Linux cgroups development
 help / color / mirror / Atom feed
From: Guopeng Zhang <guopeng.zhang@linux.dev>
To: "Waiman Long" <longman@redhat.com>,
	"Ridong Chen" <ridong.chen@linux.dev>,
	"Tejun Heo" <tj@kernel.org>,
	"Johannes Weiner" <hannes@cmpxchg.org>,
	"Michal Koutný" <mkoutny@suse.com>,
	"Shuah Khan" <shuah@kernel.org>
Cc: cgroups@vger.kernel.org, linux-kernel@vger.kernel.org,
	linux-kselftest@vger.kernel.org
Subject: Re: [PATCH-next v4 6/6] cgroup/cpuset: Fix lockdep_is_cpuset_held()
Date: Mon, 16 Nov 2026 18:34:53 +0800	[thread overview]
Message-ID: <e330c9bd-c454-4bdd-b786-052dd2e263d9@linux.dev> (raw)
In-Reply-To: <20261116012330.2271010-7-longman@redhat.com>



在 2026/11/16 09:23, Waiman Long 写道:
> Commit a84097e625f2 ("cgroup/cpuset: Call housekeeping_update()
> without holding cpus_read_lock") changes lockdep_is_cpuset_held()
> to return true if either cpuset_mutex or cpuset_top_mutex is held.
> lockdep_is_cpuset_held() is used by housekeeping_dereference_check()
> as one of the conditions that rcu_read_lock() is not needed to
> access HK_TYPE_DOMAIN cpumask that can be changed at run time.
> In reality, it should return true only if cpuset_top_mutex is held as
> housekeeping_update() is called with only cpuset_top_mutex held.
> 
> If only cpuset_mutex is held, it is possible that there can be a parallel
> housekeeping_update() call leading to a potential use-after-free situation
> when HK_TYPE_DOMAIN housekeeping cpumask is being accessed. It also
> means that rcu_read_lock will be required if only cpuset_mutex is being
> held like when calling from hotplug, scheduler or cgroup.
> 
> Fixes: a84097e625f2 ("cgroup/cpuset: Call housekeeping_update() without holding cpus_read_lock")
> Signed-off-by: Waiman Long <longman@redhat.com>
> ---
>  kernel/cgroup/cpuset-v1.c | 16 ++++++++++------
>  kernel/cgroup/cpuset.c    |  9 +++++++--
>  2 files changed, 17 insertions(+), 8 deletions(-)
> 
> diff --git a/kernel/cgroup/cpuset-v1.c b/kernel/cgroup/cpuset-v1.c
> index 7c7f2887dfaf..6bf6da639fec 100644
> --- a/kernel/cgroup/cpuset-v1.c
> +++ b/kernel/cgroup/cpuset-v1.c
> @@ -686,6 +686,7 @@ int cpuset1_generate_sched_domains(cpumask_var_t **domains,
>  	int csn;		/* how many cpuset ptrs in csa so far */
>  	int i, j;		/* indices for partition finding loops */
>  	cpumask_var_t *doms;	/* resulting partition; i.e. sched domains */
> +	cpumask_var_t hk_cpus;	/* HK_TYPE_DOMAIN housekeeping CPUs */
>  	struct sched_domain_attr *dattr;  /* attributes for custom domains */
>  	int ndoms = 0;		/* number of sched domains in result */
>  	int nslot;		/* next empty doms[] struct cpumask slot */
> @@ -698,6 +699,11 @@ int cpuset1_generate_sched_domains(cpumask_var_t **domains,
>  	dattr = NULL;
>  	csa = NULL;
>  
> +	alloc_cpumask_var(&hk_cpus, GFP_KERNEL);
> +	scoped_guard(rcu) {
> +		cpumask_copy(hk_cpus, housekeeping_cpumask(HK_TYPE_DOMAIN));
> +	}
> +

Can alloc_cpumask_var() fail? Should we add the following check?

	if (!alloc_cpumask_var(&hk_cpus, GFP_KERNEL))
		goto done;

