Merge v6.13 into drm-next

A regression was caused by commit e4b5ccd392 ("drm/v3d: Ensure job
pointer is set to NULL after job completion"), but this commit is not
yet in next-fixes, fast-forward it.

Note that this recreates Linus merge in 96c84703f1 ("Merge tag
'drm-next-2025-01-17' of https://gitlab.freedesktop.org/drm/kernel")
because I didn't want to backmerge a random point in the merge window.

Signed-off-by: Simona Vetter <simona.vetter@ffwll.ch>

kernel/cgroup/cpuset.c

@@ -197,10 +197,8 @@ static struct cpuset top_cpuset = {
 
 /*
  * There are two global locks guarding cpuset structures - cpuset_mutex and
- * callback_lock. We also require taking task_lock() when dereferencing a
- * task's cpuset pointer. See "The task_lock() exception", at the end of this
- * comment.  The cpuset code uses only cpuset_mutex. Other kernel subsystems
- * can use cpuset_lock()/cpuset_unlock() to prevent change to cpuset
+ * callback_lock. The cpuset code uses only cpuset_mutex. Other kernel
+ * subsystems can use cpuset_lock()/cpuset_unlock() to prevent change to cpuset
  * structures. Note that cpuset_mutex needs to be a mutex as it is used in
  * paths that rely on priority inheritance (e.g. scheduler - on RT) for
  * correctness.
@@ -229,9 +227,6 @@ static struct cpuset top_cpuset = {
  * The cpuset_common_seq_show() handlers only hold callback_lock across
  * small pieces of code, such as when reading out possibly multi-word
  * cpumasks and nodemasks.
- *
- * Accessing a task's cpuset should be done in accordance with the
- * guidelines for accessing subsystem state in kernel/cgroup.c
  */
 
 static DEFINE_MUTEX(cpuset_mutex);
@@ -890,7 +885,15 @@ static int generate_sched_domains(cpumask_var_t **domains,
 	 */
 	if (cgrpv2) {
 		for (i = 0; i < ndoms; i++) {
-			cpumask_copy(doms[i], csa[i]->effective_cpus);
+			/*
+			 * The top cpuset may contain some boot time isolated
+			 * CPUs that need to be excluded from the sched domain.
+			 */
+			if (csa[i] == &top_cpuset)
+				cpumask_and(doms[i], csa[i]->effective_cpus,
+					    housekeeping_cpumask(HK_TYPE_DOMAIN));
+			else
+				cpumask_copy(doms[i], csa[i]->effective_cpus);
 			if (dattr)
 				dattr[i] = SD_ATTR_INIT;
 		}
@@ -3121,29 +3124,6 @@ ssize_t cpuset_write_resmask(struct kernfs_open_file *of,
 	int retval = -ENODEV;
 
 	buf = strstrip(buf);
-
-	/*
-	 * CPU or memory hotunplug may leave @cs w/o any execution
-	 * resources, in which case the hotplug code asynchronously updates
-	 * configuration and transfers all tasks to the nearest ancestor
-	 * which can execute.
-	 *
-	 * As writes to "cpus" or "mems" may restore @cs's execution
-	 * resources, wait for the previously scheduled operations before
-	 * proceeding, so that we don't end up keep removing tasks added
-	 * after execution capability is restored.
-	 *
-	 * cpuset_handle_hotplug may call back into cgroup core asynchronously
-	 * via cgroup_transfer_tasks() and waiting for it from a cgroupfs
-	 * operation like this one can lead to a deadlock through kernfs
-	 * active_ref protection.  Let's break the protection.  Losing the
-	 * protection is okay as we check whether @cs is online after
-	 * grabbing cpuset_mutex anyway.  This only happens on the legacy
-	 * hierarchies.
-	 */
-	css_get(&cs->css);
-	kernfs_break_active_protection(of->kn);
-
 	cpus_read_lock();
 	mutex_lock(&cpuset_mutex);
 	if (!is_cpuset_online(cs))
@@ -3176,8 +3156,6 @@ ssize_t cpuset_write_resmask(struct kernfs_open_file *of,
 out_unlock:
 	mutex_unlock(&cpuset_mutex);
 	cpus_read_unlock();
-	kernfs_unbreak_active_protection(of->kn);
-	css_put(&cs->css);
 	flush_workqueue(cpuset_migrate_mm_wq);
 	return retval ?: nbytes;
 }

kernel/cpu.c

@@ -2179,7 +2179,7 @@ static struct cpuhp_step cpuhp_hp_states[] = {
 	},
 	[CPUHP_AP_HRTIMERS_DYING] = {
 		.name			= "hrtimers:dying",
-		.startup.single		= NULL,
+		.startup.single		= hrtimers_cpu_starting,
 		.teardown.single	= hrtimers_cpu_dying,
 	},
 	[CPUHP_AP_TICK_DYING] = {

kernel/events/uprobes.c

@@ -1915,6 +1915,7 @@ void uprobe_free_utask(struct task_struct *t)
 	if (!utask)
 		return;
 
