Merge: Sched: late fixes for 9.7

caringi · caringi · commit 6840458f2958 · 2025-07-07T16:55:57.000-03:00
MR: https://gitlab.com/redhat/centos-stream/src/kernel/centos-stream-9/-/merge_requests/7023 JIRA: https://issues.redhat.com/browse/RHEL-96250 A few fixes have come in upstream (as of about v6.15) that are needed in rhel9. We'll take them now to prevent hitting these issues later. Signed-off-by: Phil Auld <pauld@redhat.com> Approved-by: Herton R. Krzesinski <herton@redhat.com> Approved-by: Aristeu Rozanski <arozansk@redhat.com> Approved-by: CKI KWF Bot <cki-ci-bot+kwf-gitlab-com@redhat.com> Merged-by: Augusto Caringi <acaringi@redhat.com>
diff --git a/include/linux/sched.h b/include/linux/sched.h
@@ -1725,8 +1725,9 @@ static inline unsigned int __task_state_index(unsigned int tsk_state,
 	 * We're lying here, but rather than expose a completely new task state
 	 * to userspace, we can make this appear as if the task has gone through
 	 * a regular rt_mutex_lock() call.
+	 * Report frozen tasks as uninterruptible.
 	 */
-	if (tsk_state & TASK_RTLOCK_WAIT)
+	if ((tsk_state & TASK_RTLOCK_WAIT) || (tsk_state & TASK_FROZEN))
 		state = TASK_UNINTERRUPTIBLE;
 
 	return fls(state);
diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
@@ -466,6 +466,13 @@ enum {
 
 static inline void membarrier_mm_sync_core_before_usermode(struct mm_struct *mm)
 {
+	/*
+	 * The atomic_read() below prevents CSE. The following should
+	 * help the compiler generate more efficient code on architectures
+	 * where sync_core_before_usermode() is a no-op.
+	 */
+	if (!IS_ENABLED(CONFIG_ARCH_HAS_SYNC_CORE_BEFORE_USERMODE))
+		return;
 	if (current->mm != mm)
 		return;
 	if (likely(!(atomic_read(&mm->membarrier_state) &
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
@@ -1031,9 +1031,10 @@ void wake_up_q(struct wake_q_head *head)
 		struct task_struct *task;
 
 		task = container_of(node, struct task_struct, wake_q);
-		/* Task can safely be re-inserted now: */
 		node = node->next;
-		task->wake_q.next = NULL;
+		/* pairs with cmpxchg_relaxed() in __wake_q_add() */
+		WRITE_ONCE(task->wake_q.next, NULL);
+		/* Task can safely be re-inserted now. */
 
 		/*
 		 * wake_up_process() executes a full barrier, which pairs with
@@ -8810,7 +8811,7 @@ void sched_release_group(struct task_group *tg)
 	spin_unlock_irqrestore(&task_group_lock, flags);
 }
 
-static struct task_group *sched_get_task_group(struct task_struct *tsk)
+static void sched_change_group(struct task_struct *tsk)
 {
 	struct task_group *tg;
 
@@ -8822,13 +8823,7 @@ static struct task_group *sched_get_task_group(struct task_struct *tsk)
 	tg = container_of(task_css_check(tsk, cpu_cgrp_id, true),
 			  struct task_group, css);
 	tg = autogroup_task_group(tsk, tg);
-
-	return tg;
-}
-
-static void sched_change_group(struct task_struct *tsk, struct task_group *group)
-{
-	tsk->sched_task_group = group;
+	tsk->sched_task_group = tg;
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	if (tsk->sched_class->task_change_group)
@@ -8849,20 +8844,11 @@ void sched_move_task(struct task_struct *tsk)
 {
 	int queued, running, queue_flags =
 		DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK;
-	struct task_group *group;
 	struct rq *rq;
 
 	CLASS(task_rq_lock, rq_guard)(tsk);
 	rq = rq_guard.rq;
 
