smp: Refactor remote CPU selection in smp_call_function_any()

smp_call_function_any() disables preemption across the entire operation:
selecting a target CPU, enqueueing the IPI, and synchronously waiting for
the remote CPU. smp_call_function_single() already re-enables preemption
before the synchronous csd_lock_wait(), so callers of
smp_call_function_any() should benefit from the same shorter
preemption-disabled section.

Simply removing get_cpu() and put_cpu() from smp_call_function_any()
would leave the preemption disablement entirely to
smp_call_function_single(). That opens a preemption window between
selecting the remote CPU, for example via sched_numa_find_nth_cpu(), and
dispatching the IPI in smp_call_function_single(). If the selected CPU is
fully offlined in that window, smp_call_function_single() fails its
cpu_online() check and returns -ENXIO to the caller, violating the
guarantee that smp_call_function_any() executes on any online CPU in the
mask.

Move the remote CPU selection into a common
__smp_call_function_single() helper. Keep the target CPU selection and
IPI dispatch within the same preemption-disabled region, while still
allowing the wait path to use the shorter preemption-disabled section
provided by smp_call_function_single().

Signed-off-by: Chuyi Zhou <zhouchuyi@bytedance.com>
Signed-off-by: Thomas Gleixner <tglx@kernel.org>
Tested-by: Paul E. McKenney <paulmck@kernel.org>
Reviewed-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Link: https://patch.msgid.link/20260709122933.4021501-4-zhouchuyi@bytedance.com

include/linux/smp.h

@@ -47,8 +47,7 @@ extern void __smp_call_single_queue(int cpu, struct llist_node *node);
 /* total number of cpus in this system (may exceed NR_CPUS) */
 extern unsigned int total_cpus;
 
-int smp_call_function_single(int cpuid, smp_call_func_t func, void *info,
-			     int wait);
+int smp_call_function_single(int cpuid, smp_call_func_t func, void *info, bool wait);
 
 void on_each_cpu_cond_mask(smp_cond_func_t cond_func, smp_call_func_t func,
 			   void *info, bool wait, const struct cpumask *mask);

kernel/smp.c

@@ -653,17 +653,9 @@ void flush_smp_call_function_queue(void)
 	local_irq_restore(flags);
 }
 
-/**
- * smp_call_function_single - Run a function on a specific CPU
- * @cpu: Specific target CPU for this function.
- * @func: The function to run. This must be fast and non-blocking.
- * @info: An arbitrary pointer to pass to the function.
- * @wait: If true, wait until function has completed on other CPUs.
- *
- * Returns: %0 on success, else a negative status code.
- */
-int smp_call_function_single(int cpu, smp_call_func_t func, void *info,
-			     int wait)
+static int __smp_call_function_single(int cpu, smp_call_func_t func,
+				      void *info, const struct cpumask *mask,
+				      bool wait)
 {
 	call_single_data_t *csd;
 	call_single_data_t csd_stack = {
@@ -680,6 +672,14 @@ int smp_call_function_single(int cpu, smp_call_func_t func, void *info,
 	 */
 	this_cpu = get_cpu();
 
+	if (mask) {
+		/* Try for same CPU (cheapest) */
+		if (!cpumask_test_cpu(this_cpu, mask))
+			cpu = sched_numa_find_nth_cpu(mask, 0, cpu_to_node(this_cpu));
+		else
+			cpu = this_cpu;
+	}
+
 	/*
 	 * Can deadlock when called with interrupts disabled.
 	 * We allow cpu's that are not yet online though, as no one else can
@@ -724,6 +724,20 @@ int smp_call_function_single(int cpu, smp_call_func_t func, void *info,
 
 	return err;
 }
+
+/**
+ * smp_call_function_single - Run a function on a specific CPU
+ * @cpu:	Specific target CPU for this function.
+ * @func:	The function to run. This must be fast and non-blocking.
+ * @info:	An arbitrary pointer to pass to the function.
+ * @wait:	If true, wait until function has completed on other CPUs.
+ *
+ * Returns: %0 on success, else a negative status code.
+ */
+int smp_call_function_single(int cpu, smp_call_func_t func, void *info, bool wait)
+{
+	return __smp_call_function_single(cpu, func, info, NULL, wait);
+}
 EXPORT_SYMBOL(smp_call_function_single);
 
 /**
@@ -774,10 +788,10 @@ EXPORT_SYMBOL_GPL(smp_call_function_single_async);
 
 /**
  * smp_call_function_any - Run a function on any of the given cpus
- * @mask: The mask of cpus it can run on.
- * @func: The function to run. This must be fast and non-blocking.
- * @info: An arbitrary pointer to pass to the function.
- * @wait: If true, wait until function has completed.
+ * @mask:	The mask of cpus it can run on.
+ * @func:	The function to run. This must be fast and non-blocking.
+ * @info:	An arbitrary pointer to pass to the function.
+ * @wait:	If true, wait until function has completed.
  *
  * Selection preference:
  *	1) current cpu if in @mask
@@ -788,17 +802,7 @@ EXPORT_SYMBOL_GPL(smp_call_function_single_async);
 int smp_call_function_any(const struct cpumask *mask,
 			  smp_call_func_t func, void *info, int wait)
 {
-	unsigned int cpu;
-	int ret;
-
-	/* Try for same CPU (cheapest) */
-	cpu = get_cpu();
-	if (!cpumask_test_cpu(cpu, mask))
-		cpu = sched_numa_find_nth_cpu(mask, 0, cpu_to_node(cpu));
-
-	ret = smp_call_function_single(cpu, func, info, wait);
-	put_cpu();
-	return ret;
+	return __smp_call_function_single(-1, func, info, mask, wait);
 }
 EXPORT_SYMBOL_GPL(smp_call_function_any);
 

kernel/up.c

@@ -9,8 +9,7 @@
 #include <linux/smp.h>
 #include <linux/hypervisor.h>
 
-int smp_call_function_single(int cpu, void (*func) (void *info), void *info,
-				int wait)
+int smp_call_function_single(int cpu, void (*func)(void *info), void *info, bool wait)
 {
 	unsigned long flags;