lib: add fast path for find_next_*_bit()

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

This is the quite typical find_next_bit() user:

	unsigned int cpumask_next(int n, const struct cpumask *srcp)
	{
		/* -1 is a legal arg here. */
		if (n != -1)
			cpumask_check(n);
		return find_next_bit(cpumask_bits(srcp), nr_cpumask_bits, n + 1);
	}
	EXPORT_SYMBOL(cpumask_next);

Currently, on ARM64 the generated code looks like this:
	0000000000000000 <cpumask_next>:
	   0:   a9bf7bfd        stp     x29, x30, [sp, #-16]!
	   4:   11000402        add     w2, w0, #0x1
	   8:   aa0103e0        mov     x0, x1
	   c:   d2800401        mov     x1, #0x40                       // #64
	  10:   910003fd        mov     x29, sp
	  14:   93407c42        sxtw    x2, w2
	  18:   94000000        bl      0 <find_next_bit>
	  1c:   a8c17bfd        ldp     x29, x30, [sp], #16
	  20:   d65f03c0        ret
	  24:   d503201f        nop

After applying this patch:
	0000000000000140 <cpumask_next>:
	 140:   11000400        add     w0, w0, #0x1
	 144:   93407c00        sxtw    x0, w0
	 148:   f100fc1f        cmp     x0, #0x3f
	 14c:   54000168        b.hi    178 <cpumask_next+0x38>  // b.pmore
	 150:   f9400023        ldr     x3, [x1]
	 154:   92800001        mov     x1, #0xffffffffffffffff         // #-1
	 158:   9ac02020        lsl     x0, x1, x0
	 15c:   52800802        mov     w2, #0x40                       // #64
	 160:   8a030001        and     x1, x0, x3
	 164:   dac00020        rbit    x0, x1
	 168:   f100003f        cmp     x1, #0x0
	 16c:   dac01000        clz     x0, x0
	 170:   1a800040        csel    w0, w2, w0, eq  // eq = none
	 174:   d65f03c0        ret
	 178:   52800800        mov     w0, #0x40                       // #64
	 17c:   d65f03c0        ret

find_next_bit() call is replaced with 6 instructions.  find_next_bit()
itself is 41 instructions plus function call overhead.

Despite inlining, the scripts/bloat-o-meter report smaller .text size
after applying the series:
	add/remove: 11/9 grow/shrink: 233/176 up/down: 5780/-6768 (-988)

Link: https://lkml.kernel.org/r/20210401003153.97325-10-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>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 51 insertions, 0 deletions

diff --git a/include/asm-generic/bitops/find.h b/include/asm-generic/bitops/find.h
index 7ad70dab8e93..4148c74a1e4d 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_nbits(size)) {
+		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_nbits(size)) {
+		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_nbits(size)) {
+		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..5a28629cbf4d 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_nbits(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_nbits(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