[PATCH v8 6/7] cgroup/cpuset: Fail if isolated and nohz_full don't leave any housekeeping

[Gabriele Monaco <gmonaco@redhat.com>]

Currently the user can set up isolated cpus via cpuset and nohz_full in
such a way that leaves no housekeeping CPU (i.e. no CPU that is neither
domain isolated nor nohz full). This can be a problem for other
subsystems (e.g. the timer wheel imgration).

Prevent this configuration by blocking any assignation that would cause
the union of domain isolated cpus and nohz_full to covers all CPUs.

Signed-off-by: Gabriele Monaco <gmonaco@redhat.com>
---
 kernel/cgroup/cpuset.c | 56 ++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 56 insertions(+)

diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 6e3f44ffaa219..a946d85ce954a 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -1275,6 +1275,19 @@ static void isolated_cpus_update(int old_prs, int new_prs, struct cpumask *xcpus
 		cpumask_andnot(isolated_cpus, isolated_cpus, xcpus);
 }
 
+/*
+ * isolated_cpus_should_update - Returns if the isolated_cpus mask needs update
+ * @prs: new or old partition_root_state
+ * @parent: parent cpuset
+ * Return: true if isolated_cpus needs modification, false otherwise
+ */
+static bool isolated_cpus_should_update(int prs, struct cpuset *parent)
+{
+	if (!parent)
+		parent = &top_cpuset;
+	return prs != parent->partition_root_state;
+}
+
 /*
  * partition_xcpus_add - Add new exclusive CPUs to partition
  * @new_prs: new partition_root_state
@@ -1339,6 +1352,35 @@ static bool partition_xcpus_del(int old_prs, struct cpuset *parent,
 	return isolcpus_updated;
 }
 
+/*
+ * isolcpus_nohz_conflict - check for isolated & nohz_full conflicts
+ * @new_cpus: cpu mask for cpus that are going to be isolated
+ * Return: true if there is conflict, false otherwise
+ *
+ * If nohz_full is enabled and we have isolated CPUs, their combination must
+ * still leave housekeeping CPUs.
+ */
+static bool isolcpus_nohz_conflict(struct cpumask *new_cpus)
+{
+	cpumask_var_t full_hk_cpus;
+	int res = false;
+
+	if (!housekeeping_enabled(HK_TYPE_KERNEL_NOISE))
+		return false;
+
+	if (!alloc_cpumask_var(&full_hk_cpus, GFP_KERNEL))
+		return true;
+
+	cpumask_and(full_hk_cpus, housekeeping_cpumask(HK_TYPE_KERNEL_NOISE),
+		    housekeeping_cpumask(HK_TYPE_DOMAIN));
+	cpumask_and(full_hk_cpus, full_hk_cpus, cpu_online_mask);
+	if (!cpumask_weight_andnot(full_hk_cpus, new_cpus))
+		res = true;
+
+	free_cpumask_var(full_hk_cpus);
+	return res;
+}
+
 static void update_exclusion_cpumasks(bool isolcpus_updated)
 {
 	int ret;
@@ -1464,6 +1506,9 @@ static int remote_partition_enable(struct cpuset *cs, int new_prs,
 	if (!cpumask_intersects(tmp->new_cpus, cpu_active_mask) ||
 	    cpumask_subset(top_cpuset.effective_cpus, tmp->new_cpus))
 		return PERR_INVCPUS;
+	if (isolated_cpus_should_update(new_prs, NULL) &&
+	    isolcpus_nohz_conflict(tmp->new_cpus))
+		return PERR_HKEEPING;
 
 	spin_lock_irq(&callback_lock);
 	isolcpus_updated = partition_xcpus_add(new_prs, NULL, tmp->new_cpus);
@@ -1563,6 +1608,9 @@ static void remote_cpus_update(struct cpuset *cs, struct cpumask *xcpus,
 		else if (cpumask_intersects(tmp->addmask, subpartitions_cpus) ||
 			 cpumask_subset(top_cpuset.effective_cpus, tmp->addmask))
 			cs->prs_err = PERR_NOCPUS;
+		else if (isolated_cpus_should_update(prs, NULL) &&
+			 isolcpus_nohz_conflict(tmp->addmask))
+			cs->prs_err = PERR_HKEEPING;
 		if (cs->prs_err)
 			goto invalidate;
 	}
@@ -1914,6 +1962,12 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd,
 			return err;
 	}
 
+	if (deleting && isolated_cpus_should_update(new_prs, parent) &&
+	    isolcpus_nohz_conflict(tmp->delmask)) {
+		cs->prs_err = PERR_HKEEPING;
+		return PERR_HKEEPING;
+	}
+
 	/*
 	 * Change the parent's effective_cpus & effective_xcpus (top cpuset
 	 * only).
@@ -2934,6 +2988,8 @@ static int update_prstate(struct cpuset *cs, int new_prs)
 		 * Need to update isolated_cpus.
 		 */
 		isolcpus_updated = true;
+		if (isolcpus_nohz_conflict(cs->effective_xcpus))
+			err = PERR_HKEEPING;
 	} else {
 		/*
 		 * Switching back to member is always allowed even if it
-- 
2.50.1