s390/bitops: use generic find bit functions / reimplement _left variant

Just like all other architectures we should use out-of-line find bit
operations, since the inline variant bloat the size of the kernel image.
And also like all other architecures we should only supply optimized
variants of the __ffs, ffs, etc. primitives.

Therefore this patch removes the inlined s390 find bit functions and uses
the generic out-of-line variants instead.

The optimization of the primitives follows with the next patch.

With this patch also the functions find_first_bit_left() and
find_next_bit_left() have been reimplemented, since logically, they are
nothing else but a find_first_bit()/find_next_bit() implementation that
use an inverted __fls() instead of __ffs().
Also the restriction that these functions only work on machines which
support the "flogr" instruction is gone now.

This reduces the size of the kernel image (defconfig, -march=z9-109)
by 144,482 bytes.
Alone the size of the function build_sched_domains() gets reduced from
7 KB to 3,5 KB.

We also git rid of unused functions like find_first_bit_le()...

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

6 files changed, 126 insertions, 604 deletions

diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 7143793..a02177f 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -99,6 +99,7 @@ config S390
 	select CLONE_BACKWARDS2
 	select GENERIC_CLOCKEVENTS
 	select GENERIC_CPU_DEVICES if !SMP
+	select GENERIC_FIND_FIRST_BIT
 	select GENERIC_SMP_IDLE_THREAD
 	select GENERIC_TIME_VSYSCALL_OLD
 	select HAVE_ALIGNED_STRUCT_PAGE if SLUB
diff --git a/arch/s390/include/asm/bitops.h b/arch/s390/include/asm/bitops.h
index 16df62d..e5ca859 100644
--- a/arch/s390/include/asm/bitops.h
+++ b/arch/s390/include/asm/bitops.h
@@ -1,10 +1,40 @@
 /*
- *  S390 version
- *    Copyright IBM Corp. 1999
- *    Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com)
+ *    Copyright IBM Corp. 1999,2013
  *
- *  Derived from "include/asm-i386/bitops.h"
- *    Copyright (C) 1992, Linus Torvalds
+ *    Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>,
+ *
+ * The description below was taken in large parts from the powerpc
+ * bitops header file:
+ * Within a word, bits are numbered LSB first.  Lot's of places make
+ * this assumption by directly testing bits with (val & (1<<nr)).
+ * This can cause confusion for large (> 1 word) bitmaps on a
+ * big-endian system because, unlike little endian, the number of each
+ * bit depends on the word size.
+ *
+ * The bitop functions are defined to work on unsigned longs, so for an
+ * s390x system the bits end up numbered:
+ *   |63..............0|127............64|191...........128|255...........196|
+ * and on s390:
+ *   |31.....0|63....31|95....64|127...96|159..128|191..160|223..192|255..224|
+ *
+ * There are a few little-endian macros used mostly for filesystem
+ * bitmaps, these work on similar bit arrays layouts, but
+ * byte-oriented:
+ *   |7...0|15...8|23...16|31...24|39...32|47...40|55...48|63...56|
+ *
+ * The main difference is that bit 3-5 (64b) or 3-4 (32b) in the bit
+ * number field needs to be reversed compared to the big-endian bit
+ * fields. This can be achieved by XOR with 0x38 (64b) or 0x18 (32b).
+ *
+ * We also have special functions which work with an MSB0 encoding:
+ * on an s390x system the bits are numbered:
+ *   |0..............63|64............127|128...........191|192...........255|
+ * and on s390:
+ *   |0.....31|31....63|64....95|96...127|128..159|160..191|192..223|224..255|
+ *
+ * The main difference is that bit 0-63 (64b) or 0-31 (32b) in the bit
+ * number field needs to be reversed compared to the LSB0 encoded bit
+ * fields. This can be achieved by XOR with 0x3f (64b) or 0x1f (32b).
  *
  */
 
