sched/psi: Allow unprivileged polling of N*2s period

PSI offers 2 mechanisms to get information about a specific resource
pressure. One is reading from /proc/pressure/<resource>, which gives
average pressures aggregated every 2s. The other is creating a pollable
fd for a specific resource and cgroup.

The trigger creation requires CAP_SYS_RESOURCE, and gives the
possibility to pick specific time window and threshold, spawing an RT
thread to aggregate the data.

Systemd would like to provide containers the option to monitor pressure
on their own cgroup and sub-cgroups. For example, if systemd launches a
container that itself then launches services, the container should have
the ability to poll() for pressure in individual services. But neither
the container nor the services are privileged.

This patch implements a mechanism to allow unprivileged users to create
pressure triggers. The difference with privileged triggers creation is
that unprivileged ones must have a time window that's a multiple of 2s.
This is so that we can avoid unrestricted spawning of rt threads, and
use instead the same aggregation mechanism done for the averages, which
runs independently of any triggers.

Suggested-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Domenico Cerasuolo <cerasuolodomenico@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Link: https://lore.kernel.org/r/20230330105418.77061-5-cerasuolodomenico@gmail.com

2 files changed, 109 insertions, 68 deletions

diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 935e8121b21e..dead36969bba 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -3761,7 +3761,7 @@ static ssize_t pressure_write(struct kernfs_open_file *of, char *buf,
 	}
 
 	psi = cgroup_psi(cgrp);
-	new = psi_trigger_create(psi, buf, res);
+	new = psi_trigger_create(psi, buf, res, of->file);
 	if (IS_ERR(new)) {
 		cgroup_put(cgrp);
 		return PTR_ERR(new);
diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
index f3df6a8ff493..e072f6b31bf3 100644
--- a/kernel/sched/psi.c
+++ b/kernel/sched/psi.c
@@ -186,9 +186,14 @@ static void group_init(struct psi_group *group)
 		seqcount_init(&per_cpu_ptr(group->pcpu, cpu)->seq);
 	group->avg_last_update = sched_clock();
 	group->avg_next_update = group->avg_last_update + psi_period;
-	INIT_DELAYED_WORK(&group->avgs_work, psi_avgs_work);
 	mutex_init(&group->avgs_lock);
-	/* Init trigger-related members */
+
+	/* Init avg trigger-related members */
+	INIT_LIST_HEAD(&group->avg_triggers);
+	memset(group->avg_nr_triggers, 0, sizeof(group->avg_nr_triggers));
+	INIT_DELAYED_WORK(&group->avgs_work, psi_avgs_work);
+
+	/* Init rtpoll trigger-related members */
 	atomic_set(&group->rtpoll_scheduled, 0);
 	mutex_init(&group->rtpoll_trigger_lock);
 	INIT_LIST_HEAD(&group->rtpoll_triggers);
@@ -430,21 +435,32 @@ static u64 window_update(struct psi_window *win, u64 now, u64 value)
 	return growth;
 }
 
-static u64 update_triggers(struct psi_group *group, u64 now, bool *update_total)
+static u64 update_triggers(struct psi_group *group, u64 now, bool *update_total,
+						   enum psi_aggregators aggregator)
 {
 	struct psi_trigger *t;
-	u64 *total = group->total[PSI_POLL];
+	u64 *total = group->total[aggregator];
+	struct list_head *triggers;
+	u64 *aggregator_total;
 	*update_total = false;
 
+	if (aggregator == PSI_AVGS) {
+		triggers = &group->avg_triggers;
+		aggregator_total = group->avg_total;
+	} else {
+		triggers = &group->rtpoll_triggers;
+		aggregator_total = group->rtpoll_total;
+	}
+
 	/*
 	 * On subsequent updates, calculate growth deltas and let
 	 * watchers know when their specified thresholds are exceeded.
 	 */
-	list_for_each_entry(t, &group->rtpoll_triggers, node) {
+	list_for_each_entry(t, triggers, node) {
 		u64 growth;
 		bool new_stall;
 
