Merge v6.19.9linux-rolling-stable

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

18 files changed, 233 insertions, 177 deletions

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index b594a065b83c..9c4723cdac70 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -24641,7 +24641,6 @@ BTF_ID(func, __x64_sys_exit_group)
 BTF_ID(func, do_exit)
 BTF_ID(func, do_group_exit)
 BTF_ID(func, kthread_complete_and_exit)
-BTF_ID(func, kthread_exit)
 BTF_ID(func, make_task_dead)
 BTF_SET_END(noreturn_deny)
 
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 5f0d33b04910..3f9e4bcd7198 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -2608,6 +2608,7 @@ static void cgroup_migrate_add_task(struct task_struct *task,
 
 	mgctx->tset.nr_tasks++;
 
+	css_set_skip_task_iters(cset, task);
 	list_move_tail(&task->cg_list, &cset->mg_tasks);
 	if (list_empty(&cset->mg_node))
 		list_add_tail(&cset->mg_node,
@@ -5108,6 +5109,12 @@ repeat:
 		return;
 
 	task = list_entry(it->task_pos, struct task_struct, cg_list);
+	/*
+	 * Hide tasks that are exiting but not yet removed. Keep zombie
+	 * leaders with live threads visible.
+	 */
+	if ((task->flags & PF_EXITING) && !atomic_read(&task->signal->live))
+		goto repeat;
 
 	if (it->flags & CSS_TASK_ITER_PROCS) {
 		/* if PROCS, skip over tasks which aren't group leaders */
diff --git a/kernel/exit.c b/kernel/exit.c
index 8a87021211ae..ede3117fa7d4 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -896,11 +896,16 @@ static void synchronize_group_exit(struct task_struct *tsk, long code)
 void __noreturn do_exit(long code)
 {
 	struct task_struct *tsk = current;
+	struct kthread *kthread;
 	int group_dead;
 
 	WARN_ON(irqs_disabled());
 	WARN_ON(tsk->plug);
 
+	kthread = tsk_is_kthread(tsk);
+	if (unlikely(kthread))
+		kthread_do_exit(kthread, code);
+
 	kcov_task_exit(tsk);
 	kmsan_task_exit(tsk);
 
@@ -1013,6 +1018,7 @@ void __noreturn do_exit(long code)
 	lockdep_free_task(tsk);
 	do_task_dead();
 }
+EXPORT_SYMBOL(do_exit);
 
 void __noreturn make_task_dead(int signr)
 {
diff --git a/kernel/fork.c b/kernel/fork.c
index b1f3915d5f8e..5b45887435dc 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -999,6 +999,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
 #ifdef CONFIG_SCHED_MM_CID
 	tsk->mm_cid.cid = MM_CID_UNSET;
 	tsk->mm_cid.active = 0;
+	INIT_HLIST_NODE(&tsk->mm_cid.node);
 #endif
 	return tsk;
 
@@ -1585,7 +1586,6 @@ static int copy_mm(u64 clone_flags, struct task_struct *tsk)
 
 	tsk->mm = mm;
 	tsk->active_mm = mm;
-	sched_mm_cid_fork(tsk);
 	return 0;
 }
 
@@ -2496,7 +2496,6 @@ bad_fork_cleanup_namespaces:
 	exit_nsproxy_namespaces(p);
 bad_fork_cleanup_mm:
 	if (p->mm) {
-		sched_mm_cid_exit(p);
 		mm_clear_owner(p->mm, p);
 		mmput(p->mm);
 	}
@@ -3082,7 +3081,7 @@ static int unshare_fs(unsigned long unshare_flags, struct fs_struct **new_fsp)
 		return 0;
 
 	/* don't need lock here; in the worst case we'll do useless copy */
-	if (fs->users == 1)
+	if (!(unshare_flags & CLONE_NEWNS) && fs->users == 1)
 		return 0;
 
 	*new_fsp = copy_fs_struct(fs);
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index ab8f9fc1f0d1..87e6f4d61b95 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -1070,12 +1070,12 @@ static int __arm_kprobe_ftrace(struct kprobe *p, struct ftrace_ops *ops,
 	lockdep_assert_held(&kprobe_mutex);
 
 	ret = ftrace_set_filter_ip(ops, (unsigned long)p->addr, 0, 0);
-	if (WARN_ONCE(ret < 0, "Failed to arm kprobe-ftrace at %pS (error %d)\n", p->addr, ret))
+	if (ret < 0)
 		return ret;
 
 	if (*cnt == 0) {
 		ret = register_ftrace_function(ops);
-		if (WARN(ret < 0, "Failed to register kprobe-ftrace (error %d)\n", ret)) {
+		if (ret < 0) {
 			/*
 			 * At this point, sinec ops is not registered, we should be sefe from
 			 * registering empty filter.
@@ -1104,6 +1104,10 @@ static int __disarm_kprobe_ftrace(struct kprobe *p, struct ftrace_ops *ops,
 	int ret;
 
 	lockdep_assert_held(&kprobe_mutex);
+	if (unlikely(kprobe_ftrace_disabled)) {
+		/* Now ftrace is disabled forever, disarm is already done. */
+		return 0;
+	}
 
 	if (*cnt == 1) {
 		ret = unregister_ftrace_function(ops);
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 39511dd2abc9..9f5d3efa7a2f 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -85,24 +85,6 @@ static inline struct kthread *to_kthread(struct task_struct *k)
 	return k->worker_private;
 }
 
-/*
- * Variant of to_kthread() that doesn't assume @p is a kthread.
- *
- * When "(p->flags & PF_KTHREAD)" is set the task is a kthread and will
- * always remain a kthread.  For kthreads p->worker_private always
- * points to a struct kthread.  For tasks that are not kthreads
- * p->worker_private is used to point to other things.
- *
- * Return NULL for any task that is not a kthread.
- */
-static inline struct kthread *__to_kthread(struct task_struct *p)
-{
-	void *kthread = p->worker_private;
-	if (kthread && !(p->flags & PF_KTHREAD))
-		kthread = NULL;
-	return kthread;
-}
-
 void get_kthread_comm(char *buf, size_t buf_size, struct task_struct *tsk)
 {
 	struct kthread *kthread = to_kthread(tsk);
@@ -193,7 +175,7 @@ EXPORT_SYMBOL_GPL(kthread_should_park);
 
 bool kthread_should_stop_or_park(void)
 {
-	struct kthread *kthread = __to_kthread(current);
+	struct kthread *kthread = tsk_is_kthread(current);
 
 	if (!kthread)
 		return false;
@@ -234,7 +216,7 @@ EXPORT_SYMBOL_GPL(kthread_freezable_should_stop);
  */
 void *kthread_func(struct task_struct *task)
 {
-	struct kthread *kthread = __to_kthread(task);
+	struct kthread *kthread = tsk_is_kthread(task);
 	if (kthread)
 		return kthread->threadfn;
 	return NULL;
@@ -266,7 +248,7 @@ EXPORT_SYMBOL_GPL(kthread_data);
  */
 void *kthread_probe_data(struct task_struct *task)
 {
-	struct kthread *kthread = __to_kthread(task);
+	struct kthread *kthread = tsk_is_kthread(task);
 	void *data = NULL;
 
 	if (kthread)
@@ -309,19 +291,8 @@ void kthread_parkme(void)
 }
 EXPORT_SYMBOL_GPL(kthread_parkme);
 
