Merge commit 'v2.6.35' into kbuild/kbuild

Conflicts:
	arch/powerpc/Makefile

118 files changed, 3052 insertions, 2058 deletions

diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index c80235206c0..bee1c0f794c 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -54,6 +54,9 @@ config GENERIC_BUG
 	depends on BUG
 	default y
 
+config GENERIC_BUG_RELATIVE_POINTERS
+	def_bool y
+
 config NO_IOMEM
 	def_bool y
 
@@ -87,6 +90,7 @@ config S390
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_DYNAMIC_FTRACE
 	select HAVE_FUNCTION_GRAPH_TRACER
+	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_DEFAULT_NO_SPIN_MUTEXES
 	select HAVE_OPROFILE
 	select HAVE_KPROBES
@@ -95,6 +99,10 @@ config S390
 	select HAVE_ARCH_TRACEHOOK
 	select INIT_ALL_POSSIBLE
 	select HAVE_PERF_EVENTS
+	select HAVE_KERNEL_GZIP
+	select HAVE_KERNEL_BZIP2
+	select HAVE_KERNEL_LZMA
+	select HAVE_KERNEL_LZO
 	select ARCH_INLINE_SPIN_TRYLOCK
 	select ARCH_INLINE_SPIN_TRYLOCK_BH
 	select ARCH_INLINE_SPIN_LOCK
@@ -437,13 +445,6 @@ config FORCE_MAX_ZONEORDER
 	int
 	default "9"
 
-config PROCESS_DEBUG
-	bool "Show crashed user process info"
-	help
-	  Say Y to print all process fault locations to the console.  This is
-	  a debugging option; you probably do not want to set it unless you
-	  are an S390 port maintainer.
-
 config PFAULT
 	bool "Pseudo page fault support"
 	help
@@ -479,13 +480,6 @@ config CMM
 	  Everybody who wants to run Linux under VM should select this
 	  option.
 
-config CMM_PROC
-	bool "/proc interface to cooperative memory management"
-	depends on CMM
-	help
-	  Select this option to enable the /proc interface to the
-	  cooperative memory management.
-
 config CMM_IUCV
 	bool "IUCV special message interface to cooperative memory management"
 	depends on CMM && (SMSGIUCV=y || CMM=SMSGIUCV)
diff --git a/arch/s390/Kconfig.debug b/arch/s390/Kconfig.debug
index 2283933a9a9..45e0c6199f3 100644
--- a/arch/s390/Kconfig.debug
+++ b/arch/s390/Kconfig.debug
@@ -6,4 +6,17 @@ config TRACE_IRQFLAGS_SUPPORT
 
 source "lib/Kconfig.debug"
 
+config DEBUG_STRICT_USER_COPY_CHECKS
+	bool "Strict user copy size checks"
+	---help---
+	  Enabling this option turns a certain set of sanity checks for user
+	  copy operations into compile time warnings.
+
+	  The copy_from_user() etc checks are there to help test if there
+	  are sufficient security checks on the length argument of
+	  the copy operation, by having gcc prove that the argument is
+	  within bounds.
+
+	  If unsure, or if you run an older (pre 4.4) gcc, say N.
+
 endmenu
diff --git a/arch/s390/Makefile b/arch/s390/Makefile
index 83ef8724c83..0c9e6c6d2a6 100644
--- a/arch/s390/Makefile
+++ b/arch/s390/Makefile
@@ -14,6 +14,7 @@
 #
 
 ifndef CONFIG_64BIT
+LD_BFD		:= elf32-s390
 LDFLAGS		:= -m elf_s390
 KBUILD_CFLAGS	+= -m31
 KBUILD_AFLAGS	+= -m31
@@ -21,6 +22,7 @@ UTS_MACHINE	:= s390
 STACK_SIZE	:= 8192
 CHECKFLAGS	+= -D__s390__ -msize-long
 else
+LD_BFD		:= elf64-s390
 LDFLAGS		:= -m elf64_s390
 KBUILD_AFLAGS_MODULE += -fpic -D__PIC__
 KBUILD_CFLAGS_MODULE += -fpic -D__PIC__
@@ -31,6 +33,8 @@ STACK_SIZE	:= 16384
 CHECKFLAGS	+= -D__s390__ -D__s390x__
 endif
 
+export LD_BFD
+
 cflags-$(CONFIG_MARCH_G5)   += $(call cc-option,-march=g5)
 cflags-$(CONFIG_MARCH_Z900) += $(call cc-option,-march=z900)
 cflags-$(CONFIG_MARCH_Z990) += $(call cc-option,-march=z990)
@@ -86,7 +90,9 @@ KBUILD_AFLAGS	+= $(aflags-y)
 OBJCOPYFLAGS	:= -O binary
 LDFLAGS_vmlinux := -e start
 
-head-y		:= arch/s390/kernel/head.o arch/s390/kernel/init_task.o
+head-y		:= arch/s390/kernel/head.o
+head-y		+= arch/s390/kernel/$(if $(CONFIG_64BIT),head64.o,head31.o)
+head-y		+= arch/s390/kernel/init_task.o
 
 core-y		+= arch/s390/mm/ arch/s390/kernel/ arch/s390/crypto/ \
 		   arch/s390/appldata/ arch/s390/hypfs/ arch/s390/kvm/
@@ -100,21 +106,28 @@ drivers-$(CONFIG_OPROFILE)	+= arch/s390/oprofile/
 
 boot		:= arch/s390/boot
 
-all: image
+all: image bzImage
 
 install: vmlinux
 	$(Q)$(MAKE) $(build)=$(boot) $@
 
-image: vmlinux
+image bzImage: vmlinux
 	$(Q)$(MAKE) $(build)=$(boot) $(boot)/$@
 
 zfcpdump:
 	$(Q)$(MAKE) $(build)=$(boot) $(boot)/$@
 
+vdso_install:
+ifeq ($(CONFIG_64BIT),y)
+	$(Q)$(MAKE) $(build)=arch/$(ARCH)/kernel/vdso64 $@
+endif
+	$(Q)$(MAKE) $(build)=arch/$(ARCH)/kernel/vdso32 $@
+
 archclean:
 	$(Q)$(MAKE) $(clean)=$(boot)
 
 # Don't use tabs in echo arguments
 define archhelp
   echo  '* image           - Kernel image for IPL ($(boot)/image)'
+  echo	'* bzImage         - Compressed kernel image for IPL ($(boot)/bzImage)'
 endef
diff --git a/arch/s390/appldata/appldata_mem.c b/arch/s390/appldata/appldata_mem.c
index 4188cbe63a5..e43fe753703 100644
--- a/arch/s390/appldata/appldata_mem.c
+++ b/arch/s390/appldata/appldata_mem.c
@@ -11,7 +11,6 @@
 
 #include <linux/module.h>
 #include <linux/init.h>
-#include <linux/slab.h>
 #include <linux/errno.h>
 #include <linux/kernel_stat.h>
 #include <linux/pagemap.h>
diff --git a/arch/s390/appldata/appldata_net_sum.c b/arch/s390/appldata/appldata_net_sum.c
index 4ce7fa95880..9a9586f4103 100644
--- a/arch/s390/appldata/appldata_net_sum.c
+++ b/arch/s390/appldata/appldata_net_sum.c
@@ -12,7 +12,6 @@
 
 #include <linux/module.h>
 #include <linux/init.h>
-#include <linux/slab.h>
 #include <linux/errno.h>
 #include <linux/kernel_stat.h>
 #include <linux/netdevice.h>
diff --git a/arch/s390/appldata/appldata_os.c b/arch/s390/appldata/appldata_os.c
index 55c80ffd42b..92f1cb745d6 100644
--- a/arch/s390/appldata/appldata_os.c
+++ b/arch/s390/appldata/appldata_os.c
@@ -181,7 +181,7 @@ static int __init appldata_os_init(void)
 		goto out;
 	}
 
-	appldata_os_data = kzalloc(max_size, GFP_DMA);
+	appldata_os_data = kzalloc(max_size, GFP_KERNEL | GFP_DMA);
 	if (appldata_os_data == NULL) {
 		rc = -ENOMEM;
 		goto out;
diff --git a/arch/s390/boot/Makefile b/arch/s390/boot/Makefile
index 4d97eef36b8..8800cf09069 100644
--- a/arch/s390/boot/Makefile
+++ b/arch/s390/boot/Makefile
@@ -9,10 +9,18 @@ COMPILE_VERSION := __linux_compile_version_id__`hostname |  \
 EXTRA_CFLAGS  := -DCOMPILE_VERSION=$(COMPILE_VERSION) -gstabs -I.
 
 targets := image
+targets += bzImage
+subdir- := compressed
 
 $(obj)/image: vmlinux FORCE
 	$(call if_changed,objcopy)
 
+$(obj)/bzImage: $(obj)/compressed/vmlinux FORCE
+	$(call if_changed,objcopy)
+
+$(obj)/compressed/vmlinux: FORCE
+	$(Q)$(MAKE) $(build)=$(obj)/compressed $@
+
 install: $(CONFIGURE) $(obj)/image
 	sh -x  $(srctree)/$(obj)/install.sh $(KERNELRELEASE) $(obj)/image \
 	      System.map Kerntypes "$(INSTALL_PATH)"
diff --git a/arch/s390/boot/compressed/Makefile b/arch/s390/boot/compressed/Makefile
new file mode 100644
index 00000000000..1c999f726a5
--- /dev/null
+++ b/arch/s390/boot/compressed/Makefile
@@ -0,0 +1,63 @@
+#
+# linux/arch/s390/boot/compressed/Makefile
+#
+# create a compressed vmlinux image from the original vmlinux
+#
+
+BITS := $(if $(CONFIG_64BIT),64,31)
+
+targets	:= vmlinux.lds vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 \
+	   vmlinux.bin.lzma vmlinux.bin.lzo misc.o piggy.o sizes.h head$(BITS).o
+
+KBUILD_CFLAGS := -m$(BITS) -D__KERNEL__ $(LINUX_INCLUDE) -O2
+KBUILD_CFLAGS += $(cflags-y)
+KBUILD_CFLAGS += $(call cc-option,-mpacked-stack)
+KBUILD_CFLAGS += $(call cc-option,-ffreestanding)
+
+GCOV_PROFILE := n
+
+OBJECTS := $(addprefix $(objtree)/arch/s390/kernel/, head.o sclp.o ebcdic.o)
+OBJECTS += $(obj)/head$(BITS).o $(obj)/misc.o $(obj)/piggy.o
+
+LDFLAGS_vmlinux := --oformat $(LD_BFD) -e startup -T
+$(obj)/vmlinux: $(obj)/vmlinux.lds $(OBJECTS)
+	$(call if_changed,ld)
+	@:
+
+sed-sizes := -e 's/^\([0-9a-fA-F]*\) . \(__bss_start\|_end\)$$/\#define SZ\2 0x\1/p'
+
+quiet_cmd_sizes = GEN $@
+      cmd_sizes = $(NM) $< | sed -n $(sed-sizes) > $@
+
+$(obj)/sizes.h: vmlinux
+	$(call if_changed,sizes)
+
+AFLAGS_head$(BITS).o += -I$(obj)
+$(obj)/head$(BITS).o: $(obj)/sizes.h
+
+CFLAGS_misc.o += -I$(obj)
+$(obj)/misc.o: $(obj)/sizes.h
+
+OBJCOPYFLAGS_vmlinux.bin :=  -R .comment -S
+$(obj)/vmlinux.bin: vmlinux
+	$(call if_changed,objcopy)
+
+vmlinux.bin.all-y := $(obj)/vmlinux.bin
+
+suffix-$(CONFIG_KERNEL_GZIP)  := gz
+suffix-$(CONFIG_KERNEL_BZIP2) := bz2
+suffix-$(CONFIG_KERNEL_LZMA)  := lzma
+suffix-$(CONFIG_KERNEL_LZO)  := lzo
+
+$(obj)/vmlinux.bin.gz: $(vmlinux.bin.all-y)
+	$(call if_changed,gzip)
+$(obj)/vmlinux.bin.bz2: $(vmlinux.bin.all-y)
+	$(call if_changed,bzip2)
+$(obj)/vmlinux.bin.lzma: $(vmlinux.bin.all-y)
+	$(call if_changed,lzma)
+$(obj)/vmlinux.bin.lzo: $(vmlinux.bin.all-y)
+	$(call if_changed,lzo)
+
+LDFLAGS_piggy.o := -r --format binary --oformat $(LD_BFD) -T
+$(obj)/piggy.o: $(obj)/vmlinux.scr $(obj)/vmlinux.bin.$(suffix-y)
+	$(call if_changed,ld)
diff --git a/arch/s390/boot/compressed/head31.S b/arch/s390/boot/compressed/head31.S
new file mode 100644
index 00000000000..2a5523a32bc
--- /dev/null
+++ b/arch/s390/boot/compressed/head31.S
@@ -0,0 +1,51 @@
+/*
+ * Startup glue code to uncompress the kernel
+ *
+ * Copyright IBM Corp. 2010
+ *
+ *   Author(s):	Martin Schwidefsky <schwidefsky@de.ibm.com>
+ */
+
+#include <linux/init.h>
+#include <asm/asm-offsets.h>
+#include <asm/thread_info.h>
+#include <asm/page.h>
+#include "sizes.h"
+
+__HEAD
+	.globl	startup_continue
+startup_continue:
+	basr	%r13,0			# get base
+.LPG1:
+	# setup stack
+	l	%r15,.Lstack-.LPG1(%r13)
+	ahi	%r15,-96
+	l	%r1,.Ldecompress-.LPG1(%r13)
+	basr	%r14,%r1
+	# setup registers for memory mover & branch to target
+	lr	%r4,%r2
+	l	%r2,.Loffset-.LPG1(%r13)
+	la	%r4,0(%r2,%r4)
+	l	%r3,.Lmvsize-.LPG1(%r13)
+	lr	%r5,%r3
+	# move the memory mover someplace safe
+	la	%r1,0x200
+	mvc	0(mover_end-mover,%r1),mover-.LPG1(%r13)
+	# decompress image is started at 0x11000
+	lr	%r6,%r2
+	br	%r1
+mover:
+	mvcle	%r2,%r4,0
+	jo	mover
+	br	%r6
+mover_end:
+
+	.align	8
+.Lstack:
+	.long	0x8000 + (1<<(PAGE_SHIFT+THREAD_ORDER))
+.Ldecompress:
+	.long	decompress_kernel
+.Loffset:
+	.long	0x11000
+.Lmvsize:
+	.long	SZ__bss_start
diff --git a/arch/s390/boot/compressed/head64.S b/arch/s390/boot/compressed/head64.S
new file mode 100644
index 00000000000..2982cb14055
--- /dev/null
+++ b/arch/s390/boot/compressed/head64.S
@@ -0,0 +1,48 @@
+/*
+ * Startup glue code to uncompress the kernel
+ *
+ * Copyright IBM Corp. 2010
+ *
+ *   Author(s):	Martin Schwidefsky <schwidefsky@de.ibm.com>
+ */
+
+#include <linux/init.h>
+#include <asm/asm-offsets.h>
+#include <asm/thread_info.h>
+#include <asm/page.h>
+#include "sizes.h"
+
+__HEAD
+	.globl	startup_continue
+startup_continue:
+	basr	%r13,0			# get base
+.LPG1:
+	# setup stack
+	lg	%r15,.Lstack-.LPG1(%r13)
+	aghi	%r15,-160
+	brasl	%r14,decompress_kernel
+	# setup registers for memory mover & branch to target
+	lgr	%r4,%r2
+	lg	%r2,.Loffset-.LPG1(%r13)
+	la	%r4,0(%r2,%r4)
+	lg	%r3,.Lmvsize-.LPG1(%r13)
+	lgr	%r5,%r3
+	# move the memory mover someplace safe
+	la	%r1,0x200
+	mvc	0(mover_end-mover,%r1),mover-.LPG1(%r13)
+	# decompress image is started at 0x11000
+	lgr	%r6,%r2
+	br	%r1
+mover:
+	mvcle	%r2,%r4,0
+	jo	mover
+	br	%r6
+mover_end:
+
+	.align	8
+.Lstack:
+	.quad	0x8000 + (1<<(PAGE_SHIFT+THREAD_ORDER))
+.Loffset:
+	.quad	0x11000
+.Lmvsize:
+	.quad	SZ__bss_start
diff --git a/arch/s390/boot/compressed/misc.c b/arch/s390/boot/compressed/misc.c
new file mode 100644
index 00000000000..0851eb1e919
--- /dev/null
+++ b/arch/s390/boot/compressed/misc.c
@@ -0,0 +1,162 @@
+/*
+ * Definitions and wrapper functions for kernel decompressor
+ *
+ * Copyright IBM Corp. 2010
+ *
+ * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
+ */
+
+#include <asm/uaccess.h>
+#include <asm/page.h>
+#include <asm/ipl.h>
+#include "sizes.h"
+
+/*
+ * gzip declarations
+ */
+#define STATIC static
+
+#undef memset
+#undef memcpy
+#undef memmove
+#define memzero(s, n) memset((s), 0, (n))
+
+/* Symbols defined by linker scripts */
+extern char input_data[];
+extern int input_len;
+extern char _text, _end;
+extern char _bss, _ebss;
+
+static void error(char *m);
+
+static unsigned long free_mem_ptr;
+static unsigned long free_mem_end_ptr;
+
+#ifdef CONFIG_HAVE_KERNEL_BZIP2
+#define HEAP_SIZE	0x400000
+#else
+#define HEAP_SIZE	0x10000
+#endif
+
+#ifdef CONFIG_KERNEL_GZIP
+#include "../../../../lib/decompress_inflate.c"
+#endif
+
+#ifdef CONFIG_KERNEL_BZIP2
+#include "../../../../lib/decompress_bunzip2.c"
+#endif
+
+#ifdef CONFIG_KERNEL_LZMA
+#include "../../../../lib/decompress_unlzma.c"
+#endif
+
+#ifdef CONFIG_KERNEL_LZO
+#include "../../../../lib/decompress_unlzo.c"
+#endif
+
+extern _sclp_print_early(const char *);
+
+int puts(const char *s)
+{
+	_sclp_print_early(s);
+	return 0;
+}
+
+void *memset(void *s, int c, size_t n)
+{
+	char *xs;
+
+	if (c == 0)
+		return __builtin_memset(s, 0, n);
+
+	xs = (char *) s;
+	if (n > 0)
+		do {
+			*xs++ = c;
+		} while (--n > 0);
+	return s;
+}
+
+void *memcpy(void *__dest, __const void *__src, size_t __n)
+{
+	return __builtin_memcpy(__dest, __src, __n);
+}
+
+void *memmove(void *__dest, __const void *__src, size_t __n)
+{
+	char *d;
+	const char *s;
+
+	if (__dest <= __src)
+		return __builtin_memcpy(__dest, __src, __n);
+	d = __dest + __n;
+	s = __src + __n;
+	while (__n--)
+		*--d = *--s;
+	return __dest;
+}
+
+static void error(char *x)
+{
+	unsigned long long psw = 0x000a0000deadbeefULL;
+
+	puts("\n\n");
+	puts(x);
+	puts("\n\n -- System halted");
+
+	asm volatile("lpsw %0" : : "Q" (psw));
+}
+
+/*
+ * Safe guard the ipl parameter block against a memory area that will be
+ * overwritten. The validity check for the ipl parameter block is complex
+ * (see cio_get_iplinfo and ipl_save_parameters) but if the pointer to
+ * the ipl parameter block intersects with the passed memory area we can
+ * safely assume that we can read from that memory. In that case just copy
+ * the memory to IPL_PARMBLOCK_ORIGIN even if there is no ipl parameter
+ * block.
+ */
+static void check_ipl_parmblock(void *start, unsigned long size)
+{
+	void *src, *dst;
+
+	src = (void *)(unsigned long) S390_lowcore.ipl_parmblock_ptr;
+	if (src + PAGE_SIZE <= start || src >= start + size)
+		return;
+	dst = (void *) IPL_PARMBLOCK_ORIGIN;
+	memmove(dst, src, PAGE_SIZE);
+	S390_lowcore.ipl_parmblock_ptr = IPL_PARMBLOCK_ORIGIN;
+}
+
+unsigned long decompress_kernel(void)
+{
+	unsigned long output_addr;
+	unsigned char *output;
+
+	check_ipl_parmblock((void *) 0, (unsigned long) output + SZ__bss_start);
+	memset(&_bss, 0, &_ebss - &_bss);
+	free_mem_ptr = (unsigned long)&_end;
+	free_mem_end_ptr = free_mem_ptr + HEAP_SIZE;
+	output = (unsigned char *) ((free_mem_end_ptr + 4095UL) & -4096UL);
+
+#ifdef CONFIG_BLK_DEV_INITRD
+	/*
+	 * Move the initrd right behind the end of the decompressed
+	 * kernel image.
+	 */
+	if (INITRD_START && INITRD_SIZE &&
+	    INITRD_START < (unsigned long) output + SZ__bss_start) {
+		check_ipl_parmblock(output + SZ__bss_start,
+				    INITRD_START + INITRD_SIZE);
+		memmove(output + SZ__bss_start,
+			(void *) INITRD_START, INITRD_SIZE);
+		INITRD_START = (unsigned long) output + SZ__bss_start;
+	}
+#endif
+
+	puts("Uncompressing Linux... ");
+	decompress(input_data, input_len, NULL, NULL, output, NULL, error);
+	puts("Ok, booting the kernel.\n");
+	return (unsigned long) output;
+}
+
diff --git a/arch/s390/boot/compressed/vmlinux.lds.S b/arch/s390/boot/compressed/vmlinux.lds.S
new file mode 100644
index 00000000000..d80f79d8dd9
--- /dev/null
+++ b/arch/s390/boot/compressed/vmlinux.lds.S
@@ -0,0 +1,55 @@
+#include <asm-generic/vmlinux.lds.h>
+
+#ifdef CONFIG_64BIT
+OUTPUT_FORMAT("elf64-s390", "elf64-s390", "elf64-s390")
+OUTPUT_ARCH(s390:64-bit)
+#else
+OUTPUT_FORMAT("elf32-s390", "elf32-s390", "elf32-s390")
+OUTPUT_ARCH(s390)
+#endif
+
+ENTRY(startup)
+
+SECTIONS
+{
+	/* Be careful parts of head_64.S assume startup_32 is at
+	 * address 0.
+	 */
+	. = 0;
+	.head.text : {
+		_head = . ;
+		HEAD_TEXT
+		_ehead = . ;
+	}
+	.rodata.compressed : {
+		*(.rodata.compressed)
+	}
+	.text :	{
+		_text = .;	/* Text */
+		*(.text)
+		*(.text.*)
+		_etext = . ;
+	}
+	.rodata : {
+		_rodata = . ;
+		*(.rodata)	 /* read-only data */
+		*(.rodata.*)
+		_erodata = . ;
+	}
+	.data :	{
+		_data = . ;
+		*(.data)
+		*(.data.*)
+		_edata = . ;
+	}
+	. = ALIGN(256);
+	.bss : {
+		_bss = . ;
+		*(.bss)
+		*(.bss.*)
+		*(COMMON)
+		. = ALIGN(8);	/* For convenience during zeroing */
+		_ebss = .;
+	}
+	_end = .;
+}
diff --git a/arch/s390/boot/compressed/vmlinux.scr b/arch/s390/boot/compressed/vmlinux.scr
new file mode 100644
index 00000000000..f02382ae5c4
--- /dev/null
+++ b/arch/s390/boot/compressed/vmlinux.scr
@@ -0,0 +1,10 @@
+SECTIONS
+{
+  .rodata.compressed : {
+	input_len = .;
+	LONG(input_data_end - input_data) input_data = .;
+	*(.data)
+	output_len = . - 4;
+	input_data_end = .;
+	}
+}
diff --git a/arch/s390/crypto/aes_s390.c b/arch/s390/crypto/aes_s390.c
index 6be4503201a..58f46734465 100644
--- a/arch/s390/crypto/aes_s390.c
+++ b/arch/s390/crypto/aes_s390.c
@@ -78,14 +78,14 @@ static int setkey_fallback_cip(struct crypto_tfm *tfm, const u8 *in_key,
 	struct s390_aes_ctx *sctx = crypto_tfm_ctx(tfm);
 	int ret;
 
-	sctx->fallback.blk->base.crt_flags &= ~CRYPTO_TFM_REQ_MASK;
-	sctx->fallback.blk->base.crt_flags |= (tfm->crt_flags &
+	sctx->fallback.cip->base.crt_flags &= ~CRYPTO_TFM_REQ_MASK;
+	sctx->fallback.cip->base.crt_flags |= (tfm->crt_flags &
 			CRYPTO_TFM_REQ_MASK);
 
 	ret = crypto_cipher_setkey(sctx->fallback.cip, in_key, key_len);
 	if (ret) {
 		tfm->crt_flags &= ~CRYPTO_TFM_RES_MASK;
-		tfm->crt_flags |= (sctx->fallback.blk->base.crt_flags &
+		tfm->crt_flags |= (sctx->fallback.cip->base.crt_flags &
 				CRYPTO_TFM_RES_MASK);
 	}
 	return ret;
diff --git a/arch/s390/crypto/prng.c b/arch/s390/crypto/prng.c
index a3209906739..aa819dac236 100644
--- a/arch/s390/crypto/prng.c
+++ b/arch/s390/crypto/prng.c
@@ -10,6 +10,7 @@
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/random.h>
+#include <linux/slab.h>
 #include <asm/debug.h>
 #include <asm/uaccess.h>
 
diff --git a/arch/s390/crypto/sha_common.c b/arch/s390/crypto/sha_common.c
index 7903ec47e6b..f42dbabc0d3 100644
--- a/arch/s390/crypto/sha_common.c
+++ b/arch/s390/crypto/sha_common.c
@@ -79,7 +79,7 @@ int s390_sha_final(struct shash_desc *desc, u8 *out)
 	memset(ctx->buf + index, 0x00, end - index - 8);
 
 	/*
-	 * Append message length. Well, SHA-512 wants a 128 bit lenght value,
+	 * Append message length. Well, SHA-512 wants a 128 bit length value,
 	 * nevertheless we use u64, should be enough for now...
 	 */
 	bits = ctx->count * 8;
diff --git a/arch/s390/defconfig b/arch/s390/defconfig
index b416aa11b91..253f158db66 100644
--- a/arch/s390/defconfig
+++ b/arch/s390/defconfig
@@ -1,7 +1,7 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.33-rc2
-# Mon Jan  4 09:03:07 2010
+# Linux kernel version: 2.6.35-rc1
+# Fri Jun  4 11:32:40 2010
 #
 CONFIG_SCHED_MC=y
 CONFIG_MMU=y
@@ -17,6 +17,7 @@ CONFIG_GENERIC_TIME=y
 CONFIG_GENERIC_TIME_VSYSCALL=y
 CONFIG_GENERIC_CLOCKEVENTS=y
 CONFIG_GENERIC_BUG=y
+CONFIG_GENERIC_BUG_RELATIVE_POINTERS=y
 CONFIG_NO_IOMEM=y
 CONFIG_NO_DMA=y
 CONFIG_GENERIC_LOCKBREAK=y
@@ -34,8 +35,17 @@ CONFIG_CONSTRUCTORS=y
 CONFIG_EXPERIMENTAL=y
 CONFIG_LOCK_KERNEL=y
 CONFIG_INIT_ENV_ARG_LIMIT=32
+CONFIG_CROSS_COMPILE=""
 CONFIG_LOCALVERSION=""
 CONFIG_LOCALVERSION_AUTO=y
+CONFIG_HAVE_KERNEL_GZIP=y
+CONFIG_HAVE_KERNEL_BZIP2=y
+CONFIG_HAVE_KERNEL_LZMA=y
+CONFIG_HAVE_KERNEL_LZO=y
+CONFIG_KERNEL_GZIP=y
+# CONFIG_KERNEL_BZIP2 is not set
+# CONFIG_KERNEL_LZMA is not set
+# CONFIG_KERNEL_LZO is not set
 CONFIG_SWAP=y
 CONFIG_SYSVIPC=y
 CONFIG_SYSVIPC_SYSCTL=y
@@ -55,15 +65,11 @@ CONFIG_TREE_RCU=y
 # CONFIG_RCU_TRACE is not set
 CONFIG_RCU_FANOUT=64
 # CONFIG_RCU_FANOUT_EXACT is not set
+# CONFIG_RCU_FAST_NO_HZ is not set
 # CONFIG_TREE_RCU_TRACE is not set
 CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
 CONFIG_LOG_BUF_SHIFT=17
-CONFIG_GROUP_SCHED=y
-CONFIG_FAIR_GROUP_SCHED=y
-# CONFIG_RT_GROUP_SCHED is not set
-CONFIG_USER_SCHED=y
-# CONFIG_CGROUP_SCHED is not set
 CONFIG_CGROUPS=y
 # CONFIG_CGROUP_DEBUG is not set
 CONFIG_CGROUP_NS=y
@@ -72,6 +78,8 @@ CONFIG_CGROUP_NS=y
 # CONFIG_CPUSETS is not set
 # CONFIG_CGROUP_CPUACCT is not set
 # CONFIG_RESOURCE_COUNTERS is not set
+# CONFIG_CGROUP_SCHED is not set
+# CONFIG_BLK_CGROUP is not set
 CONFIG_SYSFS_DEPRECATED=y
 CONFIG_SYSFS_DEPRECATED_V2=y
 # CONFIG_RELAY is not set
@@ -86,6 +94,7 @@ CONFIG_INITRAMFS_SOURCE=""
 CONFIG_RD_GZIP=y
 CONFIG_RD_BZIP2=y
 CONFIG_RD_LZMA=y
+CONFIG_RD_LZO=y
 # CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
 CONFIG_SYSCTL=y
 CONFIG_ANON_INODES=y
@@ -119,6 +128,7 @@ CONFIG_SLAB=y
 # CONFIG_SLUB is not set
 # CONFIG_SLOB is not set
 # CONFIG_PROFILING is not set
+CONFIG_TRACEPOINTS=y
 CONFIG_HAVE_OPROFILE=y
 CONFIG_KPROBES=y
 CONFIG_HAVE_SYSCALL_WRAPPERS=y
@@ -127,6 +137,7 @@ CONFIG_HAVE_KPROBES=y
 CONFIG_HAVE_KRETPROBES=y
 CONFIG_HAVE_ARCH_TRACEHOOK=y
 CONFIG_USE_GENERIC_SMP_HELPERS=y
+CONFIG_HAVE_REGS_AND_STACK_ACCESS_API=y
 CONFIG_HAVE_DEFAULT_NO_SPIN_MUTEXES=y
 
 #
@@ -149,7 +160,6 @@ CONFIG_STOP_MACHINE=y
 CONFIG_BLOCK=y
 CONFIG_BLK_DEV_BSG=y
 # CONFIG_BLK_DEV_INTEGRITY is not set
-# CONFIG_BLK_CGROUP is not set
 CONFIG_BLOCK_COMPAT=y
 
 #
@@ -158,7 +168,6 @@ CONFIG_BLOCK_COMPAT=y
 CONFIG_IOSCHED_NOOP=y
 CONFIG_IOSCHED_DEADLINE=y
 CONFIG_IOSCHED_CFQ=y
-# CONFIG_CFQ_GROUP_IOSCHED is not set
 CONFIG_DEFAULT_DEADLINE=y
 # CONFIG_DEFAULT_CFQ is not set
 # CONFIG_DEFAULT_NOOP is not set
@@ -311,7 +320,6 @@ CONFIG_COMPAT_BINFMT_ELF=y
 # CONFIG_HAVE_AOUT is not set
 CONFIG_BINFMT_MISC=m
 CONFIG_FORCE_MAX_ZONEORDER=9
-# CONFIG_PROCESS_DEBUG is not set
 CONFIG_PFAULT=y
 # CONFIG_SHARED_KERNEL is not set
 # CONFIG_CMM is not set
@@ -338,13 +346,13 @@ CONFIG_PM_SLEEP=y
 CONFIG_HIBERNATION=y
 CONFIG_PM_STD_PARTITION=""
 # CONFIG_PM_RUNTIME is not set
+CONFIG_PM_OPS=y
 CONFIG_NET=y
 
 #
 # Networking options
 #
 CONFIG_PACKET=y
-# CONFIG_PACKET_MMAP is not set
 CONFIG_UNIX=y
 CONFIG_XFRM=y
 # CONFIG_XFRM_USER is not set
@@ -448,6 +456,7 @@ CONFIG_NF_CONNTRACK=m
 # CONFIG_IP6_NF_IPTABLES is not set
 # CONFIG_IP_DCCP is not set
 CONFIG_IP_SCTP=m
+# CONFIG_NET_SCTPPROBE is not set
 # CONFIG_SCTP_DBG_MSG is not set
 # CONFIG_SCTP_DBG_OBJCNT is not set
 # CONFIG_SCTP_HMAC_NONE is not set
@@ -456,6 +465,7 @@ CONFIG_SCTP_HMAC_MD5=y
 # CONFIG_RDS is not set
 # CONFIG_TIPC is not set
 # CONFIG_ATM is not set
+# CONFIG_L2TP is not set
 # CONFIG_BRIDGE is not set
 # CONFIG_VLAN_8021Q is not set
 # CONFIG_DECNET is not set
@@ -516,12 +526,14 @@ CONFIG_NET_ACT_NAT=m
 # CONFIG_NET_CLS_IND is not set
 CONFIG_NET_SCH_FIFO=y
 # CONFIG_DCB is not set
+CONFIG_RPS=y
 
 #
 # Network testing
 #
 # CONFIG_NET_PKTGEN is not set
 # CONFIG_NET_TCPPROBE is not set
+# CONFIG_NET_DROP_MONITOR is not set
 CONFIG_CAN=m
 CONFIG_CAN_RAW=m
 CONFIG_CAN_BCM=m
@@ -536,6 +548,7 @@ CONFIG_CAN_VCAN=m
 # CONFIG_WIMAX is not set
 # CONFIG_RFKILL is not set
 # CONFIG_NET_9P is not set
+# CONFIG_CAIF is not set
 # CONFIG_PCMCIA is not set
 CONFIG_CCW=y
 
@@ -598,6 +611,7 @@ CONFIG_MISC_DEVICES=y
 #
 # SCSI device support
 #
+CONFIG_SCSI_MOD=y
 # CONFIG_RAID_ATTRS is not set
 CONFIG_SCSI=y
 # CONFIG_SCSI_DMA is not set
@@ -717,6 +731,7 @@ CONFIG_VIRTIO_NET=m
 # Character devices
 #
 CONFIG_DEVKMEM=y
+# CONFIG_N_GSM is not set
 CONFIG_UNIX98_PTYS=y
 # CONFIG_DEVPTS_MULTIPLE_INSTANCES is not set
 CONFIG_LEGACY_PTYS=y
@@ -764,6 +779,7 @@ CONFIG_S390_TAPE_34XX=m
 # CONFIG_MONREADER is not set
 CONFIG_MONWRITER=m
 CONFIG_S390_VMUR=m
+# CONFIG_RAMOOPS is not set
 
 #
 # PPS support
@@ -777,10 +793,6 @@ CONFIG_S390_VMUR=m
 # CONFIG_NEW_LEDS is not set
 CONFIG_ACCESSIBILITY=y
 # CONFIG_AUXDISPLAY is not set
-
-#
-# TI VLYNQ
-#
 # CONFIG_STAGING is not set
 
 #
@@ -856,6 +868,7 @@ CONFIG_MISC_FILESYSTEMS=y
 # CONFIG_BEFS_FS is not set
 # CONFIG_BFS_FS is not set
 # CONFIG_EFS_FS is not set
+# CONFIG_LOGFS is not set
 # CONFIG_CRAMFS is not set
 # CONFIG_SQUASHFS is not set
 # CONFIG_VXFS_FS is not set
@@ -884,6 +897,7 @@ CONFIG_SUNRPC=y
 # CONFIG_RPCSEC_GSS_KRB5 is not set
 # CONFIG_RPCSEC_GSS_SPKM3 is not set
 # CONFIG_SMB_FS is not set
+# CONFIG_CEPH_FS is not set
 # CONFIG_CIFS is not set
 # CONFIG_NCP_FS is not set
 # CONFIG_CODA_FS is not set
@@ -945,6 +959,7 @@ CONFIG_DEBUG_MUTEXES=y
 # CONFIG_LOCK_STAT is not set
 CONFIG_DEBUG_SPINLOCK_SLEEP=y
 # CONFIG_DEBUG_LOCKING_API_SELFTESTS is not set
+CONFIG_STACKTRACE=y
 # CONFIG_DEBUG_KOBJECT is not set
 CONFIG_DEBUG_BUGVERBOSE=y
 # CONFIG_DEBUG_INFO is not set
@@ -962,16 +977,22 @@ CONFIG_DEBUG_MEMORY_INIT=y
 # CONFIG_DEBUG_BLOCK_EXT_DEVT is not set
 CONFIG_DEBUG_FORCE_WEAK_PER_CPU=y
 # CONFIG_LKDTM is not set
+# CONFIG_CPU_NOTIFIER_ERROR_INJECT is not set
 # CONFIG_FAULT_INJECTION is not set
 # CONFIG_LATENCYTOP is not set
 CONFIG_SYSCTL_SYSCALL_CHECK=y
 # CONFIG_DEBUG_PAGEALLOC is not set
+CONFIG_NOP_TRACER=y
 CONFIG_HAVE_FUNCTION_TRACER=y
 CONFIG_HAVE_FUNCTION_GRAPH_TRACER=y
 CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST=y
 CONFIG_HAVE_DYNAMIC_FTRACE=y
 CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y
 CONFIG_HAVE_SYSCALL_TRACEPOINTS=y
+CONFIG_RING_BUFFER=y
+CONFIG_EVENT_TRACING=y
+CONFIG_CONTEXT_SWITCH_TRACER=y
+CONFIG_TRACING=y
 CONFIG_TRACING_SUPPORT=y
 CONFIG_FTRACE=y
 # CONFIG_FUNCTION_TRACER is not set
@@ -988,10 +1009,16 @@ CONFIG_BRANCH_PROFILE_NONE=y
 # CONFIG_KMEMTRACE is not set
 # CONFIG_WORKQUEUE_TRACER is not set
 # CONFIG_BLK_DEV_IO_TRACE is not set
+CONFIG_KPROBE_EVENT=y
+# CONFIG_RING_BUFFER_BENCHMARK is not set
 # CONFIG_DYNAMIC_DEBUG is not set
+# CONFIG_ATOMIC64_SELFTEST is not set
 CONFIG_SAMPLES=y
+# CONFIG_SAMPLE_TRACEPOINTS is not set
+# CONFIG_SAMPLE_TRACE_EVENTS is not set
 # CONFIG_SAMPLE_KOBJECT is not set
 # CONFIG_SAMPLE_KPROBES is not set
+# CONFIG_DEBUG_STRICT_USER_COPY_CHECKS is not set
 
 #
 # Security options
@@ -1025,6 +1052,7 @@ CONFIG_CRYPTO_MANAGER=y
 CONFIG_CRYPTO_MANAGER2=y
 CONFIG_CRYPTO_GF128MUL=m
 # CONFIG_CRYPTO_NULL is not set
+# CONFIG_CRYPTO_PCRYPT is not set
 CONFIG_CRYPTO_WORKQUEUE=y
 # CONFIG_CRYPTO_CRYPTD is not set
 CONFIG_CRYPTO_AUTHENC=m
@@ -1112,7 +1140,7 @@ CONFIG_CRYPTO_SHA512_S390=m
 # CONFIG_CRYPTO_DES_S390 is not set
 # CONFIG_CRYPTO_AES_S390 is not set
 CONFIG_S390_PRNG=m
-# CONFIG_BINARY_PRINTF is not set
+CONFIG_BINARY_PRINTF=y
 
 #
 # Library routines
@@ -1129,14 +1157,16 @@ CONFIG_LIBCRC32C=m
 CONFIG_ZLIB_INFLATE=y
 CONFIG_ZLIB_DEFLATE=m
 CONFIG_LZO_COMPRESS=m
-CONFIG_LZO_DECOMPRESS=m
+CONFIG_LZO_DECOMPRESS=y
 CONFIG_DECOMPRESS_GZIP=y
 CONFIG_DECOMPRESS_BZIP2=y
 CONFIG_DECOMPRESS_LZMA=y
+CONFIG_DECOMPRESS_LZO=y
 CONFIG_NLATTR=y
 CONFIG_HAVE_KVM=y
 CONFIG_VIRTUALIZATION=y
 CONFIG_KVM=m
+# CONFIG_VHOST_NET is not set
 CONFIG_VIRTIO=y
 CONFIG_VIRTIO_RING=y
 CONFIG_VIRTIO_BALLOON=m
diff --git a/arch/s390/hypfs/hypfs.h b/arch/s390/hypfs/hypfs.h
index aea572009d6..fa487d4cc08 100644
--- a/arch/s390/hypfs/hypfs.h
+++ b/arch/s390/hypfs/hypfs.h
@@ -11,6 +11,7 @@
 
 #include <linux/fs.h>
 #include <linux/types.h>
+#include <linux/debugfs.h>
 
 #define REG_FILE_MODE    0440
 #define UPDATE_FILE_MODE 0220
@@ -34,6 +35,9 @@ extern int hypfs_diag_create_files(struct super_block *sb, struct dentry *root);
 
 /* VM Hypervisor */
 extern int hypfs_vm_init(void);
+extern void hypfs_vm_exit(void);
 extern int hypfs_vm_create_files(struct super_block *sb, struct dentry *root);
 
+/* Directory for debugfs files */
+extern struct dentry *hypfs_dbfs_dir;
 #endif /* _HYPFS_H_ */
diff --git a/arch/s390/hypfs/hypfs_diag.c b/arch/s390/hypfs/hypfs_diag.c
index 2b92d501425..1211bb1d2f2 100644
--- a/arch/s390/hypfs/hypfs_diag.c
+++ b/arch/s390/hypfs/hypfs_diag.c
@@ -12,10 +12,10 @@
 
 #include <linux/types.h>
 #include <linux/errno.h>
-#include <linux/gfp.h>
 #include <linux/slab.h>
 #include <linux/string.h>
 #include <linux/vmalloc.h>
+#include <linux/mm.h>
 #include <asm/ebcdic.h>
 #include "hypfs.h"
 
@@ -23,6 +23,8 @@
 #define CPU_NAME_LEN 16		/* type name len of cpus in diag224 name table */
 #define TMP_SIZE 64		/* size of temporary buffers */
 
+#define DBFS_D204_HDR_VERSION	0
+
 /* diag 204 subcodes */
 enum diag204_sc {
 	SUBC_STIB4 = 4,
@@ -48,6 +50,8 @@ static void *diag204_buf;		/* 4K aligned buffer for diag204 data */
 static void *diag204_buf_vmalloc;	/* vmalloc pointer for diag204 data */
 static int diag204_buf_pages;		/* number of pages for diag204 data */
 
+static struct dentry *dbfs_d204_file;
+
 /*
  * DIAG 204 data structures and member access functions.
  *
@@ -365,18 +369,21 @@ static void diag204_free_buffer(void)
 	} else {
 		free_pages((unsigned long) diag204_buf, 0);
 	}
-	diag204_buf_pages = 0;
 	diag204_buf = NULL;
 }
 
+static void *page_align_ptr(void *ptr)
+{
+	return (void *) PAGE_ALIGN((unsigned long) ptr);
+}
+
 static void *diag204_alloc_vbuf(int pages)
 {
 	/* The buffer has to be page aligned! */
 	diag204_buf_vmalloc = vmalloc(PAGE_SIZE * (pages + 1));
 	if (!diag204_buf_vmalloc)
 		return ERR_PTR(-ENOMEM);
-	diag204_buf = (void*)((unsigned long)diag204_buf_vmalloc
-				& ~0xfffUL) + 0x1000;
+	diag204_buf = page_align_ptr(diag204_buf_vmalloc);
 	diag204_buf_pages = pages;
 	return diag204_buf;
 }
@@ -469,17 +476,26 @@ fail_alloc:
 	return rc;
 }
 
+static int diag204_do_store(void *buf, int pages)
+{
+	int rc;
+
+	rc = diag204((unsigned long) diag204_store_sc |
+		     (unsigned long) diag204_info_type, pages, buf);
+	return rc < 0 ? -ENOSYS : 0;
+}
+
 static void *diag204_store(void)
 {
 	void *buf;
-	int pages;
+	int pages, rc;
 
 	buf = diag204_get_buffer(diag204_info_type, &pages);
 	if (IS_ERR(buf))
 		goto out;
-	if (diag204((unsigned long)diag204_store_sc |
-		    (unsigned long)diag204_info_type, pages, buf) < 0)
-		return ERR_PTR(-ENOSYS);
+	rc = diag204_do_store(buf, pages);
+	if (rc)
+		return ERR_PTR(rc);
 out:
 	return buf;
 }
@@ -488,7 +504,7 @@ out:
 
 static int diag224(void *ptr)
 {
-	int rc = -ENOTSUPP;
+	int rc = -EOPNOTSUPP;
 
 	asm volatile(
 		"	diag	%1,%2,0x224\n"
@@ -507,7 +523,7 @@ static int diag224_get_name_table(void)
 		return -ENOMEM;
 	if (diag224(diag224_cpu_names)) {
 		kfree(diag224_cpu_names);
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 	}
 	EBCASC(diag224_cpu_names + 16, (*diag224_cpu_names + 1) * 16);
 	return 0;
@@ -527,6 +543,92 @@ static int diag224_idx2name(int index, char *name)
 	return 0;
 }
 
+struct dbfs_d204_hdr {
+	u64	len;		/* Length of d204 buffer without header */
+	u16	version;	/* Version of header */
+	u8	sc;		/* Used subcode */
+	char	reserved[53];
+} __attribute__ ((packed));
+
+struct dbfs_d204 {
+	struct dbfs_d204_hdr	hdr;	/* 64 byte header */
+	char			buf[];	/* d204 buffer */
+} __attribute__ ((packed));
+
+struct dbfs_d204_private {
+	struct dbfs_d204	*d204;	/* Aligned d204 data with header */
+	void			*base;	/* Base pointer (needed for vfree) */
+};
+
+static int dbfs_d204_open(struct inode *inode, struct file *file)
+{
+	struct dbfs_d204_private *data;
+	struct dbfs_d204 *d204;
+	int rc, buf_size;
+
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+	buf_size = PAGE_SIZE * (diag204_buf_pages + 1) + sizeof(d204->hdr);
+	data->base = vmalloc(buf_size);
+	if (!data->base) {
+		rc = -ENOMEM;
+		goto fail_kfree_data;
+	}
+	memset(data->base, 0, buf_size);
+	d204 = page_align_ptr(data->base + sizeof(d204->hdr))
+		- sizeof(d204->hdr);
+	rc = diag204_do_store(&d204->buf, diag204_buf_pages);
+	if (rc)
+		goto fail_vfree_base;
+	d204->hdr.version = DBFS_D204_HDR_VERSION;
+	d204->hdr.len = PAGE_SIZE * diag204_buf_pages;
+	d204->hdr.sc = diag204_store_sc;
+	data->d204 = d204;
+	file->private_data = data;
+	return nonseekable_open(inode, file);
+
+fail_vfree_base:
+	vfree(data->base);
+fail_kfree_data:
+	kfree(data);
+	return rc;
+}
+
+static int dbfs_d204_release(struct inode *inode, struct file *file)
+{
+	struct dbfs_d204_private *data = file->private_data;
+
+	vfree(data->base);
+	kfree(data);
+	return 0;
+}
+
+static ssize_t dbfs_d204_read(struct file *file, char __user *buf,
+			      size_t size, loff_t *ppos)
+{
+	struct dbfs_d204_private *data = file->private_data;
+
+	return simple_read_from_buffer(buf, size, ppos, data->d204,
+				       data->d204->hdr.len +
+				       sizeof(data->d204->hdr));
+}
+
+static const struct file_operations dbfs_d204_ops = {
+	.open		= dbfs_d204_open,
+	.read		= dbfs_d204_read,
+	.release	= dbfs_d204_release,
+};
+
+static int hypfs_dbfs_init(void)
+{
+	dbfs_d204_file = debugfs_create_file("diag_204", 0400, hypfs_dbfs_dir,
+					     NULL, &dbfs_d204_ops);
+	if (IS_ERR(dbfs_d204_file))
+		return PTR_ERR(dbfs_d204_file);
+	return 0;
+}
+
 __init int hypfs_diag_init(void)
 {
 	int rc;
@@ -541,11 +643,17 @@ __init int hypfs_diag_init(void)
 		pr_err("The hardware system does not provide all "
 		       "functions required by hypfs\n");
 	}
+	if (diag204_info_type == INFO_EXT) {
+		rc = hypfs_dbfs_init();
+		if (rc)
+			diag204_free_buffer();
+	}
 	return rc;
 }
 
 void hypfs_diag_exit(void)
 {
+	debugfs_remove(dbfs_d204_file);
 	diag224_delete_name_table();
 	diag204_free_buffer();
 }
diff --git a/arch/s390/hypfs/hypfs_vm.c b/arch/s390/hypfs/hypfs_vm.c
index f0b0d31f0b4..ee5ab1a578e 100644
--- a/arch/s390/hypfs/hypfs_vm.c
+++ b/arch/s390/hypfs/hypfs_vm.c
@@ -10,14 +10,18 @@
 #include <linux/string.h>
 #include <linux/vmalloc.h>
 #include <asm/ebcdic.h>
+#include <asm/timex.h>
 #include "hypfs.h"
 
 #define NAME_LEN 8
+#define DBFS_D2FC_HDR_VERSION 0
 
 static char local_guest[] = "        ";
 static char all_guests[] = "*       ";
 static char *guest_query;
 
+static struct dentry *dbfs_d2fc_file;
+
 struct diag2fc_data {
 	__u32 version;
 	__u32 flags;
@@ -76,23 +80,26 @@ static int diag2fc(int size, char* query, void *addr)
 		return -residual_cnt;
 }
 
-static struct diag2fc_data *diag2fc_store(char *query, int *count)
+/*
+ * Allocate buffer for "query" and store diag 2fc at "offset"
+ */
+static void *diag2fc_store(char *query, unsigned int *count, int offset)
 {
+	void *data;
 	int size;
-	struct diag2fc_data *data;
 
 	do {
 		size = diag2fc(0, query, NULL);
 		if (size < 0)
 			return ERR_PTR(-EACCES);
-		data = vmalloc(size);
+		data = vmalloc(size + offset);
 		if (!data)
 			return ERR_PTR(-ENOMEM);
-		if (diag2fc(size, query, data) == 0)
+		if (diag2fc(size, query, data + offset) == 0)
 			break;
 		vfree(data);
 	} while (1);
-	*count = (size / sizeof(*data));
+	*count = (size / sizeof(struct diag2fc_data));
 
 	return data;
 }
@@ -168,9 +175,10 @@ int hypfs_vm_create_files(struct super_block *sb, struct dentry *root)
 {
 	struct dentry *dir, *file;
 	struct diag2fc_data *data;
-	int rc, i, count = 0;
+	unsigned int count = 0;
+	int rc, i;
 
-	data = diag2fc_store(guest_query, &count);
+	data = diag2fc_store(guest_query, &count, 0);
 	if (IS_ERR(data))
 		return PTR_ERR(data);
 
@@ -218,8 +226,61 @@ failed:
 	return rc;
 }
 
+struct dbfs_d2fc_hdr {
+	u64	len;		/* Length of d2fc buffer without header */
+	u16	version;	/* Version of header */
+	char	tod_ext[16];	/* TOD clock for d2fc */
+	u64	count;		/* Number of VM guests in d2fc buffer */
+	char	reserved[30];
+} __attribute__ ((packed));
+
+struct dbfs_d2fc {
+	struct dbfs_d2fc_hdr	hdr;	/* 64 byte header */
+	char			buf[];	/* d2fc buffer */
+} __attribute__ ((packed));
+
+static int dbfs_d2fc_open(struct inode *inode, struct file *file)
+{
+	struct dbfs_d2fc *data;
+	unsigned int count;
+
+	data = diag2fc_store(guest_query, &count, sizeof(data->hdr));
+	if (IS_ERR(data))
+		return PTR_ERR(data);
+	get_clock_ext(data->hdr.tod_ext);
+	data->hdr.len = count * sizeof(struct diag2fc_data);
+	data->hdr.version = DBFS_D2FC_HDR_VERSION;
+	data->hdr.count = count;
+	memset(&data->hdr.reserved, 0, sizeof(data->hdr.reserved));
+	file->private_data = data;
+	return nonseekable_open(inode, file);
+}
+
+static int dbfs_d2fc_release(struct inode *inode, struct file *file)
+{
+	diag2fc_free(file->private_data);
+	return 0;
+}
+
+static ssize_t dbfs_d2fc_read(struct file *file, char __user *buf,
+				    size_t size, loff_t *ppos)
+{
+	struct dbfs_d2fc *data = file->private_data;
+
+	return simple_read_from_buffer(buf, size, ppos, data, data->hdr.len +
+				       sizeof(struct dbfs_d2fc_hdr));
+}
+
+static const struct file_operations dbfs_d2fc_ops = {
+	.open		= dbfs_d2fc_open,
+	.read		= dbfs_d2fc_read,
+	.release	= dbfs_d2fc_release,
+};
+
 int hypfs_vm_init(void)
 {
+	if (!MACHINE_IS_VM)
+		return 0;
 	if (diag2fc(0, all_guests, NULL) > 0)
 		guest_query = all_guests;
 	else if (diag2fc(0, local_guest, NULL) > 0)
@@ -227,5 +288,17 @@ int hypfs_vm_init(void)
 	else
 		return -EACCES;
 
+	dbfs_d2fc_file = debugfs_create_file("diag_2fc", 0400, hypfs_dbfs_dir,
+					     NULL, &dbfs_d2fc_ops);
+	if (IS_ERR(dbfs_d2fc_file))
+		return PTR_ERR(dbfs_d2fc_file);
+
 	return 0;
 }
+
+void hypfs_vm_exit(void)
+{
+	if (!MACHINE_IS_VM)
+		return;
+	debugfs_remove(dbfs_d2fc_file);
+}
diff --git a/arch/s390/hypfs/inode.c b/arch/s390/hypfs/inode.c
index 341aff2687a..6b120f07304 100644
--- a/arch/s390/hypfs/inode.c
+++ b/arch/s390/hypfs/inode.c
@@ -14,8 +14,8 @@
 #include <linux/fs.h>
 #include <linux/namei.h>
 #include <linux/vfs.h>
+#include <linux/slab.h>
 #include <linux/pagemap.h>
-#include <linux/gfp.h>
 #include <linux/time.h>
 #include <linux/parser.h>
 #include <linux/sysfs.h>
@@ -46,6 +46,8 @@ static const struct super_operations hypfs_s_ops;
 /* start of list of all dentries, which have to be deleted on update */
 static struct dentry *hypfs_last_dentry;
 
