Merge branch 'for-7.2-fixes' into for-7.3

Pull to receive:

 477869bfaf ("sched_ext: Reject setting disallow from init_task outside the enable path")
 5f8b69642d ("sched_ext: Take cgroup_lock() first in scx_cgroup_lock()")
 8c13364db9 ("sched_ext: Skip sub-disable teardown for never-linked sub-schedulers")
 5cdc928598 ("sched_ext: Don't enable non-ext tasks in the sub-sched task loops")

as dependencies for the upcoming cgroup migration patchset and to
resolve the conflicts with the ext.c/sub.c split on for-7.3.

5f8b69642d comments scx_cgroup_lock() which for-7.3 exported for
sub.c. Resolved by keeping the exported version with the comment.

8c13364db9 and 5cdc928598 patch the pre-split sub-sched enable and
disable paths in ext.c which for-7.3 moved to sub.c. Resolved by
applying the never-linked teardown skip and the class gates to sub.c.

Signed-off-by: Tejun Heo <tj@kernel.org>

include/linux/sched/ext.h

@@ -265,11 +265,11 @@ struct sched_ext_entity {
 	 * to %SCHED_EXT with -%EACCES.
 	 *
 	 * Can be set from ops.init_task() while the BPF scheduler is being
-	 * loaded (!scx_init_task_args->fork). If set and the task's policy is
-	 * already %SCHED_EXT, the task's policy is rejected and forcefully
-	 * reverted to %SCHED_NORMAL. The number of such events are reported
-	 * through /sys/kernel/debug/sched_ext::nr_rejected. Setting this flag
-	 * during fork is not allowed.
+	 * loaded. If set and the task's policy is already %SCHED_EXT, the
+	 * task's policy is rejected and forcefully reverted to %SCHED_NORMAL.
+	 * The number of such events are reported through
+	 * /sys/kernel/sched_ext/nr_rejected. Setting this flag from any other
+	 * ops.init_task() invocation, such as during fork, fails the scheduler.
 	 */
 	bool			disallow;	/* reject switching into SCX */
 

kernel/sched/ext/ext.c

@@ -3511,6 +3511,9 @@ int __scx_init_task(struct scx_sched *sch, struct task_struct *p, bool fork)
 		} else if (unlikely(fork)) {
 			scx_error(sch, "ops.init_task() set task->scx.disallow for %s[%d] during fork",
 				  p->comm, p->pid);
+		} else if (unlikely(scx_enable_state() != SCX_ENABLING)) {
+			scx_error(sch, "ops.init_task() set task->scx.disallow for %s[%d] outside the enable path",
+				  p->comm, p->pid);
 		} else {
 			struct rq *rq;
 			struct rq_flags rf;
@@ -3872,6 +3875,17 @@ static void reweight_task_scx(struct rq *rq, struct task_struct *p,
 	if (task_dead_and_done(p))
 		return;
 
+	/*
+	 * When switching sched_class away from SCX, reweight_task_scx()
+	 * is called _after_ scx_disable_task(). Skip calling ops.set_weight()
+	 * since the BPF scheduler may have already forgotten the task in
+	 * ops.disable().
+	 * p->scx.weight will be recalculated in scx_enable_task() if the task
+	 * ever returns to SCX class.
+	 */
+	if (scx_get_task_state(p) != SCX_TASK_ENABLED)
+		return;
+
 	p->scx.weight = sched_weight_to_cgroup(scale_load_down(lw->weight));
 	if (SCX_HAS_OP(sch, set_weight))
 		SCX_CALL_OP_TASK(sch, set_weight, rq, p, p->scx.weight);
@@ -4495,20 +4509,25 @@ static struct cgroup *root_cgroup(void)
 	return &cgrp_dfl_root.cgrp;
 }
 
