All of lore.kernel.org
 help / color / mirror / Atom feed
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>,
	John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de>
Subject: [PATCH 4/5] lib: add fast path for find_next_*_bit()
Date: Fri, 29 Jan 2021 12:45:27 -0800	[thread overview]
Message-ID: <20210129204528.2118168-6-yury.norov@gmail.com> (raw)
In-Reply-To: <20210129204528.2118168-1-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       | 30 +++++++++++++++++++++++++
 include/asm-generic/bitops/le.h         | 21 +++++++++++++++++
 tools/include/asm-generic/bitops/find.h | 30 +++++++++++++++++++++++++
 3 files changed, 81 insertions(+)

diff --git a/include/asm-generic/bitops/find.h b/include/asm-generic/bitops/find.h
index 7ad70dab8e93..8bd7a33a889d 100644
--- a/include/asm-generic/bitops/find.h
+++ b/include/asm-generic/bitops/find.h
@@ -20,6 +20,16 @@ static inline
 unsigned long find_next_bit(const unsigned long *addr, unsigned long size,
 			    unsigned long offset)
 {
+	if (SMALL_CONST(size - 1)) {
+		unsigned long val;
+
+		if (unlikely(offset >= size))
+			return size;
+
+		val = *addr & GENMASK(size - 1, offset);
+		return val ? __ffs(val) : size;
+	}
+
 	return _find_next_bit(addr, NULL, size, offset, 0UL, 0);
 }
 #endif
@@ -40,6 +50,16 @@ unsigned long find_next_and_bit(const unsigned long *addr1,
 		const unsigned long *addr2, unsigned long size,
 		unsigned long offset)
 {
+	if (SMALL_CONST(size - 1)) {
+		unsigned long val;
+
+		if (unlikely(offset >= size))
+			return size;
+
+		val = *addr1 & *addr2 & GENMASK(size - 1, offset);
+		return val ? __ffs(val) : size;
+	}
+
 	return _find_next_bit(addr1, addr2, size, offset, 0UL, 0);
 }
 #endif
@@ -58,6 +78,16 @@ static inline
 unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size,
 				 unsigned long offset)
 {
+	if (SMALL_CONST(size - 1)) {
+		unsigned long val;
+
+		if (unlikely(offset >= size))
+			return size;
+
+		val = *addr | ~GENMASK(size - 1, offset);
+		return val == ~0UL ? size : ffz(val);
+	}
+
 	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 21305f6cea0b..18ebcf639d7f 100644
--- a/include/asm-generic/bitops/le.h
+++ b/include/asm-generic/bitops/le.h
@@ -5,6 +5,7 @@
 #include <asm-generic/bitops/find.h>
 #include <asm/types.h>
 #include <asm/byteorder.h>
+#include <linux/swab.h>
 
 #if defined(__LITTLE_ENDIAN)
 
