[PATCH v2 2/2] sched/core: Avoid double calling update_rq_clock()

[Hao Jia]

There are some double rq clock update warnings are triggered.
------------[ cut here ]------------
rq->clock_update_flags & RQCF_UPDATED
WARNING: CPU: 17 PID: 138 at kernel/sched/core.c:741
update_rq_clock+0xaf/0x180
Call Trace:
 <TASK>
 __balance_push_cpu_stop+0x146/0x180
 ? migration_cpu_stop+0x2a0/0x2a0
 cpu_stopper_thread+0xa3/0x140
 smpboot_thread_fn+0x14f/0x210
 ? sort_range+0x20/0x20
 kthread+0xe6/0x110
 ? kthread_complete_and_exit+0x20/0x20
 ret_from_fork+0x1f/0x30

------------[ cut here ]------------
rq->clock_update_flags & RQCF_UPDATED
WARNING: CPU: 54 PID: 0 at kernel/sched/core.c:741
update_rq_clock+0xaf/0x180
Call Trace:
 <TASK>
 unthrottle_cfs_rq+0x4b/0x300
 __cfsb_csd_unthrottle+0xe0/0x100
 __flush_smp_call_function_queue+0xaf/0x1d0
 flush_smp_call_function_queue+0x49/0x90
 do_idle+0x17c/0x270
 cpu_startup_entry+0x19/0x20
 start_secondary+0xfa/0x120
 secondary_startup_64_no_verify+0xce/0xdb

------------[ cut here ]------------
rq->clock_update_flags & RQCF_UPDATED
WARNING: CPU: 0 PID: 3323 at kernel/sched/core.c:741
update_rq_clock+0xaf/0x180
Call Trace:
 <TASK>
 unthrottle_cfs_rq+0x4b/0x300
 rq_offline_fair+0x89/0x90
 set_rq_offline.part.118+0x28/0x60
 rq_attach_root+0xc4/0xd0
 cpu_attach_domain+0x3dc/0x7f0
 partition_sched_domains_locked+0x2a5/0x3c0
 rebuild_sched_domains_locked+0x477/0x830
 rebuild_sched_domains+0x1b/0x30
 cpuset_hotplug_workfn+0x2ca/0xc90
 ? balance_push+0x56/0xf0
 ? _raw_spin_unlock+0x15/0x30
 ? finish_task_switch+0x98/0x2f0
 ? __switch_to+0x291/0x410
 ? __schedule+0x65e/0x1310
 process_one_work+0x1bc/0x3d0
 worker_thread+0x4c/0x380
 ? preempt_count_add+0x92/0xa0
 ? rescuer_thread+0x310/0x310
 kthread+0xe6/0x110
 ? kthread_complete_and_exit+0x20/0x20
 ret_from_fork+0x1f/0x30

For the __balance_push_cpu_stop() case, we remove update_rq_clock() from
the __migrate_task() function to avoid double updating the rq clock.
And in order to avoid missing rq clock update, add update_rq_clock()
call before migration_cpu_stop() calls __migrate_task().

For the unthrottle_cfs_rq() case, we use rq_clock_start_loop_update() to
prevent multiple calls to update_rq_clock() in unthrottle_cfs_rq().

Note that the rq clock has been updated before the set_rq_offline()
function runs, so we don't need to call update_rq_clock() in
unthrottle_offline_cfs_rqs().

Suggested-by: Vincent Guittot <vincent.guittot@xxxxxxxxxx>
Signed-off-by: Hao Jia <jiahao.os@xxxxxxxxxxxxx>
---
 kernel/sched/core.c  |  7 ++++---
 kernel/sched/fair.c  | 16 ++++++++++++++++
 kernel/sched/sched.h | 21 +++++++++++++++++++++
 3 files changed, 41 insertions(+), 3 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 944c3ae39861..2bcf6a8e71fc 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2398,7 +2398,6 @@ static struct rq *__migrate_task(struct rq *rq, struct rq_flags *rf,
 	if (!is_cpu_allowed(p, dest_cpu))
 		return rq;
 
-	update_rq_clock(rq);
 	rq = move_queued_task(rq, rf, p, dest_cpu);
 
 	return rq;
@@ -2456,10 +2455,12 @@ static int migration_cpu_stop(void *data)
 				goto out;
 		}
 
-		if (task_on_rq_queued(p))
+		if (task_on_rq_queued(p)) {
+			update_rq_clock(rq);
 			rq = __migrate_task(rq, &rf, p, arg->dest_cpu);
-		else
+		} else {
 			p->wake_cpu = arg->dest_cpu;
+		}
 
 		/*
 		 * XXX __migrate_task() can fail, at which point we might end
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 373ff5f55884..9ec7bde620ff 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5575,6 +5575,13 @@ static void __cfsb_csd_unthrottle(void *arg)
 	struct rq_flags rf;
 
 	rq_lock(rq, &rf);
+	/*
+	 * Iterating over the list can trigger several call to
+	 * update_rq_clock() in unthrottle_cfs_rq().
+	 * Do it once and skip the potential next ones.
+	 */
+	update_rq_clock(rq);
+	rq_clock_start_loop_update(rq);
 
 	/*
 	 * Since we hold rq lock we're safe from concurrent manipulation of
@@ -5595,6 +5602,7 @@ static void __cfsb_csd_unthrottle(void *arg)
 
 	rcu_read_unlock();
 
+	rq_clock_stop_loop_update(rq);
 	rq_unlock(rq, &rf);
 }
 
@@ -6114,6 +6122,12 @@ static void __maybe_unused unthrottle_offline_cfs_rqs(struct rq *rq)
 	struct task_group *tg;
 
 	lockdep_assert_rq_held(rq);
+	/*
+	 * The rq clock has already been updated before the
+	 * set_rq_offline() runs, so we should skip updating
+	 * the rq clock again in unthrottle_cfs_rq().
+	 */
+	rq_clock_start_loop_update(rq);
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(tg, &task_groups, list) {
@@ -6137,6 +6151,8 @@ static void __maybe_unused unthrottle_offline_cfs_rqs(struct rq *rq)
 			unthrottle_cfs_rq(cfs_rq);
 	}
 	rcu_read_unlock();
+
+	rq_clock_stop_loop_update(rq);
 }
 
 #else /* CONFIG_CFS_BANDWIDTH */
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index ec7b3e0a2b20..9c712f29e5a4 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1536,6 +1536,27 @@ static inline void rq_clock_skip_update(struct rq *rq)
 	rq->clock_update_flags |= RQCF_REQ_SKIP;
 }
 
+/*
+ * During cpu offlining and rq wide unthrottling, we can trigger
+ * an update_rq_clock() for several cfs and rt runqueues (Typically
+ * when using list_for_each_entry_*)
+ * rq_clock_start_loop_update() can be called after updating the clock
+ * once and before iterating over the list to prevent multiple update.
+ * After the iterative traversal, we need to call rq_clock_stop_loop_update()
+ * to restore rq->clock_update_flags.
+ */
+static inline void rq_clock_start_loop_update(struct rq *rq)
+{
+	lockdep_assert_rq_held(rq);
+	rq->clock_update_flags |= RQCF_ACT_SKIP;
+}
+
+static inline void rq_clock_stop_loop_update(struct rq *rq)
+{
+	lockdep_assert_rq_held(rq);
+	rq->clock_update_flags &= ~RQCF_ACT_SKIP;
+}
+
 /*
  * See rt task throttling, which is the only time a skip
  * request is canceled.
-- 
2.37.0