+struct dentry *hypfs_dbfs_dir;
+
 static void hypfs_update_update(struct super_block *sb)
 {
 	struct hypfs_sb_info *sb_info = sb->s_fs_info;
@@ -145,7 +147,7 @@ static int hypfs_open(struct inode *inode, struct file *filp)
 		}
 		mutex_unlock(&fs_info->lock);
 	}
-	return 0;
+	return nonseekable_open(inode, filp);
 }
 
 static ssize_t hypfs_aio_read(struct kiocb *iocb, const struct iovec *iov,
@@ -288,46 +290,30 @@ static int hypfs_fill_super(struct super_block *sb, void *data, int silent)
 	sb->s_blocksize_bits = PAGE_CACHE_SHIFT;
 	sb->s_magic = HYPFS_MAGIC;
 	sb->s_op = &hypfs_s_ops;
-	if (hypfs_parse_options(data, sb)) {
-		rc = -EINVAL;
-		goto err_alloc;
-	}
+	if (hypfs_parse_options(data, sb))
+		return -EINVAL;
 	root_inode = hypfs_make_inode(sb, S_IFDIR | 0755);
-	if (!root_inode) {
-		rc = -ENOMEM;
-		goto err_alloc;
-	}
+	if (!root_inode)
+		return -ENOMEM;
 	root_inode->i_op = &simple_dir_inode_operations;
 	root_inode->i_fop = &simple_dir_operations;
-	root_dentry = d_alloc_root(root_inode);
+	sb->s_root = root_dentry = d_alloc_root(root_inode);
 	if (!root_dentry) {
 		iput(root_inode);
-		rc = -ENOMEM;
-		goto err_alloc;
+		return -ENOMEM;
 	}
 	if (MACHINE_IS_VM)
 		rc = hypfs_vm_create_files(sb, root_dentry);
 	else
 		rc = hypfs_diag_create_files(sb, root_dentry);
 	if (rc)
-		goto err_tree;
+		return rc;
 	sbi->update_file = hypfs_create_update_file(sb, root_dentry);
-	if (IS_ERR(sbi->update_file)) {
-		rc = PTR_ERR(sbi->update_file);
-		goto err_tree;
-	}
+	if (IS_ERR(sbi->update_file))
+		return PTR_ERR(sbi->update_file);
 	hypfs_update_update(sb);
-	sb->s_root = root_dentry;
 	pr_info("Hypervisor filesystem mounted\n");
 	return 0;
-
-err_tree:
-	hypfs_delete_tree(root_dentry);
-	d_genocide(root_dentry);
-	dput(root_dentry);
-err_alloc:
-	kfree(sbi);
-	return rc;
 }
 
 static int hypfs_get_super(struct file_system_type *fst, int flags,
@@ -340,12 +326,12 @@ static void hypfs_kill_super(struct super_block *sb)
 {
 	struct hypfs_sb_info *sb_info = sb->s_fs_info;
 
-	if (sb->s_root) {
+	if (sb->s_root)
 		hypfs_delete_tree(sb->s_root);
+	if (sb_info->update_file)
 		hypfs_remove(sb_info->update_file);
-		kfree(sb->s_fs_info);
-		sb->s_fs_info = NULL;
-	}
+	kfree(sb->s_fs_info);
+	sb->s_fs_info = NULL;
 	kill_litter_super(sb);
 }
 
@@ -484,20 +470,22 @@ static int __init hypfs_init(void)
 {
 	int rc;
 
-	if (MACHINE_IS_VM) {
-		if (hypfs_vm_init())
-			/* no diag 2fc, just exit */
-			return -ENODATA;
-	} else {
-		if (hypfs_diag_init()) {
-			rc = -ENODATA;
-			goto fail_diag;
-		}
+	hypfs_dbfs_dir = debugfs_create_dir("s390_hypfs", NULL);
+	if (IS_ERR(hypfs_dbfs_dir))
+		return PTR_ERR(hypfs_dbfs_dir);
+
+	if (hypfs_diag_init()) {
+		rc = -ENODATA;
+		goto fail_debugfs_remove;
+	}
+	if (hypfs_vm_init()) {
+		rc = -ENODATA;
+		goto fail_hypfs_diag_exit;
 	}
 	s390_kobj = kobject_create_and_add("s390", hypervisor_kobj);
 	if (!s390_kobj) {
 		rc = -ENOMEM;
-		goto fail_sysfs;
+		goto fail_hypfs_vm_exit;
 	}
 	rc = register_filesystem(&hypfs_type);
 	if (rc)
@@ -506,18 +494,22 @@ static int __init hypfs_init(void)
 
 fail_filesystem:
 	kobject_put(s390_kobj);
-fail_sysfs:
-	if (!MACHINE_IS_VM)
-		hypfs_diag_exit();
-fail_diag:
+fail_hypfs_vm_exit:
+	hypfs_vm_exit();
+fail_hypfs_diag_exit:
+	hypfs_diag_exit();
+fail_debugfs_remove:
+	debugfs_remove(hypfs_dbfs_dir);
+
 	pr_err("Initialization of hypfs failed with rc=%i\n", rc);
 	return rc;
 }
 
 static void __exit hypfs_exit(void)
 {
-	if (!MACHINE_IS_VM)
-		hypfs_diag_exit();
+	hypfs_diag_exit();
+	hypfs_vm_exit();
+	debugfs_remove(hypfs_dbfs_dir);
 	unregister_filesystem(&hypfs_type);
 	kobject_put(s390_kobj);
 }
diff --git a/arch/s390/include/asm/atomic.h b/arch/s390/include/asm/atomic.h
index 2a113d6a7df..76daea11718 100644
--- a/arch/s390/include/asm/atomic.h
+++ b/arch/s390/include/asm/atomic.h
@@ -15,11 +15,10 @@
 
 #include <linux/compiler.h>
 #include <linux/types.h>
+#include <asm/system.h>
 
 #define ATOMIC_INIT(i)  { (i) }
 
-#if __GNUC__ > 3 || (__GNUC__ == 3 && __GNUC_MINOR__ > 2)
-
 #define __CS_LOOP(ptr, op_val, op_string) ({				\
 	int old_val, new_val;						\
 	asm volatile(							\
@@ -35,26 +34,6 @@
 	new_val;							\
 })
 
-#else /* __GNUC__ */
-
-#define __CS_LOOP(ptr, op_val, op_string) ({				\
-	int old_val, new_val;						\
-	asm volatile(							\
-		"	l	%0,0(%3)\n"				\
-		"0:	lr	%1,%0\n"				\
-		op_string "	%1,%4\n"				\
-		"	cs	%0,%1,0(%3)\n"				\
-		"	jl	0b"					\
-		: "=&d" (old_val), "=&d" (new_val),			\
-		  "=m" (((atomic_t *)(ptr))->counter)			\
-		: "a" (ptr), "d" (op_val),				\
-		  "m" (((atomic_t *)(ptr))->counter)			\
-		: "cc", "memory");					\
-	new_val;							\
-})
-
-#endif /* __GNUC__ */
-
 static inline int atomic_read(const atomic_t *v)
 {
 	barrier();
@@ -101,19 +80,11 @@ static inline void atomic_set_mask(unsigned long mask, atomic_t *v)
 
 static inline int atomic_cmpxchg(atomic_t *v, int old, int new)
 {
-#if __GNUC__ > 3 || (__GNUC__ == 3 && __GNUC_MINOR__ > 2)
 	asm volatile(
 		"	cs	%0,%2,%1"
 		: "+d" (old), "=Q" (v->counter)
 		: "d" (new), "Q" (v->counter)
 		: "cc", "memory");
-#else /* __GNUC__ */
-	asm volatile(
-		"	cs	%0,%3,0(%2)"
-		: "+d" (old), "=m" (v->counter)
-		: "a" (v), "d" (new), "m" (v->counter)
-		: "cc", "memory");
-#endif /* __GNUC__ */
 	return old;
 }
 
@@ -140,8 +111,6 @@ static inline int atomic_add_unless(atomic_t *v, int a, int u)
 
 #ifdef CONFIG_64BIT
 
-#if __GNUC__ > 3 || (__GNUC__ == 3 && __GNUC_MINOR__ > 2)
-
 #define __CSG_LOOP(ptr, op_val, op_string) ({				\
 	long long old_val, new_val;					\
 	asm volatile(							\
@@ -157,26 +126,6 @@ static inline int atomic_add_unless(atomic_t *v, int a, int u)
 	new_val;							\
 })
 
-#else /* __GNUC__ */
-
-#define __CSG_LOOP(ptr, op_val, op_string) ({				\
-	long long old_val, new_val;					\
-	asm volatile(							\
-		"	lg	%0,0(%3)\n"				\
-		"0:	lgr	%1,%0\n"				\
-		op_string "	%1,%4\n"				\
-		"	csg	%0,%1,0(%3)\n"				\
-		"	jl	0b"					\
-		: "=&d" (old_val), "=&d" (new_val),			\
-		  "=m" (((atomic_t *)(ptr))->counter)			\
-		: "a" (ptr), "d" (op_val),				\
-		  "m" (((atomic_t *)(ptr))->counter)			\
-		: "cc", "memory");					\
-	new_val;							\
-})
-
-#endif /* __GNUC__ */
-
 static inline long long atomic64_read(const atomic64_t *v)
 {
 	barrier();
@@ -214,19 +163,11 @@ static inline void atomic64_set_mask(unsigned long mask, atomic64_t *v)
 static inline long long atomic64_cmpxchg(atomic64_t *v,
 					     long long old, long long new)
 {
-#if __GNUC__ > 3 || (__GNUC__ == 3 && __GNUC_MINOR__ > 2)
 	asm volatile(
 		"	csg	%0,%2,%1"
 		: "+d" (old), "=Q" (v->counter)
 		: "d" (new), "Q" (v->counter)
 		: "cc", "memory");
-#else /* __GNUC__ */
-	asm volatile(
-		"	csg	%0,%3,0(%2)"
-		: "+d" (old), "=m" (v->counter)
-		: "a" (v), "d" (new), "m" (v->counter)
-		: "cc", "memory");
-#endif /* __GNUC__ */
 	return old;
 }
 
@@ -243,10 +184,8 @@ static inline long long atomic64_read(const atomic64_t *v)
 	register_pair rp;
 
 	asm volatile(
-		"	lm	%0,%N0,0(%1)"
-		: "=&d" (rp)
-		: "a" (&v->counter), "m" (v->counter)
-		);
+		"	lm	%0,%N0,%1"
+		: "=&d" (rp) : "Q" (v->counter)	);
 	return rp.pair;
 }
 
@@ -255,10 +194,8 @@ static inline void atomic64_set(atomic64_t *v, long long i)
 	register_pair rp = {.pair = i};
 
 	asm volatile(
-		"	stm	%1,%N1,0(%2)"
-		: "=m" (v->counter)
-		: "d" (rp), "a" (&v->counter)
-		);
+		"	stm	%1,%N1,%0"
+		: "=Q" (v->counter) : "d" (rp) );
 }
 
 static inline long long atomic64_xchg(atomic64_t *v, long long new)
@@ -267,11 +204,11 @@ static inline long long atomic64_xchg(atomic64_t *v, long long new)
 	register_pair rp_old;
 
 	asm volatile(
-		"	lm	%0,%N0,0(%2)\n"
-		"0:	cds	%0,%3,0(%2)\n"
+		"	lm	%0,%N0,%1\n"
+		"0:	cds	%0,%2,%1\n"
 		"	jl	0b\n"
-		: "=&d" (rp_old), "+m" (v->counter)
-		: "a" (&v->counter), "d" (rp_new)
+		: "=&d" (rp_old), "=Q" (v->counter)
+		: "d" (rp_new), "Q" (v->counter)
 		: "cc");
 	return rp_old.pair;
 }
@@ -283,9 +220,9 @@ static inline long long atomic64_cmpxchg(atomic64_t *v,
 	register_pair rp_new = {.pair = new};
 
 	asm volatile(
-		"	cds	%0,%3,0(%2)"
-		: "+&d" (rp_old), "+m" (v->counter)
-		: "a" (&v->counter), "d" (rp_new)
+		"	cds	%0,%2,%1"
+		: "+&d" (rp_old), "=Q" (v->counter)
+		: "d" (rp_new), "Q" (v->counter)
 		: "cc");
 	return rp_old.pair;
 }
@@ -338,6 +275,7 @@ static inline void atomic64_clear_mask(unsigned long long mask, atomic64_t *v)
 static inline int atomic64_add_unless(atomic64_t *v, long long a, long long u)
 {
 	long long c, old;
+
 	c = atomic64_read(v);
 	for (;;) {
 		if (unlikely(c == u))
@@ -350,6 +288,23 @@ static inline int atomic64_add_unless(atomic64_t *v, long long a, long long u)
 	return c != u;
 }
 
+static inline long long atomic64_dec_if_positive(atomic64_t *v)
+{
+	long long c, old, dec;
+
+	c = atomic64_read(v);
+	for (;;) {
+		dec = c - 1;
+		if (unlikely(dec < 0))
+			break;
+		old = atomic64_cmpxchg((v), c, dec);
+		if (likely(old == c))
+			break;
+		c = old;
+	}
+	return dec;
+}
+
 #define atomic64_add(_i, _v)		atomic64_add_return(_i, _v)
 #define atomic64_add_negative(_i, _v)	(atomic64_add_return(_i, _v) < 0)
 #define atomic64_inc(_v)		atomic64_add_return(1, _v)
diff --git a/arch/s390/include/asm/bitops.h b/arch/s390/include/asm/bitops.h
index b30606f6d52..2e05972c508 100644
--- a/arch/s390/include/asm/bitops.h
+++ b/arch/s390/include/asm/bitops.h
@@ -71,8 +71,6 @@ extern const char _sb_findmap[];
 #define __BITOPS_AND		"nr"
 #define __BITOPS_XOR		"xr"
 
-#if __GNUC__ > 3 || (__GNUC__ == 3 && __GNUC_MINOR__ > 2)
-
 #define __BITOPS_LOOP(__old, __new, __addr, __val, __op_string)	\
 	asm volatile(						\
 		"	l	%0,%2\n"			\
@@ -85,22 +83,6 @@ extern const char _sb_findmap[];
 		: "d" (__val), "Q" (*(unsigned long *) __addr)	\
 		: "cc");
 
-#else /* __GNUC__ */
-
-#define __BITOPS_LOOP(__old, __new, __addr, __val, __op_string)	\
-	asm volatile(						\
-		"	l	%0,0(%4)\n"			\
-		"0:	lr	%1,%0\n"			\
-		__op_string "	%1,%3\n"			\
-		"	cs	%0,%1,0(%4)\n"			\
-		"	jl	0b"				\
-		: "=&d" (__old), "=&d" (__new),			\
-		  "=m" (*(unsigned long *) __addr)		\
-		: "d" (__val), "a" (__addr),			\
-		  "m" (*(unsigned long *) __addr) : "cc");
-
-#endif /* __GNUC__ */
-
 #else /* __s390x__ */
 
 #define __BITOPS_ALIGN		7
@@ -109,8 +91,6 @@ extern const char _sb_findmap[];
 #define __BITOPS_AND		"ngr"
 #define __BITOPS_XOR		"xgr"
 
-#if __GNUC__ > 3 || (__GNUC__ == 3 && __GNUC_MINOR__ > 2)
-
 #define __BITOPS_LOOP(__old, __new, __addr, __val, __op_string)	\
 	asm volatile(						\
 		"	lg	%0,%2\n"			\
@@ -123,23 +103,6 @@ extern const char _sb_findmap[];
 		: "d" (__val), "Q" (*(unsigned long *) __addr)	\
 		: "cc");
 
-#else /* __GNUC__ */
-
-#define __BITOPS_LOOP(__old, __new, __addr, __val, __op_string)	\
-	asm volatile(						\
-		"	lg	%0,0(%4)\n"			\
-		"0:	lgr	%1,%0\n"			\
-		__op_string "	%1,%3\n"			\
-		"	csg	%0,%1,0(%4)\n"			\
-		"	jl	0b"				\
-		: "=&d" (__old), "=&d" (__new),			\
-		  "=m" (*(unsigned long *) __addr)		\
-		: "d" (__val), "a" (__addr),			\
-		  "m" (*(unsigned long *) __addr) : "cc");
-
-
-#endif /* __GNUC__ */
-
 #endif /* __s390x__ */
 
 #define __BITOPS_WORDS(bits) (((bits)+__BITOPS_WORDSIZE-1)/__BITOPS_WORDSIZE)
@@ -261,9 +224,8 @@ static inline void __set_bit(unsigned long nr, volatile unsigned long *ptr)
 
 	addr = (unsigned long) ptr + ((nr ^ (__BITOPS_WORDSIZE - 8)) >> 3);
 	asm volatile(
-		"	oc	0(1,%1),0(%2)"
-		: "=m" (*(char *) addr) : "a" (addr),
-		  "a" (_oi_bitmap + (nr & 7)), "m" (*(char *) addr) : "cc" );
+		"	oc	%O0(1,%R0),%1"
+		: "=Q" (*(char *) addr) : "Q" (_oi_bitmap[nr & 7]) : "cc" );
 }
 
 static inline void 
@@ -290,9 +252,8 @@ __clear_bit(unsigned long nr, volatile unsigned long *ptr)
 
 	addr = (unsigned long) ptr + ((nr ^ (__BITOPS_WORDSIZE - 8)) >> 3);
 	asm volatile(
-		"	nc	0(1,%1),0(%2)"
-		: "=m" (*(char *) addr)	: "a" (addr),
-		  "a" (_ni_bitmap + (nr & 7)), "m" (*(char *) addr) : "cc");
+		"	nc	%O0(1,%R0),%1"
+		: "=Q" (*(char *) addr) : "Q" (_ni_bitmap[nr & 7]) : "cc" );
 }
 
 static inline void 
@@ -318,9 +279,8 @@ static inline void __change_bit(unsigned long nr, volatile unsigned long *ptr)
 
 	addr = (unsigned long) ptr + ((nr ^ (__BITOPS_WORDSIZE - 8)) >> 3);
 	asm volatile(
-		"	xc	0(1,%1),0(%2)"
-		:  "=m" (*(char *) addr) : "a" (addr),
-		   "a" (_oi_bitmap + (nr & 7)), "m" (*(char *) addr) : "cc" );
+		"	xc	%O0(1,%R0),%1"
+		: "=Q" (*(char *) addr) : "Q" (_oi_bitmap[nr & 7]) : "cc" );
 }
 
 static inline void 
@@ -349,10 +309,9 @@ test_and_set_bit_simple(unsigned long nr, volatile unsigned long *ptr)
 	addr = (unsigned long) ptr + ((nr ^ (__BITOPS_WORDSIZE - 8)) >> 3);
 	ch = *(unsigned char *) addr;
 	asm volatile(
-		"	oc	0(1,%1),0(%2)"
-		: "=m" (*(char *) addr)
-		: "a" (addr), "a" (_oi_bitmap + (nr & 7)),
-		  "m" (*(char *) addr) : "cc", "memory");
+		"	oc	%O0(1,%R0),%1"
+		: "=Q" (*(char *) addr)	: "Q" (_oi_bitmap[nr & 7])
+		: "cc", "memory");
 	return (ch >> (nr & 7)) & 1;
 }
 #define __test_and_set_bit(X,Y)		test_and_set_bit_simple(X,Y)
@@ -369,10 +328,9 @@ test_and_clear_bit_simple(unsigned long nr, volatile unsigned long *ptr)
 	addr = (unsigned long) ptr + ((nr ^ (__BITOPS_WORDSIZE - 8)) >> 3);
 	ch = *(unsigned char *) addr;
 	asm volatile(
-		"	nc	0(1,%1),0(%2)"
-		: "=m" (*(char *) addr)
-		: "a" (addr), "a" (_ni_bitmap + (nr & 7)),
-		  "m" (*(char *) addr) : "cc", "memory");
+		"	nc	%O0(1,%R0),%1"
+		: "=Q" (*(char *) addr)	: "Q" (_ni_bitmap[nr & 7])
+		: "cc", "memory");
 	return (ch >> (nr & 7)) & 1;
 }
 #define __test_and_clear_bit(X,Y)	test_and_clear_bit_simple(X,Y)
@@ -389,10 +347,9 @@ test_and_change_bit_simple(unsigned long nr, volatile unsigned long *ptr)
 	addr = (unsigned long) ptr + ((nr ^ (__BITOPS_WORDSIZE - 8)) >> 3);
 	ch = *(unsigned char *) addr;
 	asm volatile(
-		"	xc	0(1,%1),0(%2)"
-		: "=m" (*(char *) addr)
-		: "a" (addr), "a" (_oi_bitmap + (nr & 7)),
-		  "m" (*(char *) addr) : "cc", "memory");
+		"	xc	%O0(1,%R0),%1"
+		: "=Q" (*(char *) addr)	: "Q" (_oi_bitmap[nr & 7])
+		: "cc", "memory");
 	return (ch >> (nr & 7)) & 1;
 }
 #define __test_and_change_bit(X,Y)	test_and_change_bit_simple(X,Y)
@@ -591,11 +548,11 @@ static inline unsigned long __load_ulong_le(const unsigned long *p,
 	p = (unsigned long *)((unsigned long) p + offset);
 #ifndef __s390x__
 	asm volatile(
-		"	ic	%0,0(%1)\n"
-		"	icm	%0,2,1(%1)\n"
-		"	icm	%0,4,2(%1)\n"
-		"	icm	%0,8,3(%1)"
-		: "=&d" (word) : "a" (p), "m" (*p) : "cc");
+		"	ic	%0,%O1(%R1)\n"
+		"	icm	%0,2,%O1+1(%R1)\n"
+		"	icm	%0,4,%O1+2(%R1)\n"
+		"	icm	%0,8,%O1+3(%R1)"
+		: "=&d" (word) : "Q" (*p) : "cc");
 #else
 	asm volatile(
 		"	lrvg	%0,%1"
diff --git a/arch/s390/include/asm/bug.h b/arch/s390/include/asm/bug.h
index b1066b9fb5f..bf90d1fd97a 100644
--- a/arch/s390/include/asm/bug.h
+++ b/arch/s390/include/asm/bug.h
@@ -5,12 +5,6 @@
 
 #ifdef CONFIG_BUG
 
-#ifdef CONFIG_64BIT
-#define S390_LONG ".quad"
-#else
-#define S390_LONG ".long"
-#endif
-
 #ifdef CONFIG_DEBUG_BUGVERBOSE
 
 #define __EMIT_BUG(x) do {					\
@@ -21,7 +15,7 @@
 		"2:	.asciz	\""__FILE__"\"\n"		\
 		".previous\n"					\
 		".section __bug_table,\"a\"\n"			\
-		"3:\t"	S390_LONG "\t1b,2b\n"			\
+		"3:	.long	1b-3b,2b-3b\n"			\
 		"	.short	%0,%1\n"			\
 		"	.org	3b+%2\n"			\
 		".previous\n"					\
@@ -37,7 +31,7 @@
 		"0:	j	0b+2\n"			\
 		"1:\n"					\
 		".section __bug_table,\"a\"\n"		\
-		"2:\t"	S390_LONG "\t1b\n"		\
+		"2:	.long	1b-2b\n"		\
 		"	.short	%0\n"			\
 		"	.org	2b+%1\n"		\
 		".previous\n"				\
@@ -52,18 +46,18 @@
 	unreachable();					\
 } while (0)
 
-#define __WARN() do {					\
-	__EMIT_BUG(BUGFLAG_WARNING);			\
+#define __WARN_TAINT(taint) do {			\
+	__EMIT_BUG(BUGFLAG_TAINT(taint));		\
 } while (0)
 
 #define WARN_ON(x) ({					\
 	int __ret_warn_on = !!(x);			\
 	if (__builtin_constant_p(__ret_warn_on)) {	\
 		if (__ret_warn_on)			\
-			__EMIT_BUG(BUGFLAG_WARNING);	\
+			__WARN();			\
 	} else {					\
 		if (unlikely(__ret_warn_on))		\
-			__EMIT_BUG(BUGFLAG_WARNING);	\
+			__WARN();			\
 	}						\
 	unlikely(__ret_warn_on);			\
 })
diff --git a/arch/s390/include/asm/ccwdev.h b/arch/s390/include/asm/ccwdev.h
index f4bd346a52d..1c0030f9b89 100644
--- a/arch/s390/include/asm/ccwdev.h
+++ b/arch/s390/include/asm/ccwdev.h
@@ -91,6 +91,14 @@ struct ccw_device {
 	void (*handler) (struct ccw_device *, unsigned long, struct irb *);
 };
 
+/*
+ * Possible CIO actions triggered by the unit check handler.
+ */
+enum uc_todo {
+	UC_TODO_RETRY,
+	UC_TODO_RETRY_ON_NEW_PATH,
+	UC_TODO_STOP
+};
 
 /**
  * struct ccw driver - device driver for channel attached devices
@@ -107,6 +115,7 @@ struct ccw_device {
  * @freeze: callback for freezing during hibernation snapshotting
  * @thaw: undo work done in @freeze
  * @restore: callback for restoring after hibernation
+ * @uc_handler: callback for unit check handler
  * @driver: embedded device driver structure
  * @name: device driver name
  */
@@ -124,6 +133,7 @@ struct ccw_driver {
 	int (*freeze)(struct ccw_device *);
 	int (*thaw) (struct ccw_device *);
 	int (*restore)(struct ccw_device *);
+	enum uc_todo (*uc_handler) (struct ccw_device *, struct irb *);
 	struct device_driver driver;
 	char *name;
 };
diff --git a/arch/s390/include/asm/cio.h b/arch/s390/include/asm/cio.h
index e85679af54d..e34347d567a 100644
--- a/arch/s390/include/asm/cio.h
+++ b/arch/s390/include/asm/cio.h
@@ -20,7 +20,7 @@
 /**
  * struct ccw1 - channel command word
  * @cmd_code: command code
- * @flags: flags, like IDA adressing, etc.
+ * @flags: flags, like IDA addressing, etc.
  * @count: byte count
  * @cda: data address
  *
diff --git a/arch/s390/include/asm/compat.h b/arch/s390/include/asm/compat.h
index 01a08020bc0..104f2007f09 100644
--- a/arch/s390/include/asm/compat.h
+++ b/arch/s390/include/asm/compat.h
@@ -35,7 +35,8 @@
 
 extern long psw32_user_bits;
 
-#define COMPAT_USER_HZ	100
+#define COMPAT_USER_HZ		100
+#define COMPAT_UTS_MACHINE	"s390\0\0\0\0"
 
 typedef u32		compat_size_t;
 typedef s32		compat_ssize_t;
diff --git a/arch/s390/include/asm/cputime.h b/arch/s390/include/asm/cputime.h
index 258ba88b7b5..8b1a52a137c 100644
--- a/arch/s390/include/asm/cputime.h
+++ b/arch/s390/include/asm/cputime.h
@@ -188,15 +188,16 @@ struct s390_idle_data {
 
 DECLARE_PER_CPU(struct s390_idle_data, s390_idle);
 
-void vtime_start_cpu(void);
+void vtime_start_cpu(__u64 int_clock, __u64 enter_timer);
 cputime64_t s390_get_idle_time(int cpu);
 
 #define arch_idle_time(cpu) s390_get_idle_time(cpu)
 
-static inline void s390_idle_check(void)
+static inline void s390_idle_check(struct pt_regs *regs, __u64 int_clock,
+				   __u64 enter_timer)
 {
-	if ((&__get_cpu_var(s390_idle))->idle_enter != 0ULL)
-		vtime_start_cpu();
+	if (regs->psw.mask & PSW_MASK_WAIT)
+		vtime_start_cpu(int_clock, enter_timer);
 }
 
 static inline int s390_nohz_delay(int cpu)
diff --git a/arch/s390/include/asm/crw.h b/arch/s390/include/asm/crw.h
index 2185a6d619d..749a97e61be 100644
--- a/arch/s390/include/asm/crw.h
+++ b/arch/s390/include/asm/crw.h
@@ -32,6 +32,7 @@ typedef void (*crw_handler_t)(struct crw *, struct crw *, int);
 extern int crw_register_handler(int rsc, crw_handler_t handler);
 extern void crw_unregister_handler(int rsc);
 extern void crw_handle_channel_report(void);
+void crw_wait_for_channel_report(void);
 
 #define NR_RSCS 16
 
diff --git a/arch/s390/include/asm/etr.h b/arch/s390/include/asm/etr.h
index 80ef58c6197..538e1b36a72 100644
--- a/arch/s390/include/asm/etr.h
+++ b/arch/s390/include/asm/etr.h
@@ -145,11 +145,11 @@ static inline int etr_setr(struct etr_eacr *ctrl)
 	int rc = -ENOSYS;
 
 	asm volatile(
-		"	.insn	s,0xb2160000,0(%2)\n"
+		"	.insn	s,0xb2160000,%1\n"
 		"0:	la	%0,0\n"
 		"1:\n"
 		EX_TABLE(0b,1b)
-		: "+d" (rc) : "m" (*ctrl), "a" (ctrl));
+		: "+d" (rc) : "Q" (*ctrl));
 	return rc;
 }
 
@@ -159,11 +159,11 @@ static inline int etr_stetr(struct etr_aib *aib)
 	int rc = -ENOSYS;
 
 	asm volatile(
-		"	.insn	s,0xb2170000,0(%2)\n"
+		"	.insn	s,0xb2170000,%1\n"
 		"0:	la	%0,0\n"
 		"1:\n"
 		EX_TABLE(0b,1b)
-		: "+d" (rc) : "m" (*aib), "a" (aib));
+		: "+d" (rc) : "Q" (*aib));
 	return rc;
 }
 
@@ -174,11 +174,11 @@ static inline int etr_steai(struct etr_aib *aib, unsigned int func)
 	int rc = -ENOSYS;
 
 	asm volatile(
-		"	.insn	s,0xb2b30000,0(%2)\n"
+		"	.insn	s,0xb2b30000,%1\n"
 		"0:	la	%0,0\n"
 		"1:\n"
 		EX_TABLE(0b,1b)
-		: "+d" (rc) : "m" (*aib), "a" (aib), "d" (reg0));
+		: "+d" (rc) : "Q" (*aib), "d" (reg0));
 	return rc;
 }
 
diff --git a/arch/s390/include/asm/irqflags.h b/arch/s390/include/asm/irqflags.h
index c2fb432f576..15b3ac25389 100644
--- a/arch/s390/include/asm/irqflags.h
+++ b/arch/s390/include/asm/irqflags.h
@@ -8,8 +8,6 @@
 
 #include <linux/types.h>
 
-#if __GNUC__ > 3 || (__GNUC__ == 3 && __GNUC_MINOR__ > 2)
-
 /* store then or system mask. */
 #define __raw_local_irq_stosm(__or)					\
 ({									\
@@ -36,40 +34,6 @@
 	asm volatile("ssm   %0" : : "Q" (__mask) : "memory");		\
 })
 
-#else /* __GNUC__ */
-
-/* store then or system mask. */
-#define __raw_local_irq_stosm(__or)					\
-({									\
-	unsigned long __mask;						\
-	asm volatile(							\
-		"	stosm	0(%1),%2"				\
-		: "=m" (__mask)						\
-		: "a" (&__mask), "i" (__or) : "memory");		\
-	__mask;								\
-})
-
-/* store then and system mask. */
-#define __raw_local_irq_stnsm(__and)					\
-({									\
-	unsigned long __mask;						\
-	asm volatile(							\
-		"	stnsm	0(%1),%2"				\
-		: "=m" (__mask)						\
-		: "a" (&__mask), "i" (__and) : "memory");		\
-	__mask;								\
-})
-
-/* set system mask. */
-#define __raw_local_irq_ssm(__mask)					\
-({									\
-	asm volatile(							\
-		"	ssm	0(%0)"					\
-		: : "a" (&__mask), "m" (__mask) : "memory");		\
-})
-
-#endif /* __GNUC__ */
-
 /* interrupt control.. */
 static inline unsigned long raw_local_irq_enable(void)
 {
diff --git a/arch/s390/include/asm/lowcore.h b/arch/s390/include/asm/lowcore.h
index f2ef4b619ce..0f97ef2d92a 100644
--- a/arch/s390/include/asm/lowcore.h
+++ b/arch/s390/include/asm/lowcore.h
@@ -1,141 +1,16 @@
 /*
- *  include/asm-s390/lowcore.h
- *
- *  S390 version
- *    Copyright (C) 1999,2000 IBM Deutschland Entwicklung GmbH, IBM Corporation
- *    Author(s): Hartmut Penner (hp@de.ibm.com),
- *               Martin Schwidefsky (schwidefsky@de.ibm.com),
- *               Denis Joseph Barrow (djbarrow@de.ibm.com,barrow_dj@yahoo.com)
+ *    Copyright IBM Corp. 1999,2010
+ *    Author(s): Hartmut Penner <hp@de.ibm.com>,
+ *		 Martin Schwidefsky <schwidefsky@de.ibm.com>,
+ *		 Denis Joseph Barrow,
  */
 
 #ifndef _ASM_S390_LOWCORE_H
 #define _ASM_S390_LOWCORE_H
 
-#define __LC_IPL_PARMBLOCK_PTR		0x0014
-#define __LC_EXT_PARAMS			0x0080
-#define __LC_CPU_ADDRESS		0x0084
-#define __LC_EXT_INT_CODE		0x0086
-
-#define __LC_SVC_ILC			0x0088
-#define __LC_SVC_INT_CODE		0x008a
-#define __LC_PGM_ILC			0x008c
-#define __LC_PGM_INT_CODE		0x008e
-
-#define __LC_PER_ATMID			0x0096
-#define __LC_PER_ADDRESS		0x0098
-#define __LC_PER_ACCESS_ID		0x00a1
-#define __LC_AR_MODE_ID			0x00a3
-
-#define __LC_SUBCHANNEL_ID		0x00b8
-#define __LC_SUBCHANNEL_NR		0x00ba
-#define __LC_IO_INT_PARM		0x00bc
-#define __LC_IO_INT_WORD		0x00c0
-#define __LC_STFL_FAC_LIST		0x00c8
-#define __LC_MCCK_CODE			0x00e8
-
-#define __LC_DUMP_REIPL			0x0e00
-
-#ifndef __s390x__
-#define __LC_EXT_OLD_PSW		0x0018
-#define __LC_SVC_OLD_PSW		0x0020
-#define __LC_PGM_OLD_PSW		0x0028
-#define __LC_MCK_OLD_PSW		0x0030
-#define __LC_IO_OLD_PSW			0x0038
-#define __LC_EXT_NEW_PSW		0x0058
-#define __LC_SVC_NEW_PSW		0x0060
-#define __LC_PGM_NEW_PSW		0x0068
-#define __LC_MCK_NEW_PSW		0x0070
-#define __LC_IO_NEW_PSW			0x0078
-#define __LC_SAVE_AREA			0x0200
-#define __LC_RETURN_PSW			0x0240
-#define __LC_RETURN_MCCK_PSW		0x0248
-#define __LC_SYNC_ENTER_TIMER		0x0250
-#define __LC_ASYNC_ENTER_TIMER		0x0258
-#define __LC_EXIT_TIMER			0x0260
-#define __LC_USER_TIMER			0x0268
-#define __LC_SYSTEM_TIMER		0x0270
-#define __LC_STEAL_TIMER		0x0278
-#define __LC_LAST_UPDATE_TIMER		0x0280
-#define __LC_LAST_UPDATE_CLOCK		0x0288
-#define __LC_CURRENT			0x0290
-#define __LC_THREAD_INFO		0x0294
-#define __LC_KERNEL_STACK		0x0298
-#define __LC_ASYNC_STACK		0x029c
-#define __LC_PANIC_STACK		0x02a0
-#define __LC_KERNEL_ASCE		0x02a4
-#define __LC_USER_ASCE			0x02a8
-#define __LC_USER_EXEC_ASCE		0x02ac
-#define __LC_CPUID			0x02b0
-#define __LC_INT_CLOCK			0x02c8
-#define __LC_MACHINE_FLAGS		0x02d8
-#define __LC_FTRACE_FUNC		0x02dc
-#define __LC_IRB			0x0300
-#define __LC_PFAULT_INTPARM		0x0080
-#define __LC_CPU_TIMER_SAVE_AREA	0x00d8
-#define __LC_CLOCK_COMP_SAVE_AREA	0x00e0
-#define __LC_PSW_SAVE_AREA		0x0100
-#define __LC_PREFIX_SAVE_AREA		0x0108
-#define __LC_AREGS_SAVE_AREA		0x0120
-#define __LC_FPREGS_SAVE_AREA		0x0160
-#define __LC_GPREGS_SAVE_AREA		0x0180
-#define __LC_CREGS_SAVE_AREA		0x01c0
-#else /* __s390x__ */
-#define __LC_LAST_BREAK			0x0110
-#define __LC_EXT_OLD_PSW		0x0130
-#define __LC_SVC_OLD_PSW		0x0140
-#define __LC_PGM_OLD_PSW		0x0150
-#define __LC_MCK_OLD_PSW		0x0160
-#define __LC_IO_OLD_PSW			0x0170
-#define __LC_RESTART_PSW		0x01a0
-#define __LC_EXT_NEW_PSW		0x01b0
-#define __LC_SVC_NEW_PSW		0x01c0
-#define __LC_PGM_NEW_PSW		0x01d0
-#define __LC_MCK_NEW_PSW		0x01e0
-#define __LC_IO_NEW_PSW			0x01f0
-#define __LC_SAVE_AREA			0x0200
-#define __LC_RETURN_PSW			0x0280
-#define __LC_RETURN_MCCK_PSW		0x0290
-#define __LC_SYNC_ENTER_TIMER		0x02a0
-#define __LC_ASYNC_ENTER_TIMER		0x02a8
-#define __LC_EXIT_TIMER			0x02b0
-#define __LC_USER_TIMER			0x02b8
-#define __LC_SYSTEM_TIMER		0x02c0
-#define __LC_STEAL_TIMER		0x02c8
-#define __LC_LAST_UPDATE_TIMER		0x02d0
-#define __LC_LAST_UPDATE_CLOCK		0x02d8
-#define __LC_CURRENT			0x02e0
-#define __LC_THREAD_INFO		0x02e8
-#define __LC_KERNEL_STACK		0x02f0
-#define __LC_ASYNC_STACK		0x02f8
-#define __LC_PANIC_STACK		0x0300
-#define __LC_KERNEL_ASCE		0x0308
-#define __LC_USER_ASCE			0x0310
-#define __LC_USER_EXEC_ASCE		0x0318
-#define __LC_CPUID			0x0320
-#define __LC_INT_CLOCK			0x0340
-#define __LC_VDSO_PER_CPU		0x0350
-#define __LC_MACHINE_FLAGS		0x0358
-#define __LC_FTRACE_FUNC		0x0360
-#define __LC_IRB			0x0380
-#define __LC_PASTE			0x03c0
-#define __LC_PFAULT_INTPARM		0x11b8
-#define __LC_FPREGS_SAVE_AREA		0x1200
-#define __LC_GPREGS_SAVE_AREA		0x1280
-#define __LC_PSW_SAVE_AREA		0x1300
-#define __LC_PREFIX_SAVE_AREA		0x1318
-#define __LC_FP_CREG_SAVE_AREA		0x131c
-#define __LC_TODREG_SAVE_AREA		0x1324
-#define __LC_CPU_TIMER_SAVE_AREA	0x1328
-#define __LC_CLOCK_COMP_SAVE_AREA	0x1331
-#define __LC_AREGS_SAVE_AREA		0x1340
-#define __LC_CREGS_SAVE_AREA		0x1380
-#endif /* __s390x__ */
-
-#ifndef __ASSEMBLY__
-
-#include <asm/cpu.h>
-#include <asm/ptrace.h>
 #include <linux/types.h>
+#include <asm/ptrace.h>
+#include <asm/cpu.h>
 
 void restart_int_handler(void);
 void ext_int_handler(void);
@@ -144,7 +19,12 @@ void pgm_check_handler(void);
 void mcck_int_handler(void);
 void io_int_handler(void);
 
-struct save_area_s390 {
+#ifdef CONFIG_32BIT
+
+#define LC_ORDER 0
+#define LC_PAGES 1
+
+struct save_area {
 	u32	ext_save;
 	u64	timer;
 	u64	clk_cmp;
@@ -156,54 +36,13 @@ struct save_area_s390 {
 	u64	fp_regs[4];
 	u32	gp_regs[16];
 	u32	ctrl_regs[16];
-}  __attribute__((packed));
-
-struct save_area_s390x {
-	u64	fp_regs[16];
-	u64	gp_regs[16];
-	u8	psw[16];
-	u8	pad1[8];
-	u32	pref_reg;
-	u32	fp_ctrl_reg;
-	u8	pad2[4];
-	u32	tod_reg;
-	u64	timer;
-	u64	clk_cmp;
-	u8	pad3[8];
-	u32	acc_regs[16];
-	u64	ctrl_regs[16];
-}  __attribute__((packed));
-
-union save_area {
-	struct save_area_s390	s390;
-	struct save_area_s390x	s390x;
-};
-
-#define SAVE_AREA_BASE_S390	0xd4
-#define SAVE_AREA_BASE_S390X	0x1200
-
-#ifndef __s390x__
-#define SAVE_AREA_SIZE sizeof(struct save_area_s390)
-#define SAVE_AREA_BASE SAVE_AREA_BASE_S390
-#else
-#define SAVE_AREA_SIZE sizeof(struct save_area_s390x)
-#define SAVE_AREA_BASE SAVE_AREA_BASE_S390X
-#endif
-
-#ifndef __s390x__
-#define LC_ORDER 0
-#else
-#define LC_ORDER 1
-#endif
-
-#define LC_PAGES (1UL << LC_ORDER)
+} __packed;
 
-struct _lowcore
-{
-#ifndef __s390x__
-	/* 0x0000 - 0x01ff: defined by architecture */
+struct _lowcore {
 	psw_t	restart_psw;			/* 0x0000 */
-	__u32	ccw2[4];			/* 0x0008 */
+	psw_t	restart_old_psw;		/* 0x0008 */
+	__u8	pad_0x0010[0x0014-0x0010];	/* 0x0010 */
+	__u32	ipl_parmblock_ptr;		/* 0x0014 */
 	psw_t	external_old_psw;		/* 0x0018 */
 	psw_t	svc_old_psw;			/* 0x0020 */
 	psw_t	program_old_psw;		/* 0x0028 */
@@ -229,7 +68,9 @@ struct _lowcore
 	__u32	monitor_code;			/* 0x009c */
 	__u8	exc_access_id;			/* 0x00a0 */
 	__u8	per_access_id;			/* 0x00a1 */
-	__u8	pad_0x00a2[0x00b8-0x00a2];	/* 0x00a2 */
+	__u8	op_access_id;			/* 0x00a2 */
+	__u8	ar_access_id;			/* 0x00a3 */
+	__u8	pad_0x00a4[0x00b8-0x00a4];	/* 0x00a4 */
 	__u16	subchannel_id;			/* 0x00b8 */
 	__u16	subchannel_nr;			/* 0x00ba */
 	__u32	io_int_parm;			/* 0x00bc */
@@ -245,8 +86,9 @@ struct _lowcore
 	__u32	external_damage_code;		/* 0x00f4 */
 	__u32	failing_storage_address;	/* 0x00f8 */
 	__u8	pad_0x00fc[0x0100-0x00fc];	/* 0x00fc */
-	__u32	st_status_fixed_logout[4];	/* 0x0100 */
-	__u8	pad_0x0110[0x0120-0x0110];	/* 0x0110 */
+	psw_t	psw_save_area;			/* 0x0100 */
+	__u32	prefixreg_save_area;		/* 0x0108 */
+	__u8	pad_0x010c[0x0120-0x010c];	/* 0x010c */
 
 	/* CPU register save area: defined by architecture */
 	__u32	access_regs_save_area[16];	/* 0x0120 */
@@ -262,43 +104,44 @@ struct _lowcore
 	/* CPU time accounting values */
 	__u64	sync_enter_timer;		/* 0x0250 */
 	__u64	async_enter_timer;		/* 0x0258 */
-	__u64	exit_timer;			/* 0x0260 */
-	__u64	user_timer;			/* 0x0268 */
-	__u64	system_timer;			/* 0x0270 */
-	__u64	steal_timer;			/* 0x0278 */
-	__u64	last_update_timer;		/* 0x0280 */
-	__u64	last_update_clock;		/* 0x0288 */
+	__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 */
 
 	/* Current process. */
-	__u32	current_task;			/* 0x0290 */
-	__u32	thread_info;			/* 0x0294 */
-	__u32	kernel_stack;			/* 0x0298 */
+	__u32	current_task;			/* 0x0298 */
+	__u32	thread_info;			/* 0x029c */
+	__u32	kernel_stack;			/* 0x02a0 */
 
 	/* Interrupt and panic stack. */
-	__u32	async_stack;			/* 0x029c */
-	__u32	panic_stack;			/* 0x02a0 */
+	__u32	async_stack;			/* 0x02a4 */
+	__u32	panic_stack;			/* 0x02a8 */
 
 	/* Address space pointer. */
-	__u32	kernel_asce;			/* 0x02a4 */
-	__u32	user_asce;			/* 0x02a8 */
-	__u32	user_exec_asce;			/* 0x02ac */
+	__u32	kernel_asce;			/* 0x02ac */
+	__u32	user_asce;			/* 0x02b0 */
+	__u32	user_exec_asce;			/* 0x02b4 */
 
 	/* SMP info area */
-	struct cpuid cpu_id;			/* 0x02b0 */
 	__u32	cpu_nr;				/* 0x02b8 */
 	__u32	softirq_pending;		/* 0x02bc */
 	__u32	percpu_offset;			/* 0x02c0 */
 	__u32	ext_call_fast;			/* 0x02c4 */
 	__u64	int_clock;			/* 0x02c8 */
-	__u64	clock_comparator;		/* 0x02d0 */
-	__u32	machine_flags;			/* 0x02d8 */
-	__u32	ftrace_func;			/* 0x02dc */
-	__u8	pad_0x02f0[0x0300-0x02f0];	/* 0x02f0 */
+	__u64	mcck_clock;			/* 0x02d0 */
+	__u64	clock_comparator;		/* 0x02d8 */
+	__u32	machine_flags;			/* 0x02e0 */
+	__u32	ftrace_func;			/* 0x02e4 */
+	__u8	pad_0x02e8[0x0300-0x02e8];	/* 0x02e8 */
 
 	/* Interrupt response block */
 	__u8	irb[64];			/* 0x0300 */
 
-	__u8	pad_0x0400[0x0e00-0x0400];	/* 0x0400 */
+	__u8	pad_0x0340[0x0e00-0x0340];	/* 0x0340 */
 
 	/*
 	 * 0xe00 contains the address of the IPL Parameter Information
@@ -310,10 +153,32 @@ struct _lowcore
 
 	/* Align to the top 1k of prefix area */
 	__u8	pad_0x0e08[0x1000-0x0e08];	/* 0x0e08 */
-#else /* !__s390x__ */
-	/* 0x0000 - 0x01ff: defined by architecture */
-	__u32	ccw1[2];			/* 0x0000 */
-	__u32	ccw2[4];			/* 0x0008 */
+} __packed;
+
+#else /* CONFIG_32BIT */
+
+#define LC_ORDER 1
+#define LC_PAGES 2
+
+struct save_area {
+	u64	fp_regs[16];
+	u64	gp_regs[16];
+	u8	psw[16];
+	u8	pad1[8];
+	u32	pref_reg;
+	u32	fp_ctrl_reg;
+	u8	pad2[4];
+	u32	tod_reg;
+	u64	timer;
+	u64	clk_cmp;
+	u8	pad3[8];
+	u32	acc_regs[16];
+	u64	ctrl_regs[16];
+} __packed;
+
+struct _lowcore {
+	__u8	pad_0x0000[0x0014-0x0000];	/* 0x0000 */
+	__u32	ipl_parmblock_ptr;		/* 0x0014 */
 	__u8	pad_0x0018[0x0080-0x0018];	/* 0x0018 */
 	__u32	ext_params;			/* 0x0080 */
 	__u16	cpu_addr;			/* 0x0084 */
@@ -325,14 +190,14 @@ struct _lowcore
 	__u32	data_exc_code;			/* 0x0090 */
 	__u16	mon_class_num;			/* 0x0094 */
 	__u16	per_perc_atmid;			/* 0x0096 */
-	addr_t	per_address;			/* 0x0098 */
+	__u64	per_address;			/* 0x0098 */
 	__u8	exc_access_id;			/* 0x00a0 */
 	__u8	per_access_id;			/* 0x00a1 */
 	__u8	op_access_id;			/* 0x00a2 */
 	__u8	ar_access_id;			/* 0x00a3 */
 	__u8	pad_0x00a4[0x00a8-0x00a4];	/* 0x00a4 */
-	addr_t	trans_exc_code;			/* 0x00a8 */
-	addr_t	monitor_code;			/* 0x00b0 */
+	__u64	trans_exc_code;			/* 0x00a8 */
+	__u64	monitor_code;			/* 0x00b0 */
 	__u16	subchannel_id;			/* 0x00b8 */
 	__u16	subchannel_nr;			/* 0x00ba */
 	__u32	io_int_parm;			/* 0x00bc */
@@ -343,8 +208,10 @@ struct _lowcore
 	__u32	mcck_interruption_code[2];	/* 0x00e8 */
 	__u8	pad_0x00f0[0x00f4-0x00f0];	/* 0x00f0 */
 	__u32	external_damage_code;		/* 0x00f4 */
-	addr_t	failing_storage_address;	/* 0x00f8 */
-	__u8	pad_0x0100[0x0120-0x0100];	/* 0x0100 */
+	__u64	failing_storage_address;	/* 0x00f8 */
+	__u8	pad_0x0100[0x0110-0x0100];	/* 0x0100 */
+	__u64	breaking_event_addr;		/* 0x0110 */
+	__u8	pad_0x0118[0x0120-0x0118];	/* 0x0118 */
 	psw_t	restart_old_psw;		/* 0x0120 */
 	psw_t	external_old_psw;		/* 0x0130 */
 	psw_t	svc_old_psw;			/* 0x0140 */
@@ -367,39 +234,41 @@ struct _lowcore
 	/* CPU accounting and timing values. */
 	__u64	sync_enter_timer;		/* 0x02a0 */
 	__u64	async_enter_timer;		/* 0x02a8 */
-	__u64	exit_timer;			/* 0x02b0 */
-	__u64	user_timer;			/* 0x02b8 */
-	__u64	system_timer;			/* 0x02c0 */
-	__u64	steal_timer;			/* 0x02c8 */
-	__u64	last_update_timer;		/* 0x02d0 */
-	__u64	last_update_clock;		/* 0x02d8 */
+	__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 */
 
 	/* Current process. */
-	__u64	current_task;			/* 0x02e0 */
-	__u64	thread_info;			/* 0x02e8 */
-	__u64	kernel_stack;			/* 0x02f0 */
+	__u64	current_task;			/* 0x02e8 */
+	__u64	thread_info;			/* 0x02f0 */
+	__u64	kernel_stack;			/* 0x02f8 */
 
 	/* Interrupt and panic stack. */
-	__u64	async_stack;			/* 0x02f8 */
-	__u64	panic_stack;			/* 0x0300 */
+	__u64	async_stack;			/* 0x0300 */
+	__u64	panic_stack;			/* 0x0308 */
 
 	/* Address space pointer. */
-	__u64	kernel_asce;			/* 0x0308 */
-	__u64	user_asce;			/* 0x0310 */
-	__u64	user_exec_asce;			/* 0x0318 */
+	__u64	kernel_asce;			/* 0x0310 */
+	__u64	user_asce;			/* 0x0318 */
+	__u64	user_exec_asce;			/* 0x0320 */
 
 	/* SMP info area */
-	struct cpuid cpu_id;			/* 0x0320 */
 	__u32	cpu_nr;				/* 0x0328 */
 	__u32	softirq_pending;		/* 0x032c */
 	__u64	percpu_offset;			/* 0x0330 */
 	__u64	ext_call_fast;			/* 0x0338 */
 	__u64	int_clock;			/* 0x0340 */
-	__u64	clock_comparator;		/* 0x0348 */
-	__u64	vdso_per_cpu_data;		/* 0x0350 */
-	__u64	machine_flags;			/* 0x0358 */
-	__u64	ftrace_func;			/* 0x0360 */
-	__u8	pad_0x0368[0x0380-0x0368];	/* 0x0368 */
+	__u64	mcck_clock;			/* 0x0348 */
+	__u64	clock_comparator;		/* 0x0350 */
+	__u64	vdso_per_cpu_data;		/* 0x0358 */
+	__u64	machine_flags;			/* 0x0360 */
+	__u64	ftrace_func;			/* 0x0368 */
+	__u64	sie_hook;			/* 0x0370 */
+	__u64	cmf_hpp;			/* 0x0378 */
 
 	/* Interrupt response block. */
 	__u8	irb[64];			/* 0x0380 */
@@ -425,7 +294,7 @@ struct _lowcore
 	/* CPU register save area: defined by architecture */
 	__u64	floating_pt_save_area[16];	/* 0x1200 */
 	__u64	gpregs_save_area[16];		/* 0x1280 */
-	__u32	st_status_fixed_logout[4];	/* 0x1300 */
+	psw_t	psw_save_area;			/* 0x1300 */
 	__u8	pad_0x1310[0x1318-0x1310];	/* 0x1310 */
 	__u32	prefixreg_save_area;		/* 0x1318 */
 	__u32	fpt_creg_save_area;		/* 0x131c */
@@ -439,10 +308,12 @@ struct _lowcore
 
 	/* align to the top of the prefix area */
 	__u8	pad_0x1400[0x2000-0x1400];	/* 0x1400 */
-#endif /* !__s390x__ */
-} __attribute__((packed)); /* End structure*/
+} __packed;
+
+#endif /* CONFIG_32BIT */
 
 #define S390_lowcore (*((struct _lowcore *) 0))
+
 extern struct _lowcore *lowcore_ptr[];
 
 static inline void set_prefix(__u32 address)
@@ -458,6 +329,4 @@ static inline __u32 store_prefix(void)
 	return address;
 }
 
-#endif
-
-#endif
+#endif /* _ASM_S390_LOWCORE_H */
diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h
index 5e9daf5d7f2..af650fb4720 100644
--- a/arch/s390/include/asm/page.h
+++ b/arch/s390/include/asm/page.h
@@ -107,9 +107,6 @@ typedef pte_t *pgtable_t;
 #define __pgd(x)        ((pgd_t) { (x) } )
 #define __pgprot(x)     ((pgprot_t) { (x) } )
 
-/* default storage key used for all pages */
-extern unsigned int default_storage_key;
-
 static inline void
 page_set_storage_key(unsigned long addr, unsigned int skey)
 {
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index e2fa79cf061..89a504c3f12 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -43,7 +43,7 @@ extern void vmem_map_init(void);
  * The S390 doesn't have any external MMU info: the kernel page
  * tables contain all the necessary information.
  */
-#define update_mmu_cache(vma, address, pte)     do { } while (0)
+#define update_mmu_cache(vma, address, ptep)     do { } while (0)
 
 /*
  * ZERO_PAGE is a global shared page that is always zero: used
@@ -105,7 +105,7 @@ extern char empty_zero_page[PAGE_SIZE];
 #ifndef __ASSEMBLY__
 /*
  * The vmalloc area will always be on the topmost area of the kernel
- * mapping. We reserve 96MB (31bit) / 1GB (64bit) for vmalloc,
+ * mapping. We reserve 96MB (31bit) / 128GB (64bit) for vmalloc,
  * which should be enough for any sane case.
  * By putting vmalloc at the top, we maximise the gap between physical
  * memory and vmalloc to catch misplaced memory accesses. As a side
@@ -120,8 +120,8 @@ extern unsigned long VMALLOC_START;
 #define VMALLOC_END	0x7e000000UL
 #define VMEM_MAP_END	0x80000000UL
 #else /* __s390x__ */
-#define VMALLOC_SIZE	(1UL << 30)
-#define VMALLOC_END	0x3e040000000UL
+#define VMALLOC_SIZE	(128UL << 30)
+#define VMALLOC_END	0x3e000000000UL
 #define VMEM_MAP_END	0x40000000000UL
 #endif /* __s390x__ */
 
diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index b4271545831..73e259834e1 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -28,7 +28,7 @@
 
 static inline void get_cpu_id(struct cpuid *ptr)
 {
-	asm volatile("stidp 0(%1)" : "=m" (*ptr) : "a" (ptr));
+	asm volatile("stidp %0" : "=Q" (*ptr));
 }
 
 extern void s390_adjust_jiffies(void);
@@ -184,9 +184,9 @@ static inline void psw_set_key(unsigned int key)
 static inline void __load_psw(psw_t psw)
 {
 #ifndef __s390x__
-	asm volatile("lpsw  0(%0)" : : "a" (&psw), "m" (psw) : "cc");
+	asm volatile("lpsw  %0" : : "Q" (psw) : "cc");
 #else
-	asm volatile("lpswe 0(%0)" : : "a" (&psw), "m" (psw) : "cc");
+	asm volatile("lpswe %0" : : "Q" (psw) : "cc");
 #endif
 }
 
