cpumask: Add cpumask_{first,next}_andnot() API

With the lack of the functions, client code has to abuse less efficient
cpumask_nth().

Signed-off-by: Yury Norov [NVIDIA] <yury.norov@gmail.com>
Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: James Morse <james.morse@arm.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Fenghua Yu <fenghuay@nvidia.com>
Tested-by: Fenghua Yu <fenghuay@nvidia.com>
Tested-by: James Morse <james.morse@arm.com>
Tested-by: Tony Luck <tony.luck@intel.com>
Link: https://lore.kernel.org/20250515165855.31452-4-james.morse@arm.com

Author: YuryNorov

include/linux/cpumask.h

@@ -178,6 +178,19 @@ 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_andnot - return the first cpu from *srcp1 & ~*srcp2
+ * @srcp1: the first input
+ * @srcp2: the second input
+ *
+ * Return: >= nr_cpu_ids if no such cpu found.
+ */
+static __always_inline
+unsigned int cpumask_first_andnot(const struct cpumask *srcp1, const struct cpumask *srcp2)
+{
+	return find_first_andnot_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
@@ -284,6 +297,25 @@ unsigned int cpumask_next_and(int n, const struct cpumask *src1p,
 		small_cpumask_bits, n + 1);
 }
 
+/**
+ * cpumask_next_andnot - get the next cpu in *src1p & ~*src2p
+ * @n: the cpu prior to the place to search (i.e. return will be > @n)
+ * @src1p: the first cpumask pointer
+ * @src2p: the second cpumask pointer
+ *
+ * Return: >= nr_cpu_ids if no further cpus set in both.
+ */
+static __always_inline
+unsigned int cpumask_next_andnot(int n, const struct cpumask *src1p,
+				 const struct cpumask *src2p)
+{
+	/* -1 is a legal arg here. */
+	if (n != -1)
+		cpumask_check(n);
+	return find_next_andnot_bit(cpumask_bits(src1p), cpumask_bits(src2p),
+		small_cpumask_bits, n + 1);
+}
+
 /**
  * cpumask_next_and_wrap - get the next cpu in *src1p & *src2p, starting from
  *			   @n+1. If nothing found, wrap around and start from
@@ -458,6 +490,33 @@ unsigned int cpumask_any_and_but(const struct cpumask *mask1,
 	return cpumask_next_and(cpu, mask1, mask2);
 }
 
+/**
+ * cpumask_any_andnot_but - pick an arbitrary cpu from *mask1 & ~*mask2, but not this one.
+ * @mask1: the first input cpumask
+ * @mask2: the second input cpumask
+ * @cpu: the cpu to ignore
+ *
+ * If @cpu == -1, the function returns the first matching cpu.
+ * Returns >= nr_cpu_ids if no cpus set.
+ */
+static __always_inline
+unsigned int cpumask_any_andnot_but(const struct cpumask *mask1,
+				    const struct cpumask *mask2,
+				    int cpu)
+{
+	unsigned int i;
+
+	/* -1 is a legal arg here. */
+	if (cpu != -1)
+		cpumask_check(cpu);
+
+	i = cpumask_first_andnot(mask1, mask2);
+	if (i != cpu)
+		return i;
+
+	return cpumask_next_andnot(cpu, mask1, mask2);
+}
+
 /**
  * cpumask_nth - get the Nth cpu in a cpumask
  * @srcp: the cpumask pointer