+	t->utask = NULL;
 	WARN_ON_ONCE(utask->active_uprobe || utask->xol_vaddr);
 
 	timer_delete_sync(&utask->ri_timer);
@@ -1924,7 +1925,6 @@ void uprobe_free_utask(struct task_struct *t)
 		ri = free_ret_instance(ri, true /* cleanup_hprobe */);
 
 	kfree(utask);
-	t->utask = NULL;
 }
 
 #define RI_TIMER_PERIOD (HZ / 10) /* 100 ms */

kernel/gen_kheaders.sh

@@ -89,6 +89,7 @@ find $cpio_dir -type f -print0 |
 
 # Create archive and try to normalize metadata for reproducibility.
 tar "${KBUILD_BUILD_TIMESTAMP:+--mtime=$KBUILD_BUILD_TIMESTAMP}" \
+    --exclude=".__afs*" --exclude=".nfs*" \
     --owner=0 --group=0 --sort=name --numeric-owner --mode=u=rw,go=r,a+X \
     -I $XZ -cf $tarfile -C $cpio_dir/ . > /dev/null
 

kernel/sched/ext.c

@@ -2747,6 +2747,7 @@ static int balance_one(struct rq *rq, struct task_struct *prev)
 {
 	struct scx_dsp_ctx *dspc = this_cpu_ptr(scx_dsp_ctx);
 	bool prev_on_scx = prev->sched_class == &ext_sched_class;
+	bool prev_on_rq = prev->scx.flags & SCX_TASK_QUEUED;
 	int nr_loops = SCX_DSP_MAX_LOOPS;
 
 	lockdep_assert_rq_held(rq);
@@ -2779,8 +2780,7 @@ static int balance_one(struct rq *rq, struct task_struct *prev)
 		 * See scx_ops_disable_workfn() for the explanation on the
 		 * bypassing test.
 		 */
-		if ((prev->scx.flags & SCX_TASK_QUEUED) &&
-		    prev->scx.slice && !scx_rq_bypassing(rq)) {
+		if (prev_on_rq && prev->scx.slice && !scx_rq_bypassing(rq)) {
 			rq->scx.flags |= SCX_RQ_BAL_KEEP;
 			goto has_tasks;
 		}
@@ -2813,6 +2813,10 @@ static int balance_one(struct rq *rq, struct task_struct *prev)
 
 		flush_dispatch_buf(rq);
 
+		if (prev_on_rq && prev->scx.slice) {
+			rq->scx.flags |= SCX_RQ_BAL_KEEP;
+			goto has_tasks;
+		}
 		if (rq->scx.local_dsq.nr)
 			goto has_tasks;
 		if (consume_global_dsq(rq))
@@ -2838,8 +2842,7 @@ static int balance_one(struct rq *rq, struct task_struct *prev)
 	 * Didn't find another task to run. Keep running @prev unless
 	 * %SCX_OPS_ENQ_LAST is in effect.
 	 */
-	if ((prev->scx.flags & SCX_TASK_QUEUED) &&
-	    (!static_branch_unlikely(&scx_ops_enq_last) ||
+	if (prev_on_rq && (!static_branch_unlikely(&scx_ops_enq_last) ||
 	     scx_rq_bypassing(rq))) {
 		rq->scx.flags |= SCX_RQ_BAL_KEEP;
 		goto has_tasks;
@@ -3034,7 +3037,7 @@ static void put_prev_task_scx(struct rq *rq, struct task_struct *p,
 		 */
 		if (p->scx.slice && !scx_rq_bypassing(rq)) {
 			dispatch_enqueue(&rq->scx.local_dsq, p, SCX_ENQ_HEAD);
-			return;
+			goto switch_class;
 		}
 
 		/*
@@ -3051,6 +3054,7 @@ static void put_prev_task_scx(struct rq *rq, struct task_struct *p,
 		}
 	}
 
+switch_class:
 	if (next && next->sched_class != &ext_sched_class)
 		switch_class(rq, next);
 }
@@ -3586,16 +3590,8 @@ static void reset_idle_masks(void)
 	cpumask_copy(idle_masks.smt, cpu_online_mask);
 }
 
-void __scx_update_idle(struct rq *rq, bool idle)
+static void update_builtin_idle(int cpu, bool idle)
 {
-	int cpu = cpu_of(rq);
-
-	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;
-	}
-
 	if (idle)
 		cpumask_set_cpu(cpu, idle_masks.cpu);
 	else
@@ -3622,6 +3618,57 @@ void __scx_update_idle(struct rq *rq, bool idle)
 #endif
 }
 