@@ -18,46 +48,6 @@
 #include <linux/typecheck.h>
 #include <linux/compiler.h>
 
-/*
- * 32 bit bitops format:
- * bit 0 is the LSB of *addr; bit 31 is the MSB of *addr;
- * bit 32 is the LSB of *(addr+4). That combined with the
- * big endian byte order on S390 give the following bit
- * order in memory:
- *    1f 1e 1d 1c 1b 1a 19 18 17 16 15 14 13 12 11 10 \
- *    0f 0e 0d 0c 0b 0a 09 08 07 06 05 04 03 02 01 00
- * after that follows the next long with bit numbers
- *    3f 3e 3d 3c 3b 3a 39 38 37 36 35 34 33 32 31 30
- *    2f 2e 2d 2c 2b 2a 29 28 27 26 25 24 23 22 21 20
- * The reason for this bit ordering is the fact that
- * in the architecture independent code bits operations
- * of the form "flags |= (1 << bitnr)" are used INTERMIXED
- * with operation of the form "set_bit(bitnr, flags)".
- *
- * 64 bit bitops format:
- * bit 0 is the LSB of *addr; bit 63 is the MSB of *addr;
- * bit 64 is the LSB of *(addr+8). That combined with the
- * big endian byte order on S390 give the following bit
- * order in memory:
- *    3f 3e 3d 3c 3b 3a 39 38 37 36 35 34 33 32 31 30
- *    2f 2e 2d 2c 2b 2a 29 28 27 26 25 24 23 22 21 20
- *    1f 1e 1d 1c 1b 1a 19 18 17 16 15 14 13 12 11 10
- *    0f 0e 0d 0c 0b 0a 09 08 07 06 05 04 03 02 01 00
- * after that follows the next long with bit numbers
- *    7f 7e 7d 7c 7b 7a 79 78 77 76 75 74 73 72 71 70
- *    6f 6e 6d 6c 6b 6a 69 68 67 66 65 64 63 62 61 60
- *    5f 5e 5d 5c 5b 5a 59 58 57 56 55 54 53 52 51 50
- *    4f 4e 4d 4c 4b 4a 49 48 47 46 45 44 43 42 41 40
- * The reason for this bit ordering is the fact that
- * in the architecture independent code bits operations
- * of the form "flags |= (1 << bitnr)" are used INTERMIXED
- * with operation of the form "set_bit(bitnr, flags)".
- */
-
-/* bitmap tables from arch/s390/kernel/bitmap.c */
-extern const char _zb_findmap[];
-extern const char _sb_findmap[];
-
 #ifndef CONFIG_64BIT
 
 #define __BITOPS_OR		"or"
@@ -310,522 +300,24 @@ static inline int test_bit(unsigned long nr, const volatile unsigned long *ptr)
 }
 
