sched: Adapt sched tracepoints for RV task model

Add the following tracepoint:
* sched_set_need_resched(tsk, cpu, tif)
    Called when a task is set the need resched [lazy] flag

Remove the unused ip parameter from sched_entry and sched_exit and alter
sched_entry to have a value of preempt consistent with the one used in
sched_switch.

Also adapt all monitors using sched_{entry,exit} to avoid breaking build.

These tracepoints are useful to describe the Linux task model and are
adapted from the patches by Daniel Bristot de Oliveira
(https://bristot.me/linux-task-model/).

Cc: Ingo Molnar <mingo@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Nam Cao <namcao@linutronix.de>
Cc: Tomas Glozar <tglozar@redhat.com>
Cc: Juri Lelli <jlelli@redhat.com>
Cc: Clark Williams <williams@redhat.com>
Cc: John Kacur <jkacur@redhat.com>
Link: https://lore.kernel.org/20250728135022.255578-7-gmonaco@redhat.com
Signed-off-by: Gabriele Monaco <gmonaco@redhat.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>

Author: glemco

include/linux/sched.h

@@ -339,9 +339,11 @@ extern void io_schedule_finish(int token);
 extern long io_schedule_timeout(long timeout);
 extern void io_schedule(void);
 
-/* wrapper function to trace from this header file */
+/* wrapper functions to trace from this header file */
 DECLARE_TRACEPOINT(sched_set_state_tp);
 extern void __trace_set_current_state(int state_value);
+DECLARE_TRACEPOINT(sched_set_need_resched_tp);
+extern void __trace_set_need_resched(struct task_struct *curr, int tif);
 
 /**
  * struct prev_cputime - snapshot of system and user cputime
@@ -2063,6 +2065,9 @@ static inline int test_tsk_thread_flag(struct task_struct *tsk, int flag)
 
 static inline void set_tsk_need_resched(struct task_struct *tsk)
 {
+	if (tracepoint_enabled(sched_set_need_resched_tp) &&
+	    !test_tsk_thread_flag(tsk, TIF_NEED_RESCHED))
+		__trace_set_need_resched(tsk, TIF_NEED_RESCHED);
 	set_tsk_thread_flag(tsk,TIF_NEED_RESCHED);
 }
 

include/trace/events/sched.h

@@ -882,18 +882,22 @@ DECLARE_TRACE(sched_compute_energy,
 	TP_ARGS(p, dst_cpu, energy, max_util, busy_time));
 
 DECLARE_TRACE(sched_entry,
-	TP_PROTO(bool preempt, unsigned long ip),
-	TP_ARGS(preempt, ip));
+	TP_PROTO(bool preempt),
+	TP_ARGS(preempt));
 
 DECLARE_TRACE(sched_exit,
-	TP_PROTO(bool is_switch, unsigned long ip),
-	TP_ARGS(is_switch, ip));
+	TP_PROTO(bool is_switch),
+	TP_ARGS(is_switch));
 
 DECLARE_TRACE_CONDITION(sched_set_state,
 	TP_PROTO(struct task_struct *tsk, int state),
 	TP_ARGS(tsk, state),
 	TP_CONDITION(!!(tsk->__state) != !!state));
 
+DECLARE_TRACE(sched_set_need_resched,
+	TP_PROTO(struct task_struct *tsk, int cpu, int tif),
+	TP_ARGS(tsk, cpu, tif));
+
 #endif /* _TRACE_SCHED_H */
 
 /* This part must be outside protection */

kernel/sched/core.c

@@ -1110,6 +1110,7 @@ static void __resched_curr(struct rq *rq, int tif)
 
 	cpu = cpu_of(rq);
 
+	trace_sched_set_need_resched_tp(curr, cpu, tif);
 	if (cpu == smp_processor_id()) {
 		set_ti_thread_flag(cti, tif);
 		if (tif == TIF_NEED_RESCHED)
@@ -1125,6 +1126,11 @@ static void __resched_curr(struct rq *rq, int tif)
 	}
 }
 
+void __trace_set_need_resched(struct task_struct *curr, int tif)
+{
+	trace_sched_set_need_resched_tp(curr, smp_processor_id(), tif);
+}
+
 void resched_curr(struct rq *rq)
 {
 	__resched_curr(rq, TIF_NEED_RESCHED);
@@ -5329,7 +5335,7 @@ asmlinkage __visible void schedule_tail(struct task_struct *prev)
 	 * switched the context for the first time. It is returning from
 	 * schedule for the first time in this path.
 	 */
-	trace_sched_exit_tp(true, CALLER_ADDR0);
+	trace_sched_exit_tp(true);
 	preempt_enable();
 
 	if (current->set_child_tid)
@@ -6678,7 +6684,8 @@ static void __sched notrace __schedule(int sched_mode)
 	struct rq *rq;
 	int cpu;
 