+/*
+ * Update the idle state of a CPU to @idle.
+ *
+ * If @do_notify is true, ops.update_idle() is invoked to notify the scx
+ * scheduler of an actual idle state transition (idle to busy or vice
+ * versa). If @do_notify is false, only the idle state in the idle masks is
+ * refreshed without invoking ops.update_idle().
+ *
+ * This distinction is necessary, because an idle CPU can be "reserved" and
+ * awakened via scx_bpf_pick_idle_cpu() + scx_bpf_kick_cpu(), marking it as
+ * busy even if no tasks are dispatched. In this case, the CPU may return
+ * to idle without a true state transition. Refreshing the idle masks
+ * without invoking ops.update_idle() ensures accurate idle state tracking
+ * while avoiding unnecessary updates and maintaining balanced state
+ * transitions.
+ */
+void __scx_update_idle(struct rq *rq, bool idle, bool do_notify)
+{
+	int cpu = cpu_of(rq);
+
+	lockdep_assert_rq_held(rq);
+
+	/*
+	 * Trigger ops.update_idle() only when transitioning from a task to
+	 * the idle thread and vice versa.
+	 *
+	 * Idle transitions are indicated by do_notify being set to true,
+	 * managed by put_prev_task_idle()/set_next_task_idle().
+	 */
+	if (SCX_HAS_OP(update_idle) && do_notify && !scx_rq_bypassing(rq))
+		SCX_CALL_OP(SCX_KF_REST, update_idle, cpu_of(rq), idle);
+
+	/*
+	 * Update the idle masks:
+	 * - for real idle transitions (do_notify == true)
+	 * - for idle-to-idle transitions (indicated by the previous task
+	 *   being the idle thread, managed by pick_task_idle())
+	 *
+	 * Skip updating idle masks if the previous task is not the idle
+	 * thread, since set_next_task_idle() has already handled it when
+	 * transitioning from a task to the idle thread (calling this
+	 * function with do_notify == true).
+	 *
+	 * In this way we can avoid updating the idle masks twice,
+	 * unnecessarily.
+	 */
+	if (static_branch_likely(&scx_builtin_idle_enabled))
+		if (do_notify || is_idle_task(rq->curr))
+			update_builtin_idle(cpu, idle);
+}
+
 static void handle_hotplug(struct rq *rq, bool online)
 {
 	int cpu = cpu_of(rq);
@@ -4744,10 +4791,9 @@ static void scx_ops_bypass(bool bypass)
 	 */
 	for_each_possible_cpu(cpu) {
 		struct rq *rq = cpu_rq(cpu);
-		struct rq_flags rf;
 		struct task_struct *p, *n;
 
-		rq_lock(rq, &rf);
+		raw_spin_rq_lock(rq);
 
 		if (bypass) {
 			WARN_ON_ONCE(rq->scx.flags & SCX_RQ_BYPASSING);
@@ -4763,7 +4809,7 @@ static void scx_ops_bypass(bool bypass)
 		 * sees scx_rq_bypassing() before moving tasks to SCX.
 		 */
 		if (!scx_enabled()) {
-			rq_unlock(rq, &rf);
+			raw_spin_rq_unlock(rq);
 			continue;
 		}
 
@@ -4783,10 +4829,11 @@ static void scx_ops_bypass(bool bypass)
 			sched_enq_and_set_task(&ctx);
 		}
 
-		rq_unlock(rq, &rf);
-
 		/* resched to restore ticks and idle state */
-		resched_cpu(cpu);
+		if (cpu_online(cpu) || cpu == smp_processor_id())
+			resched_curr(rq);
+
+		raw_spin_rq_unlock(rq);
 	}
 
 	atomic_dec(&scx_ops_breather_depth);

kernel/sched/ext.h

@@ -57,15 +57,15 @@ static inline void init_sched_ext_class(void) {}
 #endif	/* CONFIG_SCHED_CLASS_EXT */
 
 #if defined(CONFIG_SCHED_CLASS_EXT) && defined(CONFIG_SMP)
-void __scx_update_idle(struct rq *rq, bool idle);
+void __scx_update_idle(struct rq *rq, bool idle, bool do_notify);
 
-static inline void scx_update_idle(struct rq *rq, bool idle)
+static inline void scx_update_idle(struct rq *rq, bool idle, bool do_notify)
 {
 	if (scx_enabled())
-		__scx_update_idle(rq, idle);
+		__scx_update_idle(rq, idle, do_notify);
 }
 #else
-static inline void scx_update_idle(struct rq *rq, bool idle) {}
+static inline void scx_update_idle(struct rq *rq, bool idle, bool do_notify) {}
 #endif
 
 #ifdef CONFIG_CGROUP_SCHED

kernel/sched/fair.c

@@ -689,21 +689,16 @@ u64 avg_vruntime(struct cfs_rq *cfs_rq)
  *
  * XXX could add max_slice to the augmented data to track this.
  */
-static s64 entity_lag(u64 avruntime, struct sched_entity *se)
+static void update_entity_lag(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	s64 vlag, limit;
 
