Merge branch 'linus' into sched/urgent, to resolve conflict

 Conflicts:
	kernel/sched/ext.c

There's a context conflict between this upstream commit:

  3fdb9ebcec10 sched_ext: Start schedulers with consistent p->scx.slice values

... and this fix in sched/urgent:

  98442f0ccd82 sched: Fix delayed_dequeue vs switched_from_fair()

Resolve it.

Signed-off-by: Ingo Molnar <mingo@kernel.org>

15 files changed, 257 insertions, 182 deletions

diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 4e07cc057d6f..5e77c58e0601 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -40,7 +40,7 @@
 #include <linux/execmem.h>
 
 #include <asm/barrier.h>
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
 
 /* Registers */
 #define BPF_R0	regs[BPF_REG_0]
diff --git a/kernel/debug/gdbstub.c b/kernel/debug/gdbstub.c
index 9d34d2364b5a..f625172d4b67 100644
--- a/kernel/debug/gdbstub.c
+++ b/kernel/debug/gdbstub.c
@@ -33,7 +33,7 @@
 #include <linux/reboot.h>
 #include <linux/uaccess.h>
 #include <asm/cacheflush.h>
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
 #include "debug_core.h"
 
 #define KGDB_MAX_THREAD_QUERY 17
diff --git a/kernel/fork.c b/kernel/fork.c
index 60c0b4868fd4..89ceb4a68af2 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1756,33 +1756,30 @@ static int copy_files(unsigned long clone_flags, struct task_struct *tsk,
 		      int no_files)
 {
 	struct files_struct *oldf, *newf;
-	int error = 0;
 
 	/*
 	 * A background process may not have any files ...
 	 */
 	oldf = current->files;
 	if (!oldf)
-		goto out;
+		return 0;
 
 	if (no_files) {
 		tsk->files = NULL;
-		goto out;
+		return 0;
 	}
 
 	if (clone_flags & CLONE_FILES) {
 		atomic_inc(&oldf->count);
-		goto out;
+		return 0;
 	}
 
-	newf = dup_fd(oldf, NR_OPEN_MAX, &error);
-	if (!newf)
-		goto out;
+	newf = dup_fd(oldf, NULL);
+	if (IS_ERR(newf))
+		return PTR_ERR(newf);
 
 	tsk->files = newf;
-	error = 0;
-out:
-	return error;
+	return 0;
 }
 
 static int copy_sighand(unsigned long clone_flags, struct task_struct *tsk)
@@ -3238,17 +3235,16 @@ static int unshare_fs(unsigned long unshare_flags, struct fs_struct **new_fsp)
 /*
  * Unshare file descriptor table if it is being shared
  */
-int unshare_fd(unsigned long unshare_flags, unsigned int max_fds,
-	       struct files_struct **new_fdp)
+static int unshare_fd(unsigned long unshare_flags, struct files_struct **new_fdp)
 {
 	struct files_struct *fd = current->files;
-	int error = 0;
 
 	if ((unshare_flags & CLONE_FILES) &&
 	    (fd && atomic_read(&fd->count) > 1)) {
-		*new_fdp = dup_fd(fd, max_fds, &error);
-		if (!*new_fdp)
-			return error;
+		fd = dup_fd(fd, NULL);
+		if (IS_ERR(fd))
+			return PTR_ERR(fd);
+		*new_fdp = fd;
 	}
 
 	return 0;
@@ -3306,7 +3302,7 @@ int ksys_unshare(unsigned long unshare_flags)
 	err = unshare_fs(unshare_flags, &new_fs);
 	if (err)
 		goto bad_unshare_out;
-	err = unshare_fd(unshare_flags, NR_OPEN_MAX, &new_fd);
+	err = unshare_fd(unshare_flags, &new_fd);
 	if (err)
 		goto bad_unshare_cleanup_fs;
 	err = unshare_userns(unshare_flags, &new_cred);
@@ -3398,7 +3394,7 @@ int unshare_files(void)
 	struct files_struct *old, *copy = NULL;
 	int error;
 
-	error = unshare_fd(CLONE_FILES, NR_OPEN_MAX, &copy);
+	error = unshare_fd(CLONE_FILES, &copy);
 	if (error || !copy)
 		return error;
 
diff --git a/kernel/kthread.c b/kernel/kthread.c
index db4ceb0f503c..9bb36897b6c6 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -623,6 +623,8 @@ void kthread_unpark(struct task_struct *k)
 {
 	struct kthread *kthread = to_kthread(k);
 
+	if (!test_bit(KTHREAD_SHOULD_PARK, &kthread->flags))
+		return;
 	/*
 	 * Newly created kthread was parked when the CPU was offline.
 	 * The binding was lost and we need to set it again.
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index a60616e69b66..b1f883fcd918 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -3607,11 +3607,12 @@ kvfree_rcu_queue_batch(struct kfree_rcu_cpu *krcp)
 			}
 
