Le Tue, Mar 31, 2026 at 12:50:15PM -0400, Waiman Long a écrit :
> The ip_vs_ctl.c file and the associated ip_vs.h file are the only places
> in the kernel where HK_TYPE_KTHREAD cpumask is being retrieved and used.
> Now that HK_TYPE_KTHREAD/HK_TYPE_DOMAIN cpumask can be changed at run
> time. We need to use RCU to guard access to this cpumask to avoid a
> potential UAF problem as the returned cpumask may be freed before it
> is being used.
>
> We can replace HK_TYPE_KTHREAD by HK_TYPE_DOMAIN as they are aliases
> of each other, but keeping the HK_TYPE_KTHREAD name can highlight the
> fact that it is the kthread initiated by ipvs that is being controlled.
>
> Signed-off-by: Waiman Long <[email protected]>
Oh I see you're handling a few concerns here. But it's too late, the previous
patch broke bisection.
> ---
> include/net/ip_vs.h | 20 ++++++++++++++++----
> net/netfilter/ipvs/ip_vs_ctl.c | 13 ++++++++-----
> 2 files changed, 24 insertions(+), 9 deletions(-)
>
> diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
> index 72d325c81313..7bda92fd3fe6 100644
> --- a/include/net/ip_vs.h
> +++ b/include/net/ip_vs.h
> @@ -1411,7 +1411,7 @@ static inline int sysctl_run_estimation(struct
> netns_ipvs *ipvs)
> return ipvs->sysctl_run_estimation;
> }
>
> -static inline const struct cpumask *sysctl_est_cpulist(struct netns_ipvs
> *ipvs)
> +static inline const struct cpumask *__sysctl_est_cpulist(struct netns_ipvs
> *ipvs)
> {
> if (ipvs->est_cpulist_valid)
> return ipvs->sysctl_est_cpulist;
> @@ -1529,7 +1529,7 @@ static inline int sysctl_run_estimation(struct
> netns_ipvs *ipvs)
> return 1;
> }
>
> -static inline const struct cpumask *sysctl_est_cpulist(struct netns_ipvs
> *ipvs)
> +static inline const struct cpumask *__sysctl_est_cpulist(struct netns_ipvs
> *ipvs)
> {
> return housekeeping_cpumask(HK_TYPE_KTHREAD);
> }
> @@ -1564,6 +1564,18 @@ static inline int sysctl_svc_lfactor(struct netns_ipvs
> *ipvs)
> return READ_ONCE(ipvs->sysctl_svc_lfactor);
> }
>
> +static inline bool sysctl_est_cpulist_empty(struct netns_ipvs *ipvs)
> +{
> + guard(rcu)();
> + return cpumask_empty(__sysctl_est_cpulist(ipvs));
> +}
> +
> +static inline unsigned int sysctl_est_cpulist_weight(struct netns_ipvs *ipvs)
> +{
> + guard(rcu)();
> + return cpumask_weight(__sysctl_est_cpulist(ipvs));
> +}
> +
> /* IPVS core functions
> * (from ip_vs_core.c)
> */
> @@ -1895,7 +1907,7 @@ static inline void ip_vs_est_stopped_recalc(struct
> netns_ipvs *ipvs)
> /* Stop tasks while cpulist is empty or if disabled with flag */
> ipvs->est_stopped = !sysctl_run_estimation(ipvs) ||
> (ipvs->est_cpulist_valid &&
> - cpumask_empty(sysctl_est_cpulist(ipvs)));
> + sysctl_est_cpulist_empty(ipvs));
It's not needed, if ipvs->est_cpulist_valid, sysctl_est_cpulist() doesn't
refer to housekeeping.
> #endif
> }
>
> @@ -1911,7 +1923,7 @@ static inline bool ip_vs_est_stopped(struct netns_ipvs
> *ipvs)
> static inline int ip_vs_est_max_threads(struct netns_ipvs *ipvs)
> {
> unsigned int limit = IPVS_EST_CPU_KTHREADS *
> - cpumask_weight(sysctl_est_cpulist(ipvs));
> + sysctl_est_cpulist_weight(ipvs);
That probably works for callers ip_vs_start_estimator().
But this is not handling the core issue that related kthreads should be updated,
as is done in ipvs_proc_est_cpumask_set(), when HK_TYPE_DOMAIN mask changes.
>
> return max(1U, limit);
> }
> diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
> index 032425025d88..e253a1ceef48 100644
> --- a/net/netfilter/ipvs/ip_vs_ctl.c
> +++ b/net/netfilter/ipvs/ip_vs_ctl.c
> @@ -2338,11 +2338,14 @@ static int ipvs_proc_est_cpumask_get(const struct
> ctl_table *table,
>
> mutex_lock(&ipvs->est_mutex);
>
> - if (ipvs->est_cpulist_valid)
> - mask = *valp;
> - else
> - mask = (struct cpumask *)housekeeping_cpumask(HK_TYPE_KTHREAD);
> - ret = scnprintf(buffer, size, "%*pbl\n", cpumask_pr_args(mask));
> + /* HK_TYPE_KTHREAD cpumask needs RCU protection */
> + scoped_guard(rcu) {
> + if (ipvs->est_cpulist_valid)
> + mask = *valp;
> + else
> + mask = (struct cpumask
> *)housekeeping_cpumask(HK_TYPE_KTHREAD);
> + ret = scnprintf(buffer, size, "%*pbl\n", cpumask_pr_args(mask));
> + }
And that works.
Thanks.
>
> mutex_unlock(&ipvs->est_mutex);
>
> --
> 2.53.0
>
--
Frederic Weisbecker
SUSE Labs
