mirror of
https://gitee.com/bianbu-linux/linux-6.6
synced 2025-07-24 01:54:03 -04:00
2679a83731
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
|
||
|---|---|---|
| .. | ||
| bpf | ||
| cgroup | ||
| configs | ||
| debug | ||
| dma | ||
| entry | ||
| events | ||
| futex | ||
| gcov | ||
| irq | ||
| kcsan | ||
| livepatch | ||
| locking | ||
| power | ||
| printk | ||
| rcu | ||
| sched | ||
| time | ||
| trace | ||
| .gitignore | ||
| acct.c | ||
| async.c | ||
| audit.c | ||
| audit.h | ||
| audit_fsnotify.c | ||
| audit_tree.c | ||
| audit_watch.c | ||
| auditfilter.c | ||
| auditsc.c | ||
| backtracetest.c | ||
| bounds.c | ||
| capability.c | ||
| cfi.c | ||
| compat.c | ||
| configs.c | ||
| context_tracking.c | ||
| cpu.c | ||
| cpu_pm.c | ||
| crash_core.c | ||
| crash_dump.c | ||
| cred.c | ||
| delayacct.c | ||
| dma.c | ||
| exec_domain.c | ||
| exit.c | ||
| extable.c | ||
| fail_function.c | ||
| fork.c | ||
| freezer.c | ||
| gen_kheaders.sh | ||
| groups.c | ||
| hung_task.c | ||
| iomem.c | ||
| irq_work.c | ||
| jump_label.c | ||
| kallsyms.c | ||
| kcmp.c | ||
| Kconfig.freezer | ||
| Kconfig.hz | ||
| Kconfig.locks | ||
| Kconfig.preempt | ||
| kcov.c | ||
| kexec.c | ||
| kexec_core.c | ||
| kexec_elf.c | ||
| kexec_file.c | ||
| kexec_internal.h | ||
| kheaders.c | ||
| kmod.c | ||
| kprobes.c | ||
| ksysfs.c | ||
| kthread.c | ||
| latencytop.c | ||
| Makefile | ||
| module-internal.h | ||
| module.c | ||
| module_decompress.c | ||
| module_signature.c | ||
| module_signing.c | ||
| notifier.c | ||
| nsproxy.c | ||
| padata.c | ||
| panic.c | ||
| params.c | ||
| pid.c | ||
| pid_namespace.c | ||
| profile.c | ||
| ptrace.c | ||
| range.c | ||
| reboot.c | ||
| regset.c | ||
| relay.c | ||
| resource.c | ||
| resource_kunit.c | ||
| rseq.c | ||
| scftorture.c | ||
| scs.c | ||
| seccomp.c | ||
| signal.c | ||
| smp.c | ||
| smpboot.c | ||
| smpboot.h | ||
| softirq.c | ||
| stackleak.c | ||
| stacktrace.c | ||
| static_call.c | ||
| static_call_inline.c | ||
| stop_machine.c | ||
| sys.c | ||
| sys_ni.c | ||
| sysctl-test.c | ||
| sysctl.c | ||
| task_work.c | ||
| taskstats.c | ||
| torture.c | ||
| tracepoint.c | ||
| tsacct.c | ||
| ucount.c | ||
| uid16.c | ||
| uid16.h | ||
| umh.c | ||
| up.c | ||
| user-return-notifier.c | ||
| user.c | ||
| user_namespace.c | ||
| usermode_driver.c | ||
| utsname.c | ||
| utsname_sysctl.c | ||
| watch_queue.c | ||
| watchdog.c | ||
| watchdog_hld.c | ||
| workqueue.c | ||
| workqueue_internal.h | ||