 			// One work is per one batch, so there are three
-			// "free channels", the batch can handle. It can
-			// be that the work is in the pending state when
-			// channels have been detached following by each
-			// other.
+			// "free channels", the batch can handle. Break
+			// the loop since it is done with this CPU thus
+			// queuing an RCU work is _always_ success here.
 			queued = queue_rcu_work(system_unbound_wq, &krwp->rcu_work);
+			WARN_ON_ONCE(!queued);
+			break;
 		}
 	}
 
diff --git a/kernel/rcu/tree_nocb.h b/kernel/rcu/tree_nocb.h
index 97b99cd06923..16865475120b 100644
--- a/kernel/rcu/tree_nocb.h
+++ b/kernel/rcu/tree_nocb.h
@@ -554,13 +554,19 @@ static void __call_rcu_nocb_wake(struct rcu_data *rdp, bool was_alldone,
 			rcu_nocb_unlock(rdp);
 			wake_nocb_gp_defer(rdp, RCU_NOCB_WAKE_LAZY,
 					   TPS("WakeLazy"));
-		} else if (!irqs_disabled_flags(flags)) {
+		} else if (!irqs_disabled_flags(flags) && cpu_online(rdp->cpu)) {
 			/* ... if queue was empty ... */
 			rcu_nocb_unlock(rdp);
 			wake_nocb_gp(rdp, false);
 			trace_rcu_nocb_wake(rcu_state.name, rdp->cpu,
 					    TPS("WakeEmpty"));
 		} else {
+			/*
+			 * Don't do the wake-up upfront on fragile paths.
+			 * Also offline CPUs can't call swake_up_one_online() from
+			 * (soft-)IRQs. Rely on the final deferred wake-up from
+			 * rcutree_report_cpu_dead()
+			 */
 			rcu_nocb_unlock(rdp);
 			wake_nocb_gp_defer(rdp, RCU_NOCB_WAKE,
 					   TPS("WakeEmptyIsDeferred"));
diff --git a/kernel/resource_kunit.c b/kernel/resource_kunit.c
index 42d2d8d20f5d..b8ef75b99eb2 100644
--- a/kernel/resource_kunit.c
+++ b/kernel/resource_kunit.c
@@ -169,6 +169,8 @@ static void resource_test_intersection(struct kunit *test)
 #define RES_TEST_RAM3_SIZE	SZ_1M
 #define RES_TEST_TOTAL_SIZE	((RES_TEST_WIN1_OFFSET + RES_TEST_WIN1_SIZE))
 
+KUNIT_DEFINE_ACTION_WRAPPER(kfree_wrapper, kfree, const void *);
+
 static void remove_free_resource(void *ctx)
 {
 	struct resource *res = (struct resource *)ctx;
@@ -177,6 +179,14 @@ static void remove_free_resource(void *ctx)
 	kfree(res);
 }
 
+static void resource_test_add_action_or_abort(
+	struct kunit *test, void (*action)(void *), void *ctx)
+{
+	KUNIT_ASSERT_EQ_MSG(test, 0,
+			    kunit_add_action_or_reset(test, action, ctx),
+			    "Fail to add action");
+}
+
 static void resource_test_request_region(struct kunit *test, struct resource *parent,
 					 resource_size_t start, resource_size_t size,
 					 const char *name, unsigned long flags)
@@ -185,7 +195,7 @@ static void resource_test_request_region(struct kunit *test, struct resource *pa
 
 	res = __request_region(parent, start, size, name, flags);
 	KUNIT_ASSERT_NOT_NULL(test, res);
-	kunit_add_action_or_reset(test, remove_free_resource, res);
+	resource_test_add_action_or_abort(test, remove_free_resource, res);
 }
 
 static void resource_test_insert_resource(struct kunit *test, struct resource *parent,
@@ -202,11 +212,11 @@ static void resource_test_insert_resource(struct kunit *test, struct resource *p
 	res->end = start + size - 1;
 	res->flags = flags;
 	if (insert_resource(parent, res)) {
-		kfree(res);
+		resource_test_add_action_or_abort(test, kfree_wrapper, res);
 		KUNIT_FAIL_AND_ABORT(test, "Fail to insert resource %pR\n", res);
 	}
 
-	kunit_add_action_or_reset(test, remove_free_resource, res);
+	resource_test_add_action_or_abort(test, remove_free_resource, res);
 }
 
 static void resource_test_region_intersects(struct kunit *test)
@@ -220,7 +230,7 @@ static void resource_test_region_intersects(struct kunit *test)
 				       "test resources");
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, parent);
 	start = parent->start;
-	kunit_add_action_or_reset(test, remove_free_resource, parent);
+	resource_test_add_action_or_abort(test, remove_free_resource, parent);
 
 	resource_test_request_region(test, parent, start + RES_TEST_RAM0_OFFSET,
 				     RES_TEST_RAM0_SIZE, "Test System RAM 0", flags);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 7db711ba6d12..dbfb5717d6af 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3523,14 +3523,16 @@ 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
@@ -3664,6 +3666,8 @@ 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
@@ -4125,6 +4129,8 @@ 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)
@@ -4257,7 +4263,7 @@ 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);
@@ -4799,6 +4805,7 @@ 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);
@@ -4813,7 +4820,7 @@ 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);
@@ -4821,7 +4828,7 @@ 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 6f9de573ee93..5900b06fd036 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -9,7 +9,6 @@
 #define SCX_OP_IDX(op)		(offsetof(struct sched_ext_ops, op) / sizeof(void (*)(void)))
 
 enum scx_consts {
-	SCX_SLICE_BYPASS		= SCX_SLICE_DFL / 4,
 	SCX_DSP_DFL_MAX_BATCH		= 32,
 	SCX_DSP_MAX_LOOPS		= 32,
 	SCX_WATCHDOG_MAX_TIMEOUT	= 30 * HZ,
@@ -19,6 +18,12 @@ enum scx_consts {
 	SCX_EXIT_DUMP_DFL_LEN		= 32768,
 
