torvalds/linux
3
0
Fork 0
mirror of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git synced 2026-03-28 18:27:42 +08:00
Code Issues Packages Projects Releases Wiki Activity

cgroup/cpuset: Call rebuild_sched_domains() directly in hotplug

Browse Source 
Besides deferring the call to housekeeping_update(), commit 6df415aa46
("cgroup/cpuset: Defer housekeeping_update() calls from CPU hotplug
to workqueue") also defers the rebuild_sched_domains() call to
the workqueue. So a new offline CPU may still be in a sched domain
or new online CPU not showing up in the sched domains for a short
transition period. That could be a problem in some corner cases and
can be the cause of a reported test failure[1]. Fix it by calling
rebuild_sched_domains_cpuslocked() directly in hotplug as before. If
isolated partition invalidation or recreation is being done, the
housekeeping_update() call to update the housekeeping cpumasks will
still be deferred to a workqueue.

In commit 3bfe479671 ("cgroup/cpuset: Move
housekeeping_update()/rebuild_sched_domains() together"),
housekeeping_update() is called before rebuild_sched_domains() because
it needs to access the HK_TYPE_DOMAIN housekeeping cpumask. That is now
changed to use the static HK_TYPE_DOMAIN_BOOT cpumask as HK_TYPE_DOMAIN
cpumask is now changeable at run time.  As a result, we can move the
rebuild_sched_domains() call before housekeeping_update() with
the slight advantage that it will be done in the same cpus_read_lock
critical section without the possibility of interference by a concurrent
cpu hot add/remove operation.

As it doesn't make sense to acquire cpuset_mutex/cpuset_top_mutex after
calling housekeeping_update() and immediately release them again, move
the cpuset_full_unlock() operation inside update_hk_sched_domains()
and rename it to cpuset_update_sd_hk_unlock() to signify that it will
release the full set of locks.

[1] https://lore.kernel.org/lkml/1a89aceb-48db-4edd-a730-b445e41221fe@nvidia.com

Fixes: 6df415aa46 ("cgroup/cpuset: Defer housekeeping_update() calls from CPU hotplug to workqueue")
Tested-by: Jon Hunter <jonathanh@nvidia.com>
Reviewed-by: Chen Ridong <chenridong@huaweicloud.com>
Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
This commit is contained in:
Waiman Long
2026-03-05 14:53:29 -05:00
committed by Tejun Heo
parent 5ee8dbf546
commit ca174c705d
1 changed files with 31 additions and 28 deletions
Download Patch File Download Diff File Expand all files Collapse all files

