summaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
authorPaul E. McKenney <paulmck@linux.ibm.com>2019-03-27 09:09:47 -0700
committerPaul E. McKenney <paulmck@linux.ibm.com>2019-05-25 14:50:50 -0700
commitb9ad4d6ed18e23b0ff6a824b925a1278625d5345 (patch)
tree703d2ad10374344c97bef5c02776b8fb2de9754a /kernel
parent43e903ad3e0843d03da15d8eaffb5ada22966c76 (diff)
downloadlinux-stable-b9ad4d6ed18e23b0ff6a824b925a1278625d5345.tar.gz
linux-stable-b9ad4d6ed18e23b0ff6a824b925a1278625d5345.tar.bz2
linux-stable-b9ad4d6ed18e23b0ff6a824b925a1278625d5345.zip
rcu: Avoid self-IPI in sync_rcu_exp_select_node_cpus()
Although sync_rcu_exp_select_node_cpus() treats the current CPU as being in a quiescent state, it might well migrate to some other CPU before reaching the smp_call_function_single(), which could then result in an unnecessary simulated self-IPI. This commit therefore instead simply refuses to invoke smp_call_function_single() on the current CPU, which causes the later rcu_report_exp_cpu_mult() to report this CPU's quiescent state with less overhead. This also reduces the rcu_exp_handler() function's state space by removing the direct call that this smp_call_function_single() uses to emulate the requested self-IPI. Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com> [ paulmck: Use get_cpu() instead of preempt_disable() per Joel Fernandes. ]
Diffstat (limited to 'kernel')
-rw-r--r--kernel/rcu/tree_exp.h5
1 files changed, 5 insertions, 0 deletions
diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h
index 9c990df880d1..5390618787b6 100644
--- a/kernel/rcu/tree_exp.h
+++ b/kernel/rcu/tree_exp.h
@@ -384,7 +384,12 @@ retry_ipi:
mask_ofl_test |= mask;
continue;
}
+ if (get_cpu() == cpu) {
+ put_cpu();
+ continue;
+ }
ret = smp_call_function_single(cpu, rcu_exp_handler, NULL, 0);
+ put_cpu();
if (!ret) {
mask_ofl_ipi &= ~mask;
continue;