-	trace_sched_entry_tp(preempt, CALLER_ADDR0);
+	/* Trace preemptions consistently with task switches */
+	trace_sched_entry_tp(sched_mode == SM_PREEMPT);
 
 	cpu = smp_processor_id();
 	rq = cpu_rq(cpu);
@@ -6793,7 +6800,7 @@ static void __sched notrace __schedule(int sched_mode)
 		__balance_callbacks(rq);
 		raw_spin_rq_unlock_irq(rq);
 	}
-	trace_sched_exit_tp(is_switch, CALLER_ADDR0);
+	trace_sched_exit_tp(is_switch);
 }
 
 void __noreturn do_task_dead(void)

kernel/trace/rv/monitors/sco/sco.c

@@ -24,12 +24,12 @@ static void handle_sched_set_state(void *data, struct task_struct *tsk, int stat
 	da_handle_start_event_sco(sched_set_state_sco);
 }
 
-static void handle_schedule_entry(void *data, bool preempt, unsigned long ip)
+static void handle_schedule_entry(void *data, bool preempt)
 {
 	da_handle_event_sco(schedule_entry_sco);
 }
 
-static void handle_schedule_exit(void *data, bool is_switch, unsigned long ip)
+static void handle_schedule_exit(void *data, bool is_switch)
 {
 	da_handle_start_event_sco(schedule_exit_sco);
 }

kernel/trace/rv/monitors/scpd/scpd.c

@@ -30,12 +30,12 @@ static void handle_preempt_enable(void *data, unsigned long ip, unsigned long pa
 	da_handle_start_event_scpd(preempt_enable_scpd);
 }
 
-static void handle_schedule_entry(void *data, bool preempt, unsigned long ip)
+static void handle_schedule_entry(void *data, bool preempt)
 {
 	da_handle_event_scpd(schedule_entry_scpd);
 }
 
-static void handle_schedule_exit(void *data, bool is_switch, unsigned long ip)
+static void handle_schedule_exit(void *data, bool is_switch)
 {
 	da_handle_event_scpd(schedule_exit_scpd);
 }

kernel/trace/rv/monitors/sncid/sncid.c

@@ -30,12 +30,12 @@ static void handle_irq_enable(void *data, unsigned long ip, unsigned long parent
 	da_handle_start_event_sncid(irq_enable_sncid);
 }
 
-static void handle_schedule_entry(void *data, bool preempt, unsigned long ip)
+static void handle_schedule_entry(void *data, bool preempt)
 {
 	da_handle_start_event_sncid(schedule_entry_sncid);
 }
 
-static void handle_schedule_exit(void *data, bool is_switch, unsigned long ip)
+static void handle_schedule_exit(void *data, bool is_switch)
 {
 	da_handle_start_event_sncid(schedule_exit_sncid);
 }

kernel/trace/rv/monitors/snep/snep.c

@@ -30,12 +30,12 @@ static void handle_preempt_enable(void *data, unsigned long ip, unsigned long pa
 	da_handle_start_event_snep(preempt_enable_snep);
 }
 
-static void handle_schedule_entry(void *data, bool preempt, unsigned long ip)
+static void handle_schedule_entry(void *data, bool preempt)
 {
 	da_handle_event_snep(schedule_entry_snep);
 }
 
-static void handle_schedule_exit(void *data, bool is_switch, unsigned long ip)
+static void handle_schedule_exit(void *data, bool is_switch)
 {
 	da_handle_start_event_snep(schedule_exit_snep);
 }

kernel/trace/rv/monitors/tss/tss.c

@@ -27,12 +27,12 @@ static void handle_sched_switch(void *data, bool preempt,
 	da_handle_event_tss(sched_switch_tss);
 }
 
-static void handle_schedule_entry(void *data, bool preempt, unsigned long ip)
+static void handle_schedule_entry(void *data, bool preempt)
 {
 	da_handle_event_tss(schedule_entry_tss);
 }
 
-static void handle_schedule_exit(void *data, bool is_switch, unsigned long ip)
+static void handle_schedule_exit(void *data, bool is_switch)
 {
 	da_handle_start_event_tss(schedule_exit_tss);
 }