sched, cpuset: customize sched domains, core

[rebased for sched-devel/latest]

 - Add a new cpuset file, having levels:
     sched_relax_domain_level

 - Modify partition_sched_domains() and build_sched_domains()
   to take attributes parameter passed from cpuset.

 - Fill newidle_idx for node domains which currently unused but
   might be required if sched_relax_domain_level become higher.

 - We can change the default level by boot option 'relax_domain_level='.

Signed-off-by: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

7 files changed, 161 insertions, 11 deletions

diff --git a/include/asm-ia64/topology.h b/include/asm-ia64/topology.h
index f929dde8534..f2f72ef2a89 100644
--- a/include/asm-ia64/topology.h
+++ b/include/asm-ia64/topology.h
@@ -93,7 +93,7 @@ void build_cpu_to_node_map(void);
 	.cache_nice_tries	= 2,			\
 	.busy_idx		= 3,			\
 	.idle_idx		= 2,			\
-	.newidle_idx		= 0, /* unused */	\
+	.newidle_idx		= 2,			\
 	.wake_idx		= 1,			\
 	.forkexec_idx		= 1,			\
 	.flags			= SD_LOAD_BALANCE	\
diff --git a/include/asm-sh/topology.h b/include/asm-sh/topology.h
index f402a3b1cfa..34cdb28e8f4 100644
--- a/include/asm-sh/topology.h
+++ b/include/asm-sh/topology.h
@@ -16,7 +16,7 @@
 	.cache_nice_tries	= 2,			\
 	.busy_idx		= 3,			\
 	.idle_idx		= 2,			\
-	.newidle_idx		= 0,			\
+	.newidle_idx		= 2,			\
 	.wake_idx		= 1,			\
 	.forkexec_idx		= 1,			\
 	.flags			= SD_LOAD_BALANCE	\
diff --git a/include/asm-x86/topology.h b/include/asm-x86/topology.h
index 9ef74c5d5ad..22073268b48 100644
--- a/include/asm-x86/topology.h
+++ b/include/asm-x86/topology.h
@@ -147,7 +147,7 @@ extern unsigned long node_remap_size[];
 
 # define SD_CACHE_NICE_TRIES	2
 # define SD_IDLE_IDX		2
-# define SD_NEWIDLE_IDX		0
+# define SD_NEWIDLE_IDX		2
 # define SD_FORKEXEC_IDX	1
 
 #endif
diff --git a/include/linux/sched.h b/include/linux/sched.h
index ada24022d23..11f47249cdd 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -704,6 +704,7 @@ enum cpu_idle_type {
 #define SD_POWERSAVINGS_BALANCE	256	/* Balance for power savings */
 #define SD_SHARE_PKG_RESOURCES	512	/* Domain members share cpu pkg resources */
 #define SD_SERIALIZE		1024	/* Only a single load balancing instance */
+#define SD_WAKE_IDLE_FAR	2048	/* Gain latency sacrificing cache hit */
 
 #define BALANCE_FOR_MC_POWER	\
 	(sched_smt_power_savings ? SD_POWERSAVINGS_BALANCE : 0)
@@ -733,6 +734,24 @@ struct sched_group {
 	u32 reciprocal_cpu_power;
 };
 
+enum sched_domain_level {
+	SD_LV_NONE = 0,
+	SD_LV_SIBLING,
+	SD_LV_MC,
+	SD_LV_CPU,
+	SD_LV_NODE,
+	SD_LV_ALLNODES,
+	SD_LV_MAX
+};
+
+struct sched_domain_attr {
+	int relax_domain_level;
+};
+
+#define SD_ATTR_INIT	(struct sched_domain_attr) {	\
+	.relax_domain_level = -1,			\
+}
+
 struct sched_domain {
 	/* These fields must be setup */
 	struct sched_domain *parent;	/* top domain must be null terminated */
@@ -750,6 +769,7 @@ struct sched_domain {
 	unsigned int wake_idx;
 	unsigned int forkexec_idx;
 	int flags;			/* See SD_* */
+	enum sched_domain_level level;
 
 	/* Runtime fields. */
 	unsigned long last_balance;	/* init to jiffies. units in jiffies */
@@ -789,7 +809,8 @@ struct sched_domain {
 #endif
 };
 
