Merge tag 'smp-core-2023-04-27' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull SMP cross-CPU function-call updates from Ingo Molnar:

 - Remove diagnostics and adjust config for CSD lock diagnostics

 - Add a generic IPI-sending tracepoint, as currently there's no easy
   way to instrument IPI origins: it's arch dependent and for some major
   architectures it's not even consistently available.

* tag 'smp-core-2023-04-27' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  trace,smp: Trace all smp_function_call*() invocations
  trace: Add trace_ipi_send_cpu()
  sched, smp: Trace smp callback causing an IPI
  smp: reword smp call IPI comment
  treewide: Trace IPIs sent via smp_send_reschedule()
  irq_work: Trace self-IPIs sent via arch_irq_work_raise()
  smp: Trace IPIs sent via arch_send_call_function_ipi_mask()
  sched, smp: Trace IPIs sent via send_call_function_single_ipi()
  trace: Add trace_ipi_send_cpumask()
  kernel/smp: Make csdlock_debug= resettable
  locking/csd_lock: Remove per-CPU data indirection from CSD lock debugging
  locking/csd_lock: Remove added data from CSD lock debugging
  locking/csd_lock: Add Kconfig option for csd_debug default

2 files changed, 53 insertions, 2 deletions

diff --git a/include/linux/smp.h b/include/linux/smp.h
index 7b93504eed26..91ea4a67f8ca 100644
--- a/include/linux/smp.h
+++ b/include/linux/smp.h
@@ -125,8 +125,15 @@ extern void smp_send_stop(void);
 /*
  * sends a 'reschedule' event to another CPU:
  */
-extern void smp_send_reschedule(int cpu);
-
+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_cpu(cpu, _RET_IP_, NULL);  \
+	arch_smp_send_reschedule(cpu);		  \
+})
 
 /*
  * Prepare machine for booting other CPUs.
diff --git a/include/trace/events/ipi.h b/include/trace/events/ipi.h
index 0be71dad6ec0..3de9bfc982ce 100644
--- a/include/trace/events/ipi.h
+++ b/include/trace/events/ipi.h
@@ -35,6 +35,50 @@ 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),
+
+	TP_ARGS(cpumask, callsite, callback),
+
+	TP_STRUCT__entry(
+		__cpumask(cpumask)
+		__field(void *, callsite)
+		__field(void *, callback)
+	),
+
+	TP_fast_assign(
+		__assign_cpumask(cpumask, cpumask_bits(cpumask));
+		__entry->callsite = (void *)callsite;
+		__entry->callback = callback;
+	),
+
+	TP_printk("cpumask=%s callsite=%pS callback=%pS",
+		  __get_cpumask(cpumask), __entry->callsite, __entry->callback)
+);
+
 DECLARE_EVENT_CLASS(ipi_handler,
 
 	TP_PROTO(const char *reason),