-/**
- * kthread_exit - Cause the current kthread return @result to kthread_stop().
- * @result: The integer value to return to kthread_stop().
- *
- * While kthread_exit can be called directly, it exists so that
- * functions which do some additional work in non-modular code such as
- * module_put_and_kthread_exit can be implemented.
- *
- * Does not return.
- */
-void __noreturn kthread_exit(long result)
+void kthread_do_exit(struct kthread *kthread, long result)
 {
-	struct kthread *kthread = to_kthread(current);
 	kthread->result = result;
 	if (!list_empty(&kthread->hotplug_node)) {
 		mutex_lock(&kthreads_hotplug_lock);
@@ -333,9 +304,7 @@ void __noreturn kthread_exit(long result)
 			kthread->preferred_affinity = NULL;
 		}
 	}
-	do_exit(0);
 }
-EXPORT_SYMBOL(kthread_exit);
 
 /**
  * kthread_complete_and_exit - Exit the current kthread.
@@ -680,7 +649,7 @@ void kthread_set_per_cpu(struct task_struct *k, int cpu)
 
 bool kthread_is_per_cpu(struct task_struct *p)
 {
-	struct kthread *kthread = __to_kthread(p);
+	struct kthread *kthread = tsk_is_kthread(p);
 	if (!kthread)
 		return false;
 
diff --git a/kernel/liveupdate/luo_file.c b/kernel/liveupdate/luo_file.c
index 9f7283379ebc..6d0370107878 100644
--- a/kernel/liveupdate/luo_file.c
+++ b/kernel/liveupdate/luo_file.c
@@ -133,9 +133,12 @@ static LIST_HEAD(luo_file_handler_list);
  *                 state that is not preserved. Set by the handler's .preserve()
  *                 callback, and must be freed in the handler's .unpreserve()
  *                 callback.
- * @retrieved:     A flag indicating whether a user/kernel in the new kernel has
+ * @retrieve_status: Status code indicating whether a user/kernel in the new kernel has
  *                 successfully called retrieve() on this file. This prevents
- *                 multiple retrieval attempts.
+ *                 multiple retrieval attempts. A value of 0 means a retrieve()
+ *                 has not been attempted, a positive value means the retrieve()
+ *                 was successful, and a negative value means the retrieve()
+ *                 failed, and the value is the error code of the call.
  * @mutex:         A mutex that protects the fields of this specific instance
  *                 (e.g., @retrieved, @file), ensuring that operations like
  *                 retrieving or finishing a file are atomic.
@@ -160,7 +163,7 @@ struct luo_file {
 	struct file *file;
 	u64 serialized_data;
 	void *private_data;
-	bool retrieved;
+	int retrieve_status;
 	struct mutex mutex;
 	struct list_head list;
 	u64 token;
@@ -293,7 +296,6 @@ int luo_preserve_file(struct luo_file_set *file_set, u64 token, int fd)
 	luo_file->file = file;
 	luo_file->fh = fh;
 	luo_file->token = token;
-	luo_file->retrieved = false;
 	mutex_init(&luo_file->mutex);
 
 	args.handler = fh;
@@ -569,7 +571,12 @@ int luo_retrieve_file(struct luo_file_set *file_set, u64 token,
 		return -ENOENT;
 
 	guard(mutex)(&luo_file->mutex);
-	if (luo_file->retrieved) {
+	if (luo_file->retrieve_status < 0) {
+		/* Retrieve was attempted and it failed. Return the error code. */
+		return luo_file->retrieve_status;
+	}
+
+	if (luo_file->retrieve_status > 0) {
 		/*
 		 * Someone is asking for this file again, so get a reference
 		 * for them.
@@ -582,16 +589,19 @@ int luo_retrieve_file(struct luo_file_set *file_set, u64 token,
 	args.handler = luo_file->fh;
 	args.serialized_data = luo_file->serialized_data;
 	err = luo_file->fh->ops->retrieve(&args);
-	if (!err) {
-		luo_file->file = args.file;
-
-		/* Get reference so we can keep this file in LUO until finish */
-		get_file(luo_file->file);
-		*filep = luo_file->file;
-		luo_file->retrieved = true;
+	if (err) {
+		/* Keep the error code for later use. */
+		luo_file->retrieve_status = err;
+		return err;
 	}
 