-extern void partition_sched_domains(int ndoms_new, cpumask_t *doms_new);
+extern void partition_sched_domains(int ndoms_new, cpumask_t *doms_new,
+				    struct sched_domain_attr *dattr_new);
 extern int arch_reinit_sched_domains(void);
 
 #endif	/* CONFIG_SMP */
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index b0c870b2ac3..8b35fbd8292 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -98,6 +98,9 @@ struct cpuset {
 	/* partition number for rebuild_sched_domains() */
 	int pn;
 
+	/* for custom sched domain */
+	int relax_domain_level;
+
 	/* used for walking a cpuset heirarchy */
 	struct list_head stack_list;
 };
@@ -478,6 +481,16 @@ static int cpusets_overlap(struct cpuset *a, struct cpuset *b)
 	return cpus_intersects(a->cpus_allowed, b->cpus_allowed);
 }
 
+static void
+update_domain_attr(struct sched_domain_attr *dattr, struct cpuset *c)
+{
+	if (!dattr)
+		return;
+	if (dattr->relax_domain_level < c->relax_domain_level)
+		dattr->relax_domain_level = c->relax_domain_level;
+	return;
+}
+
 /*
  * rebuild_sched_domains()
  *
@@ -553,12 +566,14 @@ static void rebuild_sched_domains(void)
 	int csn;		/* how many cpuset ptrs in csa so far */
 	int i, j, k;		/* indices for partition finding loops */
 	cpumask_t *doms;	/* resulting partition; i.e. sched domains */
+	struct sched_domain_attr *dattr;  /* attributes for custom domains */
 	int ndoms;		/* number of sched domains in result */
 	int nslot;		/* next empty doms[] cpumask_t slot */
 
 	q = NULL;
 	csa = NULL;
 	doms = NULL;
+	dattr = NULL;
 
 	/* Special case for the 99% of systems with one, full, sched domain */
 	if (is_sched_load_balance(&top_cpuset)) {
@@ -566,6 +581,11 @@ static void rebuild_sched_domains(void)
 		doms = kmalloc(sizeof(cpumask_t), GFP_KERNEL);
 		if (!doms)
 			goto rebuild;
+		dattr = kmalloc(sizeof(struct sched_domain_attr), GFP_KERNEL);
+		if (dattr) {
+			*dattr = SD_ATTR_INIT;
+			update_domain_attr(dattr, &top_cpuset);
+		}
 		*doms = top_cpuset.cpus_allowed;
 		goto rebuild;
 	}
@@ -622,6 +642,7 @@ restart:
 	doms = kmalloc(ndoms * sizeof(cpumask_t), GFP_KERNEL);
 	if (!doms)
 		goto rebuild;
+	dattr = kmalloc(ndoms * sizeof(struct sched_domain_attr), GFP_KERNEL);
 
 	for (nslot = 0, i = 0; i < csn; i++) {
 		struct cpuset *a = csa[i];
@@ -644,12 +665,15 @@ restart:
 			}
 
 			cpus_clear(*dp);
+			if (dattr)
+				*(dattr + nslot) = SD_ATTR_INIT;
 			for (j = i; j < csn; j++) {
 				struct cpuset *b = csa[j];
 
 				if (apn == b->pn) {
 					cpus_or(*dp, *dp, b->cpus_allowed);
 					b->pn = -1;
+					update_domain_attr(dattr, b);
 				}
 			}
 			nslot++;
@@ -660,7 +684,7 @@ restart:
 rebuild:
 	/* Have scheduler rebuild sched domains */
 	get_online_cpus();
-	partition_sched_domains(ndoms, doms);
+	partition_sched_domains(ndoms, doms, dattr);
 	put_online_cpus();
 
 done:
@@ -668,6 +692,7 @@ done:
 		kfifo_free(q);
 	kfree(csa);
 	/* Don't kfree(doms) -- partition_sched_domains() does that. */
+	/* Don't kfree(dattr) -- partition_sched_domains() does that. */
 }
 
 static inline int started_after_time(struct task_struct *t1,
@@ -1011,6 +1036,21 @@ static int update_memory_pressure_enabled(struct cpuset *cs, char *buf)
 	return 0;
 }
 
