Merge tag 'cgroup-for-7.1-rc3-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup

Pull cgroup fixes from Tejun Heo:

 - cpuset fixes:
     - Partition invalidation could return CPUs still in use by sibling
       partitions, producing overlapping effective_cpus
     - cpuset_can_attach() over-reserved DL bandwidth on moves that
       stayed within the same root domain
     - Pending DL migration state leaked into later attaches when a
       later can_attach() check failed
     - Reorder PF_EXITING and __GFP_HARDWALL checks so dying tasks can
       allocate from any node and exit quickly

 - dmem: propagate -ENOMEM instead of spinning forever when the fallback
   pool allocation also fails

 - selftests/cgroup: percpu test error-path leak, bogus numeric
   comparison of cpuset strings, and a zero-length read() that silently
   passed OOM-kill tests

* tag 'cgroup-for-7.1-rc3-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup:
  cgroup/cpuset: Return only actually allocated CPUs during partition invalidation
  selftests/cgroup: Fix error path leaks in test_percpu_basic
  cgroup/cpuset: Reserve DL bandwidth only for root-domain moves
  cgroup/cpuset: Reset DL migration state on can_attach() failure
  selftests/cgroup: Fix string comparison in write_test
  selftests/cgroup: Fix cg_read_strcmp() empty string comparison
  cgroup/dmem: Return -ENOMEM on failed pool preallocation
  cgroup/cpuset: move PF_EXITING check before __GFP_HARDWALL in cpuset_current_node_allowed()

8 files changed, 63 insertions, 34 deletions

diff --git a/include/linux/sched/deadline.h b/include/linux/sched/deadline.h
index 1198138cb839..273538200a44 100644
--- a/include/linux/sched/deadline.h
+++ b/include/linux/sched/deadline.h
@@ -33,6 +33,15 @@ struct root_domain;
 extern void dl_add_task_root_domain(struct task_struct *p);
 extern void dl_clear_root_domain(struct root_domain *rd);
 extern void dl_clear_root_domain_cpu(int cpu);
+/*
+ * Return whether moving DL task @p to @new_mask requires moving DL
+ * bandwidth accounting between root domains. This helper is specific to
+ * DL bandwidth move accounting semantics and is shared by
+ * cpuset_can_attach() and set_cpus_allowed_dl() so both paths use the
+ * same source root-domain test.
+ */
+extern bool dl_task_needs_bw_move(struct task_struct *p,
+				  const struct cpumask *new_mask);
 
 extern u64 dl_cookie;
 extern bool dl_bw_visited(int cpu, u64 cookie);
diff --git a/kernel/cgroup/cpuset-internal.h b/kernel/cgroup/cpuset-internal.h
index bb4e692bea30..f7aaf01f7cd5 100644
--- a/kernel/cgroup/cpuset-internal.h
+++ b/kernel/cgroup/cpuset-internal.h
@@ -167,6 +167,7 @@ struct cpuset {
 	 */
 	int nr_deadline_tasks;
 	int nr_migrate_dl_tasks;
+	/* DL bandwidth that needs destination reservation for this attach. */
 	u64 sum_migrate_dl_bw;
 	/*
 	 * CPU used for temporary DL bandwidth allocation during attach;
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index e3a081a07c6d..5c33ab20cc20 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -1718,7 +1718,8 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd,
 		 */
 		if (is_partition_valid(parent))
 			adding = cpumask_and(tmp->addmask,
-					     xcpus, parent->effective_xcpus);
+					     cs->effective_xcpus,
+					     parent->effective_xcpus);
 		if (old_prs > 0)
 			new_prs = -old_prs;
 
@@ -2993,7 +2994,7 @@ static int cpuset_can_attach(struct cgroup_taskset *tset)
 	struct cpuset *cs, *oldcs;
 	struct task_struct *task;
 	bool setsched_check;
-	int ret;
+	int cpu, ret;
 
 	/* used later by cpuset_attach() */
 	cpuset_attach_old_cs = task_cs(cgroup_taskset_first(tset, &css));
@@ -3038,31 +3039,31 @@ static int cpuset_can_attach(struct cgroup_taskset *tset)
 		}
 
 		if (dl_task(task)) {
+			/*
+			 * Count all migrating DL tasks for cpuset task accounting.
+			 * Only tasks that need a root-domain bandwidth move
+			 * contribute to sum_migrate_dl_bw.
+			 */
 			cs->nr_migrate_dl_tasks++;
-			cs->sum_migrate_dl_bw += task->dl.dl_bw;
+			if (dl_task_needs_bw_move(task, cs->effective_cpus))
+				cs->sum_migrate_dl_bw += task->dl.dl_bw;
 		}
 	}
 
