Merge v6.19.9linux-rolling-stable

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

3 files changed, 109 insertions, 66 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index dbf4e32a063f..011fe1b2ae91 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4708,8 +4708,11 @@ void sched_cancel_fork(struct task_struct *p)
 	scx_cancel_fork(p);
 }
 
+static void sched_mm_cid_fork(struct task_struct *t);
+
 void sched_post_fork(struct task_struct *p)
 {
+	sched_mm_cid_fork(p);
 	uclamp_post_fork(p);
 	scx_post_fork(p);
 }
@@ -10565,13 +10568,10 @@ static inline void mm_cid_transit_to_cpu(struct task_struct *t, struct mm_cid_pc
 	}
 }
 
-static bool mm_cid_fixup_task_to_cpu(struct task_struct *t, struct mm_struct *mm)
+static void mm_cid_fixup_task_to_cpu(struct task_struct *t, struct mm_struct *mm)
 {
 	/* Remote access to mm::mm_cid::pcpu requires rq_lock */
 	guard(task_rq_lock)(t);
-	/* If the task is not active it is not in the users count */
-	if (!t->mm_cid.active)
-		return false;
 	if (cid_on_task(t->mm_cid.cid)) {
 		/* If running on the CPU, put the CID in transit mode, otherwise drop it */
 		if (task_rq(t)->curr == t)
@@ -10579,69 +10579,43 @@ static bool mm_cid_fixup_task_to_cpu(struct task_struct *t, struct mm_struct *mm
 		else
 			mm_unset_cid_on_task(t);
 	}
-	return true;
 }
 
-static void mm_cid_do_fixup_tasks_to_cpus(struct mm_struct *mm)
+static void mm_cid_fixup_tasks_to_cpus(void)
 {
-	struct task_struct *p, *t;
-	unsigned int users;
+	struct mm_struct *mm = current->mm;
+	struct task_struct *t;
 
-	/*
-	 * This can obviously race with a concurrent affinity change, which
-	 * increases the number of allowed CPUs for this mm, but that does
-	 * not affect the mode and only changes the CID constraints. A
-	 * possible switch back to per task mode happens either in the
-	 * deferred handler function or in the next fork()/exit().
-	 *
-	 * The caller has already transferred. The newly incoming task is
-	 * already accounted for, but not yet visible.
-	 */
-	users = mm->mm_cid.users - 2;
-	if (!users)
-		return;
+	lockdep_assert_held(&mm->mm_cid.mutex);
 
-	guard(rcu)();
-	for_other_threads(current, t) {
-		if (mm_cid_fixup_task_to_cpu(t, mm))
-			users--;
+	hlist_for_each_entry(t, &mm->mm_cid.user_list, mm_cid.node) {
+		/* Current has already transferred before invoking the fixup. */
+		if (t != current)
+			mm_cid_fixup_task_to_cpu(t, mm);
 	}
 
-	if (!users)
-		return;
-
-	/* Happens only for VM_CLONE processes. */
-	for_each_process_thread(p, t) {
-		if (t == current || t->mm != mm)
-			continue;
-		if (mm_cid_fixup_task_to_cpu(t, mm)) {
-			if (--users == 0)
-				return;
-		}
-	}
-}
-
-static void mm_cid_fixup_tasks_to_cpus(void)
-{
-	struct mm_struct *mm = current->mm;
-
-	mm_cid_do_fixup_tasks_to_cpus(mm);
 	mm_cid_complete_transit(mm, MM_CID_ONCPU);
 }
 
 static bool sched_mm_cid_add_user(struct task_struct *t, struct mm_struct *mm)
 {
+	lockdep_assert_held(&mm->mm_cid.lock);
+
 	t->mm_cid.active = 1;
+	hlist_add_head(&t->mm_cid.node, &mm->mm_cid.user_list);
 	mm->mm_cid.users++;
 	return mm_update_max_cids(mm);
 }
 
-void sched_mm_cid_fork(struct task_struct *t)
+static void sched_mm_cid_fork(struct task_struct *t)
 {
 	struct mm_struct *mm = t->mm;
 	bool percpu;
 
