diff mbox series

[PATCH-cgroup,v2] cgroup/cpuset: Enable invalid to valid local partition transition

Message ID 20231003144420.2895515-1-longman@redhat.com (mailing list archive)
State Accepted
Commit 46c521bac592251229acdd2cd67976a7b1f88bed
Headers show
Series [PATCH-cgroup,v2] cgroup/cpuset: Enable invalid to valid local partition transition | expand

Commit Message

Waiman Long Oct. 3, 2023, 2:44 p.m. UTC
When a local partition becomes invalid, it won't transition back to
valid partition automatically if a proper "cpuset.cpus.exclusive" or
"cpuset.cpus" change is made. Instead, system administrators have to
explicitly echo "root" or "isolated" into the "cpuset.cpus.partition"
file at the partition root.

This patch now enables the automatic transition of an invalid local
partition back to valid when there is a proper "cpuset.cpus.exclusive"
or "cpuset.cpus" change.

Automatic transition of an invalid remote partition to a valid one,
however, is not covered by this patch. They still need an explicit
write to "cpuset.cpus.partition" to become valid again.

The test_cpuset_prs.sh test script is updated to add new test cases to
test this automatic state transition.

Reported-by: Pierre Gondois <pierre.gondois@arm.com>
Link: https://lore.kernel.org/lkml/9777f0d2-2fdf-41cb-bd01-19c52939ef42@arm.com
Signed-off-by: Waiman Long <longman@redhat.com>
---
 kernel/cgroup/cpuset.c                        | 79 +++++++++++--------
 .../selftests/cgroup/test_cpuset_prs.sh       | 21 +++--
 2 files changed, 62 insertions(+), 38 deletions(-)

 v2: Add documentation about the new X<l> designator in
 test_cpuset_prs.sh.

Comments

Tejun Heo Oct. 4, 2023, 6:55 p.m. UTC | #1
On Tue, Oct 03, 2023 at 10:44:20AM -0400, Waiman Long wrote:
> When a local partition becomes invalid, it won't transition back to
> valid partition automatically if a proper "cpuset.cpus.exclusive" or
> "cpuset.cpus" change is made. Instead, system administrators have to
> explicitly echo "root" or "isolated" into the "cpuset.cpus.partition"
> file at the partition root.
> 
> This patch now enables the automatic transition of an invalid local
> partition back to valid when there is a proper "cpuset.cpus.exclusive"
> or "cpuset.cpus" change.
> 
> Automatic transition of an invalid remote partition to a valid one,
> however, is not covered by this patch. They still need an explicit
> write to "cpuset.cpus.partition" to become valid again.
> 
> The test_cpuset_prs.sh test script is updated to add new test cases to
> test this automatic state transition.
> 
> Reported-by: Pierre Gondois <pierre.gondois@arm.com>
> Link: https://lore.kernel.org/lkml/9777f0d2-2fdf-41cb-bd01-19c52939ef42@arm.com
> Signed-off-by: Waiman Long <longman@redhat.com>

Applied to cgroup/for-6.7.

Thanks.
diff mbox series

Patch

diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 15f399153a2e..93facdab513c 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -1806,17 +1806,28 @@  static int update_parent_effective_cpumask(struct cpuset *cs, int cmd,
 		 *
 		 * Compute add/delete mask to/from effective_cpus
 		 *
-		 * addmask = effective_xcpus & ~newmask & parent->effective_xcpus
-		 * delmask = newmask & ~cs->effective_xcpus
-		 *		     & parent->effective_xcpus
+		 * For valid partition:
+		 *   addmask = exclusive_cpus & ~newmask
+		 *			      & parent->effective_xcpus
+		 *   delmask = newmask & ~exclusive_cpus
+		 *		       & parent->effective_xcpus
+		 *
+		 * For invalid partition:
+		 *   delmask = newmask & parent->effective_xcpus
 		 */
-		cpumask_andnot(tmp->addmask, xcpus, newmask);
-		adding = cpumask_and(tmp->addmask, tmp->addmask,
-				     parent->effective_xcpus);
+		if (is_prs_invalid(old_prs)) {
+			adding = false;
+			deleting = cpumask_and(tmp->delmask,
+					newmask, parent->effective_xcpus);
+		} else {
+			cpumask_andnot(tmp->addmask, xcpus, newmask);
+			adding = cpumask_and(tmp->addmask, tmp->addmask,
+					     parent->effective_xcpus);
 
-		cpumask_andnot(tmp->delmask, newmask, xcpus);
-		deleting = cpumask_and(tmp->delmask, tmp->delmask,
-				       parent->effective_xcpus);
+			cpumask_andnot(tmp->delmask, newmask, xcpus);
+			deleting = cpumask_and(tmp->delmask, tmp->delmask,
+					       parent->effective_xcpus);
+		}
 		/*
 		 * Make partition invalid if parent's effective_cpus could
 		 * become empty and there are tasks in the parent.
@@ -1910,9 +1921,11 @@  static int update_parent_effective_cpumask(struct cpuset *cs, int cmd,
 
