup_table+32)	# .Lsysc_done
+	jl	.Lcleanup_sysc_restore
+	clg	%r9,BASED(.Lcleanup_table+40)	# .Lio_tif
+	jl	0f
+	clg	%r9,BASED(.Lcleanup_table+48)	# .Lio_restore
+	jl	.Lcleanup_io_tif
+	clg	%r9,BASED(.Lcleanup_table+56)	# .Lio_done
+	jl	.Lcleanup_io_restore
+	clg	%r9,BASED(.Lcleanup_table+64)	# psw_idle
+	jl	0f
+	clg	%r9,BASED(.Lcleanup_table+72)	# .Lpsw_idle_end
+	jl	.Lcleanup_idle
+0:	br	%r14
+
+
+.Lcleanup_system_call:
+	# check if stpt has been executed
+	clg	%r9,BASED(.Lcleanup_system_call_insn)
+	jh	0f
+	mvc	__LC_SYNC_ENTER_TIMER(8),__LC_ASYNC_ENTER_TIMER
+	cghi	%r11,__LC_SAVE_AREA_ASYNC
+	je	0f
+	mvc	__LC_SYNC_ENTER_TIMER(8),__LC_MCCK_ENTER_TIMER
+0:	# check if stmg has been executed
+	clg	%r9,BASED(.Lcleanup_system_call_insn+8)
+	jh	0f
+	mvc	__LC_SAVE_AREA_SYNC(64),0(%r11)
+0:	# check if base register setup + TIF bit load has been done
+	clg	%r9,BASED(.Lcleanup_system_call_insn+16)
+	jhe	0f
+	# set up saved registers r10 and r12
+	stg	%r10,16(%r11)		# r10 last break
+	stg	%r12,32(%r11)		# r12 thread-info pointer
+0:	# check if the user time update has been done
+	clg	%r9,BASED(.Lcleanup_system_call_insn+24)
+	jh	0f
+	lg	%r15,__LC_EXIT_TIMER
+	slg	%r15,__LC_SYNC_ENTER_TIMER
+	alg	%r15,__LC_USER_TIMER
+	stg	%r15,__LC_USER_TIMER
+0:	# check if the system time update has been done
+	clg	%r9,BASED(.Lcleanup_system_call_insn+32)
+	jh	0f
+	lg	%r15,__LC_LAST_UPDATE_TIMER
+	slg	%r15,__LC_EXIT_TIMER
+	alg	%r15,__LC_SYSTEM_TIMER
+	stg	%r15,__LC_SYSTEM_TIMER
+0:	# update accounting time stamp
+	mvc	__LC_LAST_UPDATE_TIMER(8),__LC_SYNC_ENTER_TIMER
+	# do LAST_BREAK
+	lg	%r9,16(%r11)
+	srag	%r9,%r9,23
+	jz	0f
+	mvc	__TI_last_break(8,%r12),16(%r11)
+0:	# set up saved register r11
+	lg	%r15,__LC_KERNEL_STACK
+	la	%r9,STACK_FRAME_OVERHEAD(%r15)
+	stg	%r9,24(%r11)		# r11 pt_regs pointer
+	# fill pt_regs
+	mvc	__PT_R8(64,%r9),__LC_SAVE_AREA_SYNC
+	stmg	%r0,%r7,__PT_R0(%r9)
+	mvc	__PT_PSW(16,%r9),__LC_SVC_OLD_PSW
+	mvc	__PT_INT_CODE(4,%r9),__LC_SVC_ILC
+	xc	__PT_FLAGS(8,%r9),__PT_FLAGS(%r9)
+	mvi	__PT_FLAGS+7(%r9),_PIF_SYSCALL
+	# setup saved register r15
+	stg	%r15,56(%r11)		# r15 stack pointer
+	# set new psw address and exit
+	larl	%r9,.Lsysc_do_svc
+	br	%r14
+.Lcleanup_system_call_insn:
+	.quad	system_call
+	.quad	.Lsysc_stmg
+	.quad	.Lsysc_per
+	.quad	.Lsysc_vtime+18
+	.quad	.Lsysc_vtime+42
+
+.Lcleanup_sysc_tif:
+	larl	%r9,.Lsysc_tif
+	br	%r14
+
+.Lcleanup_sysc_restore:
+	clg	%r9,BASED(.Lcleanup_sysc_restore_insn)
+	je	0f
+	lg	%r9,24(%r11)		# get saved pointer to pt_regs
+	mvc	__LC_RETURN_PSW(16),__PT_PSW(%r9)
+	mvc	0(64,%r11),__PT_R8(%r9)
+	lmg	%r0,%r7,__PT_R0(%r9)
+0:	lmg	%r8,%r9,__LC_RETURN_PSW
+	br	%r14
+.Lcleanup_sysc_restore_insn:
+	.quad	.Lsysc_done - 4
+
+.Lcleanup_io_tif:
+	larl	%r9,.Lio_tif
+	br	%r14
+
+.Lcleanup_io_restore:
+	clg	%r9,BASED(.Lcleanup_io_restore_insn)
+	je	0f
+	lg	%r9,24(%r11)		# get saved r11 pointer to pt_regs
+	mvc	__LC_RETURN_PSW(16),__PT_PSW(%r9)
+	mvc	0(64,%r11),__PT_R8(%r9)
+	lmg	%r0,%r7,__PT_R0(%r9)
+0:	lmg	%r8,%r9,__LC_RETURN_PSW
+	br	%r14
+.Lcleanup_io_restore_insn:
+	.quad	.Lio_done - 4
+
+.Lcleanup_idle:
+	# copy interrupt clock & cpu timer
+	mvc	__CLOCK_IDLE_EXIT(8,%r2),__LC_INT_CLOCK
+	mvc	__TIMER_IDLE_EXIT(8,%r2),__LC_ASYNC_ENTER_TIMER
+	cghi	%r11,__LC_SAVE_AREA_ASYNC
+	je	0f
+	mvc	__CLOCK_IDLE_EXIT(8,%r2),__LC_MCCK_CLOCK
+	mvc	__TIMER_IDLE_EXIT(8,%r2),__LC_MCCK_ENTER_TIMER
+0:	# check if stck & stpt have been executed
+	clg	%r9,BASED(.Lcleanup_idle_insn)
+	jhe	1f
+	mvc	__CLOCK_IDLE_ENTER(8,%r2),__CLOCK_IDLE_EXIT(%r2)
+	mvc	__TIMER_IDLE_ENTER(8,%r2),__TIMER_IDLE_EXIT(%r2)
+1:	# account system time going idle
+	lg	%r9,__LC_STEAL_TIMER
+	alg	%r9,__CLOCK_IDLE_ENTER(%r2)
+	slg	%r9,__LC_LAST_UPDATE_CLOCK
+	stg	%r9,__LC_STEAL_TIMER
+	mvc	__LC_LAST_UPDATE_CLOCK(8),__CLOCK_IDLE_EXIT(%r2)
+	lg	%r9,__LC_SYSTEM_TIMER
+	alg	%r9,__LC_LAST_UPDATE_TIMER
+	slg	%r9,__TIMER_IDLE_ENTER(%r2)
+	stg	%r9,__LC_SYSTEM_TIMER
+	mvc	__LC_LAST_UPDATE_TIMER(8),__TIMER_IDLE_EXIT(%r2)
+	# prepare return psw
+	nihh	%r8,0xfcfd		# clear irq & wait state bits
+	lg	%r9,48(%r11)		# return from psw_idle
+	br	%r14
+.Lcleanup_idle_insn:
+	.quad	.Lpsw_idle_lpsw
+
+/*
+ * Integer constants
+ */
+	.align	8
+.Lcritical_start:
+	.quad	.L__critical_start
+.Lcritical_length:
+	.quad	.L__critical_end - .L__critical_start
+
+
+#if IS_ENABLED(CONFIG_KVM)
+/*
+ * sie64a calling convention:
+ * %r2 pointer to sie control block
+ * %r3 guest register save area
+ */
+ENTRY(sie64a)
+	stmg	%r6,%r14,__SF_GPRS(%r15)	# save kernel registers
+	stg	%r2,__SF_EMPTY(%r15)		# save control block pointer
+	stg	%r3,__SF_EMPTY+8(%r15)		# save guest register save area
+	xc	__SF_EMPTY+16(16,%r15),__SF_EMPTY+16(%r15) # host id & reason
+	lmg	%r0,%r13,0(%r3)			# load guest gprs 0-13
+	lg	%r14,__LC_GMAP			# get gmap pointer
+	ltgr	%r14,%r14
+	jz	.Lsie_gmap
+	lctlg	%c1,%c1,__GMAP_ASCE(%r14)	# load primary asce
+.Lsie_gmap:
+	lg	%r14,__SF_EMPTY(%r15)		# get control block pointer
+	oi	__SIE_PROG0C+3(%r14),1		# we are going into SIE now
+	tm	__SIE_PROG20+3(%r14),1		# last exit...
+	jnz	.Lsie_done
+	LPP	__SF_EMPTY(%r15)		# set guest id
+	sie	0(%r14)
+.Lsie_done:
+	LPP	__SF_EMPTY+16(%r15)		# set host id
+	ni	__SIE_PROG0C+3(%r14),0xfe	# no longer in SIE
+	lctlg	%c1,%c1,__LC_USER_ASCE		# load primary asce
+# some program checks are suppressing. C code (e.g. do_protection_exception)
+# will rewind the PSW by the ILC, which is 4 bytes in case of SIE. Other
+# instructions between sie64a and .Lsie_done should not cause program
+# interrupts. So lets use a nop (47 00 00 00) as a landing pad.
+# See also HANDLE_SIE_INTERCEPT
+.Lrewind_pad:
+	nop	0
+	.globl sie_exit
+sie_exit:
+	lg	%r14,__SF_EMPTY+8(%r15)		# load guest register save area
+	stmg	%r0,%r13,0(%r14)		# save guest gprs 0-13
+	lmg	%r6,%r14,__SF_GPRS(%r15)	# restore kernel registers
+	lg	%r2,__SF_EMPTY+24(%r15)		# return exit reason code
+	br	%r14
+.Lsie_fault:
+	lghi	%r14,-EFAULT
+	stg	%r14,__SF_EMPTY+24(%r15)	# set exit reason code
+	j	sie_exit
+
+	.align	8
+.Lsie_critical:
+	.quad	.Lsie_gmap
+.Lsie_critical_length:
+	.quad	.Lsie_done - .Lsie_gmap
+
+	EX_TABLE(.Lrewind_pad,.Lsie_fault)
+	EX_TABLE(sie_exit,.Lsie_fault)
+#endif
+
+	.section .rodata, "a"
+#define SYSCALL(esame,emu)	.long esame
+	.globl	sys_call_table
+sys_call_table:
+#include "syscalls.S"
+#undef SYSCALL
+
+#ifdef CONFIG_COMPAT
+
+#define SYSCALL(esame,emu)	.long emu
+	.globl	sys_call_table_emu
+sys_call_table_emu:
+#include "syscalls.S"
+#undef SYSCALL
+#endif
diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h
new file mode 100644
index 000000000..834df047d
--- /dev/null
+++ b/arch/s390/kernel/entry.h
@@ -0,0 +1,81 @@
+#ifndef _ENTRY_H
+#define _ENTRY_H
+
+#include <linux/types.h>
+#include <linux/signal.h>
+#include <asm/ptrace.h>
+#include <asm/idle.h>
+
+extern void *restart_stack;
+extern unsigned long suspend_zero_pages;
+
+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 *, unsigned long);
+
+asmlinkage long do_syscall_trace_enter(struct pt_regs *regs);
+asmlinkage void do_syscall_trace_exit(struct pt_regs *regs);
+
+int alloc_vector_registers(struct task_struct *tsk);
+
+void do_protection_exception(struct pt_regs *regs);
+void do_dat_exception(struct pt_regs *regs);
+
+void addressing_exception(struct pt_regs *regs);
+void data_exception(struct pt_regs *regs);
+void default_trap_handler(struct pt_regs *regs);
+void divide_exception(struct pt_regs *regs);
+void execute_exception(struct pt_regs *regs);
+void hfp_divide_exception(struct pt_regs *regs);
+void hfp_overflow_exception(struct pt_regs *regs);
+void hfp_significance_exception(struct pt_regs *regs);
+void hfp_sqrt_exception(struct pt_regs *regs);
+void hfp_underflow_exception(struct pt_regs *regs);
+void illegal_op(struct pt_regs *regs);
+void operand_exception(struct pt_regs *regs);
+void overflow_exception(struct pt_regs *regs);
+void privileged_op(struct pt_regs *regs);
+void space_switch_exception(struct pt_regs *regs);
+void special_op_exception(struct pt_regs *regs);
+void specification_exception(struct pt_regs *regs);
+void transaction_exception(struct pt_regs *regs);
+void translation_exception(struct pt_regs *regs);
+void vector_exception(struct pt_regs *regs);
+
+void do_per_trap(struct pt_regs *regs);
+void do_report_trap(struct pt_regs *regs, int si_signo, int si_code, char *str);
+void syscall_trace(struct pt_regs *regs, int entryexit);
+void kernel_stack_overflow(struct pt_regs * regs);
+void do_signal(struct pt_regs *regs);
+void handle_signal32(struct ksignal *ksig, sigset_t *oldset,
+		     struct pt_regs *regs);
+void do_notify_resume(struct pt_regs *regs);
+
+void __init init_IRQ(void);
+void do_IRQ(struct pt_regs *regs, int irq);
+void do_restart(void);
+void __init startup_init(void);
+void die(struct pt_regs *regs, const char *str);
+int setup_profiling_timer(unsigned int multiplier);
+void __init time_init(void);
+int pfn_is_nosave(unsigned long);
+void s390_early_resume(void);
+unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip);
+
+struct s390_mmap_arg_struct;
+struct fadvise64_64_args;
+struct old_sigaction;
+
+long sys_rt_sigreturn(void);
+long sys_sigreturn(void);
+
+long sys_s390_personality(unsigned int personality);
+long sys_s390_runtime_instr(int command, int signum);
+long sys_s390_pci_mmio_write(unsigned long, const void __user *, size_t);
+long sys_s390_pci_mmio_read(unsigned long, void __user *, size_t);
+#endif /* _ENTRY_H */
diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c
new file mode 100644
index 000000000..e0eaf1113
--- /dev/null
+++ b/arch/s390/kernel/ftrace.c
@@ -0,0 +1,244 @@
+/*
+ * Dynamic function tracer architecture backend.
+ *
+ * Copyright IBM Corp. 2009,2014
+ *
+ *   Author(s): Heiko Carstens <heiko.carstens@de.ibm.com>,
+ *		Martin Schwidefsky <schwidefsky@de.ibm.com>
+ */
+
+#include <linux/moduleloader.h>
+#include <linux/hardirq.h>
+#include <linux/uaccess.h>
+#include <linux/ftrace.h>
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/kprobes.h>
+#include <trace/syscall.h>
+#include <asm/asm-offsets.h>
+#include <asm/cacheflush.h>
+#include "entry.h"
+
+/*
+ * The mcount code looks like this:
+ *	stg	%r14,8(%r15)		# offset 0
+ *	larl	%r1,<&counter>		# offset 6
+ *	brasl	%r14,_mcount		# offset 12
+ *	lg	%r14,8(%r15)		# offset 18
+ * Total length is 24 bytes. Only the first instruction will be patched
+ * by ftrace_make_call / ftrace_make_nop.
+ * The enabled ftrace code block looks like this:
+ * >	brasl	%r0,ftrace_caller	# offset 0
+ *	larl	%r1,<&counter>		# offset 6
+ *	brasl	%r14,_mcount		# offset 12
+ *	lg	%r14,8(%r15)		# offset 18
+ * The ftrace function gets called with a non-standard C function call ABI
+ * where r0 contains the return address. It is also expected that the called
+ * function only clobbers r0 and r1, but restores r2-r15.
+ * For module code we can't directly jump to ftrace caller, but need a
+ * trampoline (ftrace_plt), which clobbers also r1.
+ * The return point of the ftrace function has offset 24, so execution
+ * continues behind the mcount block.
+ * The disabled ftrace code block looks like this:
+ * >	jg	.+24			# offset 0
+ *	larl	%r1,<&counter>		# offset 6
+ *	brasl	%r14,_mcount		# offset 12
+ *	lg	%r14,8(%r15)		# offset 18
+ * The jg instruction branches to offset 24 to skip as many instructions
+ * as possible.
+ * In case we use gcc's hotpatch feature the original and also the disabled
+ * function prologue contains only a single six byte instruction and looks
+ * like this:
+ * >	brcl	0,0			# offset 0
+ * To enable ftrace the code gets patched like above and afterwards looks
+ * like this:
+ * >	brasl	%r0,ftrace_caller	# offset 0
+ */
+
+unsigned long ftrace_plt;
+
+static inline void ftrace_generate_orig_insn(struct ftrace_insn *insn)
+{
+#ifdef CC_USING_HOTPATCH
+	/* brcl 0,0 */
+	insn->opc = 0xc004;
+	insn->disp = 0;
+#else
+	/* stg r14,8(r15) */
+	insn->opc = 0xe3e0;
+	insn->disp = 0xf0080024;
+#endif
+}
+
+static inline int is_kprobe_on_ftrace(struct ftrace_insn *insn)
+{
+#ifdef CONFIG_KPROBES
+	if (insn->opc == BREAKPOINT_INSTRUCTION)
+		return 1;
+#endif
+	return 0;
+}
+
+static inline void ftrace_generate_kprobe_nop_insn(struct ftrace_insn *insn)
+{
+#ifdef CONFIG_KPROBES
+	insn->opc = BREAKPOINT_INSTRUCTION;
+	insn->disp = KPROBE_ON_FTRACE_NOP;
+#endif
+}
+
+static inline void ftrace_generate_kprobe_call_insn(struct ftrace_insn *insn)
+{
+#ifdef CONFIG_KPROBES
+	insn->opc = BREAKPOINT_INSTRUCTION;
+	insn->disp = KPROBE_ON_FTRACE_CALL;
+#endif
+}
+
+int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
+		       unsigned long addr)
+{
+	return 0;
+}
+
+int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec,
+		    unsigned long addr)
+{
+	struct ftrace_insn orig, new, old;
+
+	if (probe_kernel_read(&old, (void *) rec->ip, sizeof(old)))
+		return -EFAULT;
+	if (addr == MCOUNT_ADDR) {
+		/* Initial code replacement */
+		ftrace_generate_orig_insn(&orig);
+		ftrace_generate_nop_insn(&new);
+	} else if (is_kprobe_on_ftrace(&old)) {
+		/*
+		 * If we find a breakpoint instruction, a kprobe has been
+		 * placed at the beginning of the function. We write the
+		 * constant KPROBE_ON_FTRACE_NOP into the remaining four
+		 * bytes of the original instruction so that the kprobes
+		 * handler can execute a nop, if it reaches this breakpoint.
+		 */
+		ftrace_generate_kprobe_call_insn(&orig);
+		ftrace_generate_kprobe_nop_insn(&new);
+	} else {
+		/* Replace ftrace call with a nop. */
+		ftrace_generate_call_insn(&orig, rec->ip);
+		ftrace_generate_nop_insn(&new);
+	}
+	/* Verify that the to be replaced code matches what we expect. */
+	if (memcmp(&orig, &old, sizeof(old)))
+		return -EINVAL;
+	s390_kernel_write((void *) rec->ip, &new, sizeof(new));
+	return 0;
+}
+
+int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
+{
+	struct ftrace_insn orig, new, old;
+
+	if (probe_kernel_read(&old, (void *) rec->ip, sizeof(old)))
+		return -EFAULT;
+	if (is_kprobe_on_ftrace(&old)) {
+		/*
+		 * If we find a breakpoint instruction, a kprobe has been
+		 * placed at the beginning of the function. We write the
+		 * constant KPROBE_ON_FTRACE_CALL into the remaining four
+		 * bytes of the original instruction so that the kprobes
+		 * handler can execute a brasl if it reaches this breakpoint.
+		 */
+		ftrace_generate_kprobe_nop_insn(&orig);
+		ftrace_generate_kprobe_call_insn(&new);
+	} else {
+		/* Replace nop with an ftrace call. */
+		ftrace_generate_nop_insn(&orig);
+		ftrace_generate_call_insn(&new, rec->ip);
+	}
+	/* Verify that the to be replaced code matches what we expect. */
+	if (memcmp(&orig, &old, sizeof(old)))
+		return -EINVAL;
+	s390_kernel_write((void *) rec->ip, &new, sizeof(new));
+	return 0;
+}
+
+int ftrace_update_ftrace_func(ftrace_func_t func)
+{
+	return 0;
+}
+
+int __init ftrace_dyn_arch_init(void)
+{
+	return 0;
+}
+
+static int __init ftrace_plt_init(void)
+{
+	unsigned int *ip;
+
+	ftrace_plt = (unsigned long) module_alloc(PAGE_SIZE);
+	if (!ftrace_plt)
+		panic("cannot allocate ftrace plt\n");
+	ip = (unsigned int *) ftrace_plt;
+	ip[0] = 0x0d10e310; /* basr 1,0; lg 1,10(1); br 1 */
+	ip[1] = 0x100a0004;
+	ip[2] = 0x07f10000;
+	ip[3] = FTRACE_ADDR >> 32;
+	ip[4] = FTRACE_ADDR & 0xffffffff;
+	set_memory_ro(ftrace_plt, 1);
+	return 0;
+}
+device_initcall(ftrace_plt_init);
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+/*
+ * Hook the return address and push it in the stack of return addresses
+ * in current thread info.
+ */
+unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip)
+{
+	struct ftrace_graph_ent trace;
+
+	if (unlikely(ftrace_graph_is_dead()))
+		goto out;
+	if (unlikely(atomic_read(&current->tracing_graph_pause)))
+		goto out;
+	ip = (ip & PSW_ADDR_INSN) - MCOUNT_INSN_SIZE;
+	trace.func = ip;
+	trace.depth = current->curr_ret_stack + 1;
+	/* Only trace if the calling function expects to. */
+	if (!ftrace_graph_entry(&trace))
+		goto out;
+	if (ftrace_push_return_trace(parent, ip, &trace.depth, 0) == -EBUSY)
+		goto out;
+	parent = (unsigned long) return_to_handler;
+out:
+	return parent;
+}
+NOKPROBE_SYMBOL(prepare_ftrace_return);
+
+/*
+ * Patch the kernel code at ftrace_graph_caller location. The instruction
+ * there is branch relative on condition. To enable the ftrace graph code
+ * block, we simply patch the mask field of the instruction to zero and
+ * turn the instruction into a nop.
+ * To disable the ftrace graph code the mask field will be patched to
+ * all ones, which turns the instruction into an unconditional branch.
+ */
+int ftrace_enable_ftrace_graph_caller(void)
+{
+	u8 op = 0x04; /* set mask field to zero */
+
+	s390_kernel_write(__va(ftrace_graph_caller)+1, &op, sizeof(op));
+	return 0;
+}
+
+int ftrace_disable_ftrace_graph_caller(void)
+{
+	u8 op = 0xf4; /* set mask field to all ones */
+
+	s390_kernel_write(__va(ftrace_graph_caller)+1, &op, sizeof(op));
+	return 0;
+}
+
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
diff --git a/arch/s390/kernel/head.S b/arch/s390/kernel/head.S
new file mode 100644
index 000000000..59b7c6470
--- /dev/null
+++ b/arch/s390/kernel/head.S
@@ -0,0 +1,454 @@
+/*
+ * Copyright IBM Corp. 1999, 2010
+ *
+ *    Author(s): Hartmut Penner <hp@de.ibm.com>
+ *		 Martin Schwidefsky <schwidefsky@de.ibm.com>
+ *		 Rob van der Heij <rvdhei@iae.nl>
+ *		 Heiko Carstens <heiko.carstens@de.ibm.com>
+ *
+ * There are 5 different IPL methods
+ *  1) load the image directly into ram at address 0 and do an PSW restart
+ *  2) linload will load the image from address 0x10000 to memory 0x10000
+ *     and start the code thru LPSW 0x0008000080010000 (VM only, deprecated)
+ *  3) generate the tape ipl header, store the generated image on a tape
+ *     and ipl from it
+ *     In case of SL tape you need to IPL 5 times to get past VOL1 etc
+ *  4) generate the vm reader ipl header, move the generated image to the
+ *     VM reader (use option NOH!) and do a ipl from reader (VM only)
+ *  5) direct call of start by the SALIPL loader
+ *  We use the cpuid to distinguish between VM and native ipl
+ *  params for kernel are pushed to 0x10400 (see setup.h)
+ *
+ */
+
+#include <linux/init.h>
+#include <linux/linkage.h>
+#include <asm/asm-offsets.h>
+#include <asm/thread_info.h>
+#include <asm/page.h>
+
+#define ARCH_OFFSET	4
+
+__HEAD
+
+#define IPL_BS	0x730
+	.org	0
+	.long	0x00080000,0x80000000+iplstart	# The first 24 bytes are loaded
+	.long	0x02000018,0x60000050		# by ipl to addresses 0-23.
+	.long	0x02000068,0x60000050		# (a PSW and two CCWs).
+	.fill	80-24,1,0x40			# bytes 24-79 are discarded !!
+	.long	0x020000f0,0x60000050		# The next 160 byte are loaded
+	.long	0x02000140,0x60000050		# to addresses 0x18-0xb7
+	.long	0x02000190,0x60000050		# They form the continuation
+	.long	0x020001e0,0x60000050		# of the CCW program started
+	.long	0x02000230,0x60000050		# by ipl and load the range
+	.long	0x02000280,0x60000050		# 0x0f0-0x730 from the image
+	.long	0x020002d0,0x60000050		# to the range 0x0f0-0x730
+	.long	0x02000320,0x60000050		# in memory. At the end of
+	.long	0x02000370,0x60000050		# the channel program the PSW
+	.long	0x020003c0,0x60000050		# at location 0 is loaded.
+	.long	0x02000410,0x60000050		# Initial processing starts
+	.long	0x02000460,0x60000050		# at 0x200 = iplstart.
+	.long	0x020004b0,0x60000050
+	.long	0x02000500,0x60000050
+	.long	0x02000550,0x60000050
+	.long	0x020005a0,0x60000050
+	.long	0x020005f0,0x60000050
+	.long	0x02000640,0x60000050
+	.long	0x02000690,0x60000050
+	.long	0x020006e0,0x20000050
+
+	.org	0x200
+#
+# subroutine to set architecture mode
+#
+.Lsetmode:
+	mvi	__LC_AR_MODE_ID,1	# set esame flag
+	slr	%r0,%r0 		# set cpuid to zero
+	lhi	%r1,2			# mode 2 = esame (dump)
+	sigp	%r1,%r0,0x12		# switch to esame mode
+	bras	%r13,0f
+	.fill	16,4,0x0
+0:	lmh	%r0,%r15,0(%r13)	# clear high-order half of gprs
+	sam31				# switch to 31 bit addressing mode
+	br	%r14
+
+#
+# subroutine to wait for end I/O
+#
+.Lirqwait:
+	mvc	0x1f0(16),.Lnewpsw	# set up IO interrupt psw
+	lpsw	.Lwaitpsw
+.Lioint:
+	br	%r14
+	.align	8
+.Lnewpsw:
+	.quad	0x0000000080000000,.Lioint
+.Lwaitpsw:
+	.long	0x020a0000,0x80000000+.Lioint
+
+#
+# subroutine for loading cards from the reader
+#
+.Lloader:
+	la	%r4,0(%r14)
+	la	%r3,.Lorb		# r2 = address of orb into r2
+	la	%r5,.Lirb		# r4 = address of irb
+	la	%r6,.Lccws
+	la	%r7,20
+.Linit:
+	st	%r2,4(%r6)		# initialize CCW data addresses
+	la	%r2,0x50(%r2)
+	la	%r6,8(%r6)
+	bct	7,.Linit
+
+	lctl	%c6,%c6,.Lcr6		# set IO subclass mask
+	slr	%r2,%r2
+.Lldlp:
+	ssch	0(%r3)			# load chunk of 1600 bytes
+	bnz	.Llderr
+.Lwait4irq:
+	bas	%r14,.Lirqwait
+	c	%r1,0xb8		# compare subchannel number
+	bne	.Lwait4irq
+	tsch	0(%r5)
+
+	slr	%r0,%r0
+	ic	%r0,8(%r5)		# get device status
+	chi	%r0,8			# channel end ?
+	be	.Lcont
+	chi	%r0,12			# channel end + device end ?
+	be	.Lcont
+
+	l	%r0,4(%r5)
+	s	%r0,8(%r3)		# r0/8 = number of ccws executed
+	mhi	%r0,10			# *10 = number of bytes in ccws
+	lh	%r3,10(%r5)		# get residual count
+	sr	%r0,%r3 		# #ccws*80-residual=#bytes read
+	ar	%r2,%r0
+
+	br	%r4			# r2 contains the total size
+
+.Lcont:
+	ahi	%r2,0x640		# add 0x640 to total size
+	la	%r6,.Lccws
+	la	%r7,20
+.Lincr:
+	l	%r0,4(%r6)		# update CCW data addresses
+	ahi	%r0,0x640
+	st	%r0,4(%r6)
+	ahi	%r6,8
+	bct	7,.Lincr
+
+	b	.Lldlp
+.Llderr:
+	lpsw	.Lcrash
+
+	.align	8
+.Lorb:	.long	0x00000000,0x0080ff00,.Lccws
+.Lirb:	.long	0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0
+.Lcr6:	.long	0xff000000
+.Lloadp:.long	0,0
+	.align	8
+.Lcrash:.long	0x000a0000,0x00000000
+
+	.align	8
+.Lccws: .rept	19
+	.long	0x02600050,0x00000000
+	.endr
+	.long	0x02200050,0x00000000
+
+iplstart:
+	bas	%r14,.Lsetmode		# Immediately switch to 64 bit mode
+	lh	%r1,0xb8		# test if subchannel number
+	bct	%r1,.Lnoload		#  is valid
+	l	%r1,0xb8		# load ipl subchannel number
+	la	%r2,IPL_BS		# load start address
+	bas	%r14,.Lloader		# load rest of ipl image
+	l	%r12,.Lparm		# pointer to parameter area
+	st	%r1,IPL_DEVICE+ARCH_OFFSET-PARMAREA(%r12) # save ipl device number
+
+#
+# load parameter file from ipl device
+#
+.Lagain1:
+	l	%r2,.Linitrd		# ramdisk loc. is temp
+	bas	%r14,.Lloader		# load parameter file
+	ltr	%r2,%r2 		# got anything ?
+	bz	.Lnopf
+	chi	%r2,895
+	bnh	.Lnotrunc
+	la	%r2,895
+.Lnotrunc:
+	l	%r4,.Linitrd
+	clc	0(3,%r4),.L_hdr		# if it is HDRx
+	bz	.Lagain1		# skip dataset header
+	clc	0(3,%r4),.L_eof		# if it is EOFx
+	bz	.Lagain1		# skip dateset trailer
+	la	%r5,0(%r4,%r2)
+	lr	%r3,%r2
+	la	%r3,COMMAND_LINE-PARMAREA(%r12) # load adr. of command line
+	mvc	0(256,%r3),0(%r4)
+	mvc	256(256,%r3),256(%r4)
+	mvc	512(256,%r3),512(%r4)
+	mvc	768(122,%r3),768(%r4)
+	slr	%r0,%r0
+	b	.Lcntlp
+.Ldelspc:
+	ic	%r0,0(%r2,%r3)
+	chi	%r0,0x20		# is it a space ?
+	be	.Lcntlp
+	ahi	%r2,1
+	b	.Leolp
+.Lcntlp:
+	brct	%r2,.Ldelspc
+.Leolp:
+	slr	%r0,%r0
+	stc	%r0,0(%r2,%r3)		# terminate buffer
+.Lnopf:
+
+#
+# load ramdisk from ipl device
+#
+.Lagain2:
+	l	%r2,.Linitrd		# addr of ramdisk
+	st	%r2,INITRD_START+ARCH_OFFSET-PARMAREA(%r12)
+	bas	%r14,.Lloader		# load ramdisk
+	st	%r2,INITRD_SIZE+ARCH_OFFSET-PARMAREA(%r12) # store size of rd
+	ltr	%r2,%r2
+	bnz	.Lrdcont
+	st	%r2,INITRD_START+ARCH_OFFSET-PARMAREA(%r12) # no ramdisk found
+.Lrdcont:
+	l	%r2,.Linitrd
+
+	clc	0(3,%r2),.L_hdr		# skip HDRx and EOFx
+	bz	.Lagain2
+	clc	0(3,%r2),.L_eof
+	bz	.Lagain2
+
+#
+# reset files in VM reader
+#
+	stidp	.Lcpuid			# store cpuid
+	tm	.Lcpuid,0xff		# running VM ?
+	bno	.Lnoreset
+	la	%r2,.Lreset
+	lhi	%r3,26
+	diag	%r2,%r3,8
+	la	%r5,.Lirb
+	stsch	0(%r5)			# check if irq is pending
+	tm	30(%r5),0x0f		# by verifying if any of the
+	bnz	.Lwaitforirq		# activity or status control
+	tm	31(%r5),0xff		# bits is set in the schib
+	bz	.Lnoreset
+.Lwaitforirq:
+	bas	%r14,.Lirqwait		# wait for IO interrupt
+	c	%r1,0xb8		# compare subchannel number
+	bne	.Lwaitforirq
+	la	%r5,.Lirb
+	tsch	0(%r5)
+.Lnoreset:
+	b	.Lnoload
+
+#
+# everything loaded, go for it
+#
+.Lnoload:
+	l	%r1,.Lstartup
+	br	%r1
+
+.Linitrd:.long _end			# default address of initrd
+.Lparm:	.long  PARMAREA
+.Lstartup: .long startup
+.Lreset:.byte	0xc3,0xc8,0xc1,0xd5,0xc7,0xc5,0x40,0xd9,0xc4,0xd9,0x40
+	.byte	0xc1,0xd3,0xd3,0x40,0xd2,0xc5,0xc5,0xd7,0x40,0xd5,0xd6
+	.byte	0xc8,0xd6,0xd3,0xc4	# "change rdr all keep nohold"
+.L_eof: .long	0xc5d6c600	 /* C'EOF' */
+.L_hdr: .long	0xc8c4d900	 /* C'HDR' */
+	.align	8
+.Lcpuid:.fill	8,1,0
+
+#
+# SALIPL loader support. Based on a patch by Rob van der Heij.
+# This entry point is called directly from the SALIPL loader and
+# doesn't need a builtin ipl record.
+#
+	.org	0x800
+ENTRY(start)
+	stm	%r0,%r15,0x07b0		# store registers
+	bas	%r14,.Lsetmode		# Immediately switch to 64 bit mode
+	basr	%r12,%r0
+.base:
+	l	%r11,.parm
+	l	%r8,.cmd		# pointer to command buffer
+
+	ltr	%r9,%r9			# do we have SALIPL parameters?
+	bp	.sk8x8
+
+	mvc	0(64,%r8),0x00b0	# copy saved registers
+	xc	64(240-64,%r8),0(%r8)	# remainder of buffer
+	tr	0(64,%r8),.lowcase
+	b	.gotr
+.sk8x8:
+	mvc	0(240,%r8),0(%r9)	# copy iplparms into buffer
+.gotr:
+	slr	%r0,%r0
+	st	%r0,INITRD_SIZE+ARCH_OFFSET-PARMAREA(%r11)
+	st	%r0,INITRD_START+ARCH_OFFSET-PARMAREA(%r11)
+	j	startup 		# continue with startup
+.cmd:	.long	COMMAND_LINE		# address of command line buffer
+.parm:	.long	PARMAREA
+.lowcase:
+	.byte 0x00,0x01,0x02,0x03,0x04,0x05,0x06,0x07
+	.byte 0x08,0x09,0x0a,0x0b,0x0c,0x0d,0x0e,0x0f
+	.byte 0x10,0x11,0x12,0x13,0x14,0x15,0x16,0x17
+	.byte 0x18,0x19,0x1a,0x1b,0x1c,0x1d,0x1e,0x1f
+	.byte 0x20,0x21,0x22,0x23,0x24,0x25,0x26,0x27
+	.byte 0x28,0x29,0x2a,0x2b,0x2c,0x2d,0x2e,0x2f
+	.byte 0x30,0x31,0x32,0x33,0x34,0x35,0x36,0x37
+	.byte 0x38,0x39,0x3a,0x3b,0x3c,0x3d,0x3e,0x3f
+	.byte 0x40,0x41,0x42,0x43,0x44,0x45,0x46,0x47
+	.byte 0x48,0x49,0x4a,0x4b,0x4c,0x4d,0x4e,0x4f
+	.byte 0x50,0x51,0x52,0x53,0x54,0x55,0x56,0x57
+	.byte 0x58,0x59,0x5a,0x5b,0x5c,0x5d,0x5e,0x5f
+	.byte 0x60,0x61,0x62,0x63,0x64,0x65,0x66,0x67
+	.byte 0x68,0x69,0x6a,0x6b,0x6c,0x6d,0x6e,0x6f
+	.byte 0x70,0x71,0x72,0x73,0x74,0x75,0x76,0x77
+	.byte 0x78,0x79,0x7a,0x7b,0x7c,0x7d,0x7e,0x7f
+
+	.byte 0x80,0x81,0x82,0x83,0x84,0x85,0x86,0x87
+	.byte 0x88,0x89,0x8a,0x8b,0x8c,0x8d,0x8e,0x8f
+	.byte 0x90,0x91,0x92,0x93,0x94,0x95,0x96,0x97
+	.byte 0x98,0x99,0x9a,0x9b,0x9c,0x9d,0x9e,0x9f
+	.byte 0xa0,0xa1,0xa2,0xa3,0xa4,0xa5,0xa6,0xa7
+	.byte 0xa8,0xa9,0xaa,0xab,0xac,0xad,0xae,0xaf
+	.byte 0xb0,0xb1,0xb2,0xb3,0xb4,0xb5,0xb6,0xb7
+	.byte 0xb8,0xb9,0xba,0xbb,0xbc,0xbd,0xbe,0xbf
+	.byte 0xc0,0x81,0x82,0x83,0x84,0x85,0x86,0x87	# .abcdefg
+	.byte 0x88,0x89,0xca,0xcb,0xcc,0xcd,0xce,0xcf	# hi
+	.byte 0xd0,0x91,0x92,0x93,0x94,0x95,0x96,0x97	# .jklmnop
+	.byte 0x98,0x99,0xda,0xdb,0xdc,0xdd,0xde,0xdf	# qr
+	.byte 0xe0,0xe1,0xa2,0xa3,0xa4,0xa5,0xa6,0xa7	# ..stuvwx
+	.byte 0xa8,0xa9,0xea,0xeb,0xec,0xed,0xee,0xef	# yz
+	.byte 0xf0,0xf1,0xf2,0xf3,0xf4,0xf5,0xf6,0xf7
+	.byte 0xf8,0xf9,0xfa,0xfb,0xfc,0xfd,0xfe,0xff
+
+#
+# startup-code at 0x10000, running in absolute addressing mode
+# this is called either by the ipl loader or directly by PSW restart
+# or linload or SALIPL
+#
+	.org	0x10000
+ENTRY(startup)
+	j	.Lep_startup_normal
+	.org	0x10008
+#
+# This is a list of s390 kernel entry points. At address 0x1000f the number of
+# valid entry points is stored.
+#
+# IMPORTANT: Do not change this table, it is s390 kernel ABI!
+#
+	.ascii	"S390EP"
+	.byte	0x00,0x01
+#
+# kdump startup-code at 0x10010, running in 64 bit absolute addressing mode
+#
+	.org	0x10010
+ENTRY(startup_kdump)
+	j	.Lep_startup_kdump
+.Lep_startup_normal:
+	mvi	__LC_AR_MODE_ID,1	# set esame flag
+	slr	%r0,%r0 		# set cpuid to zero
+	lhi	%r1,2			# mode 2 = esame (dump)
+	sigp	%r1,%r0,0x12		# switch to esame mode
+	bras	%r13,0f
+	.fill	16,4,0x0
+0:	lmh	%r0,%r15,0(%r13)	# clear high-order half of gprs
+	sam31				# switch to 31 bit addressing mode
+	basr	%r13,0			# get base
+.LPG0:
+	xc	0x200(256),0x200	# partially clear lowcore
+	xc	0x300(256),0x300
+	xc	0xe00(256),0xe00
+	stck	__LC_LAST_UPDATE_CLOCK
+	spt	6f-.LPG0(%r13)
+	mvc	__LC_LAST_UPDATE_TIMER(8),6f-.LPG0(%r13)
+	xc	__LC_STFL_FAC_LIST(8),__LC_STFL_FAC_LIST
+	# check capabilities against MARCH_{G5,Z900,Z990,Z9_109,Z10}
+	.insn	s,0xb2b10000,0		# store facilities @ __LC_STFL_FAC_LIST
+	tm	__LC_STFL_FAC_LIST,0x01	# stfle available ?
+	jz	0f
+	la	%r0,1
+	.insn	s,0xb2b00000,__LC_STFL_FAC_LIST	# store facility list extended
+	# verify if all required facilities are supported by the machine
+0:	la	%r1,__LC_STFL_FAC_LIST
+	la	%r2,3f+8-.LPG0(%r13)
+	l	%r3,0(%r2)
+1:	l	%r0,0(%r1)
+	n	%r0,4(%r2)
+	cl	%r0,4(%r2)
+	jne	2f
+	la	%r1,4(%r1)
+	la	%r2,4(%r2)
+	ahi	%r3,-1
+	jnz	1b
+	j	4f
+2:	l	%r15,.Lstack-.LPG0(%r13)
+	ahi	%r15,-96
+	la	%r2,.Lals_string-.LPG0(%r13)
+	l	%r3,.Lsclp_print-.LPG0(%r13)
+	basr	%r14,%r3
+	lpsw	3f-.LPG0(%r13)		# machine type not good enough, crash
+.Lals_string:
+	.asciz	"The Linux kernel requires more recent processor hardware"
+.Lsclp_print:
+	.long	_sclp_print_early
+.Lstack:
+	.long	0x8000 + (1<<(PAGE_SHIFT+THREAD_ORDER))
+	.align 16
+3:	.long	0x000a0000,0x8badcccc
+
+# List of facilities that are required. If not all facilities are present
+# the kernel will crash. Format is number of facility words with bits set,
+# followed by the facility words.
+
+#if defined(CONFIG_MARCH_Z13)
+	.long 3, 0xc100eff2, 0xf46ce800, 0x00400000
+#elif defined(CONFIG_MARCH_ZEC12)
+	.long 3, 0xc100eff2, 0xf46ce800, 0x00400000
+#elif defined(CONFIG_MARCH_Z196)
+	.long 2, 0xc100eff2, 0xf46c0000
+#elif defined(CONFIG_MARCH_Z10)
+	.long 2, 0xc100eff2, 0xf0680000
+#elif defined(CONFIG_MARCH_Z9_109)
+	.long 1, 0xc100efc2
+#elif defined(CONFIG_MARCH_Z990)
+	.long 1, 0xc0002000
+#elif defined(CONFIG_MARCH_Z900)
+	.long 1, 0xc0000000
+#endif
+4:
+	/* Continue with 64bit startup code in head64.S */
+	sam64				# switch to 64 bit mode
+	jg	startup_continue
+
+	.align	8
+6:	.long	0x7fffffff,0xffffffff
+
+#include "head_kdump.S"
+
+#
+# params at 10400 (setup.h)
+#
+	.org	PARMAREA
+	.long	0,0			# IPL_DEVICE
+	.long	0,0			# INITRD_START
+	.long	0,0			# INITRD_SIZE
+	.long	0,0			# OLDMEM_BASE
+	.long	0,0			# OLDMEM_SIZE
+
+	.org	COMMAND_LINE
+	.byte	"root=/dev/ram0 ro"
+	.byte	0
+
+	.org	0x11000
diff --git a/arch/s390/kernel/head64.S b/arch/s390/kernel/head64.S
new file mode 100644
index 000000000..d7c005075
--- /dev/null
+++ b/arch/s390/kernel/head64.S
@@ -0,0 +1,105 @@
+/*
+ * Copyright IBM Corp. 1999, 2010
+ *
+ *   Author(s):	Hartmut Penner <hp@de.ibm.com>
+ *		Martin Schwidefsky <schwidefsky@de.ibm.com>
+ *		Rob van der Heij <rvdhei@iae.nl>
+ *		Heiko Carstens <heiko.carstens@de.ibm.com>
+ *
+ */
+
+#include <linux/init.h>
+#include <linux/linkage.h>
+#include <asm/asm-offsets.h>
+#include <asm/thread_info.h>
+#include <asm/page.h>
+
+__HEAD
+ENTRY(startup_continue)
+	larl	%r1,sched_clock_base_cc
+	mvc	0(8,%r1),__LC_LAST_UPDATE_CLOCK
+	larl	%r13,.LPG1		# get base
+	lctlg	%c0,%c15,.Lctl-.LPG1(%r13)	# load control registers
+	lg	%r12,.Lparmaddr-.LPG1(%r13)	# pointer to parameter area
+					# move IPL device to lowcore
+	lghi	%r0,__LC_PASTE
+	stg	%r0,__LC_VDSO_PER_CPU
+#
+# Setup stack
+#
+	larl	%r15,init_thread_union
+	stg	%r15,__LC_THREAD_INFO	# cache thread info in lowcore
+	lg	%r14,__TI_task(%r15)	# cache current in lowcore
+	stg	%r14,__LC_CURRENT
+	aghi	%r15,1<<(PAGE_SHIFT+THREAD_ORDER) # init_task_union + THREAD_SIZE
+	stg	%r15,__LC_KERNEL_STACK	# set end of kernel stack
+	aghi	%r15,-160
+#
+# Save ipl parameters, clear bss memory, initialize storage key for kernel pages,
+# and create a kernel NSS if the SAVESYS= parm is defined
+#
+	brasl	%r14,startup_init
+	lpswe	.Lentry-.LPG1(13)	# jump to _stext in primary-space,
+					# virtual and never return ...
+	.align	16
+.LPG1:
+.Lentry:.quad	0x0000000180000000,_stext
+.Lctl:	.quad	0x04040000		# cr0: AFP registers & secondary space
+	.quad	0			# cr1: primary space segment table
+	.quad	.Lduct			# cr2: dispatchable unit control table
+	.quad	0			# cr3: instruction authorization
+	.quad	0			# cr4: instruction authorization
+	.quad	.Lduct			# cr5: primary-aste origin
+	.quad	0			# cr6:	I/O interrupts
+	.quad	0			# cr7:	secondary space segment table
+	.quad	0			# cr8:	access registers translation
+	.quad	0			# cr9:	tracing off
+	.quad	0			# cr10: tracing off
+	.quad	0			# cr11: tracing off
+	.quad	0			# cr12: tracing off
+	.quad	0			# cr13: home space segment table
+	.quad	0xc0000000		# cr14: machine check handling off
+	.quad	.Llinkage_stack		# cr15: linkage stack operations
+.Lpcmsk:.quad	0x0000000180000000
+.L4malign:.quad 0xffffffffffc00000
+.Lscan2g:.quad	0x80000000 + 0x20000 - 8	# 2GB + 128K - 8
+.Lnop:	.long	0x07000700
+.Lparmaddr:
+	.quad	PARMAREA
+	.align	64
+.Lduct: .long	0,.Laste,.Laste,0,.Lduald,0,0,0
+	.long	0,0,0,0,0,0,0,0
+.Laste:	.quad	0,0xffffffffffffffff,0,0,0,0,0,0
+	.align	128
+.Lduald:.rept	8
+	.long	0x80000000,0,0,0	# invalid access-list entries
+	.endr
+.Llinkage_stack:
+	.long	0,0,0x89000000,0,0,0,0x8a000000,0
+
+ENTRY(_ehead)
+
+	.org	0x100000 - 0x11000	# head.o ends at 0x11000
+#
+# startup-code, running in absolute addressing mode
+#
+ENTRY(_stext)
+	basr	%r13,0			# get base
+.LPG3:
+# check control registers
+	stctg	%c0,%c15,0(%r15)
+	oi	6(%r15),0x60		# enable sigp emergency & external call
+	oi	4(%r15),0x10		# switch on low address proctection
+	lctlg	%c0,%c15,0(%r15)
+
+	lam	0,15,.Laregs-.LPG3(%r13)	# load acrs needed by uaccess
+	brasl	%r14,start_kernel	# go to C code
+#
+# We returned from start_kernel ?!? PANIK
+#
+	basr	%r13,0
+	lpswe	.Ldw-.(%r13)		# load disabled wait psw
+
+	.align	8
+.Ldw:	.quad	0x0002000180000000,0x0000000000000000
+.Laregs:.long	0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0
diff --git a/arch/s390/kernel/head_kdump.S b/arch/s390/kernel/head_kdump.S
new file mode 100644
index 000000000..d05950f02
--- /dev/null
+++ b/arch/s390/kernel/head_kdump.S
@@ -0,0 +1,100 @@
+/*
+ * S390 kdump lowlevel functions (new kernel)
+ *
+ * Copyright IBM Corp. 2011
+ * Author(s): Michael Holzheu <holzheu@linux.vnet.ibm.com>
+ */
+
+#include <asm/sigp.h>
+
+#define DATAMOVER_ADDR	0x4000
+#define COPY_PAGE_ADDR	0x6000
+
+#ifdef CONFIG_CRASH_DUMP
+
+#
+# kdump entry (new kernel - not yet relocated)
+#
+# Note: This code has to be position independent
+#
+
+.align 2
+.Lep_startup_kdump:
+	lhi	%r1,2				# mode 2 = esame (dump)
+	sigp	%r1,%r0,SIGP_SET_ARCHITECTURE	# Switch to esame mode
+	sam64					# Switch to 64 bit addressing
+	basr	%r13,0
+.Lbase:
+	larl	%r2,.Lbase_addr			# Check, if we have been
+	lg	%r2,0(%r2)			# already relocated:
+	clgr	%r2,%r13			#
+	jne	.Lrelocate			# No : Start data mover
+	lghi	%r2,0				# Yes: Start kdump kernel
+	brasl	%r14,startup_kdump_relocated
+
+.Lrelocate:
+	larl	%r4,startup
+	lg	%r2,0x418(%r4)			# Get kdump base
+	lg	%r3,0x420(%r4)			# Get kdump size
+
+	larl	%r10,.Lcopy_start		# Source of data mover
+	lghi	%r8,DATAMOVER_ADDR		# Target of data mover
+	mvc	0(256,%r8),0(%r10)		# Copy data mover code
+
+	agr	%r8,%r2				# Copy data mover to
+	mvc	0(256,%r8),0(%r10)		# reserved mem
+
+	lghi	%r14,DATAMOVER_ADDR		# Jump to copied data mover
+	basr	%r14,%r14
+.Lbase_addr:
+	.quad	.Lbase
+
+#
+# kdump data mover code (runs at address DATAMOVER_ADDR)
+#
+# r2: kdump base address
+# r3: kdump size
+#
+.Lcopy_start:
+	basr	%r13,0				# Base
+0:
+	lgr	%r11,%r2			# Save kdump base address
+	lgr	%r12,%r2
+	agr	%r12,%r3			# Compute kdump end address
+
+	lghi	%r5,0
+	lghi	%r10,COPY_PAGE_ADDR		# Load copy page address
+1:
+	mvc	0(256,%r10),0(%r5)		# Copy old kernel to tmp
+	mvc	0(256,%r5),0(%r11)		# Copy new kernel to old
+	mvc	0(256,%r11),0(%r10)		# Copy tmp to new
+	aghi	%r11,256
+	aghi	%r5,256
+	clgr	%r11,%r12
+	jl	1b
+
+	lg	%r14,.Lstartup_kdump-0b(%r13)
+	basr	%r14,%r14			# Start relocated kernel
+.Lstartup_kdump:
+	.long	0x00000000,0x00000000 + startup_kdump_relocated
+.Lcopy_end:
+
+#
+# Startup of kdump (relocated new kernel)
+#
+.align 2
+startup_kdump_relocated:
+	basr	%r13,0
+0:	lpswe	.Lrestart_psw-0b(%r13)		# Start new kernel...
+.align	8
+.Lrestart_psw:
+	.quad	0x0000000080000000,0x0000000000000000 + startup
+#else
+.align 2
+.Lep_startup_kdump:
+	larl	%r13,startup_kdump_crash
+	lpswe	0(%r13)
+.align 8
+startup_kdump_crash:
+	.quad	0x0002000080000000,0x0000000000000000 + startup_kdump_crash
+#endif /* CONFIG_CRASH_DUMP */
diff --git a/arch/s390/kernel/idle.c b/arch/s390/kernel/idle.c
new file mode 100644
index 000000000..7a55c29b0
--- /dev/null
+++ b/arch/s390/kernel/idle.c
@@ -0,0 +1,125 @@
+/*
+ * Idle functions for s390.
+ *
+ * Copyright IBM Corp. 2014
+ *
+ * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
+ */
+
+#include <linux/kernel.h>
+#include <linux/kernel_stat.h>
+#include <linux/kprobes.h>
+#include <linux/notifier.h>
+#include <linux/init.h>
+#include <linux/cpu.h>
+#include <asm/cputime.h>
+#include <asm/nmi.h>
+#include <asm/smp.h>
+#include "entry.h"
+
+static DEFINE_PER_CPU(struct s390_idle_data, s390_idle);
+
+void enabled_wait(void)
+{
+	struct s390_idle_data *idle = this_cpu_ptr(&s390_idle);
+	unsigned long long idle_time;
+	unsigned long psw_mask;
+
+	trace_hardirqs_on();
+
+	/* 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;
+	clear_cpu_flag(CIF_NOHZ_DELAY);
+
+	/* Call the assembler magic in entry.S */
+	psw_idle(idle, psw_mask);
+
+	trace_hardirqs_off();
+
+	/* Account time spent with enabled wait psw loaded as idle time. */
+	write_seqcount_begin(&idle->seqcount);
+	idle_time = idle->clock_idle_exit - idle->clock_idle_enter;
+	idle->clock_idle_enter = idle->clock_idle_exit = 0ULL;
+	idle->idle_time += idle_time;
+	idle->idle_count++;
+	account_idle_time(idle_time);
+	write_seqcount_end(&idle->seqcount);
+}
+NOKPROBE_SYMBOL(enabled_wait);
+
+static ssize_t show_idle_count(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	struct s390_idle_data *idle = &per_cpu(s390_idle, dev->id);
+	unsigned long long idle_count;
+	unsigned int seq;
+
+	do {
+		seq = read_seqcount_begin(&idle->seqcount);
+		idle_count = ACCESS_ONCE(idle->idle_count);
+		if (ACCESS_ONCE(idle->clock_idle_enter))
+			idle_count++;
+	} while (read_seqcount_retry(&idle->seqcount, seq));
+	return sprintf(buf, "%llu\n", idle_count);
+}
+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 = &per_cpu(s390_idle, dev->id);
+	unsigned long long now, idle_time, idle_enter, idle_exit;
+	unsigned int seq;
+
+	do {
+		now = get_tod_clock();
+		seq = read_seqcount_begin(&idle->seqcount);
+		idle_time = ACCESS_ONCE(idle->idle_time);
+		idle_enter = ACCESS_ONCE(idle->clock_idle_enter);
+		idle_exit = ACCESS_ONCE(idle->clock_idle_exit);
+	} while (read_seqcount_retry(&idle->seqcount, seq));
+	idle_time += idle_enter ? ((idle_exit ? : now) - idle_enter) : 0;
+	return sprintf(buf, "%llu\n", idle_time >> 12);
+}
+DEVICE_ATTR(idle_time_us, 0444, show_idle_time, NULL);
+
+cputime64_t arch_cpu_idle_time(int cpu)
+{
+	struct s390_idle_data *idle = &per_cpu(s390_idle, cpu);
+	unsigned long long now, idle_enter, idle_exit;
+	unsigned int seq;
+
+	do {
+		now = get_tod_clock();
+		seq = read_seqcount_begin(&idle->seqcount);
+		idle_enter = ACCESS_ONCE(idle->clock_idle_enter);
+		idle_exit = ACCESS_ONCE(idle->clock_idle_exit);
+	} while (read_seqcount_retry(&idle->seqcount, seq));
+	return idle_enter ? ((idle_exit ?: now) - idle_enter) : 0;
+}
+
+void arch_cpu_idle_enter(void)
+{
+	local_mcck_disable();
+}
+
+void arch_cpu_idle(void)
+{
+	if (!test_cpu_flag(CIF_MCCK_PENDING))
+		/* Halt the cpu and keep track of cpu time accounting. */
+		enabled_wait();
+	local_irq_enable();
+}
+
+void arch_cpu_idle_exit(void)
+{
+	local_mcck_enable();
+	if (test_cpu_flag(CIF_MCCK_PENDING))
+		s390_handle_mcck();
+}
+
+void arch_cpu_idle_dead(void)
+{
+	cpu_die();
+}
diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c
new file mode 100644
index 000000000..52fbef91d
--- /dev/null
+++ b/arch/s390/kernel/ipl.c
@@ -0,0 +1,2064 @@
+/*
+ *    ipl/reipl/dump support for Linux on s390.
+ *
+ *    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>
+ */
+
+#include <linux/types.h>
+#include <linux/module.h>
+#include <linux/device.h>
+#include <linux/delay.h>
+#include <linux/reboot.h>
+#include <linux/ctype.h>
+#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>
+#include <asm/cpcmd.h>
+#include <asm/cio.h>
+#include <asm/ebcdic.h>
+#include <asm/reset.h>
+#include <asm/sclp.h>
+#include <asm/checksum.h>
+#include <asm/debug.h>
+#include <asm/os_info.h>
+#include "entry.h"
+
+#define IPL_PARM_BLOCK_VERSION 0
+
+#define IPL_UNKNOWN_STR		"unknown"
+#define IPL_CCW_STR		"ccw"
+#define IPL_FCP_STR		"fcp"
+#define IPL_FCP_DUMP_STR	"fcp_dump"
+#define IPL_NSS_STR		"nss"
+
+#define DUMP_CCW_STR		"ccw"
+#define DUMP_FCP_STR		"fcp"
+#define DUMP_NONE_STR		"none"
+
+/*
+ * Four shutdown trigger types are supported:
+ * - panic
+ * - halt
+ * - power off
+ * - reipl
+ * - restart
+ */
+#define ON_PANIC_STR		"on_panic"
+#define ON_HALT_STR		"on_halt"
+#define ON_POFF_STR		"on_poff"
+#define ON_REIPL_STR		"on_reboot"
+#define ON_RESTART_STR		"on_restart"
+
+struct shutdown_action;
+struct shutdown_trigger {
+	char *name;
+	struct shutdown_action *action;
+};
+
+/*
+ * The following shutdown action types are supported:
+ */
+#define SHUTDOWN_ACTION_IPL_STR		"ipl"
+#define SHUTDOWN_ACTION_REIPL_STR	"reipl"
+#define SHUTDOWN_ACTION_DUMP_STR	"dump"
+#define SHUTDOWN_ACTION_VMCMD_STR	"vmcmd"
+#define SHUTDOWN_ACTION_STOP_STR	"stop"
+#define SHUTDOWN_ACTION_DUMP_REIPL_STR	"dump_reipl"
+
+struct shutdown_action {
+	char *name;
+	void (*fn) (struct shutdown_trigger *trigger);
+	int (*init) (void);
+	int init_rc;
+};
+
+static char *ipl_type_str(enum ipl_type type)
+{
+	switch (type) {
+	case IPL_TYPE_CCW:
+		return IPL_CCW_STR;
+	case IPL_TYPE_FCP:
+		return IPL_FCP_STR;
+	case IPL_TYPE_FCP_DUMP:
+		return IPL_FCP_DUMP_STR;
+	case IPL_TYPE_NSS:
+		return IPL_NSS_STR;
+	case IPL_TYPE_UNKNOWN:
+	default:
+		return IPL_UNKNOWN_STR;
+	}
+}
+
+enum dump_type {
+	DUMP_TYPE_NONE	= 1,
+	DUMP_TYPE_CCW	= 2,
+	DUMP_TYPE_FCP	= 4,
+};
+
+static char *dump_type_str(enum dump_type type)
+{
+	switch (type) {
+	case DUMP_TYPE_NONE:
+		return DUMP_NONE_STR;
+	case DUMP_TYPE_CCW:
+		return DUMP_CCW_STR;
+	case DUMP_TYPE_FCP:
+		return DUMP_FCP_STR;
+	default:
+		return NULL;
+	}
+}
+
+/*
+ * Must be in data section since the bss section
+ * is not cleared when these are accessed.
+ */
+static u16 ipl_devno __attribute__((__section__(".data"))) = 0;
+u32 ipl_flags __attribute__((__section__(".data"))) = 0;
+
+enum ipl_method {
+	REIPL_METHOD_CCW_CIO,
+	REIPL_METHOD_CCW_DIAG,
+	REIPL_METHOD_CCW_VM,
+	REIPL_METHOD_FCP_RO_DIAG,
+	REIPL_METHOD_FCP_RW_DIAG,
+	REIPL_METHOD_FCP_RO_VM,
+	REIPL_METHOD_FCP_DUMP,
+	REIPL_METHOD_NSS,
+	REIPL_METHOD_NSS_DIAG,
+	REIPL_METHOD_DEFAULT,
+};
+
+enum dump_method {
+	DUMP_METHOD_NONE,
+	DUMP_METHOD_CCW_CIO,
+	DUMP_METHOD_CCW_DIAG,
+	DUMP_METHOD_CCW_VM,
+	DUMP_METHOD_FCP_DIAG,
+};
+
+static int diag308_set_works = 0;
+
+static struct ipl_parameter_block ipl_block;
+
+static int reipl_capabilities = IPL_TYPE_UNKNOWN;
+
+static enum ipl_type reipl_type = IPL_TYPE_UNKNOWN;
+static enum ipl_method reipl_method = REIPL_METHOD_DEFAULT;
+static struct ipl_parameter_block *reipl_block_fcp;
+static struct ipl_parameter_block *reipl_block_ccw;
+static struct ipl_parameter_block *reipl_block_nss;
+static struct ipl_parameter_block *reipl_block_actual;
+
+static int dump_capabilities = DUMP_TYPE_NONE;
+static enum dump_type dump_type = DUMP_TYPE_NONE;
+static enum dump_method dump_method = DUMP_METHOD_NONE;
+static struct ipl_parameter_block *dump_block_fcp;
+static struct ipl_parameter_block *dump_block_ccw;
+
+static struct sclp_ipl_info sclp_ipl_info;
+
+int diag308(unsigned long subcode, void *addr)
+{
+	register unsigned long _addr asm("0") = (unsigned long) addr;
+	register unsigned long _rc asm("1") = 0;
+
+	asm volatile(
+		"	diag	%0,%2,0x308\n"
+		"0:\n"
+		EX_TABLE(0b,0b)
+		: "+d" (_addr), "+d" (_rc)
+		: "d" (subcode) : "cc", "memory");
+	return _rc;
+}
+EXPORT_SYMBOL_GPL(diag308);
+
+/* SYSFS */
+
+#define IPL_ATTR_SHOW_FN(_prefix, _name, _format, args...)		\
+static ssize_t sys_##_prefix##_##_name##_show(struct kobject *kobj,	\
+		struct kobj_attribute *attr,				\
+		char *page)						\
+{									\
+	return snprintf(page, PAGE_SIZE, _format, ##args);		\
+}
+
+#define DEFINE_IPL_ATTR_RO(_prefix, _name, _format, _value)		\
+IPL_ATTR_SHOW_FN(_prefix, _name, _format, _value)			\
+static struct kobj_attribute sys_##_prefix##_##_name##_attr =		\
+	__ATTR(_name, S_IRUGO, sys_##_prefix##_##_name##_show, NULL)
+
+#define DEFINE_IPL_ATTR_RW(_prefix, _name, _fmt_out, _fmt_in, _value)	\
+IPL_ATTR_SHOW_FN(_prefix, _name, _fmt_out, (unsigned long long) _value)	\
+static ssize_t sys_##_prefix##_##_name##_store(struct kobject *kobj,	\
+		struct kobj_attribute *attr,				\
+		const char *buf, size_t len)				\
+{									\
+	unsigned long long value;					\
+	if (sscanf(buf, _fmt_in, &value) != 1)				\
+		return -EINVAL;						\
+	_value = value;							\
+	return len;							\
+}									\
+static struct kobj_attribute sys_##_prefix##_##_name##_attr =		\
+	__ATTR(_name,(S_IRUGO | S_IWUSR),				\
+			sys_##_prefix##_##_name##_show,			\
+			sys_##_prefix##_##_name##_store)
+
+#define DEFINE_IPL_ATTR_STR_RW(_prefix, _name, _fmt_out, _fmt_in, _value)\
+IPL_ATTR_SHOW_FN(_prefix, _name, _fmt_out, _value)			\
+static ssize_t sys_##_prefix##_##_name##_store(struct kobject *kobj,	\
+		struct kobj_attribute *attr,				\
+		const char *buf, size_t len)				\
+{									\
+	strncpy(_value, buf, sizeof(_value) - 1);			\
+	strim(_value);							\
+	return len;							\
+}									\
+static struct kobj_attribute sys_##_prefix##_##_name##_attr =		\
+	__ATTR(_name,(S_IRUGO | S_IWUSR),				\
+			sys_##_prefix##_##_name##_show,			\
+			sys_##_prefix##_##_name##_store)
+
+static void make_attrs_ro(struct attribute **attrs)
+{
+	while (*attrs) {
+		(*attrs)->mode = S_IRUGO;
+		attrs++;
+	}
+}
+
+/*
+ * ipl section
+ */
+
+static __init enum ipl_type get_ipl_type(void)
+{
+	struct ipl_parameter_block *ipl = IPL_PARMBLOCK_START;
+
+	if (ipl_flags & IPL_NSS_VALID)
+		return IPL_TYPE_NSS;
+	if (!(ipl_flags & IPL_DEVNO_VALID))
+		return IPL_TYPE_UNKNOWN;
+	if (!(ipl_flags & IPL_PARMBLOCK_VALID))
+		return IPL_TYPE_CCW;
+	if (ipl->hdr.version > IPL_MAX_SUPPORTED_VERSION)
+		return IPL_TYPE_UNKNOWN;
+	if (ipl->hdr.pbt != DIAG308_IPL_TYPE_FCP)
+		return IPL_TYPE_UNKNOWN;
+	if (ipl->ipl_info.fcp.opt == DIAG308_IPL_OPT_DUMP)
+		return IPL_TYPE_FCP_DUMP;
+	return IPL_TYPE_FCP;
+}
+
+struct ipl_info ipl_info;
+EXPORT_SYMBOL_GPL(ipl_info);
+
+static ssize_t ipl_type_show(struct kobject *kobj, struct kobj_attribute *attr,
+			     char *page)
+{
+	return sprintf(page, "%s\n", ipl_type_str(ipl_info.type));
+}
+
+static struct kobj_attribute sys_ipl_type_attr = __ATTR_RO(ipl_type);
+
+/* VM IPL PARM routines */
+static size_t reipl_get_ascii_vmparm(char *dest, size_t size,
+				     const struct ipl_parameter_block *ipb)
+{
+	int i;
+	size_t len;
+	char has_lowercase = 0;
+
+	len = 0;
+	if ((ipb->ipl_info.ccw.vm_flags & DIAG308_VM_FLAGS_VP_VALID) &&
+	    (ipb->ipl_info.ccw.vm_parm_len > 0)) {
+
+		len = min_t(size_t, size - 1, ipb->ipl_info.ccw.vm_parm_len);
+		memcpy(dest, ipb->ipl_info.ccw.vm_parm, len);
+		/* If at least one character is lowercase, we assume mixed
+		 * case; otherwise we convert everything to lowercase.
+		 */
+		for (i = 0; i < len; i++)
+			if ((dest[i] > 0x80 && dest[i] < 0x8a) || /* a-i */
+			    (dest[i] > 0x90 && dest[i] < 0x9a) || /* j-r */
+			    (dest[i] > 0xa1 && dest[i] < 0xaa)) { /* s-z */
+				has_lowercase = 1;
+				break;
+			}
+		if (!has_lowercase)
+			EBC_TOLOWER(dest, len);
+		EBCASC(dest, len);
+	}
+	dest[len] = 0;
+
+	return len;
+}
+
+size_t append_ipl_vmparm(char *dest, size_t size)
+{
+	size_t rc;
+
+	rc = 0;
+	if (diag308_set_works && (ipl_block.hdr.pbt == DIAG308_IPL_TYPE_CCW))
+		rc = reipl_get_ascii_vmparm(dest, size, &ipl_block);
+	else
+		dest[0] = 0;
+	return rc;
+}
+
+static ssize_t ipl_vm_parm_show(struct kobject *kobj,
+				struct kobj_attribute *attr, char *page)
+{
+	char parm[DIAG308_VMPARM_SIZE + 1] = {};
+
+	append_ipl_vmparm(parm, sizeof(parm));
+	return sprintf(page, "%s\n", parm);
+}
+
+static size_t scpdata_length(const char* buf, size_t count)
+{
+	while (count) {
+		if (buf[count - 1] != '\0' && buf[count - 1] != ' ')
+			break;
+		count--;
+	}
+	return count;
+}
+
+static size_t reipl_append_ascii_scpdata(char *dest, size_t size,
+					 const struct ipl_parameter_block *ipb)
+{
+	size_t count;
+	size_t i;
+	int has_lowercase;
+
+	count = min(size - 1, scpdata_length(ipb->ipl_info.fcp.scp_data,
+					     ipb->ipl_info.fcp.scp_data_len));
+	if (!count)
+		goto out;
+
+	has_lowercase = 0;
+	for (i = 0; i < count; i++) {
+		if (!isascii(ipb->ipl_info.fcp.scp_data[i])) {
+			count = 0;
+			goto out;
+		}
+		if (!has_lowercase && islower(ipb->ipl_info.fcp.scp_data[i]))
+			has_lowercase = 1;
+	}
+
+	if (has_lowercase)
+		memcpy(dest, ipb->ipl_info.fcp.scp_data, count);
+	else
+		for (i = 0; i < count; i++)
+			dest[i] = tolower(ipb->ipl_info.fcp.scp_data[i]);
+out:
+	dest[count] = '\0';
+	return count;
+}
+
+size_t append_ipl_scpdata(char *dest, size_t len)
+{
+	size_t rc;
+
+	rc = 0;
+	if (ipl_block.hdr.pbt == DIAG308_IPL_TYPE_FCP)
+		rc = reipl_append_ascii_scpdata(dest, len, &ipl_block);
+	else
+		dest[0] = 0;
+	return rc;
+}
+
+
+static struct kobj_attribute sys_ipl_vm_parm_attr =
+	__ATTR(parm, S_IRUGO, ipl_vm_parm_show, NULL);
+
+static ssize_t sys_ipl_device_show(struct kobject *kobj,
+				   struct kobj_attribute *attr, char *page)
+{
+	struct ipl_parameter_block *ipl = IPL_PARMBLOCK_START;
+
+	switch (ipl_info.type) {
+	case IPL_TYPE_CCW:
+		return sprintf(page, "0.0.%04x\n", ipl_devno);
+	case IPL_TYPE_FCP:
+	case IPL_TYPE_FCP_DUMP:
+		return sprintf(page, "0.0.%04x\n", ipl->ipl_info.fcp.devno);
+	default:
+		return 0;
+	}
+}
+
+static struct kobj_attribute sys_ipl_device_attr =
+	__ATTR(device, S_IRUGO, sys_ipl_device_show, NULL);
+
+static ssize_t ipl_parameter_read(struct file *filp, struct kobject *kobj,
+				  struct bin_attribute *attr, char *buf,
+				  loff_t off, size_t count)
+{
+	return memory_read_from_buffer(buf, count, &off, IPL_PARMBLOCK_START,
+					IPL_PARMBLOCK_SIZE);
+}
+static struct bin_attribute ipl_parameter_attr =
+	__BIN_ATTR(binary_parameter, S_IRUGO, ipl_parameter_read, NULL,
+		   PAGE_SIZE);
+
+static ssize_t ipl_scp_data_read(struct file *filp, struct kobject *kobj,
+				 struct bin_attribute *attr, char *buf,
+				 loff_t off, size_t count)
+{
+	unsigned int size = IPL_PARMBLOCK_START->ipl_info.fcp.scp_data_len;
+	void *scp_data = &IPL_PARMBLOCK_START->ipl_info.fcp.scp_data;
+
+	return memory_read_from_buffer(buf, count, &off, scp_data, size);
+}
+static struct bin_attribute ipl_scp_data_attr =
+	__BIN_ATTR(scp_data, S_IRUGO, ipl_scp_data_read, NULL, PAGE_SIZE);
+
+static struct bin_attribute *ipl_fcp_bin_attrs[] = {
+	&ipl_parameter_attr,
+	&ipl_scp_data_attr,
+	NULL,
+};
+
+/* FCP ipl device attributes */
+
+DEFINE_IPL_ATTR_RO(ipl_fcp, wwpn, "0x%016llx\n", (unsigned long long)
+		   IPL_PARMBLOCK_START->ipl_info.fcp.wwpn);
+DEFINE_IPL_ATTR_RO(ipl_fcp, lun, "0x%016llx\n", (unsigned long long)
+		   IPL_PARMBLOCK_START->ipl_info.fcp.lun);
+DEFINE_IPL_ATTR_RO(ipl_fcp, bootprog, "%lld\n", (unsigned long long)
+		   IPL_PARMBLOCK_START->ipl_info.fcp.bootprog);
+DEFINE_IPL_ATTR_RO(ipl_fcp, br_lba, "%lld\n", (unsigned long long)
+		   IPL_PARMBLOCK_START->ipl_info.fcp.br_lba);
+
+static ssize_t ipl_ccw_loadparm_show(struct kobject *kobj,
+				     struct kobj_attribute *attr, char *page)
+{
+	char loadparm[LOADPARM_LEN + 1] = {};
+
+	if (!sclp_ipl_info.is_valid)
+		return sprintf(page, "#unknown#\n");
+	memcpy(loadparm, &sclp_ipl_info.loadparm, LOADPARM_LEN);
+	EBCASC(loadparm, LOADPARM_LEN);
+	strim(loadparm);
+	return sprintf(page, "%s\n", loadparm);
+}
+
+static struct kobj_attribute sys_ipl_ccw_loadparm_attr =
+	__ATTR(loadparm, 0444, ipl_ccw_loadparm_show, NULL);
+
+static struct attribute *ipl_fcp_attrs[] = {
+	&sys_ipl_type_attr.attr,
+	&sys_ipl_device_attr.attr,
+	&sys_ipl_fcp_wwpn_attr.attr,
+	&sys_ipl_fcp_lun_attr.attr,
+	&sys_ipl_fcp_bootprog_attr.attr,
+	&sys_ipl_fcp_br_lba_attr.attr,
+	&sys_ipl_ccw_loadparm_attr.attr,
+	NULL,
+};
+
+static struct attribute_group ipl_fcp_attr_group = {
+	.attrs = ipl_fcp_attrs,
+	.bin_attrs = ipl_fcp_bin_attrs,
+};
+
+/* CCW ipl device attributes */
+
+static struct attribute *ipl_ccw_attrs_vm[] = {
+	&sys_ipl_type_attr.attr,
+	&sys_ipl_device_attr.attr,
+	&sys_ipl_ccw_loadparm_attr.attr,
+	&sys_ipl_vm_parm_attr.attr,
+	NULL,
+};
+
+static struct attribute *ipl_ccw_attrs_lpar[] = {
+	&sys_ipl_type_attr.attr,
+	&sys_ipl_device_attr.attr,
+	&sys_ipl_ccw_loadparm_attr.attr,
+	NULL,
+};
+
+static struct attribute_group ipl_ccw_attr_group_vm = {
+	.attrs = ipl_ccw_attrs_vm,
+};
+
+static struct attribute_group ipl_ccw_attr_group_lpar = {
+	.attrs = ipl_ccw_attrs_lpar
+};
+
+/* NSS ipl device attributes */
+
+DEFINE_IPL_ATTR_RO(ipl_nss, name, "%s\n", kernel_nss_name);
+
+static struct attribute *ipl_nss_attrs[] = {
+	&sys_ipl_type_attr.attr,
+	&sys_ipl_nss_name_attr.attr,
+	&sys_ipl_ccw_loadparm_attr.attr,
+	&sys_ipl_vm_parm_attr.attr,
+	NULL,
+};
+
+static struct attribute_group ipl_nss_attr_group = {
+	.attrs = ipl_nss_attrs,
+};
+
+/* UNKNOWN ipl device attributes */
+
+static struct attribute *ipl_unknown_attrs[] = {
+	&sys_ipl_type_attr.attr,
+	NULL,
+};
+
+static struct attribute_group ipl_unknown_attr_group = {
+	.attrs = ipl_unknown_attrs,
+};
+
+static struct kset *ipl_kset;
+
+static void __ipl_run(void *unused)
+{
+	diag308(DIAG308_IPL, NULL);
+	if (MACHINE_IS_VM)
+		__cpcmd("IPL", NULL, 0, NULL);
+	else if (ipl_info.type == IPL_TYPE_CCW)
+		reipl_ccw_dev(&ipl_info.data.ccw.dev_id);
+}
+
+static void ipl_run(struct shutdown_trigger *trigger)
+{
+	smp_call_ipl_cpu(__ipl_run, NULL);
+}
+
+static int __init ipl_init(void)
+{
+	int rc;
+
+	ipl_kset = kset_create_and_add("ipl", NULL, firmware_kobj);
+	if (!ipl_kset) {
+		rc = -ENOMEM;
+		goto out;
+	}
+	switch (ipl_info.type) {
+	case IPL_TYPE_CCW:
+		if (MACHINE_IS_VM)
+			rc = sysfs_create_group(&ipl_kset->kobj,
+						&ipl_ccw_attr_group_vm);
+		else
+			rc = sysfs_create_group(&ipl_kset->kobj,
+						&ipl_ccw_attr_group_lpar);
+		break;
+	case IPL_TYPE_FCP:
+	case IPL_TYPE_FCP_DUMP:
+		rc = sysfs_create_group(&ipl_kset->kobj, &ipl_fcp_attr_group);
+		break;
+	case IPL_TYPE_NSS:
+		rc = sysfs_create_group(&ipl_kset->kobj, &ipl_nss_attr_group);
+		break;
+	default:
+		rc = sysfs_create_group(&ipl_kset->kobj,
+					&ipl_unknown_attr_group);
+		break;
+	}
+out:
+	if (rc)
+		panic("ipl_init failed: rc = %i\n", rc);
+
+	return 0;
+}
+
+static struct shutdown_action __refdata ipl_action = {
+	.name	= SHUTDOWN_ACTION_IPL_STR,
+	.fn	= ipl_run,
+	.init	= ipl_init,
+};
+
+/*
+ * reipl shutdown action: Reboot Linux on shutdown.
+ */
+
+/* VM IPL PARM attributes */
+static ssize_t reipl_generic_vmparm_show(struct ipl_parameter_block *ipb,
+					  char *page)
+{
+	char vmparm[DIAG308_VMPARM_SIZE + 1] = {};
+
+	reipl_get_ascii_vmparm(vmparm, sizeof(vmparm), ipb);
+	return sprintf(page, "%s\n", vmparm);
+}
+
+static ssize_t reipl_generic_vmparm_store(struct ipl_parameter_block *ipb,
+					  size_t vmparm_max,
+					  const char *buf, size_t len)
+{
+	int i, ip_len;
+
+	/* ignore trailing newline */
+	ip_len = len;
+	if ((len > 0) && (buf[len - 1] == '\n'))
+		ip_len--;
+
+	if (ip_len > vmparm_max)
+		return -EINVAL;
+
+	/* parm is used to store kernel options, check for common chars */
+	for (i = 0; i < ip_len; i++)
+		if (!(isalnum(buf[i]) || isascii(buf[i]) || isprint(buf[i])))
+			return -EINVAL;
+
+	memset(ipb->ipl_info.ccw.vm_parm, 0, DIAG308_VMPARM_SIZE);
+	ipb->ipl_info.ccw.vm_parm_len = ip_len;
+	if (ip_len > 0) {
+		ipb->ipl_info.ccw.vm_flags |= DIAG308_VM_FLAGS_VP_VALID;
+		memcpy(ipb->ipl_info.ccw.vm_parm, buf, ip_len);
+		ASCEBC(ipb->ipl_info.ccw.vm_parm, ip_len);
+	} else {
+		ipb->ipl_info.ccw.vm_flags &= ~DIAG308_VM_FLAGS_VP_VALID;
+	}
+
+	return len;
+}
+
+/* NSS wrapper */
+static ssize_t reipl_nss_vmparm_show(struct kobject *kobj,
+				     struct kobj_attribute *attr, char *page)
+{
+	return reipl_generic_vmparm_show(reipl_block_nss, page);
+}
+
+static ssize_t reipl_nss_vmparm_store(struct kobject *kobj,
+				      struct kobj_attribute *attr,
+				      const char *buf, size_t len)
+{
+	return reipl_generic_vmparm_store(reipl_block_nss, 56, buf, len);
+}
+
+/* CCW wrapper */
+static ssize_t reipl_ccw_vmparm_show(struct kobject *kobj,
+				     struct kobj_attribute *attr, char *page)
+{
+	return reipl_generic_vmparm_show(reipl_block_ccw, page);
+}
+
+static ssize_t reipl_ccw_vmparm_store(struct kobject *kobj,
+				      struct kobj_attribute *attr,
+				      const char *buf, size_t len)
+{
+	return reipl_generic_vmparm_store(reipl_block_ccw, 64, buf, len);
+}
+
+static struct kobj_attribute sys_reipl_nss_vmparm_attr =
+	__ATTR(parm, S_IRUGO | S_IWUSR, reipl_nss_vmparm_show,
+					reipl_nss_vmparm_store);
+static struct kobj_attribute sys_reipl_ccw_vmparm_attr =
+	__ATTR(parm, S_IRUGO | S_IWUSR, reipl_ccw_vmparm_show,
+					reipl_ccw_vmparm_store);
+
+/* FCP reipl device attributes */
+
+static ssize_t reipl_fcp_scpdata_read(struct file *filp, struct kobject *kobj,
+				      struct bin_attribute *attr,
+				      char *buf, loff_t off, size_t count)
+{
+	size_t size = reipl_block_fcp->ipl_info.fcp.scp_data_len;
+	void *scp_data = reipl_block_fcp->ipl_info.fcp.scp_data;
+
+	return memory_read_from_buffer(buf, count, &off, scp_data, size);
+}
+
+static ssize_t reipl_fcp_scpdata_write(struct file *filp, struct kobject *kobj,
+				       struct bin_attribute *attr,
+				       char *buf, loff_t off, size_t count)
+{
+	size_t padding;
+	size_t scpdata_len;
+
+	if (off < 0)
+		return -EINVAL;
+
+	if (off >= DIAG308_SCPDATA_SIZE)
+		return -ENOSPC;
+
+	if (count > DIAG308_SCPDATA_SIZE - off)
+		count = DIAG308_SCPDATA_SIZE - off;
+
+	memcpy(reipl_block_fcp->ipl_info.fcp.scp_data, buf + off, count);
+	scpdata_len = off + count;
+
+	if (scpdata_len % 8) {
+		padding = 8 - (scpdata_len % 8);
+		memset(reipl_block_fcp->ipl_info.fcp.scp_data + scpdata_len,
+		       0, padding);
+		scpdata_len += padding;
+	}
+
+	reipl_block_fcp->ipl_info.fcp.scp_data_len = scpdata_len;
+	reipl_block_fcp->hdr.len = IPL_PARM_BLK_FCP_LEN + scpdata_len;
+	reipl_block_fcp->hdr.blk0_len = IPL_PARM_BLK0_FCP_LEN + scpdata_len;
+
+	return count;
+}
+static struct bin_attribute sys_reipl_fcp_scp_data_attr =
+	__BIN_ATTR(scp_data, (S_IRUGO | S_IWUSR), reipl_fcp_scpdata_read,
+		   reipl_fcp_scpdata_write, PAGE_SIZE);
+
+static struct bin_attribute *reipl_fcp_bin_attrs[] = {
+	&sys_reipl_fcp_scp_data_attr,
+	NULL,
+};
+
+DEFINE_IPL_ATTR_RW(reipl_fcp, wwpn, "0x%016llx\n", "%llx\n",
+		   reipl_block_fcp->ipl_info.fcp.wwpn);
+DEFINE_IPL_ATTR_RW(reipl_fcp, lun, "0x%016llx\n", "%llx\n",
+		   reipl_block_fcp->ipl_info.fcp.lun);
+DEFINE_IPL_ATTR_RW(reipl_fcp, bootprog, "%lld\n", "%lld\n",
+		   reipl_block_fcp->ipl_info.fcp.bootprog);
+DEFINE_IPL_ATTR_RW(reipl_fcp, br_lba, "%lld\n", "%lld\n",
+		   reipl_block_fcp->ipl_info.fcp.br_lba);
+DEFINE_IPL_ATTR_RW(reipl_fcp, device, "0.0.%04llx\n", "0.0.%llx\n",
+		   reipl_block_fcp->ipl_info.fcp.devno);
+
+static void reipl_get_ascii_loadparm(char *loadparm,
+				     struct ipl_parameter_block *ibp)
+{
+	memcpy(loadparm, ibp->hdr.loadparm, LOADPARM_LEN);
+	EBCASC(loadparm, LOADPARM_LEN);
+	loadparm[LOADPARM_LEN] = 0;
+	strim(loadparm);
+}
+
+static ssize_t reipl_generic_loadparm_show(struct ipl_parameter_block *ipb,
+					   char *page)
+{
+	char buf[LOADPARM_LEN + 1];
+
+	reipl_get_ascii_loadparm(buf, ipb);
+	return sprintf(page, "%s\n", buf);
+}
+
+static ssize_t reipl_generic_loadparm_store(struct ipl_parameter_block *ipb,
+					    const char *buf, size_t len)
+{
+	int i, lp_len;
+
+	/* ignore trailing newline */
+	lp_len = len;
+	if ((len > 0) && (buf[len - 1] == '\n'))
+		lp_len--;
+	/* loadparm can have max 8 characters and must not start with a blank */
+	if ((lp_len > LOADPARM_LEN) || ((lp_len > 0) && (buf[0] == ' ')))
+		return -EINVAL;
+	/* loadparm can only contain "a-z,A-Z,0-9,SP,." */
+	for (i = 0; i < lp_len; i++) {
+		if (isalpha(buf[i]) || isdigit(buf[i]) || (buf[i] == ' ') ||
+		    (buf[i] == '.'))