 /*
- * Optimized find bit helper functions.
- */
-
-/**
- * __ffz_word_loop - find byte offset of first long != -1UL
- * @addr: pointer to array of unsigned long
- * @size: size of the array in bits
- */
-static inline unsigned long __ffz_word_loop(const unsigned long *addr,
-					    unsigned long size)
-{
-	typedef struct { long _[__BITOPS_WORDS(size)]; } addrtype;
-	unsigned long bytes = 0;
-
-	asm volatile(
-#ifndef CONFIG_64BIT
-		"	ahi	%1,-1\n"
-		"	sra	%1,5\n"
-		"	jz	1f\n"
-		"0:	c	%2,0(%0,%3)\n"
-		"	jne	1f\n"
-		"	la	%0,4(%0)\n"
-		"	brct	%1,0b\n"
-		"1:\n"
-#else
-		"	aghi	%1,-1\n"
-		"	srag	%1,%1,6\n"
-		"	jz	1f\n"
-		"0:	cg	%2,0(%0,%3)\n"
-		"	jne	1f\n"
-		"	la	%0,8(%0)\n"
-		"	brct	%1,0b\n"
-		"1:\n"
-#endif
-		: "+&a" (bytes), "+&d" (size)
-		: "d" (-1UL), "a" (addr), "m" (*(addrtype *) addr)
-		: "cc" );
-	return bytes;
-}
-
-/**
- * __ffs_word_loop - find byte offset of first long != 0UL
- * @addr: pointer to array of unsigned long
- * @size: size of the array in bits
- */
-static inline unsigned long __ffs_word_loop(const unsigned long *addr,
-					    unsigned long size)
-{
-	typedef struct { long _[__BITOPS_WORDS(size)]; } addrtype;
-	unsigned long bytes = 0;
-
-	asm volatile(
-#ifndef CONFIG_64BIT
-		"	ahi	%1,-1\n"
-		"	sra	%1,5\n"
-		"	jz	1f\n"
-		"0:	c	%2,0(%0,%3)\n"
-		"	jne	1f\n"
-		"	la	%0,4(%0)\n"
-		"	brct	%1,0b\n"
-		"1:\n"
-#else
-		"	aghi	%1,-1\n"
-		"	srag	%1,%1,6\n"
-		"	jz	1f\n"
-		"0:	cg	%2,0(%0,%3)\n"
-		"	jne	1f\n"
-		"	la	%0,8(%0)\n"
-		"	brct	%1,0b\n"
-		"1:\n"
-#endif
-		: "+&a" (bytes), "+&a" (size)
-		: "d" (0UL), "a" (addr), "m" (*(addrtype *) addr)
-		: "cc" );
-	return bytes;
-}
-
-/**
- * __ffz_word - add number of the first unset bit
- * @nr: base value the bit number is added to
- * @word: the word that is searched for unset bits
- */
-static inline unsigned long __ffz_word(unsigned long nr, unsigned long word)
-{
-#ifdef CONFIG_64BIT
-	if ((word & 0xffffffff) == 0xffffffff) {
-		word >>= 32;
-		nr += 32;
-	}
-#endif
-	if ((word & 0xffff) == 0xffff) {
-		word >>= 16;
-		nr += 16;
-	}
-	if ((word & 0xff) == 0xff) {
-		word >>= 8;
-		nr += 8;
-	}
-	return nr + _zb_findmap[(unsigned char) word];
-}
-
-/**
- * __ffs_word - add number of the first set bit
- * @nr: base value the bit number is added to
- * @word: the word that is searched for set bits
- */
-static inline unsigned long __ffs_word(unsigned long nr, unsigned long word)
-{
-#ifdef CONFIG_64BIT
-	if ((word & 0xffffffff) == 0) {
-		word >>= 32;
-		nr += 32;
-	}
-#endif
-	if ((word & 0xffff) == 0) {
-		word >>= 16;
-		nr += 16;
-	}
-	if ((word & 0xff) == 0) {
-		word >>= 8;
-		nr += 8;
-	}
-	return nr + _sb_findmap[(unsigned char) word];
-}
-
-
-/**
- * __load_ulong_be - load big endian unsigned long
- * @p: pointer to array of unsigned long
- * @offset: byte offset of source value in the array
- */
-static inline unsigned long __load_ulong_be(const unsigned long *p,
-					    unsigned long offset)
-{
-	p = (unsigned long *)((unsigned long) p + offset);
-	return *p;
-}
-
-/**
- * __load_ulong_le - load little endian unsigned long
- * @p: pointer to array of unsigned long
- * @offset: byte offset of source value in the array
- */
-static inline unsigned long __load_ulong_le(const unsigned long *p,
-					    unsigned long offset)
-{
-	unsigned long word;
-
-	p = (unsigned long *)((unsigned long) p + offset);
-#ifndef CONFIG_64BIT
-	asm volatile(
-		"	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"
-		: "=d" (word) : "m" (*p) );
-#endif
-	return word;
-}
-
-/*
- * The various find bit functions.
- */
-
-/*
- * ffz - find first zero in word.
- * @word: The word to search
- *
- * Undefined if no zero exists, so code should check against ~0UL first.
