kernel: time: forward timer base before migrating timers
PATCH 1/1 kernel: time: forward timer base before migrating timers
In case when timers are migrated to a CPU, after it exits idle, but before timer base is forwarded, either from run_timer_softirq()/mod_timer()/add_timer_on(), it's possible that migrated timers are queued, based on older clock value. This can cause delays in handling those timers.
For example, consider below sequence of events:
- CPU0 timer1 expires = 59969 and base->clk = 59131. So, timer is queued at level 2, with next expiry for this timer = 60032 (due to granularity addition).
- CPU1 enters idle @60007, with next timer expiry @60020.
- CPU1 exits idle.
- CPU0 is hotplugged at 60009, and timers are migrated to CPU1, with new base->clk = 60007. timer1 is queued, based on 60007 at level 0, for immediate handling (in next timer softirq handling).
- CPU1's base->clk is forwarded to 60009, so, in next sched timer interrupt, timer1 is not handled.
The issue happens as timer wheel collects expired timers starting from the current clk's index onwards, but migrated timers, if enqueued, based on older clk value can result in their index being less than clk's current index. This can only happen if new base->clk is ahead of timer->expires, resulting in timer being queued at new base->clk's current index.
kernel/time/timer.c +5 -0
@@ -1886,6 +1886,11 @@ int timers_dead_cpu(unsigned int cpu)raw_spin_lock_irq (&new_base->lock);raw_spin_lock_nested (&old_base->lock,SINGLE_DEPTH_NESTING ); +/* Before migrating timers, update new base clk to avoid +* queueing timers based on older clock value. +*/ +forward_timer_base (new_base); +BUG_ON (old_base->running_timer);for (i =0 ; i <WHEEL_SIZE ; i++)
Signature · 2 lines
QUALCOMM INDIA, on behalf of Qualcomm Innovation Center, Inc. is a member of Code Aurora Forum, a Linux Foundation Collaborative Project.
Quoted 28 lines · Lingutla Chandrasekhar
In case when timers are migrated to a CPU, after it exits idle, but before timer base is forwarded, either from run_timer_softirq()/mod_timer()/add_timer_on(), it's possible that migrated timers are queued, based on older clock value. This can cause delays in handling those timers.
For example, consider below sequence of events:
- CPU0 timer1 expires = 59969 and
base->clk= 59131. So, timer is queued at level 2, with next expiry for this timer = 60032 (due to granularity addition).
- CPU1 enters idle @60007, with next timer expiry @60020.
- CPU1 exits idle.
- CPU0 is hotplugged at 60009, and timers are migrated to CPU1, with newbase->clk= 60007. timer1 is queued, based on 60007 at level 0, for immediate handling (in next timer softirq handling).
- CPU1'sbase->clkis forwarded to 60009, so, in next sched timer interrupt, timer1 is not handled.The issue happens as timer wheel collects expired timers starting from the current clk's index onwards, but migrated timers, if enqueued, based on older clk value can result in their index being less than clk's current index. This can only happen if new
base->clkis ahead oftimer->expires, resulting in timer being queued at new base->clk's current index.
Quoted 1 line
Change-Id: Idbe737b346f00e6e7241b93181bbbd80871f1400
I asked that a gazillion of times now.
Please do not include your internal change id tags. They are completely useless for anybody else. Can you please make sure that anyone inside codeaurora knows?
Quoted 2 lines
Signed-off-by Neeraj Upadhyay <[email protected]>Signed-off-by Lingutla Chandrasekhar <[email protected]>
This SOB chain is wrong ....
kernel/time/timer.c int timers_dead_cpu(unsigned int cpu) · line 1891
Quoted 12 lines
kernel/time/timer.c +3
-0@@ -1886,6 +1886,11 @@ int timers_dead_cpu(unsigned int cpu)raw_spin_lock_irq (&new_base->lock);raw_spin_lock_nested (&old_base->lock,SINGLE_DEPTH_NESTING ); +/* Before migrating timers, update new base clk to avoid +* queueing timers based on older clock value. +*/
Multiline comments are
/* * First line * Second line */
Please do not use that retarded comment style above.
Thanks,
tglx
Quoted 1 line · Thomas Gleixner
On Wed, 17 Jan 2018, Lingutla Chandrasekhar wrote:
And please fix the subject line:
kernel: time:
is not the proper subsystem prefix.
git log should give you a hint.
Aside of that the text after the prefix starts with an uppercase letter.
Thanks,
tglx
Hi,
Sorry for the basic mistakes, posted new patch V1.
Quoted 15 lines · Thomas Gleixner
Quoted 1 line · Thomas Gleixner
On Wed, 17 Jan 2018, Lingutla Chandrasekhar wrote:
And please fix the subject line:
kernel: time:
is not the proper subsystem prefix.
git log should give you a hint.
Aside of that the text after the prefix starts with an uppercase letter.
Thanks,
tglx