+			continue;
+		return -EINVAL;
+	}
+	/* initialize loadparm with blanks */
+	memset(ipb->hdr.loadparm, ' ', LOADPARM_LEN);
+	/* copy and convert to ebcdic */
+	memcpy(ipb->hdr.loadparm, buf, lp_len);
+	ASCEBC(ipb->hdr.loadparm, LOADPARM_LEN);
+	return len;
+}
+
+/* FCP wrapper */
+static ssize_t reipl_fcp_loadparm_show(struct kobject *kobj,
+				       struct kobj_attribute *attr, char *page)
+{
+	return reipl_generic_loadparm_show(reipl_block_fcp, page);
+}
+
+static ssize_t reipl_fcp_loadparm_store(struct kobject *kobj,
+					struct kobj_attribute *attr,
+					const char *buf, size_t len)
+{
+	return reipl_generic_loadparm_store(reipl_block_fcp, buf, len);
+}
+
+static struct kobj_attribute sys_reipl_fcp_loadparm_attr =
+	__ATTR(loadparm, S_IRUGO | S_IWUSR, reipl_fcp_loadparm_show,
+					    reipl_fcp_loadparm_store);
+
+static struct attribute *reipl_fcp_attrs[] = {
+	&sys_reipl_fcp_device_attr.attr,
+	&sys_reipl_fcp_wwpn_attr.attr,
+	&sys_reipl_fcp_lun_attr.attr,
+	&sys_reipl_fcp_bootprog_attr.attr,
+	&sys_reipl_fcp_br_lba_attr.attr,
+	&sys_reipl_fcp_loadparm_attr.attr,
+	NULL,
+};
+
+static struct attribute_group reipl_fcp_attr_group = {
+	.attrs = reipl_fcp_attrs,
+	.bin_attrs = reipl_fcp_bin_attrs,
+};
+
+/* CCW reipl device attributes */
+
+DEFINE_IPL_ATTR_RW(reipl_ccw, device, "0.0.%04llx\n", "0.0.%llx\n",
+	reipl_block_ccw->ipl_info.ccw.devno);
+
+/* NSS wrapper */
+static ssize_t reipl_nss_loadparm_show(struct kobject *kobj,
+				       struct kobj_attribute *attr, char *page)
+{
+	return reipl_generic_loadparm_show(reipl_block_nss, page);
+}
+
+static ssize_t reipl_nss_loadparm_store(struct kobject *kobj,
+					struct kobj_attribute *attr,
+					const char *buf, size_t len)
+{
+	return reipl_generic_loadparm_store(reipl_block_nss, buf, len);
+}
+
+/* CCW wrapper */
+static ssize_t reipl_ccw_loadparm_show(struct kobject *kobj,
+				       struct kobj_attribute *attr, char *page)
+{
+	return reipl_generic_loadparm_show(reipl_block_ccw, page);
+}
+
+static ssize_t reipl_ccw_loadparm_store(struct kobject *kobj,
+					struct kobj_attribute *attr,
+					const char *buf, size_t len)
+{
+	return reipl_generic_loadparm_store(reipl_block_ccw, buf, len);
+}
+
+static struct kobj_attribute sys_reipl_ccw_loadparm_attr =
+	__ATTR(loadparm, S_IRUGO | S_IWUSR, reipl_ccw_loadparm_show,
+					    reipl_ccw_loadparm_store);
+
+static struct attribute *reipl_ccw_attrs_vm[] = {
+	&sys_reipl_ccw_device_attr.attr,
+	&sys_reipl_ccw_loadparm_attr.attr,
+	&sys_reipl_ccw_vmparm_attr.attr,
+	NULL,
+};
+
+static struct attribute *reipl_ccw_attrs_lpar[] = {
+	&sys_reipl_ccw_device_attr.attr,
+	&sys_reipl_ccw_loadparm_attr.attr,
+	NULL,
+};
+
+static struct attribute_group reipl_ccw_attr_group_vm = {
+	.name  = IPL_CCW_STR,
+	.attrs = reipl_ccw_attrs_vm,
+};
+
+static struct attribute_group reipl_ccw_attr_group_lpar = {
+	.name  = IPL_CCW_STR,
+	.attrs = reipl_ccw_attrs_lpar,
+};
+
+
+/* NSS reipl device attributes */
+static void reipl_get_ascii_nss_name(char *dst,
+				     struct ipl_parameter_block *ipb)
+{
+	memcpy(dst, ipb->ipl_info.ccw.nss_name, NSS_NAME_SIZE);
+	EBCASC(dst, NSS_NAME_SIZE);
+	dst[NSS_NAME_SIZE] = 0;
+}
+
+static ssize_t reipl_nss_name_show(struct kobject *kobj,
+				   struct kobj_attribute *attr, char *page)
+{
+	char nss_name[NSS_NAME_SIZE + 1] = {};
+
+	reipl_get_ascii_nss_name(nss_name, reipl_block_nss);
+	return sprintf(page, "%s\n", nss_name);
+}
+
+static ssize_t reipl_nss_name_store(struct kobject *kobj,
+				    struct kobj_attribute *attr,
+				    const char *buf, size_t len)
+{
+	int nss_len;
+
+	/* ignore trailing newline */
+	nss_len = len;
+	if ((len > 0) && (buf[len - 1] == '\n'))
+		nss_len--;
+
+	if (nss_len > NSS_NAME_SIZE)
+		return -EINVAL;
+
+	memset(reipl_block_nss->ipl_info.ccw.nss_name, 0x40, NSS_NAME_SIZE);
+	if (nss_len > 0) {
+		reipl_block_nss->ipl_info.ccw.vm_flags |=
+			DIAG308_VM_FLAGS_NSS_VALID;
+		memcpy(reipl_block_nss->ipl_info.ccw.nss_name, buf, nss_len);
+		ASCEBC(reipl_block_nss->ipl_info.ccw.nss_name, nss_len);
+		EBC_TOUPPER(reipl_block_nss->ipl_info.ccw.nss_name, nss_len);
+	} else {
+		reipl_block_nss->ipl_info.ccw.vm_flags &=
+			~DIAG308_VM_FLAGS_NSS_VALID;
+	}
+
+	return len;
+}
+
+static struct kobj_attribute sys_reipl_nss_name_attr =
+	__ATTR(name, S_IRUGO | S_IWUSR, reipl_nss_name_show,
+					reipl_nss_name_store);
+
+static struct kobj_attribute sys_reipl_nss_loadparm_attr =
+	__ATTR(loadparm, S_IRUGO | S_IWUSR, reipl_nss_loadparm_show,
+					    reipl_nss_loadparm_store);
+
+static struct attribute *reipl_nss_attrs[] = {
+	&sys_reipl_nss_name_attr.attr,
+	&sys_reipl_nss_loadparm_attr.attr,
+	&sys_reipl_nss_vmparm_attr.attr,
+	NULL,
+};
+
+static struct attribute_group reipl_nss_attr_group = {
+	.name  = IPL_NSS_STR,
+	.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)
+{
+	if (!(reipl_capabilities & type))
+		return -EINVAL;
+
+	switch(type) {
+	case IPL_TYPE_CCW:
+		if (diag308_set_works)
+			reipl_method = REIPL_METHOD_CCW_DIAG;
+		else if (MACHINE_IS_VM)
+			reipl_method = REIPL_METHOD_CCW_VM;
+		else
+			reipl_method = REIPL_METHOD_CCW_CIO;
+		set_reipl_block_actual(reipl_block_ccw);
+		break;
+	case IPL_TYPE_FCP:
+		if (diag308_set_works)
+			reipl_method = REIPL_METHOD_FCP_RW_DIAG;
+		else if (MACHINE_IS_VM)
+			reipl_method = REIPL_METHOD_FCP_RO_VM;
+		else
+			reipl_method = REIPL_METHOD_FCP_RO_DIAG;
+		set_reipl_block_actual(reipl_block_fcp);
+		break;
+	case IPL_TYPE_FCP_DUMP:
+		reipl_method = REIPL_METHOD_FCP_DUMP;
+		break;
+	case IPL_TYPE_NSS:
+		if (diag308_set_works)
+			reipl_method = REIPL_METHOD_NSS_DIAG;
+		else
+			reipl_method = REIPL_METHOD_NSS;
+		set_reipl_block_actual(reipl_block_nss);
+		break;
+	case IPL_TYPE_UNKNOWN:
+		reipl_method = REIPL_METHOD_DEFAULT;
+		break;
+	default:
+		BUG();
+	}
+	reipl_type = type;
+	return 0;
+}
+
+static ssize_t reipl_type_show(struct kobject *kobj,
+			       struct kobj_attribute *attr, char *page)
+{
+	return sprintf(page, "%s\n", ipl_type_str(reipl_type));
+}
+
+static ssize_t reipl_type_store(struct kobject *kobj,
+				struct kobj_attribute *attr,
+				const char *buf, size_t len)
+{
+	int rc = -EINVAL;
+
+	if (strncmp(buf, IPL_CCW_STR, strlen(IPL_CCW_STR)) == 0)
+		rc = reipl_set_type(IPL_TYPE_CCW);
+	else if (strncmp(buf, IPL_FCP_STR, strlen(IPL_FCP_STR)) == 0)
+		rc = reipl_set_type(IPL_TYPE_FCP);
+	else if (strncmp(buf, IPL_NSS_STR, strlen(IPL_NSS_STR)) == 0)
+		rc = reipl_set_type(IPL_TYPE_NSS);
+	return (rc != 0) ? rc : len;
+}
+
+static struct kobj_attribute reipl_type_attr =
+	__ATTR(reipl_type, 0644, reipl_type_show, reipl_type_store);
+
+static struct kset *reipl_kset;
+static struct kset *reipl_fcp_kset;
+
+static void get_ipl_string(char *dst, struct ipl_parameter_block *ipb,
+			   const enum ipl_method m)
+{
+	char loadparm[LOADPARM_LEN + 1] = {};
+	char vmparm[DIAG308_VMPARM_SIZE + 1] = {};
+	char nss_name[NSS_NAME_SIZE + 1] = {};
+	size_t pos = 0;
+
+	reipl_get_ascii_loadparm(loadparm, ipb);
+	reipl_get_ascii_nss_name(nss_name, ipb);
+	reipl_get_ascii_vmparm(vmparm, sizeof(vmparm), ipb);
+
+	switch (m) {
+	case REIPL_METHOD_CCW_VM:
+		pos = sprintf(dst, "IPL %X CLEAR", ipb->ipl_info.ccw.devno);
+		break;
+	case REIPL_METHOD_NSS:
+		pos = sprintf(dst, "IPL %s", nss_name);
+		break;
+	default:
+		break;
+	}
+	if (strlen(loadparm) > 0)
+		pos += sprintf(dst + pos, " LOADPARM '%s'", loadparm);
+	if (strlen(vmparm) > 0)
+		sprintf(dst + pos, " PARM %s", vmparm);
+}
+
+static void __reipl_run(void *unused)
+{
+	struct ccw_dev_id devid;
+	static char buf[128];
+
+	switch (reipl_method) {
+	case REIPL_METHOD_CCW_CIO:
+		devid.devno = reipl_block_ccw->ipl_info.ccw.devno;
+		devid.ssid  = 0;
+		reipl_ccw_dev(&devid);
+		break;
+	case REIPL_METHOD_CCW_VM:
+		get_ipl_string(buf, reipl_block_ccw, REIPL_METHOD_CCW_VM);
+		__cpcmd(buf, NULL, 0, NULL);
+		break;
+	case REIPL_METHOD_CCW_DIAG:
+		diag308(DIAG308_SET, reipl_block_ccw);
+		diag308(DIAG308_IPL, NULL);
+		break;
+	case REIPL_METHOD_FCP_RW_DIAG:
+		diag308(DIAG308_SET, reipl_block_fcp);
+		diag308(DIAG308_IPL, NULL);
+		break;
+	case REIPL_METHOD_FCP_RO_DIAG:
+		diag308(DIAG308_IPL, NULL);
+		break;
+	case REIPL_METHOD_FCP_RO_VM:
+		__cpcmd("IPL", NULL, 0, NULL);
+		break;
+	case REIPL_METHOD_NSS_DIAG:
+		diag308(DIAG308_SET, reipl_block_nss);
+		diag308(DIAG308_IPL, NULL);
+		break;
+	case REIPL_METHOD_NSS:
+		get_ipl_string(buf, reipl_block_nss, REIPL_METHOD_NSS);
+		__cpcmd(buf, NULL, 0, NULL);
+		break;
+	case REIPL_METHOD_DEFAULT:
+		if (MACHINE_IS_VM)
+			__cpcmd("IPL", NULL, 0, NULL);
+		diag308(DIAG308_IPL, NULL);
+		break;
+	case REIPL_METHOD_FCP_DUMP:
+		break;
+	}
+	disabled_wait((unsigned long) __builtin_return_address(0));
+}
+
+static void reipl_run(struct shutdown_trigger *trigger)
+{
+	smp_call_ipl_cpu(__reipl_run, NULL);
+}
+
+static void reipl_block_ccw_init(struct ipl_parameter_block *ipb)
+{
+	ipb->hdr.len = IPL_PARM_BLK_CCW_LEN;
+	ipb->hdr.version = IPL_PARM_BLOCK_VERSION;
+	ipb->hdr.blk0_len = IPL_PARM_BLK0_CCW_LEN;
+	ipb->hdr.pbt = DIAG308_IPL_TYPE_CCW;
+}
+
+static void reipl_block_ccw_fill_parms(struct ipl_parameter_block *ipb)
+{
+	/* LOADPARM */
+	/* check if read scp info worked and set loadparm */
+	if (sclp_ipl_info.is_valid)
+		memcpy(ipb->hdr.loadparm, &sclp_ipl_info.loadparm, LOADPARM_LEN);
+	else
+		/* read scp info failed: set empty loadparm (EBCDIC blanks) */
+		memset(ipb->hdr.loadparm, 0x40, LOADPARM_LEN);
+	ipb->hdr.flags = DIAG308_FLAGS_LP_VALID;
+
+	/* VM PARM */
+	if (MACHINE_IS_VM && diag308_set_works &&
+	    (ipl_block.ipl_info.ccw.vm_flags & DIAG308_VM_FLAGS_VP_VALID)) {
+
+		ipb->ipl_info.ccw.vm_flags |= DIAG308_VM_FLAGS_VP_VALID;
+		ipb->ipl_info.ccw.vm_parm_len =
+					ipl_block.ipl_info.ccw.vm_parm_len;
+		memcpy(ipb->ipl_info.ccw.vm_parm,
+		       ipl_block.ipl_info.ccw.vm_parm, DIAG308_VMPARM_SIZE);
+	}
+}
+
+static int __init reipl_nss_init(void)
+{
+	int rc;
+
+	if (!MACHINE_IS_VM)
+		return 0;
+
+	reipl_block_nss = (void *) get_zeroed_page(GFP_KERNEL);
+	if (!reipl_block_nss)
+		return -ENOMEM;
+
+	if (!diag308_set_works)
+		sys_reipl_nss_vmparm_attr.attr.mode = S_IRUGO;
+
+	rc = sysfs_create_group(&reipl_kset->kobj, &reipl_nss_attr_group);
+	if (rc)
+		return rc;
+
+	reipl_block_ccw_init(reipl_block_nss);
+	if (ipl_info.type == IPL_TYPE_NSS) {
+		memset(reipl_block_nss->ipl_info.ccw.nss_name,
+			' ', NSS_NAME_SIZE);
+		memcpy(reipl_block_nss->ipl_info.ccw.nss_name,
+			kernel_nss_name, strlen(kernel_nss_name));
+		ASCEBC(reipl_block_nss->ipl_info.ccw.nss_name, NSS_NAME_SIZE);
+		reipl_block_nss->ipl_info.ccw.vm_flags |=
+			DIAG308_VM_FLAGS_NSS_VALID;
+
+		reipl_block_ccw_fill_parms(reipl_block_nss);
+	}
+
+	reipl_capabilities |= IPL_TYPE_NSS;
+	return 0;
+}
+
+static int __init reipl_ccw_init(void)
+{
+	int rc;
+
+	reipl_block_ccw = (void *) get_zeroed_page(GFP_KERNEL);
+	if (!reipl_block_ccw)
+		return -ENOMEM;
+
+	if (MACHINE_IS_VM) {
+		if (!diag308_set_works)
+			sys_reipl_ccw_vmparm_attr.attr.mode = S_IRUGO;
+		rc = sysfs_create_group(&reipl_kset->kobj,
+					&reipl_ccw_attr_group_vm);
+	} else {
+		if(!diag308_set_works)
+			sys_reipl_ccw_loadparm_attr.attr.mode = S_IRUGO;
+		rc = sysfs_create_group(&reipl_kset->kobj,
+					&reipl_ccw_attr_group_lpar);
+	}
+	if (rc)
+		return rc;
+
+	reipl_block_ccw_init(reipl_block_ccw);
+	if (ipl_info.type == IPL_TYPE_CCW) {
+		reipl_block_ccw->ipl_info.ccw.devno = ipl_devno;
+		reipl_block_ccw_fill_parms(reipl_block_ccw);
+	}
+
+	reipl_capabilities |= IPL_TYPE_CCW;
+	return 0;
+}
+
+static int __init reipl_fcp_init(void)
+{
+	int rc;
+
+	if (!diag308_set_works) {
+		if (ipl_info.type == IPL_TYPE_FCP) {
+			make_attrs_ro(reipl_fcp_attrs);
+			sys_reipl_fcp_scp_data_attr.attr.mode = S_IRUGO;
+		} else
+			return 0;
+	}
+
+	reipl_block_fcp = (void *) get_zeroed_page(GFP_KERNEL);
+	if (!reipl_block_fcp)
+		return -ENOMEM;
+
+	/* sysfs: create fcp kset for mixing attr group and bin attrs */
+	reipl_fcp_kset = kset_create_and_add(IPL_FCP_STR, NULL,
+					     &reipl_kset->kobj);
+	if (!reipl_fcp_kset) {
+		free_page((unsigned long) reipl_block_fcp);
+		return -ENOMEM;
+	}
+
+	rc = sysfs_create_group(&reipl_fcp_kset->kobj, &reipl_fcp_attr_group);
+	if (rc) {
+		kset_unregister(reipl_fcp_kset);
+		free_page((unsigned long) reipl_block_fcp);
+		return rc;
+	}
+
+	if (ipl_info.type == IPL_TYPE_FCP) {
+		memcpy(reipl_block_fcp, IPL_PARMBLOCK_START, PAGE_SIZE);
+		/*
+		 * Fix loadparm: There are systems where the (SCSI) LOADPARM
+		 * is invalid in the SCSI IPL parameter block, so take it
+		 * always from sclp_ipl_info.
+		 */
+		memcpy(reipl_block_fcp->hdr.loadparm, sclp_ipl_info.loadparm,
+		       LOADPARM_LEN);
+	} else {
+		reipl_block_fcp->hdr.len = IPL_PARM_BLK_FCP_LEN;
+		reipl_block_fcp->hdr.version = IPL_PARM_BLOCK_VERSION;
+		reipl_block_fcp->hdr.blk0_len = IPL_PARM_BLK0_FCP_LEN;
+		reipl_block_fcp->hdr.pbt = DIAG308_IPL_TYPE_FCP;
+		reipl_block_fcp->ipl_info.fcp.opt = DIAG308_IPL_OPT_IPL;
+	}
+	reipl_capabilities |= IPL_TYPE_FCP;
+	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;
+
+	reipl_kset = kset_create_and_add("reipl", NULL, firmware_kobj);
+	if (!reipl_kset)
+		return -ENOMEM;
+	rc = sysfs_create_file(&reipl_kset->kobj, &reipl_type_attr.attr);
+	if (rc) {
+		kset_unregister(reipl_kset);
+		return rc;
+	}
+	rc = reipl_ccw_init();
+	if (rc)
+		return rc;
+	rc = reipl_fcp_init();
+	if (rc)
+		return rc;
+	rc = reipl_nss_init();
+	if (rc)
+		return rc;
+	return reipl_type_init();
+}
+
+static struct shutdown_action __refdata reipl_action = {
+	.name	= SHUTDOWN_ACTION_REIPL_STR,
+	.fn	= reipl_run,
+	.init	= reipl_init,
+};
+
+/*
+ * dump shutdown action: Dump Linux on shutdown.
+ */
+
+/* FCP dump device attributes */
+
+DEFINE_IPL_ATTR_RW(dump_fcp, wwpn, "0x%016llx\n", "%llx\n",
+		   dump_block_fcp->ipl_info.fcp.wwpn);
+DEFINE_IPL_ATTR_RW(dump_fcp, lun, "0x%016llx\n", "%llx\n",
+		   dump_block_fcp->ipl_info.fcp.lun);
+DEFINE_IPL_ATTR_RW(dump_fcp, bootprog, "%lld\n", "%lld\n",
+		   dump_block_fcp->ipl_info.fcp.bootprog);
+DEFINE_IPL_ATTR_RW(dump_fcp, br_lba, "%lld\n", "%lld\n",
+		   dump_block_fcp->ipl_info.fcp.br_lba);
+DEFINE_IPL_ATTR_RW(dump_fcp, device, "0.0.%04llx\n", "0.0.%llx\n",
+		   dump_block_fcp->ipl_info.fcp.devno);
+
+static struct attribute *dump_fcp_attrs[] = {
+	&sys_dump_fcp_device_attr.attr,
+	&sys_dump_fcp_wwpn_attr.attr,
+	&sys_dump_fcp_lun_attr.attr,
+	&sys_dump_fcp_bootprog_attr.attr,
+	&sys_dump_fcp_br_lba_attr.attr,
+	NULL,
+};
+
+static struct attribute_group dump_fcp_attr_group = {
+	.name  = IPL_FCP_STR,
+	.attrs = dump_fcp_attrs,
+};
+
+/* CCW dump device attributes */
+
+DEFINE_IPL_ATTR_RW(dump_ccw, device, "0.0.%04llx\n", "0.0.%llx\n",
+		   dump_block_ccw->ipl_info.ccw.devno);
+
+static struct attribute *dump_ccw_attrs[] = {
+	&sys_dump_ccw_device_attr.attr,
+	NULL,
+};
+
+static struct attribute_group dump_ccw_attr_group = {
+	.name  = IPL_CCW_STR,
+	.attrs = dump_ccw_attrs,
+};
+
+/* dump type */
+
+static int dump_set_type(enum dump_type type)
+{
+	if (!(dump_capabilities & type))
+		return -EINVAL;
+	switch (type) {
+	case DUMP_TYPE_CCW:
+		if (diag308_set_works)
+			dump_method = DUMP_METHOD_CCW_DIAG;
+		else if (MACHINE_IS_VM)
+			dump_method = DUMP_METHOD_CCW_VM;
+		else
+			dump_method = DUMP_METHOD_CCW_CIO;
+		break;
+	case DUMP_TYPE_FCP:
+		dump_method = DUMP_METHOD_FCP_DIAG;
+		break;
+	default:
+		dump_method = DUMP_METHOD_NONE;
+	}
+	dump_type = type;
+	return 0;
+}
+
+static ssize_t dump_type_show(struct kobject *kobj,
+			      struct kobj_attribute *attr, char *page)
+{
+	return sprintf(page, "%s\n", dump_type_str(dump_type));
+}
+
+static ssize_t dump_type_store(struct kobject *kobj,
+			       struct kobj_attribute *attr,
+			       const char *buf, size_t len)
+{
+	int rc = -EINVAL;
+
+	if (strncmp(buf, DUMP_NONE_STR, strlen(DUMP_NONE_STR)) == 0)
+		rc = dump_set_type(DUMP_TYPE_NONE);
+	else if (strncmp(buf, DUMP_CCW_STR, strlen(DUMP_CCW_STR)) == 0)
+		rc = dump_set_type(DUMP_TYPE_CCW);
+	else if (strncmp(buf, DUMP_FCP_STR, strlen(DUMP_FCP_STR)) == 0)
+		rc = dump_set_type(DUMP_TYPE_FCP);
+	return (rc != 0) ? rc : len;
+}
+
+static struct kobj_attribute dump_type_attr =
+	__ATTR(dump_type, 0644, dump_type_show, dump_type_store);
+
+static struct kset *dump_kset;
+
+static void diag308_dump(void *dump_block)
+{
+	diag308(DIAG308_SET, dump_block);
+	while (1) {
+		if (diag308(DIAG308_DUMP, NULL) != 0x302)
+			break;
+		udelay_simple(USEC_PER_SEC);
+	}
+}
+
+static void __dump_run(void *unused)
+{
+	struct ccw_dev_id devid;
+	static char buf[100];
+
+	switch (dump_method) {
+	case DUMP_METHOD_CCW_CIO:
+		devid.devno = dump_block_ccw->ipl_info.ccw.devno;
+		devid.ssid  = 0;
+		reipl_ccw_dev(&devid);
+		break;
+	case DUMP_METHOD_CCW_VM:
+		sprintf(buf, "STORE STATUS");
+		__cpcmd(buf, NULL, 0, NULL);
+		sprintf(buf, "IPL %X", dump_block_ccw->ipl_info.ccw.devno);
+		__cpcmd(buf, NULL, 0, NULL);
+		break;
+	case DUMP_METHOD_CCW_DIAG:
+		diag308_dump(dump_block_ccw);
+		break;
+	case DUMP_METHOD_FCP_DIAG:
+		diag308_dump(dump_block_fcp);
+		break;
+	default:
+		break;
+	}
+}
+
+static void dump_run(struct shutdown_trigger *trigger)
+{
+	if (dump_method == DUMP_METHOD_NONE)
+		return;
+	smp_send_stop();
+	smp_call_ipl_cpu(__dump_run, NULL);
+}
+
+static int __init dump_ccw_init(void)
+{
+	int rc;
+
+	dump_block_ccw = (void *) get_zeroed_page(GFP_KERNEL);
+	if (!dump_block_ccw)
+		return -ENOMEM;
+	rc = sysfs_create_group(&dump_kset->kobj, &dump_ccw_attr_group);
+	if (rc) {
+		free_page((unsigned long)dump_block_ccw);
+		return rc;
+	}
+	dump_block_ccw->hdr.len = IPL_PARM_BLK_CCW_LEN;
+	dump_block_ccw->hdr.version = IPL_PARM_BLOCK_VERSION;
+	dump_block_ccw->hdr.blk0_len = IPL_PARM_BLK0_CCW_LEN;
+	dump_block_ccw->hdr.pbt = DIAG308_IPL_TYPE_CCW;
+	dump_capabilities |= DUMP_TYPE_CCW;
+	return 0;
+}
+
+static int __init dump_fcp_init(void)
+{
+	int rc;
+
+	if (!sclp_ipl_info.has_dump)
+		return 0; /* LDIPL DUMP is not installed */
+	if (!diag308_set_works)
+		return 0;
+	dump_block_fcp = (void *) get_zeroed_page(GFP_KERNEL);
+	if (!dump_block_fcp)
+		return -ENOMEM;
+	rc = sysfs_create_group(&dump_kset->kobj, &dump_fcp_attr_group);
+	if (rc) {
+		free_page((unsigned long)dump_block_fcp);
+		return rc;
+	}
+	dump_block_fcp->hdr.len = IPL_PARM_BLK_FCP_LEN;
+	dump_block_fcp->hdr.version = IPL_PARM_BLOCK_VERSION;
+	dump_block_fcp->hdr.blk0_len = IPL_PARM_BLK0_FCP_LEN;
+	dump_block_fcp->hdr.pbt = DIAG308_IPL_TYPE_FCP;
+	dump_block_fcp->ipl_info.fcp.opt = DIAG308_IPL_OPT_DUMP;
+	dump_capabilities |= DUMP_TYPE_FCP;
+	return 0;
+}
+
+static int __init dump_init(void)
+{
+	int rc;
+
+	dump_kset = kset_create_and_add("dump", NULL, firmware_kobj);
+	if (!dump_kset)
+		return -ENOMEM;
+	rc = sysfs_create_file(&dump_kset->kobj, &dump_type_attr.attr);
+	if (rc) {
+		kset_unregister(dump_kset);
+		return rc;
+	}
+	rc = dump_ccw_init();
+	if (rc)
+		return rc;
+	rc = dump_fcp_init();
+	if (rc)
+		return rc;
+	dump_set_type(DUMP_TYPE_NONE);
+	return 0;
+}
+
+static struct shutdown_action __refdata dump_action = {
+	.name	= SHUTDOWN_ACTION_DUMP_STR,
+	.fn	= dump_run,
+	.init	= dump_init,
+};
+
+static void dump_reipl_run(struct shutdown_trigger *trigger)
+{
+	unsigned long ipib = (unsigned long) reipl_block_actual;
+	unsigned int csum;
+
+	csum = csum_partial(reipl_block_actual, reipl_block_actual->hdr.len, 0);
+	mem_assign_absolute(S390_lowcore.ipib, ipib);
+	mem_assign_absolute(S390_lowcore.ipib_checksum, csum);
+	dump_run(trigger);
+}
+
+static int __init dump_reipl_init(void)
+{
+	if (!diag308_set_works)
+		return -EOPNOTSUPP;
+	else
+		return 0;
+}
+
+static struct shutdown_action __refdata dump_reipl_action = {
+	.name	= SHUTDOWN_ACTION_DUMP_REIPL_STR,
+	.fn	= dump_reipl_run,
+	.init	= dump_reipl_init,
+};
+
+/*
+ * vmcmd shutdown action: Trigger vm command on shutdown.
+ */
+
+static char vmcmd_on_reboot[128];
+static char vmcmd_on_panic[128];
+static char vmcmd_on_halt[128];
+static char vmcmd_on_poff[128];
+static char vmcmd_on_restart[128];
+
+DEFINE_IPL_ATTR_STR_RW(vmcmd, on_reboot, "%s\n", "%s\n", vmcmd_on_reboot);
+DEFINE_IPL_ATTR_STR_RW(vmcmd, on_panic, "%s\n", "%s\n", vmcmd_on_panic);
+DEFINE_IPL_ATTR_STR_RW(vmcmd, on_halt, "%s\n", "%s\n", vmcmd_on_halt);
+DEFINE_IPL_ATTR_STR_RW(vmcmd, on_poff, "%s\n", "%s\n", vmcmd_on_poff);
+DEFINE_IPL_ATTR_STR_RW(vmcmd, on_restart, "%s\n", "%s\n", vmcmd_on_restart);
+
+static struct attribute *vmcmd_attrs[] = {
+	&sys_vmcmd_on_reboot_attr.attr,
+	&sys_vmcmd_on_panic_attr.attr,
+	&sys_vmcmd_on_halt_attr.attr,
+	&sys_vmcmd_on_poff_attr.attr,
+	&sys_vmcmd_on_restart_attr.attr,
+	NULL,
+};
+
+static struct attribute_group vmcmd_attr_group = {
+	.attrs = vmcmd_attrs,
+};
+
+static struct kset *vmcmd_kset;
+
+static void vmcmd_run(struct shutdown_trigger *trigger)
+{
+	char *cmd;
+
+	if (strcmp(trigger->name, ON_REIPL_STR) == 0)
+		cmd = vmcmd_on_reboot;
+	else if (strcmp(trigger->name, ON_PANIC_STR) == 0)
+		cmd = vmcmd_on_panic;
+	else if (strcmp(trigger->name, ON_HALT_STR) == 0)
+		cmd = vmcmd_on_halt;
+	else if (strcmp(trigger->name, ON_POFF_STR) == 0)
+		cmd = vmcmd_on_poff;
+	else if (strcmp(trigger->name, ON_RESTART_STR) == 0)
+		cmd = vmcmd_on_restart;
+	else
+		return;
+
+	if (strlen(cmd) == 0)
+		return;
+	__cpcmd(cmd, NULL, 0, NULL);
+}
+
+static int vmcmd_init(void)
+{
+	if (!MACHINE_IS_VM)
+		return -EOPNOTSUPP;
+	vmcmd_kset = kset_create_and_add("vmcmd", NULL, firmware_kobj);
+	if (!vmcmd_kset)
+		return -ENOMEM;
+	return sysfs_create_group(&vmcmd_kset->kobj, &vmcmd_attr_group);
+}
+
+static struct shutdown_action vmcmd_action = {SHUTDOWN_ACTION_VMCMD_STR,
+					      vmcmd_run, vmcmd_init};
+
+/*
+ * stop shutdown action: Stop Linux on shutdown.
+ */
+
+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));
+	smp_stop_cpu();
+}
+
+static struct shutdown_action stop_action = {SHUTDOWN_ACTION_STOP_STR,
+					     stop_run, NULL};
+
+/* action list */
+
+static struct shutdown_action *shutdown_actions_list[] = {
+	&ipl_action, &reipl_action, &dump_reipl_action, &dump_action,
+	&vmcmd_action, &stop_action};
+#define SHUTDOWN_ACTIONS_COUNT (sizeof(shutdown_actions_list) / sizeof(void *))
+
+/*
+ * Trigger section
+ */
+
+static struct kset *shutdown_actions_kset;
+
+static int set_trigger(const char *buf, struct shutdown_trigger *trigger,
+		       size_t len)
+{
+	int i;
+
+	for (i = 0; i < SHUTDOWN_ACTIONS_COUNT; i++) {
+		if (sysfs_streq(buf, shutdown_actions_list[i]->name)) {
+			if (shutdown_actions_list[i]->init_rc) {
+				return shutdown_actions_list[i]->init_rc;
+			} else {
+				trigger->action = shutdown_actions_list[i];
+				return len;
+			}
+		}
+	}
+	return -EINVAL;
+}
+
+/* on reipl */
+
+static struct shutdown_trigger on_reboot_trigger = {ON_REIPL_STR,
+						    &reipl_action};
+
+static ssize_t on_reboot_show(struct kobject *kobj,
+			      struct kobj_attribute *attr, char *page)
+{
+	return sprintf(page, "%s\n", on_reboot_trigger.action->name);
+}
+
+static ssize_t on_reboot_store(struct kobject *kobj,
+			       struct kobj_attribute *attr,
+			       const char *buf, size_t len)
+{
+	return set_trigger(buf, &on_reboot_trigger, len);
+}
+static struct kobj_attribute on_reboot_attr = __ATTR_RW(on_reboot);
+
+static void do_machine_restart(char *__unused)
+{
+	smp_send_stop();
+	on_reboot_trigger.action->fn(&on_reboot_trigger);
+	reipl_run(NULL);
+}
+void (*_machine_restart)(char *command) = do_machine_restart;
+
+/* on panic */
+
+static struct shutdown_trigger on_panic_trigger = {ON_PANIC_STR, &stop_action};
+
+static ssize_t on_panic_show(struct kobject *kobj,
+			     struct kobj_attribute *attr, char *page)
+{
+	return sprintf(page, "%s\n", on_panic_trigger.action->name);
+}
+
+static ssize_t on_panic_store(struct kobject *kobj,
+			      struct kobj_attribute *attr,
+			      const char *buf, size_t len)
+{
+	return set_trigger(buf, &on_panic_trigger, len);
+}
+static struct kobj_attribute on_panic_attr = __ATTR_RW(on_panic);
+
+static void do_panic(void)
+{
+	lgr_info_log();
+	on_panic_trigger.action->fn(&on_panic_trigger);
+	stop_run(&on_panic_trigger);
+}
+
+/* on restart */
+
+static struct shutdown_trigger on_restart_trigger = {ON_RESTART_STR,
+	&stop_action};
+
+static ssize_t on_restart_show(struct kobject *kobj,
+			       struct kobj_attribute *attr, char *page)
+{
+	return sprintf(page, "%s\n", on_restart_trigger.action->name);
+}
+
+static ssize_t on_restart_store(struct kobject *kobj,
+				struct kobj_attribute *attr,
+				const char *buf, size_t len)
+{
+	return set_trigger(buf, &on_restart_trigger, len);
+}
+static struct kobj_attribute on_restart_attr = __ATTR_RW(on_restart);
+
+static void __do_restart(void *ignore)
+{
+	__arch_local_irq_stosm(0x04); /* enable DAT */
+	smp_send_stop();
+#ifdef CONFIG_CRASH_DUMP
+	crash_kexec(NULL);
+#endif
+	on_restart_trigger.action->fn(&on_restart_trigger);
+	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};
+
+static ssize_t on_halt_show(struct kobject *kobj,
+			    struct kobj_attribute *attr, char *page)
+{
+	return sprintf(page, "%s\n", on_halt_trigger.action->name);
+}
+
+static ssize_t on_halt_store(struct kobject *kobj,
+			     struct kobj_attribute *attr,
+			     const char *buf, size_t len)
+{
+	return set_trigger(buf, &on_halt_trigger, len);
+}
+static struct kobj_attribute on_halt_attr = __ATTR_RW(on_halt);
+
+static void do_machine_halt(void)
+{
+	smp_send_stop();
+	on_halt_trigger.action->fn(&on_halt_trigger);
+	stop_run(&on_halt_trigger);
+}
+void (*_machine_halt)(void) = do_machine_halt;
+
+/* on power off */
+
+static struct shutdown_trigger on_poff_trigger = {ON_POFF_STR, &stop_action};
+
+static ssize_t on_poff_show(struct kobject *kobj,
+			    struct kobj_attribute *attr, char *page)
+{
+	return sprintf(page, "%s\n", on_poff_trigger.action->name);
+}
+
+static ssize_t on_poff_store(struct kobject *kobj,
+			     struct kobj_attribute *attr,
+			     const char *buf, size_t len)
+{
+	return set_trigger(buf, &on_poff_trigger, len);
+}
+static struct kobj_attribute on_poff_attr = __ATTR_RW(on_poff);
+
+static void do_machine_power_off(void)
+{
+	smp_send_stop();
+	on_poff_trigger.action->fn(&on_poff_trigger);
+	stop_run(&on_poff_trigger);
+}
+void (*_machine_power_off)(void) = do_machine_power_off;
+
+static struct attribute *shutdown_action_attrs[] = {
+	&on_restart_attr.attr,
+	&on_reboot_attr.attr,
+	&on_panic_attr.attr,
+	&on_halt_attr.attr,
+	&on_poff_attr.attr,
+	NULL,
+};
+
+static struct attribute_group shutdown_action_attr_group = {
+	.attrs = shutdown_action_attrs,
+};
+
+static void __init shutdown_triggers_init(void)
+{
+	shutdown_actions_kset = kset_create_and_add("shutdown_actions", NULL,
+						    firmware_kobj);
+	if (!shutdown_actions_kset)
+		goto fail;
+	if (sysfs_create_group(&shutdown_actions_kset->kobj,
+			       &shutdown_action_attr_group))
+		goto fail;
+	return;
+fail:
+	panic("shutdown_triggers_init failed\n");
+}
+
+static void __init shutdown_actions_init(void)
+{
+	int i;
+
+	for (i = 0; i < SHUTDOWN_ACTIONS_COUNT; i++) {
+		if (!shutdown_actions_list[i]->init)
+			continue;
+		shutdown_actions_list[i]->init_rc =
+			shutdown_actions_list[i]->init();
+	}
+}
+
+static int __init s390_ipl_init(void)
+{
+	char str[8] = {0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40};
+
+	sclp_get_ipl_info(&sclp_ipl_info);
+	/*
+	 * Fix loadparm: There are systems where the (SCSI) LOADPARM
+	 * returned by read SCP info is invalid (contains EBCDIC blanks)
+	 * when the system has been booted via diag308. In that case we use
+	 * the value from diag308, if available.
+	 *
+	 * There are also systems where diag308 store does not work in
+	 * case the system is booted from HMC. Fortunately in this case
+	 * READ SCP info provides the correct value.
+	 */
+	if (memcmp(sclp_ipl_info.loadparm, str, sizeof(str)) == 0 &&
+	    diag308_set_works)
+		memcpy(sclp_ipl_info.loadparm, ipl_block.hdr.loadparm,
+		       LOADPARM_LEN);
+	shutdown_actions_init();
+	shutdown_triggers_init();
+	return 0;
+}
+
+__initcall(s390_ipl_init);
+
+static void __init strncpy_skip_quote(char *dst, char *src, int n)
+{
+	int sx, dx;
+
+	dx = 0;
+	for (sx = 0; src[sx] != 0; sx++) {
+		if (src[sx] == '"')
+			continue;
+		dst[dx++] = src[sx];
+		if (dx >= n)
+			break;
+	}
+}
+
+static int __init vmcmd_on_reboot_setup(char *str)
+{
+	if (!MACHINE_IS_VM)
+		return 1;
+	strncpy_skip_quote(vmcmd_on_reboot, str, 127);
+	vmcmd_on_reboot[127] = 0;
+	on_reboot_trigger.action = &vmcmd_action;
+	return 1;
+}
+__setup("vmreboot=", vmcmd_on_reboot_setup);
+
+static int __init vmcmd_on_panic_setup(char *str)
+{
+	if (!MACHINE_IS_VM)
+		return 1;
+	strncpy_skip_quote(vmcmd_on_panic, str, 127);
+	vmcmd_on_panic[127] = 0;
+	on_panic_trigger.action = &vmcmd_action;
+	return 1;
+}
+__setup("vmpanic=", vmcmd_on_panic_setup);
+
+static int __init vmcmd_on_halt_setup(char *str)
+{
+	if (!MACHINE_IS_VM)
+		return 1;
+	strncpy_skip_quote(vmcmd_on_halt, str, 127);
+	vmcmd_on_halt[127] = 0;
+	on_halt_trigger.action = &vmcmd_action;
+	return 1;
+}
+__setup("vmhalt=", vmcmd_on_halt_setup);
+
+static int __init vmcmd_on_poff_setup(char *str)
+{
+	if (!MACHINE_IS_VM)
+		return 1;
+	strncpy_skip_quote(vmcmd_on_poff, str, 127);
+	vmcmd_on_poff[127] = 0;
+	on_poff_trigger.action = &vmcmd_action;
+	return 1;
+}
+__setup("vmpoff=", vmcmd_on_poff_setup);
+
+static int on_panic_notify(struct notifier_block *self,
+			   unsigned long event, void *data)
+{
+	do_panic();
+	return NOTIFY_OK;
+}
+
+static struct notifier_block on_panic_nb = {
+	.notifier_call = on_panic_notify,
+	.priority = INT_MIN,
+};
+
+void __init setup_ipl(void)
+{
+	ipl_info.type = get_ipl_type();
+	switch (ipl_info.type) {
+	case IPL_TYPE_CCW:
+		ipl_info.data.ccw.dev_id.devno = ipl_devno;
+		ipl_info.data.ccw.dev_id.ssid = 0;
+		break;
+	case IPL_TYPE_FCP:
+	case IPL_TYPE_FCP_DUMP:
+		ipl_info.data.fcp.dev_id.devno =
+			IPL_PARMBLOCK_START->ipl_info.fcp.devno;
+		ipl_info.data.fcp.dev_id.ssid = 0;
+		ipl_info.data.fcp.wwpn = IPL_PARMBLOCK_START->ipl_info.fcp.wwpn;
+		ipl_info.data.fcp.lun = IPL_PARMBLOCK_START->ipl_info.fcp.lun;
+		break;
+	case IPL_TYPE_NSS:
+		strncpy(ipl_info.data.nss.name, kernel_nss_name,
+			sizeof(ipl_info.data.nss.name));
+		break;
+	case IPL_TYPE_UNKNOWN:
+		/* We have no info to copy */
+		break;
+	}
+	atomic_notifier_chain_register(&panic_notifier_list, &on_panic_nb);
+}
+
+void __init ipl_update_parameters(void)
+{
+	int rc;
+
+	rc = diag308(DIAG308_STORE, &ipl_block);
+	if ((rc == DIAG308_RC_OK) || (rc == DIAG308_RC_NOCONFIG))
+		diag308_set_works = 1;
+}
+
+void __init ipl_save_parameters(void)
+{
+	struct cio_iplinfo iplinfo;
+	void *src, *dst;
+
+	if (cio_get_iplinfo(&iplinfo))
+		return;
+
+	ipl_devno = iplinfo.devno;
+	ipl_flags |= IPL_DEVNO_VALID;
+	if (!iplinfo.is_qdio)
+		return;
+	ipl_flags |= IPL_PARMBLOCK_VALID;
+	src = (void *)(unsigned long)S390_lowcore.ipl_parmblock_ptr;
+	dst = (void *)IPL_PARMBLOCK_ORIGIN;
+	memmove(dst, src, PAGE_SIZE);
+	S390_lowcore.ipl_parmblock_ptr = IPL_PARMBLOCK_ORIGIN;
+}
+
+static LIST_HEAD(rcall);
+static DEFINE_MUTEX(rcall_mutex);
+
+void register_reset_call(struct reset_call *reset)
+{
+	mutex_lock(&rcall_mutex);
+	list_add(&reset->list, &rcall);
+	mutex_unlock(&rcall_mutex);
+}
+EXPORT_SYMBOL_GPL(register_reset_call);
+
+void unregister_reset_call(struct reset_call *reset)
+{
+	mutex_lock(&rcall_mutex);
+	list_del(&reset->list);
+	mutex_unlock(&rcall_mutex);
+}
+EXPORT_SYMBOL_GPL(unregister_reset_call);
+
+static void do_reset_calls(void)
+{
+	struct reset_call *reset;
+
+	if (diag308_set_works) {
+		diag308_reset();
+		return;
+	}
+	list_for_each_entry(reset, &rcall, list)
+		reset->fn();
+}
+
+u32 dump_prefix_page;
+
+void s390_reset_system(void (*fn_pre)(void),
+		       void (*fn_post)(void *), void *data)
+{
+	struct _lowcore *lc;
+
+	lc = (struct _lowcore *)(unsigned long) store_prefix();
+
+	/* Stack for interrupt/machine check handler */
+	lc->panic_stack = S390_lowcore.panic_stack;
+
+	/* Save prefix page address for dump case */
+	dump_prefix_page = (u32)(unsigned long) lc;
+
+	/* Disable prefixing */
+	set_prefix(0);
+
+	/* Disable lowcore protection */
+	__ctl_clear_bit(0,28);
+
+	/* Set new machine check handler */
+	S390_lowcore.mcck_new_psw.mask = PSW_KERNEL_BITS | PSW_MASK_DAT;
+	S390_lowcore.mcck_new_psw.addr =
+		PSW_ADDR_AMODE | (unsigned long) s390_base_mcck_handler;
+
+	/* Set new program check handler */
+	S390_lowcore.program_new_psw.mask = PSW_KERNEL_BITS | PSW_MASK_DAT;
+	S390_lowcore.program_new_psw.addr =
+		PSW_ADDR_AMODE | (unsigned long) s390_base_pgm_handler;
+
+	/*
+	 * Clear subchannel ID and number to signal new kernel that no CCW or
+	 * SCSI IPL has been done (for kexec and kdump)
+	 */
+	S390_lowcore.subchannel_id = 0;
+	S390_lowcore.subchannel_nr = 0;
+
+	/* Store status at absolute zero */
+	store_status();
+
+	/* Call function before reset */
+	if (fn_pre)
+		fn_pre();
+	do_reset_calls();
+	/* Call function after reset */
+	if (fn_post)
+		fn_post(data);
+}
diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c
new file mode 100644
index 000000000..e9d9addfa
--- /dev/null
+++ b/arch/s390/kernel/irq.c
@@ -0,0 +1,310 @@
+/*
+ *    Copyright IBM Corp. 2004, 2011
+ *    Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>,
+ *		 Holger Smolinski <Holger.Smolinski@de.ibm.com>,
+ *		 Thomas Spatzier <tspat@de.ibm.com>,
+ *
+ * This file contains interrupt related functions.
+ */
+
+#include <linux/kernel_stat.h>
+#include <linux/interrupt.h>
+#include <linux/seq_file.h>
+#include <linux/proc_fs.h>
+#include <linux/profile.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/ftrace.h>
+#include <linux/errno.h>
+#include <linux/slab.h>
+#include <linux/cpu.h>
+#include <linux/irq.h>
+#include <asm/irq_regs.h>
+#include <asm/cputime.h>
+#include <asm/lowcore.h>
+#include <asm/irq.h>
+#include <asm/hw_irq.h>
+#include "entry.h"
+
+DEFINE_PER_CPU_SHARED_ALIGNED(struct irq_stat, irq_stat);
+EXPORT_PER_CPU_SYMBOL_GPL(irq_stat);
+
+struct irq_class {
+	int irq;
+	char *name;
+	char *desc;
+};
+
+/*
+ * The list of "main" irq classes on s390. This is the list of interrupts
+ * that appear both in /proc/stat ("intr" line) and /proc/interrupts.
+ * Historically only external and I/O interrupts have been part of /proc/stat.
+ * We can't add the split external and I/O sub classes since the first field
+ * in the "intr" line in /proc/stat is supposed to be the sum of all other
+ * fields.
+ * Since the external and I/O interrupt fields are already sums we would end
+ * up with having a sum which accounts each interrupt twice.
+ */
+static const struct irq_class irqclass_main_desc[NR_IRQS_BASE] = {
+	{.irq = EXT_INTERRUPT,	.name = "EXT"},
+	{.irq = IO_INTERRUPT,	.name = "I/O"},
+	{.irq = THIN_INTERRUPT, .name = "AIO"},
+};
+
+/*
+ * The list of split external and I/O interrupts that appear only in
+ * /proc/interrupts.
+ * In addition this list contains non external / I/O events like NMIs.
+ */
+static const struct irq_class irqclass_sub_desc[] = {
+	{.irq = IRQEXT_CLK, .name = "CLK", .desc = "[EXT] Clock Comparator"},
+	{.irq = IRQEXT_EXC, .name = "EXC", .desc = "[EXT] External Call"},
+	{.irq = IRQEXT_EMS, .name = "EMS", .desc = "[EXT] Emergency Signal"},
+	{.irq = IRQEXT_TMR, .name = "TMR", .desc = "[EXT] CPU Timer"},
+	{.irq = IRQEXT_TLA, .name = "TAL", .desc = "[EXT] Timing Alert"},
+	{.irq = IRQEXT_PFL, .name = "PFL", .desc = "[EXT] Pseudo Page Fault"},
+	{.irq = IRQEXT_DSD, .name = "DSD", .desc = "[EXT] DASD Diag"},
+	{.irq = IRQEXT_VRT, .name = "VRT", .desc = "[EXT] Virtio"},
+	{.irq = IRQEXT_SCP, .name = "SCP", .desc = "[EXT] Service Call"},
+	{.irq = IRQEXT_IUC, .name = "IUC", .desc = "[EXT] IUCV"},
+	{.irq = IRQEXT_CMS, .name = "CMS", .desc = "[EXT] CPU-Measurement: Sampling"},
+	{.irq = IRQEXT_CMC, .name = "CMC", .desc = "[EXT] CPU-Measurement: Counter"},
+	{.irq = IRQEXT_CMR, .name = "CMR", .desc = "[EXT] CPU-Measurement: RI"},
+	{.irq = IRQEXT_FTP, .name = "FTP", .desc = "[EXT] HMC FTP Service"},
+	{.irq = IRQIO_CIO,  .name = "CIO", .desc = "[I/O] Common I/O Layer Interrupt"},
+	{.irq = IRQIO_QAI,  .name = "QAI", .desc = "[I/O] QDIO Adapter Interrupt"},
+	{.irq = IRQIO_DAS,  .name = "DAS", .desc = "[I/O] DASD"},
+	{.irq = IRQIO_C15,  .name = "C15", .desc = "[I/O] 3215"},
+	{.irq = IRQIO_C70,  .name = "C70", .desc = "[I/O] 3270"},
+	{.irq = IRQIO_TAP,  .name = "TAP", .desc = "[I/O] Tape"},
+	{.irq = IRQIO_VMR,  .name = "VMR", .desc = "[I/O] Unit Record Devices"},
+	{.irq = IRQIO_LCS,  .name = "LCS", .desc = "[I/O] LCS"},
+	{.irq = IRQIO_CTC,  .name = "CTC", .desc = "[I/O] CTC"},
+	{.irq = IRQIO_APB,  .name = "APB", .desc = "[I/O] AP Bus"},
+	{.irq = IRQIO_ADM,  .name = "ADM", .desc = "[I/O] EADM Subchannel"},
+	{.irq = IRQIO_CSC,  .name = "CSC", .desc = "[I/O] CHSC Subchannel"},
+	{.irq = IRQIO_PCI,  .name = "PCI", .desc = "[I/O] PCI Interrupt" },
+	{.irq = IRQIO_MSI,  .name = "MSI", .desc = "[I/O] MSI Interrupt" },
+	{.irq = IRQIO_VIR,  .name = "VIR", .desc = "[I/O] Virtual I/O Devices"},
+	{.irq = IRQIO_VAI,  .name = "VAI", .desc = "[I/O] Virtual I/O Devices AI"},
+	{.irq = NMI_NMI,    .name = "NMI", .desc = "[NMI] Machine Check"},
+	{.irq = CPU_RST,    .name = "RST", .desc = "[CPU] CPU Restart"},
+};
+
+void __init init_IRQ(void)
+{
+	BUILD_BUG_ON(ARRAY_SIZE(irqclass_sub_desc) != NR_ARCH_IRQS);
+	init_cio_interrupts();
+	init_airq_interrupts();
+	init_ext_interrupts();
+}
+
+void do_IRQ(struct pt_regs *regs, int irq)
+{
+	struct pt_regs *old_regs;
+
+	old_regs = set_irq_regs(regs);
+	irq_enter();
+	if (S390_lowcore.int_clock >= S390_lowcore.clock_comparator)
+		/* Serve timer interrupts first. */
+		clock_comparator_work();
+	generic_handle_irq(irq);
+	irq_exit();
+	set_irq_regs(old_regs);
+}
+
+/*
+ * show_interrupts is needed by /proc/interrupts.
+ */
+int show_interrupts(struct seq_file *p, void *v)
+{
+	int index = *(loff_t *) v;
+	int cpu, irq;
+
+	get_online_cpus();
+	if (index == 0) {
+		seq_puts(p, "           ");
+		for_each_online_cpu(cpu)
+			seq_printf(p, "CPU%d       ", cpu);
+		seq_putc(p, '\n');
+	}
+	if (index < NR_IRQS) {
+		if (index >= NR_IRQS_BASE)
+			goto out;
+		seq_printf(p, "%s: ", irqclass_main_desc[index].name);
+		irq = irqclass_main_desc[index].irq;
+		for_each_online_cpu(cpu)
+			seq_printf(p, "%10u ", kstat_irqs_cpu(irq, cpu));
+		seq_putc(p, '\n');
+		goto out;
+	}
+	for (index = 0; index < NR_ARCH_IRQS; index++) {
+		seq_printf(p, "%s: ", irqclass_sub_desc[index].name);
+		irq = irqclass_sub_desc[index].irq;
+		for_each_online_cpu(cpu)
+			seq_printf(p, "%10u ",
+				   per_cpu(irq_stat, cpu).irqs[irq]);
+		if (irqclass_sub_desc[index].desc)
+			seq_printf(p, "  %s", irqclass_sub_desc[index].desc);
+		seq_putc(p, '\n');
+	}
+out:
+	put_online_cpus();
+	return 0;
+}
+
+unsigned int arch_dynirq_lower_bound(unsigned int from)
+{
+	return from < NR_IRQS_BASE ? NR_IRQS_BASE : from;
+}
+
+/*
+ * Switch to the asynchronous interrupt stack for softirq execution.
+ */
+void do_softirq_own_stack(void)
+{
+	unsigned long old, new;
+
+	/* Get current stack pointer. */
+	asm volatile("la %0,0(15)" : "=a" (old));
+	/* Check against async. stack address range. */
+	new = S390_lowcore.async_stack;
+	if (((new - old) >> (PAGE_SHIFT + THREAD_ORDER)) != 0) {
+		/* Need to switch to the async. stack. */
+		new -= STACK_FRAME_OVERHEAD;
+		((struct stack_frame *) new)->back_chain = old;
+		asm volatile("   la    15,0(%0)\n"
+			     "   basr  14,%2\n"
+			     "   la    15,0(%1)\n"
+			     : : "a" (new), "a" (old),
+			         "a" (__do_softirq)
+			     : "0", "1", "2", "3", "4", "5", "14",
+			       "cc", "memory" );
+	} else {
+		/* We are already on the async stack. */
+		__do_softirq();
+	}
+}
+
+/*
+ * ext_int_hash[index] is the list head for all external interrupts that hash
+ * to this index.
+ */
+static struct hlist_head ext_int_hash[32] ____cacheline_aligned;
+
+struct ext_int_info {
+	ext_int_handler_t handler;
+	struct hlist_node entry;
+	struct rcu_head rcu;
+	u16 code;
+};
+
+/* ext_int_hash_lock protects the handler lists for external interrupts */
+static DEFINE_SPINLOCK(ext_int_hash_lock);
+
+static inline int ext_hash(u16 code)
+{
+	BUILD_BUG_ON(!is_power_of_2(ARRAY_SIZE(ext_int_hash)));
+
+	return (code + (code >> 9)) & (ARRAY_SIZE(ext_int_hash) - 1);
+}
+
+int register_external_irq(u16 code, ext_int_handler_t handler)
+{
+	struct ext_int_info *p;
+	unsigned long flags;
+	int index;
+
+	p = kmalloc(sizeof(*p), GFP_ATOMIC);
+	if (!p)
+		return -ENOMEM;
+	p->code = code;
+	p->handler = handler;
+	index = ext_hash(code);
+
+	spin_lock_irqsave(&ext_int_hash_lock, flags);
+	hlist_add_head_rcu(&p->entry, &ext_int_hash[index]);
+	spin_unlock_irqrestore(&ext_int_hash_lock, flags);
+	return 0;
+}
+EXPORT_SYMBOL(register_external_irq);
+
+int unregister_external_irq(u16 code, ext_int_handler_t handler)
+{
+	struct ext_int_info *p;
+	unsigned long flags;
+	int index = ext_hash(code);
+
+	spin_lock_irqsave(&ext_int_hash_lock, flags);
+	hlist_for_each_entry_rcu(p, &ext_int_hash[index], entry) {
+		if (p->code == code && p->handler == handler) {
+			hlist_del_rcu(&p->entry);
+			kfree_rcu(p, rcu);
+		}
+	}
+	spin_unlock_irqrestore(&ext_int_hash_lock, flags);
+	return 0;
+}
+EXPORT_SYMBOL(unregister_external_irq);
+
+static irqreturn_t do_ext_interrupt(int irq, void *dummy)
+{
+	struct pt_regs *regs = get_irq_regs();
+	struct ext_code ext_code;
+	struct ext_int_info *p;
+	int index;
+
+	ext_code = *(struct ext_code *) &regs->int_code;
+	if (ext_code.code != EXT_IRQ_CLK_COMP)
+		set_cpu_flag(CIF_NOHZ_DELAY);
+
+	index = ext_hash(ext_code.code);
+	rcu_read_lock();
+	hlist_for_each_entry_rcu(p, &ext_int_hash[index], entry) {
+		if (unlikely(p->code != ext_code.code))
+			continue;
+		p->handler(ext_code, regs->int_parm, regs->int_parm_long);
+	}
+	rcu_read_unlock();
+	return IRQ_HANDLED;
+}
+
+static struct irqaction external_interrupt = {
+	.name	 = "EXT",
+	.handler = do_ext_interrupt,
+};
+
+void __init init_ext_interrupts(void)
+{
+	int idx;
+
+	for (idx = 0; idx < ARRAY_SIZE(ext_int_hash); idx++)
+		INIT_HLIST_HEAD(&ext_int_hash[idx]);
+
+	irq_set_chip_and_handler(EXT_INTERRUPT,
+				 &dummy_irq_chip, handle_percpu_irq);
+	setup_irq(EXT_INTERRUPT, &external_interrupt);
+}
+
+static DEFINE_SPINLOCK(irq_subclass_lock);
+static unsigned char irq_subclass_refcount[64];
+
+void irq_subclass_register(enum irq_subclass subclass)
+{
+	spin_lock(&irq_subclass_lock);
+	if (!irq_subclass_refcount[subclass])
+		ctl_set_bit(0, subclass);
+	irq_subclass_refcount[subclass]++;
+	spin_unlock(&irq_subclass_lock);
+}
+EXPORT_SYMBOL(irq_subclass_register);
+
+void irq_subclass_unregister(enum irq_subclass subclass)
+{
+	spin_lock(&irq_subclass_lock);
+	irq_subclass_refcount[subclass]--;
+	if (!irq_subclass_refcount[subclass])
+		ctl_clear_bit(0, subclass);
+	spin_unlock(&irq_subclass_lock);
+}
+EXPORT_SYMBOL(irq_subclass_unregister);
diff --git a/arch/s390/kernel/jump_label.c b/arch/s390/kernel/jump_label.c
new file mode 100644
index 000000000..a90299600
--- /dev/null
+++ b/arch/s390/kernel/jump_label.c
@@ -0,0 +1,109 @@
+/*
+ * Jump label s390 support
+ *
+ * Copyright IBM Corp. 2011
+ * Author(s): Jan Glauber <jang@linux.vnet.ibm.com>
+ */
+#include <linux/module.h>
+#include <linux/uaccess.h>
+#include <linux/stop_machine.h>
+#include <linux/jump_label.h>
+#include <asm/ipl.h>
+
+#ifdef HAVE_JUMP_LABEL
+
+struct insn {
+	u16 opcode;
+	s32 offset;
+} __packed;
+
+struct insn_args {
+	struct jump_entry *entry;
+	enum jump_label_type type;
+};
+
+static void jump_label_make_nop(struct jump_entry *entry, struct insn *insn)
+{
+	/* brcl 0,0 */
+	insn->opcode = 0xc004;
+	insn->offset = 0;
+}
+
+static void jump_label_make_branch(struct jump_entry *entry, struct insn *insn)
+{
+	/* brcl 15,offset */
+	insn->opcode = 0xc0f4;
+	insn->offset = (entry->target - entry->code) >> 1;
+}
+
+static void jump_label_bug(struct jump_entry *entry, struct insn *expected,
+			   struct insn *new)
+{
+	unsigned char *ipc = (unsigned char *)entry->code;
+	unsigned char *ipe = (unsigned char *)expected;
+	unsigned char *ipn = (unsigned char *)new;
+
+	pr_emerg("Jump label code mismatch at %pS [%p]\n", ipc, ipc);
+	pr_emerg("Found:    %02x %02x %02x %02x %02x %02x\n",
+		 ipc[0], ipc[1], ipc[2], ipc[3], ipc[4], ipc[5]);
+	pr_emerg("Expected: %02x %02x %02x %02x %02x %02x\n",
+		 ipe[0], ipe[1], ipe[2], ipe[3], ipe[4], ipe[5]);
+	pr_emerg("New:      %02x %02x %02x %02x %02x %02x\n",
+		 ipn[0], ipn[1], ipn[2], ipn[3], ipn[4], ipn[5]);
+	panic("Corrupted kernel text");
+}
+
+static struct insn orignop = {
+	.opcode = 0xc004,
+	.offset = JUMP_LABEL_NOP_OFFSET >> 1,
+};
+
+static void __jump_label_transform(struct jump_entry *entry,
+				   enum jump_label_type type,
+				   int init)
+{
+	struct insn old, new;
+
+	if (type == JUMP_LABEL_ENABLE) {
+		jump_label_make_nop(entry, &old);
+		jump_label_make_branch(entry, &new);
+	} else {
+		jump_label_make_branch(entry, &old);
+		jump_label_make_nop(entry, &new);
+	}
+	if (init) {
+		if (memcmp((void *)entry->code, &orignop, sizeof(orignop)))
+			jump_label_bug(entry, &orignop, &new);
+	} else {
+		if (memcmp((void *)entry->code, &old, sizeof(old)))
+			jump_label_bug(entry, &old, &new);
+	}
+	s390_kernel_write((void *)entry->code, &new, sizeof(new));
+}
+
+static int __sm_arch_jump_label_transform(void *data)
+{
+	struct insn_args *args = data;
+
+	__jump_label_transform(args->entry, args->type, 0);
+	return 0;
+}
+
+void arch_jump_label_transform(struct jump_entry *entry,
+			       enum jump_label_type type)
+{
+	struct insn_args args;
+
+	args.entry = entry;
+	args.type = type;
+
+	stop_machine(__sm_arch_jump_label_transform, &args, NULL);
+}
+
+void arch_jump_label_transform_static(struct jump_entry *entry,
+				      enum jump_label_type type)
+{
+	__jump_label_transform(entry, type, 1);
+}
+
+#endif
diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c
new file mode 100644
index 000000000..389db56a2
--- /dev/null
+++ b/arch/s390/kernel/kprobes.c
@@ -0,0 +1,733 @@
+/*
+ *  Kernel Probes (KProbes)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright IBM Corp. 2002, 2006
+ *
+ * s390 port, used ppc64 as template. Mike Grundy <grundym@us.ibm.com>
+ */
+
+#include <linux/kprobes.h>
+#include <linux/ptrace.h>
+#include <linux/preempt.h>
+#include <linux/stop_machine.h>
+#include <linux/kdebug.h>
+#include <linux/uaccess.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/hardirq.h>
+#include <linux/ftrace.h>
+#include <asm/cacheflush.h>
+#include <asm/sections.h>
+#include <asm/dis.h>
+
+DEFINE_PER_CPU(struct kprobe *, current_kprobe);
+DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
+
+struct kretprobe_blackpoint kretprobe_blacklist[] = { };
+
+DEFINE_INSN_CACHE_OPS(dmainsn);
+
+static void *alloc_dmainsn_page(void)
+{
+	return (void *)__get_free_page(GFP_KERNEL | GFP_DMA);
+}
+
+static void free_dmainsn_page(void *page)
+{
+	free_page((unsigned long)page);
+}
+
+struct kprobe_insn_cache kprobe_dmainsn_slots = {
+	.mutex = __MUTEX_INITIALIZER(kprobe_dmainsn_slots.mutex),
+	.alloc = alloc_dmainsn_page,
+	.free = free_dmainsn_page,
+	.pages = LIST_HEAD_INIT(kprobe_dmainsn_slots.pages),
+	.insn_size = MAX_INSN_SIZE,
+};
+
+static void copy_instruction(struct kprobe *p)
+{
+	unsigned long ip = (unsigned long) p->addr;
+	s64 disp, new_disp;
+	u64 addr, new_addr;
+
+	if (ftrace_location(ip) == ip) {
+		/*
+		 * If kprobes patches the instruction that is morphed by
+		 * ftrace make sure that kprobes always sees the branch
+		 * "jg .+24" that skips the mcount block or the "brcl 0,0"
+		 * in case of hotpatch.
+		 */
+		ftrace_generate_nop_insn((struct ftrace_insn *)p->ainsn.insn);
+		p->ainsn.is_ftrace_insn = 1;
+	} else
+		memcpy(p->ainsn.insn, p->addr, insn_length(*p->addr >> 8));
+	p->opcode = p->ainsn.insn[0];
+	if (!probe_is_insn_relative_long(p->ainsn.insn))
+		return;
+	/*
+	 * For pc-relative instructions in RIL-b or RIL-c format patch the
+	 * RI2 displacement field. We have already made sure that the insn
+	 * slot for the patched instruction is within the same 2GB area
+	 * as the original instruction (either kernel image or module area).
+	 * Therefore the new displacement will always fit.
+	 */
+	disp = *(s32 *)&p->ainsn.insn[1];
+	addr = (u64)(unsigned long)p->addr;
+	new_addr = (u64)(unsigned long)p->ainsn.insn;
+	new_disp = ((addr + (disp * 2)) - new_addr) / 2;
+	*(s32 *)&p->ainsn.insn[1] = new_disp;
+}
+NOKPROBE_SYMBOL(copy_instruction);
+
+static inline int is_kernel_addr(void *addr)
+{
+	return addr < (void *)_end;
+}
+
+static int s390_get_insn_slot(struct kprobe *p)
+{
+	/*
+	 * Get an insn slot that is within the same 2GB area like the original
+	 * instruction. That way instructions with a 32bit signed displacement
+	 * field can be patched and executed within the insn slot.
+	 */
+	p->ainsn.insn = NULL;
+	if (is_kernel_addr(p->addr))
+		p->ainsn.insn = get_dmainsn_slot();
+	else if (is_module_addr(p->addr))
+		p->ainsn.insn = get_insn_slot();
+	return p->ainsn.insn ? 0 : -ENOMEM;
+}
+NOKPROBE_SYMBOL(s390_get_insn_slot);
+
+static void s390_free_insn_slot(struct kprobe *p)
+{
+	if (!p->ainsn.insn)
+		return;
+	if (is_kernel_addr(p->addr))
+		free_dmainsn_slot(p->ainsn.insn, 0);
+	else
+		free_insn_slot(p->ainsn.insn, 0);
+	p->ainsn.insn = NULL;
+}
+NOKPROBE_SYMBOL(s390_free_insn_slot);
+
+int arch_prepare_kprobe(struct kprobe *p)
+{
+	if ((unsigned long) p->addr & 0x01)
+		return -EINVAL;
+	/* Make sure the probe isn't going on a difficult instruction */
+	if (probe_is_prohibited_opcode(p->addr))
+		return -EINVAL;
+	if (s390_get_insn_slot(p))
+		return -ENOMEM;
+	copy_instruction(p);
+	return 0;
+}
+NOKPROBE_SYMBOL(arch_prepare_kprobe);
+
+int arch_check_ftrace_location(struct kprobe *p)
+{
+	return 0;
+}
+
+struct swap_insn_args {
+	struct kprobe *p;
+	unsigned int arm_kprobe : 1;
+};
+
+static int swap_instruction(void *data)
+{
+	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
+	unsigned long status = kcb->kprobe_status;
+	struct swap_insn_args *args = data;
+	struct ftrace_insn new_insn, *insn;
+	struct kprobe *p = args->p;
+	size_t len;
+
+	new_insn.opc = args->arm_kprobe ? BREAKPOINT_INSTRUCTION : p->opcode;
+	len = sizeof(new_insn.opc);
+	if (!p->ainsn.is_ftrace_insn)
+		goto skip_ftrace;
+	len = sizeof(new_insn);
+	insn = (struct ftrace_insn *) p->addr;
+	if (args->arm_kprobe) {
+		if (is_ftrace_nop(insn))
+			new_insn.disp = KPROBE_ON_FTRACE_NOP;
+		else
+			new_insn.disp = KPROBE_ON_FTRACE_CALL;
+	} else {
+		ftrace_generate_call_insn(&new_insn, (unsigned long)p->addr);
+		if (insn->disp == KPROBE_ON_FTRACE_NOP)
+			ftrace_generate_nop_insn(&new_insn);
+	}
+skip_ftrace:
+	kcb->kprobe_status = KPROBE_SWAP_INST;
+	s390_kernel_write(p->addr, &new_insn, len);
+	kcb->kprobe_status = status;
+	return 0;
+}
+NOKPROBE_SYMBOL(swap_instruction);
+
+void arch_arm_kprobe(struct kprobe *p)
+{
+	struct swap_insn_args args = {.p = p, .arm_kprobe = 1};
+
+	stop_machine(swap_instruction, &args, NULL);
+}
+NOKPROBE_SYMBOL(arch_arm_kprobe);
+
+void arch_disarm_kprobe(struct kprobe *p)
+{
+	struct swap_insn_args args = {.p = p, .arm_kprobe = 0};
+
+	stop_machine(swap_instruction, &args, NULL);
+}
+NOKPROBE_SYMBOL(arch_disarm_kprobe);
+
+void arch_remove_kprobe(struct kprobe *p)
+{
+	s390_free_insn_slot(p);
+}
+NOKPROBE_SYMBOL(arch_remove_kprobe);
+
+static void enable_singlestep(struct kprobe_ctlblk *kcb,
+			      struct pt_regs *regs,
+			      unsigned long ip)
+{
+	struct per_regs per_kprobe;
+
+	/* Set up the PER control registers %cr9-%cr11 */
+	per_kprobe.control = PER_EVENT_IFETCH;
+	per_kprobe.start = ip;
+	per_kprobe.end = ip;
+
+	/* Save control regs and psw mask */
+	__ctl_store(kcb->kprobe_saved_ctl, 9, 11);
+	kcb->kprobe_saved_imask = regs->psw.mask &
+		(PSW_MASK_PER | PSW_MASK_IO | PSW_MASK_EXT);
+
+	/* Set PER control regs, turns on single step for the given address */
+	__ctl_load(per_kprobe, 9, 11);
+	regs->psw.mask |= PSW_MASK_PER;
+	regs->psw.mask &= ~(PSW_MASK_IO | PSW_MASK_EXT);
+	regs->psw.addr = ip | PSW_ADDR_AMODE;
+}
+NOKPROBE_SYMBOL(enable_singlestep);
+
+static void disable_singlestep(struct kprobe_ctlblk *kcb,
+			       struct pt_regs *regs,
+			       unsigned long ip)
+{
+	/* Restore control regs and psw mask, set new psw address */
+	__ctl_load(kcb->kprobe_saved_ctl, 9, 11);
+	regs->psw.mask &= ~PSW_MASK_PER;
+	regs->psw.mask |= kcb->kprobe_saved_imask;
+	regs->psw.addr = ip | PSW_ADDR_AMODE;
+}
+NOKPROBE_SYMBOL(disable_singlestep);
+
+/*
+ * Activate a kprobe by storing its pointer to current_kprobe. The
+ * previous kprobe is stored in kcb->prev_kprobe. A stack of up to
+ * two kprobes can be active, see KPROBE_REENTER.
+ */
+static void push_kprobe(struct kprobe_ctlblk *kcb, struct kprobe *p)
+{
+	kcb->prev_kprobe.kp = __this_cpu_read(current_kprobe);
+	kcb->prev_kprobe.status = kcb->kprobe_status;
+	__this_cpu_write(current_kprobe, p);
+}
+NOKPROBE_SYMBOL(push_kprobe);
+
+/*
+ * Deactivate a kprobe by backing up to the previous state. If the
+ * current state is KPROBE_REENTER prev_kprobe.kp will be non-NULL,
+ * for any other state prev_kprobe.kp will be NULL.
+ */
+static void pop_kprobe(struct kprobe_ctlblk *kcb)
+{
+	__this_cpu_write(current_kprobe, kcb->prev_kprobe.kp);
+	kcb->kprobe_status = kcb->prev_kprobe.status;
+}
+NOKPROBE_SYMBOL(pop_kprobe);
+
+void arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs)
+{
+	ri->ret_addr = (kprobe_opcode_t *) regs->gprs[14];
+
+	/* Replace the return addr with trampoline addr */
+	regs->gprs[14] = (unsigned long) &kretprobe_trampoline;
+}
+NOKPROBE_SYMBOL(arch_prepare_kretprobe);
+
+static void kprobe_reenter_check(struct kprobe_ctlblk *kcb, struct kprobe *p)
+{
+	switch (kcb->kprobe_status) {
+	case KPROBE_HIT_SSDONE:
+	case KPROBE_HIT_ACTIVE:
+		kprobes_inc_nmissed_count(p);
+		break;
+	case KPROBE_HIT_SS:
+	case KPROBE_REENTER:
+	default:
+		/*
+		 * A kprobe on the code path to single step an instruction
+		 * is a BUG. The code path resides in the .kprobes.text
+		 * section and is executed with interrupts disabled.
+		 */
+		printk(KERN_EMERG "Invalid kprobe detected at %p.\n", p->addr);
+		dump_kprobe(p);
+		BUG();
+	}
+}
+NOKPROBE_SYMBOL(kprobe_reenter_check);
+
+static int kprobe_handler(struct pt_regs *regs)
+{
+	struct kprobe_ctlblk *kcb;
+	struct kprobe *p;
+
+	/*
+	 * We want to disable preemption for the entire duration of kprobe
+	 * processing. That includes the calls to the pre/post handlers
+	 * and single stepping the kprobe instruction.
+	 */
+	preempt_disable();
+	kcb = get_kprobe_ctlblk();
+	p = get_kprobe((void *)((regs->psw.addr & PSW_ADDR_INSN) - 2));
+
+	if (p) {
+		if (kprobe_running()) {
+			/*
+			 * We have hit a kprobe while another is still
+			 * active. This can happen in the pre and post
+			 * handler. Single step the instruction of the
+			 * new probe but do not call any handler function
+			 * of this secondary kprobe.
+			 * push_kprobe and pop_kprobe saves and restores
+			 * the currently active kprobe.
+			 */
+			kprobe_reenter_check(kcb, p);
+			push_kprobe(kcb, p);
+			kcb->kprobe_status = KPROBE_REENTER;
+		} else {
+			/*
+			 * If we have no pre-handler or it returned 0, we
+			 * continue with single stepping. If we have a
+			 * pre-handler and it returned non-zero, it prepped
+			 * for calling the break_handler below on re-entry
+			 * for jprobe processing, so get out doing nothing
+			 * more here.
+			 */
+			push_kprobe(kcb, p);
+			kcb->kprobe_status = KPROBE_HIT_ACTIVE;
+			if (p->pre_handler && p->pre_handler(p, regs))
+				return 1;
+			kcb->kprobe_status = KPROBE_HIT_SS;
+		}
+		enable_singlestep(kcb, regs, (unsigned long) p->ainsn.insn);
+		return 1;
+	} else if (kprobe_running()) {
+		p = __this_cpu_read(current_kprobe);
+		if (p->break_handler && p->break_handler(p, regs)) {
+			/*
+			 * Continuation after the jprobe completed and
+			 * caused the jprobe_return trap. The jprobe
+			 * break_handler "returns" to the original
+			 * function that still has the kprobe breakpoint
+			 * installed. We continue with single stepping.
+			 */
+			kcb->kprobe_status = KPROBE_HIT_SS;
+			enable_singlestep(kcb, regs,
+					  (unsigned long) p->ainsn.insn);
+			return 1;
+		} /* else:
+		   * No kprobe at this address and the current kprobe
+		   * has no break handler (no jprobe!). The kernel just
+		   * exploded, let the standard trap handler pick up the
+		   * pieces.
+		   */
+	} /* else:
+	   * No kprobe at this address and no active kprobe. The trap has
+	   * not been caused by a kprobe breakpoint. The race of breakpoint
+	   * vs. kprobe remove does not exist because on s390 as we use
+	   * stop_machine to arm/disarm the breakpoints.
+	   */
+	preempt_enable_no_resched();
+	return 0;
+}
+NOKPROBE_SYMBOL(kprobe_handler);
+
+/*
+ * Function return probe trampoline:
+ *	- init_kprobes() establishes a probepoint here
+ *	- When the probed function returns, this probe
+ *		causes the handlers to fire
+ */
+static void __used kretprobe_trampoline_holder(void)
+{
+	asm volatile(".global kretprobe_trampoline\n"
+		     "kretprobe_trampoline: bcr 0,0\n");
+}
+
+/*
+ * Called when the probe at kretprobe trampoline is hit
+ */
+static int trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs)
+{
+	struct kretprobe_instance *ri;
+	struct hlist_head *head, empty_rp;
+	struct hlist_node *tmp;
+	unsigned long flags, orig_ret_address;
+	unsigned long trampoline_address;
+	kprobe_opcode_t *correct_ret_addr;
+
+	INIT_HLIST_HEAD(&empty_rp);
+	kretprobe_hash_lock(current, &head, &flags);
+
+	/*
+	 * It is possible to have multiple instances associated with a given
+	 * task either because an multiple functions in the call path
+	 * have a return probe installed on them, and/or more than one return
+	 * return probe was registered for a target function.
+	 *
+	 * We can handle this because:
+	 *     - instances are always inserted at the head of the list
+	 *     - when multiple return probes are registered for the same
+	 *	 function, the first instance's ret_addr will point to the
+	 *	 real return address, and all the rest will point to
+	 *	 kretprobe_trampoline
+	 */
+	ri = NULL;
+	orig_ret_address = 0;
+	correct_ret_addr = NULL;
+	trampoline_address = (unsigned long) &kretprobe_trampoline;
+	hlist_for_each_entry_safe(ri, tmp, head, hlist) {
+		if (ri->task != current)
+			/* another task is sharing our hash bucket */
+			continue;
+
+		orig_ret_address = (unsigned long) ri->ret_addr;
+
+		if (orig_ret_address != trampoline_address)
+			/*
+			 * This is the real return address. Any other
+			 * instances associated with this task are for
+			 * other calls deeper on the call stack
+			 */
+			break;
+	}
+
+	kretprobe_assert(ri, orig_ret_address, trampoline_address);
+
+	correct_ret_addr = ri->ret_addr;
+	hlist_for_each_entry_safe(ri, tmp, head, hlist) {
+		if (ri->task != current)
+			/* another task is sharing our hash bucket */
+			continue;
+
+		orig_ret_address = (unsigned long) ri->ret_addr;
+
+		if (ri->rp && ri->rp->handler) {
+			ri->ret_addr = correct_ret_addr;
+			ri->rp->handler(ri, regs);
+		}
+
+		recycle_rp_inst(ri, &empty_rp);
+
+		if (orig_ret_address != trampoline_address)
+			/*
+			 * This is the real return address. Any other
+			 * instances associated with this task are for
+			 * other calls deeper on the call stack
+			 */
+			break;
+	}
+
+	regs->psw.addr = orig_ret_address | PSW_ADDR_AMODE;
+
+	pop_kprobe(get_kprobe_ctlblk());
+	kretprobe_hash_unlock(current, &flags);
+	preempt_enable_no_resched();
+
+	hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
+		hlist_del(&ri->hlist);
+		kfree(ri);
+	}
+	/*
+	 * By returning a non-zero value, we are telling
+	 * kprobe_handler() that we don't want the post_handler
+	 * to run (and have re-enabled preemption)
+	 */
+	return 1;
+}
+NOKPROBE_SYMBOL(trampoline_probe_handler);
+
+/*
+ * Called after single-stepping.  p->addr is the address of the
+ * instruction whose first byte has been replaced by the "breakpoint"
+ * instruction.  To avoid the SMP problems that can occur when we
+ * temporarily put back the original opcode to single-step, we
+ * single-stepped a copy of the instruction.  The address of this
+ * copy is p->ainsn.insn.
+ */
+static void resume_execution(struct kprobe *p, struct pt_regs *regs)
+{
+	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
+	unsigned long ip = regs->psw.addr & PSW_ADDR_INSN;
+	int fixup = probe_get_fixup_type(p->ainsn.insn);
+
+	/* Check if the kprobes location is an enabled ftrace caller */
+	if (p->ainsn.is_ftrace_insn) {
+		struct ftrace_insn *insn = (struct ftrace_insn *) p->addr;
+		struct ftrace_insn call_insn;
+
+		ftrace_generate_call_insn(&call_insn, (unsigned long) p->addr);
+		/*
+		 * A kprobe on an enabled ftrace call site actually single
+		 * stepped an unconditional branch (ftrace nop equivalent).
+		 * Now we need to fixup things and pretend that a brasl r0,...
+		 * was executed instead.
+		 */
+		if (insn->disp == KPROBE_ON_FTRACE_CALL) {
+			ip += call_insn.disp * 2 - MCOUNT_INSN_SIZE;
+			regs->gprs[0] = (unsigned long)p->addr + sizeof(*insn);
+		}
+	}
+
+	if (fixup & FIXUP_PSW_NORMAL)
+		ip += (unsigned long) p->addr - (unsigned long) p->ainsn.insn;
+
+	if (fixup & FIXUP_BRANCH_NOT_TAKEN) {
+		int ilen = insn_length(p->ainsn.insn[0] >> 8);
+		if (ip - (unsigned long) p->ainsn.insn == ilen)
+			ip = (unsigned long) p->addr + ilen;
+	}
+
+	if (fixup & FIXUP_RETURN_REGISTER) {
+		int reg = (p->ainsn.insn[0] & 0xf0) >> 4;
+		regs->gprs[reg] += (unsigned long) p->addr -
+				   (unsigned long) p->ainsn.insn;
+	}
+
+	disable_singlestep(kcb, regs, ip);
+}
+NOKPROBE_SYMBOL(resume_execution);
+
+static int post_kprobe_handler(struct pt_regs *regs)
+{
+	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
+	struct kprobe *p = kprobe_running();
+
+	if (!p)
+		return 0;
+
+	if (kcb->kprobe_status != KPROBE_REENTER && p->post_handler) {
+		kcb->kprobe_status = KPROBE_HIT_SSDONE;
+		p->post_handler(p, regs, 0);
+	}
+
+	resume_execution(p, regs);
+	pop_kprobe(kcb);
+	preempt_enable_no_resched();
+
+	/*
+	 * if somebody else is singlestepping across a probe point, psw mask
+	 * will have PER set, in which case, continue the remaining processing
+	 * of do_single_step, as if this is not a probe hit.
+	 */
+	if (regs->psw.mask & PSW_MASK_PER)
+		return 0;
+
+	return 1;
+}
+NOKPROBE_SYMBOL(post_kprobe_handler);
+
+static int kprobe_trap_handler(struct pt_regs *regs, int trapnr)
+{
+	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
+	struct kprobe *p = kprobe_running();
+	const struct exception_table_entry *entry;
+
+	switch(kcb->kprobe_status) {
+	case KPROBE_SWAP_INST:
+		/* We are here because the instruction replacement failed */
+		return 0;
+	case KPROBE_HIT_SS:
+	case KPROBE_REENTER:
+		/*
+		 * We are here because the instruction being single
+		 * stepped caused a page fault. We reset the current
+		 * kprobe and the nip points back to the probe address
+		 * and allow the page fault handler to continue as a
+		 * normal page fault.
+		 */
+		disable_singlestep(kcb, regs, (unsigned long) p->addr);
+		pop_kprobe(kcb);
+		preempt_enable_no_resched();
+		break;
+	case KPROBE_HIT_ACTIVE:
+	case KPROBE_HIT_SSDONE:
+		/*
+		 * We increment the nmissed count for accounting,
+		 * we can also use npre/npostfault count for accounting
+		 * these specific fault cases.
+		 */
+		kprobes_inc_nmissed_count(p);
+
+		/*
+		 * We come here because instructions in the pre/post
+		 * handler caused the page_fault, this could happen
+		 * if handler tries to access user space by
+		 * copy_from_user(), get_user() etc. Let the
+		 * user-specified handler try to fix it first.
+		 */
+		if (p->fault_handler && p->fault_handler(p, regs, trapnr))
+			return 1;
+
+		/*
+		 * In case the user-specified fault handler returned
+		 * zero, try to fix up.
+		 */
+		entry = search_exception_tables(regs->psw.addr & PSW_ADDR_INSN);
+		if (entry) {
+			regs->psw.addr = extable_fixup(entry) | PSW_ADDR_AMODE;
+			return 1;
+		}
+
+		/*
+		 * fixup_exception() could not handle it,
+		 * Let do_page_fault() fix it.
+		 */
+		break;
+	default:
+		break;
+	}
+	return 0;
+}
+NOKPROBE_SYMBOL(kprobe_trap_handler);
+
+int kprobe_fault_handler(struct pt_regs *regs, int trapnr)
+{
+	int ret;
+
+	if (regs->psw.mask & (PSW_MASK_IO | PSW_MASK_EXT))
+		local_irq_disable();
+	ret = kprobe_trap_handler(regs, trapnr);
+	if (regs->psw.mask & (PSW_MASK_IO | PSW_MASK_EXT))
+		local_irq_restore(regs->psw.mask & ~PSW_MASK_PER);
+	return ret;
+}
+NOKPROBE_SYMBOL(kprobe_fault_handler);
+
+/*
+ * Wrapper routine to for handling exceptions.
+ */
+int kprobe_exceptions_notify(struct notifier_block *self,
+			     unsigned long val, void *data)
+{
+	struct die_args *args = (struct die_args *) data;
+	struct pt_regs *regs = args->regs;
+	int ret = NOTIFY_DONE;
+
+	if (regs->psw.mask & (PSW_MASK_IO | PSW_MASK_EXT))
+		local_irq_disable();
+
+	switch (val) {
+	case DIE_BPT:
+		if (kprobe_handler(regs))
+			ret = NOTIFY_STOP;
+		break;
+	case DIE_SSTEP:
+		if (post_kprobe_handler(regs))
+			ret = NOTIFY_STOP;
+		break;
+	case DIE_TRAP:
+		if (!preemptible() && kprobe_running() &&
+		    kprobe_trap_handler(regs, args->trapnr))
+			ret = NOTIFY_STOP;
+		break;
+	default:
+		break;
+	}
+
+	if (regs->psw.mask & (PSW_MASK_IO | PSW_MASK_EXT))
+		local_irq_restore(regs->psw.mask & ~PSW_MASK_PER);
+
+	return ret;
+}
+NOKPROBE_SYMBOL(kprobe_exceptions_notify);
+
+int setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
+{
+	struct jprobe *jp = container_of(p, struct jprobe, kp);
+	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
+	unsigned long stack;
+
+	memcpy(&kcb->jprobe_saved_regs, regs, sizeof(struct pt_regs));
+
+	/* setup return addr to the jprobe handler routine */
+	regs->psw.addr = (unsigned long) jp->entry | PSW_ADDR_AMODE;
+	regs->psw.mask &= ~(PSW_MASK_IO | PSW_MASK_EXT);
+
+	/* r15 is the stack pointer */
+	stack = (unsigned long) regs->gprs[15];
+
+	memcpy(kcb->jprobes_stack, (void *) stack, MIN_STACK_SIZE(stack));
+	return 1;
+}
+NOKPROBE_SYMBOL(setjmp_pre_handler);
+
+void jprobe_return(void)
+{
+	asm volatile(".word 0x0002");
+}
+NOKPROBE_SYMBOL(jprobe_return);
+
+int longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
+{
+	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
+	unsigned long stack;
+
+	stack = (unsigned long) kcb->jprobe_saved_regs.gprs[15];
+
+	/* Put the regs back */
+	memcpy(regs, &kcb->jprobe_saved_regs, sizeof(struct pt_regs));
+	/* put the stack back */
+	memcpy((void *) stack, kcb->jprobes_stack, MIN_STACK_SIZE(stack));
+	preempt_enable_no_resched();
+	return 1;
+}
+NOKPROBE_SYMBOL(longjmp_break_handler);
+
+static struct kprobe trampoline = {
+	.addr = (kprobe_opcode_t *) &kretprobe_trampoline,
+	.pre_handler = trampoline_probe_handler
+};
+
+int __init arch_init_kprobes(void)
+{
+	return register_kprobe(&trampoline);
+}
+
+int arch_trampoline_kprobe(struct kprobe *p)
+{
+	return p->addr == (kprobe_opcode_t *) &kretprobe_trampoline;
+}
+NOKPROBE_SYMBOL(arch_trampoline_kprobe);
diff --git a/arch/s390/kernel/lgr.c b/arch/s390/kernel/lgr.c
new file mode 100644
index 000000000..6ea6d6933
--- /dev/null
+++ b/arch/s390/kernel/lgr.c
@@ -0,0 +1,186 @@
+/*
+ * 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 char lgr_page[PAGE_SIZE] __aligned(PAGE_SIZE);
+static struct lgr_info lgr_info_last;
+static struct lgr_info lgr_info_cur;
+static struct debug_info *lgr_dbf;
+
+/*
+ * 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 = (void *) lgr_page;
+
+	if (stsi(si, 1, 1, 1))
+		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 = (void *) lgr_page;
+
+	if (stsi(si, 2, 2, 2))
+		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 = (void *) lgr_page;
+	int i;
+
+	if (stsi(si, 3, 2, 2))
+		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)
+{
+	int level;
+
+	memset(lgr_info, 0, sizeof(*lgr_info));
+	stfle(lgr_info->stfle_fac_list, ARRAY_SIZE(lgr_info->stfle_fac_list));
+	level = stsi(NULL, 0, 0, 0);
+	lgr_info->level = level;
+	if (level >= 1)
+		lgr_stsi_1_1_1(lgr_info);
+	if (level >= 2)
+		lgr_stsi_2_2_2(lgr_info);
+	if (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_dbf = debug_register("lgr", 1, 1, sizeof(struct lgr_info));
+	if (!lgr_dbf)
+		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
new file mode 100644
index 000000000..fb0901ec4
--- /dev/null
+++ b/arch/s390/kernel/machine_kexec.c
@@ -0,0 +1,275 @@
+/*
+ * Copyright IBM Corp. 2005, 2011
+ *
+ * Author(s): Rolf Adelsberger,
+ *	      Heiko Carstens <heiko.carstens@de.ibm.com>
+ *	      Michael Holzheu <holzheu@linux.vnet.ibm.com>
+ */
+
+#include <linux/device.h>
+#include <linux/mm.h>
+#include <linux/kexec.h>
+#include <linux/delay.h>
+#include <linux/reboot.h>
+#include <linux/ftrace.h>
+#include <linux/debug_locks.h>
+#include <linux/suspend.h>
+#include <asm/cio.h>
+#include <asm/setup.h>
+#include <asm/pgtable.h>
+#include <asm/pgalloc.h>
+#include <asm/smp.h>
+#include <asm/reset.h>
+#include <asm/ipl.h>
+#include <asm/diag.h>
+#include <asm/elf.h>
+#include <asm/asm-offsets.h>
+#include <asm/os_info.h>
+#include <asm/switch_to.h>
+
+typedef void (*relocate_kernel_t)(kimage_entry_t *, unsigned long);
+
+extern const unsigned char relocate_kernel[];
+extern const unsigned long long relocate_kernel_len;
+
+#ifdef CONFIG_CRASH_DUMP
+
+/*
+ * Create ELF notes for one CPU
+ */
+static void add_elf_notes(int cpu)
+{
+	struct save_area *sa = (void *) 4608 + store_prefix();
+	void *ptr;
+
+	memcpy((void *) (4608UL + sa->pref_reg), sa, sizeof(*sa));
+	ptr = (u64 *) per_cpu_ptr(crash_notes, cpu);
+	ptr = fill_cpu_elf_notes(ptr, sa, NULL);
+	memset(ptr, 0, sizeof(struct elf_note));
+}
+
+/*
+ * Initialize CPU ELF notes
+ */
+static void setup_regs(void)
+{
+	unsigned long sa = S390_lowcore.prefixreg_save_area + SAVE_AREA_BASE;
+	struct _lowcore *lc;
+	int cpu, this_cpu;
+
+	/* Get lowcore pointer from store status of this CPU (absolute zero) */
+	lc = (struct _lowcore *)(unsigned long)S390_lowcore.prefixreg_save_area;
+	this_cpu = smp_find_processor_id(stap());
+	add_elf_notes(this_cpu);
+	for_each_online_cpu(cpu) {
+		if (cpu == this_cpu)
+			continue;
+		if (smp_store_status(cpu))
+			continue;
+		add_elf_notes(cpu);
+	}
+	if (MACHINE_HAS_VX)
+		save_vx_regs_safe((void *) lc->vector_save_area_addr);
+	/* Copy dump CPU store status info to absolute zero */
+	memcpy((void *) SAVE_AREA_BASE, (void *) sa, sizeof(struct save_area));
+}
+
+/*
+ * PM notifier callback for kdump
+ */
+static int machine_kdump_pm_cb(struct notifier_block *nb, unsigned long action,
+			       void *ptr)
+{
+	switch (action) {
+	case PM_SUSPEND_PREPARE:
+	case PM_HIBERNATION_PREPARE:
+		if (crashk_res.start)
+			crash_map_reserved_pages();
+		break;
+	case PM_POST_SUSPEND:
+	case PM_POST_HIBERNATION:
+		if (crashk_res.start)
+			crash_unmap_reserved_pages();
+		break;
+	default:
+		return NOTIFY_DONE;
+	}
+	return NOTIFY_OK;
+}
+
+static int __init machine_kdump_pm_init(void)
+{
+	pm_notifier(machine_kdump_pm_cb, 0);
+	return 0;
+}
+arch_initcall(machine_kdump_pm_init);
+
+/*
+ * Start kdump: We expect here that a store status has been done on our CPU
+ */
+static void __do_machine_kdump(void *image)
+{
+	int (*start_kdump)(int) = (void *)((struct kimage *) image)->start;
+
+	__load_psw_mask(PSW_MASK_BASE | PSW_DEFAULT_KEY | PSW_MASK_EA | PSW_MASK_BA);
+	start_kdump(1);
+}
+#endif
+
+/*
+ * Check if kdump checksums are valid: We call purgatory with parameter "0"
+ */
+static int kdump_csum_valid(struct kimage *image)
+{
+#ifdef CONFIG_CRASH_DUMP
+	int (*start_kdump)(int) = (void *)image->start;
+	int rc;
+
+	__arch_local_irq_stnsm(0xfb); /* disable DAT */
+	rc = start_kdump(0);
+	__arch_local_irq_stosm(0x04); /* enable DAT */
+	return rc ? 0 : -EINVAL;
+#else
+	return -EINVAL;
+#endif
+}
+
+/*
+ * Map or unmap crashkernel memory
+ */
+static void crash_map_pages(int enable)
+{
+	unsigned long size = resource_size(&crashk_res);
+
+	BUG_ON(crashk_res.start % KEXEC_CRASH_MEM_ALIGN ||
+	       size % KEXEC_CRASH_MEM_ALIGN);
+	if (enable)
+		vmem_add_mapping(crashk_res.start, size);
+	else {
+		vmem_remove_mapping(crashk_res.start, size);
+		if (size)
+			os_info_crashkernel_add(crashk_res.start, size);
+		else
+			os_info_crashkernel_add(0, 0);
+	}
+}
+
+/*
+ * Map crashkernel memory
+ */
+void crash_map_reserved_pages(void)
+{
+	crash_map_pages(1);
+}
+
+/*
+ * Unmap crashkernel memory
+ */
+void crash_unmap_reserved_pages(void)
+{
+	crash_map_pages(0);
+}
+
+/*
+ * Give back memory to hypervisor before new kdump is loaded
+ */
+static int machine_kexec_prepare_kdump(void)
+{
+#ifdef CONFIG_CRASH_DUMP
+	if (MACHINE_IS_VM)
+		diag10_range(PFN_DOWN(crashk_res.start),
+			     PFN_DOWN(crashk_res.end - crashk_res.start + 1));
+	return 0;
+#else
+	return -EINVAL;
+#endif
+}
+
+int machine_kexec_prepare(struct kimage *image)
+{
+	void *reboot_code_buffer;
+
+	/* Can't replace kernel image since it is read-only. */
+	if (ipl_flags & IPL_NSS_VALID)
+		return -EOPNOTSUPP;
+
+	if (image->type == KEXEC_TYPE_CRASH)
+		return machine_kexec_prepare_kdump();
+
+	/* We don't support anything but the default image type for now. */
+	if (image->type != KEXEC_TYPE_DEFAULT)
+		return -EINVAL;
+
+	/* Get the destination where the assembler code should be copied to.*/
+	reboot_code_buffer = (void *) page_to_phys(image->control_code_page);
+
+	/* Then copy it */
+	memcpy(reboot_code_buffer, relocate_kernel, relocate_kernel_len);
+	return 0;
+}
+
+void machine_kexec_cleanup(struct kimage *image)
+{
+}
+
+void arch_crash_save_vmcoreinfo(void)
+{
+	VMCOREINFO_SYMBOL(lowcore_ptr);
+	VMCOREINFO_SYMBOL(high_memory);
+	VMCOREINFO_LENGTH(lowcore_ptr, NR_CPUS);
+}
+
+void machine_shutdown(void)
+{
+}
+
+void machine_crash_shutdown(struct pt_regs *regs)
+{
+}
+
+/*
+ * Do normal kexec
+ */
+static void __do_machine_kexec(void *data)
+{
+	relocate_kernel_t data_mover;
+	struct kimage *image = data;
+
+	data_mover = (relocate_kernel_t) page_to_phys(image->control_code_page);
+
+	/* Call the moving routine */
+	(*data_mover)(&image->head, image->start);
+}
+
+/*
+ * Reset system and call either kdump or normal kexec
+ */
+static void __machine_kexec(void *data)
+{
+	__arch_local_irq_stosm(0x04); /* enable DAT */
+	pfault_fini();
+	tracing_off();
+	debug_locks_off();
+#ifdef CONFIG_CRASH_DUMP
+	if (((struct kimage *) data)->type == KEXEC_TYPE_CRASH) {
+
+		lgr_info_log();
+		s390_reset_system(setup_regs, __do_machine_kdump, data);
+	} else
+#endif
+		s390_reset_system(NULL, __do_machine_kexec, data);
+	disabled_wait((unsigned long) __builtin_return_address(0));
+}
+
+/*
+ * Do either kdump or normal kexec. In case of kdump we first ask
+ * purgatory, if kdump checksums are valid.
+ */
+void machine_kexec(struct kimage *image)
+{
+	if (image->type == KEXEC_TYPE_CRASH && !kdump_csum_valid(image))
+		return;
+	tracer_disable();
+	smp_send_stop();
+	smp_call_ipl_cpu(__machine_kexec, image);
+}
diff --git a/arch/s390/kernel/mcount.S b/arch/s390/kernel/mcount.S
new file mode 100644
index 000000000..e499370fb
--- /dev/null
+++ b/arch/s390/kernel/mcount.S
@@ -0,0 +1,82 @@
+/*
+ * Copyright IBM Corp. 2008, 2009
+ *
+ *   Author(s): Heiko Carstens <heiko.carstens@de.ibm.com>,
+ *
+ */
+
+#include <linux/linkage.h>
+#include <asm/asm-offsets.h>
+#include <asm/ftrace.h>
+#include <asm/ptrace.h>
+
+	.section .kprobes.text, "ax"
+
+ENTRY(ftrace_stub)
+	br	%r14
+
+#define STACK_FRAME_SIZE  (STACK_FRAME_OVERHEAD + __PT_SIZE)
+#define STACK_PTREGS	  (STACK_FRAME_OVERHEAD)
+#define STACK_PTREGS_GPRS (STACK_PTREGS + __PT_GPRS)
+#define STACK_PTREGS_PSW  (STACK_PTREGS + __PT_PSW)
+
+ENTRY(_mcount)
+	br	%r14
+
+ENTRY(ftrace_caller)
+	.globl	ftrace_regs_caller
+	.set	ftrace_regs_caller,ftrace_caller
+	lgr	%r1,%r15
+#ifndef CC_USING_HOTPATCH
+	aghi	%r0,MCOUNT_RETURN_FIXUP
+#endif
+	aghi	%r15,-STACK_FRAME_SIZE
+	stg	%r1,__SF_BACKCHAIN(%r15)
+	stg	%r1,(STACK_PTREGS_GPRS+15*8)(%r15)
+	stg	%r0,(STACK_PTREGS_PSW+8)(%r15)
+	stmg	%r2,%r14,(STACK_PTREGS_GPRS+2*8)(%r15)
+#ifdef CONFIG_HAVE_MARCH_Z196_FEATURES
+	aghik	%r2,%r0,-MCOUNT_INSN_SIZE
+	lgrl	%r4,function_trace_op
+	lgrl	%r1,ftrace_trace_function
+#else
+	lgr	%r2,%r0
+	aghi	%r2,-MCOUNT_INSN_SIZE
+	larl	%r4,function_trace_op
+	lg	%r4,0(%r4)
+	larl	%r1,ftrace_trace_function
+	lg	%r1,0(%r1)
+#endif
+	lgr	%r3,%r14
+	la	%r5,STACK_PTREGS(%r15)
+	basr	%r14,%r1
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+# The j instruction gets runtime patched to a nop instruction.
+# See ftrace_enable_ftrace_graph_caller.
+ENTRY(ftrace_graph_caller)
+	j	ftrace_graph_caller_end
+	lg	%r2,(STACK_PTREGS_GPRS+14*8)(%r15)
+	lg	%r3,(STACK_PTREGS_PSW+8)(%r15)
+	brasl	%r14,prepare_ftrace_return
+	stg	%r2,(STACK_PTREGS_GPRS+14*8)(%r15)
+ftrace_graph_caller_end:
+	.globl	ftrace_graph_caller_end
+#endif
+	lg	%r1,(STACK_PTREGS_PSW+8)(%r15)
+	lmg	%r2,%r15,(STACK_PTREGS_GPRS+2*8)(%r15)
+	br	%r1
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+
+ENTRY(return_to_handler)
+	stmg	%r2,%r5,32(%r15)
+	lgr	%r1,%r15
+	aghi	%r15,-STACK_FRAME_OVERHEAD
+	stg	%r1,__SF_BACKCHAIN(%r15)
+	brasl	%r14,ftrace_return_to_handler
+	aghi	%r15,STACK_FRAME_OVERHEAD
+	lgr	%r14,%r2
+	lmg	%r2,%r5,32(%r15)
+	br	%r14
+
+#endif
diff --git a/arch/s390/kernel/module.c b/arch/s390/kernel/module.c
new file mode 100644
index 000000000..0c1a67931
--- /dev/null
+++ b/arch/s390/kernel/module.c
@@ -0,0 +1,431 @@
+/*
+ *  Kernel module help for s390.
