Patchwork [v3,13/45] sched/fair: Use get/put_online_cpus_atomic() to prevent CPU offline

login
register
mail settings
Submitter Srivatsa S. Bhat
Date June 27, 2013, 7:54 p.m.
Message ID <20130627195439.29830.96122.stgit@srivatsabhat.in.ibm.com>
Download mbox | patch
Permalink /patch/255182/
State Not Applicable
Delegated to: David Miller
Headers show

Comments

Srivatsa S. Bhat - June 27, 2013, 7:54 p.m.
Once stop_machine() is gone from the CPU offline path, we won't be able
to depend on disabling preemption to prevent CPUs from going offline
from under us.

Use the get/put_online_cpus_atomic() APIs to prevent CPUs from going
offline, while invoking from atomic context.

Cc: Ingo Molnar <mingo@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
---

 kernel/sched/fair.c |   14 +++++++++++++-
 1 file changed, 13 insertions(+), 1 deletion(-)


--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Patch

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index f77f9c5..62d98dd 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3369,7 +3369,8 @@  done:
  *
  * Returns the target CPU number, or the same CPU if no balancing is needed.
  *
- * preempt must be disabled.
+ * Must be called within get/put_online_cpus_atomic(), to prevent CPUs
+ * from going offline from under us.
  */
 static int
 select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flags)
@@ -5289,6 +5290,8 @@  void idle_balance(int this_cpu, struct rq *this_rq)
 	raw_spin_unlock(&this_rq->lock);
 
 	update_blocked_averages(this_cpu);
+
+	get_online_cpus_atomic();
 	rcu_read_lock();
 	for_each_domain(this_cpu, sd) {
 		unsigned long interval;
@@ -5312,6 +5315,7 @@  void idle_balance(int this_cpu, struct rq *this_rq)
 		}
 	}
 	rcu_read_unlock();
+	put_online_cpus_atomic();
 
 	raw_spin_lock(&this_rq->lock);
 
@@ -5338,6 +5342,7 @@  static int active_load_balance_cpu_stop(void *data)
 	struct rq *target_rq = cpu_rq(target_cpu);
 	struct sched_domain *sd;
 
+	get_online_cpus_atomic();
 	raw_spin_lock_irq(&busiest_rq->lock);
 
 	/* make sure the requested cpu hasn't gone down in the meantime */
@@ -5389,6 +5394,7 @@  static int active_load_balance_cpu_stop(void *data)
 out_unlock:
 	busiest_rq->active_balance = 0;
 	raw_spin_unlock_irq(&busiest_rq->lock);
+	put_online_cpus_atomic();
 	return 0;
 }
 
@@ -5549,6 +5555,7 @@  static void rebalance_domains(int cpu, enum cpu_idle_type idle)
 
 	update_blocked_averages(cpu);
 
+	get_online_cpus_atomic();
 	rcu_read_lock();
 	for_each_domain(cpu, sd) {
 		if (!(sd->flags & SD_LOAD_BALANCE))
@@ -5597,6 +5604,7 @@  out:
 			break;
 	}
 	rcu_read_unlock();
+	put_online_cpus_atomic();
 
 	/*
 	 * next_balance will be updated only when there is a need.
@@ -5728,6 +5736,7 @@  static void run_rebalance_domains(struct softirq_action *h)
 	enum cpu_idle_type idle = this_rq->idle_balance ?
 						CPU_IDLE : CPU_NOT_IDLE;
 
+	get_online_cpus_atomic();
 	rebalance_domains(this_cpu, idle);
 
 	/*
@@ -5736,6 +5745,7 @@  static void run_rebalance_domains(struct softirq_action *h)
 	 * stopped.
 	 */
 	nohz_idle_balance(this_cpu, idle);
+	put_online_cpus_atomic();
 }
 
 static inline int on_null_domain(int cpu)
@@ -5753,8 +5763,10 @@  void trigger_load_balance(struct rq *rq, int cpu)
 	    likely(!on_null_domain(cpu)))
 		raise_softirq(SCHED_SOFTIRQ);
 #ifdef CONFIG_NO_HZ_COMMON
+	get_online_cpus_atomic();
 	if (nohz_kick_needed(rq, cpu) && likely(!on_null_domain(cpu)))
 		nohz_balancer_kick(cpu);
+	put_online_cpus_atomic();
 #endif
 }