+static int update_relax_domain_level(struct cpuset *cs, char *buf)
+{
+	int val = simple_strtol(buf, NULL, 10);
+
+	if (val < 0)
+		val = -1;
+
+	if (val != cs->relax_domain_level) {
+		cs->relax_domain_level = val;
+		rebuild_sched_domains();
+	}
+
+	return 0;
+}
+
 /*
  * update_flag - read a 0 or a 1 in a file and update associated flag
  * bit:	the bit to update (CS_CPU_EXCLUSIVE, CS_MEM_EXCLUSIVE,
@@ -1202,6 +1242,7 @@ typedef enum {
 	FILE_CPU_EXCLUSIVE,
 	FILE_MEM_EXCLUSIVE,
 	FILE_SCHED_LOAD_BALANCE,
+	FILE_SCHED_RELAX_DOMAIN_LEVEL,
 	FILE_MEMORY_PRESSURE_ENABLED,
 	FILE_MEMORY_PRESSURE,
 	FILE_SPREAD_PAGE,
@@ -1256,6 +1297,9 @@ static ssize_t cpuset_common_file_write(struct cgroup *cont,
 	case FILE_SCHED_LOAD_BALANCE:
 		retval = update_flag(CS_SCHED_LOAD_BALANCE, cs, buffer);
 		break;
+	case FILE_SCHED_RELAX_DOMAIN_LEVEL:
+		retval = update_relax_domain_level(cs, buffer);
+		break;
 	case FILE_MEMORY_MIGRATE:
 		retval = update_flag(CS_MEMORY_MIGRATE, cs, buffer);
 		break;
@@ -1354,6 +1398,9 @@ static ssize_t cpuset_common_file_read(struct cgroup *cont,
 	case FILE_SCHED_LOAD_BALANCE:
 		*s++ = is_sched_load_balance(cs) ? '1' : '0';
 		break;
+	case FILE_SCHED_RELAX_DOMAIN_LEVEL:
+		s += sprintf(s, "%d", cs->relax_domain_level);
+		break;
 	case FILE_MEMORY_MIGRATE:
 		*s++ = is_memory_migrate(cs) ? '1' : '0';
 		break;
@@ -1424,6 +1471,13 @@ static struct cftype cft_sched_load_balance = {
 	.private = FILE_SCHED_LOAD_BALANCE,
 };
 
+static struct cftype cft_sched_relax_domain_level = {
+	.name = "sched_relax_domain_level",
+	.read = cpuset_common_file_read,
+	.write = cpuset_common_file_write,
+	.private = FILE_SCHED_RELAX_DOMAIN_LEVEL,
+};
+
 static struct cftype cft_memory_migrate = {
 	.name = "memory_migrate",
 	.read = cpuset_common_file_read,
@@ -1475,6 +1529,9 @@ static int cpuset_populate(struct cgroup_subsys *ss, struct cgroup *cont)
 		return err;
 	if ((err = cgroup_add_file(cont, ss, &cft_sched_load_balance)) < 0)
 		return err;
+	if ((err = cgroup_add_file(cont, ss,
+					&cft_sched_relax_domain_level)) < 0)
+		return err;
 	if ((err = cgroup_add_file(cont, ss, &cft_memory_pressure)) < 0)
 		return err;
 	if ((err = cgroup_add_file(cont, ss, &cft_spread_page)) < 0)
@@ -1559,6 +1616,7 @@ static struct cgroup_subsys_state *cpuset_create(
 	nodes_clear(cs->mems_allowed);
 	cs->mems_generation = cpuset_mems_generation++;
 	fmeter_init(&cs->fmeter);
+	cs->relax_domain_level = -1;
 
 	cs->parent = parent;
 	number_of_cpusets++;
@@ -1631,6 +1689,7 @@ int __init cpuset_init(void)
 	fmeter_init(&top_cpuset.fmeter);
 	top_cpuset.mems_generation = cpuset_mems_generation++;
 	set_bit(CS_SCHED_LOAD_BALANCE, &top_cpuset.flags);
+	top_cpuset.relax_domain_level = -1;
 
 	err = register_filesystem(&cpuset_fs_type);
 	if (err < 0)
diff --git a/kernel/sched.c b/kernel/sched.c
index 475e3fcab73..62d7481caca 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -6771,6 +6771,7 @@ static noinline void sd_init_##type(struct sched_domain *sd)	\
 {								\
 	memset(sd, 0, sizeof(*sd));				\
 	*sd = SD_##type##_INIT;					\
+	sd->level = SD_LV_##type;				\
 }
 
