Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/x86/linux-2.6-generic-bitops-v3

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/x86/linux-2.6-generic-bitops-v3:
  x86, bitops: select the generic bitmap search functions
  x86: include/asm-x86/pgalloc.h/bitops.h: checkpatch cleanups - formatting only
  x86: finalize bitops unification
  x86, UML: remove x86-specific implementations of find_first_bit
  x86: optimize find_first_bit for small bitmaps
  x86: switch 64-bit to generic find_first_bit
  x86: generic versions of find_first_(zero_)bit, convert i386
  bitops: use __fls for fls64 on 64-bit archs
  generic: implement __fls on all 64-bit archs
  generic: introduce a generic __fls implementation
  x86: merge the simple bitops and move them to bitops.h
  x86, generic: optimize find_next_(zero_)bit for small constant-size bitmaps
  x86, uml: fix uml with generic find_next_bit for x86
  x86: change x86 to use generic find_next_bit
  uml: Kconfig cleanup
  uml: fix build error

8 files changed, 17 insertions, 250 deletions

diff --git a/arch/um/Kconfig.x86_64 b/arch/um/Kconfig.x86_64
index 3fbe69e359ed..5696e7b374b3 100644
--- a/arch/um/Kconfig.x86_64
+++ b/arch/um/Kconfig.x86_64
@@ -1,3 +1,10 @@
+
+menu "Host processor type and features"
+
+source "arch/x86/Kconfig.cpu"
+
+endmenu
+
 config UML_X86
 	bool
 	default y
diff --git a/arch/um/os-Linux/helper.c b/arch/um/os-Linux/helper.c
index f4bd349d4412..f25c29a12d00 100644
--- a/arch/um/os-Linux/helper.c
+++ b/arch/um/os-Linux/helper.c
@@ -14,6 +14,7 @@
 #include "os.h"
 #include "um_malloc.h"
 #include "user.h"
+#include <linux/limits.h>
 
 struct helper_data {
 	void (*pre_exec)(void*);
diff --git a/arch/um/sys-i386/Makefile b/arch/um/sys-i386/Makefile
index 964dc1a04c37..598b5c1903af 100644
--- a/arch/um/sys-i386/Makefile
+++ b/arch/um/sys-i386/Makefile
@@ -6,7 +6,7 @@ obj-y = bug.o bugs.o checksum.o delay.o fault.o ksyms.o ldt.o ptrace.o \
 	ptrace_user.o setjmp.o signal.o stub.o stub_segv.o syscalls.o sysrq.o \
 	sys_call_table.o tls.o
 
-subarch-obj-y = lib/bitops_32.o lib/semaphore_32.o lib/string_32.o
+subarch-obj-y = lib/semaphore_32.o lib/string_32.o
 subarch-obj-$(CONFIG_HIGHMEM) += mm/highmem_32.o
 subarch-obj-$(CONFIG_MODULES) += kernel/module_32.o
 
diff --git a/arch/um/sys-x86_64/Makefile b/arch/um/sys-x86_64/Makefile
index 3c22de532088..c8b4cce9cfe1 100644
--- a/arch/um/sys-x86_64/Makefile
+++ b/arch/um/sys-x86_64/Makefile
@@ -10,7 +10,7 @@ obj-y = bug.o bugs.o delay.o fault.o ldt.o mem.o ptrace.o ptrace_user.o \
 
 obj-$(CONFIG_MODULES) += um_module.o
 
-subarch-obj-y = lib/bitops_64.o lib/csum-partial_64.o lib/memcpy_64.o lib/thunk_64.o
+subarch-obj-y = lib/csum-partial_64.o lib/memcpy_64.o lib/thunk_64.o
 subarch-obj-$(CONFIG_MODULES) += kernel/module_64.o
 
 ldt-y = ../sys-i386/ldt.o
diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu
index 4da3cdb9c1b1..7ef18b01f0bc 100644
--- a/arch/x86/Kconfig.cpu
+++ b/arch/x86/Kconfig.cpu
@@ -278,6 +278,11 @@ config GENERIC_CPU
 
 endchoice
 
+config X86_CPU
+	def_bool y
+	select GENERIC_FIND_FIRST_BIT
+	select GENERIC_FIND_NEXT_BIT
+
 config X86_GENERIC
 	bool "Generic x86 support"
 	depends on X86_32
@@ -398,7 +403,7 @@ config X86_TSC
 # generates cmov.
 config X86_CMOV
 	def_bool y
-	depends on (MK7 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7)
+	depends on (MK7 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || X86_64)
 
