From: Frederic Weisbecker <frederic@kernel.org>
To: LKML <linux-kernel@vger.kernel.org>
Cc: "Gabriele Monaco" <gmonaco@redhat.com>,
"Michal Koutný" <mkoutny@suse.com>,
"Andrew Morton" <akpm@linux-foundation.org>,
"Bjorn Helgaas" <bhelgaas@google.com>,
"Catalin Marinas" <catalin.marinas@arm.com>,
"Danilo Krummrich" <dakr@kernel.org>,
"David S . Miller" <davem@davemloft.net>,
"Eric Dumazet" <edumazet@google.com>,
"Frederic Weisbecker" <frederic@kernel.org>,
"Greg Kroah-Hartman" <gregkh@linuxfoundation.org>,
"Ingo Molnar" <mingo@redhat.com>,
"Jakub Kicinski" <kuba@kernel.org>,
"Jens Axboe" <axboe@kernel.dk>,
"Johannes Weiner" <hannes@cmpxchg.org>,
"Lai Jiangshan" <jiangshanlai@gmail.com>,
"Marco Crivellari" <marco.crivellari@suse.com>,
"Michal Hocko" <mhocko@suse.com>,
"Muchun Song" <muchun.song@linux.dev>,
"Paolo Abeni" <pabeni@redhat.com>,
"Peter Zijlstra" <peterz@infradead.org>,
"Phil Auld" <pauld@redhat.com>,
"Rafael J . Wysocki" <rafael@kernel.org>,
"Roman Gushchin" <roman.gushchin@linux.dev>,
"Shakeel Butt" <shakeel.butt@linux.dev>,
"Simon Horman" <horms@kernel.org>, "Tejun Heo" <tj@kernel.org>,
"Thomas Gleixner" <tglx@linutronix.de>,
"Vlastimil Babka" <vbabka@suse.cz>,
"Waiman Long" <longman@redhat.com>,
"Will Deacon" <will@kernel.org>,
cgroups@vger.kernel.org, linux-arm-kernel@lists.infradead.org,
linux-block@vger.kernel.org, linux-mm@kvack.org,
linux-pci@vger.kernel.org, netdev@vger.kernel.org
Subject: [PATCH 26/33] cgroup/cpuset: Fail if isolated and nohz_full don't leave any housekeeping
Date: Mon, 13 Oct 2025 22:31:39 +0200 [thread overview]
Message-ID: <20251013203146.10162-27-frederic@kernel.org> (raw)
In-Reply-To: <20251013203146.10162-1-frederic@kernel.org>
From: Gabriele Monaco <gmonaco@redhat.com>
Currently the user can set up isolated cpus via cpuset and nohz_full in
such a way that leaves no housekeeping CPU (i.e. no CPU that is neither
domain isolated nor nohz full). This can be a problem for other
subsystems (e.g. the timer wheel imgration).
Prevent this configuration by blocking any assignation that would cause
the union of domain isolated cpus and nohz_full to covers all CPUs.
Acked-by: Frederic Weisbecker <frederic@kernel.org>
Reviewed-by: Waiman Long <longman@redhat.com>
Signed-off-by: Gabriele Monaco <gmonaco@redhat.com>
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
---
kernel/cgroup/cpuset.c | 63 ++++++++++++++++++++++++++++++++++++++++++
1 file changed, 63 insertions(+)
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index e19d3375a4ec..d1a799e361c3 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -1327,6 +1327,19 @@ static void isolated_cpus_update(int old_prs, int new_prs, struct cpumask *xcpus
cpumask_andnot(isolated_cpus, isolated_cpus, xcpus);
}
+/*
+ * isolated_cpus_should_update - Returns if the isolated_cpus mask needs update
+ * @prs: new or old partition_root_state
+ * @parent: parent cpuset
+ * Return: true if isolated_cpus needs modification, false otherwise
+ */
+static bool isolated_cpus_should_update(int prs, struct cpuset *parent)
+{
+ if (!parent)
+ parent = &top_cpuset;
+ return prs != parent->partition_root_state;
+}
+
/*
* partition_xcpus_add - Add new exclusive CPUs to partition
* @new_prs: new partition_root_state
@@ -1391,6 +1404,42 @@ static bool partition_xcpus_del(int old_prs, struct cpuset *parent,
return isolcpus_updated;
}
+/*
+ * isolated_cpus_can_update - check for isolated & nohz_full conflicts
+ * @add_cpus: cpu mask for cpus that are going to be isolated
+ * @del_cpus: cpu mask for cpus that are no longer isolated, can be NULL
+ * Return: false if there is conflict, true otherwise
+ *
+ * If nohz_full is enabled and we have isolated CPUs, their combination must
+ * still leave housekeeping CPUs.
