Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6 into for-linus-1

* 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6: (9356 commits)
  [media] rc: update for bitop name changes
  fs: simplify iget & friends
  fs: pull inode->i_lock up out of writeback_single_inode
  fs: rename inode_lock to inode_hash_lock
  fs: move i_wb_list out from under inode_lock
  fs: move i_sb_list out from under inode_lock
  fs: remove inode_lock from iput_final and prune_icache
  fs: Lock the inode LRU list separately
  fs: factor inode disposal
  fs: protect inode->i_state with inode->i_lock
  lib, arch: add filter argument to show_mem and fix private implementations
  SLUB: Write to per cpu data when allocating it
  slub: Fix debugobjects with lockless fastpath
  autofs4: Do not potentially dereference NULL pointer returned by fget() in autofs_dev_ioctl_setpipefd()
  autofs4 - remove autofs4_lock
  autofs4 - fix d_manage() return on rcu-walk
  autofs4 - fix autofs4_expire_indirect() traversal
  autofs4 - fix dentry leak in autofs4_expire_direct()
  autofs4 - reinstate last used update on access
  vfs - check non-mountpoint dentry might block in __follow_mount_rcu()
  ...

NOTE!

This merge commit was created to fix compilation error. The block
tree was merged upstream and removed the 'elv_queue_empty()'
function which the new 'mtdswap' driver is using. So a simple
merge of the mtd tree with upstream does not compile. And the
mtd tree has already be published, so re-basing it is not an option.

To fix this unfortunate situation, I had to merge upstream into the
mtd-2.6.git tree without committing, put the fixup patch on top of
this, and then commit this. The result is that we do not have commits
which do not compile.

In other words, this merge commit "merges" 3 things: the MTD tree, the
upstream tree, and the fixup patch.

33 files changed, 1726 insertions, 223 deletions

diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index ff19efdf6fe..2508a6f3158 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -85,6 +85,7 @@ config S390
 	select HAVE_KERNEL_BZIP2
 	select HAVE_KERNEL_LZMA
 	select HAVE_KERNEL_LZO
+	select HAVE_KERNEL_XZ
 	select HAVE_GET_USER_PAGES_FAST
 	select HAVE_ARCH_MUTEX_CPU_RELAX
 	select ARCH_INLINE_SPIN_TRYLOCK
@@ -341,26 +342,16 @@ config STACK_GUARD
 	  The minimum size for the stack guard should be 256 for 31 bit and
 	  512 for 64 bit.
 
-config WARN_STACK
+config WARN_DYNAMIC_STACK
 	def_bool n
-	prompt "Emit compiler warnings for function with broken stack usage"
+	prompt "Emit compiler warnings for function with dynamic stack usage"
 	help
-	  This option enables the compiler options -mwarn-framesize and
-	  -mwarn-dynamicstack. If the compiler supports these options it
-	  will generate warnings for function which either use alloca or
-	  create a stack frame bigger than CONFIG_WARN_STACK_SIZE.
+	  This option enables the compiler option -mwarn-dynamicstack. If the
+	  compiler supports this options generates warnings for functions
+	  that dynamically allocate stack space using alloca.
 
 	  Say N if you are unsure.
 
-config WARN_STACK_SIZE
-	int "Maximum frame size considered safe (128-2048)"
-	range 128 2048
-	depends on WARN_STACK
-	default "2048"
-	help
-	  This allows you to specify the maximum frame size a function may
-	  have without the compiler complaining about it.
-
 config ARCH_POPULATES_NODE_MAP
 	def_bool y
 
@@ -406,7 +397,7 @@ config QDIO
 	  If unsure, say Y.
 
 config CHSC_SCH
-	def_tristate y
+	def_tristate m
 	prompt "Support for CHSC subchannels"
 	help
 	  This driver allows usage of CHSC subchannels. A CHSC subchannel
diff --git a/arch/s390/Kconfig.debug b/arch/s390/Kconfig.debug
index 2b380df9560..d76cef3fef3 100644
--- a/arch/s390/Kconfig.debug
+++ b/arch/s390/Kconfig.debug
@@ -31,4 +31,7 @@ config DEBUG_STRICT_USER_COPY_CHECKS
 
 	  If unsure, or if you run an older (pre 4.4) gcc, say N.
 
+config DEBUG_SET_MODULE_RONX
+	def_bool y
+	depends on MODULES
 endmenu
diff --git a/arch/s390/Makefile b/arch/s390/Makefile
index d5b8a6ade52..27a0b5df5ea 100644
--- a/arch/s390/Makefile
+++ b/arch/s390/Makefile
@@ -80,8 +80,7 @@ endif
 endif
 
 ifeq ($(call cc-option-yn,-mwarn-dynamicstack),y)
-cflags-$(CONFIG_WARN_STACK) += -mwarn-dynamicstack
-cflags-$(CONFIG_WARN_STACK) += -mwarn-framesize=$(CONFIG_WARN_STACK_SIZE)
+cflags-$(CONFIG_WARN_DYNAMIC_STACK) += -mwarn-dynamicstack
 endif
 
 KBUILD_CFLAGS	+= -mbackchain -msoft-float $(cflags-y)
diff --git a/arch/s390/boot/Makefile b/arch/s390/boot/Makefile
index 8800cf09069..635d677d328 100644
--- a/arch/s390/boot/Makefile
+++ b/arch/s390/boot/Makefile
@@ -6,7 +6,7 @@ COMPILE_VERSION := __linux_compile_version_id__`hostname |  \
 			tr -c '[0-9A-Za-z]' '_'`__`date | \
 			tr -c '[0-9A-Za-z]' '_'`_t
 
-EXTRA_CFLAGS  := -DCOMPILE_VERSION=$(COMPILE_VERSION) -gstabs -I.
+ccflags-y  := -DCOMPILE_VERSION=$(COMPILE_VERSION) -gstabs -I.
 
 targets := image
 targets += bzImage
diff --git a/arch/s390/boot/compressed/Makefile b/arch/s390/boot/compressed/Makefile
index 1c999f726a5..10e22c4ec4a 100644
--- a/arch/s390/boot/compressed/Makefile
+++ b/arch/s390/boot/compressed/Makefile
@@ -7,7 +7,8 @@
 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$(BITS).o
+	   vmlinux.bin.xz vmlinux.bin.lzma vmlinux.bin.lzo misc.o piggy.o \
+	   sizes.h head$(BITS).o
 
 KBUILD_CFLAGS := -m$(BITS) -D__KERNEL__ $(LINUX_INCLUDE) -O2
 KBUILD_CFLAGS += $(cflags-y)
@@ -48,6 +49,7 @@ suffix-$(CONFIG_KERNEL_GZIP)  := gz
 suffix-$(CONFIG_KERNEL_BZIP2) := bz2
 suffix-$(CONFIG_KERNEL_LZMA)  := lzma
 suffix-$(CONFIG_KERNEL_LZO)  := lzo
+suffix-$(CONFIG_KERNEL_XZ)  := xz
 
 $(obj)/vmlinux.bin.gz: $(vmlinux.bin.all-y)
 	$(call if_changed,gzip)
@@ -57,6 +59,8 @@ $(obj)/vmlinux.bin.lzma: $(vmlinux.bin.all-y)
 	$(call if_changed,lzma)
 $(obj)/vmlinux.bin.lzo: $(vmlinux.bin.all-y)
 	$(call if_changed,lzo)
+$(obj)/vmlinux.bin.xz: $(vmlinux.bin.all-y)
+	$(call if_changed,xzkern)
 
 LDFLAGS_piggy.o := -r --format binary --oformat $(LD_BFD) -T
 $(obj)/piggy.o: $(obj)/vmlinux.scr $(obj)/vmlinux.bin.$(suffix-y)
diff --git a/arch/s390/boot/compressed/misc.c b/arch/s390/boot/compressed/misc.c
index 0851eb1e919..028f23ea81d 100644
--- a/arch/s390/boot/compressed/misc.c
+++ b/arch/s390/boot/compressed/misc.c
@@ -19,6 +19,7 @@
 #undef memset
 #undef memcpy
 #undef memmove
+#define memmove memmove
 #define memzero(s, n) memset((s), 0, (n))
 
 /* Symbols defined by linker scripts */
@@ -54,6 +55,10 @@ static unsigned long free_mem_end_ptr;
 #include "../../../../lib/decompress_unlzo.c"
 #endif
 
+#ifdef CONFIG_KERNEL_XZ
+#include "../../../../lib/decompress_unxz.c"
+#endif
+
 extern _sclp_print_early(const char *);
 
 int puts(const char *s)
@@ -133,11 +138,12 @@ unsigned long decompress_kernel(void)
 	unsigned long output_addr;
 	unsigned char *output;
 
-	check_ipl_parmblock((void *) 0, (unsigned long) output + SZ__bss_start);
+	output_addr = ((unsigned long) &_end + HEAP_SIZE + 4095UL) & -4096UL;
+	check_ipl_parmblock((void *) 0, output_addr + 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);
+	output = (unsigned char *) output_addr;
 
 #ifdef CONFIG_BLK_DEV_INITRD
 	/*
diff --git a/arch/s390/crypto/sha_common.c b/arch/s390/crypto/sha_common.c
index f42dbabc0d3..48884f89ab9 100644
--- a/arch/s390/crypto/sha_common.c
+++ b/arch/s390/crypto/sha_common.c
@@ -38,6 +38,7 @@ int s390_sha_update(struct shash_desc *desc, const u8 *data, unsigned int len)
 		BUG_ON(ret != bsize);
 		data += bsize - index;
 		len -= bsize - index;
+		index = 0;
 	}
 
 	/* process as many blocks as possible */
diff --git a/arch/s390/include/asm/atomic.h b/arch/s390/include/asm/atomic.h
index 76daea11718..5c5ba10384c 100644
--- a/arch/s390/include/asm/atomic.h
+++ b/arch/s390/include/asm/atomic.h
@@ -36,14 +36,19 @@
 
 static inline int atomic_read(const atomic_t *v)
 {
-	barrier();
-	return v->counter;
+	int c;
+
+	asm volatile(
+		"	l	%0,%1\n"
+		: "=d" (c) : "Q" (v->counter));
+	return c;
 }
 
 static inline void atomic_set(atomic_t *v, int i)
 {
-	v->counter = i;
-	barrier();
+	asm volatile(
+		"	st	%1,%0\n"
+		: "=Q" (v->counter) : "d" (i));
 }
 
 static inline int atomic_add_return(int i, atomic_t *v)
@@ -128,14 +133,19 @@ static inline int atomic_add_unless(atomic_t *v, int a, int u)
 
 static inline long long atomic64_read(const atomic64_t *v)
 {
-	barrier();
-	return v->counter;
+	long long c;
+
+	asm volatile(
+		"	lg	%0,%1\n"
+		: "=d" (c) : "Q" (v->counter));
+	return c;
 }
 
 static inline void atomic64_set(atomic64_t *v, long long i)
 {
-	v->counter = i;
-	barrier();
+	asm volatile(
+		"	stg	%1,%0\n"
+		: "=Q" (v->counter) : "d" (i));
 }
 
 static inline long long atomic64_add_return(long long i, atomic64_t *v)
diff --git a/arch/s390/include/asm/bitops.h b/arch/s390/include/asm/bitops.h
index 2e05972c508..e1c8f3a4988 100644
--- a/arch/s390/include/asm/bitops.h
+++ b/arch/s390/include/asm/bitops.h
@@ -742,18 +742,42 @@ static inline int sched_find_first_bit(unsigned long *b)
  *    23 22 21 20 19 18 17 16 31 30 29 28 27 26 25 24
  */
 