-		new_stall = group->rtpoll_total[t->state] != total[t->state];
+		new_stall = aggregator_total[t->state] != total[t->state];
 
 		/* Check for stall activity or a previous threshold breach */
 		if (!new_stall && !t->pending_event)
@@ -546,6 +562,7 @@ static void psi_avgs_work(struct work_struct *work)
 	struct delayed_work *dwork;
 	struct psi_group *group;
 	u32 changed_states;
+	bool update_total;
 	u64 now;
 
 	dwork = to_delayed_work(work);
@@ -563,8 +580,10 @@ static void psi_avgs_work(struct work_struct *work)
 	 * Once restarted, we'll catch up the running averages in one
 	 * go - see calc_avgs() and missed_periods.
 	 */
-	if (now >= group->avg_next_update)
+	if (now >= group->avg_next_update) {
+		update_triggers(group, now, &update_total, PSI_AVGS);
 		group->avg_next_update = update_averages(group, now);
+	}
 
 	if (changed_states & PSI_STATE_RESCHEDULE) {
 		schedule_delayed_work(dwork, nsecs_to_jiffies(
@@ -574,7 +593,7 @@ static void psi_avgs_work(struct work_struct *work)
 	mutex_unlock(&group->avgs_lock);
 }
 
-static void init_triggers(struct psi_group *group, u64 now)
+static void init_rtpoll_triggers(struct psi_group *group, u64 now)
 {
 	struct psi_trigger *t;
 
@@ -667,7 +686,7 @@ static void psi_rtpoll_work(struct psi_group *group)
 	if (changed_states & group->rtpoll_states) {
 		/* Initialize trigger windows when entering polling mode */
 		if (now > group->rtpoll_until)
-			init_triggers(group, now);
+			init_rtpoll_triggers(group, now);
 
 		/*
 		 * Keep the monitor active for at least the duration of the
@@ -684,7 +703,7 @@ static void psi_rtpoll_work(struct psi_group *group)
 	}
 
 	if (now >= group->rtpoll_next_update) {
-		group->rtpoll_next_update = update_triggers(group, now, &update_total);
+		group->rtpoll_next_update = update_triggers(group, now, &update_total, PSI_POLL);
 		if (update_total)
 			memcpy(group->rtpoll_total, group->total[PSI_POLL],
 				   sizeof(group->rtpoll_total));
@@ -1254,16 +1273,23 @@ int psi_show(struct seq_file *m, struct psi_group *group, enum psi_res res)
 }
 
 struct psi_trigger *psi_trigger_create(struct psi_group *group,
-			char *buf, enum psi_res res)
+			char *buf, enum psi_res res, struct file *file)
 {
 	struct psi_trigger *t;
 	enum psi_states state;
 	u32 threshold_us;
+	bool privileged;
 	u32 window_us;
 
 	if (static_branch_likely(&psi_disabled))
 		return ERR_PTR(-EOPNOTSUPP);
 
+	/*
+	 * Checking the privilege here on file->f_cred implies that a privileged user
+	 * could open the file and delegate the write to an unprivileged one.
+	 */
+	privileged = cap_raised(file->f_cred->cap_effective, CAP_SYS_RESOURCE);
+
 	if (sscanf(buf, "some %u %u", &threshold_us, &window_us) == 2)
 		state = PSI_IO_SOME + res * 2;
 	else if (sscanf(buf, "full %u %u", &threshold_us, &window_us) == 2)
@@ -1283,6 +1309,13 @@ struct psi_trigger *psi_trigger_create(struct psi_group *group,
 		window_us > WINDOW_MAX_US)
 		return ERR_PTR(-EINVAL);
 