 config X86_MINIMUM_CPU_FAMILY
 	int
diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index 25df1c1989fe..76f60f52a885 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -11,7 +11,7 @@ lib-y += memcpy_$(BITS).o
 ifeq ($(CONFIG_X86_32),y)
         lib-y += checksum_32.o
         lib-y += strstr_32.o
-        lib-y += bitops_32.o semaphore_32.o string_32.o
+        lib-y += semaphore_32.o string_32.o
 
         lib-$(CONFIG_X86_USE_3DNOW) += mmx_32.o
 else
@@ -21,7 +21,6 @@ else
 
         lib-y += csum-partial_64.o csum-copy_64.o csum-wrappers_64.o
         lib-y += thunk_64.o clear_page_64.o copy_page_64.o
-        lib-y += bitops_64.o
         lib-y += memmove_64.o memset_64.o
         lib-y += copy_user_64.o rwlock_64.o copy_user_nocache_64.o
 endif
diff --git a/arch/x86/lib/bitops_32.c b/arch/x86/lib/bitops_32.c
deleted file mode 100644
index b65440459859..000000000000
--- a/arch/x86/lib/bitops_32.c
+++ /dev/null
@@ -1,70 +0,0 @@
-#include <linux/bitops.h>
-#include <linux/module.h>
-
-/**
- * find_next_bit - find the next 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
- */
-int find_next_bit(const unsigned long *addr, int size, int offset)
-{
-	const unsigned long *p = addr + (offset >> 5);
-	int set = 0, bit = offset & 31, res;
-
-	if (bit) {
-		/*
-		 * Look for nonzero in the first 32 bits:
-		 */
-		__asm__("bsfl %1,%0\n\t"
-			"jne 1f\n\t"
-			"movl $32, %0\n"
-			"1:"
-			: "=r" (set)
-			: "r" (*p >> bit));
-		if (set < (32 - bit))
-			return set + offset;
-		set = 32 - bit;
-		p++;
-	}
-	/*
-	 * No set bit yet, search remaining full words for a bit
-	 */
-	res = find_first_bit (p, size - 32 * (p - addr));
-	return (offset + set + res);
-}
-EXPORT_SYMBOL(find_next_bit);
-
-/**
- * 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
- */
-int find_next_zero_bit(const unsigned long *addr, int size, int offset)
-{
-	const unsigned long *p = addr + (offset >> 5);
-	int set = 0, bit = offset & 31, res;
-
-	if (bit) {
-		/*
-		 * Look for zero in the first 32 bits.
-		 */
-		__asm__("bsfl %1,%0\n\t"
-			"jne 1f\n\t"
-			"movl $32, %0\n"
-			"1:"
-			: "=r" (set)
-			: "r" (~(*p >> bit)));
-		if (set < (32 - bit))
-			return set + offset;
-		set = 32 - bit;
-		p++;
-	}
-	/*
-	 * No zero yet, search remaining full bytes for a zero
-	 */
-	res = find_first_zero_bit(p, size - 32 * (p - addr));
-	return (offset + set + res);
-}
-EXPORT_SYMBOL(find_next_zero_bit);
diff --git a/arch/x86/lib/bitops_64.c b/arch/x86/lib/bitops_64.c
deleted file mode 100644
index 0e8f491e6ccc..000000000000
--- a/arch/x86/lib/bitops_64.c
+++ /dev/null
@@ -1,175 +0,0 @@
-#include <linux/bitops.h>
-
-#undef find_first_zero_bit
-#undef find_next_zero_bit
-#undef find_first_bit
-#undef find_next_bit
-
-static inline long
-__find_first_zero_bit(const unsigned long * addr, unsigned long size)
-{
-	long d0, d1, d2;
-	long res;
-
-	/*
-	 * We must test the size in words, not in bits, because
-	 * otherwise incoming sizes in the range -63..-1 will not run
-	 * any scasq instructions, and then the flags used by the je
-	 * instruction will have whatever random value was in place
-	 * before.  Nobody should call us like that, but
-	 * find_next_zero_bit() does when offset and size are at the
-	 * same word and it fails to find a zero itself.
-	 */
-	size += 63;
-	size >>= 6;
-	if (!size)
-		return 0;
-	asm volatile(