-#define ext2_set_bit(nr, addr)       \
-	__test_and_set_bit((nr)^(__BITOPS_WORDSIZE - 8), (unsigned long *)addr)
-#define ext2_set_bit_atomic(lock, nr, addr)       \
-	test_and_set_bit((nr)^(__BITOPS_WORDSIZE - 8), (unsigned long *)addr)
-#define ext2_clear_bit(nr, addr)     \
-	__test_and_clear_bit((nr)^(__BITOPS_WORDSIZE - 8), (unsigned long *)addr)
-#define ext2_clear_bit_atomic(lock, nr, addr)     \
-	test_and_clear_bit((nr)^(__BITOPS_WORDSIZE - 8), (unsigned long *)addr)
-#define ext2_test_bit(nr, addr)      \
-	test_bit((nr)^(__BITOPS_WORDSIZE - 8), (unsigned long *)addr)
-
-static inline int ext2_find_first_zero_bit(void *vaddr, unsigned int size)
+static inline void __set_bit_le(unsigned long nr, void *addr)
+{
+	__set_bit(nr ^ (__BITOPS_WORDSIZE - 8), addr);
+}
+
+static inline void __clear_bit_le(unsigned long nr, void *addr)
+{
+	__clear_bit(nr ^ (__BITOPS_WORDSIZE - 8), addr);
+}
+
+static inline int __test_and_set_bit_le(unsigned long nr, void *addr)
+{
+	return __test_and_set_bit(nr ^ (__BITOPS_WORDSIZE - 8), addr);
+}
+
+static inline int test_and_set_bit_le(unsigned long nr, void *addr)
+{
+	return test_and_set_bit(nr ^ (__BITOPS_WORDSIZE - 8), addr);
+}
+
+static inline int __test_and_clear_bit_le(unsigned long nr, void *addr)
+{
+	return __test_and_clear_bit(nr ^ (__BITOPS_WORDSIZE - 8), addr);
+}
+
+static inline int test_and_clear_bit_le(unsigned long nr, void *addr)
+{
+	return test_and_clear_bit(nr ^ (__BITOPS_WORDSIZE - 8), addr);
+}
+
+static inline int test_bit_le(unsigned long nr, const void *addr)
+{
+	return test_bit(nr ^ (__BITOPS_WORDSIZE - 8), addr);
+}
+
+static inline int find_first_zero_bit_le(void *vaddr, unsigned int size)
 {
 	unsigned long bytes, bits;
 
@@ -764,7 +788,7 @@ static inline int ext2_find_first_zero_bit(void *vaddr, unsigned int size)
 	return (bits < size) ? bits : size;
 }
 
-static inline int ext2_find_next_zero_bit(void *vaddr, unsigned long size,
+static inline int find_next_zero_bit_le(void *vaddr, unsigned long size,
 					  unsigned long offset)
 {
         unsigned long *addr = vaddr, *p;
@@ -790,11 +814,10 @@ static inline int ext2_find_next_zero_bit(void *vaddr, unsigned long size,
 		size -= __BITOPS_WORDSIZE;
 		p++;
         }
-	return offset + ext2_find_first_zero_bit(p, size);
+	return offset + find_first_zero_bit_le(p, size);
 }
 
-static inline unsigned long ext2_find_first_bit(void *vaddr,
-						unsigned long size)
+static inline unsigned long find_first_bit_le(void *vaddr, unsigned long size)
 {
 	unsigned long bytes, bits;
 
@@ -805,7 +828,7 @@ static inline unsigned long ext2_find_first_bit(void *vaddr,
 	return (bits < size) ? bits : size;
 }
 
-static inline int ext2_find_next_bit(void *vaddr, unsigned long size,
+static inline int find_next_bit_le(void *vaddr, unsigned long size,
 				     unsigned long offset)
 {
 	unsigned long *addr = vaddr, *p;
@@ -831,10 +854,14 @@ static inline int ext2_find_next_bit(void *vaddr, unsigned long size,
 		size -= __BITOPS_WORDSIZE;
 		p++;
 	}
-	return offset + ext2_find_first_bit(p, size);
+	return offset + find_first_bit_le(p, size);
 }
 
-#include <asm-generic/bitops/minix.h>
+#define ext2_set_bit_atomic(lock, nr, addr)	\
+	test_and_set_bit_le(nr, addr)
+#define ext2_clear_bit_atomic(lock, nr, addr)	\
+	test_and_clear_bit_le(nr, addr)
+
 
 #endif /* __KERNEL__ */
 
diff --git a/arch/s390/include/asm/cache.h b/arch/s390/include/asm/cache.h
index 24aafa68b64..2a30d5ac066 100644
--- a/arch/s390/include/asm/cache.h
+++ b/arch/s390/include/asm/cache.h
@@ -13,6 +13,7 @@
 
 #define L1_CACHE_BYTES     256
 #define L1_CACHE_SHIFT     8
+#define NET_SKB_PAD	   32
 
 #define __read_mostly __attribute__((__section__(".data..read_mostly")))
 
diff --git a/arch/s390/include/asm/cacheflush.h b/arch/s390/include/asm/cacheflush.h
index 405cc97c624..43a5c78046d 100644
--- a/arch/s390/include/asm/cacheflush.h
+++ b/arch/s390/include/asm/cacheflush.h
@@ -1,32 +1,15 @@
 #ifndef _S390_CACHEFLUSH_H
 #define _S390_CACHEFLUSH_H
 
-/* Keep includes the same across arches.  */
-#include <linux/mm.h>
-
 /* Caches aren't brain-dead on the s390. */
-#define flush_cache_all()			do { } while (0)
-#define flush_cache_mm(mm)			do { } while (0)
-#define flush_cache_dup_mm(mm)			do { } while (0)
-#define flush_cache_range(vma, start, end)	do { } while (0)
-#define flush_cache_page(vma, vmaddr, pfn)	do { } while (0)
-#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0
-#define flush_dcache_page(page)			do { } while (0)
-#define flush_dcache_mmap_lock(mapping)		do { } while (0)
-#define flush_dcache_mmap_unlock(mapping)	do { } while (0)
-#define flush_icache_range(start, end)		do { } while (0)
-#define flush_icache_page(vma,pg)		do { } while (0)
-#define flush_icache_user_range(vma,pg,adr,len)	do { } while (0)
-#define flush_cache_vmap(start, end)		do { } while (0)
-#define flush_cache_vunmap(start, end)		do { } while (0)
-
-#define copy_to_user_page(vma, page, vaddr, dst, src, len) \
-	memcpy(dst, src, len)
-#define copy_from_user_page(vma, page, vaddr, dst, src, len) \
-	memcpy(dst, src, len)
+#include <asm-generic/cacheflush.h>
 
 #ifdef CONFIG_DEBUG_PAGEALLOC
 void kernel_map_pages(struct page *page, int numpages, int enable);
 #endif
 
+int set_memory_ro(unsigned long addr, int numpages);
+int set_memory_rw(unsigned long addr, int numpages);
+int set_memory_nx(unsigned long addr, int numpages);
+
 #endif /* _S390_CACHEFLUSH_H */
diff --git a/arch/s390/include/asm/futex.h b/arch/s390/include/asm/futex.h
index 5c5d02de49e..81cf36b691f 100644
--- a/arch/s390/include/asm/futex.h
+++ b/arch/s390/include/asm/futex.h
@@ -7,7 +7,7 @@
 #include <linux/uaccess.h>
 #include <asm/errno.h>
 
-static inline int futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
+static inline int futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
 {
 	int op = (encoded_op >> 28) & 7;
 	int cmp = (encoded_op >> 24) & 15;
@@ -18,7 +18,7 @@ static inline int futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
 	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
 		oparg = 1 << oparg;
 
-	if (! access_ok (VERIFY_WRITE, uaddr, sizeof(int)))
+	if (! access_ok (VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
 	pagefault_disable();
@@ -39,13 +39,13 @@ static inline int futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
 	return ret;
 }
 
-static inline int futex_atomic_cmpxchg_inatomic(int __user *uaddr,
-						int oldval, int newval)
+static inline int futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
+						u32 oldval, u32 newval)
 {
-	if (! access_ok (VERIFY_WRITE, uaddr, sizeof(int)))
+	if (! access_ok (VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
-	return uaccess.futex_atomic_cmpxchg(uaddr, oldval, newval);
+	return uaccess.futex_atomic_cmpxchg(uval, uaddr, oldval, newval);
 }
 
 #endif /* __KERNEL__ */
diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index bf3de04170a..2c79b641627 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -148,11 +148,6 @@ extern int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags);
  */
 extern unsigned long thread_saved_pc(struct task_struct *t);
 
-/*
- * Print register of task into buffer. Used in fs/proc/array.c.
- */
-extern void task_show_regs(struct seq_file *m, struct task_struct *task);
-
 extern void show_code(struct pt_regs *regs);
 
 unsigned long get_wchan(struct task_struct *p);
diff --git a/arch/s390/include/asm/rwsem.h b/arch/s390/include/asm/rwsem.h
index 423fdda2322..d0eb4653ceb 100644
--- a/arch/s390/include/asm/rwsem.h
+++ b/arch/s390/include/asm/rwsem.h
@@ -43,29 +43,6 @@
 
 #ifdef __KERNEL__
 
-#include <linux/list.h>
-#include <linux/spinlock.h>
-
-struct rwsem_waiter;
-
-extern struct rw_semaphore *rwsem_down_read_failed(struct rw_semaphore *);
-extern struct rw_semaphore *rwsem_down_write_failed(struct rw_semaphore *);
-extern struct rw_semaphore *rwsem_wake(struct rw_semaphore *);
-extern struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *);
-extern struct rw_semaphore *rwsem_downgrade_write(struct rw_semaphore *);
-
-/*
- * the semaphore definition
- */
-struct rw_semaphore {
-	signed long		count;
-	spinlock_t		wait_lock;
-	struct list_head	wait_list;
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-	struct lockdep_map	dep_map;
-#endif
-};
-
 #ifndef __s390x__
 #define RWSEM_UNLOCKED_VALUE	0x00000000
 #define RWSEM_ACTIVE_BIAS	0x00000001
@@ -81,41 +58,6 @@ struct rw_semaphore {
 #define RWSEM_ACTIVE_WRITE_BIAS	(RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
 
 /*
- * initialisation
- */
-
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-# define __RWSEM_DEP_MAP_INIT(lockname) , .dep_map = { .name = #lockname }
-#else
-# define __RWSEM_DEP_MAP_INIT(lockname)
-#endif
-
-#define __RWSEM_INITIALIZER(name) \
- { RWSEM_UNLOCKED_VALUE, __SPIN_LOCK_UNLOCKED((name).wait.lock), \
-   LIST_HEAD_INIT((name).wait_list) __RWSEM_DEP_MAP_INIT(name) }
-
-#define DECLARE_RWSEM(name) \
-	struct rw_semaphore name = __RWSEM_INITIALIZER(name)
-
-static inline void init_rwsem(struct rw_semaphore *sem)
-{
-	sem->count = RWSEM_UNLOCKED_VALUE;
-	spin_lock_init(&sem->wait_lock);
-	INIT_LIST_HEAD(&sem->wait_list);
-}
-
-extern void __init_rwsem(struct rw_semaphore *sem, const char *name,
-			 struct lock_class_key *key);
-
-#define init_rwsem(sem)				\
-do {						\
-	static struct lock_class_key __key;	\
-						\
-	__init_rwsem((sem), #sem, &__key);	\
-} while (0)
-
-
-/*
  * lock for reading
  */
 static inline void __down_read(struct rw_semaphore *sem)
@@ -377,10 +319,5 @@ static inline long rwsem_atomic_update(long delta, struct rw_semaphore *sem)
 	return new;
 }
 
-static inline int rwsem_is_locked(struct rw_semaphore *sem)
-{
-	return (sem->count != 0);
-}
-
 #endif /* __KERNEL__ */
 #endif /* _S390_RWSEM_H */
diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h
index f1f644f2240..9074a54c4d1 100644
--- a/arch/s390/include/asm/tlb.h
+++ b/arch/s390/include/asm/tlb.h
@@ -22,6 +22,7 @@
  */
 
