Merge tag 'sched-core-2022-10-07' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:
 "Debuggability:

   - Change most occurances of BUG_ON() to WARN_ON_ONCE()

   - Reorganize & fix TASK_ state comparisons, turn it into a bitmap

   - Update/fix misc scheduler debugging facilities

  Load-balancing & regular scheduling:

   - Improve the behavior of the scheduler in presence of lot of
     SCHED_IDLE tasks - in particular they should not impact other
     scheduling classes.

   - Optimize task load tracking, cleanups & fixes

   - Clean up & simplify misc load-balancing code

  Freezer:

   - Rewrite the core freezer to behave better wrt thawing and be
     simpler in general, by replacing PF_FROZEN with TASK_FROZEN &
     fixing/adjusting all the fallout.

  Deadline scheduler:

   - Fix the DL capacity-aware code

   - Factor out dl_task_is_earliest_deadline() &
     replenish_dl_new_period()

   - Relax/optimize locking in task_non_contending()

  Cleanups:

   - Factor out the update_current_exec_runtime() helper

   - Various cleanups, simplifications"

* tag 'sched-core-2022-10-07' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (41 commits)
  sched: Fix more TASK_state comparisons
  sched: Fix TASK_state comparisons
  sched/fair: Move call to list_last_entry() in detach_tasks
  sched/fair: Cleanup loop_max and loop_break
  sched/fair: Make sure to try to detach at least one movable task
  sched: Show PF_flag holes
  freezer,sched: Rewrite core freezer logic
  sched: Widen TAKS_state literals
  sched/wait: Add wait_event_state()
  sched/completion: Add wait_for_completion_state()
  sched: Add TASK_ANY for wait_task_inactive()
  sched: Change wait_task_inactive()s match_state
  freezer,umh: Clean up freezer/initrd interaction
  freezer: Have {,un}lock_system_sleep() save/restore flags
  sched: Rename task_running() to task_on_cpu()
  sched/fair: Cleanup for SIS_PROP
  sched/fair: Default to false in test_idle_cores()
  sched/fair: Remove useless check in select_idle_core()
  sched/fair: Avoid double search on same cpu
  sched/fair: Remove redundant check in select_idle_smt()
  ...

5 files changed, 59 insertions, 40 deletions

diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index 89c71fce225d..f58a0aa92310 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -92,20 +92,24 @@ bool hibernation_available(void)
  */
 void hibernation_set_ops(const struct platform_hibernation_ops *ops)
 {
+	unsigned int sleep_flags;
+
 	if (ops && !(ops->begin && ops->end &&  ops->pre_snapshot
 	    && ops->prepare && ops->finish && ops->enter && ops->pre_restore
 	    && ops->restore_cleanup && ops->leave)) {
 		WARN_ON(1);
 		return;
 	}
-	lock_system_sleep();
+
+	sleep_flags = lock_system_sleep();
+
 	hibernation_ops = ops;
 	if (ops)
 		hibernation_mode = HIBERNATION_PLATFORM;
 	else if (hibernation_mode == HIBERNATION_PLATFORM)
 		hibernation_mode = HIBERNATION_SHUTDOWN;
 
-	unlock_system_sleep();
+	unlock_system_sleep(sleep_flags);
 }
 EXPORT_SYMBOL_GPL(hibernation_set_ops);
 
@@ -713,6 +717,7 @@ static int load_image_and_restore(void)
 int hibernate(void)
 {
 	bool snapshot_test = false;
+	unsigned int sleep_flags;
 	int error;
 
 	if (!hibernation_available()) {
@@ -720,7 +725,7 @@ int hibernate(void)
 		return -EPERM;
 	}
 
