Merge branch 'next' into for-linus

65 files changed, 2388 insertions, 2227 deletions

diff --git a/arch/s390/Kbuild b/arch/s390/Kbuild
index ae4b01060edd..9858476fa0fe 100644
--- a/arch/s390/Kbuild
+++ b/arch/s390/Kbuild
@@ -1,6 +1,7 @@
-obj-y += kernel/
-obj-y += mm/
-obj-y += crypto/
-obj-y += appldata/
-obj-y += hypfs/
-obj-y += kvm/
+obj-y				+= kernel/
+obj-y				+= mm/
+obj-$(CONFIG_KVM)		+= kvm/
+obj-$(CONFIG_CRYPTO_HW)		+= crypto/
+obj-$(CONFIG_S390_HYPFS_FS)	+= hypfs/
+obj-$(CONFIG_APPLDATA_BASE)	+= appldata/
+obj-$(CONFIG_MATHEMU)		+= math-emu/
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 373679b3744a..6d99a5fcc090 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -87,11 +87,13 @@ config S390
 	select HAVE_KERNEL_LZMA
 	select HAVE_KERNEL_LZO
 	select HAVE_KERNEL_XZ
-	select HAVE_GET_USER_PAGES_FAST
 	select HAVE_ARCH_MUTEX_CPU_RELAX
 	select HAVE_ARCH_JUMP_LABEL if !MARCH_G5
 	select HAVE_RCU_TABLE_FREE if SMP
 	select ARCH_SAVE_PAGE_KEYS if HIBERNATION
+	select HAVE_MEMBLOCK
+	select HAVE_MEMBLOCK_NODE_MAP
+	select ARCH_DISCARD_MEMBLOCK
 	select ARCH_INLINE_SPIN_TRYLOCK
 	select ARCH_INLINE_SPIN_TRYLOCK_BH
 	select ARCH_INLINE_SPIN_LOCK
@@ -191,18 +193,13 @@ config HOTPLUG_CPU
 	  Say N if you want to disable CPU hotplug.
 
 config SCHED_MC
-	def_bool y
-	prompt "Multi-core scheduler support"
-	depends on SMP
-	help
-	  Multi-core scheduler support improves the CPU scheduler's decision
-	  making when dealing with multi-core CPU chips at a cost of slightly
-	  increased overhead in some places.
+	def_bool n
 
 config SCHED_BOOK
 	def_bool y
 	prompt "Book scheduler support"
-	depends on SMP && SCHED_MC
+	depends on SMP
+	select SCHED_MC
 	help
 	  Book scheduler support improves the CPU scheduler's decision making
 	  when dealing with machines that have several books.
@@ -230,6 +227,9 @@ config COMPAT
 config SYSVIPC_COMPAT
 	def_bool y if COMPAT && SYSVIPC
 
+config KEYS_COMPAT
+	def_bool y if COMPAT && KEYS
+
 config AUDIT_ARCH
 	def_bool y
 
@@ -345,9 +345,6 @@ config WARN_DYNAMIC_STACK
 
 	  Say N if you are unsure.
 
-config ARCH_POPULATES_NODE_MAP
-	def_bool y
-
 comment "Kernel preemption"
 
 source "kernel/Kconfig.preempt"
diff --git a/arch/s390/Makefile b/arch/s390/Makefile
index 27a0b5df5ead..0ad2f1e1ce9e 100644
--- a/arch/s390/Makefile
+++ b/arch/s390/Makefile
@@ -88,7 +88,6 @@ KBUILD_CFLAGS	+= -pipe -fno-strength-reduce -Wno-sign-compare
 KBUILD_AFLAGS	+= $(aflags-y)
 
 OBJCOPYFLAGS	:= -O binary
-LDFLAGS_vmlinux := -e start
 
 head-y		:= arch/s390/kernel/head.o
 head-y		+= arch/s390/kernel/$(if $(CONFIG_64BIT),head64.o,head31.o)
@@ -99,7 +98,6 @@ core-y		+= arch/s390/
 
 libs-y		+= arch/s390/lib/
 drivers-y	+= drivers/s390/
-drivers-$(CONFIG_MATHEMU) += arch/s390/math-emu/
 
 # must be linked after kernel
 drivers-$(CONFIG_OPROFILE)	+= arch/s390/oprofile/
diff --git a/arch/s390/appldata/appldata_os.c b/arch/s390/appldata/appldata_os.c
index 92f1cb745d69..4de031d6b76c 100644
--- a/arch/s390/appldata/appldata_os.c
+++ b/arch/s390/appldata/appldata_os.c
@@ -115,21 +115,21 @@ static void appldata_get_os_data(void *data)
 	j = 0;
 	for_each_online_cpu(i) {
 		os_data->os_cpu[j].per_cpu_user =
-			cputime_to_jiffies(kstat_cpu(i).cpustat.user);
+			cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_USER]);
 		os_data->os_cpu[j].per_cpu_nice =
-			cputime_to_jiffies(kstat_cpu(i).cpustat.nice);
+			cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_NICE]);
 		os_data->os_cpu[j].per_cpu_system =
-			cputime_to_jiffies(kstat_cpu(i).cpustat.system);
+			cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_SYSTEM]);
 		os_data->os_cpu[j].per_cpu_idle =
-			cputime_to_jiffies(kstat_cpu(i).cpustat.idle);
+			cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_IDLE]);
 		os_data->os_cpu[j].per_cpu_irq =
-			cputime_to_jiffies(kstat_cpu(i).cpustat.irq);
+			cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_IRQ]);
 		os_data->os_cpu[j].per_cpu_softirq =
-			cputime_to_jiffies(kstat_cpu(i).cpustat.softirq);
+			cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_SOFTIRQ]);
 		os_data->os_cpu[j].per_cpu_iowait =
-			cputime_to_jiffies(kstat_cpu(i).cpustat.iowait);
+			cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_IOWAIT]);
 		os_data->os_cpu[j].per_cpu_steal =
-			cputime_to_jiffies(kstat_cpu(i).cpustat.steal);
+			cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_STEAL]);
 		os_data->os_cpu[j].cpu_id = i;
 		j++;
 	}
diff --git a/arch/s390/boot/Makefile b/arch/s390/boot/Makefile
index 635d677d3281..f2737a005afc 100644
--- a/arch/s390/boot/Makefile
+++ b/arch/s390/boot/Makefile
@@ -23,4 +23,4 @@ $(obj)/compressed/vmlinux: FORCE
 
 install: $(CONFIGURE) $(obj)/image
 	sh -x  $(srctree)/$(obj)/install.sh $(KERNELRELEASE) $(obj)/image \
-	      System.map Kerntypes "$(INSTALL_PATH)"
+	      System.map "$(INSTALL_PATH)"
diff --git a/arch/s390/hypfs/inode.c b/arch/s390/hypfs/inode.c
index 481f4f76f664..8a2a887478cc 100644
--- a/arch/s390/hypfs/inode.c
+++ b/arch/s390/hypfs/inode.c
@@ -97,7 +97,7 @@ static void hypfs_delete_tree(struct dentry *root)
 	}
 }
 
-static struct inode *hypfs_make_inode(struct super_block *sb, int mode)
+static struct inode *hypfs_make_inode(struct super_block *sb, umode_t mode)
 {
 	struct inode *ret = new_inode(sb);
 
@@ -107,7 +107,7 @@ static struct inode *hypfs_make_inode(struct super_block *sb, int mode)
 		ret->i_uid = hypfs_info->uid;
 		ret->i_gid = hypfs_info->gid;
 		ret->i_atime = ret->i_mtime = ret->i_ctime = CURRENT_TIME;
-		if (mode & S_IFDIR)
+		if (S_ISDIR(mode))
 			set_nlink(ret, 2);
 	}
 	return ret;
@@ -259,9 +259,9 @@ static int hypfs_parse_options(char *options, struct super_block *sb)
 	return 0;
 }
 
-static int hypfs_show_options(struct seq_file *s, struct vfsmount *mnt)
+static int hypfs_show_options(struct seq_file *s, struct dentry *root)
 {
-	struct hypfs_sb_info *hypfs_info = mnt->mnt_sb->s_fs_info;
+	struct hypfs_sb_info *hypfs_info = root->d_sb->s_fs_info;
 
 	seq_printf(s, ",uid=%u", hypfs_info->uid);
 	seq_printf(s, ",gid=%u", hypfs_info->gid);
@@ -333,7 +333,7 @@ static void hypfs_kill_super(struct super_block *sb)
 
 static struct dentry *hypfs_create_file(struct super_block *sb,
 					struct dentry *parent, const char *name,
-					char *data, mode_t mode)
+					char *data, umode_t mode)
 {
 	struct dentry *dentry;
 	struct inode *inode;
@@ -350,13 +350,13 @@ static struct dentry *hypfs_create_file(struct super_block *sb,
 		dentry = ERR_PTR(-ENOMEM);
 		goto fail;
 	}
-	if (mode & S_IFREG) {
+	if (S_ISREG(mode)) {
 		inode->i_fop = &hypfs_file_ops;
 		if (data)
 			inode->i_size = strlen(data);
 		else
 			inode->i_size = 0;
-	} else if (mode & S_IFDIR) {
+	} else if (S_ISDIR(mode)) {
 		inode->i_op = &simple_dir_inode_operations;
 		inode->i_fop = &simple_dir_operations;
 		inc_nlink(parent->d_inode);
diff --git a/arch/s390/include/asm/chpid.h b/arch/s390/include/asm/chpid.h
index fc71d8a6709b..8e88e2221771 100644
--- a/arch/s390/include/asm/chpid.h
+++ b/arch/s390/include/asm/chpid.h
@@ -6,7 +6,7 @@
  */
 
 #ifndef _ASM_S390_CHPID_H
-#define _ASM_S390_CHPID_H _ASM_S390_CHPID_H
+#define _ASM_S390_CHPID_H
 
 #include <linux/string.h>
 #include <linux/types.h>
diff --git a/arch/s390/include/asm/compat.h b/arch/s390/include/asm/compat.h
index 2e49748b27da..234f1d859cea 100644
--- a/arch/s390/include/asm/compat.h
+++ b/arch/s390/include/asm/compat.h
@@ -172,13 +172,6 @@ static inline int is_compat_task(void)
 	return is_32bit_task();
 }
 
-#else
-
-static inline int is_compat_task(void)
-{
-	return 0;
-}
-
 #endif
 
 static inline void __user *arch_compat_alloc_user_space(long len)
diff --git a/arch/s390/include/asm/cputime.h b/arch/s390/include/asm/cputime.h
index 081434878296..c23c3900c304 100644
--- a/arch/s390/include/asm/cputime.h
+++ b/arch/s390/include/asm/cputime.h
@@ -16,114 +16,100 @@
 
 /* We want to use full resolution of the CPU timer: 2**-12 micro-seconds. */
 
-typedef unsigned long long cputime_t;
-typedef unsigned long long cputime64_t;
+typedef unsigned long long __nocast cputime_t;
+typedef unsigned long long __nocast cputime64_t;
 
-#ifndef __s390x__
-
-static inline unsigned int
-__div(unsigned long long n, unsigned int base)
+static inline unsigned long __div(unsigned long long n, unsigned long base)
 {
+#ifndef __s390x__
 	register_pair rp;
 
 	rp.pair = n >> 1;
 	asm ("dr %0,%1" : "+d" (rp) : "d" (base >> 1));
 	return rp.subreg.odd;
+#else /* __s390x__ */
+	return n / base;
+#endif /* __s390x__ */
 }
 
-#else /* __s390x__ */
+#define cputime_one_jiffy		jiffies_to_cputime(1)
+
+/*
+ * Convert cputime to jiffies and back.
+ */
+static inline unsigned long cputime_to_jiffies(const cputime_t cputime)
+{
+	return __div((__force unsigned long long) cputime, 4096000000ULL / HZ);
+}
 
-static inline unsigned int
-__div(unsigned long long n, unsigned int base)
+static inline cputime_t jiffies_to_cputime(const unsigned int jif)
 {
-	return n / base;
+	return (__force cputime_t)(jif * (4096000000ULL / HZ));
 }
 
-#endif /* __s390x__ */
+static inline u64 cputime64_to_jiffies64(cputime64_t cputime)
+{
+	unsigned long long jif = (__force unsigned long long) cputime;
+	do_div(jif, 4096000000ULL / HZ);
+	return jif;
+}
 
-#define cputime_zero			(0ULL)
-#define cputime_one_jiffy		jiffies_to_cputime(1)
-#define cputime_max			((~0UL >> 1) - 1)
-#define cputime_add(__a, __b)		((__a) +  (__b))
-#define cputime_sub(__a, __b)		((__a) -  (__b))
-#define cputime_div(__a, __n) ({		\
-	unsigned long long __div = (__a);	\
-	do_div(__div,__n);			\
-	__div;					\
-})
-#define cputime_halve(__a)		((__a) >> 1)
-#define cputime_eq(__a, __b)		((__a) == (__b))
-#define cputime_gt(__a, __b)		((__a) >  (__b))
-#define cputime_ge(__a, __b)		((__a) >= (__b))
-#define cputime_lt(__a, __b)		((__a) <  (__b))
-#define cputime_le(__a, __b)		((__a) <= (__b))
-#define cputime_to_jiffies(__ct)	(__div((__ct), 4096000000ULL / HZ))
-#define cputime_to_scaled(__ct)		(__ct)
-#define jiffies_to_cputime(__hz)	((cputime_t)(__hz) * (4096000000ULL / HZ))
-
-#define cputime64_zero			(0ULL)
-#define cputime64_add(__a, __b)		((__a) + (__b))
-#define cputime_to_cputime64(__ct)	(__ct)
-
-static inline u64
-cputime64_to_jiffies64(cputime64_t cputime)
-{
-	do_div(cputime, 4096000000ULL / HZ);
-	return cputime;
+static inline cputime64_t jiffies64_to_cputime64(const u64 jif)
+{
+	return (__force cputime64_t)(jif * (4096000000ULL / HZ));
 }
 
 /*
  * Convert cputime to microseconds and back.
  */
-static inline unsigned int
-cputime_to_usecs(const cputime_t cputime)
+static inline unsigned int cputime_to_usecs(const cputime_t cputime)
 {
-	return cputime_div(cputime, 4096);
+	return (__force unsigned long long) cputime >> 12;
 }
 
-static inline cputime_t
-usecs_to_cputime(const unsigned int m)
+static inline cputime_t usecs_to_cputime(const unsigned int m)
 {
-	return (cputime_t) m * 4096;
+	return (__force cputime_t)(m * 4096ULL);
 }
 
+#define usecs_to_cputime64(m)		usecs_to_cputime(m)
+
 /*
  * Convert cputime to milliseconds and back.
  */
-static inline unsigned int
-cputime_to_secs(const cputime_t cputime)
+static inline unsigned int cputime_to_secs(const cputime_t cputime)
 {
-	return __div(cputime, 2048000000) >> 1;
+	return __div((__force unsigned long long) cputime, 2048000000) >> 1;
 }
 
-static inline cputime_t
-secs_to_cputime(const unsigned int s)
+static inline cputime_t secs_to_cputime(const unsigned int s)
 {
-	return (cputime_t) s * 4096000000ULL;
+	return (__force cputime_t)(s * 4096000000ULL);
 }
 
 /*
  * Convert cputime to timespec and back.
  */
-static inline cputime_t
-timespec_to_cputime(const struct timespec *value)
+static inline cputime_t timespec_to_cputime(const struct timespec *value)
 {
-	return value->tv_nsec * 4096 / 1000 + (u64) value->tv_sec * 4096000000ULL;
+	unsigned long long ret = value->tv_sec * 4096000000ULL;
+	return (__force cputime_t)(ret + value->tv_nsec * 4096 / 1000);
 }
 
-static inline void
-cputime_to_timespec(const cputime_t cputime, struct timespec *value)
+static inline void cputime_to_timespec(const cputime_t cputime,
+				       struct timespec *value)
 {
+	unsigned long long __cputime = (__force unsigned long long) cputime;
 #ifndef __s390x__
 	register_pair rp;
 
-	rp.pair = cputime >> 1;
+	rp.pair = __cputime >> 1;
 	asm ("dr %0,%1" : "+d" (rp) : "d" (2048000000UL));
 	value->tv_nsec = rp.subreg.even * 1000 / 4096;
 	value->tv_sec = rp.subreg.odd;
 #else
-	value->tv_nsec = (cputime % 4096000000ULL) * 1000 / 4096;
-	value->tv_sec = cputime / 4096000000ULL;
+	value->tv_nsec = (__cputime % 4096000000ULL) * 1000 / 4096;
+	value->tv_sec = __cputime / 4096000000ULL;
 #endif
 }
 
@@ -132,50 +118,52 @@ cputime_to_timespec(const cputime_t cputime, struct timespec *value)
  * Since cputime and timeval have the same resolution (microseconds)
  * this is easy.
  */
-static inline cputime_t
-timeval_to_cputime(const struct timeval *value)
+static inline cputime_t timeval_to_cputime(const struct timeval *value)
 {
-	return value->tv_usec * 4096 + (u64) value->tv_sec * 4096000000ULL;
+	unsigned long long ret = value->tv_sec * 4096000000ULL;
+	return (__force cputime_t)(ret + value->tv_usec * 4096ULL);
 }
 
-static inline void
-cputime_to_timeval(const cputime_t cputime, struct timeval *value)
+static inline void cputime_to_timeval(const cputime_t cputime,
+				      struct timeval *value)
 {
+	unsigned long long __cputime = (__force unsigned long long) cputime;
 #ifndef __s390x__
 	register_pair rp;
 
-	rp.pair = cputime >> 1;
+	rp.pair = __cputime >> 1;
 	asm ("dr %0,%1" : "+d" (rp) : "d" (2048000000UL));
 	value->tv_usec = rp.subreg.even / 4096;
 	value->tv_sec = rp.subreg.odd;
 #else
-	value->tv_usec = (cputime % 4096000000ULL) / 4096;
-	value->tv_sec = cputime / 4096000000ULL;
+	value->tv_usec = (__cputime % 4096000000ULL) / 4096;
+	value->tv_sec = __cputime / 4096000000ULL;
 #endif
 }
 
 /*
  * Convert cputime to clock and back.
  */
-static inline clock_t
-cputime_to_clock_t(cputime_t cputime)
+static inline clock_t cputime_to_clock_t(cputime_t cputime)
 {
-	return cputime_div(cputime, 4096000000ULL / USER_HZ);
+	unsigned long long clock = (__force unsigned long long) cputime;
+	do_div(clock, 4096000000ULL / USER_HZ);
+	return clock;
 }
 
-static inline cputime_t
-clock_t_to_cputime(unsigned long x)
+static inline cputime_t clock_t_to_cputime(unsigned long x)
 {
-	return (cputime_t) x * (4096000000ULL / USER_HZ);
+	return (__force cputime_t)(x * (4096000000ULL / USER_HZ));
 }
 
 /*
  * Convert cputime64 to clock.
  */
-static inline clock_t
-cputime64_to_clock_t(cputime64_t cputime)
+static inline clock_t cputime64_to_clock_t(cputime64_t cputime)
 {
-       return cputime_div(cputime, 4096000000ULL / USER_HZ);
+	unsigned long long clock = (__force unsigned long long) cputime;
+	do_div(clock, 4096000000ULL / USER_HZ);
+	return clock;
 }
 
 struct s390_idle_data {
diff --git a/arch/s390/include/asm/debug.h b/arch/s390/include/asm/debug.h
index 18124b75a7ab..9d88db1f55d0 100644
--- a/arch/s390/include/asm/debug.h
+++ b/arch/s390/include/asm/debug.h
@@ -73,7 +73,7 @@ typedef struct debug_info {
 	struct dentry* debugfs_entries[DEBUG_MAX_VIEWS];
 	struct debug_view* views[DEBUG_MAX_VIEWS];	
 	char name[DEBUG_MAX_NAME_LEN];
-	mode_t mode;
+	umode_t mode;
 } debug_info_t;
 
 typedef int (debug_header_proc_t) (debug_info_t* id,
@@ -124,7 +124,7 @@ debug_info_t *debug_register(const char *name, int pages, int nr_areas,
                              int buf_size);
 
 debug_info_t *debug_register_mode(const char *name, int pages, int nr_areas,
-				  int buf_size, mode_t mode, uid_t uid,
+				  int buf_size, umode_t mode, uid_t uid,
 				  gid_t gid);
 
 void debug_unregister(debug_info_t* id);
diff --git a/arch/s390/include/asm/itcw.h b/arch/s390/include/asm/itcw.h
index a9bc5c36b32a..fb1bedd3dc0d 100644
--- a/arch/s390/include/asm/itcw.h
+++ b/arch/s390/include/asm/itcw.h
@@ -6,7 +6,7 @@
  */
 
 #ifndef _ASM_S390_ITCW_H
-#define _ASM_S390_ITCW_H _ASM_S390_ITCW_H
+#define _ASM_S390_ITCW_H
 
 #include <linux/types.h>
 #include <asm/fcx.h>
diff --git a/arch/s390/include/asm/kdebug.h b/arch/s390/include/asm/kdebug.h
index 40db27cd6e60..5c1abd47612a 100644
--- a/arch/s390/include/asm/kdebug.h
+++ b/arch/s390/include/asm/kdebug.h
@@ -22,6 +22,6 @@ enum die_val {
 	DIE_NMI_IPI,
 };
 
-extern void die(const char *, struct pt_regs *, long);
+extern void die(struct pt_regs *, const char *);
 
 #endif
diff --git a/arch/s390/include/asm/kexec.h b/arch/s390/include/asm/kexec.h
index cf4e47b0948c..3f30dac804ea 100644
--- a/arch/s390/include/asm/kexec.h
+++ b/arch/s390/include/asm/kexec.h
@@ -42,6 +42,24 @@
 /* The native architecture */
 #define KEXEC_ARCH KEXEC_ARCH_S390
 
+/*
+ * Size for s390x ELF notes per CPU
+ *
+ * Seven notes plus zero note at the end: prstatus, fpregset, timer,
+ * tod_cmp, tod_reg, control regs, and prefix
+ */
+#define KEXEC_NOTE_BYTES \
+	(ALIGN(sizeof(struct elf_note), 4) * 8 + \
+	 ALIGN(sizeof("CORE"), 4) * 7 + \
+	 ALIGN(sizeof(struct elf_prstatus), 4) + \
+	 ALIGN(sizeof(elf_fpregset_t), 4) + \
+	 ALIGN(sizeof(u64), 4) + \
+	 ALIGN(sizeof(u64), 4) + \
+	 ALIGN(sizeof(u32), 4) + \
+	 ALIGN(sizeof(u64) * 16, 4) + \
+	 ALIGN(sizeof(u32), 4) \
+	)
+
 /* Provide a dummy definition to avoid build failures. */
 static inline void crash_setup_regs(struct pt_regs *newregs,
 					struct pt_regs *oldregs) { }
diff --git a/arch/s390/include/asm/lowcore.h b/arch/s390/include/asm/lowcore.h
index 9e13c7d56cc1..707f2306725b 100644
--- a/arch/s390/include/asm/lowcore.h
+++ b/arch/s390/include/asm/lowcore.h
@@ -97,47 +97,52 @@ struct _lowcore {
 	__u32	gpregs_save_area[16];		/* 0x0180 */
 	__u32	cregs_save_area[16];		/* 0x01c0 */
 
+	/* Save areas. */
+	__u32	save_area_sync[8];		/* 0x0200 */
+	__u32	save_area_async[8];		/* 0x0220 */
+	__u32	save_area_restart[1];		/* 0x0240 */
+	__u8	pad_0x0244[0x0248-0x0244];	/* 0x0244 */
+
 	/* Return psws. */
-	__u32	save_area[16];			/* 0x0200 */
-	psw_t	return_psw;			/* 0x0240 */
-	psw_t	return_mcck_psw;		/* 0x0248 */
+	psw_t	return_psw;			/* 0x0248 */
+	psw_t	return_mcck_psw;		/* 0x0250 */
 
 	/* CPU time accounting values */
-	__u64	sync_enter_timer;		/* 0x0250 */
-	__u64	async_enter_timer;		/* 0x0258 */
-	__u64	mcck_enter_timer;		/* 0x0260 */
-	__u64	exit_timer;			/* 0x0268 */
-	__u64	user_timer;			/* 0x0270 */
-	__u64	system_timer;			/* 0x0278 */
-	__u64	steal_timer;			/* 0x0280 */
-	__u64	last_update_timer;		/* 0x0288 */
-	__u64	last_update_clock;		/* 0x0290 */
+	__u64	sync_enter_timer;		/* 0x0258 */
+	__u64	async_enter_timer;		/* 0x0260 */
+	__u64	mcck_enter_timer;		/* 0x0268 */
+	__u64	exit_timer;			/* 0x0270 */
+	__u64	user_timer;			/* 0x0278 */
+	__u64	system_timer;			/* 0x0280 */
+	__u64	steal_timer;			/* 0x0288 */
+	__u64	last_update_timer;		/* 0x0290 */
+	__u64	last_update_clock;		/* 0x0298 */
 
 	/* Current process. */
-	__u32	current_task;			/* 0x0298 */
-	__u32	thread_info;			/* 0x029c */
-	__u32	kernel_stack;			/* 0x02a0 */
+	__u32	current_task;			/* 0x02a0 */
+	__u32	thread_info;			/* 0x02a4 */
+	__u32	kernel_stack;			/* 0x02a8 */
 
 	/* Interrupt and panic stack. */
-	__u32	async_stack;			/* 0x02a4 */
-	__u32	panic_stack;			/* 0x02a8 */
+	__u32	async_stack;			/* 0x02ac */
+	__u32	panic_stack;			/* 0x02b0 */
 
 	/* Address space pointer. */
-	__u32	kernel_asce;			/* 0x02ac */
-	__u32	user_asce;			/* 0x02b0 */
-	__u32	current_pid;			/* 0x02b4 */
+	__u32	kernel_asce;			/* 0x02b4 */
+	__u32	user_asce;			/* 0x02b8 */
+	__u32	current_pid;			/* 0x02bc */
 
 	/* SMP info area */
-	__u32	cpu_nr;				/* 0x02b8 */
-	__u32	softirq_pending;		/* 0x02bc */
-	__u32	percpu_offset;			/* 0x02c0 */
-	__u32	ext_call_fast;			/* 0x02c4 */
-	__u64	int_clock;			/* 0x02c8 */
-	__u64	mcck_clock;			/* 0x02d0 */
-	__u64	clock_comparator;		/* 0x02d8 */
-	__u32	machine_flags;			/* 0x02e0 */
-	__u32	ftrace_func;			/* 0x02e4 */
-	__u8	pad_0x02e8[0x0300-0x02e8];	/* 0x02e8 */
+	__u32	cpu_nr;				/* 0x02c0 */
+	__u32	softirq_pending;		/* 0x02c4 */
+	__u32	percpu_offset;			/* 0x02c8 */
+	__u32	ext_call_fast;			/* 0x02cc */
+	__u64	int_clock;			/* 0x02d0 */
+	__u64	mcck_clock;			/* 0x02d8 */
+	__u64	clock_comparator;		/* 0x02e0 */
+	__u32	machine_flags;			/* 0x02e8 */
+	__u32	ftrace_func;			/* 0x02ec */
+	__u8	pad_0x02f8[0x0300-0x02f0];	/* 0x02f0 */
 
 	/* Interrupt response block */
 	__u8	irb[64];			/* 0x0300 */
@@ -229,57 +234,62 @@ struct _lowcore {
 	psw_t	mcck_new_psw;			/* 0x01e0 */
 	psw_t	io_new_psw;			/* 0x01f0 */
 
-	/* Entry/exit save area & return psws. */
-	__u64	save_area[16];			/* 0x0200 */
-	psw_t	return_psw;			/* 0x0280 */
-	psw_t	return_mcck_psw;		/* 0x0290 */
+	/* Save areas. */
+	__u64	save_area_sync[8];		/* 0x0200 */
+	__u64	save_area_async[8];		/* 0x0240 */
+	__u64	save_area_restart[1];		/* 0x0280 */
+	__u8	pad_0x0288[0x0290-0x0288];	/* 0x0288 */
+
+	/* Return psws. */
+	psw_t	return_psw;			/* 0x0290 */
+	psw_t	return_mcck_psw;		/* 0x02a0 */
 
 	/* CPU accounting and timing values. */
-	__u64	sync_enter_timer;		/* 0x02a0 */
-	__u64	async_enter_timer;		/* 0x02a8 */
-	__u64	mcck_enter_timer;		/* 0x02b0 */
-	__u64	exit_timer;			/* 0x02b8 */
-	__u64	user_timer;			/* 0x02c0 */
-	__u64	system_timer;			/* 0x02c8 */
-	__u64	steal_timer;			/* 0x02d0 */
-	__u64	last_update_timer;		/* 0x02d8 */
-	__u64	last_update_clock;		/* 0x02e0 */
+	__u64	sync_enter_timer;		/* 0x02b0 */
+	__u64	async_enter_timer;		/* 0x02b8 */
+	__u64	mcck_enter_timer;		/* 0x02c0 */
+	__u64	exit_timer;			/* 0x02c8 */
+	__u64	user_timer;			/* 0x02d0 */
+	__u64	system_timer;			/* 0x02d8 */
+	__u64	steal_timer;			/* 0x02e0 */
+	__u64	last_update_timer;		/* 0x02e8 */
+	__u64	last_update_clock;		/* 0x02f0 */
 
 	/* Current process. */
-	__u64	current_task;			/* 0x02e8 */
-	__u64	thread_info;			/* 0x02f0 */
-	__u64	kernel_stack;			/* 0x02f8 */
+	__u64	current_task;			/* 0x02f8 */
+	__u64	thread_info;			/* 0x0300 */
+	__u64	kernel_stack;			/* 0x0308 */
 
 	/* Interrupt and panic stack. */
-	__u64	async_stack;			/* 0x0300 */
-	__u64	panic_stack;			/* 0x0308 */
+	__u64	async_stack;			/* 0x0310 */
+	__u64	panic_stack;			/* 0x0318 */
 
 	/* Address space pointer. */
-	__u64	kernel_asce;			/* 0x0310 */
-	__u64	user_asce;			/* 0x0318 */
-	__u64	current_pid;			/* 0x0320 */
+	__u64	kernel_asce;			/* 0x0320 */
+	__u64	user_asce;			/* 0x0328 */
+	__u64	current_pid;			/* 0x0330 */
 
 	/* SMP info area */
-	__u32	cpu_nr;				/* 0x0328 */
-	__u32	softirq_pending;		/* 0x032c */
-	__u64	percpu_offset;			/* 0x0330 */
-	__u64	ext_call_fast;			/* 0x0338 */
-	__u64	int_clock;			/* 0x0340 */
-	__u64	mcck_clock;			/* 0x0348 */
-	__u64	clock_comparator;		/* 0x0350 */
-	__u64	vdso_per_cpu_data;		/* 0x0358 */
-	__u64	machine_flags;			/* 0x0360 */
-	__u64	ftrace_func;			/* 0x0368 */
-	__u64	gmap;				/* 0x0370 */
-	__u64	cmf_hpp;			/* 0x0378 */
+	__u32	cpu_nr;				/* 0x0338 */
+	__u32	softirq_pending;		/* 0x033c */
+	__u64	percpu_offset;			/* 0x0340 */
+	__u64	ext_call_fast;			/* 0x0348 */
+	__u64	int_clock;			/* 0x0350 */
+	__u64	mcck_clock;			/* 0x0358 */
+	__u64	clock_comparator;		/* 0x0360 */
+	__u64	vdso_per_cpu_data;		/* 0x0368 */
+	__u64	machine_flags;			/* 0x0370 */
+	__u64	ftrace_func;			/* 0x0378 */
+	__u64	gmap;				/* 0x0380 */
+	__u8	pad_0x0388[0x0400-0x0388];	/* 0x0388 */
 
 	/* Interrupt response block. */
-	__u8	irb[64];			/* 0x0380 */
+	__u8	irb[64];			/* 0x0400 */
 
 	/* Per cpu primary space access list */
-	__u32	paste[16];			/* 0x03c0 */
+	__u32	paste[16];			/* 0x0440 */
 
-	__u8	pad_0x0400[0x0e00-0x0400];	/* 0x0400 */
+	__u8	pad_0x0480[0x0e00-0x0480];	/* 0x0480 */
 
 	/*
 	 * 0xe00 contains the address of the IPL Parameter Information
diff --git a/arch/s390/include/asm/mman.h b/arch/s390/include/asm/mman.h
index 4e9c8ae0a637..d49760e63506 100644
--- a/arch/s390/include/asm/mman.h
+++ b/arch/s390/include/asm/mman.h
@@ -11,9 +11,11 @@
 
 #include <asm-generic/mman.h>
 
-#if defined(__KERNEL__) && !defined(__ASSEMBLY__) && defined(CONFIG_64BIT)
+#if defined(__KERNEL__)
+#if !defined(__ASSEMBLY__) && defined(CONFIG_64BIT)
 int s390_mmap_check(unsigned long addr, unsigned long len);
 #define arch_mmap_check(addr,len,flags)	s390_mmap_check(addr,len)
 #endif
+#endif
 
 #endif /* __S390_MMAN_H__ */
diff --git a/arch/s390/include/asm/percpu.h b/arch/s390/include/asm/percpu.h
index 5325c89a5843..0fbd1899c7b0 100644
--- a/arch/s390/include/asm/percpu.h
+++ b/arch/s390/include/asm/percpu.h
@@ -19,7 +19,7 @@
 #define ARCH_NEEDS_WEAK_PER_CPU
 #endif
 
-#define arch_irqsafe_cpu_to_op(pcp, val, op)				\
+#define arch_this_cpu_to_op(pcp, val, op)				\
 do {									\
 	typedef typeof(pcp) pcp_op_T__;					\
 	pcp_op_T__ old__, new__, prev__;				\
@@ -41,27 +41,27 @@ do {									\
 	preempt_enable();						\
 } while (0)
 
-#define irqsafe_cpu_add_1(pcp, val) arch_irqsafe_cpu_to_op(pcp, val, +)
-#define irqsafe_cpu_add_2(pcp, val) arch_irqsafe_cpu_to_op(pcp, val, +)
-#define irqsafe_cpu_add_4(pcp, val) arch_irqsafe_cpu_to_op(pcp, val, +)
-#define irqsafe_cpu_add_8(pcp, val) arch_irqsafe_cpu_to_op(pcp, val, +)
+#define this_cpu_add_1(pcp, val) arch_this_cpu_to_op(pcp, val, +)
+#define this_cpu_add_2(pcp, val) arch_this_cpu_to_op(pcp, val, +)
+#define this_cpu_add_4(pcp, val) arch_this_cpu_to_op(pcp, val, +)
+#define this_cpu_add_8(pcp, val) arch_this_cpu_to_op(pcp, val, +)
 
-#define irqsafe_cpu_and_1(pcp, val) arch_irqsafe_cpu_to_op(pcp, val, &)
-#define irqsafe_cpu_and_2(pcp, val) arch_irqsafe_cpu_to_op(pcp, val, &)
-#define irqsafe_cpu_and_4(pcp, val) arch_irqsafe_cpu_to_op(pcp, val, &)
-#define irqsafe_cpu_and_8(pcp, val) arch_irqsafe_cpu_to_op(pcp, val, &)
+#define this_cpu_and_1(pcp, val) arch_this_cpu_to_op(pcp, val, &)
+#define this_cpu_and_2(pcp, val) arch_this_cpu_to_op(pcp, val, &)
+#define this_cpu_and_4(pcp, val) arch_this_cpu_to_op(pcp, val, &)
+#define this_cpu_and_8(pcp, val) arch_this_cpu_to_op(pcp, val, &)
 
-#define irqsafe_cpu_or_1(pcp, val) arch_irqsafe_cpu_to_op(pcp, val, |)
-#define irqsafe_cpu_or_2(pcp, val) arch_irqsafe_cpu_to_op(pcp, val, |)
-#define irqsafe_cpu_or_4(pcp, val) arch_irqsafe_cpu_to_op(pcp, val, |)
-#define irqsafe_cpu_or_8(pcp, val) arch_irqsafe_cpu_to_op(pcp, val, |)
+#define this_cpu_or_1(pcp, val) arch_this_cpu_to_op(pcp, val, |)
+#define this_cpu_or_2(pcp, val) arch_this_cpu_to_op(pcp, val, |)
+#define this_cpu_or_4(pcp, val) arch_this_cpu_to_op(pcp, val, |)
+#define this_cpu_or_8(pcp, val) arch_this_cpu_to_op(pcp, val, |)
 
-#define irqsafe_cpu_xor_1(pcp, val) arch_irqsafe_cpu_to_op(pcp, val, ^)
-#define irqsafe_cpu_xor_2(pcp, val) arch_irqsafe_cpu_to_op(pcp, val, ^)
-#define irqsafe_cpu_xor_4(pcp, val) arch_irqsafe_cpu_to_op(pcp, val, ^)
-#define irqsafe_cpu_xor_8(pcp, val) arch_irqsafe_cpu_to_op(pcp, val, ^)
+#define this_cpu_xor_1(pcp, val) arch_this_cpu_to_op(pcp, val, ^)
+#define this_cpu_xor_2(pcp, val) arch_this_cpu_to_op(pcp, val, ^)
+#define this_cpu_xor_4(pcp, val) arch_this_cpu_to_op(pcp, val, ^)
+#define this_cpu_xor_8(pcp, val) arch_this_cpu_to_op(pcp, val, ^)
 
-#define arch_irqsafe_cpu_cmpxchg(pcp, oval, nval)			\
+#define arch_this_cpu_cmpxchg(pcp, oval, nval)			\
 ({									\
 	typedef typeof(pcp) pcp_op_T__;					\
 	pcp_op_T__ ret__;						\
@@ -79,10 +79,10 @@ do {									\
 	ret__;								\
 })
 
-#define irqsafe_cpu_cmpxchg_1(pcp, oval, nval) arch_irqsafe_cpu_cmpxchg(pcp, oval, nval)
-#define irqsafe_cpu_cmpxchg_2(pcp, oval, nval) arch_irqsafe_cpu_cmpxchg(pcp, oval, nval)
-#define irqsafe_cpu_cmpxchg_4(pcp, oval, nval) arch_irqsafe_cpu_cmpxchg(pcp, oval, nval)
-#define irqsafe_cpu_cmpxchg_8(pcp, oval, nval) arch_irqsafe_cpu_cmpxchg(pcp, oval, nval)
+#define this_cpu_cmpxchg_1(pcp, oval, nval) arch_this_cpu_cmpxchg(pcp, oval, nval)
+#define this_cpu_cmpxchg_2(pcp, oval, nval) arch_this_cpu_cmpxchg(pcp, oval, nval)
+#define this_cpu_cmpxchg_4(pcp, oval, nval) arch_this_cpu_cmpxchg(pcp, oval, nval)
+#define this_cpu_cmpxchg_8(pcp, oval, nval) arch_this_cpu_cmpxchg(pcp, oval, nval)
 
 #include <asm-generic/percpu.h>
 
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 524d23b8610c..011358c1b18e 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -128,28 +128,11 @@ static inline int is_zero_pfn(unsigned long pfn)
  * effect, this also makes sure that 64 bit module code cannot be used
  * as system call address.
  */
-
 extern unsigned long VMALLOC_START;
+extern unsigned long VMALLOC_END;
+extern struct page *vmemmap;
 
-#ifndef __s390x__
-#define VMALLOC_SIZE	(96UL << 20)
-#define VMALLOC_END	0x7e000000UL
-#define VMEM_MAP_END	0x80000000UL
-#else /* __s390x__ */
-#define VMALLOC_SIZE	(128UL << 30)
-#define VMALLOC_END	0x3e000000000UL
-#define VMEM_MAP_END	0x40000000000UL
-#endif /* __s390x__ */
-
-/*
- * VMEM_MAX_PHYS is the highest physical address that can be added to the 1:1
- * mapping. This needs to be calculated at compile time since the size of the
- * VMEM_MAP is static but the size of struct page can change.
- */
-#define VMEM_MAX_PAGES	((VMEM_MAP_END - VMALLOC_END) / sizeof(struct page))
-#define VMEM_MAX_PFN	min(VMALLOC_START >> PAGE_SHIFT, VMEM_MAX_PAGES)
-#define VMEM_MAX_PHYS	((VMEM_MAX_PFN << PAGE_SHIFT) & ~((16 << 20) - 1))
-#define vmemmap		((struct page *) VMALLOC_END)
+#define VMEM_MAX_PHYS ((unsigned long) vmemmap)
 