-	if (!cs->nr_migrate_dl_tasks)
+	if (!cs->sum_migrate_dl_bw)
 		goto out_success;
 
-	if (!cpumask_intersects(oldcs->effective_cpus, cs->effective_cpus)) {
-		int cpu = cpumask_any_and(cpu_active_mask, cs->effective_cpus);
-
-		if (unlikely(cpu >= nr_cpu_ids)) {
-			reset_migrate_dl_data(cs);
-			ret = -EINVAL;
-			goto out_unlock;
-		}
+	cpu = cpumask_any_and(cpu_active_mask, cs->effective_cpus);
+	if (unlikely(cpu >= nr_cpu_ids)) {
+		ret = -EINVAL;
+		goto out_unlock;
+	}
 
-		ret = dl_bw_alloc(cpu, cs->sum_migrate_dl_bw);
-		if (ret) {
-			reset_migrate_dl_data(cs);
-			goto out_unlock;
-		}
+	ret = dl_bw_alloc(cpu, cs->sum_migrate_dl_bw);
+	if (ret)
+		goto out_unlock;
 
-		cs->dl_bw_cpu = cpu;
-	}
+	cs->dl_bw_cpu = cpu;
 
 out_success:
 	/*
@@ -3070,7 +3071,10 @@ out_success:
 	 * changes which zero cpus/mems_allowed.
 	 */
 	cs->attach_in_progress++;
+
 out_unlock:
+	if (ret)
+		reset_migrate_dl_data(cs);
 	mutex_unlock(&cpuset_mutex);
 	return ret;
 }
@@ -4176,11 +4180,11 @@ static struct cpuset *nearest_hardwall_ancestor(struct cpuset *cs)
  * current's mems_allowed, yes.  If it's not a __GFP_HARDWALL request and this
  * node is set in the nearest hardwalled cpuset ancestor to current's cpuset,
  * yes.  If current has access to memory reserves as an oom victim, yes.
- * Otherwise, no.
+ * If the current task is PF_EXITING, yes. Otherwise, no.
  *
  * GFP_USER allocations are marked with the __GFP_HARDWALL bit,
  * and do not allow allocations outside the current tasks cpuset
- * unless the task has been OOM killed.
+ * unless the task has been OOM killed or is exiting.
  * GFP_KERNEL allocations are not so marked, so can escape to the
  * nearest enclosing hardwalled ancestor cpuset.
  *
@@ -4194,7 +4198,9 @@ static struct cpuset *nearest_hardwall_ancestor(struct cpuset *cs)
  * The first call here from mm/page_alloc:get_page_from_freelist()
  * has __GFP_HARDWALL set in gfp_mask, enforcing hardwall cpusets,
  * so no allocation on a node outside the cpuset is allowed (unless
- * in interrupt, of course).
+ * in interrupt, of course).  The PF_EXITING check must therefore
+ * come before the __GFP_HARDWALL check, otherwise a dying task
+ * would be blocked on the fast path.
  *
  * The second pass through get_page_from_freelist() doesn't even call
  * here for GFP_ATOMIC calls.  For those calls, the __alloc_pages()
@@ -4204,6 +4210,7 @@ static struct cpuset *nearest_hardwall_ancestor(struct cpuset *cs)
  *	in_interrupt - any node ok (current task context irrelevant)
  *	GFP_ATOMIC   - any node ok
  *	tsk_is_oom_victim   - any node ok
+ *	PF_EXITING   - any node ok (let dying task exit quickly)
  *	GFP_KERNEL   - any node in enclosing hardwalled cpuset ok
  *	GFP_USER     - only nodes in current tasks mems allowed ok.
  */
@@ -4223,11 +4230,10 @@ bool cpuset_current_node_allowed(int node, gfp_t gfp_mask)
 	 */
 	if (unlikely(tsk_is_oom_victim(current)))
 		return true;
-	if (gfp_mask & __GFP_HARDWALL)	/* If hardwall request, stop here */
-		return false;
-
 	if (current->flags & PF_EXITING) /* Let dying task have memory */
 		return true;
+	if (gfp_mask & __GFP_HARDWALL)	/* If hardwall request, stop here */
+		return false;
 
