[PATCH 0/4] rcu: Fix PF_IDLE related issues, part. 1

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



The modification of PF_IDLE semantics lately to fix a bug in rcutiny
eventually introduced new bugs in RCU-tasks. This series revert that
PF_IDLE modification and fix rcutiny in an alternate way.

More issues need to be fixed in RCU-tasks:

* The boot code preceding the idle entry is included in this
  quiescent state. Especially after the completion of kthreadd_done
  after which init/1 can launch userspace concurrently. The window
  is tiny before PF_IDLE is set but it exists.

* Similarly, the boot code preceding the idle entry on secondary
  CPUs is wrongly accounted as RCU tasks quiescent state.

And those will be fixed separetely.

Frederic Weisbecker (4):
  softirq: Rename __raise_softirq_irqoff() to raise_softirq_no_wake()
  softirq: Introduce raise_ksoftirqd_irqoff()
  rcu: Make tiny RCU use ksoftirqd to trigger a QS from idle
  Revert "kernel/sched: Modify initial boot task idle setup"

 block/blk-mq.c            |  2 +-
 include/linux/interrupt.h |  3 ++-
 kernel/rcu/tiny.c         | 21 +++++++++++++-----
 kernel/sched/core.c       |  2 +-
 kernel/sched/idle.c       |  1 -
 kernel/softirq.c          | 45 +++++++++++++++++++++++++--------------
 lib/irq_poll.c            |  4 ++--
 net/core/dev.c            |  8 +++----
 8 files changed, 55 insertions(+), 31 deletions(-)

-- 
2.34.1




[Index of Archives]     [Linux Samsung SoC]     [Linux Rockchip SoC]     [Linux Actions SoC]     [Linux for Synopsys ARC Processors]     [Linux NFS]     [Linux NILFS]     [Linux USB Devel]     [Video for Linux]     [Linux Audio Users]     [Yosemite News]     [Linux Kernel]     [Linux SCSI]


  Powered by Linux