 SD_INIT_FUNC(CPU)
@@ -6819,11 +6820,42 @@ struct allmasks {
 #define	SCHED_CPUMASK_VAR(v, a) 	cpumask_t *v = (cpumask_t *) \
 			((unsigned long)(a) + offsetof(struct allmasks, v))
 
+static int default_relax_domain_level = -1;
+
+static int __init setup_relax_domain_level(char *str)
+{
+	default_relax_domain_level = simple_strtoul(str, NULL, 0);
+	return 1;
+}
+__setup("relax_domain_level=", setup_relax_domain_level);
+
+static void set_domain_attribute(struct sched_domain *sd,
+				 struct sched_domain_attr *attr)
+{
+	int request;
+
+	if (!attr || attr->relax_domain_level < 0) {
+		if (default_relax_domain_level < 0)
+			return;
+		else
+			request = default_relax_domain_level;
+	} else
+		request = attr->relax_domain_level;
+	if (request < sd->level) {
+		/* turn off idle balance on this domain */
+		sd->flags &= ~(SD_WAKE_IDLE|SD_BALANCE_NEWIDLE);
+	} else {
+		/* turn on idle balance on this domain */
+		sd->flags |= (SD_WAKE_IDLE_FAR|SD_BALANCE_NEWIDLE);
+	}
+}
+
 /*
  * Build sched domains for a given set of cpus and attach the sched domains
  * to the individual cpus
  */
-static int build_sched_domains(const cpumask_t *cpu_map)
+static int __build_sched_domains(const cpumask_t *cpu_map,
+				 struct sched_domain_attr *attr)
 {
 	int i;
 	struct root_domain *rd;
@@ -6887,6 +6919,7 @@ static int build_sched_domains(const cpumask_t *cpu_map)
 				SD_NODES_PER_DOMAIN*cpus_weight(*nodemask)) {
 			sd = &per_cpu(allnodes_domains, i);
 			SD_INIT(sd, ALLNODES);
+			set_domain_attribute(sd, attr);
 			sd->span = *cpu_map;
 			cpu_to_allnodes_group(i, cpu_map, &sd->groups, tmpmask);
 			p = sd;
@@ -6896,6 +6929,7 @@ static int build_sched_domains(const cpumask_t *cpu_map)
 
 		sd = &per_cpu(node_domains, i);
 		SD_INIT(sd, NODE);
+		set_domain_attribute(sd, attr);
 		sched_domain_node_span(cpu_to_node(i), &sd->span);
 		sd->parent = p;
 		if (p)
@@ -6906,6 +6940,7 @@ static int build_sched_domains(const cpumask_t *cpu_map)
 		p = sd;
 		sd = &per_cpu(phys_domains, i);
 		SD_INIT(sd, CPU);
+		set_domain_attribute(sd, attr);
 		sd->span = *nodemask;
 		sd->parent = p;
 		if (p)
@@ -6916,6 +6951,7 @@ static int build_sched_domains(const cpumask_t *cpu_map)
 		p = sd;
 		sd = &per_cpu(core_domains, i);
 		SD_INIT(sd, MC);
+		set_domain_attribute(sd, attr);
 		sd->span = cpu_coregroup_map(i);
 		cpus_and(sd->span, sd->span, *cpu_map);
 		sd->parent = p;
@@ -6927,6 +6963,7 @@ static int build_sched_domains(const cpumask_t *cpu_map)
 		p = sd;
 		sd = &per_cpu(cpu_domains, i);
 		SD_INIT(sd, SIBLING);
+		set_domain_attribute(sd, attr);
 		sd->span = per_cpu(cpu_sibling_map, i);
 		cpus_and(sd->span, sd->span, *cpu_map);
 		sd->parent = p;
@@ -7124,8 +7161,15 @@ error:
 #endif
 }
 
+static int build_sched_domains(const cpumask_t *cpu_map)
+{
+	return __build_sched_domains(cpu_map, NULL);
+}
+
 static cpumask_t *doms_cur;	/* current sched domains */
 static int ndoms_cur;		/* number of sched domains in 'doms_cur' */
+static struct sched_domain_attr *dattr_cur;	/* attribues of custom domains
+						   in 'doms_cur' */
 