 #include <linux/mm.h>
+#include <linux/pagemap.h>
 #include <linux/swap.h>
 #include <asm/processor.h>
 #include <asm/pgalloc.h>
diff --git a/arch/s390/include/asm/types.h b/arch/s390/include/asm/types.h
index 04d6b95a89c..eeb52ccf499 100644
--- a/arch/s390/include/asm/types.h
+++ b/arch/s390/include/asm/types.h
@@ -30,14 +30,6 @@ typedef __signed__ long saddr_t;
 
 #ifndef __ASSEMBLY__
 
-typedef u64 dma64_addr_t;
-#ifdef __s390x__
-/* DMA addresses come in 32-bit and 64-bit flavours. */
-typedef u64 dma_addr_t;
-#else
-typedef u32 dma_addr_t;
-#endif
-
 #ifndef __s390x__
 typedef union {
 	unsigned long long pair;
diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h
index d6b1ed0ec52..2d9ea11f919 100644
--- a/arch/s390/include/asm/uaccess.h
+++ b/arch/s390/include/asm/uaccess.h
@@ -83,8 +83,8 @@ struct uaccess_ops {
 	size_t (*clear_user)(size_t, void __user *);
 	size_t (*strnlen_user)(size_t, const char __user *);
 	size_t (*strncpy_from_user)(size_t, const char __user *, char *);
-	int (*futex_atomic_op)(int op, int __user *, int oparg, int *old);
-	int (*futex_atomic_cmpxchg)(int __user *, int old, int new);
+	int (*futex_atomic_op)(int op, u32 __user *, int oparg, int *old);
+	int (*futex_atomic_cmpxchg)(u32 *, u32 __user *, u32 old, u32 new);
 };
 
 extern struct uaccess_ops uaccess;
diff --git a/arch/s390/kernel/machine_kexec.c b/arch/s390/kernel/machine_kexec.c
index a922d51df6b..b09b9c62573 100644
--- a/arch/s390/kernel/machine_kexec.c
+++ b/arch/s390/kernel/machine_kexec.c
@@ -12,6 +12,7 @@
 #include <linux/kexec.h>
 #include <linux/delay.h>
 #include <linux/reboot.h>
+#include <linux/ftrace.h>
 #include <asm/cio.h>
 #include <asm/setup.h>
 #include <asm/pgtable.h>
@@ -71,6 +72,7 @@ static void __machine_kexec(void *data)
 
 void machine_kexec(struct kimage *image)
 {
+	tracer_disable();
 	smp_send_stop();
 	smp_switch_to_ipl_cpu(__machine_kexec, image);
 }
diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c
index 5eb78dd584c..b5a4a739b47 100644
--- a/arch/s390/kernel/traps.c
+++ b/arch/s390/kernel/traps.c
@@ -237,43 +237,6 @@ void show_regs(struct pt_regs *regs)
 	show_last_breaking_event(regs);
 }
 
-/* This is called from fs/proc/array.c */
-void task_show_regs(struct seq_file *m, struct task_struct *task)
-{
-	struct pt_regs *regs;
-
-	regs = task_pt_regs(task);
-	seq_printf(m, "task: %p, ksp: %p\n",
-		       task, (void *)task->thread.ksp);
-	seq_printf(m, "User PSW : %p %p\n",
-		       (void *) regs->psw.mask, (void *)regs->psw.addr);
-
-	seq_printf(m, "User GPRS: " FOURLONG,
-			  regs->gprs[0], regs->gprs[1],
-			  regs->gprs[2], regs->gprs[3]);
-	seq_printf(m, "           " FOURLONG,
-			  regs->gprs[4], regs->gprs[5],
-			  regs->gprs[6], regs->gprs[7]);
-	seq_printf(m, "           " FOURLONG,
-			  regs->gprs[8], regs->gprs[9],
-			  regs->gprs[10], regs->gprs[11]);
-	seq_printf(m, "           " FOURLONG,
-			  regs->gprs[12], regs->gprs[13],
-			  regs->gprs[14], regs->gprs[15]);
-	seq_printf(m, "User ACRS: %08x %08x %08x %08x\n",
-			  task->thread.acrs[0], task->thread.acrs[1],
-			  task->thread.acrs[2], task->thread.acrs[3]);
-	seq_printf(m, "           %08x %08x %08x %08x\n",
-			  task->thread.acrs[4], task->thread.acrs[5],
-			  task->thread.acrs[6], task->thread.acrs[7]);
-	seq_printf(m, "           %08x %08x %08x %08x\n",
-			  task->thread.acrs[8], task->thread.acrs[9],
-			  task->thread.acrs[10], task->thread.acrs[11]);
-	seq_printf(m, "           %08x %08x %08x %08x\n",
-			  task->thread.acrs[12], task->thread.acrs[13],
-			  task->thread.acrs[14], task->thread.acrs[15]);
-}
-
 static DEFINE_SPINLOCK(die_lock);
 
 void die(const char * str, struct pt_regs * regs, long err)
diff --git a/arch/s390/kernel/vdso.c b/arch/s390/kernel/vdso.c
index f438d74dedb..d73630b4fe1 100644
--- a/arch/s390/kernel/vdso.c
+++ b/arch/s390/kernel/vdso.c
@@ -337,17 +337,17 @@ static int __init vdso_init(void)
 }
 arch_initcall(vdso_init);
 
-int in_gate_area_no_task(unsigned long addr)
+int in_gate_area_no_mm(unsigned long addr)
 {
 	return 0;
 }
 
-int in_gate_area(struct task_struct *task, unsigned long addr)
+int in_gate_area(struct mm_struct *mm, unsigned long addr)
 {
 	return 0;
 }
 
-struct vm_area_struct *get_gate_vma(struct task_struct *tsk)
+struct vm_area_struct *get_gate_vma(struct mm_struct *mm)
 {
 	return NULL;
 }
diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S
index a68ac10213b..1bc18cdb525 100644
--- a/arch/s390/kernel/vmlinux.lds.S
+++ b/arch/s390/kernel/vmlinux.lds.S
@@ -77,7 +77,7 @@ SECTIONS
 	. = ALIGN(PAGE_SIZE);
 	INIT_DATA_SECTION(0x100)
 
-	PERCPU(PAGE_SIZE)
+	PERCPU(0x100, PAGE_SIZE)
 	. = ALIGN(PAGE_SIZE);
 	__init_end = .;		/* freed after init ends here */
 
diff --git a/arch/s390/kvm/Makefile b/arch/s390/kvm/Makefile
index e5221ec0b8e..860d26514c0 100644
--- a/arch/s390/kvm/Makefile
+++ b/arch/s390/kvm/Makefile
@@ -8,7 +8,7 @@
 
 common-objs = $(addprefix ../../../virt/kvm/, kvm_main.o)
 
-EXTRA_CFLAGS += -Ivirt/kvm -Iarch/s390/kvm
+ccflags-y := -Ivirt/kvm -Iarch/s390/kvm
 
 kvm-objs := $(common-objs) kvm-s390.o sie64a.o intercept.o interrupt.o priv.o sigp.o diag.o
 obj-$(CONFIG_KVM) += kvm.o
diff --git a/arch/s390/lib/uaccess.h b/arch/s390/lib/uaccess.h
index 126011df14f..1d2536cb630 100644
--- a/arch/s390/lib/uaccess.h
+++ b/arch/s390/lib/uaccess.h
@@ -12,12 +12,12 @@ extern size_t copy_from_user_std(size_t, const void __user *, void *);
 extern size_t copy_to_user_std(size_t, void __user *, const void *);
 extern size_t strnlen_user_std(size_t, const char __user *);
 extern size_t strncpy_from_user_std(size_t, const char __user *, char *);
-extern int futex_atomic_cmpxchg_std(int __user *, int, int);
-extern int futex_atomic_op_std(int, int __user *, int, int *);
+extern int futex_atomic_cmpxchg_std(u32 *, u32 __user *, u32, u32);
+extern int futex_atomic_op_std(int, u32 __user *, int, int *);
 
 extern size_t copy_from_user_pt(size_t, const void __user *, void *);
 extern size_t copy_to_user_pt(size_t, void __user *, const void *);
-extern int futex_atomic_op_pt(int, int __user *, int, int *);
-extern int futex_atomic_cmpxchg_pt(int __user *, int, int);
+extern int futex_atomic_op_pt(int, u32 __user *, int, int *);
+extern int futex_atomic_cmpxchg_pt(u32 *, u32 __user *, u32, u32);
 
 #endif /* __ARCH_S390_LIB_UACCESS_H */
diff --git a/arch/s390/lib/uaccess_pt.c b/arch/s390/lib/uaccess_pt.c
index 404f2de296d..74833831417 100644
--- a/arch/s390/lib/uaccess_pt.c
+++ b/arch/s390/lib/uaccess_pt.c
@@ -302,7 +302,7 @@ fault:
 		     : "0" (-EFAULT), "d" (oparg), "a" (uaddr),		\
 		       "m" (*uaddr) : "cc" );
 
-static int __futex_atomic_op_pt(int op, int __user *uaddr, int oparg, int *old)
+static int __futex_atomic_op_pt(int op, u32 __user *uaddr, int oparg, int *old)
 {
 	int oldval = 0, newval, ret;
 
@@ -335,7 +335,7 @@ static int __futex_atomic_op_pt(int op, int __user *uaddr, int oparg, int *old)
 	return ret;
 }
 
-int futex_atomic_op_pt(int op, int __user *uaddr, int oparg, int *old)
+int futex_atomic_op_pt(int op, u32 __user *uaddr, int oparg, int *old)
 {
 	int ret;
 
@@ -354,26 +354,29 @@ int futex_atomic_op_pt(int op, int __user *uaddr, int oparg, int *old)
 	return ret;
 }
 
-static int __futex_atomic_cmpxchg_pt(int __user *uaddr, int oldval, int newval)
+static int __futex_atomic_cmpxchg_pt(u32 *uval, u32 __user *uaddr,
+				     u32 oldval, u32 newval)
 {
 	int ret;
 
 	asm volatile("0: cs   %1,%4,0(%5)\n"
-		     "1: lr   %0,%1\n"
+		     "1: la   %0,0\n"
 		     "2:\n"
 		     EX_TABLE(0b,2b) EX_TABLE(1b,2b)
 		     : "=d" (ret), "+d" (oldval), "=m" (*uaddr)
 		     : "0" (-EFAULT), "d" (newval), "a" (uaddr), "m" (*uaddr)
 		     : "cc", "memory" );
+	*uval = oldval;
 	return ret;
 }
 
