sched: Add sched tracepoints for RV task model

Add the following tracepoints:
* sched_entry(bool preempt, ip)
    Called while entering __schedule
* sched_exit(bool is_switch, ip)
    Called while exiting __schedule
* sched_set_state(task, curr_state, state)
    Called when a task changes its state (to and from running)

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: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Juri Lelli <juri.lelli@redhat.com>
Link: https://lore.kernel.org/20250305140406.350227-2-gmonaco@redhat.com
Signed-off-by: Gabriele Monaco <gmonaco@redhat.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>

include/linux/rv.h

@@ -7,7 +7,7 @@
 #ifndef _LINUX_RV_H
 #define _LINUX_RV_H
 
-#define MAX_DA_NAME_LEN	24
+#define MAX_DA_NAME_LEN	32
 
 #ifdef CONFIG_RV
 /*

include/linux/sched.h

@@ -46,6 +46,7 @@
 #include <linux/rv.h>
 #include <linux/livepatch_sched.h>
 #include <linux/uidgid_types.h>
+#include <linux/tracepoint-defs.h>
 #include <asm/kmap_size.h>
 
 /* task_struct member predeclarations (sorted alphabetically): */
@@ -186,6 +187,12 @@ struct user_event_mm;
 # define debug_rtlock_wait_restore_state()	do { } while (0)
 #endif
 
+#define trace_set_current_state(state_value)                     \
+	do {                                                     \
+		if (tracepoint_enabled(sched_set_state_tp))      \
+			__trace_set_current_state(state_value); \
+	} while (0)
+
 /*
  * set_current_state() includes a barrier so that the write of current->__state
  * is correctly serialised wrt the caller's subsequent test of whether to
@@ -226,12 +233,14 @@ struct user_event_mm;
 #define __set_current_state(state_value)				\
 	do {								\
 		debug_normal_state_change((state_value));		\
+		trace_set_current_state(state_value);			\
 		WRITE_ONCE(current->__state, (state_value));		\
 	} while (0)
 
 #define set_current_state(state_value)					\
 	do {								\
 		debug_normal_state_change((state_value));		\
+		trace_set_current_state(state_value);			\
 		smp_store_mb(current->__state, (state_value));		\
 	} while (0)
 
@@ -247,6 +256,7 @@ struct user_event_mm;
 									\
 		raw_spin_lock_irqsave(&current->pi_lock, flags);	\
 		debug_special_state_change((state_value));		\
+		trace_set_current_state(state_value);			\
 		WRITE_ONCE(current->__state, (state_value));		\
 		raw_spin_unlock_irqrestore(&current->pi_lock, flags);	\
 	} while (0)
@@ -282,6 +292,7 @@ struct user_event_mm;
 		raw_spin_lock(&current->pi_lock);			\
 		current->saved_state = current->__state;		\
 		debug_rtlock_wait_set_state();				\
+		trace_set_current_state(TASK_RTLOCK_WAIT);		\
 		WRITE_ONCE(current->__state, TASK_RTLOCK_WAIT);		\
 		raw_spin_unlock(&current->pi_lock);			\
 	} while (0);
@@ -291,6 +302,7 @@ struct user_event_mm;
 		lockdep_assert_irqs_disabled();				\
 		raw_spin_lock(&current->pi_lock);			\
 		debug_rtlock_wait_restore_state();			\
+		trace_set_current_state(current->saved_state);		\
 		WRITE_ONCE(current->__state, current->saved_state);	\
 		current->saved_state = TASK_RUNNING;			\
 		raw_spin_unlock(&current->pi_lock);			\
@@ -327,6 +339,10 @@ 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 */
+DECLARE_TRACEPOINT(sched_set_state_tp);
+extern void __trace_set_current_state(int state_value);
+
 /**
  * struct prev_cputime - snapshot of system and user cputime
  * @utime: time spent in user mode

include/trace/events/sched.h

@@ -824,6 +824,19 @@ DECLARE_TRACE(sched_compute_energy_tp,
 		 unsigned long max_util, unsigned long busy_time),
 	TP_ARGS(p, dst_cpu, energy, max_util, busy_time));
 
+DECLARE_TRACE(sched_entry_tp,
+	TP_PROTO(bool preempt, unsigned long ip),
+	TP_ARGS(preempt, ip));
+
+DECLARE_TRACE(sched_exit_tp,
+	TP_PROTO(bool is_switch, unsigned long ip),
+	TP_ARGS(is_switch, ip));
+
+DECLARE_TRACE_CONDITION(sched_set_state_tp,
+	TP_PROTO(struct task_struct *tsk, int state),
+	TP_ARGS(tsk, state),
+	TP_CONDITION(!!(tsk->__state) != !!state));
+
 #endif /* _TRACE_SCHED_H */
 
 /* This part must be outside protection */

kernel/sched/core.c

@@ -491,6 +491,16 @@ sched_core_dequeue(struct rq *rq, struct task_struct *p, int flags) { }
 
 #endif /* CONFIG_SCHED_CORE */
 
+/* need a wrapper since we may need to trace from modules */
+EXPORT_TRACEPOINT_SYMBOL(sched_set_state_tp);
+
+/* Call via the helper macro trace_set_current_state. */
+void __trace_set_current_state(int state_value)
+{
+	trace_sched_set_state_tp(current, state_value);
+}
+EXPORT_SYMBOL(__trace_set_current_state);
+
 /*
  * Serialization rules:
  *
@@ -5307,6 +5317,12 @@ asmlinkage __visible void schedule_tail(struct task_struct *prev)
 	 */
 
 	finish_task_switch(prev);
+	/*
+	 * This is a special case: the newly created task has just
+	 * 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);
 	preempt_enable();
 
 	if (current->set_child_tid)
@@ -6650,12 +6666,15 @@ static void __sched notrace __schedule(int sched_mode)
 	 * as a preemption by schedule_debug() and RCU.
 	 */
 	bool preempt = sched_mode > SM_NONE;
+	bool is_switch = false;
 	unsigned long *switch_count;
 	unsigned long prev_state;
 	struct rq_flags rf;
 	struct rq *rq;
 	int cpu;
 
+	trace_sched_entry_tp(preempt, CALLER_ADDR0);
+
 	cpu = smp_processor_id();
 	rq = cpu_rq(cpu);
 	prev = rq->curr;
@@ -6723,7 +6742,8 @@ picked:
 	rq->last_seen_need_resched_ns = 0;
 #endif
 
-	if (likely(prev != next)) {
+	is_switch = prev != next;
+	if (likely(is_switch)) {
 		rq->nr_switches++;
 		/*
 		 * RCU users of rcu_dereference(rq->curr) may not see
@@ -6768,6 +6788,7 @@ picked:
 		__balance_callbacks(rq);
 		raw_spin_rq_unlock_irq(rq);
 	}
+	trace_sched_exit_tp(is_switch, CALLER_ADDR0);
 }
 
 void __noreturn do_task_dead(void)

tools/verification/rv/include/rv.h

@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 
 #define MAX_DESCRIPTION 1024
-#define MAX_DA_NAME_LEN	24
+#define MAX_DA_NAME_LEN	32
 
 struct monitor {
 	char name[MAX_DA_NAME_LEN];