-	vlag = avruntime - se->vruntime;
-	limit = calc_delta_fair(max_t(u64, 2*se->slice, TICK_NSEC), se);
-
-	return clamp(vlag, -limit, limit);
-}
-
-static void update_entity_lag(struct cfs_rq *cfs_rq, struct sched_entity *se)
-{
 	SCHED_WARN_ON(!se->on_rq);
 
-	se->vlag = entity_lag(avg_vruntime(cfs_rq), se);
+	vlag = avg_vruntime(cfs_rq) - se->vruntime;
+	limit = calc_delta_fair(max_t(u64, 2*se->slice, TICK_NSEC), se);
+
+	se->vlag = clamp(vlag, -limit, limit);
 }
 
 /*
@@ -3774,137 +3769,32 @@ static inline void
 dequeue_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { }
 #endif
 
-static void reweight_eevdf(struct sched_entity *se, u64 avruntime,
-			   unsigned long weight)
-{
-	unsigned long old_weight = se->load.weight;
-	s64 vlag, vslice;
-
-	/*
-	 * VRUNTIME
-	 * --------
-	 *
-	 * COROLLARY #1: The virtual runtime of the entity needs to be
-	 * adjusted if re-weight at !0-lag point.
-	 *
-	 * Proof: For contradiction assume this is not true, so we can
-	 * re-weight without changing vruntime at !0-lag point.
-	 *
-	 *             Weight	VRuntime   Avg-VRuntime
-	 *     before    w          v            V
-	 *      after    w'         v'           V'
-	 *
-	 * Since lag needs to be preserved through re-weight:
-	 *
-	 *	lag = (V - v)*w = (V'- v')*w', where v = v'
-	 *	==>	V' = (V - v)*w/w' + v		(1)
-	 *
-	 * Let W be the total weight of the entities before reweight,
-	 * since V' is the new weighted average of entities:
-	 *
-	 *	V' = (WV + w'v - wv) / (W + w' - w)	(2)
-	 *
-	 * by using (1) & (2) we obtain:
-	 *
-	 *	(WV + w'v - wv) / (W + w' - w) = (V - v)*w/w' + v
-	 *	==> (WV-Wv+Wv+w'v-wv)/(W+w'-w) = (V - v)*w/w' + v
-	 *	==> (WV - Wv)/(W + w' - w) + v = (V - v)*w/w' + v
-	 *	==>	(V - v)*W/(W + w' - w) = (V - v)*w/w' (3)
-	 *
-	 * Since we are doing at !0-lag point which means V != v, we
-	 * can simplify (3):
-	 *
-	 *	==>	W / (W + w' - w) = w / w'
-	 *	==>	Ww' = Ww + ww' - ww
-	 *	==>	W * (w' - w) = w * (w' - w)
-	 *	==>	W = w	(re-weight indicates w' != w)
-	 *
-	 * So the cfs_rq contains only one entity, hence vruntime of
-	 * the entity @v should always equal to the cfs_rq's weighted
-	 * average vruntime @V, which means we will always re-weight
-	 * at 0-lag point, thus breach assumption. Proof completed.
-	 *
-	 *
-	 * COROLLARY #2: Re-weight does NOT affect weighted average
-	 * vruntime of all the entities.
-	 *
-	 * Proof: According to corollary #1, Eq. (1) should be:
-	 *
-	 *	(V - v)*w = (V' - v')*w'
-	 *	==>    v' = V' - (V - v)*w/w'		(4)
-	 *
-	 * According to the weighted average formula, we have:
-	 *
-	 *	V' = (WV - wv + w'v') / (W - w + w')
-	 *	   = (WV - wv + w'(V' - (V - v)w/w')) / (W - w + w')
-	 *	   = (WV - wv + w'V' - Vw + wv) / (W - w + w')
-	 *	   = (WV + w'V' - Vw) / (W - w + w')
-	 *
-	 *	==>  V'*(W - w + w') = WV + w'V' - Vw
-	 *	==>	V' * (W - w) = (W - w) * V	(5)
-	 *
-	 * If the entity is the only one in the cfs_rq, then reweight
-	 * always occurs at 0-lag point, so V won't change. Or else
-	 * there are other entities, hence W != w, then Eq. (5) turns
-	 * into V' = V. So V won't change in either case, proof done.
-	 *
-	 *
-	 * So according to corollary #1 & #2, the effect of re-weight
-	 * on vruntime should be:
-	 *
-	 *	v' = V' - (V - v) * w / w'		(4)
-	 *	   = V  - (V - v) * w / w'
-	 *	   = V  - vl * w / w'
-	 *	   = V  - vl'
-	 */
-	if (avruntime != se->vruntime) {
-		vlag = entity_lag(avruntime, se);
-		vlag = div_s64(vlag * old_weight, weight);
-		se->vruntime = avruntime - vlag;
-	}
-
-	/*
-	 * DEADLINE
-	 * --------
-	 *
-	 * When the weight changes, the virtual time slope changes and
-	 * we should adjust the relative virtual deadline accordingly.
-	 *
-	 *	d' = v' + (d - v)*w/w'
-	 *	   = V' - (V - v)*w/w' + (d - v)*w/w'
-	 *	   = V  - (V - v)*w/w' + (d - v)*w/w'
-	 *	   = V  + (d - V)*w/w'
-	 */
-	vslice = (s64)(se->deadline - avruntime);
-	vslice = div_s64(vslice * old_weight, weight);
-	se->deadline = avruntime + vslice;
-}
+static void place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags);
 
