From: Alexander van Heukelum <heukelum@mailshack.com>
Date: Tue, 1 Apr 2008 15:42:21 +0000 (+0200)
Subject: x86: optimize find_first_bit for small bitmaps
X-Git-Tag: v2.6.26-rc1~1037^2~4
X-Git-Url: http://pilppa.com/gitweb/?a=commitdiff_plain;h=3a48305028aa38afba93fc05066c71a6ee668ad8;p=linux-2.6-omap-h63xx.git

x86: optimize find_first_bit for small bitmaps

Avoid a call to find_first_bit if the bitmap size is know at
compile time and small enough to fit in a single long integer.
Modeled after an optimization in the original x86_64-specific
code.

Signed-off-by: Alexander van Heukelum <heukelum@fastmail.fm>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---

diff --git a/include/linux/bitops.h b/include/linux/bitops.h
index 355d67ba3bd..48bde600a2d 100644
--- a/include/linux/bitops.h
+++ b/include/linux/bitops.h
@@ -127,6 +127,20 @@ extern unsigned long __find_first_bit(const unsigned long *addr,
 static __always_inline unsigned long
 find_first_bit(const unsigned long *addr, unsigned long size)
 {
+	/* Avoid a function call if the bitmap size is a constant */
+	/* and not bigger than BITS_PER_LONG. */
+
+	/* insert a sentinel so that __ffs returns size if there */
+	/* are no set bits in the bitmap */
+	if (__builtin_constant_p(size) && (size < BITS_PER_LONG))
+		return __ffs((*addr) | (1ul << size));
+
+	/* the result of __ffs(0) is undefined, so it needs to be */
+	/* handled separately */
+	if (__builtin_constant_p(size) && (size == BITS_PER_LONG))
+		return ((*addr) == 0) ? BITS_PER_LONG : __ffs(*addr);
+
+	/* size is not constant or too big */
 	return __find_first_bit(addr, size);
 }
 
@@ -143,6 +157,21 @@ extern unsigned long __find_first_zero_bit(const unsigned long *addr,
 static __always_inline unsigned long
 find_first_zero_bit(const unsigned long *addr, unsigned long size)
 {
+	/* Avoid a function call if the bitmap size is a constant */
+	/* and not bigger than BITS_PER_LONG. */
+
+	/* insert a sentinel so that __ffs returns size if there */
+	/* are no set bits in the bitmap */
+	if (__builtin_constant_p(size) && (size < BITS_PER_LONG)) {
+		return __ffs(~(*addr) | (1ul << size));
+	}
+
+	/* the result of __ffs(0) is undefined, so it needs to be */
+	/* handled separately */
+	if (__builtin_constant_p(size) && (size == BITS_PER_LONG))
+		return (~(*addr) == 0) ? BITS_PER_LONG : __ffs(~(*addr));
+
+	/* size is not constant or too big */
 	return __find_first_zero_bit(addr, size);
 }
 #endif /* CONFIG_GENERIC_FIND_FIRST_BIT */