cpumask: Introduce cpumask_first_and_and()

Introduce cpumask_first_and_and() to get intersection between 3 cpumasks,
free of any intermediate cpumask variable. Instead, cpumask_first_and_and()
works in-place with all inputs and produces desired output directly.

Signed-off-by: Dawei Li <dawei.li@shingroup.cn>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Yury Norov <yury.norov@gmail.com>
Link: https://lore.kernel.org/r/20240416085454.3547175-2-dawei.li@shingroup.cn

include/linux/cpumask.h

@@ -187,6 +187,23 @@ unsigned int cpumask_first_and(const struct cpumask *srcp1, const struct cpumask
 	return find_first_and_bit(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits);
 }
 
+/**
+ * cpumask_first_and_and - return the first cpu from *srcp1 & *srcp2 & *srcp3
+ * @srcp1: the first input
+ * @srcp2: the second input
+ * @srcp3: the third input
+ *
+ * Return: >= nr_cpu_ids if no cpus set in all.
+ */
+static inline
+unsigned int cpumask_first_and_and(const struct cpumask *srcp1,
+				   const struct cpumask *srcp2,
+				   const struct cpumask *srcp3)
+{
+	return find_first_and_and_bit(cpumask_bits(srcp1), cpumask_bits(srcp2),
+				      cpumask_bits(srcp3), small_cpumask_bits);
+}
+
 /**
  * cpumask_last - get the last CPU in a cpumask
  * @srcp:	- the cpumask pointer

include/linux/find.h

@@ -29,6 +29,8 @@ unsigned long __find_nth_and_andnot_bit(const unsigned long *addr1, const unsign
 					unsigned long n);
 extern unsigned long _find_first_and_bit(const unsigned long *addr1,
 					 const unsigned long *addr2, unsigned long size);
+unsigned long _find_first_and_and_bit(const unsigned long *addr1, const unsigned long *addr2,
+				      const unsigned long *addr3, 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);
 
@@ -345,6 +347,31 @@ unsigned long find_first_and_bit(const unsigned long *addr1,
 }
 #endif
 
+/**
+ * find_first_and_and_bit - find the first set bit in 3 memory regions
+ * @addr1: The first address to base the search on
+ * @addr2: The second address to base the search on
+ * @addr3: The third address to base the search on
+ * @size: The bitmap size in bits
+ *
+ * Returns the bit number for the first set bit
+ * If no bits are set, returns @size.
+ */
+static inline
+unsigned long find_first_and_and_bit(const unsigned long *addr1,
+				     const unsigned long *addr2,
+				     const unsigned long *addr3,
+				     unsigned long size)
+{
+	if (small_const_nbits(size)) {
+		unsigned long val = *addr1 & *addr2 & *addr3 & GENMASK(size - 1, 0);
+
+		return val ? __ffs(val) : size;
+	}
+
+	return _find_first_and_and_bit(addr1, addr2, addr3, size);
+}
+
 #ifndef find_first_zero_bit
 /**
  * find_first_zero_bit - find the first cleared bit in a memory region

lib/find_bit.c

@@ -116,6 +116,18 @@ unsigned long _find_first_and_bit(const unsigned long *addr1,
 EXPORT_SYMBOL(_find_first_and_bit);
 #endif
 
+/*
+ * Find the first set bit in three memory regions.
+ */
+unsigned long _find_first_and_and_bit(const unsigned long *addr1,
+				      const unsigned long *addr2,
+				      const unsigned long *addr3,
+				      unsigned long size)
+{
+	return FIND_FIRST_BIT(addr1[idx] & addr2[idx] & addr3[idx], /* nop */, size);
+}
+EXPORT_SYMBOL(_find_first_and_and_bit);
+
 #ifndef find_first_zero_bit
 /*
  * Find the first cleared bit in a memory region.