 /*
  * A 31 bit pagetable entry of S390 has following format:
@@ -599,10 +582,10 @@ static inline pgste_t pgste_update_all(pte_t *ptep, pgste_t pgste)
 	skey = page_get_storage_key(address);
 	bits = skey & (_PAGE_CHANGED | _PAGE_REFERENCED);
 	/* Clear page changed & referenced bit in the storage key */
-	if (bits) {
-		skey ^= bits;
-		page_set_storage_key(address, skey, 1);
-	}
+	if (bits & _PAGE_CHANGED)
+		page_set_storage_key(address, skey ^ bits, 1);
+	else if (bits)
+		page_reset_referenced(address);
 	/* Transfer page changed & referenced bit to guest bits in pgste */
 	pgste_val(pgste) |= bits << 48;		/* RCP_GR_BIT & RCP_GC_BIT */
 	/* Get host changed & referenced bits from pgste */
diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index 5f33d37d032c..d25843a6a915 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -80,8 +80,6 @@ struct thread_struct {
 	unsigned int  acrs[NUM_ACRS];
         unsigned long ksp;              /* kernel stack pointer             */
 	mm_segment_t mm_segment;
-        unsigned long prot_addr;        /* address of protection-excep.     */
-        unsigned int trap_no;
 	unsigned long gmap_addr;	/* address of last gmap fault. */
 	struct per_regs per_user;	/* User specified PER registers */
 	struct per_event per_event;	/* Cause of the last PER trap */
@@ -238,7 +236,7 @@ static inline unsigned long __rewind_psw(psw_t psw, unsigned long ilc)
 /*
  * Function to drop a processor into disabled wait state
  */
-static inline void ATTRIB_NORET disabled_wait(unsigned long code)
+static inline void __noreturn disabled_wait(unsigned long code)
 {
         unsigned long ctl_buf;
         psw_t dw_psw;
diff --git a/arch/s390/include/asm/ptrace.h b/arch/s390/include/asm/ptrace.h
index a65846340d51..aeb77f017985 100644
--- a/arch/s390/include/asm/ptrace.h
+++ b/arch/s390/include/asm/ptrace.h
@@ -324,7 +324,8 @@ struct pt_regs
 	psw_t psw;
 	unsigned long gprs[NUM_GPRS];
 	unsigned long orig_gpr2;
-	unsigned int svc_code;
+	unsigned int int_code;
+	unsigned long int_parm_long;
 };
 
 /*
@@ -540,9 +541,13 @@ struct user_regs_struct
 #define user_mode(regs) (((regs)->psw.mask & PSW_MASK_PSTATE) != 0)
 #define instruction_pointer(regs) ((regs)->psw.addr & PSW_ADDR_INSN)
 #define user_stack_pointer(regs)((regs)->gprs[15])
-#define regs_return_value(regs)((regs)->gprs[2])
 #define profile_pc(regs) instruction_pointer(regs)
 
+static inline long regs_return_value(struct pt_regs *regs)
+{
+	return regs->gprs[2];
+}
+
 int regs_query_register_offset(const char *name);
 const char *regs_query_register_name(unsigned int offset);
 unsigned long regs_get_register(struct pt_regs *regs, unsigned int offset);
diff --git a/arch/s390/include/asm/qdio.h b/arch/s390/include/asm/qdio.h
index e63d13dd3bf5..d75c8e78f7e3 100644
--- a/arch/s390/include/asm/qdio.h
+++ b/arch/s390/include/asm/qdio.h
@@ -352,7 +352,7 @@ typedef void qdio_handler_t(struct ccw_device *, unsigned int, int,
  * @no_output_qs: number of output queues
  * @input_handler: handler to be called for input queues
  * @output_handler: handler to be called for output queues
- * @queue_start_poll: polling handlers (one per input queue or NULL)
+ * @queue_start_poll_array: polling handlers (one per input queue or NULL)
  * @int_parm: interruption parameter
  * @input_sbal_addr_array:  address of no_input_qs * 128 pointers
  * @output_sbal_addr_array: address of no_output_qs * 128 pointers
@@ -372,7 +372,8 @@ struct qdio_initialize {
 	unsigned int no_output_qs;
 	qdio_handler_t *input_handler;
 	qdio_handler_t *output_handler;
-	void (**queue_start_poll) (struct ccw_device *, int, unsigned long);
+	void (**queue_start_poll_array) (struct ccw_device *, int,
+					  unsigned long);
 	int scan_threshold;
 	unsigned long int_parm;
 	void **input_sbal_addr_array;
diff --git a/arch/s390/include/asm/sigp.h b/arch/s390/include/asm/sigp.h
index e3bffd4e2d66..7040b8567cd0 100644
--- a/arch/s390/include/asm/sigp.h
+++ b/arch/s390/include/asm/sigp.h
@@ -56,6 +56,7 @@ enum {
 	ec_schedule = 0,
 	ec_call_function,
 	ec_call_function_single,
+	ec_stop_cpu,
 };
 
 /*
diff --git a/arch/s390/include/asm/smp.h b/arch/s390/include/asm/smp.h
index ab47a69fdf07..c32e9123b40c 100644
--- a/arch/s390/include/asm/smp.h
+++ b/arch/s390/include/asm/smp.h
@@ -23,7 +23,6 @@ extern void __cpu_die (unsigned int cpu);
 extern int __cpu_up (unsigned int cpu);
 
 extern struct mutex smp_cpu_state_mutex;
-extern int smp_cpu_polarization[];
 
 extern void arch_send_call_function_single_ipi(int cpu);
 extern void arch_send_call_function_ipi_mask(const struct cpumask *mask);
diff --git a/arch/s390/include/asm/socket.h b/arch/s390/include/asm/socket.h
index fdff1e995c73..67b5c1b14b51 100644
--- a/arch/s390/include/asm/socket.h
+++ b/arch/s390/include/asm/socket.h
@@ -70,4 +70,7 @@
 
 #define SO_RXQ_OVFL             40
 
+#define SO_WIFI_STATUS		41
+#define SCM_WIFI_STATUS		SO_WIFI_STATUS
+
 #endif /* _ASM_SOCKET_H */
diff --git a/arch/s390/include/asm/sparsemem.h b/arch/s390/include/asm/sparsemem.h
index 545d219e6a2d..0fb34027d3f6 100644
--- a/arch/s390/include/asm/sparsemem.h
+++ b/arch/s390/include/asm/sparsemem.h
@@ -4,8 +4,8 @@
 #ifdef CONFIG_64BIT
 
 #define SECTION_SIZE_BITS	28
-#define MAX_PHYSADDR_BITS	42
-#define MAX_PHYSMEM_BITS	42
+#define MAX_PHYSADDR_BITS	46
+#define MAX_PHYSMEM_BITS	46
 
 #else
 
diff --git a/arch/s390/include/asm/syscall.h b/arch/s390/include/asm/syscall.h
index b239ff53b189..fb214dd9b7e0 100644
--- a/arch/s390/include/asm/syscall.h
+++ b/arch/s390/include/asm/syscall.h
@@ -27,7 +27,7 @@ static inline long syscall_get_nr(struct task_struct *task,
 				  struct pt_regs *regs)
 {
 	return test_tsk_thread_flag(task, TIF_SYSCALL) ?
-		(regs->svc_code & 0xffff) : -1;
+		(regs->int_code & 0xffff) : -1;
 }
 
 static inline void syscall_rollback(struct task_struct *task,
diff --git a/arch/s390/include/asm/system.h b/arch/s390/include/asm/system.h
index ef573c1d71a7..d73cc6b60000 100644
--- a/arch/s390/include/asm/system.h
+++ b/arch/s390/include/asm/system.h
@@ -20,8 +20,6 @@
 
 struct task_struct;
 
-extern int sysctl_userprocess_debug;
-
 extern struct task_struct *__switch_to(void *, void *);
 extern void update_per_regs(struct task_struct *task);
 
diff --git a/arch/s390/include/asm/thread_info.h b/arch/s390/include/asm/thread_info.h
index a23183423b14..a73038155e0d 100644
--- a/arch/s390/include/asm/thread_info.h
+++ b/arch/s390/include/asm/thread_info.h
@@ -102,7 +102,6 @@ static inline struct thread_info *current_thread_info(void)
 #define TIF_MEMDIE		18	/* is terminating due to OOM killer */
 #define TIF_RESTORE_SIGMASK	19	/* restore signal mask in do_signal() */
 #define TIF_SINGLE_STEP		20	/* This task is single stepped */
-#define TIF_FREEZE		21	/* thread is freezing for suspend */
 
 #define _TIF_SYSCALL		(1<<TIF_SYSCALL)
 #define _TIF_NOTIFY_RESUME	(1<<TIF_NOTIFY_RESUME)
@@ -119,7 +118,6 @@ static inline struct thread_info *current_thread_info(void)
 #define _TIF_POLLING_NRFLAG	(1<<TIF_POLLING_NRFLAG)
 #define _TIF_31BIT		(1<<TIF_31BIT)
 #define _TIF_SINGLE_STEP	(1<<TIF_SINGLE_STEP)
-#define _TIF_FREEZE		(1<<TIF_FREEZE)
 
 #ifdef CONFIG_64BIT
 #define is_32bit_task()		(test_thread_flag(TIF_31BIT))
diff --git a/arch/s390/include/asm/topology.h b/arch/s390/include/asm/topology.h
index 005d77d8ae2a..0837de80c351 100644
--- a/arch/s390/include/asm/topology.h
+++ b/arch/s390/include/asm/topology.h
@@ -4,6 +4,10 @@
 #include <linux/cpumask.h>
 #include <asm/sysinfo.h>
 
+struct cpu;
+
+#ifdef CONFIG_SCHED_BOOK
+
 extern unsigned char cpu_core_id[NR_CPUS];
 extern cpumask_t cpu_core_map[NR_CPUS];
 
@@ -16,8 +20,6 @@ static inline const struct cpumask *cpu_coregroup_mask(int cpu)
 #define topology_core_cpumask(cpu)	(&cpu_core_map[cpu])
 #define mc_capable()			(1)
 
-#ifdef CONFIG_SCHED_BOOK
-
 extern unsigned char cpu_book_id[NR_CPUS];
 extern cpumask_t cpu_book_map[NR_CPUS];
 
@@ -29,19 +31,45 @@ static inline const struct cpumask *cpu_book_mask(int cpu)
 #define topology_book_id(cpu)		(cpu_book_id[cpu])
 #define topology_book_cpumask(cpu)	(&cpu_book_map[cpu])
 
-#endif /* CONFIG_SCHED_BOOK */
-
+int topology_cpu_init(struct cpu *);
 int topology_set_cpu_management(int fc);
 void topology_schedule_update(void);
 void store_topology(struct sysinfo_15_1_x *info);
+void topology_expect_change(void);
+
+#else /* CONFIG_SCHED_BOOK */
+
+static inline void topology_schedule_update(void) { }
+static inline int topology_cpu_init(struct cpu *cpu) { return 0; }
+static inline void topology_expect_change(void) { }
 
-#define POLARIZATION_UNKNWN	(-1)
+#endif /* CONFIG_SCHED_BOOK */
+
+#define POLARIZATION_UNKNOWN	(-1)
 #define POLARIZATION_HRZ	(0)
 #define POLARIZATION_VL		(1)
 #define POLARIZATION_VM		(2)
 #define POLARIZATION_VH		(3)
 
-#ifdef CONFIG_SMP
+extern int cpu_polarization[];
+
+static inline void cpu_set_polarization(int cpu, int val)
+{
+#ifdef CONFIG_SCHED_BOOK
+	cpu_polarization[cpu] = val;
+#endif
+}
+
+static inline int cpu_read_polarization(int cpu)
+{
+#ifdef CONFIG_SCHED_BOOK
+	return cpu_polarization[cpu];
+#else
+	return POLARIZATION_HRZ;
+#endif
+}
+
+#ifdef CONFIG_SCHED_BOOK
 void s390_init_cpu_topology(void);
 #else
 static inline void s390_init_cpu_topology(void)
diff --git a/arch/s390/include/asm/types.h b/arch/s390/include/asm/types.h
index eeb52ccf499f..05ebbcdbbf6b 100644
--- a/arch/s390/include/asm/types.h
+++ b/arch/s390/include/asm/types.h
@@ -13,8 +13,6 @@
 
 #ifndef __ASSEMBLY__
 
-typedef unsigned short umode_t;
-
 /* A address type so that arithmetic can be done on it & it can be upgraded to
    64 bit when necessary 
 */
diff --git a/arch/s390/include/asm/unistd.h b/arch/s390/include/asm/unistd.h
index 58de4c91c333..8a8008fe7b8f 100644
--- a/arch/s390/include/asm/unistd.h
+++ b/arch/s390/include/asm/unistd.h
@@ -398,6 +398,7 @@
 #define __ARCH_WANT_SYS_SIGNAL
 #define __ARCH_WANT_SYS_UTIME
 #define __ARCH_WANT_SYS_SOCKETCALL
+#define __ARCH_WANT_SYS_IPC
 #define __ARCH_WANT_SYS_FADVISE64
 #define __ARCH_WANT_SYS_GETPGRP
 #define __ARCH_WANT_SYS_LLSEEK
diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile
index dd4f07640919..7d9ec924e7e7 100644
--- a/arch/s390/kernel/Makefile
+++ b/arch/s390/kernel/Makefile
@@ -32,7 +32,8 @@ extra-y				+= head.o init_task.o vmlinux.lds
 extra-y				+= $(if $(CONFIG_64BIT),head64.o,head31.o)
 
 obj-$(CONFIG_MODULES)		+= s390_ksyms.o module.o
-obj-$(CONFIG_SMP)		+= smp.o topology.o
+obj-$(CONFIG_SMP)		+= smp.o
+obj-$(CONFIG_SCHED_BOOK)	+= topology.o
 obj-$(CONFIG_SMP)		+= $(if $(CONFIG_64BIT),switch_cpu64.o, \
 							switch_cpu.o)
 obj-$(CONFIG_HIBERNATION)	+= suspend.o swsusp_asm64.o
diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c
index 751318765e2e..6e6a72e66d60 100644
--- a/arch/s390/kernel/asm-offsets.c
+++ b/arch/s390/kernel/asm-offsets.c
@@ -45,7 +45,8 @@ int main(void)
 	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_SVC_CODE, offsetof(struct pt_regs, svc_code));
+	DEFINE(__PT_INT_CODE, offsetof(struct pt_regs, int_code));
+	DEFINE(__PT_INT_PARM_LONG, offsetof(struct pt_regs, int_parm_long));
 	DEFINE(__PT_SIZE, sizeof(struct pt_regs));
 	BLANK();
 	DEFINE(__SF_BACKCHAIN, offsetof(struct stack_frame, back_chain));
@@ -108,7 +109,9 @@ int main(void)
 	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));
-	DEFINE(__LC_SAVE_AREA, offsetof(struct _lowcore, save_area));
+	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_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));
@@ -150,7 +153,6 @@ int main(void)
 	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_CMF_HPP, offsetof(struct _lowcore, cmf_hpp));
 	DEFINE(__GMAP_ASCE, offsetof(struct gmap, asce));
 #endif /* CONFIG_32BIT */
 	return 0;
diff --git a/arch/s390/kernel/base.S b/arch/s390/kernel/base.S
index f8828d38fa6e..3aa4d00aaf50 100644
--- a/arch/s390/kernel/base.S
+++ b/arch/s390/kernel/base.S
@@ -33,7 +33,7 @@ s390_base_mcck_handler_fn:
 	.previous
 
 ENTRY(s390_base_ext_handler)
-	stmg	%r0,%r15,__LC_SAVE_AREA
+	stmg	%r0,%r15,__LC_SAVE_AREA_ASYNC
 	basr	%r13,0
 0:	aghi	%r15,-STACK_FRAME_OVERHEAD
 	larl	%r1,s390_base_ext_handler_fn
@@ -41,7 +41,7 @@ ENTRY(s390_base_ext_handler)
 	ltgr	%r1,%r1
 	jz	1f
 	basr	%r14,%r1
-1:	lmg	%r0,%r15,__LC_SAVE_AREA
+1:	lmg	%r0,%r15,__LC_SAVE_AREA_ASYNC
 	ni	__LC_EXT_OLD_PSW+1,0xfd	# clear wait state bit
 	lpswe	__LC_EXT_OLD_PSW
 
@@ -53,7 +53,7 @@ s390_base_ext_handler_fn:
 	.previous
 
 ENTRY(s390_base_pgm_handler)
-	stmg	%r0,%r15,__LC_SAVE_AREA
+	stmg	%r0,%r15,__LC_SAVE_AREA_SYNC
 	basr	%r13,0
 0:	aghi	%r15,-STACK_FRAME_OVERHEAD
 	larl	%r1,s390_base_pgm_handler_fn
@@ -61,7 +61,7 @@ ENTRY(s390_base_pgm_handler)
 	ltgr	%r1,%r1
 	jz	1f
 	basr	%r14,%r1
-	lmg	%r0,%r15,__LC_SAVE_AREA
+	lmg	%r0,%r15,__LC_SAVE_AREA_SYNC
 	lpswe	__LC_PGM_OLD_PSW
 1:	lpswe	disabled_wait_psw-0b(%r13)
 
@@ -142,7 +142,7 @@ s390_base_mcck_handler_fn:
 	.previous
 
 ENTRY(s390_base_ext_handler)
-	stm	%r0,%r15,__LC_SAVE_AREA
+	stm	%r0,%r15,__LC_SAVE_AREA_ASYNC
 	basr	%r13,0
 0:	ahi	%r15,-STACK_FRAME_OVERHEAD
 	l	%r1,2f-0b(%r13)
@@ -150,7 +150,7 @@ ENTRY(s390_base_ext_handler)
 	ltr	%r1,%r1
 	jz	1f
 	basr	%r14,%r1
-1:	lm	%r0,%r15,__LC_SAVE_AREA
+1:	lm	%r0,%r15,__LC_SAVE_AREA_ASYNC
 	ni	__LC_EXT_OLD_PSW+1,0xfd	# clear wait state bit
 	lpsw	__LC_EXT_OLD_PSW
 
@@ -164,7 +164,7 @@ s390_base_ext_handler_fn:
 	.previous
 
 ENTRY(s390_base_pgm_handler)
-	stm	%r0,%r15,__LC_SAVE_AREA
+	stm	%r0,%r15,__LC_SAVE_AREA_SYNC
 	basr	%r13,0
 0:	ahi	%r15,-STACK_FRAME_OVERHEAD
 	l	%r1,2f-0b(%r13)
@@ -172,7 +172,7 @@ ENTRY(s390_base_pgm_handler)
 	ltr	%r1,%r1
 	jz	1f
 	basr	%r14,%r1
-	lm	%r0,%r15,__LC_SAVE_AREA
+	lm	%r0,%r15,__LC_SAVE_AREA_SYNC
 	lpsw	__LC_PGM_OLD_PSW
 
 1:	lpsw	disabled_wait_psw-0b(%r13)
diff --git a/arch/s390/kernel/compat_linux.c b/arch/s390/kernel/compat_linux.c
index 84a982898448..ab64bdbab2ae 100644
--- a/arch/s390/kernel/compat_linux.c
+++ b/arch/s390/kernel/compat_linux.c
@@ -278,9 +278,6 @@ asmlinkage long sys32_ipc(u32 call, int first, int second, int third, u32 ptr)
 {
 	if (call >> 16)		/* hack for backward compatibility */
 		return -EINVAL;
-
-	call &= 0xffff;
-
 	switch (call) {
 	case SEMTIMEDOP:
 		return compat_sys_semtimedop(first, compat_ptr(ptr),
diff --git a/arch/s390/kernel/compat_signal.c b/arch/s390/kernel/compat_signal.c
index 4f68c81d3ffa..6fe78c2f95d9 100644
--- a/arch/s390/kernel/compat_signal.c
+++ b/arch/s390/kernel/compat_signal.c
@@ -501,8 +501,12 @@ static int setup_frame32(int sig, struct k_sigaction *ka,
 
 	/* We forgot to include these in the sigcontext.
 	   To avoid breaking binary compatibility, they are passed as args. */
-	regs->gprs[4] = current->thread.trap_no;
-	regs->gprs[5] = current->thread.prot_addr;
+	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;
+	}
 
 	/* Place signal number on stack to allow backtrace from handler.  */
 	if (__put_user(regs->gprs[2], (int __force __user *) &frame->signo))
@@ -544,9 +548,9 @@ static int setup_rt_frame32(int sig, struct k_sigaction *ka, siginfo_t *info,
 	/* Set up to return from userspace.  If provided, use a stub
 	   already in userspace.  */
 	if (ka->sa.sa_flags & SA_RESTORER) {
-		regs->gprs[14] = (__u64) ka->sa.sa_restorer;
+		regs->gprs[14] = (__u64) ka->sa.sa_restorer | PSW32_ADDR_AMODE;
 	} else {
-		regs->gprs[14] = (__u64) frame->retcode;
+		regs->gprs[14] = (__u64) frame->retcode | PSW32_ADDR_AMODE;
 		err |= __put_user(S390_SYSCALL_OPCODE | __NR_rt_sigreturn,
 				  (u16 __force __user *)(frame->retcode));
 	}
diff --git a/arch/s390/kernel/compat_wrapper.S b/arch/s390/kernel/compat_wrapper.S
index 18c51df9fe06..ff605a39cf43 100644
--- a/arch/s390/kernel/compat_wrapper.S
+++ b/arch/s390/kernel/compat_wrapper.S
@@ -662,7 +662,7 @@ ENTRY(sys32_getresuid16_wrapper)
 ENTRY(sys32_poll_wrapper)
 	llgtr	%r2,%r2			# struct pollfd *
 	llgfr	%r3,%r3			# unsigned int
-	lgfr	%r4,%r4			# long
+	lgfr	%r4,%r4			# int
 	jg	sys_poll		# branch to system call
 
 ENTRY(sys32_setresgid16_wrapper)
diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c
index 39f8fd4438fc..c383ce440d99 100644
--- a/arch/s390/kernel/crash_dump.c
+++ b/arch/s390/kernel/crash_dump.c
@@ -11,7 +11,6 @@
 #include <linux/module.h>
 #include <linux/gfp.h>
 #include <linux/slab.h>
-#include <linux/crash_dump.h>
 #include <linux/bootmem.h>
 #include <linux/elf.h>
 #include <asm/ipl.h>
diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c
index 5ad6bc078bfd..6848828b962e 100644
--- a/arch/s390/kernel/debug.c
+++ b/arch/s390/kernel/debug.c
@@ -74,7 +74,7 @@ static ssize_t debug_input(struct file *file, const char __user *user_buf,
 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, mode_t mode);
+			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,
@@ -330,7 +330,7 @@ debug_info_free(debug_info_t* db_info){
 
 static debug_info_t*
 debug_info_create(const char *name, int pages_per_area, int nr_areas,
-		  int buf_size, mode_t mode)
+		  int buf_size, umode_t mode)
 {
 	debug_info_t* rc;
 
@@ -688,7 +688,7 @@ debug_close(struct inode *inode, struct file *file)
  */
 
 debug_info_t *debug_register_mode(const char *name, int pages_per_area,
-				  int nr_areas, int buf_size, mode_t mode,
+				  int nr_areas, int buf_size, umode_t mode,
 				  uid_t uid, gid_t gid)
 {
 	debug_info_t *rc = NULL;
@@ -1090,7 +1090,7 @@ debug_register_view(debug_info_t * id, struct debug_view *view)
 	int rc = 0;
 	int i;
 	unsigned long flags;
-	mode_t mode;
+	umode_t mode;
 	struct dentry *pde;
 
 	if (!id)
diff --git a/arch/s390/kernel/dis.c b/arch/s390/kernel/dis.c
index 45df6d456aa1..e2f847599c8e 100644
--- a/arch/s390/kernel/dis.c
+++ b/arch/s390/kernel/dis.c
@@ -1578,10 +1578,15 @@ void show_code(struct pt_regs *regs)
 	ptr += sprintf(ptr, "%s Code:", mode);
 	hops = 0;
 	while (start < end && hops < 8) {
-		*ptr++ = (start == 32) ? '>' : ' ';
+		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, ONELONG, addr);
-		opsize = insn_length(code[start]);
 		if (start + opsize >= end)
 			break;
 		for (i = 0; i < opsize; i++)
diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c
index c9ffe0025197..52098d6dfaa7 100644
--- a/arch/s390/kernel/early.c
+++ b/arch/s390/kernel/early.c
@@ -434,18 +434,22 @@ static void __init append_to_cmdline(size_t (*ipl_data)(char *, size_t))
 	}
 }
 
-static void __init setup_boot_command_line(void)
+static inline int has_ebcdic_char(const char *str)
 {
 	int i;
 
-	/* convert arch command line to ascii */
-	for (i = 0; i < ARCH_COMMAND_LINE_SIZE; i++)
-		if (COMMAND_LINE[i] & 0x80)
-			break;
-	if (i < ARCH_COMMAND_LINE_SIZE)
-		EBCASC(COMMAND_LINE, ARCH_COMMAND_LINE_SIZE);
-	COMMAND_LINE[ARCH_COMMAND_LINE_SIZE-1] = 0;
+	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);
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index b13157057e02..3705700ed374 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -19,32 +19,22 @@
 #include <asm/unistd.h>
 #include <asm/page.h>
 
-/*
- * Stack layout for the system_call stack entry.
- * The first few entries are identical to the user_regs_struct.
- */
-SP_PTREGS    =	STACK_FRAME_OVERHEAD
-SP_ARGS      =	STACK_FRAME_OVERHEAD + __PT_ARGS
-SP_PSW	     =	STACK_FRAME_OVERHEAD + __PT_PSW
-SP_R0	     =	STACK_FRAME_OVERHEAD + __PT_GPRS
-SP_R1	     =	STACK_FRAME_OVERHEAD + __PT_GPRS + 4
-SP_R2	     =	STACK_FRAME_OVERHEAD + __PT_GPRS + 8
-SP_R3	     =	STACK_FRAME_OVERHEAD + __PT_GPRS + 12
-SP_R4	     =	STACK_FRAME_OVERHEAD + __PT_GPRS + 16
-SP_R5	     =	STACK_FRAME_OVERHEAD + __PT_GPRS + 20
-SP_R6	     =	STACK_FRAME_OVERHEAD + __PT_GPRS + 24
-SP_R7	     =	STACK_FRAME_OVERHEAD + __PT_GPRS + 28
-SP_R8	     =	STACK_FRAME_OVERHEAD + __PT_GPRS + 32
-SP_R9	     =	STACK_FRAME_OVERHEAD + __PT_GPRS + 36
-SP_R10	     =	STACK_FRAME_OVERHEAD + __PT_GPRS + 40
-SP_R11	     =	STACK_FRAME_OVERHEAD + __PT_GPRS + 44
-SP_R12	     =	STACK_FRAME_OVERHEAD + __PT_GPRS + 48
-SP_R13	     =	STACK_FRAME_OVERHEAD + __PT_GPRS + 52
-SP_R14	     =	STACK_FRAME_OVERHEAD + __PT_GPRS + 56
-SP_R15	     =	STACK_FRAME_OVERHEAD + __PT_GPRS + 60
-SP_ORIG_R2   =	STACK_FRAME_OVERHEAD + __PT_ORIG_GPR2
-SP_SVC_CODE  =	STACK_FRAME_OVERHEAD + __PT_SVC_CODE
-SP_SIZE      =	STACK_FRAME_OVERHEAD + __PT_SIZE
+__PT_R0      =	__PT_GPRS
+__PT_R1      =	__PT_GPRS + 4
+__PT_R2      =	__PT_GPRS + 8
+__PT_R3      =	__PT_GPRS + 12
+__PT_R4      =	__PT_GPRS + 16
+__PT_R5      =	__PT_GPRS + 20
+__PT_R6      =	__PT_GPRS + 24
+__PT_R7      =	__PT_GPRS + 28
+__PT_R8      =	__PT_GPRS + 32
+__PT_R9      =	__PT_GPRS + 36
+__PT_R10     =	__PT_GPRS + 40
+__PT_R11     =	__PT_GPRS + 44
+__PT_R12     =	__PT_GPRS + 48
+__PT_R13     =	__PT_GPRS + 524
+__PT_R14     =	__PT_GPRS + 56
+__PT_R15     =	__PT_GPRS + 60
 
 _TIF_WORK_SVC = (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED | \
 		 _TIF_MCCK_PENDING | _TIF_PER_TRAP )
@@ -58,133 +48,91 @@ STACK_SIZE  = 1 << STACK_SHIFT
 
 #define BASED(name) name-system_call(%r13)
 
-#ifdef CONFIG_TRACE_IRQFLAGS
 	.macro	TRACE_IRQS_ON
+#ifdef CONFIG_TRACE_IRQFLAGS
 	basr	%r2,%r0
-	l	%r1,BASED(.Ltrace_irq_on_caller)
-	basr	%r14,%r1
+	l	%r1,BASED(.Lhardirqs_on)
+	basr	%r14,%r1		# call trace_hardirqs_on_caller
+#endif
 	.endm
 
 	.macro	TRACE_IRQS_OFF
+#ifdef CONFIG_TRACE_IRQFLAGS
 	basr	%r2,%r0
-	l	%r1,BASED(.Ltrace_irq_off_caller)
-	basr	%r14,%r1
-	.endm
-#else
-#define TRACE_IRQS_ON
-#define TRACE_IRQS_OFF
+	l	%r1,BASED(.Lhardirqs_off)
+	basr	%r14,%r1		# call trace_hardirqs_off_caller
 #endif
+	.endm
 
-#ifdef CONFIG_LOCKDEP
 	.macro	LOCKDEP_SYS_EXIT
-	tm	SP_PSW+1(%r15),0x01	# returning to user ?
-	jz	0f
+#ifdef CONFIG_LOCKDEP
+	tm	__PT_PSW+1(%r11),0x01	# returning to user ?
+	jz	.+10
 	l	%r1,BASED(.Llockdep_sys_exit)
-	basr	%r14,%r1
-0:
-	.endm
-#else
-#define LOCKDEP_SYS_EXIT
+	basr	%r14,%r1		# call lockdep_sys_exit
 #endif
-
-/*
- * Register usage in interrupt handlers:
- *    R9  - pointer to current task structure
- *    R13 - pointer to literal pool
- *    R14 - return register for function calls
- *    R15 - kernel stack pointer
- */
-
-	.macro	UPDATE_VTIME lc_from,lc_to,lc_sum
-	lm	%r10,%r11,\lc_from
-	sl	%r10,\lc_to
-	sl	%r11,\lc_to+4
-	bc	3,BASED(0f)
-	sl	%r10,BASED(.Lc_1)
-0:	al	%r10,\lc_sum
-	al	%r11,\lc_sum+4
-	bc	12,BASED(1f)
-	al	%r10,BASED(.Lc_1)
-1:	stm	%r10,%r11,\lc_sum
-	.endm
-
-	.macro	SAVE_ALL_SVC psworg,savearea
-	stm	%r12,%r15,\savearea
-	l	%r13,__LC_SVC_NEW_PSW+4	# load &system_call to %r13
-	l	%r15,__LC_KERNEL_STACK	# problem state -> load ksp
-	s	%r15,BASED(.Lc_spsize)	# make room for registers & psw
-	.endm
-
-	.macro	SAVE_ALL_BASE savearea
-	stm	%r12,%r15,\savearea
-	l	%r13,__LC_SVC_NEW_PSW+4	# load &system_call to %r13
 	.endm
 
-	.macro	SAVE_ALL_PGM psworg,savearea
-	tm	\psworg+1,0x01		# test problem state bit
+	.macro	CHECK_STACK stacksize,savearea
 #ifdef CONFIG_CHECK_STACK
-	bnz	BASED(1f)
-	tml	%r15,STACK_SIZE - CONFIG_STACK_GUARD
-	bnz	BASED(2f)
-	la	%r12,\psworg
-	b	BASED(stack_overflow)
-#else
-	bz	BASED(2f)
+	tml	%r15,\stacksize - CONFIG_STACK_GUARD
+	la	%r14,\savearea
+	jz	stack_overflow
 #endif
-1:	l	%r15,__LC_KERNEL_STACK	# problem state -> load ksp
-2:	s	%r15,BASED(.Lc_spsize)	# make room for registers & psw
 	.endm
 
-	.macro	SAVE_ALL_ASYNC psworg,savearea
-	stm	%r12,%r15,\savearea
-	l	%r13,__LC_SVC_NEW_PSW+4	# load &system_call to %r13
-	la	%r12,\psworg
-	tm	\psworg+1,0x01		# test problem state bit
-	bnz	BASED(1f)		# from user -> load async stack
-	clc	\psworg+4(4),BASED(.Lcritical_end)
-	bhe	BASED(0f)
-	clc	\psworg+4(4),BASED(.Lcritical_start)
-	bl	BASED(0f)
-	l	%r14,BASED(.Lcleanup_critical)
-	basr	%r14,%r14
-	tm	1(%r12),0x01		# retest problem state after cleanup
-	bnz	BASED(1f)
-0:	l	%r14,__LC_ASYNC_STACK	# are we already on the async stack ?
+	.macro	SWITCH_ASYNC savearea,stack,shift
+	tmh	%r8,0x0001		# interrupting from user ?
+	jnz	1f
+	lr	%r14,%r9
+	sl	%r14,BASED(.Lcritical_start)
+	cl	%r14,BASED(.Lcritical_length)
+	jhe	0f
+	la	%r11,\savearea		# inside critical section, do cleanup
+	bras	%r14,cleanup_critical
+	tmh	%r8,0x0001		# retest problem state after cleanup
+	jnz	1f
+0:	l	%r14,\stack		# are we already on the target stack?
 	slr	%r14,%r15
-	sra	%r14,STACK_SHIFT
-#ifdef CONFIG_CHECK_STACK
-	bnz	BASED(1f)
-	tml	%r15,STACK_SIZE - CONFIG_STACK_GUARD
-	bnz	BASED(2f)
-	b	BASED(stack_overflow)
-#else
-	bz	BASED(2f)
-#endif
-1:	l	%r15,__LC_ASYNC_STACK
-2:	s	%r15,BASED(.Lc_spsize)	# make room for registers & psw
+	sra	%r14,\shift
+	jnz	1f
+	CHECK_STACK 1<<\shift,\savearea
+	j	2f
+1:	l	%r15,\stack		# load target stack
+2:	ahi	%r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
+	la	%r11,STACK_FRAME_OVERHEAD(%r15)
 	.endm
 
-	.macro	CREATE_STACK_FRAME savearea
-	xc	__SF_BACKCHAIN(4,%r15),__SF_BACKCHAIN(%r15)
-	st	%r2,SP_ORIG_R2(%r15)	# store original content of gpr 2
-	mvc	SP_R12(16,%r15),\savearea # move %r12-%r15 to stack
-	stm	%r0,%r11,SP_R0(%r15)	# store gprs %r0-%r11 to kernel stack
+	.macro	ADD64 high,low,timer
+	al	\high,\timer
+	al	\low,\timer+4
+	brc	12,.+8
+	ahi	\high,1
 	.endm
 
-	.macro	RESTORE_ALL psworg,sync
-	mvc	\psworg(8),SP_PSW(%r15) # move user PSW to lowcore
-	.if !\sync
-	ni	\psworg+1,0xfd		# clear wait state bit
-	.endif
-	lm	%r0,%r15,SP_R0(%r15)	# load gprs 0-15 of user
-	stpt	__LC_EXIT_TIMER
-	lpsw	\psworg			# back to caller
+	.macro	SUB64 high,low,timer
+	sl	\high,\timer
+	sl	\low,\timer+4
+	brc	3,.+8
+	ahi	\high,-1
+	.endm
+
+	.macro	UPDATE_VTIME high,low,enter_timer
+	lm	\high,\low,__LC_EXIT_TIMER
+	SUB64	\high,\low,\enter_timer
+	ADD64	\high,\low,__LC_USER_TIMER
+	stm	\high,\low,__LC_USER_TIMER
+	lm	\high,\low,__LC_LAST_UPDATE_TIMER
+	SUB64	\high,\low,__LC_EXIT_TIMER
+	ADD64	\high,\low,__LC_SYSTEM_TIMER
+	stm	\high,\low,__LC_SYSTEM_TIMER
+	mvc	__LC_LAST_UPDATE_TIMER(8),\enter_timer
 	.endm
 
 	.macro REENABLE_IRQS
-	mvc	__SF_EMPTY(1,%r15),SP_PSW(%r15)
-	ni	__SF_EMPTY(%r15),0xbf
-	ssm	__SF_EMPTY(%r15)
+	st	%r8,__LC_RETURN_PSW
+	ni	__LC_RETURN_PSW,0xbf
+	ssm	__LC_RETURN_PSW
 	.endm
 
 	.section .kprobes.text, "ax"
@@ -197,14 +145,13 @@ STACK_SIZE  = 1 << STACK_SHIFT
  *  gpr2 = prev
  */
 ENTRY(__switch_to)
-	basr	%r1,0
-0:	l	%r4,__THREAD_info(%r2)		# get thread_info of prev
+	l	%r4,__THREAD_info(%r2)		# get thread_info of prev
 	l	%r5,__THREAD_info(%r3)		# get thread_info of next
 	tm	__TI_flags+3(%r4),_TIF_MCCK_PENDING # machine check pending?
-	bz	1f-0b(%r1)
+	jz	0f
 	ni	__TI_flags+3(%r4),255-_TIF_MCCK_PENDING	# clear flag in prev
 	oi	__TI_flags+3(%r5),_TIF_MCCK_PENDING	# set it in next
-1:	stm	%r6,%r15,__SF_GPRS(%r15)	# store gprs of prev task
+0:	stm	%r6,%r15,__SF_GPRS(%r15)	# store gprs of prev task
 	st	%r15,__THREAD_ksp(%r2)		# store kernel stack of prev
 	l	%r15,__THREAD_ksp(%r3)		# load kernel stack of next
 	lctl	%c4,%c4,__TASK_pid(%r3)		# load pid to control reg. 4
@@ -224,48 +171,55 @@ __critical_start:
 
 ENTRY(system_call)
 	stpt	__LC_SYNC_ENTER_TIMER
-sysc_saveall:
-	SAVE_ALL_SVC __LC_SVC_OLD_PSW,__LC_SAVE_AREA
-	CREATE_STACK_FRAME __LC_SAVE_AREA
-	l	%r12,__LC_THREAD_INFO	# load pointer to thread_info struct
-	mvc	SP_PSW(8,%r15),__LC_SVC_OLD_PSW
-	mvc	SP_SVC_CODE(4,%r15),__LC_SVC_ILC
-	oi	__TI_flags+3(%r12),_TIF_SYSCALL
+sysc_stm:
+	stm	%r8,%r15,__LC_SAVE_AREA_SYNC
+	l	%r12,__LC_THREAD_INFO
+	l	%r13,__LC_SVC_NEW_PSW+4
+sysc_per:
+	l	%r15,__LC_KERNEL_STACK
+	ahi	%r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
+	la	%r11,STACK_FRAME_OVERHEAD(%r15)	# pointer to pt_regs
 sysc_vtime:
-	UPDATE_VTIME __LC_EXIT_TIMER,__LC_SYNC_ENTER_TIMER,__LC_USER_TIMER
-sysc_stime:
-	UPDATE_VTIME __LC_LAST_UPDATE_TIMER,__LC_EXIT_TIMER,__LC_SYSTEM_TIMER
-sysc_update:
-	mvc	__LC_LAST_UPDATE_TIMER(8),__LC_SYNC_ENTER_TIMER
+	UPDATE_VTIME %r8,%r9,__LC_SYNC_ENTER_TIMER
+	stm	%r0,%r7,__PT_R0(%r11)
+	mvc	__PT_R8(32,%r11),__LC_SAVE_AREA_SYNC
+	mvc	__PT_PSW(8,%r11),__LC_SVC_OLD_PSW
+	mvc	__PT_INT_CODE(4,%r11),__LC_SVC_ILC
 sysc_do_svc:
-	xr	%r7,%r7
-	icm	%r7,3,SP_SVC_CODE+2(%r15)# load svc number and test for svc 0
-	bnz	BASED(sysc_nr_ok)	# svc number > 0
+	oi	__TI_flags+3(%r12),_TIF_SYSCALL
+	lh	%r8,__PT_INT_CODE+2(%r11)
+	sla	%r8,2				# shift and test for svc0
+	jnz	sysc_nr_ok
 	# svc 0: system call number in %r1
 	cl	%r1,BASED(.Lnr_syscalls)
-	bnl	BASED(sysc_nr_ok)
-	sth	%r1,SP_SVC_CODE+2(%r15)
-	lr	%r7,%r1 	  # copy svc number to %r7
+	jnl	sysc_nr_ok
+	sth	%r1,__PT_INT_CODE+2(%r11)
+	lr	%r8,%r1
+	sla	%r8,2
 sysc_nr_ok:
-	sll	%r7,2		  # svc number *4
-	l	%r10,BASED(.Lsysc_table)
+	l	%r10,BASED(.Lsys_call_table)	# 31 bit system call table
+	xc	__SF_BACKCHAIN(4,%r15),__SF_BACKCHAIN(%r15)
+	st	%r2,__PT_ORIG_GPR2(%r11)
+	st	%r7,STACK_FRAME_OVERHEAD(%r15)
+	l	%r9,0(%r8,%r10)			# get system call addr.
 	tm	__TI_flags+2(%r12),_TIF_TRACE >> 8
-	mvc	SP_ARGS(4,%r15),SP_R7(%r15)
-	l	%r8,0(%r7,%r10)	  # get system call addr.
-	bnz	BASED(sysc_tracesys)
-	basr	%r14,%r8	  # call sys_xxxx
-	st	%r2,SP_R2(%r15)   # store return value (change R2 on stack)
+	jnz	sysc_tracesys
+	basr	%r14,%r9			# call sys_xxxx
+	st	%r2,__PT_R2(%r11)		# store return value
 
 sysc_return:
 	LOCKDEP_SYS_EXIT
 sysc_tif:
-	tm	SP_PSW+1(%r15),0x01	# returning to user ?
-	bno	BASED(sysc_restore)
+	tm	__PT_PSW+1(%r11),0x01		# returning to user ?
+	jno	sysc_restore
 	tm	__TI_flags+3(%r12),_TIF_WORK_SVC
-	bnz	BASED(sysc_work)  # there is work to do (signals etc.)
+	jnz	sysc_work			# check for work
 	ni	__TI_flags+3(%r12),255-_TIF_SYSCALL
 sysc_restore:
-	RESTORE_ALL __LC_RETURN_PSW,1
+	mvc	__LC_RETURN_PSW(8),__PT_PSW(%r11)
+	stpt	__LC_EXIT_TIMER
+	lm	%r0,%r15,__PT_R0(%r11)
+	lpsw	__LC_RETURN_PSW
 sysc_done:
 