-	lock_system_sleep();
+	sleep_flags = lock_system_sleep();
 	/* The snapshot device should not be opened while we're running */
 	if (!hibernate_acquire()) {
 		error = -EBUSY;
@@ -794,7 +799,7 @@ int hibernate(void)
 	pm_restore_console();
 	hibernate_release();
  Unlock:
-	unlock_system_sleep();
+	unlock_system_sleep(sleep_flags);
 	pr_info("hibernation exit\n");
 
 	return error;
@@ -809,9 +814,10 @@ int hibernate(void)
  */
 int hibernate_quiet_exec(int (*func)(void *data), void *data)
 {
+	unsigned int sleep_flags;
 	int error;
 
-	lock_system_sleep();
+	sleep_flags = lock_system_sleep();
 
 	if (!hibernate_acquire()) {
 		error = -EBUSY;
@@ -891,7 +897,7 @@ restore:
 	hibernate_release();
 
 unlock:
-	unlock_system_sleep();
+	unlock_system_sleep(sleep_flags);
 
 	return error;
 }
@@ -1100,11 +1106,12 @@ static ssize_t disk_show(struct kobject *kobj, struct kobj_attribute *attr,
 static ssize_t disk_store(struct kobject *kobj, struct kobj_attribute *attr,
 			  const char *buf, size_t n)
 {
+	int mode = HIBERNATION_INVALID;
+	unsigned int sleep_flags;
 	int error = 0;
-	int i;
 	int len;
 	char *p;
-	int mode = HIBERNATION_INVALID;
+	int i;
 
 	if (!hibernation_available())
 		return -EPERM;
@@ -1112,7 +1119,7 @@ static ssize_t disk_store(struct kobject *kobj, struct kobj_attribute *attr,
 	p = memchr(buf, '\n', n);
 	len = p ? p - buf : n;
 
-	lock_system_sleep();
+	sleep_flags = lock_system_sleep();
 	for (i = HIBERNATION_FIRST; i <= HIBERNATION_MAX; i++) {
 		if (len == strlen(hibernation_modes[i])
 		    && !strncmp(buf, hibernation_modes[i], len)) {
@@ -1142,7 +1149,7 @@ static ssize_t disk_store(struct kobject *kobj, struct kobj_attribute *attr,
 	if (!error)
 		pm_pr_dbg("Hibernation mode set to '%s'\n",
 			       hibernation_modes[mode]);
-	unlock_system_sleep();
+	unlock_system_sleep(sleep_flags);
 	return error ? error : n;
 }
 
@@ -1158,9 +1165,10 @@ static ssize_t resume_show(struct kobject *kobj, struct kobj_attribute *attr,
 static ssize_t resume_store(struct kobject *kobj, struct kobj_attribute *attr,
 			    const char *buf, size_t n)
 {
-	dev_t res;
+	unsigned int sleep_flags;
 	int len = n;
 	char *name;
+	dev_t res;
 
 	if (len && buf[len-1] == '\n')
 		len--;
@@ -1173,9 +1181,10 @@ static ssize_t resume_store(struct kobject *kobj, struct kobj_attribute *attr,
 	if (!res)
 		return -EINVAL;
 
-	lock_system_sleep();
+	sleep_flags = lock_system_sleep();
 	swsusp_resume_device = res;
-	unlock_system_sleep();
+	unlock_system_sleep(sleep_flags);
+
 	pm_pr_dbg("Configured hibernation resume from disk to %u\n",
 		  swsusp_resume_device);
 	noresume = 0;
diff --git a/kernel/power/main.c b/kernel/power/main.c
index e3694034b753..31ec4a9b9d70 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -21,14 +21,16 @@
 
 #ifdef CONFIG_PM_SLEEP
 
-void lock_system_sleep(void)
+unsigned int lock_system_sleep(void)
 {
-	current->flags |= PF_FREEZER_SKIP;
+	unsigned int flags = current->flags;
+	current->flags |= PF_NOFREEZE;
 	mutex_lock(&system_transition_mutex);
+	return flags;
 }
 EXPORT_SYMBOL_GPL(lock_system_sleep);
 
