hrtimers: fix inconsistent lock state on resume in hres_timers_resume

Andrey Borzenkov reported this lockdep assert:

> [17854.688347] =================================
> [17854.688347] [ INFO: inconsistent lock state ]
> [17854.688347] 2.6.29-rc2-1avb #1
> [17854.688347] ---------------------------------
> [17854.688347] inconsistent {in-hardirq-W} -> {hardirq-on-W} usage.
> [17854.688347] pm-suspend/18240 [HC0[0]:SC0[0]:HE1:SE1] takes:
> [17854.688347]  (&cpu_base->lock){++..}, at: [<c0136fcc>] retrigger_next_event+0x5c/0xa0
> [17854.688347] {in-hardirq-W} state was registered at:
> [17854.688347]   [<c01443cd>] __lock_acquire+0x79d/0x1930
> [17854.688347]   [<c01455bc>] lock_acquire+0x5c/0x80
> [17854.688347]   [<c03092e5>] _spin_lock+0x35/0x70
> [17854.688347]   [<c0136e61>] hrtimer_run_queues+0x31/0x140
> [17854.688347]   [<c0128d98>] run_local_timers+0x8/0x20
> [17854.688347]   [<c0128dd3>] update_process_times+0x23/0x60
> [17854.688347]   [<c013e274>] tick_periodic+0x24/0x80
> [17854.688347]   [<c013e2e2>] tick_handle_periodic+0x12/0x70
> [17854.688347]   [<c0104e24>] timer_interrupt+0x14/0x20
> [17854.688347]   [<c01607b9>] handle_IRQ_event+0x29/0x60
> [17854.688347]   [<c0161c59>] handle_level_irq+0x69/0xe0
> [17854.688347]   [<ffffffff>] 0xffffffff
> [17854.688347] irq event stamp: 55771
> [17854.688347] hardirqs last  enabled at (55771): [<c0309125>] _spin_unlock_irqrestore+0x35/0x60
> [17854.688347] hardirqs last disabled at (55770): [<c0309419>] _spin_lock_irqsave+0x19/0x80
> [17854.688347] softirqs last  enabled at (54836): [<c0124f54>] __do_softirq+0xc4/0x110
> [17854.688347] softirqs last disabled at (54831): [<c01049ae>] do_softirq+0x8e/0xe0
> [17854.688347]
> [17854.688347] other info that might help us debug this:
> [17854.688347] 3 locks held by pm-suspend/18240:
> [17854.688347]  #0:  (&buffer->mutex){--..}, at: [<c01dd4c5>] sysfs_write_file+0x25/0x100
> [17854.688347]  #1:  (pm_mutex){--..}, at: [<c015056f>] enter_state+0x4f/0x140
> [17854.688347]  #2:  (dpm_list_mtx){--..}, at: [<c027880f>] device_pm_lock+0xf/0x20
> [17854.688347]
> [17854.688347] stack backtrace:
> [17854.688347] Pid: 18240, comm: pm-suspend Not tainted 2.6.29-rc2-1avb #1
> [17854.688347] Call Trace:
> [17854.688347]  [<c0306248>] ? printk+0x18/0x20
> [17854.688347]  [<c0141fac>] print_usage_bug+0x16c/0x1d0
> [17854.688347]  [<c0142bcf>] mark_lock+0x8bf/0xc90
> [17854.688347]  [<c0106b8f>] ? pit_next_event+0x2f/0x40
> [17854.688347]  [<c01441b0>] __lock_acquire+0x580/0x1930
> [17854.688347]  [<c030916d>] ? _spin_unlock+0x1d/0x20
> [17854.688347]  [<c0106b8f>] ? pit_next_event+0x2f/0x40
> [17854.688347]  [<c013dd38>] ? clockevents_program_event+0x98/0x160
> [17854.688347]  [<c0142fe8>] ? mark_held_locks+0x48/0x90
> [17854.688347]  [<c0309125>] ? _spin_unlock_irqrestore+0x35/0x60
> [17854.688347]  [<c0143229>] ? trace_hardirqs_on_caller+0x139/0x190
> [17854.688347]  [<c014328b>] ? trace_hardirqs_on+0xb/0x10
> [17854.688347]  [<c01455bc>] lock_acquire+0x5c/0x80
> [17854.688347]  [<c0136fcc>] ? retrigger_next_event+0x5c/0xa0
> [17854.688347]  [<c03092e5>] _spin_lock+0x35/0x70
> [17854.688347]  [<c0136fcc>] ? retrigger_next_event+0x5c/0xa0
> [17854.688347]  [<c0136fcc>] retrigger_next_event+0x5c/0xa0
> [17854.688347]  [<c013711a>] hres_timers_resume+0xa/0x10
> [17854.688347]  [<c013aa8e>] timekeeping_resume+0xee/0x150
> [17854.688347]  [<c0273384>] __sysdev_resume+0x14/0x50
> [17854.688347]  [<c0273407>] sysdev_resume+0x47/0x80
> [17854.688347]  [<c02791ab>] device_power_up+0xb/0x20
> [17854.688347]  [<c015043f>] suspend_devices_and_enter+0xcf/0x150
> [17854.688347]  [<c0150c2f>] ? freeze_processes+0x3f/0x90
> [17854.688347]  [<c0150614>] enter_state+0xf4/0x140
> [17854.688347]  [<c01506dd>] state_store+0x7d/0xc0
> [17854.688347]  [<c0150660>] ? state_store+0x0/0xc0
> [17854.688347]  [<c0202da4>] kobj_attr_store+0x24/0x30
> [17854.688347]  [<c01dd53c>] sysfs_write_file+0x9c/0x100
> [17854.688347]  [<c019916c>] vfs_write+0x9c/0x160
> [17854.688347]  [<c0103494>] ? restore_nocheck_notrace+0x0/0xe
> [17854.688347]  [<c01dd4a0>] ? sysfs_write_file+0x0/0x100
> [17854.688347]  [<c01992ed>] sys_write+0x3d/0x70
> [17854.688347]  [<c0103371>] sysenter_do_call+0x12/0x31

Andrey's analysis:

> timekeeping_resume() is called via class ->resume
> method; and according to comments in sysdev_resume() and
> device_power_up(), they are called with interrupts disabled.
>
> Looking at suspend_enter, irqs *are* disabled at this point.
>
> So it actually looks like something (may be some driver)
> unconditionally enabled irqs in resume path.

Add a debug check to test this theory. If it triggers then it
triggers because the resume code calls it with irqs enabled,
which is a no-no not just for timekeeping_resume(), but also
bad for a number of other resume handlers.

Reported-by: Andrey Borzenkov <arvidjaar@mail.ru>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 1455b76..cb83c6d 100644 (file)
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -614,7 +614,9 @@ void clock_was_set(void)
  */
 void hres_timers_resume(void)
 {
-       /* Retrigger the CPU local events: */
+       WARN_ONCE(!irqs_disabled(),
+                 KERN_INFO "hres_timers_resume() called with IRQs enabled!");
+
        retrigger_next_event(NULL);
 }