 #
@@ -273,16 +227,16 @@ sysc_done:
 #
 sysc_work:
 	tm	__TI_flags+3(%r12),_TIF_MCCK_PENDING
-	bo	BASED(sysc_mcck_pending)
+	jo	sysc_mcck_pending
 	tm	__TI_flags+3(%r12),_TIF_NEED_RESCHED
-	bo	BASED(sysc_reschedule)
+	jo	sysc_reschedule
 	tm	__TI_flags+3(%r12),_TIF_SIGPENDING
-	bo	BASED(sysc_sigpending)
+	jo	sysc_sigpending
 	tm	__TI_flags+3(%r12),_TIF_NOTIFY_RESUME
-	bo	BASED(sysc_notify_resume)
+	jo	sysc_notify_resume
 	tm	__TI_flags+3(%r12),_TIF_PER_TRAP
-	bo	BASED(sysc_singlestep)
-	b	BASED(sysc_return)	# beware of critical section cleanup
+	jo	sysc_singlestep
+	j	sysc_return		# beware of critical section cleanup
 
 #
 # _TIF_NEED_RESCHED is set, call schedule
@@ -290,13 +244,13 @@ sysc_work:
 sysc_reschedule:
 	l	%r1,BASED(.Lschedule)
 	la	%r14,BASED(sysc_return)
-	br	%r1			# call scheduler
+	br	%r1			# call schedule
 
 #
 # _TIF_MCCK_PENDING is set, call handler
 #
 sysc_mcck_pending:
-	l	%r1,BASED(.Ls390_handle_mcck)
+	l	%r1,BASED(.Lhandle_mcck)
 	la	%r14,BASED(sysc_return)
 	br	%r1			# TIF bit will be cleared by handler
 
@@ -305,23 +259,24 @@ sysc_mcck_pending:
 #
 sysc_sigpending:
 	ni	__TI_flags+3(%r12),255-_TIF_PER_TRAP # clear TIF_PER_TRAP
-	la	%r2,SP_PTREGS(%r15)	# load pt_regs
+	lr	%r2,%r11		# pass pointer to pt_regs
 	l	%r1,BASED(.Ldo_signal)
 	basr	%r14,%r1		# call do_signal
 	tm	__TI_flags+3(%r12),_TIF_SYSCALL
-	bno	BASED(sysc_return)
-	lm	%r2,%r6,SP_R2(%r15)	# load svc arguments
-	xr	%r7,%r7			# svc 0 returns -ENOSYS
-	clc	SP_SVC_CODE+2(2,%r15),BASED(.Lnr_syscalls+2)
-	bnl	BASED(sysc_nr_ok)	# invalid svc number -> do svc 0
-	icm	%r7,3,SP_SVC_CODE+2(%r15)# load new svc number
-	b	BASED(sysc_nr_ok)	# restart svc
+	jno	sysc_return
+	lm	%r2,%r7,__PT_R2(%r11)	# load svc arguments
+	xr	%r8,%r8			# svc 0 returns -ENOSYS
+	clc	__PT_INT_CODE+2(2,%r11),BASED(.Lnr_syscalls+2)
+	jnl	sysc_nr_ok		# invalid svc number -> do svc 0
+	lh	%r8,__PT_INT_CODE+2(%r11)	# load new svc number
+	sla	%r8,2
+	j	sysc_nr_ok		# restart svc
 
 #
 # _TIF_NOTIFY_RESUME is set, call do_notify_resume
 #
 sysc_notify_resume:
-	la	%r2,SP_PTREGS(%r15)	# load pt_regs
+	lr	%r2,%r11		# pass pointer to pt_regs
 	l	%r1,BASED(.Ldo_notify_resume)
 	la	%r14,BASED(sysc_return)
 	br	%r1			# call do_notify_resume
@@ -331,56 +286,57 @@ sysc_notify_resume:
 #
 sysc_singlestep:
 	ni	__TI_flags+3(%r12),255-(_TIF_SYSCALL | _TIF_PER_TRAP)
-	la	%r2,SP_PTREGS(%r15)	# address of register-save area
-	l	%r1,BASED(.Lhandle_per)	# load adr. of per handler
-	la	%r14,BASED(sysc_return)	# load adr. of system return
-	br	%r1			# branch to do_per_trap
+	lr	%r2,%r11		# pass pointer to pt_regs
+	l	%r1,BASED(.Ldo_per_trap)
+	la	%r14,BASED(sysc_return)
+	br	%r1			# call do_per_trap
 
 #
 # call tracehook_report_syscall_entry/tracehook_report_syscall_exit before
 # and after the system call
 #
 sysc_tracesys:
-	l	%r1,BASED(.Ltrace_entry)
-	la	%r2,SP_PTREGS(%r15)	# load pt_regs
+	l	%r1,BASED(.Ltrace_enter)
+	lr	%r2,%r11		# pass pointer to pt_regs
 	la	%r3,0
 	xr	%r0,%r0
-	icm	%r0,3,SP_SVC_CODE(%r15)
-	st	%r0,SP_R2(%r15)
-	basr	%r14,%r1
+	icm	%r0,3,__PT_INT_CODE+2(%r11)
+	st	%r0,__PT_R2(%r11)
+	basr	%r14,%r1		# call do_syscall_trace_enter
 	cl	%r2,BASED(.Lnr_syscalls)
-	bnl	BASED(sysc_tracenogo)
-	lr	%r7,%r2
-	sll	%r7,2			# svc number *4
-	l	%r8,0(%r7,%r10)
+	jnl	sysc_tracenogo
+	lr	%r8,%r2
+	sll	%r8,2
+	l	%r9,0(%r8,%r10)
 sysc_tracego:
-	lm	%r3,%r6,SP_R3(%r15)
-	mvc	SP_ARGS(4,%r15),SP_R7(%r15)
-	l	%r2,SP_ORIG_R2(%r15)
-	basr	%r14,%r8		# call sys_xxx
-	st	%r2,SP_R2(%r15)		# store return value
+	lm	%r3,%r7,__PT_R3(%r11)
+	st	%r7,STACK_FRAME_OVERHEAD(%r15)
+	l	%r2,__PT_ORIG_GPR2(%r11)
+	basr	%r14,%r9		# call sys_xxx
+	st	%r2,__PT_R2(%r11)	# store return value
 sysc_tracenogo:
 	tm	__TI_flags+2(%r12),_TIF_TRACE >> 8
-	bz	BASED(sysc_return)
+	jz	sysc_return
 	l	%r1,BASED(.Ltrace_exit)
-	la	%r2,SP_PTREGS(%r15)	# load pt_regs
+	lr	%r2,%r11		# pass pointer to pt_regs
 	la	%r14,BASED(sysc_return)
-	br	%r1
+	br	%r1			# call do_syscall_trace_exit
 
 #
 # a new process exits the kernel with ret_from_fork
 #
 ENTRY(ret_from_fork)
+	la	%r11,STACK_FRAME_OVERHEAD(%r15)
+	l	%r12,__LC_THREAD_INFO
 	l	%r13,__LC_SVC_NEW_PSW+4
-	l	%r12,__LC_THREAD_INFO	# load pointer to thread_info struct
-	tm	SP_PSW+1(%r15),0x01	# forking a kernel thread ?
-	bo	BASED(0f)
-	st	%r15,SP_R15(%r15)	# store stack pointer for new kthread
-0:	l	%r1,BASED(.Lschedtail)
-	basr	%r14,%r1
+	tm	__PT_PSW+1(%r11),0x01	# forking a kernel thread ?
+	jo	0f
+	st	%r15,__PT_R15(%r11)	# store stack pointer for new kthread
+0:	l	%r1,BASED(.Lschedule_tail)
+	basr	%r14,%r1		# call schedule_tail
 	TRACE_IRQS_ON
-	stosm	__SF_EMPTY(%r15),0x03	# reenable interrupts
-	b	BASED(sysc_tracenogo)
+	ssm	__LC_SVC_NEW_PSW	# reenable interrupts
+	j	sysc_tracenogo
 
 #
 # kernel_execve function needs to deal with pt_regs that is not
@@ -390,153 +346,98 @@ ENTRY(kernel_execve)
 	stm	%r12,%r15,48(%r15)
 	lr	%r14,%r15
 	l	%r13,__LC_SVC_NEW_PSW+4
-	s	%r15,BASED(.Lc_spsize)
+	ahi	%r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
 	st	%r14,__SF_BACKCHAIN(%r15)
-	la	%r12,SP_PTREGS(%r15)
+	la	%r12,STACK_FRAME_OVERHEAD(%r15)
 	xc	0(__PT_SIZE,%r12),0(%r12)
 	l	%r1,BASED(.Ldo_execve)
 	lr	%r5,%r12
-	basr	%r14,%r1
+	basr	%r14,%r1		# call do_execve
 	ltr	%r2,%r2
-	be	BASED(0f)
-	a	%r15,BASED(.Lc_spsize)
+	je	0f
+	ahi	%r15,(STACK_FRAME_OVERHEAD + __PT_SIZE)
 	lm	%r12,%r15,48(%r15)
 	br	%r14
 	# execve succeeded.
-0:	stnsm	__SF_EMPTY(%r15),0xfc	# disable interrupts
+0:	ssm	__LC_PGM_NEW_PSW	# disable I/O and ext. interrupts
 	l	%r15,__LC_KERNEL_STACK	# load ksp
-	s	%r15,BASED(.Lc_spsize)	# make room for registers & psw
-	mvc	SP_PTREGS(__PT_SIZE,%r15),0(%r12)	# copy pt_regs
+	ahi	%r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
+	la	%r11,STACK_FRAME_OVERHEAD(%r15)
+	mvc	0(__PT_SIZE,%r11),0(%r12)	# copy pt_regs
 	l	%r12,__LC_THREAD_INFO
 	xc	__SF_BACKCHAIN(4,%r15),__SF_BACKCHAIN(%r15)
-	stosm	__SF_EMPTY(%r15),0x03	# reenable interrupts
+	ssm	__LC_SVC_NEW_PSW	# reenable interrupts
 	l	%r1,BASED(.Lexecve_tail)
-	basr	%r14,%r1
-	b	BASED(sysc_return)
+	basr	%r14,%r1		# call execve_tail
+	j	sysc_return
 
 /*
  * Program check handler routine
  */
 
 ENTRY(pgm_check_handler)
-/*
- * First we need to check for a special case:
- * Single stepping an instruction that disables the PER event mask will
- * cause a PER event AFTER the mask has been set. Example: SVC or LPSW.
- * For a single stepped SVC the program check handler gets control after
- * the SVC new PSW has been loaded. But we want to execute the SVC first and
- * then handle the PER event. Therefore we update the SVC old PSW to point
- * to the pgm_check_handler and branch to the SVC handler after we checked
- * if we have to load the kernel stack register.
- * For every other possible cause for PER event without the PER mask set
- * we just ignore the PER event (FIXME: is there anything we have to do
- * for LPSW?).
- */
 	stpt	__LC_SYNC_ENTER_TIMER
-	SAVE_ALL_BASE __LC_SAVE_AREA
-	tm	__LC_PGM_INT_CODE+1,0x80 # check whether we got a per exception
-	bnz	BASED(pgm_per)		# got per exception -> special case
-	SAVE_ALL_PGM __LC_PGM_OLD_PSW,__LC_SAVE_AREA
-	CREATE_STACK_FRAME __LC_SAVE_AREA
-	mvc	SP_PSW(8,%r15),__LC_PGM_OLD_PSW
-	l	%r12,__LC_THREAD_INFO	# load pointer to thread_info struct
-	tm	SP_PSW+1(%r15),0x01	# interrupting from user ?
-	bz	BASED(pgm_no_vtime)
-	UPDATE_VTIME __LC_EXIT_TIMER,__LC_SYNC_ENTER_TIMER,__LC_USER_TIMER
-	UPDATE_VTIME __LC_LAST_UPDATE_TIMER,__LC_EXIT_TIMER,__LC_SYSTEM_TIMER
-	mvc	__LC_LAST_UPDATE_TIMER(8),__LC_SYNC_ENTER_TIMER
-pgm_no_vtime:
-	l	%r3,__LC_PGM_ILC	# load program interruption code
-	l	%r4,__LC_TRANS_EXC_CODE
-	REENABLE_IRQS
-	la	%r8,0x7f
-	nr	%r8,%r3
-	sll	%r8,2
-	l	%r1,BASED(.Ljump_table)
-	l	%r1,0(%r8,%r1)		# load address of handler routine
-	la	%r2,SP_PTREGS(%r15)	# address of register-save area
-	basr	%r14,%r1		# branch to interrupt-handler
-pgm_exit:
-	b	BASED(sysc_return)
-
-#
-# handle per exception
-#
-pgm_per:
-	tm	__LC_PGM_OLD_PSW,0x40	# test if per event recording is on
-	bnz	BASED(pgm_per_std)	# ok, normal per event from user space
-# ok its one of the special cases, now we need to find out which one
-	clc	__LC_PGM_OLD_PSW(8),__LC_SVC_NEW_PSW
-	be	BASED(pgm_svcper)
-# no interesting special case, ignore PER event
-	lm	%r12,%r15,__LC_SAVE_AREA
-	lpsw	0x28
-
-#
-# Normal per exception
-#
-pgm_per_std:
-	SAVE_ALL_PGM __LC_PGM_OLD_PSW,__LC_SAVE_AREA
-	CREATE_STACK_FRAME __LC_SAVE_AREA
-	mvc	SP_PSW(8,%r15),__LC_PGM_OLD_PSW
-	l	%r12,__LC_THREAD_INFO	# load pointer to thread_info struct
-	tm	SP_PSW+1(%r15),0x01	# interrupting from user ?
-	bz	BASED(pgm_no_vtime2)
-	UPDATE_VTIME __LC_EXIT_TIMER,__LC_SYNC_ENTER_TIMER,__LC_USER_TIMER
-	UPDATE_VTIME __LC_LAST_UPDATE_TIMER,__LC_EXIT_TIMER,__LC_SYSTEM_TIMER
-	mvc	__LC_LAST_UPDATE_TIMER(8),__LC_SYNC_ENTER_TIMER
-pgm_no_vtime2:
+	stm	%r8,%r15,__LC_SAVE_AREA_SYNC
+	l	%r12,__LC_THREAD_INFO
+	l	%r13,__LC_SVC_NEW_PSW+4
+	lm	%r8,%r9,__LC_PGM_OLD_PSW
+	tmh	%r8,0x0001		# test problem state bit
+	jnz	1f			# -> fault in user space
+	tmh	%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	pgm_svcper		# -> single stepped svc
+0:	CHECK_STACK STACK_SIZE,__LC_SAVE_AREA_SYNC
+	j	2f
+1:	UPDATE_VTIME %r14,%r15,__LC_SYNC_ENTER_TIMER
+	l	%r15,__LC_KERNEL_STACK
+2:	ahi	%r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
+	la	%r11,STACK_FRAME_OVERHEAD(%r15)
+	stm	%r0,%r7,__PT_R0(%r11)
+	mvc	__PT_R8(32,%r11),__LC_SAVE_AREA_SYNC
+	stm	%r8,%r9,__PT_PSW(%r11)
+	mvc	__PT_INT_CODE(4,%r11),__LC_PGM_ILC
+	mvc	__PT_INT_PARM_LONG(4,%r11),__LC_TRANS_EXC_CODE
+	tm	__LC_PGM_ILC+3,0x80	# check for per exception
+	jz	0f
 	l	%r1,__TI_task(%r12)
-	tm	SP_PSW+1(%r15),0x01	# kernel per event ?
-	bz	BASED(kernel_per)
-	mvc	__THREAD_per_cause(2,%r1),__LC_PER_CAUSE
+	tmh	%r8,0x0001		# kernel per event ?
+	jz	pgm_kprobe
+	oi	__TI_flags+3(%r12),_TIF_PER_TRAP
 	mvc	__THREAD_per_address(4,%r1),__LC_PER_ADDRESS
+	mvc	__THREAD_per_cause(2,%r1),__LC_PER_CAUSE
 	mvc	__THREAD_per_paid(1,%r1),__LC_PER_PAID
-	oi	__TI_flags+3(%r12),_TIF_PER_TRAP # set TIF_PER_TRAP
-	l	%r3,__LC_PGM_ILC	# load program interruption code
-	l	%r4,__LC_TRANS_EXC_CODE
-	REENABLE_IRQS
-	la	%r8,0x7f
-	nr	%r8,%r3 		# clear per-event-bit and ilc
-	be	BASED(pgm_exit2)	# only per or per+check ?
-	sll	%r8,2
+0:	REENABLE_IRQS
+	xc	__SF_BACKCHAIN(4,%r15),__SF_BACKCHAIN(%r15)
 	l	%r1,BASED(.Ljump_table)
-	l	%r1,0(%r8,%r1)		# load address of handler routine
-	la	%r2,SP_PTREGS(%r15)	# address of register-save area
+	la	%r10,0x7f
+	n	%r10,__PT_INT_CODE(%r11)
+	je	sysc_return
+	sll	%r10,2
+	l	%r1,0(%r10,%r1)		# load address of handler routine
+	lr	%r2,%r11		# pass pointer to pt_regs
 	basr	%r14,%r1		# branch to interrupt-handler
-pgm_exit2:
-	b	BASED(sysc_return)
+	j	sysc_return
 
 #
-# it was a single stepped SVC that is causing all the trouble
+# PER event in supervisor state, must be kprobes
 #
-pgm_svcper:
-	SAVE_ALL_PGM __LC_SVC_OLD_PSW,__LC_SAVE_AREA
-	CREATE_STACK_FRAME __LC_SAVE_AREA
-	l	%r12,__LC_THREAD_INFO	# load pointer to thread_info struct
-	mvc	SP_PSW(8,%r15),__LC_SVC_OLD_PSW
-	mvc	SP_SVC_CODE(4,%r15),__LC_SVC_ILC
-	oi	__TI_flags+3(%r12),(_TIF_SYSCALL | _TIF_PER_TRAP)
-	UPDATE_VTIME __LC_EXIT_TIMER,__LC_SYNC_ENTER_TIMER,__LC_USER_TIMER
-	UPDATE_VTIME __LC_LAST_UPDATE_TIMER,__LC_EXIT_TIMER,__LC_SYSTEM_TIMER
-	mvc	__LC_LAST_UPDATE_TIMER(8),__LC_SYNC_ENTER_TIMER
-	l	%r8,__TI_task(%r12)
-	mvc	__THREAD_per_cause(2,%r8),__LC_PER_CAUSE
-	mvc	__THREAD_per_address(4,%r8),__LC_PER_ADDRESS
-	mvc	__THREAD_per_paid(1,%r8),__LC_PER_PAID
-	stosm	__SF_EMPTY(%r15),0x03	# reenable interrupts
-	lm	%r2,%r6,SP_R2(%r15)	# load svc arguments
-	b	BASED(sysc_do_svc)
+pgm_kprobe:
+	REENABLE_IRQS
+	xc	__SF_BACKCHAIN(4,%r15),__SF_BACKCHAIN(%r15)
+	l	%r1,BASED(.Ldo_per_trap)
+	lr	%r2,%r11		# pass pointer to pt_regs
+	basr	%r14,%r1		# call do_per_trap
+	j	sysc_return
 
 #
-# per was called from kernel, must be kprobes
+# single stepped system call
 #
-kernel_per:
-	REENABLE_IRQS
-	la	%r2,SP_PTREGS(%r15)	# address of register-save area
-	l	%r1,BASED(.Lhandle_per)	# load adr. of per handler
-	basr	%r14,%r1		# branch to do_single_step
-	b	BASED(pgm_exit)
+pgm_svcper:
+	oi	__TI_flags+3(%r12),_TIF_PER_TRAP
+	mvc	__LC_RETURN_PSW(4),__LC_SVC_NEW_PSW
+	mvc	__LC_RETURN_PSW+4(4),BASED(.Lsysc_per)
+	lpsw	__LC_RETURN_PSW		# branch to sysc_per and enable irqs
 
 /*
  * IO interrupt handler routine
@@ -545,28 +446,35 @@ kernel_per:
 ENTRY(io_int_handler)
 	stck	__LC_INT_CLOCK
 	stpt	__LC_ASYNC_ENTER_TIMER
-	SAVE_ALL_ASYNC __LC_IO_OLD_PSW,__LC_SAVE_AREA+16
-	CREATE_STACK_FRAME __LC_SAVE_AREA+16
-	mvc	SP_PSW(8,%r15),0(%r12)	# move user PSW to stack
-	l	%r12,__LC_THREAD_INFO	# load pointer to thread_info struct
-	tm	SP_PSW+1(%r15),0x01	# interrupting from user ?
-	bz	BASED(io_no_vtime)
-	UPDATE_VTIME __LC_EXIT_TIMER,__LC_ASYNC_ENTER_TIMER,__LC_USER_TIMER
-	UPDATE_VTIME __LC_LAST_UPDATE_TIMER,__LC_EXIT_TIMER,__LC_SYSTEM_TIMER
-	mvc	__LC_LAST_UPDATE_TIMER(8),__LC_ASYNC_ENTER_TIMER
-io_no_vtime:
+	stm	%r8,%r15,__LC_SAVE_AREA_ASYNC
+	l	%r12,__LC_THREAD_INFO
+	l	%r13,__LC_SVC_NEW_PSW+4
+	lm	%r8,%r9,__LC_IO_OLD_PSW
+	tmh	%r8,0x0001		# interrupting from user ?
+	jz	io_skip
+	UPDATE_VTIME %r14,%r15,__LC_ASYNC_ENTER_TIMER
+io_skip:
+	SWITCH_ASYNC __LC_SAVE_AREA_ASYNC,__LC_ASYNC_STACK,STACK_SHIFT
+	stm	%r0,%r7,__PT_R0(%r11)
+	mvc	__PT_R8(32,%r11),__LC_SAVE_AREA_ASYNC
+	stm	%r8,%r9,__PT_PSW(%r11)
 	TRACE_IRQS_OFF
-	l	%r1,BASED(.Ldo_IRQ)	# load address of do_IRQ
-	la	%r2,SP_PTREGS(%r15)	# address of register-save area
-	basr	%r14,%r1		# branch to standard irq handler
+	xc	__SF_BACKCHAIN(4,%r15),__SF_BACKCHAIN(%r15)
+	l	%r1,BASED(.Ldo_IRQ)
+	lr	%r2,%r11		# pass pointer to pt_regs
+	basr	%r14,%r1		# call do_IRQ
 io_return:
 	LOCKDEP_SYS_EXIT
 	TRACE_IRQS_ON
 io_tif:
 	tm	__TI_flags+3(%r12),_TIF_WORK_INT
-	bnz	BASED(io_work)		# there is work to do (signals etc.)
+	jnz	io_work			# there is work to do (signals etc.)
 io_restore:
-	RESTORE_ALL __LC_RETURN_PSW,0
+	mvc	__LC_RETURN_PSW(8),__PT_PSW(%r11)
+	ni	__LC_RETURN_PSW+1,0xfd	# clean wait state bit
+	stpt	__LC_EXIT_TIMER
+	lm	%r0,%r15,__PT_R0(%r11)
+	lpsw	__LC_RETURN_PSW
 io_done:
 
 #
@@ -577,28 +485,29 @@ io_done:
 # Before any work can be done, a switch to the kernel stack is required.
 #
 io_work:
-	tm	SP_PSW+1(%r15),0x01	# returning to user ?
-	bo	BASED(io_work_user)	# yes -> do resched & signal
+	tm	__PT_PSW+1(%r11),0x01	# returning to user ?
+	jo	io_work_user		# yes -> do resched & signal
 #ifdef CONFIG_PREEMPT
 	# check for preemptive scheduling
 	icm	%r0,15,__TI_precount(%r12)
-	bnz	BASED(io_restore)	# preemption disabled
+	jnz	io_restore		# preemption disabled
 	tm	__TI_flags+3(%r12),_TIF_NEED_RESCHED
-	bno	BASED(io_restore)
+	jno	io_restore
 	# switch to kernel stack
-	l	%r1,SP_R15(%r15)
-	s	%r1,BASED(.Lc_spsize)
-	mvc	SP_PTREGS(__PT_SIZE,%r1),SP_PTREGS(%r15)
-	xc	__SF_BACKCHAIN(4,%r1),__SF_BACKCHAIN(%r1) # clear back chain
+	l	%r1,__PT_R15(%r11)
+	ahi	%r1,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
+	mvc	STACK_FRAME_OVERHEAD(__PT_SIZE,%r1),0(%r11)
+	xc	__SF_BACKCHAIN(4,%r1),__SF_BACKCHAIN(%r1)
+	la	%r11,STACK_FRAME_OVERHEAD(%r1)
 	lr	%r15,%r1
 	# TRACE_IRQS_ON already done at io_return, call
 	# TRACE_IRQS_OFF to keep things symmetrical
 	TRACE_IRQS_OFF
-	l	%r1,BASED(.Lpreempt_schedule_irq)
+	l	%r1,BASED(.Lpreempt_irq)
 	basr	%r14,%r1		# call preempt_schedule_irq
-	b	BASED(io_return)
+	j	io_return
 #else
-	b	BASED(io_restore)
+	j	io_restore
 #endif
 
 #
@@ -606,9 +515,10 @@ io_work:
 #
 io_work_user:
 	l	%r1,__LC_KERNEL_STACK
-	s	%r1,BASED(.Lc_spsize)
-	mvc	SP_PTREGS(__PT_SIZE,%r1),SP_PTREGS(%r15)
-	xc	__SF_BACKCHAIN(4,%r1),__SF_BACKCHAIN(%r1) # clear back chain
+	ahi	%r1,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
+	mvc	STACK_FRAME_OVERHEAD(__PT_SIZE,%r1),0(%r11)
+	xc	__SF_BACKCHAIN(4,%r1),__SF_BACKCHAIN(%r1)
+	la	%r11,STACK_FRAME_OVERHEAD(%r1)
 	lr	%r15,%r1
 
 #
@@ -618,24 +528,24 @@ io_work_user:
 #
 io_work_tif:
 	tm	__TI_flags+3(%r12),_TIF_MCCK_PENDING
-	bo	BASED(io_mcck_pending)
+	jo	io_mcck_pending
 	tm	__TI_flags+3(%r12),_TIF_NEED_RESCHED
-	bo	BASED(io_reschedule)
+	jo	io_reschedule
 	tm	__TI_flags+3(%r12),_TIF_SIGPENDING
-	bo	BASED(io_sigpending)
+	jo	io_sigpending
 	tm	__TI_flags+3(%r12),_TIF_NOTIFY_RESUME
-	bo	BASED(io_notify_resume)
-	b	BASED(io_return)	# beware of critical section cleanup
+	jo	io_notify_resume
+	j	io_return		# beware of critical section cleanup
 
 #
 # _TIF_MCCK_PENDING is set, call handler
 #
 io_mcck_pending:
 	# TRACE_IRQS_ON already done at io_return
-	l	%r1,BASED(.Ls390_handle_mcck)
+	l	%r1,BASED(.Lhandle_mcck)
 	basr	%r14,%r1		# TIF bit will be cleared by handler
 	TRACE_IRQS_OFF
-	b	BASED(io_return)
+	j	io_return
 
 #
 # _TIF_NEED_RESCHED is set, call schedule
@@ -643,37 +553,37 @@ io_mcck_pending:
 io_reschedule:
 	# TRACE_IRQS_ON already done at io_return
 	l	%r1,BASED(.Lschedule)
-	stosm	__SF_EMPTY(%r15),0x03	# reenable interrupts
+	ssm	__LC_SVC_NEW_PSW	# reenable interrupts
 	basr	%r14,%r1		# call scheduler
-	stnsm	__SF_EMPTY(%r15),0xfc	# disable I/O and ext. interrupts
+	ssm	__LC_PGM_NEW_PSW	# disable I/O and ext. interrupts
 	TRACE_IRQS_OFF
-	b	BASED(io_return)
+	j	io_return
 
 #
 # _TIF_SIGPENDING is set, call do_signal
 #
 io_sigpending:
 	# TRACE_IRQS_ON already done at io_return
-	stosm	__SF_EMPTY(%r15),0x03	# reenable interrupts
-	la	%r2,SP_PTREGS(%r15)	# load pt_regs
 	l	%r1,BASED(.Ldo_signal)
+	ssm	__LC_SVC_NEW_PSW	# reenable interrupts
+	lr	%r2,%r11		# pass pointer to pt_regs
 	basr	%r14,%r1		# call do_signal
-	stnsm	__SF_EMPTY(%r15),0xfc	# disable I/O and ext. interrupts
+	ssm	__LC_PGM_NEW_PSW	# disable I/O and ext. interrupts
 	TRACE_IRQS_OFF
-	b	BASED(io_return)
+	j	io_return
 
 #
 # _TIF_SIGPENDING is set, call do_signal
 #
 io_notify_resume:
 	# TRACE_IRQS_ON already done at io_return
-	stosm	__SF_EMPTY(%r15),0x03	# reenable interrupts
-	la	%r2,SP_PTREGS(%r15)	# load pt_regs
 	l	%r1,BASED(.Ldo_notify_resume)
-	basr	%r14,%r1		# call do_signal
-	stnsm	__SF_EMPTY(%r15),0xfc	# disable I/O and ext. interrupts
+	ssm	__LC_SVC_NEW_PSW	# reenable interrupts
+	lr	%r2,%r11		# pass pointer to pt_regs
+	basr	%r14,%r1		# call do_notify_resume
+	ssm	__LC_PGM_NEW_PSW	# disable I/O and ext. interrupts
 	TRACE_IRQS_OFF
-	b	BASED(io_return)
+	j	io_return
 
 /*
  * External interrupt handler routine
@@ -682,23 +592,25 @@ io_notify_resume:
 ENTRY(ext_int_handler)
 	stck	__LC_INT_CLOCK
 	stpt	__LC_ASYNC_ENTER_TIMER
-	SAVE_ALL_ASYNC __LC_EXT_OLD_PSW,__LC_SAVE_AREA+16
-	CREATE_STACK_FRAME __LC_SAVE_AREA+16
-	mvc	SP_PSW(8,%r15),0(%r12)	# move user PSW to stack
-	l	%r12,__LC_THREAD_INFO	# load pointer to thread_info struct
-	tm	SP_PSW+1(%r15),0x01	# interrupting from user ?
-	bz	BASED(ext_no_vtime)
-	UPDATE_VTIME __LC_EXIT_TIMER,__LC_ASYNC_ENTER_TIMER,__LC_USER_TIMER
-	UPDATE_VTIME __LC_LAST_UPDATE_TIMER,__LC_EXIT_TIMER,__LC_SYSTEM_TIMER
-	mvc	__LC_LAST_UPDATE_TIMER(8),__LC_ASYNC_ENTER_TIMER
-ext_no_vtime:
+	stm	%r8,%r15,__LC_SAVE_AREA_ASYNC
+	l	%r12,__LC_THREAD_INFO
+	l	%r13,__LC_SVC_NEW_PSW+4
+	lm	%r8,%r9,__LC_EXT_OLD_PSW
+	tmh	%r8,0x0001		# interrupting from user ?
+	jz	ext_skip
+	UPDATE_VTIME %r14,%r15,__LC_ASYNC_ENTER_TIMER
+ext_skip:
+	SWITCH_ASYNC __LC_SAVE_AREA_ASYNC,__LC_ASYNC_STACK,STACK_SHIFT
+	stm	%r0,%r7,__PT_R0(%r11)
+	mvc	__PT_R8(32,%r11),__LC_SAVE_AREA_ASYNC
+	stm	%r8,%r9,__PT_PSW(%r11)
 	TRACE_IRQS_OFF
-	la	%r2,SP_PTREGS(%r15)	# address of register-save area
+	lr	%r2,%r11		# pass pointer to pt_regs
 	l	%r3,__LC_CPU_ADDRESS	# get cpu address + interruption code
 	l	%r4,__LC_EXT_PARAMS	# get external parameters
 	l	%r1,BASED(.Ldo_extint)
-	basr	%r14,%r1
-	b	BASED(io_return)
+	basr	%r14,%r1		# call do_extint
+	j	io_return
 
 __critical_end:
 
@@ -710,82 +622,74 @@ ENTRY(mcck_int_handler)
 	stck	__LC_MCCK_CLOCK
 	spt	__LC_CPU_TIMER_SAVE_AREA	# revalidate cpu timer
 	lm	%r0,%r15,__LC_GPREGS_SAVE_AREA	# revalidate gprs
-	SAVE_ALL_BASE __LC_SAVE_AREA+32
-	la	%r12,__LC_MCK_OLD_PSW
+	l	%r12,__LC_THREAD_INFO
+	l	%r13,__LC_SVC_NEW_PSW+4
+	lm	%r8,%r9,__LC_MCK_OLD_PSW
 	tm	__LC_MCCK_CODE,0x80	# system damage?
-	bo	BASED(mcck_int_main)	# yes -> rest of mcck code invalid
-	mvc	__LC_MCCK_ENTER_TIMER(8),__LC_CPU_TIMER_SAVE_AREA
+	jo	mcck_panic		# yes -> rest of mcck code invalid
+	la	%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?
-	bo	BASED(1f)
+	jo	3f
 	la	%r14,__LC_SYNC_ENTER_TIMER
 	clc	0(8,%r14),__LC_ASYNC_ENTER_TIMER
-	bl	BASED(0f)
+	jl	0f
 	la	%r14,__LC_ASYNC_ENTER_TIMER
 0:	clc	0(8,%r14),__LC_EXIT_TIMER
-	bl	BASED(0f)
+	jl	1f
 	la	%r14,__LC_EXIT_TIMER
-0:	clc	0(8,%r14),__LC_LAST_UPDATE_TIMER
-	bl	BASED(0f)
+1:	clc	0(8,%r14),__LC_LAST_UPDATE_TIMER
+	jl	2f
 	la	%r14,__LC_LAST_UPDATE_TIMER
-0:	spt	0(%r14)
+2:	spt	0(%r14)
 	mvc	__LC_MCCK_ENTER_TIMER(8),0(%r14)
-1:	tm	__LC_MCCK_CODE+2,0x09	# mwp + ia of old psw valid?
-	bno	BASED(mcck_int_main)	# no -> skip cleanup critical
-	tm	__LC_MCK_OLD_PSW+1,0x01	# test problem state bit
-	bnz	BASED(mcck_int_main)	# from user -> load async stack
-	clc	__LC_MCK_OLD_PSW+4(4),BASED(.Lcritical_end)
-	bhe	BASED(mcck_int_main)
-	clc	__LC_MCK_OLD_PSW+4(4),BASED(.Lcritical_start)
-	bl	BASED(mcck_int_main)
-	l	%r14,BASED(.Lcleanup_critical)
-	basr	%r14,%r14
-mcck_int_main:
-	l	%r14,__LC_PANIC_STACK	# are we already on the panic stack?
-	slr	%r14,%r15
-	sra	%r14,PAGE_SHIFT
-	be	BASED(0f)
-	l	%r15,__LC_PANIC_STACK	# load panic stack
-0:	s	%r15,BASED(.Lc_spsize)	# make room for registers & psw
-	CREATE_STACK_FRAME __LC_SAVE_AREA+32
-	mvc	SP_PSW(8,%r15),0(%r12)
-	l	%r12,__LC_THREAD_INFO	# load pointer to thread_info struct
-	tm	__LC_MCCK_CODE+2,0x08	# mwp of old psw valid?
-	bno	BASED(mcck_no_vtime)	# no -> skip cleanup critical
-	tm	SP_PSW+1(%r15),0x01	# interrupting from user ?
-	bz	BASED(mcck_no_vtime)
-	UPDATE_VTIME __LC_EXIT_TIMER,__LC_MCCK_ENTER_TIMER,__LC_USER_TIMER
-	UPDATE_VTIME __LC_LAST_UPDATE_TIMER,__LC_EXIT_TIMER,__LC_SYSTEM_TIMER
-	mvc	__LC_LAST_UPDATE_TIMER(8),__LC_MCCK_ENTER_TIMER
-mcck_no_vtime:
-	la	%r2,SP_PTREGS(%r15)	# load pt_regs
-	l	%r1,BASED(.Ls390_mcck)
-	basr	%r14,%r1		# call machine check handler
-	tm	SP_PSW+1(%r15),0x01	# returning to user ?
-	bno	BASED(mcck_return)
+3:	tm	__LC_MCCK_CODE+2,0x09	# mwp + ia of old psw valid?
+	jno	mcck_panic		# no -> skip cleanup critical
+	tm	%r8,0x0001		# interrupting from user ?
+	jz	mcck_skip
+	UPDATE_VTIME %r14,%r15,__LC_MCCK_ENTER_TIMER
+mcck_skip:
+	SWITCH_ASYNC __LC_GPREGS_SAVE_AREA+32,__LC_PANIC_STACK,PAGE_SHIFT
+	mvc	__PT_R0(64,%r11),__LC_GPREGS_SAVE_AREA
+	stm	%r8,%r9,__PT_PSW(%r11)
+	xc	__SF_BACKCHAIN(4,%r15),__SF_BACKCHAIN(%r15)
+	l	%r1,BASED(.Ldo_machine_check)
+	lr	%r2,%r11		# pass pointer to pt_regs
+	basr	%r14,%r1		# call s390_do_machine_check
+	tm	__PT_PSW+1(%r11),0x01	# returning to user ?
+	jno	mcck_return
 	l	%r1,__LC_KERNEL_STACK	# switch to kernel stack
-	s	%r1,BASED(.Lc_spsize)
-	mvc	SP_PTREGS(__PT_SIZE,%r1),SP_PTREGS(%r15)
-	xc	__SF_BACKCHAIN(4,%r1),__SF_BACKCHAIN(%r1) # clear back chain
+	ahi	%r1,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
+	mvc	STACK_FRAME_OVERHEAD(__PT_SIZE,%r1),0(%r11)
+	xc	__SF_BACKCHAIN(4,%r1),__SF_BACKCHAIN(%r1)
+	la	%r11,STACK_FRAME_OVERHEAD(%r15)
 	lr	%r15,%r1
-	stosm	__SF_EMPTY(%r15),0x04	# turn dat on
+	ssm	__LC_PGM_NEW_PSW	# turn dat on, keep irqs off
 	tm	__TI_flags+3(%r12),_TIF_MCCK_PENDING
-	bno	BASED(mcck_return)
+	jno	mcck_return
 	TRACE_IRQS_OFF
-	l	%r1,BASED(.Ls390_handle_mcck)
-	basr	%r14,%r1		# call machine check handler
+	l	%r1,BASED(.Lhandle_mcck)
+	basr	%r14,%r1		# call s390_handle_mcck
 	TRACE_IRQS_ON
 mcck_return:
-	mvc	__LC_RETURN_MCCK_PSW(8),SP_PSW(%r15) # move return PSW
+	mvc	__LC_RETURN_MCCK_PSW(8),__PT_PSW(%r11) # move return PSW
 	ni	__LC_RETURN_MCCK_PSW+1,0xfd # clear wait state bit
 	tm	__LC_RETURN_MCCK_PSW+1,0x01 # returning to user ?
-	bno	BASED(0f)
-	lm	%r0,%r15,SP_R0(%r15)	# load gprs 0-15
+	jno	0f
+	lm	%r0,%r15,__PT_R0(%r11)
 	stpt	__LC_EXIT_TIMER
-	lpsw	__LC_RETURN_MCCK_PSW	# back to caller
-0:	lm	%r0,%r15,SP_R0(%r15)	# load gprs 0-15
-	lpsw	__LC_RETURN_MCCK_PSW	# back to caller
+	lpsw	__LC_RETURN_MCCK_PSW
+0:	lm	%r0,%r15,__PT_R0(%r11)
+	lpsw	__LC_RETURN_MCCK_PSW
 
-	RESTORE_ALL __LC_RETURN_MCCK_PSW,0
+mcck_panic:
+	l	%r14,__LC_PANIC_STACK
+	slr	%r14,%r15
+	sra	%r14,PAGE_SHIFT
+	jz	0f
+	l	%r15,__LC_PANIC_STACK
+0:	ahi	%r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
+	j	mcck_skip
 
