From 2fd109238925d53c44ea409df0558844af7877b8 Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Thu, 30 Apr 2026 10:44:17 +0300 Subject: ipvs: fix races around est_mutex and est_cpulist Sashiko reports for races and possible crash around the usage of est_cpulist_valid and sysctl_est_cpulist. The problem is that we do not lock est_mutex in some places which can lead to wrong write ordering and as result problems when calling cpumask_weight() and cpumask_empty(). Fix them by moving the est_max_threads read/write under locked est_mutex. Do the same for one ip_vs_est_reload_start() call to protect the cpumask_empty() usage of sysctl_est_cpulist. To remove the chance of deadlock while stopping the estimation kthreads, keep the data structure for kthread 0 even after last estimator is removed and do not hold mutexes while stopping this task. Now we will use a new flag 'needed' to know when kthread 0 should run. The kthreads above 0 do not use mutexes, so stop them under est_mutex because their kthread data still can be destroyed if they do not serve estimators. Now all kthreads will be started by the est_reload_work to properly serialize the stop/start for kthread 0. Reduce the use of service_mutex in ip_vs_est_calc_phase() because under est_mutex we can safely walk est_kt_arr to stop the kthreads above slot 0. As ip_vs_stop_estimator() for tot_stats should be called under service_mutex, do it early in the netns exit path in ip_vs_flush() to avoid locking the mutex again later. It still should be called in ip_vs_control_net_cleanup_sysctl() when we are called during netns init error. Use -2 for ktid as indicator if estimator was already stopped. Finally, fix use-after-free for kd->est_row in ip_vs_est_calc_phase(). est->ktrow should simply switch to a delay value while estimator is linked to est_temp_list. Link: https://sashiko.dev/#/patchset/20260331165015.2777765-1-longman%40redhat.com Link: https://sashiko.dev/#/patchset/20260420171308.87192-1-ja%40ssi.bg Link: https://sashiko.dev/#/patchset/20260422125123.40658-1-ja%40ssi.bg Link: https://sashiko.dev/#/patchset/20260424175858.54752-1-ja%40ssi.bg Link: https://sashiko.dev/#/patchset/20260425103918.7447-1-ja%40ssi.bg Fixes: f0be83d54217 ("ipvs: add est_cpulist and est_nice sysctl vars") Signed-off-by: Julian Anastasov Signed-off-by: Pablo Neira Ayuso --- include/net/ip_vs.h | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 72d325c81313..d28ad8a0541f 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -491,6 +491,7 @@ struct ip_vs_est_kt_data { DECLARE_BITMAP(avail, IPVS_EST_NTICKS); /* tick has space for ests */ unsigned long est_timer; /* estimation timer (jiffies) */ struct ip_vs_stats *calc_stats; /* Used for calculation */ + int needed; /* task is needed */ int tick_len[IPVS_EST_NTICKS]; /* est count */ int id; /* ktid per netns */ int chain_max; /* max ests per tick chain */ @@ -1884,11 +1885,19 @@ int ip_vs_start_estimator(struct netns_ipvs *ipvs, struct ip_vs_stats *stats); void ip_vs_stop_estimator(struct netns_ipvs *ipvs, struct ip_vs_stats *stats); void ip_vs_zero_estimator(struct ip_vs_stats *stats); void ip_vs_read_estimator(struct ip_vs_kstats *dst, struct ip_vs_stats *stats); -void ip_vs_est_reload_start(struct netns_ipvs *ipvs); +void ip_vs_est_reload_start(struct netns_ipvs *ipvs, bool restart); int ip_vs_est_kthread_start(struct netns_ipvs *ipvs, struct ip_vs_est_kt_data *kd); void ip_vs_est_kthread_stop(struct ip_vs_est_kt_data *kd); +static inline void ip_vs_stop_estimator_tot_stats(struct netns_ipvs *ipvs) +{ +#ifdef CONFIG_SYSCTL + ip_vs_stop_estimator(ipvs, &ipvs->tot_stats->s); + ipvs->tot_stats->s.est.ktid = -2; +#endif +} + static inline void ip_vs_est_stopped_recalc(struct netns_ipvs *ipvs) { #ifdef CONFIG_SYSCTL -- cgit v1.2.3 From aa6065206987278291c09d0c6aebed687114c925 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Thu, 30 Apr 2026 10:44:19 +0300 Subject: ipvs: Guard access of HK_TYPE_KTHREAD cpumask with RCU 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. Fixes: 03ff73510169 ("cpuset: Update HK_TYPE_DOMAIN cpumask from cpuset") Signed-off-by: Waiman Long Signed-off-by: Julian Anastasov Signed-off-by: Pablo Neira Ayuso --- include/net/ip_vs.h | 20 ++++++++++++++++---- net/netfilter/ipvs/ip_vs_ctl.c | 13 ++++++++----- 2 files changed, 24 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index d28ad8a0541f..02762ce73a0c 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1412,7 +1412,7 @@ 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; @@ -1530,7 +1530,7 @@ 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); } @@ -1565,6 +1565,18 @@ 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) */ @@ -1904,7 +1916,7 @@ 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)); #endif } @@ -1920,7 +1932,7 @@ 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); return max(1U, limit); } diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 5c9f8e0e238f..c7c7f6a7a9f6 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -2394,11 +2394,14 @@ 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)); + } mutex_unlock(&ipvs->est_mutex); -- cgit v1.2.3 From 8f78b749f3da0f43990490b4c1193b5ede3eec0a Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Thu, 30 Apr 2026 10:44:20 +0300 Subject: sched/isolation: Make HK_TYPE_KTHREAD an alias of HK_TYPE_DOMAIN Since commit 041ee6f3727a ("kthread: Rely on HK_TYPE_DOMAIN for preferred affinity management"), kthreads default to use the HK_TYPE_DOMAIN cpumask. IOW, it is no longer affected by the setting of the nohz_full boot kernel parameter. That means HK_TYPE_KTHREAD should now be an alias of HK_TYPE_DOMAIN instead of HK_TYPE_KERNEL_NOISE to correctly reflect the current kthread behavior. Make the change as HK_TYPE_KTHREAD is still being used in some networking code. Fixes: 041ee6f3727a ("kthread: Rely on HK_TYPE_DOMAIN for preferred affinity management") Signed-off-by: Waiman Long Signed-off-by: Julian Anastasov Signed-off-by: Pablo Neira Ayuso --- include/linux/sched/isolation.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/sched/isolation.h b/include/linux/sched/isolation.h index dc3975ff1b2e..cf0fd03dd7a2 100644 --- a/include/linux/sched/isolation.h +++ b/include/linux/sched/isolation.h @@ -20,6 +20,11 @@ enum hk_type { HK_TYPE_KERNEL_NOISE, HK_TYPE_MAX, + /* + * HK_TYPE_KTHREAD is now an alias of HK_TYPE_DOMAIN + */ + HK_TYPE_KTHREAD = HK_TYPE_DOMAIN, + /* * The following housekeeping types are only set by the nohz_full * boot commandline option. So they can share the same value. @@ -29,7 +34,6 @@ enum hk_type { HK_TYPE_RCU = HK_TYPE_KERNEL_NOISE, HK_TYPE_MISC = HK_TYPE_KERNEL_NOISE, HK_TYPE_WQ = HK_TYPE_KERNEL_NOISE, - HK_TYPE_KTHREAD = HK_TYPE_KERNEL_NOISE }; #ifdef CONFIG_CPU_ISOLATION -- cgit v1.2.3