+ *
+ *  S390 version
+ *    Copyright IBM Corp. 2002, 2003
+ *    Author(s): Arnd Bergmann (arndb@de.ibm.com)
+ *		 Martin Schwidefsky (schwidefsky@de.ibm.com)
+ *
+ *  based on i386 version
+ *    Copyright (C) 2001 Rusty Russell.
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 2 of the License, or
+ *  (at your option) any later version.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to the Free Software
+ *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+#include <linux/module.h>
+#include <linux/elf.h>
+#include <linux/vmalloc.h>
+#include <linux/fs.h>
+#include <linux/string.h>
+#include <linux/kernel.h>
+#include <linux/moduleloader.h>
+#include <linux/bug.h>
+
+#if 0
+#define DEBUGP printk
+#else
+#define DEBUGP(fmt , ...)
+#endif
+
+#define PLT_ENTRY_SIZE 20
+
+void *module_alloc(unsigned long size)
+{
+	if (PAGE_ALIGN(size) > MODULES_LEN)
+		return NULL;
+	return __vmalloc_node_range(size, 1, MODULES_VADDR, MODULES_END,
+				    GFP_KERNEL, PAGE_KERNEL, 0, NUMA_NO_NODE,
+				    __builtin_return_address(0));
+}
+
+void module_arch_freeing_init(struct module *mod)
+{
+	vfree(mod->arch.syminfo);
+	mod->arch.syminfo = NULL;
+}
+
+static void check_rela(Elf_Rela *rela, struct module *me)
+{
+	struct mod_arch_syminfo *info;
+
+	info = me->arch.syminfo + ELF_R_SYM (rela->r_info);
+	switch (ELF_R_TYPE (rela->r_info)) {
+	case R_390_GOT12:	/* 12 bit GOT offset.  */
+	case R_390_GOT16:	/* 16 bit GOT offset.  */
+	case R_390_GOT20:	/* 20 bit GOT offset.  */
+	case R_390_GOT32:	/* 32 bit GOT offset.  */
+	case R_390_GOT64:	/* 64 bit GOT offset.  */
+	case R_390_GOTENT:	/* 32 bit PC rel. to GOT entry shifted by 1. */
+	case R_390_GOTPLT12:	/* 12 bit offset to jump slot.	*/
+	case R_390_GOTPLT16:	/* 16 bit offset to jump slot.  */
+	case R_390_GOTPLT20:	/* 20 bit offset to jump slot.  */
+	case R_390_GOTPLT32:	/* 32 bit offset to jump slot.  */
+	case R_390_GOTPLT64:	/* 64 bit offset to jump slot.	*/
+	case R_390_GOTPLTENT:	/* 32 bit rel. offset to jump slot >> 1. */
+		if (info->got_offset == -1UL) {
+			info->got_offset = me->arch.got_size;
+			me->arch.got_size += sizeof(void*);
+		}
+		break;
+	case R_390_PLT16DBL:	/* 16 bit PC rel. PLT shifted by 1.  */
+	case R_390_PLT32DBL:	/* 32 bit PC rel. PLT shifted by 1.  */
+	case R_390_PLT32:	/* 32 bit PC relative PLT address.  */
+	case R_390_PLT64:	/* 64 bit PC relative PLT address.  */
+	case R_390_PLTOFF16:	/* 16 bit offset from GOT to PLT. */
+	case R_390_PLTOFF32:	/* 32 bit offset from GOT to PLT. */
+	case R_390_PLTOFF64:	/* 16 bit offset from GOT to PLT. */
+		if (info->plt_offset == -1UL) {
+			info->plt_offset = me->arch.plt_size;
+			me->arch.plt_size += PLT_ENTRY_SIZE;
+		}
+		break;
+	case R_390_COPY:
+	case R_390_GLOB_DAT:
+	case R_390_JMP_SLOT:
+	case R_390_RELATIVE:
+		/* Only needed if we want to support loading of 
+		   modules linked with -shared. */
+		break;
+	}
+}
+
+/*
+ * Account for GOT and PLT relocations. We can't add sections for
+ * got and plt but we can increase the core module size.
+ */
+int module_frob_arch_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs,
+			      char *secstrings, struct module *me)
+{
+	Elf_Shdr *symtab;
+	Elf_Sym *symbols;
+	Elf_Rela *rela;
+	char *strings;
+	int nrela, i, j;
+
+	/* Find symbol table and string table. */
+	symtab = NULL;
+	for (i = 0; i < hdr->e_shnum; i++)
+		switch (sechdrs[i].sh_type) {
+		case SHT_SYMTAB:
+			symtab = sechdrs + i;
+			break;
+		}
+	if (!symtab) {
+		printk(KERN_ERR "module %s: no symbol table\n", me->name);
+		return -ENOEXEC;
+	}
+
+	/* Allocate one syminfo structure per symbol. */
+	me->arch.nsyms = symtab->sh_size / sizeof(Elf_Sym);
+	me->arch.syminfo = vmalloc(me->arch.nsyms *
+				   sizeof(struct mod_arch_syminfo));
+	if (!me->arch.syminfo)
+		return -ENOMEM;
+	symbols = (void *) hdr + symtab->sh_offset;
+	strings = (void *) hdr + sechdrs[symtab->sh_link].sh_offset;
+	for (i = 0; i < me->arch.nsyms; i++) {
+		if (symbols[i].st_shndx == SHN_UNDEF &&
+		    strcmp(strings + symbols[i].st_name,
+			   "_GLOBAL_OFFSET_TABLE_") == 0)
+			/* "Define" it as absolute. */
+			symbols[i].st_shndx = SHN_ABS;
+		me->arch.syminfo[i].got_offset = -1UL;
+		me->arch.syminfo[i].plt_offset = -1UL;
+		me->arch.syminfo[i].got_initialized = 0;
+		me->arch.syminfo[i].plt_initialized = 0;
+	}
+
+	/* Search for got/plt relocations. */
+	me->arch.got_size = me->arch.plt_size = 0;
+	for (i = 0; i < hdr->e_shnum; i++) {
+		if (sechdrs[i].sh_type != SHT_RELA)
+			continue;
+		nrela = sechdrs[i].sh_size / sizeof(Elf_Rela);
+		rela = (void *) hdr + sechdrs[i].sh_offset;
+		for (j = 0; j < nrela; j++)
+			check_rela(rela + j, me);
+	}
+
+	/* Increase core size by size of got & plt and set start
+	   offsets for got and plt. */
+	me->core_size = ALIGN(me->core_size, 4);
+	me->arch.got_offset = me->core_size;
+	me->core_size += me->arch.got_size;
+	me->arch.plt_offset = me->core_size;
+	me->core_size += me->arch.plt_size;
+	return 0;
+}
+
+static int apply_rela_bits(Elf_Addr loc, Elf_Addr val,
+			   int sign, int bits, int shift)
+{
+	unsigned long umax;
+	long min, max;
+
+	if (val & ((1UL << shift) - 1))
+		return -ENOEXEC;
+	if (sign) {
+		val = (Elf_Addr)(((long) val) >> shift);
+		min = -(1L << (bits - 1));
+		max = (1L << (bits - 1)) - 1;
+		if ((long) val < min || (long) val > max)
+			return -ENOEXEC;
+	} else {
+		val >>= shift;
+		umax = ((1UL << (bits - 1)) << 1) - 1;
+		if ((unsigned long) val > umax)
+			return -ENOEXEC;
+	}
+
+	if (bits == 8)
+		*(unsigned char *) loc = val;
+	else if (bits == 12)
+		*(unsigned short *) loc = (val & 0xfff) |
+			(*(unsigned short *) loc & 0xf000);
+	else if (bits == 16)
+		*(unsigned short *) loc = val;
+	else if (bits == 20)
+		*(unsigned int *) loc = (val & 0xfff) << 16 |
+			(val & 0xff000) >> 4 |
+			(*(unsigned int *) loc & 0xf00000ff);
+	else if (bits == 32)
+		*(unsigned int *) loc = val;
+	else if (bits == 64)
+		*(unsigned long *) loc = val;
+	return 0;
+}
+
+static int apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab,
+		      const char *strtab, struct module *me)
+{
+	struct mod_arch_syminfo *info;
+	Elf_Addr loc, val;
+	int r_type, r_sym;
+	int rc = -ENOEXEC;
+
+	/* This is where to make the change */
+	loc = base + rela->r_offset;
+	/* This is the symbol it is referring to.  Note that all
+	   undefined symbols have been resolved.  */
+	r_sym = ELF_R_SYM(rela->r_info);
+	r_type = ELF_R_TYPE(rela->r_info);
+	info = me->arch.syminfo + r_sym;
+	val = symtab[r_sym].st_value;
+
+	switch (r_type) {
+	case R_390_NONE:	/* No relocation.  */
+		rc = 0;
+		break;
+	case R_390_8:		/* Direct 8 bit.   */
+	case R_390_12:		/* Direct 12 bit.  */
+	case R_390_16:		/* Direct 16 bit.  */
+	case R_390_20:		/* Direct 20 bit.  */
+	case R_390_32:		/* Direct 32 bit.  */
+	case R_390_64:		/* Direct 64 bit.  */
+		val += rela->r_addend;
+		if (r_type == R_390_8)
+			rc = apply_rela_bits(loc, val, 0, 8, 0);
+		else if (r_type == R_390_12)
+			rc = apply_rela_bits(loc, val, 0, 12, 0);
+		else if (r_type == R_390_16)
+			rc = apply_rela_bits(loc, val, 0, 16, 0);
+		else if (r_type == R_390_20)
+			rc = apply_rela_bits(loc, val, 1, 20, 0);
+		else if (r_type == R_390_32)
+			rc = apply_rela_bits(loc, val, 0, 32, 0);
+		else if (r_type == R_390_64)
+			rc = apply_rela_bits(loc, val, 0, 64, 0);
+		break;
+	case R_390_PC16:	/* PC relative 16 bit.  */
+	case R_390_PC16DBL:	/* PC relative 16 bit shifted by 1.  */
+	case R_390_PC32DBL:	/* PC relative 32 bit shifted by 1.  */
+	case R_390_PC32:	/* PC relative 32 bit.  */
+	case R_390_PC64:	/* PC relative 64 bit.	*/
+		val += rela->r_addend - loc;
+		if (r_type == R_390_PC16)
+			rc = apply_rela_bits(loc, val, 1, 16, 0);
+		else if (r_type == R_390_PC16DBL)
+			rc = apply_rela_bits(loc, val, 1, 16, 1);
+		else if (r_type == R_390_PC32DBL)
+			rc = apply_rela_bits(loc, val, 1, 32, 1);
+		else if (r_type == R_390_PC32)
+			rc = apply_rela_bits(loc, val, 1, 32, 0);
+		else if (r_type == R_390_PC64)
+			rc = apply_rela_bits(loc, val, 1, 64, 0);
+		break;
+	case R_390_GOT12:	/* 12 bit GOT offset.  */
+	case R_390_GOT16:	/* 16 bit GOT offset.  */
+	case R_390_GOT20:	/* 20 bit GOT offset.  */
+	case R_390_GOT32:	/* 32 bit GOT offset.  */
+	case R_390_GOT64:	/* 64 bit GOT offset.  */
+	case R_390_GOTENT:	/* 32 bit PC rel. to GOT entry shifted by 1. */
+	case R_390_GOTPLT12:	/* 12 bit offset to jump slot.	*/
+	case R_390_GOTPLT20:	/* 20 bit offset to jump slot.  */
+	case R_390_GOTPLT16:	/* 16 bit offset to jump slot.  */
+	case R_390_GOTPLT32:	/* 32 bit offset to jump slot.  */
+	case R_390_GOTPLT64:	/* 64 bit offset to jump slot.	*/
+	case R_390_GOTPLTENT:	/* 32 bit rel. offset to jump slot >> 1. */
+		if (info->got_initialized == 0) {
+			Elf_Addr *gotent;
+
+			gotent = me->module_core + me->arch.got_offset +
+				info->got_offset;
+			*gotent = val;
+			info->got_initialized = 1;
+		}
+		val = info->got_offset + rela->r_addend;
+		if (r_type == R_390_GOT12 ||
+		    r_type == R_390_GOTPLT12)
+			rc = apply_rela_bits(loc, val, 0, 12, 0);
+		else if (r_type == R_390_GOT16 ||
+			 r_type == R_390_GOTPLT16)
+			rc = apply_rela_bits(loc, val, 0, 16, 0);
+		else if (r_type == R_390_GOT20 ||
+			 r_type == R_390_GOTPLT20)
+			rc = apply_rela_bits(loc, val, 1, 20, 0);
+		else if (r_type == R_390_GOT32 ||
+			 r_type == R_390_GOTPLT32)
+			rc = apply_rela_bits(loc, val, 0, 32, 0);
+		else if (r_type == R_390_GOT64 ||
+			 r_type == R_390_GOTPLT64)
+			rc = apply_rela_bits(loc, val, 0, 64, 0);
+		else if (r_type == R_390_GOTENT ||
+			 r_type == R_390_GOTPLTENT) {
+			val += (Elf_Addr) me->module_core - loc;
+			rc = apply_rela_bits(loc, val, 1, 32, 1);
+		}
+		break;
+	case R_390_PLT16DBL:	/* 16 bit PC rel. PLT shifted by 1.  */
+	case R_390_PLT32DBL:	/* 32 bit PC rel. PLT shifted by 1.  */
+	case R_390_PLT32:	/* 32 bit PC relative PLT address.  */
+	case R_390_PLT64:	/* 64 bit PC relative PLT address.  */
+	case R_390_PLTOFF16:	/* 16 bit offset from GOT to PLT. */
+	case R_390_PLTOFF32:	/* 32 bit offset from GOT to PLT. */
+	case R_390_PLTOFF64:	/* 16 bit offset from GOT to PLT. */
+		if (info->plt_initialized == 0) {
+			unsigned int *ip;
+			ip = me->module_core + me->arch.plt_offset +
+				info->plt_offset;
+			ip[0] = 0x0d10e310; /* basr 1,0; lg 1,10(1); br 1 */
+			ip[1] = 0x100a0004;
+			ip[2] = 0x07f10000;
+			ip[3] = (unsigned int) (val >> 32);
+			ip[4] = (unsigned int) val;
+			info->plt_initialized = 1;
+		}
+		if (r_type == R_390_PLTOFF16 ||
+		    r_type == R_390_PLTOFF32 ||
+		    r_type == R_390_PLTOFF64)
+			val = me->arch.plt_offset - me->arch.got_offset +
+				info->plt_offset + rela->r_addend;
+		else {
+			if (!((r_type == R_390_PLT16DBL &&
+			       val - loc + 0xffffUL < 0x1ffffeUL) ||
+			      (r_type == R_390_PLT32DBL &&
+			       val - loc + 0xffffffffULL < 0x1fffffffeULL)))
+				val = (Elf_Addr) me->module_core +
+					me->arch.plt_offset +
+					info->plt_offset;
+			val += rela->r_addend - loc;
+		}
+		if (r_type == R_390_PLT16DBL)
+			rc = apply_rela_bits(loc, val, 1, 16, 1);
+		else if (r_type == R_390_PLTOFF16)
+			rc = apply_rela_bits(loc, val, 0, 16, 0);
+		else if (r_type == R_390_PLT32DBL)
+			rc = apply_rela_bits(loc, val, 1, 32, 1);
+		else if (r_type == R_390_PLT32 ||
+			 r_type == R_390_PLTOFF32)
+			rc = apply_rela_bits(loc, val, 0, 32, 0);
+		else if (r_type == R_390_PLT64 ||
+			 r_type == R_390_PLTOFF64)
+			rc = apply_rela_bits(loc, val, 0, 64, 0);
+		break;
+	case R_390_GOTOFF16:	/* 16 bit offset to GOT.  */
+	case R_390_GOTOFF32:	/* 32 bit offset to GOT.  */
+	case R_390_GOTOFF64:	/* 64 bit offset to GOT. */
+		val = val + rela->r_addend -
+			((Elf_Addr) me->module_core + me->arch.got_offset);
+		if (r_type == R_390_GOTOFF16)
+			rc = apply_rela_bits(loc, val, 0, 16, 0);
+		else if (r_type == R_390_GOTOFF32)
+			rc = apply_rela_bits(loc, val, 0, 32, 0);
+		else if (r_type == R_390_GOTOFF64)
+			rc = apply_rela_bits(loc, val, 0, 64, 0);
+		break;
+	case R_390_GOTPC:	/* 32 bit PC relative offset to GOT. */
+	case R_390_GOTPCDBL:	/* 32 bit PC rel. off. to GOT shifted by 1. */
+		val = (Elf_Addr) me->module_core + me->arch.got_offset +
+			rela->r_addend - loc;
+		if (r_type == R_390_GOTPC)
+			rc = apply_rela_bits(loc, val, 1, 32, 0);
+		else if (r_type == R_390_GOTPCDBL)
+			rc = apply_rela_bits(loc, val, 1, 32, 1);
+		break;
+	case R_390_COPY:
+	case R_390_GLOB_DAT:	/* Create GOT entry.  */
+	case R_390_JMP_SLOT:	/* Create PLT entry.  */
+	case R_390_RELATIVE:	/* Adjust by program base.  */
+		/* Only needed if we want to support loading of 
+		   modules linked with -shared. */
+		return -ENOEXEC;
+	default:
+		printk(KERN_ERR "module %s: unknown relocation: %u\n",
+		       me->name, r_type);
+		return -ENOEXEC;
+	}
+	if (rc) {
+		printk(KERN_ERR "module %s: relocation error for symbol %s "
+		       "(r_type %i, value 0x%lx)\n",
+		       me->name, strtab + symtab[r_sym].st_name,
+		       r_type, (unsigned long) val);
+		return rc;
+	}
+	return 0;
+}
+
+int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab,
+		       unsigned int symindex, unsigned int relsec,
+		       struct module *me)
+{
+	Elf_Addr base;
+	Elf_Sym *symtab;
+	Elf_Rela *rela;
+	unsigned long i, n;
+	int rc;
+
+	DEBUGP("Applying relocate section %u to %u\n",
+	       relsec, sechdrs[relsec].sh_info);
+	base = sechdrs[sechdrs[relsec].sh_info].sh_addr;
+	symtab = (Elf_Sym *) sechdrs[symindex].sh_addr;
+	rela = (Elf_Rela *) sechdrs[relsec].sh_addr;
+	n = sechdrs[relsec].sh_size / sizeof(Elf_Rela);
+
+	for (i = 0; i < n; i++, rela++) {
+		rc = apply_rela(rela, base, symtab, strtab, me);
+		if (rc)
+			return rc;
+	}
+	return 0;
+}
+
+int module_finalize(const Elf_Ehdr *hdr,
+		    const Elf_Shdr *sechdrs,
+		    struct module *me)
+{
+	jump_label_apply_nops(me);
+	vfree(me->arch.syminfo);
+	me->arch.syminfo = NULL;
+	return 0;
+}
diff --git a/arch/s390/kernel/nmi.c b/arch/s390/kernel/nmi.c
new file mode 100644
index 000000000..505c17c0a
--- /dev/null
+++ b/arch/s390/kernel/nmi.c
@@ -0,0 +1,352 @@
+/*
+ *   Machine check handler
+ *
+ *    Copyright IBM Corp. 2000, 2009
+ *    Author(s): Ingo Adlung <adlung@de.ibm.com>,
+ *		 Martin Schwidefsky <schwidefsky@de.ibm.com>,
+ *		 Cornelia Huck <cornelia.huck@de.ibm.com>,
+ *		 Heiko Carstens <heiko.carstens@de.ibm.com>,
+ */
+
+#include <linux/kernel_stat.h>
+#include <linux/init.h>
+#include <linux/errno.h>
+#include <linux/hardirq.h>
+#include <linux/time.h>
+#include <linux/module.h>
+#include <asm/lowcore.h>
+#include <asm/smp.h>
+#include <asm/etr.h>
+#include <asm/cputime.h>
+#include <asm/nmi.h>
+#include <asm/crw.h>
+#include <asm/switch_to.h>
+
+struct mcck_struct {
+	int kill_task;
+	int channel_report;
+	int warning;
+	unsigned long long mcck_code;
+};
+
+static DEFINE_PER_CPU(struct mcck_struct, cpu_mcck);
+
+static void s390_handle_damage(char *msg)
+{
+	smp_send_stop();
+	disabled_wait((unsigned long) __builtin_return_address(0));
+	while (1);
+}
+
+/*
+ * Main machine check handler function. Will be called with interrupts enabled
+ * or disabled and machine checks enabled or disabled.
+ */
+void s390_handle_mcck(void)
+{
+	unsigned long flags;
+	struct mcck_struct mcck;
+
+	/*
+	 * Disable machine checks and get the current state of accumulated
+	 * machine checks. Afterwards delete the old state and enable machine
+	 * checks again.
+	 */
+	local_irq_save(flags);
+	local_mcck_disable();
+	mcck = *this_cpu_ptr(&cpu_mcck);
+	memset(this_cpu_ptr(&cpu_mcck), 0, sizeof(mcck));
+	clear_cpu_flag(CIF_MCCK_PENDING);
+	local_mcck_enable();
+	local_irq_restore(flags);
+
+	if (mcck.channel_report)
+		crw_handle_channel_report();
+	/*
+	 * A warning may remain for a prolonged period on the bare iron.
+	 * (actually until the machine is powered off, or the problem is gone)
+	 * So we just stop listening for the WARNING MCH and avoid continuously
+	 * being interrupted.  One caveat is however, that we must do this per
+	 * processor and cannot use the smp version of ctl_clear_bit().
+	 * On VM we only get one interrupt per virtally presented machinecheck.
+	 * Though one suffices, we may get one interrupt per (virtual) cpu.
+	 */
+	if (mcck.warning) {	/* WARNING pending ? */
+		static int mchchk_wng_posted = 0;
+
+		/* Use single cpu clear, as we cannot handle smp here. */
+		__ctl_clear_bit(14, 24);	/* Disable WARNING MCH */
+		if (xchg(&mchchk_wng_posted, 1) == 0)
+			kill_cad_pid(SIGPWR, 1);
+	}
+	if (mcck.kill_task) {
+		local_irq_enable();
+		printk(KERN_EMERG "mcck: Terminating task because of machine "
+		       "malfunction (code 0x%016llx).\n", mcck.mcck_code);
+		printk(KERN_EMERG "mcck: task: %s, pid: %d.\n",
+		       current->comm, current->pid);
+		do_exit(SIGSEGV);
+	}
+}
+EXPORT_SYMBOL_GPL(s390_handle_mcck);
+
+/*
+ * returns 0 if all registers could be validated
+ * returns 1 otherwise
+ */
+static int notrace s390_revalidate_registers(struct mci *mci)
+{
+	int kill_task;
+	u64 zero;
+	void *fpt_save_area, *fpt_creg_save_area;
+
+	kill_task = 0;
+	zero = 0;
+
+	if (!mci->gr) {
+		/*
+		 * General purpose registers couldn't be restored and have
+		 * unknown contents. Process needs to be terminated.
+		 */
+		kill_task = 1;
+	}
+	if (!mci->fp) {
+		/*
+		 * Floating point registers can't be restored and
+		 * therefore the process needs to be terminated.
+		 */
+		kill_task = 1;
+	}
+	fpt_save_area = &S390_lowcore.floating_pt_save_area;
+	fpt_creg_save_area = &S390_lowcore.fpt_creg_save_area;
+	if (!mci->fc) {
+		/*
+		 * Floating point control register can't be restored.
+		 * Task will be terminated.
+		 */
+		asm volatile("lfpc 0(%0)" : : "a" (&zero), "m" (zero));
+		kill_task = 1;
+	} else
+		asm volatile("lfpc 0(%0)" : : "a" (fpt_creg_save_area));
+
+	asm volatile(
+		"	ld	0,0(%0)\n"
+		"	ld	1,8(%0)\n"
+		"	ld	2,16(%0)\n"
+		"	ld	3,24(%0)\n"
+		"	ld	4,32(%0)\n"
+		"	ld	5,40(%0)\n"
+		"	ld	6,48(%0)\n"
+		"	ld	7,56(%0)\n"
+		"	ld	8,64(%0)\n"
+		"	ld	9,72(%0)\n"
+		"	ld	10,80(%0)\n"
+		"	ld	11,88(%0)\n"
+		"	ld	12,96(%0)\n"
+		"	ld	13,104(%0)\n"
+		"	ld	14,112(%0)\n"
+		"	ld	15,120(%0)\n"
+		: : "a" (fpt_save_area));
+	/* Revalidate vector registers */
+	if (MACHINE_HAS_VX && current->thread.vxrs) {
+		if (!mci->vr) {
+			/*
+			 * Vector registers can't be restored and therefore
+			 * the process needs to be terminated.
+			 */
+			kill_task = 1;
+		}
+		restore_vx_regs((__vector128 *)
+				S390_lowcore.vector_save_area_addr);
+	}
+	/* Revalidate access registers */
+	asm volatile(
+		"	lam	0,15,0(%0)"
+		: : "a" (&S390_lowcore.access_regs_save_area));
+	if (!mci->ar) {
+		/*
+		 * Access registers have unknown contents.
+		 * Terminating task.
+		 */
+		kill_task = 1;
+	}
+	/* Revalidate control registers */
+	if (!mci->cr) {
+		/*
+		 * Control registers have unknown contents.
+		 * Can't recover and therefore stopping machine.
+		 */
+		s390_handle_damage("invalid control registers.");
+	} else {
+		asm volatile(
+			"	lctlg	0,15,0(%0)"
+			: : "a" (&S390_lowcore.cregs_save_area));
+	}
+	/*
+	 * We don't even try to revalidate the TOD register, since we simply
+	 * can't write something sensible into that register.
+	 */
+	/*
+	 * See if we can revalidate the TOD programmable register with its
+	 * old contents (should be zero) otherwise set it to zero.
+	 */
+	if (!mci->pr)
+		asm volatile(
+			"	sr	0,0\n"
+			"	sckpf"
+			: : : "0", "cc");
+	else
+		asm volatile(
+			"	l	0,0(%0)\n"
+			"	sckpf"
+			: : "a" (&S390_lowcore.tod_progreg_save_area)
+			: "0", "cc");
+	/* Revalidate clock comparator register */
+	set_clock_comparator(S390_lowcore.clock_comparator);
+	/* Check if old PSW is valid */
+	if (!mci->wp)
+		/*
+		 * Can't tell if we come from user or kernel mode
+		 * -> stopping machine.
+		 */
+		s390_handle_damage("old psw invalid.");
+
+	if (!mci->ms || !mci->pm || !mci->ia)
+		kill_task = 1;
+
+	return kill_task;
+}
+
+#define MAX_IPD_COUNT	29
+#define MAX_IPD_TIME	(5 * 60 * USEC_PER_SEC) /* 5 minutes */
+
+#define ED_STP_ISLAND	6	/* External damage STP island check */
+#define ED_STP_SYNC	7	/* External damage STP sync check */
+#define ED_ETR_SYNC	12	/* External damage ETR sync check */
+#define ED_ETR_SWITCH	13	/* External damage ETR switch to local */
+
+/*
+ * machine check handler.
+ */
+void notrace s390_do_machine_check(struct pt_regs *regs)
+{
+	static int ipd_count;
+	static DEFINE_SPINLOCK(ipd_lock);
+	static unsigned long long last_ipd;
+	struct mcck_struct *mcck;
+	unsigned long long tmp;
+	struct mci *mci;
+	int umode;
+
+	nmi_enter();
+	inc_irq_stat(NMI_NMI);
+	mci = (struct mci *) &S390_lowcore.mcck_interruption_code;
+	mcck = this_cpu_ptr(&cpu_mcck);
+	umode = user_mode(regs);
+
+	if (mci->sd) {
+		/* System damage -> stopping machine */
+		s390_handle_damage("received system damage machine check.");
+	}
+	if (mci->pd) {
+		if (mci->b) {
+			/* Processing backup -> verify if we can survive this */
+			u64 z_mcic, o_mcic, t_mcic;
+			z_mcic = (1ULL<<63 | 1ULL<<59 | 1ULL<<29);
+			o_mcic = (1ULL<<43 | 1ULL<<42 | 1ULL<<41 | 1ULL<<40 |
+				  1ULL<<36 | 1ULL<<35 | 1ULL<<34 | 1ULL<<32 |
+				  1ULL<<30 | 1ULL<<21 | 1ULL<<20 | 1ULL<<17 |
+				  1ULL<<16);
+			t_mcic = *(u64 *)mci;
+
+			if (((t_mcic & z_mcic) != 0) ||
+			    ((t_mcic & o_mcic) != o_mcic)) {
+				s390_handle_damage("processing backup machine "
+						   "check with damage.");
+			}
+
+			/*
+			 * Nullifying exigent condition, therefore we might
+			 * retry this instruction.
+			 */
+			spin_lock(&ipd_lock);
+			tmp = get_tod_clock();
+			if (((tmp - last_ipd) >> 12) < MAX_IPD_TIME)
+				ipd_count++;
+			else
+				ipd_count = 1;
+			last_ipd = tmp;
+			if (ipd_count == MAX_IPD_COUNT)
+				s390_handle_damage("too many ipd retries.");
+			spin_unlock(&ipd_lock);
+		} else {
+			/* Processing damage -> stopping machine */
+			s390_handle_damage("received instruction processing "
+					   "damage machine check.");
+		}
+	}
+	if (s390_revalidate_registers(mci)) {
+		if (umode) {
+			/*
+			 * Couldn't restore all register contents while in
+			 * user mode -> mark task for termination.
+			 */
+			mcck->kill_task = 1;
+			mcck->mcck_code = *(unsigned long long *) mci;
+			set_cpu_flag(CIF_MCCK_PENDING);
+		} else {
+			/*
+			 * Couldn't restore all register contents while in
+			 * kernel mode -> stopping machine.
+			 */
+			s390_handle_damage("unable to revalidate registers.");
+		}
+	}
+	if (mci->cd) {
+		/* Timing facility damage */
+		s390_handle_damage("TOD clock damaged");
+	}
+	if (mci->ed && mci->ec) {
+		/* External damage */
+		if (S390_lowcore.external_damage_code & (1U << ED_ETR_SYNC))
+			etr_sync_check();
+		if (S390_lowcore.external_damage_code & (1U << ED_ETR_SWITCH))
+			etr_switch_to_local();
+		if (S390_lowcore.external_damage_code & (1U << ED_STP_SYNC))
+			stp_sync_check();
+		if (S390_lowcore.external_damage_code & (1U << ED_STP_ISLAND))
+			stp_island_check();
+	}
+	if (mci->se)
+		/* Storage error uncorrected */
+		s390_handle_damage("received storage error uncorrected "
+				   "machine check.");
+	if (mci->ke)
+		/* Storage key-error uncorrected */
+		s390_handle_damage("received storage key-error uncorrected "
+				   "machine check.");
+	if (mci->ds && mci->fa)
+		/* Storage degradation */
+		s390_handle_damage("received storage degradation machine "
+				   "check.");
+	if (mci->cp) {
+		/* Channel report word pending */
+		mcck->channel_report = 1;
+		set_cpu_flag(CIF_MCCK_PENDING);
+	}
+	if (mci->w) {
+		/* Warning pending */
+		mcck->warning = 1;
+		set_cpu_flag(CIF_MCCK_PENDING);
+	}
+	nmi_exit();
+}
+
+static int __init machine_check_init(void)
+{
+	ctl_set_bit(14, 25);	/* enable external damage MCH */
+	ctl_set_bit(14, 27);	/* enable system recovery MCH */
+	ctl_set_bit(14, 24);	/* enable warning MCH */
+	return 0;
+}
+arch_initcall(machine_check_init);
diff --git a/arch/s390/kernel/os_info.c b/arch/s390/kernel/os_info.c
new file mode 100644
index 000000000..d112fc66f
--- /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 <linux/slab.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);
+	mem_assign_absolute(S390_lowcore.os_info, (unsigned long) 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);
+	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 000000000..56fdad479
--- /dev/null
+++ b/arch/s390/kernel/perf_cpum_cf.c
@@ -0,0 +1,696 @@
+/*
+ * 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 < 256)
+		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;
+		if ((cpuhw->info.csvn == 1 && hwc->config > 159) ||
+		    (cpuhw->info.csvn == 2 && hwc->config > 175) ||
+		    (cpuhw->info.csvn  > 2 && hwc->config > 255))
+			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 = this_cpu_ptr(&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=%x\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 = this_cpu_ptr(&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=%x\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;
+
+	inc_irq_stat(IRQEXT_CMC);
+	cpuhw = this_cpu_ptr(&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 = this_cpu_ptr(&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);
+	irq_subclass_register(IRQ_SUBCLASS_MEASUREMENT_ALERT);
+
+	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);
+	irq_subclass_unregister(IRQ_SUBCLASS_MEASUREMENT_ALERT);
+}
+
+/* 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;
+
+	/* 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 = this_cpu_ptr(&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 = this_cpu_ptr(&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 = this_cpu_ptr(&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 = this_cpu_ptr(&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 = this_cpu_ptr(&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 = this_cpu_ptr(&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 = this_cpu_ptr(&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 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_irq(EXT_IRQ_MEASURE_ALERT,
+				   cpumf_measurement_alert);
+	if (rc) {
+		pr_err("Registering for CPU-measurement alerts "
+		       "failed with rc=%i\n", rc);
+		goto out;
+	}
+
+	/* The CPU measurement counter facility does not have overflow
+	 * interrupts to do sampling.  Sampling must be provided by
+	 * external means, for example, by timers.
+	 */
+	cpumf_pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT;
+
+	cpumf_pmu.attr_groups = cpumf_cf_event_group();
+	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_irq(EXT_IRQ_MEASURE_ALERT,
+					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_cpum_cf_events.c b/arch/s390/kernel/perf_cpum_cf_events.c
new file mode 100644
index 000000000..4554a4bae
--- /dev/null
+++ b/arch/s390/kernel/perf_cpum_cf_events.c
@@ -0,0 +1,322 @@
+/*
+ * Perf PMU sysfs events attributes for available CPU-measurement counters
+ *
+ */
+
+#include <linux/slab.h>
+#include <linux/perf_event.h>
+
+
+/* BEGIN: CPUM_CF COUNTER DEFINITIONS =================================== */
+
+CPUMF_EVENT_ATTR(cf, CPU_CYCLES, 0x0000);
+CPUMF_EVENT_ATTR(cf, INSTRUCTIONS, 0x0001);
+CPUMF_EVENT_ATTR(cf, L1I_DIR_WRITES, 0x0002);
+CPUMF_EVENT_ATTR(cf, L1I_PENALTY_CYCLES, 0x0003);
+CPUMF_EVENT_ATTR(cf, PROBLEM_STATE_CPU_CYCLES, 0x0020);
+CPUMF_EVENT_ATTR(cf, PROBLEM_STATE_INSTRUCTIONS, 0x0021);
+CPUMF_EVENT_ATTR(cf, PROBLEM_STATE_L1I_DIR_WRITES, 0x0022);
+CPUMF_EVENT_ATTR(cf, PROBLEM_STATE_L1I_PENALTY_CYCLES, 0x0023);
+CPUMF_EVENT_ATTR(cf, PROBLEM_STATE_L1D_DIR_WRITES, 0x0024);
+CPUMF_EVENT_ATTR(cf, PROBLEM_STATE_L1D_PENALTY_CYCLES, 0x0025);
+CPUMF_EVENT_ATTR(cf, L1D_DIR_WRITES, 0x0004);
+CPUMF_EVENT_ATTR(cf, L1D_PENALTY_CYCLES, 0x0005);
+CPUMF_EVENT_ATTR(cf, PRNG_FUNCTIONS, 0x0040);
+CPUMF_EVENT_ATTR(cf, PRNG_CYCLES, 0x0041);
+CPUMF_EVENT_ATTR(cf, PRNG_BLOCKED_FUNCTIONS, 0x0042);
+CPUMF_EVENT_ATTR(cf, PRNG_BLOCKED_CYCLES, 0x0043);
+CPUMF_EVENT_ATTR(cf, SHA_FUNCTIONS, 0x0044);
+CPUMF_EVENT_ATTR(cf, SHA_CYCLES, 0x0045);
+CPUMF_EVENT_ATTR(cf, SHA_BLOCKED_FUNCTIONS, 0x0046);
+CPUMF_EVENT_ATTR(cf, SHA_BLOCKED_CYCLES, 0x0047);
+CPUMF_EVENT_ATTR(cf, DEA_FUNCTIONS, 0x0048);
+CPUMF_EVENT_ATTR(cf, DEA_CYCLES, 0x0049);
+CPUMF_EVENT_ATTR(cf, DEA_BLOCKED_FUNCTIONS, 0x004a);
+CPUMF_EVENT_ATTR(cf, DEA_BLOCKED_CYCLES, 0x004b);
+CPUMF_EVENT_ATTR(cf, AES_FUNCTIONS, 0x004c);
+CPUMF_EVENT_ATTR(cf, AES_CYCLES, 0x004d);
+CPUMF_EVENT_ATTR(cf, AES_BLOCKED_FUNCTIONS, 0x004e);
+CPUMF_EVENT_ATTR(cf, AES_BLOCKED_CYCLES, 0x004f);
+CPUMF_EVENT_ATTR(cf_z10, L1I_L2_SOURCED_WRITES, 0x0080);
+CPUMF_EVENT_ATTR(cf_z10, L1D_L2_SOURCED_WRITES, 0x0081);
+CPUMF_EVENT_ATTR(cf_z10, L1I_L3_LOCAL_WRITES, 0x0082);
+CPUMF_EVENT_ATTR(cf_z10, L1D_L3_LOCAL_WRITES, 0x0083);
+CPUMF_EVENT_ATTR(cf_z10, L1I_L3_REMOTE_WRITES, 0x0084);
+CPUMF_EVENT_ATTR(cf_z10, L1D_L3_REMOTE_WRITES, 0x0085);
+CPUMF_EVENT_ATTR(cf_z10, L1D_LMEM_SOURCED_WRITES, 0x0086);
+CPUMF_EVENT_ATTR(cf_z10, L1I_LMEM_SOURCED_WRITES, 0x0087);
+CPUMF_EVENT_ATTR(cf_z10, L1D_RO_EXCL_WRITES, 0x0088);
+CPUMF_EVENT_ATTR(cf_z10, L1I_CACHELINE_INVALIDATES, 0x0089);
+CPUMF_EVENT_ATTR(cf_z10, ITLB1_WRITES, 0x008a);
+CPUMF_EVENT_ATTR(cf_z10, DTLB1_WRITES, 0x008b);
+CPUMF_EVENT_ATTR(cf_z10, TLB2_PTE_WRITES, 0x008c);
+CPUMF_EVENT_ATTR(cf_z10, TLB2_CRSTE_WRITES, 0x008d);
+CPUMF_EVENT_ATTR(cf_z10, TLB2_CRSTE_HPAGE_WRITES, 0x008e);
+CPUMF_EVENT_ATTR(cf_z10, ITLB1_MISSES, 0x0091);
+CPUMF_EVENT_ATTR(cf_z10, DTLB1_MISSES, 0x0092);
+CPUMF_EVENT_ATTR(cf_z10, L2C_STORES_SENT, 0x0093);
+CPUMF_EVENT_ATTR(cf_z196, L1D_L2_SOURCED_WRITES, 0x0080);
+CPUMF_EVENT_ATTR(cf_z196, L1I_L2_SOURCED_WRITES, 0x0081);
+CPUMF_EVENT_ATTR(cf_z196, DTLB1_MISSES, 0x0082);
+CPUMF_EVENT_ATTR(cf_z196, ITLB1_MISSES, 0x0083);
+CPUMF_EVENT_ATTR(cf_z196, L2C_STORES_SENT, 0x0085);
+CPUMF_EVENT_ATTR(cf_z196, L1D_OFFBOOK_L3_SOURCED_WRITES, 0x0086);
+CPUMF_EVENT_ATTR(cf_z196, L1D_ONBOOK_L4_SOURCED_WRITES, 0x0087);
+CPUMF_EVENT_ATTR(cf_z196, L1I_ONBOOK_L4_SOURCED_WRITES, 0x0088);
+CPUMF_EVENT_ATTR(cf_z196, L1D_RO_EXCL_WRITES, 0x0089);
+CPUMF_EVENT_ATTR(cf_z196, L1D_OFFBOOK_L4_SOURCED_WRITES, 0x008a);
+CPUMF_EVENT_ATTR(cf_z196, L1I_OFFBOOK_L4_SOURCED_WRITES, 0x008b);
+CPUMF_EVENT_ATTR(cf_z196, DTLB1_HPAGE_WRITES, 0x008c);
+CPUMF_EVENT_ATTR(cf_z196, L1D_LMEM_SOURCED_WRITES, 0x008d);
+CPUMF_EVENT_ATTR(cf_z196, L1I_LMEM_SOURCED_WRITES, 0x008e);
+CPUMF_EVENT_ATTR(cf_z196, L1I_OFFBOOK_L3_SOURCED_WRITES, 0x008f);
+CPUMF_EVENT_ATTR(cf_z196, DTLB1_WRITES, 0x0090);
+CPUMF_EVENT_ATTR(cf_z196, ITLB1_WRITES, 0x0091);
+CPUMF_EVENT_ATTR(cf_z196, TLB2_PTE_WRITES, 0x0092);
+CPUMF_EVENT_ATTR(cf_z196, TLB2_CRSTE_HPAGE_WRITES, 0x0093);
+CPUMF_EVENT_ATTR(cf_z196, TLB2_CRSTE_WRITES, 0x0094);
+CPUMF_EVENT_ATTR(cf_z196, L1D_ONCHIP_L3_SOURCED_WRITES, 0x0096);
+CPUMF_EVENT_ATTR(cf_z196, L1D_OFFCHIP_L3_SOURCED_WRITES, 0x0098);
+CPUMF_EVENT_ATTR(cf_z196, L1I_ONCHIP_L3_SOURCED_WRITES, 0x0099);
+CPUMF_EVENT_ATTR(cf_z196, L1I_OFFCHIP_L3_SOURCED_WRITES, 0x009b);
+CPUMF_EVENT_ATTR(cf_zec12, DTLB1_MISSES, 0x0080);
+CPUMF_EVENT_ATTR(cf_zec12, ITLB1_MISSES, 0x0081);
+CPUMF_EVENT_ATTR(cf_zec12, L1D_L2I_SOURCED_WRITES, 0x0082);
+CPUMF_EVENT_ATTR(cf_zec12, L1I_L2I_SOURCED_WRITES, 0x0083);
+CPUMF_EVENT_ATTR(cf_zec12, L1D_L2D_SOURCED_WRITES, 0x0084);
+CPUMF_EVENT_ATTR(cf_zec12, DTLB1_WRITES, 0x0085);
+CPUMF_EVENT_ATTR(cf_zec12, L1D_LMEM_SOURCED_WRITES, 0x0087);
+CPUMF_EVENT_ATTR(cf_zec12, L1I_LMEM_SOURCED_WRITES, 0x0089);
+CPUMF_EVENT_ATTR(cf_zec12, L1D_RO_EXCL_WRITES, 0x008a);
+CPUMF_EVENT_ATTR(cf_zec12, DTLB1_HPAGE_WRITES, 0x008b);
+CPUMF_EVENT_ATTR(cf_zec12, ITLB1_WRITES, 0x008c);
+CPUMF_EVENT_ATTR(cf_zec12, TLB2_PTE_WRITES, 0x008d);
+CPUMF_EVENT_ATTR(cf_zec12, TLB2_CRSTE_HPAGE_WRITES, 0x008e);
+CPUMF_EVENT_ATTR(cf_zec12, TLB2_CRSTE_WRITES, 0x008f);
+CPUMF_EVENT_ATTR(cf_zec12, L1D_ONCHIP_L3_SOURCED_WRITES, 0x0090);
+CPUMF_EVENT_ATTR(cf_zec12, L1D_OFFCHIP_L3_SOURCED_WRITES, 0x0091);
+CPUMF_EVENT_ATTR(cf_zec12, L1D_OFFBOOK_L3_SOURCED_WRITES, 0x0092);
+CPUMF_EVENT_ATTR(cf_zec12, L1D_ONBOOK_L4_SOURCED_WRITES, 0x0093);
+CPUMF_EVENT_ATTR(cf_zec12, L1D_OFFBOOK_L4_SOURCED_WRITES, 0x0094);
+CPUMF_EVENT_ATTR(cf_zec12, TX_NC_TEND, 0x0095);
+CPUMF_EVENT_ATTR(cf_zec12, L1D_ONCHIP_L3_SOURCED_WRITES_IV, 0x0096);
+CPUMF_EVENT_ATTR(cf_zec12, L1D_OFFCHIP_L3_SOURCED_WRITES_IV, 0x0097);
+CPUMF_EVENT_ATTR(cf_zec12, L1D_OFFBOOK_L3_SOURCED_WRITES_IV, 0x0098);
+CPUMF_EVENT_ATTR(cf_zec12, L1I_ONCHIP_L3_SOURCED_WRITES, 0x0099);
+CPUMF_EVENT_ATTR(cf_zec12, L1I_OFFCHIP_L3_SOURCED_WRITES, 0x009a);
+CPUMF_EVENT_ATTR(cf_zec12, L1I_OFFBOOK_L3_SOURCED_WRITES, 0x009b);
+CPUMF_EVENT_ATTR(cf_zec12, L1I_ONBOOK_L4_SOURCED_WRITES, 0x009c);
+CPUMF_EVENT_ATTR(cf_zec12, L1I_OFFBOOK_L4_SOURCED_WRITES, 0x009d);
+CPUMF_EVENT_ATTR(cf_zec12, TX_C_TEND, 0x009e);
+CPUMF_EVENT_ATTR(cf_zec12, L1I_ONCHIP_L3_SOURCED_WRITES_IV, 0x009f);
+CPUMF_EVENT_ATTR(cf_zec12, L1I_OFFCHIP_L3_SOURCED_WRITES_IV, 0x00a0);
+CPUMF_EVENT_ATTR(cf_zec12, L1I_OFFBOOK_L3_SOURCED_WRITES_IV, 0x00a1);
+CPUMF_EVENT_ATTR(cf_zec12, TX_NC_TABORT, 0x00b1);
+CPUMF_EVENT_ATTR(cf_zec12, TX_C_TABORT_NO_SPECIAL, 0x00b2);
+CPUMF_EVENT_ATTR(cf_zec12, TX_C_TABORT_SPECIAL, 0x00b3);
+
+static struct attribute *cpumcf_pmu_event_attr[] = {
+	CPUMF_EVENT_PTR(cf, CPU_CYCLES),
+	CPUMF_EVENT_PTR(cf, INSTRUCTIONS),
+	CPUMF_EVENT_PTR(cf, L1I_DIR_WRITES),
+	CPUMF_EVENT_PTR(cf, L1I_PENALTY_CYCLES),
+	CPUMF_EVENT_PTR(cf, PROBLEM_STATE_CPU_CYCLES),
+	CPUMF_EVENT_PTR(cf, PROBLEM_STATE_INSTRUCTIONS),
+	CPUMF_EVENT_PTR(cf, PROBLEM_STATE_L1I_DIR_WRITES),
+	CPUMF_EVENT_PTR(cf, PROBLEM_STATE_L1I_PENALTY_CYCLES),
+	CPUMF_EVENT_PTR(cf, PROBLEM_STATE_L1D_DIR_WRITES),
+	CPUMF_EVENT_PTR(cf, PROBLEM_STATE_L1D_PENALTY_CYCLES),
+	CPUMF_EVENT_PTR(cf, L1D_DIR_WRITES),
+	CPUMF_EVENT_PTR(cf, L1D_PENALTY_CYCLES),
+	CPUMF_EVENT_PTR(cf, PRNG_FUNCTIONS),
+	CPUMF_EVENT_PTR(cf, PRNG_CYCLES),
+	CPUMF_EVENT_PTR(cf, PRNG_BLOCKED_FUNCTIONS),
+	CPUMF_EVENT_PTR(cf, PRNG_BLOCKED_CYCLES),
+	CPUMF_EVENT_PTR(cf, SHA_FUNCTIONS),
+	CPUMF_EVENT_PTR(cf, SHA_CYCLES),
+	CPUMF_EVENT_PTR(cf, SHA_BLOCKED_FUNCTIONS),
+	CPUMF_EVENT_PTR(cf, SHA_BLOCKED_CYCLES),
+	CPUMF_EVENT_PTR(cf, DEA_FUNCTIONS),
+	CPUMF_EVENT_PTR(cf, DEA_CYCLES),
+	CPUMF_EVENT_PTR(cf, DEA_BLOCKED_FUNCTIONS),
+	CPUMF_EVENT_PTR(cf, DEA_BLOCKED_CYCLES),
+	CPUMF_EVENT_PTR(cf, AES_FUNCTIONS),
+	CPUMF_EVENT_PTR(cf, AES_CYCLES),
+	CPUMF_EVENT_PTR(cf, AES_BLOCKED_FUNCTIONS),
+	CPUMF_EVENT_PTR(cf, AES_BLOCKED_CYCLES),
+	NULL,
+};
+
+static struct attribute *cpumcf_z10_pmu_event_attr[] __initdata = {
+	CPUMF_EVENT_PTR(cf_z10, L1I_L2_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_z10, L1D_L2_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_z10, L1I_L3_LOCAL_WRITES),
+	CPUMF_EVENT_PTR(cf_z10, L1D_L3_LOCAL_WRITES),
+	CPUMF_EVENT_PTR(cf_z10, L1I_L3_REMOTE_WRITES),
+	CPUMF_EVENT_PTR(cf_z10, L1D_L3_REMOTE_WRITES),
+	CPUMF_EVENT_PTR(cf_z10, L1D_LMEM_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_z10, L1I_LMEM_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_z10, L1D_RO_EXCL_WRITES),
+	CPUMF_EVENT_PTR(cf_z10, L1I_CACHELINE_INVALIDATES),
+	CPUMF_EVENT_PTR(cf_z10, ITLB1_WRITES),
+	CPUMF_EVENT_PTR(cf_z10, DTLB1_WRITES),
+	CPUMF_EVENT_PTR(cf_z10, TLB2_PTE_WRITES),
+	CPUMF_EVENT_PTR(cf_z10, TLB2_CRSTE_WRITES),
+	CPUMF_EVENT_PTR(cf_z10, TLB2_CRSTE_HPAGE_WRITES),
+	CPUMF_EVENT_PTR(cf_z10, ITLB1_MISSES),
+	CPUMF_EVENT_PTR(cf_z10, DTLB1_MISSES),
+	CPUMF_EVENT_PTR(cf_z10, L2C_STORES_SENT),
+	NULL,
+};
+
+static struct attribute *cpumcf_z196_pmu_event_attr[] __initdata = {
+	CPUMF_EVENT_PTR(cf_z196, L1D_L2_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_z196, L1I_L2_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_z196, DTLB1_MISSES),
+	CPUMF_EVENT_PTR(cf_z196, ITLB1_MISSES),
+	CPUMF_EVENT_PTR(cf_z196, L2C_STORES_SENT),
+	CPUMF_EVENT_PTR(cf_z196, L1D_OFFBOOK_L3_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_z196, L1D_ONBOOK_L4_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_z196, L1I_ONBOOK_L4_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_z196, L1D_RO_EXCL_WRITES),
+	CPUMF_EVENT_PTR(cf_z196, L1D_OFFBOOK_L4_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_z196, L1I_OFFBOOK_L4_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_z196, DTLB1_HPAGE_WRITES),
+	CPUMF_EVENT_PTR(cf_z196, L1D_LMEM_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_z196, L1I_LMEM_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_z196, L1I_OFFBOOK_L3_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_z196, DTLB1_WRITES),
+	CPUMF_EVENT_PTR(cf_z196, ITLB1_WRITES),
+	CPUMF_EVENT_PTR(cf_z196, TLB2_PTE_WRITES),
+	CPUMF_EVENT_PTR(cf_z196, TLB2_CRSTE_HPAGE_WRITES),
+	CPUMF_EVENT_PTR(cf_z196, TLB2_CRSTE_WRITES),
+	CPUMF_EVENT_PTR(cf_z196, L1D_ONCHIP_L3_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_z196, L1D_OFFCHIP_L3_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_z196, L1I_ONCHIP_L3_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_z196, L1I_OFFCHIP_L3_SOURCED_WRITES),
+	NULL,
+};
+
+static struct attribute *cpumcf_zec12_pmu_event_attr[] __initdata = {
+	CPUMF_EVENT_PTR(cf_zec12, DTLB1_MISSES),
+	CPUMF_EVENT_PTR(cf_zec12, ITLB1_MISSES),
+	CPUMF_EVENT_PTR(cf_zec12, L1D_L2I_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_zec12, L1I_L2I_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_zec12, L1D_L2D_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_zec12, DTLB1_WRITES),
+	CPUMF_EVENT_PTR(cf_zec12, L1D_LMEM_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_zec12, L1I_LMEM_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_zec12, L1D_RO_EXCL_WRITES),
+	CPUMF_EVENT_PTR(cf_zec12, DTLB1_HPAGE_WRITES),
+	CPUMF_EVENT_PTR(cf_zec12, ITLB1_WRITES),
+	CPUMF_EVENT_PTR(cf_zec12, TLB2_PTE_WRITES),
+	CPUMF_EVENT_PTR(cf_zec12, TLB2_CRSTE_HPAGE_WRITES),
+	CPUMF_EVENT_PTR(cf_zec12, TLB2_CRSTE_WRITES),
+	CPUMF_EVENT_PTR(cf_zec12, L1D_ONCHIP_L3_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_zec12, L1D_OFFCHIP_L3_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_zec12, L1D_OFFBOOK_L3_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_zec12, L1D_ONBOOK_L4_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_zec12, L1D_OFFBOOK_L4_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_zec12, TX_NC_TEND),
+	CPUMF_EVENT_PTR(cf_zec12, L1D_ONCHIP_L3_SOURCED_WRITES_IV),
+	CPUMF_EVENT_PTR(cf_zec12, L1D_OFFCHIP_L3_SOURCED_WRITES_IV),
+	CPUMF_EVENT_PTR(cf_zec12, L1D_OFFBOOK_L3_SOURCED_WRITES_IV),
+	CPUMF_EVENT_PTR(cf_zec12, L1I_ONCHIP_L3_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_zec12, L1I_OFFCHIP_L3_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_zec12, L1I_OFFBOOK_L3_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_zec12, L1I_ONBOOK_L4_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_zec12, L1I_OFFBOOK_L4_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_zec12, TX_C_TEND),
+	CPUMF_EVENT_PTR(cf_zec12, L1I_ONCHIP_L3_SOURCED_WRITES_IV),
+	CPUMF_EVENT_PTR(cf_zec12, L1I_OFFCHIP_L3_SOURCED_WRITES_IV),
+	CPUMF_EVENT_PTR(cf_zec12, L1I_OFFBOOK_L3_SOURCED_WRITES_IV),
+	CPUMF_EVENT_PTR(cf_zec12, TX_NC_TABORT),
+	CPUMF_EVENT_PTR(cf_zec12, TX_C_TABORT_NO_SPECIAL),
+	CPUMF_EVENT_PTR(cf_zec12, TX_C_TABORT_SPECIAL),
+	NULL,
+};
+
+/* END: CPUM_CF COUNTER DEFINITIONS ===================================== */
+
+static struct attribute_group cpumsf_pmu_events_group = {
+	.name = "events",
+	.attrs = cpumcf_pmu_event_attr,
+};
+
+PMU_FORMAT_ATTR(event, "config:0-63");
+
+static struct attribute *cpumsf_pmu_format_attr[] = {
+	&format_attr_event.attr,
+	NULL,
+};
+
+static struct attribute_group cpumsf_pmu_format_group = {
+	.name = "format",
+	.attrs = cpumsf_pmu_format_attr,
+};
+
+static const struct attribute_group *cpumsf_pmu_attr_groups[] = {
+	&cpumsf_pmu_events_group,
+	&cpumsf_pmu_format_group,
+	NULL,
+};
+
+
+static __init struct attribute **merge_attr(struct attribute **a,
+					    struct attribute **b)
+{
+	struct attribute **new;
+	int j, i;
+
+	for (j = 0; a[j]; j++)
+		;
+	for (i = 0; b[i]; i++)
+		j++;
+	j++;
+
+	new = kmalloc(sizeof(struct attribute *) * j, GFP_KERNEL);
+	if (!new)
+		return NULL;
+	j = 0;
+	for (i = 0; a[i]; i++)
+		new[j++] = a[i];
+	for (i = 0; b[i]; i++)
+		new[j++] = b[i];
+	new[j] = NULL;
+
+	return new;
+}
+
+__init const struct attribute_group **cpumf_cf_event_group(void)
+{
+	struct attribute **combined, **model;
+	struct cpuid cpu_id;
+
+	get_cpu_id(&cpu_id);
+	switch (cpu_id.machine) {
+	case 0x2097:
+	case 0x2098:
+		model = cpumcf_z10_pmu_event_attr;
+		break;
+	case 0x2817:
+	case 0x2818:
+		model = cpumcf_z196_pmu_event_attr;
+		break;
+	case 0x2827:
+	case 0x2828:
+		model = cpumcf_zec12_pmu_event_attr;
+		break;
+	default:
+		model = NULL;
+		break;
+	};
+
+	if (!model)
+		goto out;
+
+	combined = merge_attr(cpumcf_pmu_event_attr, model);
+	if (combined)
+		cpumsf_pmu_events_group.attrs = combined;
+out:
+	return cpumsf_pmu_attr_groups;
+}
diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c
new file mode 100644
index 000000000..e6a1578fc
--- /dev/null
+++ b/arch/s390/kernel/perf_cpum_sf.c
@@ -0,0 +1,1639 @@
+/*
+ * Performance event support for the System z CPU-measurement Sampling Facility
+ *
+ * Copyright IBM Corp. 2013
+ * 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_sf"
+#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/export.h>
+#include <linux/slab.h>
+#include <linux/mm.h>
+#include <linux/moduleparam.h>
+#include <asm/cpu_mf.h>
+#include <asm/irq.h>
+#include <asm/debug.h>
+#include <asm/timex.h>
+
+/* Minimum number of sample-data-block-tables:
+ * At least one table is required for the sampling buffer structure.
+ * A single table contains up to 511 pointers to sample-data-blocks.
+ */
+#define CPUM_SF_MIN_SDBT	1
+
+/* Number of sample-data-blocks per sample-data-block-table (SDBT):
+ * A table contains SDB pointers (8 bytes) and one table-link entry
+ * that points to the origin of the next SDBT.
+ */
+#define CPUM_SF_SDB_PER_TABLE	((PAGE_SIZE - 8) / 8)
+
+/* Maximum page offset for an SDBT table-link entry:
+ * If this page offset is reached, a table-link entry to the next SDBT
+ * must be added.
+ */
+#define CPUM_SF_SDBT_TL_OFFSET	(CPUM_SF_SDB_PER_TABLE * 8)
+static inline int require_table_link(const void *sdbt)
+{
+	return ((unsigned long) sdbt & ~PAGE_MASK) == CPUM_SF_SDBT_TL_OFFSET;
+}
+
+/* Minimum and maximum sampling buffer sizes:
+ *
+ * This number represents the maximum size of the sampling buffer taking
+ * the number of sample-data-block-tables into account.  Note that these
+ * numbers apply to the basic-sampling function only.
+ * The maximum number of SDBs is increased by CPUM_SF_SDB_DIAG_FACTOR if
+ * the diagnostic-sampling function is active.
+ *
+ * Sampling buffer size		Buffer characteristics
+ * ---------------------------------------------------
+ *	 64KB		    ==	  16 pages (4KB per page)
+ *				   1 page  for SDB-tables
+ *				  15 pages for SDBs
+ *
+ *  32MB		    ==	8192 pages (4KB per page)
+ *				  16 pages for SDB-tables
+ *				8176 pages for SDBs
+ */
+static unsigned long __read_mostly CPUM_SF_MIN_SDB = 15;
+static unsigned long __read_mostly CPUM_SF_MAX_SDB = 8176;
+static unsigned long __read_mostly CPUM_SF_SDB_DIAG_FACTOR = 1;
+
+struct sf_buffer {
+	unsigned long	 *sdbt;	    /* Sample-data-block-table origin */
+	/* buffer characteristics (required for buffer increments) */
+	unsigned long  num_sdb;	    /* Number of sample-data-blocks */
+	unsigned long num_sdbt;	    /* Number of sample-data-block-tables */
+	unsigned long	 *tail;	    /* last sample-data-block-table */
+};
+
+struct cpu_hw_sf {
+	/* CPU-measurement sampling information block */
+	struct hws_qsi_info_block qsi;
+	/* CPU-measurement sampling control block */
+	struct hws_lsctl_request_block lsctl;
+	struct sf_buffer sfb;	    /* Sampling buffer */
+	unsigned int flags;	    /* Status flags */
+	struct perf_event *event;   /* Scheduled perf event */
+};
+static DEFINE_PER_CPU(struct cpu_hw_sf, cpu_hw_sf);
+
+/* Debug feature */
+static debug_info_t *sfdbg;
+
+/*
+ * sf_disable() - Switch off sampling facility
+ */
+static int sf_disable(void)
+{
+	struct hws_lsctl_request_block sreq;
+
+	memset(&sreq, 0, sizeof(sreq));
+	return lsctl(&sreq);
+}
+
+/*
+ * sf_buffer_available() - Check for an allocated sampling buffer
+ */
+static int sf_buffer_available(struct cpu_hw_sf *cpuhw)
+{
+	return !!cpuhw->sfb.sdbt;
+}
+
+/*
+ * deallocate sampling facility buffer
+ */
+static void free_sampling_buffer(struct sf_buffer *sfb)
+{
+	unsigned long *sdbt, *curr;
+
+	if (!sfb->sdbt)
+		return;
+
+	sdbt = sfb->sdbt;
+	curr = sdbt;
+
+	/* Free the SDBT after all SDBs are processed... */
+	while (1) {
+		if (!*curr || !sdbt)
+			break;
+
+		/* Process table-link entries */
+		if (is_link_entry(curr)) {
+			curr = get_next_sdbt(curr);
+			if (sdbt)
+				free_page((unsigned long) sdbt);
+
+			/* If the origin is reached, sampling buffer is freed */
+			if (curr == sfb->sdbt)
+				break;
+			else
+				sdbt = curr;
+		} else {
+			/* Process SDB pointer */
+			if (*curr) {
+				free_page(*curr);
+				curr++;
+			}
+		}
+	}
+
+	debug_sprintf_event(sfdbg, 5,
+			    "free_sampling_buffer: freed sdbt=%p\n", sfb->sdbt);
+	memset(sfb, 0, sizeof(*sfb));
+}
+
+static int alloc_sample_data_block(unsigned long *sdbt, gfp_t gfp_flags)
+{
+	unsigned long sdb, *trailer;
+
+	/* Allocate and initialize sample-data-block */
+	sdb = get_zeroed_page(gfp_flags);
+	if (!sdb)
+		return -ENOMEM;
+	trailer = trailer_entry_ptr(sdb);
+	*trailer = SDB_TE_ALERT_REQ_MASK;
+
+	/* Link SDB into the sample-data-block-table */
+	*sdbt = sdb;
+
+	return 0;
+}
+
+/*
+ * realloc_sampling_buffer() - extend sampler memory
+ *
+ * Allocates new sample-data-blocks and adds them to the specified sampling
+ * buffer memory.
+ *
+ * Important: This modifies the sampling buffer and must be called when the
+ *	      sampling facility is disabled.
+ *
+ * Returns zero on success, non-zero otherwise.
+ */
+static int realloc_sampling_buffer(struct sf_buffer *sfb,
+				   unsigned long num_sdb, gfp_t gfp_flags)
+{
+	int i, rc;
+	unsigned long *new, *tail;
+
+	if (!sfb->sdbt || !sfb->tail)
+		return -EINVAL;
+
+	if (!is_link_entry(sfb->tail))
+		return -EINVAL;
+
+	/* Append to the existing sampling buffer, overwriting the table-link
+	 * register.
+	 * The tail variables always points to the "tail" (last and table-link)
+	 * entry in an SDB-table.
+	 */
+	tail = sfb->tail;
+
+	/* Do a sanity check whether the table-link entry points to
+	 * the sampling buffer origin.
+	 */
+	if (sfb->sdbt != get_next_sdbt(tail)) {
+		debug_sprintf_event(sfdbg, 3, "realloc_sampling_buffer: "
+				    "sampling buffer is not linked: origin=%p"
+				    "tail=%p\n",
+				    (void *) sfb->sdbt, (void *) tail);
+		return -EINVAL;
+	}
+
+	/* Allocate remaining SDBs */
+	rc = 0;
+	for (i = 0; i < num_sdb; i++) {
+		/* Allocate a new SDB-table if it is full. */
+		if (require_table_link(tail)) {
+			new = (unsigned long *) get_zeroed_page(gfp_flags);
+			if (!new) {
+				rc = -ENOMEM;
+				break;
+			}
+			sfb->num_sdbt++;
+			/* Link current page to tail of chain */
+			*tail = (unsigned long)(void *) new + 1;
+			tail = new;
+		}
+
+		/* Allocate a new sample-data-block.
+		 * If there is not enough memory, stop the realloc process
+		 * and simply use what was allocated.  If this is a temporary
+		 * issue, a new realloc call (if required) might succeed.
+		 */
+		rc = alloc_sample_data_block(tail, gfp_flags);
+		if (rc)
+			break;
+		sfb->num_sdb++;
+		tail++;
+	}
+
+	/* Link sampling buffer to its origin */
+	*tail = (unsigned long) sfb->sdbt + 1;
+	sfb->tail = tail;
+
+	debug_sprintf_event(sfdbg, 4, "realloc_sampling_buffer: new buffer"
+			    " settings: sdbt=%lu sdb=%lu\n",
+			    sfb->num_sdbt, sfb->num_sdb);
+	return rc;
+}
+
+/*
+ * allocate_sampling_buffer() - allocate sampler memory
+ *
+ * Allocates and initializes a sampling buffer structure using the
+ * specified number of sample-data-blocks (SDB).  For each allocation,
+ * a 4K page is used.  The number of sample-data-block-tables (SDBT)
+ * are calculated from SDBs.
+ * Also set the ALERT_REQ mask in each SDBs trailer.
+ *
+ * Returns zero on success, non-zero otherwise.
+ */
+static int alloc_sampling_buffer(struct sf_buffer *sfb, unsigned long num_sdb)
+{
+	int rc;
+
+	if (sfb->sdbt)
+		return -EINVAL;
+
+	/* Allocate the sample-data-block-table origin */
+	sfb->sdbt = (unsigned long *) get_zeroed_page(GFP_KERNEL);
+	if (!sfb->sdbt)
+		return -ENOMEM;
+	sfb->num_sdb = 0;
+	sfb->num_sdbt = 1;
+
+	/* Link the table origin to point to itself to prepare for
+	 * realloc_sampling_buffer() invocation.
+	 */
+	sfb->tail = sfb->sdbt;
+	*sfb->tail = (unsigned long)(void *) sfb->sdbt + 1;
+
+	/* Allocate requested number of sample-data-blocks */
+	rc = realloc_sampling_buffer(sfb, num_sdb, GFP_KERNEL);
+	if (rc) {
+		free_sampling_buffer(sfb);
+		debug_sprintf_event(sfdbg, 4, "alloc_sampling_buffer: "
+			"realloc_sampling_buffer failed with rc=%i\n", rc);
+	} else
+		debug_sprintf_event(sfdbg, 4,
+			"alloc_sampling_buffer: tear=%p dear=%p\n",
+			sfb->sdbt, (void *) *sfb->sdbt);
+	return rc;
+}
+
+static void sfb_set_limits(unsigned long min, unsigned long max)
+{
+	struct hws_qsi_info_block si;
+
+	CPUM_SF_MIN_SDB = min;
+	CPUM_SF_MAX_SDB = max;
+
+	memset(&si, 0, sizeof(si));
+	if (!qsi(&si))
+		CPUM_SF_SDB_DIAG_FACTOR = DIV_ROUND_UP(si.dsdes, si.bsdes);
+}
+
+static unsigned long sfb_max_limit(struct hw_perf_event *hwc)
+{
+	return SAMPL_DIAG_MODE(hwc) ? CPUM_SF_MAX_SDB * CPUM_SF_SDB_DIAG_FACTOR
+				    : CPUM_SF_MAX_SDB;
+}
+
+static unsigned long sfb_pending_allocs(struct sf_buffer *sfb,
+					struct hw_perf_event *hwc)
+{
+	if (!sfb->sdbt)
+		return SFB_ALLOC_REG(hwc);
+	if (SFB_ALLOC_REG(hwc) > sfb->num_sdb)
+		return SFB_ALLOC_REG(hwc) - sfb->num_sdb;
+	return 0;
+}
+
+static int sfb_has_pending_allocs(struct sf_buffer *sfb,
+				   struct hw_perf_event *hwc)
+{
+	return sfb_pending_allocs(sfb, hwc) > 0;
+}
+
+static void sfb_account_allocs(unsigned long num, struct hw_perf_event *hwc)
+{
+	/* Limit the number of SDBs to not exceed the maximum */
+	num = min_t(unsigned long, num, sfb_max_limit(hwc) - SFB_ALLOC_REG(hwc));
+	if (num)
+		SFB_ALLOC_REG(hwc) += num;
+}
+
+static void sfb_init_allocs(unsigned long num, struct hw_perf_event *hwc)
+{
+	SFB_ALLOC_REG(hwc) = 0;
+	sfb_account_allocs(num, hwc);
+}
+
+static size_t event_sample_size(struct hw_perf_event *hwc)
+{
+	struct sf_raw_sample *sfr = (struct sf_raw_sample *) RAWSAMPLE_REG(hwc);
+	size_t sample_size;
+
+	/* The sample size depends on the sampling function: The basic-sampling
+	 * function must be always enabled, diagnostic-sampling function is
+	 * optional.
+	 */
+	sample_size = sfr->bsdes;
+	if (SAMPL_DIAG_MODE(hwc))
+		sample_size += sfr->dsdes;
+
+	return sample_size;
+}
+
+static void deallocate_buffers(struct cpu_hw_sf *cpuhw)
+{
+	if (cpuhw->sfb.sdbt)
+		free_sampling_buffer(&cpuhw->sfb);
+}
+
+static int allocate_buffers(struct cpu_hw_sf *cpuhw, struct hw_perf_event *hwc)
+{
+	unsigned long n_sdb, freq, factor;
+	size_t sfr_size, sample_size;
+	struct sf_raw_sample *sfr;
+
+	/* Allocate raw sample buffer
+	 *
+	 *    The raw sample buffer is used to temporarily store sampling data
+	 *    entries for perf raw sample processing.  The buffer size mainly
+	 *    depends on the size of diagnostic-sampling data entries which is
+	 *    machine-specific.  The exact size calculation includes:
+	 *	1. The first 4 bytes of diagnostic-sampling data entries are
+	 *	   already reflected in the sf_raw_sample structure.  Subtract
+	 *	   these bytes.
+	 *	2. The perf raw sample data must be 8-byte aligned (u64) and
+	 *	   perf's internal data size must be considered too.  So add
+	 *	   an additional u32 for correct alignment and subtract before
+	 *	   allocating the buffer.
+	 *	3. Store the raw sample buffer pointer in the perf event
+	 *	   hardware structure.
+	 */
+	sfr_size = ALIGN((sizeof(*sfr) - sizeof(sfr->diag) + cpuhw->qsi.dsdes) +
+			 sizeof(u32), sizeof(u64));
+	sfr_size -= sizeof(u32);
+	sfr = kzalloc(sfr_size, GFP_KERNEL);
+	if (!sfr)
+		return -ENOMEM;
+	sfr->size = sfr_size;
+	sfr->bsdes = cpuhw->qsi.bsdes;
+	sfr->dsdes = cpuhw->qsi.dsdes;
+	RAWSAMPLE_REG(hwc) = (unsigned long) sfr;
+
+	/* Calculate sampling buffers using 4K pages
+	 *
+	 *    1. Determine the sample data size which depends on the used
+	 *	 sampling functions, for example, basic-sampling or
+	 *	 basic-sampling with diagnostic-sampling.
+	 *
+	 *    2. Use the sampling frequency as input.  The sampling buffer is
+	 *	 designed for almost one second.  This can be adjusted through
+	 *	 the "factor" variable.
+	 *	 In any case, alloc_sampling_buffer() sets the Alert Request
+	 *	 Control indicator to trigger a measurement-alert to harvest
+	 *	 sample-data-blocks (sdb).
+	 *
+	 *    3. Compute the number of sample-data-blocks and ensure a minimum
+	 *	 of CPUM_SF_MIN_SDB.  Also ensure the upper limit does not
+	 *	 exceed a "calculated" maximum.  The symbolic maximum is
+	 *	 designed for basic-sampling only and needs to be increased if
+	 *	 diagnostic-sampling is active.
+	 *	 See also the remarks for these symbolic constants.
+	 *
+	 *    4. Compute the number of sample-data-block-tables (SDBT) and
+	 *	 ensure a minimum of CPUM_SF_MIN_SDBT (one table can manage up
+	 *	 to 511 SDBs).
+	 */
+	sample_size = event_sample_size(hwc);
+	freq = sample_rate_to_freq(&cpuhw->qsi, SAMPL_RATE(hwc));
+	factor = 1;
+	n_sdb = DIV_ROUND_UP(freq, factor * ((PAGE_SIZE-64) / sample_size));
+	if (n_sdb < CPUM_SF_MIN_SDB)
+		n_sdb = CPUM_SF_MIN_SDB;
+
+	/* If there is already a sampling buffer allocated, it is very likely
+	 * that the sampling facility is enabled too.  If the event to be
+	 * initialized requires a greater sampling buffer, the allocation must
+	 * be postponed.  Changing the sampling buffer requires the sampling
+	 * facility to be in the disabled state.  So, account the number of
+	 * required SDBs and let cpumsf_pmu_enable() resize the buffer just
+	 * before the event is started.
+	 */
+	sfb_init_allocs(n_sdb, hwc);
+	if (sf_buffer_available(cpuhw))
+		return 0;
+
+	debug_sprintf_event(sfdbg, 3,
+			    "allocate_buffers: rate=%lu f=%lu sdb=%lu/%lu"
+			    " sample_size=%lu cpuhw=%p\n",
+			    SAMPL_RATE(hwc), freq, n_sdb, sfb_max_limit(hwc),
+			    sample_size, cpuhw);
+
+	return alloc_sampling_buffer(&cpuhw->sfb,
+				     sfb_pending_allocs(&cpuhw->sfb, hwc));
+}
+
+static unsigned long min_percent(unsigned int percent, unsigned long base,
+				 unsigned long min)
+{
+	return min_t(unsigned long, min, DIV_ROUND_UP(percent * base, 100));
+}
+
+static unsigned long compute_sfb_extent(unsigned long ratio, unsigned long base)
+{
+	/* Use a percentage-based approach to extend the sampling facility
+	 * buffer.  Accept up to 5% sample data loss.
+	 * Vary the extents between 1% to 5% of the current number of
+	 * sample-data-blocks.
+	 */
+	if (ratio <= 5)
+		return 0;
+	if (ratio <= 25)
+		return min_percent(1, base, 1);
+	if (ratio <= 50)
+		return min_percent(1, base, 1);
+	if (ratio <= 75)
+		return min_percent(2, base, 2);
+	if (ratio <= 100)
+		return min_percent(3, base, 3);
+	if (ratio <= 250)
+		return min_percent(4, base, 4);
+
+	return min_percent(5, base, 8);
+}
+
+static void sfb_account_overflows(struct cpu_hw_sf *cpuhw,
+				  struct hw_perf_event *hwc)
+{
+	unsigned long ratio, num;
+
+	if (!OVERFLOW_REG(hwc))
+		return;
+
+	/* The sample_overflow contains the average number of sample data
+	 * that has been lost because sample-data-blocks were full.
+	 *
+	 * Calculate the total number of sample data entries that has been
+	 * discarded.  Then calculate the ratio of lost samples to total samples
+	 * per second in percent.
+	 */
+	ratio = DIV_ROUND_UP(100 * OVERFLOW_REG(hwc) * cpuhw->sfb.num_sdb,
+			     sample_rate_to_freq(&cpuhw->qsi, SAMPL_RATE(hwc)));
+
+	/* Compute number of sample-data-blocks */
+	num = compute_sfb_extent(ratio, cpuhw->sfb.num_sdb);
+	if (num)
+		sfb_account_allocs(num, hwc);
+
+	debug_sprintf_event(sfdbg, 5, "sfb: overflow: overflow=%llu ratio=%lu"
+			    " num=%lu\n", OVERFLOW_REG(hwc), ratio, num);
+	OVERFLOW_REG(hwc) = 0;
+}
+
+/* extend_sampling_buffer() - Extend sampling buffer
+ * @sfb:	Sampling buffer structure (for local CPU)
+ * @hwc:	Perf event hardware structure
+ *
+ * Use this function to extend the sampling buffer based on the overflow counter
+ * and postponed allocation extents stored in the specified Perf event hardware.
+ *
+ * Important: This function disables the sampling facility in order to safely
+ *	      change the sampling buffer structure.  Do not call this function
+ *	      when the PMU is active.
+ */
+static void extend_sampling_buffer(struct sf_buffer *sfb,
+				   struct hw_perf_event *hwc)
+{
+	unsigned long num, num_old;
+	int rc;
+
+	num = sfb_pending_allocs(sfb, hwc);
+	if (!num)
+		return;
+	num_old = sfb->num_sdb;
+
+	/* Disable the sampling facility to reset any states and also
+	 * clear pending measurement alerts.
+	 */
+	sf_disable();
+
+	/* Extend the sampling buffer.
+	 * This memory allocation typically happens in an atomic context when
+	 * called by perf.  Because this is a reallocation, it is fine if the
+	 * new SDB-request cannot be satisfied immediately.
+	 */
+	rc = realloc_sampling_buffer(sfb, num, GFP_ATOMIC);
+	if (rc)
+		debug_sprintf_event(sfdbg, 5, "sfb: extend: realloc "
+				    "failed with rc=%i\n", rc);
+
+	if (sfb_has_pending_allocs(sfb, hwc))
+		debug_sprintf_event(sfdbg, 5, "sfb: extend: "
+				    "req=%lu alloc=%lu remaining=%lu\n",
+				    num, sfb->num_sdb - num_old,
+				    sfb_pending_allocs(sfb, hwc));
+}
+
+
+/* Number of perf events counting hardware events */
+static atomic_t num_events;
+/* Used to avoid races in calling reserve/release_cpumf_hardware */
+static DEFINE_MUTEX(pmc_reserve_mutex);
+
+#define PMC_INIT      0
+#define PMC_RELEASE   1
+#define PMC_FAILURE   2
+static void setup_pmc_cpu(void *flags)
+{
+	int err;
+	struct cpu_hw_sf *cpusf = this_cpu_ptr(&cpu_hw_sf);
+
+	err = 0;
+	switch (*((int *) flags)) {
+	case PMC_INIT:
+		memset(cpusf, 0, sizeof(*cpusf));
+		err = qsi(&cpusf->qsi);
+		if (err)
+			break;
+		cpusf->flags |= PMU_F_RESERVED;
+		err = sf_disable();
+		if (err)
+			pr_err("Switching off the sampling facility failed "
+			       "with rc=%i\n", err);
+		debug_sprintf_event(sfdbg, 5,
+				    "setup_pmc_cpu: initialized: cpuhw=%p\n", cpusf);
+		break;
+	case PMC_RELEASE:
+		cpusf->flags &= ~PMU_F_RESERVED;
+		err = sf_disable();
+		if (err) {
+			pr_err("Switching off the sampling facility failed "
+			       "with rc=%i\n", err);
+		} else
+			deallocate_buffers(cpusf);
+		debug_sprintf_event(sfdbg, 5,
+				    "setup_pmc_cpu: released: cpuhw=%p\n", cpusf);
+		break;
+	}
+	if (err)
+		*((int *) flags) |= PMC_FAILURE;
+}
+
+static void release_pmc_hardware(void)
+{
+	int flags = PMC_RELEASE;
+
+	irq_subclass_unregister(IRQ_SUBCLASS_MEASUREMENT_ALERT);
+	on_each_cpu(setup_pmc_cpu, &flags, 1);
+	perf_release_sampling();
+}
+
+static int reserve_pmc_hardware(void)
+{
+	int flags = PMC_INIT;
+	int err;
+
+	err = perf_reserve_sampling();
+	if (err)
+		return err;
+	on_each_cpu(setup_pmc_cpu, &flags, 1);
+	if (flags & PMC_FAILURE) {
+		release_pmc_hardware();
+		return -ENODEV;
+	}
+	irq_subclass_register(IRQ_SUBCLASS_MEASUREMENT_ALERT);
+
+	return 0;
+}
+
+static void hw_perf_event_destroy(struct perf_event *event)
+{
+	/* Free raw sample buffer */
+	if (RAWSAMPLE_REG(&event->hw))
+		kfree((void *) RAWSAMPLE_REG(&event->hw));
+
+	/* Release PMC if this is the last perf 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);
+	}
+}
+
+static void hw_init_period(struct hw_perf_event *hwc, u64 period)
+{
+	hwc->sample_period = period;
+	hwc->last_period = hwc->sample_period;
+	local64_set(&hwc->period_left, hwc->sample_period);
+}
+
+static void hw_reset_registers(struct hw_perf_event *hwc,
+			       unsigned long *sdbt_origin)
+{
+	struct sf_raw_sample *sfr;
+
+	/* (Re)set to first sample-data-block-table */
+	TEAR_REG(hwc) = (unsigned long) sdbt_origin;
+
+	/* (Re)set raw sampling buffer register */
+	sfr = (struct sf_raw_sample *) RAWSAMPLE_REG(hwc);
+	memset(&sfr->basic, 0, sizeof(sfr->basic));
+	memset(&sfr->diag, 0, sfr->dsdes);
+}
+
+static unsigned long hw_limit_rate(const struct hws_qsi_info_block *si,
+				   unsigned long rate)
+{
+	return clamp_t(unsigned long, rate,
+		       si->min_sampl_rate, si->max_sampl_rate);
+}
+
+static int __hw_perf_event_init(struct perf_event *event)
+{
+	struct cpu_hw_sf *cpuhw;
+	struct hws_qsi_info_block si;
+	struct perf_event_attr *attr = &event->attr;
+	struct hw_perf_event *hwc = &event->hw;
+	unsigned long rate;
+	int cpu, err;
+
+	/* Reserve CPU-measurement sampling facility */
+	err = 0;
+	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;
+
+	if (err)
+		goto out;
+
+	/* Access per-CPU sampling information (query sampling info) */
+	/*
+	 * The event->cpu value can be -1 to count on every CPU, for example,
+	 * when attaching to a task.  If this is specified, use the query
+	 * sampling info from the current CPU, otherwise use event->cpu to
+	 * retrieve the per-CPU information.
+	 * Later, cpuhw indicates whether to allocate sampling buffers for a
+	 * particular CPU (cpuhw!=NULL) or each online CPU (cpuw==NULL).
+	 */
+	memset(&si, 0, sizeof(si));
+	cpuhw = NULL;
+	if (event->cpu == -1)
+		qsi(&si);
+	else {
+		/* Event is pinned to a particular CPU, retrieve the per-CPU
+		 * sampling structure for accessing the CPU-specific QSI.
+		 */
+		cpuhw = &per_cpu(cpu_hw_sf, event->cpu);
+		si = cpuhw->qsi;
+	}
+
+	/* Check sampling facility authorization and, if not authorized,
+	 * fall back to other PMUs.  It is safe to check any CPU because
+	 * the authorization is identical for all configured CPUs.
+	 */
+	if (!si.as) {
+		err = -ENOENT;
+		goto out;
+	}
+
+	/* Always enable basic sampling */
+	SAMPL_FLAGS(hwc) = PERF_CPUM_SF_BASIC_MODE;
+
+	/* Check if diagnostic sampling is requested.  Deny if the required
+	 * sampling authorization is missing.
+	 */
+	if (attr->config == PERF_EVENT_CPUM_SF_DIAG) {
+		if (!si.ad) {
+			err = -EPERM;
+			goto out;
+		}
+		SAMPL_FLAGS(hwc) |= PERF_CPUM_SF_DIAG_MODE;
+	}
+
+	/* Check and set other sampling flags */
+	if (attr->config1 & PERF_CPUM_SF_FULL_BLOCKS)
+		SAMPL_FLAGS(hwc) |= PERF_CPUM_SF_FULL_BLOCKS;
+
+	/* The sampling information (si) contains information about the
+	 * min/max sampling intervals and the CPU speed.  So calculate the
+	 * correct sampling interval and avoid the whole period adjust
+	 * feedback loop.
+	 */
+	rate = 0;
+	if (attr->freq) {
+		rate = freq_to_sample_rate(&si, attr->sample_freq);
+		rate = hw_limit_rate(&si, rate);
+		attr->freq = 0;
+		attr->sample_period = rate;
+	} else {
+		/* The min/max sampling rates specifies the valid range
+		 * of sample periods.  If the specified sample period is
+		 * out of range, limit the period to the range boundary.
+		 */
+		rate = hw_limit_rate(&si, hwc->sample_period);
+
+		/* The perf core maintains a maximum sample rate that is
+		 * configurable through the sysctl interface.  Ensure the
+		 * sampling rate does not exceed this value.  This also helps
+		 * to avoid throttling when pushing samples with
+		 * perf_event_overflow().
+		 */
+		if (sample_rate_to_freq(&si, rate) >
+		      sysctl_perf_event_sample_rate) {
+			err = -EINVAL;
+			debug_sprintf_event(sfdbg, 1, "Sampling rate exceeds maximum perf sample rate\n");
+			goto out;
+		}
+	}
+	SAMPL_RATE(hwc) = rate;
+	hw_init_period(hwc, SAMPL_RATE(hwc));
+
+	/* Initialize sample data overflow accounting */
+	hwc->extra_reg.reg = REG_OVERFLOW;
+	OVERFLOW_REG(hwc) = 0;
+
+	/* Allocate the per-CPU sampling buffer using the CPU information
+	 * from the event.  If the event is not pinned to a particular
+	 * CPU (event->cpu == -1; or cpuhw == NULL), allocate sampling
+	 * buffers for each online CPU.
+	 */
+	if (cpuhw)
+		/* Event is pinned to a particular CPU */
+		err = allocate_buffers(cpuhw, hwc);
+	else {
+		/* Event is not pinned, allocate sampling buffer on
+		 * each online CPU
+		 */
+		for_each_online_cpu(cpu) {
+			cpuhw = &per_cpu(cpu_hw_sf, cpu);
+			err = allocate_buffers(cpuhw, hwc);
+			if (err)
+				break;
+		}
+	}
+out:
+	return err;
+}
+
+static int cpumsf_pmu_event_init(struct perf_event *event)
+{
+	int err;
+
+	/* No support for taken branch sampling */
+	if (has_branch_stack(event))
+		return -EOPNOTSUPP;
+
+	switch (event->attr.type) {
+	case PERF_TYPE_RAW:
+		if ((event->attr.config != PERF_EVENT_CPUM_SF) &&
+		    (event->attr.config != PERF_EVENT_CPUM_SF_DIAG))
+			return -ENOENT;
+		break;
+	case PERF_TYPE_HARDWARE:
+		/* Support sampling of CPU cycles in addition to the
+		 * counter facility.  However, the counter facility
+		 * is more precise and, hence, restrict this PMU to
+		 * sampling events only.
+		 */
+		if (event->attr.config != PERF_COUNT_HW_CPU_CYCLES)
+			return -ENOENT;
+		if (!is_sampling_event(event))
+			return -ENOENT;
+		break;
+	default:
+		return -ENOENT;
+	}
+
+	/* Check online status of the CPU to which the event is pinned */
+	if (event->cpu >= nr_cpumask_bits ||
+	    (event->cpu >= 0 && !cpu_online(event->cpu)))
+		return -ENODEV;
+
+	/* Force reset of idle/hv excludes regardless of what the
+	 * user requested.
+	 */
+	if (event->attr.exclude_hv)
+		event->attr.exclude_hv = 0;
+	if (event->attr.exclude_idle)
+		event->attr.exclude_idle = 0;
+
+	err = __hw_perf_event_init(event);
+	if (unlikely(err))
+		if (event->destroy)
+			event->destroy(event);
+	return err;
+}
+
+static void cpumsf_pmu_enable(struct pmu *pmu)
+{
+	struct cpu_hw_sf *cpuhw = this_cpu_ptr(&cpu_hw_sf);
+	struct hw_perf_event *hwc;
+	int err;
+
+	if (cpuhw->flags & PMU_F_ENABLED)
+		return;
+
+	if (cpuhw->flags & PMU_F_ERR_MASK)
+		return;
+
+	/* Check whether to extent the sampling buffer.
+	 *
+	 * Two conditions trigger an increase of the sampling buffer for a
+	 * perf event:
+	 *    1. Postponed buffer allocations from the event initialization.
+	 *    2. Sampling overflows that contribute to pending allocations.
+	 *
+	 * Note that the extend_sampling_buffer() function disables the sampling
+	 * facility, but it can be fully re-enabled using sampling controls that
+	 * have been saved in cpumsf_pmu_disable().
+	 */
+	if (cpuhw->event) {
+		hwc = &cpuhw->event->hw;
+		/* Account number of overflow-designated buffer extents */
+		sfb_account_overflows(cpuhw, hwc);
+		if (sfb_has_pending_allocs(&cpuhw->sfb, hwc))
+			extend_sampling_buffer(&cpuhw->sfb, hwc);
+	}
+
+	/* (Re)enable the PMU and sampling facility */
+	cpuhw->flags |= PMU_F_ENABLED;
+	barrier();
+
+	err = lsctl(&cpuhw->lsctl);
+	if (err) {
+		cpuhw->flags &= ~PMU_F_ENABLED;
+		pr_err("Loading sampling controls failed: op=%i err=%i\n",
+			1, err);
+		return;
+	}
+
+	debug_sprintf_event(sfdbg, 6, "pmu_enable: es=%i cs=%i ed=%i cd=%i "
+			    "tear=%p dear=%p\n", cpuhw->lsctl.es, cpuhw->lsctl.cs,
+			    cpuhw->lsctl.ed, cpuhw->lsctl.cd,
+			    (void *) cpuhw->lsctl.tear, (void *) cpuhw->lsctl.dear);
+}
+
+static void cpumsf_pmu_disable(struct pmu *pmu)
+{
+	struct cpu_hw_sf *cpuhw = this_cpu_ptr(&cpu_hw_sf);
+	struct hws_lsctl_request_block inactive;
+	struct hws_qsi_info_block si;
+	int err;
+
+	if (!(cpuhw->flags & PMU_F_ENABLED))
+		return;
+
+	if (cpuhw->flags & PMU_F_ERR_MASK)
+		return;
+
+	/* Switch off sampling activation control */
+	inactive = cpuhw->lsctl;
+	inactive.cs = 0;
+	inactive.cd = 0;
+
+	err = lsctl(&inactive);
+	if (err) {
+		pr_err("Loading sampling controls failed: op=%i err=%i\n",
+			2, err);
+		return;
+	}
+
+	/* Save state of TEAR and DEAR register contents */
+	if (!qsi(&si)) {
+		/* TEAR/DEAR values are valid only if the sampling facility is
+		 * enabled.  Note that cpumsf_pmu_disable() might be called even
+		 * for a disabled sampling facility because cpumsf_pmu_enable()
+		 * controls the enable/disable state.
+		 */
+		if (si.es) {
+			cpuhw->lsctl.tear = si.tear;
+			cpuhw->lsctl.dear = si.dear;
+		}
+	} else
+		debug_sprintf_event(sfdbg, 3, "cpumsf_pmu_disable: "
+				    "qsi() failed with err=%i\n", err);
+
+	cpuhw->flags &= ~PMU_F_ENABLED;
+}
+
+/* perf_exclude_event() - Filter event
+ * @event:	The perf event
+ * @regs:	pt_regs structure
+ * @sde_regs:	Sample-data-entry (sde) regs structure
+ *
+ * Filter perf events according to their exclude specification.
+ *
+ * Return non-zero if the event shall be excluded.
+ */
+static int perf_exclude_event(struct perf_event *event, struct pt_regs *regs,
+			      struct perf_sf_sde_regs *sde_regs)
+{
+	if (event->attr.exclude_user && user_mode(regs))
+		return 1;
+	if (event->attr.exclude_kernel && !user_mode(regs))
+		return 1;
+	if (event->attr.exclude_guest && sde_regs->in_guest)
+		return 1;
+	if (event->attr.exclude_host && !sde_regs->in_guest)
+		return 1;
+	return 0;
+}
+
+/* perf_push_sample() - Push samples to perf
+ * @event:	The perf event
+ * @sample:	Hardware sample data
+ *
+ * Use the hardware sample data to create perf event sample.  The sample
+ * is the pushed to the event subsystem and the function checks for
+ * possible event overflows.  If an event overflow occurs, the PMU is
+ * stopped.
+ *
+ * Return non-zero if an event overflow occurred.
+ */
+static int perf_push_sample(struct perf_event *event, struct sf_raw_sample *sfr)
+{
+	int overflow;
+	struct pt_regs regs;
+	struct perf_sf_sde_regs *sde_regs;
+	struct perf_sample_data data;
+	struct perf_raw_record raw;
+
+	/* Setup perf sample */
+	perf_sample_data_init(&data, 0, event->hw.last_period);
+	raw.size = sfr->size;
+	raw.data = sfr;
+	data.raw = &raw;
+
+	/* Setup pt_regs to look like an CPU-measurement external interrupt
+	 * using the Program Request Alert code.  The regs.int_parm_long
+	 * field which is unused contains additional sample-data-entry related
+	 * indicators.
+	 */
+	memset(&regs, 0, sizeof(regs));
+	regs.int_code = 0x1407;
+	regs.int_parm = CPU_MF_INT_SF_PRA;
+	sde_regs = (struct perf_sf_sde_regs *) &regs.int_parm_long;
+
+	regs.psw.addr = sfr->basic.ia;
+	if (sfr->basic.T)
+		regs.psw.mask |= PSW_MASK_DAT;
+	if (sfr->basic.W)
+		regs.psw.mask |= PSW_MASK_WAIT;
+	if (sfr->basic.P)
+		regs.psw.mask |= PSW_MASK_PSTATE;
+	switch (sfr->basic.AS) {
+	case 0x0:
+		regs.psw.mask |= PSW_ASC_PRIMARY;
+		break;
+	case 0x1:
+		regs.psw.mask |= PSW_ASC_ACCREG;
+		break;
+	case 0x2:
+		regs.psw.mask |= PSW_ASC_SECONDARY;
+		break;
+	case 0x3:
+		regs.psw.mask |= PSW_ASC_HOME;
+		break;
+	}
+
+	/* The host-program-parameter (hpp) contains the sie control
+	 * block that is set by sie64a() in entry64.S.	Check if hpp
+	 * refers to a valid control block and set sde_regs flags
+	 * accordingly.  This would allow to use hpp values for other
+	 * purposes too.
+	 * For now, simply use a non-zero value as guest indicator.