 /*
  * Restart interruption handler, kick starter for additional CPUs
@@ -799,18 +703,18 @@ restart_base:
 	stck	__LC_LAST_UPDATE_CLOCK
 	mvc	__LC_LAST_UPDATE_TIMER(8),restart_vtime-restart_base(%r1)
 	mvc	__LC_EXIT_TIMER(8),restart_vtime-restart_base(%r1)
-	l	%r15,__LC_SAVE_AREA+60	# load ksp
+	l	%r15,__LC_GPREGS_SAVE_AREA+60 # load ksp
 	lctl	%c0,%c15,__LC_CREGS_SAVE_AREA # get new ctl regs
 	lam	%a0,%a15,__LC_AREGS_SAVE_AREA
-	lm	%r6,%r15,__SF_GPRS(%r15) # load registers from clone
+	lm	%r6,%r15,__SF_GPRS(%r15)# load registers from clone
 	l	%r1,__LC_THREAD_INFO
 	mvc	__LC_USER_TIMER(8),__TI_user_timer(%r1)
 	mvc	__LC_SYSTEM_TIMER(8),__TI_system_timer(%r1)
 	xc	__LC_STEAL_TIMER(8),__LC_STEAL_TIMER
-	stosm	__SF_EMPTY(%r15),0x04	# now we can turn dat on
+	ssm	__LC_PGM_NEW_PSW	# turn dat on, keep irqs off
 	basr	%r14,0
 	l	%r14,restart_addr-.(%r14)
-	basr	%r14,%r14		# branch to start_secondary
+	basr	%r14,%r14		# call start_secondary
 restart_addr:
 	.long	start_secondary
 	.align	8
@@ -835,19 +739,19 @@ restart_go:
 # PSW restart interrupt handler
 #
 ENTRY(psw_restart_int_handler)
-	st	%r15,__LC_SAVE_AREA+48(%r0)	# save r15
+	st	%r15,__LC_SAVE_AREA_RESTART
 	basr	%r15,0
 0:	l	%r15,.Lrestart_stack-0b(%r15)	# load restart stack
 	l	%r15,0(%r15)
-	ahi	%r15,-SP_SIZE			# make room for pt_regs
-	stm	%r0,%r14,SP_R0(%r15)		# store gprs %r0-%r14 to stack
-	mvc	SP_R15(4,%r15),__LC_SAVE_AREA+48(%r0)# store saved %r15 to stack
-	mvc	SP_PSW(8,%r15),__LC_RST_OLD_PSW(%r0) # store restart old psw
-	xc	__SF_BACKCHAIN(4,%r15),__SF_BACKCHAIN(%r15) # set backchain to 0
+	ahi	%r15,-__PT_SIZE			# create pt_regs on stack
+	stm	%r0,%r14,__PT_R0(%r15)
+	mvc	__PT_R15(4,%r15),__LC_SAVE_AREA_RESTART
+	mvc	__PT_PSW(8,%r15),__LC_RST_OLD_PSW # store restart old psw
+	ahi	%r15,-STACK_FRAME_OVERHEAD
+	xc	__SF_BACKCHAIN(4,%r15),__SF_BACKCHAIN(%r15)
 	basr	%r14,0
 1:	l	%r14,.Ldo_restart-1b(%r14)
 	basr	%r14,%r14
-
 	basr	%r14,0				# load disabled wait PSW if
 2:	lpsw	restart_psw_crash-2b(%r14)	# do_restart returns
 	.align 4
@@ -869,215 +773,174 @@ restart_psw_crash:
  */
 stack_overflow:
 	l	%r15,__LC_PANIC_STACK	# change to panic stack
-	sl	%r15,BASED(.Lc_spsize)
-	mvc	SP_PSW(8,%r15),0(%r12)	# move user PSW to stack
-	stm	%r0,%r11,SP_R0(%r15)	# store gprs %r0-%r11 to kernel stack
-	la	%r1,__LC_SAVE_AREA
-	ch	%r12,BASED(.L0x020)	# old psw addr == __LC_SVC_OLD_PSW ?
-	be	BASED(0f)
-	ch	%r12,BASED(.L0x028)	# old psw addr == __LC_PGM_OLD_PSW ?
-	be	BASED(0f)
-	la	%r1,__LC_SAVE_AREA+16
-0:	mvc	SP_R12(16,%r15),0(%r1)	# move %r12-%r15 to stack
-	xc	__SF_BACKCHAIN(4,%r15),__SF_BACKCHAIN(%r15) # clear back chain
-	l	%r1,BASED(1f)		# branch to kernel_stack_overflow
-	la	%r2,SP_PTREGS(%r15)	# load pt_regs
-	br	%r1
+	ahi	%r15,-__PT_SIZE		# create pt_regs
+	stm	%r0,%r7,__PT_R0(%r15)
+	stm	%r8,%r9,__PT_PSW(%r15)
+	mvc	__PT_R8(32,%r11),0(%r14)
+	lr	%r15,%r11
+	ahi	%r15,-STACK_FRAME_OVERHEAD
+	l	%r1,BASED(1f)
+	xc	__SF_BACKCHAIN(4,%r15),__SF_BACKCHAIN(%r15)
+	lr	%r2,%r11		# pass pointer to pt_regs
+	br	%r1			# branch to kernel_stack_overflow
 1:	.long	kernel_stack_overflow
 #endif
 
-cleanup_table_system_call:
-	.long	system_call + 0x80000000, sysc_do_svc + 0x80000000
-cleanup_table_sysc_tif:
-	.long	sysc_tif + 0x80000000, sysc_restore + 0x80000000
-cleanup_table_sysc_restore:
-	.long	sysc_restore + 0x80000000, sysc_done + 0x80000000
-cleanup_table_io_tif:
-	.long	io_tif + 0x80000000, io_restore + 0x80000000
-cleanup_table_io_restore:
-	.long	io_restore + 0x80000000, io_done + 0x80000000
+cleanup_table:
+	.long	system_call + 0x80000000
+	.long	sysc_do_svc + 0x80000000
+	.long	sysc_tif + 0x80000000
+	.long	sysc_restore + 0x80000000
+	.long	sysc_done + 0x80000000
+	.long	io_tif + 0x80000000
+	.long	io_restore + 0x80000000
+	.long	io_done + 0x80000000
 
 cleanup_critical:
-	clc	4(4,%r12),BASED(cleanup_table_system_call)
-	bl	BASED(0f)
-	clc	4(4,%r12),BASED(cleanup_table_system_call+4)
-	bl	BASED(cleanup_system_call)
-0:
-	clc	4(4,%r12),BASED(cleanup_table_sysc_tif)
-	bl	BASED(0f)
-	clc	4(4,%r12),BASED(cleanup_table_sysc_tif+4)
-	bl	BASED(cleanup_sysc_tif)
-0:
-	clc	4(4,%r12),BASED(cleanup_table_sysc_restore)
-	bl	BASED(0f)
-	clc	4(4,%r12),BASED(cleanup_table_sysc_restore+4)
-	bl	BASED(cleanup_sysc_restore)
-0:
-	clc	4(4,%r12),BASED(cleanup_table_io_tif)
-	bl	BASED(0f)
-	clc	4(4,%r12),BASED(cleanup_table_io_tif+4)
-	bl	BASED(cleanup_io_tif)
-0:
-	clc	4(4,%r12),BASED(cleanup_table_io_restore)
-	bl	BASED(0f)
-	clc	4(4,%r12),BASED(cleanup_table_io_restore+4)
-	bl	BASED(cleanup_io_restore)
-0:
-	br	%r14
+	cl	%r9,BASED(cleanup_table)	# system_call
+	jl	0f
+	cl	%r9,BASED(cleanup_table+4)	# sysc_do_svc
+	jl	cleanup_system_call
+	cl	%r9,BASED(cleanup_table+8)	# sysc_tif
+	jl	0f
+	cl	%r9,BASED(cleanup_table+12)	# sysc_restore
+	jl	cleanup_sysc_tif
+	cl	%r9,BASED(cleanup_table+16)	# sysc_done
+	jl	cleanup_sysc_restore
+	cl	%r9,BASED(cleanup_table+20)	# io_tif
+	jl	0f
+	cl	%r9,BASED(cleanup_table+24)	# io_restore
+	jl	cleanup_io_tif
+	cl	%r9,BASED(cleanup_table+28)	# io_done
+	jl	cleanup_io_restore
+0:	br	%r14
 
 cleanup_system_call:
-	mvc	__LC_RETURN_PSW(8),0(%r12)
-	clc	__LC_RETURN_PSW+4(4),BASED(cleanup_system_call_insn+4)
-	bh	BASED(0f)
-	mvc	__LC_SYNC_ENTER_TIMER(8),__LC_MCCK_ENTER_TIMER
-	c	%r12,BASED(.Lmck_old_psw)
-	be	BASED(0f)
+	# check if stpt has been executed
+	cl	%r9,BASED(cleanup_system_call_insn)
+	jh	0f
 	mvc	__LC_SYNC_ENTER_TIMER(8),__LC_ASYNC_ENTER_TIMER
-0:	c	%r12,BASED(.Lmck_old_psw)
-	la	%r12,__LC_SAVE_AREA+32
-	be	BASED(0f)
-	la	%r12,__LC_SAVE_AREA+16
-0:	clc	__LC_RETURN_PSW+4(4),BASED(cleanup_system_call_insn+8)
-	bhe	BASED(cleanup_vtime)
-	clc	__LC_RETURN_PSW+4(4),BASED(cleanup_system_call_insn)
-	bh	BASED(0f)
-	mvc	__LC_SAVE_AREA(16),0(%r12)
-0:	st	%r13,4(%r12)
-	l	%r15,__LC_KERNEL_STACK	# problem state -> load ksp
-	s	%r15,BASED(.Lc_spsize)	# make room for registers & psw
-	st	%r15,12(%r12)
-	CREATE_STACK_FRAME __LC_SAVE_AREA
-	mvc	0(4,%r12),__LC_THREAD_INFO
-	l	%r12,__LC_THREAD_INFO
-	mvc	SP_PSW(8,%r15),__LC_SVC_OLD_PSW
-	mvc	SP_SVC_CODE(4,%r15),__LC_SVC_ILC
-	oi	__TI_flags+3(%r12),_TIF_SYSCALL
-cleanup_vtime:
-	clc	__LC_RETURN_PSW+4(4),BASED(cleanup_system_call_insn+12)
-	bhe	BASED(cleanup_stime)
-	UPDATE_VTIME __LC_EXIT_TIMER,__LC_SYNC_ENTER_TIMER,__LC_USER_TIMER
-cleanup_stime:
-	clc	__LC_RETURN_PSW+4(4),BASED(cleanup_system_call_insn+16)
-	bh	BASED(cleanup_update)
-	UPDATE_VTIME __LC_LAST_UPDATE_TIMER,__LC_EXIT_TIMER,__LC_SYSTEM_TIMER
-cleanup_update:
+	chi	%r11,__LC_SAVE_AREA_ASYNC
+	je	0f
+	mvc	__LC_SYNC_ENTER_TIMER(8),__LC_MCCK_ENTER_TIMER
+0:	# check if stm has been executed
+	cl	%r9,BASED(cleanup_system_call_insn+4)
+	jh	0f
+	mvc	__LC_SAVE_AREA_SYNC(32),0(%r11)
+0:	# set up saved registers r12, and r13
+	st	%r12,16(%r11)		# r12 thread-info pointer
+	st	%r13,20(%r11)		# r13 literal-pool pointer
+	# check if the user time calculation has been done
+	cl	%r9,BASED(cleanup_system_call_insn+8)
+	jh	0f
+	l	%r10,__LC_EXIT_TIMER
+	l	%r15,__LC_EXIT_TIMER+4
+	SUB64	%r10,%r15,__LC_SYNC_ENTER_TIMER
+	ADD64	%r10,%r15,__LC_USER_TIMER
+	st	%r10,__LC_USER_TIMER
+	st	%r15,__LC_USER_TIMER+4
+0:	# check if the system time calculation has been done
+	cl	%r9,BASED(cleanup_system_call_insn+12)
+	jh	0f
+	l	%r10,__LC_LAST_UPDATE_TIMER
+	l	%r15,__LC_LAST_UPDATE_TIMER+4
+	SUB64	%r10,%r15,__LC_EXIT_TIMER
+	ADD64	%r10,%r15,__LC_SYSTEM_TIMER
+	st	%r10,__LC_SYSTEM_TIMER
+	st	%r15,__LC_SYSTEM_TIMER+4
+0:	# update accounting time stamp
 	mvc	__LC_LAST_UPDATE_TIMER(8),__LC_SYNC_ENTER_TIMER
-	mvc	__LC_RETURN_PSW+4(4),BASED(cleanup_table_system_call+4)
-	la	%r12,__LC_RETURN_PSW
+	# set up saved register 11
+	l	%r15,__LC_KERNEL_STACK
+	ahi	%r15,-__PT_SIZE
+	st	%r15,12(%r11)		# r11 pt_regs pointer
+	# fill pt_regs
+	mvc	__PT_R8(32,%r15),__LC_SAVE_AREA_SYNC
+	stm	%r0,%r7,__PT_R0(%r15)
+	mvc	__PT_PSW(8,%r15),__LC_SVC_OLD_PSW
+	mvc	__PT_INT_CODE(4,%r15),__LC_SVC_ILC
+	# setup saved register 15
+	ahi	%r15,-STACK_FRAME_OVERHEAD
+	st	%r15,28(%r11)		# r15 stack pointer
+	# set new psw address and exit
+	l	%r9,BASED(cleanup_table+4)	# sysc_do_svc + 0x80000000
 	br	%r14
 cleanup_system_call_insn:
-	.long	sysc_saveall + 0x80000000
 	.long	system_call + 0x80000000
-	.long	sysc_vtime + 0x80000000
-	.long	sysc_stime + 0x80000000
-	.long	sysc_update + 0x80000000
+	.long	sysc_stm + 0x80000000
+	.long	sysc_vtime + 0x80000000 + 36
+	.long	sysc_vtime + 0x80000000 + 76
 
 cleanup_sysc_tif:
-	mvc	__LC_RETURN_PSW(4),0(%r12)
-	mvc	__LC_RETURN_PSW+4(4),BASED(cleanup_table_sysc_tif)
-	la	%r12,__LC_RETURN_PSW
+	l	%r9,BASED(cleanup_table+8)	# sysc_tif + 0x80000000
 	br	%r14
 
 cleanup_sysc_restore:
-	clc	4(4,%r12),BASED(cleanup_sysc_restore_insn)
-	be	BASED(2f)
-	mvc	__LC_EXIT_TIMER(8),__LC_MCCK_ENTER_TIMER
-	c	%r12,BASED(.Lmck_old_psw)
-	be	BASED(0f)
-	mvc	__LC_EXIT_TIMER(8),__LC_ASYNC_ENTER_TIMER
-0:	clc	4(4,%r12),BASED(cleanup_sysc_restore_insn+4)
-	be	BASED(2f)
-	mvc	__LC_RETURN_PSW(8),SP_PSW(%r15)
-	c	%r12,BASED(.Lmck_old_psw)
-	la	%r12,__LC_SAVE_AREA+32
-	be	BASED(1f)
-	la	%r12,__LC_SAVE_AREA+16
-1:	mvc	0(16,%r12),SP_R12(%r15)
-	lm	%r0,%r11,SP_R0(%r15)
-	l	%r15,SP_R15(%r15)
-2:	la	%r12,__LC_RETURN_PSW
+	cl	%r9,BASED(cleanup_sysc_restore_insn)
+	jhe	0f
+	l	%r9,12(%r11)		# get saved pointer to pt_regs
+	mvc	__LC_RETURN_PSW(8),__PT_PSW(%r9)
+	mvc	0(32,%r11),__PT_R8(%r9)
+	lm	%r0,%r7,__PT_R0(%r9)
+0:	lm	%r8,%r9,__LC_RETURN_PSW
 	br	%r14
 cleanup_sysc_restore_insn:
 	.long	sysc_done - 4 + 0x80000000
-	.long	sysc_done - 8 + 0x80000000
 
 cleanup_io_tif:
-	mvc	__LC_RETURN_PSW(4),0(%r12)
-	mvc	__LC_RETURN_PSW+4(4),BASED(cleanup_table_io_tif)
-	la	%r12,__LC_RETURN_PSW
+	l	%r9,BASED(cleanup_table+20)	# io_tif + 0x80000000
 	br	%r14
 
 cleanup_io_restore:
-	clc	4(4,%r12),BASED(cleanup_io_restore_insn)
-	be	BASED(1f)
-	mvc	__LC_EXIT_TIMER(8),__LC_MCCK_ENTER_TIMER
-	clc	4(4,%r12),BASED(cleanup_io_restore_insn+4)
-	be	BASED(1f)
-	mvc	__LC_RETURN_PSW(8),SP_PSW(%r15)
-	mvc	__LC_SAVE_AREA+32(16),SP_R12(%r15)
-	lm	%r0,%r11,SP_R0(%r15)
-	l	%r15,SP_R15(%r15)
-1:	la	%r12,__LC_RETURN_PSW
+	cl	%r9,BASED(cleanup_io_restore_insn)
+	jhe	0f
+	l	%r9,12(%r11)		# get saved r11 pointer to pt_regs
+	mvc	__LC_RETURN_PSW(8),__PT_PSW(%r9)
+	ni	__LC_RETURN_PSW+1,0xfd	# clear wait state bit
+	mvc	0(32,%r11),__PT_R8(%r9)
+	lm	%r0,%r7,__PT_R0(%r9)
+0:	lm	%r8,%r9,__LC_RETURN_PSW
 	br	%r14
 cleanup_io_restore_insn:
 	.long	io_done - 4 + 0x80000000
-	.long	io_done - 8 + 0x80000000
 
 /*
  * Integer constants
  */
-		.align	4
-.Lc_spsize:	.long	SP_SIZE
-.Lc_overhead:	.long	STACK_FRAME_OVERHEAD
-.Lnr_syscalls:	.long	NR_syscalls
-.L0x018:	.short	0x018
-.L0x020:	.short	0x020
-.L0x028:	.short	0x028
-.L0x030:	.short	0x030
-.L0x038:	.short	0x038
-.Lc_1:		.long	1
+	.align	4
+.Lnr_syscalls:		.long	NR_syscalls
 
 /*
  * Symbol constants
  */
-.Ls390_mcck:	.long	s390_do_machine_check
-.Ls390_handle_mcck:
-		.long	s390_handle_mcck
-.Lmck_old_psw:	.long	__LC_MCK_OLD_PSW
-.Ldo_IRQ:	.long	do_IRQ
-.Ldo_extint:	.long	do_extint
-.Ldo_signal:	.long	do_signal
-.Ldo_notify_resume:
-		.long	do_notify_resume
-.Lhandle_per:	.long	do_per_trap
-.Ldo_execve:	.long	do_execve
-.Lexecve_tail:	.long	execve_tail
-.Ljump_table:	.long	pgm_check_table
-.Lschedule:	.long	schedule
+.Ldo_machine_check:	.long	s390_do_machine_check
+.Lhandle_mcck:		.long	s390_handle_mcck
+.Ldo_IRQ:		.long	do_IRQ
+.Ldo_extint:		.long	do_extint
+.Ldo_signal:		.long	do_signal
+.Ldo_notify_resume:	.long	do_notify_resume
+.Ldo_per_trap:		.long	do_per_trap
+.Ldo_execve:		.long	do_execve
+.Lexecve_tail:		.long	execve_tail
+.Ljump_table:		.long	pgm_check_table
+.Lschedule:		.long	schedule
 #ifdef CONFIG_PREEMPT
-.Lpreempt_schedule_irq:
-		.long	preempt_schedule_irq
+.Lpreempt_irq:		.long	preempt_schedule_irq
 #endif
-.Ltrace_entry:	.long	do_syscall_trace_enter
-.Ltrace_exit:	.long	do_syscall_trace_exit
-.Lschedtail:	.long	schedule_tail
-.Lsysc_table:	.long	sys_call_table
+.Ltrace_enter:		.long	do_syscall_trace_enter
+.Ltrace_exit:		.long	do_syscall_trace_exit
+.Lschedule_tail:	.long	schedule_tail
+.Lsys_call_table:	.long	sys_call_table
+.Lsysc_per:		.long	sysc_per + 0x80000000
 #ifdef CONFIG_TRACE_IRQFLAGS
-.Ltrace_irq_on_caller:
-		.long	trace_hardirqs_on_caller
-.Ltrace_irq_off_caller:
-		.long	trace_hardirqs_off_caller
+.Lhardirqs_on:		.long	trace_hardirqs_on_caller
+.Lhardirqs_off:		.long	trace_hardirqs_off_caller
 #endif
 #ifdef CONFIG_LOCKDEP
-.Llockdep_sys_exit:
-		.long	lockdep_sys_exit
+.Llockdep_sys_exit:	.long	lockdep_sys_exit
 #endif
-.Lcritical_start:
-		.long	__critical_start + 0x80000000
-.Lcritical_end:
-		.long	__critical_end + 0x80000000
-.Lcleanup_critical:
-		.long	cleanup_critical
+.Lcritical_start:	.long	__critical_start + 0x80000000
+.Lcritical_length:	.long	__critical_end - __critical_start
 
 		.section .rodata, "a"
 #define SYSCALL(esa,esame,emu)	.long esa
diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h
index ef8fb1d6e8d7..bf538aaf407d 100644
--- a/arch/s390/kernel/entry.h
+++ b/arch/s390/kernel/entry.h
@@ -6,15 +6,15 @@
 #include <asm/ptrace.h>
 
 
-extern void (*pgm_check_table[128])(struct pt_regs *, long, unsigned long);
+extern void (*pgm_check_table[128])(struct pt_regs *);
 extern void *restart_stack;
 
 asmlinkage long do_syscall_trace_enter(struct pt_regs *regs);
 asmlinkage void do_syscall_trace_exit(struct pt_regs *regs);
 
-void do_protection_exception(struct pt_regs *, long, unsigned long);
-void do_dat_exception(struct pt_regs *, long, unsigned long);
-void do_asce_exception(struct pt_regs *, long, unsigned long);
+void do_protection_exception(struct pt_regs *regs);
+void do_dat_exception(struct pt_regs *regs);
+void do_asce_exception(struct pt_regs *regs);
 
 void do_per_trap(struct pt_regs *regs);
 void syscall_trace(struct pt_regs *regs, int entryexit);
@@ -28,7 +28,7 @@ void do_extint(struct pt_regs *regs, unsigned int, unsigned int, unsigned long);
 void do_restart(void);
 int __cpuinit start_secondary(void *cpuvoid);
 void __init startup_init(void);
-void die(const char * str, struct pt_regs * regs, long err);
+void die(struct pt_regs *regs, const char *str);
 
 void __init time_init(void);
 
diff --git a/arch/s390/kernel/entry64.S b/arch/s390/kernel/entry64.S
index 83a93747e2fd..412a7b8783d7 100644
--- a/arch/s390/kernel/entry64.S
+++ b/arch/s390/kernel/entry64.S
@@ -19,32 +19,22 @@
 #include <asm/unistd.h>
 #include <asm/page.h>
 
-/*
- * Stack layout for the system_call stack entry.
- * The first few entries are identical to the user_regs_struct.
- */
-SP_PTREGS    =	STACK_FRAME_OVERHEAD
-SP_ARGS      =	STACK_FRAME_OVERHEAD + __PT_ARGS
-SP_PSW	     =	STACK_FRAME_OVERHEAD + __PT_PSW
-SP_R0	     =	STACK_FRAME_OVERHEAD + __PT_GPRS
-SP_R1	     =	STACK_FRAME_OVERHEAD + __PT_GPRS + 8
-SP_R2	     =	STACK_FRAME_OVERHEAD + __PT_GPRS + 16
-SP_R3	     =	STACK_FRAME_OVERHEAD + __PT_GPRS + 24
-SP_R4	     =	STACK_FRAME_OVERHEAD + __PT_GPRS + 32
-SP_R5	     =	STACK_FRAME_OVERHEAD + __PT_GPRS + 40
-SP_R6	     =	STACK_FRAME_OVERHEAD + __PT_GPRS + 48
-SP_R7	     =	STACK_FRAME_OVERHEAD + __PT_GPRS + 56
-SP_R8	     =	STACK_FRAME_OVERHEAD + __PT_GPRS + 64
-SP_R9	     =	STACK_FRAME_OVERHEAD + __PT_GPRS + 72
-SP_R10	     =	STACK_FRAME_OVERHEAD + __PT_GPRS + 80
-SP_R11	     =	STACK_FRAME_OVERHEAD + __PT_GPRS + 88
-SP_R12	     =	STACK_FRAME_OVERHEAD + __PT_GPRS + 96
-SP_R13	     =	STACK_FRAME_OVERHEAD + __PT_GPRS + 104
-SP_R14	     =	STACK_FRAME_OVERHEAD + __PT_GPRS + 112
-SP_R15	     =	STACK_FRAME_OVERHEAD + __PT_GPRS + 120
-SP_ORIG_R2   =	STACK_FRAME_OVERHEAD + __PT_ORIG_GPR2
-SP_SVC_CODE  =	STACK_FRAME_OVERHEAD + __PT_SVC_CODE
-SP_SIZE      =	STACK_FRAME_OVERHEAD + __PT_SIZE
+__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
@@ -59,154 +49,103 @@ _TIF_EXIT_SIE = (_TIF_SIGPENDING | _TIF_NEED_RESCHED | _TIF_MCCK_PENDING)
 
 #define BASED(name) name-system_call(%r13)
 
-	.macro SPP newpp
-#if defined(CONFIG_KVM) || defined(CONFIG_KVM_MODULE)
-	tm	__LC_MACHINE_FLAGS+6,0x20	# MACHINE_FLAG_SPP
-	jz	.+8
-	.insn	s,0xb2800000,\newpp
-#endif
-	.endm
-
-	.macro	HANDLE_SIE_INTERCEPT
-#if defined(CONFIG_KVM) || defined(CONFIG_KVM_MODULE)
-	tm	__TI_flags+6(%r12),_TIF_SIE>>8
-	jz	0f
-	SPP	__LC_CMF_HPP			# set host id
-	clc	SP_PSW+8(8,%r15),BASED(.Lsie_loop)
-	jl	0f
-	clc	SP_PSW+8(8,%r15),BASED(.Lsie_done)
-	jhe	0f
-	mvc	SP_PSW+8(8,%r15),BASED(.Lsie_loop)
-0:
-#endif
-	.endm
-
-#ifdef CONFIG_TRACE_IRQFLAGS
 	.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
-	.endm
-#else
-#define TRACE_IRQS_ON
-#define TRACE_IRQS_OFF
 #endif
+	.endm
 
-#ifdef CONFIG_LOCKDEP
 	.macro	LOCKDEP_SYS_EXIT
-	tm	SP_PSW+1(%r15),0x01	# returning to user ?
-	jz	0f
+#ifdef CONFIG_LOCKDEP
+	tm	__PT_PSW+1(%r11),0x01	# returning to user ?
+	jz	.+10
 	brasl	%r14,lockdep_sys_exit
-0:
-	.endm
-#else
-#define LOCKDEP_SYS_EXIT
 #endif
-
-	.macro	UPDATE_VTIME lc_from,lc_to,lc_sum
-	lg	%r10,\lc_from
-	slg	%r10,\lc_to
-	alg	%r10,\lc_sum
-	stg	%r10,\lc_sum
 	.endm
 
-/*
- * Register usage in interrupt handlers:
- *    R9  - pointer to current task structure
- *    R13 - pointer to literal pool
- *    R14 - return register for function calls
- *    R15 - kernel stack pointer
- */
+	.macro SPP newpp
+#if defined(CONFIG_KVM) || defined(CONFIG_KVM_MODULE)
+	tm	__LC_MACHINE_FLAGS+6,0x20	# MACHINE_FLAG_SPP
+	jz	.+8
+	.insn	s,0xb2800000,\newpp
+#endif
+	.endm
 
-	.macro	SAVE_ALL_SVC psworg,savearea
-	stmg	%r11,%r15,\savearea
-	lg	%r15,__LC_KERNEL_STACK	# problem state -> load ksp
-	aghi	%r15,-SP_SIZE		# make room for registers & psw
-	lg	%r11,__LC_LAST_BREAK
+	.macro	HANDLE_SIE_INTERCEPT scratch
+#if defined(CONFIG_KVM) || defined(CONFIG_KVM_MODULE)
+	tm	__TI_flags+6(%r12),_TIF_SIE>>8
+	jz	.+42
+	tm	__LC_MACHINE_FLAGS+6,0x20	# MACHINE_FLAG_SPP
+	jz	.+8
+	.insn	s,0xb2800000,BASED(.Lhost_id)	# set host id
+	lgr	\scratch,%r9
+	slg	\scratch,BASED(.Lsie_loop)
+	clg	\scratch,BASED(.Lsie_length)
+	jhe	.+10
+	lg	%r9,BASED(.Lsie_loop)
+#endif
 	.endm
 
-	.macro	SAVE_ALL_PGM psworg,savearea
-	stmg	%r11,%r15,\savearea
-	tm	\psworg+1,0x01		# test problem state bit
+	.macro	CHECK_STACK stacksize,savearea
 #ifdef CONFIG_CHECK_STACK
-	jnz	1f
-	tml	%r15,STACK_SIZE - CONFIG_STACK_GUARD
-	jnz	2f
-	la	%r12,\psworg
-	j	stack_overflow
-#else
-	jz	2f
+	tml	%r15,\stacksize - CONFIG_STACK_GUARD
+	lghi	%r14,\savearea
+	jz	stack_overflow
 #endif
-1:	lg	%r15,__LC_KERNEL_STACK	# problem state -> load ksp
-2:	aghi	%r15,-SP_SIZE		# make room for registers & psw
-	larl	%r13,system_call
-	lg	%r11,__LC_LAST_BREAK
 	.endm
 
-	.macro	SAVE_ALL_ASYNC psworg,savearea
-	stmg	%r11,%r15,\savearea
-	larl	%r13,system_call
-	lg	%r11,__LC_LAST_BREAK
-	la	%r12,\psworg
-	tm	\psworg+1,0x01		# test problem state bit
-	jnz	1f			# from user -> load kernel stack
-	clc	\psworg+8(8),BASED(.Lcritical_end)
+	.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
-	clc	\psworg+8(8),BASED(.Lcritical_start)
-	jl	0f
+	lghi	%r11,\savearea		# inside critical section, do cleanup
 	brasl	%r14,cleanup_critical
-	tm	1(%r12),0x01		# retest problem state after cleanup
+	tmhh	%r8,0x0001		# retest problem state after cleanup
 	jnz	1f
-0:	lg	%r14,__LC_ASYNC_STACK	# are we already on the async. stack ?
+0:	lg	%r14,\stack		# are we already on the target stack?
 	slgr	%r14,%r15
-	srag	%r14,%r14,STACK_SHIFT
-#ifdef CONFIG_CHECK_STACK
+	srag	%r14,%r14,\shift
 	jnz	1f
-	tml	%r15,STACK_SIZE - CONFIG_STACK_GUARD
-	jnz	2f
-	j	stack_overflow
-#else
-	jz	2f
-#endif
-1:	lg	%r15,__LC_ASYNC_STACK	# load async stack
-2:	aghi	%r15,-SP_SIZE		# make room for registers & psw
-	.endm
-
-	.macro	CREATE_STACK_FRAME savearea
-	xc	__SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
-	stg	%r2,SP_ORIG_R2(%r15)	# store original content of gpr 2
-	mvc	SP_R11(40,%r15),\savearea # move %r11-%r15 to stack
-	stmg	%r0,%r10,SP_R0(%r15)	# store gprs %r0-%r10 to kernel stack
+	CHECK_STACK 1<<\shift,\savearea
+	j	2f
+1:	lg	%r15,\stack		# load target stack
+2:	aghi	%r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
+	la	%r11,STACK_FRAME_OVERHEAD(%r15)
 	.endm
 
-	.macro	RESTORE_ALL psworg,sync
-	mvc	\psworg(16),SP_PSW(%r15) # move user PSW to lowcore
-	.if !\sync
-	ni	\psworg+1,0xfd		# clear wait state bit
-	.endif
-	lg	%r14,__LC_VDSO_PER_CPU
-	lmg	%r0,%r13,SP_R0(%r15)	# load gprs 0-13 of user
-	stpt	__LC_EXIT_TIMER
-	mvc	__VDSO_ECTG_BASE(16,%r14),__LC_EXIT_TIMER
-	lmg	%r14,%r15,SP_R14(%r15)	# load grps 14-15 of user
-	lpswe	\psworg			# back to caller
+	.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
-	srag	%r10,%r11,23
-	jz	0f
-	stg	%r11,__TI_last_break(%r12)
-0:
+	.macro	LAST_BREAK scratch
+	srag	\scratch,%r10,23
+	jz	.+10
+	stg	%r10,__TI_last_break(%r12)
 	.endm
 
 	.macro REENABLE_IRQS
-	mvc	__SF_EMPTY(1,%r15),SP_PSW(%r15)
-	ni	__SF_EMPTY(%r15),0xbf
-	ssm	__SF_EMPTY(%r15)
+	stg	%r8,__LC_RETURN_PSW
+	ni	__LC_RETURN_PSW,0xbf
+	ssm	__LC_RETURN_PSW
 	.endm
 
 	.section .kprobes.text, "ax"
@@ -245,55 +184,66 @@ __critical_start:
 
 ENTRY(system_call)
 	stpt	__LC_SYNC_ENTER_TIMER
-sysc_saveall:
-	SAVE_ALL_SVC __LC_SVC_OLD_PSW,__LC_SAVE_AREA
-	CREATE_STACK_FRAME __LC_SAVE_AREA
-	lg	%r12,__LC_THREAD_INFO	# load pointer to thread_info struct
-	mvc	SP_PSW(16,%r15),__LC_SVC_OLD_PSW
-	mvc	SP_SVC_CODE(4,%r15),__LC_SVC_ILC
-	oi	__TI_flags+7(%r12),_TIF_SYSCALL
+sysc_stmg:
+	stmg	%r8,%r15,__LC_SAVE_AREA_SYNC
+	lg	%r10,__LC_LAST_BREAK
+	lg	%r12,__LC_THREAD_INFO
+	larl	%r13,system_call
+sysc_per:
+	lg	%r15,__LC_KERNEL_STACK
+	aghi	%r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
+	la	%r11,STACK_FRAME_OVERHEAD(%r15)	# pointer to pt_regs
 sysc_vtime:
-	UPDATE_VTIME __LC_EXIT_TIMER,__LC_SYNC_ENTER_TIMER,__LC_USER_TIMER
-sysc_stime:
-	UPDATE_VTIME __LC_LAST_UPDATE_TIMER,__LC_EXIT_TIMER,__LC_SYSTEM_TIMER
-sysc_update:
-	mvc	__LC_LAST_UPDATE_TIMER(8),__LC_SYNC_ENTER_TIMER
-	LAST_BREAK
+	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
 sysc_do_svc:
-	llgh	%r7,SP_SVC_CODE+2(%r15)
-	slag	%r7,%r7,2	# shift and test for svc 0
+	oi	__TI_flags+7(%r12),_TIF_SYSCALL
+	llgh	%r8,__PT_INT_CODE+2(%r11)
+	slag	%r8,%r8,2			# shift and test for svc 0
 	jnz	sysc_nr_ok
 	# svc 0: system call number in %r1
-	llgfr	%r1,%r1		# clear high word in r1
+	llgfr	%r1,%r1				# clear high word in r1
 	cghi	%r1,NR_syscalls
 	jnl	sysc_nr_ok
-	sth	%r1,SP_SVC_CODE+2(%r15)
-	slag	%r7,%r1,2	# shift and test for svc 0
+	sth	%r1,__PT_INT_CODE+2(%r11)
+	slag	%r8,%r1,2
 sysc_nr_ok:
-	larl	%r10,sys_call_table
+	larl	%r10,sys_call_table		# 64 bit system call table
 #ifdef CONFIG_COMPAT
-	tm	__TI_flags+5(%r12),(_TIF_31BIT>>16)  # running in 31 bit mode ?
+	tm	__TI_flags+5(%r12),(_TIF_31BIT>>16)
 	jno	sysc_noemu
-	larl	%r10,sys_call_table_emu  # use 31 bit emulation system calls
+	larl	%r10,sys_call_table_emu		# 31 bit system call table
 sysc_noemu:
 #endif
+	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+6(%r12),_TIF_TRACE >> 8
-	mvc	SP_ARGS(8,%r15),SP_R7(%r15)
-	lgf	%r8,0(%r7,%r10) # load address of system call routine
 	jnz	sysc_tracesys
-	basr	%r14,%r8	# call sys_xxxx
-	stg	%r2,SP_R2(%r15) # store return value (change R2 on stack)
+	basr	%r14,%r9			# call sys_xxxx
+	stg	%r2,__PT_R2(%r11)		# store return value
 
 sysc_return:
 	LOCKDEP_SYS_EXIT
 sysc_tif:
-	tm	SP_PSW+1(%r15),0x01	# returning to user ?
+	tm	__PT_PSW+1(%r11),0x01		# returning to user ?
 	jno	sysc_restore
 	tm	__TI_flags+7(%r12),_TIF_WORK_SVC
-	jnz	sysc_work	# there is work to do (signals etc.)
+	jnz	sysc_work			# check for work
 	ni	__TI_flags+7(%r12),255-_TIF_SYSCALL
 sysc_restore:
-	RESTORE_ALL __LC_RETURN_PSW,1
+	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
 sysc_done:
 
 #
@@ -317,7 +267,7 @@ sysc_work:
 #
 sysc_reschedule:
 	larl	%r14,sysc_return
-	jg	schedule		# return point is sysc_return
+	jg	schedule
 
 #
 # _TIF_MCCK_PENDING is set, call handler
@@ -331,33 +281,33 @@ sysc_mcck_pending:
 #
 sysc_sigpending:
 	ni	__TI_flags+7(%r12),255-_TIF_PER_TRAP # clear TIF_PER_TRAP
-	la	%r2,SP_PTREGS(%r15)	# load pt_regs
-	brasl	%r14,do_signal		# call do_signal
+	lgr	%r2,%r11		# pass pointer to pt_regs
+	brasl	%r14,do_signal
 	tm	__TI_flags+7(%r12),_TIF_SYSCALL
 	jno	sysc_return
-	lmg	%r2,%r6,SP_R2(%r15)	# load svc arguments
-	lghi	%r7,0			# svc 0 returns -ENOSYS
-	lh	%r1,SP_SVC_CODE+2(%r15)	# load new svc number
+	lmg	%r2,%r7,__PT_R2(%r11)	# load svc arguments
+	lghi	%r8,0			# svc 0 returns -ENOSYS
+	lh	%r1,__PT_INT_CODE+2(%r11)	# load new svc number
 	cghi	%r1,NR_syscalls
 	jnl	sysc_nr_ok		# invalid svc number -> do svc 0
-	slag	%r7,%r1,2
+	slag	%r8,%r1,2
 	j	sysc_nr_ok		# restart svc
 
 #
 # _TIF_NOTIFY_RESUME is set, call do_notify_resume
 #
 sysc_notify_resume:
-	la	%r2,SP_PTREGS(%r15)	# load pt_regs
+	lgr	%r2,%r11		# pass pointer to pt_regs
 	larl	%r14,sysc_return
-	jg	do_notify_resume	# call do_notify_resume
+	jg	do_notify_resume
 
 #
 # _TIF_PER_TRAP is set, call do_per_trap
 #
 sysc_singlestep:
 	ni	__TI_flags+7(%r12),255-(_TIF_SYSCALL | _TIF_PER_TRAP)
-	la	%r2,SP_PTREGS(%r15)	# address of register-save area
-	larl	%r14,sysc_return	# load adr. of system return
+	lgr	%r2,%r11		# pass pointer to pt_regs
+	larl	%r14,sysc_return
 	jg	do_per_trap
 
 #
@@ -365,41 +315,41 @@ sysc_singlestep:
 # and after the system call
 #
 sysc_tracesys:
-	la	%r2,SP_PTREGS(%r15)	# load pt_regs
+	lgr	%r2,%r11		# pass pointer to pt_regs
 	la	%r3,0
-	llgh	%r0,SP_SVC_CODE+2(%r15)
-	stg	%r0,SP_R2(%r15)
+	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	sysc_tracenogo
-	sllg	%r7,%r2,2		# svc number *4
-	lgf	%r8,0(%r7,%r10)
+	sllg	%r8,%r2,2
+	lgf	%r9,0(%r8,%r10)
 sysc_tracego:
-	lmg	%r3,%r6,SP_R3(%r15)
-	mvc	SP_ARGS(8,%r15),SP_R7(%r15)
-	lg	%r2,SP_ORIG_R2(%r15)
-	basr	%r14,%r8		# call sys_xxx
-	stg	%r2,SP_R2(%r15)		# store return value
+	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
 sysc_tracenogo:
 	tm	__TI_flags+6(%r12),_TIF_TRACE >> 8
 	jz	sysc_return
-	la	%r2,SP_PTREGS(%r15)	# load pt_regs
-	larl	%r14,sysc_return	# return point is sysc_return
+	lgr	%r2,%r11		# pass pointer to pt_regs
+	larl	%r14,sysc_return
 	jg	do_syscall_trace_exit
 
