From: Gabriele Monaco <gmonaco@redhat.com>
To: linux-kernel@vger.kernel.org,
Anna-Maria Behnsen <anna-maria@linutronix.de>,
Frederic Weisbecker <frederic@kernel.org>,
Thomas Gleixner <tglx@linutronix.de>,
Waiman Long <longman@redhat.com>
Cc: Gabriele Monaco <gmonaco@redhat.com>
Subject: [RESEND PATCH v13 7/9] cgroup/cpuset: Fail if isolated and nohz_full don't leave any housekeeping
Date: Mon, 20 Oct 2025 13:28:00 +0200 [thread overview]
Message-ID: <20251020112802.102451-8-gmonaco@redhat.com> (raw)
In-Reply-To: <20251020112802.102451-1-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>
---
kernel/cgroup/cpuset.c | 63 ++++++++++++++++++++++++++++++++++++++++++
1 file changed, 63 insertions(+)
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 217480e01be6..597a9b9c18c6 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_exclusion_cpumasks(bool isolcpus_updated)
{
int ret;
@@ -1549,6 +1598,9 @@ 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);
@@ -1648,6 +1700,9 @@ 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;
}
@@ -1994,6 +2049,12 @@ 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).
@@ -3009,6 +3070,8 @@ 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:[~2025-10-20 11:28 UTC|newest]
Thread overview: 21+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-10-20 11:27 [RESEND PATCH v13 0/9] timers: Exclude isolated cpus from timer migration Gabriele Monaco
2025-10-20 11:27 ` [RESEND PATCH v13 1/9] timers/migration: Postpone online/offline callbacks registration to late initcall Gabriele Monaco
2025-10-30 14:07 ` Frederic Weisbecker
2025-10-20 11:27 ` [RESEND PATCH v13 2/9] timers: Rename tmigr 'online' bit to 'available' Gabriele Monaco
2025-10-20 11:27 ` [RESEND PATCH v13 3/9] timers: Add the available mask in timer migration Gabriele Monaco
2025-10-20 11:27 ` [RESEND PATCH v13 4/9] timers: Use scoped_guard when setting/clearing the tmigr available flag Gabriele Monaco
2025-10-20 11:27 ` [RESEND PATCH v13 5/9] cgroup/cpuset: Rename update_unbound_workqueue_cpumask() to update_exclusion_cpumasks() Gabriele Monaco
2025-10-20 11:27 ` [RESEND PATCH v13 6/9] sched/isolation: Force housekeeping if isolcpus and nohz_full don't leave any Gabriele Monaco
2025-10-20 11:28 ` Gabriele Monaco [this message]
2025-10-20 11:28 ` [RESEND PATCH v13 8/9] cpumask: Add initialiser to use cleanup helpers Gabriele Monaco
2025-10-20 11:28 ` [RESEND PATCH v13 9/9] timers: Exclude isolated cpus from timer migration Gabriele Monaco
2025-10-30 2:56 ` [RESEND PATCH v13 0/9] " Waiman Long
2025-10-30 14:12 ` Frederic Weisbecker
[not found] ` <5457560d-f48a-4a99-8756-51b1017a6aab@redhat.com>
2025-10-30 16:09 ` Gabriele Monaco
2025-10-30 16:37 ` Waiman Long
2025-10-30 17:10 ` Frederic Weisbecker
2025-10-30 17:57 ` Waiman Long
2025-10-31 13:48 ` Frederic Weisbecker
2025-10-31 14:03 ` Gabriele Monaco
2025-10-31 16:14 ` Waiman Long
2025-10-30 17:08 ` Frederic Weisbecker
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=20251020112802.102451-8-gmonaco@redhat.com \
--to=gmonaco@redhat.com \
--cc=anna-maria@linutronix.de \
--cc=frederic@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=longman@redhat.com \
--cc=tglx@linutronix.de \
/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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox