Merge tag 'sched_ext-for-6.12-rc2-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/sched_ext

Pull sched_ext fixes from Tejun Heo:

 - ops.enqueue() didn't have a way to tell whether select_task_rq_scx()
   and thus ops.select() were skipped. Some schedulers were incorrectly
   using SCX_ENQ_WAKEUP. Add SCX_ENQ_CPU_SELECTED and fix scx_qmap using
   it.

 - Remove a spurious WARN_ON_ONCE() in scx_cgroup_exit()

 - Fix error information clobbering during load

 - Add missing __weak markers to BPF helper declarations

 - Doc update

* tag 'sched_ext-for-6.12-rc2-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/sched_ext:
  sched_ext: Documentation: Update instructions for running example schedulers
  sched_ext, scx_qmap: Add and use SCX_ENQ_CPU_SELECTED
  sched/core: Add ENQUEUE_RQ_SELECTED to indicate whether ->select_task_rq() was called
  sched/core: Make select_task_rq() take the pointer to wake_flags instead of value
  sched_ext: scx_cgroup_exit() may be called without successful scx_cgroup_init()
  sched_ext: Improve error reporting during loading
  sched_ext: Add __weak markers to BPF helper function decalarations

3 files changed, 37 insertions, 19 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 43e453ab7e20..aeb595514461 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3518,14 +3518,16 @@ out:
  * The caller (fork, wakeup) owns p->pi_lock, ->cpus_ptr is stable.
  */
 static inline
-int select_task_rq(struct task_struct *p, int cpu, int wake_flags)
+int select_task_rq(struct task_struct *p, int cpu, int *wake_flags)
 {
 	lockdep_assert_held(&p->pi_lock);
 
-	if (p->nr_cpus_allowed > 1 && !is_migration_disabled(p))
-		cpu = p->sched_class->select_task_rq(p, cpu, wake_flags);
-	else
+	if (p->nr_cpus_allowed > 1 && !is_migration_disabled(p)) {
+		cpu = p->sched_class->select_task_rq(p, cpu, *wake_flags);
+		*wake_flags |= WF_RQ_SELECTED;
+	} else {
 		cpu = cpumask_any(p->cpus_ptr);
+	}
 
 	/*
 	 * In order not to call set_task_cpu() on a blocking task we need
@@ -3659,6 +3661,8 @@ ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags,
 		rq->nr_uninterruptible--;
 
 #ifdef CONFIG_SMP
+	if (wake_flags & WF_RQ_SELECTED)
+		en_flags |= ENQUEUE_RQ_SELECTED;
 	if (wake_flags & WF_MIGRATED)
 		en_flags |= ENQUEUE_MIGRATED;
 	else
@@ -4120,6 +4124,8 @@ int try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	guard(preempt)();
 	int cpu, success = 0;
 
+	wake_flags |= WF_TTWU;
+
 	if (p == current) {
 		/*
 		 * We're waking current, this means 'p->on_rq' and 'task_cpu(p)
@@ -4252,7 +4258,7 @@ int try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 		 */
 		smp_cond_load_acquire(&p->on_cpu, !VAL);
 
-		cpu = select_task_rq(p, p->wake_cpu, wake_flags | WF_TTWU);
+		cpu = select_task_rq(p, p->wake_cpu, &wake_flags);
 		if (task_cpu(p) != cpu) {
 			if (p->in_iowait) {
 				delayacct_blkio_end(p);
@@ -4793,6 +4799,7 @@ void wake_up_new_task(struct task_struct *p)
 {
 	struct rq_flags rf;
 	struct rq *rq;
+	int wake_flags = WF_FORK;
 
 	raw_spin_lock_irqsave(&p->pi_lock, rf.flags);
 	WRITE_ONCE(p->__state, TASK_RUNNING);
@@ -4807,7 +4814,7 @@ void wake_up_new_task(struct task_struct *p)
 	 */
 	p->recent_used_cpu = task_cpu(p);
 	rseq_migrate(p);
-	__set_task_cpu(p, select_task_rq(p, task_cpu(p), WF_FORK));
+	__set_task_cpu(p, select_task_rq(p, task_cpu(p), &wake_flags));
 #endif
 	rq = __task_rq_lock(p, &rf);
 	update_rq_clock(rq);
@@ -4815,7 +4822,7 @@ void wake_up_new_task(struct task_struct *p)
 
 	activate_task(rq, p, ENQUEUE_NOCLOCK | ENQUEUE_INITIAL);
 	trace_sched_wakeup_new(p);
-	wakeup_preempt(rq, p, WF_FORK);
+	wakeup_preempt(rq, p, wake_flags);
 #ifdef CONFIG_SMP
 	if (p->sched_class->task_woken) {
 		/*
diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 3cd7c50a51c5..410a4df8a121 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -625,6 +625,10 @@ struct sched_ext_ops {
 	/**
 	 * exit - Clean up after the BPF scheduler
 	 * @info: Exit info
+	 *
+	 * ops.exit() is also called on ops.init() failure, which is a bit
+	 * unusual. This is to allow rich reporting through @info on how
+	 * ops.init() failed.
 	 */
 	void (*exit)(struct scx_exit_info *info);
 