+	 */
+	if (sfr->basic.hpp)
+		sde_regs->in_guest = 1;
+
+	overflow = 0;
+	if (perf_exclude_event(event, &regs, sde_regs))
+		goto out;
+	if (perf_event_overflow(event, &data, &regs)) {
+		overflow = 1;
+		event->pmu->stop(event, 0);
+	}
+	perf_event_update_userpage(event);
+out:
+	return overflow;
+}
+
+static void perf_event_count_update(struct perf_event *event, u64 count)
+{
+	local64_add(count, &event->count);
+}
+
+static int sample_format_is_valid(struct hws_combined_entry *sample,
+				   unsigned int flags)
+{
+	if (likely(flags & PERF_CPUM_SF_BASIC_MODE))
+		/* Only basic-sampling data entries with data-entry-format
+		 * version of 0x0001 can be processed.
+		 */
+		if (sample->basic.def != 0x0001)
+			return 0;
+	if (flags & PERF_CPUM_SF_DIAG_MODE)
+		/* The data-entry-format number of diagnostic-sampling data
+		 * entries can vary.  Because diagnostic data is just passed
+		 * through, do only a sanity check on the DEF.
+		 */
+		if (sample->diag.def < 0x8001)
+			return 0;
+	return 1;
+}
+
+static int sample_is_consistent(struct hws_combined_entry *sample,
+				unsigned long flags)
+{
+	/* This check applies only to basic-sampling data entries of potentially
+	 * combined-sampling data entries.  Invalid entries cannot be processed
+	 * by the PMU and, thus, do not deliver an associated
+	 * diagnostic-sampling data entry.
+	 */
+	if (unlikely(!(flags & PERF_CPUM_SF_BASIC_MODE)))
+		return 0;
+	/*
+	 * Samples are skipped, if they are invalid or for which the
+	 * instruction address is not predictable, i.e., the wait-state bit is
+	 * set.
+	 */
+	if (sample->basic.I || sample->basic.W)
+		return 0;
+	return 1;
+}
+
+static void reset_sample_slot(struct hws_combined_entry *sample,
+			      unsigned long flags)
+{
+	if (likely(flags & PERF_CPUM_SF_BASIC_MODE))
+		sample->basic.def = 0;
+	if (flags & PERF_CPUM_SF_DIAG_MODE)
+		sample->diag.def = 0;
+}
+
+static void sfr_store_sample(struct sf_raw_sample *sfr,
+			     struct hws_combined_entry *sample)
+{
+	if (likely(sfr->format & PERF_CPUM_SF_BASIC_MODE))
+		sfr->basic = sample->basic;
+	if (sfr->format & PERF_CPUM_SF_DIAG_MODE)
+		memcpy(&sfr->diag, &sample->diag, sfr->dsdes);
+}
+
+static void debug_sample_entry(struct hws_combined_entry *sample,
+			       struct hws_trailer_entry *te,
+			       unsigned long flags)
+{
+	debug_sprintf_event(sfdbg, 4, "hw_collect_samples: Found unknown "
+			    "sampling data entry: te->f=%i basic.def=%04x (%p)"
+			    " diag.def=%04x (%p)\n", te->f,
+			    sample->basic.def, &sample->basic,
+			    (flags & PERF_CPUM_SF_DIAG_MODE)
+					? sample->diag.def : 0xFFFF,
+			    (flags & PERF_CPUM_SF_DIAG_MODE)
+					?  &sample->diag : NULL);
+}
+
+/* hw_collect_samples() - Walk through a sample-data-block and collect samples
+ * @event:	The perf event
+ * @sdbt:	Sample-data-block table
+ * @overflow:	Event overflow counter
+ *
+ * Walks through a sample-data-block and collects sampling data entries that are
+ * then pushed to the perf event subsystem.  Depending on the sampling function,
+ * there can be either basic-sampling or combined-sampling data entries.  A
+ * combined-sampling data entry consists of a basic- and a diagnostic-sampling
+ * data entry.	The sampling function is determined by the flags in the perf
+ * event hardware structure.  The function always works with a combined-sampling
+ * data entry but ignores the the diagnostic portion if it is not available.
+ *
+ * Note that the implementation focuses on basic-sampling data entries and, if
+ * such an entry is not valid, the entire combined-sampling data entry is
+ * ignored.
+ *
+ * The overflow variables counts the number of samples that has been discarded
+ * due to a perf event overflow.
+ */
+static void hw_collect_samples(struct perf_event *event, unsigned long *sdbt,
+			       unsigned long long *overflow)
+{
+	unsigned long flags = SAMPL_FLAGS(&event->hw);
+	struct hws_combined_entry *sample;
+	struct hws_trailer_entry *te;
+	struct sf_raw_sample *sfr;
+	size_t sample_size;
+
+	/* Prepare and initialize raw sample data */
+	sfr = (struct sf_raw_sample *) RAWSAMPLE_REG(&event->hw);
+	sfr->format = flags & PERF_CPUM_SF_MODE_MASK;
+
+	sample_size = event_sample_size(&event->hw);
+	te = (struct hws_trailer_entry *) trailer_entry_ptr(*sdbt);
+	sample = (struct hws_combined_entry *) *sdbt;
+	while ((unsigned long *) sample < (unsigned long *) te) {
+		/* Check for an empty sample */
+		if (!sample->basic.def)
+			break;
+
+		/* Update perf event period */
+		perf_event_count_update(event, SAMPL_RATE(&event->hw));
+
+		/* Check sampling data entry */
+		if (sample_format_is_valid(sample, flags)) {
+			/* If an event overflow occurred, the PMU is stopped to
+			 * throttle event delivery.  Remaining sample data is
+			 * discarded.
+			 */
+			if (!*overflow) {
+				if (sample_is_consistent(sample, flags)) {
+					/* Deliver sample data to perf */
+					sfr_store_sample(sfr, sample);
+					*overflow = perf_push_sample(event, sfr);
+				}
+			} else
+				/* Count discarded samples */
+				*overflow += 1;
+		} else {
+			debug_sample_entry(sample, te, flags);
+			/* Sample slot is not yet written or other record.
+			 *
+			 * This condition can occur if the buffer was reused
+			 * from a combined basic- and diagnostic-sampling.
+			 * If only basic-sampling is then active, entries are
+			 * written into the larger diagnostic entries.
+			 * This is typically the case for sample-data-blocks
+			 * that are not full.  Stop processing if the first
+			 * invalid format was detected.
+			 */
+			if (!te->f)
+				break;
+		}
+
+		/* Reset sample slot and advance to next sample */
+		reset_sample_slot(sample, flags);
+		sample += sample_size;
+	}
+}
+
+/* hw_perf_event_update() - Process sampling buffer
+ * @event:	The perf event
+ * @flush_all:	Flag to also flush partially filled sample-data-blocks
+ *
+ * Processes the sampling buffer and create perf event samples.
+ * The sampling buffer position are retrieved and saved in the TEAR_REG
+ * register of the specified perf event.
+ *
+ * Only full sample-data-blocks are processed.	Specify the flash_all flag
+ * to also walk through partially filled sample-data-blocks.  It is ignored
+ * if PERF_CPUM_SF_FULL_BLOCKS is set.	The PERF_CPUM_SF_FULL_BLOCKS flag
+ * enforces the processing of full sample-data-blocks only (trailer entries
+ * with the block-full-indicator bit set).
+ */
+static void hw_perf_event_update(struct perf_event *event, int flush_all)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	struct hws_trailer_entry *te;
+	unsigned long *sdbt;
+	unsigned long long event_overflow, sampl_overflow, num_sdb, te_flags;
+	int done;
+
+	if (flush_all && SDB_FULL_BLOCKS(hwc))
+		flush_all = 0;
+
+	sdbt = (unsigned long *) TEAR_REG(hwc);
+	done = event_overflow = sampl_overflow = num_sdb = 0;
+	while (!done) {
+		/* Get the trailer entry of the sample-data-block */
+		te = (struct hws_trailer_entry *) trailer_entry_ptr(*sdbt);
+
+		/* Leave loop if no more work to do (block full indicator) */
+		if (!te->f) {
+			done = 1;
+			if (!flush_all)
+				break;
+		}
+
+		/* Check the sample overflow count */
+		if (te->overflow)
+			/* Account sample overflows and, if a particular limit
+			 * is reached, extend the sampling buffer.
+			 * For details, see sfb_account_overflows().
+			 */
+			sampl_overflow += te->overflow;
+
+		/* Timestamps are valid for full sample-data-blocks only */
+		debug_sprintf_event(sfdbg, 6, "hw_perf_event_update: sdbt=%p "
+				    "overflow=%llu timestamp=0x%llx\n",
+				    sdbt, te->overflow,
+				    (te->f) ? trailer_timestamp(te) : 0ULL);
+
+		/* Collect all samples from a single sample-data-block and
+		 * flag if an (perf) event overflow happened.  If so, the PMU
+		 * is stopped and remaining samples will be discarded.
+		 */
+		hw_collect_samples(event, sdbt, &event_overflow);
+		num_sdb++;
+
+		/* Reset trailer (using compare-double-and-swap) */
+		do {
+			te_flags = te->flags & ~SDB_TE_BUFFER_FULL_MASK;
+			te_flags |= SDB_TE_ALERT_REQ_MASK;
+		} while (!cmpxchg_double(&te->flags, &te->overflow,
+					 te->flags, te->overflow,
+					 te_flags, 0ULL));
+
+		/* Advance to next sample-data-block */
+		sdbt++;
+		if (is_link_entry(sdbt))
+			sdbt = get_next_sdbt(sdbt);
+
+		/* Update event hardware registers */
+		TEAR_REG(hwc) = (unsigned long) sdbt;
+
+		/* Stop processing sample-data if all samples of the current
+		 * sample-data-block were flushed even if it was not full.
+		 */
+		if (flush_all && done)
+			break;
+
+		/* If an event overflow happened, discard samples by
+		 * processing any remaining sample-data-blocks.
+		 */
+		if (event_overflow)
+			flush_all = 1;
+	}
+
+	/* Account sample overflows in the event hardware structure */
+	if (sampl_overflow)
+		OVERFLOW_REG(hwc) = DIV_ROUND_UP(OVERFLOW_REG(hwc) +
+						 sampl_overflow, 1 + num_sdb);
+	if (sampl_overflow || event_overflow)
+		debug_sprintf_event(sfdbg, 4, "hw_perf_event_update: "
+				    "overflow stats: sample=%llu event=%llu\n",
+				    sampl_overflow, event_overflow);
+}
+
+static void cpumsf_pmu_read(struct perf_event *event)
+{
+	/* Nothing to do ... updates are interrupt-driven */
+}
+
+/* Activate sampling control.
+ * Next call of pmu_enable() starts sampling.
+ */
+static void cpumsf_pmu_start(struct perf_event *event, int flags)
+{
+	struct cpu_hw_sf *cpuhw = this_cpu_ptr(&cpu_hw_sf);
+
+	if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED)))
+		return;
+
+	if (flags & PERF_EF_RELOAD)
+		WARN_ON_ONCE(!(event->hw.state & PERF_HES_UPTODATE));
+
+	perf_pmu_disable(event->pmu);
+	event->hw.state = 0;
+	cpuhw->lsctl.cs = 1;
+	if (SAMPL_DIAG_MODE(&event->hw))
+		cpuhw->lsctl.cd = 1;
+	perf_pmu_enable(event->pmu);
+}
+
+/* Deactivate sampling control.
+ * Next call of pmu_enable() stops sampling.
+ */
+static void cpumsf_pmu_stop(struct perf_event *event, int flags)
+{
+	struct cpu_hw_sf *cpuhw = this_cpu_ptr(&cpu_hw_sf);
+
+	if (event->hw.state & PERF_HES_STOPPED)
+		return;
+
+	perf_pmu_disable(event->pmu);
+	cpuhw->lsctl.cs = 0;
+	cpuhw->lsctl.cd = 0;
+	event->hw.state |= PERF_HES_STOPPED;
+
+	if ((flags & PERF_EF_UPDATE) && !(event->hw.state & PERF_HES_UPTODATE)) {
+		hw_perf_event_update(event, 1);
+		event->hw.state |= PERF_HES_UPTODATE;
+	}
+	perf_pmu_enable(event->pmu);
+}
+
+static int cpumsf_pmu_add(struct perf_event *event, int flags)
+{
+	struct cpu_hw_sf *cpuhw = this_cpu_ptr(&cpu_hw_sf);
+	int err;
+
+	if (cpuhw->flags & PMU_F_IN_USE)
+		return -EAGAIN;
+
+	if (!cpuhw->sfb.sdbt)
+		return -EINVAL;
+
+	err = 0;
+	perf_pmu_disable(event->pmu);
+
+	event->hw.state = PERF_HES_UPTODATE | PERF_HES_STOPPED;
+
+	/* Set up sampling controls.  Always program the sampling register
+	 * using the SDB-table start.  Reset TEAR_REG event hardware register
+	 * that is used by hw_perf_event_update() to store the sampling buffer
+	 * position after samples have been flushed.
+	 */
+	cpuhw->lsctl.s = 0;
+	cpuhw->lsctl.h = 1;
+	cpuhw->lsctl.tear = (unsigned long) cpuhw->sfb.sdbt;
+	cpuhw->lsctl.dear = *(unsigned long *) cpuhw->sfb.sdbt;
+	cpuhw->lsctl.interval = SAMPL_RATE(&event->hw);
+	hw_reset_registers(&event->hw, cpuhw->sfb.sdbt);
+
+	/* Ensure sampling functions are in the disabled state.  If disabled,
+	 * switch on sampling enable control. */
+	if (WARN_ON_ONCE(cpuhw->lsctl.es == 1 || cpuhw->lsctl.ed == 1)) {
+		err = -EAGAIN;
+		goto out;
+	}
+	cpuhw->lsctl.es = 1;
+	if (SAMPL_DIAG_MODE(&event->hw))
+		cpuhw->lsctl.ed = 1;
+
+	/* Set in_use flag and store event */
+	cpuhw->event = event;
+	cpuhw->flags |= PMU_F_IN_USE;
+
+	if (flags & PERF_EF_START)
+		cpumsf_pmu_start(event, PERF_EF_RELOAD);
+out:
+	perf_event_update_userpage(event);
+	perf_pmu_enable(event->pmu);
+	return err;
+}
+
+static void cpumsf_pmu_del(struct perf_event *event, int flags)
+{
+	struct cpu_hw_sf *cpuhw = this_cpu_ptr(&cpu_hw_sf);
+
+	perf_pmu_disable(event->pmu);
+	cpumsf_pmu_stop(event, PERF_EF_UPDATE);
+
+	cpuhw->lsctl.es = 0;
+	cpuhw->lsctl.ed = 0;
+	cpuhw->flags &= ~PMU_F_IN_USE;
+	cpuhw->event = NULL;
+
+	perf_event_update_userpage(event);
+	perf_pmu_enable(event->pmu);
+}
+
+CPUMF_EVENT_ATTR(SF, SF_CYCLES_BASIC, PERF_EVENT_CPUM_SF);
+CPUMF_EVENT_ATTR(SF, SF_CYCLES_BASIC_DIAG, PERF_EVENT_CPUM_SF_DIAG);
+
+static struct attribute *cpumsf_pmu_events_attr[] = {
+	CPUMF_EVENT_PTR(SF, SF_CYCLES_BASIC),
+	NULL,
+	NULL,
+};
+
+PMU_FORMAT_ATTR(event, "config:0-63");
+
+static struct attribute *cpumsf_pmu_format_attr[] = {
+	&format_attr_event.attr,
+	NULL,
+};
+
+static struct attribute_group cpumsf_pmu_events_group = {
+	.name = "events",
+	.attrs = cpumsf_pmu_events_attr,
+};
+static struct attribute_group cpumsf_pmu_format_group = {
+	.name = "format",
+	.attrs = cpumsf_pmu_format_attr,
+};
+static const struct attribute_group *cpumsf_pmu_attr_groups[] = {
+	&cpumsf_pmu_events_group,
+	&cpumsf_pmu_format_group,
+	NULL,
+};
+
+static struct pmu cpumf_sampling = {
+	.pmu_enable   = cpumsf_pmu_enable,
+	.pmu_disable  = cpumsf_pmu_disable,
+
+	.event_init   = cpumsf_pmu_event_init,
+	.add	      = cpumsf_pmu_add,
+	.del	      = cpumsf_pmu_del,
+
+	.start	      = cpumsf_pmu_start,
+	.stop	      = cpumsf_pmu_stop,
+	.read	      = cpumsf_pmu_read,
+
+	.attr_groups  = cpumsf_pmu_attr_groups,
+};
+
+static void cpumf_measurement_alert(struct ext_code ext_code,
+				    unsigned int alert, unsigned long unused)
+{
+	struct cpu_hw_sf *cpuhw;
+
+	if (!(alert & CPU_MF_INT_SF_MASK))
+		return;
+	inc_irq_stat(IRQEXT_CMS);
+	cpuhw = this_cpu_ptr(&cpu_hw_sf);
+
+	/* 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;
+
+	/* The processing below must take care of multiple alert events that
+	 * might be indicated concurrently. */
+
+	/* Program alert request */
+	if (alert & CPU_MF_INT_SF_PRA) {
+		if (cpuhw->flags & PMU_F_IN_USE)
+			hw_perf_event_update(cpuhw->event, 0);
+		else
+			WARN_ON_ONCE(!(cpuhw->flags & PMU_F_IN_USE));
+	}
+
+	/* Report measurement alerts only for non-PRA codes */
+	if (alert != CPU_MF_INT_SF_PRA)
+		debug_sprintf_event(sfdbg, 6, "measurement alert: 0x%x\n", alert);
+
+	/* Sampling authorization change request */
+	if (alert & CPU_MF_INT_SF_SACA)
+		qsi(&cpuhw->qsi);
+
+	/* Loss of sample data due to high-priority machine activities */
+	if (alert & CPU_MF_INT_SF_LSDA) {
+		pr_err("Sample data was lost\n");
+		cpuhw->flags |= PMU_F_ERR_LSDA;
+		sf_disable();
+	}
+
+	/* Invalid sampling buffer entry */
+	if (alert & (CPU_MF_INT_SF_IAE|CPU_MF_INT_SF_ISE)) {
+		pr_err("A sampling buffer entry is incorrect (alert=0x%x)\n",
+		       alert);
+		cpuhw->flags |= PMU_F_ERR_IBE;
+		sf_disable();
+	}
+}
+
+static int cpumf_pmu_notifier(struct notifier_block *self,
+			      unsigned long action, void *hcpu)
+{
+	unsigned int cpu = (long) hcpu;
+	int flags;
+
+	/* Ignore the notification if no events are scheduled on the PMU.
+	 * This might be racy...
+	 */
+	if (!atomic_read(&num_events))
+		return NOTIFY_OK;
+
+	switch (action & ~CPU_TASKS_FROZEN) {
+	case CPU_ONLINE:
+	case CPU_ONLINE_FROZEN:
+		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 param_get_sfb_size(char *buffer, const struct kernel_param *kp)
+{
+	if (!cpum_sf_avail())
+		return -ENODEV;
+	return sprintf(buffer, "%lu,%lu", CPUM_SF_MIN_SDB, CPUM_SF_MAX_SDB);
+}
+
+static int param_set_sfb_size(const char *val, const struct kernel_param *kp)
+{
+	int rc;
+	unsigned long min, max;
+
+	if (!cpum_sf_avail())
+		return -ENODEV;
+	if (!val || !strlen(val))
+		return -EINVAL;
+
+	/* Valid parameter values: "min,max" or "max" */
+	min = CPUM_SF_MIN_SDB;
+	max = CPUM_SF_MAX_SDB;
+	if (strchr(val, ','))
+		rc = (sscanf(val, "%lu,%lu", &min, &max) == 2) ? 0 : -EINVAL;
+	else
+		rc = kstrtoul(val, 10, &max);
+
+	if (min < 2 || min >= max || max > get_num_physpages())
+		rc = -EINVAL;
+	if (rc)
+		return rc;
+
+	sfb_set_limits(min, max);
+	pr_info("The sampling buffer limits have changed to: "
+		"min=%lu max=%lu (diag=x%lu)\n",
+		CPUM_SF_MIN_SDB, CPUM_SF_MAX_SDB, CPUM_SF_SDB_DIAG_FACTOR);
+	return 0;
+}
+
+#define param_check_sfb_size(name, p) __param_check(name, p, void)
+static struct kernel_param_ops param_ops_sfb_size = {
+	.set = param_set_sfb_size,
+	.get = param_get_sfb_size,
+};
+
+#define RS_INIT_FAILURE_QSI	  0x0001
+#define RS_INIT_FAILURE_BSDES	  0x0002
+#define RS_INIT_FAILURE_ALRT	  0x0003
+#define RS_INIT_FAILURE_PERF	  0x0004
+static void __init pr_cpumsf_err(unsigned int reason)
+{
+	pr_err("Sampling facility support for perf is not available: "
+	       "reason=%04x\n", reason);
+}
+
+static int __init init_cpum_sampling_pmu(void)
+{
+	struct hws_qsi_info_block si;
+	int err;
+
+	if (!cpum_sf_avail())
+		return -ENODEV;
+
+	memset(&si, 0, sizeof(si));
+	if (qsi(&si)) {
+		pr_cpumsf_err(RS_INIT_FAILURE_QSI);
+		return -ENODEV;
+	}
+
+	if (si.bsdes != sizeof(struct hws_basic_entry)) {
+		pr_cpumsf_err(RS_INIT_FAILURE_BSDES);
+		return -EINVAL;
+	}
+
+	if (si.ad) {
+		sfb_set_limits(CPUM_SF_MIN_SDB, CPUM_SF_MAX_SDB);
+		cpumsf_pmu_events_attr[1] =
+			CPUMF_EVENT_PTR(SF, SF_CYCLES_BASIC_DIAG);
+	}
+
+	sfdbg = debug_register(KMSG_COMPONENT, 2, 1, 80);
+	if (!sfdbg)
+		pr_err("Registering for s390dbf failed\n");
+	debug_register_view(sfdbg, &debug_sprintf_view);
+
+	err = register_external_irq(EXT_IRQ_MEASURE_ALERT,
+				    cpumf_measurement_alert);
+	if (err) {
+		pr_cpumsf_err(RS_INIT_FAILURE_ALRT);
+		goto out;
+	}
+
+	err = perf_pmu_register(&cpumf_sampling, "cpum_sf", PERF_TYPE_RAW);
+	if (err) {
+		pr_cpumsf_err(RS_INIT_FAILURE_PERF);
+		unregister_external_irq(EXT_IRQ_MEASURE_ALERT,
+					cpumf_measurement_alert);
+		goto out;
+	}
+	perf_cpu_notifier(cpumf_pmu_notifier);
+out:
+	return err;
+}
+arch_initcall(init_cpum_sampling_pmu);
+core_param(cpum_sfb_size, CPUM_SF_MAX_SDB, sfb_size, 0640);
diff --git a/arch/s390/kernel/perf_event.c b/arch/s390/kernel/perf_event.c
new file mode 100644
index 000000000..61595c1f0
--- /dev/null
+++ b/arch/s390/kernel/perf_event.c
@@ -0,0 +1,324 @@
+/*
+ * Performance event support for s390x
+ *
+ *  Copyright IBM Corp. 2012, 2013
+ *  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/kvm_host.h>
+#include <linux/percpu.h>
+#include <linux/export.h>
+#include <linux/seq_file.h>
+#include <linux/spinlock.h>
+#include <linux/sysfs.h>
+#include <asm/irq.h>
+#include <asm/cpu_mf.h>
+#include <asm/lowcore.h>
+#include <asm/processor.h>
+#include <asm/sysinfo.h>
+
+const char *perf_pmu_name(void)
+{
+	if (cpum_cf_avail() || cpum_sf_avail())
+		return "CPU-Measurement Facilities (CPU-MF)";
+	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;
+	if (cpum_sf_avail())
+		num += PERF_CPUM_SF_MAX_CTR;
+
+	return num;
+}
+EXPORT_SYMBOL(perf_num_counters);
+
+static struct kvm_s390_sie_block *sie_block(struct pt_regs *regs)
+{
+	struct stack_frame *stack = (struct stack_frame *) regs->gprs[15];
+
+	if (!stack)
+		return NULL;
+
+	return (struct kvm_s390_sie_block *) stack->empty1[0];
+}
+
+static bool is_in_guest(struct pt_regs *regs)
+{
+	if (user_mode(regs))
+		return false;
+#if IS_ENABLED(CONFIG_KVM)
+	return instruction_pointer(regs) == (unsigned long) &sie_exit;
+#else
+	return false;
+#endif
+}
+
+static unsigned long guest_is_user_mode(struct pt_regs *regs)
+{
+	return sie_block(regs)->gpsw.mask & PSW_MASK_PSTATE;
+}
+
+static unsigned long instruction_pointer_guest(struct pt_regs *regs)
+{
+	return sie_block(regs)->gpsw.addr & PSW_ADDR_INSN;
+}
+
+unsigned long perf_instruction_pointer(struct pt_regs *regs)
+{
+	return is_in_guest(regs) ? instruction_pointer_guest(regs)
+				 : instruction_pointer(regs);
+}
+
+static unsigned long perf_misc_guest_flags(struct pt_regs *regs)
+{
+	return guest_is_user_mode(regs) ? PERF_RECORD_MISC_GUEST_USER
+					: PERF_RECORD_MISC_GUEST_KERNEL;
+}
+
+static unsigned long perf_misc_flags_sf(struct pt_regs *regs)
+{
+	struct perf_sf_sde_regs *sde_regs;
+	unsigned long flags;
+
+	sde_regs = (struct perf_sf_sde_regs *) &regs->int_parm_long;
+	if (sde_regs->in_guest)
+		flags = user_mode(regs) ? PERF_RECORD_MISC_GUEST_USER
+					: PERF_RECORD_MISC_GUEST_KERNEL;
+	else
+		flags = user_mode(regs) ? PERF_RECORD_MISC_USER
+					: PERF_RECORD_MISC_KERNEL;
+	return flags;
+}
+
+unsigned long perf_misc_flags(struct pt_regs *regs)
+{
+	/* Check if the cpum_sf PMU has created the pt_regs structure.
+	 * In this case, perf misc flags can be easily extracted.  Otherwise,
+	 * do regular checks on the pt_regs content.
+	 */
+	if (regs->int_code == 0x1407 && regs->int_parm == CPU_MF_INT_SF_PRA)
+		if (!regs->gprs[15])
+			return perf_misc_flags_sf(regs);
+
+	if (is_in_guest(regs))
+		return perf_misc_guest_flags(regs);
+
+	return user_mode(regs) ? PERF_RECORD_MISC_USER
+			       : PERF_RECORD_MISC_KERNEL;
+}
+
+static void print_debug_cf(void)
+{
+	struct cpumf_ctr_info cf_info;
+	int 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);
+}
+
+static void print_debug_sf(void)
+{
+	struct hws_qsi_info_block si;
+	int cpu = smp_processor_id();
+
+	memset(&si, 0, sizeof(si));
+	if (qsi(&si))
+		return;
+
+	pr_info("CPU[%i] CPUM_SF: basic=%i diag=%i min=%lu max=%lu cpu_speed=%u\n",
+		cpu, si.as, si.ad, si.min_sampl_rate, si.max_sampl_rate,
+		si.cpu_speed);
+
+	if (si.as)
+		pr_info("CPU[%i] CPUM_SF: Basic-sampling: a=%i e=%i c=%i"
+			" bsdes=%i tear=%016lx dear=%016lx\n", cpu,
+			si.as, si.es, si.cs, si.bsdes, si.tear, si.dear);
+	if (si.ad)
+		pr_info("CPU[%i] CPUM_SF: Diagnostic-sampling: a=%i e=%i c=%i"
+			" dsdes=%i tear=%016lx dear=%016lx\n", cpu,
+			si.ad, si.ed, si.cd, si.dsdes, si.tear, si.dear);
+}
+
+void perf_event_print_debug(void)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	if (cpum_cf_avail())
+		print_debug_cf();
+	if (cpum_sf_avail())
+		print_debug_sf();
+	local_irq_restore(flags);
+}
+
+/* Service level infrastructure */
+static void sl_print_counter(struct seq_file *m)
+{
+	struct cpumf_ctr_info ci;
+
+	memset(&ci, 0, sizeof(ci));
+	if (qctri(&ci))
+		return;
+
+	seq_printf(m, "CPU-MF: Counter facility: version=%u.%u "
+		   "authorization=%04x\n", ci.cfvn, ci.csvn, ci.auth_ctl);
+}
+
+static void sl_print_sampling(struct seq_file *m)
+{
+	struct hws_qsi_info_block si;
+
+	memset(&si, 0, sizeof(si));
+	if (qsi(&si))
+		return;
+
+	if (!si.as && !si.ad)
+		return;
+
+	seq_printf(m, "CPU-MF: Sampling facility: min_rate=%lu max_rate=%lu"
+		   " cpu_speed=%u\n", si.min_sampl_rate, si.max_sampl_rate,
+		   si.cpu_speed);
+	if (si.as)
+		seq_printf(m, "CPU-MF: Sampling facility: mode=basic"
+			   " sample_size=%u\n", si.bsdes);
+	if (si.ad)
+		seq_printf(m, "CPU-MF: Sampling facility: mode=diagnostic"
+			   " sample_size=%u\n", si.dsdes);
+}
+
+static void service_level_perf_print(struct seq_file *m,
+				     struct service_level *sl)
+{
+	if (cpum_cf_avail())
+		sl_print_counter(m);
+	if (cpum_sf_avail())
+		sl_print_sampling(m);
+}
+
+static struct service_level service_level_perf = {
+	.seq_print = service_level_perf_print,
+};
+
+static int __init service_level_perf_register(void)
+{
+	return register_service_level(&service_level_perf);
+}
+arch_initcall(service_level_perf_register);
+
+/* 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);
+}
+
+/* Perf defintions for PMU event attributes in sysfs */
+ssize_t cpumf_events_sysfs_show(struct device *dev,
+				struct device_attribute *attr, char *page)
+{
+	struct perf_pmu_events_attr *pmu_attr;
+
+	pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr);
+	return sprintf(page, "event=0x%04llx,name=%s\n",
+		       pmu_attr->id, attr->attr.name);
+}
+
+/* Reserve/release functions for sharing perf hardware */
+static DEFINE_SPINLOCK(perf_hw_owner_lock);
+static void *perf_sampling_owner;
+
+int perf_reserve_sampling(void)
+{
+	int err;
+
+	err = 0;
+	spin_lock(&perf_hw_owner_lock);
+	if (perf_sampling_owner) {
+		pr_warn("The sampling facility is already reserved by %p\n",
+			perf_sampling_owner);
+		err = -EBUSY;
+	} else
+		perf_sampling_owner = __builtin_return_address(0);
+	spin_unlock(&perf_hw_owner_lock);
+	return err;
+}
+EXPORT_SYMBOL(perf_reserve_sampling);
+
+void perf_release_sampling(void)
+{
+	spin_lock(&perf_hw_owner_lock);
+	WARN_ON(!perf_sampling_owner);
+	perf_sampling_owner = NULL;
+	spin_unlock(&perf_hw_owner_lock);
+}
+EXPORT_SYMBOL(perf_release_sampling);
diff --git a/arch/s390/kernel/pgm_check.S b/arch/s390/kernel/pgm_check.S
new file mode 100644
index 000000000..036aa01d0
--- /dev/null
+++ b/arch/s390/kernel/pgm_check.S
@@ -0,0 +1,146 @@
+/*
+ *    Program check table.
+ *
+ *    Copyright IBM Corp. 2012
+ */
+
+#include <linux/linkage.h>
+
+#define PGM_CHECK(handler)	.long handler
+#define PGM_CHECK_DEFAULT	PGM_CHECK(default_trap_handler)
+
+/*
+ * The program check table contains exactly 128 (0x00-0x7f) entries. Each
+ * line defines the function to be called corresponding to the program check
+ * interruption code.
+ */
+.section .rodata, "a"
+ENTRY(pgm_check_table)
+PGM_CHECK_DEFAULT			/* 00 */
+PGM_CHECK(illegal_op)			/* 01 */
+PGM_CHECK(privileged_op)		/* 02 */
+PGM_CHECK(execute_exception)		/* 03 */
+PGM_CHECK(do_protection_exception)	/* 04 */
+PGM_CHECK(addressing_exception)		/* 05 */
+PGM_CHECK(specification_exception)	/* 06 */
+PGM_CHECK(data_exception)		/* 07 */
+PGM_CHECK(overflow_exception)		/* 08 */
+PGM_CHECK(divide_exception)		/* 09 */
+PGM_CHECK(overflow_exception)		/* 0a */
+PGM_CHECK(divide_exception)		/* 0b */
+PGM_CHECK(hfp_overflow_exception)	/* 0c */
+PGM_CHECK(hfp_underflow_exception)	/* 0d */
+PGM_CHECK(hfp_significance_exception)	/* 0e */
+PGM_CHECK(hfp_divide_exception)		/* 0f */
+PGM_CHECK(do_dat_exception)		/* 10 */
+PGM_CHECK(do_dat_exception)		/* 11 */
+PGM_CHECK(translation_exception)	/* 12 */
+PGM_CHECK(special_op_exception)		/* 13 */
+PGM_CHECK_DEFAULT			/* 14 */
+PGM_CHECK(operand_exception)		/* 15 */
+PGM_CHECK_DEFAULT			/* 16 */
+PGM_CHECK_DEFAULT			/* 17 */
+PGM_CHECK(transaction_exception)	/* 18 */
+PGM_CHECK_DEFAULT			/* 19 */
+PGM_CHECK_DEFAULT			/* 1a */
+PGM_CHECK(vector_exception)		/* 1b */
+PGM_CHECK(space_switch_exception)	/* 1c */
+PGM_CHECK(hfp_sqrt_exception)		/* 1d */
+PGM_CHECK_DEFAULT			/* 1e */
+PGM_CHECK_DEFAULT			/* 1f */
+PGM_CHECK_DEFAULT			/* 20 */
+PGM_CHECK_DEFAULT			/* 21 */
+PGM_CHECK_DEFAULT			/* 22 */
+PGM_CHECK_DEFAULT			/* 23 */
+PGM_CHECK_DEFAULT			/* 24 */
+PGM_CHECK_DEFAULT			/* 25 */
+PGM_CHECK_DEFAULT			/* 26 */
+PGM_CHECK_DEFAULT			/* 27 */
+PGM_CHECK_DEFAULT			/* 28 */
+PGM_CHECK_DEFAULT			/* 29 */
+PGM_CHECK_DEFAULT			/* 2a */
+PGM_CHECK_DEFAULT			/* 2b */
+PGM_CHECK_DEFAULT			/* 2c */
+PGM_CHECK_DEFAULT			/* 2d */
+PGM_CHECK_DEFAULT			/* 2e */
+PGM_CHECK_DEFAULT			/* 2f */
+PGM_CHECK_DEFAULT			/* 30 */
+PGM_CHECK_DEFAULT			/* 31 */
+PGM_CHECK_DEFAULT			/* 32 */
+PGM_CHECK_DEFAULT			/* 33 */
+PGM_CHECK_DEFAULT			/* 34 */
+PGM_CHECK_DEFAULT			/* 35 */
+PGM_CHECK_DEFAULT			/* 36 */
+PGM_CHECK_DEFAULT			/* 37 */
+PGM_CHECK(do_dat_exception)		/* 38 */
+PGM_CHECK(do_dat_exception)		/* 39 */
+PGM_CHECK(do_dat_exception)		/* 3a */
+PGM_CHECK(do_dat_exception)		/* 3b */
+PGM_CHECK_DEFAULT			/* 3c */
+PGM_CHECK_DEFAULT			/* 3d */
+PGM_CHECK_DEFAULT			/* 3e */
+PGM_CHECK_DEFAULT			/* 3f */
+PGM_CHECK_DEFAULT			/* 40 */
+PGM_CHECK_DEFAULT			/* 41 */
+PGM_CHECK_DEFAULT			/* 42 */
+PGM_CHECK_DEFAULT			/* 43 */
+PGM_CHECK_DEFAULT			/* 44 */
+PGM_CHECK_DEFAULT			/* 45 */
+PGM_CHECK_DEFAULT			/* 46 */
+PGM_CHECK_DEFAULT			/* 47 */
+PGM_CHECK_DEFAULT			/* 48 */
+PGM_CHECK_DEFAULT			/* 49 */
+PGM_CHECK_DEFAULT			/* 4a */
+PGM_CHECK_DEFAULT			/* 4b */
+PGM_CHECK_DEFAULT			/* 4c */
+PGM_CHECK_DEFAULT			/* 4d */
+PGM_CHECK_DEFAULT			/* 4e */
+PGM_CHECK_DEFAULT			/* 4f */
+PGM_CHECK_DEFAULT			/* 50 */
+PGM_CHECK_DEFAULT			/* 51 */
+PGM_CHECK_DEFAULT			/* 52 */
+PGM_CHECK_DEFAULT			/* 53 */
+PGM_CHECK_DEFAULT			/* 54 */
+PGM_CHECK_DEFAULT			/* 55 */
+PGM_CHECK_DEFAULT			/* 56 */
+PGM_CHECK_DEFAULT			/* 57 */
+PGM_CHECK_DEFAULT			/* 58 */
+PGM_CHECK_DEFAULT			/* 59 */
+PGM_CHECK_DEFAULT			/* 5a */
+PGM_CHECK_DEFAULT			/* 5b */
+PGM_CHECK_DEFAULT			/* 5c */
+PGM_CHECK_DEFAULT			/* 5d */
+PGM_CHECK_DEFAULT			/* 5e */
+PGM_CHECK_DEFAULT			/* 5f */
+PGM_CHECK_DEFAULT			/* 60 */
+PGM_CHECK_DEFAULT			/* 61 */
+PGM_CHECK_DEFAULT			/* 62 */
+PGM_CHECK_DEFAULT			/* 63 */
+PGM_CHECK_DEFAULT			/* 64 */
+PGM_CHECK_DEFAULT			/* 65 */
+PGM_CHECK_DEFAULT			/* 66 */
+PGM_CHECK_DEFAULT			/* 67 */
+PGM_CHECK_DEFAULT			/* 68 */
+PGM_CHECK_DEFAULT			/* 69 */
+PGM_CHECK_DEFAULT			/* 6a */
+PGM_CHECK_DEFAULT			/* 6b */
+PGM_CHECK_DEFAULT			/* 6c */
+PGM_CHECK_DEFAULT			/* 6d */
+PGM_CHECK_DEFAULT			/* 6e */
+PGM_CHECK_DEFAULT			/* 6f */
+PGM_CHECK_DEFAULT			/* 70 */
+PGM_CHECK_DEFAULT			/* 71 */
+PGM_CHECK_DEFAULT			/* 72 */
+PGM_CHECK_DEFAULT			/* 73 */
+PGM_CHECK_DEFAULT			/* 74 */
+PGM_CHECK_DEFAULT			/* 75 */
+PGM_CHECK_DEFAULT			/* 76 */
+PGM_CHECK_DEFAULT			/* 77 */
+PGM_CHECK_DEFAULT			/* 78 */
+PGM_CHECK_DEFAULT			/* 79 */
+PGM_CHECK_DEFAULT			/* 7a */
+PGM_CHECK_DEFAULT			/* 7b */
+PGM_CHECK_DEFAULT			/* 7c */
+PGM_CHECK_DEFAULT			/* 7d */
+PGM_CHECK_DEFAULT			/* 7e */
+PGM_CHECK_DEFAULT			/* 7f */
diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c
new file mode 100644
index 000000000..dc5edc29b
--- /dev/null
+++ b/arch/s390/kernel/process.c
@@ -0,0 +1,226 @@
+/*
+ * This file handles the architecture dependent parts of process handling.
+ *
+ *    Copyright IBM Corp. 1999, 2009
+ *    Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>,
+ *		 Hartmut Penner <hp@de.ibm.com>,
+ *		 Denis Joseph Barrow,
+ */
+
+#include <linux/compiler.h>
+#include <linux/cpu.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/elfcore.h>
+#include <linux/smp.h>
+#include <linux/slab.h>
+#include <linux/interrupt.h>
+#include <linux/tick.h>
+#include <linux/personality.h>
+#include <linux/syscalls.h>
+#include <linux/compat.h>
+#include <linux/kprobes.h>
+#include <linux/random.h>
+#include <linux/module.h>
+#include <asm/io.h>
+#include <asm/processor.h>
+#include <asm/vtimer.h>
+#include <asm/exec.h>
+#include <asm/irq.h>
+#include <asm/nmi.h>
+#include <asm/smp.h>
+#include <asm/switch_to.h>
+#include <asm/runtime_instr.h>
+#include "entry.h"
+
+asmlinkage void ret_from_fork(void) asm ("ret_from_fork");
+
+/*
+ * Return saved PC of a blocked thread. used in kernel/sched.
+ * resume in entry.S does not create a new stack frame, it
+ * just stores the registers %r6-%r15 to the frame given by
+ * schedule. We want to return the address of the caller of
+ * schedule, so we have to walk the backchain one time to
+ * find the frame schedule() store its return address.
+ */
+unsigned long thread_saved_pc(struct task_struct *tsk)
+{
+	struct stack_frame *sf, *low, *high;
+
+	if (!tsk || !task_stack_page(tsk))
+		return 0;
+	low = task_stack_page(tsk);
+	high = (struct stack_frame *) task_pt_regs(tsk);
+	sf = (struct stack_frame *) (tsk->thread.ksp & PSW_ADDR_INSN);
+	if (sf <= low || sf > high)
+		return 0;
+	sf = (struct stack_frame *) (sf->back_chain & PSW_ADDR_INSN);
+	if (sf <= low || sf > high)
+		return 0;
+	return sf->gprs[8];
+}
+
+extern void kernel_thread_starter(void);
+
+/*
+ * Free current thread data structures etc..
+ */
+void exit_thread(void)
+{
+	exit_thread_runtime_instr();
+}
+
+void flush_thread(void)
+{
+}
+
+void release_thread(struct task_struct *dead_task)
+{
+}
+
+void arch_release_task_struct(struct task_struct *tsk)
+{
+	if (tsk->thread.vxrs)
+		kfree(tsk->thread.vxrs);
+}
+
+int copy_thread(unsigned long clone_flags, unsigned long new_stackp,
+		unsigned long arg, struct task_struct *p)
+{
+	struct thread_info *ti;
+	struct fake_frame
+	{
+		struct stack_frame sf;
+		struct pt_regs childregs;
+	} *frame;
+
+	frame = container_of(task_pt_regs(p), struct fake_frame, childregs);
+	p->thread.ksp = (unsigned long) frame;
+	/* Save access registers to new thread structure. */
+	save_access_regs(&p->thread.acrs[0]);
+	/* start new process with ar4 pointing to the correct address space */
+	p->thread.mm_segment = get_fs();
+	/* Don't copy debug registers */
+	memset(&p->thread.per_user, 0, sizeof(p->thread.per_user));
+	memset(&p->thread.per_event, 0, sizeof(p->thread.per_event));
+	clear_tsk_thread_flag(p, TIF_SINGLE_STEP);
+	/* Initialize per thread user and system timer values */
+	ti = task_thread_info(p);
+	ti->user_timer = 0;
+	ti->system_timer = 0;
+
+	frame->sf.back_chain = 0;
+	/* new return point is ret_from_fork */
+	frame->sf.gprs[8] = (unsigned long) ret_from_fork;
+	/* fake return stack for resume(), don't go back to schedule */
+	frame->sf.gprs[9] = (unsigned long) frame;
+
+	/* Store access registers to kernel stack of new process. */
+	if (unlikely(p->flags & PF_KTHREAD)) {
+		/* kernel thread */
+		memset(&frame->childregs, 0, sizeof(struct pt_regs));
+		frame->childregs.psw.mask = PSW_KERNEL_BITS | PSW_MASK_DAT |
+				PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK;
+		frame->childregs.psw.addr = PSW_ADDR_AMODE |
+				(unsigned long) kernel_thread_starter;
+		frame->childregs.gprs[9] = new_stackp; /* function */
+		frame->childregs.gprs[10] = arg;
+		frame->childregs.gprs[11] = (unsigned long) do_exit;
+		frame->childregs.orig_gpr2 = -1;
+
+		return 0;
+	}
+	frame->childregs = *current_pt_regs();
+	frame->childregs.gprs[2] = 0;	/* child returns 0 on fork. */
+	frame->childregs.flags = 0;
+	if (new_stackp)
+		frame->childregs.gprs[15] = new_stackp;
+
+	/* Don't copy runtime instrumentation info */
+	p->thread.ri_cb = NULL;
+	p->thread.ri_signum = 0;
+	frame->childregs.psw.mask &= ~PSW_MASK_RI;
+
+	/* Save the fpu registers to new thread structure. */
+	save_fp_ctl(&p->thread.fp_regs.fpc);
+	save_fp_regs(p->thread.fp_regs.fprs);
+	p->thread.fp_regs.pad = 0;
+	p->thread.vxrs = NULL;
+	/* Set a new TLS ?  */
+	if (clone_flags & CLONE_SETTLS) {
+		unsigned long tls = frame->childregs.gprs[6];
+		if (is_compat_task()) {
+			p->thread.acrs[0] = (unsigned int)tls;
+		} else {
+			p->thread.acrs[0] = (unsigned int)(tls >> 32);
+			p->thread.acrs[1] = (unsigned int)tls;
+		}
+	}
+	return 0;
+}
+
+asmlinkage void execve_tail(void)
+{
+	current->thread.fp_regs.fpc = 0;
+	asm volatile("sfpc %0,%0" : : "d" (0));
+}
+
+/*
+ * fill in the FPU structure for a core dump.
+ */
+int dump_fpu (struct pt_regs * regs, s390_fp_regs *fpregs)
+{
+	save_fp_ctl(&fpregs->fpc);
+	save_fp_regs(fpregs->fprs);
+	return 1;
+}
+EXPORT_SYMBOL(dump_fpu);
+
+unsigned long get_wchan(struct task_struct *p)
+{
+	struct stack_frame *sf, *low, *high;
+	unsigned long return_address;
+	int count;
+
+	if (!p || p == current || p->state == TASK_RUNNING || !task_stack_page(p))
+		return 0;
+	low = task_stack_page(p);
+	high = (struct stack_frame *) task_pt_regs(p);
+	sf = (struct stack_frame *) (p->thread.ksp & PSW_ADDR_INSN);
+	if (sf <= low || sf > high)
+		return 0;
+	for (count = 0; count < 16; count++) {
+		sf = (struct stack_frame *) (sf->back_chain & PSW_ADDR_INSN);
+		if (sf <= low || sf > high)
+			return 0;
+		return_address = sf->gprs[8] & PSW_ADDR_INSN;
+		if (!in_sched_functions(return_address))
+			return return_address;
+	}
+	return 0;
+}
+
+unsigned long arch_align_stack(unsigned long sp)
+{
+	if (!(current->personality & ADDR_NO_RANDOMIZE) && randomize_va_space)
+		sp -= get_random_int() & ~PAGE_MASK;
+	return sp & ~0xf;
+}
+
+static inline unsigned long brk_rnd(void)
+{
+	/* 8MB for 32bit, 1GB for 64bit */
+	if (is_32bit_task())
+		return (get_random_int() & 0x7ffUL) << PAGE_SHIFT;
+	else
+		return (get_random_int() & 0x3ffffUL) << PAGE_SHIFT;
+}
+
+unsigned long arch_randomize_brk(struct mm_struct *mm)
+{
+	unsigned long ret;
+
+	ret = PAGE_ALIGN(mm->brk + brk_rnd());
+	return (ret > mm->brk) ? ret : mm->brk;
+}
diff --git a/arch/s390/kernel/processor.c b/arch/s390/kernel/processor.c
new file mode 100644
index 000000000..dc488e13b
--- /dev/null
+++ b/arch/s390/kernel/processor.c
@@ -0,0 +1,103 @@
+/*
+ *  Copyright IBM Corp. 2008
+ *  Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com)
+ */
+
+#define KMSG_COMPONENT "cpu"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/seq_file.h>
+#include <linux/delay.h>
+#include <linux/cpu.h>
+#include <asm/elf.h>
+#include <asm/lowcore.h>
+#include <asm/param.h>
+#include <asm/smp.h>
+
+static DEFINE_PER_CPU(struct cpuid, cpu_id);
+
+void notrace cpu_relax(void)
+{
+	if (!smp_cpu_mtid && MACHINE_HAS_DIAG44)
+		asm volatile("diag 0,0,0x44");
+	barrier();
+}
+EXPORT_SYMBOL(cpu_relax);
+
+/*
+ * cpu_init - initializes state that is per-CPU.
+ */
+void cpu_init(void)
+{
+	struct cpuid *id = this_cpu_ptr(&cpu_id);
+
+	get_cpu_id(id);
+	atomic_inc(&init_mm.mm_count);
+	current->active_mm = &init_mm;
+	BUG_ON(current->mm);
+	enter_lazy_tlb(&init_mm, current);
+}
+
+/*
+ * show_cpuinfo - Get information on one CPU for use by procfs.
+ */
+static int show_cpuinfo(struct seq_file *m, void *v)
+{
+	static const char *hwcap_str[] = {
+		"esan3", "zarch", "stfle", "msa", "ldisp", "eimm", "dfp",
+		"edat", "etf3eh", "highgprs", "te", "vx"
+	};
+	unsigned long n = (unsigned long) v - 1;
+	int i;
+
+	if (!n) {
+		s390_adjust_jiffies();
+		seq_printf(m, "vendor_id       : IBM/S390\n"
+			   "# processors    : %i\n"
+			   "bogomips per cpu: %lu.%02lu\n",
+			   num_online_cpus(), loops_per_jiffy/(500000/HZ),
+			   (loops_per_jiffy/(5000/HZ))%100);
+		seq_puts(m, "features\t: ");
+		for (i = 0; i < ARRAY_SIZE(hwcap_str); i++)
+			if (hwcap_str[i] && (elf_hwcap & (1UL << i)))
+				seq_printf(m, "%s ", hwcap_str[i]);
+		seq_puts(m, "\n");
+		show_cacheinfo(m);
+	}
+	get_online_cpus();
+	if (cpu_online(n)) {
+		struct cpuid *id = &per_cpu(cpu_id, n);
+		seq_printf(m, "processor %li: "
+			   "version = %02X,  "
+			   "identification = %06X,  "
+			   "machine = %04X\n",
+			   n, id->version, id->ident, id->machine);
+	}
+	put_online_cpus();
+	return 0;
+}
+
+static void *c_start(struct seq_file *m, loff_t *pos)
+{
+	return *pos < nr_cpu_ids ? (void *)((unsigned long) *pos + 1) : NULL;
+}
+
+static void *c_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	++*pos;
+	return c_start(m, pos);
+}
+
+static void c_stop(struct seq_file *m, void *v)
+{
+}
+
+const struct seq_operations cpuinfo_op = {
+	.start	= c_start,
+	.next	= c_next,
+	.stop	= c_stop,
+	.show	= show_cpuinfo,
+};
+
diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c
new file mode 100644
index 000000000..d363c9c32
--- /dev/null
+++ b/arch/s390/kernel/ptrace.c
@@ -0,0 +1,1533 @@
+/*
+ *  Ptrace user space interface.
+ *
+ *    Copyright IBM Corp. 1999, 2010
+ *    Author(s): Denis Joseph Barrow
+ *               Martin Schwidefsky (schwidefsky@de.ibm.com)
+ */
+
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/smp.h>
+#include <linux/errno.h>
+#include <linux/ptrace.h>
+#include <linux/user.h>
+#include <linux/security.h>
+#include <linux/audit.h>
+#include <linux/signal.h>
+#include <linux/elf.h>
+#include <linux/regset.h>
+#include <linux/tracehook.h>
+#include <linux/seccomp.h>
+#include <linux/compat.h>
+#include <trace/syscall.h>
+#include <asm/segment.h>
+#include <asm/page.h>
+#include <asm/pgtable.h>
+#include <asm/pgalloc.h>
+#include <asm/uaccess.h>
+#include <asm/unistd.h>
+#include <asm/switch_to.h>
+#include "entry.h"
+
+#ifdef CONFIG_COMPAT
+#include "compat_ptrace.h"
+#endif
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/syscalls.h>
+
+void update_cr_regs(struct task_struct *task)
+{
+	struct pt_regs *regs = task_pt_regs(task);
+	struct thread_struct *thread = &task->thread;
+	struct per_regs old, new;
+
+	/* Take care of the enable/disable of transactional execution. */
+	if (MACHINE_HAS_TE || MACHINE_HAS_VX) {
+		unsigned long cr, cr_new;
+
+		__ctl_store(cr, 0, 0);
+		cr_new = cr;
+		if (MACHINE_HAS_TE) {
+			/* Set or clear transaction execution TXC bit 8. */
+			cr_new |= (1UL << 55);
+			if (task->thread.per_flags & PER_FLAG_NO_TE)
+				cr_new &= ~(1UL << 55);
+		}
+		if (MACHINE_HAS_VX) {
+			/* Enable/disable of vector extension */
+			cr_new &= ~(1UL << 17);
+			if (task->thread.vxrs)
+				cr_new |= (1UL << 17);
+		}
+		if (cr_new != cr)
+			__ctl_load(cr_new, 0, 0);
+		if (MACHINE_HAS_TE) {
+			/* Set/clear transaction execution TDC bits 62/63. */
+			__ctl_store(cr, 2, 2);
+			cr_new = cr & ~3UL;
+			if (task->thread.per_flags & PER_FLAG_TE_ABORT_RAND) {
+				if (task->thread.per_flags &
+				    PER_FLAG_TE_ABORT_RAND_TEND)
+					cr_new |= 1UL;
+				else
+					cr_new |= 2UL;
+			}
+			if (cr_new != cr)
+				__ctl_load(cr_new, 2, 2);
+		}
+	}
+	/* Copy user specified PER registers */
+	new.control = thread->per_user.control;
+	new.start = thread->per_user.start;
+	new.end = thread->per_user.end;
+
+	/* merge TIF_SINGLE_STEP into user specified PER registers. */
+	if (test_tsk_thread_flag(task, TIF_SINGLE_STEP) ||
+	    test_tsk_thread_flag(task, TIF_UPROBE_SINGLESTEP)) {
+		if (test_tsk_thread_flag(task, TIF_BLOCK_STEP))
+			new.control |= PER_EVENT_BRANCH;
+		else
+			new.control |= PER_EVENT_IFETCH;
+		new.control |= PER_CONTROL_SUSPENSION;
+		new.control |= PER_EVENT_TRANSACTION_END;
+		if (test_tsk_thread_flag(task, TIF_UPROBE_SINGLESTEP))
+			new.control |= PER_EVENT_IFETCH;
+		new.start = 0;
+		new.end = PSW_ADDR_INSN;
+	}
+
+	/* Take care of the PER enablement bit in the PSW. */
+	if (!(new.control & PER_EVENT_MASK)) {
+		regs->psw.mask &= ~PSW_MASK_PER;
+		return;
+	}
+	regs->psw.mask |= PSW_MASK_PER;
+	__ctl_store(old, 9, 11);
+	if (memcmp(&new, &old, sizeof(struct per_regs)) != 0)
+		__ctl_load(new, 9, 11);
+}
+
+void user_enable_single_step(struct task_struct *task)
+{
+	clear_tsk_thread_flag(task, TIF_BLOCK_STEP);
+	set_tsk_thread_flag(task, TIF_SINGLE_STEP);
+}
+
+void user_disable_single_step(struct task_struct *task)
+{
+	clear_tsk_thread_flag(task, TIF_BLOCK_STEP);
+	clear_tsk_thread_flag(task, TIF_SINGLE_STEP);
+}
+
+void user_enable_block_step(struct task_struct *task)
+{
+	set_tsk_thread_flag(task, TIF_SINGLE_STEP);
+	set_tsk_thread_flag(task, TIF_BLOCK_STEP);
+}
+
+/*
+ * Called by kernel/ptrace.c when detaching..
+ *
+ * Clear all debugging related fields.
+ */
+void ptrace_disable(struct task_struct *task)
+{
+	memset(&task->thread.per_user, 0, sizeof(task->thread.per_user));
+	memset(&task->thread.per_event, 0, sizeof(task->thread.per_event));
+	clear_tsk_thread_flag(task, TIF_SINGLE_STEP);
+	clear_pt_regs_flag(task_pt_regs(task), PIF_PER_TRAP);
+	task->thread.per_flags = 0;
+}
+
+#define __ADDR_MASK 7
+
+static inline unsigned long __peek_user_per(struct task_struct *child,
+					    addr_t addr)
+{
+	struct per_struct_kernel *dummy = NULL;
+
+	if (addr == (addr_t) &dummy->cr9)
+		/* Control bits of the active per set. */
+		return test_thread_flag(TIF_SINGLE_STEP) ?
+			PER_EVENT_IFETCH : child->thread.per_user.control;
+	else if (addr == (addr_t) &dummy->cr10)
+		/* Start address of the active per set. */
+		return test_thread_flag(TIF_SINGLE_STEP) ?
+			0 : child->thread.per_user.start;
+	else if (addr == (addr_t) &dummy->cr11)
+		/* End address of the active per set. */
+		return test_thread_flag(TIF_SINGLE_STEP) ?
+			PSW_ADDR_INSN : child->thread.per_user.end;
+	else if (addr == (addr_t) &dummy->bits)
+		/* Single-step bit. */
+		return test_thread_flag(TIF_SINGLE_STEP) ?
+			(1UL << (BITS_PER_LONG - 1)) : 0;
+	else if (addr == (addr_t) &dummy->starting_addr)
+		/* Start address of the user specified per set. */
+		return child->thread.per_user.start;
+	else if (addr == (addr_t) &dummy->ending_addr)
+		/* End address of the user specified per set. */
+		return child->thread.per_user.end;
+	else if (addr == (addr_t) &dummy->perc_atmid)
+		/* PER code, ATMID and AI of the last PER trap */
+		return (unsigned long)
+			child->thread.per_event.cause << (BITS_PER_LONG - 16);
+	else if (addr == (addr_t) &dummy->address)
+		/* Address of the last PER trap */
+		return child->thread.per_event.address;
+	else if (addr == (addr_t) &dummy->access_id)
+		/* Access id of the last PER trap */
+		return (unsigned long)
+			child->thread.per_event.paid << (BITS_PER_LONG - 8);
+	return 0;
+}
+
+/*
+ * Read the word at offset addr from the user area of a process. The
+ * trouble here is that the information is littered over different
+ * locations. The process registers are found on the kernel stack,
+ * the floating point stuff and the trace settings are stored in
+ * the task structure. In addition the different structures in
+ * struct user contain pad bytes that should be read as zeroes.
+ * Lovely...
+ */
+static unsigned long __peek_user(struct task_struct *child, addr_t addr)
+{
+	struct user *dummy = NULL;
+	addr_t offset, tmp;
+
+	if (addr < (addr_t) &dummy->regs.acrs) {
+		/*
+		 * psw and gprs are stored on the stack
+		 */
+		tmp = *(addr_t *)((addr_t) &task_pt_regs(child)->psw + addr);
+		if (addr == (addr_t) &dummy->regs.psw.mask) {
+			/* Return a clean psw mask. */
+			tmp &= PSW_MASK_USER | PSW_MASK_RI;
+			tmp |= PSW_USER_BITS;
+		}
+
+	} else if (addr < (addr_t) &dummy->regs.orig_gpr2) {
+		/*
+		 * access registers are stored in the thread structure
+		 */
+		offset = addr - (addr_t) &dummy->regs.acrs;
+		/*
+		 * Very special case: old & broken 64 bit gdb reading
+		 * from acrs[15]. Result is a 64 bit value. Read the
+		 * 32 bit acrs[15] value and shift it by 32. Sick...
+		 */
+		if (addr == (addr_t) &dummy->regs.acrs[15])
+			tmp = ((unsigned long) child->thread.acrs[15]) << 32;
+		else
+			tmp = *(addr_t *)((addr_t) &child->thread.acrs + offset);
+
+	} else if (addr == (addr_t) &dummy->regs.orig_gpr2) {
+		/*
+		 * orig_gpr2 is stored on the kernel stack
+		 */
+		tmp = (addr_t) task_pt_regs(child)->orig_gpr2;
+
+	} else if (addr < (addr_t) &dummy->regs.fp_regs) {
+		/*
+		 * prevent reads of padding hole between
+		 * orig_gpr2 and fp_regs on s390.
+		 */
+		tmp = 0;
+
+	} else if (addr == (addr_t) &dummy->regs.fp_regs.fpc) {
+		/*
+		 * floating point control reg. is in the thread structure
+		 */
+		tmp = child->thread.fp_regs.fpc;
+		tmp <<= BITS_PER_LONG - 32;
+
+	} else if (addr < (addr_t) (&dummy->regs.fp_regs + 1)) {
+		/*
+		 * floating point regs. are either in child->thread.fp_regs
+		 * or the child->thread.vxrs array
+		 */
+		offset = addr - (addr_t) &dummy->regs.fp_regs.fprs;
+		if (child->thread.vxrs)
+			tmp = *(addr_t *)
+			       ((addr_t) child->thread.vxrs + 2*offset);
+		else
+			tmp = *(addr_t *)
+			       ((addr_t) &child->thread.fp_regs.fprs + offset);
+
+	} else if (addr < (addr_t) (&dummy->regs.per_info + 1)) {
+		/*
+		 * Handle access to the per_info structure.
+		 */
+		addr -= (addr_t) &dummy->regs.per_info;
+		tmp = __peek_user_per(child, addr);
+
+	} else
+		tmp = 0;
+
+	return tmp;
+}
+
+static int
+peek_user(struct task_struct *child, addr_t addr, addr_t data)
+{
+	addr_t tmp, mask;
+
+	/*
+	 * Stupid gdb peeks/pokes the access registers in 64 bit with
+	 * an alignment of 4. Programmers from hell...
+	 */
+	mask = __ADDR_MASK;
+	if (addr >= (addr_t) &((struct user *) NULL)->regs.acrs &&
+	    addr < (addr_t) &((struct user *) NULL)->regs.orig_gpr2)
+		mask = 3;
+	if ((addr & mask) || addr > sizeof(struct user) - __ADDR_MASK)
+		return -EIO;
+
+	tmp = __peek_user(child, addr);
+	return put_user(tmp, (addr_t __user *) data);
+}
+
+static inline void __poke_user_per(struct task_struct *child,
+				   addr_t addr, addr_t data)
+{
+	struct per_struct_kernel *dummy = NULL;
+
+	/*
+	 * There are only three fields in the per_info struct that the
+	 * debugger user can write to.
+	 * 1) cr9: the debugger wants to set a new PER event mask
+	 * 2) starting_addr: the debugger wants to set a new starting
+	 *    address to use with the PER event mask.
+	 * 3) ending_addr: the debugger wants to set a new ending
+	 *    address to use with the PER event mask.
+	 * The user specified PER event mask and the start and end
+	 * addresses are used only if single stepping is not in effect.
+	 * Writes to any other field in per_info are ignored.
+	 */
+	if (addr == (addr_t) &dummy->cr9)
+		/* PER event mask of the user specified per set. */
+		child->thread.per_user.control =
+			data & (PER_EVENT_MASK | PER_CONTROL_MASK);
+	else if (addr == (addr_t) &dummy->starting_addr)
+		/* Starting address of the user specified per set. */
+		child->thread.per_user.start = data;
+	else if (addr == (addr_t) &dummy->ending_addr)
+		/* Ending address of the user specified per set. */
+		child->thread.per_user.end = data;
+}
+
+/*
+ * Write a word to the user area of a process at location addr. This
+ * operation does have an additional problem compared to peek_user.
+ * Stores to the program status word and on the floating point
+ * control register needs to get checked for validity.
+ */
+static int __poke_user(struct task_struct *child, addr_t addr, addr_t data)
+{
+	struct user *dummy = NULL;
+	addr_t offset;
+
+	if (addr < (addr_t) &dummy->regs.acrs) {
+		/*
+		 * psw and gprs are stored on the stack
+		 */
+		if (addr == (addr_t) &dummy->regs.psw.mask) {
+			unsigned long mask = PSW_MASK_USER;
+
+			mask |= is_ri_task(child) ? PSW_MASK_RI : 0;
+			if ((data ^ PSW_USER_BITS) & ~mask)
+				/* Invalid psw mask. */
+				return -EINVAL;
+			if ((data & PSW_MASK_ASC) == PSW_ASC_HOME)
+				/* Invalid address-space-control bits */
+				return -EINVAL;
+			if ((data & PSW_MASK_EA) && !(data & PSW_MASK_BA))
+				/* Invalid addressing mode bits */
+				return -EINVAL;
+		}
+		*(addr_t *)((addr_t) &task_pt_regs(child)->psw + addr) = data;
+
+	} else if (addr < (addr_t) (&dummy->regs.orig_gpr2)) {
+		/*
+		 * access registers are stored in the thread structure
+		 */
+		offset = addr - (addr_t) &dummy->regs.acrs;
+		/*
+		 * Very special case: old & broken 64 bit gdb writing
+		 * to acrs[15] with a 64 bit value. Ignore the lower
+		 * half of the value and write the upper 32 bit to
+		 * acrs[15]. Sick...
+		 */
+		if (addr == (addr_t) &dummy->regs.acrs[15])
+			child->thread.acrs[15] = (unsigned int) (data >> 32);
+		else
+			*(addr_t *)((addr_t) &child->thread.acrs + offset) = data;
+
+	} else if (addr == (addr_t) &dummy->regs.orig_gpr2) {
+		/*
+		 * orig_gpr2 is stored on the kernel stack
+		 */
+		task_pt_regs(child)->orig_gpr2 = data;
+
+	} else if (addr < (addr_t) &dummy->regs.fp_regs) {
+		/*
+		 * prevent writes of padding hole between
+		 * orig_gpr2 and fp_regs on s390.
+		 */
+		return 0;
+
+	} else if (addr == (addr_t) &dummy->regs.fp_regs.fpc) {
+		/*
+		 * floating point control reg. is in the thread structure
+		 */
+		if ((unsigned int) data != 0 ||
+		    test_fp_ctl(data >> (BITS_PER_LONG - 32)))
+			return -EINVAL;
+		child->thread.fp_regs.fpc = data >> (BITS_PER_LONG - 32);
+
+	} else if (addr < (addr_t) (&dummy->regs.fp_regs + 1)) {
+		/*
+		 * floating point regs. are either in child->thread.fp_regs
+		 * or the child->thread.vxrs array
+		 */
+		offset = addr - (addr_t) &dummy->regs.fp_regs.fprs;
+		if (child->thread.vxrs)
+			*(addr_t *)((addr_t)
+				child->thread.vxrs + 2*offset) = data;
+		else
+			*(addr_t *)((addr_t)
+				&child->thread.fp_regs.fprs + offset) = data;
+
+	} else if (addr < (addr_t) (&dummy->regs.per_info + 1)) {
+		/*
+		 * Handle access to the per_info structure.
+		 */
+		addr -= (addr_t) &dummy->regs.per_info;
+		__poke_user_per(child, addr, data);
+
+	}
+
+	return 0;
+}
+
+static int poke_user(struct task_struct *child, addr_t addr, addr_t data)
+{
+	addr_t mask;
+
+	/*
+	 * Stupid gdb peeks/pokes the access registers in 64 bit with
+	 * an alignment of 4. Programmers from hell indeed...
+	 */
+	mask = __ADDR_MASK;
+	if (addr >= (addr_t) &((struct user *) NULL)->regs.acrs &&
+	    addr < (addr_t) &((struct user *) NULL)->regs.orig_gpr2)
+		mask = 3;
+	if ((addr & mask) || addr > sizeof(struct user) - __ADDR_MASK)
+		return -EIO;
+
+	return __poke_user(child, addr, data);
+}
+
+long arch_ptrace(struct task_struct *child, long request,
+		 unsigned long addr, unsigned long data)
+{
+	ptrace_area parea; 
+	int copied, ret;
+
+	switch (request) {
+	case PTRACE_PEEKUSR:
+		/* read the word at location addr in the USER area. */
+		return peek_user(child, addr, data);
+
+	case PTRACE_POKEUSR:
+		/* write the word at location addr in the USER area */
+		return poke_user(child, addr, data);
+
+	case PTRACE_PEEKUSR_AREA:
+	case PTRACE_POKEUSR_AREA:
+		if (copy_from_user(&parea, (void __force __user *) addr,
+							sizeof(parea)))
+			return -EFAULT;
+		addr = parea.kernel_addr;
+		data = parea.process_addr;
+		copied = 0;
+		while (copied < parea.len) {
+			if (request == PTRACE_PEEKUSR_AREA)
+				ret = peek_user(child, addr, data);
+			else {
+				addr_t utmp;
+				if (get_user(utmp,
+					     (addr_t __force __user *) data))
+					return -EFAULT;
+				ret = poke_user(child, addr, utmp);
+			}
+			if (ret)
+				return ret;
+			addr += sizeof(unsigned long);
+			data += sizeof(unsigned long);
+			copied += sizeof(unsigned long);
+		}
+		return 0;
+	case PTRACE_GET_LAST_BREAK:
+		put_user(task_thread_info(child)->last_break,
+			 (unsigned long __user *) data);
+		return 0;
+	case PTRACE_ENABLE_TE:
+		if (!MACHINE_HAS_TE)
+			return -EIO;
+		child->thread.per_flags &= ~PER_FLAG_NO_TE;
+		return 0;
+	case PTRACE_DISABLE_TE:
+		if (!MACHINE_HAS_TE)
+			return -EIO;
+		child->thread.per_flags |= PER_FLAG_NO_TE;
+		child->thread.per_flags &= ~PER_FLAG_TE_ABORT_RAND;
+		return 0;
+	case PTRACE_TE_ABORT_RAND:
+		if (!MACHINE_HAS_TE || (child->thread.per_flags & PER_FLAG_NO_TE))
+			return -EIO;
+		switch (data) {
+		case 0UL:
+			child->thread.per_flags &= ~PER_FLAG_TE_ABORT_RAND;
+			break;
+		case 1UL:
+			child->thread.per_flags |= PER_FLAG_TE_ABORT_RAND;
+			child->thread.per_flags |= PER_FLAG_TE_ABORT_RAND_TEND;
+			break;
+		case 2UL:
+			child->thread.per_flags |= PER_FLAG_TE_ABORT_RAND;
+			child->thread.per_flags &= ~PER_FLAG_TE_ABORT_RAND_TEND;
+			break;
+		default:
+			return -EINVAL;
+		}
+		return 0;
+	default:
+		/* Removing high order bit from addr (only for 31 bit). */
+		addr &= PSW_ADDR_INSN;
+		return ptrace_request(child, request, addr, data);
+	}
+}
+
+#ifdef CONFIG_COMPAT
+/*
+ * Now the fun part starts... a 31 bit program running in the
+ * 31 bit emulation tracing another program. PTRACE_PEEKTEXT,
+ * PTRACE_PEEKDATA, PTRACE_POKETEXT and PTRACE_POKEDATA are easy
+ * to handle, the difference to the 64 bit versions of the requests
+ * is that the access is done in multiples of 4 byte instead of
+ * 8 bytes (sizeof(unsigned long) on 31/64 bit).
+ * The ugly part are PTRACE_PEEKUSR, PTRACE_PEEKUSR_AREA,
+ * PTRACE_POKEUSR and PTRACE_POKEUSR_AREA. If the traced program
+ * is a 31 bit program too, the content of struct user can be
+ * emulated. A 31 bit program peeking into the struct user of
+ * a 64 bit program is a no-no.
+ */
+
+/*
+ * Same as peek_user_per but for a 31 bit program.
+ */
+static inline __u32 __peek_user_per_compat(struct task_struct *child,
+					   addr_t addr)
+{
+	struct compat_per_struct_kernel *dummy32 = NULL;
+
+	if (addr == (addr_t) &dummy32->cr9)
+		/* Control bits of the active per set. */
+		return (__u32) test_thread_flag(TIF_SINGLE_STEP) ?
+			PER_EVENT_IFETCH : child->thread.per_user.control;
+	else if (addr == (addr_t) &dummy32->cr10)
+		/* Start address of the active per set. */
+		return (__u32) test_thread_flag(TIF_SINGLE_STEP) ?
+			0 : child->thread.per_user.start;
+	else if (addr == (addr_t) &dummy32->cr11)
+		/* End address of the active per set. */
+		return test_thread_flag(TIF_SINGLE_STEP) ?
+			PSW32_ADDR_INSN : child->thread.per_user.end;
+	else if (addr == (addr_t) &dummy32->bits)
+		/* Single-step bit. */
+		return (__u32) test_thread_flag(TIF_SINGLE_STEP) ?
+			0x80000000 : 0;
+	else if (addr == (addr_t) &dummy32->starting_addr)
+		/* Start address of the user specified per set. */
+		return (__u32) child->thread.per_user.start;
+	else if (addr == (addr_t) &dummy32->ending_addr)
+		/* End address of the user specified per set. */
+		return (__u32) child->thread.per_user.end;
+	else if (addr == (addr_t) &dummy32->perc_atmid)
+		/* PER code, ATMID and AI of the last PER trap */
+		return (__u32) child->thread.per_event.cause << 16;
+	else if (addr == (addr_t) &dummy32->address)
+		/* Address of the last PER trap */
+		return (__u32) child->thread.per_event.address;
+	else if (addr == (addr_t) &dummy32->access_id)
+		/* Access id of the last PER trap */
+		return (__u32) child->thread.per_event.paid << 24;
+	return 0;
+}
+
+/*
+ * Same as peek_user but for a 31 bit program.
+ */
+static u32 __peek_user_compat(struct task_struct *child, addr_t addr)
+{
+	struct compat_user *dummy32 = NULL;
+	addr_t offset;
+	__u32 tmp;
+
+	if (addr < (addr_t) &dummy32->regs.acrs) {
+		struct pt_regs *regs = task_pt_regs(child);
+		/*
+		 * psw and gprs are stored on the stack
+		 */
+		if (addr == (addr_t) &dummy32->regs.psw.mask) {
+			/* Fake a 31 bit psw mask. */
+			tmp = (__u32)(regs->psw.mask >> 32);
+			tmp &= PSW32_MASK_USER | PSW32_MASK_RI;
+			tmp |= PSW32_USER_BITS;
+		} else if (addr == (addr_t) &dummy32->regs.psw.addr) {
+			/* Fake a 31 bit psw address. */
+			tmp = (__u32) regs->psw.addr |
+				(__u32)(regs->psw.mask & PSW_MASK_BA);
+		} else {
+			/* gpr 0-15 */
+			tmp = *(__u32 *)((addr_t) &regs->psw + addr*2 + 4);
+		}
+	} else if (addr < (addr_t) (&dummy32->regs.orig_gpr2)) {
+		/*
+		 * access registers are stored in the thread structure
+		 */
+		offset = addr - (addr_t) &dummy32->regs.acrs;
+		tmp = *(__u32*)((addr_t) &child->thread.acrs + offset);
+
+	} else if (addr == (addr_t) (&dummy32->regs.orig_gpr2)) {
+		/*
+		 * orig_gpr2 is stored on the kernel stack
+		 */
+		tmp = *(__u32*)((addr_t) &task_pt_regs(child)->orig_gpr2 + 4);
+
+	} else if (addr < (addr_t) &dummy32->regs.fp_regs) {
+		/*
+		 * prevent reads of padding hole between
+		 * orig_gpr2 and fp_regs on s390.
+		 */
+		tmp = 0;
+
+	} else if (addr == (addr_t) &dummy32->regs.fp_regs.fpc) {
+		/*
+		 * floating point control reg. is in the thread structure
+		 */
+		tmp = child->thread.fp_regs.fpc;
+
+	} else if (addr < (addr_t) (&dummy32->regs.fp_regs + 1)) {
+		/*
+		 * floating point regs. are either in child->thread.fp_regs
+		 * or the child->thread.vxrs array
+		 */
+		offset = addr - (addr_t) &dummy32->regs.fp_regs.fprs;
+		if (child->thread.vxrs)
+			tmp = *(__u32 *)
+			       ((addr_t) child->thread.vxrs + 2*offset);
+		else
+			tmp = *(__u32 *)
+			       ((addr_t) &child->thread.fp_regs.fprs + offset);
+
+	} else if (addr < (addr_t) (&dummy32->regs.per_info + 1)) {
+		/*
+		 * Handle access to the per_info structure.
+		 */
+		addr -= (addr_t) &dummy32->regs.per_info;
+		tmp = __peek_user_per_compat(child, addr);
+
+	} else
+		tmp = 0;
+
+	return tmp;
+}
+
+static int peek_user_compat(struct task_struct *child,
+			    addr_t addr, addr_t data)
+{
+	__u32 tmp;
+
+	if (!is_compat_task() || (addr & 3) || addr > sizeof(struct user) - 3)
+		return -EIO;
+
+	tmp = __peek_user_compat(child, addr);
+	return put_user(tmp, (__u32 __user *) data);
+}
+
+/*
+ * Same as poke_user_per but for a 31 bit program.
+ */
+static inline void __poke_user_per_compat(struct task_struct *child,
+					  addr_t addr, __u32 data)
+{
+	struct compat_per_struct_kernel *dummy32 = NULL;
+
+	if (addr == (addr_t) &dummy32->cr9)
+		/* PER event mask of the user specified per set. */
+		child->thread.per_user.control =
+			data & (PER_EVENT_MASK | PER_CONTROL_MASK);
+	else if (addr == (addr_t) &dummy32->starting_addr)
+		/* Starting address of the user specified per set. */
+		child->thread.per_user.start = data;
+	else if (addr == (addr_t) &dummy32->ending_addr)
+		/* Ending address of the user specified per set. */
+		child->thread.per_user.end = data;
+}
+
+/*
+ * Same as poke_user but for a 31 bit program.
+ */
+static int __poke_user_compat(struct task_struct *child,
+			      addr_t addr, addr_t data)
+{
+	struct compat_user *dummy32 = NULL;
+	__u32 tmp = (__u32) data;
+	addr_t offset;
+
+	if (addr < (addr_t) &dummy32->regs.acrs) {
+		struct pt_regs *regs = task_pt_regs(child);
+		/*
+		 * psw, gprs, acrs and orig_gpr2 are stored on the stack
+		 */
+		if (addr == (addr_t) &dummy32->regs.psw.mask) {
+			__u32 mask = PSW32_MASK_USER;
+
+			mask |= is_ri_task(child) ? PSW32_MASK_RI : 0;
+			/* Build a 64 bit psw mask from 31 bit mask. */
+			if ((tmp ^ PSW32_USER_BITS) & ~mask)
+				/* Invalid psw mask. */
+				return -EINVAL;
+			if ((data & PSW32_MASK_ASC) == PSW32_ASC_HOME)
+				/* Invalid address-space-control bits */
+				return -EINVAL;
+			regs->psw.mask = (regs->psw.mask & ~PSW_MASK_USER) |
+				(regs->psw.mask & PSW_MASK_BA) |
+				(__u64)(tmp & mask) << 32;
+		} else if (addr == (addr_t) &dummy32->regs.psw.addr) {
+			/* Build a 64 bit psw address from 31 bit address. */
+			regs->psw.addr = (__u64) tmp & PSW32_ADDR_INSN;
+			/* Transfer 31 bit amode bit to psw mask. */
+			regs->psw.mask = (regs->psw.mask & ~PSW_MASK_BA) |
+				(__u64)(tmp & PSW32_ADDR_AMODE);
+		} else {
+			/* gpr 0-15 */
+			*(__u32*)((addr_t) &regs->psw + addr*2 + 4) = tmp;
+		}
+	} else if (addr < (addr_t) (&dummy32->regs.orig_gpr2)) {
+		/*
+		 * access registers are stored in the thread structure
+		 */
+		offset = addr - (addr_t) &dummy32->regs.acrs;
+		*(__u32*)((addr_t) &child->thread.acrs + offset) = tmp;
+
+	} else if (addr == (addr_t) (&dummy32->regs.orig_gpr2)) {
+		/*
+		 * orig_gpr2 is stored on the kernel stack
+		 */
+		*(__u32*)((addr_t) &task_pt_regs(child)->orig_gpr2 + 4) = tmp;
+
+	} else if (addr < (addr_t) &dummy32->regs.fp_regs) {
+		/*
+		 * prevent writess of padding hole between
+		 * orig_gpr2 and fp_regs on s390.
+		 */
+		return 0;
+
+	} else if (addr == (addr_t) &dummy32->regs.fp_regs.fpc) {
+		/*
+		 * floating point control reg. is in the thread structure
+		 */
+		if (test_fp_ctl(tmp))
+			return -EINVAL;
+		child->thread.fp_regs.fpc = data;
+
+	} else if (addr < (addr_t) (&dummy32->regs.fp_regs + 1)) {
+		/*
+		 * floating point regs. are either in child->thread.fp_regs
+		 * or the child->thread.vxrs array
+		 */
+		offset = addr - (addr_t) &dummy32->regs.fp_regs.fprs;
+		if (child->thread.vxrs)
+			*(__u32 *)((addr_t)
+				child->thread.vxrs + 2*offset) = tmp;
+		else
+			*(__u32 *)((addr_t)
+				&child->thread.fp_regs.fprs + offset) = tmp;
+
+	} else if (addr < (addr_t) (&dummy32->regs.per_info + 1)) {
+		/*
+		 * Handle access to the per_info structure.
+		 */
+		addr -= (addr_t) &dummy32->regs.per_info;
+		__poke_user_per_compat(child, addr, data);
+	}
+
+	return 0;
+}
+
+static int poke_user_compat(struct task_struct *child,
+			    addr_t addr, addr_t data)
+{
+	if (!is_compat_task() || (addr & 3) ||
+	    addr > sizeof(struct compat_user) - 3)
+		return -EIO;
+
+	return __poke_user_compat(child, addr, data);
+}
+
+long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
+			compat_ulong_t caddr, compat_ulong_t cdata)
+{
+	unsigned long addr = caddr;
+	unsigned long data = cdata;
+	compat_ptrace_area parea;
+	int copied, ret;
+
+	switch (request) {
+	case PTRACE_PEEKUSR:
+		/* read the word at location addr in the USER area. */
+		return peek_user_compat(child, addr, data);
+
+	case PTRACE_POKEUSR:
+		/* write the word at location addr in the USER area */
+		return poke_user_compat(child, addr, data);
+
+	case PTRACE_PEEKUSR_AREA:
+	case PTRACE_POKEUSR_AREA:
+		if (copy_from_user(&parea, (void __force __user *) addr,
+							sizeof(parea)))
+			return -EFAULT;
+		addr = parea.kernel_addr;
+		data = parea.process_addr;
+		copied = 0;
+		while (copied < parea.len) {
+			if (request == PTRACE_PEEKUSR_AREA)
+				ret = peek_user_compat(child, addr, data);
+			else {
+				__u32 utmp;
+				if (get_user(utmp,
+					     (__u32 __force __user *) data))
+					return -EFAULT;
+				ret = poke_user_compat(child, addr, utmp);
+			}
+			if (ret)
+				return ret;
+			addr += sizeof(unsigned int);
+			data += sizeof(unsigned int);
+			copied += sizeof(unsigned int);
+		}
+		return 0;
+	case PTRACE_GET_LAST_BREAK:
+		put_user(task_thread_info(child)->last_break,
+			 (unsigned int __user *) data);
+		return 0;
+	}
+	return compat_ptrace_request(child, request, addr, data);
+}
+#endif
+
+asmlinkage long do_syscall_trace_enter(struct pt_regs *regs)
+{
+	long ret = 0;
+
+	/* Do the secure computing check first. */
+	if (secure_computing()) {
+		/* seccomp failures shouldn't expose any additional code. */
+		ret = -1;
+		goto out;
+	}
+
+	/*
+	 * The sysc_tracesys code in entry.S stored the system
+	 * call number to gprs[2].
+	 */
+	if (test_thread_flag(TIF_SYSCALL_TRACE) &&
+	    (tracehook_report_syscall_entry(regs) ||
+	     regs->gprs[2] >= NR_syscalls)) {
+		/*
+		 * Tracing decided this syscall should not happen or the
+		 * debugger stored an invalid system call number. Skip
+		 * the system call and the system call restart handling.
+		 */
+		clear_pt_regs_flag(regs, PIF_SYSCALL);
+		ret = -1;
+	}
+
+	if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
+		trace_sys_enter(regs, regs->gprs[2]);
+
+	audit_syscall_entry(regs->gprs[2], regs->orig_gpr2,
+			    regs->gprs[3], regs->gprs[4],
+			    regs->gprs[5]);
+out:
+	return ret ?: regs->gprs[2];
+}
+
+asmlinkage void do_syscall_trace_exit(struct pt_regs *regs)
+{
+	audit_syscall_exit(regs);
+
+	if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
+		trace_sys_exit(regs, regs->gprs[2]);
+
+	if (test_thread_flag(TIF_SYSCALL_TRACE))
+		tracehook_report_syscall_exit(regs, 0);
+}
+
+/*
+ * user_regset definitions.
+ */
+
+static int s390_regs_get(struct task_struct *target,
+			 const struct user_regset *regset,
+			 unsigned int pos, unsigned int count,
+			 void *kbuf, void __user *ubuf)
+{
+	if (target == current)
+		save_access_regs(target->thread.acrs);
+
+	if (kbuf) {
+		unsigned long *k = kbuf;
+		while (count > 0) {
+			*k++ = __peek_user(target, pos);
+			count -= sizeof(*k);
+			pos += sizeof(*k);
+		}
+	} else {
+		unsigned long __user *u = ubuf;
+		while (count > 0) {
+			if (__put_user(__peek_user(target, pos), u++))
+				return -EFAULT;
+			count -= sizeof(*u);
+			pos += sizeof(*u);
+		}
+	}
+	return 0;
+}
+
+static int s390_regs_set(struct task_struct *target,
+			 const struct user_regset *regset,
+			 unsigned int pos, unsigned int count,
+			 const void *kbuf, const void __user *ubuf)
+{
+	int rc = 0;
+
+	if (target == current)
+		save_access_regs(target->thread.acrs);
+
+	if (kbuf) {
+		const unsigned long *k = kbuf;
+		while (count > 0 && !rc) {
+			rc = __poke_user(target, pos, *k++);
+			count -= sizeof(*k);
+			pos += sizeof(*k);
+		}
+	} else {
+		const unsigned long  __user *u = ubuf;
+		while (count > 0 && !rc) {
+			unsigned long word;
+			rc = __get_user(word, u++);
+			if (rc)
+				break;
+			rc = __poke_user(target, pos, word);
+			count -= sizeof(*u);
+			pos += sizeof(*u);
+		}
+	}
+
+	if (rc == 0 && target == current)
+		restore_access_regs(target->thread.acrs);
+
+	return rc;
+}
+
+static int s390_fpregs_get(struct task_struct *target,
+			   const struct user_regset *regset, unsigned int pos,
+			   unsigned int count, void *kbuf, void __user *ubuf)
+{
+	if (target == current) {
+		save_fp_ctl(&target->thread.fp_regs.fpc);
+		save_fp_regs(target->thread.fp_regs.fprs);
+	} else if (target->thread.vxrs) {
+		int i;
+
+		for (i = 0; i < __NUM_VXRS_LOW; i++)
+			target->thread.fp_regs.fprs[i] =
+				*(freg_t *)(target->thread.vxrs + i);
+	}
+	return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+				   &target->thread.fp_regs, 0, -1);
+}
+
+static int s390_fpregs_set(struct task_struct *target,
+			   const struct user_regset *regset, unsigned int pos,
+			   unsigned int count, const void *kbuf,
+			   const void __user *ubuf)
+{
+	int rc = 0;
+
+	if (target == current) {
+		save_fp_ctl(&target->thread.fp_regs.fpc);
+		save_fp_regs(target->thread.fp_regs.fprs);
+	}
+
+	/* If setting FPC, must validate it first. */
+	if (count > 0 && pos < offsetof(s390_fp_regs, fprs)) {
+		u32 ufpc[2] = { target->thread.fp_regs.fpc, 0 };
+		rc = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &ufpc,
+					0, offsetof(s390_fp_regs, fprs));
+		if (rc)
+			return rc;
+		if (ufpc[1] != 0 || test_fp_ctl(ufpc[0]))
+			return -EINVAL;
+		target->thread.fp_regs.fpc = ufpc[0];
+	}
+
+	if (rc == 0 && count > 0)
+		rc = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+					target->thread.fp_regs.fprs,
+					offsetof(s390_fp_regs, fprs), -1);
+
+	if (rc == 0) {
+		if (target == current) {
+			restore_fp_ctl(&target->thread.fp_regs.fpc);
+			restore_fp_regs(target->thread.fp_regs.fprs);
+		} else if (target->thread.vxrs) {
+			int i;
+
+			for (i = 0; i < __NUM_VXRS_LOW; i++)
+				*(freg_t *)(target->thread.vxrs + i) =
+					target->thread.fp_regs.fprs[i];
+		}
+	}
+
+	return rc;
+}
+
+static int s390_last_break_get(struct task_struct *target,
+			       const struct user_regset *regset,
+			       unsigned int pos, unsigned int count,
+			       void *kbuf, void __user *ubuf)
+{
+	if (count > 0) {
+		if (kbuf) {
+			unsigned long *k = kbuf;
+			*k = task_thread_info(target)->last_break;
+		} else {
+			unsigned long  __user *u = ubuf;
+			if (__put_user(task_thread_info(target)->last_break, u))
+				return -EFAULT;
+		}
+	}
+	return 0;
+}
+
+static int s390_last_break_set(struct task_struct *target,
+			       const struct user_regset *regset,
+			       unsigned int pos, unsigned int count,
+			       const void *kbuf, const void __user *ubuf)
+{
+	return 0;
+}
+
+static int s390_tdb_get(struct task_struct *target,
+			const struct user_regset *regset,
+			unsigned int pos, unsigned int count,
+			void *kbuf, void __user *ubuf)
+{
+	struct pt_regs *regs = task_pt_regs(target);
+	unsigned char *data;
+
+	if (!(regs->int_code & 0x200))
+		return -ENODATA;
+	data = target->thread.trap_tdb;
+	return user_regset_copyout(&pos, &count, &kbuf, &ubuf, data, 0, 256);
+}
+
+static int s390_tdb_set(struct task_struct *target,
+			const struct user_regset *regset,
+			unsigned int pos, unsigned int count,
+			const void *kbuf, const void __user *ubuf)
+{
+	return 0;
+}
+
+static int s390_vxrs_low_get(struct task_struct *target,
+			     const struct user_regset *regset,
+			     unsigned int pos, unsigned int count,
+			     void *kbuf, void __user *ubuf)
+{
+	__u64 vxrs[__NUM_VXRS_LOW];
+	int i;
+
+	if (!MACHINE_HAS_VX)
+		return -ENODEV;
+	if (target->thread.vxrs) {
+		if (target == current)
+			save_vx_regs(target->thread.vxrs);
+		for (i = 0; i < __NUM_VXRS_LOW; i++)
+			vxrs[i] = *((__u64 *)(target->thread.vxrs + i) + 1);
+	} else
+		memset(vxrs, 0, sizeof(vxrs));
+	return user_regset_copyout(&pos, &count, &kbuf, &ubuf, vxrs, 0, -1);
+}
+
+static int s390_vxrs_low_set(struct task_struct *target,
+			     const struct user_regset *regset,
+			     unsigned int pos, unsigned int count,
+			     const void *kbuf, const void __user *ubuf)
+{
+	__u64 vxrs[__NUM_VXRS_LOW];
+	int i, rc;
+
+	if (!MACHINE_HAS_VX)
+		return -ENODEV;
+	if (!target->thread.vxrs) {
+		rc = alloc_vector_registers(target);
+		if (rc)
+			return rc;
+	} else if (target == current)
+		save_vx_regs(target->thread.vxrs);
+
+	rc = user_regset_copyin(&pos, &count, &kbuf, &ubuf, vxrs, 0, -1);
+	if (rc == 0) {
+		for (i = 0; i < __NUM_VXRS_LOW; i++)
+			*((__u64 *)(target->thread.vxrs + i) + 1) = vxrs[i];
+		if (target == current)
+			restore_vx_regs(target->thread.vxrs);
+	}
+
+	return rc;
+}
+
+static int s390_vxrs_high_get(struct task_struct *target,
+			      const struct user_regset *regset,
+			      unsigned int pos, unsigned int count,
+			      void *kbuf, void __user *ubuf)
+{
+	__vector128 vxrs[__NUM_VXRS_HIGH];
+
+	if (!MACHINE_HAS_VX)
+		return -ENODEV;
+	if (target->thread.vxrs) {
+		if (target == current)
+			save_vx_regs(target->thread.vxrs);
+		memcpy(vxrs, target->thread.vxrs + __NUM_VXRS_LOW,
+		       sizeof(vxrs));
+	} else
+		memset(vxrs, 0, sizeof(vxrs));
+	return user_regset_copyout(&pos, &count, &kbuf, &ubuf, vxrs, 0, -1);
+}
+
+static int s390_vxrs_high_set(struct task_struct *target,
+			      const struct user_regset *regset,
+			      unsigned int pos, unsigned int count,
+			      const void *kbuf, const void __user *ubuf)
+{
+	int rc;
+
+	if (!MACHINE_HAS_VX)
+		return -ENODEV;
+	if (!target->thread.vxrs) {
+		rc = alloc_vector_registers(target);
+		if (rc)
+			return rc;
+	} else if (target == current)
+		save_vx_regs(target->thread.vxrs);
+
+	rc = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				target->thread.vxrs + __NUM_VXRS_LOW, 0, -1);
+	if (rc == 0 && target == current)
+		restore_vx_regs(target->thread.vxrs);
+
+	return rc;
+}
+
+static int s390_system_call_get(struct task_struct *target,
+				const struct user_regset *regset,
+				unsigned int pos, unsigned int count,
+				void *kbuf, void __user *ubuf)
+{
+	unsigned int *data = &task_thread_info(target)->system_call;
+	return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+				   data, 0, sizeof(unsigned int));
+}
+
+static int s390_system_call_set(struct task_struct *target,
+				const struct user_regset *regset,
+				unsigned int pos, unsigned int count,
+				const void *kbuf, const void __user *ubuf)
+{
+	unsigned int *data = &task_thread_info(target)->system_call;
+	return user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				  data, 0, sizeof(unsigned int));
+}
+
+static const struct user_regset s390_regsets[] = {
+	{
+		.core_note_type = NT_PRSTATUS,
+		.n = sizeof(s390_regs) / sizeof(long),
+		.size = sizeof(long),
+		.align = sizeof(long),
+		.get = s390_regs_get,
+		.set = s390_regs_set,
+	},
+	{
+		.core_note_type = NT_PRFPREG,
+		.n = sizeof(s390_fp_regs) / sizeof(long),
+		.size = sizeof(long),
+		.align = sizeof(long),
+		.get = s390_fpregs_get,
+		.set = s390_fpregs_set,
+	},
+	{
+		.core_note_type = NT_S390_SYSTEM_CALL,
+		.n = 1,
+		.size = sizeof(unsigned int),
+		.align = sizeof(unsigned int),
+		.get = s390_system_call_get,
+		.set = s390_system_call_set,
+	},
+	{
+		.core_note_type = NT_S390_LAST_BREAK,
+		.n = 1,
+		.size = sizeof(long),
+		.align = sizeof(long),
+		.get = s390_last_break_get,
+		.set = s390_last_break_set,
+	},
+	{
+		.core_note_type = NT_S390_TDB,
+		.n = 1,
+		.size = 256,
+		.align = 1,
+		.get = s390_tdb_get,
+		.set = s390_tdb_set,
+	},
+	{
+		.core_note_type = NT_S390_VXRS_LOW,
+		.n = __NUM_VXRS_LOW,
+		.size = sizeof(__u64),
+		.align = sizeof(__u64),
+		.get = s390_vxrs_low_get,
+		.set = s390_vxrs_low_set,
+	},
+	{
+		.core_note_type = NT_S390_VXRS_HIGH,
+		.n = __NUM_VXRS_HIGH,
+		.size = sizeof(__vector128),
+		.align = sizeof(__vector128),
+		.get = s390_vxrs_high_get,
+		.set = s390_vxrs_high_set,
+	},
+};
+
+static const struct user_regset_view user_s390_view = {
+	.name = UTS_MACHINE,
+	.e_machine = EM_S390,
+	.regsets = s390_regsets,
+	.n = ARRAY_SIZE(s390_regsets)
+};
+
+#ifdef CONFIG_COMPAT
+static int s390_compat_regs_get(struct task_struct *target,
+				const struct user_regset *regset,
+				unsigned int pos, unsigned int count,
+				void *kbuf, void __user *ubuf)
+{
+	if (target == current)
+		save_access_regs(target->thread.acrs);
+
+	if (kbuf) {
+		compat_ulong_t *k = kbuf;
+		while (count > 0) {
+			*k++ = __peek_user_compat(target, pos);
+			count -= sizeof(*k);
+			pos += sizeof(*k);
+		}
+	} else {
+		compat_ulong_t __user *u = ubuf;
+		while (count > 0) {
+			if (__put_user(__peek_user_compat(target, pos), u++))
+				return -EFAULT;
+			count -= sizeof(*u);
+			pos += sizeof(*u);
+		}
+	}
+	return 0;
+}
+
+static int s390_compat_regs_set(struct task_struct *target,
+				const struct user_regset *regset,
+				unsigned int pos, unsigned int count,
+				const void *kbuf, const void __user *ubuf)
+{
+	int rc = 0;
+
+	if (target == current)
+		save_access_regs(target->thread.acrs);
+
+	if (kbuf) {
+		const compat_ulong_t *k = kbuf;
+		while (count > 0 && !rc) {
+			rc = __poke_user_compat(target, pos, *k++);
+			count -= sizeof(*k);
+			pos += sizeof(*k);
+		}
+	} else {
+		const compat_ulong_t  __user *u = ubuf;
+		while (count > 0 && !rc) {
+			compat_ulong_t word;
+			rc = __get_user(word, u++);
+			if (rc)
+				break;
+			rc = __poke_user_compat(target, pos, word);
+			count -= sizeof(*u);
+			pos += sizeof(*u);
+		}
+	}
+
+	if (rc == 0 && target == current)
+		restore_access_regs(target->thread.acrs);
+
+	return rc;
+}
+
+static int s390_compat_regs_high_get(struct task_struct *target,
+				     const struct user_regset *regset,
+				     unsigned int pos, unsigned int count,
+				     void *kbuf, void __user *ubuf)
+{
+	compat_ulong_t *gprs_high;
+
+	gprs_high = (compat_ulong_t *)
+		&task_pt_regs(target)->gprs[pos / sizeof(compat_ulong_t)];
+	if (kbuf) {
+		compat_ulong_t *k = kbuf;
+		while (count > 0) {
+			*k++ = *gprs_high;
+			gprs_high += 2;
+			count -= sizeof(*k);
+		}
+	} else {
+		compat_ulong_t __user *u = ubuf;
+		while (count > 0) {
+			if (__put_user(*gprs_high, u++))
+				return -EFAULT;
+			gprs_high += 2;
+			count -= sizeof(*u);
+		}
+	}
+	return 0;
+}
+
+static int s390_compat_regs_high_set(struct task_struct *target,
+				     const struct user_regset *regset,
+				     unsigned int pos, unsigned int count,
+				     const void *kbuf, const void __user *ubuf)
+{
+	compat_ulong_t *gprs_high;
+	int rc = 0;
+
+	gprs_high = (compat_ulong_t *)
+		&task_pt_regs(target)->gprs[pos / sizeof(compat_ulong_t)];
+	if (kbuf) {
+		const compat_ulong_t *k = kbuf;
+		while (count > 0) {
+			*gprs_high = *k++;
+			*gprs_high += 2;
+			count -= sizeof(*k);
+		}
+	} else {
+		const compat_ulong_t  __user *u = ubuf;
+		while (count > 0 && !rc) {
+			unsigned long word;
+			rc = __get_user(word, u++);
+			if (rc)
+				break;
+			*gprs_high = word;
+			*gprs_high += 2;
+			count -= sizeof(*u);
+		}
+	}
+
+	return rc;
+}
+
+static int s390_compat_last_break_get(struct task_struct *target,
+				      const struct user_regset *regset,
+				      unsigned int pos, unsigned int count,
+				      void *kbuf, void __user *ubuf)
+{
+	compat_ulong_t last_break;
+
+	if (count > 0) {
+		last_break = task_thread_info(target)->last_break;
+		if (kbuf) {
+			unsigned long *k = kbuf;
+			*k = last_break;
+		} else {
+			unsigned long  __user *u = ubuf;
+			if (__put_user(last_break, u))
+				return -EFAULT;
+		}
+	}
+	return 0;
+}
+
+static int s390_compat_last_break_set(struct task_struct *target,
+				      const struct user_regset *regset,
+				      unsigned int pos, unsigned int count,
+				      const void *kbuf, const void __user *ubuf)
+{
+	return 0;
+}
+
+static const struct user_regset s390_compat_regsets[] = {
+	{
+		.core_note_type = NT_PRSTATUS,
+		.n = sizeof(s390_compat_regs) / sizeof(compat_long_t),
+		.size = sizeof(compat_long_t),
+		.align = sizeof(compat_long_t),
+		.get = s390_compat_regs_get,
+		.set = s390_compat_regs_set,
+	},
+	{
+		.core_note_type = NT_PRFPREG,
+		.n = sizeof(s390_fp_regs) / sizeof(compat_long_t),
+		.size = sizeof(compat_long_t),
+		.align = sizeof(compat_long_t),
+		.get = s390_fpregs_get,
+		.set = s390_fpregs_set,
+	},
+	{
+		.core_note_type = NT_S390_SYSTEM_CALL,
+		.n = 1,
+		.size = sizeof(compat_uint_t),
+		.align = sizeof(compat_uint_t),
+		.get = s390_system_call_get,
+		.set = s390_system_call_set,
+	},
+	{
+		.core_note_type = NT_S390_LAST_BREAK,
+		.n = 1,
+		.size = sizeof(long),
+		.align = sizeof(long),
+		.get = s390_compat_last_break_get,
+		.set = s390_compat_last_break_set,
+	},
+	{
+		.core_note_type = NT_S390_TDB,
+		.n = 1,
+		.size = 256,
+		.align = 1,
+		.get = s390_tdb_get,
+		.set = s390_tdb_set,
+	},
+	{
+		.core_note_type = NT_S390_VXRS_LOW,
+		.n = __NUM_VXRS_LOW,
+		.size = sizeof(__u64),
+		.align = sizeof(__u64),
+		.get = s390_vxrs_low_get,
+		.set = s390_vxrs_low_set,
+	},
+	{
+		.core_note_type = NT_S390_VXRS_HIGH,
+		.n = __NUM_VXRS_HIGH,
+		.size = sizeof(__vector128),
+		.align = sizeof(__vector128),
+		.get = s390_vxrs_high_get,
+		.set = s390_vxrs_high_set,
+	},
+	{
+		.core_note_type = NT_S390_HIGH_GPRS,
+		.n = sizeof(s390_compat_regs_high) / sizeof(compat_long_t),
+		.size = sizeof(compat_long_t),
+		.align = sizeof(compat_long_t),
+		.get = s390_compat_regs_high_get,
+		.set = s390_compat_regs_high_set,
+	},
+};
+
+static const struct user_regset_view user_s390_compat_view = {
+	.name = "s390",
+	.e_machine = EM_S390,
+	.regsets = s390_compat_regsets,
+	.n = ARRAY_SIZE(s390_compat_regsets)
+};
+#endif
+
+const struct user_regset_view *task_user_regset_view(struct task_struct *task)
+{
+#ifdef CONFIG_COMPAT
+	if (test_tsk_thread_flag(task, TIF_31BIT))
+		return &user_s390_compat_view;
+#endif
+	return &user_s390_view;
+}
+
+static const char *gpr_names[NUM_GPRS] = {
+	"r0", "r1",  "r2",  "r3",  "r4",  "r5",  "r6",  "r7",
+	"r8", "r9", "r10", "r11", "r12", "r13", "r14", "r15",
+};
+
+unsigned long regs_get_register(struct pt_regs *regs, unsigned int offset)
+{
+	if (offset >= NUM_GPRS)
+		return 0;
+	return regs->gprs[offset];
+}
+
+int regs_query_register_offset(const char *name)
+{
+	unsigned long offset;
+
+	if (!name || *name != 'r')
+		return -EINVAL;
+	if (kstrtoul(name + 1, 10, &offset))
+		return -EINVAL;
+	if (offset >= NUM_GPRS)
+		return -EINVAL;
+	return offset;
+}
+
+const char *regs_query_register_name(unsigned int offset)
+{
+	if (offset >= NUM_GPRS)
+		return NULL;
+	return gpr_names[offset];
+}
+
+static int regs_within_kernel_stack(struct pt_regs *regs, unsigned long addr)
+{
+	unsigned long ksp = kernel_stack_pointer(regs);
+
+	return (addr & ~(THREAD_SIZE - 1)) == (ksp & ~(THREAD_SIZE - 1));
+}
+
+/**
+ * regs_get_kernel_stack_nth() - get Nth entry of the stack
+ * @regs:pt_regs which contains kernel stack pointer.
