[PATCH] sched: Set need-resched flags before tracing

[Andrea Righi]

sched_set_need_resched_tp is emitted before the corresponding thread
flag is set. This allows a BPF tracepoint program to recursively invoke
the same tracepoint while leaving its RCU read-side critical section.

If rcu_read_unlock_special() must defer a quiescent state while
preemption or interrupts are disabled, it calls
set_need_resched_current(). Since TIF_NEED_RESCHED is still clear, this
emits the tracepoint again and repeats until the kernel stack overflows:

  __trace_set_need_resched()
    bpf_trace_run3()
      rcu_read_unlock_migrate()
        rcu_read_unlock_special()
          set_need_resched_current()
            set_tsk_need_resched()
              __trace_set_need_resched()

Set the thread flag before emitting the tracepoint in both
set_tsk_need_resched() and __resched_curr(). For a remote reschedule,
retain the result of set_nr_and_not_polling() so that tracing remains
ahead of IPI delivery while still observing the updated flag.

Fixes: adcc3bfa8806 ("sched: Adapt sched tracepoints for RV task model")
Signed-off-by: Andrea Righi <arighi@xxxxxxxxxx>
---
 include/linux/sched.h | 5 ++++-
 kernel/sched/core.c   | 7 +++++--
 2 files changed, 9 insertions(+), 3 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 59f6366fdf501..6003dcd080e6c 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2105,8 +2105,11 @@ 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))
+	    !test_tsk_thread_flag(tsk, TIF_NEED_RESCHED)) {
+		set_tsk_thread_flag(tsk, TIF_NEED_RESCHED);
 		__trace_set_need_resched(tsk, TIF_NEED_RESCHED);
+		return;
+	}
 	set_tsk_thread_flag(tsk,TIF_NEED_RESCHED);
 }
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 91f059a556950..aed403fd2f82e 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1196,6 +1196,7 @@ static void __resched_curr(struct rq *rq, int tif)
 {
 	struct task_struct *curr = rq->curr;
 	struct thread_info *cti = task_thread_info(curr);
+	bool send_ipi;
 	int cpu;
 
 	lockdep_assert_rq_held(rq);
@@ -1212,15 +1213,17 @@ 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)
 			set_preempt_need_resched();
+		trace_sched_set_need_resched_tp(curr, cpu, tif);
 		return;
 	}
 
-	if (set_nr_and_not_polling(cti, tif)) {
+	send_ipi = set_nr_and_not_polling(cti, tif);
+	trace_sched_set_need_resched_tp(curr, cpu, tif);
+	if (send_ipi) {
 		if (tif == TIF_NEED_RESCHED)
 			smp_send_reschedule(cpu);
 	} else {
-- 
2.55.0