rcu: Unconditionally expedite during suspend/hibernate
authorPaul E. McKenney <paulmck@linux.ibm.com>
Thu, 10 Jan 2019 23:30:15 +0000 (15:30 -0800)
committerPaul E. McKenney <paulmck@linux.ibm.com>
Tue, 26 Mar 2019 21:37:49 +0000 (14:37 -0700)
commite85e6a21b2b5f31148cc3f2e785262b37c3e1ec7
tree4d7121edf1592ee510ffcaff3914ebb731f593e6
parent9e98c678c2d6ae3a17cb2de55d17f69dddaa231b
rcu: Unconditionally expedite during suspend/hibernate

The rcu_pm_notify() function refuses to switch to/from expedited grace
periods on systems with more than 256 CPUs due to the serialized
initialization of expedited grace periods.  However, expedited grace
periods are now initialized in parallel, removing this concern.
This commit therefore removes the checks from rcu_pm_notify(), so that
expedited grace periods are used unconditionally during suspend/resume
and hibernate/wake operations.

As always, real-time workloads wishing to completely avoid expedited
grace periods can use the rcupdate.rcu_normal= kernel parameter.

Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
kernel/rcu/tree.c