rcu: Add callback-free CPUs

RCU callback execution can add significant OS jitter and also can
degrade both scheduling latency and, in asymmetric multiprocessors,
energy efficiency.  This commit therefore adds the ability for selected
CPUs ("rcu_nocbs=" boot parameter) to have their callbacks offloaded
to kthreads.  If the "rcu_nocb_poll" boot parameter is also specified,
these kthreads will do polling, removing the need for the offloaded
CPUs to do wakeups.  At least one CPU must be doing normal callback
processing: currently CPU 0 cannot be selected as a no-CBs CPU.
In addition, attempts to offline the last normal-CBs CPU will fail.

This feature was inspired by Jim Houston's and Joe Korty's JRCU, and
this commit includes fixes to problems located by Fengguang Wu's
kbuild test robot.

[ paulmck: Added gfp.h include file as suggested by Fengguang Wu. ]

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

1 files changed, 47 insertions, 0 deletions

diff --git a/kernel/rcutree.h b/kernel/rcutree.h
index d274af35721..488f2ec6b66 100644
--- a/kernel/rcutree.h
+++ b/kernel/rcutree.h
@@ -317,6 +317,18 @@ struct rcu_data {
 	struct rcu_head oom_head;
 #endif /* #ifdef CONFIG_RCU_FAST_NO_HZ */
 
+	/* 7) Callback offloading. */
+#ifdef CONFIG_RCU_NOCB_CPU
+	struct rcu_head *nocb_head;	/* CBs waiting for kthread. */
+	struct rcu_head **nocb_tail;
+	atomic_long_t nocb_q_count;	/* # CBs waiting for kthread */
+	atomic_long_t nocb_q_count_lazy; /*  (approximate). */
+	int nocb_p_count;		/* # CBs being invoked by kthread */
+	int nocb_p_count_lazy;		/*  (approximate). */
+	wait_queue_head_t nocb_wq;	/* For nocb kthreads to sleep on. */
+	struct task_struct *nocb_kthread;
+#endif /* #ifdef CONFIG_RCU_NOCB_CPU */
+
 	int cpu;
 	struct rcu_state *rsp;
 };
@@ -369,6 +381,12 @@ struct rcu_state {
 	struct rcu_data __percpu *rda;		/* pointer of percu rcu_data. */
 	void (*call)(struct rcu_head *head,	/* call_rcu() flavor. */
 		     void (*func)(struct rcu_head *head));
+#ifdef CONFIG_RCU_NOCB_CPU
+	void (*call_remote)(struct rcu_head *head,
+		     void (*func)(struct rcu_head *head));
+						/* call_rcu() flavor, but for */
+						/*  placing on remote CPU. */
+#endif /* #ifdef CONFIG_RCU_NOCB_CPU */
 
 	/* The following fields are guarded by the root rcu_node's lock. */
 
@@ -439,6 +457,8 @@ struct rcu_state {
 #define RCU_GP_FLAG_FQS  0x2	/* Need grace-period quiescent-state forcing. */
 
 extern struct list_head rcu_struct_flavors;
+
+/* Sequence through rcu_state structures for each RCU flavor. */
 #define for_each_rcu_flavor(rsp) \
 	list_for_each_entry((rsp), &rcu_struct_flavors, flavors)
 
@@ -515,5 +535,32 @@ static void print_cpu_stall_info(struct rcu_state *rsp, int cpu);
 static void print_cpu_stall_info_end(void);
 static void zero_cpu_stall_ticks(struct rcu_data *rdp);
 static void increment_cpu_stall_ticks(void);
+static bool is_nocb_cpu(int cpu);
+static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp,
+			    bool lazy);
+static bool rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp,
+				      struct rcu_data *rdp);
+static bool nocb_cpu_expendable(int cpu);
+static void rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp);
+static void rcu_spawn_nocb_kthreads(struct rcu_state *rsp);
+static void init_nocb_callback_list(struct rcu_data *rdp);
+static void __init rcu_init_nocb(void);
 
 #endif /* #ifndef RCU_TREE_NONCORE */
+
+#ifdef CONFIG_RCU_TRACE
+#ifdef CONFIG_RCU_NOCB_CPU
+/* Sum up queue lengths for tracing. */
+static inline void rcu_nocb_q_lengths(struct rcu_data *rdp, long *ql, long *qll)
+{
+	*ql = atomic_long_read(&rdp->nocb_q_count) + rdp->nocb_p_count;
+	*qll = atomic_long_read(&rdp->nocb_q_count_lazy) + rdp->nocb_p_count_lazy;
+}
+#else /* #ifdef CONFIG_RCU_NOCB_CPU */
+static inline void rcu_nocb_q_lengths(struct rcu_data *rdp, long *ql, long *qll)
+{
+	*ql = 0;
+	*qll = 0;
+}
+#endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */
+#endif /* #ifdef CONFIG_RCU_TRACE */