-		"  repe; scasq\n"
-		"  je 1f\n"
-		"  xorq -8(%%rdi),%%rax\n"
-		"  subq $8,%%rdi\n"
-		"  bsfq %%rax,%%rdx\n"
-		"1:  subq %[addr],%%rdi\n"
-		"  shlq $3,%%rdi\n"
-		"  addq %%rdi,%%rdx"
-		:"=d" (res), "=&c" (d0), "=&D" (d1), "=&a" (d2)
-		:"0" (0ULL), "1" (size), "2" (addr), "3" (-1ULL),
-		 [addr] "S" (addr) : "memory");
-	/*
-	 * Any register would do for [addr] above, but GCC tends to
-	 * prefer rbx over rsi, even though rsi is readily available
-	 * and doesn't have to be saved.
-	 */
-	return res;
-}
-
-/**
- * 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.
- */
-long find_first_zero_bit(const unsigned long * addr, unsigned long size)
-{
-	return __find_first_zero_bit (addr, size);
-}
-
-/**
- * find_next_zero_bit - find the next 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
- */
-long find_next_zero_bit (const unsigned long * addr, long size, long offset)
-{
-	const unsigned long * p = addr + (offset >> 6);
-	unsigned long set = 0;
-	unsigned long res, bit = offset&63;
-
-	if (bit) {
-		/*
-		 * Look for zero in first word
-		 */
-		asm("bsfq %1,%0\n\t"
-		    "cmoveq %2,%0"
-		    : "=r" (set)
-		    : "r" (~(*p >> bit)), "r"(64L));
-		if (set < (64 - bit))
-			return set + offset;
-		set = 64 - bit;
-		p++;
-	}
-	/*
-	 * No zero yet, search remaining full words for a zero
-	 */
-	res = __find_first_zero_bit (p, size - 64 * (p - addr));
-
-	return (offset + set + res);
-}
-
-static inline long
-__find_first_bit(const unsigned long * addr, unsigned long size)
-{
-	long d0, d1;
-	long res;
-
-	/*
-	 * We must test the size in words, not in bits, because
-	 * otherwise incoming sizes in the range -63..-1 will not run
-	 * any scasq instructions, and then the flags used by the jz
-	 * instruction will have whatever random value was in place
-	 * before.  Nobody should call us like that, but
-	 * find_next_bit() does when offset and size are at the same
-	 * word and it fails to find a one itself.
-	 */
-	size += 63;
-	size >>= 6;
-	if (!size)
-		return 0;
-	asm volatile(
-		"   repe; scasq\n"
-		"   jz 1f\n"
-		"   subq $8,%%rdi\n"
-		"   bsfq (%%rdi),%%rax\n"
-		"1: subq %[addr],%%rdi\n"
-		"   shlq $3,%%rdi\n"
-		"   addq %%rdi,%%rax"
-		:"=a" (res), "=&c" (d0), "=&D" (d1)
-		:"0" (0ULL), "1" (size), "2" (addr),
-		 [addr] "r" (addr) : "memory");
-	return res;
-}
-
-/**
- * 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.
- */
-long find_first_bit(const unsigned long * addr, unsigned long size)
-{
-	return __find_first_bit(addr,size);
-}
-
-/**
- * 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
- */
-long find_next_bit(const unsigned long * addr, long size, long offset)
-{
-	const unsigned long * p = addr + (offset >> 6);
-	unsigned long set = 0, bit = offset & 63, res;
-
-	if (bit) {
-		/*
-		 * Look for nonzero in the first 64 bits:
-		 */
-		asm("bsfq %1,%0\n\t"
-		    "cmoveq %2,%0\n\t"
-		    : "=r" (set)
-		    : "r" (*p >> bit), "r" (64L));
-		if (set < (64 - bit))
-			return set + offset;
-		set = 64 - bit;
-		p++;
-	}
-	/*
-	 * No set bit yet, search remaining full words for a bit
-	 */
-	res = __find_first_bit (p, size - 64 * (p - addr));
-	return (offset + set + res);
-}
-
-#include <linux/module.h>
-
-EXPORT_SYMBOL(find_next_bit);
-EXPORT_SYMBOL(find_first_bit);
-EXPORT_SYMBOL(find_first_zero_bit);
-EXPORT_SYMBOL(find_next_zero_bit);