sched/topology: Add SD_ASYM_CPUCAPACITY flag detection

The SD_ASYM_CPUCAPACITY sched_domain flag is supposed to mark the
sched_domain in the hierarchy where all CPU capacities are visible for
any CPU's point of view on asymmetric CPU capacity systems. The
scheduler can then take to take capacity asymmetry into account when
balancing at this level. It also serves as an indicator for how wide
task placement heuristics have to search to consider all available CPU
capacities as asymmetric systems might often appear symmetric at
smallest level(s) of the sched_domain hierarchy.

The flag has been around for while but so far only been set by
out-of-tree code in Android kernels. One solution is to let each
architecture provide the flag through a custom sched_domain topology
array and associated mask and flag functions. However,
SD_ASYM_CPUCAPACITY is special in the sense that it depends on the
capacity and presence of all CPUs in the system, i.e. when hotplugging
all CPUs out except those with one particular CPU capacity the flag
should disappear even if the sched_domains don't collapse. Similarly,
the flag is affected by cpusets where load-balancing is turned off.
Detecting when the flags should be set therefore depends not only on
topology information but also the cpuset configuration and hotplug
state. The arch code doesn't have easy access to the cpuset
configuration.

Instead, this patch implements the flag detection in generic code where
cpusets and hotplug state is already taken care of. All the arch is
responsible for is to implement arch_scale_cpu_capacity() and force a
full rebuild of the sched_domain hierarchy if capacities are updated,
e.g. later in the boot process when cpufreq has initialized.

Signed-off-by: Morten Rasmussen <[e-mail]>
Signed-off-by: Peter Zijlstra (Intel) <[e-mail]>
Cc: Linus Torvalds <[e-mail]>
Cc: Peter Zijlstra <[e-mail]>
Cc: Thomas Gleixner <[e-mail]>
Cc: [e-mail]
Cc: [e-mail]
Cc: [e-mail]
Link: http://lkml.kernel.org/r/[e-mail]
[ Fixed 'CPU' capitalization. ]
Signed-off-by: Ingo Molnar <[e-mail]>

include/linux/sched/topology.h

···
 #define SD_BALANCE_FORK		0x0008	/* Balance on fork, clone */
 #define SD_BALANCE_WAKE		0x0010  /* Balance on wakeup */
 #define SD_WAKE_AFFINE		0x0020	/* Wake task to waking CPU */
-#define SD_ASYM_CPUCAPACITY	0x0040  /* Groups have different max cpu capacities */
-#define SD_SHARE_CPUCAPACITY	0x0080	/* Domain members share cpu capacity */
+#define SD_ASYM_CPUCAPACITY	0x0040  /* Domain members have different CPU capacities */
+#define SD_SHARE_CPUCAPACITY	0x0080	/* Domain members share CPU capacity */
 #define SD_SHARE_POWERDOMAIN	0x0100	/* Domain members share power domain */
-#define SD_SHARE_PKG_RESOURCES	0x0200	/* Domain members share cpu pkg resources */
+#define SD_SHARE_PKG_RESOURCES	0x0200	/* Domain members share CPU pkg resources */
 #define SD_SERIALIZE		0x0400	/* Only a single load balancing instance */
 #define SD_ASYM_PACKING		0x0800  /* Place busy groups earlier in the domain */
 #define SD_PREFER_SIBLING	0x1000	/* Prefer to place tasks in a sibling domain */

kernel/sched/topology.c

···
  *   SD_SHARE_PKG_RESOURCES - describes shared caches
  *   SD_NUMA                - describes NUMA topologies
  *   SD_SHARE_POWERDOMAIN   - describes shared power domain
- *   SD_ASYM_CPUCAPACITY    - describes mixed capacity topologies
  *
  * Odd one out, which beside describing the topology has a quirk also
  * prescribes the desired behaviour that goes along with it:
···
 	 SD_SHARE_PKG_RESOURCES |	\
 	 SD_NUMA		|	\
 	 SD_ASYM_PACKING	|	\
-	 SD_ASYM_CPUCAPACITY	|	\
 	 SD_SHARE_POWERDOMAIN)
 