-void unlock_system_sleep(void)
+void unlock_system_sleep(unsigned int flags)
 {
 	/*
 	 * Don't use freezer_count() because we don't want the call to
@@ -46,7 +48,8 @@ void unlock_system_sleep(void)
 	 * Which means, if we use try_to_freeze() here, it would make them
 	 * enter the refrigerator, thus causing hibernation to lockup.
 	 */
-	current->flags &= ~PF_FREEZER_SKIP;
+	if (!(flags & PF_NOFREEZE))
+		current->flags &= ~PF_NOFREEZE;
 	mutex_unlock(&system_transition_mutex);
 }
 EXPORT_SYMBOL_GPL(unlock_system_sleep);
@@ -263,16 +266,17 @@ static ssize_t pm_test_show(struct kobject *kobj, struct kobj_attribute *attr,
 static ssize_t pm_test_store(struct kobject *kobj, struct kobj_attribute *attr,
 				const char *buf, size_t n)
 {
+	unsigned int sleep_flags;
 	const char * const *s;
+	int error = -EINVAL;
 	int level;
 	char *p;
 	int len;
-	int error = -EINVAL;
 
 	p = memchr(buf, '\n', n);
 	len = p ? p - buf : n;
 
-	lock_system_sleep();
+	sleep_flags = lock_system_sleep();
 
 	level = TEST_FIRST;
 	for (s = &pm_tests[level]; level <= TEST_MAX; s++, level++)
@@ -282,7 +286,7 @@ static ssize_t pm_test_store(struct kobject *kobj, struct kobj_attribute *attr,
 			break;
 		}
 
-	unlock_system_sleep();
+	unlock_system_sleep(sleep_flags);
 
 	return error ? error : n;
 }
diff --git a/kernel/power/process.c b/kernel/power/process.c
index 3068601e585a..ddd9988327fe 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -50,8 +50,7 @@ static int try_to_freeze_tasks(bool user_only)
 			if (p == current || !freeze_task(p))
 				continue;
 
-			if (!freezer_should_skip(p))
-				todo++;
+			todo++;
 		}
 		read_unlock(&tasklist_lock);
 
@@ -96,8 +95,7 @@ static int try_to_freeze_tasks(bool user_only)
 		if (!wakeup || pm_debug_messages_on) {
 			read_lock(&tasklist_lock);
 			for_each_process_thread(g, p) {
-				if (p != current && !freezer_should_skip(p)
-				    && freezing(p) && !frozen(p))
+				if (p != current && freezing(p) && !frozen(p))
 					sched_show_task(p);
 			}
 			read_unlock(&tasklist_lock);
@@ -129,7 +127,7 @@ int freeze_processes(void)
 	current->flags |= PF_SUSPEND_TASK;
 
 	if (!pm_freezing)
-		atomic_inc(&system_freezing_cnt);
+		static_branch_inc(&freezer_active);
 
 	pm_wakeup_clear(0);
 	pr_info("Freezing user space processes ... ");
@@ -190,7 +188,7 @@ void thaw_processes(void)
 
 	trace_suspend_resume(TPS("thaw_processes"), 0, true);
 	if (pm_freezing)
-		atomic_dec(&system_freezing_cnt);
+		static_branch_dec(&freezer_active);
 	pm_freezing = false;
 	pm_nosig_freezing = false;
 
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index c6272d466e58..fa3bf161d13f 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -75,9 +75,11 @@ EXPORT_SYMBOL_GPL(pm_suspend_default_s2idle);
 
 void s2idle_set_ops(const struct platform_s2idle_ops *ops)
 {
-	lock_system_sleep();
+	unsigned int sleep_flags;
+
+	sleep_flags = lock_system_sleep();
 	s2idle_ops = ops;
-	unlock_system_sleep();
+	unlock_system_sleep(sleep_flags);
 }
 
 static void s2idle_begin(void)
@@ -203,7 +205,9 @@ __setup("mem_sleep_default=", mem_sleep_default_setup);
  */
 void suspend_set_ops(const struct platform_suspend_ops *ops)
 {
-	lock_system_sleep();
+	unsigned int sleep_flags;
+
+	sleep_flags = lock_system_sleep();
 
 	suspend_ops = ops;
 
