rcu: Drive quiescent-state-forcing delay from HZ

Systems with HZ=100 can have slow bootup times due to the default
three-jiffy delays between quiescent-state forcing attempts.  This
commit therefore auto-tunes the RCU_JIFFIES_TILL_FORCE_QS value based
on the value of HZ.  However, this would break very large systems that
require more time between quiescent-state forcing attempts.  This
commit therefore also ups the default delay by one jiffy for each
256 CPUs that might be on the system (based off of nr_cpu_ids at
runtime, -not- NR_CPUS at build time).

Updated to collapse #ifdefs for RCU_JIFFIES_TILL_FORCE_QS into a
step-function definition as suggested by Josh Triplett.

Reported-by: Paul Mackerras <paulus@au1.ibm.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>

kernel/rcutree.c

@@ -218,8 +218,8 @@ module_param(blimit, long, 0444);
 module_param(qhimark, long, 0444);
 module_param(qlowmark, long, 0444);
 
-static ulong jiffies_till_first_fqs = RCU_JIFFIES_TILL_FORCE_QS;
+static ulong jiffies_till_first_fqs = ULONG_MAX;
-static ulong jiffies_till_next_fqs = RCU_JIFFIES_TILL_FORCE_QS;
+static ulong jiffies_till_next_fqs = ULONG_MAX;
 
 module_param(jiffies_till_first_fqs, ulong, 0644);
 module_param(jiffies_till_next_fqs, ulong, 0644);
@@ -3265,11 +3265,25 @@ static void __init rcu_init_one(struct rcu_state *rsp,
  */
 static void __init rcu_init_geometry(void)
 {
+	ulong d;
 	int i;
 	int j;
 	int n = nr_cpu_ids;
 	int rcu_capacity[MAX_RCU_LVLS + 1];
 
+	/*
+	 * Initialize any unspecified boot parameters.
+	 * The default values of jiffies_till_first_fqs and
+	 * jiffies_till_next_fqs are set to the RCU_JIFFIES_TILL_FORCE_QS
+	 * value, which is a function of HZ, then adding one for each
+	 * RCU_JIFFIES_FQS_DIV CPUs that might be on the system.
+	 */
+	d = RCU_JIFFIES_TILL_FORCE_QS + nr_cpu_ids / RCU_JIFFIES_FQS_DIV;
+	if (jiffies_till_first_fqs == ULONG_MAX)
+		jiffies_till_first_fqs = d;
+	if (jiffies_till_next_fqs == ULONG_MAX)
+		jiffies_till_next_fqs = d;
+
 	/* If the compile-time values are accurate, just leave. */
 	if (rcu_fanout_leaf == CONFIG_RCU_FANOUT_LEAF &&
 	    nr_cpu_ids == NR_CPUS)

kernel/rcutree.h

@@ -343,12 +343,17 @@ struct rcu_data {
 #define RCU_FORCE_QS		3	/* Need to force quiescent state. */
 #define RCU_SIGNAL_INIT		RCU_SAVE_DYNTICK
 
-#define RCU_JIFFIES_TILL_FORCE_QS	 3	/* for rsp->jiffies_force_qs */
+#define RCU_JIFFIES_TILL_FORCE_QS (1 + (HZ > 250) + (HZ > 500))
+					/* For jiffies_till_first_fqs and */
+					/*  and jiffies_till_next_fqs. */
 
-#define RCU_STALL_RAT_DELAY		2	/* Allow other CPUs time */
+#define RCU_JIFFIES_FQS_DIV	256	/* Very large systems need more */
-						/*  to take at least one */
+					/*  delay between bouts of */
-						/*  scheduling clock irq */
+					/*  quiescent-state forcing. */
-						/*  before ratting on them. */
+
+#define RCU_STALL_RAT_DELAY	2	/* Allow other CPUs time to take */
+					/*  at least one scheduling clock */
+					/*  irq before ratting on them. */
 
 #define rcu_wait(cond)							\
 do {									\