Commit 10c64a0f authored by Linus Torvalds's avatar Linus Torvalds
Browse files

Merge tag 'sched_urgent_for_v5.17_rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip 

Pull scheduler fixes from Borislav Petkov:
 "A bunch of fixes: forced idle time accounting, utilization values
  propagation in the sched hierarchies and other minor cleanups and
  improvements"

* tag 'sched_urgent_for_v5.17_rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  kernel/sched: Remove dl_boosted flag comment
  sched: Avoid double preemption in __cond_resched_*lock*()
  sched/fair: Fix all kernel-doc warnings
  sched/core: Accounting forceidle time for all tasks except idle task
  sched/pelt: Relax the sync of load_sum with load_avg
  sched/pelt: Relax the sync of runnable_sum with runnable_avg
  sched/pelt: Continue to relax the sync of util_sum with util_avg
  sched/pelt: Relax the sync of util_sum with util_avg
  psi: Fix uaf issue when psi trigger is destroyed while being polled
parents 0f9e0422 0e387249

Documentation/accounting/psi.rst

+2 −1
Original line number Diff line number Diff line
@@ -92,7 +92,8 @@ Triggers can be set on more than one psi metric and more than one trigger 
for the same psi metric can be specified. However for each trigger a separate

file descriptor is required to be able to poll it separately from others,

therefore for each trigger a separate open() syscall should be made even

when opening the same psi interface file.

when opening the same psi interface file. Write operations to a file descriptor

with an already existing psi trigger will fail with EBUSY.



Monitors activate only when system enters stall state for the monitored

psi metric and deactivates upon exit from the stall state. While system is

include/linux/psi.h

+1 −1
Original line number Diff line number Diff line
@@ -33,7 +33,7 @@ void cgroup_move_task(struct task_struct *p, struct css_set *to); 


struct psi_trigger *psi_trigger_create(struct psi_group *group,

			char *buf, size_t nbytes, enum psi_res res);

void psi_trigger_replace(void **trigger_ptr, struct psi_trigger *t);

void psi_trigger_destroy(struct psi_trigger *t);



__poll_t psi_trigger_poll(void **trigger_ptr, struct file *file,

			poll_table *wait);

include/linux/psi_types.h

+0 −3
Original line number Diff line number Diff line
@@ -141,9 +141,6 @@ struct psi_trigger { 
	 * events to one per window

	 */

	u64 last_event_time;



	/* Refcounting to prevent premature destruction */

	struct kref refcount;

};



struct psi_group {

include/linux/sched.h

+0 −4
Original line number Diff line number Diff line
@@ -619,10 +619,6 @@ struct sched_dl_entity { 
	 * task has to wait for a replenishment to be performed at the

	 * next firing of dl_timer.

	 *

	 * @dl_boosted tells if we are boosted due to DI. If so we are

	 * outside bandwidth enforcement mechanism (but only until we

	 * exit the critical section);

	 *

	 * @dl_yielded tells if task gave up the CPU before consuming

	 * all its available runtime during the last job.

	 *

kernel/cgroup/cgroup.c

+8 −3
Original line number Diff line number Diff line
@@ -3643,6 +3643,12 @@ static ssize_t cgroup_pressure_write(struct kernfs_open_file *of, char *buf, 
	cgroup_get(cgrp);

	cgroup_kn_unlock(of->kn);



	/* Allow only one trigger per file descriptor */

	if (ctx->psi.trigger) {

		cgroup_put(cgrp);

		return -EBUSY;

	}



	psi = cgroup_ino(cgrp) == 1 ? &psi_system : &cgrp->psi;

	new = psi_trigger_create(psi, buf, nbytes, res);

	if (IS_ERR(new)) {
@@ -3650,8 +3656,7 @@ static ssize_t cgroup_pressure_write(struct kernfs_open_file *of, char *buf, 
		return PTR_ERR(new);

	}



	psi_trigger_replace(&ctx->psi.trigger, new);



	smp_store_release(&ctx->psi.trigger, new);

	cgroup_put(cgrp);



	return nbytes;
@@ -3690,7 +3695,7 @@ static void cgroup_pressure_release(struct kernfs_open_file *of) 
{

	struct cgroup_file_ctx *ctx = of->priv;



	psi_trigger_replace(&ctx->psi.trigger, NULL);

	psi_trigger_destroy(ctx->psi.trigger);

}



bool cgroup_psi_enabled(void)