@@ -692,6 +696,7 @@ enum scx_enq_flags {
 	/* expose select ENQUEUE_* flags as enums */
 	SCX_ENQ_WAKEUP		= ENQUEUE_WAKEUP,
 	SCX_ENQ_HEAD		= ENQUEUE_HEAD,
+	SCX_ENQ_CPU_SELECTED	= ENQUEUE_RQ_SELECTED,
 
 	/* high 32bits are SCX specific */
 
@@ -4048,7 +4053,6 @@ static void scx_cgroup_exit(void)
 
 	percpu_rwsem_assert_held(&scx_cgroup_rwsem);
 
-	WARN_ON_ONCE(!scx_cgroup_enabled);
 	scx_cgroup_enabled = false;
 
 	/*
@@ -4117,6 +4121,7 @@ static int scx_cgroup_init(void)
 				      css->cgroup, &args);
 		if (ret) {
 			css_put(css);
+			scx_ops_error("ops.cgroup_init() failed (%d)", ret);
 			return ret;
 		}
 		tg->scx_flags |= SCX_TG_INITED;
@@ -5041,6 +5046,7 @@ static int scx_ops_enable(struct sched_ext_ops *ops, struct bpf_link *link)
 		if (ret) {
 			ret = ops_sanitize_err("init", ret);
 			cpus_read_unlock();
+			scx_ops_error("ops.init() failed (%d)", ret);
 			goto err_disable;
 		}
 	}
@@ -5150,8 +5156,8 @@ static int scx_ops_enable(struct sched_ext_ops *ops, struct bpf_link *link)
 			spin_lock_irq(&scx_tasks_lock);
 			scx_task_iter_exit(&sti);
 			spin_unlock_irq(&scx_tasks_lock);
-			pr_err("sched_ext: ops.init_task() failed (%d) for %s[%d] while loading\n",
-			       ret, p->comm, p->pid);
+			scx_ops_error("ops.init_task() failed (%d) for %s[%d]",
+				      ret, p->comm, p->pid);
 			goto err_disable_unlock_all;
 		}
 
@@ -5199,14 +5205,8 @@ static int scx_ops_enable(struct sched_ext_ops *ops, struct bpf_link *link)
 
 	scx_ops_bypass(false);
 
-	/*
-	 * Returning an error code here would lose the recorded error
-	 * information. Exit indicating success so that the error is notified
-	 * through ops.exit() with all the details.
-	 */
 	if (!scx_ops_tryset_enable_state(SCX_OPS_ENABLED, SCX_OPS_ENABLING)) {
 		WARN_ON_ONCE(atomic_read(&scx_exit_kind) == SCX_EXIT_NONE);
-		ret = 0;
 		goto err_disable;
 	}
 
@@ -5241,10 +5241,18 @@ err_disable_unlock_all:
 	scx_ops_bypass(false);
 err_disable:
 	mutex_unlock(&scx_ops_enable_mutex);
-	/* must be fully disabled before returning */
-	scx_ops_disable(SCX_EXIT_ERROR);
+	/*
+	 * Returning an error code here would not pass all the error information
+	 * to userspace. Record errno using scx_ops_error() for cases
+	 * scx_ops_error() wasn't already invoked and exit indicating success so
+	 * that the error is notified through ops.exit() with all the details.
+	 *
+	 * Flush scx_ops_disable_work to ensure that error is reported before
+	 * init completion.
+	 */
+	scx_ops_error("scx_ops_enable() failed (%d)", ret);
 	kthread_flush_work(&scx_ops_disable_work);
-	return ret;
+	return 0;
 }
 
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index b1c3588a8f00..6085ef50febf 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2292,6 +2292,7 @@ static inline int task_on_rq_migrating(struct task_struct *p)
 #define WF_SYNC			0x10 /* Waker goes to sleep after wakeup */
 #define WF_MIGRATED		0x20 /* Internal use, task got migrated */
 #define WF_CURRENT_CPU		0x40 /* Prefer to move the wakee to the current CPU. */
+#define WF_RQ_SELECTED		0x80 /* ->select_task_rq() was called */
 
 #ifdef CONFIG_SMP
 static_assert(WF_EXEC == SD_BALANCE_EXEC);
@@ -2334,6 +2335,7 @@ extern const u32		sched_prio_to_wmult[40];
  * ENQUEUE_HEAD      - place at front of runqueue (tail if not specified)
  * ENQUEUE_REPLENISH - CBS (replenish runtime and postpone deadline)
  * ENQUEUE_MIGRATED  - the task was migrated during wakeup
+ * ENQUEUE_RQ_SELECTED - ->select_task_rq() was called
  *
  */
 
@@ -2360,6 +2362,7 @@ extern const u32		sched_prio_to_wmult[40];
 #define ENQUEUE_INITIAL		0x80
 #define ENQUEUE_MIGRATING	0x100
 #define ENQUEUE_DELAYED		0x200
+#define ENQUEUE_RQ_SELECTED	0x400
 
 #define RETRY_TASK		((void *)-1UL)