+ * @n:stack entry number.
+ *
+ * regs_get_kernel_stack_nth() returns @n th entry of the kernel stack which
+ * is specifined by @regs. If the @n th entry is NOT in the kernel stack,
+ * this returns 0.
+ */
+unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, unsigned int n)
+{
+	unsigned long addr;
+
+	addr = kernel_stack_pointer(regs) + n * sizeof(long);
+	if (!regs_within_kernel_stack(regs, addr))
+		return 0;
+	return *(unsigned long *)addr;
+}
diff --git a/arch/s390/kernel/reipl.S b/arch/s390/kernel/reipl.S
new file mode 100644
index 000000000..52aab0bd8
--- /dev/null
+++ b/arch/s390/kernel/reipl.S
@@ -0,0 +1,155 @@
+/*
+ *    Copyright IBM Corp 2000, 2011
+ *    Author(s): Holger Smolinski <Holger.Smolinski@de.ibm.com>,
+ *		 Denis Joseph Barrow,
+ */
+
+#include <linux/linkage.h>
+#include <asm/asm-offsets.h>
+#include <asm/sigp.h>
+
+#
+# store_status
+#
+# Prerequisites to run this function:
+# - Prefix register is set to zero
+# - Original prefix register is stored in "dump_prefix_page"
+# - Lowcore protection is off
+#
+ENTRY(store_status)
+	/* Save register one and load save area base */
+	stg	%r1,__LC_SAVE_AREA_RESTART
+	lghi	%r1,SAVE_AREA_BASE
+	/* General purpose registers */
+	stmg	%r0,%r15,__LC_GPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1)
+	lg	%r2,__LC_SAVE_AREA_RESTART
+	stg	%r2,__LC_GPREGS_SAVE_AREA-SAVE_AREA_BASE+8(%r1)
+	/* Control registers */
+	stctg	%c0,%c15,__LC_CREGS_SAVE_AREA-SAVE_AREA_BASE(%r1)
+	/* Access registers */
+	stam	%a0,%a15,__LC_AREGS_SAVE_AREA-SAVE_AREA_BASE(%r1)
+	/* Floating point registers */
+	std	%f0, 0x00 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1)
+	std	%f1, 0x08 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1)
+	std	%f2, 0x10 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1)
+	std	%f3, 0x18 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1)
+	std	%f4, 0x20 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1)
+	std	%f5, 0x28 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1)
+	std	%f6, 0x30 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1)
+	std	%f7, 0x38 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1)
+	std	%f8, 0x40 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1)
+	std	%f9, 0x48 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1)
+	std	%f10,0x50 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1)
+	std	%f11,0x58 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1)
+	std	%f12,0x60 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1)
+	std	%f13,0x68 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1)
+	std	%f14,0x70 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1)
+	std	%f15,0x78 + __LC_FPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1)
+	/* Floating point control register */
+	stfpc	__LC_FP_CREG_SAVE_AREA-SAVE_AREA_BASE(%r1)
+	/* CPU timer */
+	stpt	__LC_CPU_TIMER_SAVE_AREA-SAVE_AREA_BASE(%r1)
+	/* Saved prefix register */
+	larl	%r2,dump_prefix_page
+	mvc	__LC_PREFIX_SAVE_AREA-SAVE_AREA_BASE(4,%r1),0(%r2)
+	/* Clock comparator - seven bytes */
+	larl	%r2,.Lclkcmp
+	stckc	0(%r2)
+	mvc	__LC_CLOCK_COMP_SAVE_AREA-SAVE_AREA_BASE + 1(7,%r1),1(%r2)
+	/* Program status word */
+	epsw	%r2,%r3
+	st	%r2,__LC_PSW_SAVE_AREA-SAVE_AREA_BASE + 0(%r1)
+	st	%r3,__LC_PSW_SAVE_AREA-SAVE_AREA_BASE + 4(%r1)
+	larl	%r2,store_status
+	stg	%r2,__LC_PSW_SAVE_AREA-SAVE_AREA_BASE + 8(%r1)
+	br	%r14
+
+	.section .bss
+	.align	8
+.Lclkcmp:	.quad	0x0000000000000000
+	.previous
+
+#
+# do_reipl_asm
+# Parameter: r2 = schid of reipl device
+#
+
+ENTRY(do_reipl_asm)
+		basr	%r13,0
+.Lpg0:		lpswe	.Lnewpsw-.Lpg0(%r13)
+.Lpg1:		brasl	%r14,store_status
+
+		lctlg	%c6,%c6,.Lall-.Lpg0(%r13)
+		lgr	%r1,%r2
+		mvc	__LC_PGM_NEW_PSW(16),.Lpcnew-.Lpg0(%r13)
+		stsch	.Lschib-.Lpg0(%r13)
+		oi	.Lschib+5-.Lpg0(%r13),0x84
+.Lecs:		xi	.Lschib+27-.Lpg0(%r13),0x01
+		msch	.Lschib-.Lpg0(%r13)
+		lghi	%r0,5
+.Lssch:		ssch	.Liplorb-.Lpg0(%r13)
+		jz	.L001
+		brct	%r0,.Lssch
+		bas	%r14,.Ldisab-.Lpg0(%r13)
+.L001:		mvc	__LC_IO_NEW_PSW(16),.Lionew-.Lpg0(%r13)
+.Ltpi:		lpswe	.Lwaitpsw-.Lpg0(%r13)
+.Lcont:		c	%r1,__LC_SUBCHANNEL_ID
+		jnz	.Ltpi
+		clc	__LC_IO_INT_PARM(4),.Liplorb-.Lpg0(%r13)
+		jnz	.Ltpi
+		tsch	.Liplirb-.Lpg0(%r13)
+		tm	.Liplirb+9-.Lpg0(%r13),0xbf
+		jz	.L002
+		bas	%r14,.Ldisab-.Lpg0(%r13)
+.L002:		tm	.Liplirb+8-.Lpg0(%r13),0xf3
+		jz	.L003
+		bas	%r14,.Ldisab-.Lpg0(%r13)
+.L003:		st	%r1,__LC_SUBCHANNEL_ID
+		lhi	%r1,0		 # mode 0 = esa
+		slr	%r0,%r0		 # set cpuid to zero
+		sigp	%r1,%r0,SIGP_SET_ARCHITECTURE # switch to esa mode
+		lpsw	0
+.Ldisab:	sll	%r14,1
+		srl	%r14,1		 # need to kill hi bit to avoid specification exceptions.
+		st	%r14,.Ldispsw+12-.Lpg0(%r13)
+		lpswe	.Ldispsw-.Lpg0(%r13)
+		.align	8
+.Lall:		.quad	0x00000000ff000000
+		.align	16
+/*
+ * These addresses have to be 31 bit otherwise
+ * the sigp will throw a specifcation exception
+ * when switching to ESA mode as bit 31 be set
+ * in the ESA psw.
+ * Bit 31 of the addresses has to be 0 for the
+ * 31bit lpswe instruction a fact they appear to have
+ * omitted from the pop.
+ */
+.Lnewpsw:	.quad	0x0000000080000000
+		.quad	.Lpg1
+.Lpcnew:	.quad	0x0000000080000000
+		.quad	.Lecs
+.Lionew:	.quad	0x0000000080000000
+		.quad	.Lcont
+.Lwaitpsw:	.quad	0x0202000080000000
+		.quad	.Ltpi
+.Ldispsw:	.quad	0x0002000080000000
+		.quad	0x0000000000000000
+.Liplccws:	.long	0x02000000,0x60000018
+		.long	0x08000008,0x20000001
+.Liplorb:	.long	0x0049504c,0x0040ff80
+		.long	0x00000000+.Liplccws
+.Lschib:	.long	0x00000000,0x00000000
+		.long	0x00000000,0x00000000
+		.long	0x00000000,0x00000000
+		.long	0x00000000,0x00000000
+		.long	0x00000000,0x00000000
+		.long	0x00000000,0x00000000
+.Liplirb:	.long	0x00000000,0x00000000
+		.long	0x00000000,0x00000000
+		.long	0x00000000,0x00000000
+		.long	0x00000000,0x00000000
+		.long	0x00000000,0x00000000
+		.long	0x00000000,0x00000000
+		.long	0x00000000,0x00000000
+		.long	0x00000000,0x00000000
diff --git a/arch/s390/kernel/relocate_kernel.S b/arch/s390/kernel/relocate_kernel.S
new file mode 100644
index 000000000..cfac28330
--- /dev/null
+++ b/arch/s390/kernel/relocate_kernel.S
@@ -0,0 +1,121 @@
+/*
+ * Copyright IBM Corp. 2005
+ *
+ * Author(s): Rolf Adelsberger,
+ *	      Heiko Carstens <heiko.carstens@de.ibm.com>
+ *
+ */
+
+#include <linux/linkage.h>
+#include <asm/sigp.h>
+
+/*
+ * moves the new kernel to its destination...
+ * %r2 = pointer to first kimage_entry_t
+ * %r3 = start address - where to jump to after the job is done...
+ *
+ * %r5 will be used as temp. storage
+ * %r6 holds the destination address
+ * %r7 = PAGE_SIZE
+ * %r8 holds the source address
+ * %r9 = PAGE_SIZE
+ *
+ * 0xf000 is a page_mask
+ */
+
+	.text
+ENTRY(relocate_kernel)
+		basr	%r13,0		# base address
+	.base:
+		stnsm	sys_msk-.base(%r13),0xfb	# disable DAT
+		stctg	%c0,%c15,ctlregs-.base(%r13)
+		stmg	%r0,%r15,gprregs-.base(%r13)
+		lghi	%r0,3
+		sllg	%r0,%r0,31
+		stg	%r0,0x1d0(%r0)
+		la	%r0,.back_pgm-.base(%r13)
+		stg	%r0,0x1d8(%r0)
+		la	%r1,load_psw-.base(%r13)
+		mvc	0(8,%r0),0(%r1)
+		la	%r0,.back-.base(%r13)
+		st	%r0,4(%r0)
+		oi	4(%r0),0x80
+		lghi	%r0,0
+		diag	%r0,%r0,0x308
+	.back:
+		lhi	%r1,1		# mode 1 = esame
+		sigp	%r1,%r0,SIGP_SET_ARCHITECTURE # switch to esame mode
+		sam64			# switch to 64 bit addressing mode
+		basr	%r13,0
+	.back_base:
+		oi	have_diag308-.back_base(%r13),0x01
+		lctlg	%c0,%c15,ctlregs-.back_base(%r13)
+		lmg	%r0,%r15,gprregs-.back_base(%r13)
+		j	.top
+	.back_pgm:
+		lmg	%r0,%r15,gprregs-.base(%r13)
+	.top:
+		lghi	%r7,4096	# load PAGE_SIZE in r7
+		lghi	%r9,4096	# load PAGE_SIZE in r9
+		lg	%r5,0(%r2)	# read another word for indirection page
+		aghi	%r2,8		# increment pointer
+		tml	%r5,0x1		# is it a destination page?
+		je	.indir_check	# NO, goto "indir_check"
+		lgr	%r6,%r5		# r6 = r5
+		nill	%r6,0xf000	# mask it out and...
+		j	.top		# ...next iteration
+	.indir_check:
+		tml	%r5,0x2		# is it a indirection page?
+		je	.done_test	# NO, goto "done_test"
+		nill	%r5,0xf000	# YES, mask out,
+		lgr	%r2,%r5		# move it into the right register,
+		j	.top		# and read next...
+	.done_test:
+		tml	%r5,0x4		# is it the done indicator?
+		je	.source_test	# NO! Well, then it should be the source indicator...
+		j	.done		# ok, lets finish it here...
+	.source_test:
+		tml	%r5,0x8		# it should be a source indicator...
+		je	.top		# NO, ignore it...
+		lgr	%r8,%r5		# r8 = r5
+		nill	%r8,0xf000	# masking
+	0:	mvcle	%r6,%r8,0x0	# copy PAGE_SIZE bytes from r8 to r6 - pad with 0
+		jo	0b
+		j	.top
+	.done:
+		sgr	%r0,%r0		# clear register r0
+		la	%r4,load_psw-.base(%r13)	# load psw-address into the register
+		o	%r3,4(%r4)	# or load address into psw
+		st	%r3,4(%r4)
+		mvc	0(8,%r0),0(%r4)	# copy psw to absolute address 0
+		tm	have_diag308-.base(%r13),0x01
+		jno	.no_diag308
+		diag	%r0,%r0,0x308
+	.no_diag308:
+		sam31			# 31 bit mode
+		sr	%r1,%r1		# erase register r1
+		sr	%r2,%r2		# erase register r2
+		sigp	%r1,%r2,SIGP_SET_ARCHITECTURE # set cpuid to zero
+		lpsw	0		# hopefully start new kernel...
+
+		.align	8
+	load_psw:
+		.long	0x00080000,0x80000000
+	sys_msk:
+		.quad	0
+	ctlregs:
+		.rept	16
+		.quad	0
+		.endr
+	gprregs:
+		.rept	16
+		.quad	0
+		.endr
+	have_diag308:
+		.byte	0
+		.align	8
+	relocate_kernel_end:
+	.align 8
+	.globl	relocate_kernel_len
+	relocate_kernel_len:
+		.quad	relocate_kernel_end - relocate_kernel
diff --git a/arch/s390/kernel/runtime_instr.c b/arch/s390/kernel/runtime_instr.c
new file mode 100644
index 000000000..26b4ae96f
--- /dev/null
+++ b/arch/s390/kernel/runtime_instr.c
@@ -0,0 +1,149 @@
+/*
+ * Copyright IBM Corp. 2012
+ * Author(s): Jan Glauber <jang@linux.vnet.ibm.com>
+ */
+
+#include <linux/kernel.h>
+#include <linux/syscalls.h>
+#include <linux/signal.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/init.h>
+#include <linux/errno.h>
+#include <linux/kernel_stat.h>
+#include <asm/runtime_instr.h>
+#include <asm/cpu_mf.h>
+#include <asm/irq.h>
+
+/* empty control block to disable RI by loading it */
+struct runtime_instr_cb runtime_instr_empty_cb;
+
+static int runtime_instr_avail(void)
+{
+	return test_facility(64);
+}
+
+static void disable_runtime_instr(void)
+{
+	struct pt_regs *regs = task_pt_regs(current);
+
+	load_runtime_instr_cb(&runtime_instr_empty_cb);
+
+	/*
+	 * Make sure the RI bit is deleted from the PSW. If the user did not
+	 * switch off RI before the system call the process will get a
+	 * specification exception otherwise.
+	 */
+	regs->psw.mask &= ~PSW_MASK_RI;
+}
+
+static void init_runtime_instr_cb(struct runtime_instr_cb *cb)
+{
+	cb->buf_limit = 0xfff;
+	cb->int_requested = 1;
+	cb->pstate = 1;
+	cb->pstate_set_buf = 1;
+	cb->pstate_sample = 1;
+	cb->pstate_collect = 1;
+	cb->key = PAGE_DEFAULT_KEY;
+	cb->valid = 1;
+}
+
+void exit_thread_runtime_instr(void)
+{
+	struct task_struct *task = current;
+
+	if (!task->thread.ri_cb)
+		return;
+	disable_runtime_instr();
+	kfree(task->thread.ri_cb);
+	task->thread.ri_signum = 0;
+	task->thread.ri_cb = NULL;
+}
+
+static void runtime_instr_int_handler(struct ext_code ext_code,
+				unsigned int param32, unsigned long param64)
+{
+	struct siginfo info;
+
+	if (!(param32 & CPU_MF_INT_RI_MASK))
+		return;
+
+	inc_irq_stat(IRQEXT_CMR);
+
+	if (!current->thread.ri_cb)
+		return;
+	if (current->thread.ri_signum < SIGRTMIN ||
+	    current->thread.ri_signum > SIGRTMAX) {
+		WARN_ON_ONCE(1);
+		return;
+	}
+
+	memset(&info, 0, sizeof(info));
+	info.si_signo = current->thread.ri_signum;
+	info.si_code = SI_QUEUE;
+	if (param32 & CPU_MF_INT_RI_BUF_FULL)
+		info.si_int = ENOBUFS;
+	else if (param32 & CPU_MF_INT_RI_HALTED)
+		info.si_int = ECANCELED;
+	else
+		return; /* unknown reason */
+
+	send_sig_info(current->thread.ri_signum, &info, current);
+}
+
+SYSCALL_DEFINE2(s390_runtime_instr, int, command, int, signum)
+{
+	struct runtime_instr_cb *cb;
+
+	if (!runtime_instr_avail())
+		return -EOPNOTSUPP;
+
+	if (command == S390_RUNTIME_INSTR_STOP) {
+		preempt_disable();
+		exit_thread_runtime_instr();
+		preempt_enable();
+		return 0;
+	}
+
+	if (command != S390_RUNTIME_INSTR_START ||
+	    (signum < SIGRTMIN || signum > SIGRTMAX))
+		return -EINVAL;
+
+	if (!current->thread.ri_cb) {
+		cb = kzalloc(sizeof(*cb), GFP_KERNEL);
+		if (!cb)
+			return -ENOMEM;
+	} else {
+		cb = current->thread.ri_cb;
+		memset(cb, 0, sizeof(*cb));
+	}
+
+	init_runtime_instr_cb(cb);
+	current->thread.ri_signum = signum;
+
+	/* now load the control block to make it available */
+	preempt_disable();
+	current->thread.ri_cb = cb;
+	load_runtime_instr_cb(cb);
+	preempt_enable();
+	return 0;
+}
+
+static int __init runtime_instr_init(void)
+{
+	int rc;
+
+	if (!runtime_instr_avail())
+		return 0;
+
+	irq_subclass_register(IRQ_SUBCLASS_MEASUREMENT_ALERT);
+	rc = register_external_irq(EXT_IRQ_MEASURE_ALERT,
+				   runtime_instr_int_handler);
+	if (rc)
+		irq_subclass_unregister(IRQ_SUBCLASS_MEASUREMENT_ALERT);
+	else
+		pr_info("Runtime instrumentation facility initialized\n");
+	return rc;
+}
+device_initcall(runtime_instr_init);
diff --git a/arch/s390/kernel/s390_ksyms.c b/arch/s390/kernel/s390_ksyms.c
new file mode 100644
index 000000000..9f6046793
--- /dev/null
+++ b/arch/s390/kernel/s390_ksyms.c
@@ -0,0 +1,13 @@
+#include <linux/module.h>
+#include <linux/kvm_host.h>
+#include <asm/ftrace.h>
+
+#ifdef CONFIG_FUNCTION_TRACER
+EXPORT_SYMBOL(_mcount);
+#endif
+#if IS_ENABLED(CONFIG_KVM)
+EXPORT_SYMBOL(sie64a);
+EXPORT_SYMBOL(sie_exit);
+#endif
+EXPORT_SYMBOL(memcpy);
+EXPORT_SYMBOL(memset);
diff --git a/arch/s390/kernel/sclp.S b/arch/s390/kernel/sclp.S
new file mode 100644
index 000000000..43c3169ea
--- /dev/null
+++ b/arch/s390/kernel/sclp.S
@@ -0,0 +1,351 @@
+/*
+ * Mini SCLP driver.
+ *
+ * Copyright IBM Corp. 2004, 2009
+ *
+ *   Author(s):	Peter Oberparleiter <Peter.Oberparleiter@de.ibm.com>,
+ *		Heiko Carstens <heiko.carstens@de.ibm.com>,
+ *
+ */
+
+#include <linux/linkage.h>
+#include <asm/irq.h>
+
+LC_EXT_NEW_PSW		= 0x58			# addr of ext int handler
+LC_EXT_NEW_PSW_64	= 0x1b0			# addr of ext int handler 64 bit
+LC_EXT_INT_PARAM	= 0x80			# addr of ext int parameter
+LC_EXT_INT_CODE		= 0x86			# addr of ext int code
+LC_AR_MODE_ID		= 0xa3
+
+#
+# Subroutine which waits synchronously until either an external interruption
+# or a timeout occurs.
+#
+# Parameters:
+#   R2	= 0 for no timeout, non-zero for timeout in (approximated) seconds
+#
+# Returns:
+#   R2	= 0 on interrupt, 2 on timeout
+#   R3	= external interruption parameter if R2=0
+#
+
+_sclp_wait_int:
+	stm	%r6,%r15,24(%r15)		# save registers
+	basr	%r13,0				# get base register
+.LbaseS1:
+	ahi	%r15,-96			# create stack frame
+	la	%r8,LC_EXT_NEW_PSW		# register int handler
+	la	%r9,.LextpswS1-.LbaseS1(%r13)
+	tm	LC_AR_MODE_ID,1
+	jno	.Lesa1
+	la	%r8,LC_EXT_NEW_PSW_64		# register int handler 64 bit
+	la	%r9,.LextpswS1_64-.LbaseS1(%r13)
+.Lesa1:
+	mvc	.LoldpswS1-.LbaseS1(16,%r13),0(%r8)
+	mvc	0(16,%r8),0(%r9)
+	epsw	%r6,%r7				# set current addressing mode
+	nill	%r6,0x1				# in new psw (31 or 64 bit mode)
+	nilh	%r7,0x8000
+	stm	%r6,%r7,0(%r8)
+	lhi	%r6,0x0200			# cr mask for ext int (cr0.54)
+	ltr	%r2,%r2
+	jz	.LsetctS1
+	ahi	%r6,0x0800			# cr mask for clock int (cr0.52)
+	stck	.LtimeS1-.LbaseS1(%r13)		# initiate timeout
+	al	%r2,.LtimeS1-.LbaseS1(%r13)
+	st	%r2,.LtimeS1-.LbaseS1(%r13)
+	sckc	.LtimeS1-.LbaseS1(%r13)
+
+.LsetctS1:
+	stctl	%c0,%c0,.LctlS1-.LbaseS1(%r13)	# enable required interrupts
+	l	%r0,.LctlS1-.LbaseS1(%r13)
+	lhi	%r1,~(0x200 | 0x800)		# clear old values
+	nr	%r1,%r0
+	or	%r1,%r6				# set new value
+	st	%r1,.LctlS1-.LbaseS1(%r13)
+	lctl	%c0,%c0,.LctlS1-.LbaseS1(%r13)
+	st	%r0,.LctlS1-.LbaseS1(%r13)
+	lhi	%r2,2				# return code for timeout
+.LloopS1:
+	lpsw	.LwaitpswS1-.LbaseS1(%r13)	# wait until interrupt
+.LwaitS1:
+	lh	%r7,LC_EXT_INT_CODE
+	chi	%r7,EXT_IRQ_CLK_COMP		# timeout?
+	je	.LtimeoutS1
+	chi	%r7,EXT_IRQ_SERVICE_SIG		# service int?
+	jne	.LloopS1
+	sr	%r2,%r2
+	l	%r3,LC_EXT_INT_PARAM
+.LtimeoutS1:
+	lctl	%c0,%c0,.LctlS1-.LbaseS1(%r13)	# restore interrupt setting
+	# restore old handler
+	mvc	0(16,%r8),.LoldpswS1-.LbaseS1(%r13)
+	lm	%r6,%r15,120(%r15)		# restore registers
+	br	%r14				# return to caller
+
+	.align	8
+.LoldpswS1:
+	.long	0, 0, 0, 0			# old ext int PSW
+.LextpswS1:
+	.long	0x00080000, 0x80000000+.LwaitS1	# PSW to handle ext int
+.LextpswS1_64:
+	.quad	0, .LwaitS1			# PSW to handle ext int, 64 bit
+.LwaitpswS1:
+	.long	0x010a0000, 0x00000000+.LloopS1	# PSW to wait for ext int
+.LtimeS1:
+	.quad	0				# current time
+.LctlS1:
+	.long	0				# CT0 contents
+
+#
+# Subroutine to synchronously issue a service call.
+#
+# Parameters:
+#   R2	= command word
+#   R3	= sccb address
+#
+# Returns:
+#   R2	= 0 on success, 1 on failure
+#   R3	= sccb response code if R2 = 0
+#
+
+_sclp_servc:
+	stm	%r6,%r15,24(%r15)		# save registers
+	ahi	%r15,-96			# create stack frame
+	lr	%r6,%r2				# save command word
+	lr	%r7,%r3				# save sccb address
+.LretryS2:
+	lhi	%r2,1				# error return code
+	.insn	rre,0xb2200000,%r6,%r7		# servc
+	brc	1,.LendS2			# exit if not operational
+	brc	8,.LnotbusyS2			# go on if not busy
+	sr	%r2,%r2				# wait until no longer busy
+	bras	%r14,_sclp_wait_int
+	j	.LretryS2			# retry
+.LnotbusyS2:
+	sr	%r2,%r2				# wait until result
+	bras	%r14,_sclp_wait_int
+	sr	%r2,%r2
+	lh	%r3,6(%r7)
+.LendS2:
+	lm	%r6,%r15,120(%r15)		# restore registers
+	br	%r14
+
+#
+# Subroutine to set up the SCLP interface.
+#
+# Parameters:
+#   R2	= 0 to activate, non-zero to deactivate
+#
+# Returns:
+#   R2	= 0 on success, non-zero on failure
+#
+
+_sclp_setup:
+	stm	%r6,%r15,24(%r15)		# save registers
+	ahi	%r15,-96			# create stack frame
+	basr	%r13,0				# get base register
+.LbaseS3:
+	l	%r6,.LsccbS0-.LbaseS3(%r13)	# prepare init mask sccb
+	mvc	0(.LinitendS3-.LinitsccbS3,%r6),.LinitsccbS3-.LbaseS3(%r13)
+	ltr	%r2,%r2				# initialization?
+	jz	.LdoinitS3			# go ahead
+	# clear masks
+	xc	.LinitmaskS3-.LinitsccbS3(8,%r6),.LinitmaskS3-.LinitsccbS3(%r6)
+.LdoinitS3:
+	l	%r2,.LwritemaskS3-.LbaseS3(%r13)# get command word
+	lr	%r3,%r6				# get sccb address
+	bras	%r14,_sclp_servc		# issue service call
+	ltr	%r2,%r2				# servc successful?
+	jnz	.LerrorS3
+	chi	%r3,0x20			# write mask successful?
+	jne	.LerrorS3
+	# check masks
+	la	%r2,.LinitmaskS3-.LinitsccbS3(%r6)
+	l	%r1,0(%r2)			# receive mask ok?
+	n	%r1,12(%r2)
+	cl	%r1,0(%r2)
+	jne	.LerrorS3
+	l	%r1,4(%r2)			# send mask ok?
+	n	%r1,8(%r2)
+	cl	%r1,4(%r2)
+	sr	%r2,%r2
+	je	.LendS3
+.LerrorS3:
+	lhi	%r2,1				# error return code
+.LendS3:
+	lm	%r6,%r15,120(%r15)		# restore registers
+	br	%r14
+.LwritemaskS3:
+	.long	0x00780005			# SCLP command for write mask
+.LinitsccbS3:
+	.word	.LinitendS3-.LinitsccbS3
+	.byte	0,0,0,0
+	.word	0
+	.word	0
+	.word	4
+.LinitmaskS3:
+	.long	0x80000000
+	.long	0x40000000
+	.long	0
+	.long	0
+.LinitendS3:
+
+#
+# Subroutine which prints a given text to the SCLP console.
+#
+# Parameters:
+#   R2	= address of nil-terminated ASCII text
+#
+# Returns:
+#   R2	= 0 on success, 1 on failure
+#
+
+_sclp_print:
+	stm	%r6,%r15,24(%r15)		# save registers
+	ahi	%r15,-96			# create stack frame
+	basr	%r13,0				# get base register
+.LbaseS4:
+	l	%r8,.LsccbS0-.LbaseS4(%r13)	# prepare write data sccb
+	mvc	0(.LmtoS4-.LwritesccbS4,%r8),.LwritesccbS4-.LbaseS4(%r13)
+	la	%r7,.LmtoS4-.LwritesccbS4(%r8)	# current mto addr
+	sr	%r0,%r0
+	l	%r10,.Lascebc-.LbaseS4(%r13)	# address of translation table
+.LinitmtoS4:
+	# initialize mto
+	mvc	0(.LmtoendS4-.LmtoS4,%r7),.LmtoS4-.LbaseS4(%r13)
+	lhi	%r6,.LmtoendS4-.LmtoS4		# current mto length
+.LloopS4:
+	ic	%r0,0(%r2)			# get character
+	ahi	%r2,1
+	ltr	%r0,%r0				# end of string?
+	jz	.LfinalizemtoS4
+	chi	%r0,0x0a			# end of line (NL)?
+	jz	.LfinalizemtoS4
+	stc	%r0,0(%r6,%r7)			# copy to mto
+	la	%r11,0(%r6,%r7)
+	tr	0(1,%r11),0(%r10)		# translate to EBCDIC
+	ahi	%r6,1
+	j	.LloopS4
+.LfinalizemtoS4:
+	sth	%r6,0(%r7)			# update mto length
+	lh	%r9,.LmdbS4-.LwritesccbS4(%r8)	# update mdb length
+	ar	%r9,%r6
+	sth	%r9,.LmdbS4-.LwritesccbS4(%r8)
+	lh	%r9,.LevbufS4-.LwritesccbS4(%r8)# update evbuf length
+	ar	%r9,%r6
+	sth	%r9,.LevbufS4-.LwritesccbS4(%r8)
+	lh	%r9,0(%r8)			# update sccb length
+	ar	%r9,%r6
+	sth	%r9,0(%r8)
+	ar	%r7,%r6				# update current mto address
+	ltr	%r0,%r0				# more characters?
+	jnz	.LinitmtoS4
+	l	%r2,.LwritedataS4-.LbaseS4(%r13)# write data
+	lr	%r3,%r8
+	bras	%r14,_sclp_servc
+	ltr	%r2,%r2				# servc successful?
+	jnz	.LendS4
+	chi	%r3,0x20			# write data successful?
+	je	.LendS4
+	lhi	%r2,1				# error return code
+.LendS4:
+	lm	%r6,%r15,120(%r15)		# restore registers
+	br	%r14
+
+#
+# Function which prints a given text to the SCLP console.
+#
+# Parameters:
+#   R2	= address of nil-terminated ASCII text
+#
+# Returns:
+#   R2	= 0 on success, 1 on failure
+#
+
+ENTRY(_sclp_print_early)
+	stm	%r6,%r15,24(%r15)		# save registers
+	ahi	%r15,-96			# create stack frame
+	tm	LC_AR_MODE_ID,1
+	jno	.Lesa2
+	ahi	%r15,-80
+	stmh	%r6,%r15,96(%r15)		# store upper register halves
+.Lesa2:
+	lr	%r10,%r2			# save string pointer
+	lhi	%r2,0
+	bras	%r14,_sclp_setup		# enable console
+	ltr	%r2,%r2
+	jnz	.LendS5
+	lr	%r2,%r10
+	bras	%r14,_sclp_print		# print string
+	ltr	%r2,%r2
+	jnz	.LendS5
+	lhi	%r2,1
+	bras	%r14,_sclp_setup		# disable console
+.LendS5:
+	tm	LC_AR_MODE_ID,1
+	jno	.Lesa3
+	lgfr	%r2,%r2				# sign extend return value
+	lmh	%r6,%r15,96(%r15)		# restore upper register halves
+	ahi	%r15,80
+.Lesa3:
+	lm	%r6,%r15,120(%r15)		# restore registers
+	br	%r14
+
+.LwritedataS4:
+	.long	0x00760005			# SCLP command for write data
+.LwritesccbS4:
+	# sccb
+	.word	.LmtoS4-.LwritesccbS4
+	.byte	0
+	.byte	0,0,0
+	.word	0
+
+	# evbuf
+.LevbufS4:
+	.word	.LmtoS4-.LevbufS4
+	.byte	0x02
+	.byte	0
+	.word	0
+
+.LmdbS4:
+	# mdb
+	.word	.LmtoS4-.LmdbS4
+	.word	1
+	.long	0xd4c4c240
+	.long	1
+
+	# go
+.LgoS4:
+	.word	.LmtoS4-.LgoS4
+	.word	1
+	.long	0
+	.byte	0,0,0,0,0,0,0,0
+	.byte	0,0,0
+	.byte	0
+	.byte	0,0,0,0,0,0,0
+	.byte	0
+	.word	0
+	.byte	0,0,0,0,0,0,0,0,0,0
+	.byte	0,0,0,0,0,0,0,0
+	.byte	0,0,0,0,0,0,0,0
+
+.LmtoS4:
+	.word	.LmtoendS4-.LmtoS4
+	.word	4
+	.word	0x1000
+	.byte	0
+	.byte	0,0,0
+.LmtoendS4:
+
+	# Global constants
+.LsccbS0:
+	.long	_sclp_work_area
+.Lascebc:
+	.long	_ascebc
+
+.section .data,"aw",@progbits
+	.balign 4096
+_sclp_work_area:
+	.fill	4096
+.previous
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
new file mode 100644
index 000000000..7262fe438
--- /dev/null
+++ b/arch/s390/kernel/setup.c
@@ -0,0 +1,892 @@
+/*
+ *  S390 version
+ *    Copyright IBM Corp. 1999, 2012
+ *    Author(s): Hartmut Penner (hp@de.ibm.com),
+ *               Martin Schwidefsky (schwidefsky@de.ibm.com)
+ *
+ *  Derived from "arch/i386/kernel/setup.c"
+ *    Copyright (C) 1995, Linus Torvalds
+ */
+
+/*
+ * This file handles the architecture-dependent parts of initialization
+ */
+
+#define KMSG_COMPONENT "setup"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
+#include <linux/errno.h>
+#include <linux/export.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/memblock.h>
+#include <linux/mm.h>
+#include <linux/stddef.h>
+#include <linux/unistd.h>
+#include <linux/ptrace.h>
+#include <linux/random.h>
+#include <linux/user.h>
+#include <linux/tty.h>
+#include <linux/ioport.h>
+#include <linux/delay.h>
+#include <linux/init.h>
+#include <linux/initrd.h>
+#include <linux/bootmem.h>
+#include <linux/root_dev.h>
+#include <linux/console.h>
+#include <linux/kernel_stat.h>
+#include <linux/device.h>
+#include <linux/notifier.h>
+#include <linux/pfn.h>
+#include <linux/ctype.h>
+#include <linux/reboot.h>
+#include <linux/topology.h>
+#include <linux/kexec.h>
+#include <linux/crash_dump.h>
+#include <linux/memory.h>
+#include <linux/compat.h>
+
+#include <asm/ipl.h>
+#include <asm/facility.h>
+#include <asm/smp.h>
+#include <asm/mmu_context.h>
+#include <asm/cpcmd.h>
+#include <asm/lowcore.h>
+#include <asm/irq.h>
+#include <asm/page.h>
+#include <asm/ptrace.h>
+#include <asm/sections.h>
+#include <asm/ebcdic.h>
+#include <asm/kvm_virtio.h>
+#include <asm/diag.h>
+#include <asm/os_info.h>
+#include <asm/sclp.h>
+#include <asm/sysinfo.h>
+#include "entry.h"
+
+/*
+ * Machine setup..
+ */
+unsigned int console_mode = 0;
+EXPORT_SYMBOL(console_mode);
+
+unsigned int console_devno = -1;
+EXPORT_SYMBOL(console_devno);
+
+unsigned int console_irq = -1;
+EXPORT_SYMBOL(console_irq);
+
+unsigned long elf_hwcap = 0;
+char elf_platform[ELF_PLATFORM_SIZE];
+
+int __initdata memory_end_set;
+unsigned long __initdata memory_end;
+unsigned long __initdata max_physmem_end;
+
+unsigned long VMALLOC_START;
+EXPORT_SYMBOL(VMALLOC_START);
+
+unsigned long VMALLOC_END;
+EXPORT_SYMBOL(VMALLOC_END);
+
+struct page *vmemmap;
+EXPORT_SYMBOL(vmemmap);
+
+unsigned long MODULES_VADDR;
+unsigned long MODULES_END;
+
+/* An array with a pointer to the lowcore of every CPU. */
+struct _lowcore *lowcore_ptr[NR_CPUS];
+EXPORT_SYMBOL(lowcore_ptr);
+
+/*
+ * This is set up by the setup-routine at boot-time
+ * for S390 need to find out, what we have to setup
+ * using address 0x10400 ...
+ */
+
+#include <asm/setup.h>
+
+/*
+ * condev= and conmode= setup parameter.
+ */
+
+static int __init condev_setup(char *str)
+{
+	int vdev;
+
+	vdev = simple_strtoul(str, &str, 0);
+	if (vdev >= 0 && vdev < 65536) {
+		console_devno = vdev;
+		console_irq = -1;
+	}
+	return 1;
+}
+
+__setup("condev=", condev_setup);
+
+static void __init set_preferred_console(void)
+{
+	if (MACHINE_IS_KVM) {
+		if (sclp_has_vt220())
+			add_preferred_console("ttyS", 1, NULL);
+		else if (sclp_has_linemode())
+			add_preferred_console("ttyS", 0, NULL);
+		else
+			add_preferred_console("hvc", 0, NULL);
+	} else if (CONSOLE_IS_3215 || CONSOLE_IS_SCLP)
+		add_preferred_console("ttyS", 0, NULL);
+	else if (CONSOLE_IS_3270)
+		add_preferred_console("tty3270", 0, NULL);
+}
+
+static int __init conmode_setup(char *str)
+{
+#if defined(CONFIG_SCLP_CONSOLE) || defined(CONFIG_SCLP_VT220_CONSOLE)
+	if (strncmp(str, "hwc", 4) == 0 || strncmp(str, "sclp", 5) == 0)
+                SET_CONSOLE_SCLP;
+#endif
+#if defined(CONFIG_TN3215_CONSOLE)
+	if (strncmp(str, "3215", 5) == 0)
+		SET_CONSOLE_3215;
+#endif
+#if defined(CONFIG_TN3270_CONSOLE)
+	if (strncmp(str, "3270", 5) == 0)
+		SET_CONSOLE_3270;
+#endif
+	set_preferred_console();
+        return 1;
+}
+
+__setup("conmode=", conmode_setup);
+
+static void __init conmode_default(void)
+{
+	char query_buffer[1024];
+	char *ptr;
+
+        if (MACHINE_IS_VM) {
+		cpcmd("QUERY CONSOLE", query_buffer, 1024, NULL);
+		console_devno = simple_strtoul(query_buffer + 5, NULL, 16);
+		ptr = strstr(query_buffer, "SUBCHANNEL =");
+		console_irq = simple_strtoul(ptr + 13, NULL, 16);
+		cpcmd("QUERY TERM", query_buffer, 1024, NULL);
+		ptr = strstr(query_buffer, "CONMODE");
+		/*
+		 * Set the conmode to 3215 so that the device recognition 
+		 * will set the cu_type of the console to 3215. If the
+		 * conmode is 3270 and we don't set it back then both
+		 * 3215 and the 3270 driver will try to access the console
+		 * device (3215 as console and 3270 as normal tty).
+		 */
+		cpcmd("TERM CONMODE 3215", NULL, 0, NULL);
+		if (ptr == NULL) {
+#if defined(CONFIG_SCLP_CONSOLE) || defined(CONFIG_SCLP_VT220_CONSOLE)
+			SET_CONSOLE_SCLP;
+#endif
+			return;
+		}
+		if (strncmp(ptr + 8, "3270", 4) == 0) {
+#if defined(CONFIG_TN3270_CONSOLE)
+			SET_CONSOLE_3270;
+#elif defined(CONFIG_TN3215_CONSOLE)
+			SET_CONSOLE_3215;
+#elif defined(CONFIG_SCLP_CONSOLE) || defined(CONFIG_SCLP_VT220_CONSOLE)
+			SET_CONSOLE_SCLP;
+#endif
+		} else if (strncmp(ptr + 8, "3215", 4) == 0) {
+#if defined(CONFIG_TN3215_CONSOLE)
+			SET_CONSOLE_3215;
+#elif defined(CONFIG_TN3270_CONSOLE)
+			SET_CONSOLE_3270;
+#elif defined(CONFIG_SCLP_CONSOLE) || defined(CONFIG_SCLP_VT220_CONSOLE)
+			SET_CONSOLE_SCLP;
+#endif
+		}
+	} else {
+#if defined(CONFIG_SCLP_CONSOLE) || defined(CONFIG_SCLP_VT220_CONSOLE)
+		SET_CONSOLE_SCLP;
+#endif
+	}
+}
+
+#ifdef CONFIG_CRASH_DUMP
+static void __init setup_zfcpdump(void)
+{
+	if (ipl_info.type != IPL_TYPE_FCP_DUMP)
+		return;
+	if (OLDMEM_BASE)
+		return;
+	strcat(boot_command_line, " cio_ignore=all,!ipldev,!condev");
+	console_loglevel = 2;
+}
+#else
+static inline void setup_zfcpdump(void) {}
+#endif /* CONFIG_CRASH_DUMP */
+
+ /*
+ * Reboot, halt and power_off stubs. They just call _machine_restart,
+ * _machine_halt or _machine_power_off. 
+ */
+
+void machine_restart(char *command)
+{
+	if ((!in_interrupt() && !in_atomic()) || oops_in_progress)
+		/*
+		 * Only unblank the console if we are called in enabled
+		 * context or a bust_spinlocks cleared the way for us.
+		 */
+		console_unblank();
+	_machine_restart(command);
+}
+
+void machine_halt(void)
+{
+	if (!in_interrupt() || oops_in_progress)
+		/*
+		 * Only unblank the console if we are called in enabled
+		 * context or a bust_spinlocks cleared the way for us.
+		 */
+		console_unblank();
+	_machine_halt();
+}
+
+void machine_power_off(void)
+{
+	if (!in_interrupt() || oops_in_progress)
+		/*
+		 * Only unblank the console if we are called in enabled
+		 * context or a bust_spinlocks cleared the way for us.
+		 */
+		console_unblank();
+	_machine_power_off();
+}
+
+/*
+ * Dummy power off function.
+ */
+void (*pm_power_off)(void) = machine_power_off;
+EXPORT_SYMBOL_GPL(pm_power_off);
+
+static int __init early_parse_mem(char *p)
+{
+	memory_end = memparse(p, &p);
+	memory_end &= PAGE_MASK;
+	memory_end_set = 1;
+	return 0;
+}
+early_param("mem", early_parse_mem);
+
+static int __init parse_vmalloc(char *arg)
+{
+	if (!arg)
+		return -EINVAL;
+	VMALLOC_END = (memparse(arg, &arg) + PAGE_SIZE - 1) & PAGE_MASK;
+	return 0;
+}
+early_param("vmalloc", parse_vmalloc);
+
+void *restart_stack __attribute__((__section__(".data")));
+
+static void __init setup_lowcore(void)
+{
+	struct _lowcore *lc;
+
+	/*
+	 * Setup lowcore for boot cpu
+	 */
+	BUILD_BUG_ON(sizeof(struct _lowcore) != LC_PAGES * 4096);
+	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) restart_int_handler;
+	lc->external_new_psw.mask = PSW_KERNEL_BITS |
+		PSW_MASK_DAT | PSW_MASK_MCHECK;
+	lc->external_new_psw.addr =
+		PSW_ADDR_AMODE | (unsigned long) ext_int_handler;
+	lc->svc_new_psw.mask = PSW_KERNEL_BITS |
+		PSW_MASK_DAT | PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK;
+	lc->svc_new_psw.addr = PSW_ADDR_AMODE | (unsigned long) system_call;
+	lc->program_new_psw.mask = PSW_KERNEL_BITS |
+		PSW_MASK_DAT | PSW_MASK_MCHECK;
+	lc->program_new_psw.addr =
+		PSW_ADDR_AMODE | (unsigned long) pgm_check_handler;
+	lc->mcck_new_psw.mask = PSW_KERNEL_BITS;
+	lc->mcck_new_psw.addr =
+		PSW_ADDR_AMODE | (unsigned long) mcck_int_handler;
+	lc->io_new_psw.mask = PSW_KERNEL_BITS |
+		PSW_MASK_DAT | PSW_MASK_MCHECK;
+	lc->io_new_psw.addr = PSW_ADDR_AMODE | (unsigned long) io_int_handler;
+	lc->clock_comparator = -1ULL;
+	lc->kernel_stack = ((unsigned long) &init_thread_union)
+		+ THREAD_SIZE - STACK_FRAME_OVERHEAD - sizeof(struct pt_regs);
+	lc->async_stack = (unsigned long)
+		__alloc_bootmem(ASYNC_SIZE, ASYNC_SIZE, 0)
+		+ ASYNC_SIZE - STACK_FRAME_OVERHEAD - sizeof(struct pt_regs);
+	lc->panic_stack = (unsigned long)
+		__alloc_bootmem(PAGE_SIZE, PAGE_SIZE, 0)
+		+ PAGE_SIZE - STACK_FRAME_OVERHEAD - sizeof(struct pt_regs);
+	lc->current_task = (unsigned long) init_thread_union.thread_info.task;
+	lc->thread_info = (unsigned long) &init_thread_union;
+	lc->machine_flags = S390_lowcore.machine_flags;
+	lc->stfl_fac_list = S390_lowcore.stfl_fac_list;
+	memcpy(lc->stfle_fac_list, S390_lowcore.stfle_fac_list,
+	       MAX_FACILITY_BIT/8);
+	if (MACHINE_HAS_VX)
+		lc->vector_save_area_addr =
+			(unsigned long) &lc->vector_save_area;
+	lc->vdso_per_cpu_data = (unsigned long) &lc->paste[0];
+	lc->sync_enter_timer = S390_lowcore.sync_enter_timer;
+	lc->async_enter_timer = S390_lowcore.async_enter_timer;
+	lc->exit_timer = S390_lowcore.exit_timer;
+	lc->user_timer = S390_lowcore.user_timer;
+	lc->system_timer = S390_lowcore.system_timer;
+	lc->steal_timer = S390_lowcore.steal_timer;
+	lc->last_update_timer = S390_lowcore.last_update_timer;
+	lc->last_update_clock = S390_lowcore.last_update_clock;
+
+	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 necessary 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;
+
+	/* Setup absolute zero lowcore */
+	mem_assign_absolute(S390_lowcore.restart_stack, lc->restart_stack);
+	mem_assign_absolute(S390_lowcore.restart_fn, lc->restart_fn);
+	mem_assign_absolute(S390_lowcore.restart_data, lc->restart_data);
+	mem_assign_absolute(S390_lowcore.restart_source, lc->restart_source);
+	mem_assign_absolute(S390_lowcore.restart_psw, lc->restart_psw);
+
+#ifdef CONFIG_SMP
+	lc->spinlock_lockval = arch_spin_lockval(0);
+#endif
+
+	set_prefix((u32)(unsigned long) lc);
+	lowcore_ptr[0] = lc;
+}
+
+static struct resource code_resource = {
+	.name  = "Kernel code",
+	.flags = IORESOURCE_BUSY | IORESOURCE_MEM,
+};
+
+static struct resource data_resource = {
+	.name = "Kernel data",
+	.flags = IORESOURCE_BUSY | IORESOURCE_MEM,
+};
+
+static struct resource bss_resource = {
+	.name = "Kernel bss",
+	.flags = IORESOURCE_BUSY | IORESOURCE_MEM,
+};
+
+static struct resource __initdata *standard_resources[] = {
+	&code_resource,
+	&data_resource,
+	&bss_resource,
+};
+
+static void __init setup_resources(void)
+{
+	struct resource *res, *std_res, *sub_res;
+	struct memblock_region *reg;
+	int j;
+
+	code_resource.start = (unsigned long) &_text;
+	code_resource.end = (unsigned long) &_etext - 1;
+	data_resource.start = (unsigned long) &_etext;
+	data_resource.end = (unsigned long) &_edata - 1;
+	bss_resource.start = (unsigned long) &__bss_start;
+	bss_resource.end = (unsigned long) &__bss_stop - 1;
+
+	for_each_memblock(memory, reg) {
+		res = alloc_bootmem_low(sizeof(*res));
+		res->flags = IORESOURCE_BUSY | IORESOURCE_MEM;
+
+		res->name = "System RAM";
+		res->start = reg->base;
+		res->end = reg->base + reg->size - 1;
+		request_resource(&iomem_resource, res);
+
+		for (j = 0; j < ARRAY_SIZE(standard_resources); j++) {
+			std_res = standard_resources[j];
+			if (std_res->start < res->start ||
+			    std_res->start > res->end)
+				continue;
+			if (std_res->end > res->end) {
+				sub_res = alloc_bootmem_low(sizeof(*sub_res));
+				*sub_res = *std_res;
+				sub_res->end = res->end;
+				std_res->start = res->end + 1;
+				request_resource(res, sub_res);
+			} else {
+				request_resource(res, std_res);
+			}
+		}
+	}
+}
+
+static void __init setup_memory_end(void)
+{
+	unsigned long vmax, vmalloc_size, tmp;
+
+	/* Choose kernel address space layout: 2, 3, or 4 levels. */
+	vmalloc_size = VMALLOC_END ?: (128UL << 30) - MODULES_LEN;
+	tmp = (memory_end ?: max_physmem_end) / PAGE_SIZE;
+	tmp = tmp * (sizeof(struct page) + PAGE_SIZE);
+	if (tmp + vmalloc_size + MODULES_LEN <= (1UL << 42))
+		vmax = 1UL << 42;	/* 3-level kernel page table */
+	else
+		vmax = 1UL << 53;	/* 4-level kernel page table */
+	/* module area is at the end of the kernel address space. */
+	MODULES_END = vmax;
+	MODULES_VADDR = MODULES_END - MODULES_LEN;
+	VMALLOC_END = MODULES_VADDR;
+	VMALLOC_START = vmax - vmalloc_size;
+
+	/* Split remaining virtual space between 1:1 mapping & vmemmap array */
+	tmp = VMALLOC_START / (PAGE_SIZE + sizeof(struct page));
+	/* vmemmap contains a multiple of PAGES_PER_SECTION struct pages */
+	tmp = SECTION_ALIGN_UP(tmp);
+	tmp = VMALLOC_START - tmp * sizeof(struct page);
+	tmp &= ~((vmax >> 11) - 1);	/* align to page table level */
+	tmp = min(tmp, 1UL << MAX_PHYSMEM_BITS);
+	vmemmap = (struct page *) tmp;
+
+	/* Take care that memory_end is set and <= vmemmap */
+	memory_end = min(memory_end ?: max_physmem_end, tmp);
+	max_pfn = max_low_pfn = PFN_DOWN(memory_end);
+	memblock_remove(memory_end, ULONG_MAX);
+
+	pr_notice("Max memory size: %luMB\n", memory_end >> 20);
+}
+
+static void __init setup_vmcoreinfo(void)
+{
+	mem_assign_absolute(S390_lowcore.vmcore_info, paddr_vmcoreinfo_note());
+}
+
+#ifdef CONFIG_CRASH_DUMP
+
+/*
+ * When kdump is enabled, we have to ensure that no memory from
+ * the area [0 - crashkernel memory size] and
+ * [crashk_res.start - crashk_res.end] is set offline.
+ */
+static int kdump_mem_notifier(struct notifier_block *nb,
+			      unsigned long action, void *data)
+{
+	struct memory_notify *arg = data;
+
+	if (action != MEM_GOING_OFFLINE)
+		return NOTIFY_OK;
+	if (arg->start_pfn < PFN_DOWN(resource_size(&crashk_res)))
+		return NOTIFY_BAD;
+	if (arg->start_pfn > PFN_DOWN(crashk_res.end))
+		return NOTIFY_OK;
+	if (arg->start_pfn + arg->nr_pages - 1 < PFN_DOWN(crashk_res.start))
+		return NOTIFY_OK;
+	return NOTIFY_BAD;
+}
+
+static struct notifier_block kdump_mem_nb = {
+	.notifier_call = kdump_mem_notifier,
+};
+
+#endif
+
+/*
+ * Make sure that the area behind memory_end is protected
+ */
+static void reserve_memory_end(void)
+{
+#ifdef CONFIG_CRASH_DUMP
+	if (ipl_info.type == IPL_TYPE_FCP_DUMP &&
+	    !OLDMEM_BASE && sclp_get_hsa_size()) {
+		memory_end = sclp_get_hsa_size();
+		memory_end &= PAGE_MASK;
+		memory_end_set = 1;
+	}
+#endif
+	if (!memory_end_set)
+		return;
+	memblock_reserve(memory_end, ULONG_MAX);
+}
+
+/*
+ * Make sure that oldmem, where the dump is stored, is protected
+ */
+static void reserve_oldmem(void)
+{
+#ifdef CONFIG_CRASH_DUMP
+	if (OLDMEM_BASE)
+		/* Forget all memory above the running kdump system */
+		memblock_reserve(OLDMEM_SIZE, (phys_addr_t)ULONG_MAX);
+#endif
+}
+
+/*
+ * Make sure that oldmem, where the dump is stored, is protected
+ */
+static void remove_oldmem(void)
+{
+#ifdef CONFIG_CRASH_DUMP
+	if (OLDMEM_BASE)
+		/* Forget all memory above the running kdump system */
+		memblock_remove(OLDMEM_SIZE, (phys_addr_t)ULONG_MAX);
+#endif
+}
+
+/*
+ * Reserve memory for kdump kernel to be loaded with kexec
+ */
+static void __init reserve_crashkernel(void)
+{
+#ifdef CONFIG_CRASH_DUMP
+	unsigned long long crash_base, crash_size;
+	phys_addr_t low, high;
+	int rc;
+
+	rc = parse_crashkernel(boot_command_line, memory_end, &crash_size,
+			       &crash_base);
+
+	crash_base = ALIGN(crash_base, KEXEC_CRASH_MEM_ALIGN);
+	crash_size = ALIGN(crash_size, KEXEC_CRASH_MEM_ALIGN);
+	if (rc || crash_size == 0)
+		return;
+
+	if (memblock.memory.regions[0].size < crash_size) {
+		pr_info("crashkernel reservation failed: %s\n",
+			"first memory chunk must be at least crashkernel size");
+		return;
+	}
+
+	low = crash_base ?: OLDMEM_BASE;
+	high = low + crash_size;
+	if (low >= OLDMEM_BASE && high <= OLDMEM_BASE + OLDMEM_SIZE) {
+		/* The crashkernel fits into OLDMEM, reuse OLDMEM */
+		crash_base = low;
+	} else {
+		/* Find suitable area in free memory */
+		low = max_t(unsigned long, crash_size, sclp_get_hsa_size());
+		high = crash_base ? crash_base + crash_size : ULONG_MAX;
+
+		if (crash_base && crash_base < low) {
+			pr_info("crashkernel reservation failed: %s\n",
+				"crash_base too low");
+			return;
+		}
+		low = crash_base ?: low;
+		crash_base = memblock_find_in_range(low, high, crash_size,
+						    KEXEC_CRASH_MEM_ALIGN);
+	}
+
+	if (!crash_base) {
+		pr_info("crashkernel reservation failed: %s\n",
+			"no suitable area found");
+		return;
+	}
+
+	if (register_memory_notifier(&kdump_mem_nb))
+		return;
+
+	if (!OLDMEM_BASE && MACHINE_IS_VM)
+		diag10_range(PFN_DOWN(crash_base), PFN_DOWN(crash_size));
+	crashk_res.start = crash_base;
+	crashk_res.end = crash_base + crash_size - 1;
+	insert_resource(&iomem_resource, &crashk_res);
+	memblock_remove(crash_base, crash_size);
+	pr_info("Reserving %lluMB of memory at %lluMB "
+		"for crashkernel (System RAM: %luMB)\n",
+		crash_size >> 20, crash_base >> 20,
+		(unsigned long)memblock.memory.total_size >> 20);
+	os_info_crashkernel_add(crash_base, crash_size);
+#endif
+}
+
+/*
+ * Reserve the initrd from being used by memblock
+ */
+static void __init reserve_initrd(void)
+{
+#ifdef CONFIG_BLK_DEV_INITRD
+	initrd_start = INITRD_START;
+	initrd_end = initrd_start + INITRD_SIZE;
+	memblock_reserve(INITRD_START, INITRD_SIZE);
+#endif
+}
+
+/*
+ * Check for initrd being in usable memory
+ */
+static void __init check_initrd(void)
+{
+#ifdef CONFIG_BLK_DEV_INITRD
+	if (INITRD_START && INITRD_SIZE &&
+	    !memblock_is_region_memory(INITRD_START, INITRD_SIZE)) {
+		pr_err("initrd does not fit memory.\n");
+		memblock_free(INITRD_START, INITRD_SIZE);
+		initrd_start = initrd_end = 0;
+	}
+#endif
+}
+
+/*
+ * Reserve all kernel text
+ */
+static void __init reserve_kernel(void)
+{
+	unsigned long start_pfn;
+	start_pfn = PFN_UP(__pa(&_end));
+
+	/*
+	 * Reserve memory used for lowcore/command line/kernel image.
+	 */
+	memblock_reserve(0, (unsigned long)_ehead);
+	memblock_reserve((unsigned long)_stext, PFN_PHYS(start_pfn)
+			 - (unsigned long)_stext);
+}
+
+static void __init reserve_elfcorehdr(void)
+{
+#ifdef CONFIG_CRASH_DUMP
+	if (is_kdump_kernel())
+		memblock_reserve(elfcorehdr_addr - OLDMEM_BASE,
+				 PAGE_ALIGN(elfcorehdr_size));
+#endif
+}
+
+static void __init setup_memory(void)
+{
+	struct memblock_region *reg;
+
+	/*
+	 * Init storage key for present memory
+	 */
+	for_each_memblock(memory, reg) {
+		storage_key_init_range(reg->base, reg->base + reg->size);
+	}
+	psw_set_key(PAGE_DEFAULT_KEY);
+
+	/* Only cosmetics */
+	memblock_enforce_memory_limit(memblock_end_of_DRAM());
+}
+
+/*
+ * Setup hardware capabilities.
+ */
+static void __init setup_hwcaps(void)
+{
+	static const int stfl_bits[6] = { 0, 2, 7, 17, 19, 21 };
+	struct cpuid cpu_id;
+	int i;
+
+	/*
+	 * The store facility list bits numbers as found in the principles
+	 * of operation are numbered with bit 1UL<<31 as number 0 to
+	 * bit 1UL<<0 as number 31.
+	 *   Bit 0: instructions named N3, "backported" to esa-mode
+	 *   Bit 2: z/Architecture mode is active
+	 *   Bit 7: the store-facility-list-extended facility is installed
+	 *   Bit 17: the message-security assist is installed
+	 *   Bit 19: the long-displacement facility is installed
+	 *   Bit 21: the extended-immediate facility is installed
+	 *   Bit 22: extended-translation facility 3 is installed
+	 *   Bit 30: extended-translation facility 3 enhancement facility
+	 * These get translated to:
+	 *   HWCAP_S390_ESAN3 bit 0, HWCAP_S390_ZARCH bit 1,
+	 *   HWCAP_S390_STFLE bit 2, HWCAP_S390_MSA bit 3,
+	 *   HWCAP_S390_LDISP bit 4, HWCAP_S390_EIMM bit 5 and
+	 *   HWCAP_S390_ETF3EH bit 8 (22 && 30).
+	 */
+	for (i = 0; i < 6; i++)
+		if (test_facility(stfl_bits[i]))
+			elf_hwcap |= 1UL << i;
+
+	if (test_facility(22) && test_facility(30))
+		elf_hwcap |= HWCAP_S390_ETF3EH;
+
+	/*
+	 * Check for additional facilities with store-facility-list-extended.
+	 * stfle stores doublewords (8 byte) with bit 1ULL<<63 as bit 0
+	 * and 1ULL<<0 as bit 63. Bits 0-31 contain the same information
+	 * as stored by stfl, bits 32-xxx contain additional facilities.
+	 * How many facility words are stored depends on the number of
+	 * doublewords passed to the instruction. The additional facilities
+	 * are:
+	 *   Bit 42: decimal floating point facility is installed
+	 *   Bit 44: perform floating point operation facility is installed
+	 * translated to:
+	 *   HWCAP_S390_DFP bit 6 (42 && 44).
+	 */
+	if ((elf_hwcap & (1UL << 2)) && test_facility(42) && test_facility(44))
+		elf_hwcap |= HWCAP_S390_DFP;
+
+	/*
+	 * Huge page support HWCAP_S390_HPAGE is bit 7.
+	 */
+	if (MACHINE_HAS_HPAGE)
+		elf_hwcap |= HWCAP_S390_HPAGE;
+
+	/*
+	 * 64-bit register support for 31-bit processes
+	 * HWCAP_S390_HIGH_GPRS is bit 9.
+	 */
+	elf_hwcap |= HWCAP_S390_HIGH_GPRS;
+
+	/*
+	 * Transactional execution support HWCAP_S390_TE is bit 10.
+	 */
+	if (test_facility(50) && test_facility(73))
+		elf_hwcap |= HWCAP_S390_TE;
+
+	/*
+	 * Vector extension HWCAP_S390_VXRS is bit 11.
+	 */
+	if (test_facility(129))
+		elf_hwcap |= HWCAP_S390_VXRS;
+	get_cpu_id(&cpu_id);
+	add_device_randomness(&cpu_id, sizeof(cpu_id));
+	switch (cpu_id.machine) {
+	case 0x9672:
+		strcpy(elf_platform, "g5");
+		break;
+	case 0x2064:
+	case 0x2066:
+	default:	/* Use "z900" as default for 64 bit kernels. */
+		strcpy(elf_platform, "z900");
+		break;
+	case 0x2084:
+	case 0x2086:
+		strcpy(elf_platform, "z990");
+		break;
+	case 0x2094:
+	case 0x2096:
+		strcpy(elf_platform, "z9-109");
+		break;
+	case 0x2097:
+	case 0x2098:
+		strcpy(elf_platform, "z10");
+		break;
+	case 0x2817:
+	case 0x2818:
+		strcpy(elf_platform, "z196");
+		break;
+	case 0x2827:
+	case 0x2828:
+		strcpy(elf_platform, "zEC12");
+		break;
+	case 0x2964:
+		strcpy(elf_platform, "z13");
+		break;
+	}
+}
+
+/*
+ * Add system information as device randomness
+ */
+static void __init setup_randomness(void)
+{
+	struct sysinfo_3_2_2 *vmms;
+
+	vmms = (struct sysinfo_3_2_2 *) alloc_page(GFP_KERNEL);
+	if (vmms && stsi(vmms, 3, 2, 2) == 0 && vmms->count)
+		add_device_randomness(&vmms, vmms->count);
+	free_page((unsigned long) vmms);
+}
+
+/*
+ * Setup function called from init/main.c just after the banner
+ * was printed.
+ */
+
+void __init setup_arch(char **cmdline_p)
+{
+        /*
+         * print what head.S has found out about the machine
+         */
+	if (MACHINE_IS_VM)
+		pr_info("Linux is running as a z/VM "
+			"guest operating system in 64-bit mode\n");
+	else if (MACHINE_IS_KVM)
+		pr_info("Linux is running under KVM in 64-bit mode\n");
+	else if (MACHINE_IS_LPAR)
+		pr_info("Linux is running natively in 64-bit mode\n");
+
+	/* Have one command line that is parsed and saved in /proc/cmdline */
+	/* boot_command_line has been already set up in early.c */
+	*cmdline_p = boot_command_line;
+
+        ROOT_DEV = Root_RAM0;
+
+	/* Is init_mm really needed? */
+	init_mm.start_code = PAGE_OFFSET;
+	init_mm.end_code = (unsigned long) &_etext;
+	init_mm.end_data = (unsigned long) &_edata;
+	init_mm.brk = (unsigned long) &_end;
+
+	parse_early_param();
+	os_info_init();
+	setup_ipl();
+
+	/* Do some memory reservations *before* memory is added to memblock */
+	reserve_memory_end();
+	reserve_oldmem();
+	reserve_kernel();
+	reserve_initrd();
+	reserve_elfcorehdr();
+	memblock_allow_resize();
+
+	/* Get information about *all* installed memory */
+	detect_memory_memblock();
+
+	remove_oldmem();
+
+	/*
+	 * Make sure all chunks are MAX_ORDER aligned so we don't need the
+	 * extra checks that HOLES_IN_ZONE would require.
+	 *
+	 * Is this still required?
+	 */
+	memblock_trim_memory(1UL << (MAX_ORDER - 1 + PAGE_SHIFT));
+
+	setup_memory_end();
+	setup_memory();
+
+	check_initrd();
+	reserve_crashkernel();
+
+	setup_resources();
+	setup_vmcoreinfo();
+	setup_lowcore();
+	smp_fill_possible_mask();
+        cpu_init();
+
+	/*
+	 * Setup capabilities (ELF_HWCAP & ELF_PLATFORM).
+	 */
+	setup_hwcaps();
+
+	/*
+	 * Create kernel page tables and switch to virtual addressing.
+	 */
+        paging_init();
+
+        /* Setup default console */
+	conmode_default();
+	set_preferred_console();
+
+	/* Setup zfcpdump support */
+	setup_zfcpdump();
+
+	/* Add system specific data to the random pool */
+	setup_randomness();
+}
diff --git a/arch/s390/kernel/signal.c b/arch/s390/kernel/signal.c
new file mode 100644
index 000000000..c551f22ce
--- /dev/null
+++ b/arch/s390/kernel/signal.c
@@ -0,0 +1,559 @@
+/*
+ *    Copyright IBM Corp. 1999, 2006
+ *    Author(s): Denis Joseph Barrow (djbarrow@de.ibm.com,barrow_dj@yahoo.com)
+ *
+ *    Based on Intel version
+ * 
+ *  Copyright (C) 1991, 1992  Linus Torvalds
+ *
+ *  1997-11-28  Modified for POSIX.1b signals by Richard Henderson
+ */
+
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/smp.h>
+#include <linux/kernel.h>
+#include <linux/signal.h>
+#include <linux/errno.h>
+#include <linux/wait.h>
+#include <linux/ptrace.h>
+#include <linux/unistd.h>
+#include <linux/stddef.h>
+#include <linux/tty.h>
+#include <linux/personality.h>
+#include <linux/binfmts.h>
+#include <linux/tracehook.h>
+#include <linux/syscalls.h>
+#include <linux/compat.h>
+#include <asm/ucontext.h>
+#include <asm/uaccess.h>
+#include <asm/lowcore.h>
+#include <asm/switch_to.h>
+#include "entry.h"
+
+/*
+ * Layout of an old-style signal-frame:
+ *	-----------------------------------------
+ *	| save area (_SIGNAL_FRAMESIZE)		|
+ *	-----------------------------------------
+ *	| struct sigcontext			|
+ *	|	oldmask				|
+ *	|	_sigregs *			|
+ *	-----------------------------------------
+ *	| _sigregs with				|
+ *	|	_s390_regs_common		|
+ *	|	_s390_fp_regs			|
+ *	-----------------------------------------
+ *	| int signo				|
+ *	-----------------------------------------
+ *	| _sigregs_ext with			|
+ *	|	gprs_high 64 byte (opt)		|
+ *	|	vxrs_low 128 byte (opt)		|
+ *	|	vxrs_high 256 byte (opt)	|
+ *	|	reserved 128 byte (opt)		|
+ *	-----------------------------------------
+ *	| __u16 svc_insn			|
+ *	-----------------------------------------
+ * The svc_insn entry with the sigreturn system call opcode does not
+ * have a fixed position and moves if gprs_high or vxrs exist.
+ * Future extensions will be added to _sigregs_ext.
+ */
+struct sigframe
+{
+	__u8 callee_used_stack[__SIGNAL_FRAMESIZE];
+	struct sigcontext sc;
+	_sigregs sregs;
+	int signo;
+	_sigregs_ext sregs_ext;
+	__u16 svc_insn;		/* Offset of svc_insn is NOT fixed! */
+};
+
+/*
+ * Layout of an rt signal-frame:
+ *	-----------------------------------------
+ *	| save area (_SIGNAL_FRAMESIZE)		|
+ *	-----------------------------------------
+ *	| svc __NR_rt_sigreturn 2 byte		|
+ *	-----------------------------------------
+ *	| struct siginfo			|
+ *	-----------------------------------------
+ *	| struct ucontext_extended with		|
+ *	|	unsigned long uc_flags		|
+ *	|	struct ucontext *uc_link	|
+ *	|	stack_t uc_stack		|
+ *	|	_sigregs uc_mcontext with	|
+ *	|		_s390_regs_common	|
+ *	|		_s390_fp_regs		|
+ *	|	sigset_t uc_sigmask		|
+ *	|	_sigregs_ext uc_mcontext_ext	|
+ *	|		gprs_high 64 byte (opt)	|
+ *	|		vxrs_low 128 byte (opt)	|
+ *	|		vxrs_high 256 byte (opt)|
+ *	|		reserved 128 byte (opt)	|
+ *	-----------------------------------------
+ * Future extensions will be added to _sigregs_ext.
+ */
+struct rt_sigframe
+{
+	__u8 callee_used_stack[__SIGNAL_FRAMESIZE];
+	__u16 svc_insn;
+	struct siginfo info;
+	struct ucontext_extended uc;
+};
+
+/* Store registers needed to create the signal frame */
+static void store_sigregs(void)
+{
+	save_access_regs(current->thread.acrs);
+	save_fp_ctl(&current->thread.fp_regs.fpc);
+	if (current->thread.vxrs) {
+		int i;
+
+		save_vx_regs(current->thread.vxrs);
+		for (i = 0; i < __NUM_FPRS; i++)
+			current->thread.fp_regs.fprs[i] =
+				*(freg_t *)(current->thread.vxrs + i);
+	} else
+		save_fp_regs(current->thread.fp_regs.fprs);
+}
+
+/* Load registers after signal return */
+static void load_sigregs(void)
+{
+	restore_access_regs(current->thread.acrs);
+	/* restore_fp_ctl is done in restore_sigregs */
+	if (current->thread.vxrs) {
+		int i;
+
+		for (i = 0; i < __NUM_FPRS; i++)
+			*(freg_t *)(current->thread.vxrs + i) =
+				current->thread.fp_regs.fprs[i];
+		restore_vx_regs(current->thread.vxrs);
+	} else
+		restore_fp_regs(current->thread.fp_regs.fprs);
+}
+
+/* Returns non-zero on fault. */
+static int save_sigregs(struct pt_regs *regs, _sigregs __user *sregs)
+{
+	_sigregs user_sregs;
+
+	/* Copy a 'clean' PSW mask to the user to avoid leaking
+	   information about whether PER is currently on.  */
+	user_sregs.regs.psw.mask = PSW_USER_BITS |
+		(regs->psw.mask & (PSW_MASK_USER | PSW_MASK_RI));
+	user_sregs.regs.psw.addr = regs->psw.addr;
+	memcpy(&user_sregs.regs.gprs, &regs->gprs, sizeof(sregs->regs.gprs));
+	memcpy(&user_sregs.regs.acrs, current->thread.acrs,
+	       sizeof(user_sregs.regs.acrs));
+	memcpy(&user_sregs.fpregs, &current->thread.fp_regs,
+	       sizeof(user_sregs.fpregs));
+	if (__copy_to_user(sregs, &user_sregs, sizeof(_sigregs)))
+		return -EFAULT;
+	return 0;
+}
+
+static int restore_sigregs(struct pt_regs *regs, _sigregs __user *sregs)
+{
+	_sigregs user_sregs;
+
+	/* Alwys make any pending restarted system call return -EINTR */
+	current->restart_block.fn = do_no_restart_syscall;
+
+	if (__copy_from_user(&user_sregs, sregs, sizeof(user_sregs)))
+		return -EFAULT;
+
+	if (!is_ri_task(current) && (user_sregs.regs.psw.mask & PSW_MASK_RI))
+		return -EINVAL;
+
+	/* Loading the floating-point-control word can fail. Do that first. */
+	if (restore_fp_ctl(&user_sregs.fpregs.fpc))
+		return -EINVAL;
+
+	/* Use regs->psw.mask instead of PSW_USER_BITS to preserve PER bit. */
+	regs->psw.mask = (regs->psw.mask & ~(PSW_MASK_USER | PSW_MASK_RI)) |
+		(user_sregs.regs.psw.mask & (PSW_MASK_USER | PSW_MASK_RI));
+	/* Check for invalid user address space control. */
+	if ((regs->psw.mask & PSW_MASK_ASC) == PSW_ASC_HOME)
+		regs->psw.mask = PSW_ASC_PRIMARY |
+			(regs->psw.mask & ~PSW_MASK_ASC);
+	/* Check for invalid amode */
+	if (regs->psw.mask & PSW_MASK_EA)
+		regs->psw.mask |= PSW_MASK_BA;
+	regs->psw.addr = user_sregs.regs.psw.addr;
+	memcpy(&regs->gprs, &user_sregs.regs.gprs, sizeof(sregs->regs.gprs));
+	memcpy(&current->thread.acrs, &user_sregs.regs.acrs,
+	       sizeof(current->thread.acrs));
+
+	memcpy(&current->thread.fp_regs, &user_sregs.fpregs,
+	       sizeof(current->thread.fp_regs));
+
+	clear_pt_regs_flag(regs, PIF_SYSCALL); /* No longer in a system call */
+	return 0;
+}
+
+/* Returns non-zero on fault. */
+static int save_sigregs_ext(struct pt_regs *regs,
+			    _sigregs_ext __user *sregs_ext)
+{
+	__u64 vxrs[__NUM_VXRS_LOW];
+	int i;
+
+	/* Save vector registers to signal stack */
+	if (current->thread.vxrs) {
+		for (i = 0; i < __NUM_VXRS_LOW; i++)
+			vxrs[i] = *((__u64 *)(current->thread.vxrs + i) + 1);
+		if (__copy_to_user(&sregs_ext->vxrs_low, vxrs,
+				   sizeof(sregs_ext->vxrs_low)) ||
+		    __copy_to_user(&sregs_ext->vxrs_high,
+				   current->thread.vxrs + __NUM_VXRS_LOW,
+				   sizeof(sregs_ext->vxrs_high)))
+			return -EFAULT;
+	}
+	return 0;
+}
+
+static int restore_sigregs_ext(struct pt_regs *regs,
+			       _sigregs_ext __user *sregs_ext)
+{
+	__u64 vxrs[__NUM_VXRS_LOW];
+	int i;
+
+	/* Restore vector registers from signal stack */
+	if (current->thread.vxrs) {
+		if (__copy_from_user(vxrs, &sregs_ext->vxrs_low,
+				     sizeof(sregs_ext->vxrs_low)) ||
+		    __copy_from_user(current->thread.vxrs + __NUM_VXRS_LOW,
+				     &sregs_ext->vxrs_high,
+				     sizeof(sregs_ext->vxrs_high)))
+			return -EFAULT;
+		for (i = 0; i < __NUM_VXRS_LOW; i++)
+			*((__u64 *)(current->thread.vxrs + i) + 1) = vxrs[i];
+	}
+	return 0;
+}
+
+SYSCALL_DEFINE0(sigreturn)
+{
+	struct pt_regs *regs = task_pt_regs(current);
+	struct sigframe __user *frame =
+		(struct sigframe __user *) regs->gprs[15];
+	sigset_t set;
+
+	if (__copy_from_user(&set.sig, &frame->sc.oldmask, _SIGMASK_COPY_SIZE))
+		goto badframe;
+	set_current_blocked(&set);
+	if (restore_sigregs(regs, &frame->sregs))
+		goto badframe;
+	if (restore_sigregs_ext(regs, &frame->sregs_ext))
+		goto badframe;
+	load_sigregs();
+	return regs->gprs[2];
+badframe:
+	force_sig(SIGSEGV, current);
+	return 0;
+}
+
+SYSCALL_DEFINE0(rt_sigreturn)
+{
+	struct pt_regs *regs = task_pt_regs(current);
+	struct rt_sigframe __user *frame =
+		(struct rt_sigframe __user *)regs->gprs[15];
+	sigset_t set;
+
+	if (__copy_from_user(&set.sig, &frame->uc.uc_sigmask, sizeof(set)))
+		goto badframe;
+	set_current_blocked(&set);
+	if (restore_altstack(&frame->uc.uc_stack))
+		goto badframe;
+	if (restore_sigregs(regs, &frame->uc.uc_mcontext))
+		goto badframe;
+	if (restore_sigregs_ext(regs, &frame->uc.uc_mcontext_ext))
+		goto badframe;
+	load_sigregs();
+	return regs->gprs[2];
+badframe:
+	force_sig(SIGSEGV, current);
+	return 0;
+}
+
+/*
+ * Determine which stack to use..
+ */
+static inline void __user *
+get_sigframe(struct k_sigaction *ka, struct pt_regs * regs, size_t frame_size)
+{
+	unsigned long sp;
+
+	/* Default to using normal stack */
+	sp = regs->gprs[15];
+
+	/* Overflow on alternate signal stack gives SIGSEGV. */
+	if (on_sig_stack(sp) && !on_sig_stack((sp - frame_size) & -8UL))
+		return (void __user *) -1UL;
+
+	/* This is the X/Open sanctioned signal stack switching.  */
+	if (ka->sa.sa_flags & SA_ONSTACK) {
+		if (! sas_ss_flags(sp))
+			sp = current->sas_ss_sp + current->sas_ss_size;
+	}
+
+	return (void __user *)((sp - frame_size) & -8ul);
+}
+
+static int setup_frame(int sig, struct k_sigaction *ka,
+		       sigset_t *set, struct pt_regs * regs)
+{
+	struct sigframe __user *frame;
+	struct sigcontext sc;
+	unsigned long restorer;
+	size_t frame_size;
+
+	/*
+	 * gprs_high are only present for a 31-bit task running on
+	 * a 64-bit kernel (see compat_signal.c) but the space for
+	 * gprs_high need to be allocated if vector registers are
+	 * included in the signal frame on a 31-bit system.
+	 */
+	frame_size = sizeof(*frame) - sizeof(frame->sregs_ext);
+	if (MACHINE_HAS_VX)
+		frame_size += sizeof(frame->sregs_ext);
+	frame = get_sigframe(ka, regs, frame_size);
+	if (frame == (void __user *) -1UL)
+		return -EFAULT;
+
+	/* Set up backchain. */
+	if (__put_user(regs->gprs[15], (addr_t __user *) frame))
+		return -EFAULT;
+
+	/* Create struct sigcontext on the signal stack */
+	memcpy(&sc.oldmask, &set->sig, _SIGMASK_COPY_SIZE);
+	sc.sregs = (_sigregs __user __force *) &frame->sregs;
+	if (__copy_to_user(&frame->sc, &sc, sizeof(frame->sc)))
+		return -EFAULT;
+
+	/* Store registers needed to create the signal frame */
+	store_sigregs();
+
+	/* Create _sigregs on the signal stack */
+	if (save_sigregs(regs, &frame->sregs))
+		return -EFAULT;
+
+	/* Place signal number on stack to allow backtrace from handler.  */
+	if (__put_user(regs->gprs[2], (int __user *) &frame->signo))
+		return -EFAULT;
+
+	/* Create _sigregs_ext on the signal stack */
+	if (save_sigregs_ext(regs, &frame->sregs_ext))
+		return -EFAULT;
+
+	/* Set up to return from userspace.  If provided, use a stub
+	   already in userspace.  */
+	if (ka->sa.sa_flags & SA_RESTORER) {
+		restorer = (unsigned long) ka->sa.sa_restorer | PSW_ADDR_AMODE;
+	} else {
+		/* Signal frame without vector registers are short ! */
+		__u16 __user *svc = (void __user *) frame + frame_size - 2;
+		if (__put_user(S390_SYSCALL_OPCODE | __NR_sigreturn, svc))
+			return -EFAULT;
+		restorer = (unsigned long) svc | PSW_ADDR_AMODE;
+	}
+
+	/* Set up registers for signal handler */
+	regs->gprs[14] = restorer;
+	regs->gprs[15] = (unsigned long) frame;
+	/* Force default amode and default user address space control. */
+	regs->psw.mask = PSW_MASK_EA | PSW_MASK_BA |
+		(PSW_USER_BITS & PSW_MASK_ASC) |
+		(regs->psw.mask & ~PSW_MASK_ASC);
+	regs->psw.addr = (unsigned long) ka->sa.sa_handler | PSW_ADDR_AMODE;
+
+	regs->gprs[2] = sig;
+	regs->gprs[3] = (unsigned long) &frame->sc;
+
+	/* We forgot to include these in the sigcontext.
+	   To avoid breaking binary compatibility, they are passed as args. */
+	if (sig == SIGSEGV || sig == SIGBUS || sig == SIGILL ||
+	    sig == SIGTRAP || sig == SIGFPE) {
+		/* set extra registers only for synchronous signals */
+		regs->gprs[4] = regs->int_code & 127;
+		regs->gprs[5] = regs->int_parm_long;
+		regs->gprs[6] = task_thread_info(current)->last_break;
+	}
+	return 0;
+}
+
+static int setup_rt_frame(struct ksignal *ksig, sigset_t *set,
+			  struct pt_regs *regs)
+{
+	struct rt_sigframe __user *frame;
+	unsigned long uc_flags, restorer;
+	size_t frame_size;
+
+	frame_size = sizeof(struct rt_sigframe) - sizeof(_sigregs_ext);
+	/*
+	 * gprs_high are only present for a 31-bit task running on
+	 * a 64-bit kernel (see compat_signal.c) but the space for
+	 * gprs_high need to be allocated if vector registers are
+	 * included in the signal frame on a 31-bit system.
+	 */
+	uc_flags = 0;
+	if (MACHINE_HAS_VX) {
+		frame_size += sizeof(_sigregs_ext);
+		if (current->thread.vxrs)
+			uc_flags |= UC_VXRS;
+	}
+	frame = get_sigframe(&ksig->ka, regs, frame_size);
+	if (frame == (void __user *) -1UL)
+		return -EFAULT;
+
+	/* Set up backchain. */
+	if (__put_user(regs->gprs[15], (addr_t __user *) frame))
+		return -EFAULT;
+
+	/* Set up to return from userspace.  If provided, use a stub
+	   already in userspace.  */
+	if (ksig->ka.sa.sa_flags & SA_RESTORER) {
+		restorer = (unsigned long)
+			ksig->ka.sa.sa_restorer | PSW_ADDR_AMODE;
+	} else {
+		__u16 __user *svc = &frame->svc_insn;
+		if (__put_user(S390_SYSCALL_OPCODE | __NR_rt_sigreturn, svc))
+			return -EFAULT;
+		restorer = (unsigned long) svc | PSW_ADDR_AMODE;
+	}
+
+	/* Create siginfo on the signal stack */
+	if (copy_siginfo_to_user(&frame->info, &ksig->info))
+		return -EFAULT;
+
+	/* Store registers needed to create the signal frame */
+	store_sigregs();
+
+	/* Create ucontext on the signal stack. */
+	if (__put_user(uc_flags, &frame->uc.uc_flags) ||
+	    __put_user(NULL, &frame->uc.uc_link) ||
+	    __save_altstack(&frame->uc.uc_stack, regs->gprs[15]) ||
+	    save_sigregs(regs, &frame->uc.uc_mcontext) ||
+	    __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set)) ||
+	    save_sigregs_ext(regs, &frame->uc.uc_mcontext_ext))
+		return -EFAULT;
+
+	/* Set up registers for signal handler */
+	regs->gprs[14] = restorer;
+	regs->gprs[15] = (unsigned long) frame;
+	/* Force default amode and default user address space control. */
+	regs->psw.mask = PSW_MASK_EA | PSW_MASK_BA |
+		(PSW_USER_BITS & PSW_MASK_ASC) |
+		(regs->psw.mask & ~PSW_MASK_ASC);
+	regs->psw.addr = (unsigned long) ksig->ka.sa.sa_handler | PSW_ADDR_AMODE;
+
+	regs->gprs[2] = ksig->sig;
+	regs->gprs[3] = (unsigned long) &frame->info;
+	regs->gprs[4] = (unsigned long) &frame->uc;
+	regs->gprs[5] = task_thread_info(current)->last_break;
+	return 0;
+}
+
+static void handle_signal(struct ksignal *ksig, sigset_t *oldset,
+			  struct pt_regs *regs)
+{
+	int ret;
+
+	/* Set up the stack frame */
+	if (ksig->ka.sa.sa_flags & SA_SIGINFO)
+		ret = setup_rt_frame(ksig, oldset, regs);
+	else
+		ret = setup_frame(ksig->sig, &ksig->ka, oldset, regs);
+
+	signal_setup_done(ret, ksig, test_thread_flag(TIF_SINGLE_STEP));
+}
+
+/*
+ * Note that 'init' is a special process: it doesn't get signals it doesn't
+ * want to handle. Thus you cannot kill init even with a SIGKILL even by
+ * mistake.
+ *
+ * Note that we go through the signals twice: once to check the signals that
+ * the kernel can handle, and then we build all the user-level signal handling
+ * stack-frames in one go after that.
+ */
+void do_signal(struct pt_regs *regs)
+{
+	struct ksignal ksig;
+	sigset_t *oldset = sigmask_to_save();
+
+	/*
+	 * Get signal to deliver. When running under ptrace, at this point
+	 * the debugger may change all our registers, including the system
+	 * call information.