-int futex_atomic_cmpxchg_pt(int __user *uaddr, int oldval, int newval)
+int futex_atomic_cmpxchg_pt(u32 *uval, u32 __user *uaddr,
+			    u32 oldval, u32 newval)
 {
 	int ret;
 
 	if (segment_eq(get_fs(), KERNEL_DS))
-		return __futex_atomic_cmpxchg_pt(uaddr, oldval, newval);
+		return __futex_atomic_cmpxchg_pt(uval, uaddr, oldval, newval);
 	spin_lock(&current->mm->page_table_lock);
 	uaddr = (int __user *) __dat_user_addr((unsigned long) uaddr);
 	if (!uaddr) {
@@ -382,7 +385,7 @@ int futex_atomic_cmpxchg_pt(int __user *uaddr, int oldval, int newval)
 	}
 	get_page(virt_to_page(uaddr));
 	spin_unlock(&current->mm->page_table_lock);
-	ret = __futex_atomic_cmpxchg_pt(uaddr, oldval, newval);
+	ret = __futex_atomic_cmpxchg_pt(uval, uaddr, oldval, newval);
 	put_page(virt_to_page(uaddr));
 	return ret;
 }
diff --git a/arch/s390/lib/uaccess_std.c b/arch/s390/lib/uaccess_std.c
index 07deaeee14c..bb1a7eed42c 100644
--- a/arch/s390/lib/uaccess_std.c
+++ b/arch/s390/lib/uaccess_std.c
@@ -125,9 +125,9 @@ static size_t copy_in_user_std(size_t size, void __user *to,
 	unsigned long tmp1;
 
 	asm volatile(
+		"   sacf  256\n"
 		"  "AHI"  %0,-1\n"
 		"   jo    5f\n"
-		"   sacf  256\n"
 		"   bras  %3,3f\n"
 		"0:"AHI"  %0,257\n"
 		"1: mvc   0(1,%1),0(%2)\n"
@@ -142,9 +142,8 @@ static size_t copy_in_user_std(size_t size, void __user *to,
 		"3:"AHI"  %0,-256\n"
 		"   jnm   2b\n"
 		"4: ex    %0,1b-0b(%3)\n"
-		"   sacf  0\n"
 		"5: "SLR"  %0,%0\n"
-		"6:\n"
+		"6: sacf  0\n"
 		EX_TABLE(1b,6b) EX_TABLE(2b,0b) EX_TABLE(4b,0b)
 		: "+a" (size), "+a" (to), "+a" (from), "=a" (tmp1)
 		: : "cc", "memory");
@@ -156,9 +155,9 @@ static size_t clear_user_std(size_t size, void __user *to)
 	unsigned long tmp1, tmp2;
 
 	asm volatile(
+		"   sacf  256\n"
 		"  "AHI"  %0,-1\n"
 		"   jo    5f\n"
-		"   sacf  256\n"
 		"   bras  %3,3f\n"
 		"   xc    0(1,%1),0(%1)\n"
 		"0:"AHI"  %0,257\n"
@@ -178,9 +177,8 @@ static size_t clear_user_std(size_t size, void __user *to)
 		"3:"AHI"  %0,-256\n"
 		"   jnm   2b\n"
 		"4: ex    %0,0(%3)\n"
-		"   sacf  0\n"
 		"5: "SLR"  %0,%0\n"
-		"6:\n"
+		"6: sacf  0\n"
 		EX_TABLE(1b,6b) EX_TABLE(2b,0b) EX_TABLE(4b,0b)
 		: "+a" (size), "+a" (to), "=a" (tmp1), "=a" (tmp2)
 		: : "cc", "memory");
@@ -257,7 +255,7 @@ size_t strncpy_from_user_std(size_t size, const char __user *src, char *dst)
 		: "0" (-EFAULT), "d" (oparg), "a" (uaddr),		\
 		  "m" (*uaddr) : "cc");
 
-int futex_atomic_op_std(int op, int __user *uaddr, int oparg, int *old)
+int futex_atomic_op_std(int op, u32 __user *uaddr, int oparg, int *old)
 {
 	int oldval = 0, newval, ret;
 
@@ -289,19 +287,21 @@ int futex_atomic_op_std(int op, int __user *uaddr, int oparg, int *old)
 	return ret;
 }
 
-int futex_atomic_cmpxchg_std(int __user *uaddr, int oldval, int newval)
+int futex_atomic_cmpxchg_std(u32 *uval, u32 __user *uaddr,
+			     u32 oldval, u32 newval)
 {
 	int ret;
 
 	asm volatile(
 		"   sacf 256\n"
 		"0: cs   %1,%4,0(%5)\n"
-		"1: lr   %0,%1\n"
+		"1: la   %0,0\n"
 		"2: sacf 0\n"
 		EX_TABLE(0b,2b) EX_TABLE(1b,2b)
 		: "=d" (ret), "+d" (oldval), "=m" (*uaddr)
 		: "0" (-EFAULT), "d" (newval), "a" (uaddr), "m" (*uaddr)
 		: "cc", "memory" );
+	*uval = oldval;
 	return ret;
 }
 
diff --git a/arch/s390/math-emu/Makefile b/arch/s390/math-emu/Makefile
index c8489034105..51d399549f6 100644
--- a/arch/s390/math-emu/Makefile
+++ b/arch/s390/math-emu/Makefile
@@ -4,4 +4,4 @@
 
 obj-$(CONFIG_MATHEMU) := math.o
 
-EXTRA_CFLAGS := -I$(src) -Iinclude/math-emu -w
+ccflags-y := -I$(src) -Iinclude/math-emu -w
diff --git a/arch/s390/mm/Makefile b/arch/s390/mm/Makefile
index 6fbc6f3fbdf..d98fe9004a5 100644
--- a/arch/s390/mm/Makefile
+++ b/arch/s390/mm/Makefile
@@ -6,3 +6,4 @@ obj-y	 := init.o fault.o extmem.o mmap.o vmem.o pgtable.o maccess.o \
 	    page-states.o gup.o
 obj-$(CONFIG_CMM) += cmm.o
 obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o
+obj-$(CONFIG_DEBUG_SET_MODULE_RONX) += pageattr.o
diff --git a/arch/s390/mm/pageattr.c b/arch/s390/mm/pageattr.c
new file mode 100644
index 00000000000..122ffbd08ce
--- /dev/null
+++ b/arch/s390/mm/pageattr.c
@@ -0,0 +1,55 @@
+/*
+ * Copyright IBM Corp. 2011
+ * Author(s): Jan Glauber <jang@linux.vnet.ibm.com>
+ */
+#include <linux/module.h>
+#include <linux/mm.h>
+#include <linux/hugetlb.h>
+#include <asm/pgtable.h>
+
+static void change_page_attr(unsigned long addr, int numpages,
+			     pte_t (*set) (pte_t))
+{
+	pte_t *ptep, pte;
+	pmd_t *pmdp;
+	pud_t *pudp;
+	pgd_t *pgdp;
+	int i;
+
+	for (i = 0; i < numpages; i++) {
+		pgdp = pgd_offset(&init_mm, addr);
+		pudp = pud_offset(pgdp, addr);
+		pmdp = pmd_offset(pudp, addr);
+		if (pmd_huge(*pmdp)) {
+			WARN_ON_ONCE(1);
+			continue;
+		}
+		ptep = pte_offset_kernel(pmdp, addr + i * PAGE_SIZE);
+
+		pte = *ptep;
+		pte = set(pte);
+		ptep_invalidate(&init_mm, addr + i * PAGE_SIZE, ptep);
+		*ptep = pte;
+	}
+}
+
+int set_memory_ro(unsigned long addr, int numpages)
+{
+	change_page_attr(addr, numpages, pte_wrprotect);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(set_memory_ro);
+
+int set_memory_rw(unsigned long addr, int numpages)
+{
+	change_page_attr(addr, numpages, pte_mkwrite);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(set_memory_rw);
+
+/* not possible */
+int set_memory_nx(unsigned long addr, int numpages)
+{
+	return 0;
+}
+EXPORT_SYMBOL_GPL(set_memory_nx);
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 0c719c61972..e1850c28cd6 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -336,7 +336,8 @@ void page_table_free(struct mm_struct *mm, unsigned long *table)
 	page->flags ^= bits;
 	if (page->flags & FRAG_MASK) {
 		/* Page now has some free pgtable fragments. */
-		list_move(&page->lru, &mm->context.pgtable_list);
+		if (!list_empty(&page->lru))
+			list_move(&page->lru, &mm->context.pgtable_list);
 		page = NULL;
 	} else
 		/* All fragments of the 4K page have been freed. */
diff --git a/arch/s390/oprofile/Makefile b/arch/s390/oprofile/Makefile
index 537b2d840e6..d698cddcfbd 100644
--- a/arch/s390/oprofile/Makefile
+++ b/arch/s390/oprofile/Makefile
@@ -6,4 +6,4 @@ DRIVER_OBJS = $(addprefix ../../../drivers/oprofile/, \
 		oprofilefs.o oprofile_stats.o  \
 		timer_int.o )
 
