rcu: rcu_barrier VS cpu_hotplug: Ensure callbacks in dead cpu are migrated to online cpu
cpu hotplug may happen asynchronously, some rcu callbacks are maybe
still on dead cpu, rcu_barrier() also needs to wait for these rcu
callbacks to complete, so we must ensure callbacks in dead cpu are
migrated to online cpu.
Paul E. McKenney's review:
Good stuff, Lai!!! Simpler than any of the approaches that I was
considering, and, better yet, independent of the underlying RCU
implementation!!!
I was initially worried that wake_up() might wake only one of two
possible wait_event()s, namely rcu_barrier() and the CPU_POST_DEAD code,
but the fact that wait_event() clears WQ_FLAG_EXCLUSIVE avoids that issue.
I was also worried about the fact that different RCU implementations have
different mappings of call_rcu(), call_rcu_bh(), and call_rcu_sched(), but
this is OK as well because we just get an extra (harmless) callback in the
case that they map together (for example, Classic RCU has call_rcu_sched()
mapping to call_rcu()).
Overlap of CPU-hotplug operations is prevented by cpu_add_remove_lock,
and any stray callbacks that arrive (for example, from irq handlers
running on the dying CPU) either are ahead of the CPU_DYING callbacks on
the one hand (and thus accounted for), or happened after the rcu_barrier()
started on the other (and thus don't need to be accounted for).
Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Reviewed-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
LKML-Reference: <49C36476.1010400@cn.fujitsu.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c
index cae8a05..2c7b845 100644
--- a/kernel/rcupdate.c
+++ b/kernel/rcupdate.c
@@ -122,6 +122,8 @@
}
}
+static inline void wait_migrated_callbacks(void);
+
/*
* Orchestrate the specified type of RCU barrier, waiting for all
* RCU callbacks of the specified type to complete.
@@ -147,6 +149,7 @@
complete(&rcu_barrier_completion);
wait_for_completion(&rcu_barrier_completion);
mutex_unlock(&rcu_barrier_mutex);
+ wait_migrated_callbacks();
}
/**
@@ -176,9 +179,50 @@
}
EXPORT_SYMBOL_GPL(rcu_barrier_sched);
+static atomic_t rcu_migrate_type_count = ATOMIC_INIT(0);
+static struct rcu_head rcu_migrate_head[3];
+static DECLARE_WAIT_QUEUE_HEAD(rcu_migrate_wq);
+
+static void rcu_migrate_callback(struct rcu_head *notused)
+{
+ if (atomic_dec_and_test(&rcu_migrate_type_count))
+ wake_up(&rcu_migrate_wq);
+}
+
+static inline void wait_migrated_callbacks(void)
+{
+ wait_event(rcu_migrate_wq, !atomic_read(&rcu_migrate_type_count));
+}
+
+static int __cpuinit rcu_barrier_cpu_hotplug(struct notifier_block *self,
+ unsigned long action, void *hcpu)
+{
+ if (action == CPU_DYING) {
+ /*
+ * preempt_disable() in on_each_cpu() prevents stop_machine(),
+ * so when "on_each_cpu(rcu_barrier_func, (void *)type, 1);"
+ * returns, all online cpus have queued rcu_barrier_func(),
+ * and the dead cpu(if it exist) queues rcu_migrate_callback()s.
+ *
+ * These callbacks ensure _rcu_barrier() waits for all
+ * RCU callbacks of the specified type to complete.
+ */
+ atomic_set(&rcu_migrate_type_count, 3);
+ call_rcu_bh(rcu_migrate_head, rcu_migrate_callback);
+ call_rcu_sched(rcu_migrate_head + 1, rcu_migrate_callback);
+ call_rcu(rcu_migrate_head + 2, rcu_migrate_callback);
+ } else if (action == CPU_POST_DEAD) {
+ /* rcu_migrate_head is protected by cpu_add_remove_lock */
+ wait_migrated_callbacks();
+ }
+
+ return NOTIFY_OK;
+}
+
void __init rcu_init(void)
{
__rcu_init();
+ hotcpu_notifier(rcu_barrier_cpu_hotplug, 0);
}
void rcu_scheduler_starting(void)