 /*
  * Special case: If a kmalloc of a doms_cur partition (array of
@@ -7153,6 +7197,7 @@ static int arch_init_sched_domains(const cpumask_t *cpu_map)
 	if (!doms_cur)
 		doms_cur = &fallback_doms;
 	cpus_andnot(*doms_cur, *cpu_map, cpu_isolated_map);
+	dattr_cur = NULL;
 	err = build_sched_domains(doms_cur);
 	register_sched_domain_sysctl();
 
@@ -7182,6 +7227,22 @@ static void detach_destroy_domains(const cpumask_t *cpu_map)
 	arch_destroy_sched_domains(cpu_map, &tmpmask);
 }
 
+/* handle null as "default" */
+static int dattrs_equal(struct sched_domain_attr *cur, int idx_cur,
+			struct sched_domain_attr *new, int idx_new)
+{
+	struct sched_domain_attr tmp;
+
+	/* fast path */
+	if (!new && !cur)
+		return 1;
+
+	tmp = SD_ATTR_INIT;
+	return !memcmp(cur ? (cur + idx_cur) : &tmp,
+			new ? (new + idx_new) : &tmp,
+			sizeof(struct sched_domain_attr));
+}
+
 /*
  * Partition sched domains as specified by the 'ndoms_new'
  * cpumasks in the array doms_new[] of cpumasks. This compares
@@ -7203,7 +7264,8 @@ static void detach_destroy_domains(const cpumask_t *cpu_map)
  *
  * Call with hotplug lock held
  */
-void partition_sched_domains(int ndoms_new, cpumask_t *doms_new)
+void partition_sched_domains(int ndoms_new, cpumask_t *doms_new,
+			     struct sched_domain_attr *dattr_new)
 {
 	int i, j;
 
@@ -7216,12 +7278,14 @@ void partition_sched_domains(int ndoms_new, cpumask_t *doms_new)
 		ndoms_new = 1;
 		doms_new = &fallback_doms;
 		cpus_andnot(doms_new[0], cpu_online_map, cpu_isolated_map);
+		dattr_new = NULL;
 	}
 
 	/* Destroy deleted domains */
 	for (i = 0; i < ndoms_cur; i++) {
 		for (j = 0; j < ndoms_new; j++) {
-			if (cpus_equal(doms_cur[i], doms_new[j]))
+			if (cpus_equal(doms_cur[i], doms_new[j])
+			    && dattrs_equal(dattr_cur, i, dattr_new, j))
 				goto match1;
 		}
 		/* no match - a current sched domain not in new doms_new[] */
@@ -7233,11 +7297,13 @@ match1:
 	/* Build new domains */
 	for (i = 0; i < ndoms_new; i++) {
 		for (j = 0; j < ndoms_cur; j++) {
-			if (cpus_equal(doms_new[i], doms_cur[j]))
+			if (cpus_equal(doms_new[i], doms_cur[j])
+			    && dattrs_equal(dattr_new, i, dattr_cur, j))
 				goto match2;
 		}
 		/* no match - add a new doms_new */
-		build_sched_domains(doms_new + i);
+		__build_sched_domains(doms_new + i,
+					dattr_new ? dattr_new + i : NULL);
 match2:
 		;
 	}
@@ -7245,7 +7311,9 @@ match2:
 	/* Remember the new sched domains */
 	if (doms_cur != &fallback_doms)
 		kfree(doms_cur);
+	kfree(dattr_cur);	/* kfree(NULL) is safe */
 	doms_cur = doms_new;
+	dattr_cur = dattr_new;
 	ndoms_cur = ndoms_new;
 
 	register_sched_domain_sysctl();
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index de4250c53a1..b43748efaa7 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -940,7 +940,9 @@ static int wake_idle(int cpu, struct task_struct *p)
 		return cpu;
 
 	for_each_domain(cpu, sd) {
-		if (sd->flags & SD_WAKE_IDLE) {
+		if ((sd->flags & SD_WAKE_IDLE)
+		    || ((sd->flags & SD_WAKE_IDLE_FAR)
+			&& !task_hot(p, task_rq(p)->clock, sd))) {
 			cpus_and(tmp, sd->span, p->cpus_allowed);
 			for_each_cpu_mask(i, tmp) {
 				if (idle_cpu(i)) {