 	/*
 	 * Transitioning between invalid to valid or vice versa may require
-	 * changing CS_CPU_EXCLUSIVE.
+	 * changing CS_CPU_EXCLUSIVE. In the case of partcmd_update,
+	 * validate_change() has already been successfully called and
+	 * CPU lists in cs haven't been updated yet. So defer it to later.
 	 */
-	if (old_prs != new_prs) {
+	if ((old_prs != new_prs) && (cmd != partcmd_update))  {
 		int err = update_partition_exclusive(cs, new_prs);
 
 		if (err)
@@ -1960,6 +1973,9 @@  static int update_parent_effective_cpumask(struct cpuset *cs, int cmd,
 
 	spin_unlock_irq(&callback_lock);
 
+	if ((old_prs != new_prs) && (cmd == partcmd_update))
+		update_partition_exclusive(cs, new_prs);
+
 	if (adding || deleting) {
 		update_tasks_cpumask(parent, tmp->addmask);
 		update_sibling_cpumasks(parent, cs, tmp);
@@ -2356,8 +2372,9 @@  static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
 	if (alloc_cpumasks(NULL, &tmp))
 		return -ENOMEM;
 
-	if (is_partition_valid(cs)) {
-		if (cpumask_empty(trialcs->effective_xcpus)) {
+	if (old_prs) {
+		if (is_partition_valid(cs) &&
+		    cpumask_empty(trialcs->effective_xcpus)) {
 			invalidate = true;
 			cs->prs_err = PERR_INVCPUS;
 		} else if (prstate_housekeeping_conflict(old_prs, trialcs->effective_xcpus)) {
@@ -2391,13 +2408,16 @@  static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
 		 */
 		invalidate = true;
 		rcu_read_lock();
-		cpuset_for_each_child(cp, css, parent)
+		cpuset_for_each_child(cp, css, parent) {
+			struct cpumask *xcpus = fetch_xcpus(trialcs);
+
 			if (is_partition_valid(cp) &&
-			    cpumask_intersects(trialcs->effective_xcpus, cp->effective_xcpus)) {
+			    cpumask_intersects(xcpus, cp->effective_xcpus)) {
 				rcu_read_unlock();
 				update_parent_effective_cpumask(cp, partcmd_invalidate, NULL, &tmp);
 				rcu_read_lock();
 			}
+		}
 		rcu_read_unlock();
 		retval = 0;
 	}
@@ -2405,18 +2425,24 @@  static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
 	if (retval < 0)
 		goto out_free;
 
-	if (is_partition_valid(cs)) {
+	if (is_partition_valid(cs) ||
+	   (is_partition_invalid(cs) && !invalidate)) {
+		struct cpumask *xcpus = trialcs->effective_xcpus;
+
+		if (cpumask_empty(xcpus) && is_partition_invalid(cs))
+			xcpus = trialcs->cpus_allowed;
+
 		/*
 		 * Call remote_cpus_update() to handle valid remote partition
 		 */
 		if (is_remote_partition(cs))
-			remote_cpus_update(cs, trialcs->effective_xcpus, &tmp);
+			remote_cpus_update(cs, xcpus, &tmp);
 		else if (invalidate)
 			update_parent_effective_cpumask(cs, partcmd_invalidate,
 							NULL, &tmp);
 		else
 			update_parent_effective_cpumask(cs, partcmd_update,
-						trialcs->effective_xcpus, &tmp);
+							xcpus, &tmp);
 	} else if (!cpumask_empty(cs->exclusive_cpus)) {
 		/*
 		 * Use trialcs->effective_cpus as a temp cpumask
@@ -2493,7 +2519,7 @@  static int update_exclusive_cpumask(struct cpuset *cs, struct cpuset *trialcs,
 	if (retval)
 		return retval;
 
-	if (is_partition_valid(cs)) {
+	if (old_prs) {
 		if (cpumask_empty(trialcs->effective_xcpus)) {
 			invalidate = true;
 			cs->prs_err = PERR_INVCPUS;
@@ -2927,19 +2953,10 @@  static int update_prstate(struct cpuset *cs, int new_prs)
 		return 0;
 