@@ -219,7 +223,7 @@ void suspend_set_ops(const struct platform_suspend_ops *ops)
 			mem_sleep_current = PM_SUSPEND_MEM;
 	}
 
-	unlock_system_sleep();
+	unlock_system_sleep(sleep_flags);
 }
 EXPORT_SYMBOL_GPL(suspend_set_ops);
 
diff --git a/kernel/power/user.c b/kernel/power/user.c
index d43c2aa583b2..3a4e70366f35 100644
--- a/kernel/power/user.c
+++ b/kernel/power/user.c
@@ -47,12 +47,13 @@ int is_hibernate_resume_dev(dev_t dev)
 static int snapshot_open(struct inode *inode, struct file *filp)
 {
 	struct snapshot_data *data;
+	unsigned int sleep_flags;
 	int error;
 
 	if (!hibernation_available())
 		return -EPERM;
 
-	lock_system_sleep();
+	sleep_flags = lock_system_sleep();
 
 	if (!hibernate_acquire()) {
 		error = -EBUSY;
@@ -98,7 +99,7 @@ static int snapshot_open(struct inode *inode, struct file *filp)
 	data->dev = 0;
 
  Unlock:
-	unlock_system_sleep();
+	unlock_system_sleep(sleep_flags);
 
 	return error;
 }
@@ -106,8 +107,9 @@ static int snapshot_open(struct inode *inode, struct file *filp)
 static int snapshot_release(struct inode *inode, struct file *filp)
 {
 	struct snapshot_data *data;
+	unsigned int sleep_flags;
 
-	lock_system_sleep();
+	sleep_flags = lock_system_sleep();
 
 	swsusp_free();
 	data = filp->private_data;
@@ -124,7 +126,7 @@ static int snapshot_release(struct inode *inode, struct file *filp)
 			PM_POST_HIBERNATION : PM_POST_RESTORE);
 	hibernate_release();
 
-	unlock_system_sleep();
+	unlock_system_sleep(sleep_flags);
 
 	return 0;
 }
@@ -132,11 +134,12 @@ static int snapshot_release(struct inode *inode, struct file *filp)
 static ssize_t snapshot_read(struct file *filp, char __user *buf,
                              size_t count, loff_t *offp)
 {
+	loff_t pg_offp = *offp & ~PAGE_MASK;
 	struct snapshot_data *data;
+	unsigned int sleep_flags;
 	ssize_t res;
-	loff_t pg_offp = *offp & ~PAGE_MASK;
 
-	lock_system_sleep();
+	sleep_flags = lock_system_sleep();
 
 	data = filp->private_data;
 	if (!data->ready) {
@@ -157,7 +160,7 @@ static ssize_t snapshot_read(struct file *filp, char __user *buf,
 		*offp += res;
 
  Unlock:
-	unlock_system_sleep();
+	unlock_system_sleep(sleep_flags);
 
 	return res;
 }
@@ -165,16 +168,17 @@ static ssize_t snapshot_read(struct file *filp, char __user *buf,
 static ssize_t snapshot_write(struct file *filp, const char __user *buf,
                               size_t count, loff_t *offp)
 {
+	loff_t pg_offp = *offp & ~PAGE_MASK;
 	struct snapshot_data *data;
+	unsigned long sleep_flags;
 	ssize_t res;
-	loff_t pg_offp = *offp & ~PAGE_MASK;
 
 	if (need_wait) {
 		wait_for_device_probe();
 		need_wait = false;
 	}
 
-	lock_system_sleep();
+	sleep_flags = lock_system_sleep();
 
 	data = filp->private_data;
 
@@ -196,7 +200,7 @@ static ssize_t snapshot_write(struct file *filp, const char __user *buf,
 	if (res > 0)
 		*offp += res;
 unlock:
-	unlock_system_sleep();
+	unlock_system_sleep(sleep_flags);
 
 	return res;
 }