-	WARN_ON_ONCE(!mm || t->mm_cid.cid != MM_CID_UNSET);
+	if (!mm)
+		return;
+
+	WARN_ON_ONCE(t->mm_cid.cid != MM_CID_UNSET);
 
 	guard(mutex)(&mm->mm_cid.mutex);
 	scoped_guard(raw_spinlock_irq, &mm->mm_cid.lock) {
@@ -10680,12 +10654,13 @@ void sched_mm_cid_fork(struct task_struct *t)
 
 static bool sched_mm_cid_remove_user(struct task_struct *t)
 {
+	lockdep_assert_held(&t->mm->mm_cid.lock);
+
 	t->mm_cid.active = 0;
-	scoped_guard(preempt) {
-		/* Clear the transition bit */
-		t->mm_cid.cid = cid_from_transit_cid(t->mm_cid.cid);
-		mm_unset_cid_on_task(t);
-	}
+	/* Clear the transition bit */
+	t->mm_cid.cid = cid_from_transit_cid(t->mm_cid.cid);
+	mm_unset_cid_on_task(t);
+	hlist_del_init(&t->mm_cid.node);
 	t->mm->mm_cid.users--;
 	return mm_update_max_cids(t->mm);
 }
@@ -10828,11 +10803,13 @@ void mm_init_cid(struct mm_struct *mm, struct task_struct *p)
 	mutex_init(&mm->mm_cid.mutex);
 	mm->mm_cid.irq_work = IRQ_WORK_INIT_HARD(mm_cid_irq_work);
 	INIT_WORK(&mm->mm_cid.work, mm_cid_work_fn);
+	INIT_HLIST_HEAD(&mm->mm_cid.user_list);
 	cpumask_copy(mm_cpus_allowed(mm), &p->cpus_mask);
 	bitmap_zero(mm_cidmask(mm), num_possible_cpus());
 }
 #else /* CONFIG_SCHED_MM_CID */
 static inline void mm_update_cpus_allowed(struct mm_struct *mm, const struct cpumask *affmsk) { }
+static inline void sched_mm_cid_fork(struct task_struct *t) { }
 #endif /* !CONFIG_SCHED_MM_CID */
 
 static DEFINE_PER_CPU(struct sched_change_ctx, sched_change_ctx);
diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 0bb8fa927e9e..f7eeccbd893a 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -1464,16 +1464,15 @@ static void clr_task_runnable(struct task_struct *p, bool reset_runnable_at)
 		p->scx.flags |= SCX_TASK_RESET_RUNNABLE_AT;
 }
 
-static void enqueue_task_scx(struct rq *rq, struct task_struct *p, int enq_flags)
+static void enqueue_task_scx(struct rq *rq, struct task_struct *p, int core_enq_flags)
 {
 	struct scx_sched *sch = scx_root;
 	int sticky_cpu = p->scx.sticky_cpu;
+	u64 enq_flags = core_enq_flags | rq->scx.extra_enq_flags;
 
 	if (enq_flags & ENQUEUE_WAKEUP)
 		rq->scx.flags |= SCX_RQ_IN_WAKEUP;
 
-	enq_flags |= rq->scx.extra_enq_flags;
-
 	if (sticky_cpu >= 0)
 		p->scx.sticky_cpu = -1;
 
@@ -3553,7 +3552,6 @@ static int scx_cgroup_init(struct scx_sched *sch)
 		ret = SCX_CALL_OP_RET(sch, SCX_KF_UNLOCKED, cgroup_init, NULL,
 				      css->cgroup, &args);
 		if (ret) {
-			css_put(css);
 			scx_error(sch, "ops.cgroup_init() failed (%d)", ret);
 			return ret;
 		}
@@ -4391,10 +4389,19 @@ done:
 	scx_bypass(false);
 }
 
+/*
+ * Claim the exit on @sch. The caller must ensure that the helper kthread work
+ * is kicked before the current task can be preempted. Once exit_kind is
+ * claimed, scx_error() can no longer trigger, so if the current task gets
+ * preempted and the BPF scheduler fails to schedule it back, the helper work
+ * will never be kicked and the whole system can wedge.
+ */
 static bool scx_claim_exit(struct scx_sched *sch, enum scx_exit_kind kind)
 {
 	int none = SCX_EXIT_NONE;
 
+	lockdep_assert_preemption_disabled();
+
 	if (!atomic_try_cmpxchg(&sch->exit_kind, &none, kind))
 		return false;
 
@@ -4417,6 +4424,7 @@ static void scx_disable(enum scx_exit_kind kind)
 	rcu_read_lock();
 	sch = rcu_dereference(scx_root);
 	if (sch) {
+		guard(preempt)();
 		scx_claim_exit(sch, kind);
 		kthread_queue_work(sch->helper, &sch->disable_work);
 	}
@@ -4739,6 +4747,8 @@ static bool scx_vexit(struct scx_sched *sch,
 {
 	struct scx_exit_info *ei = sch->exit_info;
 
+	guard(preempt)();
+
 	if (!scx_claim_exit(sch, kind))
 		return false;
 