-	/*
-	 * Esp. with SCHED_AUTOGROUP enabled it is possible to get superfluous
-	 * group changes.
-	 */
-	group = sched_get_task_group(tsk);
-	if (group == tsk->sched_task_group)
-		return;
-
 	update_rq_clock(rq);
 
 	running = task_current(rq, tsk);
@@ -8873,7 +8859,7 @@ void sched_move_task(struct task_struct *tsk)
 	if (running)
 		put_prev_task(rq, tsk);
 
-	sched_change_group(tsk, group);
+	sched_change_group(tsk);
 
 	if (queued)
 		enqueue_task(rq, tsk, queue_flags);
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
@@ -81,9 +81,23 @@ static bool sugov_should_update_freq(struct sugov_policy *sg_policy, u64 time)
 	if (!cpufreq_this_cpu_can_update(sg_policy->policy))
 		return false;
 
-	if (unlikely(sg_policy->limits_changed)) {
-		sg_policy->limits_changed = false;
-		sg_policy->need_freq_update = cpufreq_driver_test_flags(CPUFREQ_NEED_UPDATE_LIMITS);
+	if (unlikely(READ_ONCE(sg_policy->limits_changed))) {
+		WRITE_ONCE(sg_policy->limits_changed, false);
+		sg_policy->need_freq_update = true;
+
+		/*
+		 * The above limits_changed update must occur before the reads
+		 * of policy limits in cpufreq_driver_resolve_freq() or a policy
+		 * limits update might be missed, so use a memory barrier to
+		 * ensure it.
+		 *
+		 * This pairs with the write memory barrier in sugov_limits().
+		 */
+		smp_mb();
+
+		return true;
+	} else if (sg_policy->need_freq_update) {
+		/* ignore_dl_rate_limit() wants a new frequency to be found. */
 		return true;
 	}
 
@@ -95,10 +109,22 @@ static bool sugov_should_update_freq(struct sugov_policy *sg_policy, u64 time)
 static bool sugov_update_next_freq(struct sugov_policy *sg_policy, u64 time,
 				   unsigned int next_freq)
 {
-	if (sg_policy->need_freq_update)
+	if (sg_policy->need_freq_update) {
 		sg_policy->need_freq_update = false;
-	else if (sg_policy->next_freq == next_freq)
+		/*
+		 * The policy limits have changed, but if the return value of
+		 * cpufreq_driver_resolve_freq() after applying the new limits
+		 * is still equal to the previously selected frequency, the
+		 * driver callback need not be invoked unless the driver
+		 * specifically wants that to happen on every update of the
+		 * policy limits.
+		 */
+		if (sg_policy->next_freq == next_freq &&
+		    !cpufreq_driver_test_flags(CPUFREQ_NEED_UPDATE_LIMITS))
+			return false;
+	} else if (sg_policy->next_freq == next_freq) {
 		return false;
+	}
 
 	sg_policy->next_freq = next_freq;
 	sg_policy->last_freq_update_time = time;
@@ -344,7 +370,7 @@ static inline bool sugov_cpu_is_busy(struct sugov_cpu *sg_cpu) { return false; }
 static inline void ignore_dl_rate_limit(struct sugov_cpu *sg_cpu)
 {
 	if (cpu_bw_dl(cpu_rq(sg_cpu->cpu)) > sg_cpu->bw_min)
-		sg_cpu->sg_policy->limits_changed = true;
+		sg_cpu->sg_policy->need_freq_update = true;
 }
 
 static inline bool sugov_update_single_common(struct sugov_cpu *sg_cpu,
@@ -880,7 +906,16 @@ static void sugov_limits(struct cpufreq_policy *policy)
 		mutex_unlock(&sg_policy->work_lock);
 	}
 
-	sg_policy->limits_changed = true;
+	/*
+	 * The limits_changed update below must take place before the updates
+	 * of policy limits in cpufreq_set_policy() or a policy limits update
+	 * might be missed, so use a memory barrier to ensure it.
+	 *
+	 * This pairs with the memory barrier in sugov_should_update_freq().
+	 */
+	smp_wmb();
+
+	WRITE_ONCE(sg_policy->limits_changed, true);
 }
 
 struct cpufreq_governor schedutil_gov = {