- */
-static inline unsigned long ffz(unsigned long word)
-{
-	return __ffz_word(0, word);
-}
-
-/**
- * __ffs - find first bit in word.
- * @word: The word to search
- *
- * Undefined if no bit exists, so code should check against 0 first.
- */
-static inline unsigned long __ffs (unsigned long word)
-{
-	return __ffs_word(0, word);
-}
-
-/**
- * ffs - find first bit set
- * @x: the word to search
- *
- * This is defined the same way as
- * the libc and compiler builtin ffs routines, therefore
- * differs in spirit from the above ffz (man ffs).
- */
-static inline int ffs(int x)
-{
-	if (!x)
-		return 0;
-	return __ffs_word(1, x);
-}
-
-/**
- * find_first_zero_bit - find the first zero bit in a memory region
- * @addr: The address to start the search at
- * @size: The maximum size to search
- *
- * Returns the bit-number of the first zero bit, not the number of the byte
- * containing a bit.
- */
-static inline unsigned long find_first_zero_bit(const unsigned long *addr,
-						unsigned long size)
-{
-	unsigned long bytes, bits;
-
-        if (!size)
-                return 0;
-	bytes = __ffz_word_loop(addr, size);
-	bits = __ffz_word(bytes*8, __load_ulong_be(addr, bytes));
-	return (bits < size) ? bits : size;
-}
-#define find_first_zero_bit find_first_zero_bit
-
-/**
- * find_first_bit - find the first set bit in a memory region
- * @addr: The address to start the search at
- * @size: The maximum size to search
- *
- * Returns the bit-number of the first set bit, not the number of the byte
- * containing a bit.
- */
-static inline unsigned long find_first_bit(const unsigned long * addr,
-					   unsigned long size)
-{
-	unsigned long bytes, bits;
-
-        if (!size)
-                return 0;
-	bytes = __ffs_word_loop(addr, size);
-	bits = __ffs_word(bytes*8, __load_ulong_be(addr, bytes));
-	return (bits < size) ? bits : size;
-}
-#define find_first_bit find_first_bit
-
-/*
- * Big endian variant whichs starts bit counting from left using
- * the flogr (find leftmost one) instruction.
+ * ATTENTION:
+ * find_first_bit_left() and find_next_bit_left() use MSB0 encoding.
  */
-static inline unsigned long __flo_word(unsigned long nr, unsigned long val)
-{
-	register unsigned long bit asm("2") = val;
-	register unsigned long out asm("3");
-
-	asm volatile (
-		"	.insn	rre,0xb9830000,%[bit],%[bit]\n"
-		: [bit] "+d" (bit), [out] "=d" (out) : : "cc");
-	return nr + bit;
-}
-
-/*
- * 64 bit special left bitops format:
- * order in memory:
- *    00 01 02 03 04 05 06 07 08 09 0a 0b 0c 0d 0e 0f
- *    10 11 12 13 14 15 16 17 18 19 1a 1b 1c 1d 1e 1f
- *    20 21 22 23 24 25 26 27 28 29 2a 2b 2c 2d 2e 2f
- *    30 31 32 33 34 35 36 37 38 39 3a 3b 3c 3d 3e 3f
- * after that follows the next long with bit numbers
- *    40 41 42 43 44 45 46 47 48 49 4a 4b 4c 4d 4e 4f
- *    50 51 52 53 54 55 56 57 58 59 5a 5b 5c 5d 5e 5f
- *    60 61 62 63 64 65 66 67 68 69 6a 6b 6c 6d 6e 6f
- *    70 71 72 73 74 75 76 77 78 79 7a 7b 7c 7d 7e 7f
- * The reason for this bit ordering is the fact that
- * the hardware sets bits in a bitmap starting at bit 0
- * and we don't want to scan the bitmap from the 'wrong
- * end'.
- */
-static inline unsigned long find_first_bit_left(const unsigned long *addr,
-						unsigned long size)
-{
-	unsigned long bytes, bits;
-
-	if (!size)
-		return 0;
-	bytes = __ffs_word_loop(addr, size);
-	bits = __flo_word(bytes * 8, __load_ulong_be(addr, bytes));
-	return (bits < size) ? bits : size;
-}
+unsigned long find_first_bit_left(const unsigned long *addr, unsigned long size);
+unsigned long find_next_bit_left(const unsigned long *addr, unsigned long size,
+				 unsigned long offset);
 
