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>
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 81a9239053a7..3cedc3580373 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -1275,6 +1275,19 @@ 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
@@ -1339,6 +1352,42 @@ 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;
@@ -1464,6 +1513,9 @@ 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);
@@ -1563,6 +1615,9 @@ 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;
}
@@ -1914,6 +1969,12 @@ 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).
@@ -2934,6 +2995,8 @@ 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
On 2025/9/15 22:59, Gabriele Monaco wrote:
> 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>
> 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 81a9239053a7..3cedc3580373 100644
> --- a/kernel/cgroup/cpuset.c
> +++ b/kernel/cgroup/cpuset.c
> @@ -1275,6 +1275,19 @@ 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;
> +}
> +
Hi all,
I'm a bit confused about the logic for updating isolated CPUs.
As I understand it, the isolated_cpus set should be updated in two scenarios:
1. When changing to an isolated partition.
2. When a valid isolated partition becomes invalid or changes its membership.
However, I find the current approach of comparing the parent's partition_root_state with prs to
determine whether to update the isolated CPUs somewhat difficult to follow.
Wouldn't a more straightforward approach be something like this?
static bool isolated_cpus_should_update(int old_prs, int new_prs)
{
if (old_prs == new_prs)
return false;
/* Changing to an isolated partition */
if (new_prs == PRS_ISOLATED)
return true;
/* Isolated partition changing to another state */
if (old_prs == PRS_ISOLATED)
return true;
return false;
}
I'd greatly appreciate it if someone could help clarify this. Thank you.
> /*
> * partition_xcpus_add - Add new exclusive CPUs to partition
> * @new_prs: new partition_root_state
> @@ -1339,6 +1352,42 @@ 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;
> @@ -1464,6 +1513,9 @@ 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);
> @@ -1563,6 +1615,9 @@ 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;
> }
> @@ -1914,6 +1969,12 @@ 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).
> @@ -2934,6 +2995,8 @@ 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
--
Best regards,
Ridong
On 9/15/25 10:59 AM, Gabriele Monaco wrote:
> 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>
> 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 81a9239053a7..3cedc3580373 100644
> --- a/kernel/cgroup/cpuset.c
> +++ b/kernel/cgroup/cpuset.c
> @@ -1275,6 +1275,19 @@ 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
> @@ -1339,6 +1352,42 @@ 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;
> @@ -1464,6 +1513,9 @@ 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);
> @@ -1563,6 +1615,9 @@ 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;
> }
> @@ -1914,6 +1969,12 @@ 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).
> @@ -2934,6 +2995,8 @@ 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
Reviewed-by: Waiman Long <longman@redhat.com>
© 2016 - 2025 Red Hat, Inc.