 static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
 			    unsigned long weight)
 {
 	bool curr = cfs_rq->curr == se;
-	u64 avruntime;
 
 	if (se->on_rq) {
 		/* commit outstanding execution time */
 		update_curr(cfs_rq);
-		avruntime = avg_vruntime(cfs_rq);
+		update_entity_lag(cfs_rq, se);
+		se->deadline -= se->vruntime;
+		se->rel_deadline = 1;
 		if (!curr)
 			__dequeue_entity(cfs_rq, se);
 		update_load_sub(&cfs_rq->load, se->load.weight);
 	}
 	dequeue_load_avg(cfs_rq, se);
 
-	if (se->on_rq) {
-		reweight_eevdf(se, avruntime, weight);
-	} else {
-		/*
-		 * Because we keep se->vlag = V - v_i, while: lag_i = w_i*(V - v_i),
-		 * we need to scale se->vlag when w_i changes.
-		 */
-		se->vlag = div_s64(se->vlag * se->load.weight, weight);
-	}
+	/*
+	 * Because we keep se->vlag = V - v_i, while: lag_i = w_i*(V - v_i),
+	 * we need to scale se->vlag when w_i changes.
+	 */
+	se->vlag = div_s64(se->vlag * se->load.weight, weight);
+	if (se->rel_deadline)
+		se->deadline = div_s64(se->deadline * se->load.weight, weight);
 
 	update_load_set(&se->load, weight);
 
@@ -3919,6 +3809,7 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
 	enqueue_load_avg(cfs_rq, se);
 	if (se->on_rq) {
 		update_load_add(&cfs_rq->load, se->load.weight);
+		place_entity(cfs_rq, se, 0);
 		if (!curr)
 			__enqueue_entity(cfs_rq, se);
 
@@ -4065,7 +3956,11 @@ static void update_cfs_group(struct sched_entity *se)
 	struct cfs_rq *gcfs_rq = group_cfs_rq(se);
 	long shares;
 
-	if (!gcfs_rq)
+	/*
+	 * When a group becomes empty, preserve its weight. This matters for
+	 * DELAY_DEQUEUE.
+	 */
+	if (!gcfs_rq || !gcfs_rq->load.weight)
 		return;
 
 	if (throttled_hierarchy(gcfs_rq))
@@ -5359,7 +5254,7 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 
 	se->vruntime = vruntime - lag;
 
-	if (sched_feat(PLACE_REL_DEADLINE) && se->rel_deadline) {
+	if (se->rel_deadline) {
 		se->deadline += se->vruntime;
 		se->rel_deadline = 0;
 		return;

kernel/sched/idle.c

@@ -452,19 +452,20 @@ static void wakeup_preempt_idle(struct rq *rq, struct task_struct *p, int flags)
 static void put_prev_task_idle(struct rq *rq, struct task_struct *prev, struct task_struct *next)
 {
 	dl_server_update_idle_time(rq, prev);
-	scx_update_idle(rq, false);
+	scx_update_idle(rq, false, true);
 }
 
 static void set_next_task_idle(struct rq *rq, struct task_struct *next, bool first)
 {
 	update_idle_core(rq);
-	scx_update_idle(rq, true);
+	scx_update_idle(rq, true, true);
 	schedstat_inc(rq->sched_goidle);
 	next->se.exec_start = rq_clock_task(rq);
 }
 
 struct task_struct *pick_task_idle(struct rq *rq)
 {
+	scx_update_idle(rq, true, false);
 	return rq->idle;
 }
 

kernel/signal.c

@@ -2007,11 +2007,22 @@ void posixtimer_send_sigqueue(struct k_itimer *tmr)
 
 		if (!list_empty(&q->list)) {
 			/*
-			 * If task group is exiting with the signal already pending,
-			 * wait for __exit_signal() to do its job. Otherwise if
-			 * ignored, it's not supposed to be queued. Try to survive.
+			 * The signal was ignored and blocked. The timer
+			 * expiry queued it because blocked signals are
+			 * queued independent of the ignored state.
+			 *
+			 * The unblocking set SIGPENDING, but the signal
+			 * was not yet dequeued from the pending list.
+			 * So prepare_signal() sees unblocked and ignored,
+			 * which ends up here. Leave it queued like a
+			 * regular signal.
+			 *
+			 * The same happens when the task group is exiting
+			 * and the signal is already queued.
+			 * prepare_signal() treats SIGNAL_GROUP_EXIT as
+			 * ignored independent of its queued state. This
+			 * gets cleaned up in __exit_signal().
 			 */
-			WARN_ON_ONCE(!(t->signal->flags & SIGNAL_GROUP_EXIT));
 			goto out;
 		}
 
