diff mbox series

[6/8] lib: inline _find_next_bit() wrappers

Message ID 20210130191719.7085-7-yury.norov@gmail.com (mailing list archive)
State New
Headers show
Series lib/find_bit: fast path for small bitmaps | expand

Commit Message

Yury Norov Jan. 30, 2021, 7:17 p.m. UTC
lib/find_bit.c declares five single-line wrappers for _find_next_bit().
We may turn those wrappers to inline functions. It eliminates unneeded
function calls and opens room for compile-time optimizations.

Signed-off-by: Yury Norov <yury.norov@gmail.com>
---
 include/asm-generic/bitops/find.h       | 28 ++++++++++---
 include/asm-generic/bitops/le.h         | 17 ++++++--
 lib/find_bit.c                          | 56 +------------------------
 tools/include/asm-generic/bitops/find.h | 27 +++++++++---
 tools/lib/find_bit.c                    | 52 ++++++++++-------------
 5 files changed, 79 insertions(+), 101 deletions(-)

Comments

Andy Shevchenko Feb. 1, 2021, 1:47 p.m. UTC | #1
On Sat, Jan 30, 2021 at 11:17:17AM -0800, Yury Norov wrote:
> lib/find_bit.c declares five single-line wrappers for _find_next_bit().
> We may turn those wrappers to inline functions. It eliminates unneeded
> function calls and opens room for compile-time optimizations.

>  tools/include/asm-generic/bitops/find.h | 27 +++++++++---
>  tools/lib/find_bit.c                    | 52 ++++++++++-------------

In a separated patch, please. I don't think we need to defer this series in
case if tools lagged (which is usual case in my practice).
Yury Norov Feb. 2, 2021, 7:13 a.m. UTC | #2
On Mon, Feb 1, 2021 at 5:47 AM Andy Shevchenko
<andriy.shevchenko@linux.intel.com> wrote:
>
> On Sat, Jan 30, 2021 at 11:17:17AM -0800, Yury Norov wrote:
> > lib/find_bit.c declares five single-line wrappers for _find_next_bit().
> > We may turn those wrappers to inline functions. It eliminates unneeded
> > function calls and opens room for compile-time optimizations.
>
> >  tools/include/asm-generic/bitops/find.h | 27 +++++++++---
> >  tools/lib/find_bit.c                    | 52 ++++++++++-------------
>
> In a separated patch, please. I don't think we need to defer this series in
> case if tools lagged (which is usual case in my practice).

Splitting it to kernel and tools parts means either a patch bomb for tools or
doubling the size of the series. Both options look worse than what we have now.

Can you explain more on the lagged tools argument?

> --
> With Best Regards,
> Andy Shevchenko
>
>
diff mbox series

Patch

diff --git a/include/asm-generic/bitops/find.h b/include/asm-generic/bitops/find.h
index 9fdf21302fdf..7ad70dab8e93 100644
--- a/include/asm-generic/bitops/find.h
+++ b/include/asm-generic/bitops/find.h
@@ -2,6 +2,10 @@ 
 #ifndef _ASM_GENERIC_BITOPS_FIND_H_
 #define _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);
+
 #ifndef find_next_bit
 /**
  * find_next_bit - find the next set bit in a memory region
@@ -12,8 +16,12 @@ 
  * Returns the bit number for the next set bit
  * If no bits are set, returns @size.
  */
-extern unsigned long find_next_bit(const unsigned long *addr, unsigned long
-		size, unsigned long offset);
+static inline
+unsigned long find_next_bit(const unsigned long *addr, unsigned long size,
+			    unsigned long offset)
+{
+	return _find_next_bit(addr, NULL, size, offset, 0UL, 0);
+}
 #endif
 
 #ifndef find_next_and_bit
@@ -27,9 +35,13 @@  extern unsigned long find_next_bit(const unsigned long *addr, unsigned long
  * Returns the bit number for the next set bit
  * If no bits are set, returns @size.
  */
-extern unsigned long find_next_and_bit(const unsigned long *addr1,
+static inline
+unsigned long find_next_and_bit(const unsigned long *addr1,
 		const unsigned long *addr2, unsigned long size,
-		unsigned long offset);
+		unsigned long offset)
+{
+	return _find_next_bit(addr1, addr2, size, offset, 0UL, 0);
+}
 #endif
 
 #ifndef find_next_zero_bit
@@ -42,8 +54,12 @@  extern unsigned long find_next_and_bit(const unsigned long *addr1,
  * Returns the bit number of the next zero bit
  * If no bits are zero, returns @size.
  */
-extern unsigned long find_next_zero_bit(const unsigned long *addr, unsigned
-		long size, unsigned long offset);
+static inline
+unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size,
+				 unsigned long offset)
+{
+	return _find_next_bit(addr, NULL, size, offset, ~0UL, 0);
+}
 #endif
 
