trace: Add trace_ipi_send_cpu()

Because copying cpumasks around when targeting a single CPU is a bit
daft...

Tested-and-reviewed-by: Valentin Schneider <vschneid@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20230322103004.GA571242%40hirez.programming.kicks-ass.net

Author: Peter Zijlstra

include/linux/smp.h

@@ -130,9 +130,9 @@ extern void arch_smp_send_reschedule(int cpu);
  * scheduler_ipi() is inline so can't be passed as callback reason, but the
  * callsite IP should be sufficient for root-causing IPIs sent from here.
  */
-#define smp_send_reschedule(cpu) ({				  \
-	trace_ipi_send_cpumask(cpumask_of(cpu), _RET_IP_, NULL);  \
-	arch_smp_send_reschedule(cpu);				  \
+#define smp_send_reschedule(cpu) ({		  \
+	trace_ipi_send_cpu(cpu, _RET_IP_, NULL);  \
+	arch_smp_send_reschedule(cpu);		  \
 })
 
 /*

include/trace/events/ipi.h

@@ -35,6 +35,28 @@ TRACE_EVENT(ipi_raise,
 	TP_printk("target_mask=%s (%s)", __get_bitmask(target_cpus), __entry->reason)
 );
 
+TRACE_EVENT(ipi_send_cpu,
+
+	TP_PROTO(const unsigned int cpu, unsigned long callsite, void *callback),
+
+	TP_ARGS(cpu, callsite, callback),
+
+	TP_STRUCT__entry(
+		__field(unsigned int, cpu)
+		__field(void *, callsite)
+		__field(void *, callback)
+	),
+
+	TP_fast_assign(
+		__entry->cpu = cpu;
+		__entry->callsite = (void *)callsite;
+		__entry->callback = callback;
+	),
+
+	TP_printk("cpu=%u callsite=%pS callback=%pS",
+		  __entry->cpu, __entry->callsite, __entry->callback)
+);
+
 TRACE_EVENT(ipi_send_cpumask,
 
 	TP_PROTO(const struct cpumask *cpumask, unsigned long callsite, void *callback),

kernel/irq_work.c

@@ -78,10 +78,8 @@ void __weak arch_irq_work_raise(void)
 
 static __always_inline void irq_work_raise(struct irq_work *work)
 {
-	if (trace_ipi_send_cpumask_enabled() && arch_irq_work_has_interrupt())
-		trace_ipi_send_cpumask(cpumask_of(smp_processor_id()),
-				       _RET_IP_,
-				       work->func);
+	if (trace_ipi_send_cpu_enabled() && arch_irq_work_has_interrupt())
+		trace_ipi_send_cpu(smp_processor_id(), _RET_IP_, work->func);
 
 	arch_irq_work_raise();
 }

kernel/sched/core.c

@@ -96,6 +96,7 @@
 #include "../../io_uring/io-wq.h"
 #include "../smpboot.h"
 
+EXPORT_TRACEPOINT_SYMBOL_GPL(ipi_send_cpu);
 EXPORT_TRACEPOINT_SYMBOL_GPL(ipi_send_cpumask);
 
 /*

kernel/smp.c

@@ -107,7 +107,7 @@ static __always_inline void
 send_call_function_single_ipi(int cpu, smp_call_func_t func)
 {
 	if (call_function_single_prep_ipi(cpu)) {
-		trace_ipi_send_cpumask(cpumask_of(cpu), _RET_IP_, func);
+		trace_ipi_send_cpu(cpu, _RET_IP_, func);
 		arch_send_call_function_single_ipi(cpu);
 	}
 }
@@ -346,7 +346,7 @@ void __smp_call_single_queue(int cpu, struct llist_node *node)
 	 * even if we haven't sent the smp_call IPI yet (e.g. the stopper
 	 * executes migration_cpu_stop() on the remote CPU).
 	 */
-	if (trace_ipi_send_cpumask_enabled()) {
+	if (trace_ipi_send_cpu_enabled()) {
 		call_single_data_t *csd;
 		smp_call_func_t func;