@@ -2046,17 +2057,25 @@ void posixtimer_send_sigqueue(struct k_itimer *tmr)
 		goto out;
 	}
 
-	/* This should never happen and leaks a reference count */
-	if (WARN_ON_ONCE(!hlist_unhashed(&tmr->ignored_list)))
-		hlist_del_init(&tmr->ignored_list);
-
 	if (unlikely(!list_empty(&q->list))) {
 		/* This holds a reference count already */
 		result = TRACE_SIGNAL_ALREADY_PENDING;
 		goto out;
 	}
 
-	posixtimer_sigqueue_getref(q);
+	/*
+	 * If the signal is on the ignore list, it got blocked after it was
+	 * ignored earlier. But nothing lifted the ignore. Move it back to
+	 * the pending list to be consistent with the regular signal
+	 * handling. This already holds a reference count.
+	 *
+	 * If it's not on the ignore list acquire a reference count.
+	 */
+	if (likely(hlist_unhashed(&tmr->ignored_list)))
+		posixtimer_sigqueue_getref(q);
+	else
+		hlist_del_init(&tmr->ignored_list);
+
 	posixtimer_queue_sigqueue(q, t, tmr->it_pid_type);
 	result = TRACE_SIGNAL_DELIVERED;
 out:

kernel/time/hrtimer.c

@@ -2202,6 +2202,15 @@ int hrtimers_prepare_cpu(unsigned int cpu)
 	}
 
 	cpu_base->cpu = cpu;
+	hrtimer_cpu_base_init_expiry_lock(cpu_base);
+	return 0;
+}
+
+int hrtimers_cpu_starting(unsigned int cpu)
+{
+	struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
+
+	/* Clear out any left over state from a CPU down operation */
 	cpu_base->active_bases = 0;
 	cpu_base->hres_active = 0;
 	cpu_base->hang_detected = 0;
@@ -2210,7 +2219,6 @@ int hrtimers_prepare_cpu(unsigned int cpu)
 	cpu_base->expires_next = KTIME_MAX;
 	cpu_base->softirq_expires_next = KTIME_MAX;
 	cpu_base->online = 1;
-	hrtimer_cpu_base_init_expiry_lock(cpu_base);
 	return 0;
 }
 
@@ -2286,5 +2294,6 @@ int hrtimers_cpu_dying(unsigned int dying_cpu)
 void __init hrtimers_init(void)
 {
 	hrtimers_prepare_cpu(smp_processor_id());
+	hrtimers_cpu_starting(smp_processor_id());
 	open_softirq(HRTIMER_SOFTIRQ, hrtimer_run_softirq);
 }

kernel/time/timer_migration.c

@@ -534,8 +534,13 @@ static void __walk_groups(up_f up, struct tmigr_walk *data,
 			break;
 
 		child = group;
-		group = group->parent;
+		/*
+		 * Pairs with the store release on group connection
+		 * to make sure group initialization is visible.
+		 */
+		group = READ_ONCE(group->parent);
 		data->childmask = child->groupmask;
+		WARN_ON_ONCE(!data->childmask);
 	} while (group);
 }
 
@@ -564,7 +569,7 @@ static struct tmigr_event *tmigr_next_groupevt(struct tmigr_group *group)
 	while ((node = timerqueue_getnext(&group->events))) {
 		evt = container_of(node, struct tmigr_event, nextevt);
 
-		if (!evt->ignore) {
+		if (!READ_ONCE(evt->ignore)) {
 			WRITE_ONCE(group->next_expiry, evt->nextevt.expires);
 			return evt;
 		}
@@ -660,7 +665,7 @@ static bool tmigr_active_up(struct tmigr_group *group,
 	 * lock is held while updating the ignore flag in idle path. So this
 	 * state change will not be lost.
 	 */
-	group->groupevt.ignore = true;
+	WRITE_ONCE(group->groupevt.ignore, true);
 
 	return walk_done;
 }
@@ -721,6 +726,7 @@ bool tmigr_update_events(struct tmigr_group *group, struct tmigr_group *child,
 	union tmigr_state childstate, groupstate;
 	bool remote = data->remote;
 	bool walk_done = false;
+	bool ignore;
 	u64 nextexp;
 
 	if (child) {
@@ -739,11 +745,19 @@ bool tmigr_update_events(struct tmigr_group *group, struct tmigr_group *child,
 		nextexp = child->next_expiry;
 		evt = &child->groupevt;
 