-oprofile-y				:= $(DRIVER_OBJS) init.o backtrace.o
+oprofile-y :=	$(DRIVER_OBJS) init.o backtrace.o hwsampler.o
diff --git a/arch/s390/oprofile/hwsampler.c b/arch/s390/oprofile/hwsampler.c
new file mode 100644
index 00000000000..3d48f4db246
--- /dev/null
+++ b/arch/s390/oprofile/hwsampler.c
@@ -0,0 +1,1256 @@
+/**
+ * arch/s390/oprofile/hwsampler.c
+ *
+ * Copyright IBM Corp. 2010
+ * Author: Heinz Graalfs <graalfs@de.ibm.com>
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/smp.h>
+#include <linux/errno.h>
+#include <linux/workqueue.h>
+#include <linux/interrupt.h>
+#include <linux/notifier.h>
+#include <linux/cpu.h>
+#include <linux/semaphore.h>
+#include <linux/oom.h>
+#include <linux/oprofile.h>
+
+#include <asm/lowcore.h>
+#include <asm/s390_ext.h>
+
+#include "hwsampler.h"
+
+#define MAX_NUM_SDB 511
+#define MIN_NUM_SDB 1
+
+#define ALERT_REQ_MASK   0x4000000000000000ul
+#define BUFFER_FULL_MASK 0x8000000000000000ul
+
+#define EI_IEA      (1 << 31)	/* invalid entry address              */
+#define EI_ISE      (1 << 30)	/* incorrect SDBT entry               */
+#define EI_PRA      (1 << 29)	/* program request alert              */
+#define EI_SACA     (1 << 23)	/* sampler authorization change alert */
+#define EI_LSDA     (1 << 22)	/* loss of sample data alert          */
+
+DECLARE_PER_CPU(struct hws_cpu_buffer, sampler_cpu_buffer);
+
+struct hws_execute_parms {
+	void *buffer;
+	signed int rc;
+};
+
+DEFINE_PER_CPU(struct hws_cpu_buffer, sampler_cpu_buffer);
+EXPORT_PER_CPU_SYMBOL(sampler_cpu_buffer);
+
+static DEFINE_MUTEX(hws_sem);
+static DEFINE_MUTEX(hws_sem_oom);
+
+static unsigned char hws_flush_all;
+static unsigned int hws_oom;
+static struct workqueue_struct *hws_wq;
+
+static unsigned int hws_state;
+enum {
+	HWS_INIT = 1,
+	HWS_DEALLOCATED,
+	HWS_STOPPED,
+	HWS_STARTED,
+	HWS_STOPPING };
+
+/* set to 1 if called by kernel during memory allocation */
+static unsigned char oom_killer_was_active;
+/* size of SDBT and SDB as of allocate API */
+static unsigned long num_sdbt = 100;
+static unsigned long num_sdb = 511;
+/* sampling interval (machine cycles) */
+static unsigned long interval;
+
+static unsigned long min_sampler_rate;
+static unsigned long max_sampler_rate;
+
+static int ssctl(void *buffer)
+{
+	int cc;
+
+	/* set in order to detect a program check */
+	cc = 1;
+
+	asm volatile(
+		"0: .insn s,0xB2870000,0(%1)\n"
+		"1: ipm %0\n"
+		"   srl %0,28\n"
+		"2:\n"
+		EX_TABLE(0b, 2b) EX_TABLE(1b, 2b)
+		: "+d" (cc), "+a" (buffer)
+		: "m" (*((struct hws_ssctl_request_block *)buffer))
+		: "cc", "memory");
+
+	return cc ? -EINVAL : 0 ;
+}
+
+static int qsi(void *buffer)
+{
+	int cc;
+	cc = 1;
+
+	asm volatile(
+		"0: .insn s,0xB2860000,0(%1)\n"
+		"1: lhi %0,0\n"
+		"2:\n"
+		EX_TABLE(0b, 2b) EX_TABLE(1b, 2b)
+		: "=d" (cc), "+a" (buffer)
+		: "m" (*((struct hws_qsi_info_block *)buffer))
+		: "cc", "memory");
+
+	return cc ? -EINVAL : 0;
+}
+
+static void execute_qsi(void *parms)
+{
+	struct hws_execute_parms *ep = parms;
+
+	ep->rc = qsi(ep->buffer);
+}
+
+static void execute_ssctl(void *parms)
+{
+	struct hws_execute_parms *ep = parms;
+
+	ep->rc = ssctl(ep->buffer);
+}
+
+static int smp_ctl_ssctl_stop(int cpu)
+{
+	int rc;
+	struct hws_execute_parms ep;
+	struct hws_cpu_buffer *cb;
+
+	cb = &per_cpu(sampler_cpu_buffer, cpu);
+
+	cb->ssctl.es = 0;
+	cb->ssctl.cs = 0;
+
+	ep.buffer = &cb->ssctl;
+	smp_call_function_single(cpu, execute_ssctl, &ep, 1);
+	rc = ep.rc;
+	if (rc) {
+		printk(KERN_ERR "hwsampler: CPU %d CPUMF SSCTL failed.\n", cpu);
+		dump_stack();
+	}
+
+	ep.buffer = &cb->qsi;
+	smp_call_function_single(cpu, execute_qsi, &ep, 1);
+
+	if (cb->qsi.es || cb->qsi.cs) {
+		printk(KERN_EMERG "CPUMF sampling did not stop properly.\n");
+		dump_stack();
+	}
+
+	return rc;
+}
+
+static int smp_ctl_ssctl_deactivate(int cpu)
+{
+	int rc;
+	struct hws_execute_parms ep;
+	struct hws_cpu_buffer *cb;
+
+	cb = &per_cpu(sampler_cpu_buffer, cpu);
+
+	cb->ssctl.es = 1;
+	cb->ssctl.cs = 0;
+
+	ep.buffer = &cb->ssctl;
+	smp_call_function_single(cpu, execute_ssctl, &ep, 1);
+	rc = ep.rc;
+	if (rc)
+		printk(KERN_ERR "hwsampler: CPU %d CPUMF SSCTL failed.\n", cpu);
+
+	ep.buffer = &cb->qsi;
+	smp_call_function_single(cpu, execute_qsi, &ep, 1);
+
+	if (cb->qsi.cs)
+		printk(KERN_EMERG "CPUMF sampling was not set inactive.\n");
+
+	return rc;
+}
+
+static int smp_ctl_ssctl_enable_activate(int cpu, unsigned long interval)
+{
+	int rc;
+	struct hws_execute_parms ep;
+	struct hws_cpu_buffer *cb;
+
+	cb = &per_cpu(sampler_cpu_buffer, cpu);
+
+	cb->ssctl.h = 1;
+	cb->ssctl.tear = cb->first_sdbt;
+	cb->ssctl.dear = *(unsigned long *) cb->first_sdbt;
+	cb->ssctl.interval = interval;
+	cb->ssctl.es = 1;
+	cb->ssctl.cs = 1;
+
+	ep.buffer = &cb->ssctl;
+	smp_call_function_single(cpu, execute_ssctl, &ep, 1);
+	rc = ep.rc;
+	if (rc)
+		printk(KERN_ERR "hwsampler: CPU %d CPUMF SSCTL failed.\n", cpu);
+
+	ep.buffer = &cb->qsi;
+	smp_call_function_single(cpu, execute_qsi, &ep, 1);
+	if (ep.rc)
+		printk(KERN_ERR "hwsampler: CPU %d CPUMF QSI failed.\n", cpu);
+
+	return rc;
+}
+
+static int smp_ctl_qsi(int cpu)
+{
+	struct hws_execute_parms ep;
+	struct hws_cpu_buffer *cb;
+
+	cb = &per_cpu(sampler_cpu_buffer, cpu);
+
+	ep.buffer = &cb->qsi;
+	smp_call_function_single(cpu, execute_qsi, &ep, 1);
+
+	return ep.rc;
+}
+
+static inline unsigned long *trailer_entry_ptr(unsigned long v)
+{
+	void *ret;
+
+	ret = (void *)v;
+	ret += PAGE_SIZE;
+	ret -= sizeof(struct hws_trailer_entry);
+
+	return (unsigned long *) ret;
+}
+
+/* prototypes for external interrupt handler and worker */
+static void hws_ext_handler(unsigned int ext_int_code,
+				unsigned int param32, unsigned long param64);
+
+static void worker(struct work_struct *work);
+
+static void add_samples_to_oprofile(unsigned cpu, unsigned long *,
+				unsigned long *dear);
+
+static void init_all_cpu_buffers(void)
+{
+	int cpu;
+	struct hws_cpu_buffer *cb;
+
+	for_each_online_cpu(cpu) {
+		cb = &per_cpu(sampler_cpu_buffer, cpu);
+		memset(cb, 0, sizeof(struct hws_cpu_buffer));
+	}
+}
+
+static int is_link_entry(unsigned long *s)
+{
+	return *s & 0x1ul ? 1 : 0;
+}
+
+static unsigned long *get_next_sdbt(unsigned long *s)
+{
+	return (unsigned long *) (*s & ~0x1ul);
+}
+
+static int prepare_cpu_buffers(void)
+{
+	int cpu;
+	int rc;
+	struct hws_cpu_buffer *cb;
+
+	rc = 0;
+	for_each_online_cpu(cpu) {
+		cb = &per_cpu(sampler_cpu_buffer, cpu);
+		atomic_set(&cb->ext_params, 0);
+		cb->worker_entry = 0;
+		cb->sample_overflow = 0;
+		cb->req_alert = 0;
+		cb->incorrect_sdbt_entry = 0;
+		cb->invalid_entry_address = 0;
+		cb->loss_of_sample_data = 0;
+		cb->sample_auth_change_alert = 0;
+		cb->finish = 0;
+		cb->oom = 0;
+		cb->stop_mode = 0;
+	}
+
+	return rc;
+}
+
+/*
+ * allocate_sdbt() - allocate sampler memory
+ * @cpu: the cpu for which sampler memory is allocated
+ *
+ * A 4K page is allocated for each requested SDBT.
+ * A maximum of 511 4K pages are allocated for the SDBs in each of the SDBTs.
+ * Set ALERT_REQ mask in each SDBs trailer.
+ * Returns zero if successful, <0 otherwise.
+ */
+static int allocate_sdbt(int cpu)
+{
+	int j, k, rc;
+	unsigned long *sdbt;
+	unsigned long  sdb;
+	unsigned long *tail;
+	unsigned long *trailer;
+	struct hws_cpu_buffer *cb;
+
+	cb = &per_cpu(sampler_cpu_buffer, cpu);
+
+	if (cb->first_sdbt)
+		return -EINVAL;
+
+	sdbt = NULL;
+	tail = sdbt;
+
+	for (j = 0; j < num_sdbt; j++) {
+		sdbt = (unsigned long *)get_zeroed_page(GFP_KERNEL);
+
+		mutex_lock(&hws_sem_oom);
+		/* OOM killer might have been activated */
+		barrier();
+		if (oom_killer_was_active || !sdbt) {
+			if (sdbt)
+				free_page((unsigned long)sdbt);
+
+			goto allocate_sdbt_error;
+		}
+		if (cb->first_sdbt == 0)
+			cb->first_sdbt = (unsigned long)sdbt;
+
+		/* link current page to tail of chain */
+		if (tail)
+			*tail = (unsigned long)(void *)sdbt + 1;
+
+		mutex_unlock(&hws_sem_oom);
+
+		for (k = 0; k < num_sdb; k++) {
+			/* get and set SDB page */
+			sdb = get_zeroed_page(GFP_KERNEL);
+
+			mutex_lock(&hws_sem_oom);
+			/* OOM killer might have been activated */
+			barrier();
+			if (oom_killer_was_active || !sdb) {
+				if (sdb)
+					free_page(sdb);
+
+				goto allocate_sdbt_error;
+			}
+			*sdbt = sdb;
+			trailer = trailer_entry_ptr(*sdbt);
+			*trailer = ALERT_REQ_MASK;
+			sdbt++;
+			mutex_unlock(&hws_sem_oom);
+		}
+		tail = sdbt;
+	}
+	mutex_lock(&hws_sem_oom);
+	if (oom_killer_was_active)
+		goto allocate_sdbt_error;
+
+	rc = 0;
+	if (tail)
+		*tail = (unsigned long)
+			((void *)cb->first_sdbt) + 1;
+
+allocate_sdbt_exit:
+	mutex_unlock(&hws_sem_oom);
+	return rc;
+
+allocate_sdbt_error:
+	rc = -ENOMEM;
+	goto allocate_sdbt_exit;
+}
+
+/*
+ * deallocate_sdbt() - deallocate all sampler memory
+ *
+ * For each online CPU all SDBT trees are deallocated.
+ * Returns the number of freed pages.
+ */
+static int deallocate_sdbt(void)
+{
+	int cpu;
+	int counter;
+
+	counter = 0;
+
+	for_each_online_cpu(cpu) {
+		unsigned long start;
+		unsigned long sdbt;
+		unsigned long *curr;
+		struct hws_cpu_buffer *cb;
+
+		cb = &per_cpu(sampler_cpu_buffer, cpu);
+
+		if (!cb->first_sdbt)
+			continue;
+
+		sdbt = cb->first_sdbt;
+		curr = (unsigned long *) sdbt;
+		start = sdbt;
+
+		/* we'll free the SDBT after all SDBs are processed... */
+		while (1) {
+			if (!*curr || !sdbt)
+				break;
+
+			/* watch for link entry reset if found */
+			if (is_link_entry(curr)) {
+				curr = get_next_sdbt(curr);
+				if (sdbt)
+					free_page(sdbt);
+
+				/* we are done if we reach the start */
+				if ((unsigned long) curr == start)
+					break;
+				else
+					sdbt = (unsigned long) curr;
+			} else {
+				/* process SDB pointer */
+				if (*curr) {
+					free_page(*curr);
+					curr++;
+				}
+			}
+			counter++;
+		}
+		cb->first_sdbt = 0;
+	}
+	return counter;
+}
+
+static int start_sampling(int cpu)
+{
+	int rc;
+	struct hws_cpu_buffer *cb;
+
+	cb = &per_cpu(sampler_cpu_buffer, cpu);
+	rc = smp_ctl_ssctl_enable_activate(cpu, interval);
+	if (rc) {
+		printk(KERN_INFO "hwsampler: CPU %d ssctl failed.\n", cpu);
+		goto start_exit;
+	}
+
+	rc = -EINVAL;
+	if (!cb->qsi.es) {
+		printk(KERN_INFO "hwsampler: CPU %d ssctl not enabled.\n", cpu);
+		goto start_exit;
+	}
+
+	if (!cb->qsi.cs) {
+		printk(KERN_INFO "hwsampler: CPU %d ssctl not active.\n", cpu);
+		goto start_exit;
+	}
+
+	printk(KERN_INFO
+		"hwsampler: CPU %d, CPUMF Sampling started, interval %lu.\n",
+		cpu, interval);
+
+	rc = 0;
+
+start_exit:
+	return rc;
+}
+
+static int stop_sampling(int cpu)
+{
+	unsigned long v;
+	int rc;
+	struct hws_cpu_buffer *cb;
+
+	rc = smp_ctl_qsi(cpu);
+	WARN_ON(rc);
+
+	cb = &per_cpu(sampler_cpu_buffer, cpu);
+	if (!rc && !cb->qsi.es)
+		printk(KERN_INFO "hwsampler: CPU %d, already stopped.\n", cpu);
+
+	rc = smp_ctl_ssctl_stop(cpu);
+	if (rc) {
+		printk(KERN_INFO "hwsampler: CPU %d, ssctl stop error %d.\n",
+				cpu, rc);
+		goto stop_exit;
+	}
+
+	printk(KERN_INFO "hwsampler: CPU %d, CPUMF Sampling stopped.\n", cpu);
+
+stop_exit:
+	v = cb->req_alert;
+	if (v)
+		printk(KERN_ERR "hwsampler: CPU %d CPUMF Request alert,"
+				" count=%lu.\n", cpu, v);
+