 #
 # a new process exits the kernel with ret_from_fork
 #
 ENTRY(ret_from_fork)
-	lg	%r13,__LC_SVC_NEW_PSW+8
-	lg	%r12,__LC_THREAD_INFO	# load pointer to thread_info struct
-	tm	SP_PSW+1(%r15),0x01	# forking a kernel thread ?
+	la	%r11,STACK_FRAME_OVERHEAD(%r15)
+	lg	%r12,__LC_THREAD_INFO
+	tm	__PT_PSW+1(%r11),0x01	# forking a kernel thread ?
 	jo	0f
-	stg	%r15,SP_R15(%r15)	# store stack pointer for new kthread
+	stg	%r15,__PT_R15(%r11)	# store stack pointer for new kthread
 0:	brasl	%r14,schedule_tail
 	TRACE_IRQS_ON
-	stosm	24(%r15),0x03		# reenable interrupts
+	ssm	__LC_SVC_NEW_PSW	# reenable interrupts
 	j	sysc_tracenogo
 
 #
@@ -409,26 +359,26 @@ ENTRY(ret_from_fork)
 ENTRY(kernel_execve)
 	stmg	%r12,%r15,96(%r15)
 	lgr	%r14,%r15
-	aghi	%r15,-SP_SIZE
+	aghi	%r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
 	stg	%r14,__SF_BACKCHAIN(%r15)
-	la	%r12,SP_PTREGS(%r15)
+	la	%r12,STACK_FRAME_OVERHEAD(%r15)
 	xc	0(__PT_SIZE,%r12),0(%r12)
 	lgr	%r5,%r12
 	brasl	%r14,do_execve
 	ltgfr	%r2,%r2
 	je	0f
-	aghi	%r15,SP_SIZE
+	aghi	%r15,(STACK_FRAME_OVERHEAD + __PT_SIZE)
 	lmg	%r12,%r15,96(%r15)
 	br	%r14
 	# execve succeeded.
-0:	stnsm	__SF_EMPTY(%r15),0xfc	# disable interrupts
+0:	ssm	__LC_PGM_NEW_PSW	# disable I/O and ext. interrupts
 	lg	%r15,__LC_KERNEL_STACK	# load ksp
-	aghi	%r15,-SP_SIZE		# make room for registers & psw
-	lg	%r13,__LC_SVC_NEW_PSW+8
-	mvc	SP_PTREGS(__PT_SIZE,%r15),0(%r12)	# copy pt_regs
+	aghi	%r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
+	la	%r11,STACK_FRAME_OVERHEAD(%r15)
+	mvc	0(__PT_SIZE,%r11),0(%r12)	# copy pt_regs
 	lg	%r12,__LC_THREAD_INFO
 	xc	__SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
-	stosm	__SF_EMPTY(%r15),0x03	# reenable interrupts
+	ssm	__LC_SVC_NEW_PSW	# reenable interrupts
 	brasl	%r14,execve_tail
 	j	sysc_return
 
@@ -437,127 +387,72 @@ ENTRY(kernel_execve)
  */
 
 ENTRY(pgm_check_handler)
-/*
- * First we need to check for a special case:
- * Single stepping an instruction that disables the PER event mask will
- * cause a PER event AFTER the mask has been set. Example: SVC or LPSW.
- * For a single stepped SVC the program check handler gets control after
- * the SVC new PSW has been loaded. But we want to execute the SVC first and
- * then handle the PER event. Therefore we update the SVC old PSW to point
- * to the pgm_check_handler and branch to the SVC handler after we checked
- * if we have to load the kernel stack register.
- * For every other possible cause for PER event without the PER mask set
- * we just ignore the PER event (FIXME: is there anything we have to do
- * for LPSW?).
- */
 	stpt	__LC_SYNC_ENTER_TIMER
-	tm	__LC_PGM_INT_CODE+1,0x80 # check whether we got a per exception
-	jnz	pgm_per 		 # got per exception -> special case
-	SAVE_ALL_PGM __LC_PGM_OLD_PSW,__LC_SAVE_AREA
-	CREATE_STACK_FRAME __LC_SAVE_AREA
-	mvc	SP_PSW(16,%r15),__LC_PGM_OLD_PSW
-	lg	%r12,__LC_THREAD_INFO	# load pointer to thread_info struct
-	HANDLE_SIE_INTERCEPT
-	tm	SP_PSW+1(%r15),0x01	# interrupting from user ?
-	jz	pgm_no_vtime
-	UPDATE_VTIME __LC_EXIT_TIMER,__LC_SYNC_ENTER_TIMER,__LC_USER_TIMER
-	UPDATE_VTIME __LC_LAST_UPDATE_TIMER,__LC_EXIT_TIMER,__LC_SYSTEM_TIMER
-	mvc	__LC_LAST_UPDATE_TIMER(8),__LC_SYNC_ENTER_TIMER
-	LAST_BREAK
-pgm_no_vtime:
-	stg	%r11,SP_ARGS(%r15)
-	lgf	%r3,__LC_PGM_ILC	# load program interruption code
-	lg	%r4,__LC_TRANS_EXC_CODE
-	REENABLE_IRQS
-	lghi	%r8,0x7f
-	ngr	%r8,%r3
-	sll	%r8,3
-	larl	%r1,pgm_check_table
-	lg	%r1,0(%r8,%r1)		# load address of handler routine
-	la	%r2,SP_PTREGS(%r15)	# address of register-save area
-	basr	%r14,%r1		# branch to interrupt-handler
-pgm_exit:
-	j	sysc_return
-
-#
-# handle per exception
-#
-pgm_per:
-	tm	__LC_PGM_OLD_PSW,0x40	# test if per event recording is on
-	jnz	pgm_per_std		# ok, normal per event from user space
-# ok its one of the special cases, now we need to find out which one
-	clc	__LC_PGM_OLD_PSW(16),__LC_SVC_NEW_PSW
-	je	pgm_svcper
-# no interesting special case, ignore PER event
-	lpswe	__LC_PGM_OLD_PSW
-
-#
-# Normal per exception
-#
-pgm_per_std:
-	SAVE_ALL_PGM __LC_PGM_OLD_PSW,__LC_SAVE_AREA
-	CREATE_STACK_FRAME __LC_SAVE_AREA
-	mvc	SP_PSW(16,%r15),__LC_PGM_OLD_PSW
-	lg	%r12,__LC_THREAD_INFO	# load pointer to thread_info struct
-	HANDLE_SIE_INTERCEPT
-	tm	SP_PSW+1(%r15),0x01	# interrupting from user ?
-	jz	pgm_no_vtime2
-	UPDATE_VTIME __LC_EXIT_TIMER,__LC_SYNC_ENTER_TIMER,__LC_USER_TIMER
-	UPDATE_VTIME __LC_LAST_UPDATE_TIMER,__LC_EXIT_TIMER,__LC_SYSTEM_TIMER
-	mvc	__LC_LAST_UPDATE_TIMER(8),__LC_SYNC_ENTER_TIMER
-	LAST_BREAK
-pgm_no_vtime2:
+	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
+	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	pgm_svcper		# -> single stepped svc
+0:	CHECK_STACK STACK_SIZE,__LC_SAVE_AREA_SYNC
+	j	2f
+1:	UPDATE_VTIME %r14,__LC_SYNC_ENTER_TIMER
+	LAST_BREAK %r14
+	lg	%r15,__LC_KERNEL_STACK
+2:	aghi	%r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
+	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
+	stg	%r10,__PT_ARGS(%r11)
+	tm	__LC_PGM_ILC+3,0x80	# check for per exception
+	jz	0f
 	lg	%r1,__TI_task(%r12)
-	tm	SP_PSW+1(%r15),0x01	# kernel per event ?
-	jz	kernel_per
-	mvc	__THREAD_per_cause(2,%r1),__LC_PER_CAUSE
+	tmhh	%r8,0x0001		# kernel per event ?
+	jz	pgm_kprobe
+	oi	__TI_flags+7(%r12),_TIF_PER_TRAP
 	mvc	__THREAD_per_address(8,%r1),__LC_PER_ADDRESS
+	mvc	__THREAD_per_cause(2,%r1),__LC_PER_CAUSE
 	mvc	__THREAD_per_paid(1,%r1),__LC_PER_PAID
-	oi	__TI_flags+7(%r12),_TIF_PER_TRAP # set TIF_PER_TRAP
-	lgf	%r3,__LC_PGM_ILC	# load program interruption code
-	lg	%r4,__LC_TRANS_EXC_CODE
-	REENABLE_IRQS
-	lghi	%r8,0x7f
-	ngr	%r8,%r3			# clear per-event-bit and ilc
-	je	pgm_exit2
-	sll	%r8,3
+0:	REENABLE_IRQS
+	xc	__SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
 	larl	%r1,pgm_check_table
-	lg	%r1,0(%r8,%r1)		# load address of handler routine
-	la	%r2,SP_PTREGS(%r15)	# address of register-save area
+	llgh	%r10,__PT_INT_CODE+2(%r11)
+	nill	%r10,0x007f
+	sll	%r10,3
+	je	sysc_return
+	lg	%r1,0(%r10,%r1)		# load address of handler routine
+	lgr	%r2,%r11		# pass pointer to pt_regs
 	basr	%r14,%r1		# branch to interrupt-handler
-pgm_exit2:
 	j	sysc_return
 
 #
-# it was a single stepped SVC that is causing all the trouble
+# PER event in supervisor state, must be kprobes
 #
-pgm_svcper:
-	SAVE_ALL_PGM __LC_SVC_OLD_PSW,__LC_SAVE_AREA
-	CREATE_STACK_FRAME __LC_SAVE_AREA
-	lg	%r12,__LC_THREAD_INFO	# load pointer to thread_info struct
-	mvc	SP_PSW(16,%r15),__LC_SVC_OLD_PSW
-	mvc	SP_SVC_CODE(4,%r15),__LC_SVC_ILC
-	oi	__TI_flags+7(%r12),(_TIF_SYSCALL | _TIF_PER_TRAP)
-	UPDATE_VTIME __LC_EXIT_TIMER,__LC_SYNC_ENTER_TIMER,__LC_USER_TIMER
-	UPDATE_VTIME __LC_LAST_UPDATE_TIMER,__LC_EXIT_TIMER,__LC_SYSTEM_TIMER
-	mvc	__LC_LAST_UPDATE_TIMER(8),__LC_SYNC_ENTER_TIMER
-	LAST_BREAK
-	lg	%r8,__TI_task(%r12)
-	mvc	__THREAD_per_cause(2,%r8),__LC_PER_CAUSE
-	mvc	__THREAD_per_address(8,%r8),__LC_PER_ADDRESS
-	mvc	__THREAD_per_paid(1,%r8),__LC_PER_PAID
-	stosm	__SF_EMPTY(%r15),0x03	# reenable interrupts
-	lmg	%r2,%r6,SP_R2(%r15)	# load svc arguments
-	j	sysc_do_svc
+pgm_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	sysc_return
 
 #
-# per was called from kernel, must be kprobes
+# single stepped system call
 #
-kernel_per:
-	REENABLE_IRQS
-	la	%r2,SP_PTREGS(%r15)	# address of register-save area
-	brasl	%r14,do_per_trap
-	j	pgm_exit
+pgm_svcper:
+	oi	__TI_flags+7(%r12),_TIF_PER_TRAP
+	mvc	__LC_RETURN_PSW(8),__LC_SVC_NEW_PSW
+	larl	%r14,sysc_per
+	stg	%r14,__LC_RETURN_PSW+8
+	lpswe	__LC_RETURN_PSW		# branch to sysc_per and enable irqs
 
 /*
  * IO interrupt handler routine
@@ -565,21 +460,25 @@ kernel_per:
 ENTRY(io_int_handler)
 	stck	__LC_INT_CLOCK
 	stpt	__LC_ASYNC_ENTER_TIMER
-	SAVE_ALL_ASYNC __LC_IO_OLD_PSW,__LC_SAVE_AREA+40
-	CREATE_STACK_FRAME __LC_SAVE_AREA+40
-	mvc	SP_PSW(16,%r15),0(%r12)	# move user PSW to stack
-	lg	%r12,__LC_THREAD_INFO	# load pointer to thread_info struct
-	HANDLE_SIE_INTERCEPT
-	tm	SP_PSW+1(%r15),0x01	# interrupting from user ?
-	jz	io_no_vtime
-	UPDATE_VTIME __LC_EXIT_TIMER,__LC_ASYNC_ENTER_TIMER,__LC_USER_TIMER
-	UPDATE_VTIME __LC_LAST_UPDATE_TIMER,__LC_EXIT_TIMER,__LC_SYSTEM_TIMER
-	mvc	__LC_LAST_UPDATE_TIMER(8),__LC_ASYNC_ENTER_TIMER
-	LAST_BREAK
-io_no_vtime:
+	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
+	SWITCH_ASYNC __LC_SAVE_AREA_ASYNC,__LC_ASYNC_STACK,STACK_SHIFT
+	tmhh	%r8,0x0001		# interrupting from user?
+	jz	io_skip
+	UPDATE_VTIME %r14,__LC_ASYNC_ENTER_TIMER
+	LAST_BREAK %r14
+io_skip:
+	stmg	%r0,%r7,__PT_R0(%r11)
+	mvc	__PT_R8(64,%r11),__LC_SAVE_AREA_ASYNC
+	stmg	%r8,%r9,__PT_PSW(%r11)
 	TRACE_IRQS_OFF
-	la	%r2,SP_PTREGS(%r15)	# address of register-save area
-	brasl	%r14,do_IRQ		# call standard irq handler
+	xc	__SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
+	lgr	%r2,%r11		# pass pointer to pt_regs
+	brasl	%r14,do_IRQ
 io_return:
 	LOCKDEP_SYS_EXIT
 	TRACE_IRQS_ON
@@ -587,7 +486,14 @@ io_tif:
 	tm	__TI_flags+7(%r12),_TIF_WORK_INT
 	jnz	io_work 		# there is work to do (signals etc.)
 io_restore:
-	RESTORE_ALL __LC_RETURN_PSW,0
+	lg	%r14,__LC_VDSO_PER_CPU
+	lmg	%r0,%r10,__PT_R0(%r11)
+	mvc	__LC_RETURN_PSW(16),__PT_PSW(%r11)
+	ni	__LC_RETURN_PSW+1,0xfd	# clear wait state bit
+	stpt	__LC_EXIT_TIMER
+	mvc	__VDSO_ECTG_BASE(16,%r14),__LC_EXIT_TIMER
+	lmg	%r11,%r15,__PT_R11(%r11)
+	lpswe	__LC_RETURN_PSW
 io_done:
 
 #
@@ -600,7 +506,7 @@ io_done:
 # Before any work can be done, a switch to the kernel stack is required.
 #
 io_work:
-	tm	SP_PSW+1(%r15),0x01	# returning to user ?
+	tm	__PT_PSW+1(%r11),0x01	# returning to user ?
 	jo	io_work_user		# yes -> do resched & signal
 #ifdef CONFIG_PREEMPT
 	# check for preemptive scheduling
@@ -609,10 +515,11 @@ io_work:
 	tm	__TI_flags+7(%r12),_TIF_NEED_RESCHED
 	jno	io_restore
 	# switch to kernel stack
-	lg	%r1,SP_R15(%r15)
-	aghi	%r1,-SP_SIZE
-	mvc	SP_PTREGS(__PT_SIZE,%r1),SP_PTREGS(%r15)
-	xc	__SF_BACKCHAIN(8,%r1),__SF_BACKCHAIN(%r1) # clear back chain
+	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 io_return, call
 	# TRACE_IRQS_OFF to keep things symmetrical
@@ -628,9 +535,10 @@ io_work:
 #
 io_work_user:
 	lg	%r1,__LC_KERNEL_STACK
-	aghi	%r1,-SP_SIZE
-	mvc	SP_PTREGS(__PT_SIZE,%r1),SP_PTREGS(%r15)
-	xc	__SF_BACKCHAIN(8,%r1),__SF_BACKCHAIN(%r1) # clear back chain
+	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
 
 #
@@ -663,9 +571,9 @@ io_mcck_pending:
 #
 io_reschedule:
 	# TRACE_IRQS_ON already done at io_return
-	stosm	__SF_EMPTY(%r15),0x03	# reenable interrupts
+	ssm	__LC_SVC_NEW_PSW	# reenable interrupts
 	brasl	%r14,schedule		# call scheduler
-	stnsm	__SF_EMPTY(%r15),0xfc	# disable I/O and ext. interrupts
+	ssm	__LC_PGM_NEW_PSW	# disable I/O and ext. interrupts
 	TRACE_IRQS_OFF
 	j	io_return
 
@@ -674,10 +582,10 @@ io_reschedule:
 #
 io_sigpending:
 	# TRACE_IRQS_ON already done at io_return
-	stosm	__SF_EMPTY(%r15),0x03	# reenable interrupts
-	la	%r2,SP_PTREGS(%r15)	# load pt_regs
-	brasl	%r14,do_signal		# call do_signal
-	stnsm	__SF_EMPTY(%r15),0xfc	# disable I/O and ext. interrupts
+	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	io_return
 
@@ -686,10 +594,10 @@ io_sigpending:
 #
 io_notify_resume:
 	# TRACE_IRQS_ON already done at io_return
-	stosm	__SF_EMPTY(%r15),0x03	# reenable interrupts
-	la	%r2,SP_PTREGS(%r15)	# load pt_regs
-	brasl	%r14,do_notify_resume	# call do_notify_resume
-	stnsm	__SF_EMPTY(%r15),0xfc	# disable I/O and ext. interrupts
+	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	io_return
 
@@ -699,21 +607,24 @@ io_notify_resume:
 ENTRY(ext_int_handler)
 	stck	__LC_INT_CLOCK
 	stpt	__LC_ASYNC_ENTER_TIMER
-	SAVE_ALL_ASYNC __LC_EXT_OLD_PSW,__LC_SAVE_AREA+40
-	CREATE_STACK_FRAME __LC_SAVE_AREA+40
-	mvc	SP_PSW(16,%r15),0(%r12)	# move user PSW to stack
-	lg	%r12,__LC_THREAD_INFO	# load pointer to thread_info struct
-	HANDLE_SIE_INTERCEPT
-	tm	SP_PSW+1(%r15),0x01	# interrupting from user ?
-	jz	ext_no_vtime
-	UPDATE_VTIME __LC_EXIT_TIMER,__LC_ASYNC_ENTER_TIMER,__LC_USER_TIMER
-	UPDATE_VTIME __LC_LAST_UPDATE_TIMER,__LC_EXIT_TIMER,__LC_SYSTEM_TIMER
-	mvc	__LC_LAST_UPDATE_TIMER(8),__LC_ASYNC_ENTER_TIMER
-	LAST_BREAK
-ext_no_vtime:
+	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
+	SWITCH_ASYNC __LC_SAVE_AREA_ASYNC,__LC_ASYNC_STACK,STACK_SHIFT
+	tmhh	%r8,0x0001		# interrupting from user ?
+	jz	ext_skip
+	UPDATE_VTIME %r14,__LC_ASYNC_ENTER_TIMER
+	LAST_BREAK %r14
+ext_skip:
+	stmg	%r0,%r7,__PT_R0(%r11)
+	mvc	__PT_R8(64,%r11),__LC_SAVE_AREA_ASYNC
+	stmg	%r8,%r9,__PT_PSW(%r11)
 	TRACE_IRQS_OFF
 	lghi	%r1,4096
-	la	%r2,SP_PTREGS(%r15)	# address of register-save area
+	lgr	%r2,%r11		# pass pointer to pt_regs
 	llgf	%r3,__LC_CPU_ADDRESS	# get cpu address + interruption code
 	llgf	%r4,__LC_EXT_PARAMS	# get external parameter
 	lg	%r5,__LC_EXT_PARAMS2-4096(%r1)	# get 64 bit external parameter
@@ -730,81 +641,77 @@ ENTRY(mcck_int_handler)
 	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
-	stmg	%r11,%r15,__LC_SAVE_AREA+80
+	lg	%r10,__LC_LAST_BREAK
+	lg	%r12,__LC_THREAD_INFO
 	larl	%r13,system_call
-	lg	%r11,__LC_LAST_BREAK
-	la	%r12,__LC_MCK_OLD_PSW
+	lmg	%r8,%r9,__LC_MCK_OLD_PSW
+	HANDLE_SIE_INTERCEPT %r14
 	tm	__LC_MCCK_CODE,0x80	# system damage?
-	jo	mcck_int_main		# yes -> rest of mcck code invalid
-	la	%r14,4095
-	mvc	__LC_MCCK_ENTER_TIMER(8),__LC_CPU_TIMER_SAVE_AREA-4095(%r14)
+	jo	mcck_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	1f
+	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	0f
+	jl	1f
 	la	%r14,__LC_EXIT_TIMER
-0:	clc	0(8,%r14),__LC_LAST_UPDATE_TIMER
-	jl	0f
+1:	clc	0(8,%r14),__LC_LAST_UPDATE_TIMER
+	jl	2f
 	la	%r14,__LC_LAST_UPDATE_TIMER
-0:	spt	0(%r14)
+2:	spt	0(%r14)
 	mvc	__LC_MCCK_ENTER_TIMER(8),0(%r14)
-1:	tm	__LC_MCCK_CODE+2,0x09	# mwp + ia of old psw valid?
-	jno	mcck_int_main		# no -> skip cleanup critical
-	tm	__LC_MCK_OLD_PSW+1,0x01 # test problem state bit
-	jnz	mcck_int_main		# from user -> load kernel stack
-	clc	__LC_MCK_OLD_PSW+8(8),BASED(.Lcritical_end)
-	jhe	mcck_int_main
-	clc	__LC_MCK_OLD_PSW+8(8),BASED(.Lcritical_start)
-	jl	mcck_int_main
-	brasl	%r14,cleanup_critical
-mcck_int_main:
-	lg	%r14,__LC_PANIC_STACK	# are we already on the panic stack?
-	slgr	%r14,%r15
-	srag	%r14,%r14,PAGE_SHIFT
-	jz	0f
-	lg	%r15,__LC_PANIC_STACK	# load panic stack
-0:	aghi	%r15,-SP_SIZE		# make room for registers & psw
-	CREATE_STACK_FRAME __LC_SAVE_AREA+80
-	mvc	SP_PSW(16,%r15),0(%r12)
-	lg	%r12,__LC_THREAD_INFO	# load pointer to thread_info struct
-	tm	__LC_MCCK_CODE+2,0x08	# mwp of old psw valid?
-	jno	mcck_no_vtime		# no -> no timer update
-	HANDLE_SIE_INTERCEPT
-	tm	SP_PSW+1(%r15),0x01	# interrupting from user ?
-	jz	mcck_no_vtime
-	UPDATE_VTIME __LC_EXIT_TIMER,__LC_MCCK_ENTER_TIMER,__LC_USER_TIMER
-	UPDATE_VTIME __LC_LAST_UPDATE_TIMER,__LC_EXIT_TIMER,__LC_SYSTEM_TIMER
-	mvc	__LC_LAST_UPDATE_TIMER(8),__LC_MCCK_ENTER_TIMER
-	LAST_BREAK
-mcck_no_vtime:
-	la	%r2,SP_PTREGS(%r15)	# load pt_regs
+3:	tm	__LC_MCCK_CODE+2,0x09	# mwp + ia of old psw valid?
+	jno	mcck_panic		# no -> skip cleanup critical
+	SWITCH_ASYNC __LC_GPREGS_SAVE_AREA+64,__LC_PANIC_STACK,PAGE_SHIFT
+	tm	%r8,0x0001		# interrupting from user ?
+	jz	mcck_skip
+	UPDATE_VTIME %r14,__LC_MCCK_ENTER_TIMER
+	LAST_BREAK %r14
+mcck_skip:
+	lghi	%r14,__LC_GPREGS_SAVE_AREA
+	mvc	__PT_R0(128,%r11),0(%r14)
+	stmg	%r8,%r9,__PT_PSW(%r11)
+	xc	__SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
+	lgr	%r2,%r11		# pass pointer to pt_regs
 	brasl	%r14,s390_do_machine_check
-	tm	SP_PSW+1(%r15),0x01	# returning to user ?
+	tm	__PT_PSW+1(%r11),0x01	# returning to user ?
 	jno	mcck_return
 	lg	%r1,__LC_KERNEL_STACK	# switch to kernel stack
-	aghi	%r1,-SP_SIZE
-	mvc	SP_PTREGS(__PT_SIZE,%r1),SP_PTREGS(%r15)
-	xc	__SF_BACKCHAIN(8,%r1),__SF_BACKCHAIN(%r1) # clear back chain
+	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
-	stosm	__SF_EMPTY(%r15),0x04	# turn dat on
+	ssm	__LC_PGM_NEW_PSW	# turn dat on, keep irqs off
 	tm	__TI_flags+7(%r12),_TIF_MCCK_PENDING
 	jno	mcck_return
 	TRACE_IRQS_OFF
 	brasl	%r14,s390_handle_mcck
 	TRACE_IRQS_ON
 mcck_return:
-	mvc	__LC_RETURN_MCCK_PSW(16),SP_PSW(%r15) # move return PSW
+	lg	%r14,__LC_VDSO_PER_CPU
+	lmg	%r0,%r10,__PT_R0(%r11)
+	mvc	__LC_RETURN_MCCK_PSW(16),__PT_PSW(%r11) # move return PSW
 	ni	__LC_RETURN_MCCK_PSW+1,0xfd # clear wait state bit
-	lmg	%r0,%r15,SP_R0(%r15)	# load gprs 0-15
 	tm	__LC_RETURN_MCCK_PSW+1,0x01 # returning to user ?
 	jno	0f
 	stpt	__LC_EXIT_TIMER
-0:	lpswe	__LC_RETURN_MCCK_PSW	# back to caller
-mcck_done:
+	mvc	__VDSO_ECTG_BASE(16,%r14),__LC_EXIT_TIMER
+0:	lmg	%r11,%r15,__PT_R11(%r11)
+	lpswe	__LC_RETURN_MCCK_PSW
+
+mcck_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	mcck_skip
 
 /*
  * Restart interruption handler, kick starter for additional CPUs
@@ -818,17 +725,18 @@ restart_base:
 	stck	__LC_LAST_UPDATE_CLOCK
 	mvc	__LC_LAST_UPDATE_TIMER(8),restart_vtime-restart_base(%r1)
 	mvc	__LC_EXIT_TIMER(8),restart_vtime-restart_base(%r1)
-	lg	%r15,__LC_SAVE_AREA+120 # load ksp
+	lghi	%r10,__LC_GPREGS_SAVE_AREA
+	lg	%r15,120(%r10)		# load ksp
 	lghi	%r10,__LC_CREGS_SAVE_AREA
-	lctlg	%c0,%c15,0(%r10) # get new ctl regs
+	lctlg	%c0,%c15,0(%r10)	# get new ctl regs
 	lghi	%r10,__LC_AREGS_SAVE_AREA
 	lam	%a0,%a15,0(%r10)
-	lmg	%r6,%r15,__SF_GPRS(%r15) # load registers from clone
+	lmg	%r6,%r15,__SF_GPRS(%r15)# load registers from clone
 	lg	%r1,__LC_THREAD_INFO
 	mvc	__LC_USER_TIMER(8),__TI_user_timer(%r1)
 	mvc	__LC_SYSTEM_TIMER(8),__TI_system_timer(%r1)
 	xc	__LC_STEAL_TIMER(8),__LC_STEAL_TIMER
-	stosm	__SF_EMPTY(%r15),0x04	# now we can turn dat on
+	ssm	__LC_PGM_NEW_PSW	# turn dat on, keep irqs off
 	brasl	%r14,start_secondary
 	.align	8
 restart_vtime:
@@ -852,16 +760,16 @@ restart_go:
 # PSW restart interrupt handler
 #
 ENTRY(psw_restart_int_handler)
-	stg	%r15,__LC_SAVE_AREA+120(%r0)	# save r15
+	stg	%r15,__LC_SAVE_AREA_RESTART
 	larl	%r15,restart_stack		# load restart stack
 	lg	%r15,0(%r15)
-	aghi	%r15,-SP_SIZE			# make room for pt_regs
-	stmg	%r0,%r14,SP_R0(%r15)		# store gprs %r0-%r14 to stack
-	mvc	SP_R15(8,%r15),__LC_SAVE_AREA+120(%r0)# store saved %r15 to stack
-	mvc	SP_PSW(16,%r15),__LC_RST_OLD_PSW(%r0)# store restart old psw
-	xc	__SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15) # set backchain to 0
+	aghi	%r15,-__PT_SIZE			# create pt_regs on stack
+	stmg	%r0,%r14,__PT_R0(%r15)
+	mvc	__PT_R15(8,%r15),__LC_SAVE_AREA_RESTART
+	mvc	__PT_PSW(16,%r15),__LC_RST_OLD_PSW # store restart old psw
+	aghi	%r15,-STACK_FRAME_OVERHEAD
+	xc	__SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
 	brasl	%r14,do_restart
-
 	larl	%r14,restart_psw_crash		# load disabled wait PSW if
 	lpswe	0(%r14)				# do_restart returns
 	.align 8
@@ -877,172 +785,153 @@ restart_psw_crash:
  * 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
-	aghi	%r15,-SP_SIZE
-	mvc	SP_PSW(16,%r15),0(%r12)	# move user PSW to stack
-	stmg	%r0,%r10,SP_R0(%r15)	# store gprs %r0-%r10 to kernel stack
-	la	%r1,__LC_SAVE_AREA
-	chi	%r12,__LC_SVC_OLD_PSW
-	je	0f
-	chi	%r12,__LC_PGM_OLD_PSW
-	je	0f
-	la	%r1,__LC_SAVE_AREA+40
-0:	mvc	SP_R11(40,%r15),0(%r1)	# move %r11-%r15 to stack
-	mvc	SP_ARGS(8,%r15),__LC_LAST_BREAK
-	xc	__SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15) # clear back chain
-	la	%r2,SP_PTREGS(%r15)	# load pt_regs
+	lg	%r11,__LC_PANIC_STACK	# change to panic stack
+	aghi	%r11,-__PT_SIZE		# create pt_regs
+	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
+	lgr	%r15,%r11
+	aghi	%r15,-STACK_FRAME_OVERHEAD
+	xc	__SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
+	lgr	%r2,%r11		# pass pointer to pt_regs
 	jg	kernel_stack_overflow
 #endif
 
-cleanup_table_system_call:
-	.quad	system_call, sysc_do_svc
-cleanup_table_sysc_tif:
-	.quad	sysc_tif, sysc_restore
-cleanup_table_sysc_restore:
-	.quad	sysc_restore, sysc_done
-cleanup_table_io_tif:
-	.quad	io_tif, io_restore
-cleanup_table_io_restore:
-	.quad	io_restore, io_done
+	.align	8
+cleanup_table:
+	.quad	system_call
+	.quad	sysc_do_svc
+	.quad	sysc_tif
+	.quad	sysc_restore
+	.quad	sysc_done
+	.quad	io_tif
+	.quad	io_restore
+	.quad	io_done
 
 cleanup_critical:
-	clc	8(8,%r12),BASED(cleanup_table_system_call)
+	clg	%r9,BASED(cleanup_table)	# system_call
 	jl	0f
-	clc	8(8,%r12),BASED(cleanup_table_system_call+8)
+	clg	%r9,BASED(cleanup_table+8)	# sysc_do_svc
 	jl	cleanup_system_call
-0:
-	clc	8(8,%r12),BASED(cleanup_table_sysc_tif)
+	clg	%r9,BASED(cleanup_table+16)	# sysc_tif
 	jl	0f
-	clc	8(8,%r12),BASED(cleanup_table_sysc_tif+8)
+	clg	%r9,BASED(cleanup_table+24)	# sysc_restore
 	jl	cleanup_sysc_tif
-0:
-	clc	8(8,%r12),BASED(cleanup_table_sysc_restore)
-	jl	0f
-	clc	8(8,%r12),BASED(cleanup_table_sysc_restore+8)
+	clg	%r9,BASED(cleanup_table+32)	# sysc_done
 	jl	cleanup_sysc_restore
-0:
-	clc	8(8,%r12),BASED(cleanup_table_io_tif)
+	clg	%r9,BASED(cleanup_table+40)	# io_tif
 	jl	0f
-	clc	8(8,%r12),BASED(cleanup_table_io_tif+8)
+	clg	%r9,BASED(cleanup_table+48)	# io_restore
 	jl	cleanup_io_tif
-0:
-	clc	8(8,%r12),BASED(cleanup_table_io_restore)
-	jl	0f
-	clc	8(8,%r12),BASED(cleanup_table_io_restore+8)
+	clg	%r9,BASED(cleanup_table+56)	# io_done
 	jl	cleanup_io_restore
-0:
-	br	%r14
+0:	br	%r14
+
 
 cleanup_system_call:
-	mvc	__LC_RETURN_PSW(16),0(%r12)
-	clc	__LC_RETURN_PSW+8(8),BASED(cleanup_system_call_insn+8)
+	# check if stpt has been executed
+	clg	%r9,BASED(cleanup_system_call_insn)
 	jh	0f
-	mvc	__LC_SYNC_ENTER_TIMER(8),__LC_MCCK_ENTER_TIMER
-	cghi	%r12,__LC_MCK_OLD_PSW
-	je	0f
 	mvc	__LC_SYNC_ENTER_TIMER(8),__LC_ASYNC_ENTER_TIMER
-0:	cghi	%r12,__LC_MCK_OLD_PSW
-	la	%r12,__LC_SAVE_AREA+80
+	cghi	%r11,__LC_SAVE_AREA_ASYNC
 	je	0f
-	la	%r12,__LC_SAVE_AREA+40
-0:	clc	__LC_RETURN_PSW+8(8),BASED(cleanup_system_call_insn+16)
-	jhe	cleanup_vtime
-	clc	__LC_RETURN_PSW+8(8),BASED(cleanup_system_call_insn)
+	mvc	__LC_SYNC_ENTER_TIMER(8),__LC_MCCK_ENTER_TIMER
+0:	# check if stmg has been executed
+	clg	%r9,BASED(cleanup_system_call_insn+8)
 	jh	0f
-	mvc	__LC_SAVE_AREA(40),0(%r12)
-0:	lg	%r15,__LC_KERNEL_STACK	# problem state -> load ksp
-	aghi	%r15,-SP_SIZE		# make room for registers & psw
-	stg	%r15,32(%r12)
-	stg	%r11,0(%r12)
-	CREATE_STACK_FRAME __LC_SAVE_AREA
-	mvc	8(8,%r12),__LC_THREAD_INFO
-	lg	%r12,__LC_THREAD_INFO
-	mvc	SP_PSW(16,%r15),__LC_SVC_OLD_PSW
-	mvc	SP_SVC_CODE(4,%r15),__LC_SVC_ILC
-	oi	__TI_flags+7(%r12),_TIF_SYSCALL
-cleanup_vtime:
-	clc	__LC_RETURN_PSW+8(8),BASED(cleanup_system_call_insn+24)
-	jhe	cleanup_stime
-	UPDATE_VTIME __LC_EXIT_TIMER,__LC_SYNC_ENTER_TIMER,__LC_USER_TIMER
-cleanup_stime:
-	clc	__LC_RETURN_PSW+8(8),BASED(cleanup_system_call_insn+32)
-	jh	cleanup_update
-	UPDATE_VTIME __LC_LAST_UPDATE_TIMER,__LC_EXIT_TIMER,__LC_SYSTEM_TIMER
-cleanup_update:
+	mvc	__LC_SAVE_AREA_SYNC(64),0(%r11)
+0:	# check if base register setup + TIF bit load has been done
+	clg	%r9,BASED(cleanup_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(cleanup_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(cleanup_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
-	srag	%r12,%r11,23
-	lg	%r12,__LC_THREAD_INFO
+	# do LAST_BREAK
+	lg	%r9,16(%r11)
+	srag	%r9,%r9,23
 	jz	0f
-	stg	%r11,__TI_last_break(%r12)
-0:	mvc	__LC_RETURN_PSW+8(8),BASED(cleanup_table_system_call+8)
-	la	%r12,__LC_RETURN_PSW
+	mvc	__TI_last_break(8,%r12),16(%r11)
+0:	# set up saved register r11
+	lg	%r15,__LC_KERNEL_STACK
+	aghi	%r15,-__PT_SIZE
+	stg	%r15,24(%r11)		# r11 pt_regs pointer
+	# fill pt_regs
+	mvc	__PT_R8(64,%r15),__LC_SAVE_AREA_SYNC
+	stmg	%r0,%r7,__PT_R0(%r15)
+	mvc	__PT_PSW(16,%r15),__LC_SVC_OLD_PSW
+	mvc	__PT_INT_CODE(4,%r15),__LC_SVC_ILC
+	# setup saved register r15
+	aghi	%r15,-STACK_FRAME_OVERHEAD
+	stg	%r15,56(%r11)		# r15 stack pointer
+	# set new psw address and exit
+	larl	%r9,sysc_do_svc
 	br	%r14
 cleanup_system_call_insn:
-	.quad	sysc_saveall
 	.quad	system_call
-	.quad	sysc_vtime
-	.quad	sysc_stime
-	.quad	sysc_update
+	.quad	sysc_stmg
+	.quad	sysc_per
+	.quad	sysc_vtime+18
+	.quad	sysc_vtime+42
 
 cleanup_sysc_tif:
-	mvc	__LC_RETURN_PSW(8),0(%r12)
-	mvc	__LC_RETURN_PSW+8(8),BASED(cleanup_table_sysc_tif)
-	la	%r12,__LC_RETURN_PSW
+	larl	%r9,sysc_tif
 	br	%r14
 
 cleanup_sysc_restore:
-	clc	8(8,%r12),BASED(cleanup_sysc_restore_insn)
-	je	2f
-	clc	8(8,%r12),BASED(cleanup_sysc_restore_insn+8)
-	jhe	0f
-	mvc	__LC_EXIT_TIMER(8),__LC_MCCK_ENTER_TIMER
-	cghi	%r12,__LC_MCK_OLD_PSW
+	clg	%r9,BASED(cleanup_sysc_restore_insn)
 	je	0f
-	mvc	__LC_EXIT_TIMER(8),__LC_ASYNC_ENTER_TIMER
-0:	mvc	__LC_RETURN_PSW(16),SP_PSW(%r15)
-	cghi	%r12,__LC_MCK_OLD_PSW
-	la	%r12,__LC_SAVE_AREA+80
-	je	1f
-	la	%r12,__LC_SAVE_AREA+40
-1:	mvc	0(40,%r12),SP_R11(%r15)
-	lmg	%r0,%r10,SP_R0(%r15)
-	lg	%r15,SP_R15(%r15)
-2:	la	%r12,__LC_RETURN_PSW
+	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
 cleanup_sysc_restore_insn:
 	.quad	sysc_done - 4
-	.quad	sysc_done - 16
 
 cleanup_io_tif:
-	mvc	__LC_RETURN_PSW(8),0(%r12)
-	mvc	__LC_RETURN_PSW+8(8),BASED(cleanup_table_io_tif)
-	la	%r12,__LC_RETURN_PSW
+	larl	%r9,io_tif
 	br	%r14
 
 cleanup_io_restore:
-	clc	8(8,%r12),BASED(cleanup_io_restore_insn)
-	je	1f
-	clc	8(8,%r12),BASED(cleanup_io_restore_insn+8)
-	jhe	0f
-	mvc	__LC_EXIT_TIMER(8),__LC_MCCK_ENTER_TIMER
-0:	mvc	__LC_RETURN_PSW(16),SP_PSW(%r15)
-	mvc	__LC_SAVE_AREA+80(40),SP_R11(%r15)
-	lmg	%r0,%r10,SP_R0(%r15)
-	lg	%r15,SP_R15(%r15)
-1:	la	%r12,__LC_RETURN_PSW
+	clg	%r9,BASED(cleanup_io_restore_insn)
+	je	0f
+	lg	%r9,24(%r11)		# get saved r11 pointer to pt_regs
+	mvc	__LC_RETURN_PSW(16),__PT_PSW(%r9)
+	ni	__LC_RETURN_PSW+1,0xfd	# clear wait state bit
+	mvc	0(64,%r11),__PT_R8(%r9)
+	lmg	%r0,%r7,__PT_R0(%r9)
+0:	lmg	%r8,%r9,__LC_RETURN_PSW
 	br	%r14
 cleanup_io_restore_insn:
 	.quad	io_done - 4
-	.quad	io_done - 16
 
 /*
  * Integer constants
  */
-		.align	4
+	.align	8
 .Lcritical_start:
-		.quad	__critical_start
-.Lcritical_end:
-		.quad	__critical_end
+	.quad	__critical_start
+.Lcritical_length:
+	.quad	__critical_end - __critical_start
+
 
