[PATCH-next v3 04/11] cgroup/cpuset: Minor fixes to prstate_housekeeping_conflict()

[Waiman Long]

Commit 9527ff78a413 ("cgroup/cpuset: Consider all the exclusive CPUs when
doing housekeeping check") changes the way prstate_housekeeping_conflict()
is being used by considering all the exclusive xcpus to be owned by the
partition when doing housekeeping check. However there are two minor
issues reported by sashiko with that patch:

 1) In partition_cpus_change(), prstate_housekeeping_conflict() can
 be called with an invalid partition root. In that case, there are
 no isolated CPUs that are going to be returned back to the system to
 become housekeeping CPUs, so the calculation of the del_cpus cpumask
 is meaningless.

 2) The checking of del_cpus in prstate_housekeeping_conflict() to see
 if it can contain an active housekeeping CPU that can be returned to the
 system ignores the fact that an active CPU not in HK_TYPE_DOMAIN_BOOT HK
 cpumask will not become an active housekeeping CPU when it is released
 by an isolated partition.

Update the existing code to handle these two issues properly to make
prstate_housekeeping_conflict() produce more accurate result.

Fixes: 9527ff78a413 ("cgroup/cpuset: Consider all the exclusive CPUs when doing housekeeping check")
Signed-off-by: Waiman Long <longman@xxxxxxxxxx>
---
 kernel/cgroup/cpuset.c | 45 +++++++++++++++++++++++++++++-------------
 1 file changed, 31 insertions(+), 14 deletions(-)

diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 37bc79d0c647..57e5334eb919 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -1446,6 +1446,9 @@ static bool prstate_housekeeping_conflict(int new_prs, int parent_prs,
 	    !cpumask_subset(new_cpus, housekeeping_cpumask(HK_TYPE_DOMAIN_BOOT)))
 		return true;
 
+	if (del_cpus && cpumask_empty(del_cpus))
+		del_cpus = NULL;
+
 	/*
 	 * Exit 2nd check early and return false if
 	 * 1) there is no boot time isolated nohz_full CPU
@@ -1454,8 +1457,7 @@ static bool prstate_housekeeping_conflict(int new_prs, int parent_prs,
 	 *    be returned back to the parent.
 	 */
 	if (!housekeeping_enabled(HK_TYPE_KERNEL_NOISE) ||
-	    (new_prs == parent_prs) ||
-	    ((new_prs == PRS_ROOT) && (!del_cpus || cpumask_empty(del_cpus))))
+	    (new_prs == parent_prs) || (!del_cpus && (new_prs == PRS_ROOT)))
 		return false;
 
 	/*
@@ -1466,20 +1468,29 @@ static bool prstate_housekeeping_conflict(int new_prs, int parent_prs,
 	if (parent_prs == PRS_ISOLATED)
 		swap(new_cpus, del_cpus);
 
-	if (del_cpus &&
-	   (cpumask_first_and_and(del_cpus, housekeeping_cpumask(HK_TYPE_KERNEL_NOISE),
-				   cpu_active_mask) < nr_cpu_ids))
-		return false;
-
 	if (!alloc_cpumask_var(&full_hk_cpus, GFP_KERNEL))
 		return true;
 
+	/*
+	 * Check if del_cpus may contain a CPU that can become an active
+	 * housekeeping CPU again.
+	 */
+	if (del_cpus) {
+		cpumask_and(full_hk_cpus, housekeeping_cpumask(HK_TYPE_KERNEL_NOISE),
+			    housekeeping_cpumask(HK_TYPE_DOMAIN_BOOT));
+		if (cpumask_first_and_and(del_cpus, full_hk_cpus,
+					  cpu_active_mask) < nr_cpu_ids) {
+			res = false;
+			goto out;
+		}
+	}
+
 	cpumask_and(full_hk_cpus, housekeeping_cpumask(HK_TYPE_KERNEL_NOISE),
 		    housekeeping_cpumask(HK_TYPE_DOMAIN));
 	cpumask_andnot(full_hk_cpus, full_hk_cpus, isolated_cpus);
 	cpumask_and(full_hk_cpus, full_hk_cpus, cpu_active_mask);
 	res = !cpumask_weight_andnot(full_hk_cpus, new_cpus);
-
+out:
 	free_cpumask_var(full_hk_cpus);
 	return res;
 }
@@ -2486,23 +2497,29 @@ static void partition_cpus_change(struct cpuset *cs, struct cpuset *trialcs,
 				  struct tmpmasks *tmp)
 {
 	enum prs_errcode prs_err;
+	int parent_prs = is_remote_partition(cs)
+		       ? PRS_ROOT : parent_cs(cs)->partition_root_state;
 
 	if (cs_is_member(cs))
 		return;
 
 	prs_err = validate_partition(cs, trialcs);
-	if (!prs_err && !cpumask_empty(trialcs->effective_xcpus)) {
+	if (!prs_err && (parent_prs > 0) &&
+	    !cpumask_empty(trialcs->effective_xcpus)) {
 		int prs = cs->partition_root_state;
-		int parent_prs = is_remote_partition(cs)
-			       ? PRS_ROOT : parent_cs(cs)->partition_root_state;
+
 		/*
 		 * Check for housekeeping conflict by passing the whole
 		 * effective_xcpus as well as those CPUs that are to be
 		 * removed from cs as delmask.
 		 */
-		cpumask_andnot(tmp->delmask, cs->effective_xcpus, trialcs->effective_xcpus);
-		if (parent_prs > 0 &&
-		    prstate_housekeeping_conflict(prs, parent_prs,
+		if (prs > 0)
+			cpumask_andnot(tmp->delmask, cs->effective_xcpus,
+				       trialcs->effective_xcpus);
+		else
+			cpumask_clear(tmp->delmask);
+
+		if (prstate_housekeeping_conflict(prs, parent_prs,
 						  trialcs->effective_xcpus, tmp->delmask))
 			prs_err = PERR_HKEEPING;
 	}
-- 
2.56.0