@@ -206,17 +206,17 @@ static inline void __load_psw_mask (unsigned long mask)
 	asm volatile(
 		"	basr	%0,0\n"
 		"0:	ahi	%0,1f-0b\n"
-		"	st	%0,4(%1)\n"
-		"	lpsw	0(%1)\n"
+		"	st	%0,%O1+4(%R1)\n"
+		"	lpsw	%1\n"
 		"1:"
-		: "=&d" (addr) : "a" (&psw), "m" (psw) : "memory", "cc");
+		: "=&d" (addr), "=Q" (psw) : "Q" (psw) : "memory", "cc");
 #else /* __s390x__ */
 	asm volatile(
 		"	larl	%0,1f\n"
-		"	stg	%0,8(%1)\n"
-		"	lpswe	0(%1)\n"
+		"	stg	%0,%O1+8(%R1)\n"
+		"	lpswe	%1\n"
 		"1:"
-		: "=&d" (addr) : "a" (&psw), "m" (psw) : "memory", "cc");
+		: "=&d" (addr), "=Q" (psw) : "Q" (psw) : "memory", "cc");
 #endif /* __s390x__ */
 }
  
diff --git a/arch/s390/include/asm/ptrace.h b/arch/s390/include/asm/ptrace.h
index 95dcf183a28..e2c218dc68a 100644
--- a/arch/s390/include/asm/ptrace.h
+++ b/arch/s390/include/asm/ptrace.h
@@ -328,8 +328,8 @@ struct pt_regs
 	psw_t psw;
 	unsigned long gprs[NUM_GPRS];
 	unsigned long orig_gpr2;
-	unsigned short svcnr;
 	unsigned short ilc;
+	unsigned short svcnr;
 };
 #endif
 
@@ -436,6 +436,7 @@ typedef struct
 #define PTRACE_PEEKDATA_AREA	      0x5003
 #define PTRACE_POKETEXT_AREA	      0x5004
 #define PTRACE_POKEDATA_AREA 	      0x5005
+#define PTRACE_GET_LAST_BREAK	      0x5006
 
 /*
  * PT_PROT definition is loosely based on hppa bsd definition in
@@ -489,16 +490,24 @@ struct user_regs_struct
  * These are defined as per linux/ptrace.h, which see.
  */
 #define arch_has_single_step()	(1)
-struct task_struct;
-extern void user_enable_single_step(struct task_struct *);
-extern void user_disable_single_step(struct task_struct *);
+extern void show_regs(struct pt_regs * regs);
 
 #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)
-extern void show_regs(struct pt_regs * regs);
+
+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);
+unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, unsigned int n);
+
+static inline unsigned long kernel_stack_pointer(struct pt_regs *regs)
+{
+	return regs->gprs[15] & PSW_ADDR_INSN;
+}
+
 #endif /* __KERNEL__ */
 #endif /* __ASSEMBLY__ */
 
diff --git a/arch/s390/include/asm/qdio.h b/arch/s390/include/asm/qdio.h
index 79d849f014f..0eaae626027 100644
--- a/arch/s390/include/asm/qdio.h
+++ b/arch/s390/include/asm/qdio.h
@@ -13,7 +13,8 @@
 #include <asm/cio.h>
 #include <asm/ccwdev.h>
 
-#define QDIO_MAX_QUEUES_PER_IRQ		32
+/* only use 4 queues to save some cachelines */
+#define QDIO_MAX_QUEUES_PER_IRQ		4
 #define QDIO_MAX_BUFFERS_PER_Q		128
 #define QDIO_MAX_BUFFERS_MASK		(QDIO_MAX_BUFFERS_PER_Q - 1)
 #define QDIO_MAX_ELEMENTS_PER_BUFFER	16
@@ -320,11 +321,6 @@ typedef void qdio_handler_t(struct ccw_device *, unsigned int, int,
 #define QDIO_ERROR_ACTIVATE_CHECK_CONDITION	0x40
 #define QDIO_ERROR_SLSB_STATE			0x80
 
-/* for qdio_initialize */
-#define QDIO_INBOUND_0COPY_SBALS		0x01
-#define QDIO_OUTBOUND_0COPY_SBALS		0x02
-#define QDIO_USE_OUTBOUND_PCIS			0x04
-
 /* for qdio_cleanup */
 #define QDIO_FLAG_CLEANUP_USING_CLEAR		0x01
 #define QDIO_FLAG_CLEANUP_USING_HALT		0x02
@@ -343,7 +339,6 @@ typedef void qdio_handler_t(struct ccw_device *, unsigned int, int,
  * @input_handler: handler to be called for input queues
  * @output_handler: handler to be called for output queues
  * @int_parm: interruption parameter
- * @flags: initialization flags
  * @input_sbal_addr_array:  address of no_input_qs * 128 pointers
  * @output_sbal_addr_array: address of no_output_qs * 128 pointers
  */
@@ -360,7 +355,6 @@ struct qdio_initialize {
 	qdio_handler_t *input_handler;
 	qdio_handler_t *output_handler;
 	unsigned long int_parm;
-	unsigned long flags;
 	void **input_sbal_addr_array;
 	void **output_sbal_addr_array;
 };
@@ -374,14 +368,12 @@ struct qdio_initialize {
 #define QDIO_FLAG_SYNC_OUTPUT		0x02
 #define QDIO_FLAG_PCI_OUT		0x10
 
-extern int qdio_initialize(struct qdio_initialize *);
 extern int qdio_allocate(struct qdio_initialize *);
 extern int qdio_establish(struct qdio_initialize *);
 extern int qdio_activate(struct ccw_device *);
 
 extern int do_QDIO(struct ccw_device *cdev, unsigned int callflags,
 		   int q_nr, unsigned int bufnr, unsigned int count);
-extern int qdio_cleanup(struct ccw_device*, int);
 extern int qdio_shutdown(struct ccw_device*, int);
 extern int qdio_free(struct ccw_device *);
 extern int qdio_get_ssqd_desc(struct ccw_device *dev, struct qdio_ssqd_desc*);
diff --git a/arch/s390/include/asm/rwsem.h b/arch/s390/include/asm/rwsem.h
index 9d2a1797180..423fdda2322 100644
--- a/arch/s390/include/asm/rwsem.h
+++ b/arch/s390/include/asm/rwsem.h
@@ -124,21 +124,21 @@ static inline void __down_read(struct rw_semaphore *sem)
 
 	asm volatile(
 #ifndef __s390x__
-		"	l	%0,0(%3)\n"
+		"	l	%0,%2\n"
 		"0:	lr	%1,%0\n"
-		"	ahi	%1,%5\n"
-		"	cs	%0,%1,0(%3)\n"
+		"	ahi	%1,%4\n"
+		"	cs	%0,%1,%2\n"
 		"	jl	0b"
 #else /* __s390x__ */
-		"	lg	%0,0(%3)\n"
+		"	lg	%0,%2\n"
 		"0:	lgr	%1,%0\n"
-		"	aghi	%1,%5\n"
-		"	csg	%0,%1,0(%3)\n"
+		"	aghi	%1,%4\n"
+		"	csg	%0,%1,%2\n"
 		"	jl	0b"
 #endif /* __s390x__ */
-		: "=&d" (old), "=&d" (new), "=m" (sem->count)
-		: "a" (&sem->count), "m" (sem->count),
-		  "i" (RWSEM_ACTIVE_READ_BIAS) : "cc", "memory");
+		: "=&d" (old), "=&d" (new), "=Q" (sem->count)
+		: "Q" (sem->count), "i" (RWSEM_ACTIVE_READ_BIAS)
+		: "cc", "memory");
 	if (old < 0)
 		rwsem_down_read_failed(sem);
 }
@@ -152,25 +152,25 @@ static inline int __down_read_trylock(struct rw_semaphore *sem)
 
 	asm volatile(
 #ifndef __s390x__
-		"	l	%0,0(%3)\n"
+		"	l	%0,%2\n"
 		"0:	ltr	%1,%0\n"
 		"	jm	1f\n"
-		"	ahi	%1,%5\n"
-		"	cs	%0,%1,0(%3)\n"
+		"	ahi	%1,%4\n"
+		"	cs	%0,%1,%2\n"
 		"	jl	0b\n"
 		"1:"
 #else /* __s390x__ */
-		"	lg	%0,0(%3)\n"
+		"	lg	%0,%2\n"
 		"0:	ltgr	%1,%0\n"
 		"	jm	1f\n"
-		"	aghi	%1,%5\n"
-		"	csg	%0,%1,0(%3)\n"
+		"	aghi	%1,%4\n"
+		"	csg	%0,%1,%2\n"
 		"	jl	0b\n"
 		"1:"
 #endif /* __s390x__ */
-		: "=&d" (old), "=&d" (new), "=m" (sem->count)
-		: "a" (&sem->count), "m" (sem->count),
-		  "i" (RWSEM_ACTIVE_READ_BIAS) : "cc", "memory");
+		: "=&d" (old), "=&d" (new), "=Q" (sem->count)
+		: "Q" (sem->count), "i" (RWSEM_ACTIVE_READ_BIAS)
+		: "cc", "memory");
 	return old >= 0 ? 1 : 0;
 }
 
@@ -184,20 +184,20 @@ static inline void __down_write_nested(struct rw_semaphore *sem, int subclass)
 	tmp = RWSEM_ACTIVE_WRITE_BIAS;
 	asm volatile(
 #ifndef __s390x__
-		"	l	%0,0(%3)\n"
+		"	l	%0,%2\n"
 		"0:	lr	%1,%0\n"
-		"	a	%1,%5\n"
-		"	cs	%0,%1,0(%3)\n"
+		"	a	%1,%4\n"
+		"	cs	%0,%1,%2\n"
 		"	jl	0b"
 #else /* __s390x__ */
-		"	lg	%0,0(%3)\n"
+		"	lg	%0,%2\n"
 		"0:	lgr	%1,%0\n"
-		"	ag	%1,%5\n"
-		"	csg	%0,%1,0(%3)\n"
+		"	ag	%1,%4\n"
+		"	csg	%0,%1,%2\n"
 		"	jl	0b"
 #endif /* __s390x__ */
-		: "=&d" (old), "=&d" (new), "=m" (sem->count)
-		: "a" (&sem->count), "m" (sem->count), "m" (tmp)
+		: "=&d" (old), "=&d" (new), "=Q" (sem->count)
+		: "Q" (sem->count), "m" (tmp)
 		: "cc", "memory");
 	if (old != 0)
 		rwsem_down_write_failed(sem);
@@ -217,22 +217,22 @@ static inline int __down_write_trylock(struct rw_semaphore *sem)
 
 	asm volatile(
 #ifndef __s390x__
-		"	l	%0,0(%2)\n"
+		"	l	%0,%1\n"
 		"0:	ltr	%0,%0\n"
 		"	jnz	1f\n"
-		"	cs	%0,%4,0(%2)\n"
+		"	cs	%0,%3,%1\n"
 		"	jl	0b\n"
 #else /* __s390x__ */
-		"	lg	%0,0(%2)\n"
+		"	lg	%0,%1\n"
 		"0:	ltgr	%0,%0\n"
 		"	jnz	1f\n"
-		"	csg	%0,%4,0(%2)\n"
+		"	csg	%0,%3,%1\n"
 		"	jl	0b\n"
 #endif /* __s390x__ */
 		"1:"
-		: "=&d" (old), "=m" (sem->count)
-		: "a" (&sem->count), "m" (sem->count),
-		  "d" (RWSEM_ACTIVE_WRITE_BIAS) : "cc", "memory");
+		: "=&d" (old), "=Q" (sem->count)
+		: "Q" (sem->count), "d" (RWSEM_ACTIVE_WRITE_BIAS)
+		: "cc", "memory");
 	return (old == RWSEM_UNLOCKED_VALUE) ? 1 : 0;
 }
 
@@ -245,21 +245,20 @@ static inline void __up_read(struct rw_semaphore *sem)
 
 	asm volatile(
 #ifndef __s390x__
-		"	l	%0,0(%3)\n"
+		"	l	%0,%2\n"
 		"0:	lr	%1,%0\n"
-		"	ahi	%1,%5\n"
-		"	cs	%0,%1,0(%3)\n"
+		"	ahi	%1,%4\n"
+		"	cs	%0,%1,%2\n"
 		"	jl	0b"
 #else /* __s390x__ */
-		"	lg	%0,0(%3)\n"
+		"	lg	%0,%2\n"
 		"0:	lgr	%1,%0\n"
-		"	aghi	%1,%5\n"
-		"	csg	%0,%1,0(%3)\n"
+		"	aghi	%1,%4\n"
+		"	csg	%0,%1,%2\n"
 		"	jl	0b"
 #endif /* __s390x__ */
-		: "=&d" (old), "=&d" (new), "=m" (sem->count)
-		: "a" (&sem->count), "m" (sem->count),
-		  "i" (-RWSEM_ACTIVE_READ_BIAS)
+		: "=&d" (old), "=&d" (new), "=Q" (sem->count)
+		: "Q" (sem->count), "i" (-RWSEM_ACTIVE_READ_BIAS)
 		: "cc", "memory");
 	if (new < 0)
 		if ((new & RWSEM_ACTIVE_MASK) == 0)
@@ -276,20 +275,20 @@ static inline void __up_write(struct rw_semaphore *sem)
 	tmp = -RWSEM_ACTIVE_WRITE_BIAS;
 	asm volatile(
 #ifndef __s390x__
-		"	l	%0,0(%3)\n"
+		"	l	%0,%2\n"
 		"0:	lr	%1,%0\n"
-		"	a	%1,%5\n"
-		"	cs	%0,%1,0(%3)\n"
+		"	a	%1,%4\n"
+		"	cs	%0,%1,%2\n"
 		"	jl	0b"
 #else /* __s390x__ */
-		"	lg	%0,0(%3)\n"
+		"	lg	%0,%2\n"
 		"0:	lgr	%1,%0\n"
-		"	ag	%1,%5\n"
-		"	csg	%0,%1,0(%3)\n"
+		"	ag	%1,%4\n"
+		"	csg	%0,%1,%2\n"
 		"	jl	0b"
 #endif /* __s390x__ */
-		: "=&d" (old), "=&d" (new), "=m" (sem->count)
-		: "a" (&sem->count), "m" (sem->count), "m" (tmp)
+		: "=&d" (old), "=&d" (new), "=Q" (sem->count)
+		: "Q" (sem->count), "m" (tmp)
 		: "cc", "memory");
 	if (new < 0)
 		if ((new & RWSEM_ACTIVE_MASK) == 0)
@@ -306,20 +305,20 @@ static inline void __downgrade_write(struct rw_semaphore *sem)
 	tmp = -RWSEM_WAITING_BIAS;
 	asm volatile(
 #ifndef __s390x__
-		"	l	%0,0(%3)\n"
+		"	l	%0,%2\n"
 		"0:	lr	%1,%0\n"
-		"	a	%1,%5\n"
-		"	cs	%0,%1,0(%3)\n"
+		"	a	%1,%4\n"
+		"	cs	%0,%1,%2\n"
 		"	jl	0b"
 #else /* __s390x__ */
-		"	lg	%0,0(%3)\n"
+		"	lg	%0,%2\n"
 		"0:	lgr	%1,%0\n"
-		"	ag	%1,%5\n"
-		"	csg	%0,%1,0(%3)\n"
+		"	ag	%1,%4\n"
+		"	csg	%0,%1,%2\n"
 		"	jl	0b"
 #endif /* __s390x__ */
-		: "=&d" (old), "=&d" (new), "=m" (sem->count)
-		: "a" (&sem->count), "m" (sem->count), "m" (tmp)
+		: "=&d" (old), "=&d" (new), "=Q" (sem->count)
+		: "Q" (sem->count), "m" (tmp)
 		: "cc", "memory");
 	if (new > 1)
 		rwsem_downgrade_wake(sem);
@@ -334,20 +333,20 @@ static inline void rwsem_atomic_add(long delta, struct rw_semaphore *sem)
 
 	asm volatile(
 #ifndef __s390x__
-		"	l	%0,0(%3)\n"
+		"	l	%0,%2\n"
 		"0:	lr	%1,%0\n"
-		"	ar	%1,%5\n"
-		"	cs	%0,%1,0(%3)\n"
+		"	ar	%1,%4\n"
+		"	cs	%0,%1,%2\n"
 		"	jl	0b"
 #else /* __s390x__ */
-		"	lg	%0,0(%3)\n"
+		"	lg	%0,%2\n"
 		"0:	lgr	%1,%0\n"
-		"	agr	%1,%5\n"
-		"	csg	%0,%1,0(%3)\n"
+		"	agr	%1,%4\n"
+		"	csg	%0,%1,%2\n"
 		"	jl	0b"
 #endif /* __s390x__ */
-		: "=&d" (old), "=&d" (new), "=m" (sem->count)
-		: "a" (&sem->count), "m" (sem->count), "d" (delta)
+		: "=&d" (old), "=&d" (new), "=Q" (sem->count)
+		: "Q" (sem->count), "d" (delta)
 		: "cc", "memory");
 }
 
@@ -360,20 +359,20 @@ static inline long rwsem_atomic_update(long delta, struct rw_semaphore *sem)
 
 	asm volatile(
 #ifndef __s390x__
-		"	l	%0,0(%3)\n"
+		"	l	%0,%2\n"
 		"0:	lr	%1,%0\n"
-		"	ar	%1,%5\n"
-		"	cs	%0,%1,0(%3)\n"
+		"	ar	%1,%4\n"
+		"	cs	%0,%1,%2\n"
 		"	jl	0b"
 #else /* __s390x__ */
-		"	lg	%0,0(%3)\n"
+		"	lg	%0,%2\n"
 		"0:	lgr	%1,%0\n"
-		"	agr	%1,%5\n"
-		"	csg	%0,%1,0(%3)\n"
+		"	agr	%1,%4\n"
+		"	csg	%0,%1,%2\n"
 		"	jl	0b"
 #endif /* __s390x__ */
-		: "=&d" (old), "=&d" (new), "=m" (sem->count)
-		: "a" (&sem->count), "m" (sem->count), "d" (delta)
+		: "=&d" (old), "=&d" (new), "=Q" (sem->count)
+		: "Q" (sem->count), "d" (delta)
 		: "cc", "memory");
 	return new;
 }
diff --git a/arch/s390/include/asm/scatterlist.h b/arch/s390/include/asm/scatterlist.h
index 35d786fe93a..be44d94cba5 100644
--- a/arch/s390/include/asm/scatterlist.h
+++ b/arch/s390/include/asm/scatterlist.h
@@ -1 +1,3 @@
+#define ISA_DMA_THRESHOLD	(~0UL)
+
 #include <asm-generic/scatterlist.h>
diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h
index 52a779c337e..25e831d58e1 100644
--- a/arch/s390/include/asm/setup.h
+++ b/arch/s390/include/asm/setup.h
@@ -2,7 +2,7 @@
  *  include/asm-s390/setup.h
  *
  *  S390 version
- *    Copyright IBM Corp. 1999,2006
+ *    Copyright IBM Corp. 1999,2010
  */
 
 #ifndef _ASM_S390_SETUP_H
@@ -14,14 +14,14 @@
 
 #ifdef __KERNEL__
 
-#include <asm/lowcore.h>
-#include <asm/types.h>
-
 #define PARMAREA		0x10400
 #define MEMORY_CHUNKS		256
 
 #ifndef __ASSEMBLY__
 
+#include <asm/lowcore.h>
+#include <asm/types.h>
+
 #ifndef __s390x__
 #define IPL_DEVICE        (*(unsigned long *)  (0x10404))
 #define INITRD_START      (*(unsigned long *)  (0x1040C))
@@ -71,9 +71,13 @@ extern unsigned int user_mode;
 #define MACHINE_FLAG_KVM	(1UL << 9)
 #define MACHINE_FLAG_HPAGE	(1UL << 10)
 #define MACHINE_FLAG_PFMF	(1UL << 11)
+#define MACHINE_FLAG_LPAR	(1UL << 12)
+#define MACHINE_FLAG_SPP	(1UL << 13)
 
 #define MACHINE_IS_VM		(S390_lowcore.machine_flags & MACHINE_FLAG_VM)
 #define MACHINE_IS_KVM		(S390_lowcore.machine_flags & MACHINE_FLAG_KVM)
+#define MACHINE_IS_LPAR		(S390_lowcore.machine_flags & MACHINE_FLAG_LPAR)
+
 #define MACHINE_HAS_DIAG9C	(S390_lowcore.machine_flags & MACHINE_FLAG_DIAG9C)
 
 #ifndef __s390x__
@@ -85,6 +89,7 @@ extern unsigned int user_mode;
 #define MACHINE_HAS_MVCOS	(0)
 #define MACHINE_HAS_HPAGE	(0)
 #define MACHINE_HAS_PFMF	(0)
+#define MACHINE_HAS_SPP		(0)
 #else /* __s390x__ */
 #define MACHINE_HAS_IEEE	(1)
 #define MACHINE_HAS_CSP		(1)
@@ -94,6 +99,7 @@ extern unsigned int user_mode;
 #define MACHINE_HAS_MVCOS	(S390_lowcore.machine_flags & MACHINE_FLAG_MVCOS)
 #define MACHINE_HAS_HPAGE	(S390_lowcore.machine_flags & MACHINE_FLAG_HPAGE)
 #define MACHINE_HAS_PFMF	(S390_lowcore.machine_flags & MACHINE_FLAG_PFMF)
+#define MACHINE_HAS_SPP		(S390_lowcore.machine_flags & MACHINE_FLAG_SPP)
 #endif /* __s390x__ */
 
 #define ZFCPDUMP_HSA_SIZE	(32UL<<20)
diff --git a/arch/s390/include/asm/sigp.h b/arch/s390/include/asm/sigp.h
index f72d611f7e1..e3bffd4e2d6 100644
--- a/arch/s390/include/asm/sigp.h
+++ b/arch/s390/include/asm/sigp.h
@@ -1,24 +1,19 @@
 /*
- *  include/asm-s390/sigp.h
+ *  Routines and structures for signalling other processors.
  *
- *  S390 version
- *    Copyright (C) 1999 IBM Deutschland Entwicklung GmbH, IBM Corporation
- *    Author(s): Denis Joseph Barrow (djbarrow@de.ibm.com,barrow_dj@yahoo.com),
- *               Martin Schwidefsky (schwidefsky@de.ibm.com)
- *               Heiko Carstens (heiko.carstens@de.ibm.com)
- *
- *  sigp.h by D.J. Barrow (c) IBM 1999
- *  contains routines / structures for signalling other S/390 processors in an
- *  SMP configuration.
+ *    Copyright IBM Corp. 1999,2010
+ *    Author(s): Denis Joseph Barrow,
+ *		 Martin Schwidefsky <schwidefsky@de.ibm.com>,
+ *		 Heiko Carstens <heiko.carstens@de.ibm.com>,
  */
 
-#ifndef __SIGP__
-#define __SIGP__
+#ifndef __ASM_SIGP_H
+#define __ASM_SIGP_H
 
 #include <asm/system.h>
 
-/* get real cpu address from logical cpu number */
-extern int __cpu_logical_map[];
+/* Get real cpu address from logical cpu number. */
+extern unsigned short __cpu_logical_map[];
 
 static inline int cpu_logical_map(int cpu)
 {
@@ -29,107 +24,108 @@ static inline int cpu_logical_map(int cpu)
 #endif
 }
 
-typedef enum
-{
-	sigp_unassigned=0x0,
-	sigp_sense,
-	sigp_external_call,
-	sigp_emergency_signal,
-	sigp_start,
-	sigp_stop,
-	sigp_restart,
-	sigp_unassigned1,
-	sigp_unassigned2,
-	sigp_stop_and_store_status,
-	sigp_unassigned3,
-	sigp_initial_cpu_reset,
-	sigp_cpu_reset,
-	sigp_set_prefix,
-	sigp_store_status_at_address,
-	sigp_store_extended_status_at_address
-} sigp_order_code;
-
-typedef __u32 sigp_status_word;
-
-typedef enum
-{
-        sigp_order_code_accepted=0,
-	sigp_status_stored,
-	sigp_busy,
-	sigp_not_operational
-} sigp_ccode;
-
+enum {
+	sigp_sense = 1,
+	sigp_external_call = 2,
+	sigp_emergency_signal = 3,
+	sigp_start = 4,
+	sigp_stop = 5,
+	sigp_restart = 6,
+	sigp_stop_and_store_status = 9,
+	sigp_initial_cpu_reset = 11,
+	sigp_cpu_reset = 12,
+	sigp_set_prefix = 13,
+	sigp_store_status_at_address = 14,
+	sigp_store_extended_status_at_address = 15,
+	sigp_set_architecture = 18,
+	sigp_conditional_emergency_signal = 19,
+	sigp_sense_running = 21,
+};
+
+enum {
+	sigp_order_code_accepted = 0,
+	sigp_status_stored = 1,
+	sigp_busy = 2,
+	sigp_not_operational = 3,
+};
 
 /*
- * Definitions for the external call
+ * Definitions for external call.
  */
-
-/* 'Bit' signals, asynchronous */
-typedef enum
-{
-	ec_schedule=0,
+enum {
+	ec_schedule = 0,
 	ec_call_function,
 	ec_call_function_single,
-	ec_bit_last
-} ec_bit_sig;
+};
 
 /*
- * Signal processor
+ * Signal processor.
  */
-static inline sigp_ccode
-signal_processor(__u16 cpu_addr, sigp_order_code order_code)
+static inline int raw_sigp(u16 cpu, int order)
 {
 	register unsigned long reg1 asm ("1") = 0;
-	sigp_ccode ccode;
+	int ccode;
 
 	asm volatile(
 		"	sigp	%1,%2,0(%3)\n"
 		"	ipm	%0\n"
 		"	srl	%0,28\n"
 		:	"=d"	(ccode)
-		: "d" (reg1), "d" (cpu_logical_map(cpu_addr)),
-		  "a" (order_code) : "cc" , "memory");
+		: "d" (reg1), "d" (cpu),
+		  "a" (order) : "cc" , "memory");
 	return ccode;
 }
 
 /*
- * Signal processor with parameter
+ * Signal processor with parameter.
  */
-static inline sigp_ccode
-signal_processor_p(__u32 parameter, __u16 cpu_addr, sigp_order_code order_code)
+static inline int raw_sigp_p(u32 parameter, u16 cpu, int order)
 {
 	register unsigned int reg1 asm ("1") = parameter;
-	sigp_ccode ccode;
+	int ccode;
 
 	asm volatile(
 		"	sigp	%1,%2,0(%3)\n"
 		"	ipm	%0\n"
 		"	srl	%0,28\n"
 		: "=d" (ccode)
-		: "d" (reg1), "d" (cpu_logical_map(cpu_addr)),
-		  "a" (order_code) : "cc" , "memory");
+		: "d" (reg1), "d" (cpu),
+		  "a" (order) : "cc" , "memory");
 	return ccode;
 }
 
 /*
- * Signal processor with parameter and return status
+ * Signal processor with parameter and return status.
  */
-static inline sigp_ccode
-signal_processor_ps(__u32 *statusptr, __u32 parameter, __u16 cpu_addr,
-		    sigp_order_code order_code)
+static inline int raw_sigp_ps(u32 *status, u32 parm, u16 cpu, int order)
 {
-	register unsigned int reg1 asm ("1") = parameter;
-	sigp_ccode ccode;
+	register unsigned int reg1 asm ("1") = parm;
+	int ccode;
 
 	asm volatile(
 		"	sigp	%1,%2,0(%3)\n"
 		"	ipm	%0\n"
 		"	srl	%0,28\n"
 		: "=d" (ccode), "+d" (reg1)
-		: "d" (cpu_logical_map(cpu_addr)), "a" (order_code)
+		: "d" (cpu), "a" (order)
 		: "cc" , "memory");
-	*statusptr = reg1;
+	*status = reg1;
 	return ccode;
 }
 
-#endif /* __SIGP__ */
+static inline int sigp(int cpu, int order)
+{
+	return raw_sigp(cpu_logical_map(cpu), order);
+}
+
+static inline int sigp_p(u32 parameter, int cpu, int order)
+{
+	return raw_sigp_p(parameter, cpu_logical_map(cpu), order);
+}
+
+static inline int sigp_ps(u32 *status, u32 parm, int cpu, int order)
+{
+	return raw_sigp_ps(status, parm, cpu_logical_map(cpu), order);
+}
+
+#endif /* __ASM_SIGP_H */
diff --git a/arch/s390/include/asm/smp.h b/arch/s390/include/asm/smp.h
index 2ab1141eeb5..edc03cb9cd7 100644
--- a/arch/s390/include/asm/smp.h
+++ b/arch/s390/include/asm/smp.h
@@ -29,7 +29,43 @@ 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);
 
-extern union save_area *zfcpdump_save_areas[NR_CPUS + 1];
+extern struct save_area *zfcpdump_save_areas[NR_CPUS + 1];
+
+extern void smp_switch_to_ipl_cpu(void (*func)(void *), void *);
+extern void smp_switch_to_cpu(void (*)(void *), void *, unsigned long sp,
+			      int from, int to);
+extern void smp_restart_cpu(void);
+
+/*
+ * returns 1 if (virtual) cpu is scheduled
+ * returns 0 otherwise
+ */
+static inline int smp_vcpu_scheduled(int cpu)
+{
+	u32 status;
+
+	switch (sigp_ps(&status, 0, cpu, sigp_sense_running)) {
+	case sigp_status_stored:
+		/* Check for running status */
+		if (status & 0x400)
+			return 0;
+		break;
+	case sigp_not_operational:
+		return 0;
+	default:
+		break;
+	}
+	return 1;
+}
+
+#else /* CONFIG_SMP */
+
+static inline void smp_switch_to_ipl_cpu(void (*func)(void *), void *data)
+{
+	func(data);
+}
+
+#define smp_vcpu_scheduled	(1)
 
 #endif /* CONFIG_SMP */
 
diff --git a/arch/s390/include/asm/spinlock.h b/arch/s390/include/asm/spinlock.h
index a587907d77f..56612fc8186 100644
--- a/arch/s390/include/asm/spinlock.h
+++ b/arch/s390/include/asm/spinlock.h
@@ -13,8 +13,6 @@
 
 #include <linux/smp.h>
 
-#if __GNUC__ > 3 || (__GNUC__ == 3 && __GNUC_MINOR__ > 2)
-
 static inline int
 _raw_compare_and_swap(volatile unsigned int *lock,
 		      unsigned int old, unsigned int new)
@@ -27,22 +25,6 @@ _raw_compare_and_swap(volatile unsigned int *lock,
 	return old;
 }
 
-#else /* __GNUC__ */
-
-static inline int
-_raw_compare_and_swap(volatile unsigned int *lock,
-		      unsigned int old, unsigned int new)
-{
-	asm volatile(
-		"	cs	%0,%3,0(%4)"
-		: "=d" (old), "=m" (*lock)
-		: "0" (old), "d" (new), "a" (lock), "m" (*lock)
-		: "cc", "memory" );
-	return old;
-}
-
-#endif /* __GNUC__ */
-
 /*
  * Simple spin lock operations.  There are two variants, one clears IRQ's
  * on the local processor, one does not.
diff --git a/arch/s390/include/asm/swab.h b/arch/s390/include/asm/swab.h
index eb18dc1f327..6bdee21c077 100644
--- a/arch/s390/include/asm/swab.h
+++ b/arch/s390/include/asm/swab.h
@@ -47,11 +47,11 @@ static inline __u32 __arch_swab32p(const __u32 *x)
 	
 	asm volatile(
 #ifndef __s390x__
-		"	icm	%0,8,3(%1)\n"
-		"	icm	%0,4,2(%1)\n"
-		"	icm	%0,2,1(%1)\n"
-		"	ic	%0,0(%1)"
-		: "=&d" (result) : "a" (x), "m" (*x) : "cc");
+		"	icm	%0,8,%O1+3(%R1)\n"
+		"	icm	%0,4,%O1+2(%R1)\n"
+		"	icm	%0,2,%O1+1(%R1)\n"
+		"	ic	%0,%1"
+		: "=&d" (result) : "Q" (*x) : "cc");
 #else /* __s390x__ */
 		"	lrv	%0,%1"
 		: "=d" (result) : "m" (*x));
@@ -77,9 +77,9 @@ static inline __u16 __arch_swab16p(const __u16 *x)
 	
 	asm volatile(
 #ifndef __s390x__
-		"	icm	%0,2,1(%1)\n"
-		"	ic	%0,0(%1)\n"
-		: "=&d" (result) : "a" (x), "m" (*x) : "cc");
+		"	icm	%0,2,%O+1(%R1)\n"
+		"	ic	%0,%1\n"
+		: "=&d" (result) : "Q" (*x) : "cc");
 #else /* __s390x__ */
 		"	lrvh	%0,%1"
 		: "=d" (result) : "m" (*x));
diff --git a/arch/s390/include/asm/syscall.h b/arch/s390/include/asm/syscall.h
index e0a73d3eb83..8429686951f 100644
--- a/arch/s390/include/asm/syscall.h
+++ b/arch/s390/include/asm/syscall.h
@@ -15,6 +15,13 @@
 #include <linux/sched.h>
 #include <asm/ptrace.h>
 
+/*
+ * The syscall table always contains 32 bit pointers since we know that the
+ * address of the function to be called is (way) below 4GB.  So the "int"
+ * type here is what we want [need] for both 32 bit and 64 bit systems.
+ */
+extern const unsigned int sys_call_table[];
+
 static inline long syscall_get_nr(struct task_struct *task,
 				  struct pt_regs *regs)
 {
diff --git a/arch/s390/include/asm/sysinfo.h b/arch/s390/include/asm/sysinfo.h
index 9d70057d828..22bdb2a0ee5 100644
--- a/arch/s390/include/asm/sysinfo.h
+++ b/arch/s390/include/asm/sysinfo.h
@@ -87,7 +87,8 @@ struct sysinfo_2_2_2 {
 
 struct sysinfo_3_2_2 {
 	char reserved_0[31];
-	unsigned char count;
+	unsigned char :4;
+	unsigned char count:4;
 	struct {
 		char reserved_0[4];
 		unsigned short cpus_total;
diff --git a/arch/s390/include/asm/system.h b/arch/s390/include/asm/system.h
index 379661d2f81..cef66210c84 100644
--- a/arch/s390/include/asm/system.h
+++ b/arch/s390/include/asm/system.h
@@ -24,65 +24,65 @@ extern struct task_struct *__switch_to(void *, void *);
 static inline void save_fp_regs(s390_fp_regs *fpregs)
 {
 	asm volatile(
-		"	std	0,8(%1)\n"
-		"	std	2,24(%1)\n"
-		"	std	4,40(%1)\n"
-		"	std	6,56(%1)"
-		: "=m" (*fpregs) : "a" (fpregs), "m" (*fpregs) : "memory");
+		"	std	0,%O0+8(%R0)\n"
+		"	std	2,%O0+24(%R0)\n"
+		"	std	4,%O0+40(%R0)\n"
+		"	std	6,%O0+56(%R0)"
+		: "=Q" (*fpregs) : "Q" (*fpregs));
 	if (!MACHINE_HAS_IEEE)
 		return;
 	asm volatile(
-		"	stfpc	0(%1)\n"
-		"	std	1,16(%1)\n"
-		"	std	3,32(%1)\n"
-		"	std	5,48(%1)\n"
-		"	std	7,64(%1)\n"
-		"	std	8,72(%1)\n"
-		"	std	9,80(%1)\n"
-		"	std	10,88(%1)\n"
-		"	std	11,96(%1)\n"
-		"	std	12,104(%1)\n"
-		"	std	13,112(%1)\n"
-		"	std	14,120(%1)\n"
-		"	std	15,128(%1)\n"
-		: "=m" (*fpregs) : "a" (fpregs), "m" (*fpregs) : "memory");
+		"	stfpc	%0\n"
+		"	std	1,%O0+16(%R0)\n"
+		"	std	3,%O0+32(%R0)\n"
+		"	std	5,%O0+48(%R0)\n"
+		"	std	7,%O0+64(%R0)\n"
+		"	std	8,%O0+72(%R0)\n"
+		"	std	9,%O0+80(%R0)\n"
+		"	std	10,%O0+88(%R0)\n"
+		"	std	11,%O0+96(%R0)\n"
+		"	std	12,%O0+104(%R0)\n"
+		"	std	13,%O0+112(%R0)\n"
+		"	std	14,%O0+120(%R0)\n"
+		"	std	15,%O0+128(%R0)\n"
+		: "=Q" (*fpregs) : "Q" (*fpregs));
 }
 
 static inline void restore_fp_regs(s390_fp_regs *fpregs)
 {
 	asm volatile(
-		"	ld	0,8(%0)\n"
-		"	ld	2,24(%0)\n"
-		"	ld	4,40(%0)\n"
-		"	ld	6,56(%0)"
-		: : "a" (fpregs), "m" (*fpregs));
+		"	ld	0,%O0+8(%R0)\n"
+		"	ld	2,%O0+24(%R0)\n"
+		"	ld	4,%O0+40(%R0)\n"
+		"	ld	6,%O0+56(%R0)"
+		: : "Q" (*fpregs));
 	if (!MACHINE_HAS_IEEE)
 		return;
 	asm volatile(
-		"	lfpc	0(%0)\n"
-		"	ld	1,16(%0)\n"
-		"	ld	3,32(%0)\n"
-		"	ld	5,48(%0)\n"
-		"	ld	7,64(%0)\n"
-		"	ld	8,72(%0)\n"
-		"	ld	9,80(%0)\n"
-		"	ld	10,88(%0)\n"
-		"	ld	11,96(%0)\n"
-		"	ld	12,104(%0)\n"
-		"	ld	13,112(%0)\n"
-		"	ld	14,120(%0)\n"
-		"	ld	15,128(%0)\n"
-		: : "a" (fpregs), "m" (*fpregs));
+		"	lfpc	%0\n"
+		"	ld	1,%O0+16(%R0)\n"
+		"	ld	3,%O0+32(%R0)\n"
+		"	ld	5,%O0+48(%R0)\n"
+		"	ld	7,%O0+64(%R0)\n"
+		"	ld	8,%O0+72(%R0)\n"
+		"	ld	9,%O0+80(%R0)\n"
+		"	ld	10,%O0+88(%R0)\n"
+		"	ld	11,%O0+96(%R0)\n"
+		"	ld	12,%O0+104(%R0)\n"
+		"	ld	13,%O0+112(%R0)\n"
+		"	ld	14,%O0+120(%R0)\n"
+		"	ld	15,%O0+128(%R0)\n"
+		: : "Q" (*fpregs));
 }
 
 static inline void save_access_regs(unsigned int *acrs)
 {
-	asm volatile("stam 0,15,0(%0)" : : "a" (acrs) : "memory");
+	asm volatile("stam 0,15,%0" : "=Q" (*acrs));
 }
 
 static inline void restore_access_regs(unsigned int *acrs)
 {
-	asm volatile("lam 0,15,0(%0)" : : "a" (acrs));
+	asm volatile("lam 0,15,%0" : : "Q" (*acrs));
 }
 
 #define switch_to(prev,next,last) do {					     \
@@ -110,6 +110,7 @@ extern void pfault_fini(void);
 #endif /* CONFIG_PFAULT */
 
 extern void cmma_init(void);
+extern int memcpy_real(void *, void *, size_t);
 
 #define finish_arch_switch(prev) do {					     \
 	set_fs(current->thread.mm_segment);				     \
@@ -139,48 +140,48 @@ static inline unsigned long __xchg(unsigned long x, void * ptr, int size)
 		shift = (3 ^ (addr & 3)) << 3;
 		addr ^= addr & 3;
 		asm volatile(
-			"	l	%0,0(%4)\n"
+			"	l	%0,%4\n"
 			"0:	lr	0,%0\n"
 			"	nr	0,%3\n"
 			"	or	0,%2\n"
-			"	cs	%0,0,0(%4)\n"
+			"	cs	%0,0,%4\n"
 			"	jl	0b\n"
-			: "=&d" (old), "=m" (*(int *) addr)
-			: "d" (x << shift), "d" (~(255 << shift)), "a" (addr),
-			  "m" (*(int *) addr) : "memory", "cc", "0");
+			: "=&d" (old), "=Q" (*(int *) addr)
+			: "d" (x << shift), "d" (~(255 << shift)),
+			  "Q" (*(int *) addr) : "memory", "cc", "0");
 		return old >> shift;
 	case 2:
 		addr = (unsigned long) ptr;
 		shift = (2 ^ (addr & 2)) << 3;
 		addr ^= addr & 2;
 		asm volatile(
-			"	l	%0,0(%4)\n"
+			"	l	%0,%4\n"
 			"0:	lr	0,%0\n"
 			"	nr	0,%3\n"
 			"	or	0,%2\n"
-			"	cs	%0,0,0(%4)\n"
+			"	cs	%0,0,%4\n"
 			"	jl	0b\n"
-			: "=&d" (old), "=m" (*(int *) addr)
-			: "d" (x << shift), "d" (~(65535 << shift)), "a" (addr),
-			  "m" (*(int *) addr) : "memory", "cc", "0");
+			: "=&d" (old), "=Q" (*(int *) addr)
+			: "d" (x << shift), "d" (~(65535 << shift)),
+			  "Q" (*(int *) addr) : "memory", "cc", "0");
 		return old >> shift;
 	case 4:
 		asm volatile(
-			"	l	%0,0(%3)\n"
-			"0:	cs	%0,%2,0(%3)\n"
+			"	l	%0,%3\n"
+			"0:	cs	%0,%2,%3\n"
 			"	jl	0b\n"
-			: "=&d" (old), "=m" (*(int *) ptr)
-			: "d" (x), "a" (ptr), "m" (*(int *) ptr)
+			: "=&d" (old), "=Q" (*(int *) ptr)
+			: "d" (x), "Q" (*(int *) ptr)
 			: "memory", "cc");
 		return old;
 #ifdef __s390x__
 	case 8:
 		asm volatile(
-			"	lg	%0,0(%3)\n"
-			"0:	csg	%0,%2,0(%3)\n"
+			"	lg	%0,%3\n"
+			"0:	csg	%0,%2,%3\n"
 			"	jl	0b\n"
 			: "=&d" (old), "=m" (*(long *) ptr)
-			: "d" (x), "a" (ptr), "m" (*(long *) ptr)
+			: "d" (x), "Q" (*(long *) ptr)
 			: "memory", "cc");
 		return old;
 #endif /* __s390x__ */
@@ -215,20 +216,20 @@ __cmpxchg(volatile void *ptr, unsigned long old, unsigned long new, int size)
 		shift = (3 ^ (addr & 3)) << 3;
 		addr ^= addr & 3;
 		asm volatile(
-			"	l	%0,0(%4)\n"
+			"	l	%0,%2\n"
 			"0:	nr	%0,%5\n"
 			"	lr	%1,%0\n"
-			"	or	%0,%2\n"
-			"	or	%1,%3\n"
-			"	cs	%0,%1,0(%4)\n"
+			"	or	%0,%3\n"
+			"	or	%1,%4\n"
+			"	cs	%0,%1,%2\n"
 			"	jnl	1f\n"
 			"	xr	%1,%0\n"
 			"	nr	%1,%5\n"
 			"	jnz	0b\n"
 			"1:"
-			: "=&d" (prev), "=&d" (tmp)
-			: "d" (old << shift), "d" (new << shift), "a" (ptr),
-			  "d" (~(255 << shift))
+			: "=&d" (prev), "=&d" (tmp), "=Q" (*(int *) ptr)
+			: "d" (old << shift), "d" (new << shift),
+			  "d" (~(255 << shift)), "Q" (*(int *) ptr)
 			: "memory", "cc");
 		return prev >> shift;
 	case 2:
@@ -236,33 +237,35 @@ __cmpxchg(volatile void *ptr, unsigned long old, unsigned long new, int size)
 		shift = (2 ^ (addr & 2)) << 3;
 		addr ^= addr & 2;
 		asm volatile(
-			"	l	%0,0(%4)\n"
+			"	l	%0,%2\n"
 			"0:	nr	%0,%5\n"
 			"	lr	%1,%0\n"
-			"	or	%0,%2\n"
-			"	or	%1,%3\n"
-			"	cs	%0,%1,0(%4)\n"
+			"	or	%0,%3\n"
+			"	or	%1,%4\n"
+			"	cs	%0,%1,%2\n"
 			"	jnl	1f\n"
 			"	xr	%1,%0\n"
 			"	nr	%1,%5\n"
 			"	jnz	0b\n"
 			"1:"
-			: "=&d" (prev), "=&d" (tmp)
-			: "d" (old << shift), "d" (new << shift), "a" (ptr),
-			  "d" (~(65535 << shift))
+			: "=&d" (prev), "=&d" (tmp), "=Q" (*(int *) ptr)
+			: "d" (old << shift), "d" (new << shift),
+			  "d" (~(65535 << shift)), "Q" (*(int *) ptr)
 			: "memory", "cc");
 		return prev >> shift;
 	case 4:
 		asm volatile(
-			"	cs	%0,%2,0(%3)\n"
-			: "=&d" (prev) : "0" (old), "d" (new), "a" (ptr)
+			"	cs	%0,%3,%1\n"
+			: "=&d" (prev), "=Q" (*(int *) ptr)
+			: "0" (old), "d" (new), "Q" (*(int *) ptr)
 			: "memory", "cc");
 		return prev;
 #ifdef __s390x__
 	case 8:
 		asm volatile(
-			"	csg	%0,%2,0(%3)\n"
-			: "=&d" (prev) : "0" (old), "d" (new), "a" (ptr)
+			"	csg	%0,%3,%1\n"
+			: "=&d" (prev), "=Q" (*(long *) ptr)
+			: "0" (old), "d" (new), "Q" (*(long *) ptr)
 			: "memory", "cc");
 		return prev;
 #endif /* __s390x__ */
@@ -302,17 +305,17 @@ __cmpxchg(volatile void *ptr, unsigned long old, unsigned long new, int size)
 #define __ctl_load(array, low, high) ({				\
 	typedef struct { char _[sizeof(array)]; } addrtype;	\
 	asm volatile(						\
-		"	lctlg	%1,%2,0(%0)\n"			\
-		: : "a" (&array), "i" (low), "i" (high),	\
-		    "m" (*(addrtype *)(&array)));		\
+		"	lctlg	%1,%2,%0\n"			\
+		: : "Q" (*(addrtype *)(&array)),		\
+		    "i" (low), "i" (high));			\
 	})
 
 #define __ctl_store(array, low, high) ({			\
 	typedef struct { char _[sizeof(array)]; } addrtype;	\
 	asm volatile(						\
-		"	stctg	%2,%3,0(%1)\n"			\
-		: "=m" (*(addrtype *)(&array))			\
-		: "a" (&array), "i" (low), "i" (high));		\
+		"	stctg	%1,%2,%0\n"			\
+		: "=Q" (*(addrtype *)(&array))			\
+		: "i" (low), "i" (high));			\
 	})
 
 #else /* __s390x__ */
@@ -320,17 +323,17 @@ __cmpxchg(volatile void *ptr, unsigned long old, unsigned long new, int size)
 #define __ctl_load(array, low, high) ({				\
 	typedef struct { char _[sizeof(array)]; } addrtype;	\
 	asm volatile(						\
-		"	lctl	%1,%2,0(%0)\n"			\
-		: : "a" (&array), "i" (low), "i" (high),	\
-		    "m" (*(addrtype *)(&array)));		\
+		"	lctl	%1,%2,%0\n"			\
+		: : "Q" (*(addrtype *)(&array)),		\
+		    "i" (low), "i" (high));			\
 })
 
 #define __ctl_store(array, low, high) ({			\
 	typedef struct { char _[sizeof(array)]; } addrtype;	\
 	asm volatile(						\
-		"	stctl	%2,%3,0(%1)\n"			\
-		: "=m" (*(addrtype *)(&array))			\
-		: "a" (&array), "i" (low), "i" (high));		\
+		"	stctl	%1,%2,%0\n"			\
+		: "=Q" (*(addrtype *)(&array))			\
+		: "i" (low), "i" (high));			\
 	})
 
 #endif /* __s390x__ */
@@ -456,11 +459,6 @@ extern void (*_machine_power_off)(void);
 
 #define arch_align_stack(x) (x)
 
-#ifdef CONFIG_TRACE_IRQFLAGS
-extern psw_t sysc_restore_trace_psw;
-extern psw_t io_restore_trace_psw;
-#endif
-
 static inline int tprot(unsigned long addr)
 {
 	int rc = -EFAULT;
diff --git a/arch/s390/include/asm/thread_info.h b/arch/s390/include/asm/thread_info.h
index 66069e73684..5baf0230b29 100644
--- a/arch/s390/include/asm/thread_info.h
+++ b/arch/s390/include/asm/thread_info.h
@@ -50,6 +50,7 @@ struct thread_info {
 	struct restart_block	restart_block;
 	__u64			user_timer;
 	__u64			system_timer;
+	unsigned long		last_break;	/* last breaking-event-address. */
 };
 
 /*
@@ -73,7 +74,7 @@ struct thread_info {
 /* how to get the thread information struct from C */
 static inline struct thread_info *current_thread_info(void)
 {
-	return (struct thread_info *)((*(unsigned long *) __LC_KERNEL_STACK)-THREAD_SIZE);
+	return (struct thread_info *)(S390_lowcore.kernel_stack - THREAD_SIZE);
 }
 
 #define THREAD_SIZE_ORDER THREAD_ORDER
@@ -96,7 +97,7 @@ static inline struct thread_info *current_thread_info(void)
 #define TIF_POLLING_NRFLAG	16	/* true if poll_idle() is polling
 					   TIF_NEED_RESCHED */
 #define TIF_31BIT		17	/* 32bit process */
-#define TIF_MEMDIE		18
+#define TIF_MEMDIE		18	/* is terminating due to OOM killer */
 #define TIF_RESTORE_SIGMASK	19	/* restore signal mask in do_signal() */
 #define TIF_FREEZE		20	/* thread is freezing for suspend */
 
diff --git a/arch/s390/include/asm/timex.h b/arch/s390/include/asm/timex.h
index 68d9fea34b4..09d345a701d 100644
--- a/arch/s390/include/asm/timex.h
+++ b/arch/s390/include/asm/timex.h
@@ -20,10 +20,10 @@ static inline int set_clock(__u64 time)
 	int cc;
 
 	asm volatile(
-		"   sck   0(%2)\n"
+		"   sck   %1\n"
 		"   ipm   %0\n"
 		"   srl   %0,28\n"
-		: "=d" (cc) : "m" (time), "a" (&time) : "cc");
+		: "=d" (cc) : "Q" (time) : "cc");
 	return cc;
 }
 
@@ -32,21 +32,21 @@ static inline int store_clock(__u64 *time)
 	int cc;
 
 	asm volatile(
-		"   stck  0(%2)\n"
+		"   stck  %1\n"
 		"   ipm   %0\n"
 		"   srl   %0,28\n"
-		: "=d" (cc), "=m" (*time) : "a" (time) : "cc");
+		: "=d" (cc), "=Q" (*time) : : "cc");
 	return cc;
 }
 
 static inline void set_clock_comparator(__u64 time)
 {
-	asm volatile("sckc 0(%1)" : : "m" (time), "a" (&time));
+	asm volatile("sckc %0" : : "Q" (time));
 }
 
 static inline void store_clock_comparator(__u64 *time)
 {
-	asm volatile("stckc 0(%1)" : "=m" (*time) : "a" (time));
+	asm volatile("stckc %0" : "=Q" (*time));
 }
 
 #define CLOCK_TICK_RATE	1193180 /* Underlying HZ */
@@ -57,25 +57,19 @@ static inline unsigned long long get_clock (void)
 {
 	unsigned long long clk;
 
-#if __GNUC__ > 3 || (__GNUC__ == 3 && __GNUC_MINOR__ > 2)
 	asm volatile("stck %0" : "=Q" (clk) : : "cc");
-#else /* __GNUC__ */
-	asm volatile("stck 0(%1)" : "=m" (clk) : "a" (&clk) : "cc");
-#endif /* __GNUC__ */
 	return clk;
 }
 
+static inline void get_clock_ext(char *clk)
+{
+	asm volatile("stcke %0" : "=Q" (*clk) : : "cc");
+}
+
 static inline unsigned long long get_clock_xt(void)
 {
 	unsigned char clk[16];
-
-#if __GNUC__ > 3 || (__GNUC__ == 3 && __GNUC_MINOR__ > 2)
-	asm volatile("stcke %0" : "=Q" (clk) : : "cc");
-#else /* __GNUC__ */
-	asm volatile("stcke 0(%1)" : "=m" (clk)
-				   : "a" (clk) : "cc");
-#endif /* __GNUC__ */
-
+	get_clock_ext(clk);
 	return *((unsigned long long *)&clk[1]);
 }
 
diff --git a/arch/s390/include/asm/topology.h b/arch/s390/include/asm/topology.h
index 6e7211abd95..dc8a67297d0 100644
--- a/arch/s390/include/asm/topology.h
+++ b/arch/s390/include/asm/topology.h
@@ -7,8 +7,10 @@
 
 const struct cpumask *cpu_coregroup_mask(unsigned int cpu);
 
+extern unsigned char cpu_core_id[NR_CPUS];
 extern cpumask_t cpu_core_map[NR_CPUS];
 
+#define topology_core_id(cpu)		(cpu_core_id[cpu])
 #define topology_core_cpumask(cpu)	(&cpu_core_map[cpu])
 
 int topology_set_cpu_management(int fc);
diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h
index cbf0a8745bf..d6b1ed0ec52 100644
--- a/arch/s390/include/asm/uaccess.h
+++ b/arch/s390/include/asm/uaccess.h
@@ -265,6 +265,12 @@ __copy_from_user(void *to, const void __user *from, unsigned long n)
 		return uaccess.copy_from_user(n, from, to);
 }
 
+extern void copy_from_user_overflow(void)
+#ifdef CONFIG_DEBUG_STRICT_USER_COPY_CHECKS
+__compiletime_warning("copy_from_user() buffer size is not provably correct")
+#endif
+;
+
 /**
  * copy_from_user: - Copy a block of data from user space.
  * @to:   Destination address, in kernel space.
@@ -284,7 +290,13 @@ __copy_from_user(void *to, const void __user *from, unsigned long n)
 static inline unsigned long __must_check
 copy_from_user(void *to, const void __user *from, unsigned long n)
 {
+	unsigned int sz = __compiletime_object_size(to);
+
 	might_fault();
+	if (unlikely(sz != -1 && sz < n)) {
+		copy_from_user_overflow();
+		return n;
+	}
 	if (access_ok(VERIFY_READ, from, n))
 		n = __copy_from_user(to, from, n);
 	else
diff --git a/arch/s390/include/asm/unistd.h b/arch/s390/include/asm/unistd.h
index 6e9f049fa82..5f0075150a6 100644
--- a/arch/s390/include/asm/unistd.h
+++ b/arch/s390/include/asm/unistd.h
@@ -392,6 +392,7 @@
 #define __ARCH_WANT_SYS_LLSEEK
 #define __ARCH_WANT_SYS_NICE
 #define __ARCH_WANT_SYS_OLD_GETRLIMIT
+#define __ARCH_WANT_SYS_OLD_MMAP
 #define __ARCH_WANT_SYS_OLDUMOUNT
 #define __ARCH_WANT_SYS_SIGPENDING
 #define __ARCH_WANT_SYS_SIGPROCMASK
diff --git a/arch/s390/include/asm/vdso.h b/arch/s390/include/asm/vdso.h
index 7bdd7c8ebc9..533f35751ae 100644
--- a/arch/s390/include/asm/vdso.h
+++ b/arch/s390/include/asm/vdso.h
@@ -7,7 +7,7 @@
 #define VDSO32_LBASE	0
 #define VDSO64_LBASE	0
 
