Merge branch 'for-4.1' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup

Pull cgroup updates from Tejun Heo:
 "Nothing too interesting.  Rik made cpuset cooperate better with
  isolcpus and there are several other cleanup patches"

* 'for-4.1' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup:
  cpuset, isolcpus: document relationship between cpusets & isolcpus
  cpusets, isolcpus: exclude isolcpus from load balancing in cpusets
  sched, isolcpu: make cpu_isolated_map visible outside scheduler
  cpuset: initialize cpuset a bit early
  cgroup: Use kvfree in pidlist_free()
  cgroup: call cgroup_subsys->bind on cgroup subsys initialization

Documentation/cgroups/cpusets.txt

@@ -392,8 +392,10 @@ Put simply, it costs less to balance between two smaller sched domains
 than one big one, but doing so means that overloads in one of the
 two domains won't be load balanced to the other one.
 
-By default, there is one sched domain covering all CPUs, except those
-marked isolated using the kernel boot time "isolcpus=" argument.
+By default, there is one sched domain covering all CPUs, including those
+marked isolated using the kernel boot time "isolcpus=" argument. However,
+the isolated CPUs will not participate in load balancing, and will not
+have tasks running on them unless explicitly assigned.
 
 This default load balancing across all CPUs is not well suited for
 the following two situations:
@@ -465,6 +467,10 @@ such partially load balanced cpusets, as they may be artificially
 constrained to some subset of the CPUs allowed to them, for lack of
 load balancing to the other CPUs.
 
+CPUs in "cpuset.isolcpus" were excluded from load balancing by the
+isolcpus= kernel boot option, and will never be load balanced regardless
+of the value of "cpuset.sched_load_balance" in any cpuset.
+
 1.7.1 sched_load_balance implementation details.
 ------------------------------------------------
 

include/linux/sched.h

@@ -337,6 +337,8 @@ extern asmlinkage void schedule_tail(struct task_struct *prev);
 extern void init_idle(struct task_struct *idle, int cpu);
 extern void init_idle_bootup_task(struct task_struct *idle);
 
+extern cpumask_var_t cpu_isolated_map;
+
 extern int runqueue_is_locked(int cpu);
 
 #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)

init/main.c

@@ -654,8 +654,8 @@ asmlinkage __visible void __init start_kernel(void)
 	page_writeback_init();
 	proc_root_init();
 	nsfs_init();
-	cgroup_init();
 	cpuset_init();
+	cgroup_init();
 	taskstats_init_early();
 	delayacct_init();
 

kernel/cgroup.c

@@ -3806,10 +3806,7 @@ static void *pidlist_allocate(int count)
 
 static void pidlist_free(void *p)
 {
-	if (is_vmalloc_addr(p))
-		vfree(p);
-	else
-		kfree(p);
+	kvfree(p);
 }
 
 /*
@@ -5040,6 +5037,9 @@ int __init cgroup_init(void)
 			WARN_ON(cgroup_add_dfl_cftypes(ss, ss->dfl_cftypes));
 			WARN_ON(cgroup_add_legacy_cftypes(ss, ss->legacy_cftypes));
 		}
+
+		if (ss->bind)
+			ss->bind(init_css_set.subsys[ssid]);
 	}
 
 	cgroup_kobj = kobject_create_and_add("cgroup", fs_kobj);

kernel/cpuset.c

@@ -622,6 +622,7 @@ static int generate_sched_domains(cpumask_var_t **domains,
 	int csn;		/* how many cpuset ptrs in csa so far */
 	int i, j, k;		/* indices for partition finding loops */
 	cpumask_var_t *doms;	/* resulting partition; i.e. sched domains */
+	cpumask_var_t non_isolated_cpus;  /* load balanced CPUs */
 	struct sched_domain_attr *dattr;  /* attributes for custom domains */
 	int ndoms = 0;		/* number of sched domains in result */
 	int nslot;		/* next empty doms[] struct cpumask slot */
@@ -631,6 +632,10 @@ static int generate_sched_domains(cpumask_var_t **domains,
 	dattr = NULL;
 	csa = NULL;
 
+	if (!alloc_cpumask_var(&non_isolated_cpus, GFP_KERNEL))
+		goto done;
+	cpumask_andnot(non_isolated_cpus, cpu_possible_mask, cpu_isolated_map);
+
 	/* Special case for the 99% of systems with one, full, sched domain */
 	if (is_sched_load_balance(&top_cpuset)) {
 		ndoms = 1;
@@ -643,7 +648,8 @@ static int generate_sched_domains(cpumask_var_t **domains,
 			*dattr = SD_ATTR_INIT;
 			update_domain_attr_tree(dattr, &top_cpuset);
 		}
-		cpumask_copy(doms[0], top_cpuset.effective_cpus);
+		cpumask_and(doms[0], top_cpuset.effective_cpus,
+				     non_isolated_cpus);
 
 		goto done;
 	}
@@ -666,7 +672,8 @@ static int generate_sched_domains(cpumask_var_t **domains,
 		 * the corresponding sched domain.
 		 */
 		if (!cpumask_empty(cp->cpus_allowed) &&
-		    !is_sched_load_balance(cp))
+		    !(is_sched_load_balance(cp) &&
+		      cpumask_intersects(cp->cpus_allowed, non_isolated_cpus)))
 			continue;
 
 		if (is_sched_load_balance(cp))
@@ -748,6 +755,7 @@ restart:
 
 			if (apn == b->pn) {
 				cpumask_or(dp, dp, b->effective_cpus);
+				cpumask_and(dp, dp, non_isolated_cpus);
 				if (dattr)
 					update_domain_attr_tree(dattr + nslot, b);
 
@@ -760,6 +768,7 @@ restart:
 	BUG_ON(nslot != ndoms);
 
 done:
+	free_cpumask_var(non_isolated_cpus);
 	kfree(csa);
 
 	/*

kernel/sched/core.c

@@ -306,6 +306,9 @@ __read_mostly int scheduler_running;
  */
 int sysctl_sched_rt_runtime = 950000;
 
+/* cpus with isolated domains */
+cpumask_var_t cpu_isolated_map;
+
 /*
  * this_rq_lock - lock this runqueue and disable interrupts.
  */
@@ -5811,9 +5814,6 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu)
 	update_top_cache_domain(cpu);
 }
 
-/* cpus with isolated domains */
-static cpumask_var_t cpu_isolated_map;
-
 /* Setup the mask of cpus configured for isolated domains */
 static int __init isolated_cpu_setup(char *str)
 {