Merge tag 'nf-26-05-05' of git://git.kernel.org/pub/scm/linux/kernel/git/netfilter/nf

Pablo Neira Ayuso says:

====================
IPVS fixes for net

The following batch contains IPVS fixes for net to address issues
from the latest net-next pull request.

Julian Anastasov made the following summary:

1-3) Fixes for the recently added resizable hash tables

4) dest from trash can be leaked if ip_vs_start_estimator() fails

5) fixed races and locking for the estimation kthreads

6) fix for wrong roundup_pow_of_two() usage in the resizable hash
   tables

7-8) v2 of the changes from Waiman Long to properly guard against
  the housekeeping_cpumask() updates:

  https://lore.kernel.org/netfilter-devel/20260331165015.2777765-1-longman@redhat.com/

  I added missing Fixes tag. The original description:

  Since commit 041ee6f3727a ("kthread: Rely on HK_TYPE_DOMAIN for preferred
  affinity management"), the HK_TYPE_KTHREAD housekeeping cpumask may no
  longer be correct in showing the actual CPU affinity of kthreads that
  have no predefined CPU affinity. As the ipvs networking code is still
  using HK_TYPE_KTHREAD, we need to make HK_TYPE_KTHREAD reflect the
  reality.

  This patch series makes HK_TYPE_KTHREAD an alias of HK_TYPE_DOMAIN
  and uses RCU to protect access to the HK_TYPE_KTHREAD housekeeping
  cpumask.

Julian plans to post a nf-next patch to limit the connections by using
"conn_max" sysctl. With Simon Horman, they agreed that this is an old
problem that we do not have a limit of connections and it is not a
stopper for this patchset.

* tag 'nf-26-05-05' of git://git.kernel.org/pub/scm/linux/kernel/git/netfilter/nf:
  sched/isolation: Make HK_TYPE_KTHREAD an alias of HK_TYPE_DOMAIN
  ipvs: Guard access of HK_TYPE_KTHREAD cpumask with RCU
  ipvs: fix shift-out-of-bounds in ip_vs_rht_desired_size
  ipvs: fix races around est_mutex and est_cpulist
  ipvs: do not leak dest after get from dest trash
  ipvs: fix the spin_lock usage for RT build
  ipvs: fix races around the conn_lfactor and svc_lfactor sysctl vars
  ipvs: fixes for the new ip_vs_status info
====================

Link: https://patch.msgid.link/20260505001648.360569-1-pablo@netfilter.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 26 insertions, 5 deletions

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 72d325c81313..02762ce73a0c 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 */
@@ -1411,7 +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;
@@ -1529,7 +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);
 }
@@ -1564,6 +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)
  */
@@ -1884,18 +1897,26 @@ 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
 	/* 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
 }
 
@@ -1911,7 +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);
 }