+	v = cb->loss_of_sample_data;
+	if (v)
+		printk(KERN_ERR "hwsampler: CPU %d CPUMF Loss of sample data,"
+				" count=%lu.\n", cpu, v);
+
+	v = cb->invalid_entry_address;
+	if (v)
+		printk(KERN_ERR "hwsampler: CPU %d CPUMF Invalid entry address,"
+				" count=%lu.\n", cpu, v);
+
+	v = cb->incorrect_sdbt_entry;
+	if (v)
+		printk(KERN_ERR
+				"hwsampler: CPU %d CPUMF Incorrect SDBT address,"
+				" count=%lu.\n", cpu, v);
+
+	v = cb->sample_auth_change_alert;
+	if (v)
+		printk(KERN_ERR
+				"hwsampler: CPU %d CPUMF Sample authorization change,"
+				" count=%lu.\n", cpu, v);
+
+	return rc;
+}
+
+static int check_hardware_prerequisites(void)
+{
+	unsigned long long facility_bits[2];
+
+	memcpy(facility_bits, S390_lowcore.stfle_fac_list, 32);
+	if (!(facility_bits[1] & (1ULL << 59)))
+		return -EOPNOTSUPP;
+
+	return 0;
+}
+/*
+ * hws_oom_callback() - the OOM callback function
+ *
+ * In case the callback is invoked during memory allocation for the
+ *  hw sampler, all obtained memory is deallocated and a flag is set
+ *  so main sampler memory allocation can exit with a failure code.
+ * In case the callback is invoked during sampling the hw sampler
+ *  is deactivated for all CPUs.
+ */
+static int hws_oom_callback(struct notifier_block *nfb,
+	unsigned long dummy, void *parm)
+{
+	unsigned long *freed;
+	int cpu;
+	struct hws_cpu_buffer *cb;
+
+	freed = parm;
+
+	mutex_lock(&hws_sem_oom);
+
+	if (hws_state == HWS_DEALLOCATED) {
+		/* during memory allocation */
+		if (oom_killer_was_active == 0) {
+			oom_killer_was_active = 1;
+			*freed += deallocate_sdbt();
+		}
+	} else {
+		int i;
+		cpu = get_cpu();
+		cb = &per_cpu(sampler_cpu_buffer, cpu);
+
+		if (!cb->oom) {
+			for_each_online_cpu(i) {
+				smp_ctl_ssctl_deactivate(i);
+				cb->oom = 1;
+			}
+			cb->finish = 1;
+
+			printk(KERN_INFO
+				"hwsampler: CPU %d, OOM notify during CPUMF Sampling.\n",
+				cpu);
+		}
+	}
+
+	mutex_unlock(&hws_sem_oom);
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block hws_oom_notifier = {
+	.notifier_call = hws_oom_callback
+};
+
+static int hws_cpu_callback(struct notifier_block *nfb,
+	unsigned long action, void *hcpu)
+{
+	/* We do not have sampler space available for all possible CPUs.
+	   All CPUs should be online when hw sampling is activated. */
+	return NOTIFY_BAD;
+}
+
+static struct notifier_block hws_cpu_notifier = {
+	.notifier_call = hws_cpu_callback
+};
+
+/**
+ * hwsampler_deactivate() - set hardware sampling temporarily inactive
+ * @cpu:  specifies the CPU to be set inactive.
+ *
+ * Returns 0 on success, !0 on failure.
+ */
+int hwsampler_deactivate(unsigned int cpu)
+{
+	/*
+	 * Deactivate hw sampling temporarily and flush the buffer
+	 * by pushing all the pending samples to oprofile buffer.
+	 *
+	 * This function can be called under one of the following conditions:
+	 *     Memory unmap, task is exiting.
+	 */
+	int rc;
+	struct hws_cpu_buffer *cb;
+
+	rc = 0;
+	mutex_lock(&hws_sem);
+
+	cb = &per_cpu(sampler_cpu_buffer, cpu);
+	if (hws_state == HWS_STARTED) {
+		rc = smp_ctl_qsi(cpu);
+		WARN_ON(rc);
+		if (cb->qsi.cs) {
+			rc = smp_ctl_ssctl_deactivate(cpu);
+			if (rc) {
+				printk(KERN_INFO
+				"hwsampler: CPU %d, CPUMF Deactivation failed.\n", cpu);
+				cb->finish = 1;
+				hws_state = HWS_STOPPING;
+			} else  {
+				hws_flush_all = 1;
+				/* Add work to queue to read pending samples.*/
+				queue_work_on(cpu, hws_wq, &cb->worker);
+			}
+		}
+	}
+	mutex_unlock(&hws_sem);
+
+	if (hws_wq)
+		flush_workqueue(hws_wq);
+
+	return rc;
+}
+
+/**
+ * hwsampler_activate() - activate/resume hardware sampling which was deactivated
+ * @cpu:  specifies the CPU to be set active.
+ *
+ * Returns 0 on success, !0 on failure.
+ */
+int hwsampler_activate(unsigned int cpu)
+{
+	/*
+	 * Re-activate hw sampling. This should be called in pair with
+	 * hwsampler_deactivate().
+	 */
+	int rc;
+	struct hws_cpu_buffer *cb;
+
+	rc = 0;
+	mutex_lock(&hws_sem);
+
+	cb = &per_cpu(sampler_cpu_buffer, cpu);
+	if (hws_state == HWS_STARTED) {
+		rc = smp_ctl_qsi(cpu);
+		WARN_ON(rc);
+		if (!cb->qsi.cs) {
+			hws_flush_all = 0;
+			rc = smp_ctl_ssctl_enable_activate(cpu, interval);
+			if (rc) {
+				printk(KERN_ERR
+				"CPU %d, CPUMF activate sampling failed.\n",
+					 cpu);
+			}
+		}
+	}
+
+	mutex_unlock(&hws_sem);
+
+	return rc;
+}
+
+static void hws_ext_handler(unsigned int ext_int_code,
+			    unsigned int param32, unsigned long param64)
+{
+	int cpu;
+	struct hws_cpu_buffer *cb;
+
+	cpu = smp_processor_id();
+	cb = &per_cpu(sampler_cpu_buffer, cpu);
+
+	atomic_xchg(
+			&cb->ext_params,
+			atomic_read(&cb->ext_params)
+				| S390_lowcore.ext_params);
+
+	if (hws_wq)
+		queue_work(hws_wq, &cb->worker);
+}
+
+static int check_qsi_on_setup(void)
+{
+	int rc;
+	unsigned int cpu;
+	struct hws_cpu_buffer *cb;
+
+	for_each_online_cpu(cpu) {
+		cb = &per_cpu(sampler_cpu_buffer, cpu);
+		rc = smp_ctl_qsi(cpu);
+		WARN_ON(rc);
+		if (rc)
+			return -EOPNOTSUPP;
+
+		if (!cb->qsi.as) {
+			printk(KERN_INFO "hwsampler: CPUMF sampling is not authorized.\n");
+			return -EINVAL;
+		}
+
+		if (cb->qsi.es) {
+			printk(KERN_WARNING "hwsampler: CPUMF is still enabled.\n");
+			rc = smp_ctl_ssctl_stop(cpu);
+			if (rc)
+				return -EINVAL;
+
+			printk(KERN_INFO
+				"CPU %d, CPUMF Sampling stopped now.\n", cpu);
+		}
+	}
+	return 0;
+}
+
+static int check_qsi_on_start(void)
+{
+	unsigned int cpu;
+	int rc;
+	struct hws_cpu_buffer *cb;
+
+	for_each_online_cpu(cpu) {
+		cb = &per_cpu(sampler_cpu_buffer, cpu);
+		rc = smp_ctl_qsi(cpu);
+		WARN_ON(rc);
+
+		if (!cb->qsi.as)
+			return -EINVAL;
+
+		if (cb->qsi.es)
+			return -EINVAL;
+
+		if (cb->qsi.cs)
+			return -EINVAL;
+	}
+	return 0;
+}
+
+static void worker_on_start(unsigned int cpu)
+{
+	struct hws_cpu_buffer *cb;
+
+	cb = &per_cpu(sampler_cpu_buffer, cpu);
+	cb->worker_entry = cb->first_sdbt;
+}
+
+static int worker_check_error(unsigned int cpu, int ext_params)
+{
+	int rc;
+	unsigned long *sdbt;
+	struct hws_cpu_buffer *cb;
+
+	rc = 0;
+	cb = &per_cpu(sampler_cpu_buffer, cpu);
+	sdbt = (unsigned long *) cb->worker_entry;
+
+	if (!sdbt || !*sdbt)
+		return -EINVAL;
+
+	if (ext_params & EI_IEA)
+		cb->req_alert++;
+
+	if (ext_params & EI_LSDA)
+		cb->loss_of_sample_data++;
+
+	if (ext_params & EI_IEA) {
+		cb->invalid_entry_address++;
+		rc = -EINVAL;
+	}
+
+	if (ext_params & EI_ISE) {
+		cb->incorrect_sdbt_entry++;
+		rc = -EINVAL;
+	}
+
+	if (ext_params & EI_SACA) {
+		cb->sample_auth_change_alert++;
+		rc = -EINVAL;
+	}
+
+	return rc;
+}
+
+static void worker_on_finish(unsigned int cpu)
+{
+	int rc, i;
+	struct hws_cpu_buffer *cb;
+
+	cb = &per_cpu(sampler_cpu_buffer, cpu);
+
+	if (cb->finish) {
+		rc = smp_ctl_qsi(cpu);
+		WARN_ON(rc);
+		if (cb->qsi.es) {
+			printk(KERN_INFO
+				"hwsampler: CPU %d, CPUMF Stop/Deactivate sampling.\n",
+				cpu);
+			rc = smp_ctl_ssctl_stop(cpu);
+			if (rc)
+				printk(KERN_INFO
+					"hwsampler: CPU %d, CPUMF Deactivation failed.\n",
+					cpu);
+
+			for_each_online_cpu(i) {
+				if (i == cpu)
+					continue;
+				if (!cb->finish) {
+					cb->finish = 1;
+					queue_work_on(i, hws_wq,
+						&cb->worker);
+				}
+			}
+		}
+	}
+}
+
+static void worker_on_interrupt(unsigned int cpu)
+{
+	unsigned long *sdbt;
+	unsigned char done;
+	struct hws_cpu_buffer *cb;
+
+	cb = &per_cpu(sampler_cpu_buffer, cpu);
+
+	sdbt = (unsigned long *) cb->worker_entry;
+
+	done = 0;
+	/* do not proceed if stop was entered,
+	 * forget the buffers not yet processed */
+	while (!done && !cb->stop_mode) {
+		unsigned long *trailer;
+		struct hws_trailer_entry *te;
+		unsigned long *dear = 0;
+
+		trailer = trailer_entry_ptr(*sdbt);
+		/* leave loop if no more work to do */
+		if (!(*trailer & BUFFER_FULL_MASK)) {
+			done = 1;
+			if (!hws_flush_all)
+				continue;
+		}
+
+		te = (struct hws_trailer_entry *)trailer;
+		cb->sample_overflow += te->overflow;
+
+		add_samples_to_oprofile(cpu, sdbt, dear);
+
+		/* reset trailer */
+		xchg((unsigned char *) te, 0x40);
+
+		/* advance to next sdb slot in current sdbt */
+		sdbt++;
+		/* in case link bit is set use address w/o link bit */
+		if (is_link_entry(sdbt))
+			sdbt = get_next_sdbt(sdbt);
+
+		cb->worker_entry = (unsigned long)sdbt;
+	}
+}
+
+static void add_samples_to_oprofile(unsigned int cpu, unsigned long *sdbt,
+		unsigned long *dear)
+{
+	struct hws_data_entry *sample_data_ptr;
+	unsigned long *trailer;
+
+	trailer = trailer_entry_ptr(*sdbt);
+	if (dear) {
+		if (dear > trailer)
+			return;
+		trailer = dear;
+	}
+
+	sample_data_ptr = (struct hws_data_entry *)(*sdbt);
+
+	while ((unsigned long *)sample_data_ptr < trailer) {
+		struct pt_regs *regs = NULL;
+		struct task_struct *tsk = NULL;
+
+		/*
+		 * Check sampling mode, 1 indicates basic (=customer) sampling
+		 * mode.
+		 */
+		if (sample_data_ptr->def != 1) {
+			/* sample slot is not yet written */
+			break;
+		} else {
+			/* make sure we don't use it twice,
+			 * the next time the sampler will set it again */
+			sample_data_ptr->def = 0;
+		}
+
+		/* Get pt_regs. */
+		if (sample_data_ptr->P == 1) {
+			/* userspace sample */
+			unsigned int pid = sample_data_ptr->prim_asn;
+			rcu_read_lock();
+			tsk = pid_task(find_vpid(pid), PIDTYPE_PID);
+			if (tsk)
+				regs = task_pt_regs(tsk);
+			rcu_read_unlock();
+		} else {
+			/* kernelspace sample */
+			regs = task_pt_regs(current);
+		}
+
+		mutex_lock(&hws_sem);
+		oprofile_add_ext_hw_sample(sample_data_ptr->ia, regs, 0,
+				!sample_data_ptr->P, tsk);
+		mutex_unlock(&hws_sem);
+
+		sample_data_ptr++;
+	}
+}
+
+static void worker(struct work_struct *work)
+{
+	unsigned int cpu;
+	int ext_params;
+	struct hws_cpu_buffer *cb;
+
+	cb = container_of(work, struct hws_cpu_buffer, worker);
+	cpu = smp_processor_id();
+	ext_params = atomic_xchg(&cb->ext_params, 0);
+
+	if (!cb->worker_entry)
+		worker_on_start(cpu);
+
+	if (worker_check_error(cpu, ext_params))
+		return;
+
+	if (!cb->finish)
+		worker_on_interrupt(cpu);
+
+	if (cb->finish)
+		worker_on_finish(cpu);
+}
+
+/**
+ * hwsampler_allocate() - allocate memory for the hardware sampler
+ * @sdbt:  number of SDBTs per online CPU (must be > 0)
+ * @sdb:   number of SDBs per SDBT (minimum 1, maximum 511)
+ *
+ * Returns 0 on success, !0 on failure.
+ */
+int hwsampler_allocate(unsigned long sdbt, unsigned long sdb)
+{
+	int cpu, rc;
+	mutex_lock(&hws_sem);
+
+	rc = -EINVAL;
+	if (hws_state != HWS_DEALLOCATED)
+		goto allocate_exit;
+
+	if (sdbt < 1)
+		goto allocate_exit;
+
+	if (sdb > MAX_NUM_SDB || sdb < MIN_NUM_SDB)
+		goto allocate_exit;
+
+	num_sdbt = sdbt;
+	num_sdb = sdb;
+
+	oom_killer_was_active = 0;
+	register_oom_notifier(&hws_oom_notifier);
+
+	for_each_online_cpu(cpu) {
+		if (allocate_sdbt(cpu)) {
+			unregister_oom_notifier(&hws_oom_notifier);
+			goto allocate_error;
+		}
+	}
+	unregister_oom_notifier(&hws_oom_notifier);
+	if (oom_killer_was_active)
+		goto allocate_error;
+
+	hws_state = HWS_STOPPED;
+	rc = 0;
+
+allocate_exit:
+	mutex_unlock(&hws_sem);
+	return rc;
+
+allocate_error:
+	rc = -ENOMEM;
+	printk(KERN_ERR "hwsampler: CPUMF Memory allocation failed.\n");
+	goto allocate_exit;
+}
+
