sched/core: Avoid obvious double update_rq_clock warning

When we use raw_spin_rq_lock() to acquire the rq lock and have to
update the rq clock while holding the lock, the kernel may issue
a WARN_DOUBLE_CLOCK warning.

Since we directly use raw_spin_rq_lock() to acquire rq lock instead of
rq_lock(), there is no corresponding change to rq->clock_update_flags.
In particular, we have obtained the rq lock of other CPUs, the
rq->clock_update_flags of this CPU may be RQCF_UPDATED at this time, and
then calling update_rq_clock() will trigger the WARN_DOUBLE_CLOCK warning.

So we need to clear RQCF_UPDATED of rq->clock_update_flags to avoid
the WARN_DOUBLE_CLOCK warning.

For the sched_rt_period_timer() and migrate_task_rq_dl() cases
we simply replace raw_spin_rq_lock()/raw_spin_rq_unlock() with
rq_lock()/rq_unlock().

For the {pull,push}_{rt,dl}_task() cases, we add the
double_rq_clock_clear_update() function to clear RQCF_UPDATED of
rq->clock_update_flags, and call double_rq_clock_clear_update()
before double_lock_balance()/double_rq_lock() returns to avoid the
WARN_DOUBLE_CLOCK warning.

Some call trace reports:
Call Trace 1:
 <IRQ>
 sched_rt_period_timer+0x10f/0x3a0
 ? enqueue_top_rt_rq+0x110/0x110
 __hrtimer_run_queues+0x1a9/0x490
 hrtimer_interrupt+0x10b/0x240
 __sysvec_apic_timer_interrupt+0x8a/0x250
 sysvec_apic_timer_interrupt+0x9a/0xd0
 </IRQ>
 <TASK>
 asm_sysvec_apic_timer_interrupt+0x12/0x20

Call Trace 2:
 <TASK>
 activate_task+0x8b/0x110
 push_rt_task.part.108+0x241/0x2c0
 push_rt_tasks+0x15/0x30
 finish_task_switch+0xaa/0x2e0
 ? __switch_to+0x134/0x420
 __schedule+0x343/0x8e0
 ? hrtimer_start_range_ns+0x101/0x340
 schedule+0x4e/0xb0
 do_nanosleep+0x8e/0x160
 hrtimer_nanosleep+0x89/0x120
 ? hrtimer_init_sleeper+0x90/0x90
 __x64_sys_nanosleep+0x96/0xd0
 do_syscall_64+0x34/0x90
 entry_SYSCALL_64_after_hwframe+0x44/0xae

Call Trace 3:
 <TASK>
 deactivate_task+0x93/0xe0
 pull_rt_task+0x33e/0x400
 balance_rt+0x7e/0x90
 __schedule+0x62f/0x8e0
 do_task_dead+0x3f/0x50
 do_exit+0x7b8/0xbb0
 do_group_exit+0x2d/0x90
 get_signal+0x9df/0x9e0
 ? preempt_count_add+0x56/0xa0
 ? __remove_hrtimer+0x35/0x70
 arch_do_signal_or_restart+0x36/0x720
 ? nanosleep_copyout+0x39/0x50
 ? do_nanosleep+0x131/0x160
 ? audit_filter_inodes+0xf5/0x120
 exit_to_user_mode_prepare+0x10f/0x1e0
 syscall_exit_to_user_mode+0x17/0x30
 do_syscall_64+0x40/0x90
 entry_SYSCALL_64_after_hwframe+0x44/0xae

Call Trace 4:
 update_rq_clock+0x128/0x1a0
 migrate_task_rq_dl+0xec/0x310
 set_task_cpu+0x84/0x1e4
 try_to_wake_up+0x1d8/0x5c0
 wake_up_process+0x1c/0x30
 hrtimer_wakeup+0x24/0x3c
 __hrtimer_run_queues+0x114/0x270
 hrtimer_interrupt+0xe8/0x244
 arch_timer_handler_phys+0x30/0x50
 handle_percpu_devid_irq+0x88/0x140
 generic_handle_domain_irq+0x40/0x60
 gic_handle_irq+0x48/0xe0
 call_on_irq_stack+0x2c/0x60
 do_interrupt_handler+0x80/0x84

Steps to reproduce:
1. Enable CONFIG_SCHED_DEBUG when compiling the kernel
2. echo 1 > /sys/kernel/debug/clear_warn_once
   echo "WARN_DOUBLE_CLOCK" > /sys/kernel/debug/sched/features
   echo "NO_RT_PUSH_IPI" > /sys/kernel/debug/sched/features
3. Run some rt/dl tasks that periodically work and sleep, e.g.
Create 2*n rt or dl (90% running) tasks via rt-app (on a system
with n CPUs), and Dietmar Eggemann reports Call Trace 4 when running
on PREEMPT_RT kernel.

Signed-off-by: Hao Jia <jiahao.os@bytedance.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Link: https://lore.kernel.org/r/20220430085843.62939-2-jiahao.os@bytedance.com

1 files changed, 24 insertions, 4 deletions

diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 7f338c53ce42..fe4d1acb7e38 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2474,6 +2474,24 @@ unsigned long arch_scale_freq_capacity(int cpu)
 }
 #endif
 
+#ifdef CONFIG_SCHED_DEBUG
+/*
+ * In double_lock_balance()/double_rq_lock(), we use raw_spin_rq_lock() to
+ * acquire rq lock instead of rq_lock(). So at the end of these two functions
+ * we need to call double_rq_clock_clear_update() to clear RQCF_UPDATED of
+ * rq->clock_update_flags to avoid the WARN_DOUBLE_CLOCK warning.
+ */
+static inline void double_rq_clock_clear_update(struct rq *rq1, struct rq *rq2)
+{
+	rq1->clock_update_flags &= (RQCF_REQ_SKIP|RQCF_ACT_SKIP);
+	/* rq1 == rq2 for !CONFIG_SMP, so just clear RQCF_UPDATED once. */
+#ifdef CONFIG_SMP
+	rq2->clock_update_flags &= (RQCF_REQ_SKIP|RQCF_ACT_SKIP);
+#endif
+}
+#else
+static inline void double_rq_clock_clear_update(struct rq *rq1, struct rq *rq2) {}
+#endif
 
 #ifdef CONFIG_SMP
 
@@ -2539,14 +2557,15 @@ static inline int _double_lock_balance(struct rq *this_rq, struct rq *busiest)
 	__acquires(busiest->lock)
 	__acquires(this_rq->lock)
 {
-	if (__rq_lockp(this_rq) == __rq_lockp(busiest))
-		return 0;
-
-	if (likely(raw_spin_rq_trylock(busiest)))
+	if (__rq_lockp(this_rq) == __rq_lockp(busiest) ||
+	    likely(raw_spin_rq_trylock(busiest))) {
+		double_rq_clock_clear_update(this_rq, busiest);
 		return 0;
+	}
 
 	if (rq_order_less(this_rq, busiest)) {
 		raw_spin_rq_lock_nested(busiest, SINGLE_DEPTH_NESTING);
+		double_rq_clock_clear_update(this_rq, busiest);
 		return 0;
 	}
 
@@ -2640,6 +2659,7 @@ static inline void double_rq_lock(struct rq *rq1, struct rq *rq2)
 	BUG_ON(rq1 != rq2);
 	raw_spin_rq_lock(rq1);
 	__acquire(rq2->lock);	/* Fake it out ;) */
+	double_rq_clock_clear_update(rq1, rq2);
 }
 
 /*