-static inline int find_next_bit_left(const unsigned long *addr,
-				     unsigned long size,
-				     unsigned long offset)
-{
-	const unsigned long *p;
-	unsigned long bit, set;
-
-	if (offset >= size)
-		return size;
-	bit = offset & (BITS_PER_LONG - 1);
-	offset -= bit;
-	size -= offset;
-	p = addr + offset / BITS_PER_LONG;
-	if (bit) {
-		set = __flo_word(0, *p & (~0UL >> bit));
-		if (set >= size)
-			return size + offset;
-		if (set < BITS_PER_LONG)
-			return set + offset;
-		offset += BITS_PER_LONG;
-		size -= BITS_PER_LONG;
-		p++;
-	}
-	return offset + find_first_bit_left(p, size);
-}
-
-#define for_each_set_bit_left(bit, addr, size)				\
-	for ((bit) = find_first_bit_left((addr), (size));		\
-	     (bit) < (size);						\
-	     (bit) = find_next_bit_left((addr), (size), (bit) + 1))
-
-/* same as for_each_set_bit() but use bit as value to start with */
-#define for_each_set_bit_left_cont(bit, addr, size)			\
-	for ((bit) = find_next_bit_left((addr), (size), (bit));		\
-	     (bit) < (size);						\
-	     (bit) = find_next_bit_left((addr), (size), (bit) + 1))
-
-/**
- * find_next_zero_bit - find the first zero bit in a memory region
- * @addr: The address to base the search on
- * @offset: The bitnumber to start searching at
- * @size: The maximum size to search
- */
-static inline int find_next_zero_bit (const unsigned long * addr,
-				      unsigned long size,
-				      unsigned long offset)
-{
-        const unsigned long *p;
-	unsigned long bit, set;
-
-	if (offset >= size)
-		return size;
-	bit = offset & (BITS_PER_LONG - 1);
-	offset -= bit;
-	size -= offset;
-	p = addr + offset / BITS_PER_LONG;
-	if (bit) {
-		/*
-		 * __ffz_word returns BITS_PER_LONG
-		 * if no zero bit is present in the word.
-		 */
-		set = __ffz_word(bit, *p >> bit);
-		if (set >= size)
-			return size + offset;
-		if (set < BITS_PER_LONG)
-			return set + offset;
-		offset += BITS_PER_LONG;
-		size -= BITS_PER_LONG;
-		p++;
-	}
-	return offset + find_first_zero_bit(p, size);
-}
-#define find_next_zero_bit find_next_zero_bit
-
-/**
- * find_next_bit - find the first set bit in a memory region
- * @addr: The address to base the search on
- * @offset: The bitnumber to start searching at
- * @size: The maximum size to search
- */
-static inline int find_next_bit (const unsigned long * addr,
-				 unsigned long size,
-				 unsigned long offset)
-{
-        const unsigned long *p;
-	unsigned long bit, set;
-
-	if (offset >= size)
-		return size;
-	bit = offset & (BITS_PER_LONG - 1);
-	offset -= bit;
-	size -= offset;
-	p = addr + offset / BITS_PER_LONG;
-	if (bit) {
-		/*
-		 * __ffs_word returns BITS_PER_LONG
-		 * if no one bit is present in the word.
-		 */
-		set = __ffs_word(0, *p & (~0UL << bit));
-		if (set >= size)
-			return size + offset;
-		if (set < BITS_PER_LONG)
-			return set + offset;
-		offset += BITS_PER_LONG;
-		size -= BITS_PER_LONG;
-		p++;
-	}
-	return offset + find_first_bit(p, size);
-}
-#define find_next_bit find_next_bit
-
-/*
- * Every architecture must define this function. It's the fastest
- * way of searching a 140-bit bitmap where the first 100 bits are
- * unlikely to be set. It's guaranteed that at least one of the 140
- * bits is cleared.
- */
-static inline int sched_find_first_bit(unsigned long *b)
-{
-	return find_first_bit(b, 140);
-}
-
-#include <asm-generic/bitops/fls.h>
+#include <asm-generic/bitops/__ffs.h>
+#include <asm-generic/bitops/ffs.h>
 #include <asm-generic/bitops/__fls.h>
+#include <asm-generic/bitops/fls.h>
 #include <asm-generic/bitops/fls64.h>
-
+#include <asm-generic/bitops/ffz.h>
+#include <asm-generic/bitops/find.h>
 #include <asm-generic/bitops/hweight.h>
 #include <asm-generic/bitops/lock.h>
-
-/*
- * ATTENTION: intel byte ordering convention for ext2 and minix !!
- * bit 0 is the LSB of addr; bit 31 is the MSB of addr;
- * bit 32 is the LSB of (addr+4).
- * That combined with the little endian byte order of Intel gives the
- * following bit order in memory:
- *    07 06 05 04 03 02 01 00 15 14 13 12 11 10 09 08 \
- *    23 22 21 20 19 18 17 16 31 30 29 28 27 26 25 24
- */
-
-static inline int find_first_zero_bit_le(void *vaddr, unsigned int size)
-{
-	unsigned long bytes, bits;
-
-        if (!size)
-                return 0;
-	bytes = __ffz_word_loop(vaddr, size);
-	bits = __ffz_word(bytes*8, __load_ulong_le(vaddr, bytes));
-	return (bits < size) ? bits : size;
-}
-#define find_first_zero_bit_le find_first_zero_bit_le
-
-static inline int find_next_zero_bit_le(void *vaddr, unsigned long size,
-					  unsigned long offset)
-{
-        unsigned long *addr = vaddr, *p;
-	unsigned long bit, set;
-
-        if (offset >= size)
-                return size;
-	bit = offset & (BITS_PER_LONG - 1);
-	offset -= bit;
-	size -= offset;
-	p = addr + offset / BITS_PER_LONG;
-        if (bit) {
-		/*
-		 * s390 version of ffz returns BITS_PER_LONG
-		 * if no zero bit is present in the word.
-		 */
-		set = __ffz_word(bit, __load_ulong_le(p, 0) >> bit);
-		if (set >= size)
-			return size + offset;
-		if (set < BITS_PER_LONG)
-			return set + offset;
-		offset += BITS_PER_LONG;
-		size -= BITS_PER_LONG;
-		p++;
-        }
-	return offset + find_first_zero_bit_le(p, size);
-}
-#define find_next_zero_bit_le find_next_zero_bit_le
-
-static inline unsigned long find_first_bit_le(void *vaddr, unsigned long size)
-{
-	unsigned long bytes, bits;
-
-	if (!size)
-		return 0;
-	bytes = __ffs_word_loop(vaddr, size);
-	bits = __ffs_word(bytes*8, __load_ulong_le(vaddr, bytes));
-	return (bits < size) ? bits : size;
-}
-#define find_first_bit_le find_first_bit_le
-
-static inline int find_next_bit_le(void *vaddr, unsigned long size,
-				     unsigned long offset)
-{
-	unsigned long *addr = vaddr, *p;
-	unsigned long bit, set;
-
-	if (offset >= size)
-		return size;
-	bit = offset & (BITS_PER_LONG - 1);
-	offset -= bit;
-	size -= offset;
-	p = addr + offset / BITS_PER_LONG;
-	if (bit) {
-		/*
-		 * s390 version of ffz returns BITS_PER_LONG
-		 * if no zero bit is present in the word.
-		 */
-		set = __ffs_word(0, __load_ulong_le(p, 0) & (~0UL << bit));
-		if (set >= size)
-			return size + offset;
-		if (set < BITS_PER_LONG)
-			return set + offset;
-		offset += BITS_PER_LONG;
-		size -= BITS_PER_LONG;
-		p++;
-	}
-	return offset + find_first_bit_le(p, size);
-}
-#define find_next_bit_le find_next_bit_le
-
+#include <asm-generic/bitops/sched.h>
 #include <asm-generic/bitops/le.h>
-
 #include <asm-generic/bitops/ext2-atomic-setbit.h>
 
