rcu: Awaken grace-period kthread if too long since FQS
Recent kernels can fail to awaken the grace-period kthread for
quiescent-state forcing. This commit is a crude hack that does
a wakeup if a scheduling-clock interrupt sees that it has been
too long since force-quiescent-state (FQS) processing.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 6116cfa..a739292 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -385,9 +385,11 @@
static ulong jiffies_till_first_fqs = ULONG_MAX;
static ulong jiffies_till_next_fqs = ULONG_MAX;
+static bool rcu_kick_kthreads;
module_param(jiffies_till_first_fqs, ulong, 0644);
module_param(jiffies_till_next_fqs, ulong, 0644);
+module_param(rcu_kick_kthreads, bool, 0644);
/*
* How long the grace period must be before we start recruiting
@@ -1251,6 +1253,24 @@
}
}
+/*
+ * If too much time has passed in the current grace period, and if
+ * so configured, go kick the relevant kthreads.
+ */
+static void rcu_stall_kick_kthreads(struct rcu_state *rsp)
+{
+ unsigned long j;
+
+ if (!rcu_kick_kthreads)
+ return;
+ j = READ_ONCE(rsp->jiffies_kick_kthreads);
+ if (time_after(jiffies, j) && rsp->gp_kthread) {
+ WARN_ONCE(1, "Kicking %s grace-period kthread\n", rsp->name);
+ wake_up_process(rsp->gp_kthread);
+ WRITE_ONCE(rsp->jiffies_kick_kthreads, j + HZ);
+ }
+}
+
static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum)
{
int cpu;
@@ -1262,6 +1282,11 @@
struct rcu_node *rnp = rcu_get_root(rsp);
long totqlen = 0;
+ /* Kick and suppress, if so configured. */
+ rcu_stall_kick_kthreads(rsp);
+ if (rcu_cpu_stall_suppress)
+ return;
+
/* Only let one CPU complain about others per time interval. */
raw_spin_lock_irqsave_rcu_node(rnp, flags);
@@ -1335,6 +1360,11 @@
struct rcu_node *rnp = rcu_get_root(rsp);
long totqlen = 0;
+ /* Kick and suppress, if so configured. */
+ rcu_stall_kick_kthreads(rsp);
+ if (rcu_cpu_stall_suppress)
+ return;
+
/*
* OK, time to rat on ourselves...
* See Documentation/RCU/stallwarn.txt for info on how to debug
@@ -1379,8 +1409,10 @@
unsigned long js;
struct rcu_node *rnp;
- if (rcu_cpu_stall_suppress || !rcu_gp_in_progress(rsp))
+ if ((rcu_cpu_stall_suppress && !rcu_kick_kthreads) ||
+ !rcu_gp_in_progress(rsp))
return;
+ rcu_stall_kick_kthreads(rsp);
j = jiffies;
/*
@@ -2119,8 +2151,11 @@
}
ret = 0;
for (;;) {
- if (!ret)
+ if (!ret) {
rsp->jiffies_force_qs = jiffies + j;
+ WRITE_ONCE(rsp->jiffies_kick_kthreads,
+ jiffies + 3 * j);
+ }
trace_rcu_grace_period(rsp->name,
READ_ONCE(rsp->gpnum),
TPS("fqswait"));