 	SCX_CPUPERF_ONE			= SCHED_CAPACITY_SCALE,
+
+	/*
+	 * Iterating all tasks may take a while. Periodically drop
+	 * scx_tasks_lock to avoid causing e.g. CSD and RCU stalls.
+	 */
+	SCX_OPS_TASK_ITER_BATCH		= 32,
 };
 
 enum scx_exit_kind {
@@ -625,6 +630,10 @@ 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 +701,7 @@ 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 */
 
@@ -1269,86 +1279,104 @@ struct scx_task_iter {
 	struct task_struct		*locked;
 	struct rq			*rq;
 	struct rq_flags			rf;
+	u32				cnt;
 };
 
 /**
- * scx_task_iter_init - Initialize a task iterator
+ * scx_task_iter_start - Lock scx_tasks_lock and start a task iteration
  * @iter: iterator to init
  *
- * Initialize @iter. Must be called with scx_tasks_lock held. Once initialized,
- * @iter must eventually be exited with scx_task_iter_exit().
+ * Initialize @iter and return with scx_tasks_lock held. Once initialized, @iter
+ * must eventually be stopped with scx_task_iter_stop().
  *
- * scx_tasks_lock may be released between this and the first next() call or
- * between any two next() calls. If scx_tasks_lock is released between two
- * next() calls, the caller is responsible for ensuring that the task being
- * iterated remains accessible either through RCU read lock or obtaining a
- * reference count.
+ * scx_tasks_lock and the rq lock may be released using scx_task_iter_unlock()
+ * between this and the first next() call or between any two next() calls. If
+ * the locks are released between two next() calls, the caller is responsible
+ * for ensuring that the task being iterated remains accessible either through
+ * RCU read lock or obtaining a reference count.
  *
  * All tasks which existed when the iteration started are guaranteed to be
  * visited as long as they still exist.
  */
-static void scx_task_iter_init(struct scx_task_iter *iter)
+static void scx_task_iter_start(struct scx_task_iter *iter)
 {
-	lockdep_assert_held(&scx_tasks_lock);
-
 	BUILD_BUG_ON(__SCX_DSQ_ITER_ALL_FLAGS &
 		     ((1U << __SCX_DSQ_LNODE_PRIV_SHIFT) - 1));
 
+	spin_lock_irq(&scx_tasks_lock);
+
 	iter->cursor = (struct sched_ext_entity){ .flags = SCX_TASK_CURSOR };
 	list_add(&iter->cursor.tasks_node, &scx_tasks);
 	iter->locked = NULL;
+	iter->cnt = 0;
+}
+
+static void __scx_task_iter_rq_unlock(struct scx_task_iter *iter)
+{
+	if (iter->locked) {
+		task_rq_unlock(iter->rq, iter->locked, &iter->rf);
+		iter->locked = NULL;
+	}
 }
 
 /**
- * scx_task_iter_rq_unlock - Unlock rq locked by a task iterator
- * @iter: iterator to unlock rq for
+ * scx_task_iter_unlock - Unlock rq and scx_tasks_lock held by a task iterator
+ * @iter: iterator to unlock
  *
  * If @iter is in the middle of a locked iteration, it may be locking the rq of
- * the task currently being visited. Unlock the rq if so. This function can be
- * safely called anytime during an iteration.
+ * the task currently being visited in addition to scx_tasks_lock. Unlock both.
+ * This function can be safely called anytime during an iteration.
+ */
+static void scx_task_iter_unlock(struct scx_task_iter *iter)
+{
+	__scx_task_iter_rq_unlock(iter);
+	spin_unlock_irq(&scx_tasks_lock);
+}
+
+/**
+ * scx_task_iter_relock - Lock scx_tasks_lock released by scx_task_iter_unlock()
+ * @iter: iterator to re-lock
  *
- * Returns %true if the rq @iter was locking is unlocked. %false if @iter was
- * not locking an rq.
+ * Re-lock scx_tasks_lock unlocked by scx_task_iter_unlock(). Note that it
+ * doesn't re-lock the rq lock. Must be called before other iterator operations.
  */
-static bool scx_task_iter_rq_unlock(struct scx_task_iter *iter)
+static void scx_task_iter_relock(struct scx_task_iter *iter)
 {
-	if (iter->locked) {
-		task_rq_unlock(iter->rq, iter->locked, &iter->rf);
-		iter->locked = NULL;
-		return true;
-	} else {
-		return false;
-	}
+	spin_lock_irq(&scx_tasks_lock);
 }
 
 /**
- * scx_task_iter_exit - Exit a task iterator
+ * scx_task_iter_stop - Stop a task iteration and unlock scx_tasks_lock
  * @iter: iterator to exit
  *
- * Exit a previously initialized @iter. Must be called with scx_tasks_lock held.
- * If the iterator holds a task's rq lock, that rq lock is released. See
- * scx_task_iter_init() for details.
+ * Exit a previously initialized @iter. Must be called with scx_tasks_lock held
+ * which is released on return. If the iterator holds a task's rq lock, that rq
+ * lock is also released. See scx_task_iter_start() for details.
  */
-static void scx_task_iter_exit(struct scx_task_iter *iter)
+static void scx_task_iter_stop(struct scx_task_iter *iter)
 {
-	lockdep_assert_held(&scx_tasks_lock);
-
-	scx_task_iter_rq_unlock(iter);
 	list_del_init(&iter->cursor.tasks_node);
+	scx_task_iter_unlock(iter);
 }
 
