rcu: Add GP-kthread-starvation checks to CPU stall warnings

This commit adds a message that is printed if the relevant grace-period
kthread has not been able to run for the two seconds preceding the
stall warning.  (The two seconds is double the maximum interval between
successive bouts of quiescent-state forcing.)

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>

2 files changed, 29 insertions, 1 deletions

diff --git a/Documentation/RCU/stallwarn.txt b/Documentation/RCU/stallwarn.txt
index 55f9707fe60a..53e7d2856db6 100644
--- a/Documentation/RCU/stallwarn.txt
+++ b/Documentation/RCU/stallwarn.txt
@@ -152,6 +152,15 @@ no non-lazy callbacks ("." is printed otherwise, as shown above) and
 "D" indicates that dyntick-idle processing is enabled ("." is printed
 otherwise, for example, if disabled via the "nohz=" kernel boot parameter).
 
+If the relevant grace-period kthread has been unable to run prior to
+the stall warning, the following additional line is printed:
+
+        rcu_preempt kthread starved for 2023 jiffies!
+
+Starving the grace-period kthreads of CPU time can of course result in
+RCU CPU stall warnings even when all CPUs and tasks have passed through
+the required quiescent states.
+
 
 Multiple Warnings From One Stall
 
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index cb00e038c2f2..e335f33d0b9f 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -1073,6 +1073,21 @@ static void record_gp_stall_check_time(struct rcu_state *rsp)
 }
 
 /*
+ * Complain about starvation of grace-period kthread.
+ */
+static void rcu_check_gp_kthread_starvation(struct rcu_state *rsp)
+{
+        unsigned long gpa;
+        unsigned long j;
+
+        j = jiffies;
+        gpa = ACCESS_ONCE(rsp->gp_activity);
+        if (j - gpa > 2 * HZ)
+                pr_err("%s kthread starved for %ld jiffies!\n",
+                       rsp->name, j - gpa);
+}
+
+/*
  * Dump stacks of all tasks running on stalled CPUs.
  */
 static void rcu_dump_cpu_stacks(struct rcu_state *rsp)
@@ -1169,9 +1184,10 @@ static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum)
         }
 
         /* Complain about tasks blocking the grace period. */
-
         rcu_print_detail_task_stall(rsp);
 
+        rcu_check_gp_kthread_starvation(rsp);
+
         force_quiescent_state(rsp);  /* Kick them all. */
 }
 
@@ -1196,6 +1212,9 @@ static void print_cpu_stall(struct rcu_state *rsp)
         pr_cont(" (t=%lu jiffies g=%ld c=%ld q=%lu)\n",
                 jiffies - rsp->gp_start,
                 (long)rsp->gpnum, (long)rsp->completed, totqlen);
+
+        rcu_check_gp_kthread_starvation(rsp);
+
         rcu_dump_cpu_stacks(rsp);
 
         raw_spin_lock_irqsave(&rnp->lock, flags);