-	return err;
+	luo_file->file = args.file;
+	/* Get reference so we can keep this file in LUO until finish */
+	get_file(luo_file->file);
+	*filep = luo_file->file;
+	luo_file->retrieve_status = 1;
+
+	return 0;
 }
 
 static int luo_file_can_finish_one(struct luo_file_set *file_set,
@@ -607,7 +617,7 @@ static int luo_file_can_finish_one(struct luo_file_set *file_set,
 		args.handler = luo_file->fh;
 		args.file = luo_file->file;
 		args.serialized_data = luo_file->serialized_data;
-		args.retrieved = luo_file->retrieved;
+		args.retrieve_status = luo_file->retrieve_status;
 		can_finish = luo_file->fh->ops->can_finish(&args);
 	}
 
@@ -624,7 +634,7 @@ static void luo_file_finish_one(struct luo_file_set *file_set,
 	args.handler = luo_file->fh;
 	args.file = luo_file->file;
 	args.serialized_data = luo_file->serialized_data;
-	args.retrieved = luo_file->retrieved;
+	args.retrieve_status = luo_file->retrieve_status;
 
 	luo_file->fh->ops->finish(&args);
 }
@@ -779,7 +789,6 @@ int luo_file_deserialize(struct luo_file_set *file_set,
 		luo_file->file = NULL;
 		luo_file->serialized_data = file_ser[i].data;
 		luo_file->token = file_ser[i].token;
-		luo_file->retrieved = false;
 		mutex_init(&luo_file->mutex);
 		list_add_tail(&luo_file->list, &file_set->files_list);
 	}
diff --git a/kernel/nscommon.c b/kernel/nscommon.c
index bdc3c86231d3..3166c1fd844a 100644
--- a/kernel/nscommon.c
+++ b/kernel/nscommon.c
@@ -309,3 +309,9 @@ void __ns_ref_active_get(struct ns_common *ns)
 			return;
 	}
 }
+
+bool may_see_all_namespaces(void)
+{
+	return (task_active_pid_ns(current) == &init_pid_ns) &&
+	       ns_capable_noaudit(init_pid_ns.user_ns, CAP_SYS_ADMIN);
+}
diff --git a/kernel/nstree.c b/kernel/nstree.c
index f36c59e6951d..6d12e5900ac0 100644
--- a/kernel/nstree.c
+++ b/kernel/nstree.c
@@ -515,32 +515,11 @@ static inline bool __must_check ns_requested(const struct klistns *kls,
 static inline bool __must_check may_list_ns(const struct klistns *kls,
 					    struct ns_common *ns)
 {
-	if (kls->user_ns) {
-		if (kls->userns_capable)
-			return true;
-	} else {
-		struct ns_common *owner;
-		struct user_namespace *user_ns;
-
-		owner = ns_owner(ns);
-		if (owner)
-			user_ns = to_user_ns(owner);
-		else
-			user_ns = &init_user_ns;
-		if (ns_capable_noaudit(user_ns, CAP_SYS_ADMIN))
-			return true;
-	}
-
-	if (is_current_namespace(ns))
+	if (kls->user_ns && kls->userns_capable)
 		return true;
-
-	if (ns->ns_type != CLONE_NEWUSER)
-		return false;
-
-	if (ns_capable_noaudit(to_user_ns(ns), CAP_SYS_ADMIN))
+	if (is_current_namespace(ns))
 		return true;
-
-	return false;
+	return may_see_all_namespaces();
 }
 
 static inline void ns_put(struct ns_common *ns)
@@ -600,7 +579,7 @@ static ssize_t do_listns_userns(struct klistns *kls)
 
 	ret = 0;
 	head = &to_ns_common(kls->user_ns)->ns_owner_root.ns_list_head;
-	kls->userns_capable = ns_capable_noaudit(kls->user_ns, CAP_SYS_ADMIN);
+	kls->userns_capable = may_see_all_namespaces();
 
 	rcu_read_lock();
 