@@ -4924,20 +4934,30 @@ static int validate_ops(struct scx_sched *sch, const struct sched_ext_ops *ops)
 	return 0;
 }
 
-static int scx_enable(struct sched_ext_ops *ops, struct bpf_link *link)
+/*
+ * scx_enable() is offloaded to a dedicated system-wide RT kthread to avoid
+ * starvation. During the READY -> ENABLED task switching loop, the calling
+ * thread's sched_class gets switched from fair to ext. As fair has higher
+ * priority than ext, the calling thread can be indefinitely starved under
+ * fair-class saturation, leading to a system hang.
+ */
+struct scx_enable_cmd {
+	struct kthread_work	work;
+	struct sched_ext_ops	*ops;
+	int			ret;
+};
+
+static void scx_enable_workfn(struct kthread_work *work)
 {
+	struct scx_enable_cmd *cmd =
+		container_of(work, struct scx_enable_cmd, work);
+	struct sched_ext_ops *ops = cmd->ops;
 	struct scx_sched *sch;
 	struct scx_task_iter sti;
 	struct task_struct *p;
 	unsigned long timeout;
 	int i, cpu, ret;
 
-	if (!cpumask_equal(housekeeping_cpumask(HK_TYPE_DOMAIN),
-			   cpu_possible_mask)) {
-		pr_err("sched_ext: Not compatible with \"isolcpus=\" domain isolation\n");
-		return -EINVAL;
-	}
-
 	mutex_lock(&scx_enable_mutex);
 
 	if (scx_enable_state() != SCX_DISABLED) {
@@ -5154,13 +5174,15 @@ static int scx_enable(struct sched_ext_ops *ops, struct bpf_link *link)
 
 	atomic_long_inc(&scx_enable_seq);
 
-	return 0;
+	cmd->ret = 0;
+	return;
 
 err_free_ksyncs:
 	free_kick_syncs();
 err_unlock:
 	mutex_unlock(&scx_enable_mutex);
-	return ret;
+	cmd->ret = ret;
+	return;
 
 err_disable_unlock_all:
 	scx_cgroup_unlock();
@@ -5179,7 +5201,42 @@ err_disable:
 	 */
 	scx_error(sch, "scx_enable() failed (%d)", ret);
 	kthread_flush_work(&sch->disable_work);
-	return 0;
+	cmd->ret = 0;
+}
+
+static int scx_enable(struct sched_ext_ops *ops, struct bpf_link *link)
+{
+	static struct kthread_worker *helper;
+	static DEFINE_MUTEX(helper_mutex);
+	struct scx_enable_cmd cmd;
+
+	if (!cpumask_equal(housekeeping_cpumask(HK_TYPE_DOMAIN),
+			   cpu_possible_mask)) {
+		pr_err("sched_ext: Not compatible with \"isolcpus=\" domain isolation\n");
+		return -EINVAL;
+	}
+
+	if (!READ_ONCE(helper)) {
+		mutex_lock(&helper_mutex);
+		if (!helper) {
+			struct kthread_worker *w =
+				kthread_run_worker(0, "scx_enable_helper");
+			if (IS_ERR_OR_NULL(w)) {
+				mutex_unlock(&helper_mutex);
+				return -ENOMEM;
+			}
+			sched_set_fifo(w->task);
+			WRITE_ONCE(helper, w);
+		}
+		mutex_unlock(&helper_mutex);
+	}
+
+	kthread_init_work(&cmd.work, scx_enable_workfn);
+	cmd.ops = ops;
+
+	kthread_queue_work(READ_ONCE(helper), &cmd.work);
+	kthread_flush_work(&cmd.work);
+	return cmd.ret;
 }
 
 
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index abf8f15d60c9..69c70d509e1c 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -221,7 +221,7 @@ static void cpuidle_idle_call(void)
 
 		next_state = cpuidle_find_deepest_state(drv, dev, max_latency_ns);
 		call_cpuidle(drv, dev, next_state);
-	} else {
+	} else if (drv->state_count > 1) {
 		bool stop_tick = true;
 
 		/*
@@ -239,6 +239,15 @@ static void cpuidle_idle_call(void)
 		 * Give the governor an opportunity to reflect on the outcome
 		 */
 		cpuidle_reflect(dev, entered_state);
+	} else {
+		tick_nohz_idle_retain_tick();
+
+		/*
+		 * If there is only a single idle state (or none), there is
+		 * nothing meaningful for the governor to choose.  Skip the
+		 * governor and always use state 0.
+		 */
+		call_cpuidle(drv, dev, 0);
 	}
 
 exit_idle: