trace,smp: Add tracepoints for scheduling remotelly called functions

Add a tracepoint for when a CSD is queued to a remote CPU's
call_single_queue. This allows finding exactly which CPU queued a given CSD
when looking at a csd_function_{entry,exit} event, and also enables us to
accurately measure IPI delivery time with e.g. a synthetic event:

  $ echo 'hist:keys=cpu,csd.hex:ts=common_timestamp.usecs' >\
      /sys/kernel/tracing/events/smp/csd_queue_cpu/trigger
  $ echo 'csd_latency unsigned int dst_cpu; unsigned long csd; u64 time' >\
      /sys/kernel/tracing/synthetic_events
  $ echo \
  'hist:keys=common_cpu,csd.hex:'\
  'time=common_timestamp.usecs-$ts:'\
  'onmatch(smp.csd_queue_cpu).trace(csd_latency,common_cpu,csd,$time)' >\
      /sys/kernel/tracing/events/smp/csd_function_entry/trigger

  $ trace-cmd record -e 'synthetic:csd_latency' hackbench
  $ trace-cmd report
  <...>-467   [001]    21.824263: csd_queue_cpu:        cpu=0 callsite=try_to_wake_up+0x2ea func=sched_ttwu_pending csd=0xffff8880076148b8
  <...>-467   [001]    21.824280: ipi_send_cpu:         cpu=0 callsite=try_to_wake_up+0x2ea callback=generic_smp_call_function_single_interrupt+0x0
  <...>-489   [000]    21.824299: csd_function_entry:   func=sched_ttwu_pending csd=0xffff8880076148b8
  <...>-489   [000]    21.824320: csd_latency:          dst_cpu=0, csd=18446612682193848504, time=36

Suggested-by: Valentin Schneider <vschneid@redhat.com>
Signed-off-by: Leonardo Bras <leobras@redhat.com>
Tested-and-reviewed-by: Valentin Schneider <vschneid@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20230615065944.188876-7-leobras@redhat.com

Author: Leonardo Bras

include/trace/events/csd.h

@@ -7,6 +7,33 @@
 
 #include <linux/tracepoint.h>
 
+TRACE_EVENT(csd_queue_cpu,
+
+	TP_PROTO(const unsigned int cpu,
+		unsigned long callsite,
+		smp_call_func_t func,
+		struct __call_single_data *csd),
+
+	TP_ARGS(cpu, callsite, func, csd),
+
+	TP_STRUCT__entry(
+		__field(unsigned int, cpu)
+		__field(void *, callsite)
+		__field(void *, func)
+		__field(void *, csd)
+		),
+
+	    TP_fast_assign(
+		__entry->cpu = cpu;
+		__entry->callsite = (void *)callsite;
+		__entry->func = func;
+		__entry->csd  = csd;
+		),
+
+	TP_printk("cpu=%u callsite=%pS func=%ps csd=%p",
+		__entry->cpu, __entry->callsite, __entry->func, __entry->csd)
+	);
+
 /*
  * Tracepoints for a function which is called as an effect of smp_call_function.*
  */

kernel/smp.c

@@ -340,15 +340,15 @@ 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_cpu_enabled()) {
+	if (trace_csd_queue_cpu_enabled()) {
 		call_single_data_t *csd;
 		smp_call_func_t func;
 
 		csd = container_of(node, call_single_data_t, node.llist);
 		func = CSD_TYPE(csd) == CSD_TYPE_TTWU ?
 			sched_ttwu_pending : csd->func;
 
-		trace_ipi_send_cpu(cpu, _RET_IP_, func);
+		trace_csd_queue_cpu(cpu, _RET_IP_, func, csd);
 	}
 
 	/*
@@ -741,7 +741,7 @@ static void smp_call_function_many_cond(const struct cpumask *mask,
 	int cpu, last_cpu, this_cpu = smp_processor_id();
 	struct call_function_data *cfd;
 	bool wait = scf_flags & SCF_WAIT;
-	int nr_cpus = 0, nr_queued = 0;
+	int nr_cpus = 0;
 	bool run_remote = false;
 	bool run_local = false;
 
@@ -799,21 +799,15 @@ static void smp_call_function_many_cond(const struct cpumask *mask,
 			csd->node.src = smp_processor_id();
 			csd->node.dst = cpu;
 #endif
+			trace_csd_queue_cpu(cpu, _RET_IP_, func, csd);
+
 			if (llist_add(&csd->node.llist, &per_cpu(call_single_queue, cpu))) {
 				__cpumask_set_cpu(cpu, cfd->cpumask_ipi);
 				nr_cpus++;
 				last_cpu = cpu;
 			}
-			nr_queued++;
 		}
 
-		/*
-		 * Trace each smp_function_call_*() as an IPI, actual IPIs
-		 * will be traced with func==generic_smp_call_function_single_ipi().
-		 */
-		if (nr_queued)
-			trace_ipi_send_cpumask(cfd->cpumask, _RET_IP_, func);
-
 		/*
 		 * Choose the most efficient way to send an IPI. Note that the
 		 * number of CPUs might be zero due to concurrent changes to the