-#define VDSO_VERSION_STRING	LINUX_2.6.26
+#define VDSO_VERSION_STRING	LINUX_2.6.29
 
 #ifndef __ASSEMBLY__
 
@@ -29,6 +29,7 @@ struct vdso_data {
 	__u32 tz_minuteswest;		/* Minutes west of Greenwich	0x30 */
 	__u32 tz_dsttime;		/* Type of dst correction	0x34 */
 	__u32 ectg_available;
+	__u32 ntp_mult;			/* NTP adjusted multiplier	0x3C */
 };
 
 struct vdso_per_cpu_data {
diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile
index 683f6381cc5..64230bc392f 100644
--- a/arch/s390/kernel/Makefile
+++ b/arch/s390/kernel/Makefile
@@ -29,9 +29,12 @@ obj-y	+= $(if $(CONFIG_64BIT),entry64.o,entry.o)
 obj-y	+= $(if $(CONFIG_64BIT),reipl64.o,reipl.o)
 
 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)		+= $(if $(CONFIG_64BIT),switch_cpu64.o, \
+							switch_cpu.o)
 obj-$(CONFIG_HIBERNATION)	+= suspend.o swsusp_asm64.o
 obj-$(CONFIG_AUDIT)		+= audit.o
 compat-obj-$(CONFIG_AUDIT)	+= compat_audit.o
diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c
index 63e46433e81..5232278d79a 100644
--- a/arch/s390/kernel/asm-offsets.c
+++ b/arch/s390/kernel/asm-offsets.c
@@ -4,18 +4,27 @@
  * and format the required data.
  */
 
-#include <linux/sched.h>
+#define ASM_OFFSETS_C
+
 #include <linux/kbuild.h>
+#include <linux/sched.h>
 #include <asm/vdso.h>
 #include <asm/sigp.h>
 
+/*
+ * Make sure that the compiler is new enough. We want a compiler that
+ * is known to work with the "Q" assembler constraint.
+ */
+#if __GNUC__ < 3 || (__GNUC__ == 3 && __GNUC_MINOR__ < 3)
+#error Your compiler is too old; please use version 3.3.3 or newer
+#endif
+
 int main(void)
 {
 	DEFINE(__THREAD_info, offsetof(struct task_struct, stack));
 	DEFINE(__THREAD_ksp, offsetof(struct task_struct, thread.ksp));
 	DEFINE(__THREAD_per, offsetof(struct task_struct, thread.per_info));
-	DEFINE(__THREAD_mm_segment,
-	       offsetof(struct task_struct, thread.mm_segment));
+	DEFINE(__THREAD_mm_segment, offsetof(struct task_struct, thread.mm_segment));
 	BLANK();
 	DEFINE(__TASK_pid, offsetof(struct task_struct, pid));
 	BLANK();
@@ -30,6 +39,7 @@ int main(void)
 	DEFINE(__TI_precount, offsetof(struct thread_info, preempt_count));
 	DEFINE(__TI_user_timer, offsetof(struct thread_info, user_timer));
 	DEFINE(__TI_system_timer, offsetof(struct thread_info, system_timer));
+	DEFINE(__TI_last_break, offsetof(struct thread_info, last_break));
 	BLANK();
 	DEFINE(__PT_ARGS, offsetof(struct pt_regs, args));
 	DEFINE(__PT_PSW, offsetof(struct pt_regs, psw));
@@ -52,18 +62,98 @@ int main(void)
 	DEFINE(__VDSO_WTOM_NSEC, offsetof(struct vdso_data, wtom_clock_nsec));
 	DEFINE(__VDSO_TIMEZONE, offsetof(struct vdso_data, tz_minuteswest));
 	DEFINE(__VDSO_ECTG_OK, offsetof(struct vdso_data, ectg_available));
-	DEFINE(__VDSO_ECTG_BASE,
-	       offsetof(struct vdso_per_cpu_data, ectg_timer_base));
-	DEFINE(__VDSO_ECTG_USER,
-	       offsetof(struct vdso_per_cpu_data, ectg_user_time));
+	DEFINE(__VDSO_NTP_MULT, offsetof(struct vdso_data, ntp_mult));
+	DEFINE(__VDSO_ECTG_BASE, offsetof(struct vdso_per_cpu_data, ectg_timer_base));
+	DEFINE(__VDSO_ECTG_USER, offsetof(struct vdso_per_cpu_data, ectg_user_time));
 	/* constants used by the vdso */
 	DEFINE(CLOCK_REALTIME, CLOCK_REALTIME);
 	DEFINE(CLOCK_MONOTONIC, CLOCK_MONOTONIC);
 	DEFINE(CLOCK_REALTIME_RES, MONOTONIC_RES_NSEC);
+	BLANK();
 	/* constants for SIGP */
 	DEFINE(__SIGP_STOP, sigp_stop);
 	DEFINE(__SIGP_RESTART, sigp_restart);
 	DEFINE(__SIGP_SENSE, sigp_sense);
 	DEFINE(__SIGP_INITIAL_CPU_RESET, sigp_initial_cpu_reset);
+	BLANK();
+	/* lowcore offsets */
+	DEFINE(__LC_EXT_PARAMS, offsetof(struct _lowcore, ext_params));
+	DEFINE(__LC_CPU_ADDRESS, offsetof(struct _lowcore, cpu_addr));
+	DEFINE(__LC_EXT_INT_CODE, offsetof(struct _lowcore, ext_int_code));
+	DEFINE(__LC_SVC_ILC, offsetof(struct _lowcore, svc_ilc));
+	DEFINE(__LC_SVC_INT_CODE, offsetof(struct _lowcore, svc_code));
+	DEFINE(__LC_PGM_ILC, offsetof(struct _lowcore, pgm_ilc));
+	DEFINE(__LC_PGM_INT_CODE, offsetof(struct _lowcore, pgm_code));
+	DEFINE(__LC_PER_ATMID, offsetof(struct _lowcore, per_perc_atmid));
+	DEFINE(__LC_PER_ADDRESS, offsetof(struct _lowcore, per_address));
+	DEFINE(__LC_PER_ACCESS_ID, offsetof(struct _lowcore, per_access_id));
+	DEFINE(__LC_AR_MODE_ID, offsetof(struct _lowcore, ar_access_id));
+	DEFINE(__LC_SUBCHANNEL_ID, offsetof(struct _lowcore, subchannel_id));
+	DEFINE(__LC_SUBCHANNEL_NR, offsetof(struct _lowcore, subchannel_nr));
+	DEFINE(__LC_IO_INT_PARM, offsetof(struct _lowcore, io_int_parm));
+	DEFINE(__LC_IO_INT_WORD, offsetof(struct _lowcore, io_int_word));
+	DEFINE(__LC_STFL_FAC_LIST, offsetof(struct _lowcore, stfl_fac_list));
+	DEFINE(__LC_MCCK_CODE, offsetof(struct _lowcore, mcck_interruption_code));
+	DEFINE(__LC_DUMP_REIPL, offsetof(struct _lowcore, ipib));
+	BLANK();
+	DEFINE(__LC_RST_NEW_PSW, offsetof(struct _lowcore, restart_psw));
+	DEFINE(__LC_RST_OLD_PSW, offsetof(struct _lowcore, restart_old_psw));
+	DEFINE(__LC_EXT_OLD_PSW, offsetof(struct _lowcore, external_old_psw));
+	DEFINE(__LC_SVC_OLD_PSW, offsetof(struct _lowcore, svc_old_psw));
+	DEFINE(__LC_PGM_OLD_PSW, offsetof(struct _lowcore, program_old_psw));
+	DEFINE(__LC_MCK_OLD_PSW, offsetof(struct _lowcore, mcck_old_psw));
+	DEFINE(__LC_IO_OLD_PSW, offsetof(struct _lowcore, io_old_psw));
+	DEFINE(__LC_EXT_NEW_PSW, offsetof(struct _lowcore, external_new_psw));
+	DEFINE(__LC_SVC_NEW_PSW, offsetof(struct _lowcore, svc_new_psw));
+	DEFINE(__LC_PGM_NEW_PSW, offsetof(struct _lowcore, program_new_psw));
+	DEFINE(__LC_MCK_NEW_PSW, offsetof(struct _lowcore, mcck_new_psw));
+	DEFINE(__LC_IO_NEW_PSW, offsetof(struct _lowcore, io_new_psw));
+	DEFINE(__LC_SAVE_AREA, offsetof(struct _lowcore, save_area));
+	DEFINE(__LC_RETURN_PSW, offsetof(struct _lowcore, return_psw));
+	DEFINE(__LC_RETURN_MCCK_PSW, offsetof(struct _lowcore, return_mcck_psw));
+	DEFINE(__LC_SYNC_ENTER_TIMER, offsetof(struct _lowcore, sync_enter_timer));
+	DEFINE(__LC_ASYNC_ENTER_TIMER, offsetof(struct _lowcore, async_enter_timer));
+	DEFINE(__LC_MCCK_ENTER_TIMER, offsetof(struct _lowcore, mcck_enter_timer));
+	DEFINE(__LC_EXIT_TIMER, offsetof(struct _lowcore, exit_timer));
+	DEFINE(__LC_USER_TIMER, offsetof(struct _lowcore, user_timer));
+	DEFINE(__LC_SYSTEM_TIMER, offsetof(struct _lowcore, system_timer));
+	DEFINE(__LC_STEAL_TIMER, offsetof(struct _lowcore, steal_timer));
+	DEFINE(__LC_LAST_UPDATE_TIMER, offsetof(struct _lowcore, last_update_timer));
+	DEFINE(__LC_LAST_UPDATE_CLOCK, offsetof(struct _lowcore, last_update_clock));
+	DEFINE(__LC_CURRENT, offsetof(struct _lowcore, current_task));
+	DEFINE(__LC_THREAD_INFO, offsetof(struct _lowcore, thread_info));
+	DEFINE(__LC_KERNEL_STACK, offsetof(struct _lowcore, kernel_stack));
+	DEFINE(__LC_ASYNC_STACK, offsetof(struct _lowcore, async_stack));
+	DEFINE(__LC_PANIC_STACK, offsetof(struct _lowcore, panic_stack));
+	DEFINE(__LC_KERNEL_ASCE, offsetof(struct _lowcore, kernel_asce));
+	DEFINE(__LC_USER_ASCE, offsetof(struct _lowcore, user_asce));
+	DEFINE(__LC_USER_EXEC_ASCE, offsetof(struct _lowcore, user_exec_asce));
+	DEFINE(__LC_INT_CLOCK, offsetof(struct _lowcore, int_clock));
+	DEFINE(__LC_MCCK_CLOCK, offsetof(struct _lowcore, mcck_clock));
+	DEFINE(__LC_MACHINE_FLAGS, offsetof(struct _lowcore, machine_flags));
+	DEFINE(__LC_FTRACE_FUNC, offsetof(struct _lowcore, ftrace_func));
+	DEFINE(__LC_IRB, offsetof(struct _lowcore, irb));
+	DEFINE(__LC_CPU_TIMER_SAVE_AREA, offsetof(struct _lowcore, cpu_timer_save_area));
+	DEFINE(__LC_CLOCK_COMP_SAVE_AREA, offsetof(struct _lowcore, clock_comp_save_area));
+	DEFINE(__LC_PSW_SAVE_AREA, offsetof(struct _lowcore, psw_save_area));
+	DEFINE(__LC_PREFIX_SAVE_AREA, offsetof(struct _lowcore, prefixreg_save_area));
+	DEFINE(__LC_AREGS_SAVE_AREA, offsetof(struct _lowcore, access_regs_save_area));
+	DEFINE(__LC_FPREGS_SAVE_AREA, offsetof(struct _lowcore, floating_pt_save_area));
+	DEFINE(__LC_GPREGS_SAVE_AREA, offsetof(struct _lowcore, gpregs_save_area));
+	DEFINE(__LC_CREGS_SAVE_AREA, offsetof(struct _lowcore, cregs_save_area));
+#ifdef CONFIG_32BIT
+	DEFINE(__LC_PFAULT_INTPARM, offsetof(struct _lowcore, ext_params));
+	DEFINE(SAVE_AREA_BASE, offsetof(struct _lowcore, extended_save_area_addr));
+#else /* CONFIG_32BIT */
+	DEFINE(__LC_PFAULT_INTPARM, offsetof(struct _lowcore, ext_params2));
+	DEFINE(__LC_EXT_PARAMS2, offsetof(struct _lowcore, ext_params2));
+	DEFINE(SAVE_AREA_BASE, offsetof(struct _lowcore, floating_pt_save_area));
+	DEFINE(__LC_PASTE, offsetof(struct _lowcore, paste));
+	DEFINE(__LC_FP_CREG_SAVE_AREA, offsetof(struct _lowcore, fpt_creg_save_area));
+	DEFINE(__LC_LAST_BREAK, offsetof(struct _lowcore, breaking_event_addr));
+	DEFINE(__LC_VDSO_PER_CPU, offsetof(struct _lowcore, vdso_per_cpu_data));
+	DEFINE(__LC_SIE_HOOK, offsetof(struct _lowcore, sie_hook));
+	DEFINE(__LC_CMF_HPP, offsetof(struct _lowcore, cmf_hpp));
+#endif /* CONFIG_32BIT */
 	return 0;
 }
diff --git a/arch/s390/kernel/base.S b/arch/s390/kernel/base.S
index dc7e5259770..15e46ca9433 100644
--- a/arch/s390/kernel/base.S
+++ b/arch/s390/kernel/base.S
@@ -6,8 +6,8 @@
  *		 Michael Holzheu <holzheu@de.ibm.com>
  */
 
+#include <asm/asm-offsets.h>
 #include <asm/ptrace.h>
-#include <asm/lowcore.h>
 
 #ifdef CONFIG_64BIT
 
diff --git a/arch/s390/kernel/compat_linux.c b/arch/s390/kernel/compat_linux.c
index 11c3aba664e..73b624ed9cd 100644
--- a/arch/s390/kernel/compat_linux.c
+++ b/arch/s390/kernel/compat_linux.c
@@ -29,7 +29,6 @@
 #include <linux/sem.h>
 #include <linux/msg.h>
 #include <linux/shm.h>
-#include <linux/slab.h>
 #include <linux/uio.h>
 #include <linux/quota.h>
 #include <linux/module.h>
@@ -52,6 +51,7 @@
 #include <linux/ptrace.h>
 #include <linux/fadvise.h>
 #include <linux/ipc.h>
+#include <linux/slab.h>
 
 #include <asm/types.h>
 #include <asm/uaccess.h>
diff --git a/arch/s390/kernel/compat_wrapper.S b/arch/s390/kernel/compat_wrapper.S
index 30de2d0e52b..672ce52341b 100644
--- a/arch/s390/kernel/compat_wrapper.S
+++ b/arch/s390/kernel/compat_wrapper.S
@@ -547,7 +547,7 @@ sys32_setdomainname_wrapper:
 	.globl	sys32_newuname_wrapper
 sys32_newuname_wrapper:
 	llgtr	%r2,%r2			# struct new_utsname *
-	jg	sys_s390_newuname	# branch to system call
+	jg	sys_newuname		# branch to system call
 
 	.globl	compat_sys_adjtimex_wrapper
 compat_sys_adjtimex_wrapper:
diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c
index 0168472b2fd..98192261491 100644
--- a/arch/s390/kernel/debug.c
+++ b/arch/s390/kernel/debug.c
@@ -655,6 +655,7 @@ found:
 	p_info->act_entry_offset = 0;
 	file->private_data = p_info;
 	debug_info_get(debug_info);
+	nonseekable_open(inode, file);
 out:
 	mutex_unlock(&debug_mutex);
 	return rc;
diff --git a/arch/s390/kernel/dis.c b/arch/s390/kernel/dis.c
index db943a7ec51..b39b27d68b4 100644
--- a/arch/s390/kernel/dis.c
+++ b/arch/s390/kernel/dis.c
@@ -86,10 +86,17 @@ enum {
 	U4_12,	/* 4 bit unsigned value starting at 12 */
 	U4_16,	/* 4 bit unsigned value starting at 16 */
 	U4_20,	/* 4 bit unsigned value starting at 20 */
+	U4_32,	/* 4 bit unsigned value starting at 32 */
 	U8_8,	/* 8 bit unsigned value starting at 8 */
 	U8_16,	/* 8 bit unsigned value starting at 16 */
+	U8_24,	/* 8 bit unsigned value starting at 24 */
+	U8_32,	/* 8 bit unsigned value starting at 32 */
+	I8_8,	/* 8 bit signed value starting at 8 */
+	I8_32,	/* 8 bit signed value starting at 32 */
 	I16_16,	/* 16 bit signed value starting at 16 */
+	I16_32,	/* 32 bit signed value starting at 16 */
 	U16_16,	/* 16 bit unsigned value starting at 16 */
+	U16_32,	/* 32 bit unsigned value starting at 16 */
 	J16_16,	/* PC relative jump offset at 16 */
 	J32_16,	/* PC relative long offset at 16 */
 	I32_16,	/* 32 bit signed value starting at 16 */
@@ -104,21 +111,37 @@ enum {
  */
 enum {
 	INSTR_INVALID,
-	INSTR_E, INSTR_RIE_RRP, INSTR_RIL_RI, INSTR_RIL_RP, INSTR_RIL_RU,
-	INSTR_RIL_UP, INSTR_RI_RI, INSTR_RI_RP, INSTR_RI_RU, INSTR_RI_UP,
+	INSTR_E,
+	INSTR_RIE_R0IU, INSTR_RIE_R0UU, INSTR_RIE_RRP, INSTR_RIE_RRPU,
+	INSTR_RIE_RRUUU, INSTR_RIE_RUPI, INSTR_RIE_RUPU,
+	INSTR_RIL_RI, INSTR_RIL_RP, INSTR_RIL_RU, INSTR_RIL_UP,
+	INSTR_RIS_R0RDU, INSTR_RIS_R0UU, INSTR_RIS_RURDI, INSTR_RIS_RURDU,
+	INSTR_RI_RI, INSTR_RI_RP, INSTR_RI_RU, INSTR_RI_UP,
 	INSTR_RRE_00, INSTR_RRE_0R, INSTR_RRE_AA, INSTR_RRE_AR, INSTR_RRE_F0,
-	INSTR_RRE_FF, INSTR_RRE_R0, INSTR_RRE_RA, INSTR_RRE_RF, INSTR_RRE_RR,
-	INSTR_RRE_RR_OPT, INSTR_RRF_F0FF, INSTR_RRF_FUFF, INSTR_RRF_M0RR,
-	INSTR_RRF_R0RR, INSTR_RRF_RURR, INSTR_RRF_U0FF, INSTR_RRF_U0RF,
+	INSTR_RRE_FF, INSTR_RRE_FR, INSTR_RRE_R0, INSTR_RRE_RA, INSTR_RRE_RF,
+	INSTR_RRE_RR, INSTR_RRE_RR_OPT,
+	INSTR_RRF_0UFF, INSTR_RRF_F0FF, INSTR_RRF_F0FF2, INSTR_RRF_F0FR,
+	INSTR_RRF_FFRU, INSTR_RRF_FUFF, INSTR_RRF_M0RR, INSTR_RRF_R0RR,
+	INSTR_RRF_RURR, INSTR_RRF_U0FF, INSTR_RRF_U0RF, INSTR_RRF_U0RR,
+	INSTR_RRF_UUFF, INSTR_RRR_F0FF, INSTR_RRS_RRRDU,
 	INSTR_RR_FF, INSTR_RR_R0, INSTR_RR_RR, INSTR_RR_U0, INSTR_RR_UR,
-	INSTR_RSE_CCRD, INSTR_RSE_RRRD, INSTR_RSE_RURD, INSTR_RSI_RRP,
-	INSTR_RSL_R0RD, INSTR_RSY_AARD, INSTR_RSY_CCRD, INSTR_RSY_RRRD,
-	INSTR_RSY_RURD, INSTR_RS_AARD, INSTR_RS_CCRD, INSTR_RS_R0RD,
-	INSTR_RS_RRRD, INSTR_RS_RURD, INSTR_RXE_FRRD, INSTR_RXE_RRRD,
-	INSTR_RXF_FRRDF, INSTR_RXY_FRRD, INSTR_RXY_RRRD, INSTR_RX_FRRD,
-	INSTR_RX_RRRD, INSTR_RX_URRD, INSTR_SIY_URD, INSTR_SI_URD,
-	INSTR_SSE_RDRD, INSTR_SSF_RRDRD, INSTR_SS_L0RDRD, INSTR_SS_LIRDRD,
-	INSTR_SS_LLRDRD, INSTR_SS_RRRDRD, INSTR_SS_RRRDRD2, INSTR_SS_RRRDRD3,
+	INSTR_RSE_CCRD, INSTR_RSE_RRRD, INSTR_RSE_RURD,
+	INSTR_RSI_RRP,
+	INSTR_RSL_R0RD,
+	INSTR_RSY_AARD, INSTR_RSY_CCRD, INSTR_RSY_RRRD, INSTR_RSY_RURD,
+	INSTR_RS_AARD, INSTR_RS_CCRD, INSTR_RS_R0RD, INSTR_RS_RRRD,
+	INSTR_RS_RURD,
+	INSTR_RXE_FRRD, INSTR_RXE_RRRD,
+	INSTR_RXF_FRRDF,
+	INSTR_RXY_FRRD, INSTR_RXY_RRRD, INSTR_RXY_URRD,
+	INSTR_RX_FRRD, INSTR_RX_RRRD, INSTR_RX_URRD,
+	INSTR_SIL_RDI, INSTR_SIL_RDU,
+	INSTR_SIY_IRD, INSTR_SIY_URD,
+	INSTR_SI_URD,
+	INSTR_SSE_RDRD,
+	INSTR_SSF_RRDRD,
+	INSTR_SS_L0RDRD, INSTR_SS_LIRDRD, INSTR_SS_LLRDRD, INSTR_SS_RRRDRD,
+	INSTR_SS_RRRDRD2, INSTR_SS_RRRDRD3,
 	INSTR_S_00, INSTR_S_RD,
 };
 
@@ -129,7 +152,7 @@ struct operand {
 };
 
 struct insn {
-	const char name[5];
+	const char name[6];
 	unsigned char opfrag;
 	unsigned char format;
 };
@@ -170,11 +193,16 @@ static const struct operand operands[] =
 	[U4_12]  = {  4, 12, 0 },
 	[U4_16]  = {  4, 16, 0 },
 	[U4_20]  = {  4, 20, 0 },
+	[U4_32]  = {  4, 32, 0 },
 	[U8_8]	 = {  8,  8, 0 },
 	[U8_16]  = {  8, 16, 0 },
+	[U8_24]  = {  8, 24, 0 },
+	[U8_32]  = {  8, 32, 0 },
 	[I16_16] = { 16, 16, OPERAND_SIGNED },
 	[U16_16] = { 16, 16, 0 },
+	[U16_32] = { 16, 32, 0 },
 	[J16_16] = { 16, 16, OPERAND_PCREL },
+	[I16_32] = { 16, 32, OPERAND_SIGNED },
 	[J32_16] = { 32, 16, OPERAND_PCREL },
 	[I32_16] = { 32, 16, OPERAND_SIGNED },
 	[U32_16] = { 32, 16, 0 },
@@ -183,82 +211,93 @@ static const struct operand operands[] =
 };
 
 static const unsigned char formats[][7] = {
-	[INSTR_E]	  = { 0xff, 0,0,0,0,0,0 },	       /* e.g. pr    */
-	[INSTR_RIE_RRP]	  = { 0xff, R_8,R_12,J16_16,0,0,0 },   /* e.g. brxhg */
-	[INSTR_RIL_RP]	  = { 0x0f, R_8,J32_16,0,0,0,0 },      /* e.g. brasl */
-	[INSTR_RIL_UP]	  = { 0x0f, U4_8,J32_16,0,0,0,0 },     /* e.g. brcl  */
-	[INSTR_RIL_RI]	  = { 0x0f, R_8,I32_16,0,0,0,0 },      /* e.g. afi   */
-	[INSTR_RIL_RU]	  = { 0x0f, R_8,U32_16,0,0,0,0 },      /* e.g. alfi  */
-	[INSTR_RI_RI]	  = { 0x0f, R_8,I16_16,0,0,0,0 },      /* e.g. ahi   */
-	[INSTR_RI_RP]	  = { 0x0f, R_8,J16_16,0,0,0,0 },      /* e.g. brct  */
-	[INSTR_RI_RU]	  = { 0x0f, R_8,U16_16,0,0,0,0 },      /* e.g. tml   */
-	[INSTR_RI_UP]	  = { 0x0f, U4_8,J16_16,0,0,0,0 },     /* e.g. brc   */
-	[INSTR_RRE_00]	  = { 0xff, 0,0,0,0,0,0 },	       /* e.g. palb  */
-	[INSTR_RRE_0R]	  = { 0xff, R_28,0,0,0,0,0 },	       /* e.g. tb    */
-	[INSTR_RRE_AA]	  = { 0xff, A_24,A_28,0,0,0,0 },       /* e.g. cpya  */
-	[INSTR_RRE_AR]	  = { 0xff, A_24,R_28,0,0,0,0 },       /* e.g. sar   */
-	[INSTR_RRE_F0]	  = { 0xff, F_24,0,0,0,0,0 },	       /* e.g. sqer  */
-	[INSTR_RRE_FF]	  = { 0xff, F_24,F_28,0,0,0,0 },       /* e.g. debr  */
-	[INSTR_RRE_R0]	  = { 0xff, R_24,0,0,0,0,0 },	       /* e.g. ipm   */
-	[INSTR_RRE_RA]	  = { 0xff, R_24,A_28,0,0,0,0 },       /* e.g. ear   */
-	[INSTR_RRE_RF]	  = { 0xff, R_24,F_28,0,0,0,0 },       /* e.g. cefbr */
-	[INSTR_RRE_RR]	  = { 0xff, R_24,R_28,0,0,0,0 },       /* e.g. lura  */
-	[INSTR_RRE_RR_OPT]= { 0xff, R_24,RO_28,0,0,0,0 },      /* efpc, sfpc */
-	[INSTR_RRF_F0FF]  = { 0xff, F_16,F_24,F_28,0,0,0 },    /* e.g. madbr */
-	[INSTR_RRF_FUFF]  = { 0xff, F_24,F_16,F_28,U4_20,0,0 },/* e.g. didbr */
-	[INSTR_RRF_RURR]  = { 0xff, R_24,R_28,R_16,U4_20,0,0 },/* e.g. .insn */
-	[INSTR_RRF_R0RR]  = { 0xff, R_24,R_16,R_28,0,0,0 },    /* e.g. idte  */
-	[INSTR_RRF_U0FF]  = { 0xff, F_24,U4_16,F_28,0,0,0 },   /* e.g. fixr  */
-	[INSTR_RRF_U0RF]  = { 0xff, R_24,U4_16,F_28,0,0,0 },   /* e.g. cfebr */
-	[INSTR_RRF_M0RR]  = { 0xff, R_24,R_28,M_16,0,0,0 },    /* e.g. sske  */
-	[INSTR_RR_FF]	  = { 0xff, F_8,F_12,0,0,0,0 },        /* e.g. adr   */
-	[INSTR_RR_R0]	  = { 0xff, R_8, 0,0,0,0,0 },	       /* e.g. spm   */
-	[INSTR_RR_RR]	  = { 0xff, R_8,R_12,0,0,0,0 },        /* e.g. lr    */
-	[INSTR_RR_U0]	  = { 0xff, U8_8, 0,0,0,0,0 },	       /* e.g. svc   */
-	[INSTR_RR_UR]	  = { 0xff, U4_8,R_12,0,0,0,0 },       /* e.g. bcr   */
-	[INSTR_RSE_RRRD]  = { 0xff, R_8,R_12,D_20,B_16,0,0 },  /* e.g. lmh   */
-	[INSTR_RSE_CCRD]  = { 0xff, C_8,C_12,D_20,B_16,0,0 },  /* e.g. lmh   */
-	[INSTR_RSE_RURD]  = { 0xff, R_8,U4_12,D_20,B_16,0,0 }, /* e.g. icmh  */
-	[INSTR_RSL_R0RD]  = { 0xff, R_8,D_20,B_16,0,0,0 },     /* e.g. tp    */
-	[INSTR_RSI_RRP]	  = { 0xff, R_8,R_12,J16_16,0,0,0 },   /* e.g. brxh  */
-	[INSTR_RSY_RRRD]  = { 0xff, R_8,R_12,D20_20,B_16,0,0 },/* e.g. stmy  */
+	[INSTR_E]	  = { 0xff, 0,0,0,0,0,0 },
+	[INSTR_RIE_R0UU]  = { 0xff, R_8,U16_16,U4_32,0,0,0 },
+	[INSTR_RIE_RRPU]  = { 0xff, R_8,R_12,U4_32,J16_16,0,0 },
+	[INSTR_RIE_RRP]	  = { 0xff, R_8,R_12,J16_16,0,0,0 },
+	[INSTR_RIE_RRUUU] = { 0xff, R_8,R_12,U8_16,U8_24,U8_32,0 },
+	[INSTR_RIE_RUPI]  = { 0xff, R_8,I8_32,U4_12,J16_16,0,0 },
+	[INSTR_RIL_RI]	  = { 0x0f, R_8,I32_16,0,0,0,0 },
+	[INSTR_RIL_RP]	  = { 0x0f, R_8,J32_16,0,0,0,0 },
+	[INSTR_RIL_RU]	  = { 0x0f, R_8,U32_16,0,0,0,0 },
+	[INSTR_RIL_UP]	  = { 0x0f, U4_8,J32_16,0,0,0,0 },
+	[INSTR_RIS_R0RDU] = { 0xff, R_8,U8_32,D_20,B_16,0,0 },
+	[INSTR_RIS_RURDI] = { 0xff, R_8,I8_32,U4_12,D_20,B_16,0 },
+	[INSTR_RIS_RURDU] = { 0xff, R_8,U8_32,U4_12,D_20,B_16,0 },
+	[INSTR_RI_RI]	  = { 0x0f, R_8,I16_16,0,0,0,0 },
+	[INSTR_RI_RP]	  = { 0x0f, R_8,J16_16,0,0,0,0 },
+	[INSTR_RI_RU]	  = { 0x0f, R_8,U16_16,0,0,0,0 },
+	[INSTR_RI_UP]	  = { 0x0f, U4_8,J16_16,0,0,0,0 },
+	[INSTR_RRE_00]	  = { 0xff, 0,0,0,0,0,0 },
+	[INSTR_RRE_0R]	  = { 0xff, R_28,0,0,0,0,0 },
+	[INSTR_RRE_AA]	  = { 0xff, A_24,A_28,0,0,0,0 },
+	[INSTR_RRE_AR]	  = { 0xff, A_24,R_28,0,0,0,0 },
+	[INSTR_RRE_F0]	  = { 0xff, F_24,0,0,0,0,0 },
+	[INSTR_RRE_FF]	  = { 0xff, F_24,F_28,0,0,0,0 },
+	[INSTR_RRE_FR]	  = { 0xff, F_24,R_28,0,0,0,0 },
+	[INSTR_RRE_R0]	  = { 0xff, R_24,0,0,0,0,0 },
+	[INSTR_RRE_RA]	  = { 0xff, R_24,A_28,0,0,0,0 },
+	[INSTR_RRE_RF]	  = { 0xff, R_24,F_28,0,0,0,0 },
+	[INSTR_RRE_RR]	  = { 0xff, R_24,R_28,0,0,0,0 },
+	[INSTR_RRE_RR_OPT]= { 0xff, R_24,RO_28,0,0,0,0 },
+	[INSTR_RRF_0UFF]  = { 0xff, F_24,F_28,U4_20,0,0,0 },
+	[INSTR_RRF_F0FF2] = { 0xff, F_24,F_16,F_28,0,0,0 },
+	[INSTR_RRF_F0FF]  = { 0xff, F_16,F_24,F_28,0,0,0 },
+	[INSTR_RRF_F0FR]  = { 0xff, F_24,F_16,R_28,0,0,0 },
+	[INSTR_RRF_FFRU]  = { 0xff, F_24,F_16,R_28,U4_20,0,0 },
+	[INSTR_RRF_FUFF]  = { 0xff, F_24,F_16,F_28,U4_20,0,0 },
+	[INSTR_RRF_M0RR]  = { 0xff, R_24,R_28,M_16,0,0,0 },
+	[INSTR_RRF_R0RR]  = { 0xff, R_24,R_16,R_28,0,0,0 },
+	[INSTR_RRF_RURR]  = { 0xff, R_24,R_28,R_16,U4_20,0,0 },
+	[INSTR_RRF_U0FF]  = { 0xff, F_24,U4_16,F_28,0,0,0 },
+	[INSTR_RRF_U0RF]  = { 0xff, R_24,U4_16,F_28,0,0,0 },
+	[INSTR_RRF_U0RR]  = { 0xff, R_24,R_28,U4_16,0,0,0 },
+	[INSTR_RRF_UUFF]  = { 0xff, F_24,U4_16,F_28,U4_20,0,0 },
+	[INSTR_RRR_F0FF]  = { 0xff, F_24,F_28,F_16,0,0,0 },
+	[INSTR_RRS_RRRDU] = { 0xff, R_8,R_12,U4_32,D_20,B_16,0 },
+	[INSTR_RR_FF]	  = { 0xff, F_8,F_12,0,0,0,0 },
+	[INSTR_RR_R0]	  = { 0xff, R_8, 0,0,0,0,0 },
+	[INSTR_RR_RR]	  = { 0xff, R_8,R_12,0,0,0,0 },
+	[INSTR_RR_U0]	  = { 0xff, U8_8, 0,0,0,0,0 },
+	[INSTR_RR_UR]	  = { 0xff, U4_8,R_12,0,0,0,0 },
+	[INSTR_RSE_CCRD]  = { 0xff, C_8,C_12,D_20,B_16,0,0 },
+	[INSTR_RSE_RRRD]  = { 0xff, R_8,R_12,D_20,B_16,0,0 },
+	[INSTR_RSE_RURD]  = { 0xff, R_8,U4_12,D_20,B_16,0,0 },
+	[INSTR_RSI_RRP]	  = { 0xff, R_8,R_12,J16_16,0,0,0 },
+	[INSTR_RSL_R0RD]  = { 0xff, D_20,L4_8,B_16,0,0,0 },
+	[INSTR_RSY_AARD]  = { 0xff, A_8,A_12,D20_20,B_16,0,0 },
+	[INSTR_RSY_CCRD]  = { 0xff, C_8,C_12,D20_20,B_16,0,0 },
+	[INSTR_RSY_RRRD]  = { 0xff, R_8,R_12,D20_20,B_16,0,0 },
 	[INSTR_RSY_RURD]  = { 0xff, R_8,U4_12,D20_20,B_16,0,0 },
-							       /* e.g. icmh  */
-	[INSTR_RSY_AARD]  = { 0xff, A_8,A_12,D20_20,B_16,0,0 },/* e.g. lamy  */
-	[INSTR_RSY_CCRD]  = { 0xff, C_8,C_12,D20_20,B_16,0,0 },/* e.g. lamy  */
-	[INSTR_RS_AARD]	  = { 0xff, A_8,A_12,D_20,B_16,0,0 },  /* e.g. lam   */
-	[INSTR_RS_CCRD]	  = { 0xff, C_8,C_12,D_20,B_16,0,0 },  /* e.g. lctl  */
-	[INSTR_RS_R0RD]	  = { 0xff, R_8,D_20,B_16,0,0,0 },     /* e.g. sll   */
-	[INSTR_RS_RRRD]	  = { 0xff, R_8,R_12,D_20,B_16,0,0 },  /* e.g. cs    */
-	[INSTR_RS_RURD]	  = { 0xff, R_8,U4_12,D_20,B_16,0,0 }, /* e.g. icm   */
-	[INSTR_RXE_FRRD]  = { 0xff, F_8,D_20,X_12,B_16,0,0 },  /* e.g. axbr  */
-	[INSTR_RXE_RRRD]  = { 0xff, R_8,D_20,X_12,B_16,0,0 },  /* e.g. lg    */
+	[INSTR_RS_AARD]	  = { 0xff, A_8,A_12,D_20,B_16,0,0 },
+	[INSTR_RS_CCRD]	  = { 0xff, C_8,C_12,D_20,B_16,0,0 },
+	[INSTR_RS_R0RD]	  = { 0xff, R_8,D_20,B_16,0,0,0 },
+	[INSTR_RS_RRRD]	  = { 0xff, R_8,R_12,D_20,B_16,0,0 },
+	[INSTR_RS_RURD]	  = { 0xff, R_8,U4_12,D_20,B_16,0,0 },
+	[INSTR_RXE_FRRD]  = { 0xff, F_8,D_20,X_12,B_16,0,0 },
+	[INSTR_RXE_RRRD]  = { 0xff, R_8,D_20,X_12,B_16,0,0 },
 	[INSTR_RXF_FRRDF] = { 0xff, F_32,F_8,D_20,X_12,B_16,0 },
-							       /* e.g. madb  */
-	[INSTR_RXY_RRRD]  = { 0xff, R_8,D20_20,X_12,B_16,0,0 },/* e.g. ly    */
-	[INSTR_RXY_FRRD]  = { 0xff, F_8,D20_20,X_12,B_16,0,0 },/* e.g. ley   */
-	[INSTR_RX_FRRD]	  = { 0xff, F_8,D_20,X_12,B_16,0,0 },  /* e.g. ae    */
-	[INSTR_RX_RRRD]	  = { 0xff, R_8,D_20,X_12,B_16,0,0 },  /* e.g. l     */
-	[INSTR_RX_URRD]	  = { 0xff, U4_8,D_20,X_12,B_16,0,0 }, /* e.g. bc    */
-	[INSTR_SI_URD]	  = { 0xff, D_20,B_16,U8_8,0,0,0 },    /* e.g. cli   */
-	[INSTR_SIY_URD]	  = { 0xff, D20_20,B_16,U8_8,0,0,0 },  /* e.g. tmy   */
-	[INSTR_SSE_RDRD]  = { 0xff, D_20,B_16,D_36,B_32,0,0 }, /* e.g. mvsdk */
+	[INSTR_RXY_FRRD]  = { 0xff, F_8,D20_20,X_12,B_16,0,0 },
+	[INSTR_RXY_RRRD]  = { 0xff, R_8,D20_20,X_12,B_16,0,0 },
+	[INSTR_RXY_URRD]  = { 0xff, U4_8,D20_20,X_12,B_16,0,0 },
+	[INSTR_RX_FRRD]	  = { 0xff, F_8,D_20,X_12,B_16,0,0 },
+	[INSTR_RX_RRRD]	  = { 0xff, R_8,D_20,X_12,B_16,0,0 },
+	[INSTR_RX_URRD]	  = { 0xff, U4_8,D_20,X_12,B_16,0,0 },
+	[INSTR_SIL_RDI]   = { 0xff, D_20,B_16,I16_32,0,0,0 },
+	[INSTR_SIL_RDU]   = { 0xff, D_20,B_16,U16_32,0,0,0 },
+	[INSTR_SIY_IRD]   = { 0xff, D20_20,B_16,I8_8,0,0,0 },
+	[INSTR_SIY_URD]	  = { 0xff, D20_20,B_16,U8_8,0,0,0 },
+	[INSTR_SI_URD]	  = { 0xff, D_20,B_16,U8_8,0,0,0 },
+	[INSTR_SSE_RDRD]  = { 0xff, D_20,B_16,D_36,B_32,0,0 },
+	[INSTR_SSF_RRDRD] = { 0x00, D_20,B_16,D_36,B_32,R_8,0 },
 	[INSTR_SS_L0RDRD] = { 0xff, D_20,L8_8,B_16,D_36,B_32,0 },
-							       /* e.g. mvc   */
 	[INSTR_SS_LIRDRD] = { 0xff, D_20,L4_8,B_16,D_36,B_32,U4_12 },
-							       /* e.g. srp   */
 	[INSTR_SS_LLRDRD] = { 0xff, D_20,L4_8,B_16,D_36,L4_12,B_32 },
-							       /* e.g. pack  */
-	[INSTR_SS_RRRDRD] = { 0xff, D_20,R_8,B_16,D_36,B_32,R_12 },
-							       /* e.g. mvck  */
 	[INSTR_SS_RRRDRD2]= { 0xff, R_8,D_20,B_16,R_12,D_36,B_32 },
-							       /* e.g. plo   */
 	[INSTR_SS_RRRDRD3]= { 0xff, R_8,R_12,D_20,B_16,D_36,B_32 },
-							       /* e.g. lmd   */
-	[INSTR_S_00]	  = { 0xff, 0,0,0,0,0,0 },	       /* e.g. hsch  */
-	[INSTR_S_RD]	  = { 0xff, D_20,B_16,0,0,0,0 },       /* e.g. lpsw  */
-	[INSTR_SSF_RRDRD] = { 0x00, D_20,B_16,D_36,B_32,R_8,0 },
-							       /* e.g. mvcos */
+	[INSTR_SS_RRRDRD] = { 0xff, D_20,R_8,B_16,D_36,B_32,R_12 },
+	[INSTR_S_00]	  = { 0xff, 0,0,0,0,0,0 },
+	[INSTR_S_RD]	  = { 0xff, D_20,B_16,0,0,0,0 },
 };
 
 static struct insn opcode[] = {
@@ -454,6 +493,8 @@ static struct insn opcode[] = {
 static struct insn opcode_01[] = {
 #ifdef CONFIG_64BIT
 	{ "sam64", 0x0e, INSTR_E },
+	{ "pfpo", 0x0a, INSTR_E },
+	{ "ptff", 0x04, INSTR_E },
 #endif
 	{ "pr", 0x01, INSTR_E },
 	{ "upt", 0x02, INSTR_E },
@@ -519,6 +560,8 @@ static struct insn opcode_b2[] = {
 	{ "cutfu", 0xa7, INSTR_RRF_M0RR },
 	{ "stfle", 0xb0, INSTR_S_RD },
 	{ "lpswe", 0xb2, INSTR_S_RD },
+	{ "srnmt", 0xb9, INSTR_S_RD },
+	{ "lfas", 0xbd, INSTR_S_RD },
 #endif
 	{ "stidp", 0x02, INSTR_S_RD },
 	{ "sck", 0x04, INSTR_S_RD },
@@ -589,7 +632,6 @@ static struct insn opcode_b2[] = {
 	{ "clst", 0x5d, INSTR_RRE_RR },
 	{ "srst", 0x5e, INSTR_RRE_RR },
 	{ "cmpsc", 0x63, INSTR_RRE_RR },
-	{ "cmpsc", 0x63, INSTR_RRE_RR },
 	{ "siga", 0x74, INSTR_S_RD },
 	{ "xsch", 0x76, INSTR_S_00 },
 	{ "rp", 0x77, INSTR_S_RD },
@@ -630,6 +672,57 @@ static struct insn opcode_b3[] = {
 	{ "cger", 0xc8, INSTR_RRF_U0RF },
 	{ "cgdr", 0xc9, INSTR_RRF_U0RF },
 	{ "cgxr", 0xca, INSTR_RRF_U0RF },
+	{ "lpdfr", 0x70, INSTR_RRE_FF },
+	{ "lndfr", 0x71, INSTR_RRE_FF },
+	{ "cpsdr", 0x72, INSTR_RRF_F0FF2 },
+	{ "lcdfr", 0x73, INSTR_RRE_FF },
+	{ "ldgr", 0xc1, INSTR_RRE_FR },
+	{ "lgdr", 0xcd, INSTR_RRE_RF },
+	{ "adtr", 0xd2, INSTR_RRR_F0FF },
+	{ "axtr", 0xda, INSTR_RRR_F0FF },
+	{ "cdtr", 0xe4, INSTR_RRE_FF },
+	{ "cxtr", 0xec, INSTR_RRE_FF },
+	{ "kdtr", 0xe0, INSTR_RRE_FF },
+	{ "kxtr", 0xe8, INSTR_RRE_FF },
+	{ "cedtr", 0xf4, INSTR_RRE_FF },
+	{ "cextr", 0xfc, INSTR_RRE_FF },
+	{ "cdgtr", 0xf1, INSTR_RRE_FR },
+	{ "cxgtr", 0xf9, INSTR_RRE_FR },
+	{ "cdstr", 0xf3, INSTR_RRE_FR },
+	{ "cxstr", 0xfb, INSTR_RRE_FR },
+	{ "cdutr", 0xf2, INSTR_RRE_FR },
+	{ "cxutr", 0xfa, INSTR_RRE_FR },
+	{ "cgdtr", 0xe1, INSTR_RRF_U0RF },
+	{ "cgxtr", 0xe9, INSTR_RRF_U0RF },
+	{ "csdtr", 0xe3, INSTR_RRE_RF },
+	{ "csxtr", 0xeb, INSTR_RRE_RF },
+	{ "cudtr", 0xe2, INSTR_RRE_RF },
+	{ "cuxtr", 0xea, INSTR_RRE_RF },
+	{ "ddtr", 0xd1, INSTR_RRR_F0FF },
+	{ "dxtr", 0xd9, INSTR_RRR_F0FF },
+	{ "eedtr", 0xe5, INSTR_RRE_RF },
+	{ "eextr", 0xed, INSTR_RRE_RF },
+	{ "esdtr", 0xe7, INSTR_RRE_RF },
+	{ "esxtr", 0xef, INSTR_RRE_RF },
+	{ "iedtr", 0xf6, INSTR_RRF_F0FR },
+	{ "iextr", 0xfe, INSTR_RRF_F0FR },
+	{ "ltdtr", 0xd6, INSTR_RRE_FF },
+	{ "ltxtr", 0xde, INSTR_RRE_FF },
+	{ "fidtr", 0xd7, INSTR_RRF_UUFF },
+	{ "fixtr", 0xdf, INSTR_RRF_UUFF },
+	{ "ldetr", 0xd4, INSTR_RRF_0UFF },
+	{ "lxdtr", 0xdc, INSTR_RRF_0UFF },
+	{ "ledtr", 0xd5, INSTR_RRF_UUFF },
+	{ "ldxtr", 0xdd, INSTR_RRF_UUFF },
+	{ "mdtr", 0xd0, INSTR_RRR_F0FF },
+	{ "mxtr", 0xd8, INSTR_RRR_F0FF },
+	{ "qadtr", 0xf5, INSTR_RRF_FUFF },
+	{ "qaxtr", 0xfd, INSTR_RRF_FUFF },
+	{ "rrdtr", 0xf7, INSTR_RRF_FFRU },
+	{ "rrxtr", 0xff, INSTR_RRF_FFRU },
+	{ "sfasr", 0x85, INSTR_RRE_R0 },
+	{ "sdtr", 0xd3, INSTR_RRR_F0FF },
+	{ "sxtr", 0xdb, INSTR_RRR_F0FF },
 #endif
 	{ "lpebr", 0x00, INSTR_RRE_FF },
 	{ "lnebr", 0x01, INSTR_RRE_FF },
@@ -780,6 +873,14 @@ static struct insn opcode_b9[] = {
 	{ "cu24", 0xb1, INSTR_RRF_M0RR },
 	{ "cu41", 0xb2, INSTR_RRF_M0RR },
 	{ "cu42", 0xb3, INSTR_RRF_M0RR },
+	{ "crt", 0x72, INSTR_RRF_U0RR },
+	{ "cgrt", 0x60, INSTR_RRF_U0RR },
+	{ "clrt", 0x73, INSTR_RRF_U0RR },
+	{ "clgrt", 0x61, INSTR_RRF_U0RR },
+	{ "ptf", 0xa2, INSTR_RRE_R0 },
+	{ "pfmf", 0xaf, INSTR_RRE_RR },
+	{ "trte", 0xbf, INSTR_RRF_M0RR },
+	{ "trtre", 0xbd, INSTR_RRF_M0RR },
 #endif
 	{ "kmac", 0x1e, INSTR_RRE_RR },
 	{ "lrvr", 0x1f, INSTR_RRE_RR },
@@ -835,6 +936,43 @@ static struct insn opcode_c2[] = {
 	{ "cfi", 0x0d, INSTR_RIL_RI },
 	{ "clgfi", 0x0e, INSTR_RIL_RU },
 	{ "clfi", 0x0f, INSTR_RIL_RU },
+	{ "msfi", 0x01, INSTR_RIL_RI },
+	{ "msgfi", 0x00, INSTR_RIL_RI },
+#endif
+	{ "", 0, INSTR_INVALID }
+};
+
+static struct insn opcode_c4[] = {
+#ifdef CONFIG_64BIT
+	{ "lrl", 0x0d, INSTR_RIL_RP },
+	{ "lgrl", 0x08, INSTR_RIL_RP },
+	{ "lgfrl", 0x0c, INSTR_RIL_RP },
+	{ "lhrl", 0x05, INSTR_RIL_RP },
+	{ "lghrl", 0x04, INSTR_RIL_RP },
+	{ "llgfrl", 0x0e, INSTR_RIL_RP },
+	{ "llhrl", 0x02, INSTR_RIL_RP },
+	{ "llghrl", 0x06, INSTR_RIL_RP },
+	{ "strl", 0x0f, INSTR_RIL_RP },
+	{ "stgrl", 0x0b, INSTR_RIL_RP },
+	{ "sthrl", 0x07, INSTR_RIL_RP },
+#endif
+	{ "", 0, INSTR_INVALID }
+};
+
+static struct insn opcode_c6[] = {
+#ifdef CONFIG_64BIT
+	{ "crl", 0x0d, INSTR_RIL_RP },
+	{ "cgrl", 0x08, INSTR_RIL_RP },
+	{ "cgfrl", 0x0c, INSTR_RIL_RP },
+	{ "chrl", 0x05, INSTR_RIL_RP },
+	{ "cghrl", 0x04, INSTR_RIL_RP },
+	{ "clrl", 0x0f, INSTR_RIL_RP },
+	{ "clgrl", 0x0a, INSTR_RIL_RP },
+	{ "clgfrl", 0x0e, INSTR_RIL_RP },
+	{ "clhrl", 0x07, INSTR_RIL_RP },
+	{ "clghrl", 0x06, INSTR_RIL_RP },
+	{ "pfdrl", 0x02, INSTR_RIL_UP },
+	{ "exrl", 0x00, INSTR_RIL_RP },
 #endif
 	{ "", 0, INSTR_INVALID }
 };
@@ -842,6 +980,8 @@ static struct insn opcode_c2[] = {
 static struct insn opcode_c8[] = {
 #ifdef CONFIG_64BIT
 	{ "mvcos", 0x00, INSTR_SSF_RRDRD },
+	{ "ectg", 0x01, INSTR_SSF_RRDRD },
+	{ "csst", 0x02, INSTR_SSF_RRDRD },
 #endif
 	{ "", 0, INSTR_INVALID }
 };
@@ -917,6 +1057,12 @@ static struct insn opcode_e3[] = {
 	{ "llgh", 0x91, INSTR_RXY_RRRD },
 	{ "llc", 0x94, INSTR_RXY_RRRD },
 	{ "llh", 0x95, INSTR_RXY_RRRD },
+	{ "cgh", 0x34, INSTR_RXY_RRRD },
+	{ "laey", 0x75, INSTR_RXY_RRRD },
+	{ "ltgf", 0x32, INSTR_RXY_RRRD },
+	{ "mfy", 0x5c, INSTR_RXY_RRRD },
+	{ "mhy", 0x7c, INSTR_RXY_RRRD },
+	{ "pfd", 0x36, INSTR_RXY_URRD },
 #endif
 	{ "lrv", 0x1e, INSTR_RXY_RRRD },
 	{ "lrvh", 0x1f, INSTR_RXY_RRRD },
@@ -931,6 +1077,15 @@ static struct insn opcode_e3[] = {
 static struct insn opcode_e5[] = {
 #ifdef CONFIG_64BIT
 	{ "strag", 0x02, INSTR_SSE_RDRD },
+	{ "chhsi", 0x54, INSTR_SIL_RDI },
+	{ "chsi", 0x5c, INSTR_SIL_RDI },
+	{ "cghsi", 0x58, INSTR_SIL_RDI },
+	{ "clhhsi", 0x55, INSTR_SIL_RDU },
+	{ "clfhsi", 0x5d, INSTR_SIL_RDU },
+	{ "clghsi", 0x59, INSTR_SIL_RDU },
+	{ "mvhhi", 0x44, INSTR_SIL_RDI },
+	{ "mvhi", 0x4c, INSTR_SIL_RDI },
+	{ "mvghi", 0x48, INSTR_SIL_RDI },
 #endif
 	{ "lasp", 0x00, INSTR_SSE_RDRD },
 	{ "tprot", 0x01, INSTR_SSE_RDRD },
@@ -977,6 +1132,11 @@ static struct insn opcode_eb[] = {
 	{ "lmy", 0x98, INSTR_RSY_RRRD },
 	{ "lamy", 0x9a, INSTR_RSY_AARD },
 	{ "stamy", 0x9b, INSTR_RSY_AARD },
+	{ "asi", 0x6a, INSTR_SIY_IRD },
+	{ "agsi", 0x7a, INSTR_SIY_IRD },
+	{ "alsi", 0x6e, INSTR_SIY_IRD },
+	{ "algsi", 0x7e, INSTR_SIY_IRD },
+	{ "ecag", 0x4c, INSTR_RSY_RRRD },
 #endif
 	{ "rll", 0x1d, INSTR_RSY_RRRD },
 	{ "mvclu", 0x8e, INSTR_RSY_RRRD },
@@ -988,6 +1148,30 @@ static struct insn opcode_ec[] = {
 #ifdef CONFIG_64BIT
 	{ "brxhg", 0x44, INSTR_RIE_RRP },
 	{ "brxlg", 0x45, INSTR_RIE_RRP },
+	{ "crb", 0xf6, INSTR_RRS_RRRDU },
+	{ "cgrb", 0xe4, INSTR_RRS_RRRDU },
+	{ "crj", 0x76, INSTR_RIE_RRPU },
+	{ "cgrj", 0x64, INSTR_RIE_RRPU },
+	{ "cib", 0xfe, INSTR_RIS_RURDI },
+	{ "cgib", 0xfc, INSTR_RIS_RURDI },
+	{ "cij", 0x7e, INSTR_RIE_RUPI },
+	{ "cgij", 0x7c, INSTR_RIE_RUPI },
+	{ "cit", 0x72, INSTR_RIE_R0IU },
+	{ "cgit", 0x70, INSTR_RIE_R0IU },
+	{ "clrb", 0xf7, INSTR_RRS_RRRDU },
+	{ "clgrb", 0xe5, INSTR_RRS_RRRDU },
+	{ "clrj", 0x77, INSTR_RIE_RRPU },
+	{ "clgrj", 0x65, INSTR_RIE_RRPU },
+	{ "clib", 0xff, INSTR_RIS_RURDU },
+	{ "clgib", 0xfd, INSTR_RIS_RURDU },
+	{ "clij", 0x7f, INSTR_RIE_RUPU },
+	{ "clgij", 0x7d, INSTR_RIE_RUPU },
+	{ "clfit", 0x73, INSTR_RIE_R0UU },
+	{ "clgit", 0x71, INSTR_RIE_R0UU },
+	{ "rnsbg", 0x54, INSTR_RIE_RRUUU },
+	{ "rxsbg", 0x57, INSTR_RIE_RRUUU },
+	{ "rosbg", 0x56, INSTR_RIE_RRUUU },
+	{ "risbg", 0x55, INSTR_RIE_RRUUU },
 #endif
 	{ "", 0, INSTR_INVALID }
 };
@@ -1004,6 +1188,16 @@ static struct insn opcode_ed[] = {
 	{ "ldy", 0x65, INSTR_RXY_FRRD },
 	{ "stey", 0x66, INSTR_RXY_FRRD },
 	{ "stdy", 0x67, INSTR_RXY_FRRD },
+	{ "sldt", 0x40, INSTR_RXF_FRRDF },
+	{ "slxt", 0x48, INSTR_RXF_FRRDF },
+	{ "srdt", 0x41, INSTR_RXF_FRRDF },
+	{ "srxt", 0x49, INSTR_RXF_FRRDF },
+	{ "tdcet", 0x50, INSTR_RXE_FRRD },
+	{ "tdcdt", 0x54, INSTR_RXE_FRRD },
+	{ "tdcxt", 0x58, INSTR_RXE_FRRD },
+	{ "tdget", 0x51, INSTR_RXE_FRRD },
+	{ "tdgdt", 0x55, INSTR_RXE_FRRD },
+	{ "tdgxt", 0x59, INSTR_RXE_FRRD },
 #endif
 	{ "ldeb", 0x04, INSTR_RXE_FRRD },
 	{ "lxdb", 0x05, INSTR_RXE_FRRD },
@@ -1037,6 +1231,7 @@ static struct insn opcode_ed[] = {
 	{ "mae", 0x2e, INSTR_RXF_FRRDF },
 	{ "mse", 0x2f, INSTR_RXF_FRRDF },
 	{ "sqe", 0x34, INSTR_RXE_FRRD },
+	{ "sqd", 0x35, INSTR_RXE_FRRD },
 	{ "mee", 0x37, INSTR_RXE_FRRD },
 	{ "mad", 0x3e, INSTR_RXF_FRRDF },
 	{ "msd", 0x3f, INSTR_RXF_FRRDF },
@@ -1117,6 +1312,12 @@ static struct insn *find_insn(unsigned char *code)
 	case 0xc2:
 		table = opcode_c2;
 		break;
+	case 0xc4:
+		table = opcode_c4;
+		break;
+	case 0xc6:
+		table = opcode_c6;
+		break;
 	case 0xc8:
 		table = opcode_c8;
 		break;
diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c
index e49e9e0c69f..c00856ad4e5 100644
--- a/arch/s390/kernel/early.c
+++ b/arch/s390/kernel/early.c
@@ -82,7 +82,8 @@ asm(
 	"	lm	6,15,24(15)\n"
 #endif
 	"	br	14\n"
-	"	.size	savesys_ipl_nss, .-savesys_ipl_nss\n");
+	"	.size	savesys_ipl_nss, .-savesys_ipl_nss\n"
+	"	.previous\n");
 
 static __initdata char upper_command_line[COMMAND_LINE_SIZE];
 