+	/*
+	 * Unprivileged users can only use 2s windows so that averages aggregation
+	 * work is used, and no RT threads need to be spawned.
+	 */
+	if (!privileged && window_us % 2000000)
+		return ERR_PTR(-EINVAL);
+
 	/* Check threshold */
 	if (threshold_us == 0 || threshold_us > window_us)
 		return ERR_PTR(-EINVAL);
@@ -1302,31 +1335,40 @@ struct psi_trigger *psi_trigger_create(struct psi_group *group,
 	t->last_event_time = 0;
 	init_waitqueue_head(&t->event_wait);
 	t->pending_event = false;
+	t->aggregator = privileged ? PSI_POLL : PSI_AVGS;
 
-	mutex_lock(&group->rtpoll_trigger_lock);
+	if (privileged) {
+		mutex_lock(&group->rtpoll_trigger_lock);
 
-	if (!rcu_access_pointer(group->rtpoll_task)) {
-		struct task_struct *task;
+		if (!rcu_access_pointer(group->rtpoll_task)) {
+			struct task_struct *task;
 
-		task = kthread_create(psi_rtpoll_worker, group, "psimon");
-		if (IS_ERR(task)) {
-			kfree(t);
-			mutex_unlock(&group->rtpoll_trigger_lock);
-			return ERR_CAST(task);
+			task = kthread_create(psi_rtpoll_worker, group, "psimon");
+			if (IS_ERR(task)) {
+				kfree(t);
+				mutex_unlock(&group->rtpoll_trigger_lock);
+				return ERR_CAST(task);
+			}
+			atomic_set(&group->rtpoll_wakeup, 0);
+			wake_up_process(task);
+			rcu_assign_pointer(group->rtpoll_task, task);
 		}
-		atomic_set(&group->rtpoll_wakeup, 0);
-		wake_up_process(task);
-		rcu_assign_pointer(group->rtpoll_task, task);
-	}
 
-	list_add(&t->node, &group->rtpoll_triggers);
-	group->rtpoll_min_period = min(group->rtpoll_min_period,
-		div_u64(t->win.size, UPDATES_PER_WINDOW));
-	group->rtpoll_nr_triggers[t->state]++;
-	group->rtpoll_states |= (1 << t->state);
+		list_add(&t->node, &group->rtpoll_triggers);
+		group->rtpoll_min_period = min(group->rtpoll_min_period,
+			div_u64(t->win.size, UPDATES_PER_WINDOW));
+		group->rtpoll_nr_triggers[t->state]++;
+		group->rtpoll_states |= (1 << t->state);
 
-	mutex_unlock(&group->rtpoll_trigger_lock);
+		mutex_unlock(&group->rtpoll_trigger_lock);
+	} else {
+		mutex_lock(&group->avgs_lock);
+
+		list_add(&t->node, &group->avg_triggers);
+		group->avg_nr_triggers[t->state]++;
 
+		mutex_unlock(&group->avgs_lock);
+	}
 	return t;
 }
 
@@ -1350,34 +1392,41 @@ void psi_trigger_destroy(struct psi_trigger *t)
 	 */
 	wake_up_pollfree(&t->event_wait);
 
