lib: add fast path for find_first_*_bit() and find_last_bit()

Similarly to bitmap functions, users would benefit if we'll handle a case
of small-size bitmaps that fit into a single word.

While here, move the find_last_bit() declaration to bitops/find.h where
other find_*_bit() functions sit.

Link: https://lkml.kernel.org/r/[e-mail]
Signed-off-by: Yury Norov <[e-mail]>
Acked-by: Rasmus Villemoes <[e-mail]>
Acked-by: Andy Shevchenko <[e-mail]>
Cc: Alexey Klimov <[e-mail]>
Cc: Arnd Bergmann <[e-mail]>
Cc: David Sterba <[e-mail]>
Cc: Dennis Zhou <[e-mail]>
Cc: Geert Uytterhoeven <[e-mail]>
Cc: Jianpeng Ma <[e-mail]>
Cc: Joe Perches <[e-mail]>
Cc: John Paul Adrian Glaubitz <[e-mail]>
Cc: Josh Poimboeuf <[e-mail]>
Cc: Rich Felker <[e-mail]>
Cc: Stefano Brivio <[e-mail]>
Cc: Wei Yang <[e-mail]>
Cc: Wolfram Sang <[e-mail]>
Cc: Yoshinori Sato <[e-mail]>
Signed-off-by: Andrew Morton <[e-mail]>
Signed-off-by: Linus Torvalds <[e-mail]>

include/asm-generic/bitops/find.h

···
 extern unsigned long _find_next_bit(const unsigned long *addr1,
 		const unsigned long *addr2, unsigned long nbits,
 		unsigned long start, unsigned long invert, unsigned long le);
+extern unsigned long _find_first_bit(const unsigned long *addr, unsigned long size);
+extern unsigned long _find_first_zero_bit(const unsigned long *addr, unsigned long size);
+extern unsigned long _find_last_bit(const unsigned long *addr, unsigned long size);
 
 #ifndef find_next_bit
 /**
···
  * Returns the bit number of the first set bit.
  * If no bits are set, returns @size.
  */
-extern unsigned long find_first_bit(const unsigned long *addr,
-				    unsigned long size);
+static inline
+unsigned long find_first_bit(const unsigned long *addr, unsigned long size)
+{
+	if (small_const_nbits(size)) {
+		unsigned long val = *addr & GENMASK(size - 1, 0);
+
+		return val ? __ffs(val) : size;
+	}
+
+	return _find_first_bit(addr, size);
+}
 
 /**
  * find_first_zero_bit - find the first cleared bit in a memory region
···
  * Returns the bit number of the first cleared bit.
  * If no bits are zero, returns @size.
  */
-extern unsigned long find_first_zero_bit(const unsigned long *addr,
-					 unsigned long size);
+static inline
+unsigned long find_first_zero_bit(const unsigned long *addr, unsigned long size)
+{
+	if (small_const_nbits(size)) {
+		unsigned long val = *addr | ~GENMASK(size - 1, 0);
+
+		return val == ~0UL ? size : ffz(val);
+	}
+
+	return _find_first_zero_bit(addr, size);
+}
 #else /* CONFIG_GENERIC_FIND_FIRST_BIT */
 
 #ifndef find_first_bit
···
 #endif
 
 #endif /* CONFIG_GENERIC_FIND_FIRST_BIT */
+
+#ifndef find_last_bit
+/**
+ * find_last_bit - find the last set bit in a memory region
+ * @addr: The address to start the search at
+ * @size: The number of bits to search
+ *
+ * Returns the bit number of the last set bit, or size.
+ */
+static inline
+unsigned long find_last_bit(const unsigned long *addr, unsigned long size)
+{
+	if (small_const_nbits(size)) {
+		unsigned long val = *addr & GENMASK(size - 1, 0);
+
+		return val ? __fls(val) : size;
+	}
+
+	return _find_last_bit(addr, size);
+}
+#endif
 
 /**
  * find_next_clump8 - find next 8-bit clump with set bits in a memory region

include/linux/bitops.h

···
 })
 #endif
 
-#ifndef find_last_bit
-/**
- * find_last_bit - find the last set bit in a memory region
- * @addr: The address to start the search at
- * @size: The number of bits to search
- *
- * Returns the bit number of the last set bit, or size.
- */
-extern unsigned long find_last_bit(const unsigned long *addr,
-				   unsigned long size);
-#endif
-
 #endif /* __KERNEL__ */
 #endif

lib/find_bit.c

···
 /*
  * Find the first set bit in a memory region.
  */
-unsigned long find_first_bit(const unsigned long *addr, unsigned long size)
+unsigned long _find_first_bit(const unsigned long *addr, unsigned long size)
 {
 	unsigned long idx;
 
···
 
 	return size;
 }
-EXPORT_SYMBOL(find_first_bit);
+EXPORT_SYMBOL(_find_first_bit);
 #endif
 
 #ifndef find_first_zero_bit
 /*
  * Find the first cleared bit in a memory region.
  */
-unsigned long find_first_zero_bit(const unsigned long *addr, unsigned long size)
+unsigned long _find_first_zero_bit(const unsigned long *addr, unsigned long size)
 {
 	unsigned long idx;
 
···
 
 	return size;
 }
-EXPORT_SYMBOL(find_first_zero_bit);
+EXPORT_SYMBOL(_find_first_zero_bit);
 #endif
 
 #ifndef find_last_bit
-unsigned long find_last_bit(const unsigned long *addr, unsigned long size)
+unsigned long _find_last_bit(const unsigned long *addr, unsigned long size)
 {
 	if (size) {
 		unsigned long val = BITMAP_LAST_WORD_MASK(size);
···
 	}
 	return size;
 }
-EXPORT_SYMBOL(find_last_bit);
+EXPORT_SYMBOL(_find_last_bit);
 #endif
 
 unsigned long find_next_clump8(unsigned long *clump, const unsigned long *addr,