@@ -214,10 +215,13 @@ static __initdata struct sysinfo_3_2_2 vmms __aligned(PAGE_SIZE);
 
 static noinline __init void detect_machine_type(void)
 {
-	/* No VM information? Looks like LPAR */
-	if (stsi(&vmms, 3, 2, 2) == -ENOSYS)
+	/* Check current-configuration-level */
+	if ((stsi(NULL, 0, 0, 0) >> 28) <= 2) {
+		S390_lowcore.machine_flags |= MACHINE_FLAG_LPAR;
 		return;
-	if (!vmms.count)
+	}
+	/* Get virtual-machine cpu information. */
+	if (stsi(&vmms, 3, 2, 2) == -ENOSYS || !vmms.count)
 		return;
 
 	/* Running under KVM? If not we assume z/VM */
@@ -352,6 +356,7 @@ static __init void detect_machine_facilities(void)
 {
 #ifdef CONFIG_64BIT
 	unsigned int facilities;
+	unsigned long long facility_bits;
 
 	facilities = stfl();
 	if (facilities & (1 << 28))
@@ -360,6 +365,9 @@ static __init void detect_machine_facilities(void)
 		S390_lowcore.machine_flags |= MACHINE_FLAG_PFMF;
 	if (facilities & (1 << 4))
 		S390_lowcore.machine_flags |= MACHINE_FLAG_MVCOS;
+	if ((stfle(&facility_bits, 1) > 0) &&
+	    (facility_bits & (1ULL << (63 - 40))))
+		S390_lowcore.machine_flags |= MACHINE_FLAG_SPP;
 #endif
 }
 
@@ -402,8 +410,19 @@ static void __init append_to_cmdline(size_t (*ipl_data)(char *, size_t))
 
 static void __init setup_boot_command_line(void)
 {
+	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;
+
 	/* copy arch command line */
-	strlcpy(boot_command_line, COMMAND_LINE, ARCH_COMMAND_LINE_SIZE);
+	strlcpy(boot_command_line, strstrip(COMMAND_LINE),
+		ARCH_COMMAND_LINE_SIZE);
 
 	/* append IPL PARM data to the boot command line */
 	if (MACHINE_IS_VM)
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index e8ef21c51bb..bea9ee37ac9 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -13,7 +13,6 @@
 #include <linux/linkage.h>
 #include <linux/init.h>
 #include <asm/cache.h>
-#include <asm/lowcore.h>
 #include <asm/errno.h>
 #include <asm/ptrace.h>
 #include <asm/thread_info.h>
@@ -74,21 +73,24 @@ STACK_SIZE  = 1 << STACK_SHIFT
 	basr	%r14,%r1
 	.endm
 
-	.macro	TRACE_IRQS_CHECK
-	basr	%r2,%r0
+	.macro	TRACE_IRQS_CHECK_ON
 	tm	SP_PSW(%r15),0x03	# irqs enabled?
-	jz	0f
-	l	%r1,BASED(.Ltrace_irq_on_caller)
-	basr	%r14,%r1
-	j	1f
-0:	l	%r1,BASED(.Ltrace_irq_off_caller)
-	basr	%r14,%r1
-1:
+	bz	BASED(0f)
+	TRACE_IRQS_ON
+0:
+	.endm
+
+	.macro	TRACE_IRQS_CHECK_OFF
+	tm	SP_PSW(%r15),0x03	# irqs enabled?
+	bz	BASED(0f)
+	TRACE_IRQS_OFF
+0:
 	.endm
 #else
 #define TRACE_IRQS_ON
 #define TRACE_IRQS_OFF
-#define TRACE_IRQS_CHECK
+#define TRACE_IRQS_CHECK_ON
+#define TRACE_IRQS_CHECK_OFF
 #endif
 
 #ifdef CONFIG_LOCKDEP
@@ -178,9 +180,9 @@ STACK_SIZE  = 1 << STACK_SHIFT
 	s	%r15,BASED(.Lc_spsize)	# make room for registers & psw
 	mvc	SP_PSW(8,%r15),0(%r12)	# move user PSW to stack
 	st	%r2,SP_ORIG_R2(%r15)	# store original content of gpr 2
-	icm	%r12,3,__LC_SVC_ILC
+	icm	%r12,12,__LC_SVC_ILC
 	stm	%r0,%r11,SP_R0(%r15)	# store gprs %r0-%r11 to kernel stack
-	st	%r12,SP_SVCNR(%r15)
+	st	%r12,SP_ILC(%r15)
 	mvc	SP_R12(16,%r15),\savearea # move %r12-%r15 to stack
 	la	%r12,0
 	st	%r12,__SF_BACKCHAIN(%r15)	# clear back chain
@@ -274,66 +276,45 @@ sysc_do_restart:
 	st	%r2,SP_R2(%r15)   # store return value (change R2 on stack)
 
 sysc_return:
+	LOCKDEP_SYS_EXIT
+sysc_tif:
 	tm	__TI_flags+3(%r9),_TIF_WORK_SVC
 	bnz	BASED(sysc_work)  # there is work to do (signals etc.)
 sysc_restore:
-#ifdef CONFIG_TRACE_IRQFLAGS
-	la	%r1,BASED(sysc_restore_trace_psw_addr)
-	l	%r1,0(%r1)
-	lpsw	0(%r1)
-sysc_restore_trace:
-	TRACE_IRQS_CHECK
-	LOCKDEP_SYS_EXIT
-#endif
-sysc_leave:
 	RESTORE_ALL __LC_RETURN_PSW,1
 sysc_done:
 
-#ifdef CONFIG_TRACE_IRQFLAGS
-sysc_restore_trace_psw_addr:
-	.long sysc_restore_trace_psw
-
-	.section .data,"aw",@progbits
-	.align	8
-	.globl	sysc_restore_trace_psw
-sysc_restore_trace_psw:
-	.long	0, sysc_restore_trace + 0x80000000
-	.previous
-#endif
-
 #
-# recheck if there is more work to do
-#
-sysc_work_loop:
-	tm	__TI_flags+3(%r9),_TIF_WORK_SVC
-	bz	BASED(sysc_restore)	# there is no work to do
-#
-# One of the work bits is on. Find out which one.
+# There is work to do, but first we need to check if we return to userspace.
 #
 sysc_work:
 	tm	SP_PSW+1(%r15),0x01	# returning to user ?
 	bno	BASED(sysc_restore)
+
+#
+# One of the work bits is on. Find out which one.
+#
+sysc_work_tif:
 	tm	__TI_flags+3(%r9),_TIF_MCCK_PENDING
 	bo	BASED(sysc_mcck_pending)
 	tm	__TI_flags+3(%r9),_TIF_NEED_RESCHED
 	bo	BASED(sysc_reschedule)
 	tm	__TI_flags+3(%r9),_TIF_SIGPENDING
-	bnz	BASED(sysc_sigpending)
+	bo	BASED(sysc_sigpending)
 	tm	__TI_flags+3(%r9),_TIF_NOTIFY_RESUME
-	bnz	BASED(sysc_notify_resume)
+	bo	BASED(sysc_notify_resume)
 	tm	__TI_flags+3(%r9),_TIF_RESTART_SVC
 	bo	BASED(sysc_restart)
 	tm	__TI_flags+3(%r9),_TIF_SINGLE_STEP
 	bo	BASED(sysc_singlestep)
-	b	BASED(sysc_restore)
-sysc_work_done:
+	b	BASED(sysc_return)	# beware of critical section cleanup
 
 #
 # _TIF_NEED_RESCHED is set, call schedule
 #
 sysc_reschedule:
 	l	%r1,BASED(.Lschedule)
-	la	%r14,BASED(sysc_work_loop)
+	la	%r14,BASED(sysc_return)
 	br	%r1			# call scheduler
 
 #
@@ -341,7 +322,7 @@ sysc_reschedule:
 #
 sysc_mcck_pending:
 	l	%r1,BASED(.Ls390_handle_mcck)
-	la	%r14,BASED(sysc_work_loop)
+	la	%r14,BASED(sysc_return)
 	br	%r1			# TIF bit will be cleared by handler
 
 #
@@ -356,7 +337,7 @@ sysc_sigpending:
 	bo	BASED(sysc_restart)
 	tm	__TI_flags+3(%r9),_TIF_SINGLE_STEP
 	bo	BASED(sysc_singlestep)
-	b	BASED(sysc_work_loop)
+	b	BASED(sysc_return)
 
 #
 # _TIF_NOTIFY_RESUME is set, call do_notify_resume
@@ -364,7 +345,7 @@ sysc_sigpending:
 sysc_notify_resume:
 	la	%r2,SP_PTREGS(%r15)	# load pt_regs
 	l	%r1,BASED(.Ldo_notify_resume)
-	la	%r14,BASED(sysc_work_loop)
+	la	%r14,BASED(sysc_return)
 	br	%r1			# call do_notify_resume
 
 
@@ -459,11 +440,13 @@ kernel_execve:
 	br	%r14
 	# execve succeeded.
 0:	stnsm	__SF_EMPTY(%r15),0xfc	# disable interrupts
+	TRACE_IRQS_OFF
 	l	%r15,__LC_KERNEL_STACK	# load ksp
 	s	%r15,BASED(.Lc_spsize)	# make room for registers & psw
 	l	%r9,__LC_THREAD_INFO
 	mvc	SP_PTREGS(__PT_SIZE,%r15),0(%r12)	# copy pt_regs
 	xc	__SF_BACKCHAIN(4,%r15),__SF_BACKCHAIN(%r15)
+	TRACE_IRQS_ON
 	stosm	__SF_EMPTY(%r15),0x03	# reenable interrupts
 	l	%r1,BASED(.Lexecve_tail)
 	basr	%r14,%r1
@@ -500,8 +483,8 @@ pgm_check_handler:
 	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:
+	TRACE_IRQS_CHECK_OFF
 	l	%r9,__LC_THREAD_INFO	# load pointer to thread_info struct
-	TRACE_IRQS_OFF
 	l	%r3,__LC_PGM_ILC	# load program interruption code
 	la	%r8,0x7f
 	nr	%r8,%r3
@@ -510,8 +493,10 @@ pgm_do_call:
 	sll	%r8,2
 	l	%r7,0(%r8,%r7)		# load address of handler routine
 	la	%r2,SP_PTREGS(%r15)	# address of register-save area
-	la	%r14,BASED(sysc_return)
-	br	%r7			# branch to interrupt-handler
+	basr	%r14,%r7		# branch to interrupt-handler
+pgm_exit:
+	TRACE_IRQS_CHECK_ON
+	b	BASED(sysc_return)
 
 #
 # handle per exception
@@ -538,20 +523,28 @@ pgm_per_std:
 	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:
+	TRACE_IRQS_CHECK_OFF
 	l	%r9,__LC_THREAD_INFO	# load pointer to thread_info struct
-	TRACE_IRQS_OFF
 	l	%r1,__TI_task(%r9)
+	tm	SP_PSW+1(%r15),0x01	# kernel per event ?
+	bz	BASED(kernel_per)
 	mvc	__THREAD_per+__PER_atmid(2,%r1),__LC_PER_ATMID
 	mvc	__THREAD_per+__PER_address(4,%r1),__LC_PER_ADDRESS
 	mvc	__THREAD_per+__PER_access_id(1,%r1),__LC_PER_ACCESS_ID
 	oi	__TI_flags+3(%r9),_TIF_SINGLE_STEP # set TIF_SINGLE_STEP
-	tm	SP_PSW+1(%r15),0x01	# kernel per event ?
-	bz	BASED(kernel_per)
 	l	%r3,__LC_PGM_ILC	# load program interruption code
 	la	%r8,0x7f
 	nr	%r8,%r3 		# clear per-event-bit and ilc
-	be	BASED(sysc_return)	# only per or per+check ?
-	b	BASED(pgm_do_call)
+	be	BASED(pgm_exit2)	# only per or per+check ?
+	l	%r7,BASED(.Ljump_table)
+	sll	%r8,2
+	l	%r7,0(%r8,%r7)		# load address of handler routine
+	la	%r2,SP_PTREGS(%r15)	# address of register-save area
+	basr	%r14,%r7		# branch to interrupt-handler
+pgm_exit2:
+	TRACE_IRQS_ON
+	stosm	__SF_EMPTY(%r15),0x03	# reenable interrupts
+	b	BASED(sysc_return)
 
 #
 # it was a single stepped SVC that is causing all the trouble
@@ -571,8 +564,8 @@ pgm_svcper:
 	mvc	__THREAD_per+__PER_access_id(1,%r8),__LC_PER_ACCESS_ID
 	oi	__TI_flags+3(%r9),_TIF_SINGLE_STEP # set TIF_SINGLE_STEP
 	TRACE_IRQS_ON
-	lm	%r2,%r6,SP_R2(%r15)	# load svc arguments
 	stosm	__SF_EMPTY(%r15),0x03	# reenable interrupts
+	lm	%r2,%r6,SP_R2(%r15)	# load svc arguments
 	b	BASED(sysc_do_svc)
 
 #
@@ -583,8 +576,8 @@ kernel_per:
 	mvi	SP_SVCNR+1(%r15),0xff
 	la	%r2,SP_PTREGS(%r15)	# address of register-save area
 	l	%r1,BASED(.Lhandle_per)	# load adr. of per handler
-	la	%r14,BASED(sysc_restore)# load adr. of system return
-	br	%r1			# branch to do_single_step
+	basr	%r14,%r1		# branch to do_single_step
+	b	BASED(pgm_exit)
 
 /*
  * IO interrupt handler routine
@@ -603,134 +596,126 @@ io_int_handler:
 	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:
-	l	%r9,__LC_THREAD_INFO	# load pointer to thread_info struct
 	TRACE_IRQS_OFF
+	l	%r9,__LC_THREAD_INFO	# load pointer to thread_info struct
 	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
 io_return:
+	LOCKDEP_SYS_EXIT
+	TRACE_IRQS_ON
+io_tif:
 	tm	__TI_flags+3(%r9),_TIF_WORK_INT
 	bnz	BASED(io_work)		# there is work to do (signals etc.)
 io_restore:
-#ifdef CONFIG_TRACE_IRQFLAGS
-	la	%r1,BASED(io_restore_trace_psw_addr)
-	l	%r1,0(%r1)
-	lpsw	0(%r1)
-io_restore_trace:
-	TRACE_IRQS_CHECK
-	LOCKDEP_SYS_EXIT
-#endif
-io_leave:
 	RESTORE_ALL __LC_RETURN_PSW,0
 io_done:
 
-#ifdef CONFIG_TRACE_IRQFLAGS
-io_restore_trace_psw_addr:
-	.long io_restore_trace_psw
-
-	.section .data,"aw",@progbits
-	.align	8
-	.globl	io_restore_trace_psw
-io_restore_trace_psw:
-	.long	0, io_restore_trace + 0x80000000
-	.previous
-#endif
-
 #
-# switch to kernel stack, then check the TIF bits
+# There is work todo, find out in which context we have been interrupted:
+# 1) if we return to user space we can do all _TIF_WORK_INT work
+# 2) if we return to kernel code and preemptive scheduling is enabled check
+#    the preemption counter and if it is zero call preempt_schedule_irq
+# Before any work can be done, a switch to the kernel stack is required.
 #
 io_work:
 	tm	SP_PSW+1(%r15),0x01	# returning to user ?
-#ifndef CONFIG_PREEMPT
-	bno	BASED(io_restore)	# no-> skip resched & signal
-#else
-	bnz	BASED(io_work_user)	# no -> check for preemptive scheduling
+	bo	BASED(io_work_user)	# yes -> do resched & signal
+#ifdef CONFIG_PREEMPT
 	# check for preemptive scheduling
 	icm	%r0,15,__TI_precount(%r9)
 	bnz	BASED(io_restore)	# preemption disabled
+	tm	__TI_flags+3(%r9),_TIF_NEED_RESCHED
+	bno	BASED(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
 	lr	%r15,%r1
-io_resume_loop:
-	tm	__TI_flags+3(%r9),_TIF_NEED_RESCHED
-	bno	BASED(io_restore)
+	# 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)
-	la	%r14,BASED(io_resume_loop)
-	br	%r1			# call schedule
+	basr	%r14,%r1		# call preempt_schedule_irq
+	b	BASED(io_return)
+#else
+	b	BASED(io_restore)
 #endif
 
+#
+# Need to do work before returning to userspace, switch to kernel stack
+#
 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
 	lr	%r15,%r1
+
 #
 # One of the work bits is on. Find out which one.
-# Checked are: _TIF_SIGPENDING, _TIF_NEED_RESCHED
+# Checked are: _TIF_SIGPENDING, _TIF_NOTIFY_RESUME, _TIF_NEED_RESCHED
 #		and _TIF_MCCK_PENDING
 #
-io_work_loop:
+io_work_tif:
 	tm	__TI_flags+3(%r9),_TIF_MCCK_PENDING
 	bo	BASED(io_mcck_pending)
 	tm	__TI_flags+3(%r9),_TIF_NEED_RESCHED
 	bo	BASED(io_reschedule)
 	tm	__TI_flags+3(%r9),_TIF_SIGPENDING
-	bnz	BASED(io_sigpending)
+	bo	BASED(io_sigpending)
 	tm	__TI_flags+3(%r9),_TIF_NOTIFY_RESUME
-	bnz	BASED(io_notify_resume)
-	b	BASED(io_restore)
-io_work_done:
+	bo	BASED(io_notify_resume)
+	b	BASED(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)
 	basr	%r14,%r1		# TIF bit will be cleared by handler
-	b	BASED(io_work_loop)
+	TRACE_IRQS_OFF
+	b	BASED(io_return)
 
 #
 # _TIF_NEED_RESCHED is set, call schedule
 #
 io_reschedule:
-	TRACE_IRQS_ON
+	# TRACE_IRQS_ON already done at io_return
 	l	%r1,BASED(.Lschedule)
 	stosm	__SF_EMPTY(%r15),0x03	# reenable interrupts
 	basr	%r14,%r1		# call scheduler
 	stnsm	__SF_EMPTY(%r15),0xfc	# disable I/O and ext. interrupts
 	TRACE_IRQS_OFF
-	tm	__TI_flags+3(%r9),_TIF_WORK_INT
-	bz	BASED(io_restore)	# there is no work to do
-	b	BASED(io_work_loop)
+	b	BASED(io_return)
 
 #
 # _TIF_SIGPENDING is set, call do_signal
 #
 io_sigpending:
-	TRACE_IRQS_ON
+	# 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)
 	basr	%r14,%r1		# call do_signal
 	stnsm	__SF_EMPTY(%r15),0xfc	# disable I/O and ext. interrupts
 	TRACE_IRQS_OFF
-	b	BASED(io_work_loop)
+	b	BASED(io_return)
 
 #
 # _TIF_SIGPENDING is set, call do_signal
 #
 io_notify_resume:
-	TRACE_IRQS_ON
+	# 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
 	TRACE_IRQS_OFF
-	b	BASED(io_work_loop)
+	b	BASED(io_return)
 
 /*
  * External interrupt handler routine
@@ -765,15 +750,14 @@ __critical_end:
 
 	.globl mcck_int_handler
 mcck_int_handler:
-	stck	__LC_INT_CLOCK
+	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
 	tm	__LC_MCCK_CODE,0x80	# system damage?
 	bo	BASED(mcck_int_main)	# yes -> rest of mcck code invalid
-	mvc	__LC_SAVE_AREA+52(8),__LC_ASYNC_ENTER_TIMER
-	mvc	__LC_ASYNC_ENTER_TIMER(8),__LC_CPU_TIMER_SAVE_AREA
+	mvc	__LC_MCCK_ENTER_TIMER(8),__LC_CPU_TIMER_SAVE_AREA
 	tm	__LC_MCCK_CODE+5,0x02	# stored cpu timer value valid?
 	bo	BASED(1f)
 	la	%r14,__LC_SYNC_ENTER_TIMER
@@ -787,7 +771,7 @@ mcck_int_handler:
 	bl	BASED(0f)
 	la	%r14,__LC_LAST_UPDATE_TIMER
 0:	spt	0(%r14)
-	mvc	__LC_ASYNC_ENTER_TIMER(8),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
@@ -809,9 +793,9 @@ mcck_int_main:
 	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_ASYNC_ENTER_TIMER,__LC_USER_TIMER
+	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_ASYNC_ENTER_TIMER
+	mvc	__LC_LAST_UPDATE_TIMER(8),__LC_MCCK_ENTER_TIMER
 mcck_no_vtime:
 	l	%r9,__LC_THREAD_INFO	# load pointer to thread_info struct
 	la	%r2,SP_PTREGS(%r15)	# load pt_regs
@@ -834,7 +818,6 @@ mcck_no_vtime:
 mcck_return:
 	mvc	__LC_RETURN_MCCK_PSW(8),SP_PSW(%r15) # move return PSW
 	ni	__LC_RETURN_MCCK_PSW+1,0xfd # clear wait state bit
-	mvc	__LC_ASYNC_ENTER_TIMER(8),__LC_SAVE_AREA+52
 	tm	__LC_RETURN_MCCK_PSW+1,0x01 # returning to user ?
 	bno	BASED(0f)
 	lm	%r0,%r15,SP_R0(%r15)	# load gprs 0-15
@@ -918,18 +901,14 @@ stack_overflow:
 
 cleanup_table_system_call:
 	.long	system_call + 0x80000000, sysc_do_svc + 0x80000000
-cleanup_table_sysc_return:
-	.long	sysc_return + 0x80000000, sysc_leave + 0x80000000
-cleanup_table_sysc_leave:
-	.long	sysc_leave + 0x80000000, sysc_done + 0x80000000
-cleanup_table_sysc_work_loop:
-	.long	sysc_work_loop + 0x80000000, sysc_work_done + 0x80000000
-cleanup_table_io_return:
-	.long	io_return + 0x80000000, io_leave + 0x80000000
-cleanup_table_io_leave:
-	.long	io_leave + 0x80000000, io_done + 0x80000000
-cleanup_table_io_work_loop:
-	.long	io_work_loop + 0x80000000, io_work_done + 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_critical:
 	clc	4(4,%r12),BASED(cleanup_table_system_call)
@@ -937,49 +916,40 @@ cleanup_critical:
 	clc	4(4,%r12),BASED(cleanup_table_system_call+4)
 	bl	BASED(cleanup_system_call)
 0:
-	clc	4(4,%r12),BASED(cleanup_table_sysc_return)
-	bl	BASED(0f)
-	clc	4(4,%r12),BASED(cleanup_table_sysc_return+4)
-	bl	BASED(cleanup_sysc_return)
-0:
-	clc	4(4,%r12),BASED(cleanup_table_sysc_leave)
+	clc	4(4,%r12),BASED(cleanup_table_sysc_tif)
 	bl	BASED(0f)
-	clc	4(4,%r12),BASED(cleanup_table_sysc_leave+4)
-	bl	BASED(cleanup_sysc_leave)
+	clc	4(4,%r12),BASED(cleanup_table_sysc_tif+4)
+	bl	BASED(cleanup_sysc_tif)
 0:
-	clc	4(4,%r12),BASED(cleanup_table_sysc_work_loop)
+	clc	4(4,%r12),BASED(cleanup_table_sysc_restore)
 	bl	BASED(0f)
-	clc	4(4,%r12),BASED(cleanup_table_sysc_work_loop+4)
-	bl	BASED(cleanup_sysc_return)
+	clc	4(4,%r12),BASED(cleanup_table_sysc_restore+4)
+	bl	BASED(cleanup_sysc_restore)
 0:
-	clc	4(4,%r12),BASED(cleanup_table_io_return)
+	clc	4(4,%r12),BASED(cleanup_table_io_tif)
 	bl	BASED(0f)
-	clc	4(4,%r12),BASED(cleanup_table_io_return+4)
-	bl	BASED(cleanup_io_return)
+	clc	4(4,%r12),BASED(cleanup_table_io_tif+4)
+	bl	BASED(cleanup_io_tif)
 0:
-	clc	4(4,%r12),BASED(cleanup_table_io_leave)
+	clc	4(4,%r12),BASED(cleanup_table_io_restore)
 	bl	BASED(0f)
-	clc	4(4,%r12),BASED(cleanup_table_io_leave+4)
-	bl	BASED(cleanup_io_leave)
-0:
-	clc	4(4,%r12),BASED(cleanup_table_io_work_loop)
-	bl	BASED(0f)
-	clc	4(4,%r12),BASED(cleanup_table_io_work_loop+4)
-	bl	BASED(cleanup_io_return)
+	clc	4(4,%r12),BASED(cleanup_table_io_restore+4)
+	bl	BASED(cleanup_io_restore)
 0:
 	br	%r14
 
 cleanup_system_call:
 	mvc	__LC_RETURN_PSW(8),0(%r12)
-	c	%r12,BASED(.Lmck_old_psw)
-	be	BASED(0f)
-	la	%r12,__LC_SAVE_AREA+16
-	b	BASED(1f)
-0:	la	%r12,__LC_SAVE_AREA+32
-1:
 	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)
 	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)
@@ -1012,55 +982,54 @@ cleanup_system_call_insn:
 	.long	sysc_stime + 0x80000000
 	.long	sysc_update + 0x80000000
 
-cleanup_sysc_return:
+cleanup_sysc_tif:
 	mvc	__LC_RETURN_PSW(4),0(%r12)
-	mvc	__LC_RETURN_PSW+4(4),BASED(cleanup_table_sysc_return)
+	mvc	__LC_RETURN_PSW+4(4),BASED(cleanup_table_sysc_tif)
 	la	%r12,__LC_RETURN_PSW
 	br	%r14
 
-cleanup_sysc_leave:
-	clc	4(4,%r12),BASED(cleanup_sysc_leave_insn)
+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
-	clc	4(4,%r12),BASED(cleanup_sysc_leave_insn+4)
+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)
-	bne	BASED(0f)
-	mvc	__LC_SAVE_AREA+32(16),SP_R12(%r15)
-	b	BASED(1f)
-0:	mvc	__LC_SAVE_AREA+16(16),SP_R12(%r15)
-1:	lm	%r0,%r11,SP_R0(%r15)
+	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
 	br	%r14
-cleanup_sysc_leave_insn:
+cleanup_sysc_restore_insn:
 	.long	sysc_done - 4 + 0x80000000
 	.long	sysc_done - 8 + 0x80000000
 
-cleanup_io_return:
+cleanup_io_tif:
 	mvc	__LC_RETURN_PSW(4),0(%r12)
-	mvc	__LC_RETURN_PSW+4(4),BASED(cleanup_table_io_work_loop)
+	mvc	__LC_RETURN_PSW+4(4),BASED(cleanup_table_io_tif)
 	la	%r12,__LC_RETURN_PSW
 	br	%r14
 
-cleanup_io_leave:
-	clc	4(4,%r12),BASED(cleanup_io_leave_insn)
-	be	BASED(2f)
-	mvc	__LC_EXIT_TIMER(8),__LC_ASYNC_ENTER_TIMER
-	clc	4(4,%r12),BASED(cleanup_io_leave_insn+4)
-	be	BASED(2f)
+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)
-	c	%r12,BASED(.Lmck_old_psw)
-	bne	BASED(0f)
 	mvc	__LC_SAVE_AREA+32(16),SP_R12(%r15)
-	b	BASED(1f)
-0:	mvc	__LC_SAVE_AREA+16(16),SP_R12(%r15)
-1:	lm	%r0,%r11,SP_R0(%r15)
+	lm	%r0,%r11,SP_R0(%r15)
 	l	%r15,SP_R15(%r15)
-2:	la	%r12,__LC_RETURN_PSW
+1:	la	%r12,__LC_RETURN_PSW
 	br	%r14
-cleanup_io_leave_insn:
+cleanup_io_restore_insn:
 	.long	io_done - 4 + 0x80000000
 	.long	io_done - 8 + 0x80000000
 
diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h
index e1e5e767ab5..eb15c12ec15 100644
--- a/arch/s390/kernel/entry.h
+++ b/arch/s390/kernel/entry.h
@@ -24,17 +24,13 @@ int __cpuinit start_secondary(void *cpuvoid);
 void __init startup_init(void);
 void die(const char * str, struct pt_regs * regs, long err);
 
-struct new_utsname;
-struct mmap_arg_struct;
+struct s390_mmap_arg_struct;
 struct fadvise64_64_args;
 struct old_sigaction;
-struct sel_arg_struct;
 
-long sys_mmap2(struct mmap_arg_struct __user  *arg);
-long sys_s390_old_mmap(struct mmap_arg_struct __user *arg);
-long sys_ipc(uint call, int first, unsigned long second,
+long sys_mmap2(struct s390_mmap_arg_struct __user  *arg);
+long sys_s390_ipc(uint call, int first, unsigned long second,
 	     unsigned long third, void __user *ptr);
-long sys_s390_newuname(struct new_utsname __user *name);
 long sys_s390_personality(unsigned long personality);
 long sys_s390_fadvise64(int fd, u32 offset_high, u32 offset_low,
 		    size_t len, int advice);
diff --git a/arch/s390/kernel/entry64.S b/arch/s390/kernel/entry64.S
index f33658f09dd..8bccec15ea9 100644
--- a/arch/s390/kernel/entry64.S
+++ b/arch/s390/kernel/entry64.S
@@ -2,18 +2,16 @@
  *  arch/s390/kernel/entry64.S
  *    S390 low-level entry points.
  *
- *    Copyright (C) IBM Corp. 1999,2006
+ *    Copyright (C) IBM Corp. 1999,2010
  *    Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com),
  *		 Hartmut Penner (hp@de.ibm.com),
  *		 Denis Joseph Barrow (djbarrow@de.ibm.com,barrow_dj@yahoo.com),
  *		 Heiko Carstens <heiko.carstens@de.ibm.com>
  */
 
-#include <linux/sys.h>
 #include <linux/linkage.h>
 #include <linux/init.h>
 #include <asm/cache.h>
-#include <asm/lowcore.h>
 #include <asm/errno.h>
 #include <asm/ptrace.h>
 #include <asm/thread_info.h>
@@ -61,30 +59,45 @@ _TIF_SYSCALL = (_TIF_SYSCALL_TRACE>>8 | _TIF_SYSCALL_AUDIT>>8 | \
 
 #define BASED(name) name-system_call(%r13)
 
+	.macro	HANDLE_SIE_INTERCEPT
+#if defined(CONFIG_KVM) || defined(CONFIG_KVM_MODULE)
+	lg	%r3,__LC_SIE_HOOK
+	ltgr	%r3,%r3
+	jz	0f
+	basr	%r14,%r3
+0:
+#endif
+	.endm
+
 #ifdef CONFIG_TRACE_IRQFLAGS
 	.macro	TRACE_IRQS_ON
-	 basr	%r2,%r0
-	 brasl	%r14,trace_hardirqs_on_caller
+	basr	%r2,%r0
+	brasl	%r14,trace_hardirqs_on_caller
 	.endm
 
 	.macro	TRACE_IRQS_OFF
-	 basr	%r2,%r0
-	 brasl	%r14,trace_hardirqs_off_caller
+	basr	%r2,%r0
+	brasl	%r14,trace_hardirqs_off_caller
 	.endm
 
-	.macro TRACE_IRQS_CHECK
-	basr	%r2,%r0
+	.macro TRACE_IRQS_CHECK_ON
 	tm	SP_PSW(%r15),0x03	# irqs enabled?
 	jz	0f
-	brasl	%r14,trace_hardirqs_on_caller
-	j	1f
-0:	brasl	%r14,trace_hardirqs_off_caller
-1:
+	TRACE_IRQS_ON
+0:
+	.endm
+
+	.macro TRACE_IRQS_CHECK_OFF
+	tm	SP_PSW(%r15),0x03	# irqs enabled?
+	jz	0f
+	TRACE_IRQS_OFF
+0:
 	.endm
 #else
 #define TRACE_IRQS_ON
 #define TRACE_IRQS_OFF
-#define TRACE_IRQS_CHECK
+#define TRACE_IRQS_CHECK_ON
+#define TRACE_IRQS_CHECK_OFF
 #endif
 
 #ifdef CONFIG_LOCKDEP
@@ -113,31 +126,35 @@ _TIF_SYSCALL = (_TIF_SYSCALL_TRACE>>8 | _TIF_SYSCALL_AUDIT>>8 | \
  *    R15 - kernel stack pointer
  */
 
-	.macro	SAVE_ALL_BASE savearea
-	stmg	%r12,%r15,\savearea
-	larl	%r13,system_call
-	.endm
-
 	.macro	SAVE_ALL_SVC psworg,savearea
-	la	%r12,\psworg
+	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
 	.endm
 
-	.macro	SAVE_ALL_SYNC psworg,savearea
-	la	%r12,\psworg
+	.macro	SAVE_ALL_PGM psworg,savearea
+	stmg	%r11,%r15,\savearea
 	tm	\psworg+1,0x01		# test problem state bit
-	jz	2f			# skip stack setup save
-	lg	%r15,__LC_KERNEL_STACK	# problem state -> load ksp
 #ifdef CONFIG_CHECK_STACK
-	j	3f
-2:	tml	%r15,STACK_SIZE - CONFIG_STACK_GUARD
-	jz	stack_overflow
-3:
+	jnz	1f
+	tml	%r15,STACK_SIZE - CONFIG_STACK_GUARD
+	jnz	2f
+	la	%r12,\psworg
+	j	stack_overflow
+#else
+	jz	2f
 #endif
-2:
+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
@@ -151,27 +168,23 @@ _TIF_SYSCALL = (_TIF_SYSCALL_TRACE>>8 | _TIF_SYSCALL_AUDIT>>8 | \
 0:	lg	%r14,__LC_ASYNC_STACK	# are we already on the async. stack ?
 	slgr	%r14,%r15
 	srag	%r14,%r14,STACK_SHIFT
-	jz	2f
-1:	lg	%r15,__LC_ASYNC_STACK	# load async stack
 #ifdef CONFIG_CHECK_STACK
-	j	3f
-2:	tml	%r15,STACK_SIZE - CONFIG_STACK_GUARD
-	jz	stack_overflow
-3:
+	jnz	1f
+	tml	%r15,STACK_SIZE - CONFIG_STACK_GUARD
+	jnz	2f
+	j	stack_overflow
+#else
+	jz	2f
 #endif
-2:
+1:	lg	%r15,__LC_ASYNC_STACK	# load async stack
+2:	aghi	%r15,-SP_SIZE		# make room for registers & psw
 	.endm
 
-	.macro	CREATE_STACK_FRAME psworg,savearea
-	aghi	%r15,-SP_SIZE		# make room for registers & psw
-	mvc	SP_PSW(16,%r15),0(%r12)	# move user PSW to stack
+	.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
-	icm	%r12,3,__LC_SVC_ILC
-	stmg	%r0,%r11,SP_R0(%r15)	# store gprs %r0-%r11 to kernel stack
-	st	%r12,SP_SVCNR(%r15)
-	mvc	SP_R12(32,%r15),\savearea # move %r12-%r15 to stack
-	la	%r12,0
-	stg	%r12,__SF_BACKCHAIN(%r15)
+	mvc	SP_R11(40,%r15),\savearea # move %r11-%r15 to stack
+	stmg	%r0,%r10,SP_R0(%r15)	# store gprs %r0-%r10 to kernel stack
 	.endm
 
 	.macro	RESTORE_ALL psworg,sync
@@ -187,6 +200,13 @@ _TIF_SYSCALL = (_TIF_SYSCALL_TRACE>>8 | _TIF_SYSCALL_AUDIT>>8 | \
 	lpswe	\psworg			# back to caller
 	.endm
 
+	.macro	LAST_BREAK
+	srag	%r10,%r11,23
+	jz	0f
+	stg	%r11,__TI_last_break(%r12)
+0:
+	.endm
+
 /*
  * Scheduler resume function, called by switch_to
  *  gpr2 = (task_struct *) prev
@@ -232,143 +252,129 @@ __critical_start:
 system_call:
 	stpt	__LC_SYNC_ENTER_TIMER
 sysc_saveall:
-	SAVE_ALL_BASE __LC_SAVE_AREA
 	SAVE_ALL_SVC __LC_SVC_OLD_PSW,__LC_SAVE_AREA
-	CREATE_STACK_FRAME __LC_SVC_OLD_PSW,__LC_SAVE_AREA
-	llgh	%r7,__LC_SVC_INT_CODE	# get svc number from lowcore
+	CREATE_STACK_FRAME __LC_SAVE_AREA
+	mvc	SP_PSW(16,%r15),__LC_SVC_OLD_PSW
+	mvc	SP_ILC(4,%r15),__LC_SVC_ILC
+	stg	%r7,SP_ARGS(%r15)
+	lg	%r12,__LC_THREAD_INFO	# load pointer to thread_info struct
 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
 sysc_do_svc:
-	lg	%r9,__LC_THREAD_INFO	# load pointer to thread_info struct
-	ltgr	%r7,%r7		# test for svc 0
+	llgh	%r7,SP_SVCNR(%r15)
+	slag	%r7,%r7,2	# shift and test for svc 0
 	jnz	sysc_nr_ok
 	# svc 0: system call number in %r1
-	cl	%r1,BASED(.Lnr_syscalls)
+	llgfr	%r1,%r1		# clear high word in r1
+	cghi	%r1,NR_syscalls
 	jnl	sysc_nr_ok
-	lgfr	%r7,%r1 	# clear high word in r1
+	sth	%r1,SP_SVCNR(%r15)
+	slag	%r7,%r1,2	# shift and test for svc 0
 sysc_nr_ok:
-	mvc	SP_ARGS(8,%r15),SP_R7(%r15)
-sysc_do_restart:
-	sth	%r7,SP_SVCNR(%r15)
-	sllg	%r7,%r7,2	# svc number * 4
 	larl	%r10,sys_call_table
 #ifdef CONFIG_COMPAT
-	tm	__TI_flags+5(%r9),(_TIF_31BIT>>16)  # running in 31 bit mode ?
+	tm	__TI_flags+5(%r12),(_TIF_31BIT>>16)  # running in 31 bit mode ?
 	jno	sysc_noemu
 	larl	%r10,sys_call_table_emu  # use 31 bit emulation system calls
 sysc_noemu:
 #endif
-	tm	__TI_flags+6(%r9),_TIF_SYSCALL
+	tm	__TI_flags+6(%r12),_TIF_SYSCALL
 	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)
 
 sysc_return:
-	tm	__TI_flags+7(%r9),_TIF_WORK_SVC
+	LOCKDEP_SYS_EXIT
+sysc_tif:
+	tm	__TI_flags+7(%r12),_TIF_WORK_SVC
 	jnz	sysc_work	# there is work to do (signals etc.)
 sysc_restore:
-#ifdef CONFIG_TRACE_IRQFLAGS
-	larl	%r1,sysc_restore_trace_psw
-	lpswe	0(%r1)
-sysc_restore_trace:
-	TRACE_IRQS_CHECK
-	LOCKDEP_SYS_EXIT
-#endif
-sysc_leave:
 	RESTORE_ALL __LC_RETURN_PSW,1
 sysc_done:
 
-#ifdef CONFIG_TRACE_IRQFLAGS
-	.section .data,"aw",@progbits
-	.align	8
-	.globl sysc_restore_trace_psw
-sysc_restore_trace_psw:
-	.quad	0, sysc_restore_trace
-	.previous
-#endif
-
-#
-# recheck if there is more work to do
 #
-sysc_work_loop:
-	tm	__TI_flags+7(%r9),_TIF_WORK_SVC
-	jz	sysc_restore	  # there is no work to do
-#
-# One of the work bits is on. Find out which one.
+# There is work to do, but first we need to check if we return to userspace.
 #
 sysc_work:
 	tm	SP_PSW+1(%r15),0x01	# returning to user ?
 	jno	sysc_restore
-	tm	__TI_flags+7(%r9),_TIF_MCCK_PENDING
+
+#
+# One of the work bits is on. Find out which one.
+#
+sysc_work_tif:
+	tm	__TI_flags+7(%r12),_TIF_MCCK_PENDING
 	jo	sysc_mcck_pending
-	tm	__TI_flags+7(%r9),_TIF_NEED_RESCHED
+	tm	__TI_flags+7(%r12),_TIF_NEED_RESCHED
 	jo	sysc_reschedule
-	tm	__TI_flags+7(%r9),_TIF_SIGPENDING
-	jnz	sysc_sigpending
-	tm	__TI_flags+7(%r9),_TIF_NOTIFY_RESUME
-	jnz	sysc_notify_resume
-	tm	__TI_flags+7(%r9),_TIF_RESTART_SVC
+	tm	__TI_flags+7(%r12),_TIF_SIGPENDING
+	jo	sysc_sigpending
+	tm	__TI_flags+7(%r12),_TIF_NOTIFY_RESUME
+	jo	sysc_notify_resume
+	tm	__TI_flags+7(%r12),_TIF_RESTART_SVC
 	jo	sysc_restart
-	tm	__TI_flags+7(%r9),_TIF_SINGLE_STEP
+	tm	__TI_flags+7(%r12),_TIF_SINGLE_STEP
 	jo	sysc_singlestep
-	j	sysc_restore
-sysc_work_done:
+	j	sysc_return		# beware of critical section cleanup
 
 #
 # _TIF_NEED_RESCHED is set, call schedule
 #
 sysc_reschedule:
-	larl	%r14,sysc_work_loop
-	jg	schedule	# return point is sysc_return
+	larl	%r14,sysc_return
+	jg	schedule		# return point is sysc_return
 
 #
 # _TIF_MCCK_PENDING is set, call handler
 #
 sysc_mcck_pending:
-	larl	%r14,sysc_work_loop
+	larl	%r14,sysc_return
 	jg	s390_handle_mcck	# TIF bit will be cleared by handler
 
 #
 # _TIF_SIGPENDING is set, call do_signal
 #
 sysc_sigpending:
-	ni	__TI_flags+7(%r9),255-_TIF_SINGLE_STEP # clear TIF_SINGLE_STEP
+	ni	__TI_flags+7(%r12),255-_TIF_SINGLE_STEP # clear TIF_SINGLE_STEP
 	la	%r2,SP_PTREGS(%r15)	# load pt_regs
 	brasl	%r14,do_signal		# call do_signal
-	tm	__TI_flags+7(%r9),_TIF_RESTART_SVC
+	tm	__TI_flags+7(%r12),_TIF_RESTART_SVC
 	jo	sysc_restart
-	tm	__TI_flags+7(%r9),_TIF_SINGLE_STEP
+	tm	__TI_flags+7(%r12),_TIF_SINGLE_STEP
 	jo	sysc_singlestep
-	j	sysc_work_loop
+	j	sysc_return
 
 #
 # _TIF_NOTIFY_RESUME is set, call do_notify_resume
 #
 sysc_notify_resume:
 	la	%r2,SP_PTREGS(%r15)	# load pt_regs
-	larl	%r14,sysc_work_loop
+	larl	%r14,sysc_return
 	jg	do_notify_resume	# call do_notify_resume
 
 #
 # _TIF_RESTART_SVC is set, set up registers and restart svc
 #
 sysc_restart:
-	ni	__TI_flags+7(%r9),255-_TIF_RESTART_SVC # clear TIF_RESTART_SVC
+	ni	__TI_flags+7(%r12),255-_TIF_RESTART_SVC # clear TIF_RESTART_SVC
 	lg	%r7,SP_R2(%r15)		# load new svc number
 	mvc	SP_R2(8,%r15),SP_ORIG_R2(%r15) # restore first argument
 	lmg	%r2,%r6,SP_R2(%r15)	# load svc arguments
-	j	sysc_do_restart 	# restart svc
+	sth	%r7,SP_SVCNR(%r15)
+	slag	%r7,%r7,2
+	j	sysc_nr_ok		# restart svc
 
 #
 # _TIF_SINGLE_STEP is set, call do_single_step
 #
 sysc_singlestep:
-	ni	__TI_flags+7(%r9),255-_TIF_SINGLE_STEP	# clear TIF_SINGLE_STEP
+	ni	__TI_flags+7(%r12),255-_TIF_SINGLE_STEP	# clear TIF_SINGLE_STEP
 	xc	SP_SVCNR(2,%r15),SP_SVCNR(%r15)		# clear svc number
 	la	%r2,SP_PTREGS(%r15)	# address of register-save area
 	larl	%r14,sysc_return	# load adr. of system return
@@ -381,8 +387,8 @@ sysc_singlestep:
 sysc_tracesys:
 	la	%r2,SP_PTREGS(%r15)	# load pt_regs
 	la	%r3,0
-	srl	%r7,2
-	stg	%r7,SP_R2(%r15)
+	llgh	%r0,SP_SVCNR(%r15)
+	stg	%r0,SP_R2(%r15)
 	brasl	%r14,do_syscall_trace_enter
 	lghi	%r0,NR_syscalls
 	clgr	%r0,%r2
@@ -395,7 +401,7 @@ sysc_tracego:
 	basr	%r14,%r8		# call sys_xxx
 	stg	%r2,SP_R2(%r15)		# store return value
 sysc_tracenogo:
-	tm	__TI_flags+6(%r9),_TIF_SYSCALL
+	tm	__TI_flags+6(%r12),_TIF_SYSCALL
 	jz	sysc_return
 	la	%r2,SP_PTREGS(%r15)	# load pt_regs
 	larl	%r14,sysc_return	# return point is sysc_return
@@ -407,7 +413,7 @@ sysc_tracenogo:
 	.globl	ret_from_fork
 ret_from_fork:
 	lg	%r13,__LC_SVC_NEW_PSW+8
-	lg	%r9,__LC_THREAD_INFO	# load pointer to thread_info struct
+	lg	%r12,__LC_THREAD_INFO	# load pointer to thread_info struct
 	tm	SP_PSW+1(%r15),0x01	# forking a kernel thread ?
 	jo	0f
 	stg	%r15,SP_R15(%r15)	# store stack pointer for new kthread
@@ -437,12 +443,14 @@ kernel_execve:
 	br	%r14
 	# execve succeeded.
 0:	stnsm	__SF_EMPTY(%r15),0xfc	# disable interrupts
+#	TRACE_IRQS_OFF
 	lg	%r15,__LC_KERNEL_STACK	# load ksp
 	aghi	%r15,-SP_SIZE		# make room for registers & psw
 	lg	%r13,__LC_SVC_NEW_PSW+8
-	lg	%r9,__LC_THREAD_INFO
 	mvc	SP_PTREGS(__PT_SIZE,%r15),0(%r12)	# copy pt_regs
+	lg	%r12,__LC_THREAD_INFO
 	xc	__SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
+#	TRACE_IRQS_ON
 	stosm	__SF_EMPTY(%r15),0x03	# reenable interrupts
 	brasl	%r14,execve_tail
 	j	sysc_return
@@ -467,20 +475,23 @@ pgm_check_handler:
  * 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
 	jnz	pgm_per 		 # got per exception -> special case
-	SAVE_ALL_SYNC __LC_PGM_OLD_PSW,__LC_SAVE_AREA
-	CREATE_STACK_FRAME __LC_PGM_OLD_PSW,__LC_SAVE_AREA
+	SAVE_ALL_PGM __LC_PGM_OLD_PSW,__LC_SAVE_AREA
+	CREATE_STACK_FRAME __LC_SAVE_AREA
+	xc	SP_ILC(4,%r15),SP_ILC(%r15)
+	mvc	SP_PSW(16,%r15),__LC_PGM_OLD_PSW
+	lg	%r12,__LC_THREAD_INFO	# load pointer to thread_info struct
 	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:
-	lg	%r9,__LC_THREAD_INFO	# load pointer to thread_info struct
-	mvc	SP_ARGS(8,%r15),__LC_LAST_BREAK
-	TRACE_IRQS_OFF
+	HANDLE_SIE_INTERCEPT
+	TRACE_IRQS_CHECK_OFF
+	stg	%r11,SP_ARGS(%r15)
 	lgf	%r3,__LC_PGM_ILC	# load program interruption code
 	lghi	%r8,0x7f
 	ngr	%r8,%r3
@@ -489,8 +500,10 @@ pgm_do_call:
 	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
-	larl	%r14,sysc_return
-	br	%r1			# branch to interrupt-handler
+	basr	%r14,%r1		# branch to interrupt-handler
+pgm_exit:
+	TRACE_IRQS_CHECK_ON
+	j	sysc_return
 
 #
 # handle per exception
@@ -502,55 +515,68 @@ pgm_per:
 	clc	__LC_PGM_OLD_PSW(16),__LC_SVC_NEW_PSW
 	je	pgm_svcper
 # no interesting special case, ignore PER event
-	lmg	%r12,%r15,__LC_SAVE_AREA
 	lpswe	__LC_PGM_OLD_PSW
 
 #
 # Normal per exception
 #
 pgm_per_std:
-	SAVE_ALL_SYNC __LC_PGM_OLD_PSW,__LC_SAVE_AREA
-	CREATE_STACK_FRAME __LC_PGM_OLD_PSW,__LC_SAVE_AREA
+	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
 	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:
-	lg	%r9,__LC_THREAD_INFO	# load pointer to thread_info struct
-	TRACE_IRQS_OFF
-	lg	%r1,__TI_task(%r9)
+	HANDLE_SIE_INTERCEPT
+	TRACE_IRQS_CHECK_OFF
+	lg	%r1,__TI_task(%r12)
 	tm	SP_PSW+1(%r15),0x01	# kernel per event ?
 	jz	kernel_per
 	mvc	__THREAD_per+__PER_atmid(2,%r1),__LC_PER_ATMID
 	mvc	__THREAD_per+__PER_address(8,%r1),__LC_PER_ADDRESS
 	mvc	__THREAD_per+__PER_access_id(1,%r1),__LC_PER_ACCESS_ID
-	oi	__TI_flags+7(%r9),_TIF_SINGLE_STEP # set TIF_SINGLE_STEP
+	oi	__TI_flags+7(%r12),_TIF_SINGLE_STEP # set TIF_SINGLE_STEP
 	lgf	%r3,__LC_PGM_ILC	# load program interruption code
 	lghi	%r8,0x7f
 	ngr	%r8,%r3			# clear per-event-bit and ilc
-	je	sysc_return
-	j	pgm_do_call
+	je	pgm_exit2
+	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_exit2:
+	TRACE_IRQS_ON
+	stosm	__SF_EMPTY(%r15),0x03	# reenable interrupts
+	j	sysc_return
 
 #
 # it was a single stepped SVC that is causing all the trouble
 #
 pgm_svcper:
-	SAVE_ALL_SYNC __LC_SVC_OLD_PSW,__LC_SAVE_AREA
-	CREATE_STACK_FRAME __LC_SVC_OLD_PSW,__LC_SAVE_AREA
+	SAVE_ALL_PGM __LC_SVC_OLD_PSW,__LC_SAVE_AREA
+	CREATE_STACK_FRAME __LC_SAVE_AREA
+	mvc	SP_PSW(16,%r15),__LC_SVC_OLD_PSW
+	mvc	SP_ILC(4,%r15),__LC_SVC_ILC
+	lg	%r12,__LC_THREAD_INFO	# load pointer to thread_info struct
 	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
-	llgh	%r7,__LC_SVC_INT_CODE	# get svc number from lowcore
-	lg	%r9,__LC_THREAD_INFO	# load pointer to thread_info struct
-	lg	%r8,__TI_task(%r9)
+	LAST_BREAK
+	TRACE_IRQS_OFF
+	lg	%r8,__TI_task(%r12)
 	mvc	__THREAD_per+__PER_atmid(2,%r8),__LC_PER_ATMID
 	mvc	__THREAD_per+__PER_address(8,%r8),__LC_PER_ADDRESS
 	mvc	__THREAD_per+__PER_access_id(1,%r8),__LC_PER_ACCESS_ID
-	oi	__TI_flags+7(%r9),_TIF_SINGLE_STEP # set TIF_SINGLE_STEP
+	oi	__TI_flags+7(%r12),_TIF_SINGLE_STEP # set TIF_SINGLE_STEP
 	TRACE_IRQS_ON
-	lmg	%r2,%r6,SP_R2(%r15)	# load svc arguments
 	stosm	__SF_EMPTY(%r15),0x03	# reenable interrupts
+	lmg	%r2,%r6,SP_R2(%r15)	# load svc arguments
 	j	sysc_do_svc
 
 #
@@ -559,8 +585,8 @@ pgm_svcper:
 kernel_per:
 	xc	SP_SVCNR(2,%r15),SP_SVCNR(%r15)	# clear svc number
 	la	%r2,SP_PTREGS(%r15)	# address of register-save area
-	larl	%r14,sysc_restore	# load adr. of system ret, no work
-	jg	do_single_step		# branch to do_single_step
+	brasl	%r14,do_single_step
+	j	pgm_exit
 