+ */
+static bool isolated_cpus_can_update(struct cpumask *add_cpus,
+ struct cpumask *del_cpus)
+{
+ cpumask_var_t full_hk_cpus;
+ int res = true;
+
+ if (!housekeeping_enabled(HK_TYPE_KERNEL_NOISE))
+ return true;
+
+ if (del_cpus && cpumask_weight_and(del_cpus,
+ housekeeping_cpumask(HK_TYPE_KERNEL_NOISE)))
+ return true;
+
+ if (!alloc_cpumask_var(&full_hk_cpus, GFP_KERNEL))
+ return false;
+
+ cpumask_and(full_hk_cpus, housekeeping_cpumask(HK_TYPE_KERNEL_NOISE),
+ housekeeping_cpumask(HK_TYPE_DOMAIN));
+ cpumask_andnot(full_hk_cpus, full_hk_cpus, isolated_cpus);
+ cpumask_and(full_hk_cpus, full_hk_cpus, cpu_active_mask);
+ if (!cpumask_weight_andnot(full_hk_cpus, add_cpus))
+ res = false;
+
+ free_cpumask_var(full_hk_cpus);
+ return res;
+}
+
static void update_housekeeping_cpumask(bool isolcpus_updated)
{
int ret;
@@ -1538,6 +1587,9 @@ static int remote_partition_enable(struct cpuset *cs, int new_prs,
if (!cpumask_intersects(tmp->new_cpus, cpu_active_mask) ||
cpumask_subset(top_cpuset.effective_cpus, tmp->new_cpus))
return PERR_INVCPUS;
+ if (isolated_cpus_should_update(new_prs, NULL) &&
+ !isolated_cpus_can_update(tmp->new_cpus, NULL))
+ return PERR_HKEEPING;
spin_lock_irq(&callback_lock);
isolcpus_updated = partition_xcpus_add(new_prs, NULL, tmp->new_cpus);
@@ -1637,6 +1689,9 @@ static void remote_cpus_update(struct cpuset *cs, struct cpumask *xcpus,
else if (cpumask_intersects(tmp->addmask, subpartitions_cpus) ||
cpumask_subset(top_cpuset.effective_cpus, tmp->addmask))
cs->prs_err = PERR_NOCPUS;
+ else if (isolated_cpus_should_update(prs, NULL) &&
+ !isolated_cpus_can_update(tmp->addmask, tmp->delmask))
+ cs->prs_err = PERR_HKEEPING;
if (cs->prs_err)
goto invalidate;
}
@@ -1984,6 +2039,12 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd,
return err;
}
+ if (deleting && isolated_cpus_should_update(new_prs, parent) &&
+ !isolated_cpus_can_update(tmp->delmask, tmp->addmask)) {
+ cs->prs_err = PERR_HKEEPING;
+ return PERR_HKEEPING;
+ }
+
/*
* Change the parent's effective_cpus & effective_xcpus (top cpuset
* only).
@@ -2999,6 +3060,8 @@ static int update_prstate(struct cpuset *cs, int new_prs)
* Need to update isolated_cpus.
