find: micro-optimize for_each_{set,clear}_bit()

The macros iterate thru all set/clear bits in a bitmap. They search a
first bit using find_first_bit(), and the rest bits using find_next_bit().

Since find_next_bit() is called shortly after find_first_bit(), we can
save few lines of I-cache by not using find_first_bit().

Signed-off-by: Yury Norov <yury.norov@gmail.com>
Tested-by: Wolfram Sang <wsa+renesas@sang-engineering.com>

include/linux/find.h

@@ -280,7 +280,7 @@ unsigned long find_next_bit_le(const void *addr, unsigned
 #endif
 
 #define for_each_set_bit(bit, addr, size) \
-	for ((bit) = find_first_bit((addr), (size));		\
+	for ((bit) = find_next_bit((addr), (size), 0);		\
 	     (bit) < (size);					\
 	     (bit) = find_next_bit((addr), (size), (bit) + 1))
 
@@ -291,7 +291,7 @@ unsigned long find_next_bit_le(const void *addr, unsigned
 	     (bit) = find_next_bit((addr), (size), (bit) + 1))
 
 #define for_each_clear_bit(bit, addr, size) \
-	for ((bit) = find_first_zero_bit((addr), (size));	\
+	for ((bit) = find_next_zero_bit((addr), (size), 0);	\
 	     (bit) < (size);					\
 	     (bit) = find_next_zero_bit((addr), (size), (bit) + 1))