 	/*
-	 * For a previously invalid partition root with valid partition root
-	 * parent, treat it as if it is a "member". Otherwise, reject it as
-	 * remote partition cannot currently self-recover from an invalid
-	 * state.
+	 * Treat a previously invalid partition root as if it is a "member".
 	 */
-	if (new_prs && is_prs_invalid(old_prs)) {
-		if (is_partition_valid(parent)) {
-			old_prs = PRS_MEMBER;
-		} else {
-			cs->partition_root_state = -new_prs;
-			return 0;
-		}
-	}
+	if (new_prs && is_prs_invalid(old_prs))
+		old_prs = PRS_MEMBER;
 
 	if (alloc_cpumasks(NULL, &tmpmask))
 		return -ENOMEM;
diff --git a/tools/testing/selftests/cgroup/test_cpuset_prs.sh b/tools/testing/selftests/cgroup/test_cpuset_prs.sh
index 0f4f4a57ae12..a6e9848189d6 100755
--- a/tools/testing/selftests/cgroup/test_cpuset_prs.sh
+++ b/tools/testing/selftests/cgroup/test_cpuset_prs.sh
@@ -220,7 +220,8 @@  test_isolated()
 #      +- B1
 #
 #  P<v> = set cpus.partition (0:member, 1:root, 2:isolated)
-#  C<l> = add cpu-list
+#  C<l> = add cpu-list to cpuset.cpus
+#  X<l> = add cpu-list to cpuset.cpus.exclusive
 #  S<p> = use prefix in subtree_control
 #  T    = put a task into cgroup
 #  O<c>=<v> = Write <v> to CPU online file of <c>
@@ -318,16 +319,19 @@  TEST_MATRIX=(
 	" C0-3:S+ C1-3:S+  C2      .    X2-3   X2-3   T:P2:O2=0 O2=1 0 A1:0-3,A2:1-3,A3:2 A1:P0,A3:P-2"
 
 	# cpus.exclusive.effective clearing test
-	" C0-3:S+ C1-3:S+  C2      .   X2-3:X    .      .      .      0 A1:0-3,A2:1-3,A3:2,XA1:"
+	" C0-3:S+ C1-3:S+  C2      .   X2-3:X    .      .      .     0 A1:0-3,A2:1-3,A3:2,XA1:"
 
-	# Invalid to valid remote partition indirect transition test via member
-	" C0-3:S+   C1-3    .      .      .    X3:P2    .      .      0 A1:0-3,A2:1-3,XA2: A2:P-2"
+	# Invalid to valid remote partition transition test
+	" C0-3:S+   C1-3    .      .      .    X3:P2    .      .     0 A1:0-3,A2:1-3,XA2: A2:P-2"
 	" C0-3:S+ C1-3:X3:P2
-			    .      .    X2-3   P0:P2    .      .      0 A1:0-2,A2:3,XA2:3 A2:P2 3"
+			    .      .    X2-3    P2      .      .     0 A1:0-2,A2:3,XA2:3 A2:P2 3"
 
 	# Invalid to valid local partition direct transition tests
-	" C1-3:S+:P2 C2-3:X1:P2 .  .      .      .      .      .      0 A1:1-3,XA1:1-3,A2:2-3:XA2: A1:P2,A2:P-2 1-3"
-	" C1-3:S+:P2 C2-3:X1:P2 .  .      .    X3:P2    .      .      0 A1:1-2,XA1:1-3,A2:3:XA2:3 A1:P2,A2:P2 1-3"
+	" C1-3:S+:P2 C2-3:X1:P2 .  .      .      .      .      .     0 A1:1-3,XA1:1-3,A2:2-3:XA2: A1:P2,A2:P-2 1-3"
+	" C1-3:S+:P2 C2-3:X1:P2 .  .      .    X3:P2    .      .     0 A1:1-2,XA1:1-3,A2:3:XA2:3 A1:P2,A2:P2 1-3"
+	"  C0-3:P2   .      .    C4-6   C0-4     .      .      .     0 A1:0-4,B1:4-6 A1:P-2,B1:P0"
+	"  C0-3:P2   .      .    C4-6 C0-4:C0-3  .      .      .     0 A1:0-3,B1:4-6 A1:P2,B1:P0 0-3"
+	"  C0-3:P2   .      .  C3-5:C4-5  .      .      .      .     0 A1:0-3,B1:4-5 A1:P2,B1:P0 0-3"
 
 	# Local partition invalidation tests
 	" C0-3:X1-3:S+:P2 C1-3:X2-3:S+:P2 C2-3:X3:P2 \
@@ -336,6 +340,9 @@  TEST_MATRIX=(
 				   .      .     X4      .      .     0 A1:1-3,A2:1-3,A3:2-3,XA2:,XA3: A1:P2,A2:P-2,A3:P-2 1-3"
 	" C0-3:X1-3:S+:P2 C1-3:X2-3:S+:P2 C2-3:X3:P2 \
 				   .      .     C4      .      .     0 A1:1-3,A2:1-3,A3:2-3,XA2:,XA3: A1:P2,A2:P-2,A3:P-2 1-3"
+	# Local partition CPU change tests
+	" C0-5:S+:P2 C4-5:S+:P1 .  .      .    C3-5     .      .     0 A1:0-2,A2:3-5 A1:P2,A2:P1 0-2"
+	" C0-5:S+:P2 C4-5:S+:P1 .  .    C1-5     .      .      .     0 A1:1-3,A2:4-5 A1:P2,A2:P1 1-3"
 
 	# cpus_allowed/exclusive_cpus update tests
 	" C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3 \