rcu: Kick CPU halfway to RCU CPU stall warning

When an RCU CPU stall warning occurs, the CPU invokes resched_cpu() on
itself.  This can help move the grace period forward in some situations,
but it would be even better to do this -before- the RCU CPU stall warning.
This commit therefore causes resched_cpu() to be called every five jiffies
once the system is halfway to an RCU CPU stall warning.

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

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index dd081987a8ec62349ad7721476cb97606077f28a..5243ebea0fc1eeabd9ca70cb7e0786541e5db2f3 100644 (file)
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -754,6 +754,12 @@ static int dyntick_save_progress_counter(struct rcu_data *rdp,
        return (rdp->dynticks_snap & 0x1) == 0;
 }
 
+/*
+ * This function really isn't for public consumption, but RCU is special in
+ * that context switches can allow the state machine to make progress.
+ */
+extern void resched_cpu(int cpu);
+
 /*
  * Return true if the specified CPU has passed through a quiescent
  * state by virtue of being in or having passed through an dynticks
@@ -812,16 +818,34 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp,
         */
        rcu_kick_nohz_cpu(rdp->cpu);
 
+       /*
+        * Alternatively, the CPU might be running in the kernel
+        * for an extended period of time without a quiescent state.
+        * Attempt to force the CPU through the scheduler to gain the
+        * needed quiescent state, but only if the grace period has gone
+        * on for an uncommonly long time.  If there are many stuck CPUs,
+        * we will beat on the first one until it gets unstuck, then move
+        * to the next.  Only do this for the primary flavor of RCU.
+        */
+       if (rdp->rsp == rcu_state &&
+           ULONG_CMP_GE(ACCESS_ONCE(jiffies), rdp->rsp->jiffies_resched)) {
+               rdp->rsp->jiffies_resched += 5;
+               resched_cpu(rdp->cpu);
+       }
+
        return 0;
 }
 
 static void record_gp_stall_check_time(struct rcu_state *rsp)
 {
        unsigned long j = ACCESS_ONCE(jiffies);
+       unsigned long j1;
 
        rsp->gp_start = j;
        smp_wmb(); /* Record start time before stall time. */
-       rsp->jiffies_stall = j + rcu_jiffies_till_stall_check();
+       j1 = rcu_jiffies_till_stall_check();
+       rsp->jiffies_stall = j + j1;
+       rsp->jiffies_resched = j + j1 / 2;
 }
 
 /*

diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 52be957c9fe22360a7a307842795c09353b42789..8e34d8674a4e6e438d4d2acaaf260ee507b83d5d 100644 (file)
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -453,6 +453,8 @@ struct rcu_state {
                                                /*  but in jiffies. */
        unsigned long jiffies_stall;            /* Time at which to check */
                                                /*  for CPU stalls. */
+       unsigned long jiffies_resched;          /* Time at which to resched */
+                                               /*  a reluctant CPU. */
        unsigned long gp_max;                   /* Maximum GP duration in */
                                                /*  jiffies. */
        const char *name;                       /* Name of structure. */