[PATCH] x86: generic versions of find_first_(zero_)bit, convert i386

!MAILaRCHIVE_VOTE_RePLACE
Previous message: [thread] [date] [author]
Next message: [thread] [date] [author]
To: Ingo Molnar <mingo@...>, Andi Kleen <andi@...>, LKML <linux-kernel@...>
Cc: Alexander van Heukelum <heukelum@...>
Date: Monday, March 31, 2008 - 1:15 pm

Generic versions of __find_first_bit and __find_first_zero_bit
are introduced as simplified versions of __find_next_bit and
__find_next_zero_bit. Their compilation and use are guarded by
a new config variable GENERIC_FIND_FIRST_BIT.

The generic versions of find_first_bit and find_first_zero_bit
are implemented in terms of the newly introduced __find_first_bit
and __find_first_zero_bit.

This patch also converts i386 to the generic functions. The text
size shrinks slightly due to uninlining of the find_*_bit functions.

   text    data     bss     dec     hex filename
4764939  480324  622592 5867855  59894f vmlinux  (i386 defconfig before)
4764645  480324  622592 5867561  598829 vmlinux  (i386 defconfig after)

Signed-off-by: Alexander van Heukelum <heukelum@fastmail.fm>

---

Hi Ingo,

Here is another step in the unification of the bitops for i386
and x86_64. This patch implements a minimal conversion to a
generic implementation of find_first_bit/find_first_zero_bit
for i386. The optimization for small bitmaps and the conversion
of x86_64 will follow soon.

Compiles and runs fine on i386 and x86_64 (current x86#testing).

Greetings,
	Alexander

 arch/x86/Kconfig            |    3 ++
 include/asm-x86/bitops_32.h |   56 -----------------------------------------
 include/linux/bitops.h      |   34 +++++++++++++++++++++++++
 lib/Makefile                |    1 +
 lib/find_next_bit.c         |   58 +++++++++++++++++++++++++++++++++++++++++++
 5 files changed, 96 insertions(+), 56 deletions(-)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 6b3626d..fa7d16d 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -80,6 +80,9 @@ config GENERIC_BUG
 	def_bool y
 	depends on BUG
 
+config GENERIC_FIND_FIRST_BIT
+	def_bool X86_32
+
 config GENERIC_FIND_NEXT_BIT
 	def_bool y
 
diff --git a/include/asm-x86/bitops_32.h b/include/asm-x86/bitops_32.h
index 3ed64b2..2e86302 100644
--- a/include/asm-x86/bitops_32.h
+++ b/include/asm-x86/bitops_32.h
@@ -4,62 +4,6 @@
 /*
  * Copyright 1992, Linus Torvalds.
  */
-
-/**
- * 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 int find_first_zero_bit(const unsigned long *addr, unsigned size)
-{
-	int d0, d1, d2;
-	int res;
-
-	if (!size)
-		return 0;
-	/* This looks at memory.
-	 * Mark it volatile to tell gcc not to move it around
-	 */
-	asm volatile("movl $-1,%%eax\n\t"
-		     "xorl %%edx,%%edx\n\t"
-		     "repe; scasl\n\t"
-		     "je 1f\n\t"
-		     "xorl -4(%%edi),%%eax\n\t"
-		     "subl $4,%%edi\n\t"
-		     "bsfl %%eax,%%edx\n"
-		     "1:\tsubl %%ebx,%%edi\n\t"
-		     "shll $3,%%edi\n\t"
-		     "addl %%edi,%%edx"
-		     : "=d" (res), "=&c" (d0), "=&D" (d1), "=&a" (d2)
-		     : "1" ((size + 31) >> 5), "2" (addr),
-		       "b" (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.
- */
-static inline unsigned find_first_bit(const unsigned long *addr, unsigned size)
-{
-	unsigned x = 0;
-
-	while (x < size) {
-		unsigned long val = *addr++;
-		if (val)
-			return __ffs(val) + x;
-		x += sizeof(*addr) << 3;
-	}
-	return x;
-}
-
 #ifdef __KERNEL__
 
 #include <asm-generic/bitops/sched.h>
diff --git a/include/linux/bitops.h b/include/linux/bitops.h
index 3865f2c..355d67b 100644
--- a/include/linux/bitops.h
+++ b/include/linux/bitops.h
@@ -113,6 +113,40 @@ static inline unsigned fls_long(unsigned long l)
 }
 
 #ifdef __KERNEL__
+#ifdef CONFIG_GENERIC_FIND_FIRST_BIT
+extern unsigned long __find_first_bit(const unsigned long *addr,
+		unsigned long size);
+
+/**
+ * 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.
+ */
+static __always_inline unsigned long
+find_first_bit(const unsigned long *addr, unsigned long size)
+{
+	return __find_first_bit(addr, size);
+}
+
+extern unsigned long __find_first_zero_bit(const unsigned long *addr,
+		unsigned long size);
+
+/**
+ * find_first_zero_bit - find the first cleared 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 cleared bit.
+ */
+static __always_inline unsigned long
+find_first_zero_bit(const unsigned long *addr, unsigned long size)
+{
+	return __find_first_zero_bit(addr, size);
+}
+#endif /* CONFIG_GENERIC_FIND_FIRST_BIT */
+
 #ifdef CONFIG_GENERIC_FIND_NEXT_BIT
 extern unsigned long __find_next_bit(const unsigned long *addr,
 		unsigned long size, unsigned long offset);
diff --git a/lib/Makefile b/lib/Makefile
index 23de261..14c93e1 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -30,6 +30,7 @@ obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock_debug.o
 lib-$(CONFIG_RWSEM_GENERIC_SPINLOCK) += rwsem-spinlock.o
 lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o
 lib-$(CONFIG_SEMAPHORE_SLEEPERS) += semaphore-sleepers.o
+lib-$(CONFIG_GENERIC_FIND_FIRST_BIT) += find_next_bit.o
 lib-$(CONFIG_GENERIC_FIND_NEXT_BIT) += find_next_bit.o
 obj-$(CONFIG_GENERIC_HWEIGHT) += hweight.o
 obj-$(CONFIG_LOCK_KERNEL) += kernel_lock.o
diff --git a/lib/find_next_bit.c b/lib/find_next_bit.c
index ce94c4c..d3f5784 100644
--- a/lib/find_next_bit.c
+++ b/lib/find_next_bit.c
@@ -16,6 +16,7 @@
 