 /*
  * IO interrupt handler routine
@@ -569,162 +595,133 @@ kernel_per:
 io_int_handler:
 	stck	__LC_INT_CLOCK
 	stpt	__LC_ASYNC_ENTER_TIMER
-	SAVE_ALL_BASE __LC_SAVE_AREA+32
-	SAVE_ALL_ASYNC __LC_IO_OLD_PSW,__LC_SAVE_AREA+32
-	CREATE_STACK_FRAME __LC_IO_OLD_PSW,__LC_SAVE_AREA+32
+	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
 	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:
-	lg	%r9,__LC_THREAD_INFO	# load pointer to thread_info struct
+	HANDLE_SIE_INTERCEPT
 	TRACE_IRQS_OFF
 	la	%r2,SP_PTREGS(%r15)	# address of register-save area
 	brasl	%r14,do_IRQ		# call standard irq handler
 io_return:
-	tm	__TI_flags+7(%r9),_TIF_WORK_INT
+	LOCKDEP_SYS_EXIT
+	TRACE_IRQS_ON
+io_tif:
+	tm	__TI_flags+7(%r12),_TIF_WORK_INT
 	jnz	io_work 		# there is work to do (signals etc.)
 io_restore:
-#ifdef CONFIG_TRACE_IRQFLAGS
-	larl	%r1,io_restore_trace_psw
-	lpswe	0(%r1)
-io_restore_trace:
-	TRACE_IRQS_CHECK
-	LOCKDEP_SYS_EXIT
-#endif
-io_leave:
 	RESTORE_ALL __LC_RETURN_PSW,0
 io_done:
 
-#ifdef CONFIG_TRACE_IRQFLAGS
-	.section .data,"aw",@progbits
-	.align	8
-	.globl io_restore_trace_psw
-io_restore_trace_psw:
-	.quad	0, io_restore_trace
-	.previous
-#endif
-
 #
-# There is work todo, we need to check if we return to userspace, then
-# check, if we are in SIE, if yes leave it
+# There is work todo, find out in which context we have been interrupted:
+# 1) if we return to user space we can do all _TIF_WORK_INT work
+# 2) if we return to kernel code and kvm is enabled check if we need to
+#    modify the psw to leave SIE
+# 3) if we return to kernel code and preemptive scheduling is enabled check
+#    the preemption counter and if it is zero call preempt_schedule_irq
+# Before any work can be done, a switch to the kernel stack is required.
 #
 io_work:
 	tm	SP_PSW+1(%r15),0x01	# returning to user ?
-#ifndef CONFIG_PREEMPT
-#if defined(CONFIG_KVM) || defined(CONFIG_KVM_MODULE)
-	jnz	io_work_user		# yes -> no need to check for SIE
-	la	%r1, BASED(sie_opcode)	# we return to kernel here
-	lg	%r2, SP_PSW+8(%r15)
-	clc	0(2,%r1), 0(%r2)	# is current instruction = SIE?
-	jne	io_restore		# no-> return to kernel
-	lg	%r1, SP_PSW+8(%r15)	# yes-> add 4 bytes to leave SIE
-	aghi	%r1, 4
-	stg	%r1, SP_PSW+8(%r15)
-	j	io_restore		# return to kernel
-#else
-	jno	io_restore		# no-> skip resched & signal
-#endif
-#else
-	jnz	io_work_user		# yes -> do resched & signal
-#if defined(CONFIG_KVM) || defined(CONFIG_KVM_MODULE)
-	la	%r1, BASED(sie_opcode)
-	lg	%r2, SP_PSW+8(%r15)
-	clc	0(2,%r1), 0(%r2)	# is current instruction = SIE?
-	jne	0f			# no -> leave PSW alone
-	lg	%r1, SP_PSW+8(%r15)	# yes-> add 4 bytes to leave SIE
-	aghi	%r1, 4
-	stg	%r1, SP_PSW+8(%r15)
-0:
-#endif
+	jo	io_work_user		# yes -> do resched & signal
+#ifdef CONFIG_PREEMPT
 	# check for preemptive scheduling
-	icm	%r0,15,__TI_precount(%r9)
+	icm	%r0,15,__TI_precount(%r12)
 	jnz	io_restore		# preemption is disabled
+	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
 	lgr	%r15,%r1
-io_resume_loop:
-	tm	__TI_flags+7(%r9),_TIF_NEED_RESCHED
-	jno	io_restore
-	larl	%r14,io_resume_loop
-	jg	preempt_schedule_irq
+	# TRACE_IRQS_ON already done at io_return, call
+	# TRACE_IRQS_OFF to keep things symmetrical
+	TRACE_IRQS_OFF
+	brasl	%r14,preempt_schedule_irq
+	j	io_return
+#else
+	j	io_restore
 #endif
 
+#
+# Need to do work before returning to userspace, switch to kernel stack
+#
 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
 	lgr	%r15,%r1
+
 #
 # One of the work bits is on. Find out which one.
-# Checked are: _TIF_SIGPENDING, _TIF_RESTORE_SIGPENDING, _TIF_NEED_RESCHED
+# Checked are: _TIF_SIGPENDING, _TIF_NOTIFY_RESUME, _TIF_NEED_RESCHED
 #	       and _TIF_MCCK_PENDING
 #
-io_work_loop:
-	tm	__TI_flags+7(%r9),_TIF_MCCK_PENDING
+io_work_tif:
+	tm	__TI_flags+7(%r12),_TIF_MCCK_PENDING
 	jo	io_mcck_pending
-	tm	__TI_flags+7(%r9),_TIF_NEED_RESCHED
+	tm	__TI_flags+7(%r12),_TIF_NEED_RESCHED
 	jo	io_reschedule
-	tm	__TI_flags+7(%r9),_TIF_SIGPENDING
-	jnz	io_sigpending
-	tm	__TI_flags+7(%r9),_TIF_NOTIFY_RESUME
-	jnz	io_notify_resume
-	j	io_restore
-io_work_done:
-
-#if defined(CONFIG_KVM) || defined(CONFIG_KVM_MODULE)
-sie_opcode:
-	.long 0xb2140000
-#endif
+	tm	__TI_flags+7(%r12),_TIF_SIGPENDING
+	jo	io_sigpending
+	tm	__TI_flags+7(%r12),_TIF_NOTIFY_RESUME
+	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
 	brasl	%r14,s390_handle_mcck	# TIF bit will be cleared by handler
-	j	io_work_loop
+	TRACE_IRQS_OFF
+	j	io_return
 
 #
 # _TIF_NEED_RESCHED is set, call schedule
 #
 io_reschedule:
-	TRACE_IRQS_ON
+	# TRACE_IRQS_ON already done at io_return
 	stosm	__SF_EMPTY(%r15),0x03	# reenable interrupts
 	brasl	%r14,schedule		# call scheduler
 	stnsm	__SF_EMPTY(%r15),0xfc	# disable I/O and ext. interrupts
 	TRACE_IRQS_OFF
-	tm	__TI_flags+7(%r9),_TIF_WORK_INT
-	jz	io_restore		# there is no work to do
-	j	io_work_loop
+	j	io_return
 
 #
 # _TIF_SIGPENDING or is set, call do_signal
 #
 io_sigpending:
-	TRACE_IRQS_ON
+	# 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
 	TRACE_IRQS_OFF
-	j	io_work_loop
+	j	io_return
 
 #
 # _TIF_NOTIFY_RESUME or is set, call do_notify_resume
 #
 io_notify_resume:
-	TRACE_IRQS_ON
+	# 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
 	TRACE_IRQS_OFF
-	j	io_work_loop
+	j	io_return
 
 /*
  * External interrupt handler routine
@@ -733,16 +730,18 @@ io_notify_resume:
 ext_int_handler:
 	stck	__LC_INT_CLOCK
 	stpt	__LC_ASYNC_ENTER_TIMER
-	SAVE_ALL_BASE __LC_SAVE_AREA+32
-	SAVE_ALL_ASYNC __LC_EXT_OLD_PSW,__LC_SAVE_AREA+32
-	CREATE_STACK_FRAME __LC_EXT_OLD_PSW,__LC_SAVE_AREA+32
+	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
 	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:
-	lg	%r9,__LC_THREAD_INFO	# load pointer to thread_info struct
+	HANDLE_SIE_INTERCEPT
 	TRACE_IRQS_OFF
 	la	%r2,SP_PTREGS(%r15)	# address of register-save area
 	llgh	%r3,__LC_EXT_INT_CODE	# get interruption code
@@ -756,17 +755,18 @@ __critical_end:
  */
 	.globl mcck_int_handler
 mcck_int_handler:
-	stck	__LC_INT_CLOCK
+	stck	__LC_MCCK_CLOCK
 	la	%r1,4095		# revalidate r1
 	spt	__LC_CPU_TIMER_SAVE_AREA-4095(%r1)	# revalidate cpu timer
 	lmg	%r0,%r15,__LC_GPREGS_SAVE_AREA-4095(%r1)# revalidate gprs
-	SAVE_ALL_BASE __LC_SAVE_AREA+64
+	stmg	%r11,%r15,__LC_SAVE_AREA+80
+	larl	%r13,system_call
+	lg	%r11,__LC_LAST_BREAK
 	la	%r12,__LC_MCK_OLD_PSW
 	tm	__LC_MCCK_CODE,0x80	# system damage?
 	jo	mcck_int_main		# yes -> rest of mcck code invalid
 	la	%r14,4095
-	mvc	__LC_SAVE_AREA+104(8),__LC_ASYNC_ENTER_TIMER
-	mvc	__LC_ASYNC_ENTER_TIMER(8),__LC_CPU_TIMER_SAVE_AREA-4095(%r14)
+	mvc	__LC_MCCK_ENTER_TIMER(8),__LC_CPU_TIMER_SAVE_AREA-4095(%r14)
 	tm	__LC_MCCK_CODE+5,0x02	# stored cpu timer value valid?
 	jo	1f
 	la	%r14,__LC_SYNC_ENTER_TIMER
@@ -780,7 +780,7 @@ mcck_int_handler:
 	jl	0f
 	la	%r14,__LC_LAST_UPDATE_TIMER
 0:	spt	0(%r14)
-	mvc	__LC_ASYNC_ENTER_TIMER(8),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
@@ -796,16 +796,19 @@ mcck_int_main:
 	srag	%r14,%r14,PAGE_SHIFT
 	jz	0f
 	lg	%r15,__LC_PANIC_STACK	# load panic stack
-0:	CREATE_STACK_FRAME __LC_MCK_OLD_PSW,__LC_SAVE_AREA+64
+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
 	tm	SP_PSW+1(%r15),0x01	# interrupting from user ?
 	jz	mcck_no_vtime
-	UPDATE_VTIME __LC_EXIT_TIMER,__LC_ASYNC_ENTER_TIMER,__LC_USER_TIMER
+	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_ASYNC_ENTER_TIMER
+	mvc	__LC_LAST_UPDATE_TIMER(8),__LC_MCCK_ENTER_TIMER
+	LAST_BREAK
 mcck_no_vtime:
-	lg	%r9,__LC_THREAD_INFO	# load pointer to thread_info struct
 	la	%r2,SP_PTREGS(%r15)	# load pt_regs
 	brasl	%r14,s390_do_machine_check
 	tm	SP_PSW+1(%r15),0x01	# returning to user ?
@@ -816,8 +819,9 @@ mcck_no_vtime:
 	xc	__SF_BACKCHAIN(8,%r1),__SF_BACKCHAIN(%r1) # clear back chain
 	lgr	%r15,%r1
 	stosm	__SF_EMPTY(%r15),0x04	# turn dat on
-	tm	__TI_flags+7(%r9),_TIF_MCCK_PENDING
+	tm	__TI_flags+7(%r12),_TIF_MCCK_PENDING
 	jno	mcck_return
+	HANDLE_SIE_INTERCEPT
 	TRACE_IRQS_OFF
 	brasl	%r14,s390_handle_mcck
 	TRACE_IRQS_ON
@@ -825,11 +829,11 @@ mcck_return:
 	mvc	__LC_RETURN_MCCK_PSW(16),SP_PSW(%r15) # move return PSW
 	ni	__LC_RETURN_MCCK_PSW+1,0xfd # clear wait state bit
 	lmg	%r0,%r15,SP_R0(%r15)	# load gprs 0-15
-	mvc	__LC_ASYNC_ENTER_TIMER(8),__LC_SAVE_AREA+104
 	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:
 
 /*
  * Restart interruption handler, kick starter for additional CPUs
@@ -885,14 +889,14 @@ 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,%r11,SP_R0(%r15)	# store gprs %r0-%r11 to kernel 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+32
-0:	mvc	SP_R12(32,%r15),0(%r1)	# move %r12-%r15 to stack
+	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
@@ -901,18 +905,14 @@ stack_overflow:
 
 cleanup_table_system_call:
 	.quad	system_call, sysc_do_svc
-cleanup_table_sysc_return:
-	.quad	sysc_return, sysc_leave
-cleanup_table_sysc_leave:
-	.quad	sysc_leave, sysc_done
-cleanup_table_sysc_work_loop:
-	.quad	sysc_work_loop, sysc_work_done
-cleanup_table_io_return:
-	.quad	io_return, io_leave
-cleanup_table_io_leave:
-	.quad	io_leave, io_done
-cleanup_table_io_work_loop:
-	.quad	io_work_loop, io_work_done
+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
 
 cleanup_critical:
 	clc	8(8,%r12),BASED(cleanup_table_system_call)
@@ -920,61 +920,54 @@ cleanup_critical:
 	clc	8(8,%r12),BASED(cleanup_table_system_call+8)
 	jl	cleanup_system_call
 0:
-	clc	8(8,%r12),BASED(cleanup_table_sysc_return)
+	clc	8(8,%r12),BASED(cleanup_table_sysc_tif)
 	jl	0f
-	clc	8(8,%r12),BASED(cleanup_table_sysc_return+8)
-	jl	cleanup_sysc_return
+	clc	8(8,%r12),BASED(cleanup_table_sysc_tif+8)
+	jl	cleanup_sysc_tif
 0:
-	clc	8(8,%r12),BASED(cleanup_table_sysc_leave)
+	clc	8(8,%r12),BASED(cleanup_table_sysc_restore)
 	jl	0f
-	clc	8(8,%r12),BASED(cleanup_table_sysc_leave+8)
-	jl	cleanup_sysc_leave
+	clc	8(8,%r12),BASED(cleanup_table_sysc_restore+8)
+	jl	cleanup_sysc_restore
 0:
-	clc	8(8,%r12),BASED(cleanup_table_sysc_work_loop)
+	clc	8(8,%r12),BASED(cleanup_table_io_tif)
 	jl	0f
-	clc	8(8,%r12),BASED(cleanup_table_sysc_work_loop+8)
-	jl	cleanup_sysc_return
+	clc	8(8,%r12),BASED(cleanup_table_io_tif+8)
+	jl	cleanup_io_tif
 0:
-	clc	8(8,%r12),BASED(cleanup_table_io_return)
+	clc	8(8,%r12),BASED(cleanup_table_io_restore)
 	jl	0f
-	clc	8(8,%r12),BASED(cleanup_table_io_return+8)
-	jl	cleanup_io_return
-0:
-	clc	8(8,%r12),BASED(cleanup_table_io_leave)
-	jl	0f
-	clc	8(8,%r12),BASED(cleanup_table_io_leave+8)
-	jl	cleanup_io_leave
-0:
-	clc	8(8,%r12),BASED(cleanup_table_io_work_loop)
-	jl	0f
-	clc	8(8,%r12),BASED(cleanup_table_io_work_loop+8)
-	jl	cleanup_io_return
+	clc	8(8,%r12),BASED(cleanup_table_io_restore+8)
+	jl	cleanup_io_restore
 0:
 	br	%r14
 
 cleanup_system_call:
 	mvc	__LC_RETURN_PSW(16),0(%r12)
-	cghi	%r12,__LC_MCK_OLD_PSW
-	je	0f
-	la	%r12,__LC_SAVE_AREA+32
-	j	1f
-0:	la	%r12,__LC_SAVE_AREA+64
-1:
 	clc	__LC_RETURN_PSW+8(8),BASED(cleanup_system_call_insn+8)
 	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
+	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)
 	jh	0f
-	mvc	__LC_SAVE_AREA(32),0(%r12)
-0:	stg	%r13,8(%r12)
-	stg	%r12,__LC_SAVE_AREA+96	# argh
-	SAVE_ALL_SYNC __LC_SVC_OLD_PSW,__LC_SAVE_AREA
-	CREATE_STACK_FRAME __LC_SVC_OLD_PSW,__LC_SAVE_AREA
-	lg	%r12,__LC_SAVE_AREA+96	# argh
-	stg	%r15,24(%r12)
-	llgh	%r7,__LC_SVC_INT_CODE
+	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	SP_PSW(16,%r15),__LC_SVC_OLD_PSW
+	mvc	SP_ILC(4,%r15),__LC_SVC_ILC
+	stg	%r7,SP_ARGS(%r15)
+	mvc	8(8,%r12),__LC_THREAD_INFO
 cleanup_vtime:
 	clc	__LC_RETURN_PSW+8(8),BASED(cleanup_system_call_insn+24)
 	jhe	cleanup_stime
@@ -985,7 +978,11 @@ cleanup_stime:
 	UPDATE_VTIME __LC_LAST_UPDATE_TIMER,__LC_EXIT_TIMER,__LC_SYSTEM_TIMER
 cleanup_update:
 	mvc	__LC_LAST_UPDATE_TIMER(8),__LC_SYNC_ENTER_TIMER
-	mvc	__LC_RETURN_PSW+8(8),BASED(cleanup_table_system_call+8)
+	srag	%r12,%r11,23
+	lg	%r12,__LC_THREAD_INFO
+	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
 	br	%r14
 cleanup_system_call_insn:
@@ -995,55 +992,54 @@ cleanup_system_call_insn:
 	.quad	sysc_stime
 	.quad	sysc_update
 
-cleanup_sysc_return:
+cleanup_sysc_tif:
 	mvc	__LC_RETURN_PSW(8),0(%r12)
-	mvc	__LC_RETURN_PSW+8(8),BASED(cleanup_table_sysc_return)
+	mvc	__LC_RETURN_PSW+8(8),BASED(cleanup_table_sysc_tif)
 	la	%r12,__LC_RETURN_PSW
 	br	%r14
 
-cleanup_sysc_leave:
-	clc	8(8,%r12),BASED(cleanup_sysc_leave_insn)
-	je	3f
-	clc	8(8,%r12),BASED(cleanup_sysc_leave_insn+8)
+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
+	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
-	jne	1f
-	mvc	__LC_SAVE_AREA+64(32),SP_R12(%r15)
-	j	2f
-1:	mvc	__LC_SAVE_AREA+32(32),SP_R12(%r15)
-2:	lmg	%r0,%r11,SP_R0(%r15)
+	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)
-3:	la	%r12,__LC_RETURN_PSW
+2:	la	%r12,__LC_RETURN_PSW
 	br	%r14
-cleanup_sysc_leave_insn:
+cleanup_sysc_restore_insn:
 	.quad	sysc_done - 4
 	.quad	sysc_done - 16
 
-cleanup_io_return:
+cleanup_io_tif:
 	mvc	__LC_RETURN_PSW(8),0(%r12)
-	mvc	__LC_RETURN_PSW+8(8),BASED(cleanup_table_io_work_loop)
+	mvc	__LC_RETURN_PSW+8(8),BASED(cleanup_table_io_tif)
 	la	%r12,__LC_RETURN_PSW
 	br	%r14
 
-cleanup_io_leave:
-	clc	8(8,%r12),BASED(cleanup_io_leave_insn)
-	je	3f
-	clc	8(8,%r12),BASED(cleanup_io_leave_insn+8)
+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_ASYNC_ENTER_TIMER
+	mvc	__LC_EXIT_TIMER(8),__LC_MCCK_ENTER_TIMER
 0:	mvc	__LC_RETURN_PSW(16),SP_PSW(%r15)
-	cghi	%r12,__LC_MCK_OLD_PSW
-	jne	1f
-	mvc	__LC_SAVE_AREA+64(32),SP_R12(%r15)
-	j	2f
-1:	mvc	__LC_SAVE_AREA+32(32),SP_R12(%r15)
-2:	lmg	%r0,%r11,SP_R0(%r15)
+	mvc	__LC_SAVE_AREA+80(40),SP_R11(%r15)
+	lmg	%r0,%r10,SP_R0(%r15)
 	lg	%r15,SP_R15(%r15)
-3:	la	%r12,__LC_RETURN_PSW
+1:	la	%r12,__LC_RETURN_PSW
 	br	%r14
-cleanup_io_leave_insn:
+cleanup_io_restore_insn:
 	.quad	io_done - 4
 	.quad	io_done - 16
 
@@ -1051,13 +1047,6 @@ cleanup_io_leave_insn:
  * Integer constants
  */
 		.align	4
-.Lconst:
-.Lnr_syscalls:	.long	NR_syscalls
-.L0x0130:	.short	0x130
-.L0x0140:	.short	0x140
-.L0x0150:	.short	0x150
-.L0x0160:	.short	0x160
-.L0x0170:	.short	0x170
 .Lcritical_start:
 		.quad	__critical_start
 .Lcritical_end:
diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c
index 5a82bc68193..6a83d058131 100644
--- a/arch/s390/kernel/ftrace.c
+++ b/arch/s390/kernel/ftrace.c
@@ -13,7 +13,7 @@
 #include <linux/kernel.h>
 #include <linux/types.h>
 #include <trace/syscall.h>
-#include <asm/lowcore.h>
+#include <asm/asm-offsets.h>
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 
@@ -200,13 +200,3 @@ out:
 	return parent;
 }
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
-
-#ifdef CONFIG_FTRACE_SYSCALLS
-
-extern unsigned int sys_call_table[];
-
-unsigned long __init arch_syscall_addr(int nr)
-{
-	return (unsigned long)sys_call_table[nr];
-}
-#endif
diff --git a/arch/s390/kernel/head.S b/arch/s390/kernel/head.S
index c52b4f7742f..51838ad42d5 100644
--- a/arch/s390/kernel/head.S
+++ b/arch/s390/kernel/head.S
@@ -1,5 +1,5 @@
 /*
- * Copyright IBM Corp. 1999,2009
+ * Copyright IBM Corp. 1999,2010
  *
  *    Author(s): Hartmut Penner <hp@de.ibm.com>
  *		 Martin Schwidefsky <schwidefsky@de.ibm.com>
@@ -22,12 +22,9 @@
  */
 
 #include <linux/init.h>
-#include <asm/setup.h>
-#include <asm/lowcore.h>
 #include <asm/asm-offsets.h>
 #include <asm/thread_info.h>
 #include <asm/page.h>
-#include <asm/cpu.h>
 
 #ifdef CONFIG_64BIT
 #define ARCH_OFFSET	4
@@ -288,19 +285,7 @@ iplstart:
 	bz	.Lagain1		# skip dateset trailer
 	la	%r5,0(%r4,%r2)
 	lr	%r3,%r2
-.Lidebc:
-	tm	0(%r5),0x80		# high order bit set ?
-	bo	.Ldocv			#  yes -> convert from EBCDIC
-	ahi	%r5,-1
-	bct	%r3,.Lidebc
-	b	.Lnocv
-.Ldocv:
-	l	%r3,.Lcvtab
-	tr	0(256,%r4),0(%r3)	# convert parameters to ascii
-	tr	256(256,%r4),0(%r3)
-	tr	512(256,%r4),0(%r3)
-	tr	768(122,%r4),0(%r3)
-.Lnocv: la	%r3,COMMAND_LINE-PARMAREA(%r12) # load adr. of command line
+	la	%r3,COMMAND_LINE-PARMAREA(%r12) # load adr. of command line
 	mvc	0(256,%r3),0(%r4)
 	mvc	256(256,%r3),256(%r4)
 	mvc	512(256,%r3),512(%r4)
@@ -343,8 +328,8 @@ iplstart:
 #
 # reset files in VM reader
 #
-	stidp	__LC_CPUID		# store cpuid
-	tm	__LC_CPUID,0xff 	# running VM ?
+	stidp	__LC_SAVE_AREA		# store cpuid
+	tm	__LC_SAVE_AREA,0xff	# running VM ?
 	bno	.Lnoreset
 	la	%r2,.Lreset
 	lhi	%r3,26
@@ -384,7 +369,6 @@ iplstart:
 .Linitrd:.long _end + 0x400000		# default address of initrd
 .Lparm:	.long  PARMAREA
 .Lstartup: .long startup
-.Lcvtab:.long	_ebcasc 		# ebcdic to ascii table
 .Lreset:.byte	0xc3,0xc8,0xc1,0xd5,0xc7,0xc5,0x40,0xd9,0xc4,0xd9,0x40
 	.byte	0xc1,0xd3,0xd3,0x40,0xd2,0xc5,0xc5,0xd7,0x40,0xd5,0xd6
 	.byte	0xc8,0xd6,0xd3,0xc4	# "change rdr all keep nohold"
@@ -417,13 +401,10 @@ start:
 .sk8x8:
 	mvc	0(240,%r8),0(%r9)	# copy iplparms into buffer
 .gotr:
-	l	%r10,.tbl		# EBCDIC to ASCII table
-	tr	0(240,%r8),0(%r10)
 	slr	%r0,%r0
 	st	%r0,INITRD_SIZE+ARCH_OFFSET-PARMAREA(%r11)
 	st	%r0,INITRD_START+ARCH_OFFSET-PARMAREA(%r11)
 	j	startup 		# continue with startup
-.tbl:	.long	_ebcasc			# translate table
 .cmd:	.long	COMMAND_LINE		# address of command line buffer
 .parm:	.long	PARMAREA
 .lowcase:
@@ -467,16 +448,15 @@ start:
 # or linload or SALIPL
 #
 	.org	0x10000
-startup:basr	%r13,0			# get base
+	.globl	startup
+startup:
+	basr	%r13,0			# get base
 .LPG0:
 	xc	0x200(256),0x200	# partially clear lowcore
 	xc	0x300(256),0x300
-	l	%r1,5f-.LPG0(%r13)
-	stck	0(%r1)
-	spt	6f-.LPG0(%r13)
-	mvc	__LC_LAST_UPDATE_CLOCK(8),0(%r1)
-	mvc	__LC_LAST_UPDATE_TIMER(8),6f-.LPG0(%r13)
-	mvc	__LC_EXIT_TIMER(8),5f-.LPG0(%r13)
+	stck	__LC_LAST_UPDATE_CLOCK
+	spt	5f-.LPG0(%r13)
+	mvc	__LC_LAST_UPDATE_TIMER(8),5f-.LPG0(%r13)
 #ifndef CONFIG_MARCH_G5
 	# check capabilities against MARCH_{G5,Z900,Z990,Z9_109,Z10}
 	xc	__LC_STFL_FAC_LIST(8),__LC_STFL_FAC_LIST
@@ -494,7 +474,6 @@ startup:basr	%r13,0			# get base
 	cl	%r0,2f+12-.LPG0(%r13)
 	je	3f
 1:	l	%r15,.Lstack-.LPG0(%r13)
-	ahi	%r15,1<<(PAGE_SHIFT+THREAD_ORDER) # init_task_union+THREAD_SIZE
 	ahi	%r15,-96
 	la	%r2,.Lals_string-.LPG0(%r13)
 	l	%r3,.Lsclp_print-.LPG0(%r13)
@@ -505,7 +484,7 @@ startup:basr	%r13,0			# get base
 .Lsclp_print:
 	.long	_sclp_print_early
 .Lstack:
-	.long	init_thread_union
+	.long	0x8000 + (1<<(PAGE_SHIFT+THREAD_ORDER))
 	.align 16
 2:	.long	0x000a0000,0x8badcccc
 #if defined(CONFIG_64BIT)
@@ -532,13 +511,25 @@ startup:basr	%r13,0			# get base
 3:
 #endif
 
+#ifdef CONFIG_64BIT
+	mvi	__LC_AR_MODE_ID,1	# set esame flag
+	slr	%r0,%r0 		# set cpuid to zero
+	lhi	%r1,2			# mode 2 = esame (dump)
+	sigp	%r1,%r0,0x12		# switch to esame mode
+	sam64				# switch to 64 bit mode
+	larl	%r13,4f
+	lmh	%r0,%r15,0(%r13)	# clear high-order half
+	jg	startup_continue
+4:	.fill	16,4,0x0
+#else
+	mvi	__LC_AR_MODE_ID,0	# set ESA flag (mode 0)
 	l	%r13,4f-.LPG0(%r13)
 	b	0(%r13)
-	.align	4
+	.align	8
 4:	.long	startup_continue
-5:	.long	sched_clock_base_cc
+#endif
 	.align	8
-6:	.long	0x7fffffff,0xffffffff
+5:	.long	0x7fffffff,0xffffffff
 
 #
 # params at 10400 (setup.h)
@@ -552,8 +543,4 @@ startup:basr	%r13,0			# get base
 	.byte	"root=/dev/ram0 ro"
 	.byte	0
 
-#ifdef CONFIG_64BIT
-#include "head64.S"
-#else
-#include "head31.S"
-#endif
+	.org	0x11000
diff --git a/arch/s390/kernel/head31.S b/arch/s390/kernel/head31.S
index 602b508cd4c..b8f8dc12610 100644
--- a/arch/s390/kernel/head31.S
+++ b/arch/s390/kernel/head31.S
@@ -1,7 +1,7 @@
 /*
  * arch/s390/kernel/head31.S
  *
- * Copyright (C) IBM Corp. 2005,2006
+ * Copyright (C) IBM Corp. 2005,2010
  *
  *   Author(s):	Hartmut Penner <hp@de.ibm.com>
  *		Martin Schwidefsky <schwidefsky@de.ibm.com>
@@ -10,13 +10,19 @@
  *
  */
 
-	.org	0x11000
+#include <linux/init.h>
+#include <asm/asm-offsets.h>
+#include <asm/thread_info.h>
+#include <asm/page.h>
 
+__HEAD
+	.globl	startup_continue
 startup_continue:
 	basr	%r13,0			# get base
 .LPG1:
 
-	mvi	__LC_AR_MODE_ID,0	# set ESA flag (mode 0)
+	l	%r1,.Lbase_cc-.LPG1(%r13)
+	mvc	0(8,%r1),__LC_LAST_UPDATE_CLOCK
 	lctl	%c0,%c15,.Lctl-.LPG1(%r13) # load control registers
 	l	%r12,.Lparmaddr-.LPG1(%r13) # pointer to parameter area
 					# move IPL device to lowcore
@@ -69,12 +75,14 @@ startup_continue:
 .Lduald:.rept	8
 	.long	0x80000000,0,0,0	# invalid access-list entries
 	.endr
+.Lbase_cc:
+	.long	sched_clock_base_cc
 
-	.org	0x12000
 	.globl	_ehead
 _ehead:
+
 #ifdef CONFIG_SHARED_KERNEL
-	.org	0x100000
+	.org	0x100000 - 0x11000	# head.o ends at 0x11000
 #endif
 
 #
diff --git a/arch/s390/kernel/head64.S b/arch/s390/kernel/head64.S
index d984a2a380c..cdef6871741 100644
--- a/arch/s390/kernel/head64.S
+++ b/arch/s390/kernel/head64.S
@@ -1,7 +1,7 @@
 /*
  * arch/s390/kernel/head64.S
  *
- * Copyright (C) IBM Corp. 1999,2006
+ * Copyright (C) IBM Corp. 1999,2010
  *
  *   Author(s):	Hartmut Penner <hp@de.ibm.com>
  *		Martin Schwidefsky <schwidefsky@de.ibm.com>
@@ -10,81 +10,17 @@
  *
  */
 
-	.org	0x11000
+#include <linux/init.h>
+#include <asm/asm-offsets.h>
+#include <asm/thread_info.h>
+#include <asm/page.h>
 
+__HEAD
+	.globl	startup_continue
 startup_continue:
-	basr	%r13,0			# get base
-.LPG1:	sll	%r13,1			# remove high order bit
-	srl	%r13,1
-
-#ifdef CONFIG_ZFCPDUMP
-
-	# check if we have been ipled using zfcp dump:
-
-	tm	0xb9,0x01		# test if subchannel is enabled
-	jno	.nodump			# subchannel disabled
-	l	%r1,0xb8
-	la	%r5,.Lipl_schib-.LPG1(%r13)
-	stsch	0(%r5)			# get schib of subchannel
-	jne	.nodump			# schib not available
-	tm	5(%r5),0x01		# devno valid?
-	jno	.nodump
-	tm	4(%r5),0x80		# qdio capable device?
-	jno	.nodump
-	l	%r2,20(%r0)		# address of ipl parameter block
-	lhi	%r3,0
-	ic	%r3,0x148(%r2)		# get opt field
-	chi	%r3,0x20		# load with dump?
-	jne	.nodump
-
-	# store all prefix registers in case of load with dump:
-
-	la	%r7,0			# base register for 0 page
-	la	%r8,0			# first cpu
-	l	%r11,.Lpref_arr_ptr-.LPG1(%r13)	# address of prefix array
-	ahi	%r11,4			# skip boot cpu
-	lr	%r12,%r11
-	ahi	%r12,(CONFIG_NR_CPUS*4)	# end of prefix array
-	stap	.Lcurrent_cpu+2-.LPG1(%r13)	# store current cpu addr
-1:
-	cl	%r8,.Lcurrent_cpu-.LPG1(%r13)	# is ipl cpu ?
-	je	4f				# if yes get next cpu
-2:
-	lr	%r9,%r7
-	sigp	%r9,%r8,0x9		# stop & store status of cpu
-	brc	8,3f			# accepted
-	brc	4,4f			# status stored: next cpu
-	brc	2,2b			# busy: 	 try again
-	brc	1,4f			# not op:	 next cpu
-3:
-	mvc	0(4,%r11),264(%r7)	# copy prefix register to prefix array
-	ahi	%r11,4			# next element in prefix array
-	clr	%r11,%r12
-	je	5f			# no more space in prefix array
-4:
-	ahi	%r8,1			# next cpu (r8 += 1)
-	chi	%r8,MAX_CPU_ADDRESS	# is last possible cpu ?
-	jle	1b			# jump if not last cpu
-5:
-	lhi	%r1,2			# mode 2 = esame (dump)
-	j	6f
-	.align 4
-.Lipl_schib:
-	.rept 13
-	.long 0
-	.endr
-.nodump:
-	lhi	%r1,1			# mode 1 = esame (normal ipl)
-6:
-#else
-	lhi	%r1,1			# mode 1 = esame (normal ipl)
-#endif /* CONFIG_ZFCPDUMP */
-	mvi	__LC_AR_MODE_ID,1	# set esame flag
-	slr	%r0,%r0 		# set cpuid to zero
-	sigp	%r1,%r0,0x12		# switch to esame mode
-	sam64				# switch to 64 bit mode
-	llgfr	%r13,%r13		# clear high-order half of base reg
-	lmh	%r0,%r15,.Lzero64-.LPG1(%r13)	# clear high-order half
+	larl	%r1,sched_clock_base_cc
+	mvc	0(8,%r1),__LC_LAST_UPDATE_CLOCK
+	larl	%r13,.LPG1		# get base
 	lctlg	%c0,%c15,.Lctl-.LPG1(%r13)	# load control registers
 	lg	%r12,.Lparmaddr-.LPG1(%r13)	# pointer to parameter area
 					# move IPL device to lowcore
@@ -108,6 +44,7 @@ startup_continue:
 	lpswe	.Lentry-.LPG1(13)	# jump to _stext in primary-space,
 					# virtual and never return ...
 	.align	16
+.LPG1:
 .Lentry:.quad	0x0000000180000000,_stext
 .Lctl:	.quad	0x04350002		# cr0: various things
 	.quad	0			# cr1: primary space segment table
@@ -129,13 +66,6 @@ startup_continue:
 .L4malign:.quad 0xffffffffffc00000
 .Lscan2g:.quad	0x80000000 + 0x20000 - 8	# 2GB + 128K - 8
 .Lnop:	.long	0x07000700
-.Lzero64:.fill	16,4,0x0
-#ifdef CONFIG_ZFCPDUMP
-.Lcurrent_cpu:
-	.long 0x0
-.Lpref_arr_ptr:
-	.long zfcpdump_prefix_array
-#endif /* CONFIG_ZFCPDUMP */
 .Lparmaddr:
 	.quad	PARMAREA
 	.align	64
@@ -146,11 +76,11 @@ startup_continue:
 	.long	0x80000000,0,0,0	# invalid access-list entries
 	.endr
 
-	.org	0x12000
 	.globl	_ehead
 _ehead:
+
 #ifdef CONFIG_SHARED_KERNEL
-	.org	0x100000
+	.org	0x100000 - 0x11000	# head.o ends at 0x11000
 #endif
 
 #
diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c
index 4d73296fed7..a689070be28 100644
--- a/arch/s390/kernel/ipl.c
+++ b/arch/s390/kernel/ipl.c
@@ -15,6 +15,7 @@
 #include <linux/reboot.h>
 #include <linux/ctype.h>
 #include <linux/fs.h>
+#include <linux/gfp.h>
 #include <asm/ipl.h>
 #include <asm/smp.h>
 #include <asm/setup.h>
@@ -402,8 +403,9 @@ static ssize_t sys_ipl_device_show(struct kobject *kobj,
 static struct kobj_attribute sys_ipl_device_attr =
 	__ATTR(device, S_IRUGO, sys_ipl_device_show, NULL);
 
-static ssize_t ipl_parameter_read(struct kobject *kobj, struct bin_attribute *attr,
-				  char *buf, loff_t off, size_t count)
+static ssize_t ipl_parameter_read(struct file *filp, struct kobject *kobj,
+				  struct bin_attribute *attr, char *buf,
+				  loff_t off, size_t count)
 {
 	return memory_read_from_buffer(buf, count, &off, IPL_PARMBLOCK_START,
 					IPL_PARMBLOCK_SIZE);
@@ -418,8 +420,9 @@ static struct bin_attribute ipl_parameter_attr = {
 	.read = &ipl_parameter_read,
 };
 
-static ssize_t ipl_scp_data_read(struct kobject *kobj, struct bin_attribute *attr,
-				 char *buf, loff_t off, size_t count)
+static ssize_t ipl_scp_data_read(struct file *filp, struct kobject *kobj,
+				 struct bin_attribute *attr, char *buf,
+				 loff_t off, size_t count)
 {
 	unsigned int size = IPL_PARMBLOCK_START->ipl_info.fcp.scp_data_len;
 	void *scp_data = &IPL_PARMBLOCK_START->ipl_info.fcp.scp_data;
@@ -553,7 +556,7 @@ out:
 	return rc;
 }
 
-static void ipl_run(struct shutdown_trigger *trigger)
+static void __ipl_run(void *unused)
 {
 	diag308(DIAG308_IPL, NULL);
 	if (MACHINE_IS_VM)
@@ -562,6 +565,11 @@ static void ipl_run(struct shutdown_trigger *trigger)
 		reipl_ccw_dev(&ipl_info.data.ccw.dev_id);
 }
 
+static void ipl_run(struct shutdown_trigger *trigger)
+{
+	smp_switch_to_ipl_cpu(__ipl_run, NULL);
+}
+
 static int __init ipl_init(void)
 {
 	int rc;
@@ -688,7 +696,7 @@ static struct kobj_attribute sys_reipl_ccw_vmparm_attr =
 
 /* FCP reipl device attributes */
 
-static ssize_t reipl_fcp_scpdata_read(struct kobject *kobj,
+static ssize_t reipl_fcp_scpdata_read(struct file *filp, struct kobject *kobj,
 				      struct bin_attribute *attr,
 				      char *buf, loff_t off, size_t count)
 {
@@ -698,7 +706,7 @@ static ssize_t reipl_fcp_scpdata_read(struct kobject *kobj,
 	return memory_read_from_buffer(buf, count, &off, scp_data, size);
 }
 
-static ssize_t reipl_fcp_scpdata_write(struct kobject *kobj,
+static ssize_t reipl_fcp_scpdata_write(struct file *filp, struct kobject *kobj,
 				       struct bin_attribute *attr,
 				       char *buf, loff_t off, size_t count)
 {
@@ -1039,7 +1047,7 @@ static void get_ipl_string(char *dst, struct ipl_parameter_block *ipb,
 		sprintf(dst + pos, " PARM %s", vmparm);
 }
 
-static void reipl_run(struct shutdown_trigger *trigger)
+static void __reipl_run(void *unused)
 {
 	struct ccw_dev_id devid;
 	static char buf[128];
@@ -1087,6 +1095,11 @@ static void reipl_run(struct shutdown_trigger *trigger)
 	disabled_wait((unsigned long) __builtin_return_address(0));
 }
 
+static void reipl_run(struct shutdown_trigger *trigger)
+{
+	smp_switch_to_ipl_cpu(__reipl_run, NULL);
+}
+
 static void reipl_block_ccw_init(struct ipl_parameter_block *ipb)
 {
 	ipb->hdr.len = IPL_PARM_BLK_CCW_LEN;
@@ -1369,20 +1382,18 @@ static struct kobj_attribute dump_type_attr =
 
 static struct kset *dump_kset;
 
-static void dump_run(struct shutdown_trigger *trigger)
+static void __dump_run(void *unused)
 {
 	struct ccw_dev_id devid;
 	static char buf[100];
 
 	switch (dump_method) {
 	case DUMP_METHOD_CCW_CIO:
-		smp_send_stop();
 		devid.devno = dump_block_ccw->ipl_info.ccw.devno;
 		devid.ssid  = 0;
 		reipl_ccw_dev(&devid);
 		break;
 	case DUMP_METHOD_CCW_VM:
-		smp_send_stop();
 		sprintf(buf, "STORE STATUS");
 		__cpcmd(buf, NULL, 0, NULL);
 		sprintf(buf, "IPL %X", dump_block_ccw->ipl_info.ccw.devno);
@@ -1396,10 +1407,17 @@ static void dump_run(struct shutdown_trigger *trigger)
 		diag308(DIAG308_SET, dump_block_fcp);
 		diag308(DIAG308_DUMP, NULL);
 		break;
-	case DUMP_METHOD_NONE:
-		return;
+	default:
+		break;
 	}
-	printk(KERN_EMERG "Dump failed!\n");
+}
+
+static void dump_run(struct shutdown_trigger *trigger)
+{
+	if (dump_method == DUMP_METHOD_NONE)
+		return;
+	smp_send_stop();
+	smp_switch_to_ipl_cpu(__dump_run, NULL);
 }
 
 static int __init dump_ccw_init(void)
@@ -1577,7 +1595,7 @@ static void vmcmd_run(struct shutdown_trigger *trigger)
 static int vmcmd_init(void)
 {
 	if (!MACHINE_IS_VM)
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 	vmcmd_kset = kset_create_and_add("vmcmd", NULL, firmware_kobj);
 	if (!vmcmd_kset)
 		return -ENOMEM;
@@ -1595,7 +1613,7 @@ static void stop_run(struct shutdown_trigger *trigger)
 {
 	if (strcmp(trigger->name, ON_PANIC_STR) == 0)
 		disabled_wait((unsigned long) __builtin_return_address(0));
-	while (signal_processor(smp_processor_id(), sigp_stop) == sigp_busy)
+	while (sigp(smp_processor_id(), sigp_stop) == sigp_busy)
 		cpu_relax();
 	for (;;);
 }
@@ -1902,7 +1920,6 @@ void __init ipl_update_parameters(void)
 void __init ipl_save_parameters(void)
 {
 	struct cio_iplinfo iplinfo;
-	unsigned int *ipl_ptr;
 	void *src, *dst;
 
 	if (cio_get_iplinfo(&iplinfo))
@@ -1913,11 +1930,10 @@ void __init ipl_save_parameters(void)
 	if (!iplinfo.is_qdio)
 		return;
 	ipl_flags |= IPL_PARMBLOCK_VALID;
-	ipl_ptr = (unsigned int *)__LC_IPL_PARMBLOCK_PTR;
-	src = (void *)(unsigned long)*ipl_ptr;
+	src = (void *)(unsigned long)S390_lowcore.ipl_parmblock_ptr;
 	dst = (void *)IPL_PARMBLOCK_ORIGIN;
 	memmove(dst, src, PAGE_SIZE);
-	*ipl_ptr = IPL_PARMBLOCK_ORIGIN;
+	S390_lowcore.ipl_parmblock_ptr = IPL_PARMBLOCK_ORIGIN;
 }
 
 static LIST_HEAD(rcall);
diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c
index 86783efa24e..2a3d2bf6f08 100644
--- a/arch/s390/kernel/kprobes.c
+++ b/arch/s390/kernel/kprobes.c
@@ -29,6 +29,7 @@
 #include <asm/cacheflush.h>
 #include <asm/sections.h>
 #include <linux/module.h>
+#include <linux/slab.h>
 
 DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL;
 DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
@@ -62,6 +63,8 @@ int __kprobes is_prohibited_opcode(kprobe_opcode_t *instruction)
 	case 0x0b:	/* bsm	 */
 	case 0x83:	/* diag  */
 	case 0x44:	/* ex	 */
+	case 0xac:	/* stnsm */
+	case 0xad:	/* stosm */
 		return -EINVAL;
 	}
 	switch (*(__u16 *) instruction) {
@@ -71,6 +74,7 @@ int __kprobes is_prohibited_opcode(kprobe_opcode_t *instruction)
 	case 0xb258:	/* bsg	 */
 	case 0xb218:	/* pc	 */
 	case 0xb228:	/* pt	 */
+	case 0xb98d:	/* epsw	 */
 		return -EINVAL;
 	}
 	return 0;
diff --git a/arch/s390/kernel/machine_kexec.c b/arch/s390/kernel/machine_kexec.c
index 131d7ee8b41..a922d51df6b 100644
--- a/arch/s390/kernel/machine_kexec.c
+++ b/arch/s390/kernel/machine_kexec.c
@@ -54,11 +54,11 @@ void machine_shutdown(void)
 {
 }
 
-void machine_kexec(struct kimage *image)
+static void __machine_kexec(void *data)
 {
 	relocate_kernel_t data_mover;
+	struct kimage *image = data;
 
-	smp_send_stop();
 	pfault_fini();
 	s390_reset_system();
 
@@ -68,3 +68,9 @@ void machine_kexec(struct kimage *image)
 	(*data_mover)(&image->head, image->start);
 	for (;;);
 }
+
+void machine_kexec(struct kimage *image)
+{
+	smp_send_stop();
+	smp_switch_to_ipl_cpu(__machine_kexec, image);
+}
diff --git a/arch/s390/kernel/module.c b/arch/s390/kernel/module.c
index 639380a0c45..22cfd634c35 100644
--- a/arch/s390/kernel/module.c
+++ b/arch/s390/kernel/module.c
@@ -55,8 +55,10 @@ void *module_alloc(unsigned long size)
 /* Free memory returned from module_alloc */
 void module_free(struct module *mod, void *module_region)
 {
-	vfree(mod->arch.syminfo);
-	mod->arch.syminfo = NULL;
+	if (mod) {
+		vfree(mod->arch.syminfo);
+		mod->arch.syminfo = NULL;
+	}
 	vfree(module_region);
 }
 
diff --git a/arch/s390/kernel/nmi.c b/arch/s390/kernel/nmi.c
index 015e27da40e..ac151399ef3 100644
--- a/arch/s390/kernel/nmi.c
+++ b/arch/s390/kernel/nmi.c
@@ -255,7 +255,8 @@ void notrace s390_do_machine_check(struct pt_regs *regs)
 	int umode;
 
 	nmi_enter();
-	s390_idle_check();
+	s390_idle_check(regs, S390_lowcore.mcck_clock,
+			S390_lowcore.mcck_enter_timer);
 
 	mci = (struct mci *) &S390_lowcore.mcck_interruption_code;
 	mcck = &__get_cpu_var(cpu_mcck);
diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c
index 00b6d1d292f..1039fdea15b 100644
--- a/arch/s390/kernel/process.c
+++ b/arch/s390/kernel/process.c
@@ -16,9 +16,9 @@
 #include <linux/fs.h>
 #include <linux/smp.h>
 #include <linux/stddef.h>
+#include <linux/slab.h>
 #include <linux/unistd.h>
 #include <linux/ptrace.h>
-#include <linux/slab.h>
 #include <linux/vmalloc.h>
 #include <linux/user.h>
 #include <linux/interrupt.h>
diff --git a/arch/s390/kernel/processor.c b/arch/s390/kernel/processor.c
index 0729f36c2fe..ecb2d02b02e 100644
--- a/arch/s390/kernel/processor.c
+++ b/arch/s390/kernel/processor.c
@@ -18,24 +18,42 @@
 #include <asm/lowcore.h>
 #include <asm/param.h>
 
+static DEFINE_PER_CPU(struct cpuid, cpu_id);
+
+/*
+ * cpu_init - initializes state that is per-CPU.
+ */
+void __cpuinit cpu_init(void)
+{
+	struct cpuid *id = &per_cpu(cpu_id, smp_processor_id());
+
+	get_cpu_id(id);
+	atomic_inc(&init_mm.mm_count);
+	current->active_mm = &init_mm;
+	BUG_ON(current->mm);
+	enter_lazy_tlb(&init_mm, current);
+}
+
+/*
+ * print_cpu_info - print basic information about a cpu
+ */
 void __cpuinit print_cpu_info(void)
 {
+	struct cpuid *id = &per_cpu(cpu_id, smp_processor_id());
+
 	pr_info("Processor %d started, address %d, identification %06X\n",
-		S390_lowcore.cpu_nr, S390_lowcore.cpu_addr,
-		S390_lowcore.cpu_id.ident);
+		S390_lowcore.cpu_nr, S390_lowcore.cpu_addr, id->ident);
 }
 
 /*
  * show_cpuinfo - Get information on one CPU for use by procfs.
  */
-
 static int show_cpuinfo(struct seq_file *m, void *v)
 {
 	static const char *hwcap_str[10] = {
 		"esan3", "zarch", "stfle", "msa", "ldisp", "eimm", "dfp",
 		"edat", "etf3eh", "highgprs"
 	};
-	struct _lowcore *lc;
 	unsigned long n = (unsigned long) v - 1;
 	int i;
 
@@ -55,19 +73,12 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 	}
 
 	if (cpu_online(n)) {
-#ifdef CONFIG_SMP
-		lc = (smp_processor_id() == n) ?
-			&S390_lowcore : lowcore_ptr[n];
-#else
-		lc = &S390_lowcore;
-#endif
+		struct cpuid *id = &per_cpu(cpu_id, n);
 		seq_printf(m, "processor %li: "
 			   "version = %02X,  "
 			   "identification = %06X,  "
 			   "machine = %04X\n",
-			   n, lc->cpu_id.version,
-			   lc->cpu_id.ident,
-			   lc->cpu_id.machine);
+			   n, id->version, id->ident, id->machine);
 	}
 	preempt_enable();
 	return 0;
diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c
index 7cf46423441..83339d33c4b 100644
--- a/arch/s390/kernel/ptrace.c
+++ b/arch/s390/kernel/ptrace.c
@@ -57,6 +57,7 @@
 enum s390_regset {
 	REGSET_GENERAL,
 	REGSET_FP,
+	REGSET_LAST_BREAK,
 	REGSET_GENERAL_EXTENDED,
 };
 
@@ -381,6 +382,10 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data)
 			copied += sizeof(unsigned long);
 		}
 		return 0;
+	case PTRACE_GET_LAST_BREAK:
+		put_user(task_thread_info(child)->last_break,
+			 (unsigned long __user *) data);
+		return 0;
 	default:
 		/* Removing high order bit from addr (only for 31 bit). */
 		addr &= PSW_ADDR_INSN;
@@ -633,6 +638,10 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
 			copied += sizeof(unsigned int);
 		}
 		return 0;
+	case PTRACE_GET_LAST_BREAK:
+		put_user(task_thread_info(child)->last_break,
+			 (unsigned int __user *) data);
+		return 0;
 	}
 	return compat_ptrace_request(child, request, addr, data);
 }
@@ -640,7 +649,7 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
 
 asmlinkage long do_syscall_trace_enter(struct pt_regs *regs)
 {
-	long ret;
+	long ret = 0;
 
 	/* Do the secure computing check first. */
 	secure_computing(regs->gprs[2]);
@@ -649,7 +658,6 @@ asmlinkage long do_syscall_trace_enter(struct pt_regs *regs)
 	 * The sysc_tracesys code in entry.S stored the system
 	 * call number to gprs[2].
 	 */
-	ret = regs->gprs[2];
 	if (test_thread_flag(TIF_SYSCALL_TRACE) &&
 	    (tracehook_report_syscall_entry(regs) ||
 	     regs->gprs[2] >= NR_syscalls)) {
@@ -671,7 +679,7 @@ asmlinkage long do_syscall_trace_enter(struct pt_regs *regs)
 				    regs->gprs[2], regs->orig_gpr2,
 				    regs->gprs[3], regs->gprs[4],
 				    regs->gprs[5]);
-	return ret;
+	return ret ?: regs->gprs[2];
 }
 
 asmlinkage void do_syscall_trace_exit(struct pt_regs *regs)
@@ -798,6 +806,28 @@ static int s390_fpregs_set(struct task_struct *target,
 	return rc;
 }
 
+#ifdef CONFIG_64BIT
+
+static int s390_last_break_get(struct task_struct *target,
+			       const struct user_regset *regset,
+			       unsigned int pos, unsigned int count,
+			       void *kbuf, void __user *ubuf)
+{
+	if (count > 0) {
+		if (kbuf) {
+			unsigned long *k = kbuf;
+			*k = task_thread_info(target)->last_break;
+		} else {
+			unsigned long  __user *u = ubuf;
+			if (__put_user(task_thread_info(target)->last_break, u))
+				return -EFAULT;
+		}
+	}
+	return 0;
+}
+
+#endif
+
 static const struct user_regset s390_regsets[] = {
 	[REGSET_GENERAL] = {
 		.core_note_type = NT_PRSTATUS,
@@ -815,6 +845,15 @@ static const struct user_regset s390_regsets[] = {
 		.get = s390_fpregs_get,
 		.set = s390_fpregs_set,
 	},
+#ifdef CONFIG_64BIT
+	[REGSET_LAST_BREAK] = {
+		.core_note_type = NT_S390_LAST_BREAK,
+		.n = 1,
+		.size = sizeof(long),
+		.align = sizeof(long),
+		.get = s390_last_break_get,
+	},
+#endif
 };
 
 static const struct user_regset_view user_s390_view = {
@@ -949,6 +988,27 @@ static int s390_compat_regs_high_set(struct task_struct *target,
 	return rc;
 }
 