 #ifdef CONFIG_GENERIC_FIND_FIRST_BIT
diff --git a/include/asm-generic/bitops/le.h b/include/asm-generic/bitops/le.h
index 188d3eba3ace..21305f6cea0b 100644
--- a/include/asm-generic/bitops/le.h
+++ b/include/asm-generic/bitops/le.h
@@ -2,6 +2,7 @@ 
 #ifndef _ASM_GENERIC_BITOPS_LE_H_
 #define _ASM_GENERIC_BITOPS_LE_H_
 
+#include <asm-generic/bitops/find.h>
 #include <asm/types.h>
 #include <asm/byteorder.h>
 
@@ -32,13 +33,21 @@  static inline unsigned long find_first_zero_bit_le(const void *addr,
 #define BITOP_LE_SWIZZLE	((BITS_PER_LONG-1) & ~0x7)
 
 #ifndef find_next_zero_bit_le
-extern unsigned long find_next_zero_bit_le(const void *addr,
-		unsigned long size, unsigned long offset);
+static inline
+unsigned long find_next_zero_bit_le(const void *addr, unsigned
+		long size, unsigned long offset)
+{
+	return _find_next_bit(addr, NULL, size, offset, ~0UL, 1);
+}
 #endif
 
 #ifndef find_next_bit_le
-extern unsigned long find_next_bit_le(const void *addr,
-		unsigned long size, unsigned long offset);
+static inline
+unsigned long find_next_bit_le(const void *addr, unsigned
+		long size, unsigned long offset)
+{
+	return _find_next_bit(addr, NULL, size, offset, 0UL, 1);
+}
 #endif
 
 #ifndef find_first_zero_bit_le
diff --git a/lib/find_bit.c b/lib/find_bit.c
index 8c2a71a18793..2470ae390f3c 100644
--- a/lib/find_bit.c
+++ b/lib/find_bit.c
@@ -29,7 +29,7 @@ 
  *    searching it for one bits.
  *  - The optional "addr2", which is anded with "addr1" if present.
  */
-static unsigned long _find_next_bit(const unsigned long *addr1,
+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)
 {
@@ -68,37 +68,7 @@  static unsigned long _find_next_bit(const unsigned long *addr1,
 
 	return min(start + __ffs(tmp), nbits);
 }
-#endif
-
-#ifndef find_next_bit
-/*
- * Find the next set bit in a memory region.
- */
-unsigned long find_next_bit(const unsigned long *addr, unsigned long size,
-			    unsigned long offset)
-{
-	return _find_next_bit(addr, NULL, size, offset, 0UL, 0);
-}
-EXPORT_SYMBOL(find_next_bit);
-#endif
-
-#ifndef find_next_zero_bit
-unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size,
-				 unsigned long offset)
-{
-	return _find_next_bit(addr, NULL, size, offset, ~0UL, 0);
-}
-EXPORT_SYMBOL(find_next_zero_bit);
-#endif
-
-#if !defined(find_next_and_bit)
-unsigned long find_next_and_bit(const unsigned long *addr1,
-		const unsigned long *addr2, unsigned long size,
-		unsigned long offset)
-{
-	return _find_next_bit(addr1, addr2, size, offset, 0UL, 0);
-}
-EXPORT_SYMBOL(find_next_and_bit);
+EXPORT_SYMBOL(_find_next_bit);
 #endif
 
 #ifndef find_first_bit
@@ -157,28 +127,6 @@  unsigned long find_last_bit(const unsigned long *addr, unsigned long size)
 EXPORT_SYMBOL(find_last_bit);
 #endif
 
-#ifdef __BIG_ENDIAN
-
-#ifndef find_next_zero_bit_le
-unsigned long find_next_zero_bit_le(const void *addr, unsigned
-		long size, unsigned long offset)
-{
-	return _find_next_bit(addr, NULL, size, offset, ~0UL, 1);
-}
-EXPORT_SYMBOL(find_next_zero_bit_le);
-#endif
-
-#ifndef find_next_bit_le
-unsigned long find_next_bit_le(const void *addr, unsigned
-		long size, unsigned long offset)
-{
-	return _find_next_bit(addr, NULL, size, offset, 0UL, 1);
-}
-EXPORT_SYMBOL(find_next_bit_le);
-#endif
-
-#endif /* __BIG_ENDIAN */
-
 unsigned long find_next_clump8(unsigned long *clump, const unsigned long *addr,
 			       unsigned long size, unsigned long offset)
 {
diff --git a/tools/include/asm-generic/bitops/find.h b/tools/include/asm-generic/bitops/find.h
index 16ed1982cb34..9fe62d10b084 100644
--- a/tools/include/asm-generic/bitops/find.h
+++ b/tools/include/asm-generic/bitops/find.h
@@ -2,6 +2,10 @@ 
 #ifndef _TOOLS_LINUX_ASM_GENERIC_BITOPS_FIND_H_
 #define _TOOLS_LINUX_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);
+
 #ifndef find_next_bit
 /**
  * find_next_bit - find the next set bit in a memory region
@@ -12,8 +16,12 @@ 
  * Returns the bit number for the next set bit
  * If no bits are set, returns @size.
  */
-extern unsigned long find_next_bit(const unsigned long *addr, unsigned long
-		size, unsigned long offset);
+static inline
+unsigned long find_next_bit(const unsigned long *addr, unsigned long size,
+			    unsigned long offset)
+{
+	return _find_next_bit(addr, NULL, size, offset, 0UL, 0);
+}
 #endif
 
