[IA64] top level scheduler domain for ia64

Some have noticed that the overlapping sched domains code doesn't quite work
as intended (it results in disjoint domains on some machines), and that a top
level, machine spanning domain is needed.  This patch from John Hawkes adds
it to the ia64 code.  This allows processes to run on all CPUs in large
systems, though balancing is limited.  It should go to Linus soon now
otherwise large systems will only have ~16p (depending on topology) usable by
the scheduler.  I sanity checked it on a small system after rediffing John's
original, and he's done some testing on very large systems.
 
 Nick, can you buy off on the sched.c change?  Alternatively, do you want to
 send that fix separately John? Nick did indeed ACK this change, but it isn't
 dependent on this ia64 specific part ... so it's going to be submitted
 separately.
Signed-off-by: John Hawkes <hawkes@sgi.com>
Signed-off-by: Jesse Barnes <jbarnes@sgi.com>
Signed-off-by: Tony Luck <tony.luck@intel.com>

arch/ia64/kernel/domain.c

@@ -119,6 +119,14 @@ static int __devinit cpu_to_phys_group(int cpu)
  */
 static DEFINE_PER_CPU(struct sched_domain, node_domains);
 static struct sched_group *sched_group_nodes[MAX_NUMNODES];
+
+static DEFINE_PER_CPU(struct sched_domain, allnodes_domains);
+static struct sched_group sched_group_allnodes[MAX_NUMNODES];
+
+static int __devinit cpu_to_allnodes_group(int cpu)
+{
+	return cpu_to_node(cpu);
+}
 #endif
 
 /*
@@ -149,9 +157,21 @@ void __devinit arch_init_sched_domains(void)
 		cpus_and(nodemask, nodemask, cpu_default_map);
 
 #ifdef CONFIG_NUMA
+		if (num_online_cpus()
+				> SD_NODES_PER_DOMAIN*cpus_weight(nodemask)) {
+			sd = &per_cpu(allnodes_domains, i);
+			*sd = SD_ALLNODES_INIT;
+			sd->span = cpu_default_map;
+			group = cpu_to_allnodes_group(i);
+			sd->groups = &sched_group_allnodes[group];
+			p = sd;
+		} else
+			p = NULL;
+
 		sd = &per_cpu(node_domains, i);
 		*sd = SD_NODE_INIT;
 		sd->span = sched_domain_node_span(node);
+		sd->parent = p;
 		cpus_and(sd->span, sd->span, cpu_default_map);
 #endif
 
@@ -201,6 +221,9 @@ void __devinit arch_init_sched_domains(void)
 	}
 
 #ifdef CONFIG_NUMA
+	init_sched_build_groups(sched_group_allnodes, cpu_default_map,
+				&cpu_to_allnodes_group);
+
 	for (i = 0; i < MAX_NUMNODES; i++) {
 		/* Set up node groups */
 		struct sched_group *sg, *prev;
@@ -282,6 +305,15 @@ void __devinit arch_init_sched_domains(void)
 		power = SCHED_LOAD_SCALE + SCHED_LOAD_SCALE *
 				(cpus_weight(sd->groups->cpumask)-1) / 10;
 		sd->groups->cpu_power = power;
+
+#ifdef CONFIG_NUMA
+		sd = &per_cpu(allnodes_domains, i);
+		if (sd->groups) {
+			power = SCHED_LOAD_SCALE + SCHED_LOAD_SCALE *
+				(cpus_weight(sd->groups->cpumask)-1) / 10;
+			sd->groups->cpu_power = power;
+		}
+#endif
 	}
 
 #ifdef CONFIG_NUMA

include/asm-ia64/topology.h

@@ -58,7 +58,26 @@ void build_cpu_to_node_map(void);
 				| SD_BALANCE_EXEC	\
 				| SD_WAKE_BALANCE,	\
 	.last_balance		= jiffies,		\
-	.balance_interval	= 10,			\
+	.balance_interval	= 1,			\
+	.nr_balance_failed	= 0,			\
+}
+
+/* sched_domains SD_ALLNODES_INIT for IA64 NUMA machines */
+#define SD_ALLNODES_INIT (struct sched_domain) {	\
+	.span			= CPU_MASK_NONE,	\
+	.parent			= NULL,			\
+	.groups			= NULL,			\
+	.min_interval		= 80,			\
+	.max_interval		= 320,			\
+	.busy_factor		= 320,			\
+	.imbalance_pct		= 125,			\
+	.cache_hot_time		= (10*1000000),		\
+	.cache_nice_tries	= 1,			\
+	.per_cpu_gain		= 100,			\
+	.flags			= SD_LOAD_BALANCE	\
+				| SD_BALANCE_EXEC,	\
+	.last_balance		= jiffies,		\
+	.balance_interval	= 100*(63+num_online_cpus())/64,   \
 	.nr_balance_failed	= 0,			\
 }