 #define BITOP_WORD(nr)		((nr) / BITS_PER_LONG)
 
+#ifdef CONFIG_GENERIC_FIND_NEXT_BIT
 /*
  * Find the next set bit in a memory region.
  */
@@ -102,6 +103,63 @@ found_middle:
 	return result + ffz(tmp);
 }
 EXPORT_SYMBOL(__find_next_zero_bit);
+#endif /* CONFIG_GENERIC_FIND_NEXT_BIT */
+
+#ifdef CONFIG_GENERIC_FIND_FIRST_BIT
+/*
+ * Find the first set bit in a memory region.
+ */
+unsigned long __find_first_bit(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 == 0UL)		/* Are any bits set? */
+		return result + size;	/* Nope. */
+found:
+	return result + __ffs(tmp);
+}
+EXPORT_SYMBOL(__find_first_bit);
+
+/*
+ * Find the first cleared bit in a memory region.
+ */
+unsigned long __find_first_zero_bit(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 << size);
+	if (tmp == ~0UL)	/* Are any bits zero? */
+		return result + size;	/* Nope. */
+found:
+	return result + ffz(tmp);
+}
+EXPORT_SYMBOL(__find_first_zero_bit);
+#endif /* CONFIG_GENERIC_FIND_FIRST_BIT */
 
 #ifdef __BIG_ENDIAN
 
--
Previous message: [thread] [date] [author]
Next message: [thread] [date] [author]

Messages in current thread:
[PATCH] x86: generic versions of find_first_(zero_)bit, conv..., Alexander van Heukelum, (Mon Mar 31, 1:15 pm)
Re: [PATCH] x86: generic versions of find_first_(zero_)bit, ..., Alexander van Heukelum, (Tue Apr 1, 5:46 am)
Re: [PATCH] x86: generic versions of find_first_(zero_)bit, ..., Alexander van Heukelum, (Sun Apr 6, 2:51 pm)
Re: [PATCH] x86: generic versions of find_first_(zero_)bit, ..., Alexander van Heukelum, (Mon Apr 7, 6:25 am)
Alternative implementation of the generic __ffs, Alexander van Heukelum, (Fri Apr 18, 4:18 pm)
Re: Alternative implementation of the generic __ffs, dean gaudet, (Fri Apr 18, 7:46 pm)
Re: Alternative implementation of the generic __ffs, Harvey Harrison, (Fri Apr 18, 8:09 pm)
Re: Alternative implementation of the generic __ffs, dean gaudet, (Fri Apr 18, 8:20 pm)
Re: Alternative implementation of the generic __ffs, Joe Perches, (Fri Apr 18, 8:58 pm)
Re: Alternative implementation of the generic __ffs, Harvey Harrison, (Fri Apr 18, 9:04 pm)
Re: Alternative implementation of the generic __ffs, dean gaudet, (Fri Apr 18, 9:11 pm)
Re: Alternative implementation of the generic __ffs, Joe Perches, (Fri Apr 18, 10:55 pm)
Re: Alternative implementation of the generic __ffs, Matti Aarnio, (Sat Apr 19, 6:29 pm)
Re: Alternative implementation of the generic __ffs, Joe Perches, (Sat Apr 19, 11:06 pm)
Re: Alternative implementation of the generic __ffs, Alexander van Heukelum, (Sun Apr 20, 4:42 am)
Re: Alternative implementation of the generic __ffs, Matti Aarnio, (Sun Apr 20, 8:31 am)
Re: Alternative implementation of the generic __ffs, Alexander van Heukelum, (Mon Apr 21, 7:43 am)
Re: Alternative implementation of the generic __ffs, dean gaudet, (Sat Apr 19, 12:13 am)
Re: Alternative implementation of the generic __ffs, Alexander van Heukelum, (Sat Apr 19, 8:10 am)
Re: Alternative implementation of the generic __ffs, Joe Perches, (Sat Apr 19, 2:17 pm)
Re: Alternative implementation of the generic __ffs, Alexander van Heukelum, (Sat Apr 19, 4:26 pm)
Re: Alternative implementation of the generic __ffs, Mikael Pettersson, (Sat Apr 19, 6:05 am)
[PATCH] x86: switch x86_64 to generic find_first_bit, Alexander van Heukelum, (Tue Apr 1, 11:41 am)
[PATCH] x86: optimize find_first_bit for small bitmaps, Alexander van Heukelum, (Tue Apr 1, 11:42 am)
[PATCH] x86: remove x86-specific implementations of find_fir..., Alexander van Heukelum, (Tue Apr 1, 11:47 am)
Re: [PATCH] x86: remove x86-specific implementations of find..., Alexander van Heukelum, (Thu Apr 3, 5:34 am)
Re: [PATCH] x86: generic versions of find_first_(zero_)bit, ..., Stephen Hemminger, (Mon Mar 31, 1:22 pm)
Re: [PATCH] x86: generic versions of find_first_(zero_)bit, ..., Alexander van Heukelum, (Mon Mar 31, 3:38 pm)