[patch 23/91] lib: add fast path for find_first_*_bit() and find_last_bit()

[Andrew Morton <akpm@linux-foundation.org>]

From: Yury Norov <yury.norov@gmail.com>
Subject: 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/20210401003153.97325-11-yury.norov@gmail.com
Signed-off-by: Yury Norov <yury.norov@gmail.com>
Acked-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Acked-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Cc: Alexey Klimov <aklimov@redhat.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: David Sterba <dsterba@suse.com>
Cc: Dennis Zhou <dennis@kernel.org>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Jianpeng Ma <jianpeng.ma@intel.com>
Cc: Joe Perches <joe@perches.com>
Cc: John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Rich Felker <dalias@libc.org>
Cc: Stefano Brivio <sbrivio@redhat.com>
Cc: Wei Yang <richard.weiyang@linux.alibaba.com>
Cc: Wolfram Sang <wsa+renesas@sang-engineering.com>
Cc: Yoshinori Sato <ysato@users.osdn.me>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 include/asm-generic/bitops/find.h |   50 +++++++++++++++++++++++++---
 include/linux/bitops.h            |   12 ------
 lib/find_bit.c                    |   12 +++---
 3 files changed, 52 insertions(+), 22 deletions(-)

--- a/include/asm-generic/bitops/find.h~lib-add-fast-path-for-find_first__bit-and-find_last_bit
+++ a/include/asm-generic/bitops/find.h
@@ -5,6 +5,9 @@
 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
 /**
@@ -102,8 +105,17 @@ unsigned long find_next_zero_bit(const u
  * 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
@@ -113,8 +125,17 @@ extern unsigned long find_first_bit(cons
  * 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
@@ -126,6 +147,27 @@ extern unsigned long find_first_zero_bit
 
 #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
  * @clump: location to store copy of found clump
--- a/include/linux/bitops.h~lib-add-fast-path-for-find_first__bit-and-find_last_bit
+++ a/include/linux/bitops.h
@@ -286,17 +286,5 @@ static __always_inline void __assign_bit
 })
 #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
--- a/lib/find_bit.c~lib-add-fast-path-for-find_first__bit-and-find_last_bit
+++ a/lib/find_bit.c
@@ -75,7 +75,7 @@ EXPORT_SYMBOL(_find_next_bit);
 /*
  * 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;
 
@@ -86,14 +86,14 @@ unsigned long find_first_bit(const unsig
 
 	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;
 
@@ -104,11 +104,11 @@ unsigned long find_first_zero_bit(const
 
 	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);
@@ -124,7 +124,7 @@ unsigned long find_last_bit(const unsign
 	}
 	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,
_