[PATCH -next RFC -v2 01/11] cpuset: move the root cpuset write check earlier

Chen Ridong posted 11 patches 3 weeks, 2 days ago
There is a newer version of this series
[PATCH -next RFC -v2 01/11] cpuset: move the root cpuset write check earlier
Posted by Chen Ridong 3 weeks, 2 days ago
From: Chen Ridong <chenridong@huawei.com>

The 'cpus' or 'mems' lists of the top_cpuset cannot be modified.
This check can be moved before acquiring any locks as a common code
block to improve efficiency and maintainability.

Signed-off-by: Chen Ridong <chenridong@huawei.com>
---
 kernel/cgroup/cpuset.c | 17 ++++-------------
 1 file changed, 4 insertions(+), 13 deletions(-)

diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index c0c281a8860d..7e1bc1e1bde1 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -2337,10 +2337,6 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
 	bool force = false;
 	int old_prs = cs->partition_root_state;
 
-	/* top_cpuset.cpus_allowed tracks cpu_active_mask; it's read-only */
-	if (cs == &top_cpuset)
-		return -EACCES;
-
 	/*
 	 * An empty cpus_allowed is ok only if the cpuset has no tasks.
 	 * Since cpulist_parse() fails on an empty mask, we special case
@@ -2786,15 +2782,6 @@ static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs,
 {
 	int retval;
 
-	/*
-	 * top_cpuset.mems_allowed tracks node_stats[N_MEMORY];
-	 * it's read-only
-	 */
-	if (cs == &top_cpuset) {
-		retval = -EACCES;
-		goto done;
-	}
-
 	/*
 	 * An empty mems_allowed is ok iff there are no tasks in the cpuset.
 	 * Since nodelist_parse() fails on an empty mask, we special case
@@ -3260,6 +3247,10 @@ ssize_t cpuset_write_resmask(struct kernfs_open_file *of,
 	struct cpuset *trialcs;
 	int retval = -ENODEV;
 
+	/* root is read-only */
+	if (cs == &top_cpuset)
+		return -EACCES;
+
 	buf = strstrip(buf);
 	cpuset_full_lock();
 	if (!is_cpuset_online(cs))
-- 
2.34.1
Re: [PATCH -next RFC -v2 01/11] cpuset: move the root cpuset write check earlier
Posted by Waiman Long 2 weeks, 3 days ago
On 9/8/25 11:32 PM, Chen Ridong wrote:
> From: Chen Ridong <chenridong@huawei.com>
>
> The 'cpus' or 'mems' lists of the top_cpuset cannot be modified.
> This check can be moved before acquiring any locks as a common code
> block to improve efficiency and maintainability.
>
> Signed-off-by: Chen Ridong <chenridong@huawei.com>
> ---
>   kernel/cgroup/cpuset.c | 17 ++++-------------
>   1 file changed, 4 insertions(+), 13 deletions(-)
>
> diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
> index c0c281a8860d..7e1bc1e1bde1 100644
> --- a/kernel/cgroup/cpuset.c
> +++ b/kernel/cgroup/cpuset.c
> @@ -2337,10 +2337,6 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
>   	bool force = false;
>   	int old_prs = cs->partition_root_state;
>   
> -	/* top_cpuset.cpus_allowed tracks cpu_active_mask; it's read-only */
> -	if (cs == &top_cpuset)
> -		return -EACCES;
> -
>   	/*
>   	 * An empty cpus_allowed is ok only if the cpuset has no tasks.
>   	 * Since cpulist_parse() fails on an empty mask, we special case
> @@ -2786,15 +2782,6 @@ static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs,
>   {
>   	int retval;
>   
> -	/*
> -	 * top_cpuset.mems_allowed tracks node_stats[N_MEMORY];
> -	 * it's read-only
> -	 */
> -	if (cs == &top_cpuset) {
> -		retval = -EACCES;
> -		goto done;
> -	}
> -
>   	/*
>   	 * An empty mems_allowed is ok iff there are no tasks in the cpuset.
>   	 * Since nodelist_parse() fails on an empty mask, we special case
> @@ -3260,6 +3247,10 @@ ssize_t cpuset_write_resmask(struct kernfs_open_file *of,
>   	struct cpuset *trialcs;
>   	int retval = -ENODEV;
>   
> +	/* root is read-only */
> +	if (cs == &top_cpuset)
> +		return -EACCES;
> +
>   	buf = strstrip(buf);
>   	cpuset_full_lock();
>   	if (!is_cpuset_online(cs))
Reviewed-by: Waiman Long <longman@redhat.com>


