From: Paul E. McKenney <paulmck@kernel.org>
Date: Mon, 3 Feb 2020 22:20:00 +0000 (-0800)
Subject: rcu: Optimize and protect atomic_cmpxchg() loop
X-Git-Url: http://git.maquefel.me/?a=commitdiff_plain;h=faa059c397dec8a452c79e9dba64419113ea64e2;p=linux.git

rcu: Optimize and protect atomic_cmpxchg() loop

This commit reworks the atomic_cmpxchg() loop in rcu_eqs_special_set()
to do only the initial read from the current CPU's rcu_data structure's
->dynticks field explicitly.  On subsequent passes, this value is instead
retained from the failing atomic_cmpxchg() operation.

Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
---

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 4a4a975503e52..6c624814ee2de 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -342,14 +342,17 @@ bool rcu_eqs_special_set(int cpu)
 {
 	int old;
 	int new;
+	int new_old;
 	struct rcu_data *rdp = &per_cpu(rcu_data, cpu);
 
+	new_old = atomic_read(&rdp->dynticks);
 	do {
-		old = atomic_read(&rdp->dynticks);
+		old = new_old;
 		if (old & RCU_DYNTICK_CTRL_CTR)
 			return false;
 		new = old | RCU_DYNTICK_CTRL_MASK;
-	} while (atomic_cmpxchg(&rdp->dynticks, old, new) != old);
+		new_old = atomic_cmpxchg(&rdp->dynticks, old, new);
+	} while (new_old != old);
 	return true;
 }