- Remove a cgroup from under a polling process properly

- Fix the idle sibling selection
 -----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCgAdFiEEzv7L6UO9uDPlPSfHEsHwGGHeVUoFAmS0N8AACgkQEsHwGGHe
 VUq4qhAAhLlRz7V0txbvj65xrQAuF7RiqWQlIm6NYX+eWb5wpqasy8mTpVr37Lhg
 JJIdSlI0sw3vIgnjgmuLU6e6MKO2pDWCqppv7CB4YjTT6/ifyIWvFotHTtfOBDjy
 eTV/wEpfDKOKHJDdWHRdUjiDgktZs1gJVV8e65/ViuWoCEV3ARy7tS4liORiwNpr
 RTuG6C3lDAfw6RKWCvBxDV15XhMDNYYQzN1bwedTAryP8jAFFUKce2de6HK6qyUF
 pNqzX0eGkN+6TG13uKLJIsAfdydWHWvkXWqFzVZsS7Upu4lyAyjslHK5UEF/MgCy
 4c4/xaqcDTKn8dtQycQ3FMwujbamHdnct9or4aDsEa9PIIAcab/gKxojNPlBSkCt
 0FpBjJUP2X/DBGpMaNX02fwQhhXwj0dN/4OWI5kXrL2sctqzueMSfTUKpjsLZMAx
 VTngoXVcVlLxqB2LqIzjhsWG+awlw/IKEKotjhX4vyra9L50CRbMLJo7hJdHD16J
 dmGQmsJRlGyQYEOgoyI7BU/Bqs/+iE1r5fAcVgjWWUPotl7XKDgcwTpELTPj5xzO
 b7ALkUXRcHf2NdfaLDZeyJzT/Z1mq1znPTsDqi94f1ASbmAd0iXLFNHtyJxXJabZ
 /aTLUj/GmmaCw2R02S4l67uC/BHChToloNVCGsq2KfBYcUunod0=
 =bSNb
 -----END PGP SIGNATURE-----

Merge tag 'sched_urgent_for_v6.5_rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler fixes from Borislav Petkov:

 - Remove a cgroup from under a polling process properly

 - Fix the idle sibling selection

* tag 'sched_urgent_for_v6.5_rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  sched/psi: use kernfs polling functions for PSI trigger polling
  sched/fair: Use recent_used_cpu to test p->cpus_ptr

include/linux/psi.h

@@ -23,8 +23,9 @@ void psi_memstall_enter(unsigned long *flags);
 void psi_memstall_leave(unsigned long *flags);
 
 int psi_show(struct seq_file *s, struct psi_group *group, enum psi_res res);
-struct psi_trigger *psi_trigger_create(struct psi_group *group,
+struct psi_trigger *psi_trigger_create(struct psi_group *group, char *buf,
-			char *buf, enum psi_res res, struct file *file);
+				       enum psi_res res, struct file *file,
+				       struct kernfs_open_file *of);
 void psi_trigger_destroy(struct psi_trigger *t);
 
 __poll_t psi_trigger_poll(void **trigger_ptr, struct file *file,

include/linux/psi_types.h

@@ -137,6 +137,9 @@ struct psi_trigger {
 	/* Wait queue for polling */
 	wait_queue_head_t event_wait;
 
+	/* Kernfs file for cgroup triggers */
+	struct kernfs_open_file *of;
+
 	/* Pending event flag */
 	int event;
 

kernel/cgroup/cgroup.c

@@ -3730,7 +3730,7 @@ static ssize_t pressure_write(struct kernfs_open_file *of, char *buf,
 	}
 
 	psi = cgroup_psi(cgrp);
-	new = psi_trigger_create(psi, buf, res, of->file);
+	new = psi_trigger_create(psi, buf, res, of->file, of);
 	if (IS_ERR(new)) {
 		cgroup_put(cgrp);
 		return PTR_ERR(new);

kernel/sched/fair.c

@@ -7174,7 +7174,7 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
 	    recent_used_cpu != target &&
 	    cpus_share_cache(recent_used_cpu, target) &&
 	    (available_idle_cpu(recent_used_cpu) || sched_idle_cpu(recent_used_cpu)) &&
-	    cpumask_test_cpu(p->recent_used_cpu, p->cpus_ptr) &&
+	    cpumask_test_cpu(recent_used_cpu, p->cpus_ptr) &&
 	    asym_fits_cpu(task_util, util_min, util_max, recent_used_cpu)) {
 		return recent_used_cpu;
 	}

kernel/sched/psi.c

@@ -493,8 +493,12 @@ static u64 update_triggers(struct psi_group *group, u64 now, bool *update_total,
 			continue;
 
 		/* Generate an event */
-		if (cmpxchg(&t->event, 0, 1) == 0)
+		if (cmpxchg(&t->event, 0, 1) == 0) {
-			wake_up_interruptible(&t->event_wait);
+			if (t->of)
+				kernfs_notify(t->of->kn);
+			else
+				wake_up_interruptible(&t->event_wait);
+		}
 		t->last_event_time = now;
 		/* Reset threshold breach flag once event got generated */
 		t->pending_event = false;
@@ -1271,8 +1275,9 @@ int psi_show(struct seq_file *m, struct psi_group *group, enum psi_res res)
 	return 0;
 }
 
-struct psi_trigger *psi_trigger_create(struct psi_group *group,
+struct psi_trigger *psi_trigger_create(struct psi_group *group, char *buf,
-			char *buf, enum psi_res res, struct file *file)
+				       enum psi_res res, struct file *file,
+				       struct kernfs_open_file *of)
 {
 	struct psi_trigger *t;
 	enum psi_states state;
@@ -1331,7 +1336,9 @@ struct psi_trigger *psi_trigger_create(struct psi_group *group,
 
 	t->event = 0;
 	t->last_event_time = 0;
-	init_waitqueue_head(&t->event_wait);
+	t->of = of;
+	if (!of)
+		init_waitqueue_head(&t->event_wait);
 	t->pending_event = false;
 	t->aggregator = privileged ? PSI_POLL : PSI_AVGS;
 
@@ -1388,7 +1395,10 @@ void psi_trigger_destroy(struct psi_trigger *t)
 	 * being accessed later. Can happen if cgroup is deleted from under a
 	 * polling process.
 	 */
-	wake_up_pollfree(&t->event_wait);
+	if (t->of)
+		kernfs_notify(t->of->kn);
+	else
+		wake_up_interruptible(&t->event_wait);
 
 	if (t->aggregator == PSI_AVGS) {
 		mutex_lock(&group->avgs_lock);
@@ -1465,7 +1475,10 @@ __poll_t psi_trigger_poll(void **trigger_ptr,
 	if (!t)
 		return DEFAULT_POLLMASK | EPOLLERR | EPOLLPRI;
 
-	poll_wait(file, &t->event_wait, wait);
+	if (t->of)
+		kernfs_generic_poll(t->of, wait);
+	else
+		poll_wait(file, &t->event_wait, wait);
 
 	if (cmpxchg(&t->event, 1, 0) == 1)
 		ret |= EPOLLPRI;
@@ -1535,7 +1548,7 @@ static ssize_t psi_write(struct file *file, const char __user *user_buf,
 		return -EBUSY;
 	}
 
-	new = psi_trigger_create(&psi_system, buf, res, file);
+	new = psi_trigger_create(&psi_system, buf, res, file, NULL);
 	if (IS_ERR(new)) {
 		mutex_unlock(&seq->lock);
 		return PTR_ERR(new);