From: Gabriele Monaco <gmonaco@redhat.com>
To: linux-kernel@vger.kernel.org,
Frederic Weisbecker <frederic@kernel.org>,
Thomas Gleixner <tglx@linutronix.de>,
Waiman Long <longman@redhat.com>
Cc: Gabriele Monaco <gmonaco@redhat.com>
Subject: [PATCH v5 5/6] cgroup/cpuset: Fail if isolated and nohz_full don't leave any housekeeping
Date: Thu, 8 May 2025 16:53:25 +0200 [thread overview]
Message-ID: <20250508145319.97794-13-gmonaco@redhat.com> (raw)
In-Reply-To: <20250508145319.97794-8-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.
Signed-off-by: Gabriele Monaco <gmonaco@redhat.com>
---
kernel/cgroup/cpuset.c | 67 ++++++++++++++++++++++++++++++++++++++++--
1 file changed, 65 insertions(+), 2 deletions(-)
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 95316d39c282..2f1df6f5b988 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -80,6 +80,12 @@ static cpumask_var_t subpartitions_cpus;
*/
static cpumask_var_t isolated_cpus;
+/*
+ * Housekeeping CPUs for both HK_TYPE_DOMAIN and HK_TYPE_KERNEL_NOISE
+ */
+static cpumask_var_t full_hk_cpus;
+static bool have_boot_nohz_full;
+
/*
* Housekeeping (HK_TYPE_DOMAIN) CPUs at boot
*/
@@ -1253,10 +1259,26 @@ static void reset_partition_data(struct cpuset *cs)
static void isolated_cpus_update(int old_prs, int new_prs, struct cpumask *xcpus)
{
WARN_ON_ONCE(old_prs == new_prs);
- if (new_prs == PRS_ISOLATED)
+ if (new_prs == PRS_ISOLATED) {
cpumask_or(isolated_cpus, isolated_cpus, xcpus);
- else
+ cpumask_andnot(full_hk_cpus, full_hk_cpus, xcpus);
+ } else {
cpumask_andnot(isolated_cpus, isolated_cpus, xcpus);
+ cpumask_or(full_hk_cpus, full_hk_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;
}
/*
@@ -1323,6 +1345,25 @@ static bool partition_xcpus_del(int old_prs, struct cpuset *parent,
return isolcpus_updated;
}
+/*
+ * isolcpus_nohz_conflict - check for isolated & nohz_full conflicts
+ * @new_cpus: cpu mask
+ * Return: true if there is conflict, false otherwise
+ *
+ * If nohz_full is enabled and we have isolated CPUs, their combination must
+ * still leave housekeeping CPUs.
+ */
+static bool isolcpus_nohz_conflict(struct cpumask *new_cpus)
+{
+ if (!have_boot_nohz_full)
+ return false;
+
+ if (!cpumask_weight_andnot(full_hk_cpus, new_cpus))
+ return true;
+
+ return false;
+}
+
static void update_exclusion_cpumasks(bool isolcpus_updated)
{
int ret;
@@ -1448,6 +1489,9 @@ static int remote_partition_enable(struct cpuset *cs, int new_prs,
cpumask_intersects(tmp->new_cpus, subpartitions_cpus) ||
cpumask_subset(top_cpuset.effective_cpus, tmp->new_cpus))
return PERR_INVCPUS;
+ if (isolated_cpus_should_update(new_prs, NULL) &&
+ isolcpus_nohz_conflict(tmp->new_cpus))
+ return PERR_HKEEPING;
spin_lock_irq(&callback_lock);
isolcpus_updated = partition_xcpus_add(new_prs, NULL, tmp->new_cpus);
@@ -1546,6 +1590,9 @@ 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) &&
+ isolcpus_nohz_conflict(tmp->addmask))
+ cs->prs_err = PERR_HKEEPING;
if (cs->prs_err)
goto invalidate;
}
@@ -1877,6 +1924,12 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd,
return err;
}
+ if (deleting && isolated_cpus_should_update(new_prs, parent) &&
+ isolcpus_nohz_conflict(tmp->delmask)) {
+ cs->prs_err = PERR_HKEEPING;
+ return PERR_HKEEPING;
+ }
+
/*
* Change the parent's effective_cpus & effective_xcpus (top cpuset
* only).
@@ -2897,6 +2950,8 @@ static int update_prstate(struct cpuset *cs, int new_prs)
* Need to update isolated_cpus.
*/
isolcpus_updated = true;
+ if (isolcpus_nohz_conflict(cs->effective_xcpus))
+ err = PERR_HKEEPING;
} else {
/*
* Switching back to member is always allowed even if it
@@ -3715,6 +3770,7 @@ int __init cpuset_init(void)
BUG_ON(!alloc_cpumask_var(&top_cpuset.exclusive_cpus, GFP_KERNEL));
BUG_ON(!zalloc_cpumask_var(&subpartitions_cpus, GFP_KERNEL));
BUG_ON(!zalloc_cpumask_var(&isolated_cpus, GFP_KERNEL));
+ BUG_ON(!alloc_cpumask_var(&full_hk_cpus, GFP_KERNEL));
cpumask_setall(top_cpuset.cpus_allowed);
nodes_setall(top_cpuset.mems_allowed);
@@ -3722,17 +3778,24 @@ int __init cpuset_init(void)
cpumask_setall(top_cpuset.effective_xcpus);
cpumask_setall(top_cpuset.exclusive_cpus);
nodes_setall(top_cpuset.effective_mems);
+ cpumask_copy(full_hk_cpus, cpu_present_mask);
fmeter_init(&top_cpuset.fmeter);
INIT_LIST_HEAD(&remote_children);
BUG_ON(!alloc_cpumask_var(&cpus_attach, GFP_KERNEL));
+ have_boot_nohz_full = housekeeping_enabled(HK_TYPE_KERNEL_NOISE);
+ if (have_boot_nohz_full)
+ cpumask_and(full_hk_cpus, cpu_possible_mask,
+ housekeeping_cpumask(HK_TYPE_KERNEL_NOISE));
+
have_boot_isolcpus = housekeeping_enabled(HK_TYPE_DOMAIN);
if (have_boot_isolcpus) {
BUG_ON(!alloc_cpumask_var(&boot_hk_cpus, GFP_KERNEL));
cpumask_copy(boot_hk_cpus, housekeeping_cpumask(HK_TYPE_DOMAIN));
cpumask_andnot(isolated_cpus, cpu_possible_mask, boot_hk_cpus);
+ cpumask_and(full_hk_cpus, full_hk_cpus, boot_hk_cpus);
}
return 0;
--
2.49.0
next prev parent reply other threads:[~2025-05-08 14:54 UTC|newest]
Thread overview: 18+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-05-08 14:53 [PATCH v5 0/6] timers: Exclude isolated cpus from timer migation Gabriele Monaco
2025-05-08 14:53 ` [PATCH v5 1/6] timers: Rename tmigr 'online' bit to 'available' Gabriele Monaco
2025-05-08 14:53 ` [PATCH v5 2/6] timers: Add the available mask in timer migration Gabriele Monaco
2025-05-08 14:53 ` [PATCH v5 3/6] cgroup/cpuset: Rename update_unbound_workqueue_cpumask() to update_exclusion_cpumasks() Gabriele Monaco
2025-05-08 14:53 ` [PATCH v5 4/6] sched/isolation: Force housekeeping if isolcpus and nohz_full don't leave any Gabriele Monaco
2025-05-20 10:17 ` Frederic Weisbecker
2025-05-20 11:17 ` Gabriele Monaco
2025-05-20 11:57 ` Frederic Weisbecker
2025-05-20 12:02 ` Frederic Weisbecker
2025-05-20 12:28 ` Gabriele Monaco
2025-05-08 14:53 ` Gabriele Monaco [this message]
2025-05-20 13:39 ` [PATCH v5 5/6] cgroup/cpuset: Fail if isolated and nohz_full don't leave any housekeeping Gabriele Monaco
2025-05-20 14:28 ` Frederic Weisbecker
2025-05-20 15:24 ` Gabriele Monaco
2025-05-23 11:15 ` Gabriele Monaco
2025-06-24 14:11 ` Frederic Weisbecker
2025-05-08 14:53 ` [PATCH v5 6/6] timers: Exclude isolated cpus from timer migation Gabriele Monaco
2025-05-20 14:43 ` 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=20250508145319.97794-13-gmonaco@redhat.com \
--to=gmonaco@redhat.com \
--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
all inboxes | Powered by JetHome®