+/*
+ * cgroup_lock() must nest outside the rwsem write side: a writer waiting
+ * for cgroup_mutex deadlocks with cgroup teardown, which holds it while
+ * draining a set_* file write blocked on the rwsem behind the writer.
+ */
 void scx_cgroup_lock(void)
 {
+	cgroup_lock();
 #ifdef CONFIG_EXT_GROUP_SCHED
 	percpu_down_write(&scx_cgroup_ops_rwsem);
 #endif
-	cgroup_lock();
 }
 
 void scx_cgroup_unlock(void)
 {
-	cgroup_unlock();
 #ifdef CONFIG_EXT_GROUP_SCHED
 	percpu_up_write(&scx_cgroup_ops_rwsem);
 #endif
+	cgroup_unlock();
 }
 #else	/* CONFIG_EXT_GROUP_SCHED || CONFIG_EXT_SUB_SCHED */
 static inline struct cgroup *root_cgroup(void) { return NULL; }

kernel/sched/ext/sub.c

@@ -812,6 +812,15 @@ void scx_sub_disable(struct scx_sched *sch)
 	percpu_down_write(&scx_fork_rwsem);
 	scx_cgroup_lock();
 
+	/*
+	 * An enable that failed before scx_link_sched() never owned a cgroup or
+	 * task and won't be waited on by an ancestor's drain_descendants().
+	 * Nothing to reparent and walking the tasks can misbehave as the task
+	 * ownership invariant (either owned by self or parent) does not hold.
+	 */
+	if (list_empty(&sch->sibling))
+		goto dump;
+
 	set_cgroup_sched(sch_cgroup(sch), parent);
 
 	scx_task_iter_start(&sti, sch->cgrp);
@@ -824,8 +833,8 @@ void scx_sub_disable(struct scx_sched *sch)
 			continue;
 
 		/*
-		 * By the time control reaches here, all descendant schedulers
-		 * should already have been disabled.
+		 * By the time control reaches here, all linked descendant
+		 * schedulers should have been disabled.
 		 */
 		WARN_ON_ONCE(!scx_task_on_sched(sch, p));
 
@@ -876,15 +885,22 @@ void scx_sub_disable(struct scx_sched *sch)
 			/*
 			 * $p is initialized for $parent and still attached to
 			 * @sch. Disable and exit for @sch, switch over to
-			 * $parent, override the state to READY to account for
-			 * $p having already been initialized, and then enable.
+			 * $parent and override the state to READY to account
+			 * for $p having already been initialized.
 			 */
 			scx_disable_and_exit_task(sch, p);
 			scx_set_task_state(p, SCX_TASK_INIT_BEGIN);
 			scx_set_task_state(p, SCX_TASK_INIT);
 			scx_set_task_sched(p, parent);
 			scx_set_task_state(p, SCX_TASK_READY);
-			scx_enable_task(parent, p);
+
+			/*
+			 * A task on a non-ext class, possible under an
+			 * %SCX_OPS_SWITCH_PARTIAL root, stays READY and is
+			 * enabled by switching_to_scx() if it switches over.
+			 */
+			if (p->sched_class == &ext_sched_class)
+				scx_enable_task(parent, p);
 		}
 
 		task_rq_unlock(rq, p, &rf);
@@ -892,6 +908,7 @@ void scx_sub_disable(struct scx_sched *sch)
 	}
 	scx_task_iter_stop(&sti);
 
+dump:
 	scx_disable_dump(sch);
 
 	scx_cgroup_unlock();
@@ -1219,10 +1236,14 @@ void scx_sub_enable_workfn(struct kthread_work *work)
 
 			/*
 			 * $p is now only initialized for @sch and READY, which
-			 * is what we want. Assign it to @sch and enable.
+			 * is what we want. Assign it to @sch and, if it's on
+			 * the ext class, enable. A non-ext task, possible under
+			 * an %SCX_OPS_SWITCH_PARTIAL root, stays READY and is
+			 * enabled by switching_to_scx() if it switches over.
 			 */
 			scx_set_task_sched(p, sch);
-			scx_enable_task(sch, p);
+			if (p->sched_class == &ext_sched_class)
+				scx_enable_task(sch, p);
 
 			p->scx.flags &= ~SCX_TASK_SUB_INIT;
 		}