[PATCH 5/6] lib: add fast path for find_next_*_bit()

From: Yury Norov <yury.norov@gmail.com>
To: linux-m68k@lists.linux-m68k.org, linux-kernel@vger.kernel.org,
	linux-sh@vger.kernel.org, linux-arch@vger.kernel.org
Cc: Yury Norov <yury.norov@gmail.com>,
	Geert Uytterhoeven <geert@linux-m68k.org>,
	Yoshinori Sato <ysato@users.sourceforge.jp>,
	Rich Felker <dalias@libc.org>, Arnd Bergmann <arnd@arndb.de>,
	Dennis Zhou <dennis@kernel.org>,
	Andrew Morton <akpm@linux-foundation.org>,
	Wolfram Sang <wsa+renesas@sang-engineering.com>,
	David Sterba <dsterba@suse.com>,
	Andy Shevchenko <andriy.shevchenko@linux.intel.com>,
	Stefano Brivio <sbrivio@redhat.com>,
	"Ma, Jianpeng" <jianpeng.ma@intel.com>,
	Wei Yang <richard.weiyang@linux.alibaba.com>,
	Josh Poimboeuf <jpoimboe@redhat.com>,
	Rasmus Villemoes <rasmus.villemoes@prevas.dk>
Subject: [PATCH 5/6] lib: add fast path for find_next_*_bit()
Date: Wed, 20 Jan 2021 16:06:29 -0800	[thread overview]
Message-ID: <20210121000630.371883-6-yury.norov@gmail.com> (raw)
In-Reply-To: <20210121000630.371883-1-yury.norov@gmail.com>

Similarly to bitmap functions, find_next_*_bit() users will benefit
if we'll handle a case of bitmaps that fit into a single word. In the
very best case, the compiler may replace a function call with a
single ffs or ffz instruction.

Signed-off-by: Yury Norov <yury.norov@gmail.com>
---
 include/asm-generic/bitops/find.h | 39 +++++++++++++++++++++++++++++++
 include/asm-generic/bitops/le.h   | 28 ++++++++++++++++++++++
 2 files changed, 67 insertions(+)

diff --git a/include/asm-generic/bitops/find.h b/include/asm-generic/bitops/find.h
index 7ad70dab8e93..d45096069011 100644
--- a/include/asm-generic/bitops/find.h
+++ b/include/asm-generic/bitops/find.h
@@ -20,6 +20,18 @@ static inline
 unsigned long find_next_bit(const unsigned long *addr, unsigned long size,
 			    unsigned long offset)
 {
+	if (small_const_nbits(size)) {
+		unsigned long val;
+
+		if (unlikely(offset >= size))
+			return size;
+
+		val = *addr & BITMAP_FIRST_WORD_MASK(offset)
+				& BITMAP_LAST_WORD_MASK(size);
+
+		return val ? __ffs(val) : size;
+	}
+
 	return _find_next_bit(addr, NULL, size, offset, 0UL, 0);
 }
 #endif
@@ -40,6 +52,18 @@ unsigned long find_next_and_bit(const unsigned long *addr1,
 		const unsigned long *addr2, unsigned long size,
 		unsigned long offset)
 {
+	if (small_const_nbits(size)) {
+		unsigned long val;
+
+		if (unlikely(offset >= size))
+			return size;
+
+		val = *addr1 & *addr2 & BITMAP_FIRST_WORD_MASK(offset)
+				      & BITMAP_LAST_WORD_MASK(size);
+
+		return val ? __ffs(val) : size;
+	}
+
 	return _find_next_bit(addr1, addr2, size, offset, 0UL, 0);
 }
 #endif
@@ -58,6 +82,21 @@ static inline
 unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size,
 				 unsigned long offset)
 {
+	if (small_const_nbits(size)) {
+		unsigned long val, idx;
+
+		if (unlikely(offset >= size))
+			return size;
+
+		val = *addr | ~BITMAP_FIRST_WORD_MASK(offset);
+		if (val == ~0UL)
+			return size;
+
+		idx = ffz(val);
+
+		return idx < size ? idx : size;
+	}
+
 	return _find_next_bit(addr, NULL, size, offset, ~0UL, 0);
 }
 #endif
diff --git a/include/asm-generic/bitops/le.h b/include/asm-generic/bitops/le.h
index 4cf44ea16ec0..f4a76d3d145f 100644
--- a/include/asm-generic/bitops/le.h
+++ b/include/asm-generic/bitops/le.h
@@ -5,6 +5,7 @@
 #include <asm/types.h>
 #include <asm/byteorder.h>
 #include <asm-generic/bitops/find.h>
+#include <linux/swab.h>
 
 #if defined(__LITTLE_ENDIAN)
 
@@ -37,6 +38,21 @@ static inline
 unsigned long find_next_zero_bit_le(const void *addr, unsigned
 		long size, unsigned long offset)
 {
+	if (small_const_nbits(size)) {
+		unsigned long val = *(const unsigned long *)addr, idx;
+
+		if (unlikely(offset >= size))
+			return size;
+
+		val = swab(val) | ~BITMAP_FIRST_WORD_MASK(offset);
+		if (val == ~0UL)
+			return size;
+
+		idx = ffz(val);
+
+		return idx < size ? idx : size;
+	}
+
 	return _find_next_bit(addr, NULL, size, offset, ~0UL, 1);
 }
 #endif
@@ -46,6 +62,18 @@ static inline
 unsigned long find_next_bit_le(const void *addr, unsigned
 		long size, unsigned long offset)
 {
+	if (small_const_nbits(size)) {
+		unsigned long val = *(const unsigned long *)addr;
+
+		if (unlikely(offset >= size))
+			return size;
+
+		val = swab(val) & BITMAP_FIRST_WORD_MASK(offset)
+				& BITMAP_LAST_WORD_MASK(size);
+
+		return val ? __ffs(val) : size;
+	}
+
 	return _find_next_bit(addr, NULL, size, offset, 0UL, 1);
 }
 #endif
-- 
2.25.1