*/
isolcpus_updated = true;
+ if (!isolated_cpus_can_update(cs->effective_xcpus, NULL))
+ err = PERR_HKEEPING;
} else {
/*
* Switching back to member is always allowed even if it
--
2.51.0
next prev parent reply other threads:[~2025-10-13 20:35 UTC|newest]
Thread overview: 78+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-10-13 20:31 [PATCH 00/33 v3] cpuset/isolation: Honour kthreads preferred affinity Frederic Weisbecker
2025-10-13 20:31 ` [PATCH 01/33] PCI: Prepare to protect against concurrent isolated cpuset change Frederic Weisbecker
2025-10-14 20:53 ` Bjorn Helgaas
2025-10-31 15:30 ` Frederic Weisbecker
2025-10-13 20:31 ` [PATCH 02/33] cpu: Revert "cpu/hotplug: Prevent self deadlock on CPU hot-unplug" Frederic Weisbecker
2025-10-13 20:31 ` [PATCH 03/33] memcg: Prepare to protect against concurrent isolated cpuset change Frederic Weisbecker
2025-10-13 20:31 ` [PATCH 04/33] mm: vmstat: " Frederic Weisbecker
2025-10-13 20:31 ` [PATCH 05/33] sched/isolation: Save boot defined domain flags Frederic Weisbecker
2025-10-23 15:45 ` Valentin Schneider
2025-10-31 15:36 ` Frederic Weisbecker
2025-10-13 20:31 ` [PATCH 06/33] cpuset: Convert boot_hk_cpus to use HK_TYPE_DOMAIN_BOOT Frederic Weisbecker
2025-10-13 20:31 ` [PATCH 07/33] driver core: cpu: Convert /sys/devices/system/cpu/isolated " Frederic Weisbecker
2025-10-13 20:31 ` [PATCH 08/33] net: Keep ignoring isolated cpuset change Frederic Weisbecker
2025-10-13 20:31 ` [PATCH 09/33] block: Protect against concurrent " Frederic Weisbecker
2025-10-13 20:31 ` [PATCH 10/33] cpu: Provide lockdep check for CPU hotplug lock write-held Frederic Weisbecker
2025-10-13 20:31 ` [PATCH 11/33] cpuset: Provide lockdep check for cpuset lock held Frederic Weisbecker
2025-10-14 13:29 ` Chen Ridong
2025-10-31 16:08 ` Frederic Weisbecker
2025-11-03 2:32 ` Chen Ridong
2025-10-13 20:31 ` [PATCH 12/33] sched/isolation: Convert housekeeping cpumasks to rcu pointers Frederic Weisbecker
2025-10-21 1:46 ` Chen Ridong
2025-10-21 1:57 ` Chen Ridong
2025-10-21 4:03 ` Waiman Long
2025-10-31 16:17 ` Frederic Weisbecker
2025-10-31 19:29 ` Waiman Long
2025-11-03 2:22 ` Chen Ridong
2025-11-05 15:18 ` Frederic Weisbecker
2025-10-21 3:49 ` Waiman Long
2025-11-05 15:23 ` Frederic Weisbecker
2025-10-13 20:31 ` [PATCH 13/33] cpuset: Update HK_TYPE_DOMAIN cpumask from cpuset Frederic Weisbecker
2025-10-21 4:10 ` Waiman Long
2025-10-22 1:36 ` Chen Ridong
2025-11-05 15:42 ` Frederic Weisbecker
2025-11-05 19:33 ` Waiman Long
2025-10-21 13:39 ` Waiman Long
2025-11-05 15:45 ` Frederic Weisbecker
2025-11-05 19:39 ` Waiman Long
2025-10-31 12:59 ` Phil Auld
2025-11-05 15:57 ` Frederic Weisbecker
2025-10-13 20:31 ` [PATCH 14/33] sched/isolation: Flush memcg workqueues on cpuset isolated partition change Frederic Weisbecker
2025-10-21 19:16 ` Waiman Long
2025-10-21 19:28 ` Waiman Long
2025-11-05 16:20 ` Frederic Weisbecker
2025-11-05 16:17 ` Frederic Weisbecker
2025-10-13 20:31 ` [PATCH 15/33] sched/isolation: Flush vmstat " Frederic Weisbecker
2025-10-13 20:31 ` [PATCH 16/33] PCI: Flush PCI probe workqueue " Frederic Weisbecker
2025-10-14 20:50 ` Bjorn Helgaas
2025-11-05 16:28 ` Frederic Weisbecker
2025-10-13 20:31 ` [PATCH 17/33] cpuset: Propagate cpuset isolation update to workqueue through housekeeping Frederic Weisbecker
2025-10-13 20:31 ` [PATCH 18/33] cpuset: Remove cpuset_cpu_is_isolated() Frederic Weisbecker
2025-10-29 18:05 ` Waiman Long