 #if defined(CONFIG_KVM) || defined(CONFIG_KVM_MODULE)
 /*
@@ -1054,6 +943,7 @@ 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(8,%r15),__SF_EMPTY+16(%r15) # host id == 0
 	lmg	%r0,%r13,0(%r3)			# load guest gprs 0-13
 	lg	%r14,__LC_THREAD_INFO		# pointer thread_info struct
 	oi	__TI_flags+6(%r14),_TIF_SIE>>8
@@ -1070,7 +960,7 @@ sie_gmap:
 	SPP	__SF_EMPTY(%r15)		# set guest id
 	sie	0(%r14)
 sie_done:
-	SPP	__LC_CMF_HPP			# set host id
+	SPP	__SF_EMPTY+16(%r15)		# set host id
 	lg	%r14,__LC_THREAD_INFO		# pointer thread_info struct
 sie_exit:
 	lctlg	%c1,%c1,__LC_USER_ASCE		# load primary asce
@@ -1093,8 +983,10 @@ sie_fault:
 	.align	8
 .Lsie_loop:
 	.quad	sie_loop
-.Lsie_done:
-	.quad	sie_done
+.Lsie_length:
+	.quad	sie_done - sie_loop
+.Lhost_id:
+	.quad	0
 
 	.section __ex_table,"a"
 	.quad	sie_loop,sie_fault
diff --git a/arch/s390/kernel/head.S b/arch/s390/kernel/head.S
index 900068d2bf92..c27a0727f930 100644
--- a/arch/s390/kernel/head.S
+++ b/arch/s390/kernel/head.S
@@ -329,8 +329,8 @@ iplstart:
 #
 # reset files in VM reader
 #
-	stidp	__LC_SAVE_AREA		# store cpuid
-	tm	__LC_SAVE_AREA,0xff	# running VM ?
+	stidp	__LC_SAVE_AREA_SYNC	# store cpuid
+	tm	__LC_SAVE_AREA_SYNC,0xff# running VM ?
 	bno	.Lnoreset
 	la	%r2,.Lreset
 	lhi	%r3,26
diff --git a/arch/s390/kernel/machine_kexec.c b/arch/s390/kernel/machine_kexec.c
index 3cd0f25ab015..47b168fb29c4 100644
--- a/arch/s390/kernel/machine_kexec.c
+++ b/arch/s390/kernel/machine_kexec.c
@@ -208,6 +208,7 @@ 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);
 }
 
diff --git a/arch/s390/kernel/mem_detect.c b/arch/s390/kernel/mem_detect.c
index 19b4568f4cee..22d502e885ed 100644
--- a/arch/s390/kernel/mem_detect.c
+++ b/arch/s390/kernel/mem_detect.c
@@ -64,70 +64,82 @@ void detect_memory_layout(struct mem_chunk chunk[])
 EXPORT_SYMBOL(detect_memory_layout);
 
 /*
+ * Move memory chunks array from index "from" to index "to"
+ */
+static void mem_chunk_move(struct mem_chunk chunk[], int to, int from)
+{
+	int cnt = MEMORY_CHUNKS - to;
+
+	memmove(&chunk[to], &chunk[from], cnt * sizeof(struct mem_chunk));
+}
+
+/*
+ * Initialize memory chunk
+ */
+static void mem_chunk_init(struct mem_chunk *chunk, unsigned long addr,
+			   unsigned long size, int type)
+{
+	chunk->type = type;
+	chunk->addr = addr;
+	chunk->size = size;
+}
+
+/*
  * Create memory hole with given address, size, and type
  */
-void create_mem_hole(struct mem_chunk chunks[], unsigned long addr,
+void create_mem_hole(struct mem_chunk chunk[], unsigned long addr,
 		     unsigned long size, int type)
 {
-	unsigned long start, end, new_size;
-	int i;
+	unsigned long lh_start, lh_end, lh_size, ch_start, ch_end, ch_size;
+	int i, ch_type;
 
 	for (i = 0; i < MEMORY_CHUNKS; i++) {
-		if (chunks[i].size == 0)
-			continue;
-		if (addr + size < chunks[i].addr)
-			continue;
-		if (addr >= chunks[i].addr + chunks[i].size)
+		if (chunk[i].size == 0)
 			continue;
-		start = max(addr, chunks[i].addr);
-		end = min(addr + size, chunks[i].addr + chunks[i].size);
-		new_size = end - start;
-		if (new_size == 0)
-			continue;
-		if (start == chunks[i].addr &&
-		    end == chunks[i].addr + chunks[i].size) {
-			/* Remove chunk */
-			chunks[i].type = type;
-		} else if (start == chunks[i].addr) {
-			/* Make chunk smaller at start */
-			if (i >= MEMORY_CHUNKS - 1)
-				panic("Unable to create memory hole");
-			memmove(&chunks[i + 1], &chunks[i],
-				sizeof(struct mem_chunk) *
-				(MEMORY_CHUNKS - (i + 1)));
-			chunks[i + 1].addr = chunks[i].addr + new_size;
-			chunks[i + 1].size = chunks[i].size - new_size;
-			chunks[i].size = new_size;
-			chunks[i].type = type;
-			i += 1;
-		} else if (end == chunks[i].addr + chunks[i].size) {
-			/* Make chunk smaller at end */
-			if (i >= MEMORY_CHUNKS - 1)
-				panic("Unable to create memory hole");
-			memmove(&chunks[i + 1], &chunks[i],
-				sizeof(struct mem_chunk) *
-				(MEMORY_CHUNKS - (i + 1)));
-			chunks[i + 1].addr = start;
-			chunks[i + 1].size = new_size;
-			chunks[i + 1].type = type;
-			chunks[i].size -= new_size;
+
+		/* Define chunk properties */
+		ch_start = chunk[i].addr;
+		ch_size = chunk[i].size;
+		ch_end = ch_start + ch_size - 1;
+		ch_type = chunk[i].type;
+
+		/* Is memory chunk hit by memory hole? */
+		if (addr + size <= ch_start)
+			continue; /* No: memory hole in front of chunk */
+		if (addr > ch_end)
+			continue; /* No: memory hole after chunk */
+
+		/* Yes: Define local hole properties */
+		lh_start = max(addr, chunk[i].addr);
+		lh_end = min(addr + size - 1, ch_end);
+		lh_size = lh_end - lh_start + 1;
+
+		if (lh_start == ch_start && lh_end == ch_end) {
+			/* Hole covers complete memory chunk */
+			mem_chunk_init(&chunk[i], lh_start, lh_size, type);
+		} else if (lh_end == ch_end) {
+			/* Hole starts in memory chunk and convers chunk end */
+			mem_chunk_move(chunk, i + 1, i);
+			mem_chunk_init(&chunk[i], ch_start, ch_size - lh_size,
+				       ch_type);
+			mem_chunk_init(&chunk[i + 1], lh_start, lh_size, type);
 			i += 1;
+		} else if (lh_start == ch_start) {
+			/* Hole ends in memory chunk */
+			mem_chunk_move(chunk, i + 1, i);
+			mem_chunk_init(&chunk[i], lh_start, lh_size, type);
+			mem_chunk_init(&chunk[i + 1], lh_end + 1,
+				       ch_size - lh_size, ch_type);
+			break;
 		} else {
-			/* Create memory hole */
-			if (i >= MEMORY_CHUNKS - 2)
-				panic("Unable to create memory hole");
-			memmove(&chunks[i + 2], &chunks[i],
-				sizeof(struct mem_chunk) *
-				(MEMORY_CHUNKS - (i + 2)));
-			chunks[i + 1].addr = addr;
-			chunks[i + 1].size = size;
-			chunks[i + 1].type = type;
-			chunks[i + 2].addr = addr + size;
-			chunks[i + 2].size =
-				chunks[i].addr + chunks[i].size - (addr + size);
-			chunks[i + 2].type = chunks[i].type;
-			chunks[i].size = addr - chunks[i].addr;
-			i += 2;
+			/* Hole splits memory chunk */
+			mem_chunk_move(chunk, i + 2, i);
+			mem_chunk_init(&chunk[i], ch_start,
+				       lh_start - ch_start, ch_type);
+			mem_chunk_init(&chunk[i + 1], lh_start, lh_size, type);
+			mem_chunk_init(&chunk[i + 2], lh_end + 1,
+				       ch_end - lh_end, ch_type);
+			break;
 		}
 	}
 }
diff --git a/arch/s390/kernel/nmi.c b/arch/s390/kernel/nmi.c
index fab88431a06f..0fd2e863e114 100644
--- a/arch/s390/kernel/nmi.c
+++ b/arch/s390/kernel/nmi.c
@@ -30,7 +30,7 @@ struct mcck_struct {
 
 static DEFINE_PER_CPU(struct mcck_struct, cpu_mcck);
 
-static NORET_TYPE void s390_handle_damage(char *msg)
+static void s390_handle_damage(char *msg)
 {
 	smp_send_stop();
 	disabled_wait((unsigned long) __builtin_return_address(0));
diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c
index 9451b210a1b4..e795933eb2cb 100644
--- a/arch/s390/kernel/process.c
+++ b/arch/s390/kernel/process.c
@@ -29,7 +29,6 @@
 #include <asm/irq.h>
 #include <asm/timer.h>
 #include <asm/nmi.h>
-#include <asm/compat.h>
 #include <asm/smp.h>
 #include "entry.h"
 
@@ -76,7 +75,6 @@ static void default_idle(void)
 	if (test_thread_flag(TIF_MCCK_PENDING)) {
 		local_mcck_enable();
 		local_irq_enable();
-		s390_handle_mcck();
 		return;
 	}
 	trace_hardirqs_on();
@@ -91,10 +89,14 @@ static void default_idle(void)
 void cpu_idle(void)
 {
 	for (;;) {
-		tick_nohz_stop_sched_tick(1);
-		while (!need_resched())
+		tick_nohz_idle_enter();
+		rcu_idle_enter();
+		while (!need_resched() && !test_thread_flag(TIF_MCCK_PENDING))
 			default_idle();
-		tick_nohz_restart_sched_tick();
+		rcu_idle_exit();
+		tick_nohz_idle_exit();
+		if (test_thread_flag(TIF_MCCK_PENDING))
+			s390_handle_mcck();
 		preempt_enable_no_resched();
 		schedule();
 		preempt_disable();
diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c
index 450931a45b68..61f95489d70c 100644
--- a/arch/s390/kernel/ptrace.c
+++ b/arch/s390/kernel/ptrace.c
@@ -20,8 +20,8 @@
 #include <linux/regset.h>
 #include <linux/tracehook.h>
 #include <linux/seccomp.h>
+#include <linux/compat.h>
 #include <trace/syscall.h>
-#include <asm/compat.h>
 #include <asm/segment.h>
 #include <asm/page.h>
 #include <asm/pgtable.h>
@@ -296,13 +296,6 @@ static int __poke_user(struct task_struct *child, addr_t addr, addr_t data)
 		     ((data & PSW_MASK_EA) && !(data & PSW_MASK_BA))))
 			/* Invalid psw mask. */
 			return -EINVAL;
-		if (addr == (addr_t) &dummy->regs.psw.addr)
-			/*
-			 * The debugger changed the instruction address,
-			 * reset system call restart, see signal.c:do_signal
-			 */
-			task_thread_info(child)->system_call = 0;
-
 		*(addr_t *)((addr_t) &task_pt_regs(child)->psw + addr) = data;
 
 	} else if (addr < (addr_t) (&dummy->regs.orig_gpr2)) {
@@ -614,11 +607,6 @@ static int __poke_user_compat(struct task_struct *child,
 			/* Transfer 31 bit amode bit to psw mask. */
 			regs->psw.mask = (regs->psw.mask & ~PSW_MASK_BA) |
 				(__u64)(tmp & PSW32_ADDR_AMODE);
-			/*
-			 * The debugger changed the instruction address,
-			 * reset system call restart, see signal.c:do_signal
-			 */
-			task_thread_info(child)->system_call = 0;
 		} else {
 			/* gpr 0-15 */
 			*(__u32*)((addr_t) &regs->psw + addr*2 + 4) = tmp;
@@ -752,20 +740,17 @@ asmlinkage long do_syscall_trace_enter(struct pt_regs *regs)
 	if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
 		trace_sys_enter(regs, regs->gprs[2]);
 
-	if (unlikely(current->audit_context))
-		audit_syscall_entry(is_compat_task() ?
-					AUDIT_ARCH_S390 : AUDIT_ARCH_S390X,
-				    regs->gprs[2], regs->orig_gpr2,
-				    regs->gprs[3], regs->gprs[4],
-				    regs->gprs[5]);
+	audit_syscall_entry(is_compat_task() ?
+				AUDIT_ARCH_S390 : AUDIT_ARCH_S390X,
+			    regs->gprs[2], regs->orig_gpr2,
+			    regs->gprs[3], regs->gprs[4],
+			    regs->gprs[5]);
 	return ret ?: regs->gprs[2];
 }
 
 asmlinkage void do_syscall_trace_exit(struct pt_regs *regs)
 {
-	if (unlikely(current->audit_context))
-		audit_syscall_exit(AUDITSC_RESULT(regs->gprs[2]),
-				   regs->gprs[2]);
+	audit_syscall_exit(regs);
 
 	if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
 		trace_sys_exit(regs, regs->gprs[2]);
@@ -905,6 +890,14 @@ static int s390_last_break_get(struct task_struct *target,
 	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;
+}
+
 #endif
 
 static int s390_system_call_get(struct task_struct *target,
@@ -951,6 +944,7 @@ static const struct user_regset s390_regsets[] = {
 		.size = sizeof(long),
 		.align = sizeof(long),
 		.get = s390_last_break_get,
+		.set = s390_last_break_set,
 	},
 #endif
 	[REGSET_SYSTEM_CALL] = {
@@ -1116,6 +1110,14 @@ static int s390_compat_last_break_get(struct task_struct *target,
 	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[] = {
 	[REGSET_GENERAL] = {
 		.core_note_type = NT_PRSTATUS,
@@ -1139,6 +1141,7 @@ static const struct user_regset s390_compat_regsets[] = {
 		.size = sizeof(long),
 		.align = sizeof(long),
 		.get = s390_compat_last_break_get,
+		.set = s390_compat_last_break_set,
 	},
 	[REGSET_SYSTEM_CALL] = {
 		.core_note_type = NT_S390_SYSTEM_CALL,
diff --git a/arch/s390/kernel/reipl64.S b/arch/s390/kernel/reipl64.S
index 732a793ec53a..36b32658fb24 100644
--- a/arch/s390/kernel/reipl64.S
+++ b/arch/s390/kernel/reipl64.S
@@ -17,11 +17,11 @@
 #
 ENTRY(store_status)
 	/* Save register one and load save area base */
-	stg	%r1,__LC_SAVE_AREA+120(%r0)
+	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+120(%r0)
+	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)
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index e58a462949b1..3b2efc81f34e 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -21,6 +21,7 @@
 #include <linux/module.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>
@@ -45,6 +46,7 @@
 #include <linux/kexec.h>
 #include <linux/crash_dump.h>
 #include <linux/memory.h>
+#include <linux/compat.h>
 
 #include <asm/ipl.h>
 #include <asm/uaccess.h>
@@ -58,7 +60,6 @@
 #include <asm/ptrace.h>
 #include <asm/sections.h>
 #include <asm/ebcdic.h>
-#include <asm/compat.h>
 #include <asm/kvm_virtio.h>
 #include <asm/diag.h>
 
@@ -94,6 +95,15 @@ struct mem_chunk __initdata memory_chunk[MEMORY_CHUNKS];
 int __initdata memory_end_set;
 unsigned long __initdata memory_end;
 
+unsigned long VMALLOC_START;
+EXPORT_SYMBOL(VMALLOC_START);
+
+unsigned long VMALLOC_END;
+EXPORT_SYMBOL(VMALLOC_END);
+
+struct page *vmemmap;
+EXPORT_SYMBOL(vmemmap);
+
 /* An array with a pointer to the lowcore of every CPU. */
 struct _lowcore *lowcore_ptr[NR_CPUS];
 EXPORT_SYMBOL(lowcore_ptr);
@@ -277,6 +287,15 @@ static int __init early_parse_mem(char *p)
 }
 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);
+
 unsigned int user_mode = HOME_SPACE_MODE;
 EXPORT_SYMBOL_GPL(user_mode);
 
@@ -382,7 +401,6 @@ setup_lowcore(void)
 		__ctl_set_bit(14, 29);
 	}
 #else
-	lc->cmf_hpp = -1ULL;
 	lc->vdso_per_cpu_data = (unsigned long) &lc->paste[0];
 #endif
 	lc->sync_enter_timer = S390_lowcore.sync_enter_timer;
@@ -478,8 +496,7 @@ EXPORT_SYMBOL_GPL(real_memory_size);
 
 static void __init setup_memory_end(void)
 {
-	unsigned long memory_size;
-	unsigned long max_mem;
+	unsigned long vmax, vmalloc_size, tmp;
 	int i;
 
 
@@ -489,12 +506,9 @@ static void __init setup_memory_end(void)
 		memory_end_set = 1;
 	}
 #endif
-	memory_size = 0;
+	real_memory_size = 0;
 	memory_end &= PAGE_MASK;
 
-	max_mem = memory_end ? min(VMEM_MAX_PHYS, memory_end) : VMEM_MAX_PHYS;
-	memory_end = min(max_mem, memory_end);
-
 	/*
 	 * Make sure all chunks are MAX_ORDER aligned so we don't need the
 	 * extra checks that HOLES_IN_ZONE would require.
@@ -514,23 +528,48 @@ static void __init setup_memory_end(void)
 			chunk->addr = start;
 			chunk->size = end - start;
 		}
+		real_memory_size = max(real_memory_size,
+				       chunk->addr + chunk->size);
 	}
 
+	/* Choose kernel address space layout: 2, 3, or 4 levels. */
+#ifdef CONFIG_64BIT
+	vmalloc_size = VMALLOC_END ?: 128UL << 30;
+	tmp = (memory_end ?: real_memory_size) / PAGE_SIZE;
+	tmp = tmp * (sizeof(struct page) + PAGE_SIZE) + vmalloc_size;
+	if (tmp <= (1UL << 42))
+		vmax = 1UL << 42;	/* 3-level kernel page table */
+	else
+		vmax = 1UL << 53;	/* 4-level kernel page table */
+#else
+	vmalloc_size = VMALLOC_END ?: 96UL << 20;
+	vmax = 1UL << 31;		/* 2-level kernel page table */
+#endif
+	/* vmalloc area is at the end of the kernel address space. */
+	VMALLOC_END = vmax;
+	VMALLOC_START = vmax - vmalloc_size;
+
+	/* Split remaining virtual space between 1:1 mapping & vmemmap array */
+	tmp = VMALLOC_START / (PAGE_SIZE + sizeof(struct page));
+	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 ?: real_memory_size, tmp);
+
+	/* Fixup memory chunk array to fit into 0..memory_end */
 	for (i = 0; i < MEMORY_CHUNKS; i++) {
 		struct mem_chunk *chunk = &memory_chunk[i];
 
-		real_memory_size = max(real_memory_size,
-				       chunk->addr + chunk->size);
-		if (chunk->addr >= max_mem) {
+		if (chunk->addr >= memory_end) {
 			memset(chunk, 0, sizeof(*chunk));
 			continue;
 		}
-		if (chunk->addr + chunk->size > max_mem)
-			chunk->size = max_mem - chunk->addr;
-		memory_size = max(memory_size, chunk->addr + chunk->size);
+		if (chunk->addr + chunk->size > memory_end)
+			chunk->size = memory_end - chunk->addr;
 	}
-	if (!memory_end)
-		memory_end = memory_size;
 }
 
 void *restart_stack __attribute__((__section__(".data")));
@@ -579,7 +618,7 @@ static unsigned long __init find_crash_base(unsigned long crash_size,
 		*msg = "first memory chunk must be at least crashkernel size";
 		return 0;
 	}
-	if (is_kdump_kernel() && (crash_size == OLDMEM_SIZE))
+	if (OLDMEM_BASE && crash_size == OLDMEM_SIZE)
 		return OLDMEM_BASE;
 
 	for (i = MEMORY_CHUNKS - 1; i >= 0; i--) {
@@ -654,7 +693,6 @@ static int __init verify_crash_base(unsigned long crash_base,
 static void __init reserve_kdump_bootmem(unsigned long addr, unsigned long size,
 					 int type)
 {
-
 	create_mem_hole(memory_chunk, addr, size, type);
 }
 
@@ -820,7 +858,8 @@ setup_memory(void)
 		end_chunk = min(end_chunk, end_pfn);
 		if (start_chunk >= end_chunk)
 			continue;
-		add_active_range(0, start_chunk, end_chunk);
+		memblock_add_node(PFN_PHYS(start_chunk),
+				  PFN_PHYS(end_chunk - start_chunk), 0);
 		pfn = max(start_chunk, start_pfn);
 		for (; pfn < end_chunk; pfn++)
 			page_set_storage_key(PFN_PHYS(pfn),
diff --git a/arch/s390/kernel/signal.c b/arch/s390/kernel/signal.c
index 05a85bc14c98..2d421d90fada 100644
--- a/arch/s390/kernel/signal.c
+++ b/arch/s390/kernel/signal.c
@@ -30,7 +30,6 @@
 #include <asm/ucontext.h>
 #include <asm/uaccess.h>
 #include <asm/lowcore.h>
-#include <asm/compat.h>
 #include "entry.h"
 
 #define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP)))
@@ -302,9 +301,13 @@ static int setup_frame(int sig, struct k_sigaction *ka,
 
 	/* We forgot to include these in the sigcontext.
 	   To avoid breaking binary compatibility, they are passed as args. */
-	regs->gprs[4] = current->thread.trap_no;
-	regs->gprs[5] = current->thread.prot_addr;
-	regs->gprs[6] = task_thread_info(current)->last_break;
+	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;
+	}
 
 	/* Place signal number on stack to allow backtrace from handler.  */
 	if (__put_user(regs->gprs[2], (int __user *) &frame->signo))
@@ -434,13 +437,13 @@ void do_signal(struct pt_regs *regs)
 	 * call information.
 	 */
 	current_thread_info()->system_call =
-		test_thread_flag(TIF_SYSCALL) ? regs->svc_code : 0;
+		test_thread_flag(TIF_SYSCALL) ? regs->int_code : 0;
 	signr = get_signal_to_deliver(&info, &ka, regs, NULL);
 
 	if (signr > 0) {
 		/* Whee!  Actually deliver the signal.  */
 		if (current_thread_info()->system_call) {
-			regs->svc_code = 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:
@@ -457,12 +460,12 @@ void do_signal(struct pt_regs *regs)
 				regs->gprs[2] = regs->orig_gpr2;
 				regs->psw.addr =
 					__rewind_psw(regs->psw,
-						     regs->svc_code >> 16);
+						     regs->int_code >> 16);
 				break;
 			}
-			/* No longer in a system call */
-			clear_thread_flag(TIF_SYSCALL);
 		}
+		/* No longer in a system call */
+		clear_thread_flag(TIF_SYSCALL);
 
 		if ((is_compat_task() ?
 		     handle_signal32(signr, &ka, &info, oldset, regs) :
@@ -486,12 +489,13 @@ void do_signal(struct pt_regs *regs)
 	}
 
 	/* No handlers present - check for system call restart */
+	clear_thread_flag(TIF_SYSCALL);
 	if (current_thread_info()->system_call) {
-		regs->svc_code = 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->svc_code = __NR_restart_syscall;
+			regs->int_code = __NR_restart_syscall;
 		/* fallthrough */
 		case -ERESTARTNOHAND:
 		case -ERESTARTSYS:
@@ -500,9 +504,6 @@ void do_signal(struct pt_regs *regs)
 			regs->gprs[2] = regs->orig_gpr2;
 			set_thread_flag(TIF_SYSCALL);
 			break;
-		default:
-			clear_thread_flag(TIF_SYSCALL);
-			break;
 		}
 	}
 
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index 3ea872890da2..2398ce6b15ae 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -69,9 +69,7 @@ enum s390_cpu_state {
 };
 
 DEFINE_MUTEX(smp_cpu_state_mutex);
-int smp_cpu_polarization[NR_CPUS];
 static int smp_cpu_state[NR_CPUS];
-static int cpu_management;
 
 static DEFINE_PER_CPU(struct cpu, cpu_devices);
 
@@ -149,29 +147,59 @@ void smp_switch_to_ipl_cpu(void (*func)(void *), void *data)
 	sp -= sizeof(struct pt_regs);
 	regs = (struct pt_regs *) sp;
 	memcpy(&regs->gprs, &current_lc->gpregs_save_area, sizeof(regs->gprs));
-	regs->psw = lc->psw_save_area;
+	regs->psw = current_lc->psw_save_area;
 	sp -= STACK_FRAME_OVERHEAD;
 	sf = (struct stack_frame *) sp;
-	sf->back_chain = regs->gprs[15];
+	sf->back_chain = 0;
 	smp_switch_to_cpu(func, data, sp, stap(), __cpu_logical_map[0]);
 }
 
+static void smp_stop_cpu(void)
+{
+	while (sigp(smp_processor_id(), sigp_stop) == sigp_busy)
+		cpu_relax();
+}
+
 void smp_send_stop(void)
 {
-	int cpu, rc;
+	cpumask_t cpumask;
+	int cpu;
+	u64 end;
 
 	/* Disable all interrupts/machine checks */
 	__load_psw_mask(psw_kernel_bits | PSW_MASK_DAT);
 	trace_hardirqs_off();
 
-	/* stop all processors */
-	for_each_online_cpu(cpu) {
-		if (cpu == smp_processor_id())
-			continue;
-		do {
-			rc = sigp(cpu, sigp_stop);
-		} while (rc == sigp_busy);
+	cpumask_copy(&cpumask, cpu_online_mask);
+	cpumask_clear_cpu(smp_processor_id(), &cpumask);
+
+	if (oops_in_progress) {
+		/*
+		 * Give the other cpus the opportunity to complete
+		 * outstanding interrupts before stopping them.
+		 */
+		end = get_clock() + (1000000UL << 12);
+		for_each_cpu(cpu, &cpumask) {
+			set_bit(ec_stop_cpu, (unsigned long *)
+				&lowcore_ptr[cpu]->ext_call_fast);
+			while (sigp(cpu, sigp_emergency_signal) == sigp_busy &&
+			       get_clock() < end)
+				cpu_relax();
+		}
+		while (get_clock() < end) {
+			for_each_cpu(cpu, &cpumask)
+				if (cpu_stopped(cpu))
+					cpumask_clear_cpu(cpu, &cpumask);
+			if (cpumask_empty(&cpumask))
+				break;
+			cpu_relax();
+		}
+	}
 
+	/* stop all processors */
+	for_each_cpu(cpu, &cpumask) {
+		while (sigp(cpu, sigp_stop) == sigp_busy)
+			cpu_relax();
 		while (!cpu_stopped(cpu))
 			cpu_relax();
 	}
@@ -187,7 +215,7 @@ static void do_ext_call_interrupt(unsigned int ext_int_code,
 {
 	unsigned long bits;
 
-	if (ext_int_code == 0x1202)
+	if ((ext_int_code & 0xffff) == 0x1202)
 		kstat_cpu(smp_processor_id()).irqs[EXTINT_EXC]++;
 	else
 		kstat_cpu(smp_processor_id()).irqs[EXTINT_EMS]++;
@@ -196,6 +224,9 @@ static void do_ext_call_interrupt(unsigned int ext_int_code,
 	 */
 	bits = xchg(&S390_lowcore.ext_call_fast, 0);
 
+	if (test_bit(ec_stop_cpu, &bits))
+		smp_stop_cpu();
+
 	if (test_bit(ec_schedule, &bits))
 		scheduler_ipi();
 
@@ -204,6 +235,7 @@ static void do_ext_call_interrupt(unsigned int ext_int_code,
 
 	if (test_bit(ec_call_function_single, &bits))
 		generic_smp_call_function_single_interrupt();
+
 }
 
 /*
@@ -369,7 +401,7 @@ static int smp_rescan_cpus_sigp(cpumask_t avail)
 		if (cpu_known(cpu_id))
 			continue;
 		__cpu_logical_map[logical_cpu] = cpu_id;
-		smp_cpu_polarization[logical_cpu] = POLARIZATION_UNKNWN;
+		cpu_set_polarization(logical_cpu, POLARIZATION_UNKNOWN);
 		if (!cpu_stopped(logical_cpu))
 			continue;
 		set_cpu_present(logical_cpu, true);
@@ -403,7 +435,7 @@ static int smp_rescan_cpus_sclp(cpumask_t avail)
 		if (cpu_known(cpu_id))
 			continue;
 		__cpu_logical_map[logical_cpu] = cpu_id;
-		smp_cpu_polarization[logical_cpu] = POLARIZATION_UNKNWN;
+		cpu_set_polarization(logical_cpu, POLARIZATION_UNKNOWN);
 		set_cpu_present(logical_cpu, true);
 		if (cpu >= info->configured)
 			smp_cpu_state[logical_cpu] = CPU_STATE_STANDBY;
@@ -656,7 +688,7 @@ int __cpuinit __cpu_up(unsigned int cpu)
 				     - sizeof(struct stack_frame));
 	memset(sf, 0, sizeof(struct stack_frame));
 	sf->gprs[9] = (unsigned long) sf;
-	cpu_lowcore->save_area[15] = (unsigned long) sf;
+	cpu_lowcore->gpregs_save_area[15] = (unsigned long) sf;
 	__ctl_store(cpu_lowcore->cregs_save_area, 0, 15);
 	atomic_inc(&init_mm.context.attach_count);
 	asm volatile(
@@ -806,7 +838,7 @@ void __init smp_prepare_boot_cpu(void)
 	S390_lowcore.percpu_offset = __per_cpu_offset[0];
 	current_set[0] = current;
 	smp_cpu_state[0] = CPU_STATE_CONFIGURED;
-	smp_cpu_polarization[0] = POLARIZATION_UNKNWN;
+	cpu_set_polarization(0, POLARIZATION_UNKNOWN);
 }
 
 void __init smp_cpus_done(unsigned int max_cpus)
@@ -831,8 +863,8 @@ int setup_profiling_timer(unsigned int multiplier)
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
-static ssize_t cpu_configure_show(struct sys_device *dev,
-				struct sysdev_attribute *attr, char *buf)
+static ssize_t cpu_configure_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
 {
 	ssize_t count;
 
@@ -842,8 +874,8 @@ static ssize_t cpu_configure_show(struct sys_device *dev,
 	return count;
 }
 
-static ssize_t cpu_configure_store(struct sys_device *dev,
-				  struct sysdev_attribute *attr,
+static ssize_t cpu_configure_store(struct device *dev,
+				  struct device_attribute *attr,
 				  const char *buf, size_t count)
 {
 	int cpu = dev->id;
@@ -868,7 +900,8 @@ static ssize_t cpu_configure_store(struct sys_device *dev,
 			rc = sclp_cpu_deconfigure(__cpu_logical_map[cpu]);
 			if (!rc) {
 				smp_cpu_state[cpu] = CPU_STATE_STANDBY;
-				smp_cpu_polarization[cpu] = POLARIZATION_UNKNWN;
+				cpu_set_polarization(cpu, POLARIZATION_UNKNOWN);
+				topology_expect_change();
 			}
 		}
 		break;
@@ -877,7 +910,8 @@ static ssize_t cpu_configure_store(struct sys_device *dev,
 			rc = sclp_cpu_configure(__cpu_logical_map[cpu]);
 			if (!rc) {
 				smp_cpu_state[cpu] = CPU_STATE_CONFIGURED;
-				smp_cpu_polarization[cpu] = POLARIZATION_UNKNWN;
+				cpu_set_polarization(cpu, POLARIZATION_UNKNOWN);
+				topology_expect_change();
 			}
 		}
 		break;
@@ -889,52 +923,21 @@ out:
 	put_online_cpus();
 	return rc ? rc : count;
 }
-static SYSDEV_ATTR(configure, 0644, cpu_configure_show, cpu_configure_store);
+static DEVICE_ATTR(configure, 0644, cpu_configure_show, cpu_configure_store);
 #endif /* CONFIG_HOTPLUG_CPU */
 
-static ssize_t cpu_polarization_show(struct sys_device *dev,
-				     struct sysdev_attribute *attr, char *buf)
-{
-	int cpu = dev->id;
-	ssize_t count;
-
-	mutex_lock(&smp_cpu_state_mutex);
-	switch (smp_cpu_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 SYSDEV_ATTR(polarization, 0444, cpu_polarization_show, NULL);
-
-static ssize_t show_cpu_address(struct sys_device *dev,
-				struct sysdev_attribute *attr, char *buf)
+static ssize_t show_cpu_address(struct device *dev,
+				struct device_attribute *attr, char *buf)
 {
 	return sprintf(buf, "%d\n", __cpu_logical_map[dev->id]);
 }
-static SYSDEV_ATTR(address, 0444, show_cpu_address, NULL);
-
+static DEVICE_ATTR(address, 0444, show_cpu_address, NULL);
 
 static struct attribute *cpu_common_attrs[] = {
 #ifdef CONFIG_HOTPLUG_CPU
-	&attr_configure.attr,
+	&dev_attr_configure.attr,
 #endif
-	&attr_address.attr,
-	&attr_polarization.attr,
+	&dev_attr_address.attr,
 	NULL,
 };
 
@@ -942,8 +945,8 @@ static struct attribute_group cpu_common_attr_group = {
 	.attrs = cpu_common_attrs,
 };
 
-static ssize_t show_capability(struct sys_device *dev,
-				struct sysdev_attribute *attr, char *buf)
+static ssize_t show_capability(struct device *dev,
+				struct device_attribute *attr, char *buf)
 {
 	unsigned int capability;
 	int rc;
@@ -953,10 +956,10 @@ static ssize_t show_capability(struct sys_device *dev,
 		return rc;
 	return sprintf(buf, "%u\n", capability);
 }
-static SYSDEV_ATTR(capability, 0444, show_capability, NULL);
+static DEVICE_ATTR(capability, 0444, show_capability, NULL);
 
-static ssize_t show_idle_count(struct sys_device *dev,
-				struct sysdev_attribute *attr, char *buf)
+static ssize_t show_idle_count(struct device *dev,
+				struct device_attribute *attr, char *buf)
 {
 	struct s390_idle_data *idle;
 	unsigned long long idle_count;
@@ -976,10 +979,10 @@ repeat:
 		goto repeat;
 	return sprintf(buf, "%llu\n", idle_count);
 }
-static SYSDEV_ATTR(idle_count, 0444, show_idle_count, NULL);
+static DEVICE_ATTR(idle_count, 0444, show_idle_count, NULL);
 
-static ssize_t show_idle_time(struct sys_device *dev,
-				struct sysdev_attribute *attr, char *buf)
+static ssize_t show_idle_time(struct device *dev,
+				struct device_attribute *attr, char *buf)
 {
 	struct s390_idle_data *idle;
 	unsigned long long now, idle_time, idle_enter;
@@ -1001,12 +1004,12 @@ repeat:
 		goto repeat;
 	return sprintf(buf, "%llu\n", idle_time >> 12);
 }
-static SYSDEV_ATTR(idle_time_us, 0444, show_idle_time, NULL);
+static DEVICE_ATTR(idle_time_us, 0444, show_idle_time, NULL);
 
 static struct attribute *cpu_online_attrs[] = {
-	&attr_capability.attr,
-	&attr_idle_count.attr,
-	&attr_idle_time_us.attr,
+	&dev_attr_capability.attr,
+	&dev_attr_idle_count.attr,
+	&dev_attr_idle_time_us.attr,
 	NULL,
 };
 
@@ -1019,7 +1022,7 @@ static int __cpuinit smp_cpu_notify(struct notifier_block *self,
 {
 	unsigned int cpu = (unsigned int)(long)hcpu;
 	struct cpu *c = &per_cpu(cpu_devices, cpu);
-	struct sys_device *s = &c->sysdev;
+	struct device *s = &c->dev;
 	struct s390_idle_data *idle;
 	int err = 0;
 
@@ -1045,7 +1048,7 @@ static struct notifier_block __cpuinitdata smp_cpu_nb = {
 static int __devinit smp_add_present_cpu(int cpu)
 {
 	struct cpu *c = &per_cpu(cpu_devices, cpu);
-	struct sys_device *s = &c->sysdev;
+	struct device *s = &c->dev;
 	int rc;
 
 	c->hotpluggable = 1;
@@ -1055,11 +1058,20 @@ static int __devinit smp_add_present_cpu(int cpu)
 	rc = sysfs_create_group(&s->kobj, &cpu_common_attr_group);
 	if (rc)
 		goto out_cpu;
-	if (!cpu_online(cpu))
-		goto out;
-	rc = sysfs_create_group(&s->kobj, &cpu_online_attr_group);
-	if (!rc)
-		return 0;
+	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
@@ -1098,8 +1110,8 @@ out:
 	return rc;
 }
 
-static ssize_t __ref rescan_store(struct sysdev_class *class,
-				  struct sysdev_class_attribute *attr,
+static ssize_t __ref rescan_store(struct device *dev,
+				  struct device_attribute *attr,
 				  const char *buf,
 				  size_t count)
 {
@@ -1108,64 +1120,19 @@ static ssize_t __ref rescan_store(struct sysdev_class *class,
 	rc = smp_rescan_cpus();
 	return rc ? rc : count;
 }
-static SYSDEV_CLASS_ATTR(rescan, 0200, NULL, rescan_store);
+static DEVICE_ATTR(rescan, 0200, NULL, rescan_store);
 #endif /* CONFIG_HOTPLUG_CPU */
 
-static ssize_t dispatching_show(struct sysdev_class *class,
-				struct sysdev_class_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 sysdev_class *dev,
-				 struct sysdev_class_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)
-		cpu_management = val;
-out:
-	mutex_unlock(&smp_cpu_state_mutex);
-	put_online_cpus();
-	return rc ? rc : count;
-}
-static SYSDEV_CLASS_ATTR(dispatching, 0644, dispatching_show,
-			 dispatching_store);
-
-static int __init topology_init(void)
+static int __init s390_smp_init(void)
 {
-	int cpu;
-	int rc;
+	int cpu, rc;
 
 	register_cpu_notifier(&smp_cpu_nb);
-
 #ifdef CONFIG_HOTPLUG_CPU
-	rc = sysdev_class_create_file(&cpu_sysdev_class, &attr_rescan);
+	rc = device_create_file(cpu_subsys.dev_root, &dev_attr_rescan);
 	if (rc)
 		return rc;
 #endif
-	rc = sysdev_class_create_file(&cpu_sysdev_class, &attr_dispatching);
-	if (rc)
-		return rc;
 	for_each_present_cpu(cpu) {
 		rc = smp_add_present_cpu(cpu);
 		if (rc)
@@ -1173,4 +1140,4 @@ static int __init topology_init(void)
 	}
 	return 0;
 }
-subsys_initcall(topology_init);
+subsys_initcall(s390_smp_init);
diff --git a/arch/s390/kernel/sys_s390.c b/arch/s390/kernel/sys_s390.c
index 476081440df9..78ea1948ff51 100644
--- a/arch/s390/kernel/sys_s390.c
+++ b/arch/s390/kernel/sys_s390.c
@@ -60,74 +60,22 @@ out:
 }
 
 /*
- * sys_ipc() is the de-multiplexer for the SysV IPC calls..
- *
- * This is really horribly ugly.
+ * 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)
 {
-        struct ipc_kludge tmp;
-	int ret;
-
-        switch (call) {
-        case SEMOP:
-		return sys_semtimedop(first, (struct sembuf __user *)ptr,
-				       (unsigned)second, NULL);
-	case SEMTIMEDOP:
-		return sys_semtimedop(first, (struct sembuf __user *)ptr,
-				       (unsigned)second,
-				       (const struct timespec __user *) third);
-        case SEMGET:
-                return sys_semget(first, (int)second, third);
-        case SEMCTL: {
-                union semun fourth;
-                if (!ptr)
-                        return -EINVAL;
-                if (get_user(fourth.__pad, (void __user * __user *) ptr))
-                        return -EFAULT;
-                return sys_semctl(first, (int)second, third, fourth);
-        }
-        case MSGSND:
-		return sys_msgsnd (first, (struct msgbuf __user *) ptr,
-                                   (size_t)second, third);
-		break;
-        case MSGRCV:
-                if (!ptr)
-                        return -EINVAL;
-                if (copy_from_user (&tmp, (struct ipc_kludge __user *) ptr,
-                                    sizeof (struct ipc_kludge)))
-                        return -EFAULT;
-                return sys_msgrcv (first, tmp.msgp,
-                                   (size_t)second, tmp.msgtyp, third);
-        case MSGGET:
-                return sys_msgget((key_t)first, (int)second);
-        case MSGCTL:
-                return sys_msgctl(first, (int)second,
-				   (struct msqid_ds __user *)ptr);
-
-	case SHMAT: {
-		ulong raddr;
-		ret = do_shmat(first, (char __user *)ptr,
-				(int)second, &raddr);
-		if (ret)
-			return ret;
-		return put_user (raddr, (ulong __user *) third);
-		break;
-        }
-	case SHMDT:
-		return sys_shmdt ((char __user *)ptr);
-	case SHMGET:
-		return sys_shmget(first, (size_t)second, third);
-	case SHMCTL:
-		return sys_shmctl(first, (int)second,
-                                   (struct shmid_ds __user *) ptr);
-	default:
-		return -ENOSYS;
-
-	}
-
-	return -EINVAL;
+	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);
 }
 
