[PATCH] x86_64: fls in asm for x86_64

Use single instruction for find largest set bit on x86_64.

[Updated by Jan Beulich to fix wrong asm constraints in original
patch -AK]

Cc: jbeulich@novell.com
Signed-off-by: Stephen Hemminger <shemminger@osdl.org>
Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

diff --git a/include/asm-x86_64/bitops.h b/include/asm-x86_64/bitops.h
index 3638ffff87fd7abf6b7938058a25dd65f0a1b773..eb4df23e1e411c45c19d9de8d701b8fd30bcdfaa 100644 (file)
--- a/include/asm-x86_64/bitops.h
+++ b/include/asm-x86_64/bitops.h
@@ -396,6 +396,22 @@ static __inline__ int fls64(__u64 x)
        return __fls(x) + 1;
 }
 
+/**
+ * fls - find last bit set
+ * @x: the word to search
+ *
+ * This is defined the same way as ffs.
+ */
+static __inline__ int fls(int x)
+{
+       int r;
+
+       __asm__("bsrl %1,%0\n\t"
+               "cmovzl %2,%0"
+               : "=&r" (r) : "rm" (x), "rm" (-1));
+       return r+1;
+}
+
 /**
  * hweightN - returns the hamming weight of a N-bit word
  * @x: the word to weigh
@@ -434,9 +450,6 @@ static __inline__ int fls64(__u64 x)
 #define minix_find_first_zero_bit(addr,size) \
        find_first_zero_bit((void*)addr,size)
 
-/* find last set bit */
-#define fls(x) generic_fls(x)
-
 #endif /* __KERNEL__ */
 
 #endif /* _X86_64_BITOPS_H */