+/**
+ * hwsampler_deallocate() - deallocate hardware sampler memory
+ *
+ * Returns 0 on success, !0 on failure.
+ */
+int hwsampler_deallocate()
+{
+	int rc;
+
+	mutex_lock(&hws_sem);
+
+	rc = -EINVAL;
+	if (hws_state != HWS_STOPPED)
+		goto deallocate_exit;
+
+	smp_ctl_clear_bit(0, 5); /* set bit 58 CR0 off */
+	deallocate_sdbt();
+
+	hws_state = HWS_DEALLOCATED;
+	rc = 0;
+
+deallocate_exit:
+	mutex_unlock(&hws_sem);
+
+	return rc;
+}
+
+long hwsampler_query_min_interval(void)
+{
+	if (min_sampler_rate)
+		return min_sampler_rate;
+	else
+		return -EINVAL;
+}
+
+long hwsampler_query_max_interval(void)
+{
+	if (max_sampler_rate)
+		return max_sampler_rate;
+	else
+		return -EINVAL;
+}
+
+unsigned long hwsampler_get_sample_overflow_count(unsigned int cpu)
+{
+	struct hws_cpu_buffer *cb;
+
+	cb = &per_cpu(sampler_cpu_buffer, cpu);
+
+	return cb->sample_overflow;
+}
+
+int hwsampler_setup()
+{
+	int rc;
+	int cpu;
+	struct hws_cpu_buffer *cb;
+
+	mutex_lock(&hws_sem);
+
+	rc = -EINVAL;
+	if (hws_state)
+		goto setup_exit;
+
+	hws_state = HWS_INIT;
+
+	init_all_cpu_buffers();
+
+	rc = check_hardware_prerequisites();
+	if (rc)
+		goto setup_exit;
+
+	rc = check_qsi_on_setup();
+	if (rc)
+		goto setup_exit;
+
+	rc = -EINVAL;
+	hws_wq = create_workqueue("hwsampler");
+	if (!hws_wq)
+		goto setup_exit;
+
+	register_cpu_notifier(&hws_cpu_notifier);
+
+	for_each_online_cpu(cpu) {
+		cb = &per_cpu(sampler_cpu_buffer, cpu);
+		INIT_WORK(&cb->worker, worker);
+		rc = smp_ctl_qsi(cpu);
+		WARN_ON(rc);
+		if (min_sampler_rate != cb->qsi.min_sampl_rate) {
+			if (min_sampler_rate) {
+				printk(KERN_WARNING
+					"hwsampler: different min sampler rate values.\n");
+				if (min_sampler_rate < cb->qsi.min_sampl_rate)
+					min_sampler_rate =
+						cb->qsi.min_sampl_rate;
+			} else
+				min_sampler_rate = cb->qsi.min_sampl_rate;
+		}
+		if (max_sampler_rate != cb->qsi.max_sampl_rate) {
+			if (max_sampler_rate) {
+				printk(KERN_WARNING
+					"hwsampler: different max sampler rate values.\n");
+				if (max_sampler_rate > cb->qsi.max_sampl_rate)
+					max_sampler_rate =
+						cb->qsi.max_sampl_rate;
+			} else
+				max_sampler_rate = cb->qsi.max_sampl_rate;
+		}
+	}
+	register_external_interrupt(0x1407, hws_ext_handler);
+
+	hws_state = HWS_DEALLOCATED;
+	rc = 0;
+
+setup_exit:
+	mutex_unlock(&hws_sem);
+	return rc;
+}
+
+int hwsampler_shutdown()
+{
+	int rc;
+
+	mutex_lock(&hws_sem);
+
+	rc = -EINVAL;
+	if (hws_state == HWS_DEALLOCATED || hws_state == HWS_STOPPED) {
+		mutex_unlock(&hws_sem);
+
+		if (hws_wq)
+			flush_workqueue(hws_wq);
+
+		mutex_lock(&hws_sem);
+
+		if (hws_state == HWS_STOPPED) {
+			smp_ctl_clear_bit(0, 5); /* set bit 58 CR0 off */
+			deallocate_sdbt();
+		}
+		if (hws_wq) {
+			destroy_workqueue(hws_wq);
+			hws_wq = NULL;
+		}
+
+		unregister_external_interrupt(0x1407, hws_ext_handler);
+		hws_state = HWS_INIT;
+		rc = 0;
+	}
+	mutex_unlock(&hws_sem);
+
+	unregister_cpu_notifier(&hws_cpu_notifier);
+
+	return rc;
+}
+
+/**
+ * hwsampler_start_all() - start hardware sampling on all online CPUs
+ * @rate:  specifies the used interval when samples are taken
+ *
+ * Returns 0 on success, !0 on failure.
+ */
+int hwsampler_start_all(unsigned long rate)
+{
+	int rc, cpu;
+
+	mutex_lock(&hws_sem);
+
+	hws_oom = 0;
+
+	rc = -EINVAL;
+	if (hws_state != HWS_STOPPED)
+		goto start_all_exit;
+
+	interval = rate;
+
+	/* fail if rate is not valid */
+	if (interval < min_sampler_rate || interval > max_sampler_rate)
+		goto start_all_exit;
+
+	rc = check_qsi_on_start();
+	if (rc)
+		goto start_all_exit;
+
+	rc = prepare_cpu_buffers();
+	if (rc)
+		goto start_all_exit;
+
+	for_each_online_cpu(cpu) {
+		rc = start_sampling(cpu);
+		if (rc)
+			break;
+	}
+	if (rc) {
+		for_each_online_cpu(cpu) {
+			stop_sampling(cpu);
+		}
+		goto start_all_exit;
+	}
+	hws_state = HWS_STARTED;
+	rc = 0;
+
+start_all_exit:
+	mutex_unlock(&hws_sem);
+
+	if (rc)
+		return rc;
+
+	register_oom_notifier(&hws_oom_notifier);
+	hws_oom = 1;
+	hws_flush_all = 0;
+	/* now let them in, 1407 CPUMF external interrupts */
+	smp_ctl_set_bit(0, 5); /* set CR0 bit 58 */
+
+	return 0;
+}
+
+/**
+ * hwsampler_stop_all() - stop hardware sampling on all online CPUs
+ *
+ * Returns 0 on success, !0 on failure.
+ */
+int hwsampler_stop_all()
+{
+	int tmp_rc, rc, cpu;
+	struct hws_cpu_buffer *cb;
+
+	mutex_lock(&hws_sem);
+
+	rc = 0;
+	if (hws_state == HWS_INIT) {
+		mutex_unlock(&hws_sem);
+		return rc;
+	}
+	hws_state = HWS_STOPPING;
+	mutex_unlock(&hws_sem);
+
+	for_each_online_cpu(cpu) {
+		cb = &per_cpu(sampler_cpu_buffer, cpu);
+		cb->stop_mode = 1;
+		tmp_rc = stop_sampling(cpu);
+		if (tmp_rc)
+			rc = tmp_rc;
+	}
+
+	if (hws_wq)
+		flush_workqueue(hws_wq);
+
+	mutex_lock(&hws_sem);
+	if (hws_oom) {
+		unregister_oom_notifier(&hws_oom_notifier);
+		hws_oom = 0;
+	}
+	hws_state = HWS_STOPPED;
+	mutex_unlock(&hws_sem);
+
+	return rc;
+}
diff --git a/arch/s390/oprofile/hwsampler.h b/arch/s390/oprofile/hwsampler.h
new file mode 100644
index 00000000000..8c72b59316b
--- /dev/null
+++ b/arch/s390/oprofile/hwsampler.h
@@ -0,0 +1,113 @@
+/*
+ * CPUMF HW sampler functions and internal structures
+ *
+ *    Copyright IBM Corp. 2010
+ *    Author(s): Heinz Graalfs <graalfs@de.ibm.com>
+ */
+
+#ifndef HWSAMPLER_H_
+#define HWSAMPLER_H_
+
+#include <linux/workqueue.h>
+
+struct hws_qsi_info_block          /* QUERY SAMPLING information block  */
+{ /* Bit(s) */
+	unsigned int b0_13:14;      /* 0-13: zeros                       */
+	unsigned int as:1;          /* 14: sampling authorisation control*/
+	unsigned int b15_21:7;      /* 15-21: zeros                      */
+	unsigned int es:1;          /* 22: sampling enable control       */
+	unsigned int b23_29:7;      /* 23-29: zeros                      */
+	unsigned int cs:1;          /* 30: sampling activation control   */
+	unsigned int:1;             /* 31: reserved                      */
+	unsigned int bsdes:16;      /* 4-5: size of sampling entry       */
+	unsigned int:16;            /* 6-7: reserved                     */
+	unsigned long min_sampl_rate; /* 8-15: minimum sampling interval */
+	unsigned long max_sampl_rate; /* 16-23: maximum sampling interval*/
+	unsigned long tear;         /* 24-31: TEAR contents              */
+	unsigned long dear;         /* 32-39: DEAR contents              */
+	unsigned int rsvrd0;        /* 40-43: reserved                   */
+	unsigned int cpu_speed;     /* 44-47: CPU speed                  */
+	unsigned long long rsvrd1;  /* 48-55: reserved                   */
+	unsigned long long rsvrd2;  /* 56-63: reserved                   */
+};
+
+struct hws_ssctl_request_block     /* SET SAMPLING CONTROLS req block   */
+{ /* bytes 0 - 7  Bit(s) */
+	unsigned int s:1;           /* 0: maximum buffer indicator       */
+	unsigned int h:1;           /* 1: part. level reserved for VM use*/
+	unsigned long b2_53:52;     /* 2-53: zeros                       */
+	unsigned int es:1;          /* 54: sampling enable control       */
+	unsigned int b55_61:7;      /* 55-61: - zeros                    */
+	unsigned int cs:1;          /* 62: sampling activation control   */
+	unsigned int b63:1;         /* 63: zero                          */
+	unsigned long interval;     /* 8-15: sampling interval           */
+	unsigned long tear;         /* 16-23: TEAR contents              */
+	unsigned long dear;         /* 24-31: DEAR contents              */
+	/* 32-63:                                                        */
+	unsigned long rsvrd1;       /* reserved                          */
+	unsigned long rsvrd2;       /* reserved                          */
+	unsigned long rsvrd3;       /* reserved                          */
+	unsigned long rsvrd4;       /* reserved                          */
+};
+
+struct hws_cpu_buffer {
+	unsigned long first_sdbt;       /* @ of 1st SDB-Table for this CP*/
+	unsigned long worker_entry;
+	unsigned long sample_overflow;  /* taken from SDB ...            */
+	struct hws_qsi_info_block qsi;
+	struct hws_ssctl_request_block ssctl;
+	struct work_struct worker;
+	atomic_t ext_params;
+	unsigned long req_alert;
+	unsigned long loss_of_sample_data;
+	unsigned long invalid_entry_address;
+	unsigned long incorrect_sdbt_entry;
+	unsigned long sample_auth_change_alert;
+	unsigned int finish:1;
+	unsigned int oom:1;
+	unsigned int stop_mode:1;
+};
+
+struct hws_data_entry {
+	unsigned int def:16;        /* 0-15  Data Entry Format           */
+	unsigned int R:4;           /* 16-19 reserved                    */
+	unsigned int U:4;           /* 20-23 Number of unique instruct.  */
+	unsigned int z:2;           /* zeros                             */
+	unsigned int T:1;           /* 26 PSW DAT mode                   */
+	unsigned int W:1;           /* 27 PSW wait state                 */
+	unsigned int P:1;           /* 28 PSW Problem state              */
+	unsigned int AS:2;          /* 29-30 PSW address-space control   */
+	unsigned int I:1;           /* 31 entry valid or invalid         */
+	unsigned int:16;
+	unsigned int prim_asn:16;   /* primary ASN                       */
+	unsigned long long ia;      /* Instruction Address               */
+	unsigned long long lpp;     /* Logical-Partition Program Param.  */
+	unsigned long long vpp;     /* Virtual-Machine Program Param.    */
+};
+
+struct hws_trailer_entry {
+	unsigned int f:1;           /* 0 - Block Full Indicator          */
+	unsigned int a:1;           /* 1 - Alert request control         */
+	unsigned long:62;           /* 2 - 63: Reserved                  */
+	unsigned long overflow;     /* 64 - sample Overflow count        */
+	unsigned long timestamp;    /* 16 - time-stamp                   */
+	unsigned long timestamp1;   /*                                   */
+	unsigned long reserved1;    /* 32 -Reserved                      */
+	unsigned long reserved2;    /*                                   */
+	unsigned long progusage1;   /* 48 - reserved for programming use */
+	unsigned long progusage2;   /*                                   */
+};
+
+int hwsampler_setup(void);
+int hwsampler_shutdown(void);
+int hwsampler_allocate(unsigned long sdbt, unsigned long sdb);
+int hwsampler_deallocate(void);
+long hwsampler_query_min_interval(void);
+long hwsampler_query_max_interval(void);
+int hwsampler_start_all(unsigned long interval);
+int hwsampler_stop_all(void);
+int hwsampler_deactivate(unsigned int cpu);
+int hwsampler_activate(unsigned int cpu);
+unsigned long hwsampler_get_sample_overflow_count(unsigned int cpu);
+
+#endif /*HWSAMPLER_H_*/
diff --git a/arch/s390/oprofile/init.c b/arch/s390/oprofile/init.c
index 7a995113b91..16c76def4a9 100644
--- a/arch/s390/oprofile/init.c
+++ b/arch/s390/oprofile/init.c
@@ -4,23 +4,182 @@
  * S390 Version
  *   Copyright (C) 2003 IBM Deutschland Entwicklung GmbH, IBM Corporation
  *   Author(s): Thomas Spatzier (tspat@de.ibm.com)
+ *   Author(s): Mahesh Salgaonkar (mahesh@linux.vnet.ibm.com)
+ *   Author(s): Heinz Graalfs (graalfs@linux.vnet.ibm.com)
  *
- * @remark Copyright 2002 OProfile authors
+ * @remark Copyright 2002-2011 OProfile authors
  */
 