+	 */
+	current_thread_info()->system_call =
+		test_pt_regs_flag(regs, PIF_SYSCALL) ? regs->int_code : 0;
+
+	if (get_signal(&ksig)) {
+		/* Whee!  Actually deliver the signal.  */
+		if (current_thread_info()->system_call) {
+			regs->int_code = current_thread_info()->system_call;
+			/* Check for system call restarting. */
+			switch (regs->gprs[2]) {
+			case -ERESTART_RESTARTBLOCK:
+			case -ERESTARTNOHAND:
+				regs->gprs[2] = -EINTR;
+				break;
+			case -ERESTARTSYS:
+				if (!(ksig.ka.sa.sa_flags & SA_RESTART)) {
+					regs->gprs[2] = -EINTR;
+					break;
+				}
+			/* fallthrough */
+			case -ERESTARTNOINTR:
+				regs->gprs[2] = regs->orig_gpr2;
+				regs->psw.addr =
+					__rewind_psw(regs->psw,
+						     regs->int_code >> 16);
+				break;
+			}
+		}
+		/* No longer in a system call */
+		clear_pt_regs_flag(regs, PIF_SYSCALL);
+
+		if (is_compat_task())
+			handle_signal32(&ksig, oldset, regs);
+		else
+			handle_signal(&ksig, oldset, regs);
+		return;
+	}
+
+	/* No handlers present - check for system call restart */
+	clear_pt_regs_flag(regs, PIF_SYSCALL);
+	if (current_thread_info()->system_call) {
+		regs->int_code = current_thread_info()->system_call;
+		switch (regs->gprs[2]) {
+		case -ERESTART_RESTARTBLOCK:
+			/* Restart with sys_restart_syscall */
+			regs->int_code = __NR_restart_syscall;
+		/* fallthrough */
+		case -ERESTARTNOHAND:
+		case -ERESTARTSYS:
+		case -ERESTARTNOINTR:
+			/* Restart system call with magic TIF bit. */
+			regs->gprs[2] = regs->orig_gpr2;
+			set_pt_regs_flag(regs, PIF_SYSCALL);
+			if (test_thread_flag(TIF_SINGLE_STEP))
+				clear_pt_regs_flag(regs, PIF_PER_TRAP);
+			break;
+		}
+	}
+
+	/*
+	 * If there's no signal to deliver, we just put the saved sigmask back.
+	 */
+	restore_saved_sigmask();
+}
+
+void do_notify_resume(struct pt_regs *regs)
+{
+	clear_thread_flag(TIF_NOTIFY_RESUME);
+	tracehook_notify_resume(regs);
+}
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
new file mode 100644
index 000000000..efd2c1968
--- /dev/null
+++ b/arch/s390/kernel/smp.c
@@ -0,0 +1,1161 @@
+/*
+ *  SMP related functions
+ *
+ *    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
+ *
+ * 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"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
+#include <linux/workqueue.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/mm.h>
+#include <linux/err.h>
+#include <linux/spinlock.h>
+#include <linux/kernel_stat.h>
+#include <linux/delay.h>
+#include <linux/interrupt.h>
+#include <linux/irqflags.h>
+#include <linux/cpu.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/irq.h>
+#include <asm/tlbflush.h>
+#include <asm/vtimer.h>
+#include <asm/lowcore.h>
+#include <asm/sclp.h>
+#include <asm/vdso.h>
+#include <asm/debug.h>
+#include <asm/os_info.h>
+#include <asm/sigp.h>
+#include <asm/idle.h>
+#include "entry.h"
+
+enum {
+	ec_schedule = 0,
+	ec_call_function_single,
+	ec_stop_cpu,
+};
+
+enum {
+	CPU_STATE_STANDBY,
+	CPU_STATE_CONFIGURED,
+};
+
+static DEFINE_PER_CPU(struct cpu *, cpu_device);
+
+struct pcpu {
+	struct _lowcore *lowcore;	/* lowcore page(s) for the cpu */
+	unsigned long ec_mask;		/* bit mask for ec_xxx functions */
+	signed char state;		/* physical cpu state */
+	signed char polarization;	/* physical polarization */
+	u16 address;			/* physical cpu address */
+};
+
+static u8 boot_cpu_type;
+static struct pcpu pcpu_devices[NR_CPUS];
+
+unsigned int smp_cpu_mt_shift;
+EXPORT_SYMBOL(smp_cpu_mt_shift);
+
+unsigned int smp_cpu_mtid;
+EXPORT_SYMBOL(smp_cpu_mtid);
+
+static unsigned int smp_max_threads __initdata = -1U;
+
+static int __init early_nosmt(char *s)
+{
+	smp_max_threads = 1;
+	return 0;
+}
+early_param("nosmt", early_nosmt);
+
+static int __init early_smt(char *s)
+{
+	get_option(&s, &smp_max_threads);
+	return 0;
+}
+early_param("smt", early_smt);
+
+/*
+ * The smp_cpu_state_mutex must be held when changing the state or polarization
+ * member of a pcpu data structure within the pcpu_devices arreay.
+ */
+DEFINE_MUTEX(smp_cpu_state_mutex);
+
+/*
+ * Signal processor helper functions.
+ */
+static inline int __pcpu_sigp_relax(u16 addr, u8 order, unsigned long parm,
+				    u32 *status)
+{
+	int cc;
+
+	while (1) {
+		cc = __pcpu_sigp(addr, order, parm, NULL);
+		if (cc != SIGP_CC_BUSY)
+			return cc;
+		cpu_relax();
+	}
+}
+
+static int pcpu_sigp_retry(struct pcpu *pcpu, u8 order, u32 parm)
+{
+	int cc, retry;
+
+	for (retry = 0; ; retry++) {
+		cc = __pcpu_sigp(pcpu->address, order, parm, NULL);
+		if (cc != SIGP_CC_BUSY)
+			break;
+		if (retry >= 3)
+			udelay(10);
+	}
+	return cc;
+}
+
+static inline int pcpu_stopped(struct pcpu *pcpu)
+{
+	u32 uninitialized_var(status);
+
+	if (__pcpu_sigp(pcpu->address, SIGP_SENSE,
+			0, &status) != SIGP_CC_STATUS_STORED)
+		return 0;
+	return !!(status & (SIGP_STATUS_CHECK_STOP|SIGP_STATUS_STOPPED));
+}
+
+static inline int pcpu_running(struct pcpu *pcpu)
+{
+	if (__pcpu_sigp(pcpu->address, SIGP_SENSE_RUNNING,
+			0, NULL) != SIGP_CC_STATUS_STORED)
+		return 1;
+	/* Status stored condition code is equivalent to cpu not running. */
+	return 0;
+}
+
+/*
+ * Find struct pcpu by cpu address.
+ */
+static struct pcpu *pcpu_find_address(const struct cpumask *mask, u16 address)
+{
+	int cpu;
+
+	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;
+
+	if (test_and_set_bit(ec_bit, &pcpu->ec_mask))
+		return;
+	order = pcpu_running(pcpu) ? SIGP_EXTERNAL_CALL : SIGP_EMERGENCY_SIGNAL;
+	pcpu_sigp_retry(pcpu, order, 0);
+}
+
+#define ASYNC_FRAME_OFFSET (ASYNC_SIZE - STACK_FRAME_OVERHEAD - __PT_SIZE)
+#define PANIC_FRAME_OFFSET (PAGE_SIZE - STACK_FRAME_OVERHEAD - __PT_SIZE)
+
+static int pcpu_alloc_lowcore(struct pcpu *pcpu, int cpu)
+{
+	unsigned long async_stack, panic_stack;
+	struct _lowcore *lc;
+
+	if (pcpu != &pcpu_devices[0]) {
+		pcpu->lowcore =	(struct _lowcore *)
+			__get_free_pages(GFP_KERNEL | GFP_DMA, LC_ORDER);
+		async_stack = __get_free_pages(GFP_KERNEL, ASYNC_ORDER);
+		panic_stack = __get_free_page(GFP_KERNEL);
+		if (!pcpu->lowcore || !panic_stack || !async_stack)
+			goto out;
+	} else {
+		async_stack = pcpu->lowcore->async_stack - ASYNC_FRAME_OFFSET;
+		panic_stack = pcpu->lowcore->panic_stack - PANIC_FRAME_OFFSET;
+	}
+	lc = pcpu->lowcore;
+	memcpy(lc, &S390_lowcore, 512);
+	memset((char *) lc + 512, 0, sizeof(*lc) - 512);
+	lc->async_stack = async_stack + ASYNC_FRAME_OFFSET;
+	lc->panic_stack = panic_stack + PANIC_FRAME_OFFSET;
+	lc->cpu_nr = cpu;
+	lc->spinlock_lockval = arch_spin_lockval(cpu);
+	if (MACHINE_HAS_VX)
+		lc->vector_save_area_addr =
+			(unsigned long) &lc->vector_save_area;
+	if (vdso_alloc_per_cpu(lc))
+		goto out;
+	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(panic_stack);
+		free_pages(async_stack, ASYNC_ORDER);
+		free_pages((unsigned long) pcpu->lowcore, LC_ORDER);
+	}
+	return -ENOMEM;
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+
+static void pcpu_free_lowcore(struct pcpu *pcpu)
+{
+	pcpu_sigp_retry(pcpu, SIGP_SET_PREFIX, 0);
+	lowcore_ptr[pcpu - pcpu_devices] = NULL;
+	vdso_free_per_cpu(pcpu->lowcore);
+	if (pcpu == &pcpu_devices[0])
+		return;
+	free_page(pcpu->lowcore->panic_stack-PANIC_FRAME_OFFSET);
+	free_pages(pcpu->lowcore->async_stack-ASYNC_FRAME_OFFSET, ASYNC_ORDER);
+	free_pages((unsigned long) pcpu->lowcore, LC_ORDER);
+}
+
+#endif /* CONFIG_HOTPLUG_CPU */
+
+static void pcpu_prepare_secondary(struct pcpu *pcpu, int cpu)
+{
+	struct _lowcore *lc = pcpu->lowcore;
+
+	if (MACHINE_HAS_TLB_LC)
+		cpumask_set_cpu(cpu, &init_mm.context.cpu_attach_mask);
+	cpumask_set_cpu(cpu, mm_cpumask(&init_mm));
+	atomic_inc(&init_mm.context.attach_count);
+	lc->cpu_nr = cpu;
+	lc->spinlock_lockval = arch_spin_lockval(cpu);
+	lc->percpu_offset = __per_cpu_offset[cpu];
+	lc->kernel_asce = S390_lowcore.kernel_asce;
+	lc->machine_flags = S390_lowcore.machine_flags;
+	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 - STACK_FRAME_OVERHEAD - sizeof(struct pt_regs);
+	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 = lowcore_ptr[pcpu - pcpu_devices];
+	unsigned long source_cpu = stap();
+
+	__load_psw_mask(PSW_KERNEL_BITS);
+	if (pcpu->address == source_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. */
+	mem_assign_absolute(lc->restart_stack, stack);
+	mem_assign_absolute(lc->restart_fn, (unsigned long) func);
+	mem_assign_absolute(lc->restart_data, (unsigned long) data);
+	mem_assign_absolute(lc->restart_source, source_cpu);
+	asm volatile(
+		"0:	sigp	0,%0,%2	# sigp restart to target cpu\n"
+		"	brc	2,0b	# busy, try again\n"
+		"1:	sigp	0,%1,%3	# sigp stop to current cpu\n"
+		"	brc	2,1b	# busy, try again\n"
+		: : "d" (pcpu->address), "d" (source_cpu),
+		    "K" (SIGP_RESTART), "K" (SIGP_STOP)
+		: "0", "1", "cc");
+	for (;;) ;
+}
+
+/*
+ * Enable additional logical cpus for multi-threading.
+ */
+static int pcpu_set_smt(unsigned int mtid)
+{
+	register unsigned long reg1 asm ("1") = (unsigned long) mtid;
+	int cc;
+
+	if (smp_cpu_mtid == mtid)
+		return 0;
+	asm volatile(
+		"	sigp	%1,0,%2	# sigp set multi-threading\n"
+		"	ipm	%0\n"
+		"	srl	%0,28\n"
+		: "=d" (cc) : "d" (reg1), "K" (SIGP_SET_MULTI_THREADING)
+		: "cc");
+	if (cc == 0) {
+		smp_cpu_mtid = mtid;
+		smp_cpu_mt_shift = 0;
+		while (smp_cpu_mtid >= (1U << smp_cpu_mt_shift))
+			smp_cpu_mt_shift++;
+		pcpu_devices[0].address = stap();
+	}
+	return cc;
+}
+
+/*
+ * 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);
+}
+
+/*
+ * Call function on the ipl CPU.
+ */
+void smp_call_ipl_cpu(void (*func)(void *), void *data)
+{
+	pcpu_delegate(&pcpu_devices[0], func, data,
+		      pcpu_devices->lowcore->panic_stack -
+		      PANIC_FRAME_OFFSET + 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_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.
+ */
+static void smp_emergency_stop(cpumask_t *cpumask)
+{
+	u64 end;
+	int cpu;
+
+	end = get_tod_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_CC_BUSY &&
+		       get_tod_clock() < end)
+			cpu_relax();
+	}
+	while (get_tod_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;
+
+	/* 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)
+		smp_emergency_stop(&cpumask);
+
+	/* stop all processors */
+	for_each_cpu(cpu, &cpumask) {
+		struct pcpu *pcpu = pcpu_devices + cpu;
+		pcpu_sigp_retry(pcpu, SIGP_STOP, 0);
+		while (!pcpu_stopped(pcpu))
+			cpu_relax();
+	}
+}
+
+/*
+ * This is the main routine where commands issued by other
+ * cpus are handled.
+ */
+static void smp_handle_ext_call(void)
+{
+	unsigned long bits;
+
+	/* handle bit signal external calls */
+	bits = xchg(&pcpu_devices[smp_processor_id()].ec_mask, 0);
+	if (test_bit(ec_stop_cpu, &bits))
+		smp_stop_cpu();
+	if (test_bit(ec_schedule, &bits))
+		scheduler_ipi();
+	if (test_bit(ec_call_function_single, &bits))
+		generic_smp_call_function_single_interrupt();
+}
+
+static void do_ext_call_interrupt(struct ext_code ext_code,
+				  unsigned int param32, unsigned long param64)
+{
+	inc_irq_stat(ext_code.code == 0x1202 ? IRQEXT_EXC : IRQEXT_EMS);
+	smp_handle_ext_call();
+}
+
+void arch_send_call_function_ipi_mask(const struct cpumask *mask)
+{
+	int cpu;
+
+	for_each_cpu(cpu, mask)
+		pcpu_ec_call(pcpu_devices + cpu, ec_call_function_single);
+}
+
+void arch_send_call_function_single_ipi(int cpu)
+{
+	pcpu_ec_call(pcpu_devices + cpu, ec_call_function_single);
+}
+
+/*
+ * this function sends a 'reschedule' IPI to another CPU.
+ * it goes straight through and wastes no time serializing
+ * anything. Worst case is that we lose a reschedule ...
+ */
+void smp_send_reschedule(int cpu)
+{
+	pcpu_ec_call(pcpu_devices + cpu, ec_schedule);
+}
+
+/*
+ * parameter area for the set/clear control bit callbacks
+ */
+struct ec_creg_mask_parms {
+	unsigned long orval;
+	unsigned long andval;
+	int cr;
+};
+
+/*
+ * callback for setting/clearing control bits
+ */
+static void smp_ctl_bit_callback(void *info)
+{
+	struct ec_creg_mask_parms *pp = info;
+	unsigned long cregs[16];
+
+	__ctl_store(cregs, 0, 15);
+	cregs[pp->cr] = (cregs[pp->cr] & pp->andval) | pp->orval;
+	__ctl_load(cregs, 0, 15);
+}
+
+/*
+ * Set a bit in a control register of all cpus
+ */
+void smp_ctl_set_bit(int cr, int bit)
+{
+	struct ec_creg_mask_parms parms = { 1UL << bit, -1UL, cr };
+
+	on_each_cpu(smp_ctl_bit_callback, &parms, 1);
+}
+EXPORT_SYMBOL(smp_ctl_set_bit);
+
+/*
+ * Clear a bit in a control register of all cpus
+ */
+void smp_ctl_clear_bit(int cr, int bit)
+{
+	struct ec_creg_mask_parms parms = { 0, ~(1UL << bit), cr };
+
+	on_each_cpu(smp_ctl_bit_callback, &parms, 1);
+}
+EXPORT_SYMBOL(smp_ctl_clear_bit);
+
+#ifdef CONFIG_CRASH_DUMP
+
+static inline void __smp_store_cpu_state(int cpu, u16 address, int is_boot_cpu)
+{
+	void *lc = pcpu_devices[0].lowcore;
+	struct save_area_ext *sa_ext;
+	unsigned long vx_sa;
+
+	sa_ext = dump_save_area_create(cpu);
+	if (!sa_ext)
+		panic("could not allocate memory for save area\n");
+	if (is_boot_cpu) {
+		/* Copy the registers of the boot CPU. */
+		copy_oldmem_page(1, (void *) &sa_ext->sa, sizeof(sa_ext->sa),
+				 SAVE_AREA_BASE - PAGE_SIZE, 0);
+		if (MACHINE_HAS_VX)
+			save_vx_regs_safe(sa_ext->vx_regs);
+		return;
+	}
+	/* Get the registers of a non-boot cpu. */
+	__pcpu_sigp_relax(address, SIGP_STOP_AND_STORE_STATUS, 0, NULL);
+	memcpy_real(&sa_ext->sa, lc + SAVE_AREA_BASE, sizeof(sa_ext->sa));
+	if (!MACHINE_HAS_VX)
+		return;
+	/* Get the VX registers */
+	vx_sa = __get_free_page(GFP_KERNEL);
+	if (!vx_sa)
+		panic("could not allocate memory for VX save area\n");
+	__pcpu_sigp_relax(address, SIGP_STORE_ADDITIONAL_STATUS, vx_sa, NULL);
+	memcpy(sa_ext->vx_regs, (void *) vx_sa, sizeof(sa_ext->vx_regs));
+	free_page(vx_sa);
+}
+
+/*
+ * Collect CPU state of the previous, crashed system.
+ * There are four cases:
+ * 1) standard zfcp dump
+ *    condition: OLDMEM_BASE == NULL && ipl_info.type == IPL_TYPE_FCP_DUMP
+ *    The state for all CPUs except the boot CPU needs to be collected
+ *    with sigp stop-and-store-status. The boot CPU state is located in
+ *    the absolute lowcore of the memory stored in the HSA. The zcore code
+ *    will allocate the save area and copy the boot CPU state from the HSA.
+ * 2) stand-alone kdump for SCSI (zfcp dump with swapped memory)
+ *    condition: OLDMEM_BASE != NULL && ipl_info.type == IPL_TYPE_FCP_DUMP
+ *    The state for all CPUs except the boot CPU needs to be collected
+ *    with sigp stop-and-store-status. The firmware or the boot-loader
+ *    stored the registers of the boot CPU in the absolute lowcore in the
+ *    memory of the old system.
+ * 3) kdump and the old kernel did not store the CPU state,
+ *    or stand-alone kdump for DASD
+ *    condition: OLDMEM_BASE != NULL && !is_kdump_kernel()
+ *    The state for all CPUs except the boot CPU needs to be collected
+ *    with sigp stop-and-store-status. The kexec code or the boot-loader
+ *    stored the registers of the boot CPU in the memory of the old system.
+ * 4) kdump and the old kernel stored the CPU state
+ *    condition: OLDMEM_BASE != NULL && is_kdump_kernel()
+ *    The state of all CPUs is stored in ELF sections in the memory of the
+ *    old system. The ELF sections are picked up by the crash_dump code
+ *    via elfcorehdr_addr.
+ */
+static void __init smp_store_cpu_states(struct sclp_cpu_info *info)
+{
+	unsigned int cpu, address, i, j;
+	int is_boot_cpu;
+
+	if (is_kdump_kernel())
+		/* Previous system stored the CPU states. Nothing to do. */
+		return;
+	if (!(OLDMEM_BASE || ipl_info.type == IPL_TYPE_FCP_DUMP))
+		/* No previous system present, normal boot. */
+		return;
+	/* Set multi-threading state to the previous system. */
+	pcpu_set_smt(sclp_get_mtid_prev());
+	/* Collect CPU states. */
+	cpu = 0;
+	for (i = 0; i < info->configured; i++) {
+		/* Skip CPUs with different CPU type. */
+		if (info->has_cpu_type && info->cpu[i].type != boot_cpu_type)
+			continue;
+		for (j = 0; j <= smp_cpu_mtid; j++, cpu++) {
+			address = (info->cpu[i].core_id << smp_cpu_mt_shift) + j;
+			is_boot_cpu = (address == pcpu_devices[0].address);
+			if (is_boot_cpu && !OLDMEM_BASE)
+				/* Skip boot CPU for standard zfcp dump. */
+				continue;
+			/* Get state for this CPu. */
+			__smp_store_cpu_state(cpu, address, is_boot_cpu);
+		}
+	}
+}
+
+int smp_store_status(int cpu)
+{
+	unsigned long vx_sa;
+	struct pcpu *pcpu;
+
+	pcpu = pcpu_devices + cpu;
+	if (__pcpu_sigp_relax(pcpu->address, SIGP_STOP_AND_STORE_STATUS,
+			      0, NULL) != SIGP_CC_ORDER_CODE_ACCEPTED)
+		return -EIO;
+	if (!MACHINE_HAS_VX)
+		return 0;
+	vx_sa = __pa(pcpu->lowcore->vector_save_area_addr);
+	__pcpu_sigp_relax(pcpu->address, SIGP_STORE_ADDITIONAL_STATUS,
+			  vx_sa, NULL);
+	return 0;
+}
+
+#endif /* CONFIG_CRASH_DUMP */
+
+void smp_cpu_set_polarization(int cpu, int val)
+{
+	pcpu_devices[cpu].polarization = val;
+}
+
+int smp_cpu_get_polarization(int cpu)
+{
+	return pcpu_devices[cpu].polarization;
+}
+
+static struct sclp_cpu_info *smp_get_cpu_info(void)
+{
+	static int use_sigp_detection;
+	struct sclp_cpu_info *info;
+	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 += (1U << smp_cpu_mt_shift)) {
+			if (__pcpu_sigp_relax(address, SIGP_SENSE, 0, NULL) ==
+			    SIGP_CC_NOT_OPERATIONAL)
+				continue;
+			info->cpu[info->configured].core_id =
+				address >> smp_cpu_mt_shift;
+			info->configured++;
+		}
+		info->combined = info->configured;
+	}
+	return info;
+}
+
+static int smp_add_present_cpu(int cpu);
+
+static int __smp_rescan_cpus(struct sclp_cpu_info *info, int sysfs_add)
+{
+	struct pcpu *pcpu;
+	cpumask_t avail;
+	int cpu, nr, i, j;
+	u16 address;
+
+	nr = 0;
+	cpumask_xor(&avail, cpu_possible_mask, cpu_present_mask);
+	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;
+		address = info->cpu[i].core_id << smp_cpu_mt_shift;
+		for (j = 0; j <= smp_cpu_mtid; j++) {
+			if (pcpu_find_address(cpu_present_mask, address + j))
+				continue;
+			pcpu = pcpu_devices + cpu;
+			pcpu->address = address + j;
+			pcpu->state =
+				(cpu >= info->configured*(smp_cpu_mtid + 1)) ?
+				CPU_STATE_STANDBY : CPU_STATE_CONFIGURED;
+			smp_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);
+			if (cpu >= nr_cpu_ids)
+				break;
+		}
+	}
+	return nr;
+}
+
+static void __init smp_detect_cpus(void)
+{
+	unsigned int cpu, mtid, c_cpus, s_cpus;
+	struct sclp_cpu_info *info;
+	u16 address;
+
+	/* Get CPU information */
+	info = smp_get_cpu_info();
+	if (!info)
+		panic("smp_detect_cpus failed to allocate memory\n");
+
+	/* Find boot CPU type */
+	if (info->has_cpu_type) {
+		address = stap();
+		for (cpu = 0; cpu < info->combined; cpu++)
+			if (info->cpu[cpu].core_id == address) {
+				/* The boot cpu dictates the cpu type. */
+				boot_cpu_type = info->cpu[cpu].type;
+				break;
+			}
+		if (cpu >= info->combined)
+			panic("Could not find boot CPU type");
+	}
+
+#ifdef CONFIG_CRASH_DUMP
+	/* Collect CPU state of previous system */
+	smp_store_cpu_states(info);
+#endif
+
+	/* Set multi-threading state for the current system */
+	mtid = sclp_get_mtid(boot_cpu_type);
+	mtid = (mtid < smp_max_threads) ? mtid : smp_max_threads - 1;
+	pcpu_set_smt(mtid);
+
+	/* Print number of CPUs */
+	c_cpus = s_cpus = 0;
+	for (cpu = 0; cpu < info->combined; cpu++) {
+		if (info->has_cpu_type && info->cpu[cpu].type != boot_cpu_type)
+			continue;
+		if (cpu < info->configured)
+			c_cpus += smp_cpu_mtid + 1;
+		else
+			s_cpus += smp_cpu_mtid + 1;
+	}
+	pr_info("%d configured CPUs, %d standby CPUs\n", c_cpus, s_cpus);
+
+	/* Add CPUs present at boot */
+	get_online_cpus();
+	__smp_rescan_cpus(info, 0);
+	put_online_cpus();
+	kfree(info);
+}
+
+/*
+ *	Activate a secondary processor.
+ */
+static void smp_start_secondary(void *cpuvoid)
+{
+	S390_lowcore.last_update_clock = get_tod_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();
+	vtime_init();
+	pfault_init();
+	notify_cpu_starting(smp_processor_id());
+	set_cpu_online(smp_processor_id(), true);
+	inc_irq_stat(CPU_RST);
+	local_irq_enable();
+	cpu_startup_entry(CPUHP_ONLINE);
+}
+
+/* Upping and downing of CPUs */
+int __cpu_up(unsigned int cpu, struct task_struct *tidle)
+{
+	struct pcpu *pcpu;
+	int base, i, rc;
+
+	pcpu = pcpu_devices + cpu;
+	if (pcpu->state != CPU_STATE_CONFIGURED)
+		return -EIO;
+	base = cpu - (cpu % (smp_cpu_mtid + 1));
+	for (i = 0; i <= smp_cpu_mtid; i++) {
+		if (base + i < nr_cpu_ids)
+			if (cpu_online(base + i))
+				break;
+	}
+	/*
+	 * If this is the first CPU of the core to get online
+	 * do an initial CPU reset.
+	 */
+	if (i > smp_cpu_mtid &&
+	    pcpu_sigp_retry(pcpu_devices + base, SIGP_INITIAL_CPU_RESET, 0) !=
+	    SIGP_CC_ORDER_CODE_ACCEPTED)
+		return -EIO;
+
+	rc = pcpu_alloc_lowcore(pcpu, cpu);
+	if (rc)
+		return rc;
+	pcpu_prepare_secondary(pcpu, cpu);
+	pcpu_attach_task(pcpu, tidle);
+	pcpu_start_fn(pcpu, smp_start_secondary, NULL);
+	/* Wait until cpu puts itself in the online & active maps */
+	while (!cpu_online(cpu) || !cpu_active(cpu))
+		cpu_relax();
+	return 0;
+}
+
+static unsigned int setup_possible_cpus __initdata;
+
+static int __init _setup_possible_cpus(char *s)
+{
+	get_option(&s, &setup_possible_cpus);
+	return 0;
+}
+early_param("possible_cpus", _setup_possible_cpus);
+
+#ifdef CONFIG_HOTPLUG_CPU
+
+int __cpu_disable(void)
+{
+	unsigned long cregs[16];
+
+	/* Handle possible pending IPIs */
+	smp_handle_ext_call();
+	set_cpu_online(smp_processor_id(), false);
+	/* Disable pseudo page faults on this cpu. */
+	pfault_fini();
+	/* 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);
+	clear_cpu_flag(CIF_NOHZ_DELAY);
+	return 0;
+}
+
+void __cpu_die(unsigned int cpu)
+{
+	struct pcpu *pcpu;
+
+	/* Wait until target cpu is down */
+	pcpu = pcpu_devices + cpu;
+	while (!pcpu_stopped(pcpu))
+		cpu_relax();
+	pcpu_free_lowcore(pcpu);
+	atomic_dec(&init_mm.context.attach_count);
+	cpumask_clear_cpu(cpu, mm_cpumask(&init_mm));
+	if (MACHINE_HAS_TLB_LC)
+		cpumask_clear_cpu(cpu, &init_mm.context.cpu_attach_mask);
+}
+
+void __noreturn cpu_die(void)
+{
+	idle_task_exit();
+	pcpu_sigp_retry(pcpu_devices + smp_processor_id(), SIGP_STOP, 0);
+	for (;;) ;
+}
+
+#endif /* CONFIG_HOTPLUG_CPU */
+
+void __init smp_fill_possible_mask(void)
+{
+	unsigned int possible, sclp, cpu;
+
+	sclp = min(smp_max_threads, sclp_get_mtid_max() + 1);
+	sclp = sclp_get_max_cpu()*sclp ?: nr_cpu_ids;
+	possible = setup_possible_cpus ?: nr_cpu_ids;
+	possible = min(possible, sclp);
+	for (cpu = 0; cpu < possible && cpu < nr_cpu_ids; cpu++)
+		set_cpu_possible(cpu, true);
+}
+
+void __init smp_prepare_cpus(unsigned int max_cpus)
+{
+	/* request the 0x1201 emergency signal external interrupt */
+	if (register_external_irq(EXT_IRQ_EMERGENCY_SIG, do_ext_call_interrupt))
+		panic("Couldn't request external interrupt 0x1201");
+	/* request the 0x1202 external call external interrupt */
+	if (register_external_irq(EXT_IRQ_EXTERNAL_CALL, do_ext_call_interrupt))
+		panic("Couldn't request external interrupt 0x1202");
+	smp_detect_cpus();
+}
+
+void __init smp_prepare_boot_cpu(void)
+{
+	struct pcpu *pcpu = pcpu_devices;
+
+	pcpu->state = CPU_STATE_CONFIGURED;
+	pcpu->address = stap();
+	pcpu->lowcore = (struct _lowcore *)(unsigned long) store_prefix();
+	S390_lowcore.percpu_offset = __per_cpu_offset[0];
+	smp_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)
+{
+}
+
+void __init smp_setup_processor_id(void)
+{
+	S390_lowcore.cpu_nr = 0;
+	S390_lowcore.spinlock_lockval = arch_spin_lockval(0);
+}
+
+/*
+ * the frequency of the profiling timer can be changed
+ * by writing a multiplier value into /proc/profile.
+ *
+ * usually you want to run this on all CPUs ;)
+ */
+int setup_profiling_timer(unsigned int multiplier)
+{
+	return 0;
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+static ssize_t cpu_configure_show(struct device *dev,
+				  struct device_attribute *attr, char *buf)
+{
+	ssize_t count;
+
+	mutex_lock(&smp_cpu_state_mutex);
+	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 pcpu *pcpu;
+	int cpu, val, rc, i;
+	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;
+	cpu -= cpu % (smp_cpu_mtid + 1);
+	if (cpu == 0)
+		goto out;
+	for (i = 0; i <= smp_cpu_mtid; i++)
+		if (cpu_online(cpu + i))
+			goto out;
+	pcpu = pcpu_devices + cpu;
+	rc = 0;
+	switch (val) {
+	case 0:
+		if (pcpu->state != CPU_STATE_CONFIGURED)
+			break;
+		rc = sclp_cpu_deconfigure(pcpu->address >> smp_cpu_mt_shift);
+		if (rc)
+			break;
+		for (i = 0; i <= smp_cpu_mtid; i++) {
+			if (cpu + i >= nr_cpu_ids || !cpu_present(cpu + i))
+				continue;
+			pcpu[i].state = CPU_STATE_STANDBY;
+			smp_cpu_set_polarization(cpu + i,
+						 POLARIZATION_UNKNOWN);
+		}
+		topology_expect_change();
+		break;
+	case 1:
+		if (pcpu->state != CPU_STATE_STANDBY)
+			break;
+		rc = sclp_cpu_configure(pcpu->address >> smp_cpu_mt_shift);
+		if (rc)
+			break;
+		for (i = 0; i <= smp_cpu_mtid; i++) {
+			if (cpu + i >= nr_cpu_ids || !cpu_present(cpu + i))
+				continue;
+			pcpu[i].state = CPU_STATE_CONFIGURED;
+			smp_cpu_set_polarization(cpu + i,
+						 POLARIZATION_UNKNOWN);
+		}
+		topology_expect_change();
+		break;
+	default:
+		break;
+	}
+out:
+	mutex_unlock(&smp_cpu_state_mutex);
+	put_online_cpus();
+	return rc ? rc : count;
+}
+static DEVICE_ATTR(configure, 0644, cpu_configure_show, cpu_configure_store);
+#endif /* CONFIG_HOTPLUG_CPU */
+
+static ssize_t show_cpu_address(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	return sprintf(buf, "%d\n", pcpu_devices[dev->id].address);
+}
+static DEVICE_ATTR(address, 0444, show_cpu_address, NULL);
+
+static struct attribute *cpu_common_attrs[] = {
+#ifdef CONFIG_HOTPLUG_CPU
+	&dev_attr_configure.attr,
+#endif
+	&dev_attr_address.attr,
+	NULL,
+};
+
+static struct attribute_group cpu_common_attr_group = {
+	.attrs = cpu_common_attrs,
+};
+
+static struct attribute *cpu_online_attrs[] = {
+	&dev_attr_idle_count.attr,
+	&dev_attr_idle_time_us.attr,
+	NULL,
+};
+
+static struct attribute_group cpu_online_attr_group = {
+	.attrs = cpu_online_attrs,
+};
+
+static int smp_cpu_notify(struct notifier_block *self, unsigned long action,
+			  void *hcpu)
+{
+	unsigned int cpu = (unsigned int)(long)hcpu;
+	struct device *s = &per_cpu(cpu_device, cpu)->dev;
+	int err = 0;
+
+	switch (action & ~CPU_TASKS_FROZEN) {
+	case CPU_ONLINE:
+		err = sysfs_create_group(&s->kobj, &cpu_online_attr_group);
+		break;
+	case CPU_DEAD:
+		sysfs_remove_group(&s->kobj, &cpu_online_attr_group);
+		break;
+	}
+	return notifier_from_errno(err);
+}
+
+static int smp_add_present_cpu(int cpu)
+{
+	struct device *s;
+	struct cpu *c;
+	int rc;
+
+	c = kzalloc(sizeof(*c), GFP_KERNEL);
+	if (!c)
+		return -ENOMEM;
+	per_cpu(cpu_device, cpu) = c;
+	s = &c->dev;
+	c->hotpluggable = 1;
+	rc = register_cpu(c, cpu);
+	if (rc)
+		goto out;
+	rc = sysfs_create_group(&s->kobj, &cpu_common_attr_group);
+	if (rc)
+		goto out_cpu;
+	if (cpu_online(cpu)) {
+		rc = sysfs_create_group(&s->kobj, &cpu_online_attr_group);
+		if (rc)
+			goto out_online;
+	}
+	rc = topology_cpu_init(c);
+	if (rc)
+		goto out_topology;
+	return 0;
+
+out_topology:
+	if (cpu_online(cpu))
+		sysfs_remove_group(&s->kobj, &cpu_online_attr_group);
+out_online:
+	sysfs_remove_group(&s->kobj, &cpu_common_attr_group);
+out_cpu:
+#ifdef CONFIG_HOTPLUG_CPU
+	unregister_cpu(c);
+#endif
+out:
+	return rc;
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+
+int __ref smp_rescan_cpus(void)
+{
+	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);
+	nr = __smp_rescan_cpus(info, 1);
+	mutex_unlock(&smp_cpu_state_mutex);
+	put_online_cpus();
+	kfree(info);
+	if (nr)
+		topology_schedule_update();
+	return 0;
+}
+
+static ssize_t __ref rescan_store(struct device *dev,
+				  struct device_attribute *attr,
+				  const char *buf,
+				  size_t count)
+{
+	int rc;
+
+	rc = smp_rescan_cpus();
+	return rc ? rc : count;
+}
+static DEVICE_ATTR(rescan, 0200, NULL, rescan_store);
+#endif /* CONFIG_HOTPLUG_CPU */
+
+static int __init s390_smp_init(void)
+{
+	int cpu, rc = 0;
+
+#ifdef CONFIG_HOTPLUG_CPU
+	rc = device_create_file(cpu_subsys.dev_root, &dev_attr_rescan);
+	if (rc)
+		return rc;
+#endif
+	cpu_notifier_register_begin();
+	for_each_present_cpu(cpu) {
+		rc = smp_add_present_cpu(cpu);
+		if (rc)
+			goto out;
+	}
+
+	__hotcpu_notifier(smp_cpu_notify, 0);
+
+out:
+	cpu_notifier_register_done();
+	return rc;
+}
+subsys_initcall(s390_smp_init);
diff --git a/arch/s390/kernel/stacktrace.c b/arch/s390/kernel/stacktrace.c
new file mode 100644
index 000000000..1785cd822
--- /dev/null
+++ b/arch/s390/kernel/stacktrace.c
@@ -0,0 +1,96 @@
+/*
+ * Stack trace management functions
+ *
+ *  Copyright IBM Corp. 2006
+ *  Author(s): Heiko Carstens <heiko.carstens@de.ibm.com>
+ */
+
+#include <linux/sched.h>
+#include <linux/stacktrace.h>
+#include <linux/kallsyms.h>
+#include <linux/module.h>
+
+static unsigned long save_context_stack(struct stack_trace *trace,
+					unsigned long sp,
+					unsigned long low,
+					unsigned long high,
+					int savesched)
+{
+	struct stack_frame *sf;
+	struct pt_regs *regs;
+	unsigned long addr;
+
+	while(1) {
+		sp &= PSW_ADDR_INSN;
+		if (sp < low || sp > high)
+			return sp;
+		sf = (struct stack_frame *)sp;
+		while(1) {
+			addr = sf->gprs[8] & PSW_ADDR_INSN;
+			if (!trace->skip)
+				trace->entries[trace->nr_entries++] = addr;
+			else
+				trace->skip--;
+			if (trace->nr_entries >= trace->max_entries)
+				return sp;
+			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;
+		}
+		/* 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;
+		addr = regs->psw.addr & PSW_ADDR_INSN;
+		if (savesched || !in_sched_functions(addr)) {
+			if (!trace->skip)
+				trace->entries[trace->nr_entries++] = addr;
+			else
+				trace->skip--;
+		}
+		if (trace->nr_entries >= trace->max_entries)
+			return sp;
+		low = sp;
+		sp = regs->gprs[15];
+	}
+}
+
+void save_stack_trace(struct stack_trace *trace)
+{
+	register unsigned long sp asm ("15");
+	unsigned long orig_sp, new_sp;
+
+	orig_sp = sp & PSW_ADDR_INSN;
+	new_sp = save_context_stack(trace, orig_sp,
+				    S390_lowcore.panic_stack - PAGE_SIZE,
+				    S390_lowcore.panic_stack, 1);
+	if (new_sp != orig_sp)
+		return;
+	new_sp = save_context_stack(trace, new_sp,
+				    S390_lowcore.async_stack - ASYNC_SIZE,
+				    S390_lowcore.async_stack, 1);
+	if (new_sp != orig_sp)
+		return;
+	save_context_stack(trace, new_sp,
+			   S390_lowcore.thread_info,
+			   S390_lowcore.thread_info + THREAD_SIZE, 1);
+}
+EXPORT_SYMBOL_GPL(save_stack_trace);
+
+void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
+{
+	unsigned long sp, low, high;
+
+	sp = tsk->thread.ksp & PSW_ADDR_INSN;
+	low = (unsigned long) task_stack_page(tsk);
+	high = (unsigned long) task_pt_regs(tsk);
+	save_context_stack(trace, sp, low, high, 0);
+	if (trace->nr_entries < trace->max_entries)
+		trace->entries[trace->nr_entries++] = ULONG_MAX;
+}
+EXPORT_SYMBOL_GPL(save_stack_trace_tsk);
diff --git a/arch/s390/kernel/suspend.c b/arch/s390/kernel/suspend.c
new file mode 100644
index 000000000..d3236c9e2
--- /dev/null
+++ b/arch/s390/kernel/suspend.c
@@ -0,0 +1,225 @@
+/*
+ * Suspend support specific for s390.
+ *
+ * Copyright IBM Corp. 2009
+ *
+ * Author(s): Hans-Joachim Picht <hans@linux.vnet.ibm.com>
+ */
+
+#include <linux/pfn.h>
+#include <linux/suspend.h>
+#include <linux/mm.h>
+#include <asm/ctl_reg.h>
+#include <asm/ipl.h>
+#include <asm/cio.h>
+#include <asm/pci.h>
+#include <asm/sections.h>
+#include "entry.h"
+
+/*
+ * The restore of the saved pages in an hibernation image will set
+ * the change and referenced bits in the storage key for each page.
+ * Overindication of the referenced bits after an hibernation cycle
+ * does not cause any harm but the overindication of the change bits
+ * would cause trouble.
+ * Use the ARCH_SAVE_PAGE_KEYS hooks to save the storage key of each
+ * page to the most significant byte of the associated page frame
+ * number in the hibernation image.
+ */
+
+/*
+ * Key storage is allocated as a linked list of pages.
+ * The size of the keys array is (PAGE_SIZE - sizeof(long))
+ */
+struct page_key_data {
+	struct page_key_data *next;
+	unsigned char data[];
+};
+
+#define PAGE_KEY_DATA_SIZE	(PAGE_SIZE - sizeof(struct page_key_data *))
+
+static struct page_key_data *page_key_data;
+static struct page_key_data *page_key_rp, *page_key_wp;
+static unsigned long page_key_rx, page_key_wx;
+unsigned long suspend_zero_pages;
+
+/*
+ * For each page in the hibernation image one additional byte is
+ * stored in the most significant byte of the page frame number.
+ * On suspend no additional memory is required but on resume the
+ * keys need to be memorized until the page data has been restored.
+ * Only then can the storage keys be set to their old state.
+ */
+unsigned long page_key_additional_pages(unsigned long pages)
+{
+	return DIV_ROUND_UP(pages, PAGE_KEY_DATA_SIZE);
+}
+
+/*
+ * Free page_key_data list of arrays.
+ */
+void page_key_free(void)
+{
+	struct page_key_data *pkd;
+
+	while (page_key_data) {
+		pkd = page_key_data;
+		page_key_data = pkd->next;
+		free_page((unsigned long) pkd);
+	}
+}
+
+/*
+ * Allocate page_key_data list of arrays with enough room to store
+ * one byte for each page in the hibernation image.
+ */
+int page_key_alloc(unsigned long pages)
+{
+	struct page_key_data *pk;
+	unsigned long size;
+
+	size = DIV_ROUND_UP(pages, PAGE_KEY_DATA_SIZE);
+	while (size--) {
+		pk = (struct page_key_data *) get_zeroed_page(GFP_KERNEL);
+		if (!pk) {
+			page_key_free();
+			return -ENOMEM;
+		}
+		pk->next = page_key_data;
+		page_key_data = pk;
+	}
+	page_key_rp = page_key_wp = page_key_data;
+	page_key_rx = page_key_wx = 0;
+	return 0;
+}
+
+/*
+ * Save the storage key into the upper 8 bits of the page frame number.
+ */
+void page_key_read(unsigned long *pfn)
+{
+	unsigned long addr;
+
+	addr = (unsigned long) page_address(pfn_to_page(*pfn));
+	*(unsigned char *) pfn = (unsigned char) page_get_storage_key(addr);
+}
+
+/*
+ * Extract the storage key from the upper 8 bits of the page frame number
+ * and store it in the page_key_data list of arrays.
+ */
+void page_key_memorize(unsigned long *pfn)
+{
+	page_key_wp->data[page_key_wx] = *(unsigned char *) pfn;
+	*(unsigned char *) pfn = 0;
+	if (++page_key_wx < PAGE_KEY_DATA_SIZE)
+		return;
+	page_key_wp = page_key_wp->next;
+	page_key_wx = 0;
+}
+
+/*
+ * Get the next key from the page_key_data list of arrays and set the
+ * storage key of the page referred by @address. If @address refers to
+ * a "safe" page the swsusp_arch_resume code will transfer the storage
+ * key from the buffer page to the original page.
+ */
+void page_key_write(void *address)
+{
+	page_set_storage_key((unsigned long) address,
+			     page_key_rp->data[page_key_rx], 0);
+	if (++page_key_rx >= PAGE_KEY_DATA_SIZE)
+		return;
+	page_key_rp = page_key_rp->next;
+	page_key_rx = 0;
+}
+
+int pfn_is_nosave(unsigned long pfn)
+{
+	unsigned long nosave_begin_pfn = PFN_DOWN(__pa(&__nosave_begin));
+	unsigned long nosave_end_pfn = PFN_DOWN(__pa(&__nosave_end));
+	unsigned long eshared_pfn = PFN_DOWN(__pa(&_eshared)) - 1;
+	unsigned long stext_pfn = PFN_DOWN(__pa(&_stext));
+
+	/* Always save lowcore pages (LC protection might be enabled). */
+	if (pfn <= LC_PAGES)
+		return 0;
+	if (pfn >= nosave_begin_pfn && pfn < nosave_end_pfn)
+		return 1;
+	/* Skip memory holes and read-only pages (NSS, DCSS, ...). */
+	if (pfn >= stext_pfn && pfn <= eshared_pfn)
+		return ipl_info.type == IPL_TYPE_NSS ? 1 : 0;
+	if (tprot(PFN_PHYS(pfn)))
+		return 1;
+	return 0;
+}
+
+/*
+ * PM notifier callback for suspend
+ */
+static int suspend_pm_cb(struct notifier_block *nb, unsigned long action,
+			 void *ptr)
+{
+	switch (action) {
+	case PM_SUSPEND_PREPARE:
+	case PM_HIBERNATION_PREPARE:
+		suspend_zero_pages = __get_free_pages(GFP_KERNEL, LC_ORDER);
+		if (!suspend_zero_pages)
+			return NOTIFY_BAD;
+		break;
+	case PM_POST_SUSPEND:
+	case PM_POST_HIBERNATION:
+		free_pages(suspend_zero_pages, LC_ORDER);
+		break;
+	default:
+		return NOTIFY_DONE;
+	}
+	return NOTIFY_OK;
+}
+
+static int __init suspend_pm_init(void)
+{
+	pm_notifier(suspend_pm_cb, 0);
+	return 0;
+}
+arch_initcall(suspend_pm_init);
+
+void save_processor_state(void)
+{
+	/* swsusp_arch_suspend() actually saves all cpu register contents.
+	 * Machine checks must be disabled since swsusp_arch_suspend() stores
+	 * register contents to their lowcore save areas. That's the same
+	 * place where register contents on machine checks would be saved.
+	 * To avoid register corruption disable machine checks.
+	 * We must also disable machine checks in the new psw mask for
+	 * program checks, since swsusp_arch_suspend() may generate program
+	 * checks. Disabling machine checks for all other new psw masks is
+	 * just paranoia.
+	 */
+	local_mcck_disable();
+	/* Disable lowcore protection */
+	__ctl_clear_bit(0,28);
+	S390_lowcore.external_new_psw.mask &= ~PSW_MASK_MCHECK;
+	S390_lowcore.svc_new_psw.mask &= ~PSW_MASK_MCHECK;
+	S390_lowcore.io_new_psw.mask &= ~PSW_MASK_MCHECK;
+	S390_lowcore.program_new_psw.mask &= ~PSW_MASK_MCHECK;
+}
+
+void restore_processor_state(void)
+{
+	S390_lowcore.external_new_psw.mask |= PSW_MASK_MCHECK;
+	S390_lowcore.svc_new_psw.mask |= PSW_MASK_MCHECK;
+	S390_lowcore.io_new_psw.mask |= PSW_MASK_MCHECK;
+	S390_lowcore.program_new_psw.mask |= PSW_MASK_MCHECK;
+	/* Enable lowcore protection */
+	__ctl_set_bit(0,28);
+	local_mcck_enable();
+}
+
+/* Called at the end of swsusp_arch_resume */
+void s390_early_resume(void)
+{
+	lgr_info_log();
+	channel_subsystem_reinit();
+	zpci_rescan();
+}
diff --git a/arch/s390/kernel/swsusp.S b/arch/s390/kernel/swsusp.S
new file mode 100644
index 000000000..ca6294645
--- /dev/null
+++ b/arch/s390/kernel/swsusp.S
@@ -0,0 +1,317 @@
+/*
+ * S390 64-bit swsusp implementation
+ *
+ * Copyright IBM Corp. 2009
+ *
+ * Author(s): Hans-Joachim Picht <hans@linux.vnet.ibm.com>
+ *	      Michael Holzheu <holzheu@linux.vnet.ibm.com>
+ */
+
+#include <linux/linkage.h>
+#include <asm/page.h>
+#include <asm/ptrace.h>
+#include <asm/thread_info.h>
+#include <asm/asm-offsets.h>
+#include <asm/sigp.h>
+
+/*
+ * Save register context in absolute 0 lowcore and call swsusp_save() to
+ * create in-memory kernel image. The context is saved in the designated
+ * "store status" memory locations (see POP).
+ * We return from this function twice. The first time during the suspend to
+ * disk process. The second time via the swsusp_arch_resume() function
+ * (see below) in the resume process.
+ * This function runs with disabled interrupts.
+ */
+	.section .text
+ENTRY(swsusp_arch_suspend)
+	stmg	%r6,%r15,__SF_GPRS(%r15)
+	lgr	%r1,%r15
+	aghi	%r15,-STACK_FRAME_OVERHEAD
+	stg	%r1,__SF_BACKCHAIN(%r15)
+
+	/* Deactivate DAT */
+	stnsm	__SF_EMPTY(%r15),0xfb
+
+	/* Store prefix register on stack */
+	stpx	__SF_EMPTY(%r15)
+
+	/* Save prefix register contents for lowcore copy */
+	llgf	%r10,__SF_EMPTY(%r15)
+
+	/* Get pointer to save area */
+	lghi	%r1,0x1000
+
+	/* Save CPU address */
+	stap	__LC_EXT_CPU_ADDR(%r0)
+
+	/* Store registers */
+	mvc	0x318(4,%r1),__SF_EMPTY(%r15)	/* move prefix to lowcore */
+	stfpc	0x31c(%r1)			/* store fpu control */
+	std	0,0x200(%r1)			/* store f0 */
+	std	1,0x208(%r1)			/* store f1 */
+	std	2,0x210(%r1)			/* store f2 */
+	std	3,0x218(%r1)			/* store f3 */
+	std	4,0x220(%r1)			/* store f4 */
+	std	5,0x228(%r1)			/* store f5 */
+	std	6,0x230(%r1)			/* store f6 */
+	std	7,0x238(%r1)			/* store f7 */
+	std	8,0x240(%r1)			/* store f8 */
+	std	9,0x248(%r1)			/* store f9 */
+	std	10,0x250(%r1)			/* store f10 */
+	std	11,0x258(%r1)			/* store f11 */
+	std	12,0x260(%r1)			/* store f12 */
+	std	13,0x268(%r1)			/* store f13 */
+	std	14,0x270(%r1)			/* store f14 */
+	std	15,0x278(%r1)			/* store f15 */
+	stam	%a0,%a15,0x340(%r1)		/* store access registers */
+	stctg	%c0,%c15,0x380(%r1)		/* store control registers */
+	stmg	%r0,%r15,0x280(%r1)		/* store general registers */
+
+	stpt	0x328(%r1)			/* store timer */
+	stck	__SF_EMPTY(%r15)		/* store clock */
+	stckc	0x330(%r1)			/* store clock comparator */
+
+	/* Update cputime accounting before going to sleep */
+	lg	%r0,__LC_LAST_UPDATE_TIMER
+	slg	%r0,0x328(%r1)
+	alg	%r0,__LC_SYSTEM_TIMER
+	stg	%r0,__LC_SYSTEM_TIMER
+	mvc	__LC_LAST_UPDATE_TIMER(8),0x328(%r1)
+	lg	%r0,__LC_LAST_UPDATE_CLOCK
+	slg	%r0,__SF_EMPTY(%r15)
+	alg	%r0,__LC_STEAL_TIMER
+	stg	%r0,__LC_STEAL_TIMER
+	mvc	__LC_LAST_UPDATE_CLOCK(8),__SF_EMPTY(%r15)
+
+	/* Activate DAT */
+	stosm	__SF_EMPTY(%r15),0x04
+
+	/* Set prefix page to zero */
+	xc	__SF_EMPTY(4,%r15),__SF_EMPTY(%r15)
+	spx	__SF_EMPTY(%r15)
+
+	/* Save absolute zero pages */
+	larl	%r2,suspend_zero_pages
+	lg	%r2,0(%r2)
+	lghi	%r4,0
+	lghi	%r3,2*PAGE_SIZE
+	lghi	%r5,2*PAGE_SIZE
+1:	mvcle	%r2,%r4,0
+	jo	1b
+
+	/* Copy lowcore to absolute zero lowcore */
+	lghi	%r2,0
+	lgr	%r4,%r10
+	lghi	%r3,2*PAGE_SIZE
+	lghi	%r5,2*PAGE_SIZE
+1:	mvcle	%r2,%r4,0
+	jo	1b
+
+	/* Save image */
+	brasl	%r14,swsusp_save
+
+	/* Restore prefix register and return */
+	lghi	%r1,0x1000
+	spx	0x318(%r1)
+	lmg	%r6,%r15,STACK_FRAME_OVERHEAD + __SF_GPRS(%r15)
+	lghi	%r2,0
+	br	%r14
+
+/*
+ * Restore saved memory image to correct place and restore register context.
+ * Then we return to the function that called swsusp_arch_suspend().
+ * swsusp_arch_resume() runs with disabled interrupts.
+ */
+ENTRY(swsusp_arch_resume)
+	stmg	%r6,%r15,__SF_GPRS(%r15)
+	lgr	%r1,%r15
+	aghi	%r15,-STACK_FRAME_OVERHEAD
+	stg	%r1,__SF_BACKCHAIN(%r15)
+
+	/* Make all free pages stable */
+	lghi	%r2,1
+	brasl	%r14,arch_set_page_states
+
+	/* Deactivate DAT */
+	stnsm	__SF_EMPTY(%r15),0xfb
+
+	/* Set prefix page to zero */
+	xc	__SF_EMPTY(4,%r15),__SF_EMPTY(%r15)
+	spx	__SF_EMPTY(%r15)
+
+	/* Restore saved image */
+	larl	%r1,restore_pblist
+	lg	%r1,0(%r1)
+	ltgr	%r1,%r1
+	jz	2f
+0:
+	lg	%r2,8(%r1)
+	lg	%r4,0(%r1)
+	iske	%r0,%r4
+	lghi	%r3,PAGE_SIZE
+	lghi	%r5,PAGE_SIZE
+1:
+	mvcle	%r2,%r4,0
+	jo	1b
+	lg	%r2,8(%r1)
+	sske	%r0,%r2
+	lg	%r1,16(%r1)
+	ltgr	%r1,%r1
+	jnz	0b
+2:
+	ptlb				/* flush tlb */
+
+	/* Reset System */
+	larl	%r1,restart_entry
+	larl	%r2,.Lrestart_diag308_psw
+	og	%r1,0(%r2)
+	stg	%r1,0(%r0)
+	larl	%r1,.Lnew_pgm_check_psw
+	epsw	%r2,%r3
+	stm	%r2,%r3,0(%r1)
+	mvc	__LC_PGM_NEW_PSW(16,%r0),0(%r1)
+	lghi	%r0,0
+	diag	%r0,%r0,0x308
+restart_entry:
+	lhi	%r1,1
+	sigp	%r1,%r0,SIGP_SET_ARCHITECTURE
+	sam64
+#ifdef CONFIG_SMP
+	larl	%r1,smp_cpu_mt_shift
+	icm	%r1,15,0(%r1)
+	jz	smt_done
+	llgfr	%r1,%r1
+smt_loop:
+	sigp	%r1,%r0,SIGP_SET_MULTI_THREADING
+	brc	8,smt_done			/* accepted */
+	brc	2,smt_loop			/* busy, try again */
+smt_done:
+#endif
+	larl	%r1,.Lnew_pgm_check_psw
+	lpswe	0(%r1)
+pgm_check_entry:
+
+	/* Switch to original suspend CPU */
+	larl	%r1,.Lresume_cpu		/* Resume CPU address: r2 */
+	stap	0(%r1)
+	llgh	%r2,0(%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	/* sigp initial cpu reset */
+	brc	8,4f				/* accepted */
+	brc	2,3b				/* busy, try again */
+
+	/* Suspend CPU not available -> panic */
+	larl	%r15,init_thread_union
+	ahi	%r15,1<<(PAGE_SHIFT+THREAD_ORDER)
+	larl	%r2,.Lpanic_string
+	larl	%r3,_sclp_print_early
+	lghi	%r1,0
+	sam31
+	sigp	%r1,%r0,SIGP_SET_ARCHITECTURE
+	basr	%r14,%r3
+	larl	%r3,.Ldisabled_wait_31
+	lpsw	0(%r3)
+4:
+	/* Switch to suspend CPU */
+	sigp	%r9,%r1,SIGP_RESTART	/* sigp restart to suspend CPU */
+	brc	2,4b			/* busy, try again */
+5:
+	sigp	%r9,%r2,SIGP_STOP	/* sigp stop to current resume CPU */
+	brc	2,5b			/* busy, try again */
+6:	j	6b
+
+restart_suspend:
+	larl	%r1,.Lresume_cpu
+	llgh	%r2,0(%r1)
+7:
+	sigp	%r9,%r2,SIGP_SENSE	/* 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 */
+	jz	7b
+
+restore_registers:
+	/* Restore registers */
+	lghi	%r13,0x1000		/* %r1 = pointer to save area */
+
+	/* Ignore time spent in suspended state. */
+	llgf	%r1,0x318(%r13)
+	stck	__LC_LAST_UPDATE_CLOCK(%r1)
+	spt	0x328(%r13)		/* reprogram timer */
+	//sckc	0x330(%r13)		/* set clock comparator */
+
+	lctlg	%c0,%c15,0x380(%r13)	/* load control registers */
+	lam	%a0,%a15,0x340(%r13)	/* load access registers */
+
+	lfpc	0x31c(%r13)		/* load fpu control */
+	ld	0,0x200(%r13)		/* load f0 */
+	ld	1,0x208(%r13)		/* load f1 */
+	ld	2,0x210(%r13)		/* load f2 */
+	ld	3,0x218(%r13)		/* load f3 */
+	ld	4,0x220(%r13)		/* load f4 */
+	ld	5,0x228(%r13)		/* load f5 */
+	ld	6,0x230(%r13)		/* load f6 */
+	ld	7,0x238(%r13)		/* load f7 */
+	ld	8,0x240(%r13)		/* load f8 */
+	ld	9,0x248(%r13)		/* load f9 */
+	ld	10,0x250(%r13)		/* load f10 */
+	ld	11,0x258(%r13)		/* load f11 */
+	ld	12,0x260(%r13)		/* load f12 */
+	ld	13,0x268(%r13)		/* load f13 */
+	ld	14,0x270(%r13)		/* load f14 */
+	ld	15,0x278(%r13)		/* load f15 */
+
+	/* Load old stack */
+	lg	%r15,0x2f8(%r13)
+
+	/* Save prefix register */
+	mvc __SF_EMPTY(4,%r15),0x318(%r13)
+
+	/* Restore absolute zero pages */
+	lghi	%r2,0
+	larl	%r4,suspend_zero_pages
+	lg	%r4,0(%r4)
+	lghi	%r3,2*PAGE_SIZE
+	lghi	%r5,2*PAGE_SIZE
+1:	mvcle	%r2,%r4,0
+	jo	1b
+
+	/* Restore prefix register */
+	spx	__SF_EMPTY(%r15)
+
+	/* Activate DAT */
+	stosm	__SF_EMPTY(%r15),0x04
+
+	/* Make all free pages unstable */
+	lghi	%r2,0
+	brasl	%r14,arch_set_page_states
+
+	/* Call arch specific early resume code */
+	brasl	%r14,s390_early_resume
+
+	/* Return 0 */
+	lmg	%r6,%r15,STACK_FRAME_OVERHEAD + __SF_GPRS(%r15)
+	lghi	%r2,0
+	br	%r14
+
+	.section .data..nosave,"aw",@progbits
+	.align	8
+.Ldisabled_wait_31:
+	.long  0x000a0000,0x00000000
+.Lpanic_string:
+	.asciz	"Resume not possible because suspend CPU is no longer available"
+	.align	8
+.Lrestart_diag308_psw:
+	.long	0x00080000,0x80000000
+.Lrestart_suspend_psw:
+	.quad	0x0000000180000000,restart_suspend
+.Lnew_pgm_check_psw:
+	.quad	0,pgm_check_entry
+.Lresume_cpu:
+	.byte	0,0
diff --git a/arch/s390/kernel/sys_s390.c b/arch/s390/kernel/sys_s390.c
new file mode 100644
index 000000000..f145490cc
--- /dev/null
+++ b/arch/s390/kernel/sys_s390.c
@@ -0,0 +1,91 @@
+/*
+ *  S390 version
+ *    Copyright IBM Corp. 1999, 2000
+ *    Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com),
+ *               Thomas Spatzier (tspat@de.ibm.com)
+ *
+ *  Derived from "arch/i386/kernel/sys_i386.c"
+ *
+ *  This file contains various random system calls that
+ *  have a non-standard calling sequence on the Linux/s390
+ *  platform.
+ */
+
+#include <linux/errno.h>
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/fs.h>
+#include <linux/smp.h>
+#include <linux/sem.h>
+#include <linux/msg.h>
+#include <linux/shm.h>
+#include <linux/stat.h>
+#include <linux/syscalls.h>
+#include <linux/mman.h>
+#include <linux/file.h>
+#include <linux/utsname.h>
+#include <linux/personality.h>
+#include <linux/unistd.h>
+#include <linux/ipc.h>
+#include <asm/uaccess.h>
+#include "entry.h"
+
+/*
+ * Perform the mmap() system call. Linux for S/390 isn't able to handle more
+ * than 5 system call parameters, so this system call uses a memory block
+ * for parameter passing.
+ */
+
+struct s390_mmap_arg_struct {
+	unsigned long addr;
+	unsigned long len;
+	unsigned long prot;
+	unsigned long flags;
+	unsigned long fd;
+	unsigned long offset;
+};
+
+SYSCALL_DEFINE1(mmap2, struct s390_mmap_arg_struct __user *, arg)
+{
+	struct s390_mmap_arg_struct a;
+	int error = -EFAULT;
+
+	if (copy_from_user(&a, arg, sizeof(a)))
+		goto out;
+	error = sys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, a.fd, a.offset);
+out:
+	return error;
+}
+
+/*
+ * sys_ipc() is the de-multiplexer for the SysV IPC calls.
+ */
+SYSCALL_DEFINE5(s390_ipc, uint, call, int, first, unsigned long, second,
+		unsigned long, third, void __user *, ptr)
+{
+	if (call >> 16)
+		return -EINVAL;
+	/* The s390 sys_ipc variant has only five parameters instead of six
+	 * like the generic variant. The only difference is the handling of
+	 * the SEMTIMEDOP subcall where on s390 the third parameter is used
+	 * as a pointer to a struct timespec where the generic variant uses
+	 * the fifth parameter.
+	 * Therefore we can call the generic variant by simply passing the
+	 * third parameter also as fifth parameter.
+	 */
+	return sys_ipc(call, first, second, third, ptr, third);
+}
+
+SYSCALL_DEFINE1(s390_personality, unsigned int, personality)
+{
+	unsigned int ret;
+
+	if (personality(current->personality) == PER_LINUX32 &&
+	    personality(personality) == PER_LINUX)
+		personality |= PER_LINUX32;
+	ret = sys_personality(personality);
+	if (personality(ret) == PER_LINUX32)
+		ret &= ~PER_LINUX32;
+
+	return ret;
+}
diff --git a/arch/s390/kernel/syscalls.S b/arch/s390/kernel/syscalls.S
new file mode 100644
index 000000000..1acad0268
--- /dev/null
+++ b/arch/s390/kernel/syscalls.S
@@ -0,0 +1,365 @@
+/*
+ * definitions for sys_call_table, each line represents an
+ * entry in the table in the form
+ * SYSCALL(64 bit syscall, 31 bit emulated syscall)
+ *
+ * this file is meant to be included from entry.S
+ */
+
+#define NI_SYSCALL SYSCALL(sys_ni_syscall,sys_ni_syscall)
+
+NI_SYSCALL						/* 0 */
+SYSCALL(sys_exit,compat_sys_exit)
+SYSCALL(sys_fork,sys_fork)
+SYSCALL(sys_read,compat_sys_s390_read)
+SYSCALL(sys_write,compat_sys_s390_write)
+SYSCALL(sys_open,compat_sys_open)			/* 5 */
+SYSCALL(sys_close,compat_sys_close)
+SYSCALL(sys_restart_syscall,sys_restart_syscall)
+SYSCALL(sys_creat,compat_sys_creat)
+SYSCALL(sys_link,compat_sys_link)
+SYSCALL(sys_unlink,compat_sys_unlink)			/* 10 */
+SYSCALL(sys_execve,compat_sys_execve)
+SYSCALL(sys_chdir,compat_sys_chdir)
+SYSCALL(sys_ni_syscall,compat_sys_time)			/* old time syscall */
+SYSCALL(sys_mknod,compat_sys_mknod)
+SYSCALL(sys_chmod,compat_sys_chmod)			/* 15 */
+SYSCALL(sys_ni_syscall,compat_sys_s390_lchown16)	/* old lchown16 syscall*/
+NI_SYSCALL						/* old break syscall holder */
+NI_SYSCALL						/* old stat syscall holder */
+SYSCALL(sys_lseek,compat_sys_lseek)
+SYSCALL(sys_getpid,sys_getpid)				/* 20 */
+SYSCALL(sys_mount,compat_sys_mount)
+SYSCALL(sys_oldumount,compat_sys_oldumount)
+SYSCALL(sys_ni_syscall,compat_sys_s390_setuid16)	/* old setuid16 syscall*/
+SYSCALL(sys_ni_syscall,compat_sys_s390_getuid16)	/* old getuid16 syscall*/
+SYSCALL(sys_ni_syscall,compat_sys_stime)		/* 25 old stime syscall */
+SYSCALL(sys_ptrace,compat_sys_ptrace)
+SYSCALL(sys_alarm,compat_sys_alarm)
+NI_SYSCALL						/* old fstat syscall */
+SYSCALL(sys_pause,sys_pause)
+SYSCALL(sys_utime,compat_sys_utime)			/* 30 */
+NI_SYSCALL						/* old stty syscall */
+NI_SYSCALL						/* old gtty syscall */
+SYSCALL(sys_access,compat_sys_access)
+SYSCALL(sys_nice,compat_sys_nice)
+NI_SYSCALL						/* 35 old ftime syscall */
+SYSCALL(sys_sync,sys_sync)
+SYSCALL(sys_kill,compat_sys_kill)
+SYSCALL(sys_rename,compat_sys_rename)
+SYSCALL(sys_mkdir,compat_sys_mkdir)
+SYSCALL(sys_rmdir,compat_sys_rmdir)			/* 40 */
+SYSCALL(sys_dup,compat_sys_dup)
+SYSCALL(sys_pipe,compat_sys_pipe)
+SYSCALL(sys_times,compat_sys_times)
+NI_SYSCALL						/* old prof syscall */
+SYSCALL(sys_brk,compat_sys_brk)				/* 45 */
+SYSCALL(sys_ni_syscall,compat_sys_s390_setgid16)	/* old setgid16 syscall*/
+SYSCALL(sys_ni_syscall,compat_sys_s390_getgid16)	/* old getgid16 syscall*/
+SYSCALL(sys_signal,compat_sys_signal)
+SYSCALL(sys_ni_syscall,compat_sys_s390_geteuid16)	/* old geteuid16 syscall */
+SYSCALL(sys_ni_syscall,compat_sys_s390_getegid16)	/* 50 old getegid16 syscall */
+SYSCALL(sys_acct,compat_sys_acct)
+SYSCALL(sys_umount,compat_sys_umount)
+NI_SYSCALL						/* old lock syscall */
+SYSCALL(sys_ioctl,compat_sys_ioctl)
+SYSCALL(sys_fcntl,compat_sys_fcntl)			/* 55 */
+NI_SYSCALL						/* intel mpx syscall */
+SYSCALL(sys_setpgid,compat_sys_setpgid)
+NI_SYSCALL						/* old ulimit syscall */
+NI_SYSCALL						/* old uname syscall */
+SYSCALL(sys_umask,compat_sys_umask)			/* 60 */
+SYSCALL(sys_chroot,compat_sys_chroot)
+SYSCALL(sys_ustat,compat_sys_ustat)
+SYSCALL(sys_dup2,compat_sys_dup2)
+SYSCALL(sys_getppid,sys_getppid)
+SYSCALL(sys_getpgrp,sys_getpgrp)			/* 65 */
+SYSCALL(sys_setsid,sys_setsid)
+SYSCALL(sys_sigaction,compat_sys_sigaction)
+NI_SYSCALL						/* old sgetmask syscall*/
+NI_SYSCALL						/* old ssetmask syscall*/
+SYSCALL(sys_ni_syscall,compat_sys_s390_setreuid16)	/* old setreuid16 syscall */
+SYSCALL(sys_ni_syscall,compat_sys_s390_setregid16)	/* old setregid16 syscall */
+SYSCALL(sys_sigsuspend,compat_sys_sigsuspend)
+SYSCALL(sys_sigpending,compat_sys_sigpending)
+SYSCALL(sys_sethostname,compat_sys_sethostname)
+SYSCALL(sys_setrlimit,compat_sys_setrlimit)		/* 75 */
+SYSCALL(sys_getrlimit,compat_sys_old_getrlimit)
+SYSCALL(sys_getrusage,compat_sys_getrusage)
+SYSCALL(sys_gettimeofday,compat_sys_gettimeofday)
+SYSCALL(sys_settimeofday,compat_sys_settimeofday)
+SYSCALL(sys_ni_syscall,compat_sys_s390_getgroups16)	/* 80 old getgroups16 syscall */
+SYSCALL(sys_ni_syscall,compat_sys_s390_setgroups16)	/* old setgroups16 syscall */
+NI_SYSCALL						/* old select syscall */
+SYSCALL(sys_symlink,compat_sys_symlink)
+NI_SYSCALL						/* old lstat syscall */
+SYSCALL(sys_readlink,compat_sys_readlink)		/* 85 */
+SYSCALL(sys_uselib,compat_sys_uselib)
+SYSCALL(sys_swapon,compat_sys_swapon)
+SYSCALL(sys_reboot,compat_sys_reboot)
+SYSCALL(sys_ni_syscall,compat_sys_old_readdir)		/* old readdir syscall */
+SYSCALL(sys_old_mmap,compat_sys_s390_old_mmap)		/* 90 */
+SYSCALL(sys_munmap,compat_sys_munmap)
+SYSCALL(sys_truncate,compat_sys_truncate)
+SYSCALL(sys_ftruncate,compat_sys_ftruncate)
+SYSCALL(sys_fchmod,compat_sys_fchmod)
+SYSCALL(sys_ni_syscall,compat_sys_s390_fchown16)	/* 95 old fchown16 syscall*/
+SYSCALL(sys_getpriority,compat_sys_getpriority)
+SYSCALL(sys_setpriority,compat_sys_setpriority)
+NI_SYSCALL						/* old profil syscall */
+SYSCALL(sys_statfs,compat_sys_statfs)
+SYSCALL(sys_fstatfs,compat_sys_fstatfs)			/* 100 */
+NI_SYSCALL						/* ioperm for i386 */
+SYSCALL(sys_socketcall,compat_sys_socketcall)
+SYSCALL(sys_syslog,compat_sys_syslog)
+SYSCALL(sys_setitimer,compat_sys_setitimer)
+SYSCALL(sys_getitimer,compat_sys_getitimer)		/* 105 */
+SYSCALL(sys_newstat,compat_sys_newstat)
+SYSCALL(sys_newlstat,compat_sys_newlstat)
+SYSCALL(sys_newfstat,compat_sys_newfstat)
+NI_SYSCALL						/* old uname syscall */
+SYSCALL(sys_lookup_dcookie,compat_sys_lookup_dcookie)	/* 110 */
+SYSCALL(sys_vhangup,sys_vhangup)
+NI_SYSCALL						/* old "idle" system call */
+NI_SYSCALL						/* vm86old for i386 */
+SYSCALL(sys_wait4,compat_sys_wait4)
+SYSCALL(sys_swapoff,compat_sys_swapoff)			/* 115 */
+SYSCALL(sys_sysinfo,compat_sys_sysinfo)
+SYSCALL(sys_s390_ipc,compat_sys_s390_ipc)
+SYSCALL(sys_fsync,compat_sys_fsync)
+SYSCALL(sys_sigreturn,compat_sys_sigreturn)
+SYSCALL(sys_clone,compat_sys_clone)			/* 120 */
+SYSCALL(sys_setdomainname,compat_sys_setdomainname)
+SYSCALL(sys_newuname,compat_sys_newuname)
+NI_SYSCALL						/* modify_ldt for i386 */
+SYSCALL(sys_adjtimex,compat_sys_adjtimex)
+SYSCALL(sys_mprotect,compat_sys_mprotect)		/* 125 */
+SYSCALL(sys_sigprocmask,compat_sys_sigprocmask)
+NI_SYSCALL						/* old "create module" */
+SYSCALL(sys_init_module,compat_sys_init_module)
+SYSCALL(sys_delete_module,compat_sys_delete_module)
+NI_SYSCALL						/* 130: old get_kernel_syms */
+SYSCALL(sys_quotactl,compat_sys_quotactl)
+SYSCALL(sys_getpgid,compat_sys_getpgid)
+SYSCALL(sys_fchdir,compat_sys_fchdir)
+SYSCALL(sys_bdflush,compat_sys_bdflush)
+SYSCALL(sys_sysfs,compat_sys_sysfs)			/* 135 */
+SYSCALL(sys_s390_personality,compat_sys_s390_personality)
+NI_SYSCALL						/* for afs_syscall */
+SYSCALL(sys_ni_syscall,compat_sys_s390_setfsuid16)	/* old setfsuid16 syscall */
+SYSCALL(sys_ni_syscall,compat_sys_s390_setfsgid16)	/* old setfsgid16 syscall */
+SYSCALL(sys_llseek,compat_sys_llseek)			/* 140 */
+SYSCALL(sys_getdents,compat_sys_getdents)
+SYSCALL(sys_select,compat_sys_select)
+SYSCALL(sys_flock,compat_sys_flock)
+SYSCALL(sys_msync,compat_sys_msync)
+SYSCALL(sys_readv,compat_sys_readv)			/* 145 */
+SYSCALL(sys_writev,compat_sys_writev)
+SYSCALL(sys_getsid,compat_sys_getsid)
+SYSCALL(sys_fdatasync,compat_sys_fdatasync)
+SYSCALL(sys_sysctl,compat_sys_sysctl)
+SYSCALL(sys_mlock,compat_sys_mlock)			/* 150 */
+SYSCALL(sys_munlock,compat_sys_munlock)
+SYSCALL(sys_mlockall,compat_sys_mlockall)
+SYSCALL(sys_munlockall,sys_munlockall)
+SYSCALL(sys_sched_setparam,compat_sys_sched_setparam)
+SYSCALL(sys_sched_getparam,compat_sys_sched_getparam)	/* 155 */
+SYSCALL(sys_sched_setscheduler,compat_sys_sched_setscheduler)
+SYSCALL(sys_sched_getscheduler,compat_sys_sched_getscheduler)
+SYSCALL(sys_sched_yield,sys_sched_yield)
+SYSCALL(sys_sched_get_priority_max,compat_sys_sched_get_priority_max)
+SYSCALL(sys_sched_get_priority_min,compat_sys_sched_get_priority_min)	/* 160 */
+SYSCALL(sys_sched_rr_get_interval,compat_sys_sched_rr_get_interval)
+SYSCALL(sys_nanosleep,compat_sys_nanosleep)
+SYSCALL(sys_mremap,compat_sys_mremap)
+SYSCALL(sys_ni_syscall,compat_sys_s390_setresuid16)	/* old setresuid16 syscall */
+SYSCALL(sys_ni_syscall,compat_sys_s390_getresuid16)	/* 165 old getresuid16 syscall */
+NI_SYSCALL						/* for vm86 */
+NI_SYSCALL						/* old sys_query_module */
+SYSCALL(sys_poll,compat_sys_poll)
+NI_SYSCALL						/* old nfsservctl */
+SYSCALL(sys_ni_syscall,compat_sys_s390_setresgid16)	/* 170 old setresgid16 syscall */
+SYSCALL(sys_ni_syscall,compat_sys_s390_getresgid16)	/* old getresgid16 syscall */
+SYSCALL(sys_prctl,compat_sys_prctl)
+SYSCALL(sys_rt_sigreturn,compat_sys_rt_sigreturn)
+SYSCALL(sys_rt_sigaction,compat_sys_rt_sigaction)
+SYSCALL(sys_rt_sigprocmask,compat_sys_rt_sigprocmask)	/* 175 */
+SYSCALL(sys_rt_sigpending,compat_sys_rt_sigpending)
+SYSCALL(sys_rt_sigtimedwait,compat_sys_rt_sigtimedwait)
+SYSCALL(sys_rt_sigqueueinfo,compat_sys_rt_sigqueueinfo)
+SYSCALL(sys_rt_sigsuspend,compat_sys_rt_sigsuspend)
+SYSCALL(sys_pread64,compat_sys_s390_pread64)		/* 180 */
+SYSCALL(sys_pwrite64,compat_sys_s390_pwrite64)
+SYSCALL(sys_ni_syscall,compat_sys_s390_chown16)		/* old chown16 syscall */
+SYSCALL(sys_getcwd,compat_sys_getcwd)
+SYSCALL(sys_capget,compat_sys_capget)
+SYSCALL(sys_capset,compat_sys_capset)			/* 185 */
+SYSCALL(sys_sigaltstack,compat_sys_sigaltstack)
+SYSCALL(sys_sendfile64,compat_sys_sendfile)
+NI_SYSCALL						/* streams1 */
+NI_SYSCALL						/* streams2 */
+SYSCALL(sys_vfork,sys_vfork)				/* 190 */
+SYSCALL(sys_getrlimit,compat_sys_getrlimit)
+SYSCALL(sys_mmap2,compat_sys_s390_mmap2)
+SYSCALL(sys_ni_syscall,compat_sys_s390_truncate64)
+SYSCALL(sys_ni_syscall,compat_sys_s390_ftruncate64)
+SYSCALL(sys_ni_syscall,compat_sys_s390_stat64)		/* 195 */
+SYSCALL(sys_ni_syscall,compat_sys_s390_lstat64)
+SYSCALL(sys_ni_syscall,compat_sys_s390_fstat64)
+SYSCALL(sys_lchown,compat_sys_lchown)
+SYSCALL(sys_getuid,sys_getuid)
+SYSCALL(sys_getgid,sys_getgid)				/* 200 */
+SYSCALL(sys_geteuid,sys_geteuid)
+SYSCALL(sys_getegid,sys_getegid)
+SYSCALL(sys_setreuid,compat_sys_setreuid)
+SYSCALL(sys_setregid,compat_sys_setregid)
+SYSCALL(sys_getgroups,compat_sys_getgroups)		/* 205 */
+SYSCALL(sys_setgroups,compat_sys_setgroups)
+SYSCALL(sys_fchown,compat_sys_fchown)
+SYSCALL(sys_setresuid,compat_sys_setresuid)
+SYSCALL(sys_getresuid,compat_sys_getresuid)
+SYSCALL(sys_setresgid,compat_sys_setresgid)		/* 210 */
+SYSCALL(sys_getresgid,compat_sys_getresgid)
+SYSCALL(sys_chown,compat_sys_chown)
+SYSCALL(sys_setuid,compat_sys_setuid)
+SYSCALL(sys_setgid,compat_sys_setgid)
+SYSCALL(sys_setfsuid,compat_sys_setfsuid)		/* 215 */
+SYSCALL(sys_setfsgid,compat_sys_setfsgid)
+SYSCALL(sys_pivot_root,compat_sys_pivot_root)
+SYSCALL(sys_mincore,compat_sys_mincore)
+SYSCALL(sys_madvise,compat_sys_madvise)
+SYSCALL(sys_getdents64,compat_sys_getdents64)		/* 220 */
+SYSCALL(sys_ni_syscall,compat_sys_fcntl64)
+SYSCALL(sys_readahead,compat_sys_s390_readahead)
+SYSCALL(sys_ni_syscall,compat_sys_sendfile64)
+SYSCALL(sys_setxattr,compat_sys_setxattr)
+SYSCALL(sys_lsetxattr,compat_sys_lsetxattr)		/* 225 */
+SYSCALL(sys_fsetxattr,compat_sys_fsetxattr)
+SYSCALL(sys_getxattr,compat_sys_getxattr)
+SYSCALL(sys_lgetxattr,compat_sys_lgetxattr)
+SYSCALL(sys_fgetxattr,compat_sys_fgetxattr)
+SYSCALL(sys_listxattr,compat_sys_listxattr)		/* 230 */
+SYSCALL(sys_llistxattr,compat_sys_llistxattr)
+SYSCALL(sys_flistxattr,compat_sys_flistxattr)
+SYSCALL(sys_removexattr,compat_sys_removexattr)
+SYSCALL(sys_lremovexattr,compat_sys_lremovexattr)
+SYSCALL(sys_fremovexattr,compat_sys_fremovexattr)	/* 235 */
+SYSCALL(sys_gettid,sys_gettid)
+SYSCALL(sys_tkill,compat_sys_tkill)
+SYSCALL(sys_futex,compat_sys_futex)
+SYSCALL(sys_sched_setaffinity,compat_sys_sched_setaffinity)
+SYSCALL(sys_sched_getaffinity,compat_sys_sched_getaffinity)	/* 240 */
+SYSCALL(sys_tgkill,compat_sys_tgkill)
+NI_SYSCALL						/* reserved for TUX */
+SYSCALL(sys_io_setup,compat_sys_io_setup)
+SYSCALL(sys_io_destroy,compat_sys_io_destroy)
+SYSCALL(sys_io_getevents,compat_sys_io_getevents)	/* 245 */
+SYSCALL(sys_io_submit,compat_sys_io_submit)
+SYSCALL(sys_io_cancel,compat_sys_io_cancel)
+SYSCALL(sys_exit_group,compat_sys_exit_group)
+SYSCALL(sys_epoll_create,compat_sys_epoll_create)
+SYSCALL(sys_epoll_ctl,compat_sys_epoll_ctl)		/* 250 */
+SYSCALL(sys_epoll_wait,compat_sys_epoll_wait)
+SYSCALL(sys_set_tid_address,compat_sys_set_tid_address)
+SYSCALL(sys_fadvise64_64,compat_sys_s390_fadvise64)
+SYSCALL(sys_timer_create,compat_sys_timer_create)
+SYSCALL(sys_timer_settime,compat_sys_timer_settime)	/* 255 */
+SYSCALL(sys_timer_gettime,compat_sys_timer_gettime)
+SYSCALL(sys_timer_getoverrun,compat_sys_timer_getoverrun)
+SYSCALL(sys_timer_delete,compat_sys_timer_delete)
+SYSCALL(sys_clock_settime,compat_sys_clock_settime)
+SYSCALL(sys_clock_gettime,compat_sys_clock_gettime)	/* 260 */
+SYSCALL(sys_clock_getres,compat_sys_clock_getres)
+SYSCALL(sys_clock_nanosleep,compat_sys_clock_nanosleep)
+NI_SYSCALL						/* reserved for vserver */
+SYSCALL(sys_ni_syscall,compat_sys_s390_fadvise64_64)
+SYSCALL(sys_statfs64,compat_sys_statfs64)
+SYSCALL(sys_fstatfs64,compat_sys_fstatfs64)
+SYSCALL(sys_remap_file_pages,compat_sys_remap_file_pages)
+NI_SYSCALL						/* 268 sys_mbind */
+NI_SYSCALL						/* 269 sys_get_mempolicy */
+NI_SYSCALL						/* 270 sys_set_mempolicy */
+SYSCALL(sys_mq_open,compat_sys_mq_open)
+SYSCALL(sys_mq_unlink,compat_sys_mq_unlink)
+SYSCALL(sys_mq_timedsend,compat_sys_mq_timedsend)
+SYSCALL(sys_mq_timedreceive,compat_sys_mq_timedreceive)
+SYSCALL(sys_mq_notify,compat_sys_mq_notify)		/* 275 */
+SYSCALL(sys_mq_getsetattr,compat_sys_mq_getsetattr)
+SYSCALL(sys_kexec_load,compat_sys_kexec_load)
+SYSCALL(sys_add_key,compat_sys_add_key)
+SYSCALL(sys_request_key,compat_sys_request_key)
+SYSCALL(sys_keyctl,compat_sys_keyctl)			/* 280 */
+SYSCALL(sys_waitid,compat_sys_waitid)
+SYSCALL(sys_ioprio_set,compat_sys_ioprio_set)
+SYSCALL(sys_ioprio_get,compat_sys_ioprio_get)
+SYSCALL(sys_inotify_init,sys_inotify_init)
+SYSCALL(sys_inotify_add_watch,compat_sys_inotify_add_watch)	/* 285 */
+SYSCALL(sys_inotify_rm_watch,compat_sys_inotify_rm_watch)
+NI_SYSCALL						/* 287 sys_migrate_pages */
+SYSCALL(sys_openat,compat_sys_openat)
+SYSCALL(sys_mkdirat,compat_sys_mkdirat)
+SYSCALL(sys_mknodat,compat_sys_mknodat)			/* 290 */
+SYSCALL(sys_fchownat,compat_sys_fchownat)
+SYSCALL(sys_futimesat,compat_sys_futimesat)
+SYSCALL(sys_newfstatat,compat_sys_s390_fstatat64)
+SYSCALL(sys_unlinkat,compat_sys_unlinkat)
+SYSCALL(sys_renameat,compat_sys_renameat)		/* 295 */
+SYSCALL(sys_linkat,compat_sys_linkat)
+SYSCALL(sys_symlinkat,compat_sys_symlinkat)
+SYSCALL(sys_readlinkat,compat_sys_readlinkat)
+SYSCALL(sys_fchmodat,compat_sys_fchmodat)
+SYSCALL(sys_faccessat,compat_sys_faccessat)		/* 300 */
+SYSCALL(sys_pselect6,compat_sys_pselect6)
+SYSCALL(sys_ppoll,compat_sys_ppoll)
+SYSCALL(sys_unshare,compat_sys_unshare)
+SYSCALL(sys_set_robust_list,compat_sys_set_robust_list)
+SYSCALL(sys_get_robust_list,compat_sys_get_robust_list)
+SYSCALL(sys_splice,compat_sys_splice)
+SYSCALL(sys_sync_file_range,compat_sys_s390_sync_file_range)
+SYSCALL(sys_tee,compat_sys_tee)
+SYSCALL(sys_vmsplice,compat_sys_vmsplice)
+NI_SYSCALL						/* 310 sys_move_pages */
+SYSCALL(sys_getcpu,compat_sys_getcpu)
+SYSCALL(sys_epoll_pwait,compat_sys_epoll_pwait)
+SYSCALL(sys_utimes,compat_sys_utimes)
+SYSCALL(sys_fallocate,compat_sys_s390_fallocate)
+SYSCALL(sys_utimensat,compat_sys_utimensat)		/* 315 */
+SYSCALL(sys_signalfd,compat_sys_signalfd)
+NI_SYSCALL						/* 317 old sys_timer_fd */
+SYSCALL(sys_eventfd,compat_sys_eventfd)
+SYSCALL(sys_timerfd_create,compat_sys_timerfd_create)
+SYSCALL(sys_timerfd_settime,compat_sys_timerfd_settime) /* 320 */
+SYSCALL(sys_timerfd_gettime,compat_sys_timerfd_gettime)
+SYSCALL(sys_signalfd4,compat_sys_signalfd4)
+SYSCALL(sys_eventfd2,compat_sys_eventfd2)
+SYSCALL(sys_inotify_init1,compat_sys_inotify_init1)
+SYSCALL(sys_pipe2,compat_sys_pipe2)			/* 325 */
+SYSCALL(sys_dup3,compat_sys_dup3)
+SYSCALL(sys_epoll_create1,compat_sys_epoll_create1)
+SYSCALL(sys_preadv,compat_sys_preadv)
+SYSCALL(sys_pwritev,compat_sys_pwritev)
+SYSCALL(sys_rt_tgsigqueueinfo,compat_sys_rt_tgsigqueueinfo) /* 330 */
+SYSCALL(sys_perf_event_open,compat_sys_perf_event_open)
+SYSCALL(sys_fanotify_init,compat_sys_fanotify_init)
+SYSCALL(sys_fanotify_mark,compat_sys_fanotify_mark)
+SYSCALL(sys_prlimit64,compat_sys_prlimit64)
+SYSCALL(sys_name_to_handle_at,compat_sys_name_to_handle_at) /* 335 */
+SYSCALL(sys_open_by_handle_at,compat_sys_open_by_handle_at)
+SYSCALL(sys_clock_adjtime,compat_sys_clock_adjtime)
+SYSCALL(sys_syncfs,compat_sys_syncfs)
+SYSCALL(sys_setns,compat_sys_setns)
+SYSCALL(sys_process_vm_readv,compat_sys_process_vm_readv) /* 340 */
+SYSCALL(sys_process_vm_writev,compat_sys_process_vm_writev)
+SYSCALL(sys_s390_runtime_instr,compat_sys_s390_runtime_instr)
+SYSCALL(sys_kcmp,compat_sys_kcmp)
+SYSCALL(sys_finit_module,compat_sys_finit_module)
+SYSCALL(sys_sched_setattr,compat_sys_sched_setattr)	/* 345 */
+SYSCALL(sys_sched_getattr,compat_sys_sched_getattr)
+SYSCALL(sys_renameat2,compat_sys_renameat2)
+SYSCALL(sys_seccomp,compat_sys_seccomp)
+SYSCALL(sys_getrandom,compat_sys_getrandom)
+SYSCALL(sys_memfd_create,compat_sys_memfd_create)	/* 350 */
+SYSCALL(sys_bpf,compat_sys_bpf)
+SYSCALL(sys_s390_pci_mmio_write,compat_sys_s390_pci_mmio_write)
+SYSCALL(sys_s390_pci_mmio_read,compat_sys_s390_pci_mmio_read)
+SYSCALL(sys_execveat,compat_sys_execveat)
diff --git a/arch/s390/kernel/sysinfo.c b/arch/s390/kernel/sysinfo.c
new file mode 100644
index 000000000..99babea02
--- /dev/null
+++ b/arch/s390/kernel/sysinfo.c
@@ -0,0 +1,465 @@
+/*
+ *  Copyright IBM Corp. 2001, 2009
+ *  Author(s): Ulrich Weigand <Ulrich.Weigand@de.ibm.com>,
+ *	       Martin Schwidefsky <schwidefsky@de.ibm.com>,
+ */
+
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include <linux/init.h>
+#include <linux/delay.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <asm/ebcdic.h>
+#include <asm/sysinfo.h>
+#include <asm/cpcmd.h>
+#include <asm/topology.h>
+
+/* Sigh, math-emu. Don't ask. */
+#include <asm/sfp-util.h>
+#include <math-emu/soft-fp.h>
+#include <math-emu/single.h>
+
+int topology_max_mnest;
+
+/*
+ * stsi - store system information
+ *
+ * Returns the current configuration level if function code 0 was specified.
+ * Otherwise returns 0 on success or a negative value on error.
+ */
+int stsi(void *sysinfo, int fc, int sel1, int sel2)
+{
+	register int r0 asm("0") = (fc << 28) | sel1;
+	register int r1 asm("1") = sel2;
+	int rc = 0;
+
+	asm volatile(
+		"	stsi	0(%3)\n"
+		"0:	jz	2f\n"
+		"1:	lhi	%1,%4\n"
+		"2:\n"
+		EX_TABLE(0b, 1b)
+		: "+d" (r0), "+d" (rc)
+		: "d" (r1), "a" (sysinfo), "K" (-EOPNOTSUPP)
+		: "cc", "memory");
+	if (rc)
+		return rc;
+	return fc ? 0 : ((unsigned int) r0) >> 28;
+}
+EXPORT_SYMBOL(stsi);
+
+static void stsi_1_1_1(struct seq_file *m, struct sysinfo_1_1_1 *info)
+{
+	int i;
+
+	if (stsi(info, 1, 1, 1))
+		return;
+	EBCASC(info->manufacturer, sizeof(info->manufacturer));
+	EBCASC(info->type, sizeof(info->type));
+	EBCASC(info->model, sizeof(info->model));
+	EBCASC(info->sequence, sizeof(info->sequence));
+	EBCASC(info->plant, sizeof(info->plant));
+	EBCASC(info->model_capacity, sizeof(info->model_capacity));
+	EBCASC(info->model_perm_cap, sizeof(info->model_perm_cap));
+	EBCASC(info->model_temp_cap, sizeof(info->model_temp_cap));
+	seq_printf(m, "Manufacturer:         %-16.16s\n", info->manufacturer);
+	seq_printf(m, "Type:                 %-4.4s\n", info->type);
+	/*
+	 * Sigh: the model field has been renamed with System z9
+	 * to model_capacity and a new model field has been added
+	 * after the plant field. To avoid confusing older programs
+	 * the "Model:" prints "model_capacity model" or just
+	 * "model_capacity" if the model string is empty .
+	 */
+	seq_printf(m, "Model:                %-16.16s", info->model_capacity);
+	if (info->model[0] != '\0')
+		seq_printf(m, " %-16.16s", info->model);
+	seq_putc(m, '\n');
+	seq_printf(m, "Sequence Code:        %-16.16s\n", info->sequence);
+	seq_printf(m, "Plant:                %-4.4s\n", info->plant);
+	seq_printf(m, "Model Capacity:       %-16.16s %08u\n",
+		   info->model_capacity, info->model_cap_rating);
+	if (info->model_perm_cap_rating)
+		seq_printf(m, "Model Perm. Capacity: %-16.16s %08u\n",
+			   info->model_perm_cap,
+			   info->model_perm_cap_rating);
+	if (info->model_temp_cap_rating)
+		seq_printf(m, "Model Temp. Capacity: %-16.16s %08u\n",
+			   info->model_temp_cap,
+			   info->model_temp_cap_rating);
+	if (info->ncr)
+		seq_printf(m, "Nominal Cap. Rating:  %08u\n", info->ncr);
+	if (info->npr)
+		seq_printf(m, "Nominal Perm. Rating: %08u\n", info->npr);
+	if (info->ntr)
+		seq_printf(m, "Nominal Temp. Rating: %08u\n", info->ntr);
+	if (info->cai) {
+		seq_printf(m, "Capacity Adj. Ind.:   %d\n", info->cai);
+		seq_printf(m, "Capacity Ch. Reason:  %d\n", info->ccr);
+		seq_printf(m, "Capacity Transient:   %d\n", info->t);
+	}
+	if (info->p) {
+		for (i = 1; i <= ARRAY_SIZE(info->typepct); i++) {
+			seq_printf(m, "Type %d Percentage:    %d\n",
+				   i, info->typepct[i - 1]);
+		}
+	}
+}
+
+static void stsi_15_1_x(struct seq_file *m, struct sysinfo_15_1_x *info)
+{
+	static int max_mnest;
+	int i, rc;
+
+	seq_putc(m, '\n');
+	if (!MACHINE_HAS_TOPOLOGY)
+		return;
+	if (stsi(info, 15, 1, topology_max_mnest))
+		return;
+	seq_printf(m, "CPU Topology HW:     ");
+	for (i = 0; i < TOPOLOGY_NR_MAG; i++)
+		seq_printf(m, " %d", info->mag[i]);
+	seq_putc(m, '\n');
+#ifdef CONFIG_SCHED_MC
+	store_topology(info);
+	seq_printf(m, "CPU Topology SW:     ");
+	for (i = 0; i < TOPOLOGY_NR_MAG; i++)
+		seq_printf(m, " %d", info->mag[i]);
+	seq_putc(m, '\n');
+#endif
+}
+
+static void stsi_1_2_2(struct seq_file *m, struct sysinfo_1_2_2 *info)
+{
+	struct sysinfo_1_2_2_extension *ext;
+	int i;
+
+	if (stsi(info, 1, 2, 2))
+		return;
+	ext = (struct sysinfo_1_2_2_extension *)
+		((unsigned long) info + info->acc_offset);
+	seq_printf(m, "CPUs Total:           %d\n", info->cpus_total);
+	seq_printf(m, "CPUs Configured:      %d\n", info->cpus_configured);
+	seq_printf(m, "CPUs Standby:         %d\n", info->cpus_standby);
+	seq_printf(m, "CPUs Reserved:        %d\n", info->cpus_reserved);
+	/*
+	 * Sigh 2. According to the specification the alternate
+	 * capability field is a 32 bit floating point number
+	 * if the higher order 8 bits are not zero. Printing
+	 * a floating point number in the kernel is a no-no,
+	 * always print the number as 32 bit unsigned integer.