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:
diff --git a/kernel/time/time.c b/kernel/time/time.c
index 0ba8e3c50d62..155cf7def914 100644
--- a/kernel/time/time.c
+++ b/kernel/time/time.c
@@ -702,7 +702,7 @@ EXPORT_SYMBOL(clock_t_to_jiffies);
  *
  * Return: jiffies_64 value converted to 64-bit "clock_t" (CLOCKS_PER_SEC)
  */
-u64 jiffies_64_to_clock_t(u64 x)
+notrace u64 jiffies_64_to_clock_t(u64 x)
 {
 #if (TICK_NSEC % (NSEC_PER_SEC / USER_HZ)) == 0
 # if HZ < USER_HZ
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 325579c7da26..e448a2553f7c 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -2441,8 +2441,10 @@ static void bpf_kprobe_multi_show_fdinfo(const struct bpf_link *link,
 					 struct seq_file *seq)
 {
 	struct bpf_kprobe_multi_link *kmulti_link;
+	bool has_cookies;
 
 	kmulti_link = container_of(link, struct bpf_kprobe_multi_link, link);
+	has_cookies = !!kmulti_link->cookies;
 
 	seq_printf(seq,
 		   "kprobe_cnt:\t%u\n"
@@ -2454,7 +2456,7 @@ static void bpf_kprobe_multi_show_fdinfo(const struct bpf_link *link,
 	for (int i = 0; i < kmulti_link->cnt; i++) {
 		seq_printf(seq,
 			   "%llu\t %pS\n",
-			   kmulti_link->cookies[i],
+			   has_cookies ? kmulti_link->cookies[i] : 0,
 			   (void *)kmulti_link->addrs[i]);
 	}
 }
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index bce112e1bbba..04c81fbf483f 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -10136,7 +10136,7 @@ static void setup_trace_scratch(struct trace_array *tr,
 }
 
 static int
-allocate_trace_buffer(struct trace_array *tr, struct array_buffer *buf, int size)
+allocate_trace_buffer(struct trace_array *tr, struct array_buffer *buf, unsigned long size)
 {
 	enum ring_buffer_flags rb_flags;
 	struct trace_scratch *tscratch;
@@ -10191,7 +10191,7 @@ static void free_trace_buffer(struct array_buffer *buf)
 	}
 }
 
-static int allocate_trace_buffers(struct trace_array *tr, int size)
+static int allocate_trace_buffers(struct trace_array *tr, unsigned long size)
 {
 	int ret;
 
@@ -11557,7 +11557,7 @@ __init static void enable_instances(void)
 
 __init static int tracer_alloc_buffers(void)
 {
-	int ring_buf_size;
+	unsigned long ring_buf_size;
 	int ret = -ENOMEM;
 
 
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index ec6617063710..1833c2a42aa9 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -4341,7 +4341,11 @@ static char bootup_event_buf[COMMAND_LINE_SIZE] __initdata;
 
 static __init int setup_trace_event(char *str)
 {
-	strscpy(bootup_event_buf, str, COMMAND_LINE_SIZE);
+	if (bootup_event_buf[0] != '\0')
+		strlcat(bootup_event_buf, ",", COMMAND_LINE_SIZE);
+
+	strlcat(bootup_event_buf, str, COMMAND_LINE_SIZE);
+
 	trace_set_ring_buffer_expanded(NULL);
 	disable_tracing_selftest("running event tracing");
 
@@ -4512,26 +4516,22 @@ static __init int event_trace_memsetup(void)
 	return 0;
 }
 
-__init void
-early_enable_events(struct trace_array *tr, char *buf, bool disable_first)
+/*
+ * Helper function to enable or disable a comma-separated list of events
+ * from the bootup buffer.
+ */
+static __init void __early_set_events(struct trace_array *tr, char *buf, bool enable)
 {
 	char *token;
-	int ret;
-
-	while (true) {
-		token = strsep(&buf, ",");
-
-		if (!token)
-			break;
 