 #ifdef CONFIG_64BIT
diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c
index ebbfab3c6e5a..14da278febbf 100644
--- a/arch/s390/kernel/time.c
+++ b/arch/s390/kernel/time.c
@@ -27,7 +27,7 @@
 #include <linux/cpu.h>
 #include <linux/stop_machine.h>
 #include <linux/time.h>
-#include <linux/sysdev.h>
+#include <linux/device.h>
 #include <linux/delay.h>
 #include <linux/init.h>
 #include <linux/smp.h>
@@ -113,11 +113,14 @@ static void fixup_clock_comparator(unsigned long long delta)
 static int s390_next_ktime(ktime_t expires,
 			   struct clock_event_device *evt)
 {
+	struct timespec ts;
 	u64 nsecs;
 
-	nsecs = ktime_to_ns(ktime_sub(expires, ktime_get_monotonic_offset()));
+	ts.tv_sec = ts.tv_nsec = 0;
+	monotonic_to_bootbased(&ts);
+	nsecs = ktime_to_ns(ktime_add(timespec_to_ktime(ts), expires));
 	do_div(nsecs, 125);
-	S390_lowcore.clock_comparator = TOD_UNIX_EPOCH + (nsecs << 9);
+	S390_lowcore.clock_comparator = sched_clock_base_cc + (nsecs << 9);
 	set_clock_comparator(S390_lowcore.clock_comparator);
 	return 0;
 }
@@ -1116,34 +1119,35 @@ out_unlock:
 /*
  * Sysfs interface functions
  */
-static struct sysdev_class etr_sysclass = {
-	.name	= "etr",
+static struct bus_type etr_subsys = {
+	.name		= "etr",
+	.dev_name	= "etr",
 };
 
-static struct sys_device etr_port0_dev = {
+static struct device etr_port0_dev = {
 	.id	= 0,
-	.cls	= &etr_sysclass,
+	.bus	= &etr_subsys,
 };
 
-static struct sys_device etr_port1_dev = {
+static struct device etr_port1_dev = {
 	.id	= 1,
-	.cls	= &etr_sysclass,
+	.bus	= &etr_subsys,
 };
 
 /*
- * ETR class attributes
+ * ETR subsys attributes
  */
-static ssize_t etr_stepping_port_show(struct sysdev_class *class,
-					struct sysdev_class_attribute *attr,
+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 SYSDEV_CLASS_ATTR(stepping_port, 0400, etr_stepping_port_show, NULL);
+static DEVICE_ATTR(stepping_port, 0400, etr_stepping_port_show, NULL);
 
-static ssize_t etr_stepping_mode_show(struct sysdev_class *class,
-				      	struct sysdev_class_attribute *attr,
+static ssize_t etr_stepping_mode_show(struct device *dev,
+					struct device_attribute *attr,
 					char *buf)
 {
 	char *mode_str;
@@ -1157,12 +1161,12 @@ static ssize_t etr_stepping_mode_show(struct sysdev_class *class,
 	return sprintf(buf, "%s\n", mode_str);
 }
 
-static SYSDEV_CLASS_ATTR(stepping_mode, 0400, etr_stepping_mode_show, NULL);
+static DEVICE_ATTR(stepping_mode, 0400, etr_stepping_mode_show, NULL);
 
 /*
  * ETR port attributes
  */
-static inline struct etr_aib *etr_aib_from_dev(struct sys_device *dev)
+static inline struct etr_aib *etr_aib_from_dev(struct device *dev)
 {
 	if (dev == &etr_port0_dev)
 		return etr_port0_online ? &etr_port0 : NULL;
@@ -1170,8 +1174,8 @@ static inline struct etr_aib *etr_aib_from_dev(struct sys_device *dev)
 		return etr_port1_online ? &etr_port1 : NULL;
 }
 
-static ssize_t etr_online_show(struct sys_device *dev,
-				struct sysdev_attribute *attr,
+static ssize_t etr_online_show(struct device *dev,
+				struct device_attribute *attr,
 				char *buf)
 {
 	unsigned int online;
@@ -1180,8 +1184,8 @@ static ssize_t etr_online_show(struct sys_device *dev,
 	return sprintf(buf, "%i\n", online);
 }
 
-static ssize_t etr_online_store(struct sys_device *dev,
-				struct sysdev_attribute *attr,
+static ssize_t etr_online_store(struct device *dev,
+				struct device_attribute *attr,
 				const char *buf, size_t count)
 {
 	unsigned int value;
@@ -1218,20 +1222,20 @@ out:
 	return count;
 }
 
-static SYSDEV_ATTR(online, 0600, etr_online_show, etr_online_store);
+static DEVICE_ATTR(online, 0600, etr_online_show, etr_online_store);
 
-static ssize_t etr_stepping_control_show(struct sys_device *dev,
-					struct sysdev_attribute *attr,
+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 SYSDEV_ATTR(stepping_control, 0400, etr_stepping_control_show, NULL);
+static DEVICE_ATTR(stepping_control, 0400, etr_stepping_control_show, NULL);
 
-static ssize_t etr_mode_code_show(struct sys_device *dev,
-				struct sysdev_attribute *attr, char *buf)
+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. */
@@ -1240,10 +1244,10 @@ static ssize_t etr_mode_code_show(struct sys_device *dev,
 		       etr_port0.esw.psc0 : etr_port0.esw.psc1);
 }
 
-static SYSDEV_ATTR(state_code, 0400, etr_mode_code_show, NULL);
+static DEVICE_ATTR(state_code, 0400, etr_mode_code_show, NULL);
 
-static ssize_t etr_untuned_show(struct sys_device *dev,
-				struct sysdev_attribute *attr, char *buf)
+static ssize_t etr_untuned_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
 {
 	struct etr_aib *aib = etr_aib_from_dev(dev);
 
@@ -1252,10 +1256,10 @@ static ssize_t etr_untuned_show(struct sys_device *dev,
 	return sprintf(buf, "%i\n", aib->edf1.u);
 }
 
-static SYSDEV_ATTR(untuned, 0400, etr_untuned_show, NULL);
+static DEVICE_ATTR(untuned, 0400, etr_untuned_show, NULL);
 
-static ssize_t etr_network_id_show(struct sys_device *dev,
-				struct sysdev_attribute *attr, char *buf)
+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);
 
@@ -1264,10 +1268,10 @@ static ssize_t etr_network_id_show(struct sys_device *dev,
 	return sprintf(buf, "%i\n", aib->edf1.net_id);
 }
 
-static SYSDEV_ATTR(network, 0400, etr_network_id_show, NULL);
+static DEVICE_ATTR(network, 0400, etr_network_id_show, NULL);
 
-static ssize_t etr_id_show(struct sys_device *dev,
-			struct sysdev_attribute *attr, char *buf)
+static ssize_t etr_id_show(struct device *dev,
+			struct device_attribute *attr, char *buf)
 {
 	struct etr_aib *aib = etr_aib_from_dev(dev);
 
@@ -1276,10 +1280,10 @@ static ssize_t etr_id_show(struct sys_device *dev,
 	return sprintf(buf, "%i\n", aib->edf1.etr_id);
 }
 
-static SYSDEV_ATTR(id, 0400, etr_id_show, NULL);
+static DEVICE_ATTR(id, 0400, etr_id_show, NULL);
 
-static ssize_t etr_port_number_show(struct sys_device *dev,
-			struct sysdev_attribute *attr, char *buf)
+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);
 
@@ -1288,10 +1292,10 @@ static ssize_t etr_port_number_show(struct sys_device *dev,
 	return sprintf(buf, "%i\n", aib->edf1.etr_pn);
 }
 
-static SYSDEV_ATTR(port, 0400, etr_port_number_show, NULL);
+static DEVICE_ATTR(port, 0400, etr_port_number_show, NULL);
 
-static ssize_t etr_coupled_show(struct sys_device *dev,
-			struct sysdev_attribute *attr, char *buf)
+static ssize_t etr_coupled_show(struct device *dev,
+			struct device_attribute *attr, char *buf)
 {
 	struct etr_aib *aib = etr_aib_from_dev(dev);
 
@@ -1300,10 +1304,10 @@ static ssize_t etr_coupled_show(struct sys_device *dev,
 	return sprintf(buf, "%i\n", aib->edf3.c);
 }
 
-static SYSDEV_ATTR(coupled, 0400, etr_coupled_show, NULL);
+static DEVICE_ATTR(coupled, 0400, etr_coupled_show, NULL);
 
-static ssize_t etr_local_time_show(struct sys_device *dev,
-			struct sysdev_attribute *attr, char *buf)
+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);
 
@@ -1312,10 +1316,10 @@ static ssize_t etr_local_time_show(struct sys_device *dev,
 	return sprintf(buf, "%i\n", aib->edf3.blto);
 }
 
-static SYSDEV_ATTR(local_time, 0400, etr_local_time_show, NULL);
+static DEVICE_ATTR(local_time, 0400, etr_local_time_show, NULL);
 
-static ssize_t etr_utc_offset_show(struct sys_device *dev,
-			struct sysdev_attribute *attr, char *buf)
+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);
 
@@ -1324,64 +1328,64 @@ static ssize_t etr_utc_offset_show(struct sys_device *dev,
 	return sprintf(buf, "%i\n", aib->edf3.buo);
 }
 
-static SYSDEV_ATTR(utc_offset, 0400, etr_utc_offset_show, NULL);
+static DEVICE_ATTR(utc_offset, 0400, etr_utc_offset_show, NULL);
 
-static struct sysdev_attribute *etr_port_attributes[] = {
-	&attr_online,
-	&attr_stepping_control,
-	&attr_state_code,
-	&attr_untuned,
-	&attr_network,
-	&attr_id,
-	&attr_port,
-	&attr_coupled,
-	&attr_local_time,
-	&attr_utc_offset,
+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 sys_device *dev)
+static int __init etr_register_port(struct device *dev)
 {
-	struct sysdev_attribute **attr;
+	struct device_attribute **attr;
 	int rc;
 
-	rc = sysdev_register(dev);
+	rc = device_register(dev);
 	if (rc)
 		goto out;
 	for (attr = etr_port_attributes; *attr; attr++) {
-		rc = sysdev_create_file(dev, *attr);
+		rc = device_create_file(dev, *attr);
 		if (rc)
 			goto out_unreg;
 	}
 	return 0;
 out_unreg:
 	for (; attr >= etr_port_attributes; attr--)
-		sysdev_remove_file(dev, *attr);
-	sysdev_unregister(dev);
+		device_remove_file(dev, *attr);
+	device_unregister(dev);
 out:
 	return rc;
 }
 
-static void __init etr_unregister_port(struct sys_device *dev)
+static void __init etr_unregister_port(struct device *dev)
 {
-	struct sysdev_attribute **attr;
+	struct device_attribute **attr;
 
 	for (attr = etr_port_attributes; *attr; attr++)
-		sysdev_remove_file(dev, *attr);
-	sysdev_unregister(dev);
+		device_remove_file(dev, *attr);
+	device_unregister(dev);
 }
 
 static int __init etr_init_sysfs(void)
 {
 	int rc;
 
-	rc = sysdev_class_register(&etr_sysclass);
+	rc = subsys_system_register(&etr_subsys, NULL);
 	if (rc)
 		goto out;
-	rc = sysdev_class_create_file(&etr_sysclass, &attr_stepping_port);
+	rc = device_create_file(etr_subsys.dev_root, &dev_attr_stepping_port);
 	if (rc)
-		goto out_unreg_class;
-	rc = sysdev_class_create_file(&etr_sysclass, &attr_stepping_mode);
+		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);
@@ -1395,11 +1399,11 @@ static int __init etr_init_sysfs(void)
 out_remove_port0:
 	etr_unregister_port(&etr_port0_dev);
 out_remove_stepping_mode:
-	sysdev_class_remove_file(&etr_sysclass, &attr_stepping_mode);
+	device_remove_file(etr_subsys.dev_root, &dev_attr_stepping_mode);
 out_remove_stepping_port:
-	sysdev_class_remove_file(&etr_sysclass, &attr_stepping_port);
-out_unreg_class:
-	sysdev_class_unregister(&etr_sysclass);
+	device_remove_file(etr_subsys.dev_root, &dev_attr_stepping_port);
+out_unreg_subsys:
+	bus_unregister(&etr_subsys);
 out:
 	return rc;
 }
@@ -1599,14 +1603,15 @@ out_unlock:
 }
 
 /*
- * STP class sysfs interface functions
+ * STP subsys sysfs interface functions
  */
-static struct sysdev_class stp_sysclass = {
-	.name	= "stp",
+static struct bus_type stp_subsys = {
+	.name		= "stp",
+	.dev_name	= "stp",
 };
 
-static ssize_t stp_ctn_id_show(struct sysdev_class *class,
-				struct sysdev_class_attribute *attr,
+static ssize_t stp_ctn_id_show(struct device *dev,
+				struct device_attribute *attr,
 				char *buf)
 {
 	if (!stp_online)
@@ -1615,10 +1620,10 @@ static ssize_t stp_ctn_id_show(struct sysdev_class *class,
 		       *(unsigned long long *) stp_info.ctnid);
 }
 
-static SYSDEV_CLASS_ATTR(ctn_id, 0400, stp_ctn_id_show, NULL);
+static DEVICE_ATTR(ctn_id, 0400, stp_ctn_id_show, NULL);
 
-static ssize_t stp_ctn_type_show(struct sysdev_class *class,
-				struct sysdev_class_attribute *attr,
+static ssize_t stp_ctn_type_show(struct device *dev,
+				struct device_attribute *attr,
 				char *buf)
 {
 	if (!stp_online)
@@ -1626,10 +1631,10 @@ static ssize_t stp_ctn_type_show(struct sysdev_class *class,
 	return sprintf(buf, "%i\n", stp_info.ctn);
 }
 
-static SYSDEV_CLASS_ATTR(ctn_type, 0400, stp_ctn_type_show, NULL);
+static DEVICE_ATTR(ctn_type, 0400, stp_ctn_type_show, NULL);
 
-static ssize_t stp_dst_offset_show(struct sysdev_class *class,
-				   struct sysdev_class_attribute *attr,
+static ssize_t stp_dst_offset_show(struct device *dev,
+				   struct device_attribute *attr,
 				   char *buf)
 {
 	if (!stp_online || !(stp_info.vbits & 0x2000))
@@ -1637,10 +1642,10 @@ static ssize_t stp_dst_offset_show(struct sysdev_class *class,
 	return sprintf(buf, "%i\n", (int)(s16) stp_info.dsto);
 }
 
-static SYSDEV_CLASS_ATTR(dst_offset, 0400, stp_dst_offset_show, NULL);
+static DEVICE_ATTR(dst_offset, 0400, stp_dst_offset_show, NULL);
 
-static ssize_t stp_leap_seconds_show(struct sysdev_class *class,
-					struct sysdev_class_attribute *attr,
+static ssize_t stp_leap_seconds_show(struct device *dev,
+					struct device_attribute *attr,
 					char *buf)
 {
 	if (!stp_online || !(stp_info.vbits & 0x8000))
@@ -1648,10 +1653,10 @@ static ssize_t stp_leap_seconds_show(struct sysdev_class *class,
 	return sprintf(buf, "%i\n", (int)(s16) stp_info.leaps);
 }
 
-static SYSDEV_CLASS_ATTR(leap_seconds, 0400, stp_leap_seconds_show, NULL);
+static DEVICE_ATTR(leap_seconds, 0400, stp_leap_seconds_show, NULL);
 
-static ssize_t stp_stratum_show(struct sysdev_class *class,
-				struct sysdev_class_attribute *attr,
+static ssize_t stp_stratum_show(struct device *dev,
+				struct device_attribute *attr,
 				char *buf)
 {
 	if (!stp_online)
@@ -1659,10 +1664,10 @@ static ssize_t stp_stratum_show(struct sysdev_class *class,
 	return sprintf(buf, "%i\n", (int)(s16) stp_info.stratum);
 }
 
-static SYSDEV_CLASS_ATTR(stratum, 0400, stp_stratum_show, NULL);
+static DEVICE_ATTR(stratum, 0400, stp_stratum_show, NULL);
 
-static ssize_t stp_time_offset_show(struct sysdev_class *class,
-				struct sysdev_class_attribute *attr,
+static ssize_t stp_time_offset_show(struct device *dev,
+				struct device_attribute *attr,
 				char *buf)
 {
 	if (!stp_online || !(stp_info.vbits & 0x0800))
@@ -1670,10 +1675,10 @@ static ssize_t stp_time_offset_show(struct sysdev_class *class,
 	return sprintf(buf, "%i\n", (int) stp_info.tto);
 }
 
-static SYSDEV_CLASS_ATTR(time_offset, 0400, stp_time_offset_show, NULL);
+static DEVICE_ATTR(time_offset, 0400, stp_time_offset_show, NULL);
 
-static ssize_t stp_time_zone_offset_show(struct sysdev_class *class,
-				struct sysdev_class_attribute *attr,
+static ssize_t stp_time_zone_offset_show(struct device *dev,
+				struct device_attribute *attr,
 				char *buf)
 {
 	if (!stp_online || !(stp_info.vbits & 0x4000))
@@ -1681,11 +1686,11 @@ static ssize_t stp_time_zone_offset_show(struct sysdev_class *class,
 	return sprintf(buf, "%i\n", (int)(s16) stp_info.tzo);
 }
 
-static SYSDEV_CLASS_ATTR(time_zone_offset, 0400,
+static DEVICE_ATTR(time_zone_offset, 0400,
 			 stp_time_zone_offset_show, NULL);
 
-static ssize_t stp_timing_mode_show(struct sysdev_class *class,
-				struct sysdev_class_attribute *attr,
+static ssize_t stp_timing_mode_show(struct device *dev,
+				struct device_attribute *attr,
 				char *buf)
 {
 	if (!stp_online)
@@ -1693,10 +1698,10 @@ static ssize_t stp_timing_mode_show(struct sysdev_class *class,
 	return sprintf(buf, "%i\n", stp_info.tmd);
 }
 
-static SYSDEV_CLASS_ATTR(timing_mode, 0400, stp_timing_mode_show, NULL);
+static DEVICE_ATTR(timing_mode, 0400, stp_timing_mode_show, NULL);
 
-static ssize_t stp_timing_state_show(struct sysdev_class *class,
-				struct sysdev_class_attribute *attr,
+static ssize_t stp_timing_state_show(struct device *dev,
+				struct device_attribute *attr,
 				char *buf)
 {
 	if (!stp_online)
@@ -1704,17 +1709,17 @@ static ssize_t stp_timing_state_show(struct sysdev_class *class,
 	return sprintf(buf, "%i\n", stp_info.tst);
 }
 
-static SYSDEV_CLASS_ATTR(timing_state, 0400, stp_timing_state_show, NULL);
+static DEVICE_ATTR(timing_state, 0400, stp_timing_state_show, NULL);
 
-static ssize_t stp_online_show(struct sysdev_class *class,
-				struct sysdev_class_attribute *attr,
+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 sysdev_class *class,
-				struct sysdev_class_attribute *attr,
+static ssize_t stp_online_store(struct device *dev,
+				struct device_attribute *attr,
 				const char *buf, size_t count)
 {
 	unsigned int value;
@@ -1736,47 +1741,47 @@ static ssize_t stp_online_store(struct sysdev_class *class,
 }
 
 /*
- * Can't use SYSDEV_CLASS_ATTR because the attribute should be named
- * stp/online but attr_online already exists in this file ..
+ * Can't use DEVICE_ATTR because the attribute should be named
+ * stp/online but dev_attr_online already exists in this file ..
  */
-static struct sysdev_class_attribute attr_stp_online = {
+static struct device_attribute dev_attr_stp_online = {
 	.attr = { .name = "online", .mode = 0600 },
 	.show	= stp_online_show,
 	.store	= stp_online_store,
 };
 
-static struct sysdev_class_attribute *stp_attributes[] = {
-	&attr_ctn_id,
-	&attr_ctn_type,
-	&attr_dst_offset,
-	&attr_leap_seconds,
-	&attr_stp_online,
-	&attr_stratum,
-	&attr_time_offset,
-	&attr_time_zone_offset,
-	&attr_timing_mode,
-	&attr_timing_state,
+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 sysdev_class_attribute **attr;
+	struct device_attribute **attr;
 	int rc;
 
-	rc = sysdev_class_register(&stp_sysclass);
+	rc = subsys_system_register(&stp_subsys, NULL);
 	if (rc)
 		goto out;
 	for (attr = stp_attributes; *attr; attr++) {
-		rc = sysdev_class_create_file(&stp_sysclass, *attr);
+		rc = device_create_file(stp_subsys.dev_root, *attr);
 		if (rc)
 			goto out_unreg;
 	}
 	return 0;
 out_unreg:
 	for (; attr >= stp_attributes; attr--)
-		sysdev_class_remove_file(&stp_sysclass, *attr);
-	sysdev_class_unregister(&stp_sysclass);
+		device_remove_file(stp_subsys.dev_root, *attr);
+	bus_unregister(&stp_subsys);
 out:
 	return rc;
 }
diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c
index fdb5b8cb260f..7370a41948ca 100644
--- a/arch/s390/kernel/topology.c
+++ b/arch/s390/kernel/topology.c
@@ -1,22 +1,22 @@
 /*
- *    Copyright IBM Corp. 2007
+ *    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/kernel.h>
-#include <linux/mm.h>
-#include <linux/init.h>
-#include <linux/device.h>
+#include <linux/workqueue.h>
 #include <linux/bootmem.h>
+#include <linux/cpuset.h>
+#include <linux/device.h>
+#include <linux/kernel.h>
 #include <linux/sched.h>
-#include <linux/workqueue.h>
+#include <linux/init.h>
+#include <linux/delay.h>
 #include <linux/cpu.h>
 #include <linux/smp.h>
-#include <linux/cpuset.h>
-#include <asm/delay.h>
+#include <linux/mm.h>
 
 #define PTF_HORIZONTAL	(0UL)
 #define PTF_VERTICAL	(1UL)
@@ -31,7 +31,6 @@ struct mask_info {
 static int topology_enabled = 1;
 static void topology_work_fn(struct work_struct *work);
 static struct sysinfo_15_1_x *tl_info;
-static struct timer_list topology_timer;
 static void set_topology_timer(void);
 static DECLARE_WORK(topology_work, topology_work_fn);
 /* topology_lock protects the core linked list */
@@ -41,11 +40,12 @@ static struct mask_info core_info;
 cpumask_t cpu_core_map[NR_CPUS];
 unsigned char cpu_core_id[NR_CPUS];
 
-#ifdef CONFIG_SCHED_BOOK
 static struct mask_info book_info;
 cpumask_t cpu_book_map[NR_CPUS];
 unsigned char cpu_book_id[NR_CPUS];
-#endif
+
+/* smp_cpu_state_mutex must be held when accessing this array */
+int cpu_polarization[NR_CPUS];
 
 static cpumask_t cpu_group_map(struct mask_info *info, unsigned int cpu)
 {
@@ -71,7 +71,7 @@ static cpumask_t cpu_group_map(struct mask_info *info, unsigned int cpu)
 static struct mask_info *add_cpus_to_mask(struct topology_cpu *tl_cpu,
 					  struct mask_info *book,
 					  struct mask_info *core,
-					  int z10)
+					  int one_core_per_cpu)
 {
 	unsigned int cpu;
 
@@ -85,18 +85,16 @@ static struct mask_info *add_cpus_to_mask(struct topology_cpu *tl_cpu,
 		for_each_present_cpu(lcpu) {
 			if (cpu_logical_map(lcpu) != rcpu)
 				continue;
-#ifdef CONFIG_SCHED_BOOK
 			cpumask_set_cpu(lcpu, &book->mask);
 			cpu_book_id[lcpu] = book->id;
-#endif
 			cpumask_set_cpu(lcpu, &core->mask);
-			if (z10) {
+			if (one_core_per_cpu) {
 				cpu_core_id[lcpu] = rcpu;
 				core = core->next;
 			} else {
 				cpu_core_id[lcpu] = core->id;
 			}
-			smp_cpu_polarization[lcpu] = tl_cpu->pp;
+			cpu_set_polarization(lcpu, tl_cpu->pp);
 		}
 	}
 	return core;
@@ -111,13 +109,11 @@ static void clear_masks(void)
 		cpumask_clear(&info->mask);
 		info = info->next;
 	}
-#ifdef CONFIG_SCHED_BOOK
 	info = &book_info;
 	while (info) {
 		cpumask_clear(&info->mask);
 		info = info->next;
 	}
-#endif
 }
 
 static union topology_entry *next_tle(union topology_entry *tle)
@@ -127,66 +123,75 @@ static union topology_entry *next_tle(union topology_entry *tle)
 	return (union topology_entry *)((struct topology_container *)tle + 1);
 }
 
-static void tl_to_cores(struct sysinfo_15_1_x *info)
+static void __tl_to_cores_generic(struct sysinfo_15_1_x *info)
 {
-#ifdef CONFIG_SCHED_BOOK
-	struct mask_info *book = &book_info;
-	struct cpuid cpu_id;
-#else
-	struct mask_info *book = NULL;
-#endif
 	struct mask_info *core = &core_info;
+	struct mask_info *book = &book_info;
 	union topology_entry *tle, *end;
-	int z10 = 0;
 
-#ifdef CONFIG_SCHED_BOOK
-	get_cpu_id(&cpu_id);
-	z10 = cpu_id.machine == 0x2097 || cpu_id.machine == 0x2098;
-#endif
-	spin_lock_irq(&topology_lock);
-	clear_masks();
 	tle = info->tle;
 	end = (union topology_entry *)((unsigned long)info + info->length);
 	while (tle < end) {
-#ifdef CONFIG_SCHED_BOOK
-		if (z10) {
-			switch (tle->nl) {
-			case 1:
-				book = book->next;
-				book->id = tle->container.id;
-				break;
-			case 0:
-				core = add_cpus_to_mask(&tle->cpu, book, core, z10);
-				break;
-			default:
-				clear_masks();
-				goto out;
-			}
-			tle = next_tle(tle);
-			continue;
-		}
-#endif
 		switch (tle->nl) {
-#ifdef CONFIG_SCHED_BOOK
 		case 2:
 			book = book->next;
 			book->id = tle->container.id;
 			break;
-#endif
 		case 1:
 			core = core->next;
 			core->id = tle->container.id;
 			break;
 		case 0:
-			add_cpus_to_mask(&tle->cpu, book, core, z10);
+			add_cpus_to_mask(&tle->cpu, book, core, 0);
 			break;
 		default:
 			clear_masks();
-			goto out;
+			return;
 		}
 		tle = next_tle(tle);
 	}
-out:
+}
+
+static void __tl_to_cores_z10(struct sysinfo_15_1_x *info)
+{
+	struct mask_info *core = &core_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:
+			core = add_cpus_to_mask(&tle->cpu, book, core, 1);
+			break;
+		default:
+			clear_masks();
+			return;
+		}
+		tle = next_tle(tle);
+	}
+}
+
+static void tl_to_cores(struct sysinfo_15_1_x *info)
+{
+	struct cpuid cpu_id;
+
+	get_cpu_id(&cpu_id);
+	spin_lock_irq(&topology_lock);
+	clear_masks();
+	switch (cpu_id.machine) {
+	case 0x2097:
+	case 0x2098:
+		__tl_to_cores_z10(info);
+		break;
+	default:
+		__tl_to_cores_generic(info);
+	}
 	spin_unlock_irq(&topology_lock);
 }
 
@@ -196,7 +201,7 @@ static void topology_update_polarization_simple(void)
 
 	mutex_lock(&smp_cpu_state_mutex);
 	for_each_possible_cpu(cpu)
-		smp_cpu_polarization[cpu] = POLARIZATION_HRZ;
+		cpu_set_polarization(cpu, POLARIZATION_HRZ);
 	mutex_unlock(&smp_cpu_state_mutex);
 }
 
@@ -215,8 +220,7 @@ static int ptf(unsigned long fc)
 
 int topology_set_cpu_management(int fc)
 {
-	int cpu;
-	int rc;
+	int cpu, rc;
 
 	if (!MACHINE_HAS_TOPOLOGY)
 		return -EOPNOTSUPP;
@@ -227,7 +231,7 @@ int topology_set_cpu_management(int fc)
 	if (rc)
 		return -EBUSY;
 	for_each_possible_cpu(cpu)
-		smp_cpu_polarization[cpu] = POLARIZATION_UNKNWN;
+		cpu_set_polarization(cpu, POLARIZATION_UNKNOWN);
 	return rc;
 }
 
@@ -239,29 +243,25 @@ static void update_cpu_core_map(void)
 	spin_lock_irqsave(&topology_lock, flags);
 	for_each_possible_cpu(cpu) {
 		cpu_core_map[cpu] = cpu_group_map(&core_info, cpu);
-#ifdef CONFIG_SCHED_BOOK
 		cpu_book_map[cpu] = cpu_group_map(&book_info, cpu);
-#endif
 	}
 	spin_unlock_irqrestore(&topology_lock, flags);
 }
 
 void store_topology(struct sysinfo_15_1_x *info)
 {
-#ifdef CONFIG_SCHED_BOOK
 	int rc;
 
 	rc = stsi(info, 15, 1, 3);
 	if (rc != -ENOSYS)
 		return;
-#endif
 	stsi(info, 15, 1, 2);
 }
 
 int arch_update_cpu_topology(void)
 {
 	struct sysinfo_15_1_x *info = tl_info;
-	struct sys_device *sysdev;
+	struct device *dev;
 	int cpu;
 
 	if (!MACHINE_HAS_TOPOLOGY) {
@@ -273,8 +273,8 @@ int arch_update_cpu_topology(void)
 	tl_to_cores(info);
 	update_cpu_core_map();
 	for_each_online_cpu(cpu) {
-		sysdev = get_cpu_sysdev(cpu);
-		kobject_uevent(&sysdev->kobj, KOBJ_CHANGE);
+		dev = get_cpu_device(cpu);
+		kobject_uevent(&dev->kobj, KOBJ_CHANGE);
 	}
 	return 1;
 }
@@ -296,12 +296,30 @@ static void topology_timer_fn(unsigned long ignored)
 	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)
 {
-	topology_timer.function = topology_timer_fn;
-	topology_timer.data = 0;
-	topology_timer.expires = jiffies + 60 * HZ;
-	add_timer(&topology_timer);
+	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 __init early_parse_topology(char *p)
@@ -313,23 +331,6 @@ static int __init early_parse_topology(char *p)
 }
 early_param("topology", early_parse_topology);
 
-static int __init init_topology_update(void)
-{
-	int rc;
-
-	rc = 0;
-	if (!MACHINE_HAS_TOPOLOGY) {
-		topology_update_polarization_simple();
-		goto out;
-	}
-	init_timer_deferrable(&topology_timer);
-	set_topology_timer();
-out:
-	update_cpu_core_map();
-	return rc;
-}
-__initcall(init_topology_update);
-
 static void __init alloc_masks(struct sysinfo_15_1_x *info,
 			       struct mask_info *mask, int offset)
 {
@@ -357,10 +358,108 @@ void __init s390_init_cpu_topology(void)
 	store_topology(info);
 	pr_info("The CPU configuration topology of the machine is:");
 	for (i = 0; i < TOPOLOGY_NR_MAG; i++)
-		printk(" %d", info->mag[i]);
-	printk(" / %d\n", info->mnest);
+		printk(KERN_CONT " %d", info->mag[i]);
+	printk(KERN_CONT " / %d\n", info->mnest);
 	alloc_masks(info, &core_info, 1);
-#ifdef CONFIG_SCHED_BOOK
 	alloc_masks(info, &book_info, 2);
-#endif
 }
+
+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 (cpu_read_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 int __init topology_init(void)
+{
+	if (!MACHINE_HAS_TOPOLOGY) {
+		topology_update_polarization_simple();
+		goto out;
+	}
+	set_topology_timer();
+out:
+	update_cpu_core_map();
+	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
index a9807dd86276..5ce3750b181f 100644
--- a/arch/s390/kernel/traps.c
+++ b/arch/s390/kernel/traps.c
@@ -43,9 +43,9 @@
 #include <asm/debug.h>
 #include "entry.h"
 
-void (*pgm_check_table[128])(struct pt_regs *, long, unsigned long);
+void (*pgm_check_table[128])(struct pt_regs *regs);
 
-int show_unhandled_signals;
+int show_unhandled_signals = 1;
 
 #define stack_pointer ({ void **sp; asm("la %0,0(15)" : "=&d" (sp)); sp; })
 
@@ -234,7 +234,7 @@ void show_regs(struct pt_regs *regs)
 
 static DEFINE_SPINLOCK(die_lock);
 
-void die(const char * str, struct pt_regs * regs, long err)
+void die(struct pt_regs *regs, const char *str)
 {
 	static int die_counter;
 
@@ -243,7 +243,7 @@ void die(const char * str, struct pt_regs * regs, long err)
 	console_verbose();
 	spin_lock_irq(&die_lock);
 	bust_spinlocks(1);
-	printk("%s: %04lx [#%d] ", str, err & 0xffff, ++die_counter);
+	printk("%s: %04x [#%d] ", str, regs->int_code & 0xffff, ++die_counter);
 #ifdef CONFIG_PREEMPT
 	printk("PREEMPT ");
 #endif
@@ -254,7 +254,7 @@ void die(const char * str, struct pt_regs * regs, long err)
 	printk("DEBUG_PAGEALLOC");
 #endif
 	printk("\n");
-	notify_die(DIE_OOPS, str, regs, err, current->thread.trap_no, SIGSEGV);
+	notify_die(DIE_OOPS, str, regs, 0, regs->int_code & 0xffff, SIGSEGV);
 	show_regs(regs);
 	bust_spinlocks(0);
 	add_taint(TAINT_DIE);
@@ -267,8 +267,7 @@ void die(const char * str, struct pt_regs * regs, long err)
 	do_exit(SIGSEGV);
 }
 
-static void inline report_user_fault(struct pt_regs *regs, long int_code,
-				     int signr)
+static inline void report_user_fault(struct pt_regs *regs, int signr)
 {
 	if ((task_pid_nr(current) > 1) && !show_unhandled_signals)
 		return;
@@ -276,7 +275,7 @@ static void inline report_user_fault(struct pt_regs *regs, long int_code,
 		return;
 	if (!printk_ratelimit())
 		return;
-	printk("User process fault: interruption code 0x%lX ", int_code);
+	printk("User process fault: interruption code 0x%X ", regs->int_code);
 	print_vma_addr("in ", regs->psw.addr & PSW_ADDR_INSN);
 	printk("\n");
 	show_regs(regs);
@@ -287,19 +286,28 @@ int is_valid_bugaddr(unsigned long addr)
 	return 1;
 }
 
-static inline void __kprobes do_trap(long pgm_int_code, int signr, char *str,
-				     struct pt_regs *regs, siginfo_t *info)
+static inline void __user *get_psw_address(struct pt_regs *regs)
 {
-	if (notify_die(DIE_TRAP, str, regs, pgm_int_code,
-		       pgm_int_code, signr) == NOTIFY_STOP)
+	return (void __user *)
+		((regs->psw.addr - (regs->int_code >> 16)) & PSW_ADDR_INSN);
+}
+
+static void __kprobes do_trap(struct pt_regs *regs,
+			      int si_signo, int si_code, char *str)
+{
+	siginfo_t info;
+
+	if (notify_die(DIE_TRAP, str, regs, 0,
+		       regs->int_code, si_signo) == NOTIFY_STOP)
 		return;
 
         if (regs->psw.mask & PSW_MASK_PSTATE) {
-                struct task_struct *tsk = current;
-
-		tsk->thread.trap_no = pgm_int_code & 0xffff;
-		force_sig_info(signr, info, tsk);
-		report_user_fault(regs, pgm_int_code, signr);
+		info.si_signo = si_signo;
+		info.si_errno = 0;
+		info.si_code = si_code;
+		info.si_addr = get_psw_address(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);
@@ -311,18 +319,11 @@ static inline void __kprobes do_trap(long pgm_int_code, int signr, char *str,
 			btt = report_bug(regs->psw.addr & PSW_ADDR_INSN, regs);
 			if (btt == BUG_TRAP_TYPE_WARN)
 				return;
-			die(str, regs, pgm_int_code);
+			die(regs, str);
 		}
         }
 }
 
-static inline void __user *get_psw_address(struct pt_regs *regs,
-					   long pgm_int_code)
-{
-	return (void __user *)
-		((regs->psw.addr - (pgm_int_code >> 16)) & PSW_ADDR_INSN);
-}
-
 void __kprobes do_per_trap(struct pt_regs *regs)
 {
 	siginfo_t info;
@@ -339,26 +340,19 @@ void __kprobes do_per_trap(struct pt_regs *regs)
 	force_sig_info(SIGTRAP, &info, current);
 }
 
-static void default_trap_handler(struct pt_regs *regs, long pgm_int_code,
-				 unsigned long trans_exc_code)
+static void default_trap_handler(struct pt_regs *regs)
 {
         if (regs->psw.mask & PSW_MASK_PSTATE) {
-		report_user_fault(regs, pgm_int_code, SIGSEGV);
+		report_user_fault(regs, SIGSEGV);
 		do_exit(SIGSEGV);
 	} else
-		die("Unknown program exception", regs, pgm_int_code);
+		die(regs, "Unknown program exception");
 }
 
 #define DO_ERROR_INFO(name, signr, sicode, str) \
-static void name(struct pt_regs *regs, long pgm_int_code, \
-		 unsigned long trans_exc_code) \
+static void name(struct pt_regs *regs) \
 { \
-        siginfo_t info; \
-        info.si_signo = signr; \
-        info.si_errno = 0; \
-        info.si_code = sicode; \
-	info.si_addr = get_psw_address(regs, pgm_int_code); \
-	do_trap(pgm_int_code, signr, str, regs, &info);	    \
+	do_trap(regs, signr, sicode, str); \
 }
 
 DO_ERROR_INFO(addressing_exception, SIGILL, ILL_ILLADR,
@@ -388,42 +382,34 @@ DO_ERROR_INFO(special_op_exception, SIGILL, ILL_ILLOPN,
 DO_ERROR_INFO(translation_exception, SIGILL, ILL_ILLOPN,
 	      "translation exception")
 
-static inline void do_fp_trap(struct pt_regs *regs, void __user *location,
-			      int fpc, long pgm_int_code)
+static inline void do_fp_trap(struct pt_regs *regs, int fpc)
 {
-	siginfo_t si;
-
-	si.si_signo = SIGFPE;
-	si.si_errno = 0;
-	si.si_addr = location;
-	si.si_code = 0;
+	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.si_code = FPE_FLTINV;
+			si_code = FPE_FLTINV;
 		else if (fpc & 0x4000) /* div by 0 */
-			si.si_code = FPE_FLTDIV;
+			si_code = FPE_FLTDIV;
 		else if (fpc & 0x2000) /* overflow */
-			si.si_code = FPE_FLTOVF;
+			si_code = FPE_FLTOVF;
 		else if (fpc & 0x1000) /* underflow */
-			si.si_code = FPE_FLTUND;
+			si_code = FPE_FLTUND;
 		else if (fpc & 0x0800) /* inexact */
-			si.si_code = FPE_FLTRES;
+			si_code = FPE_FLTRES;
 	}
-	do_trap(pgm_int_code, SIGFPE,
-		"floating point exception", regs, &si);
+	do_trap(regs, SIGFPE, si_code, "floating point exception");
 }
 
-static void __kprobes illegal_op(struct pt_regs *regs, long pgm_int_code,
-				 unsigned long trans_exc_code)
+static void __kprobes illegal_op(struct pt_regs *regs)
 {
 	siginfo_t info;
         __u8 opcode[6];
 	__u16 __user *location;
 	int signal = 0;
 
-	location = get_psw_address(regs, pgm_int_code);
+	location = get_psw_address(regs);
 
 	if (regs->psw.mask & PSW_MASK_PSTATE) {
 		if (get_user(*((__u16 *) opcode), (__u16 __user *) location))
@@ -467,44 +453,31 @@ static void __kprobes illegal_op(struct pt_regs *regs, long pgm_int_code,
 		 * If we get an illegal op in kernel mode, send it through the
 		 * kprobes notifier. If kprobes doesn't pick it up, SIGILL
 		 */
-		if (notify_die(DIE_BPT, "bpt", regs, pgm_int_code,
+		if (notify_die(DIE_BPT, "bpt", regs, 0,
 			       3, SIGTRAP) != NOTIFY_STOP)
 			signal = SIGILL;
 	}
 
 #ifdef CONFIG_MATHEMU
         if (signal == SIGFPE)
-		do_fp_trap(regs, location,
-			   current->thread.fp_regs.fpc, pgm_int_code);
-        else if (signal == SIGSEGV) {
-		info.si_signo = signal;
-		info.si_errno = 0;
-		info.si_code = SEGV_MAPERR;
-		info.si_addr = (void __user *) location;
-		do_trap(pgm_int_code, signal,
-			"user address fault", regs, &info);
-	} else
+		do_fp_trap(regs, current->thread.fp_regs.fpc);
+	else if (signal == SIGSEGV)
+		do_trap(regs, signal, SEGV_MAPERR, "user address fault");
+	else
 #endif
-        if (signal) {
-		info.si_signo = signal;
-		info.si_errno = 0;
-		info.si_code = ILL_ILLOPC;
-		info.si_addr = (void __user *) location;
-		do_trap(pgm_int_code, signal,
-			"illegal operation", regs, &info);
-	}
+	if (signal)
+		do_trap(regs, signal, ILL_ILLOPC, "illegal operation");
 }
 
