cpumask: Introduce cpu_preferred_mask

Provide the preferred CPU infrastructure. Define get/set macros
which could be used to get/set CPU state as preferred.

CONFIG_PREFERRED_CPU will be selected by the driver which handles
steal time values. It is going to set/clear preferred CPU state.
This driver will be called steal_governor and it is introduced in
subsequent patches. It periodically computes the steal ratio and
decides on preferred CPU state.

A CPU is set to preferred when it becomes active. Later it may be
marked as non-preferred depending on steal ratio by the steal_governor.

Always maintain design construct of preferred is subset of active.
i.e. preferred ⊆ active ⊆ online ⊆ present ⊆ possible

With CONFIG_PREFERRED_CPU=n, ensure set_cpu_preferred is a nop and get
method returns the active state in that case.

Signed-off-by: Shrikanth Hegde <sshegde@linux.ibm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://patch.msgid.link/20260928053728.797539-5-sshegde@linux.ibm.com

include/linux/cpumask.h

@@ -121,12 +121,20 @@ extern struct cpumask __cpu_enabled_mask;
 extern struct cpumask __cpu_present_mask;
 extern struct cpumask __cpu_active_mask;
 extern struct cpumask __cpu_dying_mask;
+
+#ifdef CONFIG_PREFERRED_CPU
+extern struct cpumask __cpu_preferred_mask;
+#else
+#define __cpu_preferred_mask __cpu_active_mask
+#endif
+
 #define cpu_possible_mask ((const struct cpumask *)&__cpu_possible_mask)
 #define cpu_online_mask   ((const struct cpumask *)&__cpu_online_mask)
 #define cpu_enabled_mask   ((const struct cpumask *)&__cpu_enabled_mask)
 #define cpu_present_mask  ((const struct cpumask *)&__cpu_present_mask)
 #define cpu_active_mask   ((const struct cpumask *)&__cpu_active_mask)
 #define cpu_dying_mask    ((const struct cpumask *)&__cpu_dying_mask)
+#define cpu_preferred_mask ((const struct cpumask *)&__cpu_preferred_mask)
 
 extern atomic_t __num_online_cpus;
 extern unsigned int __num_possible_cpus;
@@ -1181,6 +1189,12 @@ void init_cpu_possible(const struct cpumask *src);
 #define set_cpu_active(cpu, active)	assign_cpu((cpu), &__cpu_active_mask, (active))
 #define set_cpu_dying(cpu, dying)	assign_cpu((cpu), &__cpu_dying_mask, (dying))
 
+#ifdef CONFIG_PREFERRED_CPU
+#define set_cpu_preferred(cpu, preferred) assign_cpu((cpu), &__cpu_preferred_mask, (preferred))
+#else
+#define set_cpu_preferred(cpu, preferred) do { } while (0)
+#endif
+
 void set_cpu_online(unsigned int cpu, bool online);
 void set_cpu_possible(unsigned int cpu, bool possible);
 
@@ -1275,6 +1289,11 @@ static __always_inline bool cpu_dying(unsigned int cpu)
 	return cpumask_test_cpu(cpu, cpu_dying_mask);
 }
 
+static __always_inline bool cpu_preferred(unsigned int cpu)
+{
+	return cpumask_test_cpu(cpu, cpu_preferred_mask);
+}
+
 #else
 
 #define num_online_cpus()	1U
@@ -1313,6 +1332,11 @@ static __always_inline bool cpu_dying(unsigned int cpu)
 	return false;
 }
 
+static __always_inline bool cpu_preferred(unsigned int cpu)
+{
+	return cpu == 0;
+}
+
 #endif /* NR_CPUS > 1 */
 
 #define cpu_is_offline(cpu)	unlikely(!cpu_online(cpu))

kernel/Kconfig.preempt

@@ -194,3 +194,7 @@ config SCHED_CLASS_EXT
 	  For more information:
 	    Documentation/scheduler/sched-ext.rst
 	    https://github.com/sched-ext/scx
+
+config PREFERRED_CPU
+	bool
+	depends on SMP && PARAVIRT

kernel/cpu.c

@@ -3103,6 +3103,11 @@ EXPORT_SYMBOL(__cpu_dying_mask);
 atomic_t __num_online_cpus __read_mostly;
 EXPORT_SYMBOL(__num_online_cpus);
 
+#ifdef CONFIG_PREFERRED_CPU
+struct cpumask __cpu_preferred_mask __read_mostly;
+EXPORT_SYMBOL_GPL(__cpu_preferred_mask);
+#endif
+
 void init_cpu_present(const struct cpumask *src)
 {
 	cpumask_copy(&__cpu_present_mask, src);
@@ -3160,6 +3165,7 @@ void __init boot_cpu_init(void)
 	/* Mark the boot cpu "present", "online" etc for SMP and UP case */
 	set_cpu_online(cpu, true);
 	set_cpu_active(cpu, true);
+	set_cpu_preferred(cpu, true);
 	set_cpu_present(cpu, true);
 	set_cpu_possible(cpu, true);
 

kernel/sched/core.c

@@ -8632,6 +8632,9 @@ int sched_cpu_activate(unsigned int cpu)
 	 */
 	sched_set_rq_online(rq, cpu);
 
+	/* preferred is subset of active and follows its state */
+	set_cpu_preferred(cpu, true);
+
 	return 0;
 }
 
@@ -8645,6 +8648,8 @@ int sched_cpu_deactivate(unsigned int cpu)
 	if (ret)
 		return ret;
 
+	set_cpu_preferred(cpu, false);
+
 	/*
 	 * Remove CPU from nohz.idle_cpus_mask to prevent participating in
 	 * load balancing when not active