 #endif /* _S390_BITOPS_H */
diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile
index 4bb2a46..2403303 100644
--- a/arch/s390/kernel/Makefile
+++ b/arch/s390/kernel/Makefile
@@ -28,7 +28,7 @@ CFLAGS_ptrace.o		+= -DUTS_MACHINE='"$(UTS_MACHINE)"'
 
 CFLAGS_sysinfo.o += -Iinclude/math-emu -Iarch/s390/math-emu -w
 
-obj-y	:= bitmap.o traps.o time.o process.o base.o early.o setup.o vtime.o
+obj-y	:= traps.o time.o process.o base.o early.o setup.o vtime.o
 obj-y	+= processor.o sys_s390.o ptrace.o signal.o cpcmd.o ebcdic.o nmi.o
 obj-y	+= debug.o irq.o ipl.o dis.o diag.o sclp.o vdso.o
 obj-y	+= sysinfo.o jump_label.o lgr.o os_info.o machine_kexec.o pgm_check.o
diff --git a/arch/s390/kernel/bitmap.c b/arch/s390/kernel/bitmap.c
deleted file mode 100644
index 5cdb813..0000000
--- a/arch/s390/kernel/bitmap.c
+++ /dev/null
@@ -1,48 +0,0 @@
-/*
- *    Bitmaps for set_bit, clear_bit, test_and_set_bit, ...
- *    See include/asm/{bitops.h|posix_types.h} for details
- *
- *    Copyright IBM Corp. 1999, 2009
- *    Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>,
- */
-
-#include <linux/bitops.h>
-#include <linux/module.h>
-
-const char _zb_findmap[] = {
-	0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,4,
-	0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,5,
-	0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,4,
-	0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,6,
-	0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,4,
-	0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,5,
-	0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,4,
-	0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,7,
-	0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,4,
-	0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,5,
-	0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,4,
-	0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,6,
-	0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,4,
-	0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,5,
-	0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,4,
-	0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,8 };
-EXPORT_SYMBOL(_zb_findmap);
-
-const char _sb_findmap[] = {
-	8,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,
-	4,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,
-	5,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,
-	4,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,
-	6,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,
-	4,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,
-	5,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,
-	4,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,
-	7,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,
-	4,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,
-	5,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,
-	4,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,
-	6,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,
-	4,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,
-	5,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,
-	4,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0 };
-EXPORT_SYMBOL(_sb_findmap);
diff --git a/arch/s390/lib/Makefile b/arch/s390/lib/Makefile
index 20b0e97..e506c5f 100644
--- a/arch/s390/lib/Makefile
+++ b/arch/s390/lib/Makefile
@@ -2,7 +2,7 @@
 # Makefile for s390-specific library files..
 #
 