 /**
  * scx_task_iter_next - Next task
  * @iter: iterator to walk
  *
- * Visit the next task. See scx_task_iter_init() for details.
+ * Visit the next task. See scx_task_iter_start() for details. Locks are dropped
+ * and re-acquired every %SCX_OPS_TASK_ITER_BATCH iterations to avoid causing
+ * stalls by holding scx_tasks_lock for too long.
  */
 static struct task_struct *scx_task_iter_next(struct scx_task_iter *iter)
 {
 	struct list_head *cursor = &iter->cursor.tasks_node;
 	struct sched_ext_entity *pos;
 
-	lockdep_assert_held(&scx_tasks_lock);
+	if (!(++iter->cnt % SCX_OPS_TASK_ITER_BATCH)) {
+		scx_task_iter_unlock(iter);
+		cond_resched();
+		scx_task_iter_relock(iter);
+	}
 
 	list_for_each_entry(pos, cursor, tasks_node) {
 		if (&pos->tasks_node == &scx_tasks)
@@ -1369,14 +1397,14 @@ static struct task_struct *scx_task_iter_next(struct scx_task_iter *iter)
  * @include_dead: Whether we should include dead tasks in the iteration
  *
  * Visit the non-idle task with its rq lock held. Allows callers to specify
- * whether they would like to filter out dead tasks. See scx_task_iter_init()
+ * whether they would like to filter out dead tasks. See scx_task_iter_start()
  * for details.
  */
 static struct task_struct *scx_task_iter_next_locked(struct scx_task_iter *iter)
 {
 	struct task_struct *p;
 
-	scx_task_iter_rq_unlock(iter);
+	__scx_task_iter_rq_unlock(iter);
 
 	while ((p = scx_task_iter_next(iter))) {
 		/*
@@ -1944,7 +1972,6 @@ static bool scx_rq_online(struct rq *rq)
 static void do_enqueue_task(struct rq *rq, struct task_struct *p, u64 enq_flags,
 			    int sticky_cpu)
 {
-	bool bypassing = scx_rq_bypassing(rq);
 	struct task_struct **ddsp_taskp;
 	unsigned long qseq;
 
@@ -1962,7 +1989,7 @@ static void do_enqueue_task(struct rq *rq, struct task_struct *p, u64 enq_flags,
 	if (!scx_rq_online(rq))
 		goto local;
 
-	if (bypassing)
+	if (scx_rq_bypassing(rq))
 		goto global;
 
 	if (p->scx.ddsp_dsq_id != SCX_DSQ_INVALID)
@@ -2017,7 +2044,7 @@ local_norefill:
 
 global:
 	touch_core_sched(rq, p);	/* see the comment in local: */
-	p->scx.slice = bypassing ? SCX_SLICE_BYPASS : SCX_SLICE_DFL;
+	p->scx.slice = SCX_SLICE_DFL;
 	dispatch_enqueue(find_global_dsq(p), p, enq_flags);
 }
 
@@ -2953,8 +2980,8 @@ static struct task_struct *pick_task_scx(struct rq *rq)
 
 		if (unlikely(!p->scx.slice)) {
 			if (!scx_rq_bypassing(rq) && !scx_warned_zero_slice) {
-				printk_deferred(KERN_WARNING "sched_ext: %s[%d] has zero slice in pick_next_task_scx()\n",
-						p->comm, p->pid);
+				printk_deferred(KERN_WARNING "sched_ext: %s[%d] has zero slice in %s()\n",
+						p->comm, p->pid, __func__);
 				scx_warned_zero_slice = true;
 			}
 			p->scx.slice = SCX_SLICE_DFL;
@@ -3059,11 +3086,6 @@ static s32 scx_select_cpu_dfl(struct task_struct *p, s32 prev_cpu,
 
 	*found = false;
 
-	if (!static_branch_likely(&scx_builtin_idle_enabled)) {
-		scx_ops_error("built-in idle tracking is disabled");
-		return prev_cpu;
-	}
-
 	/*
 	 * If WAKE_SYNC, the waker's local DSQ is empty, and the system is
 	 * under utilized, wake up @p to the local DSQ of the waker. Checking
@@ -3128,7 +3150,7 @@ static int select_task_rq_scx(struct task_struct *p, int prev_cpu, int wake_flag
 	if (unlikely(wake_flags & WF_EXEC))
 		return prev_cpu;
 
-	if (SCX_HAS_OP(select_cpu)) {
+	if (SCX_HAS_OP(select_cpu) && !scx_rq_bypassing(task_rq(p))) {
 		s32 cpu;
 		struct task_struct **ddsp_taskp;
 
@@ -3193,7 +3215,7 @@ void __scx_update_idle(struct rq *rq, bool idle)
 {
 	int cpu = cpu_of(rq);
 
