Merge branch 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:

 - MAINTAINERS: Add Mark Rutland as perf submaintainer, Juri Lelli and
   Vincent Guittot as scheduler submaintainers. Add Dietmar Eggemann,
   Steven Rostedt, Ben Segall and Mel Gorman as scheduler reviewers.

   As perf and the scheduler is getting bigger and more complex,
   document the status quo of current responsibilities and interests,
   and spread the review pain^H^H^H^H fun via an increase in the Cc:
   linecount generated by scripts/get_maintainer.pl. :-)

 - Add another series of patches that brings the -rt (PREEMPT_RT) tree
   closer to mainline: split the monolithic CONFIG_PREEMPT dependencies
   into a new CONFIG_PREEMPTION category that will allow the eventual
   introduction of CONFIG_PREEMPT_RT. Still a few more hundred patches
   to go though.

 - Extend the CPU cgroup controller with uclamp.min and uclamp.max to
   allow the finer shaping of CPU bandwidth usage.

 - Micro-optimize energy-aware wake-ups from O(CPUS^2) to O(CPUS).

 - Improve the behavior of high CPU count, high thread count
   applications running under cpu.cfs_quota_us constraints.

 - Improve balancing with SCHED_IDLE (SCHED_BATCH) tasks present.

 - Improve CPU isolation housekeeping CPU allocation NUMA locality.

 - Fix deadline scheduler bandwidth calculations and logic when cpusets
   rebuilds the topology, or when it gets deadline-throttled while it's
   being offlined.

 - Convert the cpuset_mutex to percpu_rwsem, to allow it to be used from
   setscheduler() system calls without creating global serialization.
   Add new synchronization between cpuset topology-changing events and
   the deadline acceptance tests in setscheduler(), which were broken
   before.

 - Rework the active_mm state machine to be less confusing and more
   optimal.

 - Rework (simplify) the pick_next_task() slowpath.

 - Improve load-balancing on AMD EPYC systems.

 - ... and misc cleanups, smaller fixes and improvements - please see
   the Git log for more details.

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (53 commits)
  sched/psi: Correct overly pessimistic size calculation
  sched/fair: Speed-up energy-aware wake-ups
  sched/uclamp: Always use 'enum uclamp_id' for clamp_id values
  sched/uclamp: Update CPU's refcount on TG's clamp changes
  sched/uclamp: Use TG's clamps to restrict TASK's clamps
  sched/uclamp: Propagate system defaults to the root group
  sched/uclamp: Propagate parent clamps
  sched/uclamp: Extend CPU's cgroup controller
  sched/topology: Improve load balancing on AMD EPYC systems
  arch, ia64: Make NUMA select SMP
  sched, perf: MAINTAINERS update, add submaintainers and reviewers
  sched/fair: Use rq_lock/unlock in online_fair_sched_group
  cpufreq: schedutil: fix equation in comment
  sched: Rework pick_next_task() slow-path
  sched: Allow put_prev_task() to drop rq->lock
  sched/fair: Expose newidle_balance()
  sched: Add task_struct pointer to sched_class::set_curr_task
  sched: Rework CPU hotplug task selection
  sched/{rt,deadline}: Fix set_next_task vs pick_next_task
  sched: Fix kerneldoc comment for ia64_set_curr_task
  ...

2 files changed, 126 insertions, 39 deletions

diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 8be1da1ebd9a..a7ce73a2c401 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -1891,7 +1891,7 @@ static int cgroup_reconfigure(struct fs_context *fc)
  */
 static bool use_task_css_set_links __read_mostly;
 
-static void cgroup_enable_task_cg_lists(void)
+void cgroup_enable_task_cg_lists(void)
 {
 	struct task_struct *p, *g;
 
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 5aa37531ce76..c52bc91f882b 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -45,6 +45,7 @@
 #include <linux/proc_fs.h>
 #include <linux/rcupdate.h>
 #include <linux/sched.h>
+#include <linux/sched/deadline.h>
 #include <linux/sched/mm.h>
 #include <linux/sched/task.h>
 #include <linux/seq_file.h>
@@ -332,7 +333,18 @@ static struct cpuset top_cpuset = {
  * guidelines for accessing subsystem state in kernel/cgroup.c
  */
 
-static DEFINE_MUTEX(cpuset_mutex);
+DEFINE_STATIC_PERCPU_RWSEM(cpuset_rwsem);
+
+void cpuset_read_lock(void)
+{
+	percpu_down_read(&cpuset_rwsem);
+}
+
+void cpuset_read_unlock(void)
+{
+	percpu_up_read(&cpuset_rwsem);
+}
+
 static DEFINE_SPINLOCK(callback_lock);
 
 static struct workqueue_struct *cpuset_migrate_mm_wq;
@@ -894,6 +906,67 @@ done:
 	return ndoms;
 }
 
+static void update_tasks_root_domain(struct cpuset *cs)
+{
+	struct css_task_iter it;
+	struct task_struct *task;
+
+	css_task_iter_start(&cs->css, 0, &it);
+
+	while ((task = css_task_iter_next(&it)))
+		dl_add_task_root_domain(task);
+
+	css_task_iter_end(&it);
+}
+
+static void rebuild_root_domains(void)
+{
+	struct cpuset *cs = NULL;
+	struct cgroup_subsys_state *pos_css;
+
+	percpu_rwsem_assert_held(&cpuset_rwsem);
+	lockdep_assert_cpus_held();
+	lockdep_assert_held(&sched_domains_mutex);
+
+	cgroup_enable_task_cg_lists();
+
+	rcu_read_lock();
+
+	/*
+	 * Clear default root domain DL accounting, it will be computed again
+	 * if a task belongs to it.
+	 */
+	dl_clear_root_domain(&def_root_domain);
+
+	cpuset_for_each_descendant_pre(cs, pos_css, &top_cpuset) {
+
+		if (cpumask_empty(cs->effective_cpus)) {
+			pos_css = css_rightmost_descendant(pos_css);
+			continue;
+		}
+
+		css_get(&cs->css);
+
+		rcu_read_unlock();
+
+		update_tasks_root_domain(cs);
+
+		rcu_read_lock();
+		css_put(&cs->css);
+	}
+	rcu_read_unlock();
+}
+
+static void
+partition_and_rebuild_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
+				    struct sched_domain_attr *dattr_new)
+{
+	mutex_lock(&sched_domains_mutex);
+	partition_sched_domains_locked(ndoms_new, doms_new, dattr_new);
+	rebuild_root_domains();
+	mutex_unlock(&sched_domains_mutex);
+}
+
 /*
  * Rebuild scheduler domains.
  *
@@ -911,8 +984,8 @@ static void rebuild_sched_domains_locked(void)
 	cpumask_var_t *doms;
 	int ndoms;
 
-	lockdep_assert_held(&cpuset_mutex);
-	get_online_cpus();
+	lockdep_assert_cpus_held();
+	percpu_rwsem_assert_held(&cpuset_rwsem);
 
 	/*
 	 * We have raced with CPU hotplug. Don't do anything to avoid
@@ -921,19 +994,17 @@ static void rebuild_sched_domains_locked(void)
 	 */
 	if (!top_cpuset.nr_subparts_cpus &&
 	    !cpumask_equal(top_cpuset.effective_cpus, cpu_active_mask))
-		goto out;
+		return;
 
 	if (top_cpuset.nr_subparts_cpus &&
 	   !cpumask_subset(top_cpuset.effective_cpus, cpu_active_mask))
-		goto out;
+		return;
 
 	/* Generate domain masks and attrs */
 	ndoms = generate_sched_domains(&doms, &attr);
 
 	/* Have scheduler rebuild the domains */
-	partition_sched_domains(ndoms, doms, attr);
-out:
-	put_online_cpus();
+	partition_and_rebuild_sched_domains(ndoms, doms, attr);
 }
 #else /* !CONFIG_SMP */
 static void rebuild_sched_domains_locked(void)
@@ -943,9 +1014,11 @@ static void rebuild_sched_domains_locked(void)
 
 void rebuild_sched_domains(void)
 {
-	mutex_lock(&cpuset_mutex);
+	get_online_cpus();
+	percpu_down_write(&cpuset_rwsem);
 	rebuild_sched_domains_locked();
-	mutex_unlock(&cpuset_mutex);
+	percpu_up_write(&cpuset_rwsem);
+	put_online_cpus();
 }
 
 /**
@@ -1051,7 +1124,7 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd,
 	int deleting;	/* Moving cpus from subparts_cpus to effective_cpus */
 	bool part_error = false;	/* Partition error? */
 
-	lockdep_assert_held(&cpuset_mutex);
+	percpu_rwsem_assert_held(&cpuset_rwsem);
 
 	/*
 	 * The parent must be a partition root.
@@ -2039,7 +2112,7 @@ static int cpuset_can_attach(struct cgroup_taskset *tset)
 	cpuset_attach_old_cs = task_cs(cgroup_taskset_first(tset, &css));
 	cs = css_cs(css);
 
-	mutex_lock(&cpuset_mutex);
+	percpu_down_write(&cpuset_rwsem);
 
 	/* allow moving tasks into an empty cpuset if on default hierarchy */
 	ret = -ENOSPC;
@@ -2063,7 +2136,7 @@ static int cpuset_can_attach(struct cgroup_taskset *tset)
 	cs->attach_in_progress++;
 	ret = 0;
 out_unlock:
-	mutex_unlock(&cpuset_mutex);
+	percpu_up_write(&cpuset_rwsem);
 	return ret;
 }
 
@@ -2073,9 +2146,9 @@ static void cpuset_cancel_attach(struct cgroup_taskset *tset)
 
 	cgroup_taskset_first(tset, &css);
 
-	mutex_lock(&cpuset_mutex);
+	percpu_down_write(&cpuset_rwsem);
 	css_cs(css)->attach_in_progress--;
-	mutex_unlock(&cpuset_mutex);
+	percpu_up_write(&cpuset_rwsem);
 }
 
 /*
@@ -2098,7 +2171,7 @@ static void cpuset_attach(struct cgroup_taskset *tset)
 	cgroup_taskset_first(tset, &css);
 	cs = css_cs(css);
 
-	mutex_lock(&cpuset_mutex);
+	percpu_down_write(&cpuset_rwsem);
 
 	/* prepare for attach */
 	if (cs == &top_cpuset)
@@ -2152,7 +2225,7 @@ static void cpuset_attach(struct cgroup_taskset *tset)
 	if (!cs->attach_in_progress)
 		wake_up(&cpuset_attach_wq);
 
-	mutex_unlock(&cpuset_mutex);
+	percpu_up_write(&cpuset_rwsem);
 }
 
 /* The various types of files and directories in a cpuset file system */
@@ -2183,7 +2256,8 @@ static int cpuset_write_u64(struct cgroup_subsys_state *css, struct cftype *cft,
 	cpuset_filetype_t type = cft->private;
 	int retval = 0;
 
-	mutex_lock(&cpuset_mutex);
+	get_online_cpus();
+	percpu_down_write(&cpuset_rwsem);
 	if (!is_cpuset_online(cs)) {
 		retval = -ENODEV;
 		goto out_unlock;
@@ -2219,7 +2293,8 @@ static int cpuset_write_u64(struct cgroup_subsys_state *css, struct cftype *cft,
 		break;
 	}
 out_unlock:
-	mutex_unlock(&cpuset_mutex);
+	percpu_up_write(&cpuset_rwsem);
+	put_online_cpus();
 	return retval;
 }
 
@@ -2230,7 +2305,8 @@ static int cpuset_write_s64(struct cgroup_subsys_state *css, struct cftype *cft,
 	cpuset_filetype_t type = cft->private;
 	int retval = -ENODEV;
 
-	mutex_lock(&cpuset_mutex);
+	get_online_cpus();
+	percpu_down_write(&cpuset_rwsem);
 	if (!is_cpuset_online(cs))
 		goto out_unlock;
 
@@ -2243,7 +2319,8 @@ static int cpuset_write_s64(struct cgroup_subsys_state *css, struct cftype *cft,
 		break;
 	}
 out_unlock:
-	mutex_unlock(&cpuset_mutex);
+	percpu_up_write(&cpuset_rwsem);
+	put_online_cpus();
 	return retval;
 }
 
@@ -2282,7 +2359,8 @@ static ssize_t cpuset_write_resmask(struct kernfs_open_file *of,
 	kernfs_break_active_protection(of->kn);
 	flush_work(&cpuset_hotplug_work);
 
-	mutex_lock(&cpuset_mutex);
+	get_online_cpus();
+	percpu_down_write(&cpuset_rwsem);
 	if (!is_cpuset_online(cs))
 		goto out_unlock;
 
@@ -2306,7 +2384,8 @@ static ssize_t cpuset_write_resmask(struct kernfs_open_file *of,
 
 	free_cpuset(trialcs);
 out_unlock:
-	mutex_unlock(&cpuset_mutex);
+	percpu_up_write(&cpuset_rwsem);
+	put_online_cpus();
 	kernfs_unbreak_active_protection(of->kn);
 	css_put(&cs->css);
 	flush_workqueue(cpuset_migrate_mm_wq);
@@ -2437,13 +2516,15 @@ static ssize_t sched_partition_write(struct kernfs_open_file *of, char *buf,
 		return -EINVAL;
 
 	css_get(&cs->css);
-	mutex_lock(&cpuset_mutex);
+	get_online_cpus();
+	percpu_down_write(&cpuset_rwsem);
 	if (!is_cpuset_online(cs))
 		goto out_unlock;
 
 	retval = update_prstate(cs, val);
 out_unlock:
-	mutex_unlock(&cpuset_mutex);
+	percpu_up_write(&cpuset_rwsem);
+	put_online_cpus();
 	css_put(&cs->css);
 	return retval ?: nbytes;
 }
@@ -2649,7 +2730,8 @@ static int cpuset_css_online(struct cgroup_subsys_state *css)
 	if (!parent)
 		return 0;
 
-	mutex_lock(&cpuset_mutex);
+	get_online_cpus();
+	percpu_down_write(&cpuset_rwsem);
 
 	set_bit(CS_ONLINE, &cs->flags);
 	if (is_spread_page(parent))
@@ -2700,7 +2782,8 @@ static int cpuset_css_online(struct cgroup_subsys_state *css)
 	cpumask_copy(cs->effective_cpus, parent->cpus_allowed);
 	spin_unlock_irq(&callback_lock);
 out_unlock:
-	mutex_unlock(&cpuset_mutex);
+	percpu_up_write(&cpuset_rwsem);
+	put_online_cpus();
 	return 0;
 }
 
@@ -2719,7 +2802,8 @@ static void cpuset_css_offline(struct cgroup_subsys_state *css)
 {
 	struct cpuset *cs = css_cs(css);
 
-	mutex_lock(&cpuset_mutex);
+	get_online_cpus();
+	percpu_down_write(&cpuset_rwsem);
 
 	if (is_partition_root(cs))
 		update_prstate(cs, 0);
@@ -2738,7 +2822,8 @@ static void cpuset_css_offline(struct cgroup_subsys_state *css)
 	cpuset_dec();
 	clear_bit(CS_ONLINE, &cs->flags);
 