+static int s390_compat_last_break_get(struct task_struct *target,
+				      const struct user_regset *regset,
+				      unsigned int pos, unsigned int count,
+				      void *kbuf, void __user *ubuf)
+{
+	compat_ulong_t last_break;
+
+	if (count > 0) {
+		last_break = task_thread_info(target)->last_break;
+		if (kbuf) {
+			unsigned long *k = kbuf;
+			*k = last_break;
+		} else {
+			unsigned long  __user *u = ubuf;
+			if (__put_user(last_break, u))
+				return -EFAULT;
+		}
+	}
+	return 0;
+}
+
 static const struct user_regset s390_compat_regsets[] = {
 	[REGSET_GENERAL] = {
 		.core_note_type = NT_PRSTATUS,
@@ -966,6 +1026,13 @@ static const struct user_regset s390_compat_regsets[] = {
 		.get = s390_fpregs_get,
 		.set = s390_fpregs_set,
 	},
+	[REGSET_LAST_BREAK] = {
+		.core_note_type = NT_S390_LAST_BREAK,
+		.n = 1,
+		.size = sizeof(long),
+		.align = sizeof(long),
+		.get = s390_compat_last_break_get,
+	},
 	[REGSET_GENERAL_EXTENDED] = {
 		.core_note_type = NT_S390_HIGH_GPRS,
 		.n = sizeof(s390_compat_regs_high) / sizeof(compat_long_t),
@@ -992,3 +1059,61 @@ const struct user_regset_view *task_user_regset_view(struct task_struct *task)
 #endif
 	return &user_s390_view;
 }
+
+static const char *gpr_names[NUM_GPRS] = {
+	"r0", "r1",  "r2",  "r3",  "r4",  "r5",  "r6",  "r7",
+	"r8", "r9", "r10", "r11", "r12", "r13", "r14", "r15",
+};
+
+unsigned long regs_get_register(struct pt_regs *regs, unsigned int offset)
+{
+	if (offset >= NUM_GPRS)
+		return 0;
+	return regs->gprs[offset];
+}
+
+int regs_query_register_offset(const char *name)
+{
+	unsigned long offset;
+
+	if (!name || *name != 'r')
+		return -EINVAL;
+	if (strict_strtoul(name + 1, 10, &offset))
+		return -EINVAL;
+	if (offset >= NUM_GPRS)
+		return -EINVAL;
+	return offset;
+}
+
+const char *regs_query_register_name(unsigned int offset)
+{
+	if (offset >= NUM_GPRS)
+		return NULL;
+	return gpr_names[offset];
+}
+
+static int regs_within_kernel_stack(struct pt_regs *regs, unsigned long addr)
+{
+	unsigned long ksp = kernel_stack_pointer(regs);
+
+	return (addr & ~(THREAD_SIZE - 1)) == (ksp & ~(THREAD_SIZE - 1));
+}
+
+/**
+ * regs_get_kernel_stack_nth() - get Nth entry of the stack
+ * @regs:pt_regs which contains kernel stack pointer.
+ * @n:stack entry number.
+ *
+ * regs_get_kernel_stack_nth() returns @n th entry of the kernel stack which
+ * is specifined by @regs. If the @n th entry is NOT in the kernel stack,
+ * this returns 0.
+ */
+unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, unsigned int n)
+{
+	unsigned long addr;
+
+	addr = kernel_stack_pointer(regs) + n * sizeof(long);
+	if (!regs_within_kernel_stack(regs, addr))
+		return 0;
+	return *(unsigned long *)addr;
+}
diff --git a/arch/s390/kernel/reipl.S b/arch/s390/kernel/reipl.S
index 2f481cc3d1c..cb899d9f850 100644
--- a/arch/s390/kernel/reipl.S
+++ b/arch/s390/kernel/reipl.S
@@ -6,7 +6,7 @@
  *    Author(s): Holger Smolinski (Holger.Smolinski@de.ibm.com)
  */
 
-#include <asm/lowcore.h>
+#include <asm/asm-offsets.h>
 
 #
 # do_reipl_asm
diff --git a/arch/s390/kernel/reipl64.S b/arch/s390/kernel/reipl64.S
index 774147824c3..5e73dee63ba 100644
--- a/arch/s390/kernel/reipl64.S
+++ b/arch/s390/kernel/reipl64.S
@@ -4,7 +4,7 @@
  *		 Denis Joseph Barrow,
  */
 
-#include <asm/lowcore.h>
+#include <asm/asm-offsets.h>
 
 #
 # do_reipl_asm
diff --git a/arch/s390/kernel/s390_ext.c b/arch/s390/kernel/s390_ext.c
index 59618bcd99b..9ce641b5291 100644
--- a/arch/s390/kernel/s390_ext.c
+++ b/arch/s390/kernel/s390_ext.c
@@ -120,7 +120,8 @@ void __irq_entry do_extint(struct pt_regs *regs, unsigned short code)
 	struct pt_regs *old_regs;
 
 	old_regs = set_irq_regs(regs);
-	s390_idle_check();
+	s390_idle_check(regs, S390_lowcore.int_clock,
+			S390_lowcore.async_enter_timer);
 	irq_enter();
 	if (S390_lowcore.int_clock >= S390_lowcore.clock_comparator)
 		/* Serve timer interrupts first. */
diff --git a/arch/s390/kernel/sclp.S b/arch/s390/kernel/sclp.S
index e27ca63076d..2e82fdd8932 100644
--- a/arch/s390/kernel/sclp.S
+++ b/arch/s390/kernel/sclp.S
@@ -9,8 +9,10 @@
  */
 
 LC_EXT_NEW_PSW		= 0x58			# addr of ext int handler
+LC_EXT_NEW_PSW_64	= 0x1b0			# addr of ext int handler 64 bit
 LC_EXT_INT_PARAM	= 0x80			# addr of ext int parameter
 LC_EXT_INT_CODE		= 0x86			# addr of ext int code
+LC_AR_MODE_ID		= 0xa3
 
 #
 # Subroutine which waits synchronously until either an external interruption
@@ -30,8 +32,16 @@ _sclp_wait_int:
 .LbaseS1:
 	ahi	%r15,-96			# create stack frame
 	la	%r8,LC_EXT_NEW_PSW		# register int handler
-	mvc	.LoldpswS1-.LbaseS1(8,%r13),0(%r8)
-	mvc	0(8,%r8),.LextpswS1-.LbaseS1(%r13)
+	la	%r9,.LextpswS1-.LbaseS1(%r13)
+#ifdef CONFIG_64BIT
+	tm	LC_AR_MODE_ID,1
+	jno	.Lesa1
+	la	%r8,LC_EXT_NEW_PSW_64		# register int handler 64 bit
+	la	%r9,.LextpswS1_64-.LbaseS1(%r13)
+.Lesa1:
+#endif
+	mvc	.LoldpswS1-.LbaseS1(16,%r13),0(%r8)
+	mvc	0(16,%r8),0(%r9)
 	lhi	%r6,0x0200			# cr mask for ext int (cr0.54)
 	ltr	%r2,%r2
 	jz	.LsetctS1
@@ -64,15 +74,19 @@ _sclp_wait_int:
 .LtimeoutS1:
 	lctl	%c0,%c0,.LctlS1-.LbaseS1(%r13)	# restore interrupt setting
 	# restore old handler
-	mvc	0(8,%r8),.LoldpswS1-.LbaseS1(%r13)
+	mvc	0(16,%r8),.LoldpswS1-.LbaseS1(%r13)
 	lm	%r6,%r15,120(%r15)		# restore registers
 	br	%r14				# return to caller
 
 	.align	8
 .LoldpswS1:
-	.long	0, 0				# old ext int PSW
+	.long	0, 0, 0, 0			# old ext int PSW
 .LextpswS1:
 	.long	0x00080000, 0x80000000+.LwaitS1	# PSW to handle ext int
+#ifdef CONFIG_64BIT
+.LextpswS1_64:
+	.quad	0x0000000180000000, .LwaitS1	# PSW to handle ext int, 64 bit
+#endif
 .LwaitpswS1:
 	.long	0x010a0000, 0x00000000+.LloopS1	# PSW to wait for ext int
 .LtimeS1:
@@ -221,7 +235,7 @@ _sclp_print:
 	lh	%r9,0(%r8)			# update sccb length
 	ar	%r9,%r6
 	sth	%r9,0(%r8)
-	ar	%r7,%r6				# update current mto adress
+	ar	%r7,%r6				# update current mto address
 	ltr	%r0,%r0				# more characters?
 	jnz	.LinitmtoS4
 	l	%r2,.LwritedataS4-.LbaseS4(%r13)# write data
@@ -250,6 +264,13 @@ _sclp_print:
 _sclp_print_early:
 	stm	%r6,%r15,24(%r15)		# save registers
 	ahi	%r15,-96			# create stack frame
+#ifdef CONFIG_64BIT
+	tm	LC_AR_MODE_ID,1
+	jno	.Lesa2
+	ahi	%r15,-80
+	stmh	%r6,%r15,96(%r15)		# store upper register halves
+.Lesa2:
+#endif
 	lr	%r10,%r2			# save string pointer
 	lhi	%r2,0
 	bras	%r14,_sclp_setup		# enable console
@@ -262,6 +283,13 @@ _sclp_print_early:
 	lhi	%r2,1
 	bras	%r14,_sclp_setup		# disable console
 .LendS5:
+#ifdef CONFIG_64BIT
+	tm	LC_AR_MODE_ID,1
+	jno	.Lesa3
+	lmh	%r6,%r15,96(%r15)		# store upper register halves
+	ahi	%r15,80
+.Lesa3:
+#endif
 	lm	%r6,%r15,120(%r15)		# restore registers
 	br	%r14
 
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index 8d8957b38ab..c8e8e1354e1 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -2,7 +2,7 @@
  *  arch/s390/kernel/setup.c
  *
  *  S390 version
- *    Copyright (C) 1999,2000 IBM Deutschland Entwicklung GmbH, IBM Corporation
+ *    Copyright (C) IBM Corp. 1999,2010
  *    Author(s): Hartmut Penner (hp@de.ibm.com),
  *               Martin Schwidefsky (schwidefsky@de.ibm.com)
  *
@@ -25,7 +25,6 @@
 #include <linux/stddef.h>
 #include <linux/unistd.h>
 #include <linux/ptrace.h>
-#include <linux/slab.h>
 #include <linux/user.h>
 #include <linux/tty.h>
 #include <linux/ioport.h>
@@ -114,22 +113,6 @@ static struct resource data_resource = {
 };
 
 /*
- * cpu_init() initializes state that is per-CPU.
- */
-void __cpuinit cpu_init(void)
-{
-        /*
-         * Store processor id in lowcore (used e.g. in timer_interrupt)
-         */
-	get_cpu_id(&S390_lowcore.cpu_id);
-
-	atomic_inc(&init_mm.mm_count);
-	current->active_mm = &init_mm;
-	BUG_ON(current->mm);
-        enter_lazy_tlb(&init_mm, current);
-}
-
-/*
  * condev= and conmode= setup parameter.
  */
 
@@ -386,25 +369,18 @@ static void setup_addressing_mode(void)
 			pr_info("Address spaces switched, "
 				"mvcos not available\n");
 	}
-#ifdef CONFIG_TRACE_IRQFLAGS
-	sysc_restore_trace_psw.mask = psw_kernel_bits & ~PSW_MASK_MCHECK;
-	io_restore_trace_psw.mask = psw_kernel_bits & ~PSW_MASK_MCHECK;
-#endif
 }
 
 static void __init
 setup_lowcore(void)
 {
 	struct _lowcore *lc;
-	int lc_pages;
 
 	/*
 	 * Setup lowcore for boot cpu
 	 */
-	lc_pages = sizeof(void *) == 8 ? 2 : 1;
-	lc = (struct _lowcore *)
-		__alloc_bootmem(lc_pages * PAGE_SIZE, lc_pages * PAGE_SIZE, 0);
-	memset(lc, 0, lc_pages * PAGE_SIZE);
+	BUILD_BUG_ON(sizeof(struct _lowcore) != LC_PAGES * 4096);
+	lc = __alloc_bootmem_low(LC_PAGES * PAGE_SIZE, LC_PAGES * PAGE_SIZE, 0);
 	lc->restart_psw.mask = PSW_BASE_BITS | PSW_DEFAULT_KEY;
 	lc->restart_psw.addr =
 		PSW_ADDR_AMODE | (unsigned long) restart_int_handler;
@@ -436,11 +412,12 @@ setup_lowcore(void)
 #ifndef CONFIG_64BIT
 	if (MACHINE_HAS_IEEE) {
 		lc->extended_save_area_addr = (__u32)
-			__alloc_bootmem(PAGE_SIZE, PAGE_SIZE, 0);
+			__alloc_bootmem_low(PAGE_SIZE, PAGE_SIZE, 0);
 		/* enable extended save area */
 		__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;
@@ -699,6 +676,7 @@ static void __init setup_hwcaps(void)
 	static const int stfl_bits[6] = { 0, 2, 7, 17, 19, 21 };
 	unsigned long long facility_list_extended;
 	unsigned int facility_list;
+	struct cpuid cpu_id;
 	int i;
 
 	facility_list = stfl();
@@ -760,7 +738,8 @@ static void __init setup_hwcaps(void)
 	 */
 	elf_hwcap |= HWCAP_S390_HIGH_GPRS;
 
-	switch (S390_lowcore.cpu_id.machine) {
+	get_cpu_id(&cpu_id);
+	switch (cpu_id.machine) {
 	case 0x9672:
 #if !defined(CONFIG_64BIT)
 	default:	/* Use "g5" as default for 31 bit kernels. */
@@ -804,7 +783,7 @@ setup_arch(char **cmdline_p)
 	if (MACHINE_IS_VM)
 		pr_info("Linux is running as a z/VM "
 			"guest operating system in 31-bit mode\n");
-	else
+	else if (MACHINE_IS_LPAR)
 		pr_info("Linux is running natively in 31-bit mode\n");
 	if (MACHINE_HAS_IEEE)
 		pr_info("The hardware system has IEEE compatible "
@@ -818,7 +797,7 @@ setup_arch(char **cmdline_p)
 			"guest operating system in 64-bit mode\n");
 	else if (MACHINE_IS_KVM)
 		pr_info("Linux is running under KVM in 64-bit mode\n");
-	else
+	else if (MACHINE_IS_LPAR)
 		pr_info("Linux is running natively in 64-bit mode\n");
 #endif /* CONFIG_64BIT */
 
diff --git a/arch/s390/kernel/signal.c b/arch/s390/kernel/signal.c
index 6289945562b..ee7ac8b1178 100644
--- a/arch/s390/kernel/signal.c
+++ b/arch/s390/kernel/signal.c
@@ -313,6 +313,7 @@ static int setup_frame(int sig, struct k_sigaction *ka,
 	   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;
 
 	/* Place signal number on stack to allow backtrace from handler.  */
 	if (__put_user(regs->gprs[2], (int __user *) &frame->signo))
@@ -376,6 +377,7 @@ static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
 	regs->gprs[2] = map_signal(sig);
 	regs->gprs[3] = (unsigned long) &frame->info;
 	regs->gprs[4] = (unsigned long) &frame->uc;
+	regs->gprs[5] = task_thread_info(current)->last_break;
 	return 0;
 
 give_sigsegv:
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index 76a6fdd46c4..541053ed234 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -36,6 +36,8 @@
 #include <linux/cpu.h>
 #include <linux/timex.h>
 #include <linux/bootmem.h>
+#include <linux/slab.h>
+#include <asm/asm-offsets.h>
 #include <asm/ipl.h>
 #include <asm/setup.h>
 #include <asm/sigp.h>
@@ -53,7 +55,7 @@
 #include "entry.h"
 
 /* logical cpu to cpu address */
-int __cpu_logical_map[NR_CPUS];
+unsigned short __cpu_logical_map[NR_CPUS];
 
 static struct task_struct *current_set[NR_CPUS];
 
@@ -72,13 +74,13 @@ static int cpu_management;
 
 static DEFINE_PER_CPU(struct cpu, cpu_devices);
 
-static void smp_ext_bitcall(int, ec_bit_sig);
+static void smp_ext_bitcall(int, int);
 
-static int cpu_stopped(int cpu)
+static int raw_cpu_stopped(int cpu)
 {
-	__u32 status;
+	u32 status;
 
-	switch (signal_processor_ps(&status, 0, cpu, sigp_sense)) {
+	switch (raw_sigp_ps(&status, 0, cpu, sigp_sense)) {
 	case sigp_status_stored:
 		/* Check for stopped and check stop state */
 		if (status & 0x50)
@@ -90,6 +92,44 @@ static int cpu_stopped(int cpu)
 	return 0;
 }
 
+static inline int cpu_stopped(int cpu)
+{
+	return raw_cpu_stopped(cpu_logical_map(cpu));
+}
+
+void smp_switch_to_ipl_cpu(void (*func)(void *), void *data)
+{
+	struct _lowcore *lc, *current_lc;
+	struct stack_frame *sf;
+	struct pt_regs *regs;
+	unsigned long sp;
+
+	if (smp_processor_id() == 0)
+		func(data);
+	__load_psw_mask(PSW_BASE_BITS | PSW_DEFAULT_KEY);
+	/* Disable lowcore protection */
+	__ctl_clear_bit(0, 28);
+	current_lc = lowcore_ptr[smp_processor_id()];
+	lc = lowcore_ptr[0];
+	if (!lc)
+		lc = current_lc;
+	lc->restart_psw.mask = PSW_BASE_BITS | PSW_DEFAULT_KEY;
+	lc->restart_psw.addr = PSW_ADDR_AMODE | (unsigned long) smp_restart_cpu;
+	if (!cpu_online(0))
+		smp_switch_to_cpu(func, data, 0, stap(), __cpu_logical_map[0]);
+	while (sigp(0, sigp_stop_and_store_status) == sigp_busy)
+		cpu_relax();
+	sp = lc->panic_stack;
+	sp -= sizeof(struct pt_regs);
+	regs = (struct pt_regs *) sp;
+	memcpy(&regs->gprs, &current_lc->gpregs_save_area, sizeof(regs->gprs));
+	regs->psw = lc->psw_save_area;
+	sp -= STACK_FRAME_OVERHEAD;
+	sf = (struct stack_frame *) sp;
+	sf->back_chain = regs->gprs[15];
+	smp_switch_to_cpu(func, data, sp, stap(), __cpu_logical_map[0]);
+}
+
 void smp_send_stop(void)
 {
 	int cpu, rc;
@@ -103,7 +143,7 @@ void smp_send_stop(void)
 		if (cpu == smp_processor_id())
 			continue;
 		do {
-			rc = signal_processor(cpu, sigp_stop);
+			rc = sigp(cpu, sigp_stop);
 		} while (rc == sigp_busy);
 
 		while (!cpu_stopped(cpu))
@@ -139,13 +179,13 @@ static void do_ext_call_interrupt(__u16 code)
  * Send an external call sigp to another cpu and return without waiting
  * for its completion.
  */
-static void smp_ext_bitcall(int cpu, ec_bit_sig sig)
+static void smp_ext_bitcall(int cpu, int sig)
 {
 	/*
 	 * Set signaling bit in lowcore of target cpu and kick it
 	 */
 	set_bit(sig, (unsigned long *) &lowcore_ptr[cpu]->ext_call_fast);
-	while (signal_processor(cpu, sigp_emergency_signal) == sigp_busy)
+	while (sigp(cpu, sigp_emergency_signal) == sigp_busy)
 		udelay(10);
 }
 
@@ -239,24 +279,8 @@ void smp_ctl_clear_bit(int cr, int bit)
 }
 EXPORT_SYMBOL(smp_ctl_clear_bit);
 
-/*
- * In early ipl state a temp. logically cpu number is needed, so the sigp
- * functions can be used to sense other cpus. Since NR_CPUS is >= 2 on
- * CONFIG_SMP and the ipl cpu is logical cpu 0, it must be 1.
- */
-#define CPU_INIT_NO	1
-
 #ifdef CONFIG_ZFCPDUMP
 
-/*
- * zfcpdump_prefix_array holds prefix registers for the following scenario:
- * 64 bit zfcpdump kernel and 31 bit kernel which is to be dumped. We have to
- * save its prefix registers, since they get lost, when switching from 31 bit
- * to 64 bit.
- */
-unsigned int zfcpdump_prefix_array[NR_CPUS + 1] \
-	__attribute__((__section__(".data")));
-
 static void __init smp_get_save_area(unsigned int cpu, unsigned int phy_cpu)
 {
 	if (ipl_info.type != IPL_TYPE_FCP_DUMP)
@@ -266,21 +290,15 @@ static void __init smp_get_save_area(unsigned int cpu, unsigned int phy_cpu)
 			   "the dump\n", cpu, NR_CPUS - 1);
 		return;
 	}
-	zfcpdump_save_areas[cpu] = kmalloc(sizeof(union save_area), GFP_KERNEL);
-	__cpu_logical_map[CPU_INIT_NO] = (__u16) phy_cpu;
-	while (signal_processor(CPU_INIT_NO, sigp_stop_and_store_status) ==
-	       sigp_busy)
+	zfcpdump_save_areas[cpu] = kmalloc(sizeof(struct save_area), GFP_KERNEL);
+	while (raw_sigp(phy_cpu, sigp_stop_and_store_status) == sigp_busy)
 		cpu_relax();
-	memcpy(zfcpdump_save_areas[cpu],
-	       (void *)(unsigned long) store_prefix() + SAVE_AREA_BASE,
-	       SAVE_AREA_SIZE);
-#ifdef CONFIG_64BIT
-	/* copy original prefix register */
-	zfcpdump_save_areas[cpu]->s390x.pref_reg = zfcpdump_prefix_array[cpu];
-#endif
+	memcpy_real(zfcpdump_save_areas[cpu],
+		    (void *)(unsigned long) store_prefix() + SAVE_AREA_BASE,
+		    sizeof(struct save_area));
 }
 
-union save_area *zfcpdump_save_areas[NR_CPUS + 1];
+struct save_area *zfcpdump_save_areas[NR_CPUS + 1];
 EXPORT_SYMBOL_GPL(zfcpdump_save_areas);
 
 #else
@@ -389,8 +407,7 @@ static void __init smp_detect_cpus(void)
 		for (cpu = 0; cpu <= MAX_CPU_ADDRESS; cpu++) {
 			if (cpu == boot_cpu_addr)
 				continue;
-			__cpu_logical_map[CPU_INIT_NO] = cpu;
-			if (!cpu_stopped(CPU_INIT_NO))
+			if (!raw_cpu_stopped(cpu))
 				continue;
 			smp_get_save_area(c_cpus, cpu);
 			c_cpus++;
@@ -413,8 +430,7 @@ static void __init smp_detect_cpus(void)
 		cpu_addr = info->cpu[cpu].address;
 		if (cpu_addr == boot_cpu_addr)
 			continue;
-		__cpu_logical_map[CPU_INIT_NO] = cpu_addr;
-		if (!cpu_stopped(CPU_INIT_NO)) {
+		if (!raw_cpu_stopped(cpu_addr)) {
 			s_cpus++;
 			continue;
 		}
@@ -533,18 +549,18 @@ static void smp_free_lowcore(int cpu)
 /* Upping and downing of CPUs */
 int __cpuinit __cpu_up(unsigned int cpu)
 {
-	struct task_struct *idle;
 	struct _lowcore *cpu_lowcore;
+	struct task_struct *idle;
 	struct stack_frame *sf;
-	sigp_ccode ccode;
 	u32 lowcore;
+	int ccode;
 
 	if (smp_cpu_state[cpu] != CPU_STATE_CONFIGURED)
 		return -EIO;
 	if (smp_alloc_lowcore(cpu))
 		return -ENOMEM;
 	do {
-		ccode = signal_processor(cpu, sigp_initial_cpu_reset);
+		ccode = sigp(cpu, sigp_initial_cpu_reset);
 		if (ccode == sigp_busy)
 			udelay(10);
 		if (ccode == sigp_not_operational)
@@ -552,7 +568,7 @@ int __cpuinit __cpu_up(unsigned int cpu)
 	} while (ccode == sigp_busy);
 
 	lowcore = (u32)(unsigned long)lowcore_ptr[cpu];
-	while (signal_processor_p(lowcore, cpu, sigp_set_prefix) == sigp_busy)
+	while (sigp_p(lowcore, cpu, sigp_set_prefix) == sigp_busy)
 		udelay(10);
 
 	idle = current_set[cpu];
@@ -578,7 +594,7 @@ int __cpuinit __cpu_up(unsigned int cpu)
 	cpu_lowcore->ftrace_func = S390_lowcore.ftrace_func;
 	eieio();
 
-	while (signal_processor(cpu, sigp_restart) == sigp_busy)
+	while (sigp(cpu, sigp_restart) == sigp_busy)
 		udelay(10);
 
 	while (!cpu_online(cpu))
@@ -640,7 +656,7 @@ void __cpu_die(unsigned int cpu)
 	/* Wait until target cpu is down */
 	while (!cpu_stopped(cpu))
 		cpu_relax();
-	while (signal_processor_p(0, cpu, sigp_set_prefix) == sigp_busy)
+	while (sigp_p(0, cpu, sigp_set_prefix) == sigp_busy)
 		udelay(10);
 	smp_free_lowcore(cpu);
 	pr_info("Processor %d stopped\n", cpu);
@@ -649,7 +665,7 @@ void __cpu_die(unsigned int cpu)
 void cpu_die(void)
 {
 	idle_task_exit();
-	while (signal_processor(smp_processor_id(), sigp_stop) == sigp_busy)
+	while (sigp(smp_processor_id(), sigp_stop) == sigp_busy)
 		cpu_relax();
 	for (;;);
 }
@@ -765,7 +781,8 @@ static ssize_t cpu_configure_store(struct sys_device *dev,
 	get_online_cpus();
 	mutex_lock(&smp_cpu_state_mutex);
 	rc = -EBUSY;
-	if (cpu_online(cpu))
+	/* disallow configuration changes of online cpus and cpu 0 */
+	if (cpu_online(cpu) || cpu == 0)
 		goto out;
 	rc = 0;
 	switch (val) {
@@ -927,21 +944,21 @@ static int __cpuinit smp_cpu_notify(struct notifier_block *self,
 	struct cpu *c = &per_cpu(cpu_devices, cpu);
 	struct sys_device *s = &c->sysdev;
 	struct s390_idle_data *idle;
+	int err = 0;
 
 	switch (action) {
 	case CPU_ONLINE:
 	case CPU_ONLINE_FROZEN:
 		idle = &per_cpu(s390_idle, cpu);
 		memset(idle, 0, sizeof(struct s390_idle_data));
-		if (sysfs_create_group(&s->kobj, &cpu_online_attr_group))
-			return NOTIFY_BAD;
+		err = sysfs_create_group(&s->kobj, &cpu_online_attr_group);
 		break;
 	case CPU_DEAD:
 	case CPU_DEAD_FROZEN:
 		sysfs_remove_group(&s->kobj, &cpu_online_attr_group);
 		break;
 	}
-	return NOTIFY_OK;
+	return notifier_from_errno(err);
 }
 
 static struct notifier_block __cpuinitdata smp_cpu_nb = {
@@ -1004,7 +1021,9 @@ out:
 	return rc;
 }
 
-static ssize_t __ref rescan_store(struct sysdev_class *class, const char *buf,
+static ssize_t __ref rescan_store(struct sysdev_class *class,
+				  struct sysdev_class_attribute *attr,
+				  const char *buf,
 				  size_t count)
 {
 	int rc;
@@ -1015,7 +1034,9 @@ static ssize_t __ref rescan_store(struct sysdev_class *class, const char *buf,
 static SYSDEV_CLASS_ATTR(rescan, 0200, NULL, rescan_store);
 #endif /* CONFIG_HOTPLUG_CPU */
 
-static ssize_t dispatching_show(struct sysdev_class *class, char *buf)
+static ssize_t dispatching_show(struct sysdev_class *class,
+				struct sysdev_class_attribute *attr,
+				char *buf)
 {
 	ssize_t count;
 
@@ -1025,7 +1046,9 @@ static ssize_t dispatching_show(struct sysdev_class *class, char *buf)
 	return count;
 }
 
-static ssize_t dispatching_store(struct sysdev_class *dev, const char *buf,
+static ssize_t dispatching_store(struct sysdev_class *dev,
+				 struct sysdev_class_attribute *attr,
+				 const char *buf,
 				 size_t count)
 {
 	int val, rc;
diff --git a/arch/s390/kernel/switch_cpu.S b/arch/s390/kernel/switch_cpu.S
new file mode 100644
index 00000000000..469f11b574f
--- /dev/null
+++ b/arch/s390/kernel/switch_cpu.S
@@ -0,0 +1,58 @@
+/*
+ * 31-bit switch cpu code
+ *
+ * Copyright IBM Corp. 2009
+ *
+ */
+
+#include <asm/asm-offsets.h>
+#include <asm/ptrace.h>
+
+# smp_switch_to_cpu switches to destination cpu and executes the passed function
+# Parameter: %r2 - function to call
+#	     %r3 - function parameter
+#	     %r4 - stack poiner
+#	     %r5 - current cpu
+#	     %r6 - destination cpu
+
+	.section .text
+	.align 4
+	.globl smp_switch_to_cpu
+smp_switch_to_cpu:
+	stm	%r6,%r15,__SF_GPRS(%r15)
+	lr	%r1,%r15
+	ahi	%r15,-STACK_FRAME_OVERHEAD
+	st	%r1,__SF_BACKCHAIN(%r15)
+	basr	%r13,0
+0:	la	%r1,.gprregs_addr-0b(%r13)
+	l	%r1,0(%r1)
+	stm	%r0,%r15,0(%r1)
+1:	sigp	%r0,%r6,__SIGP_RESTART	/* start destination CPU */
+	brc	2,1b			/* busy, try again */
+2:	sigp	%r0,%r5,__SIGP_STOP	/* stop current CPU */
+	brc	2,2b			/* busy, try again */
+3:	j	3b
+
+	.globl	smp_restart_cpu
+smp_restart_cpu:
+	basr	%r13,0
+0:	la	%r1,.gprregs_addr-0b(%r13)
+	l	%r1,0(%r1)
+	lm	%r0,%r15,0(%r1)
+1:	sigp	%r0,%r5,__SIGP_SENSE	/* Wait for calling CPU */
+	brc	10,1b			/* busy, accepted (status 0), running */
+	tmll	%r0,0x40		/* Test if calling CPU is stopped */
+	jz	1b
+	ltr	%r4,%r4			/* New stack ? */
+	jz	1f
+	lr	%r15,%r4
+1:	basr	%r14,%r2
+
+.gprregs_addr:
+	.long	.gprregs
+
+	.section .data,"aw",@progbits
+.gprregs:
+	.rept	16
+	.long	0
+	.endr
diff --git a/arch/s390/kernel/switch_cpu64.S b/arch/s390/kernel/switch_cpu64.S
new file mode 100644
index 00000000000..d94aacc898c
--- /dev/null
+++ b/arch/s390/kernel/switch_cpu64.S
@@ -0,0 +1,51 @@
+/*
+ * 64-bit switch cpu code
+ *
+ * Copyright IBM Corp. 2009
+ *
+ */
+
+#include <asm/asm-offsets.h>
+#include <asm/ptrace.h>
+
+# smp_switch_to_cpu switches to destination cpu and executes the passed function
+# Parameter: %r2 - function to call
+#	     %r3 - function parameter
+#	     %r4 - stack poiner
+#	     %r5 - current cpu
+#	     %r6 - destination cpu
+
+	.section .text
+	.align 4
+	.globl smp_switch_to_cpu
+smp_switch_to_cpu:
+	stmg	%r6,%r15,__SF_GPRS(%r15)
+	lgr	%r1,%r15
+	aghi	%r15,-STACK_FRAME_OVERHEAD
+	stg	%r1,__SF_BACKCHAIN(%r15)
+	larl	%r1,.gprregs
+	stmg	%r0,%r15,0(%r1)
+1:	sigp	%r0,%r6,__SIGP_RESTART	/* start destination CPU */
+	brc	2,1b			/* busy, try again */
+2:	sigp	%r0,%r5,__SIGP_STOP	/* stop current CPU */
+	brc	2,2b			/* busy, try again */
+3:	j	3b
+
+	.globl	smp_restart_cpu
+smp_restart_cpu:
+	larl	%r1,.gprregs
+	lmg	%r0,%r15,0(%r1)
+1:	sigp	%r0,%r5,__SIGP_SENSE	/* Wait for calling CPU */
+	brc	10,1b			/* busy, accepted (status 0), running */
+	tmll	%r0,0x40		/* Test if calling CPU is stopped */
+	jz	1b
+	ltgr	%r4,%r4			/* New stack ? */
+	jz	1f
+	lgr	%r15,%r4
+1:	basr	%r14,%r2
+
+	.section .data,"aw",@progbits
+.gprregs:
+	.rept	16
+	.quad	0
+	.endr
diff --git a/arch/s390/kernel/swsusp_asm64.S b/arch/s390/kernel/swsusp_asm64.S
index e5cd623cb02..1f066e46e83 100644
--- a/arch/s390/kernel/swsusp_asm64.S
+++ b/arch/s390/kernel/swsusp_asm64.S
@@ -176,7 +176,7 @@ pgm_check_entry:
 	cgr	%r1,%r2
 	je	restore_registers		/* r1 = r2 -> nothing to do */
 	larl	%r4,.Lrestart_suspend_psw	/* Set new restart PSW */
-	mvc	__LC_RESTART_PSW(16,%r0),0(%r4)
+	mvc	__LC_RST_NEW_PSW(16,%r0),0(%r4)
 3:
 	sigp	%r9,%r1,__SIGP_INITIAL_CPU_RESET
 	brc	8,4f	/* accepted */
@@ -256,6 +256,9 @@ restore_registers:
 	lghi	%r2,0
 	brasl	%r14,arch_set_page_states
 
+	/* Reinitialize the channel subsystem */
+	brasl	%r14,channel_subsystem_reinit
+
 	/* Return 0 */
 	lmg	%r6,%r15,STACK_FRAME_OVERHEAD + __SF_GPRS(%r15)
 	lghi	%r2,0
diff --git a/arch/s390/kernel/sys_s390.c b/arch/s390/kernel/sys_s390.c
index 86a74c9c9e6..7b6b0f81a28 100644
--- a/arch/s390/kernel/sys_s390.c
+++ b/arch/s390/kernel/sys_s390.c
@@ -33,13 +33,12 @@
 #include "entry.h"
 
 /*
- * Perform the select(nd, in, out, ex, tv) and mmap() system
- * calls. Linux for S/390 isn't able to handle more than 5
- * system call parameters, so these system calls used a memory
- * block for parameter passing..
+ * Perform the mmap() system call. Linux for S/390 isn't able to handle more
+ * than 5 system call parameters, so this system call uses a memory block
+ * for parameter passing.
  */
 
-struct mmap_arg_struct {
+struct s390_mmap_arg_struct {
 	unsigned long addr;
 	unsigned long len;
 	unsigned long prot;
@@ -48,9 +47,9 @@ struct mmap_arg_struct {
 	unsigned long offset;
 };
 
-SYSCALL_DEFINE1(mmap2, struct mmap_arg_struct __user *, arg)
+SYSCALL_DEFINE1(mmap2, struct s390_mmap_arg_struct __user *, arg)
 {
-	struct mmap_arg_struct a;
+	struct s390_mmap_arg_struct a;
 	int error = -EFAULT;
 
 	if (copy_from_user(&a, arg, sizeof(a)))
@@ -60,29 +59,12 @@ out:
 	return error;
 }
 
-SYSCALL_DEFINE1(s390_old_mmap, struct mmap_arg_struct __user *, arg)
-{
-	struct mmap_arg_struct a;
-	long error = -EFAULT;
-
-	if (copy_from_user(&a, arg, sizeof(a)))
-		goto out;
-
-	error = -EINVAL;
-	if (a.offset & ~PAGE_MASK)
-		goto out;
-
-	error = sys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, a.fd, a.offset >> PAGE_SHIFT);
-out:
-	return error;
-}
-
 /*
  * sys_ipc() is the de-multiplexer for the SysV IPC calls..
  *
  * This is really horribly ugly.
  */
-SYSCALL_DEFINE5(ipc, uint, call, int, first, unsigned long, second,
+SYSCALL_DEFINE5(s390_ipc, uint, call, int, first, unsigned long, second,
 		unsigned long, third, void __user *, ptr)
 {
         struct ipc_kludge tmp;
@@ -149,17 +131,6 @@ SYSCALL_DEFINE5(ipc, uint, call, int, first, unsigned long, second,
 }
 
 #ifdef CONFIG_64BIT
-SYSCALL_DEFINE1(s390_newuname, struct new_utsname __user *, name)
-{
-	int ret = sys_newuname(name);
-
-	if (personality(current->personality) == PER_LINUX32 && !ret) {
-		ret = copy_to_user(name->machine, "s390\0\0\0\0", 8);
-		if (ret) ret = -EFAULT;
-	}
-	return ret;
-}
-
 SYSCALL_DEFINE1(s390_personality, unsigned long, personality)
 {
 	int ret;
diff --git a/arch/s390/kernel/syscalls.S b/arch/s390/kernel/syscalls.S
index 30eca070d42..201ce6bed34 100644
--- a/arch/s390/kernel/syscalls.S
+++ b/arch/s390/kernel/syscalls.S
@@ -98,7 +98,7 @@ SYSCALL(sys_uselib,sys_uselib,sys32_uselib_wrapper)
 SYSCALL(sys_swapon,sys_swapon,sys32_swapon_wrapper)
 SYSCALL(sys_reboot,sys_reboot,sys32_reboot_wrapper)
 SYSCALL(sys_ni_syscall,sys_ni_syscall,old32_readdir_wrapper)	/* old readdir syscall */
-SYSCALL(sys_s390_old_mmap,sys_s390_old_mmap,old32_mmap_wrapper)	/* 90 */
+SYSCALL(sys_old_mmap,sys_old_mmap,old32_mmap_wrapper)		/* 90 */
 SYSCALL(sys_munmap,sys_munmap,sys32_munmap_wrapper)
 SYSCALL(sys_truncate,sys_truncate,sys32_truncate_wrapper)
 SYSCALL(sys_ftruncate,sys_ftruncate,sys32_ftruncate_wrapper)
@@ -125,12 +125,12 @@ NI_SYSCALL							/* vm86old for i386 */
 SYSCALL(sys_wait4,sys_wait4,compat_sys_wait4_wrapper)
 SYSCALL(sys_swapoff,sys_swapoff,sys32_swapoff_wrapper)		/* 115 */
 SYSCALL(sys_sysinfo,sys_sysinfo,compat_sys_sysinfo_wrapper)
-SYSCALL(sys_ipc,sys_ipc,sys32_ipc_wrapper)
+SYSCALL(sys_s390_ipc,sys_s390_ipc,sys32_ipc_wrapper)
 SYSCALL(sys_fsync,sys_fsync,sys32_fsync_wrapper)
 SYSCALL(sys_sigreturn,sys_sigreturn,sys32_sigreturn)
 SYSCALL(sys_clone,sys_clone,sys_clone_wrapper)			/* 120 */
 SYSCALL(sys_setdomainname,sys_setdomainname,sys32_setdomainname_wrapper)
-SYSCALL(sys_newuname,sys_s390_newuname,sys32_newuname_wrapper)
+SYSCALL(sys_newuname,sys_newuname,sys32_newuname_wrapper)
 NI_SYSCALL							/* modify_ldt for i386 */
 SYSCALL(sys_adjtimex,sys_adjtimex,compat_sys_adjtimex_wrapper)
 SYSCALL(sys_mprotect,sys_mprotect,sys32_mprotect_wrapper)	/* 125 */
diff --git a/arch/s390/kernel/sysinfo.c b/arch/s390/kernel/sysinfo.c
index b5e75e1061c..a0ffc7717ed 100644
--- a/arch/s390/kernel/sysinfo.c
+++ b/arch/s390/kernel/sysinfo.c
@@ -11,6 +11,7 @@
 #include <linux/init.h>
 #include <linux/delay.h>
 #include <linux/module.h>
+#include <linux/slab.h>
 #include <asm/ebcdic.h>
 #include <asm/sysinfo.h>
 #include <asm/cpcmd.h>
diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c
index 65065ac48ed..15a7536452d 100644
--- a/arch/s390/kernel/time.c
+++ b/arch/s390/kernel/time.c
@@ -36,6 +36,7 @@
 #include <linux/notifier.h>
 #include <linux/clocksource.h>
 #include <linux/clockchips.h>
+#include <linux/gfp.h>
 #include <asm/uaccess.h>
 #include <asm/delay.h>
 #include <asm/s390_ext.h>
@@ -51,14 +52,6 @@
 #define USECS_PER_JIFFY     ((unsigned long) 1000000/HZ)
 #define CLK_TICKS_PER_JIFFY ((unsigned long) USECS_PER_JIFFY << 12)
 
-/*
- * Create a small time difference between the timer interrupts
- * on the different cpus to avoid lock contention.
- */
-#define CPU_DEVIATION       (smp_processor_id() << 12)
-
-#define TICK_SIZE tick
-
 u64 sched_clock_base_cc = -1;	/* Force to data section. */
 EXPORT_SYMBOL_GPL(sched_clock_base_cc);
 
@@ -81,15 +74,15 @@ unsigned long long monotonic_clock(void)
 }
 EXPORT_SYMBOL(monotonic_clock);
 
-void tod_to_timeval(__u64 todval, struct timespec *xtime)
+void tod_to_timeval(__u64 todval, struct timespec *xt)
 {
 	unsigned long long sec;
 
 	sec = todval >> 12;
 	do_div(sec, 1000000);
-	xtime->tv_sec = sec;
+	xt->tv_sec = sec;
 	todval -= (sec * 1000000) << 12;
-	xtime->tv_nsec = ((todval * 1000) >> 12);
+	xt->tv_nsec = ((todval * 1000) >> 12);
 }
 EXPORT_SYMBOL(tod_to_timeval);
 
@@ -224,10 +217,11 @@ void update_vsyscall(struct timespec *wall_time, struct clocksource *clock,
 	++vdso_data->tb_update_count;
 	smp_wmb();
 	vdso_data->xtime_tod_stamp = clock->cycle_last;
-	vdso_data->xtime_clock_sec = xtime.tv_sec;
-	vdso_data->xtime_clock_nsec = xtime.tv_nsec;
+	vdso_data->xtime_clock_sec = wall_time->tv_sec;
+	vdso_data->xtime_clock_nsec = wall_time->tv_nsec;
 	vdso_data->wtom_clock_sec = wall_to_monotonic.tv_sec;
 	vdso_data->wtom_clock_nsec = wall_to_monotonic.tv_nsec;
+	vdso_data->ntp_mult = mult;
 	smp_wmb();
 	++vdso_data->tb_update_count;
 }
@@ -397,7 +391,6 @@ static void __init time_init_wq(void)
 	if (time_sync_wq)
 		return;
 	time_sync_wq = create_singlethread_workqueue("timesync");
-	stop_machine_create();
 }
 
 /*
@@ -531,8 +524,11 @@ void etr_switch_to_local(void)
 	if (!etr_eacr.sl)
 		return;
 	disable_sync_clock(NULL);
-	set_bit(ETR_EVENT_SWITCH_LOCAL, &etr_events);
-	queue_work(time_sync_wq, &etr_work);
+	if (!test_and_set_bit(ETR_EVENT_SWITCH_LOCAL, &etr_events)) {
+		etr_eacr.es = etr_eacr.sl = 0;
+		etr_setr(&etr_eacr);
+		queue_work(time_sync_wq, &etr_work);
+	}
 }
 
 /*
@@ -546,8 +542,11 @@ void etr_sync_check(void)
 	if (!etr_eacr.es)
 		return;
 	disable_sync_clock(NULL);
-	set_bit(ETR_EVENT_SYNC_CHECK, &etr_events);
-	queue_work(time_sync_wq, &etr_work);
+	if (!test_and_set_bit(ETR_EVENT_SYNC_CHECK, &etr_events)) {
+		etr_eacr.es = 0;
+		etr_setr(&etr_eacr);
+		queue_work(time_sync_wq, &etr_work);
+	}
 }
 
 /*
@@ -909,7 +908,7 @@ static struct etr_eacr etr_handle_update(struct etr_aib *aib,
 	 * Do not try to get the alternate port aib if the clock
 	 * is not in sync yet.
 	 */
-	if (!check_sync_clock())
+	if (!eacr.es || !check_sync_clock())
 		return eacr;
 
 	/*
@@ -1071,7 +1070,7 @@ static void etr_work_fn(struct work_struct *work)
 	 * If the clock is in sync just update the eacr and return.
 	 * If there is no valid sync port wait for a port update.
 	 */
-	if (check_sync_clock() || sync_port < 0) {
+	if ((eacr.es && check_sync_clock()) || sync_port < 0) {
 		etr_update_eacr(eacr);
 		etr_set_tolec_timeout(now);
 		goto out_unlock;
@@ -1124,14 +1123,18 @@ static struct sys_device etr_port1_dev = {
 /*
  * ETR class attributes
  */
-static ssize_t etr_stepping_port_show(struct sysdev_class *class, char *buf)
+static ssize_t etr_stepping_port_show(struct sysdev_class *class,
+					struct sysdev_class_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 ssize_t etr_stepping_mode_show(struct sysdev_class *class, char *buf)
+static ssize_t etr_stepping_mode_show(struct sysdev_class *class,
+				      	struct sysdev_class_attribute *attr,
+					char *buf)
 {
 	char *mode_str;
 
@@ -1592,7 +1595,9 @@ static struct sysdev_class stp_sysclass = {
 	.name	= "stp",
 };
 
-static ssize_t stp_ctn_id_show(struct sysdev_class *class, char *buf)
+static ssize_t stp_ctn_id_show(struct sysdev_class *class,
+				struct sysdev_class_attribute *attr,
+				char *buf)
 {
 	if (!stp_online)
 		return -ENODATA;
@@ -1602,7 +1607,9 @@ static ssize_t stp_ctn_id_show(struct sysdev_class *class, char *buf)
 
 static SYSDEV_CLASS_ATTR(ctn_id, 0400, stp_ctn_id_show, NULL);
 
-static ssize_t stp_ctn_type_show(struct sysdev_class *class, char *buf)
+static ssize_t stp_ctn_type_show(struct sysdev_class *class,
+				struct sysdev_class_attribute *attr,
+				char *buf)
 {
 	if (!stp_online)
 		return -ENODATA;
@@ -1611,7 +1618,9 @@ static ssize_t stp_ctn_type_show(struct sysdev_class *class, char *buf)
 
 static SYSDEV_CLASS_ATTR(ctn_type, 0400, stp_ctn_type_show, NULL);
 
-static ssize_t stp_dst_offset_show(struct sysdev_class *class, char *buf)
+static ssize_t stp_dst_offset_show(struct sysdev_class *class,
+				   struct sysdev_class_attribute *attr,
+				   char *buf)
 {
 	if (!stp_online || !(stp_info.vbits & 0x2000))
 		return -ENODATA;
@@ -1620,7 +1629,9 @@ static ssize_t stp_dst_offset_show(struct sysdev_class *class, char *buf)
 
 static SYSDEV_CLASS_ATTR(dst_offset, 0400, stp_dst_offset_show, NULL);
 
-static ssize_t stp_leap_seconds_show(struct sysdev_class *class, char *buf)
+static ssize_t stp_leap_seconds_show(struct sysdev_class *class,
+					struct sysdev_class_attribute *attr,
+					char *buf)
 {
 	if (!stp_online || !(stp_info.vbits & 0x8000))
 		return -ENODATA;
@@ -1629,7 +1640,9 @@ static ssize_t stp_leap_seconds_show(struct sysdev_class *class, char *buf)
 
 static SYSDEV_CLASS_ATTR(leap_seconds, 0400, stp_leap_seconds_show, NULL);
 
-static ssize_t stp_stratum_show(struct sysdev_class *class, char *buf)
+static ssize_t stp_stratum_show(struct sysdev_class *class,
+				struct sysdev_class_attribute *attr,
+				char *buf)
 {
 	if (!stp_online)
 		return -ENODATA;
@@ -1638,7 +1651,9 @@ static ssize_t stp_stratum_show(struct sysdev_class *class, char *buf)
 
 static SYSDEV_CLASS_ATTR(stratum, 0400, stp_stratum_show, NULL);
 
-static ssize_t stp_time_offset_show(struct sysdev_class *class, char *buf)
+static ssize_t stp_time_offset_show(struct sysdev_class *class,
+				struct sysdev_class_attribute *attr,
+				char *buf)
 {
 	if (!stp_online || !(stp_info.vbits & 0x0800))
 		return -ENODATA;
@@ -1647,7 +1662,9 @@ static ssize_t stp_time_offset_show(struct sysdev_class *class, char *buf)
 
 static SYSDEV_CLASS_ATTR(time_offset, 0400, stp_time_offset_show, NULL);
 
-static ssize_t stp_time_zone_offset_show(struct sysdev_class *class, char *buf)
+static ssize_t stp_time_zone_offset_show(struct sysdev_class *class,
+				struct sysdev_class_attribute *attr,
+				char *buf)
 {
 	if (!stp_online || !(stp_info.vbits & 0x4000))
 		return -ENODATA;
@@ -1657,7 +1674,9 @@ static ssize_t stp_time_zone_offset_show(struct sysdev_class *class, char *buf)
 static SYSDEV_CLASS_ATTR(time_zone_offset, 0400,
 			 stp_time_zone_offset_show, NULL);
 
-static ssize_t stp_timing_mode_show(struct sysdev_class *class, char *buf)
+static ssize_t stp_timing_mode_show(struct sysdev_class *class,
+				struct sysdev_class_attribute *attr,
+				char *buf)
 {
 	if (!stp_online)
 		return -ENODATA;
@@ -1666,7 +1685,9 @@ static ssize_t stp_timing_mode_show(struct sysdev_class *class, char *buf)
 
 static SYSDEV_CLASS_ATTR(timing_mode, 0400, stp_timing_mode_show, NULL);
 
-static ssize_t stp_timing_state_show(struct sysdev_class *class, char *buf)
+static ssize_t stp_timing_state_show(struct sysdev_class *class,
+				struct sysdev_class_attribute *attr,
+				char *buf)
 {
 	if (!stp_online)
 		return -ENODATA;
@@ -1675,12 +1696,15 @@ static ssize_t stp_timing_state_show(struct sysdev_class *class, char *buf)
 
 static SYSDEV_CLASS_ATTR(timing_state, 0400, stp_timing_state_show, NULL);
 
-static ssize_t stp_online_show(struct sysdev_class *class, char *buf)
+static ssize_t stp_online_show(struct sysdev_class *class,
+				struct sysdev_class_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,
 				const char *buf, size_t count)
 {
 	unsigned int value;
diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c
index 14ef6f05e43..bcef00766a6 100644
--- a/arch/s390/kernel/topology.c
+++ b/arch/s390/kernel/topology.c
@@ -37,7 +37,8 @@ struct tl_cpu {
 };
 
 struct tl_container {
-	unsigned char reserved[8];
+	unsigned char reserved[7];
+	unsigned char id;
 };
 
 union tl_entry {
@@ -58,6 +59,7 @@ struct tl_info {
 
 struct core_info {
 	struct core_info *next;
+	unsigned char id;
 	cpumask_t mask;
 };
 
@@ -73,6 +75,7 @@ static DECLARE_WORK(topology_work, topology_work_fn);
 static DEFINE_SPINLOCK(topology_lock);
 
 cpumask_t cpu_core_map[NR_CPUS];
+unsigned char cpu_core_id[NR_CPUS];
 
 static cpumask_t cpu_coregroup_map(unsigned int cpu)
 {
@@ -116,6 +119,7 @@ static void add_cpus_to_core(struct tl_cpu *tl_cpu, struct core_info *core)
 		for_each_present_cpu(lcpu) {
 			if (cpu_logical_map(lcpu) == rcpu) {
 				cpu_set(lcpu, core->mask);
+				cpu_core_id[lcpu] = core->id;
 				smp_cpu_polarization[lcpu] = tl_cpu->pp;
 			}
 		}
@@ -158,6 +162,7 @@ static void tl_to_cores(struct tl_info *info)
 			break;
 		case 1:
 			core = core->next;
+			core->id = tle->container.id;
 			break;
 		case 0:
 			add_cpus_to_core(&tle->cpu, core);
@@ -165,10 +170,11 @@ static void tl_to_cores(struct tl_info *info)
 		default:
 			clear_cores();
 			machine_has_topology = 0;
-			return;
+			goto out;
 		}
 		tle = next_tle(tle);
 	}
+out:
 	spin_unlock_irq(&topology_lock);
 }
 
diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c
index 6e7ad63854c..5d8f0f3d025 100644
--- a/arch/s390/kernel/traps.c
+++ b/arch/s390/kernel/traps.c
@@ -46,13 +46,7 @@
 
 pgm_check_handler_t *pgm_check_table[128];
 
-#ifdef CONFIG_SYSCTL
-#ifdef CONFIG_PROCESS_DEBUG
-int sysctl_userprocess_debug = 1;
-#else
-int sysctl_userprocess_debug = 0;
-#endif
-#endif
+int show_unhandled_signals;
 
 extern pgm_check_handler_t do_protection_exception;
 extern pgm_check_handler_t do_dat_exception;
@@ -315,18 +309,19 @@ void die(const char * str, struct pt_regs * regs, long err)
 	do_exit(SIGSEGV);
 }
 