-	if (SCX_HAS_OP(update_idle)) {
+	if (SCX_HAS_OP(update_idle) && !scx_rq_bypassing(rq)) {
 		SCX_CALL_OP(SCX_KF_REST, update_idle, cpu_of(rq), idle);
 		if (!static_branch_unlikely(&scx_builtin_idle_enabled))
 			return;
@@ -4048,7 +4070,6 @@ 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 +4138,7 @@ 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;
@@ -4256,21 +4278,23 @@ bool task_should_scx(struct task_struct *p)
  * the DISABLING state and then cycling the queued tasks through dequeue/enqueue
  * to force global FIFO scheduling.
  *
- * a. ops.enqueue() is ignored and tasks are queued in simple global FIFO order.
- *    %SCX_OPS_ENQ_LAST is also ignored.
+ * - ops.select_cpu() is ignored and the default select_cpu() is used.
+ *
+ * - ops.enqueue() is ignored and tasks are queued in simple global FIFO order.
+ *   %SCX_OPS_ENQ_LAST is also ignored.
  *
- * b. ops.dispatch() is ignored.
+ * - ops.dispatch() is ignored.
  *
- * c. balance_scx() does not set %SCX_RQ_BAL_KEEP on non-zero slice as slice
- *    can't be trusted. Whenever a tick triggers, the running task is rotated to
- *    the tail of the queue with core_sched_at touched.
+ * - balance_scx() does not set %SCX_RQ_BAL_KEEP on non-zero slice as slice
+ *   can't be trusted. Whenever a tick triggers, the running task is rotated to
+ *   the tail of the queue with core_sched_at touched.
  *
- * d. pick_next_task() suppresses zero slice warning.
+ * - pick_next_task() suppresses zero slice warning.
  *
- * e. scx_bpf_kick_cpu() is disabled to avoid irq_work malfunction during PM
- *    operations.
+ * - scx_bpf_kick_cpu() is disabled to avoid irq_work malfunction during PM
+ *   operations.
  *
- * f. scx_prio_less() reverts to the default core_sched_at order.
+ * - scx_prio_less() reverts to the default core_sched_at order.
  */
 static void scx_ops_bypass(bool bypass)
 {
@@ -4340,7 +4364,7 @@ static void scx_ops_bypass(bool bypass)
 
 		rq_unlock_irqrestore(rq, &rf);
 
-		/* kick to restore ticks */
+		/* resched to restore ticks and idle state */
 		resched_cpu(cpu);
 	}
 }
@@ -4462,15 +4486,13 @@ static void scx_ops_disable_workfn(struct kthread_work *work)
 
 	scx_ops_init_task_enabled = false;
 
-	spin_lock_irq(&scx_tasks_lock);
-	scx_task_iter_init(&sti);
+	scx_task_iter_start(&sti);
 	while ((p = scx_task_iter_next_locked(&sti))) {
 		const struct sched_class *old_class = p->sched_class;
 		struct sched_enq_and_set_ctx ctx;
 
 		sched_deq_and_put_task(p, DEQUEUE_SAVE | DEQUEUE_MOVE, &ctx);
 
-		p->scx.slice = min_t(u64, p->scx.slice, SCX_SLICE_DFL);
 		p->sched_class = __setscheduler_class(p, p->prio);
 		check_class_changing(task_rq(p), p, old_class);
 
@@ -4479,8 +4501,7 @@ static void scx_ops_disable_workfn(struct kthread_work *work)
 		check_class_changed(task_rq(p), p, old_class, p->prio);
 		scx_ops_exit_task(p);
 	}
-	scx_task_iter_exit(&sti);
-	spin_unlock_irq(&scx_tasks_lock);
+	scx_task_iter_stop(&sti);
 	percpu_up_write(&scx_fork_rwsem);
 
 	/* no task is on scx, turn off all the switches and flush in-progress calls */
@@ -5041,6 +5062,7 @@ 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;
 		}
 	}
@@ -5130,8 +5152,7 @@ static int scx_ops_enable(struct sched_ext_ops *ops, struct bpf_link *link)
 	if (ret)
 		goto err_disable_unlock_all;
 
-	spin_lock_irq(&scx_tasks_lock);
-	scx_task_iter_init(&sti);
+	scx_task_iter_start(&sti);
 	while ((p = scx_task_iter_next_locked(&sti))) {
 		/*
 		 * @p may already be dead, have lost all its usages counts and
@@ -5141,27 +5162,24 @@ static int scx_ops_enable(struct sched_ext_ops *ops, struct bpf_link *link)
 		if (!tryget_task_struct(p))
 			continue;
 
-		scx_task_iter_rq_unlock(&sti);
-		spin_unlock_irq(&scx_tasks_lock);
+		scx_task_iter_unlock(&sti);
 
 		ret = scx_ops_init_task(p, task_group(p), false);
 		if (ret) {
 			put_task_struct(p);
-			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_task_iter_relock(&sti);
+			scx_task_iter_stop(&sti);
+			scx_ops_error("ops.init_task() failed (%d) for %s[%d]",
+				      ret, p->comm, p->pid);
 			goto err_disable_unlock_all;
 		}
 
 		scx_set_task_state(p, SCX_TASK_READY);
 
 		put_task_struct(p);
-		spin_lock_irq(&scx_tasks_lock);
+		scx_task_iter_relock(&sti);
 	}
-	scx_task_iter_exit(&sti);
-	spin_unlock_irq(&scx_tasks_lock);
+	scx_task_iter_stop(&sti);
 	scx_cgroup_unlock();
 	percpu_up_write(&scx_fork_rwsem);
 
@@ -5178,14 +5196,14 @@ static int scx_ops_enable(struct sched_ext_ops *ops, struct bpf_link *link)
 	 * scx_tasks_lock.
 	 */
 	percpu_down_write(&scx_fork_rwsem);
-	spin_lock_irq(&scx_tasks_lock);
-	scx_task_iter_init(&sti);
+	scx_task_iter_start(&sti);
 	while ((p = scx_task_iter_next_locked(&sti))) {
 		const struct sched_class *old_class = p->sched_class;
 		struct sched_enq_and_set_ctx ctx;
 
 		sched_deq_and_put_task(p, DEQUEUE_SAVE | DEQUEUE_MOVE, &ctx);
 
+		p->scx.slice = SCX_SLICE_DFL;
 		p->sched_class = __setscheduler_class(p, p->prio);
 		check_class_changing(task_rq(p), p, old_class);
 
@@ -5193,20 +5211,13 @@ static int scx_ops_enable(struct sched_ext_ops *ops, struct bpf_link *link)
 
 		check_class_changed(task_rq(p), p, old_class, p->prio);
 	}
-	scx_task_iter_exit(&sti);
-	spin_unlock_irq(&scx_tasks_lock);
+	scx_task_iter_stop(&sti);
 	percpu_up_write(&scx_fork_rwsem);
 
 	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 +5252,18 @@ 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;
 }
 
 
@@ -5864,16 +5883,21 @@ __bpf_kfunc_start_defs();
 __bpf_kfunc s32 scx_bpf_select_cpu_dfl(struct task_struct *p, s32 prev_cpu,
 				       u64 wake_flags, bool *is_idle)
 {
-	if (!scx_kf_allowed(SCX_KF_SELECT_CPU)) {
-		*is_idle = false;
-		return prev_cpu;
+	if (!static_branch_likely(&scx_builtin_idle_enabled)) {
+		scx_ops_error("built-in idle tracking is disabled");
+		goto prev_cpu;
 	}
+
+	if (!scx_kf_allowed(SCX_KF_SELECT_CPU))
+		goto prev_cpu;
+
 #ifdef CONFIG_SMP
 	return scx_select_cpu_dfl(p, prev_cpu, wake_flags, is_idle);
-#else
+#endif
+
+prev_cpu:
 	*is_idle = false;
 	return prev_cpu;
-#endif
 }
 
 __bpf_kfunc_end_defs();
diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
index 020d58967d4e..84dad1511d1e 100644
--- a/kernel/sched/psi.c
+++ b/kernel/sched/psi.c
@@ -769,12 +769,13 @@ static void record_times(struct psi_group_cpu *groupc, u64 now)
 }
 
 static void psi_group_change(struct psi_group *group, int cpu,
-			     unsigned int clear, unsigned int set, u64 now,
+			     unsigned int clear, unsigned int set,
 			     bool wake_clock)
 {
 	struct psi_group_cpu *groupc;
 	unsigned int t, m;
 	u32 state_mask;
+	u64 now;
 
 	lockdep_assert_rq_held(cpu_rq(cpu));
 	groupc = per_cpu_ptr(group->pcpu, cpu);
@@ -789,6 +790,7 @@ static void psi_group_change(struct psi_group *group, int cpu,
 	 * SOME and FULL time these may have resulted in.
 	 */
 	write_seqcount_begin(&groupc->seq);
+	now = cpu_clock(cpu);
 
 	/*
 	 * Start with TSK_ONCPU, which doesn't have a corresponding
@@ -899,18 +901,15 @@ void psi_task_change(struct task_struct *task, int clear, int set)
 {
 	int cpu = task_cpu(task);
 	struct psi_group *group;
-	u64 now;
 
 	if (!task->pid)
 		return;
 
 	psi_flags_change(task, clear, set);
 
-	now = cpu_clock(cpu);
-
 	group = task_psi_group(task);
 	do {
-		psi_group_change(group, cpu, clear, set, now, true);
+		psi_group_change(group, cpu, clear, set, true);
 	} while ((group = group->parent));
 }
 
@@ -919,7 +918,6 @@ void psi_task_switch(struct task_struct *prev, struct task_struct *next,
 {
 	struct psi_group *group, *common = NULL;
 	int cpu = task_cpu(prev);
-	u64 now = cpu_clock(cpu);
 
 	if (next->pid) {
 		psi_flags_change(next, 0, TSK_ONCPU);
@@ -936,7 +934,7 @@ void psi_task_switch(struct task_struct *prev, struct task_struct *next,
 				break;
 			}
 
-			psi_group_change(group, cpu, 0, TSK_ONCPU, now, true);
+			psi_group_change(group, cpu, 0, TSK_ONCPU, true);
 		} while ((group = group->parent));
 	}
 
@@ -974,7 +972,7 @@ void psi_task_switch(struct task_struct *prev, struct task_struct *next,
 		do {
 			if (group == common)
 				break;
-			psi_group_change(group, cpu, clear, set, now, wake_clock);
+			psi_group_change(group, cpu, clear, set, wake_clock);
 		} while ((group = group->parent));
 
 		/*
@@ -986,7 +984,7 @@ void psi_task_switch(struct task_struct *prev, struct task_struct *next,
 		if ((prev->psi_flags ^ next->psi_flags) & ~TSK_ONCPU) {
 			clear &= ~TSK_ONCPU;
 			for (; group; group = group->parent)
-				psi_group_change(group, cpu, clear, set, now, wake_clock);
+				psi_group_change(group, cpu, clear, set, wake_clock);
 		}
 	}
 }
@@ -997,8 +995,8 @@ void psi_account_irqtime(struct rq *rq, struct task_struct *curr, struct task_st
 	int cpu = task_cpu(curr);
 	struct psi_group *group;
 	struct psi_group_cpu *groupc;
-	u64 now, irq;
 	s64 delta;
+	u64 irq;
 
 	if (static_branch_likely(&psi_disabled))
 		return;
@@ -1011,7 +1009,6 @@ void psi_account_irqtime(struct rq *rq, struct task_struct *curr, struct task_st
 	if (prev && task_psi_group(prev) == group)
 		return;
 