-	mutex_unlock(&cpuset_mutex);
+	percpu_up_write(&cpuset_rwsem);
+	put_online_cpus();
 }
 
 static void cpuset_css_free(struct cgroup_subsys_state *css)
@@ -2750,7 +2835,7 @@ static void cpuset_css_free(struct cgroup_subsys_state *css)
 
 static void cpuset_bind(struct cgroup_subsys_state *root_css)
 {
-	mutex_lock(&cpuset_mutex);
+	percpu_down_write(&cpuset_rwsem);
 	spin_lock_irq(&callback_lock);
 
 	if (is_in_v2_mode()) {
@@ -2763,7 +2848,7 @@ static void cpuset_bind(struct cgroup_subsys_state *root_css)
 	}
 
 	spin_unlock_irq(&callback_lock);
-	mutex_unlock(&cpuset_mutex);
+	percpu_up_write(&cpuset_rwsem);
 }
 
 /*
@@ -2805,6 +2890,8 @@ struct cgroup_subsys cpuset_cgrp_subsys = {
 
 int __init cpuset_init(void)
 {
+	BUG_ON(percpu_init_rwsem(&cpuset_rwsem));
+
 	BUG_ON(!alloc_cpumask_var(&top_cpuset.cpus_allowed, GFP_KERNEL));
 	BUG_ON(!alloc_cpumask_var(&top_cpuset.effective_cpus, GFP_KERNEL));
 	BUG_ON(!zalloc_cpumask_var(&top_cpuset.subparts_cpus, GFP_KERNEL));
@@ -2876,7 +2963,7 @@ hotplug_update_tasks_legacy(struct cpuset *cs,
 	is_empty = cpumask_empty(cs->cpus_allowed) ||
 		   nodes_empty(cs->mems_allowed);
 
-	mutex_unlock(&cpuset_mutex);
+	percpu_up_write(&cpuset_rwsem);
 
 	/*
 	 * Move tasks to the nearest ancestor with execution resources,
@@ -2886,7 +2973,7 @@ hotplug_update_tasks_legacy(struct cpuset *cs,
 	if (is_empty)
 		remove_tasks_in_empty_cpuset(cs);
 
-	mutex_lock(&cpuset_mutex);
+	percpu_down_write(&cpuset_rwsem);
 }
 
 static void
@@ -2936,14 +3023,14 @@ static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp)
 retry:
 	wait_event(cpuset_attach_wq, cs->attach_in_progress == 0);
 
-	mutex_lock(&cpuset_mutex);
+	percpu_down_write(&cpuset_rwsem);
 
 	/*
 	 * We have raced with task attaching. We wait until attaching
 	 * is finished, so we won't attach a task to an empty cpuset.
 	 */
 	if (cs->attach_in_progress) {
-		mutex_unlock(&cpuset_mutex);
+		percpu_up_write(&cpuset_rwsem);
 		goto retry;
 	}
 
@@ -3011,7 +3098,7 @@ update_tasks:
 		hotplug_update_tasks_legacy(cs, &new_cpus, &new_mems,
 					    cpus_updated, mems_updated);
 
-	mutex_unlock(&cpuset_mutex);
+	percpu_up_write(&cpuset_rwsem);
 }
 
 /**
@@ -3041,7 +3128,7 @@ static void cpuset_hotplug_workfn(struct work_struct *work)
 	if (on_dfl && !alloc_cpumasks(NULL, &tmp))
 		ptmp = &tmp;
 
-	mutex_lock(&cpuset_mutex);
+	percpu_down_write(&cpuset_rwsem);
 
 	/* fetch the available cpus/mems and find out which changed how */
 	cpumask_copy(&new_cpus, cpu_active_mask);
@@ -3091,7 +3178,7 @@ static void cpuset_hotplug_workfn(struct work_struct *work)
 		update_tasks_nodemask(&top_cpuset);
 	}
 
-	mutex_unlock(&cpuset_mutex);
+	percpu_up_write(&cpuset_rwsem);
 
 	/* if cpus or mems changed, we need to propagate to descendants */
 	if (cpus_updated || mems_updated) {