59
kernel/cgroup/cpuset.c
View File

@@ -879,7 +879,7 @@ generate_doms:
/*
* Cgroup v2 doesn't support domain attributes, just set all of them
* to SD_ATTR_INIT. Also non-isolating partition root CPUs are a
* subset of HK_TYPE_DOMAIN housekeeping CPUs.
* subset of HK_TYPE_DOMAIN_BOOT housekeeping CPUs.
*/
for (i = 0; i < ndoms; i++) {
/*
@@ -888,7 +888,7 @@ generate_doms:
*/
if (!csa || csa[i] == &top_cpuset)
cpumask_and(doms[i], top_cpuset.effective_cpus,
housekeeping_cpumask(HK_TYPE_DOMAIN));
housekeeping_cpumask(HK_TYPE_DOMAIN_BOOT));
else
cpumask_copy(doms[i], csa[i]->effective_cpus);
if (dattr)
@@ -1329,17 +1329,22 @@ static bool prstate_housekeeping_conflict(int prstate, struct cpumask *new_cpus)
}
/*
* update_hk_sched_domains - Update HK cpumasks & rebuild sched domains
* cpuset_update_sd_hk_unlock - Rebuild sched domains, update HK & unlock
*
* Update housekeeping cpumasks and rebuild sched domains if necessary.
* This should be called at the end of cpuset or hotplug actions.
* Update housekeeping cpumasks and rebuild sched domains if necessary and
* then do a cpuset_full_unlock().
* This should be called at the end of cpuset operation.
*/
static void update_hk_sched_domains(void)
static void cpuset_update_sd_hk_unlock(void)
__releases(&cpuset_mutex)
__releases(&cpuset_top_mutex)
{
/* force_sd_rebuild will be cleared in rebuild_sched_domains_locked() */
if (force_sd_rebuild)
rebuild_sched_domains_locked();
if (update_housekeeping) {
/* Updating HK cpumasks implies rebuild sched domains */
update_housekeeping = false;
force_sd_rebuild = true;
cpumask_copy(isolated_hk_cpus, isolated_cpus);
/*
@@ -1350,22 +1355,19 @@ static void update_hk_sched_domains(void)
mutex_unlock(&cpuset_mutex);
cpus_read_unlock();
WARN_ON_ONCE(housekeeping_update(isolated_hk_cpus));
cpus_read_lock();
mutex_lock(&cpuset_mutex);
mutex_unlock(&cpuset_top_mutex);
} else {
cpuset_full_unlock();
}
/* force_sd_rebuild will be cleared in rebuild_sched_domains_locked() */
if (force_sd_rebuild)
rebuild_sched_domains_locked();
}
/*
* Work function to invoke update_hk_sched_domains()
* Work function to invoke cpuset_update_sd_hk_unlock()
*/
static void hk_sd_workfn(struct work_struct *work)
{
cpuset_full_lock();
update_hk_sched_domains();
cpuset_full_unlock();
cpuset_update_sd_hk_unlock();
}
/**
@@ -3230,8 +3232,7 @@ ssize_t cpuset_write_resmask(struct kernfs_open_file *of,
free_cpuset(trialcs);
out_unlock:
update_hk_sched_domains();
cpuset_full_unlock();
cpuset_update_sd_hk_unlock();
if (of_cft(of)->private == FILE_MEMLIST)
schedule_flush_migrate_mm();
return retval ?: nbytes;
@@ -3338,8 +3339,7 @@ static ssize_t cpuset_partition_write(struct kernfs_open_file *of, char *buf,
cpuset_full_lock();
if (is_cpuset_online(cs))
retval = update_prstate(cs, val);
update_hk_sched_domains();
cpuset_full_unlock();
cpuset_update_sd_hk_unlock();
return retval ?: nbytes;
}
@@ -3513,8 +3513,7 @@ static void cpuset_css_killed(struct cgroup_subsys_state *css)
/* Reset valid partition back to member */
if (is_partition_valid(cs))
update_prstate(cs, PRS_MEMBER);
update_hk_sched_domains();
cpuset_full_unlock();
cpuset_update_sd_hk_unlock();
}
static void cpuset_css_free(struct cgroup_subsys_state *css)
@@ -3923,11 +3922,13 @@ static void cpuset_handle_hotplug(void)
rcu_read_unlock();
}
/*
* Queue a work to call housekeeping_update() & rebuild_sched_domains()
* There will be a slight delay before the HK_TYPE_DOMAIN housekeeping
* cpumask can correctly reflect what is in isolated_cpus.
* rebuild_sched_domains() will always be called directly if needed
* to make sure that newly added or removed CPU will be reflected in
* the sched domains. However, if isolated partition invalidation
* or recreation is being done (update_housekeeping set), a work item
* will be queued to call housekeeping_update() to update the
* corresponding housekeeping cpumasks after some slight delay.
*
* We rely on WORK_STRUCT_PENDING_BIT to not requeue a work item that
* is still pending. Before the pending bit is cleared, the work data
@@ -3936,8 +3937,10 @@ static void cpuset_handle_hotplug(void)
* previously queued work. Since hk_sd_workfn() doesn't use the work
* item at all, this is not a problem.
*/
if (update_housekeeping || force_sd_rebuild)
queue_work(system_unbound_wq, &hk_sd_work);
if (force_sd_rebuild)
rebuild_sched_domains_cpuslocked();
if (update_housekeeping)
queue_work(system_dfl_wq, &hk_sd_work);
free_tmpmasks(ptmp);
}