rcu: Distinguish "rcuo" kthreads by RCU flavor

Currently, the per-no-CBs-CPU kthreads are named "rcuo" followed by
the CPU number, for example, "rcuo".  This is problematic given that
there are either two or three RCU flavors, each of which gets a per-CPU
kthread with exactly the same name.  This commit therefore introduces
a one-letter abbreviation for each RCU flavor, namely 'b' for RCU-bh,
'p' for RCU-preempt, and 's' for RCU-sched.  This abbreviation is used
to distinguish the "rcuo" kthreads, for example, for CPU 0 we would have
"rcuob/0", "rcuop/0", and "rcuos/0".

Signed-off-by: Paul E. McKenney <paul.mckenney@linaro.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Tested-by: Dietmar Eggemann <dietmar.eggemann@arm.com>

Documentation/kernel-parameters.txt

@@ -2461,9 +2461,12 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			In kernels built with CONFIG_RCU_NOCB_CPU=y, set
 			the specified list of CPUs to be no-callback CPUs.
 			Invocation of these CPUs' RCU callbacks will
-			be offloaded to "rcuoN" kthreads created for
+			be offloaded to "rcuox/N" kthreads created for
-			that purpose.  This reduces OS jitter on the
+			that purpose, where "x" is "b" for RCU-bh, "p"
+			for RCU-preempt, and "s" for RCU-sched, and "N"
+			is the CPU number.  This reduces OS jitter on the
 			offloaded CPUs, which can be useful for HPC and
+
 			real-time workloads.  It can also improve energy
 			efficiency for asymmetric multiprocessors.
 

init/Kconfig

@@ -666,12 +666,13 @@ config RCU_NOCB_CPU
 
 	  This option offloads callback invocation from the set of
 	  CPUs specified at boot time by the rcu_nocbs parameter.
-	  For each such CPU, a kthread ("rcuoN") will be created to
+	  For each such CPU, a kthread ("rcuox/N") will be created to
-	  invoke callbacks, where the "N" is the CPU being offloaded.
+	  invoke callbacks, where the "N" is the CPU being offloaded,
-	  Nothing prevents this kthread from running on the specified
+	  and where the "x" is "b" for RCU-bh, "p" for RCU-preempt, and
-	  CPUs, but (1) the kthreads may be preempted between each
+	  "s" for RCU-sched.  Nothing prevents this kthread from running
-	  callback, and (2) affinity or cgroups can be used to force
+	  on the specified CPUs, but (1) the kthreads may be preempted
-	  the kthreads to run on whatever set of CPUs is desired.
+	  between each callback, and (2) affinity or cgroups can be used
+	  to force the kthreads to run on whatever set of CPUs is desired.
 
 	  Say Y here if you want to help to debug reduced OS jitter.
 	  Say N here if you are unsure.

kernel/rcutree.c

@@ -64,7 +64,7 @@
 static struct lock_class_key rcu_node_class[RCU_NUM_LVLS];
 static struct lock_class_key rcu_fqs_class[RCU_NUM_LVLS];
 
-#define RCU_STATE_INITIALIZER(sname, cr) { \
+#define RCU_STATE_INITIALIZER(sname, sabbr, cr) { \
 	.level = { &sname##_state.node[0] }, \
 	.call = cr, \
 	.fqs_state = RCU_GP_IDLE, \
@@ -76,13 +76,14 @@ static struct lock_class_key rcu_fqs_class[RCU_NUM_LVLS];
 	.barrier_mutex = __MUTEX_INITIALIZER(sname##_state.barrier_mutex), \
 	.onoff_mutex = __MUTEX_INITIALIZER(sname##_state.onoff_mutex), \
 	.name = #sname, \
+	.abbr = sabbr, \
 }
 
 struct rcu_state rcu_sched_state =
-	RCU_STATE_INITIALIZER(rcu_sched, call_rcu_sched);
+	RCU_STATE_INITIALIZER(rcu_sched, 's', call_rcu_sched);
 DEFINE_PER_CPU(struct rcu_data, rcu_sched_data);
 
-struct rcu_state rcu_bh_state = RCU_STATE_INITIALIZER(rcu_bh, call_rcu_bh);
+struct rcu_state rcu_bh_state = RCU_STATE_INITIALIZER(rcu_bh, 'b', call_rcu_bh);
 DEFINE_PER_CPU(struct rcu_data, rcu_bh_data);
 
 static struct rcu_state *rcu_state;

kernel/rcutree.h

@@ -443,6 +443,7 @@ struct rcu_state {
 	unsigned long gp_max;			/* Maximum GP duration in */
 						/*  jiffies. */
 	char *name;				/* Name of structure. */
+	char abbr;				/* Abbreviated name. */
 	struct list_head flavors;		/* List of RCU flavors. */
 };
 

kernel/rcutree_plugin.h

@@ -111,7 +111,7 @@ static void __init rcu_bootup_announce_oddness(void)
 #ifdef CONFIG_TREE_PREEMPT_RCU
 
 struct rcu_state rcu_preempt_state =
-	RCU_STATE_INITIALIZER(rcu_preempt, call_rcu);
+	RCU_STATE_INITIALIZER(rcu_preempt, 'p', call_rcu);
 DEFINE_PER_CPU(struct rcu_data, rcu_preempt_data);
 static struct rcu_state *rcu_state = &rcu_preempt_state;
 
@@ -2517,7 +2517,8 @@ static void __init rcu_spawn_nocb_kthreads(struct rcu_state *rsp)
 		return;
 	for_each_cpu(cpu, rcu_nocb_mask) {
 		rdp = per_cpu_ptr(rsp->rda, cpu);
-		t = kthread_run(rcu_nocb_kthread, rdp, "rcuo%d", cpu);
+		t = kthread_run(rcu_nocb_kthread, rdp,
+				"rcuo%c/%d", rsp->abbr, cpu);
 		BUG_ON(IS_ERR(t));
 		ACCESS_ONCE(rdp->nocb_kthread) = t;
 	}