 
 #ifdef CONFIG_MATHEMU
-void specification_exception(struct pt_regs *regs, long pgm_int_code,
-			     unsigned long trans_exc_code)
+void specification_exception(struct pt_regs *regs)
 {
         __u8 opcode[6];
 	__u16 __user *location = NULL;
 	int signal = 0;
 
-	location = (__u16 __user *) get_psw_address(regs, pgm_int_code);
+	location = (__u16 __user *) get_psw_address(regs);
 
         if (regs->psw.mask & PSW_MASK_PSTATE) {
 		get_user(*((__u16 *) opcode), location);
@@ -539,30 +512,21 @@ void specification_exception(struct pt_regs *regs, long pgm_int_code,
 		signal = SIGILL;
 
         if (signal == SIGFPE)
-		do_fp_trap(regs, location,
-			   current->thread.fp_regs.fpc, pgm_int_code);
-        else if (signal) {
-		siginfo_t info;
-		info.si_signo = signal;
-		info.si_errno = 0;
-		info.si_code = ILL_ILLOPN;
-		info.si_addr = location;
-		do_trap(pgm_int_code, signal,
-			"specification exception", regs, &info);
-	}
+		do_fp_trap(regs, current->thread.fp_regs.fpc);
+	else if (signal)
+		do_trap(regs, signal, ILL_ILLOPN, "specification exception");
 }
 #else
 DO_ERROR_INFO(specification_exception, SIGILL, ILL_ILLOPN,
 	      "specification exception");
 #endif
 
-static void data_exception(struct pt_regs *regs, long pgm_int_code,
-			   unsigned long trans_exc_code)
+static void data_exception(struct pt_regs *regs)
 {
 	__u16 __user *location;
 	int signal = 0;
 
-	location = get_psw_address(regs, pgm_int_code);
+	location = get_psw_address(regs);
 
 	if (MACHINE_HAS_IEEE)
 		asm volatile("stfpc %0" : "=m" (current->thread.fp_regs.fpc));
@@ -627,32 +591,18 @@ static void data_exception(struct pt_regs *regs, long pgm_int_code,
 	else
 		signal = SIGILL;
         if (signal == SIGFPE)
-		do_fp_trap(regs, location,
-			   current->thread.fp_regs.fpc, pgm_int_code);
-        else if (signal) {
-		siginfo_t info;
-		info.si_signo = signal;
-		info.si_errno = 0;
-		info.si_code = ILL_ILLOPN;
-		info.si_addr = location;
-		do_trap(pgm_int_code, signal, "data exception", regs, &info);
-	}
+		do_fp_trap(regs, current->thread.fp_regs.fpc);
+	else if (signal)
+		do_trap(regs, signal, ILL_ILLOPN, "data exception");
 }
 
-static void space_switch_exception(struct pt_regs *regs, long pgm_int_code,
-				   unsigned long trans_exc_code)
+static void space_switch_exception(struct pt_regs *regs)
 {
-        siginfo_t info;
-
 	/* Set user psw back to home space mode. */
 	if (regs->psw.mask & PSW_MASK_PSTATE)
 		regs->psw.mask |= PSW_ASC_HOME;
 	/* Send SIGILL. */
-        info.si_signo = SIGILL;
-        info.si_errno = 0;
-        info.si_code = ILL_PRVOPC;
-	info.si_addr = get_psw_address(regs, pgm_int_code);
-	do_trap(pgm_int_code, SIGILL, "space switch event", regs, &info);
+	do_trap(regs, SIGILL, ILL_PRVOPC, "space switch event");
 }
 
 void __kprobes kernel_stack_overflow(struct pt_regs * regs)
diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S
index e4c79ebb40e6..21109c63eb12 100644
--- a/arch/s390/kernel/vmlinux.lds.S
+++ b/arch/s390/kernel/vmlinux.lds.S
@@ -9,12 +9,12 @@
 #ifndef CONFIG_64BIT
 OUTPUT_FORMAT("elf32-s390", "elf32-s390", "elf32-s390")
 OUTPUT_ARCH(s390)
-ENTRY(_start)
+ENTRY(startup)
 jiffies = jiffies_64 + 4;
 #else
 OUTPUT_FORMAT("elf64-s390", "elf64-s390", "elf64-s390")
 OUTPUT_ARCH(s390:64-bit)
-ENTRY(_start)
+ENTRY(startup)
 jiffies = jiffies_64;
 #endif
 
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index a9a301866b3c..e8fcd928dc78 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -36,7 +36,6 @@
 #include <asm/pgtable.h>
 #include <asm/irq.h>
 #include <asm/mmu_context.h>
-#include <asm/compat.h>
 #include "../kernel/entry.h"
 
 #ifndef CONFIG_64BIT
@@ -125,8 +124,7 @@ static inline int user_space_fault(unsigned long trans_exc_code)
 	return trans_exc_code != 3;
 }
 
-static inline void report_user_fault(struct pt_regs *regs, long int_code,
-				     int signr, unsigned long address)
+static inline void report_user_fault(struct pt_regs *regs, long signr)
 {
 	if ((task_pid_nr(current) > 1) && !show_unhandled_signals)
 		return;
@@ -134,10 +132,12 @@ static inline void report_user_fault(struct pt_regs *regs, long int_code,
 		return;
 	if (!printk_ratelimit())
 		return;
-	printk("User process fault: interruption code 0x%lX ", int_code);
+	printk(KERN_ALERT "User process fault: interruption code 0x%X ",
+	       regs->int_code);
 	print_vma_addr(KERN_CONT "in ", regs->psw.addr & PSW_ADDR_INSN);
-	printk("\n");
-	printk("failing address: %lX\n", address);
+	printk(KERN_CONT "\n");
+	printk(KERN_ALERT "failing address: %lX\n",
+	       regs->int_parm_long & __FAIL_ADDR_MASK);
 	show_regs(regs);
 }
 
@@ -145,24 +145,18 @@ static inline void report_user_fault(struct pt_regs *regs, long int_code,
  * Send SIGSEGV to task.  This is an external routine
  * to keep the stack usage of do_page_fault small.
  */
-static noinline void do_sigsegv(struct pt_regs *regs, long int_code,
-				int si_code, unsigned long trans_exc_code)
+static noinline void do_sigsegv(struct pt_regs *regs, int si_code)
 {
 	struct siginfo si;
-	unsigned long address;
 
-	address = trans_exc_code & __FAIL_ADDR_MASK;
-	current->thread.prot_addr = address;
-	current->thread.trap_no = int_code;
-	report_user_fault(regs, int_code, SIGSEGV, address);
+	report_user_fault(regs, SIGSEGV);
 	si.si_signo = SIGSEGV;
 	si.si_code = si_code;
-	si.si_addr = (void __user *) address;
+	si.si_addr = (void __user *)(regs->int_parm_long & __FAIL_ADDR_MASK);
 	force_sig_info(SIGSEGV, &si, current);
 }
 
-static noinline void do_no_context(struct pt_regs *regs, long int_code,
-				   unsigned long trans_exc_code)
+static noinline void do_no_context(struct pt_regs *regs)
 {
 	const struct exception_table_entry *fixup;
 	unsigned long address;
@@ -178,55 +172,48 @@ static noinline void do_no_context(struct pt_regs *regs, long int_code,
 	 * Oops. The kernel tried to access some bad page. We'll have to
 	 * terminate things with extreme prejudice.
 	 */
-	address = trans_exc_code & __FAIL_ADDR_MASK;
-	if (!user_space_fault(trans_exc_code))
+	address = regs->int_parm_long & __FAIL_ADDR_MASK;
+	if (!user_space_fault(regs->int_parm_long))
 		printk(KERN_ALERT "Unable to handle kernel pointer dereference"
 		       " at virtual kernel address %p\n", (void *)address);
 	else
 		printk(KERN_ALERT "Unable to handle kernel paging request"
 		       " at virtual user address %p\n", (void *)address);
 
-	die("Oops", regs, int_code);
+	die(regs, "Oops");
 	do_exit(SIGKILL);
 }
 
-static noinline void do_low_address(struct pt_regs *regs, long int_code,
-				    unsigned long trans_exc_code)
+static noinline void do_low_address(struct pt_regs *regs)
 {
 	/* Low-address protection hit in kernel mode means
 	   NULL pointer write access in kernel mode.  */
 	if (regs->psw.mask & PSW_MASK_PSTATE) {
 		/* Low-address protection hit in user mode 'cannot happen'. */
-		die ("Low-address protection", regs, int_code);
+		die (regs, "Low-address protection");
 		do_exit(SIGKILL);
 	}
 
-	do_no_context(regs, int_code, trans_exc_code);
+	do_no_context(regs);
 }
 
-static noinline void do_sigbus(struct pt_regs *regs, long int_code,
-			       unsigned long trans_exc_code)
+static noinline void do_sigbus(struct pt_regs *regs)
 {
 	struct task_struct *tsk = current;
-	unsigned long address;
 	struct siginfo si;
 
 	/*
 	 * Send a sigbus, regardless of whether we were in kernel
 	 * or user mode.
 	 */
-	address = trans_exc_code & __FAIL_ADDR_MASK;
-	tsk->thread.prot_addr = address;
-	tsk->thread.trap_no = int_code;
 	si.si_signo = SIGBUS;
 	si.si_errno = 0;
 	si.si_code = BUS_ADRERR;
-	si.si_addr = (void __user *) address;
+	si.si_addr = (void __user *)(regs->int_parm_long & __FAIL_ADDR_MASK);
 	force_sig_info(SIGBUS, &si, tsk);
 }
 
-static noinline void do_fault_error(struct pt_regs *regs, long int_code,
-				    unsigned long trans_exc_code, int fault)
+static noinline void do_fault_error(struct pt_regs *regs, int fault)
 {
 	int si_code;
 
@@ -238,24 +225,24 @@ static noinline void do_fault_error(struct pt_regs *regs, long int_code,
 			/* User mode accesses just cause a SIGSEGV */
 			si_code = (fault == VM_FAULT_BADMAP) ?
 				SEGV_MAPERR : SEGV_ACCERR;
-			do_sigsegv(regs, int_code, si_code, trans_exc_code);
+			do_sigsegv(regs, si_code);
 			return;
 		}
 	case VM_FAULT_BADCONTEXT:
-		do_no_context(regs, int_code, trans_exc_code);
+		do_no_context(regs);
 		break;
 	default: /* fault & VM_FAULT_ERROR */
 		if (fault & VM_FAULT_OOM) {
 			if (!(regs->psw.mask & PSW_MASK_PSTATE))
-				do_no_context(regs, int_code, trans_exc_code);
+				do_no_context(regs);
 			else
 				pagefault_out_of_memory();
 		} else if (fault & VM_FAULT_SIGBUS) {
 			/* Kernel mode? Handle exceptions or die */
 			if (!(regs->psw.mask & PSW_MASK_PSTATE))
-				do_no_context(regs, int_code, trans_exc_code);
+				do_no_context(regs);
 			else
-				do_sigbus(regs, int_code, trans_exc_code);
+				do_sigbus(regs);
 		} else
 			BUG();
 		break;
@@ -273,12 +260,12 @@ static noinline void do_fault_error(struct pt_regs *regs, long int_code,
  *   11       Page translation     ->  Not present       (nullification)
  *   3b       Region third trans.  ->  Not present       (nullification)
  */
-static inline int do_exception(struct pt_regs *regs, int access,
-			       unsigned long trans_exc_code)
+static inline int do_exception(struct pt_regs *regs, int access)
 {
 	struct task_struct *tsk;
 	struct mm_struct *mm;
 	struct vm_area_struct *vma;
+	unsigned long trans_exc_code;
 	unsigned long address;
 	unsigned int flags;
 	int fault;
@@ -288,6 +275,7 @@ static inline int do_exception(struct pt_regs *regs, int access,
 
 	tsk = current;
 	mm = tsk->mm;
+	trans_exc_code = regs->int_parm_long;
 
 	/*
 	 * Verify that the fault happened in user space, that
@@ -387,45 +375,46 @@ out:
 	return fault;
 }
 
-void __kprobes do_protection_exception(struct pt_regs *regs, long pgm_int_code,
-				       unsigned long trans_exc_code)
+void __kprobes do_protection_exception(struct pt_regs *regs)
 {
+	unsigned long trans_exc_code;
 	int fault;
 
+	trans_exc_code = regs->int_parm_long;
 	/* Protection exception is suppressing, decrement psw address. */
-	regs->psw.addr = __rewind_psw(regs->psw, pgm_int_code >> 16);
+	regs->psw.addr = __rewind_psw(regs->psw, regs->int_code >> 16);
 	/*
 	 * Check for low-address protection.  This needs to be treated
 	 * as a special case because the translation exception code
 	 * field is not guaranteed to contain valid data in this case.
 	 */
 	if (unlikely(!(trans_exc_code & 4))) {
-		do_low_address(regs, pgm_int_code, trans_exc_code);
+		do_low_address(regs);
 		return;
 	}
-	fault = do_exception(regs, VM_WRITE, trans_exc_code);
+	fault = do_exception(regs, VM_WRITE);
 	if (unlikely(fault))
-		do_fault_error(regs, 4, trans_exc_code, fault);
+		do_fault_error(regs, fault);
 }
 
-void __kprobes do_dat_exception(struct pt_regs *regs, long pgm_int_code,
-				unsigned long trans_exc_code)
+void __kprobes do_dat_exception(struct pt_regs *regs)
 {
 	int access, fault;
 
 	access = VM_READ | VM_EXEC | VM_WRITE;
-	fault = do_exception(regs, access, trans_exc_code);
+	fault = do_exception(regs, access);
 	if (unlikely(fault))
-		do_fault_error(regs, pgm_int_code & 255, trans_exc_code, fault);
+		do_fault_error(regs, fault);
 }
 
 #ifdef CONFIG_64BIT
-void __kprobes do_asce_exception(struct pt_regs *regs, long pgm_int_code,
-				 unsigned long trans_exc_code)
+void __kprobes do_asce_exception(struct pt_regs *regs)
 {
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma;
+	unsigned long trans_exc_code;
 
+	trans_exc_code = regs->int_parm_long;
 	if (unlikely(!user_space_fault(trans_exc_code) || in_atomic() || !mm))
 		goto no_context;
 
@@ -440,12 +429,12 @@ void __kprobes do_asce_exception(struct pt_regs *regs, long pgm_int_code,
 
 	/* User mode accesses just cause a SIGSEGV */
 	if (regs->psw.mask & PSW_MASK_PSTATE) {
-		do_sigsegv(regs, pgm_int_code, SEGV_MAPERR, trans_exc_code);
+		do_sigsegv(regs, SEGV_MAPERR);
 		return;
 	}
 
 no_context:
-	do_no_context(regs, pgm_int_code, trans_exc_code);
+	do_no_context(regs);
 }
 #endif
 
@@ -459,14 +448,15 @@ int __handle_fault(unsigned long uaddr, unsigned long pgm_int_code, int write)
 		regs.psw.mask |= PSW_MASK_IO | PSW_MASK_EXT;
 	regs.psw.addr = (unsigned long) __builtin_return_address(0);
 	regs.psw.addr |= PSW_ADDR_AMODE;
-	uaddr &= PAGE_MASK;
+	regs.int_code = pgm_int_code;
+	regs.int_parm_long = (uaddr & PAGE_MASK) | 2;
 	access = write ? VM_WRITE : VM_READ;
-	fault = do_exception(&regs, access, uaddr | 2);
+	fault = do_exception(&regs, access);
 	if (unlikely(fault)) {
 		if (fault & VM_FAULT_OOM)
 			return -EFAULT;
 		else if (fault & VM_FAULT_SIGBUS)
-			do_sigbus(&regs, pgm_int_code, uaddr);
+			do_sigbus(&regs);
 	}
 	return fault ? -EFAULT : 0;
 }
@@ -509,7 +499,7 @@ int pfault_init(void)
 		.reserved = __PF_RES_FIELD };
         int rc;
 
-	if (!MACHINE_IS_VM || pfault_disable)
+	if (pfault_disable)
 		return -1;
 	asm volatile(
 		"	diag	%1,%0,0x258\n"
@@ -530,7 +520,7 @@ void pfault_fini(void)
 		.refversn = 2,
 	};
 
-	if (!MACHINE_IS_VM || pfault_disable)
+	if (pfault_disable)
 		return;
 	asm volatile(
 		"	diag	%0,0,0x258\n"
@@ -643,8 +633,6 @@ static int __init pfault_irq_init(void)
 {
 	int rc;
 
-	if (!MACHINE_IS_VM)
-		return 0;
 	rc = register_external_interrupt(0x2603, pfault_interrupt);
 	if (rc)
 		goto out_extint;
diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index d4b9fb4d0042..50236610de83 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -93,18 +93,22 @@ static unsigned long setup_zero_pages(void)
 void __init paging_init(void)
 {
 	unsigned long max_zone_pfns[MAX_NR_ZONES];
-	unsigned long pgd_type;
+	unsigned long pgd_type, asce_bits;
 
 	init_mm.pgd = swapper_pg_dir;
-	S390_lowcore.kernel_asce = __pa(init_mm.pgd) & PAGE_MASK;
 #ifdef CONFIG_64BIT
-	/* A three level page table (4TB) is enough for the kernel space. */
-	S390_lowcore.kernel_asce |= _ASCE_TYPE_REGION3 | _ASCE_TABLE_LENGTH;
-	pgd_type = _REGION3_ENTRY_EMPTY;
+	if (VMALLOC_END > (1UL << 42)) {
+		asce_bits = _ASCE_TYPE_REGION2 | _ASCE_TABLE_LENGTH;
+		pgd_type = _REGION2_ENTRY_EMPTY;
+	} else {
+		asce_bits = _ASCE_TYPE_REGION3 | _ASCE_TABLE_LENGTH;
+		pgd_type = _REGION3_ENTRY_EMPTY;
+	}
 #else
-	S390_lowcore.kernel_asce |= _ASCE_TABLE_LENGTH;
+	asce_bits = _ASCE_TABLE_LENGTH;
 	pgd_type = _SEGMENT_ENTRY_EMPTY;
 #endif
+	S390_lowcore.kernel_asce = (__pa(init_mm.pgd) & PAGE_MASK) | asce_bits;
 	clear_table((unsigned long *) init_mm.pgd, pgd_type,
 		    sizeof(unsigned long)*2048);
 	vmem_map_init();
@@ -219,16 +223,38 @@ void free_initrd_mem(unsigned long start, unsigned long end)
 #ifdef CONFIG_MEMORY_HOTPLUG
 int arch_add_memory(int nid, u64 start, u64 size)
 {
-	struct pglist_data *pgdat;
+	unsigned long zone_start_pfn, zone_end_pfn, nr_pages;
+	unsigned long start_pfn = PFN_DOWN(start);
+	unsigned long size_pages = PFN_DOWN(size);
 	struct zone *zone;
 	int rc;
 
-	pgdat = NODE_DATA(nid);
-	zone = pgdat->node_zones + ZONE_MOVABLE;
 	rc = vmem_add_mapping(start, size);
 	if (rc)
 		return rc;
-	rc = __add_pages(nid, zone, PFN_DOWN(start), PFN_DOWN(size));
+	for_each_zone(zone) {
+		if (zone_idx(zone) != ZONE_MOVABLE) {
+			/* Add range within existing zone limits */
+			zone_start_pfn = zone->zone_start_pfn;
+			zone_end_pfn = zone->zone_start_pfn +
+				       zone->spanned_pages;
+		} else {
+			/* Add remaining range to ZONE_MOVABLE */
+			zone_start_pfn = start_pfn;
+			zone_end_pfn = start_pfn + size_pages;
+		}
+		if (start_pfn < zone_start_pfn || start_pfn >= zone_end_pfn)
+			continue;
+		nr_pages = (start_pfn + size_pages > zone_end_pfn) ?
+			   zone_end_pfn - start_pfn : size_pages;
+		rc = __add_pages(nid, zone, start_pfn, nr_pages);
+		if (rc)
+			break;
+		start_pfn += nr_pages;
+		size_pages -= nr_pages;
+		if (!size_pages)
+			break;
+	}
 	if (rc)
 		vmem_remove_mapping(start, size);
 	return rc;
diff --git a/arch/s390/mm/mmap.c b/arch/s390/mm/mmap.c
index f09c74881b7e..a0155c02e324 100644
--- a/arch/s390/mm/mmap.c
+++ b/arch/s390/mm/mmap.c
@@ -29,8 +29,8 @@
 #include <linux/mman.h>
 #include <linux/module.h>
 #include <linux/random.h>
+#include <linux/compat.h>
 #include <asm/pgalloc.h>
-#include <asm/compat.h>
 
 static unsigned long stack_maxrandom_size(void)
 {
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 301c84d3b542..51b0738e13d1 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -33,17 +33,6 @@
 #define FRAG_MASK	0x03
 #endif
 
-unsigned long VMALLOC_START = VMALLOC_END - VMALLOC_SIZE;
-EXPORT_SYMBOL(VMALLOC_START);
-
-static int __init parse_vmalloc(char *arg)
-{
-	if (!arg)
-		return -EINVAL;
-	VMALLOC_START = (VMALLOC_END - memparse(arg, &arg)) & PAGE_MASK;
-	return 0;
-}
-early_param("vmalloc", parse_vmalloc);
 
 unsigned long *crst_table_alloc(struct mm_struct *mm)
 {
@@ -267,7 +256,10 @@ static int gmap_alloc_table(struct gmap *gmap,
 	struct page *page;
 	unsigned long *new;
 
+	/* since we dont free the gmap table until gmap_free we can unlock */
+	spin_unlock(&gmap->mm->page_table_lock);
 	page = alloc_pages(GFP_KERNEL, ALLOC_ORDER);
+	spin_lock(&gmap->mm->page_table_lock);
 	if (!page)
 		return -ENOMEM;
 	new = (unsigned long *) page_to_phys(page);
@@ -582,7 +574,7 @@ static inline void page_table_free_pgste(unsigned long *table)
 	page = pfn_to_page(__pa(table) >> PAGE_SHIFT);
 	mp = (struct gmap_pgtable *) page->index;
 	BUG_ON(!list_empty(&mp->mapper));
-	pgtable_page_ctor(page);
+	pgtable_page_dtor(page);
 	atomic_set(&page->_mapcount, -1);
 	kfree(mp);
 	__free_page(page);
diff --git a/arch/s390/oprofile/hwsampler.c b/arch/s390/oprofile/hwsampler.c
index f43c0e4282af..9daee91e6c3f 100644
--- a/arch/s390/oprofile/hwsampler.c
+++ b/arch/s390/oprofile/hwsampler.c
@@ -22,6 +22,7 @@
 #include <asm/irq.h>
 
 #include "hwsampler.h"
+#include "op_counter.h"
 
 #define MAX_NUM_SDB 511
 #define MIN_NUM_SDB 1
@@ -896,6 +897,8 @@ static void add_samples_to_oprofile(unsigned int cpu, unsigned long *sdbt,
 		if (sample_data_ptr->P == 1) {
 			/* userspace sample */
 			unsigned int pid = sample_data_ptr->prim_asn;
+			if (!counter_config.user)
+				goto skip_sample;
 			rcu_read_lock();
 			tsk = pid_task(find_vpid(pid), PIDTYPE_PID);
 			if (tsk)
@@ -903,6 +906,8 @@ static void add_samples_to_oprofile(unsigned int cpu, unsigned long *sdbt,
 			rcu_read_unlock();
 		} else {
 			/* kernelspace sample */
+			if (!counter_config.kernel)
+				goto skip_sample;
 			regs = task_pt_regs(current);
 		}
 
@@ -910,7 +915,7 @@ static void add_samples_to_oprofile(unsigned int cpu, unsigned long *sdbt,
 		oprofile_add_ext_hw_sample(sample_data_ptr->ia, regs, 0,
 				!sample_data_ptr->P, tsk);
 		mutex_unlock(&hws_sem);
-
+	skip_sample:
 		sample_data_ptr++;
 	}
 }
diff --git a/arch/s390/oprofile/init.c b/arch/s390/oprofile/init.c
index 6efc18b5e60a..2297be406c61 100644
--- a/arch/s390/oprofile/init.c
+++ b/arch/s390/oprofile/init.c
@@ -2,10 +2,11 @@
  * arch/s390/oprofile/init.c
  *
  * S390 Version
- *   Copyright (C) 2003 IBM Deutschland Entwicklung GmbH, IBM Corporation
+ *   Copyright (C) 2002-2011 IBM Deutschland Entwicklung GmbH, IBM Corporation
  *   Author(s): Thomas Spatzier (tspat@de.ibm.com)
  *   Author(s): Mahesh Salgaonkar (mahesh@linux.vnet.ibm.com)
  *   Author(s): Heinz Graalfs (graalfs@linux.vnet.ibm.com)
+ *   Author(s): Andreas Krebbel (krebbel@linux.vnet.ibm.com)
  *
  * @remark Copyright 2002-2011 OProfile authors
  */
@@ -14,6 +15,8 @@
 #include <linux/init.h>
 #include <linux/errno.h>
 #include <linux/fs.h>
+#include <linux/module.h>
+#include <asm/processor.h>
 
 #include "../../../drivers/oprofile/oprof.h"
 
@@ -22,6 +25,7 @@ extern void s390_backtrace(struct pt_regs * const regs, unsigned int depth);
 #ifdef CONFIG_64BIT
 
 #include "hwsampler.h"
+#include "op_counter.h"
 
 #define DEFAULT_INTERVAL	4127518
 
@@ -35,16 +39,41 @@ static unsigned long oprofile_max_interval;
 static unsigned long oprofile_sdbt_blocks = DEFAULT_SDBT_BLOCKS;
 static unsigned long oprofile_sdb_blocks = DEFAULT_SDB_BLOCKS;
 
-static int hwsampler_file;
+static int hwsampler_enabled;
 static int hwsampler_running;	/* start_mutex must be held to change */
+static int hwsampler_available;
 
 static struct oprofile_operations timer_ops;
 
+struct op_counter_config counter_config;
+
+enum __force_cpu_type {
+	reserved = 0,		/* do not force */
+	timer,
+};
+static int force_cpu_type;
+
+static int set_cpu_type(const char *str, struct kernel_param *kp)
+{
+	if (!strcmp(str, "timer")) {
+		force_cpu_type = timer;
+		printk(KERN_INFO "oprofile: forcing timer to be returned "
+		                 "as cpu type\n");
+	} else {
+		force_cpu_type = 0;
+	}
+
+	return 0;
+}
+module_param_call(cpu_type, set_cpu_type, NULL, NULL, 0);
+MODULE_PARM_DESC(cpu_type, "Force legacy basic mode sampling"
+		           "(report cpu_type \"timer\"");
+
 static int oprofile_hwsampler_start(void)
 {
 	int retval;
 
-	hwsampler_running = hwsampler_file;
+	hwsampler_running = hwsampler_enabled;
 
 	if (!hwsampler_running)
 		return timer_ops.start();
@@ -72,10 +101,16 @@ static void oprofile_hwsampler_stop(void)
 	return;
 }
 
+/*
+ * File ops used for:
+ * /dev/oprofile/0/enabled
+ * /dev/oprofile/hwsampling/hwsampler  (cpu_type = timer)
+ */
+
 static ssize_t hwsampler_read(struct file *file, char __user *buf,
 		size_t count, loff_t *offset)
 {
-	return oprofilefs_ulong_to_user(hwsampler_file, buf, count, offset);
+	return oprofilefs_ulong_to_user(hwsampler_enabled, buf, count, offset);
 }
 
 static ssize_t hwsampler_write(struct file *file, char const __user *buf,
@@ -88,9 +123,12 @@ static ssize_t hwsampler_write(struct file *file, char const __user *buf,
 		return -EINVAL;
 
 	retval = oprofilefs_ulong_from_user(&val, buf, count);
-	if (retval)
+	if (retval <= 0)
 		return retval;
 
+	if (val != 0 && val != 1)
+		return -EINVAL;
+
 	if (oprofile_started)
 		/*
 		 * save to do without locking as we set
@@ -99,7 +137,7 @@ static ssize_t hwsampler_write(struct file *file, char const __user *buf,
 		 */
 		return -EBUSY;
 
-	hwsampler_file = val;
+	hwsampler_enabled = val;
 
 	return count;
 }
@@ -109,38 +147,311 @@ static const struct file_operations hwsampler_fops = {
 	.write		= hwsampler_write,
 };
 
+/*
+ * File ops used for:
+ * /dev/oprofile/0/count
+ * /dev/oprofile/hwsampling/hw_interval  (cpu_type = timer)
+ *
+ * Make sure that the value is within the hardware range.
+ */
+
+static ssize_t hw_interval_read(struct file *file, char __user *buf,
+				size_t count, loff_t *offset)
+{
+	return oprofilefs_ulong_to_user(oprofile_hw_interval, buf,
+					count, offset);
+}
+
+static ssize_t hw_interval_write(struct file *file, char const __user *buf,
+				 size_t count, loff_t *offset)
+{
+	unsigned long val;
+	int retval;
+
+	if (*offset)
+		return -EINVAL;
+	retval = oprofilefs_ulong_from_user(&val, buf, count);
+	if (retval)
+		return retval;
+	if (val < oprofile_min_interval)
+		oprofile_hw_interval = oprofile_min_interval;
+	else if (val > oprofile_max_interval)
+		oprofile_hw_interval = oprofile_max_interval;
+	else
+		oprofile_hw_interval = val;
+
+	return count;
+}
+
+static const struct file_operations hw_interval_fops = {
+	.read		= hw_interval_read,
+	.write		= hw_interval_write,
+};
+
+/*
+ * File ops used for:
+ * /dev/oprofile/0/event
+ * Only a single event with number 0 is supported with this counter.
+ *
+ * /dev/oprofile/0/unit_mask
+ * This is a dummy file needed by the user space tools.
+ * No value other than 0 is accepted or returned.
+ */
+
+static ssize_t hwsampler_zero_read(struct file *file, char __user *buf,
+				    size_t count, loff_t *offset)
+{
+	return oprofilefs_ulong_to_user(0, buf, count, offset);
+}
+
+static ssize_t hwsampler_zero_write(struct file *file, char const __user *buf,
+				     size_t count, loff_t *offset)
+{
+	unsigned long val;
+	int retval;
+
+	if (*offset)
+		return -EINVAL;
+
+	retval = oprofilefs_ulong_from_user(&val, buf, count);
+	if (retval)
+		return retval;
+	if (val != 0)
+		return -EINVAL;
+	return count;
+}
+
+static const struct file_operations zero_fops = {
+	.read		= hwsampler_zero_read,
+	.write		= hwsampler_zero_write,
+};
+
+/* /dev/oprofile/0/kernel file ops.  */
+
+static ssize_t hwsampler_kernel_read(struct file *file, char __user *buf,
+				     size_t count, loff_t *offset)
+{
+	return oprofilefs_ulong_to_user(counter_config.kernel,
+					buf, count, offset);
+}
+
+static ssize_t hwsampler_kernel_write(struct file *file, char const __user *buf,
+				      size_t count, loff_t *offset)
+{
+	unsigned long val;
+	int retval;
+
+	if (*offset)
+		return -EINVAL;
+
+	retval = oprofilefs_ulong_from_user(&val, buf, count);
+	if (retval)
+		return retval;
+
+	if (val != 0 && val != 1)
+		return -EINVAL;
+
+	counter_config.kernel = val;
+
+	return count;
+}
+
+static const struct file_operations kernel_fops = {
+	.read		= hwsampler_kernel_read,
+	.write		= hwsampler_kernel_write,
+};
+
+/* /dev/oprofile/0/user file ops. */
+
+static ssize_t hwsampler_user_read(struct file *file, char __user *buf,
+				   size_t count, loff_t *offset)
+{
+	return oprofilefs_ulong_to_user(counter_config.user,
+					buf, count, offset);
+}
+
+static ssize_t hwsampler_user_write(struct file *file, char const __user *buf,
+				    size_t count, loff_t *offset)
+{
+	unsigned long val;
+	int retval;
+
+	if (*offset)
+		return -EINVAL;
+
+	retval = oprofilefs_ulong_from_user(&val, buf, count);
+	if (retval)
+		return retval;
+
+	if (val != 0 && val != 1)
+		return -EINVAL;
+
+	counter_config.user = val;
+
+	return count;
+}
+
+static const struct file_operations user_fops = {
+	.read		= hwsampler_user_read,
+	.write		= hwsampler_user_write,
+};
+
+
+/*
+ * File ops used for: /dev/oprofile/timer/enabled
+ * The value always has to be the inverted value of hwsampler_enabled. So
+ * no separate variable is created. That way we do not need locking.
+ */
+
+static ssize_t timer_enabled_read(struct file *file, char __user *buf,
+				  size_t count, loff_t *offset)
+{
+	return oprofilefs_ulong_to_user(!hwsampler_enabled, buf, count, offset);
+}
+
+static ssize_t timer_enabled_write(struct file *file, char const __user *buf,
+				   size_t count, loff_t *offset)
+{
+	unsigned long val;
+	int retval;
+
+	if (*offset)
+		return -EINVAL;
+
+	retval = oprofilefs_ulong_from_user(&val, buf, count);
+	if (retval)
+		return retval;
+
+	if (val != 0 && val != 1)
+		return -EINVAL;
+
+	/* Timer cannot be disabled without having hardware sampling.  */
+	if (val == 0 && !hwsampler_available)
+		return -EINVAL;
+
+	if (oprofile_started)
+		/*
+		 * save to do without locking as we set
+		 * hwsampler_running in start() when start_mutex is
+		 * held
+		 */
+		return -EBUSY;
+
+	hwsampler_enabled = !val;
+
+	return count;
+}
+
+static const struct file_operations timer_enabled_fops = {
+	.read		= timer_enabled_read,
+	.write		= timer_enabled_write,
+};
+
+
 static int oprofile_create_hwsampling_files(struct super_block *sb,
-						struct dentry *root)
+					    struct dentry *root)
 {
-	struct dentry *hw_dir;
+	struct dentry *dir;
+
+	dir = oprofilefs_mkdir(sb, root, "timer");
+	if (!dir)
+		return -EINVAL;
+
+	oprofilefs_create_file(sb, dir, "enabled", &timer_enabled_fops);
+
+	if (!hwsampler_available)
+		return 0;
 
 	/* reinitialize default values */
-	hwsampler_file = 1;
+	hwsampler_enabled = 1;
+	counter_config.kernel = 1;
+	counter_config.user = 1;
 
-	hw_dir = oprofilefs_mkdir(sb, root, "hwsampling");
-	if (!hw_dir)
-		return -EINVAL;
+	if (!force_cpu_type) {
+		/*
+		 * Create the counter file system.  A single virtual
+		 * counter is created which can be used to
+		 * enable/disable hardware sampling dynamically from
+		 * user space.  The user space will configure a single
+		 * counter with a single event.  The value of 'event'
+		 * and 'unit_mask' are not evaluated by the kernel code
+		 * and can only be set to 0.
+		 */
+
+		dir = oprofilefs_mkdir(sb, root, "0");
+		if (!dir)
+			return -EINVAL;
 
-	oprofilefs_create_file(sb, hw_dir, "hwsampler", &hwsampler_fops);
-	oprofilefs_create_ulong(sb, hw_dir, "hw_interval",
-				&oprofile_hw_interval);
-	oprofilefs_create_ro_ulong(sb, hw_dir, "hw_min_interval",
-				&oprofile_min_interval);
-	oprofilefs_create_ro_ulong(sb, hw_dir, "hw_max_interval",
-				&oprofile_max_interval);
-	oprofilefs_create_ulong(sb, hw_dir, "hw_sdbt_blocks",
-				&oprofile_sdbt_blocks);
+		oprofilefs_create_file(sb, dir, "enabled", &hwsampler_fops);
+		oprofilefs_create_file(sb, dir, "event", &zero_fops);
+		oprofilefs_create_file(sb, dir, "count", &hw_interval_fops);
+		oprofilefs_create_file(sb, dir, "unit_mask", &zero_fops);
+		oprofilefs_create_file(sb, dir, "kernel", &kernel_fops);
+		oprofilefs_create_file(sb, dir, "user", &user_fops);
+		oprofilefs_create_ulong(sb, dir, "hw_sdbt_blocks",
+					&oprofile_sdbt_blocks);
 
+	} else {
+		/*
+		 * Hardware sampling can be used but the cpu_type is
+		 * forced to timer in order to deal with legacy user
+		 * space tools.  The /dev/oprofile/hwsampling fs is
+		 * provided in that case.
+		 */
+		dir = oprofilefs_mkdir(sb, root, "hwsampling");
+		if (!dir)
+			return -EINVAL;
+
+		oprofilefs_create_file(sb, dir, "hwsampler",
+				       &hwsampler_fops);
+		oprofilefs_create_file(sb, dir, "hw_interval",
+				       &hw_interval_fops);
+		oprofilefs_create_ro_ulong(sb, dir, "hw_min_interval",
+					   &oprofile_min_interval);
+		oprofilefs_create_ro_ulong(sb, dir, "hw_max_interval",
+					   &oprofile_max_interval);
+		oprofilefs_create_ulong(sb, dir, "hw_sdbt_blocks",
+					&oprofile_sdbt_blocks);
+	}
 	return 0;
 }
 
 static int oprofile_hwsampler_init(struct oprofile_operations *ops)
 {
+	/*
+	 * Initialize the timer mode infrastructure as well in order
+	 * to be able to switch back dynamically.  oprofile_timer_init
+	 * is not supposed to fail.
+	 */
+	if (oprofile_timer_init(ops))
+		BUG();
+
+	memcpy(&timer_ops, ops, sizeof(timer_ops));
+	ops->create_files = oprofile_create_hwsampling_files;
+
+	/*
+	 * If the user space tools do not support newer cpu types,
+	 * the force_cpu_type module parameter
+	 * can be used to always return \"timer\" as cpu type.
+	 */
+	if (force_cpu_type != timer) {
+		struct cpuid id;
+
+		get_cpu_id (&id);
+
+		switch (id.machine) {
+		case 0x2097: case 0x2098: ops->cpu_type = "s390/z10"; break;
+		case 0x2817: case 0x2818: ops->cpu_type = "s390/z196"; break;
+		default: return -ENODEV;
+		}
+	}
+
 	if (hwsampler_setup())
 		return -ENODEV;
 
 	/*
-	 * create hwsampler files only if hwsampler_setup() succeeds.
+	 * Query the range for the sampling interval from the
+	 * hardware.
 	 */
 	oprofile_min_interval = hwsampler_query_min_interval();
 	if (oprofile_min_interval == 0)
@@ -155,23 +466,17 @@ static int oprofile_hwsampler_init(struct oprofile_operations *ops)
 	if (oprofile_hw_interval > oprofile_max_interval)
 		oprofile_hw_interval = oprofile_max_interval;
 
-	if (oprofile_timer_init(ops))
-		return -ENODEV;
-
-	printk(KERN_INFO "oprofile: using hardware sampling\n");
-
-	memcpy(&timer_ops, ops, sizeof(timer_ops));
+	printk(KERN_INFO "oprofile: System z hardware sampling "
+	       "facility found.\n");
 
 	ops->start = oprofile_hwsampler_start;
 	ops->stop = oprofile_hwsampler_stop;
-	ops->create_files = oprofile_create_hwsampling_files;
 
 	return 0;
 }
 
 static void oprofile_hwsampler_exit(void)
 {
-	oprofile_timer_exit();
 	hwsampler_shutdown();
 }
 
@@ -182,7 +487,15 @@ int __init oprofile_arch_init(struct oprofile_operations *ops)
 	ops->backtrace = s390_backtrace;
 
 #ifdef CONFIG_64BIT
-	return oprofile_hwsampler_init(ops);
+
+	/*
+	 * -ENODEV is not reported to the caller.  The module itself
+         * will use the timer mode sampling as fallback and this is
+         * always available.
+	 */
+	hwsampler_available = oprofile_hwsampler_init(ops) == 0;
+
+	return 0;
 #else
 	return -ENODEV;
 #endif
diff --git a/arch/s390/oprofile/op_counter.h b/arch/s390/oprofile/op_counter.h
new file mode 100644
index 000000000000..1a8d3ca09014
--- /dev/null
+++ b/arch/s390/oprofile/op_counter.h
@@ -0,0 +1,23 @@
+/**
+ * arch/s390/oprofile/op_counter.h
+ *
+ *   Copyright (C) 2011 IBM Deutschland Entwicklung GmbH, IBM Corporation
+ *   Author(s): Andreas Krebbel (krebbel@linux.vnet.ibm.com)
+ *
+ * @remark Copyright 2011 OProfile authors
+ */
+
+#ifndef OP_COUNTER_H
+#define OP_COUNTER_H
+
+struct op_counter_config {
+	/* `enabled' maps to the hwsampler_file variable.  */
+	/* `count' maps to the oprofile_hw_interval variable.  */
+	/* `event' and `unit_mask' are unused. */
+	unsigned long kernel;
+	unsigned long user;
+};
+
+extern struct op_counter_config counter_config;
+
+#endif /* OP_COUNTER_H */