+	 * The user-space needs to know about the strange
+	 * encoding of the alternate cpu capability.
+	 */
+	seq_printf(m, "Capability:           %u", info->capability);
+	if (info->format == 1)
+		seq_printf(m, " %u", ext->alt_capability);
+	seq_putc(m, '\n');
+	if (info->nominal_cap)
+		seq_printf(m, "Nominal Capability:   %d\n", info->nominal_cap);
+	if (info->secondary_cap)
+		seq_printf(m, "Secondary Capability: %d\n", info->secondary_cap);
+	for (i = 2; i <= info->cpus_total; i++) {
+		seq_printf(m, "Adjustment %02d-way:    %u",
+			   i, info->adjustment[i-2]);
+		if (info->format == 1)
+			seq_printf(m, " %u", ext->alt_adjustment[i-2]);
+		seq_putc(m, '\n');
+	}
+}
+
+static void stsi_2_2_2(struct seq_file *m, struct sysinfo_2_2_2 *info)
+{
+	if (stsi(info, 2, 2, 2))
+		return;
+	EBCASC(info->name, sizeof(info->name));
+	seq_putc(m, '\n');
+	seq_printf(m, "LPAR Number:          %d\n", info->lpar_number);
+	seq_printf(m, "LPAR Characteristics: ");
+	if (info->characteristics & LPAR_CHAR_DEDICATED)
+		seq_printf(m, "Dedicated ");
+	if (info->characteristics & LPAR_CHAR_SHARED)
+		seq_printf(m, "Shared ");
+	if (info->characteristics & LPAR_CHAR_LIMITED)
+		seq_printf(m, "Limited ");
+	seq_putc(m, '\n');
+	seq_printf(m, "LPAR Name:            %-8.8s\n", info->name);
+	seq_printf(m, "LPAR Adjustment:      %d\n", info->caf);
+	seq_printf(m, "LPAR CPUs Total:      %d\n", info->cpus_total);
+	seq_printf(m, "LPAR CPUs Configured: %d\n", info->cpus_configured);
+	seq_printf(m, "LPAR CPUs Standby:    %d\n", info->cpus_standby);
+	seq_printf(m, "LPAR CPUs Reserved:   %d\n", info->cpus_reserved);
+	seq_printf(m, "LPAR CPUs Dedicated:  %d\n", info->cpus_dedicated);
+	seq_printf(m, "LPAR CPUs Shared:     %d\n", info->cpus_shared);
+	if (info->mt_installed & 0x80) {
+		seq_printf(m, "LPAR CPUs G-MTID:     %d\n",
+			   info->mt_general & 0x1f);
+		seq_printf(m, "LPAR CPUs S-MTID:     %d\n",
+			   info->mt_installed & 0x1f);
+		seq_printf(m, "LPAR CPUs PS-MTID:    %d\n",
+			   info->mt_psmtid & 0x1f);
+	}
+}
+
+static void print_ext_name(struct seq_file *m, int lvl,
+			   struct sysinfo_3_2_2 *info)
+{
+	if (info->vm[lvl].ext_name_encoding == 0)
+		return;
+	if (info->ext_names[lvl][0] == 0)
+		return;
+	switch (info->vm[lvl].ext_name_encoding) {
+	case 1: /* EBCDIC */
+		EBCASC(info->ext_names[lvl], sizeof(info->ext_names[lvl]));
+		break;
+	case 2:	/* UTF-8 */
+		break;
+	default:
+		return;
+	}
+	seq_printf(m, "VM%02d Extended Name:   %-.256s\n", lvl,
+		   info->ext_names[lvl]);
+}
+
+static void print_uuid(struct seq_file *m, int i, struct sysinfo_3_2_2 *info)
+{
+	if (!memcmp(&info->vm[i].uuid, &NULL_UUID_BE, sizeof(uuid_be)))
+		return;
+	seq_printf(m, "VM%02d UUID:            %pUb\n", i, &info->vm[i].uuid);
+}
+
+static void stsi_3_2_2(struct seq_file *m, struct sysinfo_3_2_2 *info)
+{
+	int i;
+
+	if (stsi(info, 3, 2, 2))
+		return;
+	for (i = 0; i < info->count; i++) {
+		EBCASC(info->vm[i].name, sizeof(info->vm[i].name));
+		EBCASC(info->vm[i].cpi, sizeof(info->vm[i].cpi));
+		seq_putc(m, '\n');
+		seq_printf(m, "VM%02d Name:            %-8.8s\n", i, info->vm[i].name);
+		seq_printf(m, "VM%02d Control Program: %-16.16s\n", i, info->vm[i].cpi);
+		seq_printf(m, "VM%02d Adjustment:      %d\n", i, info->vm[i].caf);
+		seq_printf(m, "VM%02d CPUs Total:      %d\n", i, info->vm[i].cpus_total);
+		seq_printf(m, "VM%02d CPUs Configured: %d\n", i, info->vm[i].cpus_configured);
+		seq_printf(m, "VM%02d CPUs Standby:    %d\n", i, info->vm[i].cpus_standby);
+		seq_printf(m, "VM%02d CPUs Reserved:   %d\n", i, info->vm[i].cpus_reserved);
+		print_ext_name(m, i, info);
+		print_uuid(m, i, info);
+	}
+}
+
+static int sysinfo_show(struct seq_file *m, void *v)
+{
+	void *info = (void *)get_zeroed_page(GFP_KERNEL);
+	int level;
+
+	if (!info)
+		return 0;
+	level = stsi(NULL, 0, 0, 0);
+	if (level >= 1)
+		stsi_1_1_1(m, info);
+	if (level >= 1)
+		stsi_15_1_x(m, info);
+	if (level >= 1)
+		stsi_1_2_2(m, info);
+	if (level >= 2)
+		stsi_2_2_2(m, info);
+	if (level >= 3)
+		stsi_3_2_2(m, info);
+	free_page((unsigned long)info);
+	return 0;
+}
+
+static int sysinfo_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, sysinfo_show, NULL);
+}
+
+static const struct file_operations sysinfo_fops = {
+	.open		= sysinfo_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int __init sysinfo_create_proc(void)
+{
+	proc_create("sysinfo", 0444, NULL, &sysinfo_fops);
+	return 0;
+}
+device_initcall(sysinfo_create_proc);
+
+/*
+ * Service levels interface.
+ */
+
+static DECLARE_RWSEM(service_level_sem);
+static LIST_HEAD(service_level_list);
+
+int register_service_level(struct service_level *slr)
+{
+	struct service_level *ptr;
+
+	down_write(&service_level_sem);
+	list_for_each_entry(ptr, &service_level_list, list)
+		if (ptr == slr) {
+			up_write(&service_level_sem);
+			return -EEXIST;
+		}
+	list_add_tail(&slr->list, &service_level_list);
+	up_write(&service_level_sem);
+	return 0;
+}
+EXPORT_SYMBOL(register_service_level);
+
+int unregister_service_level(struct service_level *slr)
+{
+	struct service_level *ptr, *next;
+	int rc = -ENOENT;
+
+	down_write(&service_level_sem);
+	list_for_each_entry_safe(ptr, next, &service_level_list, list) {
+		if (ptr != slr)
+			continue;
+		list_del(&ptr->list);
+		rc = 0;
+		break;
+	}
+	up_write(&service_level_sem);
+	return rc;
+}
+EXPORT_SYMBOL(unregister_service_level);
+
+static void *service_level_start(struct seq_file *m, loff_t *pos)
+{
+	down_read(&service_level_sem);
+	return seq_list_start(&service_level_list, *pos);
+}
+
+static void *service_level_next(struct seq_file *m, void *p, loff_t *pos)
+{
+	return seq_list_next(p, &service_level_list, pos);
+}
+
+static void service_level_stop(struct seq_file *m, void *p)
+{
+	up_read(&service_level_sem);
+}
+
+static int service_level_show(struct seq_file *m, void *p)
+{
+	struct service_level *slr;
+
+	slr = list_entry(p, struct service_level, list);
+	slr->seq_print(m, slr);
+	return 0;
+}
+
+static const struct seq_operations service_level_seq_ops = {
+	.start		= service_level_start,
+	.next		= service_level_next,
+	.stop		= service_level_stop,
+	.show		= service_level_show
+};
+
+static int service_level_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &service_level_seq_ops);
+}
+
+static const struct file_operations service_level_ops = {
+	.open		= service_level_open,
+	.read		= seq_read,
+	.llseek 	= seq_lseek,
+	.release	= seq_release
+};
+
+static void service_level_vm_print(struct seq_file *m,
+				   struct service_level *slr)
+{
+	char *query_buffer, *str;
+
+	query_buffer = kmalloc(1024, GFP_KERNEL | GFP_DMA);
+	if (!query_buffer)
+		return;
+	cpcmd("QUERY CPLEVEL", query_buffer, 1024, NULL);
+	str = strchr(query_buffer, '\n');
+	if (str)
+		*str = 0;
+	seq_printf(m, "VM: %s\n", query_buffer);
+	kfree(query_buffer);
+}
+
+static struct service_level service_level_vm = {
+	.seq_print = service_level_vm_print
+};
+
+static __init int create_proc_service_level(void)
+{
+	proc_create("service_levels", 0, NULL, &service_level_ops);
+	if (MACHINE_IS_VM)
+		register_service_level(&service_level_vm);
+	return 0;
+}
+subsys_initcall(create_proc_service_level);
+
+/*
+ * CPU capability might have changed. Therefore recalculate loops_per_jiffy.
+ */
+void s390_adjust_jiffies(void)
+{
+	struct sysinfo_1_2_2 *info;
+	const unsigned int fmil = 0x4b189680;	/* 1e7 as 32-bit float. */
+	FP_DECL_S(SA); FP_DECL_S(SB); FP_DECL_S(SR);
+	FP_DECL_EX;
+	unsigned int capability;
+
+	info = (void *) get_zeroed_page(GFP_KERNEL);
+	if (!info)
+		return;
+
+	if (stsi(info, 1, 2, 2) == 0) {
+		/*
+		 * Major sigh. The cpu capability encoding is "special".
+		 * If the first 9 bits of info->capability are 0 then it
+		 * is a 32 bit unsigned integer in the range 0 .. 2^23.
+		 * If the first 9 bits are != 0 then it is a 32 bit float.
+		 * In addition a lower value indicates a proportionally
+		 * higher cpu capacity. Bogomips are the other way round.
+		 * To get to a halfway suitable number we divide 1e7
+		 * by the cpu capability number. Yes, that means a floating
+		 * point division .. math-emu here we come :-)
+		 */
+		FP_UNPACK_SP(SA, &fmil);
+		if ((info->capability >> 23) == 0)
+			FP_FROM_INT_S(SB, (long) info->capability, 64, long);
+		else
+			FP_UNPACK_SP(SB, &info->capability);
+		FP_DIV_S(SR, SA, SB);
+		FP_TO_INT_S(capability, SR, 32, 0);
+	} else
+		/*
+		 * Really old machine without stsi block for basic
+		 * cpu information. Report 42.0 bogomips.
+		 */
+		capability = 42;
+	loops_per_jiffy = capability * (500000/HZ);
+	free_page((unsigned long) info);
+}
+
+/*
+ * calibrate the delay loop
+ */
+void calibrate_delay(void)
+{
+	s390_adjust_jiffies();
+	/* Print the good old Bogomips line .. */
+	printk(KERN_DEBUG "Calibrating delay loop (skipped)... "
+	       "%lu.%02lu BogoMIPS preset\n", loops_per_jiffy/(500000/HZ),
+	       (loops_per_jiffy/(5000/HZ)) % 100);
+}
diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c
new file mode 100644
index 000000000..170ddd201
--- /dev/null
+++ b/arch/s390/kernel/time.c
@@ -0,0 +1,1802 @@
+/*
+ *    Time of day based timer functions.
+ *
+ *  S390 version
+ *    Copyright IBM Corp. 1999, 2008
+ *    Author(s): Hartmut Penner (hp@de.ibm.com),
+ *               Martin Schwidefsky (schwidefsky@de.ibm.com),
+ *               Denis Joseph Barrow (djbarrow@de.ibm.com,barrow_dj@yahoo.com)
+ *
+ *  Derived from "arch/i386/kernel/time.c"
+ *    Copyright (C) 1991, 1992, 1995  Linus Torvalds
+ */
+
+#define KMSG_COMPONENT "time"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
+#include <linux/kernel_stat.h>
+#include <linux/errno.h>
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/param.h>
+#include <linux/string.h>
+#include <linux/mm.h>
+#include <linux/interrupt.h>
+#include <linux/cpu.h>
+#include <linux/stop_machine.h>
+#include <linux/time.h>
+#include <linux/device.h>
+#include <linux/delay.h>
+#include <linux/init.h>
+#include <linux/smp.h>
+#include <linux/types.h>
+#include <linux/profile.h>
+#include <linux/timex.h>
+#include <linux/notifier.h>
+#include <linux/timekeeper_internal.h>
+#include <linux/clockchips.h>
+#include <linux/gfp.h>
+#include <linux/kprobes.h>
+#include <asm/uaccess.h>
+#include <asm/delay.h>
+#include <asm/div64.h>
+#include <asm/vdso.h>
+#include <asm/irq.h>
+#include <asm/irq_regs.h>
+#include <asm/vtimer.h>
+#include <asm/etr.h>
+#include <asm/cio.h>
+#include "entry.h"
+
+/* change this if you have some constant time drift */
+#define USECS_PER_JIFFY     ((unsigned long) 1000000/HZ)
+#define CLK_TICKS_PER_JIFFY ((unsigned long) USECS_PER_JIFFY << 12)
+
+u64 sched_clock_base_cc = -1;	/* Force to data section. */
+EXPORT_SYMBOL_GPL(sched_clock_base_cc);
+
+static DEFINE_PER_CPU(struct clock_event_device, comparators);
+
+/*
+ * Scheduler clock - returns current time in nanosec units.
+ */
+unsigned long long notrace sched_clock(void)
+{
+	return tod_to_ns(get_tod_clock_monotonic());
+}
+NOKPROBE_SYMBOL(sched_clock);
+
+/*
+ * Monotonic_clock - returns # of nanoseconds passed since time_init()
+ */
+unsigned long long monotonic_clock(void)
+{
+	return sched_clock();
+}
+EXPORT_SYMBOL(monotonic_clock);
+
+void tod_to_timeval(__u64 todval, struct timespec *xt)
+{
+	unsigned long long sec;
+
+	sec = todval >> 12;
+	do_div(sec, 1000000);
+	xt->tv_sec = sec;
+	todval -= (sec * 1000000) << 12;
+	xt->tv_nsec = ((todval * 1000) >> 12);
+}
+EXPORT_SYMBOL(tod_to_timeval);
+
+void clock_comparator_work(void)
+{
+	struct clock_event_device *cd;
+
+	S390_lowcore.clock_comparator = -1ULL;
+	cd = this_cpu_ptr(&comparators);
+	cd->event_handler(cd);
+}
+
+/*
+ * Fixup the clock comparator.
+ */
+static void fixup_clock_comparator(unsigned long long delta)
+{
+	/* If nobody is waiting there's nothing to fix. */
+	if (S390_lowcore.clock_comparator == -1ULL)
+		return;
+	S390_lowcore.clock_comparator += delta;
+	set_clock_comparator(S390_lowcore.clock_comparator);
+}
+
+static int s390_next_event(unsigned long delta,
+			   struct clock_event_device *evt)
+{
+	S390_lowcore.clock_comparator = get_tod_clock() + delta;
+	set_clock_comparator(S390_lowcore.clock_comparator);
+	return 0;
+}
+
+static void s390_set_mode(enum clock_event_mode mode,
+			  struct clock_event_device *evt)
+{
+}
+
+/*
+ * Set up lowcore and control register of the current cpu to
+ * enable TOD clock and clock comparator interrupts.
+ */
+void init_cpu_timer(void)
+{
+	struct clock_event_device *cd;
+	int cpu;
+
+	S390_lowcore.clock_comparator = -1ULL;
+	set_clock_comparator(S390_lowcore.clock_comparator);
+
+	cpu = smp_processor_id();
+	cd = &per_cpu(comparators, cpu);
+	cd->name		= "comparator";
+	cd->features		= CLOCK_EVT_FEAT_ONESHOT;
+	cd->mult		= 16777;
+	cd->shift		= 12;
+	cd->min_delta_ns	= 1;
+	cd->max_delta_ns	= LONG_MAX;
+	cd->rating		= 400;
+	cd->cpumask		= cpumask_of(cpu);
+	cd->set_next_event	= s390_next_event;
+	cd->set_mode		= s390_set_mode;
+
+	clockevents_register_device(cd);
+
+	/* Enable clock comparator timer interrupt. */
+	__ctl_set_bit(0,11);
+
+	/* Always allow the timing alert external interrupt. */
+	__ctl_set_bit(0, 4);
+}
+
+static void clock_comparator_interrupt(struct ext_code ext_code,
+				       unsigned int param32,
+				       unsigned long param64)
+{
+	inc_irq_stat(IRQEXT_CLK);
+	if (S390_lowcore.clock_comparator == -1ULL)
+		set_clock_comparator(S390_lowcore.clock_comparator);
+}
+
+static void etr_timing_alert(struct etr_irq_parm *);
+static void stp_timing_alert(struct stp_irq_parm *);
+
+static void timing_alert_interrupt(struct ext_code ext_code,
+				   unsigned int param32, unsigned long param64)
+{
+	inc_irq_stat(IRQEXT_TLA);
+	if (param32 & 0x00c40000)
+		etr_timing_alert((struct etr_irq_parm *) &param32);
+	if (param32 & 0x00038000)
+		stp_timing_alert((struct stp_irq_parm *) &param32);
+}
+
+static void etr_reset(void);
+static void stp_reset(void);
+
+void read_persistent_clock(struct timespec *ts)
+{
+	tod_to_timeval(get_tod_clock() - TOD_UNIX_EPOCH, ts);
+}
+
+void read_boot_clock(struct timespec *ts)
+{
+	tod_to_timeval(sched_clock_base_cc - TOD_UNIX_EPOCH, ts);
+}
+
+static cycle_t read_tod_clock(struct clocksource *cs)
+{
+	return get_tod_clock();
+}
+
+static struct clocksource clocksource_tod = {
+	.name		= "tod",
+	.rating		= 400,
+	.read		= read_tod_clock,
+	.mask		= -1ULL,
+	.mult		= 1000,
+	.shift		= 12,
+	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
+};
+
+struct clocksource * __init clocksource_default_clock(void)
+{
+	return &clocksource_tod;
+}
+
+void update_vsyscall(struct timekeeper *tk)
+{
+	u64 nsecps;
+
+	if (tk->tkr_mono.clock != &clocksource_tod)
+		return;
+
+	/* Make userspace gettimeofday spin until we're done. */
+	++vdso_data->tb_update_count;
+	smp_wmb();
+	vdso_data->xtime_tod_stamp = tk->tkr_mono.cycle_last;
+	vdso_data->xtime_clock_sec = tk->xtime_sec;
+	vdso_data->xtime_clock_nsec = tk->tkr_mono.xtime_nsec;
+	vdso_data->wtom_clock_sec =
+		tk->xtime_sec + tk->wall_to_monotonic.tv_sec;
+	vdso_data->wtom_clock_nsec = tk->tkr_mono.xtime_nsec +
+		+ ((u64) tk->wall_to_monotonic.tv_nsec << tk->tkr_mono.shift);
+	nsecps = (u64) NSEC_PER_SEC << tk->tkr_mono.shift;
+	while (vdso_data->wtom_clock_nsec >= nsecps) {
+		vdso_data->wtom_clock_nsec -= nsecps;
+		vdso_data->wtom_clock_sec++;
+	}
+
+	vdso_data->xtime_coarse_sec = tk->xtime_sec;
+	vdso_data->xtime_coarse_nsec =
+		(long)(tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift);
+	vdso_data->wtom_coarse_sec =
+		vdso_data->xtime_coarse_sec + tk->wall_to_monotonic.tv_sec;
+	vdso_data->wtom_coarse_nsec =
+		vdso_data->xtime_coarse_nsec + tk->wall_to_monotonic.tv_nsec;
+	while (vdso_data->wtom_coarse_nsec >= NSEC_PER_SEC) {
+		vdso_data->wtom_coarse_nsec -= NSEC_PER_SEC;
+		vdso_data->wtom_coarse_sec++;
+	}
+
+	vdso_data->tk_mult = tk->tkr_mono.mult;
+	vdso_data->tk_shift = tk->tkr_mono.shift;
+	smp_wmb();
+	++vdso_data->tb_update_count;
+}
+
+extern struct timezone sys_tz;
+
+void update_vsyscall_tz(void)
+{
+	/* Make userspace gettimeofday spin until we're done. */
+	++vdso_data->tb_update_count;
+	smp_wmb();
+	vdso_data->tz_minuteswest = sys_tz.tz_minuteswest;
+	vdso_data->tz_dsttime = sys_tz.tz_dsttime;
+	smp_wmb();
+	++vdso_data->tb_update_count;
+}
+
+/*
+ * Initialize the TOD clock and the CPU timer of
+ * the boot cpu.
+ */
+void __init time_init(void)
+{
+	/* Reset time synchronization interfaces. */
+	etr_reset();
+	stp_reset();
+
+	/* request the clock comparator external interrupt */
+	if (register_external_irq(EXT_IRQ_CLK_COMP, clock_comparator_interrupt))
+		panic("Couldn't request external interrupt 0x1004");
+
+	/* request the timing alert external interrupt */
+	if (register_external_irq(EXT_IRQ_TIMING_ALERT, timing_alert_interrupt))
+		panic("Couldn't request external interrupt 0x1406");
+
+	if (__clocksource_register(&clocksource_tod) != 0)
+		panic("Could not register TOD clock source");
+
+	/* Enable TOD clock interrupts on the boot cpu. */
+	init_cpu_timer();
+
+	/* Enable cpu timer interrupts on the boot cpu. */
+	vtime_init();
+}
+
+/*
+ * The time is "clock". old is what we think the time is.
+ * Adjust the value by a multiple of jiffies and add the delta to ntp.
+ * "delay" is an approximation how long the synchronization took. If
+ * the time correction is positive, then "delay" is subtracted from
+ * the time difference and only the remaining part is passed to ntp.
+ */
+static unsigned long long adjust_time(unsigned long long old,
+				      unsigned long long clock,
+				      unsigned long long delay)
+{
+	unsigned long long delta, ticks;
+	struct timex adjust;
+
+	if (clock > old) {
+		/* It is later than we thought. */
+		delta = ticks = clock - old;
+		delta = ticks = (delta < delay) ? 0 : delta - delay;
+		delta -= do_div(ticks, CLK_TICKS_PER_JIFFY);
+		adjust.offset = ticks * (1000000 / HZ);
+	} else {
+		/* It is earlier than we thought. */
+		delta = ticks = old - clock;
+		delta -= do_div(ticks, CLK_TICKS_PER_JIFFY);
+		delta = -delta;
+		adjust.offset = -ticks * (1000000 / HZ);
+	}
+	sched_clock_base_cc += delta;
+	if (adjust.offset != 0) {
+		pr_notice("The ETR interface has adjusted the clock "
+			  "by %li microseconds\n", adjust.offset);
+		adjust.modes = ADJ_OFFSET_SINGLESHOT;
+		do_adjtimex(&adjust);
+	}
+	return delta;
+}
+
+static DEFINE_PER_CPU(atomic_t, clock_sync_word);
+static DEFINE_MUTEX(clock_sync_mutex);
+static unsigned long clock_sync_flags;
+
+#define CLOCK_SYNC_HAS_ETR	0
+#define CLOCK_SYNC_HAS_STP	1
+#define CLOCK_SYNC_ETR		2
+#define CLOCK_SYNC_STP		3
+
+/*
+ * The synchronous get_clock function. It will write the current clock
+ * value to the clock pointer and return 0 if the clock is in sync with
+ * the external time source. If the clock mode is local it will return
+ * -EOPNOTSUPP and -EAGAIN if the clock is not in sync with the external
+ * reference.
+ */
+int get_sync_clock(unsigned long long *clock)
+{
+	atomic_t *sw_ptr;
+	unsigned int sw0, sw1;
+
+	sw_ptr = &get_cpu_var(clock_sync_word);
+	sw0 = atomic_read(sw_ptr);
+	*clock = get_tod_clock();
+	sw1 = atomic_read(sw_ptr);
+	put_cpu_var(clock_sync_word);
+	if (sw0 == sw1 && (sw0 & 0x80000000U))
+		/* Success: time is in sync. */
+		return 0;
+	if (!test_bit(CLOCK_SYNC_HAS_ETR, &clock_sync_flags) &&
+	    !test_bit(CLOCK_SYNC_HAS_STP, &clock_sync_flags))
+		return -EOPNOTSUPP;
+	if (!test_bit(CLOCK_SYNC_ETR, &clock_sync_flags) &&
+	    !test_bit(CLOCK_SYNC_STP, &clock_sync_flags))
+		return -EACCES;
+	return -EAGAIN;
+}
+EXPORT_SYMBOL(get_sync_clock);
+
+/*
+ * Make get_sync_clock return -EAGAIN.
+ */
+static void disable_sync_clock(void *dummy)
+{
+	atomic_t *sw_ptr = this_cpu_ptr(&clock_sync_word);
+	/*
+	 * Clear the in-sync bit 2^31. All get_sync_clock calls will
+	 * fail until the sync bit is turned back on. In addition
+	 * increase the "sequence" counter to avoid the race of an
+	 * etr event and the complete recovery against get_sync_clock.
+	 */
+	atomic_clear_mask(0x80000000, sw_ptr);
+	atomic_inc(sw_ptr);
+}
+
+/*
+ * Make get_sync_clock return 0 again.
+ * Needs to be called from a context disabled for preemption.
+ */
+static void enable_sync_clock(void)
+{
+	atomic_t *sw_ptr = this_cpu_ptr(&clock_sync_word);
+	atomic_set_mask(0x80000000, sw_ptr);
+}
+
+/*
+ * Function to check if the clock is in sync.
+ */
+static inline int check_sync_clock(void)
+{
+	atomic_t *sw_ptr;
+	int rc;
+
+	sw_ptr = &get_cpu_var(clock_sync_word);
+	rc = (atomic_read(sw_ptr) & 0x80000000U) != 0;
+	put_cpu_var(clock_sync_word);
+	return rc;
+}
+
+/* Single threaded workqueue used for etr and stp sync events */
+static struct workqueue_struct *time_sync_wq;
+
+static void __init time_init_wq(void)
+{
+	if (time_sync_wq)
+		return;
+	time_sync_wq = create_singlethread_workqueue("timesync");
+}
+
+/*
+ * External Time Reference (ETR) code.
+ */
+static int etr_port0_online;
+static int etr_port1_online;
+static int etr_steai_available;
+
+static int __init early_parse_etr(char *p)
+{
+	if (strncmp(p, "off", 3) == 0)
+		etr_port0_online = etr_port1_online = 0;
+	else if (strncmp(p, "port0", 5) == 0)
+		etr_port0_online = 1;
+	else if (strncmp(p, "port1", 5) == 0)
+		etr_port1_online = 1;
+	else if (strncmp(p, "on", 2) == 0)
+		etr_port0_online = etr_port1_online = 1;
+	return 0;
+}
+early_param("etr", early_parse_etr);
+
+enum etr_event {
+	ETR_EVENT_PORT0_CHANGE,
+	ETR_EVENT_PORT1_CHANGE,
+	ETR_EVENT_PORT_ALERT,
+	ETR_EVENT_SYNC_CHECK,
+	ETR_EVENT_SWITCH_LOCAL,
+	ETR_EVENT_UPDATE,
+};
+
+/*
+ * Valid bit combinations of the eacr register are (x = don't care):
+ * e0 e1 dp p0 p1 ea es sl
+ *  0  0  x  0	0  0  0  0  initial, disabled state
+ *  0  0  x  0	1  1  0  0  port 1 online
+ *  0  0  x  1	0  1  0  0  port 0 online
+ *  0  0  x  1	1  1  0  0  both ports online
+ *  0  1  x  0	1  1  0  0  port 1 online and usable, ETR or PPS mode
+ *  0  1  x  0	1  1  0  1  port 1 online, usable and ETR mode
+ *  0  1  x  0	1  1  1  0  port 1 online, usable, PPS mode, in-sync
+ *  0  1  x  0	1  1  1  1  port 1 online, usable, ETR mode, in-sync
+ *  0  1  x  1	1  1  0  0  both ports online, port 1 usable
+ *  0  1  x  1	1  1  1  0  both ports online, port 1 usable, PPS mode, in-sync
+ *  0  1  x  1	1  1  1  1  both ports online, port 1 usable, ETR mode, in-sync
+ *  1  0  x  1	0  1  0  0  port 0 online and usable, ETR or PPS mode
+ *  1  0  x  1	0  1  0  1  port 0 online, usable and ETR mode
+ *  1  0  x  1	0  1  1  0  port 0 online, usable, PPS mode, in-sync
+ *  1  0  x  1	0  1  1  1  port 0 online, usable, ETR mode, in-sync
+ *  1  0  x  1	1  1  0  0  both ports online, port 0 usable
+ *  1  0  x  1	1  1  1  0  both ports online, port 0 usable, PPS mode, in-sync
+ *  1  0  x  1	1  1  1  1  both ports online, port 0 usable, ETR mode, in-sync
+ *  1  1  x  1	1  1  1  0  both ports online & usable, ETR, in-sync
+ *  1  1  x  1	1  1  1  1  both ports online & usable, ETR, in-sync
+ */
+static struct etr_eacr etr_eacr;
+static u64 etr_tolec;			/* time of last eacr update */
+static struct etr_aib etr_port0;
+static int etr_port0_uptodate;
+static struct etr_aib etr_port1;
+static int etr_port1_uptodate;
+static unsigned long etr_events;
+static struct timer_list etr_timer;
+
+static void etr_timeout(unsigned long dummy);
+static void etr_work_fn(struct work_struct *work);
+static DEFINE_MUTEX(etr_work_mutex);
+static DECLARE_WORK(etr_work, etr_work_fn);
+
+/*
+ * Reset ETR attachment.
+ */
+static void etr_reset(void)
+{
+	etr_eacr =  (struct etr_eacr) {
+		.e0 = 0, .e1 = 0, ._pad0 = 4, .dp = 0,
+		.p0 = 0, .p1 = 0, ._pad1 = 0, .ea = 0,
+		.es = 0, .sl = 0 };
+	if (etr_setr(&etr_eacr) == 0) {
+		etr_tolec = get_tod_clock();
+		set_bit(CLOCK_SYNC_HAS_ETR, &clock_sync_flags);
+		if (etr_port0_online && etr_port1_online)
+			set_bit(CLOCK_SYNC_ETR, &clock_sync_flags);
+	} else if (etr_port0_online || etr_port1_online) {
+		pr_warning("The real or virtual hardware system does "
+			   "not provide an ETR interface\n");
+		etr_port0_online = etr_port1_online = 0;
+	}
+}
+
+static int __init etr_init(void)
+{
+	struct etr_aib aib;
+
+	if (!test_bit(CLOCK_SYNC_HAS_ETR, &clock_sync_flags))
+		return 0;
+	time_init_wq();
+	/* Check if this machine has the steai instruction. */
+	if (etr_steai(&aib, ETR_STEAI_STEPPING_PORT) == 0)
+		etr_steai_available = 1;
+	setup_timer(&etr_timer, etr_timeout, 0UL);
+	if (etr_port0_online) {
+		set_bit(ETR_EVENT_PORT0_CHANGE, &etr_events);
+		queue_work(time_sync_wq, &etr_work);
+	}
+	if (etr_port1_online) {
+		set_bit(ETR_EVENT_PORT1_CHANGE, &etr_events);
+		queue_work(time_sync_wq, &etr_work);
+	}
+	return 0;
+}
+
+arch_initcall(etr_init);
+
+/*
+ * Two sorts of ETR machine checks. The architecture reads:
+ * "When a machine-check niterruption occurs and if a switch-to-local or
+ *  ETR-sync-check interrupt request is pending but disabled, this pending
+ *  disabled interruption request is indicated and is cleared".
+ * Which means that we can get etr_switch_to_local events from the machine
+ * check handler although the interruption condition is disabled. Lovely..
+ */
+
+/*
+ * Switch to local machine check. This is called when the last usable
+ * ETR port goes inactive. After switch to local the clock is not in sync.
+ */
+void etr_switch_to_local(void)
+{
+	if (!etr_eacr.sl)
+		return;
+	disable_sync_clock(NULL);
+	if (!test_and_set_bit(ETR_EVENT_SWITCH_LOCAL, &etr_events)) {
+		etr_eacr.es = etr_eacr.sl = 0;
+		etr_setr(&etr_eacr);
+		queue_work(time_sync_wq, &etr_work);
+	}
+}
+
+/*
+ * ETR sync check machine check. This is called when the ETR OTE and the
+ * local clock OTE are farther apart than the ETR sync check tolerance.
+ * After a ETR sync check the clock is not in sync. The machine check
+ * is broadcasted to all cpus at the same time.
+ */
+void etr_sync_check(void)
+{
+	if (!etr_eacr.es)
+		return;
+	disable_sync_clock(NULL);
+	if (!test_and_set_bit(ETR_EVENT_SYNC_CHECK, &etr_events)) {
+		etr_eacr.es = 0;
+		etr_setr(&etr_eacr);
+		queue_work(time_sync_wq, &etr_work);
+	}
+}
+
+/*
+ * ETR timing alert. There are two causes:
+ * 1) port state change, check the usability of the port
+ * 2) port alert, one of the ETR-data-validity bits (v1-v2 bits of the
+ *    sldr-status word) or ETR-data word 1 (edf1) or ETR-data word 3 (edf3)
+ *    or ETR-data word 4 (edf4) has changed.
+ */
+static void etr_timing_alert(struct etr_irq_parm *intparm)
+{
+	if (intparm->pc0)
+		/* ETR port 0 state change. */
+		set_bit(ETR_EVENT_PORT0_CHANGE, &etr_events);
+	if (intparm->pc1)
+		/* ETR port 1 state change. */
+		set_bit(ETR_EVENT_PORT1_CHANGE, &etr_events);
+	if (intparm->eai)
+		/*
+		 * ETR port alert on either port 0, 1 or both.
+		 * Both ports are not up-to-date now.
+		 */
+		set_bit(ETR_EVENT_PORT_ALERT, &etr_events);
+	queue_work(time_sync_wq, &etr_work);
+}
+
+static void etr_timeout(unsigned long dummy)
+{
+	set_bit(ETR_EVENT_UPDATE, &etr_events);
+	queue_work(time_sync_wq, &etr_work);
+}
+
+/*
+ * Check if the etr mode is pss.
+ */
+static inline int etr_mode_is_pps(struct etr_eacr eacr)
+{
+	return eacr.es && !eacr.sl;
+}
+
+/*
+ * Check if the etr mode is etr.
+ */
+static inline int etr_mode_is_etr(struct etr_eacr eacr)
+{
+	return eacr.es && eacr.sl;
+}
+
+/*
+ * Check if the port can be used for TOD synchronization.
+ * For PPS mode the port has to receive OTEs. For ETR mode
+ * the port has to receive OTEs, the ETR stepping bit has to
+ * be zero and the validity bits for data frame 1, 2, and 3
+ * have to be 1.
+ */
+static int etr_port_valid(struct etr_aib *aib, int port)
+{
+	unsigned int psc;
+
+	/* Check that this port is receiving OTEs. */
+	if (aib->tsp == 0)
+		return 0;
+
+	psc = port ? aib->esw.psc1 : aib->esw.psc0;
+	if (psc == etr_lpsc_pps_mode)
+		return 1;
+	if (psc == etr_lpsc_operational_step)
+		return !aib->esw.y && aib->slsw.v1 &&
+			aib->slsw.v2 && aib->slsw.v3;
+	return 0;
+}
+
+/*
+ * Check if two ports are on the same network.
+ */
+static int etr_compare_network(struct etr_aib *aib1, struct etr_aib *aib2)
+{
+	// FIXME: any other fields we have to compare?
+	return aib1->edf1.net_id == aib2->edf1.net_id;
+}
+
+/*
+ * Wrapper for etr_stei that converts physical port states
+ * to logical port states to be consistent with the output
+ * of stetr (see etr_psc vs. etr_lpsc).
+ */
+static void etr_steai_cv(struct etr_aib *aib, unsigned int func)
+{
+	BUG_ON(etr_steai(aib, func) != 0);
+	/* Convert port state to logical port state. */
+	if (aib->esw.psc0 == 1)
+		aib->esw.psc0 = 2;
+	else if (aib->esw.psc0 == 0 && aib->esw.p == 0)
+		aib->esw.psc0 = 1;
+	if (aib->esw.psc1 == 1)
+		aib->esw.psc1 = 2;
+	else if (aib->esw.psc1 == 0 && aib->esw.p == 1)
+		aib->esw.psc1 = 1;
+}
+
+/*
+ * Check if the aib a2 is still connected to the same attachment as
+ * aib a1, the etv values differ by one and a2 is valid.
+ */
+static int etr_aib_follows(struct etr_aib *a1, struct etr_aib *a2, int p)
+{
+	int state_a1, state_a2;
+
+	/* Paranoia check: e0/e1 should better be the same. */
+	if (a1->esw.eacr.e0 != a2->esw.eacr.e0 ||
+	    a1->esw.eacr.e1 != a2->esw.eacr.e1)
+		return 0;
+
+	/* Still connected to the same etr ? */
+	state_a1 = p ? a1->esw.psc1 : a1->esw.psc0;
+	state_a2 = p ? a2->esw.psc1 : a2->esw.psc0;
+	if (state_a1 == etr_lpsc_operational_step) {
+		if (state_a2 != etr_lpsc_operational_step ||
+		    a1->edf1.net_id != a2->edf1.net_id ||
+		    a1->edf1.etr_id != a2->edf1.etr_id ||
+		    a1->edf1.etr_pn != a2->edf1.etr_pn)
+			return 0;
+	} else if (state_a2 != etr_lpsc_pps_mode)
+		return 0;
+
+	/* The ETV value of a2 needs to be ETV of a1 + 1. */
+	if (a1->edf2.etv + 1 != a2->edf2.etv)
+		return 0;
+
+	if (!etr_port_valid(a2, p))
+		return 0;
+
+	return 1;
+}
+
+struct clock_sync_data {
+	atomic_t cpus;
+	int in_sync;
+	unsigned long long fixup_cc;
+	int etr_port;
+	struct etr_aib *etr_aib;
+};
+
+static void clock_sync_cpu(struct clock_sync_data *sync)
+{
+	atomic_dec(&sync->cpus);
+	enable_sync_clock();
+	/*
+	 * This looks like a busy wait loop but it isn't. etr_sync_cpus
+	 * is called on all other cpus while the TOD clocks is stopped.
+	 * __udelay will stop the cpu on an enabled wait psw until the
+	 * TOD is running again.
+	 */
+	while (sync->in_sync == 0) {
+		__udelay(1);
+		/*
+		 * A different cpu changes *in_sync. Therefore use
+		 * barrier() to force memory access.
+		 */
+		barrier();
+	}
+	if (sync->in_sync != 1)
+		/* Didn't work. Clear per-cpu in sync bit again. */
+		disable_sync_clock(NULL);
+	/*
+	 * This round of TOD syncing is done. Set the clock comparator
+	 * to the next tick and let the processor continue.
+	 */
+	fixup_clock_comparator(sync->fixup_cc);
+}
+
+/*
+ * Sync the TOD clock using the port referred to by aibp. This port
+ * has to be enabled and the other port has to be disabled. The
+ * last eacr update has to be more than 1.6 seconds in the past.
+ */
+static int etr_sync_clock(void *data)
+{
+	static int first;
+	unsigned long long clock, old_clock, delay, delta;
+	struct clock_sync_data *etr_sync;
+	struct etr_aib *sync_port, *aib;
+	int port;
+	int rc;
+
+	etr_sync = data;
+
+	if (xchg(&first, 1) == 1) {
+		/* Slave */
+		clock_sync_cpu(etr_sync);
+		return 0;
+	}
+
+	/* Wait until all other cpus entered the sync function. */
+	while (atomic_read(&etr_sync->cpus) != 0)
+		cpu_relax();
+
+	port = etr_sync->etr_port;
+	aib = etr_sync->etr_aib;
+	sync_port = (port == 0) ? &etr_port0 : &etr_port1;
+	enable_sync_clock();
+
+	/* Set clock to next OTE. */
+	__ctl_set_bit(14, 21);
+	__ctl_set_bit(0, 29);
+	clock = ((unsigned long long) (aib->edf2.etv + 1)) << 32;
+	old_clock = get_tod_clock();
+	if (set_tod_clock(clock) == 0) {
+		__udelay(1);	/* Wait for the clock to start. */
+		__ctl_clear_bit(0, 29);
+		__ctl_clear_bit(14, 21);
+		etr_stetr(aib);
+		/* Adjust Linux timing variables. */
+		delay = (unsigned long long)
+			(aib->edf2.etv - sync_port->edf2.etv) << 32;
+		delta = adjust_time(old_clock, clock, delay);
+		etr_sync->fixup_cc = delta;
+		fixup_clock_comparator(delta);
+		/* Verify that the clock is properly set. */
+		if (!etr_aib_follows(sync_port, aib, port)) {
+			/* Didn't work. */
+			disable_sync_clock(NULL);
+			etr_sync->in_sync = -EAGAIN;
+			rc = -EAGAIN;
+		} else {
+			etr_sync->in_sync = 1;
+			rc = 0;
+		}
+	} else {
+		/* Could not set the clock ?!? */
+		__ctl_clear_bit(0, 29);
+		__ctl_clear_bit(14, 21);
+		disable_sync_clock(NULL);
+		etr_sync->in_sync = -EAGAIN;
+		rc = -EAGAIN;
+	}
+	xchg(&first, 0);
+	return rc;
+}
+
+static int etr_sync_clock_stop(struct etr_aib *aib, int port)
+{
+	struct clock_sync_data etr_sync;
+	struct etr_aib *sync_port;
+	int follows;
+	int rc;
+
+	/* Check if the current aib is adjacent to the sync port aib. */
+	sync_port = (port == 0) ? &etr_port0 : &etr_port1;
+	follows = etr_aib_follows(sync_port, aib, port);
+	memcpy(sync_port, aib, sizeof(*aib));
+	if (!follows)
+		return -EAGAIN;
+	memset(&etr_sync, 0, sizeof(etr_sync));
+	etr_sync.etr_aib = aib;
+	etr_sync.etr_port = port;
+	get_online_cpus();
+	atomic_set(&etr_sync.cpus, num_online_cpus() - 1);
+	rc = stop_machine(etr_sync_clock, &etr_sync, cpu_online_mask);
+	put_online_cpus();
+	return rc;
+}
+
+/*
+ * Handle the immediate effects of the different events.
+ * The port change event is used for online/offline changes.
+ */
+static struct etr_eacr etr_handle_events(struct etr_eacr eacr)
+{
+	if (test_and_clear_bit(ETR_EVENT_SYNC_CHECK, &etr_events))
+		eacr.es = 0;
+	if (test_and_clear_bit(ETR_EVENT_SWITCH_LOCAL, &etr_events))
+		eacr.es = eacr.sl = 0;
+	if (test_and_clear_bit(ETR_EVENT_PORT_ALERT, &etr_events))
+		etr_port0_uptodate = etr_port1_uptodate = 0;
+
+	if (test_and_clear_bit(ETR_EVENT_PORT0_CHANGE, &etr_events)) {
+		if (eacr.e0)
+			/*
+			 * Port change of an enabled port. We have to
+			 * assume that this can have caused an stepping
+			 * port switch.
+			 */
+			etr_tolec = get_tod_clock();
+		eacr.p0 = etr_port0_online;
+		if (!eacr.p0)
+			eacr.e0 = 0;
+		etr_port0_uptodate = 0;
+	}
+	if (test_and_clear_bit(ETR_EVENT_PORT1_CHANGE, &etr_events)) {
+		if (eacr.e1)
+			/*
+			 * Port change of an enabled port. We have to
+			 * assume that this can have caused an stepping
+			 * port switch.
+			 */
+			etr_tolec = get_tod_clock();
+		eacr.p1 = etr_port1_online;
+		if (!eacr.p1)
+			eacr.e1 = 0;
+		etr_port1_uptodate = 0;
+	}
+	clear_bit(ETR_EVENT_UPDATE, &etr_events);
+	return eacr;
+}
+
+/*
+ * Set up a timer that expires after the etr_tolec + 1.6 seconds if
+ * one of the ports needs an update.
+ */
+static void etr_set_tolec_timeout(unsigned long long now)
+{
+	unsigned long micros;
+
+	if ((!etr_eacr.p0 || etr_port0_uptodate) &&
+	    (!etr_eacr.p1 || etr_port1_uptodate))
+		return;
+	micros = (now > etr_tolec) ? ((now - etr_tolec) >> 12) : 0;
+	micros = (micros > 1600000) ? 0 : 1600000 - micros;
+	mod_timer(&etr_timer, jiffies + (micros * HZ) / 1000000 + 1);
+}
+
+/*
+ * Set up a time that expires after 1/2 second.
+ */
+static void etr_set_sync_timeout(void)
+{
+	mod_timer(&etr_timer, jiffies + HZ/2);
+}
+
+/*
+ * Update the aib information for one or both ports.
+ */
+static struct etr_eacr etr_handle_update(struct etr_aib *aib,
+					 struct etr_eacr eacr)
+{
+	/* With both ports disabled the aib information is useless. */
+	if (!eacr.e0 && !eacr.e1)
+		return eacr;
+
+	/* Update port0 or port1 with aib stored in etr_work_fn. */
+	if (aib->esw.q == 0) {
+		/* Information for port 0 stored. */
+		if (eacr.p0 && !etr_port0_uptodate) {
+			etr_port0 = *aib;
+			if (etr_port0_online)
+				etr_port0_uptodate = 1;
+		}
+	} else {
+		/* Information for port 1 stored. */
+		if (eacr.p1 && !etr_port1_uptodate) {
+			etr_port1 = *aib;
+			if (etr_port0_online)
+				etr_port1_uptodate = 1;
+		}
+	}
+
+	/*
+	 * Do not try to get the alternate port aib if the clock
+	 * is not in sync yet.
+	 */
+	if (!eacr.es || !check_sync_clock())
+		return eacr;
+
+	/*
+	 * If steai is available we can get the information about
+	 * the other port immediately. If only stetr is available the
+	 * data-port bit toggle has to be used.
+	 */
+	if (etr_steai_available) {
+		if (eacr.p0 && !etr_port0_uptodate) {
+			etr_steai_cv(&etr_port0, ETR_STEAI_PORT_0);
+			etr_port0_uptodate = 1;
+		}
+		if (eacr.p1 && !etr_port1_uptodate) {
+			etr_steai_cv(&etr_port1, ETR_STEAI_PORT_1);
+			etr_port1_uptodate = 1;
+		}
+	} else {
+		/*
+		 * One port was updated above, if the other
+		 * port is not uptodate toggle dp bit.
+		 */
+		if ((eacr.p0 && !etr_port0_uptodate) ||
+		    (eacr.p1 && !etr_port1_uptodate))
+			eacr.dp ^= 1;
+		else
+			eacr.dp = 0;
+	}
+	return eacr;
+}
+
+/*
+ * Write new etr control register if it differs from the current one.
+ * Return 1 if etr_tolec has been updated as well.
+ */
+static void etr_update_eacr(struct etr_eacr eacr)
+{
+	int dp_changed;
+
+	if (memcmp(&etr_eacr, &eacr, sizeof(eacr)) == 0)
+		/* No change, return. */
+		return;
+	/*
+	 * The disable of an active port of the change of the data port
+	 * bit can/will cause a change in the data port.
+	 */
+	dp_changed = etr_eacr.e0 > eacr.e0 || etr_eacr.e1 > eacr.e1 ||
+		(etr_eacr.dp ^ eacr.dp) != 0;
+	etr_eacr = eacr;
+	etr_setr(&etr_eacr);
+	if (dp_changed)
+		etr_tolec = get_tod_clock();
+}
+
+/*
+ * ETR work. In this function you'll find the main logic. In
+ * particular this is the only function that calls etr_update_eacr(),
+ * it "controls" the etr control register.
+ */
+static void etr_work_fn(struct work_struct *work)
+{
+	unsigned long long now;
+	struct etr_eacr eacr;
+	struct etr_aib aib;
+	int sync_port;
+
+	/* prevent multiple execution. */
+	mutex_lock(&etr_work_mutex);
+
+	/* Create working copy of etr_eacr. */
+	eacr = etr_eacr;
+
+	/* Check for the different events and their immediate effects. */
+	eacr = etr_handle_events(eacr);
+
+	/* Check if ETR is supposed to be active. */
+	eacr.ea = eacr.p0 || eacr.p1;
+	if (!eacr.ea) {
+		/* Both ports offline. Reset everything. */
+		eacr.dp = eacr.es = eacr.sl = 0;
+		on_each_cpu(disable_sync_clock, NULL, 1);
+		del_timer_sync(&etr_timer);
+		etr_update_eacr(eacr);
+		goto out_unlock;
+	}
+
+	/* Store aib to get the current ETR status word. */
+	BUG_ON(etr_stetr(&aib) != 0);
+	etr_port0.esw = etr_port1.esw = aib.esw;	/* Copy status word. */
+	now = get_tod_clock();
+
+	/*
+	 * Update the port information if the last stepping port change
+	 * or data port change is older than 1.6 seconds.
+	 */
+	if (now >= etr_tolec + (1600000 << 12))
+		eacr = etr_handle_update(&aib, eacr);
+
+	/*
+	 * Select ports to enable. The preferred synchronization mode is PPS.
+	 * If a port can be enabled depends on a number of things:
+	 * 1) The port needs to be online and uptodate. A port is not
+	 *    disabled just because it is not uptodate, but it is only
+	 *    enabled if it is uptodate.
+	 * 2) The port needs to have the same mode (pps / etr).
+	 * 3) The port needs to be usable -> etr_port_valid() == 1
+	 * 4) To enable the second port the clock needs to be in sync.
+	 * 5) If both ports are useable and are ETR ports, the network id
+	 *    has to be the same.
+	 * The eacr.sl bit is used to indicate etr mode vs. pps mode.
+	 */
+	if (eacr.p0 && aib.esw.psc0 == etr_lpsc_pps_mode) {
+		eacr.sl = 0;
+		eacr.e0 = 1;
+		if (!etr_mode_is_pps(etr_eacr))
+			eacr.es = 0;
+		if (!eacr.es || !eacr.p1 || aib.esw.psc1 != etr_lpsc_pps_mode)
+			eacr.e1 = 0;
+		// FIXME: uptodate checks ?
+		else if (etr_port0_uptodate && etr_port1_uptodate)
+			eacr.e1 = 1;
+		sync_port = (etr_port0_uptodate &&
+			     etr_port_valid(&etr_port0, 0)) ? 0 : -1;
+	} else if (eacr.p1 && aib.esw.psc1 == etr_lpsc_pps_mode) {
+		eacr.sl = 0;
+		eacr.e0 = 0;
+		eacr.e1 = 1;
+		if (!etr_mode_is_pps(etr_eacr))
+			eacr.es = 0;
+		sync_port = (etr_port1_uptodate &&
+			     etr_port_valid(&etr_port1, 1)) ? 1 : -1;
+	} else if (eacr.p0 && aib.esw.psc0 == etr_lpsc_operational_step) {
+		eacr.sl = 1;
+		eacr.e0 = 1;
+		if (!etr_mode_is_etr(etr_eacr))
+			eacr.es = 0;
+		if (!eacr.es || !eacr.p1 ||
+		    aib.esw.psc1 != etr_lpsc_operational_alt)
+			eacr.e1 = 0;
+		else if (etr_port0_uptodate && etr_port1_uptodate &&
+			 etr_compare_network(&etr_port0, &etr_port1))
+			eacr.e1 = 1;
+		sync_port = (etr_port0_uptodate &&
+			     etr_port_valid(&etr_port0, 0)) ? 0 : -1;
+	} else if (eacr.p1 && aib.esw.psc1 == etr_lpsc_operational_step) {
+		eacr.sl = 1;
+		eacr.e0 = 0;
+		eacr.e1 = 1;
+		if (!etr_mode_is_etr(etr_eacr))
+			eacr.es = 0;
+		sync_port = (etr_port1_uptodate &&
+			     etr_port_valid(&etr_port1, 1)) ? 1 : -1;
+	} else {
+		/* Both ports not usable. */
+		eacr.es = eacr.sl = 0;
+		sync_port = -1;
+	}
+
+	/*
+	 * If the clock is in sync just update the eacr and return.
+	 * If there is no valid sync port wait for a port update.
+	 */
+	if ((eacr.es && check_sync_clock()) || sync_port < 0) {
+		etr_update_eacr(eacr);
+		etr_set_tolec_timeout(now);
+		goto out_unlock;
+	}
+
+	/*
+	 * Prepare control register for clock syncing
+	 * (reset data port bit, set sync check control.
+	 */
+	eacr.dp = 0;
+	eacr.es = 1;
+
+	/*
+	 * Update eacr and try to synchronize the clock. If the update
+	 * of eacr caused a stepping port switch (or if we have to
+	 * assume that a stepping port switch has occurred) or the
+	 * clock syncing failed, reset the sync check control bit
+	 * and set up a timer to try again after 0.5 seconds
+	 */
+	etr_update_eacr(eacr);
+	if (now < etr_tolec + (1600000 << 12) ||
+	    etr_sync_clock_stop(&aib, sync_port) != 0) {
+		/* Sync failed. Try again in 1/2 second. */
+		eacr.es = 0;
+		etr_update_eacr(eacr);
+		etr_set_sync_timeout();
+	} else
+		etr_set_tolec_timeout(now);
+out_unlock:
+	mutex_unlock(&etr_work_mutex);
+}
+
+/*
+ * Sysfs interface functions
+ */
+static struct bus_type etr_subsys = {
+	.name		= "etr",
+	.dev_name	= "etr",
+};
+
+static struct device etr_port0_dev = {
+	.id	= 0,
+	.bus	= &etr_subsys,
+};
+
+static struct device etr_port1_dev = {
+	.id	= 1,
+	.bus	= &etr_subsys,
+};
+
+/*
+ * ETR subsys attributes
+ */
+static ssize_t etr_stepping_port_show(struct device *dev,
+					struct device_attribute *attr,
+					char *buf)
+{
+	return sprintf(buf, "%i\n", etr_port0.esw.p);
+}
+
+static DEVICE_ATTR(stepping_port, 0400, etr_stepping_port_show, NULL);
+
+static ssize_t etr_stepping_mode_show(struct device *dev,
+					struct device_attribute *attr,
+					char *buf)
+{
+	char *mode_str;
+
+	if (etr_mode_is_pps(etr_eacr))
+		mode_str = "pps";
+	else if (etr_mode_is_etr(etr_eacr))
+		mode_str = "etr";
+	else
+		mode_str = "local";
+	return sprintf(buf, "%s\n", mode_str);
+}
+
+static DEVICE_ATTR(stepping_mode, 0400, etr_stepping_mode_show, NULL);
+
+/*
+ * ETR port attributes
+ */
+static inline struct etr_aib *etr_aib_from_dev(struct device *dev)
+{
+	if (dev == &etr_port0_dev)
+		return etr_port0_online ? &etr_port0 : NULL;
+	else
+		return etr_port1_online ? &etr_port1 : NULL;
+}
+
+static ssize_t etr_online_show(struct device *dev,
+				struct device_attribute *attr,
+				char *buf)
+{
+	unsigned int online;
+
+	online = (dev == &etr_port0_dev) ? etr_port0_online : etr_port1_online;
+	return sprintf(buf, "%i\n", online);
+}
+
+static ssize_t etr_online_store(struct device *dev,
+				struct device_attribute *attr,
+				const char *buf, size_t count)
+{
+	unsigned int value;
+
+	value = simple_strtoul(buf, NULL, 0);
+	if (value != 0 && value != 1)
+		return -EINVAL;
+	if (!test_bit(CLOCK_SYNC_HAS_ETR, &clock_sync_flags))
+		return -EOPNOTSUPP;
+	mutex_lock(&clock_sync_mutex);
+	if (dev == &etr_port0_dev) {
+		if (etr_port0_online == value)
+			goto out;	/* Nothing to do. */
+		etr_port0_online = value;
+		if (etr_port0_online && etr_port1_online)
+			set_bit(CLOCK_SYNC_ETR, &clock_sync_flags);
+		else
+			clear_bit(CLOCK_SYNC_ETR, &clock_sync_flags);
+		set_bit(ETR_EVENT_PORT0_CHANGE, &etr_events);
+		queue_work(time_sync_wq, &etr_work);
+	} else {
+		if (etr_port1_online == value)
+			goto out;	/* Nothing to do. */
+		etr_port1_online = value;
+		if (etr_port0_online && etr_port1_online)
+			set_bit(CLOCK_SYNC_ETR, &clock_sync_flags);
+		else
+			clear_bit(CLOCK_SYNC_ETR, &clock_sync_flags);
+		set_bit(ETR_EVENT_PORT1_CHANGE, &etr_events);
+		queue_work(time_sync_wq, &etr_work);
+	}
+out:
+	mutex_unlock(&clock_sync_mutex);
+	return count;
+}
+
+static DEVICE_ATTR(online, 0600, etr_online_show, etr_online_store);
+
+static ssize_t etr_stepping_control_show(struct device *dev,
+					struct device_attribute *attr,
+					char *buf)
+{
+	return sprintf(buf, "%i\n", (dev == &etr_port0_dev) ?
+		       etr_eacr.e0 : etr_eacr.e1);
+}
+
+static DEVICE_ATTR(stepping_control, 0400, etr_stepping_control_show, NULL);
+
+static ssize_t etr_mode_code_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	if (!etr_port0_online && !etr_port1_online)
+		/* Status word is not uptodate if both ports are offline. */
+		return -ENODATA;
+	return sprintf(buf, "%i\n", (dev == &etr_port0_dev) ?
+		       etr_port0.esw.psc0 : etr_port0.esw.psc1);
+}
+
+static DEVICE_ATTR(state_code, 0400, etr_mode_code_show, NULL);
+
+static ssize_t etr_untuned_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	struct etr_aib *aib = etr_aib_from_dev(dev);
+
+	if (!aib || !aib->slsw.v1)
+		return -ENODATA;
+	return sprintf(buf, "%i\n", aib->edf1.u);
+}
+
+static DEVICE_ATTR(untuned, 0400, etr_untuned_show, NULL);
+
+static ssize_t etr_network_id_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	struct etr_aib *aib = etr_aib_from_dev(dev);
+
+	if (!aib || !aib->slsw.v1)
+		return -ENODATA;
+	return sprintf(buf, "%i\n", aib->edf1.net_id);
+}
+
+static DEVICE_ATTR(network, 0400, etr_network_id_show, NULL);
+
+static ssize_t etr_id_show(struct device *dev,
+			struct device_attribute *attr, char *buf)
+{
+	struct etr_aib *aib = etr_aib_from_dev(dev);
+
+	if (!aib || !aib->slsw.v1)
+		return -ENODATA;
+	return sprintf(buf, "%i\n", aib->edf1.etr_id);
+}
+
+static DEVICE_ATTR(id, 0400, etr_id_show, NULL);
+
+static ssize_t etr_port_number_show(struct device *dev,
+			struct device_attribute *attr, char *buf)
+{
+	struct etr_aib *aib = etr_aib_from_dev(dev);
+
+	if (!aib || !aib->slsw.v1)
+		return -ENODATA;
+	return sprintf(buf, "%i\n", aib->edf1.etr_pn);
+}
+
+static DEVICE_ATTR(port, 0400, etr_port_number_show, NULL);
+
+static ssize_t etr_coupled_show(struct device *dev,
+			struct device_attribute *attr, char *buf)
+{
+	struct etr_aib *aib = etr_aib_from_dev(dev);
+
+	if (!aib || !aib->slsw.v3)
+		return -ENODATA;
+	return sprintf(buf, "%i\n", aib->edf3.c);
+}
+
+static DEVICE_ATTR(coupled, 0400, etr_coupled_show, NULL);
+
+static ssize_t etr_local_time_show(struct device *dev,
+			struct device_attribute *attr, char *buf)
+{
+	struct etr_aib *aib = etr_aib_from_dev(dev);
+
+	if (!aib || !aib->slsw.v3)
+		return -ENODATA;
+	return sprintf(buf, "%i\n", aib->edf3.blto);
+}
+
+static DEVICE_ATTR(local_time, 0400, etr_local_time_show, NULL);
+
+static ssize_t etr_utc_offset_show(struct device *dev,
+			struct device_attribute *attr, char *buf)
+{
+	struct etr_aib *aib = etr_aib_from_dev(dev);
+
+	if (!aib || !aib->slsw.v3)
+		return -ENODATA;
+	return sprintf(buf, "%i\n", aib->edf3.buo);
+}
+
+static DEVICE_ATTR(utc_offset, 0400, etr_utc_offset_show, NULL);
+
+static struct device_attribute *etr_port_attributes[] = {
+	&dev_attr_online,
+	&dev_attr_stepping_control,
+	&dev_attr_state_code,
+	&dev_attr_untuned,
+	&dev_attr_network,
+	&dev_attr_id,
+	&dev_attr_port,
+	&dev_attr_coupled,
+	&dev_attr_local_time,
+	&dev_attr_utc_offset,
+	NULL
+};
+
+static int __init etr_register_port(struct device *dev)
+{
+	struct device_attribute **attr;
+	int rc;
+
+	rc = device_register(dev);
+	if (rc)
+		goto out;
+	for (attr = etr_port_attributes; *attr; attr++) {
+		rc = device_create_file(dev, *attr);
+		if (rc)
+			goto out_unreg;
+	}
+	return 0;
+out_unreg:
+	for (; attr >= etr_port_attributes; attr--)
+		device_remove_file(dev, *attr);
+	device_unregister(dev);
+out:
+	return rc;
+}
+
+static void __init etr_unregister_port(struct device *dev)
+{
+	struct device_attribute **attr;
+
+	for (attr = etr_port_attributes; *attr; attr++)
+		device_remove_file(dev, *attr);
+	device_unregister(dev);
+}
+
+static int __init etr_init_sysfs(void)
+{
+	int rc;
+
+	rc = subsys_system_register(&etr_subsys, NULL);
+	if (rc)
+		goto out;
+	rc = device_create_file(etr_subsys.dev_root, &dev_attr_stepping_port);
+	if (rc)
+		goto out_unreg_subsys;
+	rc = device_create_file(etr_subsys.dev_root, &dev_attr_stepping_mode);
+	if (rc)
+		goto out_remove_stepping_port;
+	rc = etr_register_port(&etr_port0_dev);
+	if (rc)
+		goto out_remove_stepping_mode;
+	rc = etr_register_port(&etr_port1_dev);
+	if (rc)
+		goto out_remove_port0;
+	return 0;
+
+out_remove_port0:
+	etr_unregister_port(&etr_port0_dev);
+out_remove_stepping_mode:
+	device_remove_file(etr_subsys.dev_root, &dev_attr_stepping_mode);
+out_remove_stepping_port:
+	device_remove_file(etr_subsys.dev_root, &dev_attr_stepping_port);
+out_unreg_subsys:
+	bus_unregister(&etr_subsys);
+out:
+	return rc;
+}
+
+device_initcall(etr_init_sysfs);
+
+/*
+ * Server Time Protocol (STP) code.
+ */
+static int stp_online;
+static struct stp_sstpi stp_info;
+static void *stp_page;
+
+static void stp_work_fn(struct work_struct *work);
+static DEFINE_MUTEX(stp_work_mutex);
+static DECLARE_WORK(stp_work, stp_work_fn);
+static struct timer_list stp_timer;
+
+static int __init early_parse_stp(char *p)
+{
+	if (strncmp(p, "off", 3) == 0)
+		stp_online = 0;
+	else if (strncmp(p, "on", 2) == 0)
+		stp_online = 1;
+	return 0;
+}
+early_param("stp", early_parse_stp);
+
+/*
+ * Reset STP attachment.
+ */
+static void __init stp_reset(void)
+{
+	int rc;
+
+	stp_page = (void *) get_zeroed_page(GFP_ATOMIC);
+	rc = chsc_sstpc(stp_page, STP_OP_CTRL, 0x0000);
+	if (rc == 0)
+		set_bit(CLOCK_SYNC_HAS_STP, &clock_sync_flags);
+	else if (stp_online) {
+		pr_warning("The real or virtual hardware system does "
+			   "not provide an STP interface\n");
+		free_page((unsigned long) stp_page);
+		stp_page = NULL;
+		stp_online = 0;
+	}
+}
+
+static void stp_timeout(unsigned long dummy)
+{
+	queue_work(time_sync_wq, &stp_work);
+}
+
+static int __init stp_init(void)
+{
+	if (!test_bit(CLOCK_SYNC_HAS_STP, &clock_sync_flags))
+		return 0;
+	setup_timer(&stp_timer, stp_timeout, 0UL);
+	time_init_wq();
+	if (!stp_online)
+		return 0;
+	queue_work(time_sync_wq, &stp_work);
+	return 0;
+}
+
+arch_initcall(stp_init);
+
+/*
+ * STP timing alert. There are three causes:
+ * 1) timing status change
+ * 2) link availability change
+ * 3) time control parameter change
+ * In all three cases we are only interested in the clock source state.
+ * If a STP clock source is now available use it.
+ */
+static void stp_timing_alert(struct stp_irq_parm *intparm)
+{
+	if (intparm->tsc || intparm->lac || intparm->tcpc)
+		queue_work(time_sync_wq, &stp_work);
+}
+
+/*
+ * STP sync check machine check. This is called when the timing state
+ * changes from the synchronized state to the unsynchronized state.
+ * After a STP sync check the clock is not in sync. The machine check
+ * is broadcasted to all cpus at the same time.
+ */
+void stp_sync_check(void)
+{
+	disable_sync_clock(NULL);
+	queue_work(time_sync_wq, &stp_work);
+}
+
+/*
+ * STP island condition machine check. This is called when an attached
+ * server  attempts to communicate over an STP link and the servers
+ * have matching CTN ids and have a valid stratum-1 configuration
+ * but the configurations do not match.
+ */
+void stp_island_check(void)
+{
+	disable_sync_clock(NULL);
+	queue_work(time_sync_wq, &stp_work);
+}
+
+
+static int stp_sync_clock(void *data)
+{
+	static int first;
+	unsigned long long old_clock, delta;
+	struct clock_sync_data *stp_sync;
+	int rc;
+
+	stp_sync = data;
+
+	if (xchg(&first, 1) == 1) {
+		/* Slave */
+		clock_sync_cpu(stp_sync);
+		return 0;
+	}
+
+	/* Wait until all other cpus entered the sync function. */
+	while (atomic_read(&stp_sync->cpus) != 0)
+		cpu_relax();
+
+	enable_sync_clock();
+
+	rc = 0;
+	if (stp_info.todoff[0] || stp_info.todoff[1] ||
+	    stp_info.todoff[2] || stp_info.todoff[3] ||
+	    stp_info.tmd != 2) {
+		old_clock = get_tod_clock();
+		rc = chsc_sstpc(stp_page, STP_OP_SYNC, 0);
+		if (rc == 0) {
+			delta = adjust_time(old_clock, get_tod_clock(), 0);
+			fixup_clock_comparator(delta);
+			rc = chsc_sstpi(stp_page, &stp_info,
+					sizeof(struct stp_sstpi));
+			if (rc == 0 && stp_info.tmd != 2)
+				rc = -EAGAIN;
+		}
+	}
+	if (rc) {
+		disable_sync_clock(NULL);
+		stp_sync->in_sync = -EAGAIN;
+	} else
+		stp_sync->in_sync = 1;
+	xchg(&first, 0);
+	return 0;
+}
+
+/*
+ * STP work. Check for the STP state and take over the clock
+ * synchronization if the STP clock source is usable.
+ */
+static void stp_work_fn(struct work_struct *work)
+{
+	struct clock_sync_data stp_sync;
+	int rc;
+
+	/* prevent multiple execution. */
+	mutex_lock(&stp_work_mutex);
+
+	if (!stp_online) {
+		chsc_sstpc(stp_page, STP_OP_CTRL, 0x0000);
+		del_timer_sync(&stp_timer);
+		goto out_unlock;
+	}
+
+	rc = chsc_sstpc(stp_page, STP_OP_CTRL, 0xb0e0);
+	if (rc)
+		goto out_unlock;
+
+	rc = chsc_sstpi(stp_page, &stp_info, sizeof(struct stp_sstpi));
+	if (rc || stp_info.c == 0)
+		goto out_unlock;
+
+	/* Skip synchronization if the clock is already in sync. */
+	if (check_sync_clock())
+		goto out_unlock;
+
+	memset(&stp_sync, 0, sizeof(stp_sync));
+	get_online_cpus();
+	atomic_set(&stp_sync.cpus, num_online_cpus() - 1);
+	stop_machine(stp_sync_clock, &stp_sync, cpu_online_mask);
+	put_online_cpus();
+
+	if (!check_sync_clock())
+		/*
+		 * There is a usable clock but the synchonization failed.
+		 * Retry after a second.
+		 */
+		mod_timer(&stp_timer, jiffies + HZ);
+
+out_unlock:
+	mutex_unlock(&stp_work_mutex);
+}
+
+/*
+ * STP subsys sysfs interface functions
+ */
+static struct bus_type stp_subsys = {
+	.name		= "stp",
+	.dev_name	= "stp",
+};
+
+static ssize_t stp_ctn_id_show(struct device *dev,
+				struct device_attribute *attr,
+				char *buf)
+{
+	if (!stp_online)
+		return -ENODATA;
+	return sprintf(buf, "%016llx\n",
+		       *(unsigned long long *) stp_info.ctnid);
+}
+
+static DEVICE_ATTR(ctn_id, 0400, stp_ctn_id_show, NULL);
+
+static ssize_t stp_ctn_type_show(struct device *dev,
+				struct device_attribute *attr,
+				char *buf)
+{
+	if (!stp_online)
+		return -ENODATA;
+	return sprintf(buf, "%i\n", stp_info.ctn);
+}
+
+static DEVICE_ATTR(ctn_type, 0400, stp_ctn_type_show, NULL);
+
+static ssize_t stp_dst_offset_show(struct device *dev,
+				   struct device_attribute *attr,
+				   char *buf)
+{
+	if (!stp_online || !(stp_info.vbits & 0x2000))
+		return -ENODATA;
+	return sprintf(buf, "%i\n", (int)(s16) stp_info.dsto);
+}
+
+static DEVICE_ATTR(dst_offset, 0400, stp_dst_offset_show, NULL);
+
+static ssize_t stp_leap_seconds_show(struct device *dev,
+					struct device_attribute *attr,
+					char *buf)
+{
+	if (!stp_online || !(stp_info.vbits & 0x8000))
+		return -ENODATA;
+	return sprintf(buf, "%i\n", (int)(s16) stp_info.leaps);
+}
+
+static DEVICE_ATTR(leap_seconds, 0400, stp_leap_seconds_show, NULL);
+
+static ssize_t stp_stratum_show(struct device *dev,
+				struct device_attribute *attr,
+				char *buf)
+{
+	if (!stp_online)
+		return -ENODATA;
+	return sprintf(buf, "%i\n", (int)(s16) stp_info.stratum);
+}
+
+static DEVICE_ATTR(stratum, 0400, stp_stratum_show, NULL);
+
+static ssize_t stp_time_offset_show(struct device *dev,
+				struct device_attribute *attr,
+				char *buf)
+{
+	if (!stp_online || !(stp_info.vbits & 0x0800))
+		return -ENODATA;
+	return sprintf(buf, "%i\n", (int) stp_info.tto);
+}
+
+static DEVICE_ATTR(time_offset, 0400, stp_time_offset_show, NULL);
+
+static ssize_t stp_time_zone_offset_show(struct device *dev,
+				struct device_attribute *attr,
+				char *buf)
+{
+	if (!stp_online || !(stp_info.vbits & 0x4000))
+		return -ENODATA;
+	return sprintf(buf, "%i\n", (int)(s16) stp_info.tzo);
+}
+
+static DEVICE_ATTR(time_zone_offset, 0400,
+			 stp_time_zone_offset_show, NULL);
+
+static ssize_t stp_timing_mode_show(struct device *dev,
+				struct device_attribute *attr,
+				char *buf)
+{
+	if (!stp_online)
+		return -ENODATA;
+	return sprintf(buf, "%i\n", stp_info.tmd);
+}
+
+static DEVICE_ATTR(timing_mode, 0400, stp_timing_mode_show, NULL);
+
+static ssize_t stp_timing_state_show(struct device *dev,
+				struct device_attribute *attr,
+				char *buf)
+{
+	if (!stp_online)
+		return -ENODATA;
+	return sprintf(buf, "%i\n", stp_info.tst);
+}
+
+static DEVICE_ATTR(timing_state, 0400, stp_timing_state_show, NULL);
+
+static ssize_t stp_online_show(struct device *dev,
+				struct device_attribute *attr,
+				char *buf)
+{
+	return sprintf(buf, "%i\n", stp_online);
+}
+
+static ssize_t stp_online_store(struct device *dev,
+				struct device_attribute *attr,
+				const char *buf, size_t count)
+{
+	unsigned int value;
+
+	value = simple_strtoul(buf, NULL, 0);
+	if (value != 0 && value != 1)
+		return -EINVAL;
+	if (!test_bit(CLOCK_SYNC_HAS_STP, &clock_sync_flags))
+		return -EOPNOTSUPP;
+	mutex_lock(&clock_sync_mutex);
+	stp_online = value;
+	if (stp_online)
+		set_bit(CLOCK_SYNC_STP, &clock_sync_flags);
+	else
+		clear_bit(CLOCK_SYNC_STP, &clock_sync_flags);
+	queue_work(time_sync_wq, &stp_work);
+	mutex_unlock(&clock_sync_mutex);
+	return count;
+}
+
+/*
+ * Can't use DEVICE_ATTR because the attribute should be named
+ * stp/online but dev_attr_online already exists in this file ..
+ */
+static struct device_attribute dev_attr_stp_online = {
+	.attr = { .name = "online", .mode = 0600 },
+	.show	= stp_online_show,
+	.store	= stp_online_store,
+};
+
+static struct device_attribute *stp_attributes[] = {
+	&dev_attr_ctn_id,
+	&dev_attr_ctn_type,
+	&dev_attr_dst_offset,
+	&dev_attr_leap_seconds,
+	&dev_attr_stp_online,
+	&dev_attr_stratum,
+	&dev_attr_time_offset,
+	&dev_attr_time_zone_offset,
+	&dev_attr_timing_mode,
+	&dev_attr_timing_state,
+	NULL
+};
+
+static int __init stp_init_sysfs(void)
+{
+	struct device_attribute **attr;
+	int rc;
+
+	rc = subsys_system_register(&stp_subsys, NULL);
+	if (rc)
+		goto out;
+	for (attr = stp_attributes; *attr; attr++) {
+		rc = device_create_file(stp_subsys.dev_root, *attr);
+		if (rc)
+			goto out_unreg;
+	}
+	return 0;
+out_unreg:
+	for (; attr >= stp_attributes; attr--)
+		device_remove_file(stp_subsys.dev_root, *attr);
+	bus_unregister(&stp_subsys);
+out:
+	return rc;
+}
+
+device_initcall(stp_init_sysfs);
diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c
new file mode 100644
index 000000000..5728c5bd4
--- /dev/null
+++ b/arch/s390/kernel/topology.c
@@ -0,0 +1,501 @@
+/*
+ *    Copyright IBM Corp. 2007, 2011
+ *    Author(s): Heiko Carstens <heiko.carstens@de.ibm.com>
+ */
+
+#define KMSG_COMPONENT "cpu"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
+#include <linux/workqueue.h>
+#include <linux/cpuset.h>
+#include <linux/device.h>
+#include <linux/export.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/delay.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/cpu.h>
+#include <linux/smp.h>
+#include <linux/mm.h>
+#include <asm/sysinfo.h>
+
+#define PTF_HORIZONTAL	(0UL)
+#define PTF_VERTICAL	(1UL)
+#define PTF_CHECK	(2UL)
+
+struct mask_info {
+	struct mask_info *next;
+	unsigned char id;
+	cpumask_t mask;
+};
+
+static void set_topology_timer(void);
+static void topology_work_fn(struct work_struct *work);
+static struct sysinfo_15_1_x *tl_info;
+
+static int topology_enabled = 1;
+static DECLARE_WORK(topology_work, topology_work_fn);
+
+/* topology_lock protects the socket and book linked lists */
+static DEFINE_SPINLOCK(topology_lock);
+static struct mask_info socket_info;
+static struct mask_info book_info;
+
+DEFINE_PER_CPU(struct cpu_topology_s390, cpu_topology);
+EXPORT_PER_CPU_SYMBOL_GPL(cpu_topology);
+
+static cpumask_t cpu_group_map(struct mask_info *info, unsigned int cpu)
+{
+	cpumask_t mask;
+
+	cpumask_copy(&mask, cpumask_of(cpu));
+	if (!topology_enabled || !MACHINE_HAS_TOPOLOGY)
+		return mask;
+	for (; info; info = info->next) {
+		if (cpumask_test_cpu(cpu, &info->mask))
+			return info->mask;
+	}
+	return mask;
+}
+
+static cpumask_t cpu_thread_map(unsigned int cpu)
+{
+	cpumask_t mask;
+	int i;
+
+	cpumask_copy(&mask, cpumask_of(cpu));
+	if (!topology_enabled || !MACHINE_HAS_TOPOLOGY)
+		return mask;
+	cpu -= cpu % (smp_cpu_mtid + 1);
+	for (i = 0; i <= smp_cpu_mtid; i++)
+		if (cpu_present(cpu + i))
+			cpumask_set_cpu(cpu + i, &mask);
+	return mask;
+}
+
+static struct mask_info *add_cpus_to_mask(struct topology_core *tl_core,
+					  struct mask_info *book,
+					  struct mask_info *socket,
+					  int one_socket_per_cpu)
+{
+	unsigned int core;
+
+	for_each_set_bit(core, &tl_core->mask[0], TOPOLOGY_CORE_BITS) {
+		unsigned int rcore;
+		int lcpu, i;
+
+		rcore = TOPOLOGY_CORE_BITS - 1 - core + tl_core->origin;
+		lcpu = smp_find_processor_id(rcore << smp_cpu_mt_shift);
+		if (lcpu < 0)
+			continue;
+		for (i = 0; i <= smp_cpu_mtid; i++) {
+			per_cpu(cpu_topology, lcpu + i).book_id = book->id;
+			per_cpu(cpu_topology, lcpu + i).core_id = rcore;
+			per_cpu(cpu_topology, lcpu + i).thread_id = lcpu + i;
+			cpumask_set_cpu(lcpu + i, &book->mask);
+			cpumask_set_cpu(lcpu + i, &socket->mask);
+			if (one_socket_per_cpu)
+				per_cpu(cpu_topology, lcpu + i).socket_id = rcore;
+			else
+				per_cpu(cpu_topology, lcpu + i).socket_id = socket->id;
+			smp_cpu_set_polarization(lcpu + i, tl_core->pp);
+		}
+		if (one_socket_per_cpu)
+			socket = socket->next;
+	}
+	return socket;
+}
+
+static void clear_masks(void)
+{
+	struct mask_info *info;
+
+	info = &socket_info;
+	while (info) {
+		cpumask_clear(&info->mask);
+		info = info->next;
+	}
+	info = &book_info;
+	while (info) {
+		cpumask_clear(&info->mask);
+		info = info->next;
+	}
+}
+
+static union topology_entry *next_tle(union topology_entry *tle)
+{
+	if (!tle->nl)
+		return (union topology_entry *)((struct topology_core *)tle + 1);
+	return (union topology_entry *)((struct topology_container *)tle + 1);
+}
+
+static void __tl_to_masks_generic(struct sysinfo_15_1_x *info)
+{
+	struct mask_info *socket = &socket_info;
+	struct mask_info *book = &book_info;
+	union topology_entry *tle, *end;
+
+	tle = info->tle;
+	end = (union topology_entry *)((unsigned long)info + info->length);
+	while (tle < end) {
+		switch (tle->nl) {
+		case 2:
+			book = book->next;
+			book->id = tle->container.id;
+			break;
+		case 1:
+			socket = socket->next;
+			socket->id = tle->container.id;
+			break;
+		case 0:
+			add_cpus_to_mask(&tle->cpu, book, socket, 0);
+			break;
+		default:
+			clear_masks();
+			return;
+		}
+		tle = next_tle(tle);
+	}
+}
+
+static void __tl_to_masks_z10(struct sysinfo_15_1_x *info)
+{
+	struct mask_info *socket = &socket_info;
+	struct mask_info *book = &book_info;
+	union topology_entry *tle, *end;
+
+	tle = info->tle;
+	end = (union topology_entry *)((unsigned long)info + info->length);
+	while (tle < end) {
+		switch (tle->nl) {
+		case 1:
+			book = book->next;
+			book->id = tle->container.id;
+			break;
+		case 0:
+			socket = add_cpus_to_mask(&tle->cpu, book, socket, 1);
+			break;
+		default:
+			clear_masks();
+			return;
+		}
+		tle = next_tle(tle);
+	}
+}
+
+static void tl_to_masks(struct sysinfo_15_1_x *info)
+{
+	struct cpuid cpu_id;
+
+	spin_lock_irq(&topology_lock);
+	get_cpu_id(&cpu_id);
+	clear_masks();
+	switch (cpu_id.machine) {
+	case 0x2097:
+	case 0x2098:
+		__tl_to_masks_z10(info);
+		break;
+	default:
+		__tl_to_masks_generic(info);
+	}
+	spin_unlock_irq(&topology_lock);
+}
+
+static void topology_update_polarization_simple(void)
+{
+	int cpu;
+
+	mutex_lock(&smp_cpu_state_mutex);
+	for_each_possible_cpu(cpu)
+		smp_cpu_set_polarization(cpu, POLARIZATION_HRZ);
+	mutex_unlock(&smp_cpu_state_mutex);
+}
+
+static int ptf(unsigned long fc)
+{
+	int rc;
+
+	asm volatile(
+		"	.insn	rre,0xb9a20000,%1,%1\n"
+		"	ipm	%0\n"
+		"	srl	%0,28\n"
+		: "=d" (rc)
+		: "d" (fc)  : "cc");
+	return rc;
+}
+
+int topology_set_cpu_management(int fc)
+{
+	int cpu, rc;
+
+	if (!MACHINE_HAS_TOPOLOGY)
+		return -EOPNOTSUPP;
+	if (fc)
+		rc = ptf(PTF_VERTICAL);
+	else
+		rc = ptf(PTF_HORIZONTAL);
+	if (rc)
+		return -EBUSY;
+	for_each_possible_cpu(cpu)
+		smp_cpu_set_polarization(cpu, POLARIZATION_UNKNOWN);
+	return rc;
+}
+
+static void update_cpu_masks(void)
+{
+	unsigned long flags;
+	int cpu;
+
+	spin_lock_irqsave(&topology_lock, flags);
+	for_each_possible_cpu(cpu) {
+		per_cpu(cpu_topology, cpu).thread_mask = cpu_thread_map(cpu);
+		per_cpu(cpu_topology, cpu).core_mask = cpu_group_map(&socket_info, cpu);
+		per_cpu(cpu_topology, cpu).book_mask = cpu_group_map(&book_info, cpu);
+		if (!MACHINE_HAS_TOPOLOGY) {
+			per_cpu(cpu_topology, cpu).thread_id = cpu;
+			per_cpu(cpu_topology, cpu).core_id = cpu;
+			per_cpu(cpu_topology, cpu).socket_id = cpu;
+			per_cpu(cpu_topology, cpu).book_id = cpu;
+		}
+	}
+	spin_unlock_irqrestore(&topology_lock, flags);
+}
+
+void store_topology(struct sysinfo_15_1_x *info)
+{
+	if (topology_max_mnest >= 3)
+		stsi(info, 15, 1, 3);
+	else
+		stsi(info, 15, 1, 2);
+}
+
+int arch_update_cpu_topology(void)
+{
+	struct sysinfo_15_1_x *info = tl_info;
+	struct device *dev;
+	int cpu;
+
+	if (!MACHINE_HAS_TOPOLOGY) {
+		update_cpu_masks();
+		topology_update_polarization_simple();
+		return 0;
+	}
+	store_topology(info);
+	tl_to_masks(info);
+	update_cpu_masks();
+	for_each_online_cpu(cpu) {
+		dev = get_cpu_device(cpu);
+		kobject_uevent(&dev->kobj, KOBJ_CHANGE);
+	}
+	return 1;
+}
+
+static void topology_work_fn(struct work_struct *work)
+{
+	rebuild_sched_domains();
+}
+
+void topology_schedule_update(void)
+{
+	schedule_work(&topology_work);
+}
+
+static void topology_timer_fn(unsigned long ignored)
+{
+	if (ptf(PTF_CHECK))
+		topology_schedule_update();
+	set_topology_timer();
+}
+
+static struct timer_list topology_timer =
+	TIMER_DEFERRED_INITIALIZER(topology_timer_fn, 0, 0);
+
+static atomic_t topology_poll = ATOMIC_INIT(0);
+
+static void set_topology_timer(void)
+{
+	if (atomic_add_unless(&topology_poll, -1, 0))
+		mod_timer(&topology_timer, jiffies + HZ / 10);
+	else
+		mod_timer(&topology_timer, jiffies + HZ * 60);
+}
+
+void topology_expect_change(void)
+{
+	if (!MACHINE_HAS_TOPOLOGY)
+		return;
+	/* This is racy, but it doesn't matter since it is just a heuristic.
+	 * Worst case is that we poll in a higher frequency for a bit longer.
+	 */
+	if (atomic_read(&topology_poll) > 60)
+		return;
+	atomic_add(60, &topology_poll);
+	set_topology_timer();
+}
+
+static int cpu_management;
+
+static ssize_t dispatching_show(struct device *dev,
+				struct device_attribute *attr,
+				char *buf)
+{
+	ssize_t count;
+
+	mutex_lock(&smp_cpu_state_mutex);
+	count = sprintf(buf, "%d\n", cpu_management);
+	mutex_unlock(&smp_cpu_state_mutex);
+	return count;
+}
+
+static ssize_t dispatching_store(struct device *dev,
+				 struct device_attribute *attr,
+				 const char *buf,
+				 size_t count)
+{
+	int val, rc;
+	char delim;
+
+	if (sscanf(buf, "%d %c", &val, &delim) != 1)
+		return -EINVAL;
+	if (val != 0 && val != 1)
+		return -EINVAL;
+	rc = 0;
+	get_online_cpus();
+	mutex_lock(&smp_cpu_state_mutex);
+	if (cpu_management == val)
+		goto out;
+	rc = topology_set_cpu_management(val);
+	if (rc)
+		goto out;
+	cpu_management = val;
+	topology_expect_change();
+out:
+	mutex_unlock(&smp_cpu_state_mutex);
+	put_online_cpus();
+	return rc ? rc : count;
+}
+static DEVICE_ATTR(dispatching, 0644, dispatching_show,
+			 dispatching_store);
+
+static ssize_t cpu_polarization_show(struct device *dev,
+				     struct device_attribute *attr, char *buf)
+{
+	int cpu = dev->id;
+	ssize_t count;
+
+	mutex_lock(&smp_cpu_state_mutex);
+	switch (smp_cpu_get_polarization(cpu)) {
+	case POLARIZATION_HRZ:
+		count = sprintf(buf, "horizontal\n");
+		break;
+	case POLARIZATION_VL:
+		count = sprintf(buf, "vertical:low\n");
+		break;
+	case POLARIZATION_VM:
+		count = sprintf(buf, "vertical:medium\n");
+		break;
+	case POLARIZATION_VH:
+		count = sprintf(buf, "vertical:high\n");
+		break;
+	default:
+		count = sprintf(buf, "unknown\n");
+		break;
+	}
+	mutex_unlock(&smp_cpu_state_mutex);
+	return count;
+}
+static DEVICE_ATTR(polarization, 0444, cpu_polarization_show, NULL);
+
+static struct attribute *topology_cpu_attrs[] = {
+	&dev_attr_polarization.attr,
+	NULL,
+};
+
+static struct attribute_group topology_cpu_attr_group = {
+	.attrs = topology_cpu_attrs,
+};
+
+int topology_cpu_init(struct cpu *cpu)
+{
+	return sysfs_create_group(&cpu->dev.kobj, &topology_cpu_attr_group);
+}
+
+static const struct cpumask *cpu_thread_mask(int cpu)
+{
+	return &per_cpu(cpu_topology, cpu).thread_mask;
+}
+
+
+const struct cpumask *cpu_coregroup_mask(int cpu)
+{
+	return &per_cpu(cpu_topology, cpu).core_mask;
+}
+
+static const struct cpumask *cpu_book_mask(int cpu)
+{
+	return &per_cpu(cpu_topology, cpu).book_mask;
+}
+
+static int __init early_parse_topology(char *p)
+{
+	if (strncmp(p, "off", 3))
+		return 0;
+	topology_enabled = 0;
+	return 0;
+}
+early_param("topology", early_parse_topology);
+
+static struct sched_domain_topology_level s390_topology[] = {
+	{ cpu_thread_mask, cpu_smt_flags, SD_INIT_NAME(SMT) },
+	{ cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) },
+	{ cpu_book_mask, SD_INIT_NAME(BOOK) },
+	{ cpu_cpu_mask, SD_INIT_NAME(DIE) },
+	{ NULL, },
+};
+
+static void __init alloc_masks(struct sysinfo_15_1_x *info,
+			       struct mask_info *mask, int offset)
+{
+	int i, nr_masks;
+
+	nr_masks = info->mag[TOPOLOGY_NR_MAG - offset];
+	for (i = 0; i < info->mnest - offset; i++)
+		nr_masks *= info->mag[TOPOLOGY_NR_MAG - offset - 1 - i];
+	nr_masks = max(nr_masks, 1);
+	for (i = 0; i < nr_masks; i++) {
+		mask->next = kzalloc(sizeof(*mask->next), GFP_KERNEL);
+		mask = mask->next;
+	}
+}
+
+static int __init s390_topology_init(void)
+{
+	struct sysinfo_15_1_x *info;
+	int i;
+
+	if (!MACHINE_HAS_TOPOLOGY)
+		return 0;
+	tl_info = (struct sysinfo_15_1_x *)__get_free_page(GFP_KERNEL);
+	info = tl_info;
+	store_topology(info);
+	pr_info("The CPU configuration topology of the machine is:");
+	for (i = 0; i < TOPOLOGY_NR_MAG; i++)
+		printk(KERN_CONT " %d", info->mag[i]);
+	printk(KERN_CONT " / %d\n", info->mnest);
+	alloc_masks(info, &socket_info, 1);
+	alloc_masks(info, &book_info, 2);
+	set_sched_topology(s390_topology);
+	return 0;
+}
+early_initcall(s390_topology_init);
+
+static int __init topology_init(void)
+{
+	if (MACHINE_HAS_TOPOLOGY)
+		set_topology_timer();
+	else
+		topology_update_polarization_simple();
+	return device_create_file(cpu_subsys.dev_root, &dev_attr_dispatching);
+}
+device_initcall(topology_init);
diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c
new file mode 100644
index 000000000..4d96c9f53
--- /dev/null
+++ b/arch/s390/kernel/traps.c
@@ -0,0 +1,342 @@
+/*
+ *  S390 version
+ *    Copyright IBM Corp. 1999, 2000
+ *    Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com),
+ *               Denis Joseph Barrow (djbarrow@de.ibm.com,barrow_dj@yahoo.com),
+ *
+ *  Derived from "arch/i386/kernel/traps.c"
+ *    Copyright (C) 1991, 1992 Linus Torvalds
+ */
+
+/*
+ * 'Traps.c' handles hardware traps and faults after we have saved some
+ * state in 'asm.s'.
