nohz_full: Add full-system-idle state machine

This commit adds the state machine that takes the per-CPU idle data
as input and produces a full-system-idle indication as output.  This
state machine is driven out of RCU's quiescent-state-forcing
mechanism, which invokes rcu_sysidle_check_cpu() to collect per-CPU
idle state and then rcu_sysidle_report() to drive the state machine.

The full-system-idle state is sampled using rcu_sys_is_idle(), which
also drives the state machine if RCU is idle (and does so by forcing
RCU to become non-idle).  This function returns true if all but the
timekeeping CPU (tick_do_timer_cpu) are idle and have been idle long
enough to avoid memory contention on the full_sysidle_state state
variable.  The rcu_sysidle_force_exit() may be called externally
to reset the state machine back into non-idle state.

For large systems the state machine is driven out of RCU's
force-quiescent-state logic, which provides good scalability at the price
of millisecond-scale latencies on the transition to full-system-idle
state.  This is not so good for battery-powered systems, which are usually
small enough that they don't need to care about scalability, but which
do care deeply about energy efficiency.  Small systems therefore drive
the state machine directly out of the idle-entry code.  The number of
CPUs in a "small" system is defined by a new NO_HZ_FULL_SYSIDLE_SMALL
Kconfig parameter, which defaults to 8.  Note that this is a build-time
definition.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Lai Jiangshan <laijs@cn.fujitsu.com>
[ paulmck: Use true and false for boolean constants per Lai Jiangshan. ]
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
[ paulmck: Simplify logic and provide better comments for memory barriers,
  based on review comments and questions by Lai Jiangshan. ]

include/linux/rcupdate.h

@@ -1011,4 +1011,22 @@ static inline bool rcu_is_nocb_cpu(int cpu) { return false; }
 #endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */
 
 
+/* Only for use by adaptive-ticks code. */
+#ifdef CONFIG_NO_HZ_FULL_SYSIDLE
+extern bool rcu_sys_is_idle(void);
+extern void rcu_sysidle_force_exit(void);
+#else /* #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */
+
+static inline bool rcu_sys_is_idle(void)
+{
+	return false;
+}
+
+static inline void rcu_sysidle_force_exit(void)
+{
+}
+
+#endif /* #else #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */
+
+
 #endif /* __LINUX_RCUPDATE_H */

kernel/rcutree.c

@@ -734,6 +734,7 @@ static int dyntick_save_progress_counter(struct rcu_data *rdp,
 					 bool *isidle, unsigned long *maxj)
 {
 	rdp->dynticks_snap = atomic_add_return(0, &rdp->dynticks->dynticks);
+	rcu_sysidle_check_cpu(rdp, isidle, maxj);
 	return (rdp->dynticks_snap & 0x1) == 0;
 }
 
@@ -1373,11 +1374,17 @@ int rcu_gp_fqs(struct rcu_state *rsp, int fqs_state_in)
 	rsp->n_force_qs++;
 	if (fqs_state == RCU_SAVE_DYNTICK) {
 		/* Collect dyntick-idle snapshots. */
+		if (is_sysidle_rcu_state(rsp)) {
+			isidle = 1;
+			maxj = jiffies - ULONG_MAX / 4;
+		}
 		force_qs_rnp(rsp, dyntick_save_progress_counter,
 			     &isidle, &maxj);
+		rcu_sysidle_report_gp(rsp, isidle, maxj);
 		fqs_state = RCU_FORCE_QS;
 	} else {
 		/* Handle dyntick-idle and offline CPUs. */
+		isidle = 0;
 		force_qs_rnp(rsp, rcu_implicit_dynticks_qs, &isidle, &maxj);
 	}
 	/* Clear flag to prevent immediate re-entry. */
@@ -2103,9 +2110,12 @@ static void force_qs_rnp(struct rcu_state *rsp,
 		cpu = rnp->grplo;
 		bit = 1;
 		for (; cpu <= rnp->grphi; cpu++, bit <<= 1) {
-			if ((rnp->qsmask & bit) != 0 &&
-			    f(per_cpu_ptr(rsp->rda, cpu), isidle, maxj))
-				mask |= bit;
+			if ((rnp->qsmask & bit) != 0) {
+				if ((rnp->qsmaskinit & bit) != 0)
+					*isidle = 0;
+				if (f(per_cpu_ptr(rsp->rda, cpu), isidle, maxj))
+					mask |= bit;
+			}
 		}
 		if (mask != 0) {
 

kernel/rcutree.h

@@ -555,6 +555,11 @@ static void rcu_kick_nohz_cpu(int cpu);
 static bool init_nocb_callback_list(struct rcu_data *rdp);
 static void rcu_sysidle_enter(struct rcu_dynticks *rdtp, int irq);
 static void rcu_sysidle_exit(struct rcu_dynticks *rdtp, int irq);
+static void rcu_sysidle_check_cpu(struct rcu_data *rdp, bool *isidle,
+				  unsigned long *maxj);
+static bool is_sysidle_rcu_state(struct rcu_state *rsp);
+static void rcu_sysidle_report_gp(struct rcu_state *rsp, int isidle,
+				  unsigned long maxj);
 static void rcu_sysidle_init_percpu_data(struct rcu_dynticks *rdtp);
 
 #endif /* #ifndef RCU_TREE_NONCORE */

kernel/time/Kconfig

@@ -157,6 +157,33 @@ config NO_HZ_FULL_SYSIDLE
 
 	 Say N if you are unsure.
 
+config NO_HZ_FULL_SYSIDLE_SMALL
+	int "Number of CPUs above which large-system approach is used"
+	depends on NO_HZ_FULL_SYSIDLE
+	range 1 NR_CPUS
+	default 8
+	help
+	 The full-system idle detection mechanism takes a lazy approach
+	 on large systems, as is required to attain decent scalability.
+	 However, on smaller systems, scalability is not anywhere near as
+	 large a concern as is energy efficiency.  The sysidle subsystem
+	 therefore uses a fast but non-scalable algorithm for small
+	 systems and a lazier but scalable algorithm for large systems.
+	 This Kconfig parameter defines the number of CPUs in the largest
+	 system that will be considered to be "small".
+
+	 The default value will be fine in most cases.	Battery-powered
+	 systems that (1) enable NO_HZ_FULL_SYSIDLE, (2) have larger
+	 numbers of CPUs, and (3) are suffering from battery-lifetime
+	 problems due to long sysidle latencies might wish to experiment
+	 with larger values for this Kconfig parameter.  On the other
+	 hand, they might be even better served by disabling NO_HZ_FULL
+	 entirely, given that NO_HZ_FULL is intended for HPC and
+	 real-time workloads that at present do not tend to be run on
+	 battery-powered systems.
+
+	 Take the default if you are unsure.
+
 config NO_HZ
 	bool "Old Idle dynticks config"
 	depends on !ARCH_USES_GETTIMEOFFSET && GENERIC_CLOCKEVENTS