 #ifndef find_next_and_bit
@@ -27,13 +35,16 @@  extern unsigned long find_next_bit(const unsigned long *addr, unsigned long
  * Returns the bit number for the next set bit
  * If no bits are set, returns @size.
  */
-extern unsigned long find_next_and_bit(const unsigned long *addr1,
+static inline
+unsigned long find_next_and_bit(const unsigned long *addr1,
 		const unsigned long *addr2, unsigned long size,
-		unsigned long offset);
+		unsigned long offset)
+{
+	return _find_next_bit(addr1, addr2, size, offset, 0UL, 0);
+}
 #endif
 
 #ifndef find_next_zero_bit
-
 /**
  * find_next_zero_bit - find the next cleared bit in a memory region
  * @addr: The address to base the search on
@@ -43,8 +54,12 @@  extern unsigned long find_next_and_bit(const unsigned long *addr1,
  * Returns the bit number of the next zero bit
  * If no bits are zero, returns @size.
  */
+static inline
 unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size,
-				 unsigned long offset);
+				 unsigned long offset)
+{
+	return _find_next_bit(addr, NULL, size, offset, ~0UL, 0);
+}
 #endif
 
 #ifndef find_first_bit
diff --git a/tools/lib/find_bit.c b/tools/lib/find_bit.c
index 49abb18549cc..c3378b291205 100644
--- a/tools/lib/find_bit.c
+++ b/tools/lib/find_bit.c
@@ -28,11 +28,12 @@ 
  *    searching it for one bits.
  *  - The optional "addr2", which is anded with "addr1" if present.
  */
-static inline unsigned long _find_next_bit(const unsigned long *addr1,
+unsigned long _find_next_bit(const unsigned long *addr1,
 		const unsigned long *addr2, unsigned long nbits,
-		unsigned long start, unsigned long invert)
+		unsigned long start, unsigned long invert, unsigned long le)
 {
-	unsigned long tmp;
+	unsigned long tmp, mask;
+	(void) le;
 
 	if (unlikely(start >= nbits))
 		return nbits;
@@ -43,7 +44,19 @@  static inline unsigned long _find_next_bit(const unsigned long *addr1,
 	tmp ^= invert;
 
 	/* Handle 1st word. */
-	tmp &= BITS_LAST_MASK(start);
+	mask = BITS_LAST_MASK(start);
+
+	/*
+	 * Due to the lack of swab() in tools, and the fact that it doesn't
+	 * need little-endian support, just comment it out
+	 */
+#if (0)
+	if (le)
+		mask = swab(mask);
+#endif
+
+	tmp &= mask;
+
 	start = round_down(start, BITS_PER_LONG);
 
 	while (!tmp) {
@@ -57,18 +70,12 @@  static inline unsigned long _find_next_bit(const unsigned long *addr1,
 		tmp ^= invert;
 	}
 
-	return min(start + __ffs(tmp), nbits);
-}
+#if (0)
+	if (le)
+		tmp = swab(tmp);
 #endif
 
-#ifndef find_next_bit
-/*
- * Find the next set bit in a memory region.
- */
-unsigned long find_next_bit(const unsigned long *addr, unsigned long size,
-			    unsigned long offset)
-{
-	return _find_next_bit(addr, NULL, size, offset, 0UL);
+	return min(start + __ffs(tmp), nbits);
 }
 #endif
 
@@ -105,20 +112,3 @@  unsigned long find_first_zero_bit(const unsigned long *addr, unsigned long size)
 	return size;
 }
 #endif
-
-#ifndef find_next_zero_bit
-unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size,
-				 unsigned long offset)
-{
-	return _find_next_bit(addr, NULL, size, offset, ~0UL);
-}
-#endif
-
-#ifndef find_next_and_bit
-unsigned long find_next_and_bit(const unsigned long *addr1,
-		const unsigned long *addr2, unsigned long size,
-		unsigned long offset)
-{
-	return _find_next_bit(addr1, addr2, size, offset, 0UL);
-}
-#endif