2025-11-05 16:36 ` Frederic Weisbecker
2025-10-13 20:31 ` [PATCH 19/33] sched/isolation: Remove HK_TYPE_TICK test from cpu_is_isolated() Frederic Weisbecker
2025-10-13 20:31 ` [PATCH 20/33] PCI: Remove superfluous HK_TYPE_WQ check Frederic Weisbecker
2025-10-13 20:31 ` [PATCH 21/33] kthread: Refine naming of affinity related fields Frederic Weisbecker
2025-10-13 20:31 ` [PATCH 22/33] kthread: Include unbound kthreads in the managed affinity list Frederic Weisbecker
2025-10-21 22:42 ` Waiman Long
2025-11-05 16:57 ` Frederic Weisbecker
2025-10-13 20:31 ` [PATCH 23/33] kthread: Include kthreadd to " Frederic Weisbecker
2025-10-13 20:31 ` [PATCH 24/33] kthread: Rely on HK_TYPE_DOMAIN for preferred affinity management Frederic Weisbecker
2025-10-13 20:31 ` [PATCH 25/33] sched: Switch the fallback task allowed cpumask to HK_TYPE_DOMAIN Frederic Weisbecker
2025-10-13 20:31 ` Frederic Weisbecker [this message]
2025-10-13 20:31 ` [PATCH 27/33] sched/arm64: Move fallback task " Frederic Weisbecker
2025-10-13 20:31 ` [PATCH 28/33] kthread: Honour kthreads preferred affinity after cpuset changes Frederic Weisbecker
2025-10-13 20:31 ` [PATCH 29/33] kthread: Comment on the purpose and placement of kthread_affine_node() call Frederic Weisbecker
2025-10-13 20:31 ` [PATCH 30/33] kthread: Add API to update preferred affinity on kthread runtime Frederic Weisbecker
2025-10-14 12:35 ` Simon Horman
2025-11-05 17:26 ` Frederic Weisbecker
2025-10-13 20:31 ` [PATCH 31/33] kthread: Document kthread_affine_preferred() Frederic Weisbecker
2025-10-13 20:31 ` [PATCH 32/33] genirq: Correctly handle preferred kthreads affinity Frederic Weisbecker
2025-10-13 20:31 ` [PATCH 33/33] doc: Add housekeeping documentation Frederic Weisbecker
2025-10-14 11:27 ` [PATCH 00/33 v3] cpuset/isolation: Honour kthreads preferred affinity shinichiro.kawasaki
2025-10-14 12:17 ` Johannes Thumshirn
2025-10-15 9:43 ` Shinichiro Kawasaki
-- strict thread matches above, loose matches on Subject: below --
2025-08-29 15:47 [PATCH 00/33 v2] " Frederic Weisbecker
2025-08-29 15:48 ` [PATCH 26/33] cgroup/cpuset: Fail if isolated and nohz_full don't leave any housekeeping Frederic Weisbecker
2025-09-02 15:44 ` Waiman Long
2025-09-23 9:17 ` Frederic Weisbecker
2025-09-23 9:24 ` Gabriele Monaco
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20251013203146.10162-27-frederic@kernel.org \
--to=frederic@kernel.org \
--cc=akpm@linux-foundation.org \
--cc=axboe@kernel.dk \
--cc=bhelgaas@google.com \
--cc=catalin.marinas@arm.com \
--cc=cgroups@vger.kernel.org \
--cc=dakr@kernel.org \
--cc=davem@davemloft.net \
--cc=edumazet@google.com \
--cc=gmonaco@redhat.com \
--cc=gregkh@linuxfoundation.org \
--cc=hannes@cmpxchg.org \
--cc=horms@kernel.org \
--cc=jiangshanlai@gmail.com \
--cc=kuba@kernel.org \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-block@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=linux-pci@vger.kernel.org \
--cc=longman@redhat.com \
--cc=marco.crivellari@suse.com \
--cc=mhocko@suse.com \
--cc=mingo@redhat.com \
--cc=mkoutny@suse.com \
--cc=muchun.song@linux.dev \
--cc=netdev@vger.kernel.org \
--cc=pabeni@redhat.com \
--cc=pauld@redhat.com \
--cc=peterz@infradead.org \
--cc=rafael@kernel.org \
--cc=roman.gushchin@linux.dev \
--cc=shakeel.butt@linux.dev \
--cc=tglx@linutronix.de \
--cc=tj@kernel.org \
--cc=vbabka@suse.cz \
--cc=will@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.