rcu/nocb: Optimize kthreads and rdp initialization

Currently cpumask_available() is used to prevent from unwanted NOCB
initialization.  However if neither "rcu_nocbs=" nor "nohz_full="
parameters are passed to a kernel built with CONFIG_CPUMASK_OFFSTACK=n,
the initialization path is still taken, running through all sorts of
needless operations and iterations on an empty cpumask.

Fix this by relying on a real initialization state instead.  This also
optimizes kthread creation, preventing needless iteration over all online
CPUs when the kernel is booted without any offloaded CPUs.

Reviewed-by: Neeraj Upadhyay <quic_neeraju@quicinc.com>
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Uladzislau Rezki <urezki@gmail.com>
Cc: Josh Triplett <josh@joshtriplett.org>
Cc: Joel Fernandes <joel@joelfernandes.org>
Tested-by: Juri Lelli <juri.lelli@redhat.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>

diff --git a/kernel/rcu/tree_nocb.h b/kernel/rcu/tree_nocb.h
index cd596cf4ee79a846e63091cce2404dcf3b948c4a..42092de677054f8b9bfe92d885d73624078f5fba 100644 (file)
--- a/kernel/rcu/tree_nocb.h
+++ b/kernel/rcu/tree_nocb.h
@@ -60,6 +60,9 @@ static inline bool rcu_current_is_nocb_kthread(struct rcu_data *rdp)
  * Parse the boot-time rcu_nocb_mask CPU list from the kernel parameters.
  * If the list is invalid, a warning is emitted and all CPUs are offloaded.
  */
+
+static bool rcu_nocb_is_setup;
+
 static int __init rcu_nocb_setup(char *str)
 {
        alloc_bootmem_cpumask_var(&rcu_nocb_mask);
@@ -67,6 +70,7 @@ static int __init rcu_nocb_setup(char *str)
                pr_warn("rcu_nocbs= bad CPU range, all CPUs set\n");
                cpumask_setall(rcu_nocb_mask);
        }
+       rcu_nocb_is_setup = true;
        return 1;
 }
 __setup("rcu_nocbs=", rcu_nocb_setup);
@@ -1167,13 +1171,17 @@ void __init rcu_init_nohz(void)
                need_rcu_nocb_mask = true;
 #endif /* #if defined(CONFIG_NO_HZ_FULL) */
 
-       if (!cpumask_available(rcu_nocb_mask) && need_rcu_nocb_mask) {
-               if (!zalloc_cpumask_var(&rcu_nocb_mask, GFP_KERNEL)) {
-                       pr_info("rcu_nocb_mask allocation failed, callback offloading disabled.\n");
-                       return;
+       if (need_rcu_nocb_mask) {
+               if (!cpumask_available(rcu_nocb_mask)) {
+                       if (!zalloc_cpumask_var(&rcu_nocb_mask, GFP_KERNEL)) {
+                               pr_info("rcu_nocb_mask allocation failed, callback offloading disabled.\n");
+                               return;
+                       }
                }
+               rcu_nocb_is_setup = true;
        }
-       if (!cpumask_available(rcu_nocb_mask))
+
+       if (!rcu_nocb_is_setup)
                return;
 
 #if defined(CONFIG_NO_HZ_FULL)
@@ -1275,8 +1283,10 @@ static void __init rcu_spawn_nocb_kthreads(void)
 {
        int cpu;
 
-       for_each_online_cpu(cpu)
-               rcu_spawn_cpu_nocb_kthread(cpu);
+       if (rcu_nocb_is_setup) {
+               for_each_online_cpu(cpu)
+                       rcu_spawn_cpu_nocb_kthread(cpu);
+       }
 }
 
 /* How many CB CPU IDs per GP kthread?  Default of -1 for sqrt(nr_cpu_ids). */