 static struct sched_domain *
 sd_init(struct sched_domain_topology_level *tl,
 	const struct cpumask *cpu_map,
-	struct sched_domain *child, int cpu)
+	struct sched_domain *child, int dflags, int cpu)
 {
 	struct sd_data *sdd = &tl->data;
 	struct sched_domain *sd = *per_cpu_ptr(sdd->sd, cpu);
···
 	if (WARN_ONCE(sd_flags & ~TOPOLOGY_SD_FLAGS,
 			"wrong sd_flags in topology description\n"))
 		sd_flags &= ~TOPOLOGY_SD_FLAGS;
+
+	/* Apply detected topology flags */
+	sd_flags |= dflags;
 
 	*sd = (struct sched_domain){
 		.min_interval		= sd_weight,
···
 
 static struct sched_domain *build_sched_domain(struct sched_domain_topology_level *tl,
 		const struct cpumask *cpu_map, struct sched_domain_attr *attr,
-		struct sched_domain *child, int cpu)
+		struct sched_domain *child, int dflags, int cpu)
 {
-	struct sched_domain *sd = sd_init(tl, cpu_map, child, cpu);
+	struct sched_domain *sd = sd_init(tl, cpu_map, child, dflags, cpu);
 
 	if (child) {
 		sd->level = child->level + 1;
···
 }
 
 /*
+ * Find the sched_domain_topology_level where all CPU capacities are visible
+ * for all CPUs.
+ */
+static struct sched_domain_topology_level
+*asym_cpu_capacity_level(const struct cpumask *cpu_map)
+{
+	int i, j, asym_level = 0;
+	bool asym = false;
+	struct sched_domain_topology_level *tl, *asym_tl = NULL;
+	unsigned long cap;
+
+	/* Is there any asymmetry? */
+	cap = arch_scale_cpu_capacity(NULL, cpumask_first(cpu_map));
+
+	for_each_cpu(i, cpu_map) {
+		if (arch_scale_cpu_capacity(NULL, i) != cap) {
+			asym = true;
+			break;
+		}
+	}
+
+	if (!asym)
+		return NULL;
+
+	/*
+	 * Examine topology from all CPU's point of views to detect the lowest
+	 * sched_domain_topology_level where a highest capacity CPU is visible
+	 * to everyone.
+	 */
+	for_each_cpu(i, cpu_map) {
+		unsigned long max_capacity = arch_scale_cpu_capacity(NULL, i);
+		int tl_id = 0;
+
+		for_each_sd_topology(tl) {
+			if (tl_id < asym_level)
+				goto next_level;
+
+			for_each_cpu_and(j, tl->mask(i), cpu_map) {
+				unsigned long capacity;
+
+				capacity = arch_scale_cpu_capacity(NULL, j);
+
+				if (capacity <= max_capacity)
+					continue;
+
+				max_capacity = capacity;
+				asym_level = tl_id;
+				asym_tl = tl;
+			}
+next_level:
+			tl_id++;
+		}
+	}
+
+	return asym_tl;
+}
+
+
+/*
  * Build sched domains for a given set of CPUs and attach the sched domains
  * to the individual CPUs
  */
···
 	struct s_data d;
 	struct rq *rq = NULL;
 	int i, ret = -ENOMEM;
+	struct sched_domain_topology_level *tl_asym;
 
 	alloc_state = __visit_domain_allocation_hell(&d, cpu_map);
 	if (alloc_state != sa_rootdomain)
 		goto error;
+
+	tl_asym = asym_cpu_capacity_level(cpu_map);
 
 	/* Set up domains for CPUs specified by the cpu_map: */
 	for_each_cpu(i, cpu_map) {
···
 
 		sd = NULL;
 		for_each_sd_topology(tl) {
-			sd = build_sched_domain(tl, cpu_map, attr, sd, i);
+			int dflags = 0;
+
+			if (tl == tl_asym)
+				dflags |= SD_ASYM_CPUCAPACITY;
+
+			sd = build_sched_domain(tl, cpu_map, attr, sd, dflags, i);
+
 			if (tl == sched_domain_topology)
 				*per_cpu_ptr(d.sd, i) = sd;
 			if (tl->flags & SDTL_OVERLAP)