-		evt->ignore = (nextexp == KTIME_MAX) ? true : false;
+		/*
+		 * This can race with concurrent idle exit (activate).
+		 * If the current writer wins, a useless remote expiration may
+		 * be scheduled. If the activate wins, the event is properly
+		 * ignored.
+		 */
+		ignore = (nextexp == KTIME_MAX) ? true : false;
+		WRITE_ONCE(evt->ignore, ignore);
 	} else {
 		nextexp = data->nextexp;
 
 		first_childevt = evt = data->evt;
+		ignore = evt->ignore;
 
 		/*
 		 * Walking the hierarchy is required in any case when a
@@ -769,7 +783,7 @@ bool tmigr_update_events(struct tmigr_group *group, struct tmigr_group *child,
 		 * first event information of the group is updated properly and
 		 * also handled properly, so skip this fast return path.
 		 */
-		if (evt->ignore && !remote && group->parent)
+		if (ignore && !remote && group->parent)
 			return true;
 
 		raw_spin_lock(&group->lock);
@@ -783,7 +797,7 @@ bool tmigr_update_events(struct tmigr_group *group, struct tmigr_group *child,
 	 * queue when the expiry time changed only or when it could be ignored.
 	 */
 	if (timerqueue_node_queued(&evt->nextevt)) {
-		if ((evt->nextevt.expires == nextexp) && !evt->ignore) {
+		if ((evt->nextevt.expires == nextexp) && !ignore) {
 			/* Make sure not to miss a new CPU event with the same expiry */
 			evt->cpu = first_childevt->cpu;
 			goto check_toplvl;
@@ -793,7 +807,7 @@ bool tmigr_update_events(struct tmigr_group *group, struct tmigr_group *child,
 			WRITE_ONCE(group->next_expiry, KTIME_MAX);
 	}
 
-	if (evt->ignore) {
+	if (ignore) {
 		/*
 		 * When the next child event could be ignored (nextexp is
 		 * KTIME_MAX) and there was no remote timer handling before or
@@ -1487,6 +1501,21 @@ static void tmigr_init_group(struct tmigr_group *group, unsigned int lvl,
 	s.seq = 0;
 	atomic_set(&group->migr_state, s.state);
 
+	/*
+	 * If this is a new top-level, prepare its groupmask in advance.
+	 * This avoids accidents where yet another new top-level is
+	 * created in the future and made visible before the current groupmask.
+	 */
+	if (list_empty(&tmigr_level_list[lvl])) {
+		group->groupmask = BIT(0);
+		/*
+		 * The previous top level has prepared its groupmask already,
+		 * simply account it as the first child.
+		 */
+		if (lvl > 0)
+			group->num_children = 1;
+	}
+
 	timerqueue_init_head(&group->events);
 	timerqueue_init(&group->groupevt.nextevt);
 	group->groupevt.nextevt.expires = KTIME_MAX;
@@ -1550,8 +1579,25 @@ static void tmigr_connect_child_parent(struct tmigr_group *child,
 	raw_spin_lock_irq(&child->lock);
 	raw_spin_lock_nested(&parent->lock, SINGLE_DEPTH_NESTING);
 
-	child->parent = parent;
-	child->groupmask = BIT(parent->num_children++);
+	if (activate) {
+		/*
+		 * @child is the old top and @parent the new one. In this
+		 * case groupmask is pre-initialized and @child already
+		 * accounted, along with its new sibling corresponding to the
+		 * CPU going up.
+		 */
+		WARN_ON_ONCE(child->groupmask != BIT(0) || parent->num_children != 2);
+	} else {
+		/* Adding @child for the CPU going up to @parent. */
+		child->groupmask = BIT(parent->num_children++);
+	}
+
+	/*
+	 * Make sure parent initialization is visible before publishing it to a
+	 * racing CPU entering/exiting idle. This RELEASE barrier enforces an
+	 * address dependency that pairs with the READ_ONCE() in __walk_groups().
+	 */
+	smp_store_release(&child->parent, parent);
 
 	raw_spin_unlock(&parent->lock);
 	raw_spin_unlock_irq(&child->lock);

kernel/trace/trace.c

@@ -4122,6 +4122,7 @@ print_trace_header(struct seq_file *m, struct trace_iterator *iter)
 		   preempt_model_none()      ? "server" :
 		   preempt_model_voluntary() ? "desktop" :
 		   preempt_model_full()      ? "preempt" :
+		   preempt_model_lazy()	     ? "lazy"    :
 		   preempt_model_rt()        ? "preempt_rt" :
 		   "unknown",
 		   /* These are reserved for later use */

kernel/trace/trace_irqsoff.c

@@ -182,6 +182,7 @@ static int irqsoff_graph_entry(struct ftrace_graph_ent *trace,
 	struct trace_array_cpu *data;
 	unsigned long flags;
 	unsigned int trace_ctx;
+	u64 *calltime;
 	int ret;
 
 	if (ftrace_graph_ignore_func(gops, trace))
@@ -199,6 +200,12 @@ static int irqsoff_graph_entry(struct ftrace_graph_ent *trace,
 	if (!func_prolog_dec(tr, &data, &flags))
 		return 0;
 
