cgroup/cpuset: Move housekeeping_update()/rebuild_sched_domains() together

With the latest changes in sched/isolation.c, rebuild_sched_domains*()
requires the HK_TYPE_DOMAIN housekeeping cpumask to be properly
updated first, if needed, before the sched domains can be
rebuilt. So the two naturally fit together. Do that by creating a new
update_hk_sched_domains() helper to house both actions.

The name of the isolated_cpus_updating flag to control the
call to housekeeping_update() is now outdated. So change it to
update_housekeeping to better reflect its purpose. Also move the call
to update_hk_sched_domains() to the end of cpuset and hotplug operations
before releasing the cpuset_mutex.

Signed-off-by: Waiman Long <[email protected]>
Signed-off-by: Tejun Heo <[email protected]>

Author: Waiman-Long

kernel/cgroup/cpuset.c

@@ -130,10 +130,9 @@ static cpumask_var_t	subpartitions_cpus;	/* RWCS */
 static cpumask_var_t	isolated_cpus;		/* CSCB */
 
 /*
- * Set if isolated_cpus is being updated in the current cpuset_mutex
- * critical section.
+ * Set if housekeeping cpumasks are to be updated.
  */
-static bool		isolated_cpus_updating;	/* RWCS */
+static bool		update_housekeeping;	/* RWCS */
 
 /*
  * A flag to force sched domain rebuild at the end of an operation.
@@ -1189,7 +1188,7 @@ static void isolated_cpus_update(int old_prs, int new_prs, struct cpumask *xcpus
 			return;
 		cpumask_andnot(isolated_cpus, isolated_cpus, xcpus);
 	}
-	isolated_cpus_updating = true;
+	update_housekeeping = true;
 }
 
 /*
@@ -1307,22 +1306,22 @@ static bool prstate_housekeeping_conflict(int prstate, struct cpumask *new_cpus)
 }
 
 /*
- * update_isolation_cpumasks - Update external isolation related CPU masks
+ * update_hk_sched_domains - Update HK cpumasks & rebuild sched domains
  *
- * The following external CPU masks will be updated if necessary:
- * - workqueue unbound cpumask
+ * Update housekeeping cpumasks and rebuild sched domains if necessary.
+ * This should be called at the end of cpuset or hotplug actions.
  */
-static void update_isolation_cpumasks(void)
+static void update_hk_sched_domains(void)
 {
-	int ret;
-
-	if (!isolated_cpus_updating)
-		return;
-
-	ret = housekeeping_update(isolated_cpus);
-	WARN_ON_ONCE(ret < 0);
-
-	isolated_cpus_updating = false;
+	if (update_housekeeping) {
+		/* Updating HK cpumasks implies rebuild sched domains */
+		WARN_ON_ONCE(housekeeping_update(isolated_cpus));
+		update_housekeeping = false;
+		force_sd_rebuild = true;
+	}
+	/* force_sd_rebuild will be cleared in rebuild_sched_domains_locked() */
+	if (force_sd_rebuild)
+		rebuild_sched_domains_locked();
 }
 
 /**
@@ -1473,7 +1472,6 @@ static int remote_partition_enable(struct cpuset *cs, int new_prs,
 	cs->remote_partition = true;
 	cpumask_copy(cs->effective_xcpus, tmp->new_cpus);
 	spin_unlock_irq(&callback_lock);
-	update_isolation_cpumasks();
 	cpuset_force_rebuild();
 	cs->prs_err = 0;
 
@@ -1518,7 +1516,6 @@ static void remote_partition_disable(struct cpuset *cs, struct tmpmasks *tmp)
 	compute_excpus(cs, cs->effective_xcpus);
 	reset_partition_data(cs);
 	spin_unlock_irq(&callback_lock);
-	update_isolation_cpumasks();
 	cpuset_force_rebuild();
 
 	/*
@@ -1589,7 +1586,6 @@ static void remote_cpus_update(struct cpuset *cs, struct cpumask *xcpus,
 	if (xcpus)
 		cpumask_copy(cs->exclusive_cpus, xcpus);
 	spin_unlock_irq(&callback_lock);
-	update_isolation_cpumasks();
 	if (adding || deleting)
 		cpuset_force_rebuild();
 
@@ -1933,7 +1929,6 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd,
 		partition_xcpus_add(new_prs, parent, tmp->delmask);
 
 	spin_unlock_irq(&callback_lock);
-	update_isolation_cpumasks();
 
 	if ((old_prs != new_prs) && (cmd == partcmd_update))
 		update_partition_exclusive_flag(cs, new_prs);
@@ -2901,7 +2896,6 @@ static int update_prstate(struct cpuset *cs, int new_prs)
 	else if (isolcpus_updated)
 		isolated_cpus_update(old_prs, new_prs, cs->effective_xcpus);
 	spin_unlock_irq(&callback_lock);
-	update_isolation_cpumasks();
 
 	/* Force update if switching back to member & update effective_xcpus */
 	update_cpumasks_hier(cs, &tmpmask, !new_prs);
@@ -3191,9 +3185,8 @@ ssize_t cpuset_write_resmask(struct kernfs_open_file *of,
 	}
 
 	free_cpuset(trialcs);
-	if (force_sd_rebuild)
-		rebuild_sched_domains_locked();
 out_unlock:
+	update_hk_sched_domains();
 	cpuset_full_unlock();
 	if (of_cft(of)->private == FILE_MEMLIST)
 		schedule_flush_migrate_mm();
@@ -3301,6 +3294,7 @@ static ssize_t cpuset_partition_write(struct kernfs_open_file *of, char *buf,
 	cpuset_full_lock();
 	if (is_cpuset_online(cs))
 		retval = update_prstate(cs, val);
+	update_hk_sched_domains();
 	cpuset_full_unlock();
 	return retval ?: nbytes;
 }
@@ -3475,6 +3469,7 @@ static void cpuset_css_killed(struct cgroup_subsys_state *css)
 	/* Reset valid partition back to member */
 	if (is_partition_valid(cs))
 		update_prstate(cs, PRS_MEMBER);
+	update_hk_sched_domains();
 	cpuset_full_unlock();
 }
 
@@ -3882,10 +3877,12 @@ static void cpuset_handle_hotplug(void)
 		rcu_read_unlock();
 	}
 
-	/* rebuild sched domains if necessary */
-	if (force_sd_rebuild)
-		rebuild_sched_domains_cpuslocked();
 
+	if (update_housekeeping || force_sd_rebuild) {
+		mutex_lock(&cpuset_mutex);
+		update_hk_sched_domains();
+		mutex_unlock(&cpuset_mutex);
+	}
 	free_tmpmasks(ptmp);
 }