@@ -37,6 +38,16 @@ static inline
 unsigned long find_next_zero_bit_le(const void *addr, unsigned
 		long size, unsigned long offset)
 {
+	if (SMALL_CONST(size)) {
+		unsigned long val = *(const unsigned long *)addr;
+
+		if (unlikely(offset >= size))
+			return size;
+
+		val = swab(val) | ~GENMASK(size - 1, offset);
+		return val == ~0UL ? size : ffz(val);
+	}
+
 	return _find_next_bit(addr, NULL, size, offset, ~0UL, 1);
 }
 #endif
@@ -46,6 +57,16 @@ static inline
 unsigned long find_next_bit_le(const void *addr, unsigned
 		long size, unsigned long offset)
 {
+	if (SMALL_CONST(size)) {
+		unsigned long val = *(const unsigned long *)addr;
+
+		if (unlikely(offset >= size))
+			return size;
+
+		val = swab(val) & GENMASK(size - 1, offset);
+		return val ? __ffs(val) : size;
+	}
+
 	return _find_next_bit(addr, NULL, size, offset, 0UL, 1);
 }
 #endif
diff --git a/tools/include/asm-generic/bitops/find.h b/tools/include/asm-generic/bitops/find.h
index 9fe62d10b084..eff868bd22f8 100644
--- a/tools/include/asm-generic/bitops/find.h
+++ b/tools/include/asm-generic/bitops/find.h
@@ -20,6 +20,16 @@ static inline
 unsigned long find_next_bit(const unsigned long *addr, unsigned long size,
 			    unsigned long offset)
 {
+	if (SMALL_CONST(size - 1)) {
+		unsigned long val;
+
+		if (unlikely(offset >= size))
+			return size;
+
+		val = *addr & GENMASK(size - 1, offset);
+		return val ? __ffs(val) : size;
+	}
+
 	return _find_next_bit(addr, NULL, size, offset, 0UL, 0);
 }
 #endif
@@ -40,6 +50,16 @@ unsigned long find_next_and_bit(const unsigned long *addr1,
 		const unsigned long *addr2, unsigned long size,
 		unsigned long offset)
 {
+	if (SMALL_CONST(size - 1)) {
+		unsigned long val;
+
+		if (unlikely(offset >= size))
+			return size;
+
+		val = *addr1 & *addr2 & GENMASK(size - 1, offset);
+		return val ? __ffs(val) : size;
+	}
+
 	return _find_next_bit(addr1, addr2, size, offset, 0UL, 0);
 }
 #endif
@@ -58,6 +78,16 @@ static inline
 unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size,
 				 unsigned long offset)
 {
+	if (SMALL_CONST(size - 1)) {
+		unsigned long val;
+
+		if (unlikely(offset >= size))
+			return size;
+
+		val = *addr | ~GENMASK(size - 1, offset);
+		return val == ~0UL ? size : ffz(val);
+	}
+
 	return _find_next_bit(addr, NULL, size, offset, ~0UL, 0);
 }
 #endif
-- 
2.25.1


  parent reply	other threads:[~2021-01-29 20:48 UTC|newest]

Thread overview: 13+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-01-29 20:45 [PATCH 0/6] lib/find_bit: fast path for small bitmaps Yury Norov
2021-01-29 20:45 ` [PATCH 1/6] arch: rearrange headers inclusion order in asm/bitops for m68k and sh Yury Norov
2021-01-29 20:45 ` [PATCH 2/6] lib: inttroduce BITS_{FIRST,LAST}() macro Yury Norov
2021-01-29 20:45 ` [PATCH 2/5] bits_per_long.h: introduce SMALL_CONST() macro Yury Norov
2021-01-29 21:10   ` Andy Shevchenko
2021-01-29 21:24     ` Joe Perches
2021-01-29 21:28     ` Yury Norov
2021-01-29 22:25     ` Yury Norov
2021-01-29 20:45 ` [PATCH 3/5] lib: inline _find_next_bit() wrappers Yury Norov
2021-01-29 20:45 ` Yury Norov [this message]
2021-01-29 20:45 ` [PATCH 6/6] lib: add fast path for find_first_*_bit() and find_last_bit() Yury Norov
2021-01-29 20:51 ` [PATCH 0/6] lib/find_bit: fast path for small bitmaps Yury Norov
2021-01-29 21:12   ` Andy Shevchenko

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20210129204528.2118168-6-yury.norov@gmail.com \
    --to=yury.norov@gmail.com \
    --cc=akpm@linux-foundation.org \
    --cc=andriy.shevchenko@linux.intel.com \
    --cc=arnd@arndb.de \
    --cc=dalias@libc.org \
    --cc=dennis@kernel.org \
    --cc=dsterba@suse.com \
    --cc=geert@linux-m68k.org \
    --cc=glaubitz@physik.fu-berlin.de \
    --cc=jianpeng.ma@intel.com \
    --cc=jpoimboe@redhat.com \
    --cc=linux-arch@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-m68k@lists.linux-m68k.org \
    --cc=linux-sh@vger.kernel.org \
    --cc=richard.weiyang@linux.alibaba.com \
    --cc=sbrivio@redhat.com \
    --cc=wsa+renesas@sang-engineering.com \
    --cc=ysato@users.sourceforge.jp \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body. 
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.