-lib-y += delay.o string.o uaccess_std.o uaccess_pt.o
+lib-y += delay.o string.o uaccess_std.o uaccess_pt.o find.o
 obj-$(CONFIG_32BIT) += div64.o qrnnd.o ucmpdi2.o mem32.o
 obj-$(CONFIG_64BIT) += mem64.o
 lib-$(CONFIG_64BIT) += uaccess_mvcos.o
diff --git a/arch/s390/lib/find.c b/arch/s390/lib/find.c
new file mode 100644
index 0000000..8963929
--- /dev/null
+++ b/arch/s390/lib/find.c
@@ -0,0 +1,77 @@
+/*
+ * MSB0 numbered special bitops handling.
+ *
+ * On s390x the bits are numbered:
+ *   |0..............63|64............127|128...........191|192...........255|
+ * and on s390:
+ *   |0.....31|31....63|64....95|96...127|128..159|160..191|192..223|224..255|
+ *
+ * The reason for this bit numbering is the fact that the hardware sets bits
+ * in a bitmap starting at bit 0 (MSB) and we don't want to scan the bitmap
+ * from the 'wrong end'.
+ */
+
+#include <linux/compiler.h>
+#include <linux/bitops.h>
+#include <linux/export.h>
+
+unsigned long find_first_bit_left(const unsigned long *addr, unsigned long size)
+{
+	const unsigned long *p = addr;
+	unsigned long result = 0;
+	unsigned long tmp;
+
+	while (size & ~(BITS_PER_LONG - 1)) {
+		if ((tmp = *(p++)))
+			goto found;
+		result += BITS_PER_LONG;
+		size -= BITS_PER_LONG;
+	}
+	if (!size)
+		return result;
+	tmp = (*p) & (~0UL << (BITS_PER_LONG - size));
+	if (!tmp)		/* Are any bits set? */
+		return result + size;	/* Nope. */
+found:
+	return result + (__fls(tmp) ^ (BITS_PER_LONG - 1));
+}
+EXPORT_SYMBOL(find_first_bit_left);
+
+unsigned long find_next_bit_left(const unsigned long *addr, unsigned long size,
+				 unsigned long offset)
+{
+	const unsigned long *p = addr + (offset / BITS_PER_LONG);
+	unsigned long result = offset & ~(BITS_PER_LONG - 1);
+	unsigned long tmp;
+
+	if (offset >= size)
+		return size;
+	size -= result;
+	offset %= BITS_PER_LONG;
+	if (offset) {
+		tmp = *(p++);
+		tmp &= (~0UL >> offset);
+		if (size < BITS_PER_LONG)
+			goto found_first;
+		if (tmp)
+			goto found_middle;
+		size -= BITS_PER_LONG;
+		result += BITS_PER_LONG;
+	}
+	while (size & ~(BITS_PER_LONG-1)) {
+		if ((tmp = *(p++)))
+			goto found_middle;
+		result += BITS_PER_LONG;
+		size -= BITS_PER_LONG;
+	}
+	if (!size)
+		return result;
+	tmp = *p;
+found_first:
+	tmp &= (~0UL << (BITS_PER_LONG - size));
+	if (!tmp)		/* Are any bits set? */
+		return result + size;	/* Nope. */
+found_middle:
+	return result + (__fls(tmp) ^ (BITS_PER_LONG - 1));
+}
+EXPORT_SYMBOL(find_next_bit_left);