+	while ((token = strsep(&buf, ","))) {
 		if (*token) {
-			/* Restarting syscalls requires that we stop them first */
-			if (disable_first)
+			if (enable) {
+				if (ftrace_set_clr_event(tr, token, 1))
+					pr_warn("Failed to enable trace event: %s\n", token);
+			} else {
 				ftrace_set_clr_event(tr, token, 0);
-
-			ret = ftrace_set_clr_event(tr, token, 1);
-			if (ret)
-				pr_warn("Failed to enable trace event: %s\n", token);
+			}
 		}
 
 		/* Put back the comma to allow this to be called again */
@@ -4540,6 +4540,32 @@ early_enable_events(struct trace_array *tr, char *buf, bool disable_first)
 	}
 }
 
+/**
+ * early_enable_events - enable events from the bootup buffer
+ * @tr: The trace array to enable the events in
+ * @buf: The buffer containing the comma separated list of events
+ * @disable_first: If true, disable all events in @buf before enabling them
+ *
+ * This function enables events from the bootup buffer. If @disable_first
+ * is true, it will first disable all events in the buffer before enabling
+ * them.
+ *
+ * For syscall events, which rely on a global refcount to register the
+ * SYSCALL_WORK_SYSCALL_TRACEPOINT flag (especially for pid 1), we must
+ * ensure the refcount hits zero before re-enabling them. A simple
+ * "disable then enable" per-event is not enough if multiple syscalls are
+ * used, as the refcount will stay above zero. Thus, we need a two-phase
+ * approach: disable all, then enable all.
+ */
+__init void
+early_enable_events(struct trace_array *tr, char *buf, bool disable_first)
+{
+	if (disable_first)
+		__early_set_events(tr, buf, false);
+
+	__early_set_events(tr, buf, true);
+}
+
 static __init int event_trace_enable(void)
 {
 	struct trace_array *tr = top_trace_array();
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 1de6f1573621..b9c81fbd98dc 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -400,14 +400,19 @@ static void trace_graph_thresh_return(struct ftrace_graph_ret *trace,
 				      struct fgraph_ops *gops,
 				      struct ftrace_regs *fregs)
 {
+	unsigned long *task_var = fgraph_get_task_var(gops);
 	struct fgraph_times *ftimes;
 	struct trace_array *tr;
+	unsigned int trace_ctx;
+	u64 calltime, rettime;
 	int size;
 
+	rettime = trace_clock_local();
+
 	ftrace_graph_addr_finish(gops, trace);
 
-	if (trace_recursion_test(TRACE_GRAPH_NOTRACE_BIT)) {
-		trace_recursion_clear(TRACE_GRAPH_NOTRACE_BIT);
+	if (*task_var & TRACE_GRAPH_NOTRACE) {
+		*task_var &= ~TRACE_GRAPH_NOTRACE;
 		return;
 	}
 
@@ -418,11 +423,13 @@ static void trace_graph_thresh_return(struct ftrace_graph_ret *trace,
 	tr = gops->private;
 	handle_nosleeptime(tr, trace, ftimes, size);
 
-	if (tracing_thresh &&
-	    (trace_clock_local() - ftimes->calltime < tracing_thresh))
+	calltime = ftimes->calltime;
+
+	if (tracing_thresh && (rettime - calltime < tracing_thresh))
 		return;
-	else
-		trace_graph_return(trace, gops, fregs);
+
+	trace_ctx = tracing_gen_ctx();
+	__trace_graph_return(tr, trace, trace_ctx, calltime, rettime);
 }
 
 static struct fgraph_ops funcgraph_ops = {
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 2909c19540ed..a4574c1e276a 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -6254,7 +6254,7 @@ static void pr_cont_worker_id(struct worker *worker)
 {
 	struct worker_pool *pool = worker->pool;
 
-	if (pool->flags & WQ_BH)
+	if (pool->flags & POOL_BH)
 		pr_cont("bh%s",
 			pool->attrs->nice == HIGHPRI_NICE_LEVEL ? "-hi" : "");
 	else