Merge tag 'smp-core-2025-07-27' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull smp updates from Thomas Gleixner:
 "A set of updates for SMP function calls:

   - Improve locality of smp_call_function_any() by utilizing
     sched_numa_find_nth_cpu() instead of picking a random CPU

   - Wait for work completion in smp_call_function_many_cond() only when
     there was actually work enqueued

   - Simplify functions by unutlizing the appropriate cpumask_*()
     interfaces

   - Trivial cleanups"

* tag 'smp-core-2025-07-27' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  smp: Wait only if work was enqueued
  smp: Defer check for local execution in smp_call_function_many_cond()
  smp: Use cpumask_any_but() in smp_call_function_many_cond()
  smp: Improve locality in smp_call_function_any()
  smp: Fix typo in comment for raw_smp_processor_id()

Author: torvalds

include/linux/smp.h

@@ -234,7 +234,7 @@ static inline int get_boot_cpu_id(void)
 #endif /* !SMP */
 
 /**
- * raw_processor_id() - get the current (unstable) CPU id
+ * raw_smp_processor_id() - get the current (unstable) CPU id
  *
  * For then you know what you are doing and need an unstable
  * CPU id.

kernel/smp.c

@@ -741,32 +741,19 @@ EXPORT_SYMBOL_GPL(smp_call_function_single_async);
  *
  * Selection preference:
  *	1) current cpu if in @mask
- *	2) any cpu of current node if in @mask
- *	3) any other online cpu in @mask
+ *	2) nearest cpu in @mask, based on NUMA topology
  */
 int smp_call_function_any(const struct cpumask *mask,
 			  smp_call_func_t func, void *info, int wait)
 {
 	unsigned int cpu;
-	const struct cpumask *nodemask;
 	int ret;
 
 	/* Try for same CPU (cheapest) */
 	cpu = get_cpu();
-	if (cpumask_test_cpu(cpu, mask))
-		goto call;
-
-	/* Try for same node. */
-	nodemask = cpumask_of_node(cpu_to_node(cpu));
-	for (cpu = cpumask_first_and(nodemask, mask); cpu < nr_cpu_ids;
-	     cpu = cpumask_next_and(cpu, nodemask, mask)) {
-		if (cpu_online(cpu))
-			goto call;
-	}
+	if (!cpumask_test_cpu(cpu, mask))
+		cpu = sched_numa_find_nth_cpu(mask, 0, cpu_to_node(cpu));
 
-	/* Any online will do: smp_call_function_single handles nr_cpu_ids. */
-	cpu = cpumask_any_and(mask, cpu_online_mask);
-call:
 	ret = smp_call_function_single(cpu, func, info, wait);
 	put_cpu();
 	return ret;
@@ -792,7 +779,6 @@ static void smp_call_function_many_cond(const struct cpumask *mask,
 	bool wait = scf_flags & SCF_WAIT;
 	int nr_cpus = 0;
 	bool run_remote = false;
-	bool run_local = false;
 
 	lockdep_assert_preemption_disabled();
 
@@ -814,19 +800,8 @@ static void smp_call_function_many_cond(const struct cpumask *mask,
 	 */
 	WARN_ON_ONCE(!in_task());
 
-	/* Check if we need local execution. */
-	if ((scf_flags & SCF_RUN_LOCAL) && cpumask_test_cpu(this_cpu, mask) &&
-	    (!cond_func || cond_func(this_cpu, info)))
-		run_local = true;
-
 	/* Check if we need remote execution, i.e., any CPU excluding this one. */
-	cpu = cpumask_first_and(mask, cpu_online_mask);
-	if (cpu == this_cpu)
-		cpu = cpumask_next_and(cpu, mask, cpu_online_mask);
-	if (cpu < nr_cpu_ids)
-		run_remote = true;
-
-	if (run_remote) {
+	if (cpumask_any_and_but(mask, cpu_online_mask, this_cpu) < nr_cpu_ids) {
 		cfd = this_cpu_ptr(&cfd_data);
 		cpumask_and(cfd->cpumask, mask, cpu_online_mask);
 		__cpumask_clear_cpu(this_cpu, cfd->cpumask);
@@ -840,6 +815,9 @@ static void smp_call_function_many_cond(const struct cpumask *mask,
 				continue;
 			}
 
+			/* Work is enqueued on a remote CPU. */
+			run_remote = true;
+
 			csd_lock(csd);
 			if (wait)
 				csd->node.u_flags |= CSD_TYPE_SYNC;
@@ -851,6 +829,10 @@ static void smp_call_function_many_cond(const struct cpumask *mask,
 #endif
 			trace_csd_queue_cpu(cpu, _RET_IP_, func, csd);
 
+			/*
+			 * Kick the remote CPU if this is the first work
+			 * item enqueued.
+			 */
 			if (llist_add(&csd->node.llist, &per_cpu(call_single_queue, cpu))) {
 				__cpumask_set_cpu(cpu, cfd->cpumask_ipi);
 				nr_cpus++;
@@ -869,7 +851,9 @@ static void smp_call_function_many_cond(const struct cpumask *mask,
 			send_call_function_ipi_mask(cfd->cpumask_ipi);
 	}
 
-	if (run_local) {
+	/* Check if we need local execution. */
+	if ((scf_flags & SCF_RUN_LOCAL) && cpumask_test_cpu(this_cpu, mask) &&
+	    (!cond_func || cond_func(this_cpu, info))) {
 		unsigned long flags;
 
 		local_irq_save(flags);