-	mutex_lock(&group->rtpoll_trigger_lock);
-
-	if (!list_empty(&t->node)) {
-		struct psi_trigger *tmp;
-		u64 period = ULLONG_MAX;
-
-		list_del(&t->node);
-		group->rtpoll_nr_triggers[t->state]--;
-		if (!group->rtpoll_nr_triggers[t->state])
-			group->rtpoll_states &= ~(1 << t->state);
-		/* reset min update period for the remaining triggers */
-		list_for_each_entry(tmp, &group->rtpoll_triggers, node)
-			period = min(period, div_u64(tmp->win.size,
-					UPDATES_PER_WINDOW));
-		group->rtpoll_min_period = period;
-		/* Destroy rtpoll_task when the last trigger is destroyed */
-		if (group->rtpoll_states == 0) {
-			group->rtpoll_until = 0;
-			task_to_destroy = rcu_dereference_protected(
-					group->rtpoll_task,
-					lockdep_is_held(&group->rtpoll_trigger_lock));
-			rcu_assign_pointer(group->rtpoll_task, NULL);
-			del_timer(&group->rtpoll_timer);
+	if (t->aggregator == PSI_AVGS) {
+		mutex_lock(&group->avgs_lock);
+		if (!list_empty(&t->node)) {
+			list_del(&t->node);
+			group->avg_nr_triggers[t->state]--;
 		}
+		mutex_unlock(&group->avgs_lock);
+	} else {
+		mutex_lock(&group->rtpoll_trigger_lock);
+		if (!list_empty(&t->node)) {
+			struct psi_trigger *tmp;
+			u64 period = ULLONG_MAX;
+
+			list_del(&t->node);
+			group->rtpoll_nr_triggers[t->state]--;
+			if (!group->rtpoll_nr_triggers[t->state])
+				group->rtpoll_states &= ~(1 << t->state);
+			/* reset min update period for the remaining triggers */
+			list_for_each_entry(tmp, &group->rtpoll_triggers, node)
+				period = min(period, div_u64(tmp->win.size,
+						UPDATES_PER_WINDOW));
+			group->rtpoll_min_period = period;
+			/* Destroy rtpoll_task when the last trigger is destroyed */
+			if (group->rtpoll_states == 0) {
+				group->rtpoll_until = 0;
+				task_to_destroy = rcu_dereference_protected(
+						group->rtpoll_task,
+						lockdep_is_held(&group->rtpoll_trigger_lock));
+				rcu_assign_pointer(group->rtpoll_task, NULL);
+				del_timer(&group->rtpoll_timer);
+			}
+		}
+		mutex_unlock(&group->rtpoll_trigger_lock);
 	}
 
-	mutex_unlock(&group->rtpoll_trigger_lock);
-
 	/*
 	 * Wait for psi_schedule_rtpoll_work RCU to complete its read-side
 	 * critical section before destroying the trigger and optionally the
@@ -1437,27 +1486,19 @@ static int psi_cpu_show(struct seq_file *m, void *v)
 	return psi_show(m, &psi_system, PSI_CPU);
 }
 
-static int psi_open(struct file *file, int (*psi_show)(struct seq_file *, void *))
-{
-	if (file->f_mode & FMODE_WRITE && !capable(CAP_SYS_RESOURCE))
-		return -EPERM;
-
-	return single_open(file, psi_show, NULL);
-}
-
 static int psi_io_open(struct inode *inode, struct file *file)
 {
-	return psi_open(file, psi_io_show);
+	return single_open(file, psi_io_show, NULL);
 }
 
 static int psi_memory_open(struct inode *inode, struct file *file)
 {
-	return psi_open(file, psi_memory_show);
+	return single_open(file, psi_memory_show, NULL);
 }
 
 static int psi_cpu_open(struct inode *inode, struct file *file)
 {
-	return psi_open(file, psi_cpu_show);
+	return single_open(file, psi_cpu_show, NULL);
 }
 
 static ssize_t psi_write(struct file *file, const char __user *user_buf,
@@ -1491,7 +1532,7 @@ static ssize_t psi_write(struct file *file, const char __user *user_buf,
 		return -EBUSY;
 	}
 
-	new = psi_trigger_create(&psi_system, buf, res);
+	new = psi_trigger_create(&psi_system, buf, res, file);
 	if (IS_ERR(new)) {
 		mutex_unlock(&seq->lock);
 		return PTR_ERR(new);
@@ -1571,7 +1612,7 @@ static int psi_irq_show(struct seq_file *m, void *v)
 
 static int psi_irq_open(struct inode *inode, struct file *file)
 {
-	return psi_open(file, psi_irq_show);
+	return single_open(file, psi_irq_show, NULL);
 }
 
 static ssize_t psi_irq_write(struct file *file, const char __user *user_buf,