 #include <linux/oprofile.h>
 #include <linux/init.h>
 #include <linux/errno.h>
+#include <linux/oprofile.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+
+#include "../../../drivers/oprofile/oprof.h"
+#include "hwsampler.h"
+
+#define DEFAULT_INTERVAL	4096
+
+#define DEFAULT_SDBT_BLOCKS	1
+#define DEFAULT_SDB_BLOCKS	511
+
+static unsigned long oprofile_hw_interval = DEFAULT_INTERVAL;
+static unsigned long oprofile_min_interval;
+static unsigned long oprofile_max_interval;
+
+static unsigned long oprofile_sdbt_blocks = DEFAULT_SDBT_BLOCKS;
+static unsigned long oprofile_sdb_blocks = DEFAULT_SDB_BLOCKS;
 
+static int hwsampler_file;
+static int hwsampler_running;	/* start_mutex must be held to change */
+
+static struct oprofile_operations timer_ops;
 
 extern void s390_backtrace(struct pt_regs * const regs, unsigned int depth);
 
-int __init oprofile_arch_init(struct oprofile_operations* ops)
+static int oprofile_hwsampler_start(void)
+{
+	int retval;
+
+	hwsampler_running = hwsampler_file;
+
+	if (!hwsampler_running)
+		return timer_ops.start();
+
+	retval = hwsampler_allocate(oprofile_sdbt_blocks, oprofile_sdb_blocks);
+	if (retval)
+		return retval;
+
+	retval = hwsampler_start_all(oprofile_hw_interval);
+	if (retval)
+		hwsampler_deallocate();
+
+	return retval;
+}
+
+static void oprofile_hwsampler_stop(void)
+{
+	if (!hwsampler_running) {
+		timer_ops.stop();
+		return;
+	}
+
+	hwsampler_stop_all();
+	hwsampler_deallocate();
+	return;
+}
+
+static ssize_t hwsampler_read(struct file *file, char __user *buf,
+		size_t count, loff_t *offset)
+{
+	return oprofilefs_ulong_to_user(hwsampler_file, buf, count, offset);
+}
+
+static ssize_t hwsampler_write(struct file *file, char const __user *buf,
+		size_t count, loff_t *offset)
+{
+	unsigned long val;
+	int retval;
+
+	if (*offset)
+		return -EINVAL;
+
+	retval = oprofilefs_ulong_from_user(&val, buf, count);
+	if (retval)
+		return retval;
+
+	if (oprofile_started)
+		/*
+		 * save to do without locking as we set
+		 * hwsampler_running in start() when start_mutex is
+		 * held
+		 */
+		return -EBUSY;
+
+	hwsampler_file = val;
+
+	return count;
+}
+
+static const struct file_operations hwsampler_fops = {
+	.read		= hwsampler_read,
+	.write		= hwsampler_write,
+};
+
+static int oprofile_create_hwsampling_files(struct super_block *sb,
+						struct dentry *root)
+{
+	struct dentry *hw_dir;
+
+	/* reinitialize default values */
+	hwsampler_file = 1;
+
+	hw_dir = oprofilefs_mkdir(sb, root, "hwsampling");
+	if (!hw_dir)
+		return -EINVAL;
+
+	oprofilefs_create_file(sb, hw_dir, "hwsampler", &hwsampler_fops);
+	oprofilefs_create_ulong(sb, hw_dir, "hw_interval",
+				&oprofile_hw_interval);
+	oprofilefs_create_ro_ulong(sb, hw_dir, "hw_min_interval",
+				&oprofile_min_interval);
+	oprofilefs_create_ro_ulong(sb, hw_dir, "hw_max_interval",
+				&oprofile_max_interval);
+	oprofilefs_create_ulong(sb, hw_dir, "hw_sdbt_blocks",
+				&oprofile_sdbt_blocks);
+
+	return 0;
+}
+
+static int oprofile_hwsampler_init(struct oprofile_operations *ops)
+{
+	if (hwsampler_setup())
+		return -ENODEV;
+
+	/*
+	 * create hwsampler files only if hwsampler_setup() succeeds.
+	 */
+	oprofile_min_interval = hwsampler_query_min_interval();
+	if (oprofile_min_interval < 0) {
+		oprofile_min_interval = 0;
+		return -ENODEV;
+	}
+	oprofile_max_interval = hwsampler_query_max_interval();
+	if (oprofile_max_interval < 0) {
+		oprofile_max_interval = 0;
+		return -ENODEV;
+	}
+
+	if (oprofile_timer_init(ops))
+		return -ENODEV;
+
+	printk(KERN_INFO "oprofile: using hardware sampling\n");
+
+	memcpy(&timer_ops, ops, sizeof(timer_ops));
+
+	ops->start = oprofile_hwsampler_start;
+	ops->stop = oprofile_hwsampler_stop;
+	ops->create_files = oprofile_create_hwsampling_files;
+
+	return 0;
+}
+
+static void oprofile_hwsampler_exit(void)
+{
+	oprofile_timer_exit();
+	hwsampler_shutdown();
+}
+
+int __init oprofile_arch_init(struct oprofile_operations *ops)
 {
 	ops->backtrace = s390_backtrace;
-	return -ENODEV;
+
+	return oprofile_hwsampler_init(ops);
 }
 
 void oprofile_arch_exit(void)
 {
+	oprofile_hwsampler_exit();
 }