lib: add find_first_and_bit()

Currently find_first_and_bit() is an alias to find_next_and_bit(). However,
it is widely used in cpumask, so it worth to optimize it. This patch adds
its own implementation for find_first_and_bit().

On x86_64 find_bit_benchmark says:

Before (#define find_first_and_bit(...) find_next_and_bit(..., 0):
Start testing find_bit() with random-filled bitmap
[  140.291468] find_first_and_bit:           46890919 ns,  32671 iterations
Start testing find_bit() with sparse bitmap
[  140.295028] find_first_and_bit:               7103 ns,      1 iterations

After:
Start testing find_bit() with random-filled bitmap
[  162.574907] find_first_and_bit:           25045813 ns,  32846 iterations
Start testing find_bit() with sparse bitmap
[  162.578458] find_first_and_bit:               4900 ns,      1 iterations

(Thanks to Alexey Klimov for thorough testing.)

Signed-off-by: Yury Norov <yury.norov@gmail.com>
Tested-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Tested-by: Alexey Klimov <aklimov@redhat.com>

Author: YuryNorov

include/linux/find.h

@@ -12,6 +12,8 @@ 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_and_bit(const unsigned long *addr1,
+					 const unsigned long *addr2, 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);
 
@@ -123,6 +125,31 @@ unsigned long find_first_bit(const unsigned long *addr, unsigned long size)
 }
 #endif
 
+#ifndef find_first_and_bit
+/**
+ * find_first_and_bit - find the first set bit in both memory regions
+ * @addr1: The first address to base the search on
+ * @addr2: The second address to base the search on
+ * @size: The bitmap size in bits
+ *
+ * Returns the bit number for the next set bit
+ * If no bits are set, returns @size.
+ */
+static inline
+unsigned long find_first_and_bit(const unsigned long *addr1,
+				 const unsigned long *addr2,
+				 unsigned long size)
+{
+	if (small_const_nbits(size)) {
+		unsigned long val = *addr1 & *addr2 & GENMASK(size - 1, 0);
+
+		return val ? __ffs(val) : size;
+	}
+
+	return _find_first_and_bit(addr1, addr2, size);
+}
+#endif
+
 #ifndef find_first_zero_bit
 /**
  * find_first_zero_bit - find the first cleared bit in a memory region

lib/find_bit.c

@@ -89,6 +89,27 @@ unsigned long _find_first_bit(const unsigned long *addr, unsigned long size)
 EXPORT_SYMBOL(_find_first_bit);
 #endif
 
+#ifndef find_first_and_bit
+/*
+ * Find the first set bit in two memory regions.
+ */
+unsigned long _find_first_and_bit(const unsigned long *addr1,
+				  const unsigned long *addr2,
+				  unsigned long size)
+{
+	unsigned long idx, val;
+
+	for (idx = 0; idx * BITS_PER_LONG < size; idx++) {
+		val = addr1[idx] & addr2[idx];
+		if (val)
+			return min(idx * BITS_PER_LONG + __ffs(val), size);
+	}
+
+	return size;
+}
+EXPORT_SYMBOL(_find_first_and_bit);
+#endif
+
 #ifndef find_first_zero_bit
 /*
  * Find the first cleared bit in a memory region.

lib/find_bit_benchmark.c

@@ -49,6 +49,25 @@ static int __init test_find_first_bit(void *bitmap, unsigned long len)
 	return 0;
 }
 
+static int __init test_find_first_and_bit(void *bitmap, const void *bitmap2, unsigned long len)
+{
+	static DECLARE_BITMAP(cp, BITMAP_LEN) __initdata;
+	unsigned long i, cnt;
+	ktime_t time;
+
+	bitmap_copy(cp, bitmap, BITMAP_LEN);
+
+	time = ktime_get();
+	for (cnt = i = 0; i < len; cnt++) {
+		i = find_first_and_bit(cp, bitmap2, len);
+		__clear_bit(i, cp);
+	}
+	time = ktime_get() - time;
+	pr_err("find_first_and_bit: %18llu ns, %6ld iterations\n", time, cnt);
+
+	return 0;
+}
+
 static int __init test_find_next_bit(const void *bitmap, unsigned long len)
 {
 	unsigned long i, cnt;
@@ -129,6 +148,7 @@ static int __init find_bit_test(void)
 	 * traverse only part of bitmap to avoid soft lockup.
 	 */
 	test_find_first_bit(bitmap, BITMAP_LEN / 10);
+	test_find_first_and_bit(bitmap, bitmap2, BITMAP_LEN / 2);
 	test_find_next_and_bit(bitmap, bitmap2, BITMAP_LEN);
 
 	pr_err("\nStart testing find_bit() with sparse bitmap\n");
@@ -145,6 +165,7 @@ static int __init find_bit_test(void)
 	test_find_next_zero_bit(bitmap, BITMAP_LEN);
 	test_find_last_bit(bitmap, BITMAP_LEN);
 	test_find_first_bit(bitmap, BITMAP_LEN);
+	test_find_first_and_bit(bitmap, bitmap2, BITMAP_LEN);
 	test_find_next_and_bit(bitmap, bitmap2, BITMAP_LEN);
 
 	/*