So this set happens to have more changes than expected because I
found out that the timer list full nohz kick also relies on the scheduler
IPI. So I had to convert it as well, hence a few more change splitups.
Changes:
* Check also raised lists from irq_work_needs_cpu() (thanks Peterz)
* Comment on SMP functions priority in
generic_smp_call_function_single_interrupt() because IPI callbacks there
are often synchronous as opposed to irq works. (thanks Peterz)
* s/native_send_call_func_single_ipi/native_send_call_func_single_ipi
(thanks Eric Dumazet)
* Only build irq_work_queue_on() on CONFIG_SMP, fixes some broken builds
* Convert full nohz timer list kick
git://git.kernel.org/pub/scm/linux/kernel/git/frederic/linux-dynticks.git
timers/nohz-irq-work-v6
Thanks,
Frederic
---
Frederic Weisbecker (6):
irq_work: Split raised and lazy lists
irq_work: Implement remote queueing
nohz: Support nohz full remote kick
nohz: Switch to nohz full remote kick on timer enqueue
nohz: Use nohz own full kick on 2nd task enqueue
nohz: Use IPI implicit full barrier against rq->nr_running r/w
include/linux/irq_work.h | 5 ++++
include/linux/tick.h | 9 +++++-
kernel/irq_work.c | 76 ++++++++++++++++++++++++++++++------------------
kernel/sched/core.c | 22 ++++++++------
kernel/sched/sched.h | 12 ++++++--
kernel/smp.c | 9 ++++++
kernel/time/tick-sched.c | 10 ++++---
7 files changed, 97 insertions(+), 46 deletions(-)
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
