smp: Inline on_each_cpu_cond() and on_each_cpu()

Simplify the code and avoid having an additional function on the stack
by inlining on_each_cpu_cond() and on_each_cpu().
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Nadav Amit <namit@vmware.com>
[ Minor edits. ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20210220231712.2475218-10-namit@vmware.com

include/linux/smp.h

@@ -50,30 +50,52 @@ extern unsigned int total_cpus;
 int smp_call_function_single(int cpuid, smp_call_func_t func, void *info,
 			     int 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);
+
+int smp_call_function_single_async(int cpu, call_single_data_t *csd);
+
 /*
  * Call a function on all processors
  */
-void on_each_cpu(smp_call_func_t func, void *info, int wait);
+static inline void on_each_cpu(smp_call_func_t func, void *info, int wait)
+{
+	on_each_cpu_cond_mask(NULL, func, info, wait, cpu_online_mask);
+}
 
-/*
- * Call a function on processors specified by mask, which might include
- * the local one.
+/**
+ * on_each_cpu_mask(): Run a function on processors specified by
+ * cpumask, which may include the local processor.
+ * @mask: The set of cpus to run on (only runs on online subset).
+ * @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 (atomically) until function has completed
+ *        on other CPUs.
+ *
+ * If @wait is true, then returns once @func has returned.
+ *
+ * You must not call this function with disabled interrupts or from a
+ * hardware interrupt handler or from a bottom half handler.  The
+ * exception is that it may be used during early boot while
+ * early_boot_irqs_disabled is set.
  */
-void on_each_cpu_mask(const struct cpumask *mask, smp_call_func_t func,
-		void *info, bool wait);
+static inline void on_each_cpu_mask(const struct cpumask *mask,
+				    smp_call_func_t func, void *info, bool wait)
+{
+	on_each_cpu_cond_mask(NULL, func, info, wait, mask);
+}
 
 /*
  * Call a function on each processor for which the supplied function
  * cond_func returns a positive value. This may include the local
- * processor.
+ * processor.  May be used during early boot while early_boot_irqs_disabled is
+ * set. Use local_irq_save/restore() instead of local_irq_disable/enable().
  */
-void on_each_cpu_cond(smp_cond_func_t cond_func, 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);
-
-int smp_call_function_single_async(int cpu, call_single_data_t *csd);
+static inline void on_each_cpu_cond(smp_cond_func_t cond_func,
+				    smp_call_func_t func, void *info, bool wait)
+{
+	on_each_cpu_cond_mask(cond_func, func, info, wait, cpu_online_mask);
+}
 
 #ifdef CONFIG_SMP
 

kernel/smp.c

@@ -847,55 +847,6 @@ void __init smp_init(void)
 	smp_cpus_done(setup_max_cpus);
 }
 
-/*
- * Call a function on all processors.  May be used during early boot while
- * early_boot_irqs_disabled is set.  Use local_irq_save/restore() instead
- * of local_irq_disable/enable().
- */
-void on_each_cpu(smp_call_func_t func, void *info, int wait)
-{
-	unsigned long flags;
-
-	preempt_disable();
-	smp_call_function(func, info, wait);
-	local_irq_save(flags);
-	func(info);
-	local_irq_restore(flags);
-	preempt_enable();
-}
-EXPORT_SYMBOL(on_each_cpu);
-
-/**
- * on_each_cpu_mask(): Run a function on processors specified by
- * cpumask, which may include the local processor.
- * @mask: The set of cpus to run on (only runs on online subset).
- * @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 (atomically) until function has completed
- *        on other CPUs.
- *
- * If @wait is true, then returns once @func has returned.
- *
- * You must not call this function with disabled interrupts or from a
- * hardware interrupt handler or from a bottom half handler.  The
- * exception is that it may be used during early boot while
- * early_boot_irqs_disabled is set.
- */
-void on_each_cpu_mask(const struct cpumask *mask, smp_call_func_t func,
-			void *info, bool wait)
-{
-	unsigned int scf_flags;
-
-	scf_flags = SCF_RUN_LOCAL;
-	if (wait)
-		scf_flags |= SCF_WAIT;
-
-	preempt_disable();
-	smp_call_function_many_cond(mask, func, info, scf_flags, NULL);
-	preempt_enable();
-}
-EXPORT_SYMBOL(on_each_cpu_mask);
-
 /*
  * on_each_cpu_cond(): Call a function on each processor for which
  * the supplied function cond_func returns true, optionally waiting
@@ -932,13 +883,6 @@ void on_each_cpu_cond_mask(smp_cond_func_t cond_func, smp_call_func_t func,
 }
 EXPORT_SYMBOL(on_each_cpu_cond_mask);
 
-void on_each_cpu_cond(smp_cond_func_t cond_func, smp_call_func_t func,
-		      void *info, bool wait)
-{
-	on_each_cpu_cond_mask(cond_func, func, info, wait, cpu_online_mask);
-}
-EXPORT_SYMBOL(on_each_cpu_cond);
-
 static void do_nothing(void *unused)
 {
 }

kernel/up.c

@@ -36,35 +36,6 @@ int smp_call_function_single_async(int cpu, call_single_data_t *csd)
 }
 EXPORT_SYMBOL(smp_call_function_single_async);
 
-void on_each_cpu(smp_call_func_t func, void *info, int wait)
-{
-	unsigned long flags;
-
-	local_irq_save(flags);
-	func(info);
-	local_irq_restore(flags);
-}
-EXPORT_SYMBOL(on_each_cpu);
-
-/*
- * Note we still need to test the mask even for UP
- * because we actually can get an empty mask from
- * code that on SMP might call us without the local
- * CPU in the mask.
- */
-void on_each_cpu_mask(const struct cpumask *mask,
-		      smp_call_func_t func, void *info, bool wait)
-{
-	unsigned long flags;
-
-	if (cpumask_test_cpu(0, mask)) {
-		local_irq_save(flags);
-		func(info);
-		local_irq_restore(flags);
-	}
-}
-EXPORT_SYMBOL(on_each_cpu_mask);
-
 /*
  * Preemption is disabled here to make sure the cond_func is called under the
  * same condtions in UP and SMP.
@@ -75,7 +46,7 @@ void on_each_cpu_cond_mask(smp_cond_func_t cond_func, smp_call_func_t func,
 	unsigned long flags;
 
 	preempt_disable();
-	if (cond_func(0, info)) {
+	if ((!cond_func || cond_func(0, info)) && cpumask_test_cpu(0, mask)) {
 		local_irq_save(flags);
 		func(info);
 		local_irq_restore(flags);
@@ -84,13 +55,6 @@ void on_each_cpu_cond_mask(smp_cond_func_t cond_func, smp_call_func_t func,
 }
 EXPORT_SYMBOL(on_each_cpu_cond_mask);
 
-void on_each_cpu_cond(smp_cond_func_t cond_func, smp_call_func_t func,
-		      void *info, bool wait)
-{
-	on_each_cpu_cond_mask(cond_func, func, info, wait, NULL);
-}
-EXPORT_SYMBOL(on_each_cpu_cond);
-
 int smp_call_on_cpu(unsigned int cpu, int (*func)(void *), void *par, bool phys)
 {
 	int ret;