> 3. The 'cpuset.cpus' of one cpuset must not form a subset of another
>     cpuset's 'cpuset.cpus.exclusive'.
>
> Signed-off-by: Chen Ridong <chenridong@huawei.com>
> ---
>   kernel/cgroup/cpuset.c | 74 +++++++++++++++++++++++++-----------------
>   1 file changed, 44 insertions(+), 30 deletions(-)
>
> diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
> index 55674a5ad2f9..389dfd5be6c8 100644
> --- a/kernel/cgroup/cpuset.c
> +++ b/kernel/cgroup/cpuset.c
> @@ -582,6 +582,47 @@ static inline bool cpusets_are_exclusive(struct cpuset *cs1, struct cpuset *cs2)
>   	return true;
>   }
>   
> +/**
> + * cpus_excl_conflict - Check if two cpusets have exclusive CPU conflicts
> + * @cs1: first cpuset to check
> + * @cs2: second cpuset to check
> + *
> + * Returns: true if CPU exclusivity conflict exists, false otherwise
> + *
> + * Conflict detection rules:
> + * 1. If either cpuset is CPU exclusive, they must be mutually exclusive
> + * 2. exclusive_cpus masks cannot intersect between cpusets
> + * 3. The allowed CPUs of one cpuset cannot be a subset of another's exclusive CPUs
> + */
> +static inline bool cpus_excl_conflict(struct cpuset *cs1, struct cpuset *cs2)
> +{
> +	/* If either cpuset is exclusive, check if they are mutually exclusive */
> +	if (is_cpu_exclusive(cs1) || is_cpu_exclusive(cs2))
> +		return !cpusets_are_exclusive(cs1, cs2);
> +
> +	/* Exclusive_cpus cannot intersect */
> +	if (cpumask_intersects(cs1->exclusive_cpus, cs2->exclusive_cpus))
> +		return true;
> +
> +	/* The cpus_allowed of one cpuset cannot be a subset of another cpuset's exclusive_cpus */
> +	if (!cpumask_empty(cs1->cpus_allowed) &&
> +	    cpumask_subset(cs1->cpus_allowed, cs2->exclusive_cpus))
> +		return true;
> +
> +	if (!cpumask_empty(cs2->cpus_allowed) &&
> +	    cpumask_subset(cs2->cpus_allowed, cs1->exclusive_cpus))
> +		return true;
> +
> +	return false;
> +}
> +
> +static inline bool mems_excl_conflict(struct cpuset *cs1, struct cpuset *cs2)
> +{
> +	if ((is_mem_exclusive(cs1) || is_mem_exclusive(cs2)))
> +		return nodes_intersects(cs1->mems_allowed, cs2->mems_allowed);
> +	return false;
> +}
> +
>   /*
>    * validate_change() - Used to validate that any proposed cpuset change
>    *		       follows the structural rules for cpusets.
> @@ -663,38 +704,11 @@ static int validate_change(struct cpuset *cur, struct cpuset *trial)
>   	 */
>   	ret = -EINVAL;
>   	cpuset_for_each_child(c, css, par) {
> -		bool txset, cxset;	/* Are exclusive_cpus set? */
> -
>   		if (c == cur)
>   			continue;
> -
> -		txset = !cpumask_empty(trial->exclusive_cpus);
> -		cxset = !cpumask_empty(c->exclusive_cpus);
> -		if (is_cpu_exclusive(trial) || is_cpu_exclusive(c) ||
> -		    (txset && cxset)) {
> -			if (!cpusets_are_exclusive(trial, c))
> -				goto out;
> -		} else if (txset || cxset) {
> -			struct cpumask *xcpus, *acpus;
> -
> -			/*
> -			 * When just one of the exclusive_cpus's is set,
> -			 * cpus_allowed of the other cpuset, if set, cannot be
> -			 * a subset of it or none of those CPUs will be
> -			 * available if these exclusive CPUs are activated.
> -			 */
> -			if (txset) {
> -				xcpus = trial->exclusive_cpus;
> -				acpus = c->cpus_allowed;
> -			} else {
> -				xcpus = c->exclusive_cpus;
> -				acpus = trial->cpus_allowed;
> -			}
> -			if (!cpumask_empty(acpus) && cpumask_subset(acpus, xcpus))
> -				goto out;
> -		}
> -		if ((is_mem_exclusive(trial) || is_mem_exclusive(c)) &&
> -		    nodes_intersects(trial->mems_allowed, c->mems_allowed))
> +		if (cpus_excl_conflict(trial, c))
> +			goto out;
> +		if (mems_excl_conflict(trial, c))
>   			goto out;
>   	}
>