-	now = cpu_clock(cpu);
 	irq = irq_time_read(cpu);
 	delta = (s64)(irq - rq->psi_irq_time);
 	if (delta < 0)
@@ -1019,12 +1016,15 @@ void psi_account_irqtime(struct rq *rq, struct task_struct *curr, struct task_st
 	rq->psi_irq_time = irq;
 
 	do {
+		u64 now;
+
 		if (!group->enabled)
 			continue;
 
 		groupc = per_cpu_ptr(group->pcpu, cpu);
 
 		write_seqcount_begin(&groupc->seq);
+		now = cpu_clock(cpu);
 
 		record_times(groupc, now);
 		groupc->times[PSI_IRQ_FULL] += delta;
@@ -1223,11 +1223,9 @@ void psi_cgroup_restart(struct psi_group *group)
 	for_each_possible_cpu(cpu) {
 		struct rq *rq = cpu_rq(cpu);
 		struct rq_flags rf;
-		u64 now;
 
 		rq_lock_irq(rq, &rf);
-		now = cpu_clock(cpu);
-		psi_group_change(group, cpu, 0, 0, now, true);
+		psi_group_change(group, cpu, 0, 0, true);
 		rq_unlock_irq(rq, &rf);
 	}
 }
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index fba524c81c63..081519ffab46 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)
 
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 77dc0b25140e..3ea4f7bb1837 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -2337,9 +2337,12 @@ static struct trace_buffer *alloc_buffer(unsigned long size, unsigned flags,
 	if (!buffer->buffers[cpu])
 		goto fail_free_buffers;
 
-	ret = cpuhp_state_add_instance(CPUHP_TRACE_RB_PREPARE, &buffer->node);
-	if (ret < 0)
-		goto fail_free_buffers;
+	/* If already mapped, do not hook to CPU hotplug */
+	if (!start) {
+		ret = cpuhp_state_add_instance(CPUHP_TRACE_RB_PREPARE, &buffer->node);
+		if (ret < 0)
+			goto fail_free_buffers;
+	}
 
 	mutex_init(&buffer->mutex);
 
@@ -6725,39 +6728,38 @@ int ring_buffer_subbuf_order_set(struct trace_buffer *buffer, int order)
 	}
 
 	for_each_buffer_cpu(buffer, cpu) {
+		struct buffer_data_page *old_free_data_page;
+		struct list_head old_pages;
+		unsigned long flags;
 
 		if (!cpumask_test_cpu(cpu, buffer->cpumask))
 			continue;
 
 		cpu_buffer = buffer->buffers[cpu];
 
+		raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+
 		/* Clear the head bit to make the link list normal to read */
 		rb_head_page_deactivate(cpu_buffer);
 
-		/* Now walk the list and free all the old sub buffers */
-		list_for_each_entry_safe(bpage, tmp, cpu_buffer->pages, list) {
-			list_del_init(&bpage->list);
-			free_buffer_page(bpage);
-		}
-		/* The above loop stopped an the last page needing to be freed */
-		bpage = list_entry(cpu_buffer->pages, struct buffer_page, list);
-		free_buffer_page(bpage);
-
-		/* Free the current reader page */
-		free_buffer_page(cpu_buffer->reader_page);
+		/*
+		 * Collect buffers from the cpu_buffer pages list and the
+		 * reader_page on old_pages, so they can be freed later when not
+		 * under a spinlock. The pages list is a linked list with no
+		 * head, adding old_pages turns it into a regular list with
+		 * old_pages being the head.
+		 */
+		list_add(&old_pages, cpu_buffer->pages);
+		list_add(&cpu_buffer->reader_page->list, &old_pages);
 
 		/* One page was allocated for the reader page */
 		cpu_buffer->reader_page = list_entry(cpu_buffer->new_pages.next,
 						     struct buffer_page, list);
 		list_del_init(&cpu_buffer->reader_page->list);
 
-		/* The cpu_buffer pages are a link list with no head */
+		/* Install the new pages, remove the head from the list */
 		cpu_buffer->pages = cpu_buffer->new_pages.next;
-		cpu_buffer->new_pages.next->prev = cpu_buffer->new_pages.prev;
-		cpu_buffer->new_pages.prev->next = cpu_buffer->new_pages.next;
-
-		/* Clear the new_pages list */
-		INIT_LIST_HEAD(&cpu_buffer->new_pages);
+		list_del_init(&cpu_buffer->new_pages);
 
 		cpu_buffer->head_page
 			= list_entry(cpu_buffer->pages, struct buffer_page, list);
@@ -6766,11 +6768,20 @@ int ring_buffer_subbuf_order_set(struct trace_buffer *buffer, int order)
 		cpu_buffer->nr_pages = cpu_buffer->nr_pages_to_update;
 		cpu_buffer->nr_pages_to_update = 0;
 
-		free_pages((unsigned long)cpu_buffer->free_page, old_order);
+		old_free_data_page = cpu_buffer->free_page;
 		cpu_buffer->free_page = NULL;
 
 		rb_head_page_activate(cpu_buffer);
 
+		raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+
+		/* Free old sub buffers */
+		list_for_each_entry_safe(bpage, tmp, &old_pages, list) {
+			list_del_init(&bpage->list);
+			free_buffer_page(bpage);
+		}
+		free_pages((unsigned long)old_free_data_page, old_order);
+
 		rb_check_pages(cpu_buffer);
 	}
 