-static void inline
-report_user_fault(long interruption_code, struct pt_regs *regs)
+static void inline report_user_fault(struct pt_regs *regs, long int_code,
+				     int signr)
 {
-#if defined(CONFIG_SYSCTL)
-	if (!sysctl_userprocess_debug)
+	if ((task_pid_nr(current) > 1) && !show_unhandled_signals)
 		return;
-#endif
-#if defined(CONFIG_SYSCTL) || defined(CONFIG_PROCESS_DEBUG)
-	printk("User process fault: interruption code 0x%lX\n",
-	       interruption_code);
+	if (!unhandled_signal(current, signr))
+		return;
+	if (!printk_ratelimit())
+		return;
+	printk("User process fault: interruption code 0x%lX ", int_code);
+	print_vma_addr("in ", regs->psw.addr & PSW_ADDR_INSN);
+	printk("\n");
 	show_regs(regs);
-#endif
 }
 
 int is_valid_bugaddr(unsigned long addr)
@@ -354,7 +349,7 @@ static void __kprobes inline do_trap(long interruption_code, int signr,
 
                 tsk->thread.trap_no = interruption_code & 0xffff;
 		force_sig_info(signr, info, tsk);
-		report_user_fault(interruption_code, regs);
+		report_user_fault(regs, interruption_code, signr);
         } else {
                 const struct exception_table_entry *fixup;
                 fixup = search_exception_tables(regs->psw.addr & PSW_ADDR_INSN);
@@ -390,8 +385,8 @@ static void default_trap_handler(struct pt_regs * regs, long interruption_code)
 {
         if (regs->psw.mask & PSW_MASK_PSTATE) {
 		local_irq_enable();
+		report_user_fault(regs, interruption_code, SIGSEGV);
 		do_exit(SIGSEGV);
-		report_user_fault(interruption_code, regs);
 	} else
 		die("Unknown program exception", regs, interruption_code);
 }
diff --git a/arch/s390/kernel/vdso.c b/arch/s390/kernel/vdso.c
index 5f99e66c51c..6b83870507d 100644
--- a/arch/s390/kernel/vdso.c
+++ b/arch/s390/kernel/vdso.c
@@ -23,6 +23,7 @@
 #include <linux/security.h>
 #include <linux/bootmem.h>
 #include <linux/compat.h>
+#include <asm/asm-offsets.h>
 #include <asm/pgtable.h>
 #include <asm/system.h>
 #include <asm/processor.h>
@@ -101,11 +102,7 @@ static void vdso_init_per_cpu_data(int cpu, struct vdso_per_cpu_data *vpcd)
 /*
  * Allocate/free per cpu vdso data.
  */
-#ifdef CONFIG_64BIT
 #define SEGMENT_ORDER	2
-#else
-#define SEGMENT_ORDER	1
-#endif
 
 int vdso_alloc_per_cpu(int cpu, struct _lowcore *lowcore)
 {
diff --git a/arch/s390/kernel/vdso32/clock_gettime.S b/arch/s390/kernel/vdso32/clock_gettime.S
index 4a98909a831..96964395427 100644
--- a/arch/s390/kernel/vdso32/clock_gettime.S
+++ b/arch/s390/kernel/vdso32/clock_gettime.S
@@ -38,13 +38,13 @@ __kernel_clock_gettime:
 	sl	%r1,__VDSO_XTIME_STAMP+4(%r5)
 	brc	3,2f
 	ahi	%r0,-1
-2:	mhi	%r0,1000			/* cyc2ns(clock,cycle_delta) */
+2:	ms	%r0,__VDSO_NTP_MULT(%r5)	/* cyc2ns(clock,cycle_delta) */
 	lr	%r2,%r0
-	lhi	%r0,1000
+	l	%r0,__VDSO_NTP_MULT(%r5)
 	ltr	%r1,%r1
 	mr	%r0,%r0
 	jnm	3f
-	ahi	%r0,1000
+	a	%r0,__VDSO_NTP_MULT(%r5)
 3:	alr	%r0,%r2
 	srdl	%r0,12
 	al	%r0,__VDSO_XTIME_NSEC(%r5)	/*  + xtime */
@@ -86,13 +86,13 @@ __kernel_clock_gettime:
 	sl	%r1,__VDSO_XTIME_STAMP+4(%r5)
 	brc	3,12f
 	ahi	%r0,-1
-12:	mhi	%r0,1000			/* cyc2ns(clock,cycle_delta) */
+12:	ms	%r0,__VDSO_NTP_MULT(%r5)	/* cyc2ns(clock,cycle_delta) */
 	lr	%r2,%r0
-	lhi	%r0,1000
+	l	%r0,__VDSO_NTP_MULT(%r5)
 	ltr	%r1,%r1
 	mr	%r0,%r0
 	jnm	13f
-	ahi	%r0,1000
+	a	%r0,__VDSO_NTP_MULT(%r5)
 13:	alr	%r0,%r2
 	srdl	%r0,12
 	al	%r0,__VDSO_XTIME_NSEC(%r5)	/*  + xtime */
diff --git a/arch/s390/kernel/vdso32/gettimeofday.S b/arch/s390/kernel/vdso32/gettimeofday.S
index ad8acfc949f..2d3633175e3 100644
--- a/arch/s390/kernel/vdso32/gettimeofday.S
+++ b/arch/s390/kernel/vdso32/gettimeofday.S
@@ -35,13 +35,13 @@ __kernel_gettimeofday:
 	sl	%r1,__VDSO_XTIME_STAMP+4(%r5)
 	brc	3,3f
 	ahi	%r0,-1
-3:	mhi	%r0,1000			/* cyc2ns(clock,cycle_delta) */
+3:	ms	%r0,__VDSO_NTP_MULT(%r5)	/* cyc2ns(clock,cycle_delta) */
 	st	%r0,24(%r15)
-	lhi	%r0,1000
+	l	%r0,__VDSO_NTP_MULT(%r5)
 	ltr	%r1,%r1
 	mr	%r0,%r0
 	jnm	4f
-	ahi	%r0,1000
+	a	%r0,__VDSO_NTP_MULT(%r5)
 4:	al	%r0,24(%r15)
 	srdl	%r0,12
 	al	%r0,__VDSO_XTIME_NSEC(%r5)	/*  + xtime */
diff --git a/arch/s390/kernel/vdso64/clock_gettime.S b/arch/s390/kernel/vdso64/clock_gettime.S
index 49106c6e6f8..f40467884a0 100644
--- a/arch/s390/kernel/vdso64/clock_gettime.S
+++ b/arch/s390/kernel/vdso64/clock_gettime.S
@@ -36,7 +36,7 @@ __kernel_clock_gettime:
 	stck	48(%r15)			/* Store TOD clock */
 	lg	%r1,48(%r15)
 	sg	%r1,__VDSO_XTIME_STAMP(%r5)	/* TOD - cycle_last */
-	mghi	%r1,1000
+	msgf	%r1,__VDSO_NTP_MULT(%r5)	/*  * NTP adjustment */
 	srlg	%r1,%r1,12			/* cyc2ns(clock,cycle_delta) */
 	alg	%r1,__VDSO_XTIME_NSEC(%r5)	/*  + xtime */
 	lg	%r0,__VDSO_XTIME_SEC(%r5)
@@ -64,7 +64,7 @@ __kernel_clock_gettime:
 	stck	48(%r15)			/* Store TOD clock */
 	lg	%r1,48(%r15)
 	sg	%r1,__VDSO_XTIME_STAMP(%r5)	/* TOD - cycle_last */
-	mghi	%r1,1000
+	msgf	%r1,__VDSO_NTP_MULT(%r5)	/*  * NTP adjustment */
 	srlg	%r1,%r1,12			/* cyc2ns(clock,cycle_delta) */
 	alg	%r1,__VDSO_XTIME_NSEC(%r5)	/*  + xtime */
 	lg	%r0,__VDSO_XTIME_SEC(%r5)
diff --git a/arch/s390/kernel/vdso64/gettimeofday.S b/arch/s390/kernel/vdso64/gettimeofday.S
index f873e75634e..36ee674722e 100644
--- a/arch/s390/kernel/vdso64/gettimeofday.S
+++ b/arch/s390/kernel/vdso64/gettimeofday.S
@@ -31,7 +31,7 @@ __kernel_gettimeofday:
 	stck	48(%r15)			/* Store TOD clock */
 	lg	%r1,48(%r15)
 	sg	%r1,__VDSO_XTIME_STAMP(%r5)	/* TOD - cycle_last */
-	mghi	%r1,1000
+	msgf	%r1,__VDSO_NTP_MULT(%r5)	/*  * NTP adjustment */
 	srlg	%r1,%r1,12			/* cyc2ns(clock,cycle_delta) */
 	alg	%r1,__VDSO_XTIME_NSEC(%r5)	/*  + xtime.tv_nsec */
 	lg	%r0,__VDSO_XTIME_SEC(%r5)	/* xtime.tv_sec */
diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c
index b59a812a010..3479f1b0d4e 100644
--- a/arch/s390/kernel/vtime.c
+++ b/arch/s390/kernel/vtime.c
@@ -121,32 +121,35 @@ void account_system_vtime(struct task_struct *tsk)
 }
 EXPORT_SYMBOL_GPL(account_system_vtime);
 
-void vtime_start_cpu(void)
+void vtime_start_cpu(__u64 int_clock, __u64 enter_timer)
 {
 	struct s390_idle_data *idle = &__get_cpu_var(s390_idle);
 	struct vtimer_queue *vq = &__get_cpu_var(virt_cpu_timer);
 	__u64 idle_time, expires;
 
+	if (idle->idle_enter == 0ULL)
+		return;
+
 	/* Account time spent with enabled wait psw loaded as idle time. */
-	idle_time = S390_lowcore.int_clock - idle->idle_enter;
+	idle_time = int_clock - idle->idle_enter;
 	account_idle_time(idle_time);
 	S390_lowcore.steal_timer +=
 		idle->idle_enter - S390_lowcore.last_update_clock;
-	S390_lowcore.last_update_clock = S390_lowcore.int_clock;
+	S390_lowcore.last_update_clock = int_clock;
 
 	/* Account system time spent going idle. */
 	S390_lowcore.system_timer += S390_lowcore.last_update_timer - vq->idle;
-	S390_lowcore.last_update_timer = S390_lowcore.async_enter_timer;
+	S390_lowcore.last_update_timer = enter_timer;
 
 	/* Restart vtime CPU timer */
 	if (vq->do_spt) {
 		/* Program old expire value but first save progress. */
-		expires = vq->idle - S390_lowcore.async_enter_timer;
+		expires = vq->idle - enter_timer;
 		expires += get_vtimer();
 		set_vtimer(expires);
 	} else {
 		/* Don't account the CPU timer delta while the cpu was idle. */
-		vq->elapsed -= vq->idle - S390_lowcore.async_enter_timer;
+		vq->elapsed -= vq->idle - enter_timer;
 	}
 
 	idle->sequence++;
diff --git a/arch/s390/kvm/Kconfig b/arch/s390/kvm/Kconfig
index 6ee55ae84ce..a7251580891 100644
--- a/arch/s390/kvm/Kconfig
+++ b/arch/s390/kvm/Kconfig
@@ -35,6 +35,7 @@ config KVM
 
 # OK, it's a little counter-intuitive to do this, but it puts it neatly under
 # the virtualization menu.
+source drivers/vhost/Kconfig
 source drivers/virtio/Kconfig
 
 endif # VIRTUALIZATION
diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c
index 8300309698f..9e4c84187cf 100644
--- a/arch/s390/kvm/diag.c
+++ b/arch/s390/kvm/diag.c
@@ -39,7 +39,7 @@ static int __diag_ipl_functions(struct kvm_vcpu *vcpu)
 		vcpu->run->s390_reset_flags = 0;
 		break;
 	default:
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 	}
 
 	atomic_clear_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
@@ -62,6 +62,6 @@ int kvm_s390_handle_diag(struct kvm_vcpu *vcpu)
 	case 0x308:
 		return __diag_ipl_functions(vcpu);
 	default:
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 	}
 }
diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c
index b40096494e4..3ddc30895e3 100644
--- a/arch/s390/kvm/intercept.c
+++ b/arch/s390/kvm/intercept.c
@@ -32,7 +32,7 @@ static int handle_lctlg(struct kvm_vcpu *vcpu)
 
 	vcpu->stat.instruction_lctlg++;
 	if ((vcpu->arch.sie_block->ipb & 0xff) != 0x2f)
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	useraddr = disp2;
 	if (base2)
@@ -138,7 +138,7 @@ static int handle_stop(struct kvm_vcpu *vcpu)
 		rc = __kvm_s390_vcpu_store_status(vcpu,
 						  KVM_S390_STORE_STATUS_NOADDR);
 		if (rc >= 0)
-			rc = -ENOTSUPP;
+			rc = -EOPNOTSUPP;
 	}
 
 	if (vcpu->arch.local_int.action_bits & ACTION_RELOADVCPU_ON_STOP) {
@@ -150,7 +150,7 @@ static int handle_stop(struct kvm_vcpu *vcpu)
 	if (vcpu->arch.local_int.action_bits & ACTION_STOP_ON_STOP) {
 		vcpu->arch.local_int.action_bits &= ~ACTION_STOP_ON_STOP;
 		VCPU_EVENT(vcpu, 3, "%s", "cpu stopped");
-		rc = -ENOTSUPP;
+		rc = -EOPNOTSUPP;
 	}
 
 	spin_unlock_bh(&vcpu->arch.local_int.lock);
@@ -171,9 +171,9 @@ static int handle_validity(struct kvm_vcpu *vcpu)
 			 2*PAGE_SIZE);
 		if (rc)
 			/* user will receive sigsegv, exit to user */
-			rc = -ENOTSUPP;
+			rc = -EOPNOTSUPP;
 	} else
-		rc = -ENOTSUPP;
+		rc = -EOPNOTSUPP;
 
 	if (rc)
 		VCPU_EVENT(vcpu, 2, "unhandled validity intercept code %d",
@@ -189,7 +189,7 @@ static int handle_instruction(struct kvm_vcpu *vcpu)
 	handler = instruction_handlers[vcpu->arch.sie_block->ipa >> 8];
 	if (handler)
 		return handler(vcpu);
-	return -ENOTSUPP;
+	return -EOPNOTSUPP;
 }
 
 static int handle_prog(struct kvm_vcpu *vcpu)
@@ -206,7 +206,7 @@ static int handle_instruction_and_prog(struct kvm_vcpu *vcpu)
 	rc = handle_instruction(vcpu);
 	rc2 = handle_prog(vcpu);
 
-	if (rc == -ENOTSUPP)
+	if (rc == -EOPNOTSUPP)
 		vcpu->arch.sie_block->icptcode = 0x04;
 	if (rc)
 		return rc;
@@ -231,9 +231,9 @@ int kvm_handle_sie_intercept(struct kvm_vcpu *vcpu)
 	u8 code = vcpu->arch.sie_block->icptcode;
 
 	if (code & 3 || (code >> 2) >= ARRAY_SIZE(intercept_funcs))
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 	func = intercept_funcs[code >> 2];
 	if (func)
 		return func(vcpu);
-	return -ENOTSUPP;
+	return -EOPNOTSUPP;
 }
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 43486c2408e..35c21bf910c 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -10,12 +10,13 @@
  *    Author(s): Carsten Otte <cotte@de.ibm.com>
  */
 
-#include <asm/lowcore.h>
-#include <asm/uaccess.h>
-#include <linux/hrtimer.h>
 #include <linux/interrupt.h>
 #include <linux/kvm_host.h>
+#include <linux/hrtimer.h>
 #include <linux/signal.h>
+#include <linux/slab.h>
+#include <asm/asm-offsets.h>
+#include <asm/uaccess.h>
 #include "kvm-s390.h"
 #include "gaccess.h"
 
@@ -187,8 +188,8 @@ static void __do_deliver_interrupt(struct kvm_vcpu *vcpu,
 		if (rc == -EFAULT)
 			exception = 1;
 
-		rc = put_guest_u64(vcpu, __LC_PFAULT_INTPARM,
-			inti->ext.ext_params2);
+		rc = put_guest_u64(vcpu, __LC_EXT_PARAMS2,
+				   inti->ext.ext_params2);
 		if (rc == -EFAULT)
 			exception = 1;
 		break;
@@ -342,7 +343,7 @@ int kvm_s390_handle_wait(struct kvm_vcpu *vcpu)
 	if (psw_interrupts_disabled(vcpu)) {
 		VCPU_EVENT(vcpu, 3, "%s", "disabled wait");
 		__unset_cpu_idle(vcpu);
-		return -ENOTSUPP; /* disabled wait */
+		return -EOPNOTSUPP; /* disabled wait */
 	}
 
 	if (psw_extint_disabled(vcpu) ||
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index f8bcaefd7d3..ae370581687 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -23,6 +23,7 @@
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/timer.h>
+#include <asm/asm-offsets.h>
 #include <asm/lowcore.h>
 #include <asm/pgtable.h>
 #include <asm/nmi.h>
@@ -241,6 +242,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 	kvm_free_physmem(kvm);
 	free_page((unsigned long)(kvm->arch.sca));
 	debug_unregister(kvm->arch.dbf);
+	cleanup_srcu_struct(&kvm->srcu);
 	kfree(kvm);
 }
 
@@ -339,11 +341,13 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
 
 	rc = kvm_vcpu_init(vcpu, kvm, id);
 	if (rc)
-		goto out_free_cpu;
+		goto out_free_sie_block;
 	VM_EVENT(kvm, 3, "create cpu %d at %p, sie block at %p", id, vcpu,
 		 vcpu->arch.sie_block);
 
 	return vcpu;
+out_free_sie_block:
+	free_page((unsigned long)(vcpu->arch.sie_block));
 out_free_cpu:
 	kfree(vcpu);
 out_nomem:
@@ -543,7 +547,7 @@ rerun_vcpu:
 		rc = -EINTR;
 	}
 
-	if (rc == -ENOTSUPP) {
+	if (rc == -EOPNOTSUPP) {
 		/* intercept cannot be handled in-kernel, prepare kvm-run */
 		kvm_run->exit_reason         = KVM_EXIT_S390_SIEIC;
 		kvm_run->s390_sieic.icptcode = vcpu->arch.sie_block->icptcode;
@@ -603,45 +607,45 @@ int __kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr)
 	} else
 		prefix = 0;
 
-	if (__guestcopy(vcpu, addr + offsetof(struct save_area_s390x, fp_regs),
+	if (__guestcopy(vcpu, addr + offsetof(struct save_area, fp_regs),
 			vcpu->arch.guest_fpregs.fprs, 128, prefix))
 		return -EFAULT;
 
-	if (__guestcopy(vcpu, addr + offsetof(struct save_area_s390x, gp_regs),
+	if (__guestcopy(vcpu, addr + offsetof(struct save_area, gp_regs),
 			vcpu->arch.guest_gprs, 128, prefix))
 		return -EFAULT;
 
-	if (__guestcopy(vcpu, addr + offsetof(struct save_area_s390x, psw),
+	if (__guestcopy(vcpu, addr + offsetof(struct save_area, psw),
 			&vcpu->arch.sie_block->gpsw, 16, prefix))
 		return -EFAULT;
 
-	if (__guestcopy(vcpu, addr + offsetof(struct save_area_s390x, pref_reg),
+	if (__guestcopy(vcpu, addr + offsetof(struct save_area, pref_reg),
 			&vcpu->arch.sie_block->prefix, 4, prefix))
 		return -EFAULT;
 
 	if (__guestcopy(vcpu,
-			addr + offsetof(struct save_area_s390x, fp_ctrl_reg),
+			addr + offsetof(struct save_area, fp_ctrl_reg),
 			&vcpu->arch.guest_fpregs.fpc, 4, prefix))
 		return -EFAULT;
 
-	if (__guestcopy(vcpu, addr + offsetof(struct save_area_s390x, tod_reg),
+	if (__guestcopy(vcpu, addr + offsetof(struct save_area, tod_reg),
 			&vcpu->arch.sie_block->todpr, 4, prefix))
 		return -EFAULT;
 
-	if (__guestcopy(vcpu, addr + offsetof(struct save_area_s390x, timer),
+	if (__guestcopy(vcpu, addr + offsetof(struct save_area, timer),
 			&vcpu->arch.sie_block->cputm, 8, prefix))
 		return -EFAULT;
 
-	if (__guestcopy(vcpu, addr + offsetof(struct save_area_s390x, clk_cmp),
+	if (__guestcopy(vcpu, addr + offsetof(struct save_area, clk_cmp),
 			&vcpu->arch.sie_block->ckc, 8, prefix))
 		return -EFAULT;
 
-	if (__guestcopy(vcpu, addr + offsetof(struct save_area_s390x, acc_regs),
+	if (__guestcopy(vcpu, addr + offsetof(struct save_area, acc_regs),
 			&vcpu->arch.guest_acrs, 64, prefix))
 		return -EFAULT;
 
 	if (__guestcopy(vcpu,
-			addr + offsetof(struct save_area_s390x, ctrl_regs),
+			addr + offsetof(struct save_area, ctrl_regs),
 			&vcpu->arch.sie_block->gcr, 128, prefix))
 		return -EFAULT;
 	return 0;
@@ -689,14 +693,12 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 }
 
 /* Section: memory related */
-int kvm_arch_set_memory_region(struct kvm *kvm,
-				struct kvm_userspace_memory_region *mem,
-				struct kvm_memory_slot old,
-				int user_alloc)
+int kvm_arch_prepare_memory_region(struct kvm *kvm,
+				   struct kvm_memory_slot *memslot,
+				   struct kvm_memory_slot old,
+				   struct kvm_userspace_memory_region *mem,
+				   int user_alloc)
 {
-	int i;
-	struct kvm_vcpu *vcpu;
-
 	/* A few sanity checks. We can have exactly one memory slot which has
 	   to start at guest virtual zero and which has to be located at a
 	   page boundary in userland and which has to end at a page boundary.
@@ -719,14 +721,23 @@ int kvm_arch_set_memory_region(struct kvm *kvm,
 	if (!user_alloc)
 		return -EINVAL;
 
+	return 0;
+}
+
+void kvm_arch_commit_memory_region(struct kvm *kvm,
+				struct kvm_userspace_memory_region *mem,
+				struct kvm_memory_slot old,
+				int user_alloc)
+{
+	int i;
+	struct kvm_vcpu *vcpu;
+
 	/* request update of sie control block for all available vcpus */
 	kvm_for_each_vcpu(i, vcpu, kvm) {
 		if (test_and_set_bit(KVM_REQ_MMU_RELOAD, &vcpu->requests))
 			continue;
 		kvm_s390_inject_sigp_stop(vcpu, ACTION_RELOADVCPU_ON_STOP);
 	}
-
-	return 0;
 }
 
 void kvm_arch_flush_shadow(struct kvm *kvm)
@@ -741,7 +752,7 @@ gfn_t unalias_gfn(struct kvm *kvm, gfn_t gfn)
 static int __init kvm_s390_init(void)
 {
 	int ret;
-	ret = kvm_init(NULL, sizeof(struct kvm_vcpu), THIS_MODULE);
+	ret = kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE);
 	if (ret)
 		return ret;
 
@@ -750,7 +761,7 @@ static int __init kvm_s390_init(void)
 	 * to hold the maximum amount of facilites. On the other hand, we
 	 * only set facilities that are known to work in KVM.
 	 */
-	facilities = (unsigned long long *) get_zeroed_page(GFP_DMA);
+	facilities = (unsigned long long *) get_zeroed_page(GFP_KERNEL|GFP_DMA);
 	if (!facilities) {
 		kvm_exit();
 		return -ENOMEM;
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index 06cce8285ba..cfa9d177745 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -67,10 +67,14 @@ static inline long kvm_s390_vcpu_get_memsize(struct kvm_vcpu *vcpu)
 
 static inline void kvm_s390_vcpu_set_mem(struct kvm_vcpu *vcpu)
 {
+	int idx;
 	struct kvm_memory_slot *mem;
+	struct kvm_memslots *memslots;
 
-	down_read(&vcpu->kvm->slots_lock);
-	mem = &vcpu->kvm->memslots[0];
+	idx = srcu_read_lock(&vcpu->kvm->srcu);
+	memslots = kvm_memslots(vcpu->kvm);
+
+	mem = &memslots->memslots[0];
 
 	vcpu->arch.sie_block->gmsor = mem->userspace_addr;
 	vcpu->arch.sie_block->gmslm =
@@ -78,7 +82,7 @@ static inline void kvm_s390_vcpu_set_mem(struct kvm_vcpu *vcpu)
 		(mem->npages << PAGE_SHIFT) +
 		VIRTIODESCSPACE - 1ul;
 
-	up_read(&vcpu->kvm->slots_lock);
+	srcu_read_unlock(&vcpu->kvm->srcu, idx);
 }
 
 /* implemented in priv.c */
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index d426aac8095..44205507717 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -12,6 +12,7 @@
  */
 
 #include <linux/kvm.h>
+#include <linux/gfp.h>
 #include <linux/errno.h>
 #include <asm/current.h>
 #include <asm/debug.h>
@@ -323,5 +324,5 @@ int kvm_s390_handle_b2(struct kvm_vcpu *vcpu)
 		else
 			return handler(vcpu);
 	}
-	return -ENOTSUPP;
+	return -EOPNOTSUPP;
 }
diff --git a/arch/s390/kvm/sie64a.S b/arch/s390/kvm/sie64a.S
index 934fd6a885f..7e9d30d567b 100644
--- a/arch/s390/kvm/sie64a.S
+++ b/arch/s390/kvm/sie64a.S
@@ -1,20 +1,58 @@
 /*
  * sie64a.S - low level sie call
  *
- * Copyright IBM Corp. 2008
+ * Copyright IBM Corp. 2008,2010
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License (version 2 only)
  * as published by the Free Software Foundation.
  *
  *    Author(s): Heiko Carstens <heiko.carstens@de.ibm.com>
+ *		 Christian Ehrhardt <ehrhardt@linux.vnet.ibm.com>
  */
 
 #include <linux/errno.h>
 #include <asm/asm-offsets.h>
+#include <asm/setup.h>
+#include <asm/asm-offsets.h>
+#include <asm/ptrace.h>
+#include <asm/thread_info.h>
+
+_TIF_EXIT_SIE = (_TIF_SIGPENDING | _TIF_NEED_RESCHED | _TIF_MCCK_PENDING)
+
+/*
+ * offsets into stackframe
+ * SP_	= offsets into stack sie64 is called with
+ * SPI_ = offsets into irq stack
+ */
+SP_GREGS = __SF_EMPTY
+SP_HOOK  = __SF_EMPTY+8
+SP_GPP	 = __SF_EMPTY+16
+SPI_PSW  = STACK_FRAME_OVERHEAD + __PT_PSW
+
 
-SP_R5 =	5 * 8	# offset into stackframe
-SP_R6 =	6 * 8
+	.macro SPP newpp
+	tm	__LC_MACHINE_FLAGS+6,0x20	# MACHINE_FLAG_SPP
+	jz	0f
+	.insn	s,0xb2800000,\newpp
+0:
+	.endm
+
+sie_irq_handler:
+	SPP	__LC_CMF_HPP			# set host id
+	larl	%r2,sie_inst
+	clg	%r2,SPI_PSW+8(0,%r15)		# intercepted sie
+	jne	1f
+	xc	__LC_SIE_HOOK(8),__LC_SIE_HOOK
+	lg	%r2,__LC_THREAD_INFO		# pointer thread_info struct
+	tm	__TI_flags+7(%r2),_TIF_EXIT_SIE
+	jz	0f
+	larl	%r2,sie_exit			# work pending, leave sie
+	stg	%r2,__LC_RETURN_PSW+8
+	br	%r14
+0:	larl	%r2,sie_reenter			# re-enter with guest id
+	stg	%r2,__LC_RETURN_PSW+8
+1:	br	%r14
 
 /*
  * sie64a calling convention:
@@ -23,23 +61,34 @@ SP_R6 =	6 * 8
  */
 	.globl	sie64a
 sie64a:
-	lgr	%r5,%r3
-	stmg	%r5,%r14,SP_R5(%r15)	# save register on entry
-	lgr	%r14,%r2		# pointer to sie control block
-	lmg	%r0,%r13,0(%r3)		# load guest gprs 0-13
+	stg	%r3,SP_GREGS(%r15)		# save guest register save area
+	stmg	%r6,%r14,__SF_GPRS(%r15)	# save registers on entry
+	lgr	%r14,%r2			# pointer to sie control block
+	larl	%r5,sie_irq_handler
+	stg	%r2,SP_GPP(%r15)
+	stg	%r5,SP_HOOK(%r15)		# save hook target
+	lmg	%r0,%r13,0(%r3)			# load guest gprs 0-13
+sie_reenter:
+	mvc	__LC_SIE_HOOK(8),SP_HOOK(%r15)
+	SPP	SP_GPP(%r15)			# set guest id
 sie_inst:
 	sie	0(%r14)
-	lg	%r14,SP_R5(%r15)
-	stmg	%r0,%r13,0(%r14)	# save guest gprs 0-13
+	xc	__LC_SIE_HOOK(8),__LC_SIE_HOOK
+	SPP	__LC_CMF_HPP			# set host id
+sie_exit:
+	lg	%r14,SP_GREGS(%r15)
+	stmg	%r0,%r13,0(%r14)		# save guest gprs 0-13
 	lghi	%r2,0
-	lmg	%r6,%r14,SP_R6(%r15)
+	lmg	%r6,%r14,__SF_GPRS(%r15)
 	br	%r14
 
 sie_err:
-	lg	%r14,SP_R5(%r15)
-	stmg	%r0,%r13,0(%r14)	# save guest gprs 0-13
+	xc	__LC_SIE_HOOK(8),__LC_SIE_HOOK
+	SPP	__LC_CMF_HPP			# set host id
+	lg	%r14,SP_GREGS(%r15)
+	stmg	%r0,%r13,0(%r14)		# save guest gprs 0-13
 	lghi	%r2,-EFAULT
-	lmg	%r6,%r14,SP_R6(%r15)
+	lmg	%r6,%r14,__SF_GPRS(%r15)
 	br	%r14
 
 	.section __ex_table,"a"
diff --git a/arch/s390/kvm/sigp.c b/arch/s390/kvm/sigp.c
index 15ee1111de5..702276f5e2f 100644
--- a/arch/s390/kvm/sigp.c
+++ b/arch/s390/kvm/sigp.c
@@ -14,6 +14,7 @@
 
 #include <linux/kvm.h>
 #include <linux/kvm_host.h>
+#include <linux/slab.h>
 #include "gaccess.h"
 #include "kvm-s390.h"
 
@@ -112,7 +113,7 @@ static int __inject_sigp_stop(struct kvm_s390_local_interrupt *li, int action)
 {
 	struct kvm_s390_interrupt_info *inti;
 
-	inti = kzalloc(sizeof(*inti), GFP_KERNEL);
+	inti = kzalloc(sizeof(*inti), GFP_ATOMIC);
 	if (!inti)
 		return -ENOMEM;
 	inti->type = KVM_S390_SIGP_STOP;
@@ -172,7 +173,7 @@ static int __sigp_set_arch(struct kvm_vcpu *vcpu, u32 parameter)
 		rc = 0; /* order accepted */
 		break;
 	default:
-		rc = -ENOTSUPP;
+		rc = -EOPNOTSUPP;
 	}
 	return rc;
 }
@@ -293,7 +294,7 @@ int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu)
 		vcpu->stat.instruction_sigp_restart++;
 		/* user space must know about restart */
 	default:
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 	}
 
 	if (rc < 0)
diff --git a/arch/s390/lib/Makefile b/arch/s390/lib/Makefile
index 97975ec7a27..761ab8b56af 100644
--- a/arch/s390/lib/Makefile
+++ b/arch/s390/lib/Makefile
@@ -3,6 +3,7 @@
 #
 
 lib-y += delay.o string.o uaccess_std.o uaccess_pt.o
+obj-y += usercopy.o
 obj-$(CONFIG_32BIT) += div64.o qrnnd.o ucmpdi2.o
 lib-$(CONFIG_64BIT) += uaccess_mvcos.o
 lib-$(CONFIG_SMP) += spinlock.o
diff --git a/arch/s390/lib/spinlock.c b/arch/s390/lib/spinlock.c
index cff327f109a..91754ffb920 100644
--- a/arch/s390/lib/spinlock.c
+++ b/arch/s390/lib/spinlock.c
@@ -43,16 +43,24 @@ void arch_spin_lock_wait(arch_spinlock_t *lp)
 {
 	int count = spin_retry;
 	unsigned int cpu = ~smp_processor_id();
+	unsigned int owner;
 
 	while (1) {
-		if (count-- <= 0) {
-			unsigned int owner = lp->owner_cpu;
-			if (owner != 0)
-				_raw_yield_cpu(~owner);
-			count = spin_retry;
+		owner = lp->owner_cpu;
+		if (!owner || smp_vcpu_scheduled(~owner)) {
+			for (count = spin_retry; count > 0; count--) {
+				if (arch_spin_is_locked(lp))
+					continue;
+				if (_raw_compare_and_swap(&lp->owner_cpu, 0,
+							  cpu) == 0)
+					return;
+			}
+			if (MACHINE_IS_LPAR)
+				continue;
 		}
-		if (arch_spin_is_locked(lp))
-			continue;
+		owner = lp->owner_cpu;
+		if (owner)
+			_raw_yield_cpu(~owner);
 		if (_raw_compare_and_swap(&lp->owner_cpu, 0, cpu) == 0)
 			return;
 	}
@@ -63,17 +71,27 @@ void arch_spin_lock_wait_flags(arch_spinlock_t *lp, unsigned long flags)
 {
 	int count = spin_retry;
 	unsigned int cpu = ~smp_processor_id();
+	unsigned int owner;
 
 	local_irq_restore(flags);
 	while (1) {
-		if (count-- <= 0) {
-			unsigned int owner = lp->owner_cpu;
-			if (owner != 0)
-				_raw_yield_cpu(~owner);
-			count = spin_retry;
+		owner = lp->owner_cpu;
+		if (!owner || smp_vcpu_scheduled(~owner)) {
+			for (count = spin_retry; count > 0; count--) {
+				if (arch_spin_is_locked(lp))
+					continue;
+				local_irq_disable();
+				if (_raw_compare_and_swap(&lp->owner_cpu, 0,
+							  cpu) == 0)
+					return;
+				local_irq_restore(flags);
+			}
+			if (MACHINE_IS_LPAR)
+				continue;
 		}
-		if (arch_spin_is_locked(lp))
-			continue;
+		owner = lp->owner_cpu;
+		if (owner)
+			_raw_yield_cpu(~owner);
 		local_irq_disable();
 		if (_raw_compare_and_swap(&lp->owner_cpu, 0, cpu) == 0)
 			return;
@@ -100,8 +118,11 @@ EXPORT_SYMBOL(arch_spin_trylock_retry);
 void arch_spin_relax(arch_spinlock_t *lock)
 {
 	unsigned int cpu = lock->owner_cpu;
-	if (cpu != 0)
-		_raw_yield_cpu(~cpu);
+	if (cpu != 0) {
+		if (MACHINE_IS_VM || MACHINE_IS_KVM ||
+		    !smp_vcpu_scheduled(~cpu))
+			_raw_yield_cpu(~cpu);
+	}
 }
 EXPORT_SYMBOL(arch_spin_relax);
 
diff --git a/arch/s390/lib/usercopy.c b/arch/s390/lib/usercopy.c
new file mode 100644
index 00000000000..14b363fec8a
--- /dev/null
+++ b/arch/s390/lib/usercopy.c
@@ -0,0 +1,8 @@
+#include <linux/module.h>
+#include <linux/bug.h>
+
+void copy_from_user_overflow(void)
+{
+	WARN(1, "Buffer overflow detected!\n");
+}
+EXPORT_SYMBOL(copy_from_user_overflow);
diff --git a/arch/s390/mm/cmm.c b/arch/s390/mm/cmm.c
index 76a3637b88e..eb6a2ef5f82 100644
--- a/arch/s390/mm/cmm.c
+++ b/arch/s390/mm/cmm.c
@@ -1,17 +1,16 @@
 /*
- *  arch/s390/mm/cmm.c
+ *  Collaborative memory management interface.
  *
- *  S390 version
- *    Copyright (C) 2003 IBM Deutschland Entwicklung GmbH, IBM Corporation
- *    Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com)
+ *    Copyright IBM Corp 2003,2010
+ *    Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>,
  *
- *  Collaborative memory management interface.
  */
 
 #include <linux/errno.h>
 #include <linux/fs.h>
 #include <linux/init.h>
 #include <linux/module.h>
+#include <linux/gfp.h>
 #include <linux/sched.h>
 #include <linux/sysctl.h>
 #include <linux/ctype.h>
@@ -19,9 +18,9 @@
 #include <linux/kthread.h>
 #include <linux/oom.h>
 #include <linux/suspend.h>
+#include <linux/uaccess.h>
 
 #include <asm/pgalloc.h>
-#include <asm/uaccess.h>
 #include <asm/diag.h>
 
 static char *sender = "VMRMSVM";
@@ -52,14 +51,14 @@ static struct cmm_page_array *cmm_timed_page_list;
 static DEFINE_SPINLOCK(cmm_lock);
 
 static struct task_struct *cmm_thread_ptr;
-static wait_queue_head_t cmm_thread_wait;
-static struct timer_list cmm_timer;
+static DECLARE_WAIT_QUEUE_HEAD(cmm_thread_wait);
+static DEFINE_TIMER(cmm_timer, NULL, 0, 0);
 
 static void cmm_timer_fn(unsigned long);
 static void cmm_set_timer(void);
 
-static long
-cmm_alloc_pages(long nr, long *counter, struct cmm_page_array **list)
+static long cmm_alloc_pages(long nr, long *counter,
+			    struct cmm_page_array **list)
 {
 	struct cmm_page_array *pa, *npa;
 	unsigned long addr;
@@ -98,8 +97,7 @@ cmm_alloc_pages(long nr, long *counter, struct cmm_page_array **list)
 	return nr;
 }
 
-static long
-cmm_free_pages(long nr, long *counter, struct cmm_page_array **list)
+static long cmm_free_pages(long nr, long *counter, struct cmm_page_array **list)
 {
 	struct cmm_page_array *pa;
 	unsigned long addr;
@@ -139,11 +137,10 @@ static int cmm_oom_notify(struct notifier_block *self,
 }
 
 static struct notifier_block cmm_oom_nb = {
-	.notifier_call = cmm_oom_notify
+	.notifier_call = cmm_oom_notify,
 };
 
-static int
-cmm_thread(void *dummy)
+static int cmm_thread(void *dummy)
 {
 	int rc;
 
@@ -169,7 +166,7 @@ cmm_thread(void *dummy)
 				cmm_timed_pages_target = cmm_timed_pages;
 		} else if (cmm_timed_pages_target < cmm_timed_pages) {
 			cmm_free_pages(1, &cmm_timed_pages,
-			       	       &cmm_timed_page_list);
+				       &cmm_timed_page_list);
 		}
 		if (cmm_timed_pages > 0 && !timer_pending(&cmm_timer))
 			cmm_set_timer();
@@ -177,14 +174,12 @@ cmm_thread(void *dummy)
 	return 0;
 }
 
-static void
-cmm_kick_thread(void)
+static void cmm_kick_thread(void)
 {
 	wake_up(&cmm_thread_wait);
 }
 
-static void
-cmm_set_timer(void)
+static void cmm_set_timer(void)
 {
 	if (cmm_timed_pages_target <= 0 || cmm_timeout_seconds <= 0) {
 		if (timer_pending(&cmm_timer))
@@ -201,8 +196,7 @@ cmm_set_timer(void)
 	add_timer(&cmm_timer);
 }
 
-static void
-cmm_timer_fn(unsigned long ignored)
+static void cmm_timer_fn(unsigned long ignored)
 {
 	long nr;
 
@@ -215,57 +209,49 @@ cmm_timer_fn(unsigned long ignored)
 	cmm_set_timer();
 }
 
-void
-cmm_set_pages(long nr)
+static void cmm_set_pages(long nr)
 {
 	cmm_pages_target = nr;
 	cmm_kick_thread();
 }
 
-long
-cmm_get_pages(void)
+static long cmm_get_pages(void)
 {
 	return cmm_pages;
 }
 
-void
-cmm_add_timed_pages(long nr)
+static void cmm_add_timed_pages(long nr)
 {
 	cmm_timed_pages_target += nr;
 	cmm_kick_thread();
 }
 
-long
-cmm_get_timed_pages(void)
+static long cmm_get_timed_pages(void)
 {
 	return cmm_timed_pages;
 }
 
-void
-cmm_set_timeout(long nr, long seconds)
+static void cmm_set_timeout(long nr, long seconds)
 {
 	cmm_timeout_pages = nr;
 	cmm_timeout_seconds = seconds;
 	cmm_set_timer();
 }
 
-static int
-cmm_skip_blanks(char *cp, char **endp)
+static int cmm_skip_blanks(char *cp, char **endp)
 {
 	char *str;
 
-	for (str = cp; *str == ' ' || *str == '\t'; str++);
+	for (str = cp; *str == ' ' || *str == '\t'; str++)
+		;
 	*endp = str;
 	return str != cp;
 }
 
-#ifdef CONFIG_CMM_PROC
-
 static struct ctl_table cmm_table[];
 
-static int
-cmm_pages_handler(ctl_table *ctl, int write,
-		  void __user *buffer, size_t *lenp, loff_t *ppos)
+static int cmm_pages_handler(ctl_table *ctl, int write, void __user *buffer,
+			     size_t *lenp, loff_t *ppos)
 {
 	char buf[16], *p;
 	long nr;
@@ -304,9 +290,8 @@ cmm_pages_handler(ctl_table *ctl, int write,
 	return 0;
 }
 
-static int
-cmm_timeout_handler(ctl_table *ctl, int write,
-		    void __user *buffer, size_t *lenp, loff_t *ppos)
+static int cmm_timeout_handler(ctl_table *ctl, int write,  void __user *buffer,
+			       size_t *lenp, loff_t *ppos)
 {
 	char buf[64], *p;
 	long nr, seconds;
@@ -369,12 +354,10 @@ static struct ctl_table cmm_dir_table[] = {
 	},
 	{ }
 };
-#endif
 
 #ifdef CONFIG_CMM_IUCV
 #define SMSG_PREFIX "CMM"
-static void
-cmm_smsg_target(char *from, char *msg)
+static void cmm_smsg_target(const char *from, char *msg)
 {
 	long nr, seconds;
 
@@ -444,16 +427,13 @@ static struct notifier_block cmm_power_notifier = {
 	.notifier_call = cmm_power_event,
 };
 
-static int
-cmm_init (void)
+static int cmm_init(void)
 {
 	int rc = -ENOMEM;
 
-#ifdef CONFIG_CMM_PROC
 	cmm_sysctl_header = register_sysctl_table(cmm_dir_table);
 	if (!cmm_sysctl_header)
 		goto out_sysctl;
-#endif
 #ifdef CONFIG_CMM_IUCV
 	rc = smsg_register_callback(SMSG_PREFIX, cmm_smsg_target);
 	if (rc < 0)
@@ -465,8 +445,6 @@ cmm_init (void)
 	rc = register_pm_notifier(&cmm_power_notifier);
 	if (rc)
 		goto out_pm;
-	init_waitqueue_head(&cmm_thread_wait);
-	init_timer(&cmm_timer);
 	cmm_thread_ptr = kthread_run(cmm_thread, NULL, "cmmthread");
 	rc = IS_ERR(cmm_thread_ptr) ? PTR_ERR(cmm_thread_ptr) : 0;
 	if (rc)
@@ -482,36 +460,26 @@ out_oom_notify:
 	smsg_unregister_callback(SMSG_PREFIX, cmm_smsg_target);
 out_smsg:
 #endif
-#ifdef CONFIG_CMM_PROC
 	unregister_sysctl_table(cmm_sysctl_header);
 out_sysctl:
-#endif
+	del_timer_sync(&cmm_timer);
 	return rc;
 }
+module_init(cmm_init);
 
-static void
-cmm_exit(void)
+static void cmm_exit(void)
 {
-	kthread_stop(cmm_thread_ptr);
-	unregister_pm_notifier(&cmm_power_notifier);
-	unregister_oom_notifier(&cmm_oom_nb);
-	cmm_free_pages(cmm_pages, &cmm_pages, &cmm_page_list);
-	cmm_free_pages(cmm_timed_pages, &cmm_timed_pages, &cmm_timed_page_list);
-#ifdef CONFIG_CMM_PROC
 	unregister_sysctl_table(cmm_sysctl_header);
-#endif
 #ifdef CONFIG_CMM_IUCV
 	smsg_unregister_callback(SMSG_PREFIX, cmm_smsg_target);
 #endif
+	unregister_pm_notifier(&cmm_power_notifier);
+	unregister_oom_notifier(&cmm_oom_nb);
+	kthread_stop(cmm_thread_ptr);
+	del_timer_sync(&cmm_timer);
+	cmm_free_pages(cmm_pages, &cmm_pages, &cmm_page_list);
+	cmm_free_pages(cmm_timed_pages, &cmm_timed_pages, &cmm_timed_page_list);
 }
-
-module_init(cmm_init);
 module_exit(cmm_exit);
 
-EXPORT_SYMBOL(cmm_set_pages);
-EXPORT_SYMBOL(cmm_get_pages);
-EXPORT_SYMBOL(cmm_add_timed_pages);
-EXPORT_SYMBOL(cmm_get_timed_pages);
-EXPORT_SYMBOL(cmm_set_timeout);
-
 MODULE_LICENSE("GPL");
diff --git a/arch/s390/mm/extmem.c b/arch/s390/mm/extmem.c
index 5c845712960..3cc95dd0a3a 100644
--- a/arch/s390/mm/extmem.c
+++ b/arch/s390/mm/extmem.c
@@ -105,7 +105,7 @@ static int
 dcss_set_subcodes(void)
 {
 #ifdef CONFIG_64BIT
-	char *name = kmalloc(8 * sizeof(char), GFP_DMA);
+	char *name = kmalloc(8 * sizeof(char), GFP_KERNEL | GFP_DMA);
 	unsigned long rx, ry;
 	int rc;
 
@@ -252,12 +252,13 @@ dcss_diag_translate_rc (int vm_rc) {
 static int
 query_segment_type (struct dcss_segment *seg)
 {
-	struct qin64  *qin = kmalloc (sizeof(struct qin64), GFP_DMA);
-	struct qout64 *qout = kmalloc (sizeof(struct qout64), GFP_DMA);
-
-	int diag_cc, rc, i;
 	unsigned long dummy, vmrc;
+	int diag_cc, rc, i;
+	struct qout64 *qout;
+	struct qin64 *qin;
 
+	qin = kmalloc(sizeof(*qin), GFP_KERNEL | GFP_DMA);
+	qout = kmalloc(sizeof(*qout), GFP_KERNEL | GFP_DMA);
 	if ((qin == NULL) || (qout == NULL)) {
 		rc = -ENOMEM;
 		goto out_free;
@@ -286,7 +287,7 @@ query_segment_type (struct dcss_segment *seg)
 	   copy data for the new format. */
 	if (segext_scode == DCSS_SEGEXT) {
 		struct qout64_old *qout_old;
-		qout_old = kzalloc(sizeof(struct qout64_old), GFP_DMA);
+		qout_old = kzalloc(sizeof(*qout_old), GFP_KERNEL | GFP_DMA);
 		if (qout_old == NULL) {
 			rc = -ENOMEM;
 			goto out_free;
@@ -309,7 +310,7 @@ query_segment_type (struct dcss_segment *seg)
 	}
 #endif
 	if (qout->segcnt > 6) {
-		rc = -ENOTSUPP;
+		rc = -EOPNOTSUPP;
 		goto out_free;
 	}
 
@@ -324,11 +325,11 @@ query_segment_type (struct dcss_segment *seg)
 		for (i=0; i<qout->segcnt; i++) {
 			if (((qout->range[i].start & 0xff) != SEG_TYPE_EW) &&
 			    ((qout->range[i].start & 0xff) != SEG_TYPE_EN)) {
-				rc = -ENOTSUPP;
+				rc = -EOPNOTSUPP;
 				goto out_free;
 			}
 			if (start != qout->range[i].start >> PAGE_SHIFT) {
-				rc = -ENOTSUPP;
+				rc = -EOPNOTSUPP;
 				goto out_free;
 			}
 			start = (qout->range[i].end >> PAGE_SHIFT) + 1;
@@ -357,7 +358,7 @@ query_segment_type (struct dcss_segment *seg)
  * -ENOSYS  : we are not running on VM
  * -EIO     : could not perform query diagnose
  * -ENOENT  : no such segment
- * -ENOTSUPP: multi-part segment cannot be used with linux
+ * -EOPNOTSUPP: multi-part segment cannot be used with linux
  * -ENOMEM  : out of memory
  * 0 .. 6   : type of segment as defined in include/asm-s390/extmem.h
  */
@@ -407,11 +408,11 @@ segment_overlaps_others (struct dcss_segment *seg)
 static int
 __segment_load (char *name, int do_nonshared, unsigned long *addr, unsigned long *end)
 {
-	struct dcss_segment *seg = kmalloc(sizeof(struct dcss_segment),
-			GFP_DMA);
-	int rc, diag_cc;
 	unsigned long start_addr, end_addr, dummy;
+	struct dcss_segment *seg;
+	int rc, diag_cc;
 
+	seg = kmalloc(sizeof(*seg), GFP_KERNEL | GFP_DMA);
 	if (seg == NULL) {
 		rc = -ENOMEM;
 		goto out;
@@ -515,7 +516,7 @@ __segment_load (char *name, int do_nonshared, unsigned long *addr, unsigned long
  * -ENOSYS  : we are not running on VM
  * -EIO     : could not perform query or load diagnose
  * -ENOENT  : no such segment
- * -ENOTSUPP: multi-part segment cannot be used with linux
+ * -EOPNOTSUPP: multi-part segment cannot be used with linux
  * -ENOSPC  : segment cannot be used (overlaps with storage)
  * -EBUSY   : segment can temporarily not be used (overlaps with dcss)
  * -ERANGE  : segment cannot be used (exceeds kernel mapping range)
@@ -742,7 +743,7 @@ void segment_warning(int rc, char *seg_name)
 		pr_err("Loading or querying DCSS %s resulted in a "
 		       "hardware error\n", seg_name);
 		break;
-	case -ENOTSUPP:
+	case -EOPNOTSUPP:
 		pr_err("DCSS %s has multiple page ranges and cannot be "
 		       "loaded or queried\n", seg_name);
 		break;
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index fc102e70d9c..2505b2ea0ef 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -30,6 +30,7 @@
 #include <linux/kprobes.h>
 #include <linux/uaccess.h>
 #include <linux/hugetlb.h>
+#include <asm/asm-offsets.h>
 #include <asm/system.h>
 #include <asm/pgtable.h>
 #include <asm/s390_ext.h>
@@ -47,10 +48,6 @@
 #define __PF_RES_FIELD 0x8000000000000000ULL
 #endif /* CONFIG_64BIT */
 
-#ifdef CONFIG_SYSCTL
-extern int sysctl_userprocess_debug;
-#endif
-
 #define VM_FAULT_BADCONTEXT	0x010000
 #define VM_FAULT_BADMAP		0x020000
 #define VM_FAULT_BADACCESS	0x040000
@@ -59,15 +56,13 @@ static inline int notify_page_fault(struct pt_regs *regs)
 {
 	int ret = 0;
 
-#ifdef CONFIG_KPROBES
 	/* kprobe_running() needs smp_processor_id() */
-	if (!user_mode(regs)) {
+	if (kprobes_built_in() && !user_mode(regs)) {
 		preempt_disable();
 		if (kprobe_running() && kprobe_fault_handler(regs, 14))
 			ret = 1;
 		preempt_enable();
 	}
-#endif
 	return ret;
 }
 
@@ -121,6 +116,22 @@ 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)
+{
+	if ((task_pid_nr(current) > 1) && !show_unhandled_signals)
+		return;
+	if (!unhandled_signal(current, signr))
+		return;
+	if (!printk_ratelimit())
+		return;
+	printk("User process fault: interruption code 0x%lX ", int_code);
+	print_vma_addr(KERN_CONT "in ", regs->psw.addr & PSW_ADDR_INSN);
+	printk("\n");
+	printk("failing address: %lX\n", address);
+	show_regs(regs);
+}
+
 /*
  * Send SIGSEGV to task.  This is an external routine
  * to keep the stack usage of do_page_fault small.
@@ -134,17 +145,7 @@ static noinline void do_sigsegv(struct pt_regs *regs, long int_code,
 	address = trans_exc_code & __FAIL_ADDR_MASK;
 	current->thread.prot_addr = address;
 	current->thread.trap_no = int_code;
-#if defined(CONFIG_SYSCTL) || defined(CONFIG_PROCESS_DEBUG)
-#if defined(CONFIG_SYSCTL)
-	if (sysctl_userprocess_debug)
-#endif
-	{
-		printk("User process fault: interruption code 0x%lX\n",
-		       int_code);
-		printk("failing address: %lX\n", address);
-		show_regs(regs);
-	}
-#endif
+	report_user_fault(regs, int_code, SIGSEGV, address);
 	si.si_signo = SIGSEGV;
 	si.si_code = si_code;
 	si.si_addr = (void __user *) address;
diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index 76564795222..acc91c75bc9 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -26,6 +26,7 @@
 #include <linux/pfn.h>
 #include <linux/poison.h>
 #include <linux/initrd.h>
+#include <linux/gfp.h>
 #include <asm/processor.h>
 #include <asm/system.h>
 #include <asm/uaccess.h>
@@ -143,33 +144,34 @@ void kernel_map_pages(struct page *page, int numpages, int enable)
 }
 #endif
 
-void free_initmem(void)
+void free_init_pages(char *what, unsigned long begin, unsigned long end)
 {
-        unsigned long addr;
+	unsigned long addr = begin;
 
-        addr = (unsigned long)(&__init_begin);
-        for (; addr < (unsigned long)(&__init_end); addr += PAGE_SIZE) {
+	if (begin >= end)
+		return;
+	for (; addr < end; addr += PAGE_SIZE) {
 		ClearPageReserved(virt_to_page(addr));
 		init_page_count(virt_to_page(addr));
-		memset((void *)addr, POISON_FREE_INITMEM, PAGE_SIZE);
+		memset((void *)(addr & PAGE_MASK), POISON_FREE_INITMEM,
+		       PAGE_SIZE);
 		free_page(addr);
 		totalram_pages++;
-        }
-        printk ("Freeing unused kernel memory: %ldk freed\n",
-		((unsigned long)&__init_end - (unsigned long)&__init_begin) >> 10);
+	}
+	printk(KERN_INFO "Freeing %s: %luk freed\n", what, (end - begin) >> 10);
+}
+
+void free_initmem(void)
+{
+	free_init_pages("unused kernel memory",
+			(unsigned long)&__init_begin,
+			(unsigned long)&__init_end);
 }
 
 #ifdef CONFIG_BLK_DEV_INITRD
 void free_initrd_mem(unsigned long start, unsigned long end)
 {
-        if (start < end)
-                printk ("Freeing initrd memory: %ldk freed\n", (end - start) >> 10);
-        for (; start < end; start += PAGE_SIZE) {
-                ClearPageReserved(virt_to_page(start));
-                init_page_count(virt_to_page(start));
-                free_page(start);
-                totalram_pages++;
-        }
+	free_init_pages("initrd memory", start, end);
 }
 #endif
 
diff --git a/arch/s390/mm/maccess.c b/arch/s390/mm/maccess.c
index 81756271dc4..a8c2af8c650 100644
--- a/arch/s390/mm/maccess.c
+++ b/arch/s390/mm/maccess.c
@@ -59,3 +59,29 @@ long probe_kernel_write(void *dst, void *src, size_t size)
 	}
 	return copied < 0 ? -EFAULT : 0;
 }
+
+int memcpy_real(void *dest, void *src, size_t count)
+{
+	register unsigned long _dest asm("2") = (unsigned long) dest;
+	register unsigned long _len1 asm("3") = (unsigned long) count;
+	register unsigned long _src  asm("4") = (unsigned long) src;
+	register unsigned long _len2 asm("5") = (unsigned long) count;
+	unsigned long flags;
+	int rc = -EFAULT;
+
+	if (!count)
+		return 0;
+	flags = __raw_local_irq_stnsm(0xf8UL);
+	asm volatile (
+		"0:	mvcle	%1,%2,0x0\n"
+		"1:	jo	0b\n"
+		"	lhi	%0,0x0\n"
+		"2:\n"
+		EX_TABLE(1b,2b)
+		: "+d" (rc), "+d" (_dest), "+d" (_src), "+d" (_len1),
+		  "+d" (_len2), "=m" (*((long *) dest))
+		: "m" (*((long *) src))
+		: "cc", "memory");
+	__raw_local_irq_ssm(flags);
+	return rc;
+}
diff --git a/arch/s390/mm/page-states.c b/arch/s390/mm/page-states.c
index 098923ae458..a90d45e9dfb 100644
--- a/arch/s390/mm/page-states.c
+++ b/arch/s390/mm/page-states.c
@@ -10,6 +10,7 @@
 #include <linux/errno.h>
 #include <linux/types.h>
 #include <linux/mm.h>
+#include <linux/gfp.h>
 #include <linux/init.h>
 
 #define ESSA_SET_STABLE		1
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index ad621e06ada..8d999249d35 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -6,11 +6,11 @@
 #include <linux/sched.h>
 #include <linux/kernel.h>
 #include <linux/errno.h>
+#include <linux/gfp.h>
 #include <linux/mm.h>
 #include <linux/swap.h>
 #include <linux/smp.h>
 #include <linux/highmem.h>
-#include <linux/slab.h>
 #include <linux/pagemap.h>
 #include <linux/spinlock.h>
 #include <linux/module.h>
diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c
index 300ab012b0f..90165e7ca04 100644
--- a/arch/s390/mm/vmem.c
+++ b/arch/s390/mm/vmem.c
@@ -11,6 +11,7 @@
 #include <linux/module.h>
 #include <linux/list.h>
 #include <linux/hugetlb.h>
+#include <linux/slab.h>
 #include <asm/pgalloc.h>
 #include <asm/pgtable.h>
 #include <asm/setup.h>
@@ -70,12 +71,8 @@ static pte_t __ref *vmem_pte_alloc(void)
 		pte = alloc_bootmem(PTRS_PER_PTE * sizeof(pte_t));
 	if (!pte)
 		return NULL;
-	if (MACHINE_HAS_HPAGE)
-		clear_table((unsigned long *) pte, _PAGE_TYPE_EMPTY | _PAGE_CO,
-			    PTRS_PER_PTE * sizeof(pte_t));
-	else
-		clear_table((unsigned long *) pte, _PAGE_TYPE_EMPTY,
-			    PTRS_PER_PTE * sizeof(pte_t));
+	clear_table((unsigned long *) pte, _PAGE_TYPE_EMPTY,
+		    PTRS_PER_PTE * sizeof(pte_t));
 	return pte;
 }
 
@@ -116,8 +113,7 @@ static int vmem_add_mem(unsigned long start, unsigned long size, int ro)
 		if (MACHINE_HAS_HPAGE && !(address & ~HPAGE_MASK) &&
 		    (address + HPAGE_SIZE <= start + size) &&
 		    (address >= HPAGE_SIZE)) {
-			pte_val(pte) |= _SEGMENT_ENTRY_LARGE |
-					_SEGMENT_ENTRY_CO;
+			pte_val(pte) |= _SEGMENT_ENTRY_LARGE;
 			pmd_val(*pm_dir) = pte_val(pte);
 			address += HPAGE_SIZE - PAGE_SIZE;
 			continue;