+	calltime = fgraph_reserve_data(gops->idx, sizeof(*calltime));
+	if (!calltime)
+		return 0;
+
+	*calltime = trace_clock_local();
+
 	trace_ctx = tracing_gen_ctx_flags(flags);
 	ret = __trace_graph_entry(tr, trace, trace_ctx);
 	atomic_dec(&data->disabled);
@@ -213,12 +220,19 @@ static void irqsoff_graph_return(struct ftrace_graph_ret *trace,
 	struct trace_array_cpu *data;
 	unsigned long flags;
 	unsigned int trace_ctx;
+	u64 *calltime;
+	int size;
 
 	ftrace_graph_addr_finish(gops, trace);
 
 	if (!func_prolog_dec(tr, &data, &flags))
 		return;
 
+	calltime = fgraph_retrieve_data(gops->idx, &size);
+	if (!calltime)
+		return;
+	trace->calltime = *calltime;
+
 	trace_ctx = tracing_gen_ctx_flags(flags);
 	__trace_graph_return(tr, trace, trace_ctx);
 	atomic_dec(&data->disabled);

kernel/trace/trace_kprobe.c

@@ -940,8 +940,10 @@ static int __trace_kprobe_create(int argc, const char *argv[])
 		}
 		/* a symbol specified */
 		symbol = kstrdup(argv[1], GFP_KERNEL);
-		if (!symbol)
-			return -ENOMEM;
+		if (!symbol) {
+			ret = -ENOMEM;
+			goto error;
+		}
 
 		tmp = strchr(symbol, '%');
 		if (tmp) {

kernel/trace/trace_sched_wakeup.c

@@ -118,6 +118,7 @@ static int wakeup_graph_entry(struct ftrace_graph_ent *trace,
 	struct trace_array *tr = wakeup_trace;
 	struct trace_array_cpu *data;
 	unsigned int trace_ctx;
+	u64 *calltime;
 	int ret = 0;
 
 	if (ftrace_graph_ignore_func(gops, trace))
@@ -135,6 +136,12 @@ static int wakeup_graph_entry(struct ftrace_graph_ent *trace,
 	if (!func_prolog_preempt_disable(tr, &data, &trace_ctx))
 		return 0;
 
+	calltime = fgraph_reserve_data(gops->idx, sizeof(*calltime));
+	if (!calltime)
+		return 0;
+
+	*calltime = trace_clock_local();
+
 	ret = __trace_graph_entry(tr, trace, trace_ctx);
 	atomic_dec(&data->disabled);
 	preempt_enable_notrace();
@@ -148,12 +155,19 @@ static void wakeup_graph_return(struct ftrace_graph_ret *trace,
 	struct trace_array *tr = wakeup_trace;
 	struct trace_array_cpu *data;
 	unsigned int trace_ctx;
+	u64 *calltime;
+	int size;
 
 	ftrace_graph_addr_finish(gops, trace);
 
 	if (!func_prolog_preempt_disable(tr, &data, &trace_ctx))
 		return;
 
+	calltime = fgraph_retrieve_data(gops->idx, &size);
+	if (!calltime)
+		return;
+	trace->calltime = *calltime;
+
 	__trace_graph_return(tr, trace, trace_ctx);
 	atomic_dec(&data->disabled);
 

kernel/workqueue.c

@@ -2508,6 +2508,7 @@ static void __queue_delayed_work(int cpu, struct workqueue_struct *wq,
 		return;
 	}
 
+	WARN_ON_ONCE(cpu != WORK_CPU_UNBOUND && !cpu_online(cpu));
 	dwork->wq = wq;
 	dwork->cpu = cpu;
 	timer->expires = jiffies + delay;
@@ -2533,6 +2534,12 @@ static void __queue_delayed_work(int cpu, struct workqueue_struct *wq,
  * @dwork: work to queue
  * @delay: number of jiffies to wait before queueing
  *
+ * We queue the delayed_work to a specific CPU, for non-zero delays the
+ * caller must ensure it is online and can't go away. Callers that fail
+ * to ensure this, may get @dwork->timer queued to an offlined CPU and
+ * this will prevent queueing of @dwork->work unless the offlined CPU
+ * becomes online again.
+ *
  * Return: %false if @work was already on a queue, %true otherwise.  If
  * @delay is zero and @dwork is idle, it will be scheduled for immediate
  * execution.