Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
From:   "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
To:     linux-kernel@vger.kernel.org
Cc:     mingo@kernel.org, jiangshanlai@gmail.com, dipankar@in.ibm.com,
        akpm@linux-foundation.org, mathieu.desnoyers@efficios.com,
        josh@joshtriplett.org, tglx@linutronix.de, peterz@infradead.org,
        rostedt@goodmis.org, dhowells@redhat.com, edumazet@google.com,
        fweisbec@gmail.com, oleg@redhat.com, joel@joelfernandes.org,
        "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Subject: [PATCH tip/core/rcu 15/27] rcu: Use RCU CPU stall timeout for rcu_check_gp_start_stall()
Date:   Mon, 25 Jun 2018 17:35:01 -0700
In-Reply-To: <20180626003448.GA26209@linux.vnet.ibm.com>
References: <20180626003448.GA26209@linux.vnet.ibm.com>
Message-Id: <20180626003513.27812-15-paulmck@linux.vnet.ibm.com>
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

Currently, rcu_check_gp_start_stall() waits for one second after the first
request before complaining that a grace period has not yet started.  This
was desirable while testing the conversion from ->future_gp_needed[] to
->gp_seq_needed, but it is a bit on the hair-trigger side for production
use under heavy load.  This commit therefore makes this wait time be
exactly that of the RCU CPU stall warning, allowing easy adjustment of
both timeouts to suit the distribution or installation at hand.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/tree.c | 17 +++++++++--------
 1 file changed, 9 insertions(+), 8 deletions(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index a95d49730cfc..c5fec335bc31 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -2753,6 +2753,7 @@ static void
 rcu_check_gp_start_stall(struct rcu_state *rsp, struct rcu_node *rnp,
 			 struct rcu_data *rdp)
 {
+	const unsigned long gpssdelay = rcu_jiffies_till_stall_check() * HZ;
 	unsigned long flags;
 	unsigned long j;
 	struct rcu_node *rnp_root = rcu_get_root(rsp);
@@ -2762,8 +2763,8 @@ rcu_check_gp_start_stall(struct rcu_state *rsp, struct rcu_node *rnp,
 	    ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed))
 		return;
 	j = jiffies; /* Expensive access, and in common case don't get here. */
-	if (time_before(j, READ_ONCE(rsp->gp_req_activity) + HZ) ||
-	    time_before(j, READ_ONCE(rsp->gp_activity) + HZ) ||
+	if (time_before(j, READ_ONCE(rsp->gp_req_activity) + gpssdelay) ||
+	    time_before(j, READ_ONCE(rsp->gp_activity) + gpssdelay) ||
 	    atomic_read(&warned))
 		return;
 
@@ -2771,8 +2772,8 @@ rcu_check_gp_start_stall(struct rcu_state *rsp, struct rcu_node *rnp,
 	j = jiffies;
 	if (rcu_gp_in_progress(rsp) ||
 	    ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed) ||
-	    time_before(j, READ_ONCE(rsp->gp_req_activity) + HZ) ||
-	    time_before(j, READ_ONCE(rsp->gp_activity) + HZ) ||
+	    time_before(j, READ_ONCE(rsp->gp_req_activity) + gpssdelay) ||
+	    time_before(j, READ_ONCE(rsp->gp_activity) + gpssdelay) ||
 	    atomic_read(&warned)) {
 		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 		return;
@@ -2783,18 +2784,18 @@ rcu_check_gp_start_stall(struct rcu_state *rsp, struct rcu_node *rnp,
 	j = jiffies;
 	if (rcu_gp_in_progress(rsp) ||
 	    ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed) ||
-	    time_before(j, rsp->gp_req_activity + HZ) ||
-	    time_before(j, rsp->gp_activity + HZ) ||
+	    time_before(j, rsp->gp_req_activity + gpssdelay) ||
+	    time_before(j, rsp->gp_activity + gpssdelay) ||
 	    atomic_xchg(&warned, 1)) {
 		raw_spin_unlock_rcu_node(rnp_root); /* irqs remain disabled. */
 		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 		return;
 	}
-	pr_alert("%s: g%ld->%ld gar:%lu ga:%lu f%#x %s->state:%#lx\n",
+	pr_alert("%s: g%ld->%ld gar:%lu ga:%lu f%#x gs:%d %s->state:%#lx\n",
 		 __func__, (long)READ_ONCE(rsp->gp_seq),
 		 (long)READ_ONCE(rnp_root->gp_seq_needed),
 		 j - rsp->gp_req_activity, j - rsp->gp_activity,
-		 rsp->gp_flags, rsp->name,
+		 rsp->gp_flags, rsp->gp_state, rsp->name,
 		 rsp->gp_kthread ? rsp->gp_kthread->state : 0x1ffffL);
 	WARN_ON(1);
 	raw_spin_unlock_rcu_node(rnp_root);
-- 
2.17.1