 	/* Not hardwall and node outside mems_allowed: scan up cpusets */
 	spin_lock_irqsave(&callback_lock, flags);
diff --git a/kernel/cgroup/dmem.c b/kernel/cgroup/dmem.c
index 1ab1fb47f271..4753a67d0f0f 100644
--- a/kernel/cgroup/dmem.c
+++ b/kernel/cgroup/dmem.c
@@ -602,6 +602,7 @@ get_cg_pool_unlocked(struct dmemcg_state *cg, struct dmem_cgroup_region *region)
 				pool = NULL;
 				continue;
 			}
+			pool = ERR_PTR(-ENOMEM);
 		}
 	}
 
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index edca7849b165..7db4c87df83b 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -3107,20 +3107,18 @@ static void task_woken_dl(struct rq *rq, struct task_struct *p)
 static void set_cpus_allowed_dl(struct task_struct *p,
 				struct affinity_context *ctx)
 {
-	struct root_domain *src_rd;
 	struct rq *rq;
 
 	WARN_ON_ONCE(!dl_task(p));
 
 	rq = task_rq(p);
-	src_rd = rq->rd;
 	/*
 	 * Migrating a SCHED_DEADLINE task between exclusive
 	 * cpusets (different root_domains) entails a bandwidth
 	 * update. We already made space for us in the destination
 	 * domain (see cpuset_can_attach()).
 	 */
-	if (!cpumask_intersects(src_rd->span, ctx->new_mask)) {
+	if (dl_task_needs_bw_move(p, ctx->new_mask)) {
 		struct dl_bw *src_dl_b;
 
 		src_dl_b = dl_bw_of(cpu_of(rq));
@@ -3137,6 +3135,15 @@ static void set_cpus_allowed_dl(struct task_struct *p,
 	set_cpus_allowed_common(p, ctx);
 }
 
+bool dl_task_needs_bw_move(struct task_struct *p,
+			   const struct cpumask *new_mask)
+{
+	if (!dl_task(p))
+		return false;
+
+	return !cpumask_intersects(task_rq(p)->rd->span, new_mask);
+}
+
 /* Assumes rq->lock is held */
 static void rq_online_dl(struct rq *rq)
 {
diff --git a/tools/testing/selftests/cgroup/lib/cgroup_util.c b/tools/testing/selftests/cgroup/lib/cgroup_util.c
index 6a7295347e90..42f54936f4bb 100644
--- a/tools/testing/selftests/cgroup/lib/cgroup_util.c
+++ b/tools/testing/selftests/cgroup/lib/cgroup_util.c
@@ -106,8 +106,9 @@ int cg_read_strcmp(const char *cgroup, const char *control,
 	/* Handle the case of comparing against empty string */
 	if (!expected)
 		return -1;
-	else
-		size = strlen(expected) + 1;
+
+	/* needs size > 1, otherwise cg_read() reads 0 bytes */
+	size = (expected[0] == '\0') ? 2 : strlen(expected) + 1;
 
 	buf = malloc(size);
 	if (!buf)
diff --git a/tools/testing/selftests/cgroup/test_cpuset_v1_base.sh b/tools/testing/selftests/cgroup/test_cpuset_v1_base.sh
index 42a6628fb8bc..1c0444729e70 100755
--- a/tools/testing/selftests/cgroup/test_cpuset_v1_base.sh
+++ b/tools/testing/selftests/cgroup/test_cpuset_v1_base.sh
@@ -18,7 +18,7 @@ write_test() {
 	echo "testing $interface $value"
 	echo $value > $dir/$interface
 	new=$(cat $dir/$interface)
-	[[ $value -ne $(cat $dir/$interface) ]] && {
+	[[ "$value" != "$new" ]] && {
 		echo "$interface write $value failed: new:$new"
 		exit 1
 	}
diff --git a/tools/testing/selftests/cgroup/test_kmem.c b/tools/testing/selftests/cgroup/test_kmem.c
index eeabd34bf083..12f59925500b 100644
--- a/tools/testing/selftests/cgroup/test_kmem.c
+++ b/tools/testing/selftests/cgroup/test_kmem.c
@@ -368,11 +368,15 @@ static int test_percpu_basic(const char *root)
 
 	for (i = 0; i < 1000; i++) {
 		child = cg_name_indexed(parent, "child", i);
-		if (!child)
-			return -1;
+		if (!child) {
+			ret = -1;
+			goto cleanup_children;
+		}
 
-		if (cg_create(child))
+		if (cg_create(child)) {
+			free(child);
 			goto cleanup_children;
+		}
 
 		free(child);
 	}