From 0f7b468b6eace87ecdc59b3ec8476d50b0561ac2 Mon Sep 17 00:00:00 2001
From: Michael Hennerich <michael.hennerich@analog.com>
Date: Tue, 22 Dec 2009 11:32:06 +0000
Subject: [PATCH] Blackfin: add optimized version of Hamming Weight functions

Signed-off-by: Michael Hennerich <michael.hennerich@analog.com>
Signed-off-by: Mike Frysinger <vapier@gentoo.org>
---
 arch/blackfin/Kconfig              |  3 --
 arch/blackfin/include/asm/bitops.h | 74 ++++++++++++++++++++++++++++----------
 2 files changed, 55 insertions(+), 22 deletions(-)

diff --git a/arch/blackfin/Kconfig b/arch/blackfin/Kconfig
index 3bd8e83..b483639 100644
--- a/arch/blackfin/Kconfig
+++ b/arch/blackfin/Kconfig
@@ -45,9 +45,6 @@ config ZONE_DMA
 config GENERIC_FIND_NEXT_BIT
 	def_bool y
 
-config GENERIC_HWEIGHT
-	def_bool y
-
 config GENERIC_HARDIRQS
 	def_bool y
 
diff --git a/arch/blackfin/include/asm/bitops.h b/arch/blackfin/include/asm/bitops.h
index a2ff3fb..605ba8e 100644
--- a/arch/blackfin/include/asm/bitops.h
+++ b/arch/blackfin/include/asm/bitops.h
@@ -7,22 +7,41 @@
 #ifndef _BLACKFIN_BITOPS_H
 #define _BLACKFIN_BITOPS_H
 
-#ifndef CONFIG_SMP
-# include <asm-generic/bitops.h>
-#else
+#include <linux/compiler.h>
+
+#include <asm-generic/bitops/__ffs.h>
+#include <asm-generic/bitops/ffz.h>
+#include <asm-generic/bitops/fls.h>
+#include <asm-generic/bitops/__fls.h>
+#include <asm-generic/bitops/fls64.h>
+#include <asm-generic/bitops/find.h>
 
 #ifndef _LINUX_BITOPS_H
 #error only <linux/bitops.h> can be included directly
 #endif
 
-#include <linux/compiler.h>
-#include <asm/byteorder.h>	/* swab32 */
-
-#include <asm-generic/bitops/ffs.h>
-#include <asm-generic/bitops/__ffs.h>
 #include <asm-generic/bitops/sched.h>
-#include <asm-generic/bitops/ffz.h>
+#include <asm-generic/bitops/ffs.h>
+#include <asm-generic/bitops/lock.h>
+#include <asm-generic/bitops/ext2-non-atomic.h>
+#include <asm-generic/bitops/ext2-atomic.h>
+#include <asm-generic/bitops/minix.h>
+
+#ifndef CONFIG_SMP
+#include <linux/irqflags.h>
+
+/*
+ * clear_bit may not imply a memory barrier
+ */
+#ifndef smp_mb__before_clear_bit
+#define smp_mb__before_clear_bit()	smp_mb()
+#define smp_mb__after_clear_bit()	smp_mb()
+#endif
+#include <asm-generic/bitops/atomic.h>
+#include <asm-generic/bitops/non-atomic.h>
+#else
 
+#include <asm/byteorder.h>	/* swab32 */
 #include <linux/linkage.h>
 
 asmlinkage int __raw_bit_set_asm(volatile unsigned long *addr, int nr);
@@ -89,19 +108,36 @@ static inline int test_and_change_bit(int nr, volatile unsigned long *addr)
 
 #include <asm-generic/bitops/non-atomic.h>
 
-#include <asm-generic/bitops/find.h>
-#include <asm-generic/bitops/hweight.h>
-#include <asm-generic/bitops/lock.h>
+#endif /* CONFIG_SMP */
 
-#include <asm-generic/bitops/ext2-atomic.h>
-#include <asm-generic/bitops/ext2-non-atomic.h>
+/*
+ * hweightN: returns the hamming weight (i.e. the number
+ * of bits set) of a N-bit word
+ */
 
-#include <asm-generic/bitops/minix.h>
+static inline unsigned int hweight32(unsigned int w)
+{
+	unsigned int res;
 
-#include <asm-generic/bitops/fls.h>
-#include <asm-generic/bitops/__fls.h>
-#include <asm-generic/bitops/fls64.h>
+	__asm__ ("%0.l = ONES %0;"
+		"%0 = %0.l (Z);"
+		: "=d" (res) : "d" (w));
+	return res;
+}
 
-#endif /* CONFIG_SMP */
+static inline unsigned int hweight64(__u64 w)
+{
+	return hweight32((unsigned int)(w >> 32)) + hweight32((unsigned int)w);
+}
+
+static inline unsigned int hweight16(unsigned int w)
+{
+	return hweight32(w & 0xffff);
+}
+
+static inline unsigned int hweight8(unsigned int w)
+{
+	return hweight32(w & 0xff);
+}
 
 #endif				/* _BLACKFIN_BITOPS_H */
-- 
1.8.2.3