+ */
+#include <linux/kprobes.h>
+#include <linux/kdebug.h>
+#include <linux/module.h>
+#include <linux/ptrace.h>
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <asm/switch_to.h>
+#include "entry.h"
+
+int show_unhandled_signals = 1;
+
+static inline void __user *get_trap_ip(struct pt_regs *regs)
+{
+	unsigned long address;
+
+	if (regs->int_code & 0x200)
+		address = *(unsigned long *)(current->thread.trap_tdb + 24);
+	else
+		address = regs->psw.addr;
+	return (void __user *)
+		((address - (regs->int_code >> 16)) & PSW_ADDR_INSN);
+}
+
+static inline void report_user_fault(struct pt_regs *regs, int signr)
+{
+	if ((task_pid_nr(current) > 1) && !show_unhandled_signals)
+		return;
+	if (!unhandled_signal(current, signr))
+		return;
+	if (!printk_ratelimit())
+		return;
+	printk("User process fault: interruption code %04x ilc:%d ",
+	       regs->int_code & 0xffff, regs->int_code >> 17);
+	print_vma_addr("in ", regs->psw.addr & PSW_ADDR_INSN);
+	printk("\n");
+	show_regs(regs);
+}
+
+int is_valid_bugaddr(unsigned long addr)
+{
+	return 1;
+}
+
+void do_report_trap(struct pt_regs *regs, int si_signo, int si_code, char *str)
+{
+	siginfo_t info;
+
+	if (user_mode(regs)) {
+		info.si_signo = si_signo;
+		info.si_errno = 0;
+		info.si_code = si_code;
+		info.si_addr = get_trap_ip(regs);
+		force_sig_info(si_signo, &info, current);
+		report_user_fault(regs, si_signo);
+        } else {
+                const struct exception_table_entry *fixup;
+                fixup = search_exception_tables(regs->psw.addr & PSW_ADDR_INSN);
+                if (fixup)
+			regs->psw.addr = extable_fixup(fixup) | PSW_ADDR_AMODE;
+		else {
+			enum bug_trap_type btt;
+
+			btt = report_bug(regs->psw.addr & PSW_ADDR_INSN, regs);
+			if (btt == BUG_TRAP_TYPE_WARN)
+				return;
+			die(regs, str);
+		}
+        }
+}
+
+static void do_trap(struct pt_regs *regs, int si_signo, int si_code, char *str)
+{
+	if (notify_die(DIE_TRAP, str, regs, 0,
+		       regs->int_code, si_signo) == NOTIFY_STOP)
+		return;
+	do_report_trap(regs, si_signo, si_code, str);
+}
+NOKPROBE_SYMBOL(do_trap);
+
+void do_per_trap(struct pt_regs *regs)
+{
+	siginfo_t info;
+
+	if (notify_die(DIE_SSTEP, "sstep", regs, 0, 0, SIGTRAP) == NOTIFY_STOP)
+		return;
+	if (!current->ptrace)
+		return;
+	info.si_signo = SIGTRAP;
+	info.si_errno = 0;
+	info.si_code = TRAP_HWBKPT;
+	info.si_addr =
+		(void __force __user *) current->thread.per_event.address;
+	force_sig_info(SIGTRAP, &info, current);
+}
+NOKPROBE_SYMBOL(do_per_trap);
+
+void default_trap_handler(struct pt_regs *regs)
+{
+	if (user_mode(regs)) {
+		report_user_fault(regs, SIGSEGV);
+		do_exit(SIGSEGV);
+	} else
+		die(regs, "Unknown program exception");
+}
+
+#define DO_ERROR_INFO(name, signr, sicode, str) \
+void name(struct pt_regs *regs)			\
+{						\
+	do_trap(regs, signr, sicode, str);	\
+}
+
+DO_ERROR_INFO(addressing_exception, SIGILL, ILL_ILLADR,
+	      "addressing exception")
+DO_ERROR_INFO(execute_exception, SIGILL, ILL_ILLOPN,
+	      "execute exception")
+DO_ERROR_INFO(divide_exception, SIGFPE, FPE_INTDIV,
+	      "fixpoint divide exception")
+DO_ERROR_INFO(overflow_exception, SIGFPE, FPE_INTOVF,
+	      "fixpoint overflow exception")
+DO_ERROR_INFO(hfp_overflow_exception, SIGFPE, FPE_FLTOVF,
+	      "HFP overflow exception")
+DO_ERROR_INFO(hfp_underflow_exception, SIGFPE, FPE_FLTUND,
+	      "HFP underflow exception")
+DO_ERROR_INFO(hfp_significance_exception, SIGFPE, FPE_FLTRES,
+	      "HFP significance exception")
+DO_ERROR_INFO(hfp_divide_exception, SIGFPE, FPE_FLTDIV,
+	      "HFP divide exception")
+DO_ERROR_INFO(hfp_sqrt_exception, SIGFPE, FPE_FLTINV,
+	      "HFP square root exception")
+DO_ERROR_INFO(operand_exception, SIGILL, ILL_ILLOPN,
+	      "operand exception")
+DO_ERROR_INFO(privileged_op, SIGILL, ILL_PRVOPC,
+	      "privileged operation")
+DO_ERROR_INFO(special_op_exception, SIGILL, ILL_ILLOPN,
+	      "special operation exception")
+DO_ERROR_INFO(transaction_exception, SIGILL, ILL_ILLOPN,
+	      "transaction constraint exception")
+
+static inline void do_fp_trap(struct pt_regs *regs, int fpc)
+{
+	int si_code = 0;
+	/* FPC[2] is Data Exception Code */
+	if ((fpc & 0x00000300) == 0) {
+		/* bits 6 and 7 of DXC are 0 iff IEEE exception */
+		if (fpc & 0x8000) /* invalid fp operation */
+			si_code = FPE_FLTINV;
+		else if (fpc & 0x4000) /* div by 0 */
+			si_code = FPE_FLTDIV;
+		else if (fpc & 0x2000) /* overflow */
+			si_code = FPE_FLTOVF;
+		else if (fpc & 0x1000) /* underflow */
+			si_code = FPE_FLTUND;
+		else if (fpc & 0x0800) /* inexact */
+			si_code = FPE_FLTRES;
+	}
+	do_trap(regs, SIGFPE, si_code, "floating point exception");
+}
+
+void translation_exception(struct pt_regs *regs)
+{
+	/* May never happen. */
+	panic("Translation exception");
+}
+
+void illegal_op(struct pt_regs *regs)
+{
+	siginfo_t info;
+        __u8 opcode[6];
+	__u16 __user *location;
+	int is_uprobe_insn = 0;
+	int signal = 0;
+
+	location = get_trap_ip(regs);
+
+	if (user_mode(regs)) {
+		if (get_user(*((__u16 *) opcode), (__u16 __user *) location))
+			return;
+		if (*((__u16 *) opcode) == S390_BREAKPOINT_U16) {
+			if (current->ptrace) {
+				info.si_signo = SIGTRAP;
+				info.si_errno = 0;
+				info.si_code = TRAP_BRKPT;
+				info.si_addr = location;
+				force_sig_info(SIGTRAP, &info, current);
+			} else
+				signal = SIGILL;
+#ifdef CONFIG_UPROBES
+		} else if (*((__u16 *) opcode) == UPROBE_SWBP_INSN) {
+			is_uprobe_insn = 1;
+#endif
+		} else
+			signal = SIGILL;
+	}
+	/*
+	 * We got either an illegal op in kernel mode, or user space trapped
+	 * on a uprobes illegal instruction. See if kprobes or uprobes picks
+	 * it up. If not, SIGILL.
+	 */
+	if (is_uprobe_insn || !user_mode(regs)) {
+		if (notify_die(DIE_BPT, "bpt", regs, 0,
+			       3, SIGTRAP) != NOTIFY_STOP)
+			signal = SIGILL;
+	}
+	if (signal)
+		do_trap(regs, signal, ILL_ILLOPC, "illegal operation");
+}
+NOKPROBE_SYMBOL(illegal_op);
+
+DO_ERROR_INFO(specification_exception, SIGILL, ILL_ILLOPN,
+	      "specification exception");
+
+int alloc_vector_registers(struct task_struct *tsk)
+{
+	__vector128 *vxrs;
+	int i;
+
+	/* Allocate vector register save area. */
+	vxrs = kzalloc(sizeof(__vector128) * __NUM_VXRS,
+		       GFP_KERNEL|__GFP_REPEAT);
+	if (!vxrs)
+		return -ENOMEM;
+	preempt_disable();
+	if (tsk == current)
+		save_fp_regs(tsk->thread.fp_regs.fprs);
+	/* Copy the 16 floating point registers */
+	for (i = 0; i < 16; i++)
+		*(freg_t *) &vxrs[i] = tsk->thread.fp_regs.fprs[i];
+	tsk->thread.vxrs = vxrs;
+	if (tsk == current) {
+		__ctl_set_bit(0, 17);
+		restore_vx_regs(vxrs);
+	}
+	preempt_enable();
+	return 0;
+}
+
+void vector_exception(struct pt_regs *regs)
+{
+	int si_code, vic;
+
+	if (!MACHINE_HAS_VX) {
+		do_trap(regs, SIGILL, ILL_ILLOPN, "illegal operation");
+		return;
+	}
+
+	/* get vector interrupt code from fpc */
+	asm volatile("stfpc %0" : "=m" (current->thread.fp_regs.fpc));
+	vic = (current->thread.fp_regs.fpc & 0xf00) >> 8;
+	switch (vic) {
+	case 1: /* invalid vector operation */
+		si_code = FPE_FLTINV;
+		break;
+	case 2: /* division by zero */
+		si_code = FPE_FLTDIV;
+		break;
+	case 3: /* overflow */
+		si_code = FPE_FLTOVF;
+		break;
+	case 4: /* underflow */
+		si_code = FPE_FLTUND;
+		break;
+	case 5:	/* inexact */
+		si_code = FPE_FLTRES;
+		break;
+	default: /* unknown cause */
+		si_code = 0;
+	}
+	do_trap(regs, SIGFPE, si_code, "vector exception");
+}
+
+static int __init disable_vector_extension(char *str)
+{
+	S390_lowcore.machine_flags &= ~MACHINE_FLAG_VX;
+	return 1;
+}
+__setup("novx", disable_vector_extension);
+
+void data_exception(struct pt_regs *regs)
+{
+	__u16 __user *location;
+	int signal = 0;
+
+	location = get_trap_ip(regs);
+
+	asm volatile("stfpc %0" : "=m" (current->thread.fp_regs.fpc));
+	/* Check for vector register enablement */
+	if (MACHINE_HAS_VX && !current->thread.vxrs &&
+	    (current->thread.fp_regs.fpc & FPC_DXC_MASK) == 0xfe00) {
+		alloc_vector_registers(current);
+		/* Vector data exception is suppressing, rewind psw. */
+		regs->psw.addr = __rewind_psw(regs->psw, regs->int_code >> 16);
+		clear_pt_regs_flag(regs, PIF_PER_TRAP);
+		return;
+	}
+	if (current->thread.fp_regs.fpc & FPC_DXC_MASK)
+		signal = SIGFPE;
+	else
+		signal = SIGILL;
+	if (signal == SIGFPE)
+		do_fp_trap(regs, current->thread.fp_regs.fpc);
+	else if (signal)
+		do_trap(regs, signal, ILL_ILLOPN, "data exception");
+}
+
+void space_switch_exception(struct pt_regs *regs)
+{
+	/* Set user psw back to home space mode. */
+	if (user_mode(regs))
+		regs->psw.mask |= PSW_ASC_HOME;
+	/* Send SIGILL. */
+	do_trap(regs, SIGILL, ILL_PRVOPC, "space switch event");
+}
+
+void kernel_stack_overflow(struct pt_regs *regs)
+{
+	bust_spinlocks(1);
+	printk("Kernel stack overflow.\n");
+	show_regs(regs);
+	bust_spinlocks(0);
+	panic("Corrupt kernel stack, can't continue.");
+}
+NOKPROBE_SYMBOL(kernel_stack_overflow);
+
+void __init trap_init(void)
+{
+	local_mcck_enable();
+}
diff --git a/arch/s390/kernel/uprobes.c b/arch/s390/kernel/uprobes.c
new file mode 100644
index 000000000..66956c09d
--- /dev/null
+++ b/arch/s390/kernel/uprobes.c
@@ -0,0 +1,385 @@
+/*
+ *  User-space Probes (UProbes) for s390
+ *
+ *    Copyright IBM Corp. 2014
+ *    Author(s): Jan Willeke,
+ */
+
+#include <linux/uaccess.h>
+#include <linux/uprobes.h>
+#include <linux/compat.h>
+#include <linux/kdebug.h>
+#include <asm/switch_to.h>
+#include <asm/facility.h>
+#include <asm/kprobes.h>
+#include <asm/dis.h>
+#include "entry.h"
+
+#define	UPROBE_TRAP_NR	UINT_MAX
+
+int arch_uprobe_analyze_insn(struct arch_uprobe *auprobe, struct mm_struct *mm,
+			     unsigned long addr)
+{
+	return probe_is_prohibited_opcode(auprobe->insn);
+}
+
+int arch_uprobe_pre_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
+{
+	if (psw_bits(regs->psw).eaba == PSW_AMODE_24BIT)
+		return -EINVAL;
+	if (!is_compat_task() && psw_bits(regs->psw).eaba == PSW_AMODE_31BIT)
+		return -EINVAL;
+	clear_pt_regs_flag(regs, PIF_PER_TRAP);
+	auprobe->saved_per = psw_bits(regs->psw).r;
+	auprobe->saved_int_code = regs->int_code;
+	regs->int_code = UPROBE_TRAP_NR;
+	regs->psw.addr = current->utask->xol_vaddr;
+	set_tsk_thread_flag(current, TIF_UPROBE_SINGLESTEP);
+	update_cr_regs(current);
+	return 0;
+}
+
+bool arch_uprobe_xol_was_trapped(struct task_struct *tsk)
+{
+	struct pt_regs *regs = task_pt_regs(tsk);
+
+	if (regs->int_code != UPROBE_TRAP_NR)
+		return true;
+	return false;
+}
+
+static int check_per_event(unsigned short cause, unsigned long control,
+			   struct pt_regs *regs)
+{
+	if (!(regs->psw.mask & PSW_MASK_PER))
+		return 0;
+	/* user space single step */
+	if (control == 0)
+		return 1;
+	/* over indication for storage alteration */
+	if ((control & 0x20200000) && (cause & 0x2000))
+		return 1;
+	if (cause & 0x8000) {
+		/* all branches */
+		if ((control & 0x80800000) == 0x80000000)
+			return 1;
+		/* branch into selected range */
+		if (((control & 0x80800000) == 0x80800000) &&
+		    regs->psw.addr >= current->thread.per_user.start &&
+		    regs->psw.addr <= current->thread.per_user.end)
+			return 1;
+	}
+	return 0;
+}
+
+int arch_uprobe_post_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
+{
+	int fixup = probe_get_fixup_type(auprobe->insn);
+	struct uprobe_task *utask = current->utask;
+
+	clear_tsk_thread_flag(current, TIF_UPROBE_SINGLESTEP);
+	update_cr_regs(current);
+	psw_bits(regs->psw).r = auprobe->saved_per;
+	regs->int_code = auprobe->saved_int_code;
+
+	if (fixup & FIXUP_PSW_NORMAL)
+		regs->psw.addr += utask->vaddr - utask->xol_vaddr;
+	if (fixup & FIXUP_RETURN_REGISTER) {
+		int reg = (auprobe->insn[0] & 0xf0) >> 4;
+
+		regs->gprs[reg] += utask->vaddr - utask->xol_vaddr;
+	}
+	if (fixup & FIXUP_BRANCH_NOT_TAKEN) {
+		int ilen = insn_length(auprobe->insn[0] >> 8);
+
+		if (regs->psw.addr - utask->xol_vaddr == ilen)
+			regs->psw.addr = utask->vaddr + ilen;
+	}
+	if (check_per_event(current->thread.per_event.cause,
+			    current->thread.per_user.control, regs)) {
+		/* fix per address */
+		current->thread.per_event.address = utask->vaddr;
+		/* trigger per event */
+		set_pt_regs_flag(regs, PIF_PER_TRAP);
+	}
+	return 0;
+}
+
+int arch_uprobe_exception_notify(struct notifier_block *self, unsigned long val,
+				 void *data)
+{
+	struct die_args *args = data;
+	struct pt_regs *regs = args->regs;
+
+	if (!user_mode(regs))
+		return NOTIFY_DONE;
+	if (regs->int_code & 0x200) /* Trap during transaction */
+		return NOTIFY_DONE;
+	switch (val) {
+	case DIE_BPT:
+		if (uprobe_pre_sstep_notifier(regs))
+			return NOTIFY_STOP;
+		break;
+	case DIE_SSTEP:
+		if (uprobe_post_sstep_notifier(regs))
+			return NOTIFY_STOP;
+	default:
+		break;
+	}
+	return NOTIFY_DONE;
+}
+
+void arch_uprobe_abort_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
+{
+	clear_thread_flag(TIF_UPROBE_SINGLESTEP);
+	regs->int_code = auprobe->saved_int_code;
+	regs->psw.addr = current->utask->vaddr;
+	current->thread.per_event.address = current->utask->vaddr;
+}
+
+unsigned long arch_uretprobe_hijack_return_addr(unsigned long trampoline,
+						struct pt_regs *regs)
+{
+	unsigned long orig;
+
+	orig = regs->gprs[14];
+	regs->gprs[14] = trampoline;
+	return orig;
+}
+
+/* Instruction Emulation */
+
+static void adjust_psw_addr(psw_t *psw, unsigned long len)
+{
+	psw->addr = __rewind_psw(*psw, -len);
+}
+
+#define EMU_ILLEGAL_OP		1
+#define EMU_SPECIFICATION	2
+#define EMU_ADDRESSING		3
+
+#define emu_load_ril(ptr, output)			\
+({							\
+	unsigned int mask = sizeof(*(ptr)) - 1;		\
+	__typeof__(*(ptr)) input;			\
+	int __rc = 0;					\
+							\
+	if (!test_facility(34))				\
+		__rc = EMU_ILLEGAL_OP;			\
+	else if ((u64 __force)ptr & mask)		\
+		__rc = EMU_SPECIFICATION;		\
+	else if (get_user(input, ptr))			\
+		__rc = EMU_ADDRESSING;			\
+	else						\
+		*(output) = input;			\
+	__rc;						\
+})
+
+#define emu_store_ril(regs, ptr, input)			\
+({							\
+	unsigned int mask = sizeof(*(ptr)) - 1;		\
+	__typeof__(ptr) __ptr = (ptr);			\
+	int __rc = 0;					\
+							\
+	if (!test_facility(34))				\
+		__rc = EMU_ILLEGAL_OP;			\
+	else if ((u64 __force)__ptr & mask)		\
+		__rc = EMU_SPECIFICATION;		\
+	else if (put_user(*(input), __ptr))		\
+		__rc = EMU_ADDRESSING;			\
+	if (__rc == 0)					\
+		sim_stor_event(regs,			\
+			       (void __force *)__ptr,	\
+			       mask + 1);		\
+	__rc;						\
+})
+
+#define emu_cmp_ril(regs, ptr, cmp)			\
+({							\
+	unsigned int mask = sizeof(*(ptr)) - 1;		\
+	__typeof__(*(ptr)) input;			\
+	int __rc = 0;					\
+							\
+	if (!test_facility(34))				\
+		__rc = EMU_ILLEGAL_OP;			\
+	else if ((u64 __force)ptr & mask)		\
+		__rc = EMU_SPECIFICATION;		\
+	else if (get_user(input, ptr))			\
+		__rc = EMU_ADDRESSING;			\
+	else if (input > *(cmp))			\
+		psw_bits((regs)->psw).cc = 1;		\
+	else if (input < *(cmp))			\
+		psw_bits((regs)->psw).cc = 2;		\
+	else						\
+		psw_bits((regs)->psw).cc = 0;		\
+	__rc;						\
+})
+
+struct insn_ril {
+	u8 opc0;
+	u8 reg	: 4;
+	u8 opc1 : 4;
+	s32 disp;
+} __packed;
+
+union split_register {
+	u64 u64;
+	u32 u32[2];
+	u16 u16[4];
+	s64 s64;
+	s32 s32[2];
+	s16 s16[4];
+};
+
+/*
+ * If user per registers are setup to trace storage alterations and an
+ * emulated store took place on a fitting address a user trap is generated.
+ */
+static void sim_stor_event(struct pt_regs *regs, void *addr, int len)
+{
+	if (!(regs->psw.mask & PSW_MASK_PER))
+		return;
+	if (!(current->thread.per_user.control & PER_EVENT_STORE))
+		return;
+	if ((void *)current->thread.per_user.start > (addr + len))
+		return;
+	if ((void *)current->thread.per_user.end < addr)
+		return;
+	current->thread.per_event.address = regs->psw.addr;
+	current->thread.per_event.cause = PER_EVENT_STORE >> 16;
+	set_pt_regs_flag(regs, PIF_PER_TRAP);
+}
+
+/*
+ * pc relative instructions are emulated, since parameters may not be
+ * accessible from the xol area due to range limitations.
+ */
+static void handle_insn_ril(struct arch_uprobe *auprobe, struct pt_regs *regs)
+{
+	union split_register *rx;
+	struct insn_ril *insn;
+	unsigned int ilen;
+	void *uptr;
+	int rc = 0;
+
+	insn = (struct insn_ril *) &auprobe->insn;
+	rx = (union split_register *) &regs->gprs[insn->reg];
+	uptr = (void *)(regs->psw.addr + (insn->disp * 2));
+	ilen = insn_length(insn->opc0);
+
+	switch (insn->opc0) {
+	case 0xc0:
+		switch (insn->opc1) {
+		case 0x00: /* larl */
+			rx->u64 = (unsigned long)uptr;
+			break;
+		}
+		break;
+	case 0xc4:
+		switch (insn->opc1) {
+		case 0x02: /* llhrl */
+			rc = emu_load_ril((u16 __user *)uptr, &rx->u32[1]);
+			break;
+		case 0x04: /* lghrl */
+			rc = emu_load_ril((s16 __user *)uptr, &rx->u64);
+			break;
+		case 0x05: /* lhrl */
+			rc = emu_load_ril((s16 __user *)uptr, &rx->u32[1]);
+			break;
+		case 0x06: /* llghrl */
+			rc = emu_load_ril((u16 __user *)uptr, &rx->u64);
+			break;
+		case 0x08: /* lgrl */
+			rc = emu_load_ril((u64 __user *)uptr, &rx->u64);
+			break;
+		case 0x0c: /* lgfrl */
+			rc = emu_load_ril((s32 __user *)uptr, &rx->u64);
+			break;
+		case 0x0d: /* lrl */
+			rc = emu_load_ril((u32 __user *)uptr, &rx->u32[1]);
+			break;
+		case 0x0e: /* llgfrl */
+			rc = emu_load_ril((u32 __user *)uptr, &rx->u64);
+			break;
+		case 0x07: /* sthrl */
+			rc = emu_store_ril(regs, (u16 __user *)uptr, &rx->u16[3]);
+			break;
+		case 0x0b: /* stgrl */
+			rc = emu_store_ril(regs, (u64 __user *)uptr, &rx->u64);
+			break;
+		case 0x0f: /* strl */
+			rc = emu_store_ril(regs, (u32 __user *)uptr, &rx->u32[1]);
+			break;
+		}
+		break;
+	case 0xc6:
+		switch (insn->opc1) {
+		case 0x02: /* pfdrl */
+			if (!test_facility(34))
+				rc = EMU_ILLEGAL_OP;
+			break;
+		case 0x04: /* cghrl */
+			rc = emu_cmp_ril(regs, (s16 __user *)uptr, &rx->s64);
+			break;
+		case 0x05: /* chrl */
+			rc = emu_cmp_ril(regs, (s16 __user *)uptr, &rx->s32[1]);
+			break;
+		case 0x06: /* clghrl */
+			rc = emu_cmp_ril(regs, (u16 __user *)uptr, &rx->u64);
+			break;
+		case 0x07: /* clhrl */
+			rc = emu_cmp_ril(regs, (u16 __user *)uptr, &rx->u32[1]);
+			break;
+		case 0x08: /* cgrl */
+			rc = emu_cmp_ril(regs, (s64 __user *)uptr, &rx->s64);
+			break;
+		case 0x0a: /* clgrl */
+			rc = emu_cmp_ril(regs, (u64 __user *)uptr, &rx->u64);
+			break;
+		case 0x0c: /* cgfrl */
+			rc = emu_cmp_ril(regs, (s32 __user *)uptr, &rx->s64);
+			break;
+		case 0x0d: /* crl */
+			rc = emu_cmp_ril(regs, (s32 __user *)uptr, &rx->s32[1]);
+			break;
+		case 0x0e: /* clgfrl */
+			rc = emu_cmp_ril(regs, (u32 __user *)uptr, &rx->u64);
+			break;
+		case 0x0f: /* clrl */
+			rc = emu_cmp_ril(regs, (u32 __user *)uptr, &rx->u32[1]);
+			break;
+		}
+		break;
+	}
+	adjust_psw_addr(&regs->psw, ilen);
+	switch (rc) {
+	case EMU_ILLEGAL_OP:
+		regs->int_code = ilen << 16 | 0x0001;
+		do_report_trap(regs, SIGILL, ILL_ILLOPC, NULL);
+		break;
+	case EMU_SPECIFICATION:
+		regs->int_code = ilen << 16 | 0x0006;
+		do_report_trap(regs, SIGILL, ILL_ILLOPC , NULL);
+		break;
+	case EMU_ADDRESSING:
+		regs->int_code = ilen << 16 | 0x0005;
+		do_report_trap(regs, SIGSEGV, SEGV_MAPERR, NULL);
+		break;
+	}
+}
+
+bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs)
+{
+	if ((psw_bits(regs->psw).eaba == PSW_AMODE_24BIT) ||
+	    ((psw_bits(regs->psw).eaba == PSW_AMODE_31BIT) &&
+	     !is_compat_task())) {
+		regs->psw.addr = __rewind_psw(regs->psw, UPROBE_SWBP_INSN_SIZE);
+		do_report_trap(regs, SIGILL, ILL_ILLADR, NULL);
+		return true;
+	}
+	if (probe_is_insn_relative_long(auprobe->insn)) {
+		handle_insn_ril(auprobe, regs);
+		return true;
+	}
+	return false;
+}
diff --git a/arch/s390/kernel/vdso.c b/arch/s390/kernel/vdso.c
new file mode 100644
index 000000000..0d58269ff
--- /dev/null
+++ b/arch/s390/kernel/vdso.c
@@ -0,0 +1,306 @@
+/*
+ * vdso setup for s390
+ *
+ *  Copyright IBM Corp. 2008
+ *  Author(s): Martin Schwidefsky (schwidefsky@de.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.
+ */
+
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/smp.h>
+#include <linux/stddef.h>
+#include <linux/unistd.h>
+#include <linux/slab.h>
+#include <linux/user.h>
+#include <linux/elf.h>
+#include <linux/security.h>
+#include <linux/bootmem.h>
+#include <linux/compat.h>
+#include <asm/asm-offsets.h>
+#include <asm/pgtable.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>
+
+#ifdef CONFIG_COMPAT
+extern char vdso32_start, vdso32_end;
+static void *vdso32_kbase = &vdso32_start;
+static unsigned int vdso32_pages;
+static struct page **vdso32_pagelist;
+#endif
+
+extern char vdso64_start, vdso64_end;
+static void *vdso64_kbase = &vdso64_start;
+static unsigned int vdso64_pages;
+static struct page **vdso64_pagelist;
+
+/*
+ * Should the kernel map a VDSO page into processes and pass its
+ * address down to glibc upon exec()?
+ */
+unsigned int __read_mostly vdso_enabled = 1;
+
+static int __init vdso_setup(char *s)
+{
+	unsigned long val;
+	int rc;
+
+	rc = 0;
+	if (strncmp(s, "on", 3) == 0)
+		vdso_enabled = 1;
+	else if (strncmp(s, "off", 4) == 0)
+		vdso_enabled = 0;
+	else {
+		rc = kstrtoul(s, 0, &val);
+		vdso_enabled = rc ? 0 : !!val;
+	}
+	return !rc;
+}
+__setup("vdso=", vdso_setup);
+
+/*
+ * The vdso data page
+ */
+static union {
+	struct vdso_data	data;
+	u8			page[PAGE_SIZE];
+} vdso_data_store __page_aligned_data;
+struct vdso_data *vdso_data = &vdso_data_store.data;
+
+/*
+ * Setup vdso data page.
+ */
+static void vdso_init_data(struct vdso_data *vd)
+{
+	vd->ectg_available = test_facility(31);
+}
+
+/*
+ * Allocate/free per cpu vdso data.
+ */
+#define SEGMENT_ORDER	2
+
+int vdso_alloc_per_cpu(struct _lowcore *lowcore)
+{
+	unsigned long segment_table, page_table, page_frame;
+	u32 *psal, *aste;
+	int i;
+
+	lowcore->vdso_per_cpu_data = __LC_PASTE;
+
+	if (!vdso_enabled)
+		return 0;
+
+	segment_table = __get_free_pages(GFP_KERNEL, SEGMENT_ORDER);
+	page_table = get_zeroed_page(GFP_KERNEL | GFP_DMA);
+	page_frame = get_zeroed_page(GFP_KERNEL);
+	if (!segment_table || !page_table || !page_frame)
+		goto out;
+
+	clear_table((unsigned long *) segment_table, _SEGMENT_ENTRY_EMPTY,
+		    PAGE_SIZE << SEGMENT_ORDER);
+	clear_table((unsigned long *) page_table, _PAGE_INVALID,
+		    256*sizeof(unsigned long));
+
+	*(unsigned long *) segment_table = _SEGMENT_ENTRY + page_table;
+	*(unsigned long *) page_table = _PAGE_PROTECT + page_frame;
+
+	psal = (u32 *) (page_table + 256*sizeof(unsigned long));
+	aste = psal + 32;
+
+	for (i = 4; i < 32; i += 4)
+		psal[i] = 0x80000000;
+
+	lowcore->paste[4] = (u32)(addr_t) psal;
+	psal[0] = 0x02000000;
+	psal[2] = (u32)(addr_t) aste;
+	*(unsigned long *) (aste + 2) = segment_table +
+		_ASCE_TABLE_LENGTH + _ASCE_USER_BITS + _ASCE_TYPE_SEGMENT;
+	aste[4] = (u32)(addr_t) psal;
+	lowcore->vdso_per_cpu_data = page_frame;
+
+	return 0;
+
+out:
+	free_page(page_frame);
+	free_page(page_table);
+	free_pages(segment_table, SEGMENT_ORDER);
+	return -ENOMEM;
+}
+
+void vdso_free_per_cpu(struct _lowcore *lowcore)
+{
+	unsigned long segment_table, page_table, page_frame;
+	u32 *psal, *aste;
+
+	if (!vdso_enabled)
+		return;
+
+	psal = (u32 *)(addr_t) lowcore->paste[4];
+	aste = (u32 *)(addr_t) psal[2];
+	segment_table = *(unsigned long *)(aste + 2) & PAGE_MASK;
+	page_table = *(unsigned long *) segment_table;
+	page_frame = *(unsigned long *) page_table;
+
+	free_page(page_frame);
+	free_page(page_table);
+	free_pages(segment_table, SEGMENT_ORDER);
+}
+
+static void vdso_init_cr5(void)
+{
+	unsigned long cr5;
+
+	if (!vdso_enabled)
+		return;
+	cr5 = offsetof(struct _lowcore, paste);
+	__ctl_load(cr5, 5, 5);
+}
+
+/*
+ * This is called from binfmt_elf, we create the special vma for the
+ * vDSO and insert it into the mm struct tree
+ */
+int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
+{
+	struct mm_struct *mm = current->mm;
+	struct page **vdso_pagelist;
+	unsigned long vdso_pages;
+	unsigned long vdso_base;
+	int rc;
+
+	if (!vdso_enabled)
+		return 0;
+	/*
+	 * Only map the vdso for dynamically linked elf binaries.
+	 */
+	if (!uses_interp)
+		return 0;
+
+	vdso_pagelist = vdso64_pagelist;
+	vdso_pages = vdso64_pages;
+#ifdef CONFIG_COMPAT
+	if (is_compat_task()) {
+		vdso_pagelist = vdso32_pagelist;
+		vdso_pages = vdso32_pages;
+	}
+#endif
+	/*
+	 * vDSO has a problem and was disabled, just don't "enable" it for
+	 * the process
+	 */
+	if (vdso_pages == 0)
+		return 0;
+
+	current->mm->context.vdso_base = 0;
+
+	/*
+	 * pick a base address for the vDSO in process space. We try to put
+	 * it at vdso_base which is the "natural" base for it, but we might
+	 * fail and end up putting it elsewhere.
+	 */
+	down_write(&mm->mmap_sem);
+	vdso_base = get_unmapped_area(NULL, 0, vdso_pages << PAGE_SHIFT, 0, 0);
+	if (IS_ERR_VALUE(vdso_base)) {
+		rc = vdso_base;
+		goto out_up;
+	}
+
+	/*
+	 * Put vDSO base into mm struct. We need to do this before calling
+	 * install_special_mapping or the perf counter mmap tracking code
+	 * will fail to recognise it as a vDSO (since arch_vma_name fails).
+	 */
+	current->mm->context.vdso_base = vdso_base;
+
+	/*
+	 * our vma flags don't have VM_WRITE so by default, the process
+	 * isn't allowed to write those pages.
+	 * gdb can break that with ptrace interface, and thus trigger COW
+	 * on those pages but it's then your responsibility to never do that
+	 * 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.
+	 */
+	rc = install_special_mapping(mm, vdso_base, vdso_pages << PAGE_SHIFT,
+				     VM_READ|VM_EXEC|
+				     VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
+				     vdso_pagelist);
+	if (rc)
+		current->mm->context.vdso_base = 0;
+out_up:
+	up_write(&mm->mmap_sem);
+	return rc;
+}
+
+const char *arch_vma_name(struct vm_area_struct *vma)
+{
+	if (vma->vm_mm && vma->vm_start == vma->vm_mm->context.vdso_base)
+		return "[vdso]";
+	return NULL;
+}
+
+static int __init vdso_init(void)
+{
+	int i;
+
+	if (!vdso_enabled)
+		return 0;
+	vdso_init_data(vdso_data);
+#ifdef CONFIG_COMPAT
+	/* Calculate the size of the 32 bit vDSO */
+	vdso32_pages = ((&vdso32_end - &vdso32_start
+			 + PAGE_SIZE - 1) >> PAGE_SHIFT) + 1;
+
+	/* Make sure pages are in the correct state */
+	vdso32_pagelist = kzalloc(sizeof(struct page *) * (vdso32_pages + 1),
+				  GFP_KERNEL);
+	BUG_ON(vdso32_pagelist == NULL);
+	for (i = 0; i < vdso32_pages - 1; i++) {
+		struct page *pg = virt_to_page(vdso32_kbase + i*PAGE_SIZE);
+		ClearPageReserved(pg);
+		get_page(pg);
+		vdso32_pagelist[i] = pg;
+	}
+	vdso32_pagelist[vdso32_pages - 1] = virt_to_page(vdso_data);
+	vdso32_pagelist[vdso32_pages] = NULL;
+#endif
+
+	/* Calculate the size of the 64 bit vDSO */
+	vdso64_pages = ((&vdso64_end - &vdso64_start
+			 + PAGE_SIZE - 1) >> PAGE_SHIFT) + 1;
+
+	/* Make sure pages are in the correct state */
+	vdso64_pagelist = kzalloc(sizeof(struct page *) * (vdso64_pages + 1),
+				  GFP_KERNEL);
+	BUG_ON(vdso64_pagelist == NULL);
+	for (i = 0; i < vdso64_pages - 1; i++) {
+		struct page *pg = virt_to_page(vdso64_kbase + i*PAGE_SIZE);
+		ClearPageReserved(pg);
+		get_page(pg);
+		vdso64_pagelist[i] = pg;
+	}
+	vdso64_pagelist[vdso64_pages - 1] = virt_to_page(vdso_data);
+	vdso64_pagelist[vdso64_pages] = NULL;
+	if (vdso_alloc_per_cpu(&S390_lowcore))
+		BUG();
+	vdso_init_cr5();
+
+	get_page(virt_to_page(vdso_data));
+
+	smp_wmb();
+
+	return 0;
+}
+early_initcall(vdso_init);
diff --git a/arch/s390/kernel/vdso32/.gitignore b/arch/s390/kernel/vdso32/.gitignore
new file mode 100644
index 000000000..e45fba9d0
--- /dev/null
+++ b/arch/s390/kernel/vdso32/.gitignore
@@ -0,0 +1 @@
+vdso32.lds
diff --git a/arch/s390/kernel/vdso32/Makefile b/arch/s390/kernel/vdso32/Makefile
new file mode 100644
index 000000000..8ad2b34ad
--- /dev/null
+++ b/arch/s390/kernel/vdso32/Makefile
@@ -0,0 +1,58 @@
+# List of files in the vdso, has to be asm only for now
+
+obj-vdso32 = gettimeofday.o clock_getres.o clock_gettime.o note.o
+
+# Build rules
+
+targets := $(obj-vdso32) vdso32.so vdso32.so.dbg
+obj-vdso32 := $(addprefix $(obj)/, $(obj-vdso32))
+
+KBUILD_AFLAGS_31 := $(filter-out -m64,$(KBUILD_AFLAGS))
+KBUILD_AFLAGS_31 += -m31 -s
+
+KBUILD_CFLAGS_31 := $(filter-out -m64,$(KBUILD_CFLAGS))
+KBUILD_CFLAGS_31 += -m31 -fPIC -shared -fno-common -fno-builtin
+KBUILD_CFLAGS_31 += -nostdlib -Wl,-soname=linux-vdso32.so.1 \
+			$(call cc-ldoption, -Wl$(comma)--hash-style=sysv)
+
+$(targets:%=$(obj)/%.dbg): KBUILD_CFLAGS = $(KBUILD_CFLAGS_31)
+$(targets:%=$(obj)/%.dbg): KBUILD_AFLAGS = $(KBUILD_AFLAGS_31)
+
+obj-y += vdso32_wrapper.o
+extra-y += vdso32.lds
+CPPFLAGS_vdso32.lds += -P -C -U$(ARCH)
+
+# Disable gcov profiling for VDSO code
+GCOV_PROFILE := n
+
+# Force dependency (incbin is bad)
+$(obj)/vdso32_wrapper.o : $(obj)/vdso32.so
+
+# link rule for the .so file, .lds has to be first
+$(obj)/vdso32.so.dbg: $(src)/vdso32.lds $(obj-vdso32)
+	$(call if_changed,vdso32ld)
+
+# strip rule for the .so file
+$(obj)/%.so: OBJCOPYFLAGS := -S
+$(obj)/%.so: $(obj)/%.so.dbg FORCE
+	$(call if_changed,objcopy)
+
+# assembly rules for the .S files
+$(obj-vdso32): %.o: %.S
+	$(call if_changed_dep,vdso32as)
+
+# actual build commands
+quiet_cmd_vdso32ld = VDSO32L $@
+      cmd_vdso32ld = $(CC) $(c_flags) -Wl,-T $^ -o $@
+quiet_cmd_vdso32as = VDSO32A $@
+      cmd_vdso32as = $(CC) $(a_flags) -c -o $@ $<
+
+# install commands for the unstripped file
+quiet_cmd_vdso_install = INSTALL $@
+      cmd_vdso_install = cp $(obj)/$@.dbg $(MODLIB)/vdso/$@
+
+vdso32.so: $(obj)/vdso32.so.dbg
+	@mkdir -p $(MODLIB)/vdso
+	$(call cmd,vdso_install)
+
+vdso_install: vdso32.so
diff --git a/arch/s390/kernel/vdso32/clock_getres.S b/arch/s390/kernel/vdso32/clock_getres.S
new file mode 100644
index 000000000..eca3f001f
--- /dev/null
+++ b/arch/s390/kernel/vdso32/clock_getres.S
@@ -0,0 +1,46 @@
+/*
+ * Userland implementation of clock_getres() for 32 bits processes in a
+ * s390 kernel for use in the vDSO
+ *
+ *  Copyright IBM Corp. 2008
+ *  Author(s): Martin Schwidefsky (schwidefsky@de.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.
+ */
+#include <asm/vdso.h>
+#include <asm/asm-offsets.h>
+#include <asm/unistd.h>
+
+	.text
+	.align 4
+	.globl __kernel_clock_getres
+	.type  __kernel_clock_getres,@function
+__kernel_clock_getres:
+	.cfi_startproc
+	basr	%r1,0
+	la	%r1,4f-.(%r1)
+	chi	%r2,__CLOCK_REALTIME
+	je	0f
+	chi	%r2,__CLOCK_MONOTONIC
+	je	0f
+	la	%r1,5f-4f(%r1)
+	chi	%r2,__CLOCK_REALTIME_COARSE
+	je	0f
+	chi	%r2,__CLOCK_MONOTONIC_COARSE
+	jne	3f
+0:	ltr	%r3,%r3
+	jz	2f				/* res == NULL */
+1:	l	%r0,0(%r1)
+	xc	0(4,%r3),0(%r3)			/* set tp->tv_sec to zero */
+	st	%r0,4(%r3)			/* store tp->tv_usec */
+2:	lhi	%r2,0
+	br	%r14
+3:	lhi	%r1,__NR_clock_getres		/* fallback to svc */
+	svc	0
+	br	%r14
+4:	.long	__CLOCK_REALTIME_RES
+5:	.long	__CLOCK_COARSE_RES
+	.cfi_endproc
+	.size	__kernel_clock_getres,.-__kernel_clock_getres
diff --git a/arch/s390/kernel/vdso32/clock_gettime.S b/arch/s390/kernel/vdso32/clock_gettime.S
new file mode 100644
index 000000000..5eec9afbb
--- /dev/null
+++ b/arch/s390/kernel/vdso32/clock_gettime.S
@@ -0,0 +1,149 @@
+/*
+ * Userland implementation of clock_gettime() for 32 bits processes in a
+ * s390 kernel for use in the vDSO
+ *
+ *  Copyright IBM Corp. 2008
+ *  Author(s): Martin Schwidefsky (schwidefsky@de.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.
+ */
+#include <asm/vdso.h>
+#include <asm/asm-offsets.h>
+#include <asm/unistd.h>
+
+	.text
+	.align 4
+	.globl __kernel_clock_gettime
+	.type  __kernel_clock_gettime,@function
+__kernel_clock_gettime:
+	.cfi_startproc
+	ahi	%r15,-16
+	basr	%r5,0
+0:	al	%r5,21f-0b(%r5)			/* get &_vdso_data */
+	chi	%r2,__CLOCK_REALTIME_COARSE
+	je	10f
+	chi	%r2,__CLOCK_REALTIME
+	je	11f
+	chi	%r2,__CLOCK_MONOTONIC_COARSE
+	je	9f
+	chi	%r2,__CLOCK_MONOTONIC
+	jne	19f
+
+	/* CLOCK_MONOTONIC */
+1:	l	%r4,__VDSO_UPD_COUNT+4(%r5)	/* load update counter */
+	tml	%r4,0x0001			/* pending update ? loop */
+	jnz	1b
+	stcke	0(%r15)				/* Store TOD clock */
+	lm	%r0,%r1,1(%r15)
+	s	%r0,__VDSO_XTIME_STAMP(%r5)	/* TOD - cycle_last */
+	sl	%r1,__VDSO_XTIME_STAMP+4(%r5)
+	brc	3,2f
+	ahi	%r0,-1
+2:	ms	%r0,__VDSO_TK_MULT(%r5)		/*  * tk->mult */
+	lr	%r2,%r0
+	l	%r0,__VDSO_TK_MULT(%r5)
+	ltr	%r1,%r1
+	mr	%r0,%r0
+	jnm	3f
+	a	%r0,__VDSO_TK_MULT(%r5)
+3:	alr	%r0,%r2
+	al	%r0,__VDSO_WTOM_NSEC(%r5)
+	al	%r1,__VDSO_WTOM_NSEC+4(%r5)
+	brc	12,5f
+	ahi	%r0,1
+5:	l	%r2,__VDSO_TK_SHIFT(%r5)	/* Timekeeper shift */
+	srdl	%r0,0(%r2)			/*  >> tk->shift */
+	l	%r2,__VDSO_WTOM_SEC+4(%r5)
+	cl	%r4,__VDSO_UPD_COUNT+4(%r5)	/* check update counter */
+	jne	1b
+	basr	%r5,0
+6:	ltr	%r0,%r0
+	jnz	7f
+	cl	%r1,20f-6b(%r5)
+	jl	8f
+7:	ahi	%r2,1
+	sl	%r1,20f-6b(%r5)
+	brc	3,6b
+	ahi	%r0,-1
+	j	6b
+8:	st	%r2,0(%r3)			/* store tp->tv_sec */
+	st	%r1,4(%r3)			/* store tp->tv_nsec */
+	lhi	%r2,0
+	ahi	%r15,16
+	br	%r14
+
+	/* CLOCK_MONOTONIC_COARSE */
+9:	l	%r4,__VDSO_UPD_COUNT+4(%r5)	/* load update counter */
+	tml	%r4,0x0001			/* pending update ? loop */
+	jnz	9b
+	l	%r2,__VDSO_WTOM_CRS_SEC+4(%r5)
+	l	%r1,__VDSO_WTOM_CRS_NSEC+4(%r5)
+	cl	%r4,__VDSO_UPD_COUNT+4(%r5)	/* check update counter */
+	jne	9b
+	j	8b
+
+	/* CLOCK_REALTIME_COARSE */
+10:	l	%r4,__VDSO_UPD_COUNT+4(%r5)	/* load update counter */
+	tml	%r4,0x0001			/* pending update ? loop */
+	jnz	10b
+	l	%r2,__VDSO_XTIME_CRS_SEC+4(%r5)
+	l	%r1,__VDSO_XTIME_CRS_NSEC+4(%r5)
+	cl	%r4,__VDSO_UPD_COUNT+4(%r5)	/* check update counter */
+	jne	10b
+	j	17f
+
+	/* CLOCK_REALTIME */
+11:	l	%r4,__VDSO_UPD_COUNT+4(%r5)	/* load update counter */
+	tml	%r4,0x0001			/* pending update ? loop */
+	jnz	11b
+	stcke	0(%r15)				/* Store TOD clock */
+	lm	%r0,%r1,1(%r15)
+	s	%r0,__VDSO_XTIME_STAMP(%r5)	/* TOD - cycle_last */
+	sl	%r1,__VDSO_XTIME_STAMP+4(%r5)
+	brc	3,12f
+	ahi	%r0,-1
+12:	ms	%r0,__VDSO_TK_MULT(%r5)		/*  * tk->mult */
+	lr	%r2,%r0
+	l	%r0,__VDSO_TK_MULT(%r5)
+	ltr	%r1,%r1
+	mr	%r0,%r0
+	jnm	13f
+	a	%r0,__VDSO_TK_MULT(%r5)
+13:	alr	%r0,%r2
+	al	%r0,__VDSO_XTIME_NSEC(%r5)	/*  + tk->xtime_nsec */
+	al	%r1,__VDSO_XTIME_NSEC+4(%r5)
+	brc	12,14f
+	ahi	%r0,1
+14:	l	%r2,__VDSO_TK_SHIFT(%r5)	/* Timekeeper shift */
+	srdl	%r0,0(%r2)			/*  >> tk->shift */
+	l	%r2,__VDSO_XTIME_SEC+4(%r5)
+	cl	%r4,__VDSO_UPD_COUNT+4(%r5)	/* check update counter */
+	jne	11b
+	basr	%r5,0
+15:	ltr	%r0,%r0
+	jnz	16f
+	cl	%r1,20f-15b(%r5)
+	jl	17f
+16:	ahi	%r2,1
+	sl	%r1,20f-15b(%r5)
+	brc	3,15b
+	ahi	%r0,-1
+	j	15b
+17:	st	%r2,0(%r3)			/* store tp->tv_sec */
+	st	%r1,4(%r3)			/* store tp->tv_nsec */
+	lhi	%r2,0
+	ahi	%r15,16
+	br	%r14
+
+	/* Fallback to system call */
+19:	lhi	%r1,__NR_clock_gettime
+	svc	0
+	ahi	%r15,16
+	br	%r14
+
+20:	.long	1000000000
+21:	.long	_vdso_data - 0b
+	.cfi_endproc
+	.size	__kernel_clock_gettime,.-__kernel_clock_gettime
diff --git a/arch/s390/kernel/vdso32/gettimeofday.S b/arch/s390/kernel/vdso32/gettimeofday.S
new file mode 100644
index 000000000..719de6186
--- /dev/null
+++ b/arch/s390/kernel/vdso32/gettimeofday.S
@@ -0,0 +1,81 @@
+/*
+ * Userland implementation of gettimeofday() for 32 bits processes in a
+ * s390 kernel for use in the vDSO
+ *
+ *  Copyright IBM Corp. 2008
+ *  Author(s): Martin Schwidefsky (schwidefsky@de.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.
+ */
+#include <asm/vdso.h>
+#include <asm/asm-offsets.h>
+#include <asm/unistd.h>
+
+	.text
+	.align 4
+	.globl __kernel_gettimeofday
+	.type  __kernel_gettimeofday,@function
+__kernel_gettimeofday:
+	.cfi_startproc
+	ahi	%r15,-16
+	basr	%r5,0
+0:	al	%r5,13f-0b(%r5)			/* get &_vdso_data */
+1:	ltr	%r3,%r3				/* check if tz is NULL */
+	je	2f
+	mvc	0(8,%r3),__VDSO_TIMEZONE(%r5)
+2:	ltr	%r2,%r2				/* check if tv is NULL */
+	je	10f
+	l	%r4,__VDSO_UPD_COUNT+4(%r5)	/* load update counter */
+	tml	%r4,0x0001			/* pending update ? loop */
+	jnz	1b
+	stcke	0(%r15)				/* Store TOD clock */
+	lm	%r0,%r1,1(%r15)
+	s	%r0,__VDSO_XTIME_STAMP(%r5)	/* TOD - cycle_last */
+	sl	%r1,__VDSO_XTIME_STAMP+4(%r5)
+	brc	3,3f
+	ahi	%r0,-1
+3:	ms	%r0,__VDSO_TK_MULT(%r5)		/*  * tk->mult */
+	st	%r0,0(%r15)
+	l	%r0,__VDSO_TK_MULT(%r5)
+	ltr	%r1,%r1
+	mr	%r0,%r0
+	jnm	4f
+	a	%r0,__VDSO_TK_MULT(%r5)
+4:	al	%r0,0(%r15)
+	al	%r0,__VDSO_XTIME_NSEC(%r5)	/*  + xtime */
+	al	%r1,__VDSO_XTIME_NSEC+4(%r5)
+	brc	12,5f
+	ahi	%r0,1
+5:	mvc	0(4,%r15),__VDSO_XTIME_SEC+4(%r5)
+	cl	%r4,__VDSO_UPD_COUNT+4(%r5)	/* check update counter */
+	jne	1b
+	l	%r4,__VDSO_TK_SHIFT(%r5)	/* Timekeeper shift */
+	srdl	%r0,0(%r4)			/*  >> tk->shift */
+	l	%r4,0(%r15)			/* get tv_sec from stack */
+	basr	%r5,0
+6:	ltr	%r0,%r0
+	jnz	7f
+	cl	%r1,11f-6b(%r5)
+	jl	8f
+7:	ahi	%r4,1
+	sl	%r1,11f-6b(%r5)
+	brc	3,6b
+	ahi	%r0,-1
+	j	6b
+8:	st	%r4,0(%r2)			/* store tv->tv_sec */
+	ltr	%r1,%r1
+	m	%r0,12f-6b(%r5)
+	jnm	9f
+	al	%r0,12f-6b(%r5)
+9:	srl	%r0,6
+	st	%r0,4(%r2)			/* store tv->tv_usec */
+10:	slr	%r2,%r2
+	ahi	%r15,16
+	br	%r14
+11:	.long	1000000000
+12:	.long	274877907
+13:	.long	_vdso_data - 0b
+	.cfi_endproc
+	.size	__kernel_gettimeofday,.-__kernel_gettimeofday
diff --git a/arch/s390/kernel/vdso32/note.S b/arch/s390/kernel/vdso32/note.S
new file mode 100644
index 000000000..79a071e43
--- /dev/null
+++ b/arch/s390/kernel/vdso32/note.S
@@ -0,0 +1,12 @@
+/*
+ * This supplies .note.* sections to go into the PT_NOTE inside the vDSO text.
+ * Here we can supply some information useful to userland.
+ */
+
+#include <linux/uts.h>
+#include <linux/version.h>
+#include <linux/elfnote.h>
+
+ELFNOTE_START(Linux, 0, "a")
+	.long LINUX_VERSION_CODE
+ELFNOTE_END
diff --git a/arch/s390/kernel/vdso32/vdso32.lds.S b/arch/s390/kernel/vdso32/vdso32.lds.S
new file mode 100644
index 000000000..a8c379fa1
--- /dev/null
+++ b/arch/s390/kernel/vdso32/vdso32.lds.S
@@ -0,0 +1,138 @@
+/*
+ * This is the infamous ld script for the 32 bits vdso
+ * library
+ */
+#include <asm/vdso.h>
+
+OUTPUT_FORMAT("elf32-s390", "elf32-s390", "elf32-s390")
+OUTPUT_ARCH(s390:31-bit)
+ENTRY(_start)
+
+SECTIONS
+{
+	. = VDSO32_LBASE + SIZEOF_HEADERS;
+
+	.hash		: { *(.hash) }			:text
+	.gnu.hash	: { *(.gnu.hash) }
+	.dynsym		: { *(.dynsym) }
+	.dynstr		: { *(.dynstr) }
+	.gnu.version	: { *(.gnu.version) }
+	.gnu.version_d	: { *(.gnu.version_d) }
+	.gnu.version_r	: { *(.gnu.version_r) }
+
+	.note		: { *(.note.*) }		:text	:note
+
+	. = ALIGN(16);
+	.text		: {
+		*(.text .stub .text.* .gnu.linkonce.t.*)
+	} :text
+	PROVIDE(__etext = .);
+	PROVIDE(_etext = .);
+	PROVIDE(etext = .);
+
+	/*
+	 * Other stuff is appended to the text segment:
+	 */
+	.rodata		: { *(.rodata .rodata.* .gnu.linkonce.r.*) }
+	.rodata1	: { *(.rodata1) }
+
+	.dynamic	: { *(.dynamic) }		:text	:dynamic
+
+	.eh_frame_hdr	: { *(.eh_frame_hdr) }		:text	:eh_frame_hdr
+	.eh_frame	: { KEEP (*(.eh_frame)) }	:text
+	.gcc_except_table : { *(.gcc_except_table .gcc_except_table.*) }
+
+	.rela.dyn ALIGN(8) : { *(.rela.dyn) }
+	.got ALIGN(8)	: { *(.got .toc) }
+
+	_end = .;
+	PROVIDE(end = .);
+
+	/*
+	 * Stabs debugging sections are here too.
+	 */
+	.stab	       0 : { *(.stab) }
+	.stabstr       0 : { *(.stabstr) }
+	.stab.excl     0 : { *(.stab.excl) }
+	.stab.exclstr  0 : { *(.stab.exclstr) }
+	.stab.index    0 : { *(.stab.index) }
+	.stab.indexstr 0 : { *(.stab.indexstr) }
+	.comment       0 : { *(.comment) }
+
+	/*
+	 * DWARF debug sections.
+	 * Symbols in the DWARF debugging sections are relative to the
+	 * beginning of the section so we begin them at 0.
+	 */
+	/* DWARF 1 */
+	.debug		0 : { *(.debug) }
+	.line		0 : { *(.line) }
+	/* GNU DWARF 1 extensions */
+	.debug_srcinfo	0 : { *(.debug_srcinfo) }
+	.debug_sfnames	0 : { *(.debug_sfnames) }
+	/* DWARF 1.1 and DWARF 2 */
+	.debug_aranges	0 : { *(.debug_aranges) }
+	.debug_pubnames 0 : { *(.debug_pubnames) }
+	/* DWARF 2 */
+	.debug_info	0 : { *(.debug_info .gnu.linkonce.wi.*) }
+	.debug_abbrev	0 : { *(.debug_abbrev) }
+	.debug_line	0 : { *(.debug_line) }
+	.debug_frame	0 : { *(.debug_frame) }
+	.debug_str	0 : { *(.debug_str) }
+	.debug_loc	0 : { *(.debug_loc) }
+	.debug_macinfo	0 : { *(.debug_macinfo) }
+	/* SGI/MIPS DWARF 2 extensions */
+	.debug_weaknames 0 : { *(.debug_weaknames) }
+	.debug_funcnames 0 : { *(.debug_funcnames) }
+	.debug_typenames 0 : { *(.debug_typenames) }
+	.debug_varnames  0 : { *(.debug_varnames) }
+	/* DWARF 3 */
+	.debug_pubtypes 0 : { *(.debug_pubtypes) }
+	.debug_ranges	0 : { *(.debug_ranges) }
+	.gnu.attributes 0 : { KEEP (*(.gnu.attributes)) }
+
+	. = ALIGN(4096);
+	PROVIDE(_vdso_data = .);
+
+	/DISCARD/	: {
+		*(.note.GNU-stack)
+		*(.branch_lt)
+		*(.data .data.* .gnu.linkonce.d.* .sdata*)
+		*(.bss .sbss .dynbss .dynsbss)
+	}
+}
+
+/*
+ * Very old versions of ld do not recognize this name token; use the constant.
+ */
+#define PT_GNU_EH_FRAME	0x6474e550
+
+/*
+ * We must supply the ELF program headers explicitly to get just one
+ * PT_LOAD segment, and set the flags explicitly to make segments read-only.
+ */
+PHDRS
+{
+	text		PT_LOAD FILEHDR PHDRS FLAGS(5);	/* PF_R|PF_X */
+	dynamic		PT_DYNAMIC FLAGS(4);		/* PF_R */
+	note		PT_NOTE FLAGS(4);		/* PF_R */
+	eh_frame_hdr	PT_GNU_EH_FRAME;
+}
+
+/*
+ * This controls what symbols we export from the DSO.
+ */
+VERSION
+{
+	VDSO_VERSION_STRING {
+	global:
+		/*
+		 * Has to be there for the kernel to find
+		 */
+		__kernel_gettimeofday;
+		__kernel_clock_gettime;
+		__kernel_clock_getres;
+
+	local: *;
+	};
+}
diff --git a/arch/s390/kernel/vdso32/vdso32_wrapper.S b/arch/s390/kernel/vdso32/vdso32_wrapper.S
new file mode 100644
index 000000000..ae42f8ce3
--- /dev/null
+++ b/arch/s390/kernel/vdso32/vdso32_wrapper.S
@@ -0,0 +1,14 @@
+#include <linux/init.h>
+#include <linux/linkage.h>
+#include <asm/page.h>
+
+	__PAGE_ALIGNED_DATA
+
+	.globl vdso32_start, vdso32_end
+	.balign PAGE_SIZE
+vdso32_start:
+	.incbin "arch/s390/kernel/vdso32/vdso32.so"
+	.balign PAGE_SIZE
+vdso32_end:
+
+	.previous
diff --git a/arch/s390/kernel/vdso64/.gitignore b/arch/s390/kernel/vdso64/.gitignore
new file mode 100644
index 000000000..3fd18cf9f
--- /dev/null
+++ b/arch/s390/kernel/vdso64/.gitignore
@@ -0,0 +1 @@
+vdso64.lds
diff --git a/arch/s390/kernel/vdso64/Makefile b/arch/s390/kernel/vdso64/Makefile
new file mode 100644
index 000000000..2a8ddfd12
--- /dev/null
+++ b/arch/s390/kernel/vdso64/Makefile
@@ -0,0 +1,58 @@
+# List of files in the vdso, has to be asm only for now
+
+obj-vdso64 = gettimeofday.o clock_getres.o clock_gettime.o note.o
+
+# Build rules
+
+targets := $(obj-vdso64) vdso64.so vdso64.so.dbg
+obj-vdso64 := $(addprefix $(obj)/, $(obj-vdso64))
+
+KBUILD_AFLAGS_64 := $(filter-out -m64,$(KBUILD_AFLAGS))
+KBUILD_AFLAGS_64 += -m64 -s
+
+KBUILD_CFLAGS_64 := $(filter-out -m64,$(KBUILD_CFLAGS))
+KBUILD_CFLAGS_64 += -m64 -fPIC -shared -fno-common -fno-builtin
+KBUILD_CFLAGS_64 += -nostdlib -Wl,-soname=linux-vdso64.so.1 \
+			$(call cc-ldoption, -Wl$(comma)--hash-style=sysv)
+
+$(targets:%=$(obj)/%.dbg): KBUILD_CFLAGS = $(KBUILD_CFLAGS_64)
+$(targets:%=$(obj)/%.dbg): KBUILD_AFLAGS = $(KBUILD_AFLAGS_64)
+
+obj-y += vdso64_wrapper.o
+extra-y += vdso64.lds
+CPPFLAGS_vdso64.lds += -P -C -U$(ARCH)
+
+# Disable gcov profiling for VDSO code
+GCOV_PROFILE := n
+
+# Force dependency (incbin is bad)
+$(obj)/vdso64_wrapper.o : $(obj)/vdso64.so
+
+# link rule for the .so file, .lds has to be first
+$(obj)/vdso64.so.dbg: $(src)/vdso64.lds $(obj-vdso64)
+	$(call if_changed,vdso64ld)
+
+# strip rule for the .so file
+$(obj)/%.so: OBJCOPYFLAGS := -S
+$(obj)/%.so: $(obj)/%.so.dbg FORCE
+	$(call if_changed,objcopy)
+
+# assembly rules for the .S files
+$(obj-vdso64): %.o: %.S
+	$(call if_changed_dep,vdso64as)
+
+# actual build commands
+quiet_cmd_vdso64ld = VDSO64L $@
+      cmd_vdso64ld = $(CC) $(c_flags) -Wl,-T $^ -o $@
+quiet_cmd_vdso64as = VDSO64A $@
+      cmd_vdso64as = $(CC) $(a_flags) -c -o $@ $<
+
+# install commands for the unstripped file
+quiet_cmd_vdso_install = INSTALL $@
+      cmd_vdso_install = cp $(obj)/$@.dbg $(MODLIB)/vdso/$@
+
+vdso64.so: $(obj)/vdso64.so.dbg
+	@mkdir -p $(MODLIB)/vdso
+	$(call cmd,vdso_install)
+
+vdso_install: vdso64.so
diff --git a/arch/s390/kernel/vdso64/clock_getres.S b/arch/s390/kernel/vdso64/clock_getres.S
new file mode 100644
index 000000000..c8513deb8
--- /dev/null
+++ b/arch/s390/kernel/vdso64/clock_getres.S
@@ -0,0 +1,52 @@
+/*
+ * Userland implementation of clock_getres() for 64 bits processes in a
+ * s390 kernel for use in the vDSO
+ *
+ *  Copyright IBM Corp. 2008
+ *  Author(s): Martin Schwidefsky (schwidefsky@de.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.
+ */
+#include <asm/vdso.h>
+#include <asm/asm-offsets.h>
+#include <asm/unistd.h>
+
+	.text
+	.align 4
+	.globl __kernel_clock_getres
+	.type  __kernel_clock_getres,@function
+__kernel_clock_getres:
+	.cfi_startproc
+	larl	%r1,4f
+	cghi	%r2,__CLOCK_REALTIME_COARSE
+	je	0f
+	cghi	%r2,__CLOCK_MONOTONIC_COARSE
+	je	0f
+	larl	%r1,3f
+	cghi	%r2,__CLOCK_REALTIME
+	je	0f
+	cghi	%r2,__CLOCK_MONOTONIC
+	je	0f
+	cghi	%r2,__CLOCK_THREAD_CPUTIME_ID
+	je	0f
+	cghi	%r2,-2		/* Per-thread CPUCLOCK with PID=0, VIRT=1 */
+	jne	2f
+	larl	%r5,_vdso_data
+	icm	%r0,15,__LC_ECTG_OK(%r5)
+	jz	2f
+0:	ltgr	%r3,%r3
+	jz	1f				/* res == NULL */
+	lg	%r0,0(%r1)
+	xc	0(8,%r3),0(%r3)			/* set tp->tv_sec to zero */
+	stg	%r0,8(%r3)			/* store tp->tv_usec */
+1:	lghi	%r2,0
+	br	%r14
+2:	lghi	%r1,__NR_clock_getres		/* fallback to svc */
+	svc	0
+	br	%r14
+3:	.quad	__CLOCK_REALTIME_RES
+4:	.quad	__CLOCK_COARSE_RES
+	.cfi_endproc
+	.size	__kernel_clock_getres,.-__kernel_clock_getres
diff --git a/arch/s390/kernel/vdso64/clock_gettime.S b/arch/s390/kernel/vdso64/clock_gettime.S
new file mode 100644
index 000000000..61541fb93
--- /dev/null
+++ b/arch/s390/kernel/vdso64/clock_gettime.S
@@ -0,0 +1,150 @@
+/*
+ * Userland implementation of clock_gettime() for 64 bits processes in a
+ * s390 kernel for use in the vDSO
+ *
+ *  Copyright IBM Corp. 2008
+ *  Author(s): Martin Schwidefsky (schwidefsky@de.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.
+ */
+#include <asm/vdso.h>
+#include <asm/asm-offsets.h>
+#include <asm/unistd.h>
+
+	.text
+	.align 4
+	.globl __kernel_clock_gettime
+	.type  __kernel_clock_gettime,@function
+__kernel_clock_gettime:
+	.cfi_startproc
+	aghi	%r15,-16
+	larl	%r5,_vdso_data
+	cghi	%r2,__CLOCK_REALTIME_COARSE
+	je	4f
+	cghi	%r2,__CLOCK_REALTIME
+	je	5f
+	cghi	%r2,-3		/* Per-thread CPUCLOCK with PID=0, VIRT=1 */
+	je	9f
+	cghi	%r2,__CLOCK_MONOTONIC_COARSE
+	je	3f
+	cghi	%r2,__CLOCK_MONOTONIC
+	jne	12f
+
+	/* CLOCK_MONOTONIC */
+0:	lg	%r4,__VDSO_UPD_COUNT(%r5)	/* load update counter */
+	tmll	%r4,0x0001			/* pending update ? loop */
+	jnz	0b
+	stcke	0(%r15)				/* Store TOD clock */
+	lgf	%r2,__VDSO_TK_SHIFT(%r5)	/* Timekeeper shift */
+	lg	%r0,__VDSO_WTOM_SEC(%r5)
+	lg	%r1,1(%r15)
+	sg	%r1,__VDSO_XTIME_STAMP(%r5)	/* TOD - cycle_last */
+	msgf	%r1,__VDSO_TK_MULT(%r5)		/*  * tk->mult */
+	alg	%r1,__VDSO_WTOM_NSEC(%r5)
+	srlg	%r1,%r1,0(%r2)			/*  >> tk->shift */
+	clg	%r4,__VDSO_UPD_COUNT(%r5)	/* check update counter */
+	jne	0b
+	larl	%r5,13f
+1:	clg	%r1,0(%r5)
+	jl	2f
+	slg	%r1,0(%r5)
+	aghi	%r0,1
+	j	1b
+2:	stg	%r0,0(%r3)			/* store tp->tv_sec */
+	stg	%r1,8(%r3)			/* store tp->tv_nsec */
+	lghi	%r2,0
+	aghi	%r15,16
+	br	%r14
+
+	/* CLOCK_MONOTONIC_COARSE */
+3:	lg	%r4,__VDSO_UPD_COUNT(%r5)	/* load update counter */
+	tmll	%r4,0x0001			/* pending update ? loop */
+	jnz	3b
+	lg	%r0,__VDSO_WTOM_CRS_SEC(%r5)
+	lg	%r1,__VDSO_WTOM_CRS_NSEC(%r5)
+	clg	%r4,__VDSO_UPD_COUNT(%r5)	/* check update counter */
+	jne	3b
+	j	2b
+
+	/* CLOCK_REALTIME_COARSE */
+4:	lg	%r4,__VDSO_UPD_COUNT(%r5)	/* load update counter */
+	tmll	%r4,0x0001			/* pending update ? loop */
+	jnz	4b
+	lg	%r0,__VDSO_XTIME_CRS_SEC(%r5)
+	lg	%r1,__VDSO_XTIME_CRS_NSEC(%r5)
+	clg	%r4,__VDSO_UPD_COUNT(%r5)	/* check update counter */
+	jne	4b
+	j	7f
+
+	/* CLOCK_REALTIME */
+5:	lg	%r4,__VDSO_UPD_COUNT(%r5)	/* load update counter */
+	tmll	%r4,0x0001			/* pending update ? loop */
+	jnz	5b
+	stcke	0(%r15)				/* Store TOD clock */
+	lgf	%r2,__VDSO_TK_SHIFT(%r5)	/* Timekeeper shift */
+	lg	%r1,1(%r15)
+	sg	%r1,__VDSO_XTIME_STAMP(%r5)	/* TOD - cycle_last */
+	msgf	%r1,__VDSO_TK_MULT(%r5)		/*  * tk->mult */
+	alg	%r1,__VDSO_XTIME_NSEC(%r5)	/*  + tk->xtime_nsec */
+	srlg	%r1,%r1,0(%r2)			/*  >> tk->shift */
+	lg	%r0,__VDSO_XTIME_SEC(%r5)	/* tk->xtime_sec */
+	clg	%r4,__VDSO_UPD_COUNT(%r5)	/* check update counter */
+	jne	5b
+	larl	%r5,13f
+6:	clg	%r1,0(%r5)
+	jl	7f
+	slg	%r1,0(%r5)
+	aghi	%r0,1
+	j	6b
+7:	stg	%r0,0(%r3)			/* store tp->tv_sec */
+	stg	%r1,8(%r3)			/* store tp->tv_nsec */
+	lghi	%r2,0
+	aghi	%r15,16
+	br	%r14
+
+	/* CPUCLOCK_VIRT for this thread */
+9:	icm	%r0,15,__VDSO_ECTG_OK(%r5)
+	jz	12f
+	ear	%r2,%a4
+	llilh	%r4,0x0100
+	sar	%a4,%r4
+	lghi	%r4,0
+	epsw	%r5,0
+	sacf	512				/* Magic ectg instruction */
+	.insn	ssf,0xc80100000000,__VDSO_ECTG_BASE(4),__VDSO_ECTG_USER(4),4
+	tml	%r5,0x4000
+	jo	11f
+	tml	%r5,0x8000
+	jno	10f
+	sacf	256
+	j	11f
+10:	sacf	0
+11:	sar	%a4,%r2
+	algr	%r1,%r0				/* r1 = cputime as TOD value */
+	mghi	%r1,1000			/* convert to nanoseconds */
+	srlg	%r1,%r1,12			/* r1 = cputime in nanosec */
+	lgr	%r4,%r1
+	larl	%r5,13f
+	srlg	%r1,%r1,9			/* divide by 1000000000 */
+	mlg	%r0,8(%r5)
+	srlg	%r0,%r0,11			/* r0 = tv_sec */
+	stg	%r0,0(%r3)
+	msg	%r0,0(%r5)			/* calculate tv_nsec */
+	slgr	%r4,%r0				/* r4 = tv_nsec */
+	stg	%r4,8(%r3)
+	lghi	%r2,0
+	aghi	%r15,16
+	br	%r14
+
+	/* Fallback to system call */
+12:	lghi	%r1,__NR_clock_gettime
+	svc	0
+	aghi	%r15,16
+	br	%r14
+
+13:	.quad	1000000000
+14:	.quad	19342813113834067
+	.cfi_endproc
+	.size	__kernel_clock_gettime,.-__kernel_clock_gettime
diff --git a/arch/s390/kernel/vdso64/gettimeofday.S b/arch/s390/kernel/vdso64/gettimeofday.S
new file mode 100644
index 000000000..6ce467076
--- /dev/null
+++ b/arch/s390/kernel/vdso64/gettimeofday.S
@@ -0,0 +1,59 @@
+/*
+ * Userland implementation of gettimeofday() for 64 bits processes in a
+ * s390 kernel for use in the vDSO
+ *
+ *  Copyright IBM Corp. 2008
+ *  Author(s): Martin Schwidefsky (schwidefsky@de.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.
+ */
+#include <asm/vdso.h>
+#include <asm/asm-offsets.h>
+#include <asm/unistd.h>
+
+	.text
+	.align 4
+	.globl __kernel_gettimeofday
+	.type  __kernel_gettimeofday,@function
+__kernel_gettimeofday:
+	.cfi_startproc
+	aghi	%r15,-16
+	larl	%r5,_vdso_data
+0:	ltgr	%r3,%r3				/* check if tz is NULL */
+	je	1f
+	mvc	0(8,%r3),__VDSO_TIMEZONE(%r5)
+1:	ltgr	%r2,%r2				/* check if tv is NULL */
+	je	4f
+	lg	%r4,__VDSO_UPD_COUNT(%r5)	/* load update counter */
+	tmll	%r4,0x0001			/* pending update ? loop */
+	jnz	0b
+	stcke	0(%r15)				/* Store TOD clock */
+	lg	%r1,1(%r15)
+	sg	%r1,__VDSO_XTIME_STAMP(%r5)	/* TOD - cycle_last */
+	msgf	%r1,__VDSO_TK_MULT(%r5)		/*  * tk->mult */
+	alg	%r1,__VDSO_XTIME_NSEC(%r5)	/*  + tk->xtime_nsec */
+	lg	%r0,__VDSO_XTIME_SEC(%r5)	/* tk->xtime_sec */
+	clg	%r4,__VDSO_UPD_COUNT(%r5)	/* check update counter */
+	jne	0b
+	lgf	%r5,__VDSO_TK_SHIFT(%r5)	/* Timekeeper shift */
+	srlg	%r1,%r1,0(%r5)			/*  >> tk->shift */
+	larl	%r5,5f
+2:	clg	%r1,0(%r5)
+	jl	3f
+	slg	%r1,0(%r5)
+	aghi	%r0,1
+	j	2b
+3:	stg	%r0,0(%r2)			/* store tv->tv_sec */
+	slgr	%r0,%r0				/* tv_nsec -> tv_usec */
+	ml	%r0,8(%r5)
+	srlg	%r0,%r0,6
+	stg	%r0,8(%r2)			/* store tv->tv_usec */
+4:	lghi	%r2,0
+	aghi	%r15,16
+	br	%r14
+5:	.quad	1000000000
+	.long	274877907
+	.cfi_endproc
+	.size	__kernel_gettimeofday,.-__kernel_gettimeofday
diff --git a/arch/s390/kernel/vdso64/note.S b/arch/s390/kernel/vdso64/note.S
new file mode 100644
index 000000000..79a071e43
--- /dev/null
+++ b/arch/s390/kernel/vdso64/note.S
@@ -0,0 +1,12 @@
+/*
+ * This supplies .note.* sections to go into the PT_NOTE inside the vDSO text.
+ * Here we can supply some information useful to userland.
+ */
+
+#include <linux/uts.h>
+#include <linux/version.h>
+#include <linux/elfnote.h>
+
+ELFNOTE_START(Linux, 0, "a")
+	.long LINUX_VERSION_CODE
+ELFNOTE_END
diff --git a/arch/s390/kernel/vdso64/vdso64.lds.S b/arch/s390/kernel/vdso64/vdso64.lds.S
new file mode 100644
index 000000000..9f5979d10
--- /dev/null
+++ b/arch/s390/kernel/vdso64/vdso64.lds.S
@@ -0,0 +1,138 @@
+/*
+ * This is the infamous ld script for the 64 bits vdso
+ * library
+ */
+#include <asm/vdso.h>
+
+OUTPUT_FORMAT("elf64-s390", "elf64-s390", "elf64-s390")
+OUTPUT_ARCH(s390:64-bit)
+ENTRY(_start)
+
+SECTIONS
+{
+	. = VDSO64_LBASE + SIZEOF_HEADERS;
+
+	.hash		: { *(.hash) }			:text
+	.gnu.hash	: { *(.gnu.hash) }
+	.dynsym		: { *(.dynsym) }
+	.dynstr		: { *(.dynstr) }
+	.gnu.version	: { *(.gnu.version) }
+	.gnu.version_d	: { *(.gnu.version_d) }
+	.gnu.version_r	: { *(.gnu.version_r) }
+
+	.note		: { *(.note.*) }		:text	:note
+
+	. = ALIGN(16);
+	.text		: {
+		*(.text .stub .text.* .gnu.linkonce.t.*)
+	} :text
+	PROVIDE(__etext = .);
+	PROVIDE(_etext = .);
+	PROVIDE(etext = .);
+
+	/*
+	 * Other stuff is appended to the text segment:
+	 */
+	.rodata		: { *(.rodata .rodata.* .gnu.linkonce.r.*) }
+	.rodata1	: { *(.rodata1) }
+
+	.dynamic	: { *(.dynamic) }		:text	:dynamic
+
+	.eh_frame_hdr	: { *(.eh_frame_hdr) }		:text	:eh_frame_hdr
+	.eh_frame	: { KEEP (*(.eh_frame)) }	:text
+	.gcc_except_table : { *(.gcc_except_table .gcc_except_table.*) }
+
+	.rela.dyn ALIGN(8) : { *(.rela.dyn) }
+	.got ALIGN(8)	: { *(.got .toc) }
+
+	_end = .;
+	PROVIDE(end = .);
+
+	/*
+	 * Stabs debugging sections are here too.
+	 */
+	.stab	       0 : { *(.stab) }
+	.stabstr       0 : { *(.stabstr) }
+	.stab.excl     0 : { *(.stab.excl) }
+	.stab.exclstr  0 : { *(.stab.exclstr) }
+	.stab.index    0 : { *(.stab.index) }
+	.stab.indexstr 0 : { *(.stab.indexstr) }
+	.comment       0 : { *(.comment) }
+
+	/*
+	 * DWARF debug sections.
+	 * Symbols in the DWARF debugging sections are relative to the
+	 * beginning of the section so we begin them at 0.
+	 */
+	/* DWARF 1 */
+	.debug		0 : { *(.debug) }
+	.line		0 : { *(.line) }
+	/* GNU DWARF 1 extensions */
+	.debug_srcinfo	0 : { *(.debug_srcinfo) }
+	.debug_sfnames	0 : { *(.debug_sfnames) }
+	/* DWARF 1.1 and DWARF 2 */
+	.debug_aranges	0 : { *(.debug_aranges) }
+	.debug_pubnames 0 : { *(.debug_pubnames) }
+	/* DWARF 2 */
+	.debug_info	0 : { *(.debug_info .gnu.linkonce.wi.*) }
+	.debug_abbrev	0 : { *(.debug_abbrev) }
+	.debug_line	0 : { *(.debug_line) }
+	.debug_frame	0 : { *(.debug_frame) }
+	.debug_str	0 : { *(.debug_str) }
+	.debug_loc	0 : { *(.debug_loc) }
+	.debug_macinfo	0 : { *(.debug_macinfo) }
+	/* SGI/MIPS DWARF 2 extensions */
+	.debug_weaknames 0 : { *(.debug_weaknames) }
+	.debug_funcnames 0 : { *(.debug_funcnames) }
+	.debug_typenames 0 : { *(.debug_typenames) }
+	.debug_varnames  0 : { *(.debug_varnames) }
+	/* DWARF 3 */
+	.debug_pubtypes 0 : { *(.debug_pubtypes) }
+	.debug_ranges	0 : { *(.debug_ranges) }
+	.gnu.attributes 0 : { KEEP (*(.gnu.attributes)) }
+
+	. = ALIGN(4096);
+	PROVIDE(_vdso_data = .);
+
+	/DISCARD/	: {
+		*(.note.GNU-stack)
+		*(.branch_lt)
+		*(.data .data.* .gnu.linkonce.d.* .sdata*)
+		*(.bss .sbss .dynbss .dynsbss)
+	}
+}
+
+/*
+ * Very old versions of ld do not recognize this name token; use the constant.
+ */
+#define PT_GNU_EH_FRAME	0x6474e550
+
+/*
+ * We must supply the ELF program headers explicitly to get just one
+ * PT_LOAD segment, and set the flags explicitly to make segments read-only.
+ */
+PHDRS
+{
+	text		PT_LOAD FILEHDR PHDRS FLAGS(5);	/* PF_R|PF_X */
+	dynamic		PT_DYNAMIC FLAGS(4);		/* PF_R */
+	note		PT_NOTE FLAGS(4);		/* PF_R */
+	eh_frame_hdr	PT_GNU_EH_FRAME;
+}
+
+/*
+ * This controls what symbols we export from the DSO.
+ */
+VERSION
+{
+	VDSO_VERSION_STRING {
+	global:
+		/*
+		 * Has to be there for the kernel to find
+		 */
+		__kernel_gettimeofday;
+		__kernel_clock_gettime;
+		__kernel_clock_getres;
+
+	local: *;
+	};
+}
diff --git a/arch/s390/kernel/vdso64/vdso64_wrapper.S b/arch/s390/kernel/vdso64/vdso64_wrapper.S
new file mode 100644
index 000000000..c245842b5
--- /dev/null
+++ b/arch/s390/kernel/vdso64/vdso64_wrapper.S
@@ -0,0 +1,14 @@
+#include <linux/init.h>
+#include <linux/linkage.h>
+#include <asm/page.h>
+
+	__PAGE_ALIGNED_DATA
+
+	.globl vdso64_start, vdso64_end
+	.balign PAGE_SIZE
+vdso64_start:
+	.incbin "arch/s390/kernel/vdso64/vdso64.so"
+	.balign PAGE_SIZE
+vdso64_end:
+
+	.previous
diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S
new file mode 100644
index 000000000..445657fe6
--- /dev/null
+++ b/arch/s390/kernel/vmlinux.lds.S
@@ -0,0 +1,93 @@
+/* ld script to make s390 Linux kernel
+ * Written by Martin Schwidefsky (schwidefsky@de.ibm.com)
+ */
+
+#include <asm/thread_info.h>
+#include <asm/page.h>
+#include <asm-generic/vmlinux.lds.h>
+
+OUTPUT_FORMAT("elf64-s390", "elf64-s390", "elf64-s390")
+OUTPUT_ARCH(s390:64-bit)
+ENTRY(startup)
+jiffies = jiffies_64;
+
+PHDRS {
+	text PT_LOAD FLAGS(5);	/* R_E */
+	data PT_LOAD FLAGS(7);	/* RWE */
+	note PT_NOTE FLAGS(0);	/* ___ */
+}
+
+SECTIONS
+{
+	. = 0x00000000;
+	.text : {
+	_text = .;		/* Text and read-only data */
+		HEAD_TEXT
+		TEXT_TEXT
+		SCHED_TEXT
+		LOCK_TEXT
+		KPROBES_TEXT
+		IRQENTRY_TEXT
+		*(.fixup)
+		*(.gnu.warning)
+	} :text = 0x0700
+
+	_etext = .;		/* End of text section */
+
+	NOTES :text :note
+
+	.dummy : { *(.dummy) } :data
+
+	RO_DATA_SECTION(PAGE_SIZE)
+
+#ifdef CONFIG_SHARED_KERNEL
+	. = ALIGN(0x100000);	/* VM shared segments are 1MB aligned */
+#endif
+
+	. = ALIGN(PAGE_SIZE);
+	_eshared = .;		/* End of shareable data */
+	_sdata = .;		/* Start of data section */
+
+	EXCEPTION_TABLE(16) :data
+
+	RW_DATA_SECTION(0x100, PAGE_SIZE, THREAD_SIZE)
+
+	_edata = .;		/* End of data section */
+
+	/* will be freed after init */
+	. = ALIGN(PAGE_SIZE);	/* Init code and data */
+	__init_begin = .;
+
+	INIT_TEXT_SECTION(PAGE_SIZE)
+
+	/*
+	 * .exit.text is discarded at runtime, not link time,
+	 * to deal with references from __bug_table
+	*/
+	.exit.text : {
+		EXIT_TEXT
+	}
+
+	.exit.data : {
+		EXIT_DATA
+	}
+
+	/* early.c uses stsi, which requires page aligned data. */
+	. = ALIGN(PAGE_SIZE);
+	INIT_DATA_SECTION(0x100)
+
+	PERCPU_SECTION(0x100)
+	. = ALIGN(PAGE_SIZE);
+	__init_end = .;		/* freed after init ends here */
+
+	BSS_SECTION(0, 2, 0)
+
+	_end = . ;
+
+	/* Debugging sections.	*/
+	STABS_DEBUG
+	DWARF_DEBUG
+
+	/* Sections to be discarded */
+	DISCARDS
+}
diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c
new file mode 100644
index 000000000..e53d3595a
--- /dev/null
+++ b/arch/s390/kernel/vtime.c
@@ -0,0 +1,379 @@
+/*
+ *    Virtual cpu timer based timer functions.
+ *
+ *    Copyright IBM Corp. 2004, 2012
+ *    Author(s): Jan Glauber <jan.glauber@de.ibm.com>
+ */
+
+#include <linux/kernel_stat.h>
+#include <linux/export.h>
+#include <linux/kernel.h>
+#include <linux/timex.h>
+#include <linux/types.h>
+#include <linux/time.h>
+
+#include <asm/cputime.h>
+#include <asm/vtimer.h>
+#include <asm/vtime.h>
+#include <asm/cpu_mf.h>
+#include <asm/smp.h>
+
+static void virt_timer_expire(void);
+
+static LIST_HEAD(virt_timer_list);
+static DEFINE_SPINLOCK(virt_timer_lock);
+static atomic64_t virt_timer_current;
+static atomic64_t virt_timer_elapsed;
+
+static DEFINE_PER_CPU(u64, mt_cycles[32]);
+static DEFINE_PER_CPU(u64, mt_scaling_mult) = { 1 };
+static DEFINE_PER_CPU(u64, mt_scaling_div) = { 1 };
+
+static inline u64 get_vtimer(void)
+{
+	u64 timer;
+
+	asm volatile("stpt %0" : "=m" (timer));
+	return timer;
+}
+
+static inline void set_vtimer(u64 expires)
+{
+	u64 timer;
+
+	asm volatile(
+		"	stpt	%0\n"	/* Store current cpu timer value */
+		"	spt	%1"	/* Set new value imm. afterwards */
+		: "=m" (timer) : "m" (expires));
+	S390_lowcore.system_timer += S390_lowcore.last_update_timer - timer;
+	S390_lowcore.last_update_timer = expires;
+}
+
+static inline int virt_timer_forward(u64 elapsed)
+{
+	BUG_ON(!irqs_disabled());
+
+	if (list_empty(&virt_timer_list))
+		return 0;
+	elapsed = atomic64_add_return(elapsed, &virt_timer_elapsed);
+	return elapsed >= atomic64_read(&virt_timer_current);
+}
+
+/*
+ * Update process times based on virtual cpu times stored by entry.S
+ * to the lowcore fields user_timer, system_timer & steal_clock.
+ */
+static int do_account_vtime(struct task_struct *tsk, int hardirq_offset)
+{
+	struct thread_info *ti = task_thread_info(tsk);
+	u64 timer, clock, user, system, steal;
+	u64 user_scaled, system_scaled;
+	int i;
+
+	timer = S390_lowcore.last_update_timer;
+	clock = S390_lowcore.last_update_clock;
+	asm volatile(
+		"	stpt	%0\n"	/* Store current cpu timer value */
+#ifdef CONFIG_HAVE_MARCH_Z9_109_FEATURES
+		"	stckf	%1"	/* Store current tod clock value */
+#else
+		"	stck	%1"	/* Store current tod clock value */
+#endif
+		: "=m" (S390_lowcore.last_update_timer),
+		  "=m" (S390_lowcore.last_update_clock));
+	S390_lowcore.system_timer += timer - S390_lowcore.last_update_timer;
+	S390_lowcore.steal_timer += S390_lowcore.last_update_clock - clock;
+
+	/* Do MT utilization calculation */
+	if (smp_cpu_mtid) {
+		u64 cycles_new[32], *cycles_old;
+		u64 delta, mult, div;
+
+		cycles_old = this_cpu_ptr(mt_cycles);
+		if (stcctm5(smp_cpu_mtid + 1, cycles_new) < 2) {
+			mult = div = 0;
+			for (i = 0; i <= smp_cpu_mtid; i++) {
+				delta = cycles_new[i] - cycles_old[i];
+				mult += delta;
+				div += (i + 1) * delta;
+			}
+			if (mult > 0) {
+				/* Update scaling factor */
+				__this_cpu_write(mt_scaling_mult, mult);
+				__this_cpu_write(mt_scaling_div, div);
+				memcpy(cycles_old, cycles_new,
+				       sizeof(u64) * (smp_cpu_mtid + 1));
+			}
+		}
+	}
+
+	user = S390_lowcore.user_timer - ti->user_timer;
+	S390_lowcore.steal_timer -= user;
+	ti->user_timer = S390_lowcore.user_timer;
+
+	system = S390_lowcore.system_timer - ti->system_timer;
+	S390_lowcore.steal_timer -= system;
+	ti->system_timer = S390_lowcore.system_timer;
+
+	user_scaled = user;
+	system_scaled = system;
+	/* Do MT utilization scaling */
+	if (smp_cpu_mtid) {
+		u64 mult = __this_cpu_read(mt_scaling_mult);
+		u64 div = __this_cpu_read(mt_scaling_div);
+
+		user_scaled = (user_scaled * mult) / div;
+		system_scaled = (system_scaled * mult) / div;
+	}
+	account_user_time(tsk, user, user_scaled);
+	account_system_time(tsk, hardirq_offset, system, system_scaled);
+
+	steal = S390_lowcore.steal_timer;
+	if ((s64) steal > 0) {
+		S390_lowcore.steal_timer = 0;
+		account_steal_time(steal);
+	}
+
+	return virt_timer_forward(user + system);
+}
+
+void vtime_task_switch(struct task_struct *prev)
+{
+	struct thread_info *ti;
+
+	do_account_vtime(prev, 0);
+	ti = task_thread_info(prev);
+	ti->user_timer = S390_lowcore.user_timer;
+	ti->system_timer = S390_lowcore.system_timer;
+	ti = task_thread_info(current);
+	S390_lowcore.user_timer = ti->user_timer;
+	S390_lowcore.system_timer = ti->system_timer;
+}
+
+/*
+ * In s390, accounting pending user time also implies
+ * accounting system time in order to correctly compute
+ * the stolen time accounting.
+ */
+void vtime_account_user(struct task_struct *tsk)
+{
+	if (do_account_vtime(tsk, HARDIRQ_OFFSET))
+		virt_timer_expire();
+}
+
+/*
+ * Update process times based on virtual cpu times stored by entry.S
+ * to the lowcore fields user_timer, system_timer & steal_clock.
+ */
+void vtime_account_irq_enter(struct task_struct *tsk)
+{
+	struct thread_info *ti = task_thread_info(tsk);
+	u64 timer, system, system_scaled;
+
+	timer = S390_lowcore.last_update_timer;
+	S390_lowcore.last_update_timer = get_vtimer();
+	S390_lowcore.system_timer += timer - S390_lowcore.last_update_timer;
+
+	system = S390_lowcore.system_timer - ti->system_timer;
+	S390_lowcore.steal_timer -= system;
+	ti->system_timer = S390_lowcore.system_timer;
+	system_scaled = system;
+	/* Do MT utilization scaling */
+	if (smp_cpu_mtid) {
+		u64 mult = __this_cpu_read(mt_scaling_mult);
+		u64 div = __this_cpu_read(mt_scaling_div);
+
+		system_scaled = (system_scaled * mult) / div;
+	}
+	account_system_time(tsk, 0, system, system_scaled);
+
+	virt_timer_forward(system);
+}
+EXPORT_SYMBOL_GPL(vtime_account_irq_enter);
+
+void vtime_account_system(struct task_struct *tsk)
+__attribute__((alias("vtime_account_irq_enter")));
+EXPORT_SYMBOL_GPL(vtime_account_system);
+
+/*
+ * Sorted add to a list. List is linear searched until first bigger
+ * element is found.
+ */
+static void list_add_sorted(struct vtimer_list *timer, struct list_head *head)
+{
+	struct vtimer_list *tmp;
+
+	list_for_each_entry(tmp, head, entry) {
+		if (tmp->expires > timer->expires) {
+			list_add_tail(&timer->entry, &tmp->entry);
+			return;
+		}
+	}
+	list_add_tail(&timer->entry, head);
+}
+
+/*
+ * Handler for expired virtual CPU timer.
+ */
+static void virt_timer_expire(void)
+{
+	struct vtimer_list *timer, *tmp;
+	unsigned long elapsed;
+	LIST_HEAD(cb_list);
+
+	/* walk timer list, fire all expired timers */
+	spin_lock(&virt_timer_lock);
+	elapsed = atomic64_read(&virt_timer_elapsed);
+	list_for_each_entry_safe(timer, tmp, &virt_timer_list, entry) {
+		if (timer->expires < elapsed)
+			/* move expired timer to the callback queue */
+			list_move_tail(&timer->entry, &cb_list);
+		else
+			timer->expires -= elapsed;
+	}
+	if (!list_empty(&virt_timer_list)) {
+		timer = list_first_entry(&virt_timer_list,
+					 struct vtimer_list, entry);
+		atomic64_set(&virt_timer_current, timer->expires);
+	}
+	atomic64_sub(elapsed, &virt_timer_elapsed);
+	spin_unlock(&virt_timer_lock);
+
+	/* Do callbacks and recharge periodic timers */
+	list_for_each_entry_safe(timer, tmp, &cb_list, entry) {
+		list_del_init(&timer->entry);
+		timer->function(timer->data);
+		if (timer->interval) {
+			/* Recharge interval timer */
+			timer->expires = timer->interval +
+				atomic64_read(&virt_timer_elapsed);
+			spin_lock(&virt_timer_lock);
+			list_add_sorted(timer, &virt_timer_list);
+			spin_unlock(&virt_timer_lock);
+		}
+	}
+}
+
+void init_virt_timer(struct vtimer_list *timer)
+{
+	timer->function = NULL;
+	INIT_LIST_HEAD(&timer->entry);
+}
+EXPORT_SYMBOL(init_virt_timer);
+
+static inline int vtimer_pending(struct vtimer_list *timer)
+{
+	return !list_empty(&timer->entry);
+}
+
+static void internal_add_vtimer(struct vtimer_list *timer)
+{
+	if (list_empty(&virt_timer_list)) {
+		/* First timer, just program it. */
+		atomic64_set(&virt_timer_current, timer->expires);
+		atomic64_set(&virt_timer_elapsed, 0);
+		list_add(&timer->entry, &virt_timer_list);
+	} else {
+		/* Update timer against current base. */
+		timer->expires += atomic64_read(&virt_timer_elapsed);
+		if (likely((s64) timer->expires <
+			   (s64) atomic64_read(&virt_timer_current)))
+			/* The new timer expires before the current timer. */
+			atomic64_set(&virt_timer_current, timer->expires);
+		/* Insert new timer into the list. */
+		list_add_sorted(timer, &virt_timer_list);
+	}
+}
+
+static void __add_vtimer(struct vtimer_list *timer, int periodic)
+{
+	unsigned long flags;
+
+	timer->interval = periodic ? timer->expires : 0;
+	spin_lock_irqsave(&virt_timer_lock, flags);
+	internal_add_vtimer(timer);
+	spin_unlock_irqrestore(&virt_timer_lock, flags);
+}
+
+/*
+ * add_virt_timer - add an oneshot virtual CPU timer
+ */
+void add_virt_timer(struct vtimer_list *timer)
+{
+	__add_vtimer(timer, 0);
+}
+EXPORT_SYMBOL(add_virt_timer);
+
+/*
+ * add_virt_timer_int - add an interval virtual CPU timer
+ */
+void add_virt_timer_periodic(struct vtimer_list *timer)
+{
+	__add_vtimer(timer, 1);
+}
+EXPORT_SYMBOL(add_virt_timer_periodic);
+
+static int __mod_vtimer(struct vtimer_list *timer, u64 expires, int periodic)
+{
+	unsigned long flags;
+	int rc;
+
+	BUG_ON(!timer->function);
+
+	if (timer->expires == expires && vtimer_pending(timer))
+		return 1;
+	spin_lock_irqsave(&virt_timer_lock, flags);
+	rc = vtimer_pending(timer);
+	if (rc)
+		list_del_init(&timer->entry);
+	timer->interval = periodic ? expires : 0;
+	timer->expires = expires;
+	internal_add_vtimer(timer);
+	spin_unlock_irqrestore(&virt_timer_lock, flags);
+	return rc;
+}
+
+/*
+ * returns whether it has modified a pending timer (1) or not (0)
+ */
+int mod_virt_timer(struct vtimer_list *timer, u64 expires)
+{
+	return __mod_vtimer(timer, expires, 0);
+}
+EXPORT_SYMBOL(mod_virt_timer);
+
+/*
+ * returns whether it has modified a pending timer (1) or not (0)
+ */
+int mod_virt_timer_periodic(struct vtimer_list *timer, u64 expires)
+{
+	return __mod_vtimer(timer, expires, 1);
+}
+EXPORT_SYMBOL(mod_virt_timer_periodic);
+
+/*
+ * Delete a virtual timer.
+ *
+ * returns whether the deleted timer was pending (1) or not (0)
+ */
+int del_virt_timer(struct vtimer_list *timer)
+{
+	unsigned long flags;
+
+	if (!vtimer_pending(timer))
+		return 0;
+	spin_lock_irqsave(&virt_timer_lock, flags);
+	list_del_init(&timer->entry);
+	spin_unlock_irqrestore(&virt_timer_lock, flags);
+	return 1;
+}
+EXPORT_SYMBOL(del_virt_timer);
+
+/*
+ * Start the virtual CPU timer on the current CPU.
+ */
+void vtime_init(void)
+{
+	/* set initial cpu timer */
+	set_vtimer(VTIMER_MAX_SLICE);
+}