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index c01375adc471..a8f52b6527ca 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -3697,8 +3697,8 @@ static void test_can_verify(void)
 void trace_check_vprintf(struct trace_iterator *iter, const char *fmt,
 			 va_list ap)
 {
-	long text_delta = iter->tr->text_delta;
-	long data_delta = iter->tr->data_delta;
+	long text_delta = 0;
+	long data_delta = 0;
 	const char *p = fmt;
 	const char *str;
 	bool good;
@@ -3710,6 +3710,17 @@ void trace_check_vprintf(struct trace_iterator *iter, const char *fmt,
 	if (static_branch_unlikely(&trace_no_verify))
 		goto print;
 
+	/*
+	 * When the kernel is booted with the tp_printk command line
+	 * parameter, trace events go directly through to printk().
+	 * It also is checked by this function, but it does not
+	 * have an associated trace_array (tr) for it.
+	 */
+	if (iter->tr) {
+		text_delta = iter->tr->text_delta;
+		data_delta = iter->tr->data_delta;
+	}
+
 	/* Don't bother checking when doing a ftrace_dump() */
 	if (iter->fmt == static_fmt_buf)
 		goto print;
@@ -10610,10 +10621,10 @@ __init static void enable_instances(void)
 		 * cannot be deleted by user space, so keep the reference
 		 * to it.
 		 */
-		if (start)
+		if (start) {
 			tr->flags |= TRACE_ARRAY_FL_BOOT;
-		else
-			trace_array_put(tr);
+			tr->ref++;
+		}
 
 		while ((tok = strsep(&curr_str, ","))) {
 			early_enable_events(tr, tok, true);
diff --git a/kernel/trace/trace_hwlat.c b/kernel/trace/trace_hwlat.c
index b791524a6536..3bd6071441ad 100644
--- a/kernel/trace/trace_hwlat.c
+++ b/kernel/trace/trace_hwlat.c
@@ -520,6 +520,8 @@ static void hwlat_hotplug_workfn(struct work_struct *dummy)
 	if (!hwlat_busy || hwlat_data.thread_mode != MODE_PER_CPU)
 		goto out_unlock;
 
+	if (!cpu_online(cpu))
+		goto out_unlock;
 	if (!cpumask_test_cpu(cpu, tr->tracing_cpumask))
 		goto out_unlock;
 
diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c
index 1439064f65d6..a50ed23bee77 100644
--- a/kernel/trace/trace_osnoise.c
+++ b/kernel/trace/trace_osnoise.c
@@ -1953,12 +1953,8 @@ static void stop_kthread(unsigned int cpu)
 {
 	struct task_struct *kthread;
 
-	mutex_lock(&interface_lock);
-	kthread = per_cpu(per_cpu_osnoise_var, cpu).kthread;
+	kthread = xchg_relaxed(&(per_cpu(per_cpu_osnoise_var, cpu).kthread), NULL);
 	if (kthread) {
-		per_cpu(per_cpu_osnoise_var, cpu).kthread = NULL;
-		mutex_unlock(&interface_lock);
-
 		if (cpumask_test_and_clear_cpu(cpu, &kthread_cpumask) &&
 		    !WARN_ON(!test_bit(OSN_WORKLOAD, &osnoise_options))) {
 			kthread_stop(kthread);
@@ -1972,7 +1968,6 @@ static void stop_kthread(unsigned int cpu)
 			put_task_struct(kthread);
 		}
 	} else {
-		mutex_unlock(&interface_lock);
 		/* if no workload, just return */
 		if (!test_bit(OSN_WORKLOAD, &osnoise_options)) {
 			/*
@@ -1994,8 +1989,12 @@ static void stop_per_cpu_kthreads(void)
 {
 	int cpu;
 
-	for_each_possible_cpu(cpu)
+	cpus_read_lock();
+
+	for_each_online_cpu(cpu)
 		stop_kthread(cpu);
+
+	cpus_read_unlock();
 }
 
 /*
@@ -2007,6 +2006,10 @@ static int start_kthread(unsigned int cpu)
 	void *main = osnoise_main;
 	char comm[24];
 
+	/* Do not start a new thread if it is already running */
+	if (per_cpu(per_cpu_osnoise_var, cpu).kthread)
+		return 0;
+
 	if (timerlat_enabled()) {
 		snprintf(comm, 24, "timerlat/%d", cpu);
 		main = timerlat_main;
@@ -2061,11 +2064,10 @@ static int start_per_cpu_kthreads(void)
 		if (cpumask_test_and_clear_cpu(cpu, &kthread_cpumask)) {
 			struct task_struct *kthread;
 
-			kthread = per_cpu(per_cpu_osnoise_var, cpu).kthread;
+			kthread = xchg_relaxed(&(per_cpu(per_cpu_osnoise_var, cpu).kthread), NULL);
 			if (!WARN_ON(!kthread))
 				kthread_stop(kthread);
 		}
-		per_cpu(per_cpu_osnoise_var, cpu).kthread = NULL;
 	}
 
 	for_each_cpu(cpu, current_mask) {
@@ -2095,6 +2097,8 @@ static void osnoise_hotplug_workfn(struct work_struct *dummy)
 	mutex_lock(&interface_lock);
 	cpus_read_lock();
 
+	if (!cpu_online(cpu))
+		goto out_unlock;
 	if (!cpumask_test_cpu(cpu, &osnoise_cpumask))
 		goto out_unlock;