The following warning is being encountered at boot time:
WARNING: CPU: 94 PID: 588 at kernel/time/hrtimer.c:1086 hrtimer_start_range_ns+0x289/0x2d0
Modules linked in:
CPU: 94 UID: 0 PID: 588 Comm: migration/94 Not tainted
Stopper: multi_cpu_stop+0x0/0x120 <- stop_machine_cpuslocked+0x66/0xc0
RIP: 0010:hrtimer_start_range_ns+0x289/0x2d0
Code: 41 5c 41 5d 41 5e 41 5f 5d e9 63 94 ea 00 0f 0b 48 83 c4 10 5b 41 5c 41 5d 41 5e 41 5f 5d e9 39 fc 15 01 0f 0b e9 c1 fd ff ff <0f> 0b 48 8b 45 00 e9 59 ff ff ff f3 0f 1e fa 65 8b 05 1d ec e8 7e
RSP: 0018:ffffc900019cbcc8 EFLAGS: 00010046
RAX: ffff88bf449a4c40 RBX: 0000000000000082 RCX: 0000000000000001
RDX: 0000000000000001 RSI: ffff88bf43224c80 RDI: ffff88bf449a4c40
RBP: ffff88bf449a4c80 R08: ffff888280970090 R09: 0000000000000000
R10: ffff88bf432252e0 R11: ffffffff811abf70 R12: ffff88bf449a4c40
R13: ffff88bf43234b28 R14: ffff88bf43224c80 R15: 0000000000000000
FS: 0000000000000000(0000) GS:ffff88bf44980000(0000) knlGS:0000000000000000
CR2: 0000000000000000 CR3: 000000404b230001 CR4: 0000000000770ef0
PKRU: 55555554
Call Trace:
<TASK>
? __warn+0xcf/0x1b0
? hrtimer_start_range_ns+0x289/0x2d0
? report_bug+0x120/0x1a0
? handle_bug+0x60/0x90
? exc_invalid_op+0x1a/0x50
? asm_exc_invalid_op+0x1a/0x20
? register_refined_jiffies+0xb0/0xb0
? hrtimer_start_range_ns+0x289/0x2d0
? hrtimer_start_range_ns+0x186/0x2d0
start_dl_timer+0xfc/0x150
enqueue_dl_entity+0x367/0x640
dl_server_start+0x53/0xa0
enqueue_task_fair+0x363/0x460
enqueue_task+0x3c/0x200
ttwu_do_activate+0x94/0x240
try_to_wake_up+0x315/0x600
complete+0x4b/0x80
? stop_two_cpus+0x2f0/0x2f0
cpu_stopper_thread+0xb1/0x120
? smpboot_unregister_percpu_thread+0xc0/0xc0
smpboot_thread_fn+0xf7/0x150
kthread+0x121/0x130
? kthread_blkcg+0x40/0x40
ret_from_fork+0x39/0x50
? kthread_blkcg+0x40/0x40
ret_from_fork_asm+0x11/0x20
</TASK>
It looks like completion that requires an hrtimer is being scheduled on a
CPU that is not yet completely online. There have been other issues with
hrtimer that have been fixed recently [1]. A possible fix would be to
defer the completion to be done by a CPU already online.
This bug might have been introduced in [2].
[1] https://lore.kernel.org/all/20240913214205.12359-2-frederic@xxxxxxxxxx/
[2] https://lore.kernel.org/all/169972295552.3135.1094880886431606890.tip-bot2@tip-bot2/
Reported-by: Vlad Poenaru <vlad.wing@xxxxxxxxx>
Signed-off-by: Usama Arif <usamaarif642@xxxxxxxxx>
---
kernel/sched/completion.c | 25 ++++++++++++++++++++++++-
1 file changed, 24 insertions(+), 1 deletion(-)
diff --git a/kernel/sched/completion.c b/kernel/sched/completion.c
index 3561ab533dd4..b79d0868f997 100644
--- a/kernel/sched/completion.c
+++ b/kernel/sched/completion.c
@@ -30,6 +30,13 @@ void complete_on_current_cpu(struct completion *x)
return complete_with_flags(x, WF_CURRENT_CPU);
}
+static void complete_ipi(void *arg)
+{
+ struct completion *x = arg;
+
+ complete_with_flags(x, 0);
+}
+
/**
* complete: - signals a single thread waiting on this completion
* @x: holds the state of this particular completion
@@ -44,7 +51,23 @@ void complete_on_current_cpu(struct completion *x)
*/
void complete(struct completion *x)
{
- complete_with_flags(x, 0);
+ int cpu = get_cpu();
+
+ /* The scheduler might queue an ignored hrtimer. Defer the wake up
+ * to an online CPU instead.
+ */
+ if (unlikely(cpu_is_offline(cpu))) {
+ int target;
+
+ target = cpumask_any_and(housekeeping_cpumask(HK_TYPE_RCU),
+ cpu_online_mask);
+
+ smp_call_function_single(target, complete_ipi, x, 1);
+ put_cpu();
+ } else {
+ put_cpu();
+ complete_with_flags(x, 0);
+ }
}
EXPORT_SYMBOL(complete);
--
2.43.5