Thanks,
Guopeng

>  	/* Special case for the 99% of systems with one, full, sched domain */
>  	if (is_sched_load_balance(&top_cpuset)) {
>  		ndoms = 1;
> @@ -710,9 +716,7 @@ int cpuset1_generate_sched_domains(cpumask_var_t **domains,
>  			*dattr = SD_ATTR_INIT;
>  			update_domain_attr_tree(dattr, &top_cpuset);
>  		}
> -		cpumask_and(doms[0], top_cpuset.effective_cpus,
> -			    housekeeping_cpumask(HK_TYPE_DOMAIN));
> -
> +		cpumask_and(doms[0], top_cpuset.effective_cpus, hk_cpus);
>  		goto done;
>  	}
>  
> @@ -736,8 +740,7 @@ int cpuset1_generate_sched_domains(cpumask_var_t **domains,
>  		 */
>  		if (!cpumask_empty(cp->cpus_allowed) &&
>  		    !(is_sched_load_balance(cp) &&
> -		      cpumask_intersects(cp->cpus_allowed,
> -					 housekeeping_cpumask(HK_TYPE_DOMAIN))))
> +		      cpumask_intersects(cp->cpus_allowed, hk_cpus)))
>  			continue;
>  
>  		if (is_sched_load_balance(cp) &&
> @@ -794,7 +797,7 @@ int cpuset1_generate_sched_domains(cpumask_var_t **domains,
>  						*(dattr + nslot) = SD_ATTR_INIT;
>  				}
>  				cpumask_or(dp, dp, csa[j]->effective_cpus);
> -				cpumask_and(dp, dp, housekeeping_cpumask(HK_TYPE_DOMAIN));
> +				cpumask_and(dp, dp, hk_cpus);
>  				if (dattr)
>  					update_domain_attr_tree(dattr + nslot, csa[j]);
>  			}
> @@ -806,6 +809,7 @@ int cpuset1_generate_sched_domains(cpumask_var_t **domains,
>  
>  done:
>  	kfree(csa);
> +	free_cpumask_var(hk_cpus);
>  
>  	/*
>  	 * Fallback to the default domain if kmalloc() failed.
> diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
> index 64cbcbdbf6da..d18439e13bce 100644
> --- a/kernel/cgroup/cpuset.c
> +++ b/kernel/cgroup/cpuset.c
> @@ -343,10 +343,13 @@ void cpuset_full_unlock(void)
>  }
>  
>  #ifdef CONFIG_LOCKDEP
> +/*
> + * Holding cpuset_top_mutex will guarantee that a parallel
> + * housekeeping_update() call modifying housekeeping cpumasks is not possible.
> + */
>  bool lockdep_is_cpuset_held(void)
>  {
> -	return lockdep_is_held(&cpuset_mutex) ||
> -	       lockdep_is_held(&cpuset_top_mutex);
> +	return lockdep_is_held(&cpuset_top_mutex);
>  }
>  #endif
>  
> @@ -1416,8 +1419,10 @@ static bool prstate_housekeeping_conflict(int new_prs, int parent_prs,
>  		}
>  	}
>  
> +	rcu_read_lock();
>  	cpumask_and(full_hk_cpus, housekeeping_cpumask(HK_TYPE_KERNEL_NOISE),
>  		    housekeeping_cpumask(HK_TYPE_DOMAIN));
> +	rcu_read_unlock();
>  	cpumask_andnot(full_hk_cpus, full_hk_cpus, isolated_cpus);
>  	cpumask_and(full_hk_cpus, full_hk_cpus, cpu_active_mask);
>  	res = !cpumask_weight_andnot(full_hk_cpus, new_cpus);


      parent reply	other threads:[~2026-11-16 10:34 UTC|newest]

Thread overview: 18+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-11-16  1:23 [PATCH-next v4 0/6] cgroup/cpuset: More fix patches Waiman Long
2026-11-16  1:23 ` [PATCH-next v4 1/6] cgroup/cpuset: Fix incorrect partition invalidation logic in cpuset_hotplug_update_tasks() Waiman Long
2026-11-16 10:19   ` Guopeng Zhang
2026-11-16  1:23 ` [PATCH-next v4 2/6] cgroup/cpuset: excpus parameter of remote_cpus_update() must have at least 1 active CPU Waiman Long
2026-11-16  3:07   ` Ridong Chen
2026-11-16  3:34     ` Waiman Long
2026-11-16  7:37       ` Ridong Chen
2026-11-16  1:23 ` [PATCH-next v4 3/6] cgroup/cpuset: Check remote partition underneath before making an invalid partition valid Waiman Long
2026-11-16  3:47   ` Ridong Chen
2026-11-16  4:21     ` Waiman Long
2026-11-16  1:23 ` [PATCH-next v4 4/6] cgroup/cpuset: Revert "remove global remote_children list" Waiman Long
2026-11-16  1:23 ` [PATCH-next v4 5/6] cgroup/cpuset: Handle remote partitions before local partitions in cpuset_handle_hotplug() Waiman Long
2026-11-16  7:08   ` Ridong Chen
2026-11-16  8:56   ` kernel test robot
2026-11-16 10:33   ` Guopeng Zhang
2026-11-16  1:23 ` [PATCH-next v4 6/6] cgroup/cpuset: Fix lockdep_is_cpuset_held() Waiman Long
2026-11-16  7:24   ` Ridong Chen
2026-11-16 10:34   ` Guopeng Zhang [this message]

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=e330c9bd-c454-4bdd-b786-052dd2e263d9@linux.dev \
    --to=guopeng.zhang@linux.dev \
    --cc=cgroups@vger.kernel.org \
    --cc=hannes@cmpxchg.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-kselftest@vger.kernel.org \
    --cc=longman@redhat.com \
    --cc=mkoutny@suse.com \
    --cc=ridong.chen@linux.dev \
    --cc=shuah@kernel.org \
    --cc=tj@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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox