Packet processing uses CT limit state under RCU, while netns teardown frees that state under ovs_mutex. The CT limit pointer was neither removed from readers nor protected by a grace period, allowing packet processing to dereference the freed state. An unprivileged user can trigger this bug from a user and network namespace, causing a slab-use-after-free in ovs_ct_execute() when the netns is torn down. Publish the CT limit pointer through RCU, remove it before teardown, and wait for readers before freeing its contents. Keep ovs_mutex around individual CT limit updates, and use the RCU read-side lock while GET traverses the RCU-protected limit lists. Netns teardown detaches the RCU-protected CT limit state while holding ovs_mutex, then completes the teardown - waiting for the RCU grace period and freeing the state - after the mutex is released. This keeps the grace period wait out of ovs_mutex so that it does not stall concurrent OVS users. The netlink command handlers do not need NULL checks because the userspace netlink socket holds an active reference to its network namespace while a request is processed. The per-netns exit path therefore cannot run concurrently with SET, DEL, or GET for that socket's namespace. Fixes: 11efd5cb04a1 ("openvswitch: Support conntrack zone limit") Cc: stable@vger.kernel.org Reported-by: Vega Link: https://lore.kernel.org/all/cover.1784711445.git.xuyuqiabc@gmail.com Assisted-by: Codex:GPT-5.4 Co-developed-by: Nan Li Signed-off-by: Nan Li Signed-off-by: Yuqi Xu Reviewed-by: Ren Wei --- Changes in v7: - Split CT limit teardown into a start/finish pair so that the RCU grace period wait happens after ovs_mutex is released, keeping the lock from blocking other ovs_mutex users during the wait. - v6 Link: https://lore.kernel.org/all/cover.1786506548.git.xuyuqiabc@gmail.com/ Changes in v6: - Explain why netlink command handlers do not need NULL checks. - Document that teardown currently waits for the RCU grace period while holding ovs_mutex, leaving lock-scope optimization for a separate change. - v5 Link: https://lore.kernel.org/all/cover.1786441097.git.xuyuqiabc@gmail.com/ Changes in v5: - Remove unreachable command-path NULL handling because netlink sockets keep their network namespaces alive while requests are processed. - Restore the previous SET, DEL, and GET command semantics. - Document the ct_limit_info RCU and ovs_mutex locking contract. - v4 Link: https://lore.kernel.org/all/cover.1785908366.git.xuyuqiabc@gmail.com/ Changes in v4: - Restore per-entry ovs_mutex locking for CT limit SET and DEL. - Treat CT limit updates racing with netns teardown as successful no-ops. - Free an uninstalled CT limit allocation and document GET helpers' RCU contract. - v3 Link: https://lore.kernel.org/all/cover.1784866791.git.xuyuqiabc@gmail.com/ Changes in v3: - Use RCU dereference and a NULL check for CT limit GET requests. - Limit ovs_mutex to CT limit updates; do not hold it while preparing replies. - Use ovsl_dereference() for update paths and clarify the RCU grace-period comment. - v2 Link: https://lore.kernel.org/all/cover.1784711445.git.xuyuqiabc@gmail.com Changes in v2: - Sort local declarations modified by this patch in reverse Christmas-tree order. - v1 Link: https://lore.kernel.org/all/aa8a1d8dcbac8a13dbdf077a642a66f4c5d81e4b.1784355642.git.xuyuqiabc@gmail.com/ net/openvswitch/conntrack.c | 115 +++++++++++++++++++++++------------- net/openvswitch/conntrack.h | 6 +- net/openvswitch/datapath.c | 7 ++- net/openvswitch/datapath.h | 6 +- 4 files changed, 88 insertions(+), 46 deletions(-) diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index 95697d4e16e6..0c1308fc23b4 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -933,10 +933,14 @@ static int ovs_ct_check_limit(struct net *net, const struct ovs_conntrack_info *info) { struct ovs_net *ovs_net = net_generic(net, ovs_net_id); - const struct ovs_ct_limit_info *ct_limit_info = ovs_net->ct_limit_info; + const struct ovs_ct_limit_info *ct_limit_info; u32 per_zone_limit, connections; u32 conncount_key; + ct_limit_info = rcu_dereference(ovs_net->ct_limit_info); + if (!ct_limit_info) + return 0; + conncount_key = info->zone.id; per_zone_limit = ct_limit_get(ct_limit_info, info->zone.id); @@ -1585,40 +1589,54 @@ static void __ovs_ct_free_action(struct ovs_conntrack_info *ct_info) #if IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT) static int ovs_ct_limit_init(struct net *net, struct ovs_net *ovs_net) { + struct ovs_ct_limit_info *info; int i, err; - ovs_net->ct_limit_info = kmalloc_obj(*ovs_net->ct_limit_info); - if (!ovs_net->ct_limit_info) + info = kmalloc_obj(*info); + if (!info) return -ENOMEM; - ovs_net->ct_limit_info->default_limit = OVS_CT_LIMIT_DEFAULT; - ovs_net->ct_limit_info->limits = + info->default_limit = OVS_CT_LIMIT_DEFAULT; + info->limits = kmalloc_objs(struct hlist_head, CT_LIMIT_HASH_BUCKETS); - if (!ovs_net->ct_limit_info->limits) { - kfree(ovs_net->ct_limit_info); + if (!info->limits) { + kfree(info); return -ENOMEM; } for (i = 0; i < CT_LIMIT_HASH_BUCKETS; i++) - INIT_HLIST_HEAD(&ovs_net->ct_limit_info->limits[i]); + INIT_HLIST_HEAD(&info->limits[i]); - ovs_net->ct_limit_info->data = nf_conncount_init(net, sizeof(u32)); + info->data = nf_conncount_init(net, sizeof(u32)); - if (IS_ERR(ovs_net->ct_limit_info->data)) { - err = PTR_ERR(ovs_net->ct_limit_info->data); - kfree(ovs_net->ct_limit_info->limits); - kfree(ovs_net->ct_limit_info); + if (IS_ERR(info->data)) { + err = PTR_ERR(info->data); + kfree(info->limits); + kfree(info); pr_err("openvswitch: failed to init nf_conncount %d\n", err); return err; } + rcu_assign_pointer(ovs_net->ct_limit_info, info); return 0; } -static void ovs_ct_limit_exit(struct net *net, struct ovs_net *ovs_net) +static void *ovs_ct_limit_exit_start(struct ovs_net *ovs_net) { - const struct ovs_ct_limit_info *info = ovs_net->ct_limit_info; + return rcu_replace_pointer(ovs_net->ct_limit_info, NULL, + lockdep_ovsl_is_held()); +} + +static void ovs_ct_limit_exit_finish(struct net *net, void *data) +{ + const struct ovs_ct_limit_info *info = data; int i; + if (!info) + return; + + /* Wait for RCU readers to stop using the CT limits. */ + synchronize_rcu(); + nf_conncount_destroy(net, info->data); for (i = 0; i < CT_LIMIT_HASH_BUCKETS; ++i) { struct hlist_head *head = &info->limits[i]; @@ -1665,12 +1683,13 @@ static bool check_zone_id(int zone_id, u16 *pzone) return false; } -static int ovs_ct_limit_set_zone_limit(struct nlattr *nla_zone_limit, - struct ovs_ct_limit_info *info) +static int ovs_ct_limit_set_zone_limit(struct ovs_net *ovs_net, + struct nlattr *nla_zone_limit) { struct ovs_zone_limit *zone_limit; - int rem; + struct ovs_ct_limit_info *info; u16 zone; + int rem; rem = NLA_ALIGN(nla_len(nla_zone_limit)); zone_limit = (struct ovs_zone_limit *)nla_data(nla_zone_limit); @@ -1679,6 +1698,7 @@ static int ovs_ct_limit_set_zone_limit(struct nlattr *nla_zone_limit, if (unlikely(zone_limit->zone_id == OVS_ZONE_LIMIT_DEFAULT_ZONE)) { ovs_lock(); + info = ovsl_dereference(ovs_net->ct_limit_info); info->default_limit = zone_limit->limit; ovs_unlock(); } else if (unlikely(!check_zone_id( @@ -1695,6 +1715,7 @@ static int ovs_ct_limit_set_zone_limit(struct nlattr *nla_zone_limit, ct_limit->limit = zone_limit->limit; ovs_lock(); + info = ovsl_dereference(ovs_net->ct_limit_info); ct_limit_set(info, ct_limit); ovs_unlock(); } @@ -1709,12 +1730,13 @@ static int ovs_ct_limit_set_zone_limit(struct nlattr *nla_zone_limit, return 0; } -static int ovs_ct_limit_del_zone_limit(struct nlattr *nla_zone_limit, - struct ovs_ct_limit_info *info) +static int ovs_ct_limit_del_zone_limit(struct ovs_net *ovs_net, + struct nlattr *nla_zone_limit) { struct ovs_zone_limit *zone_limit; - int rem; + struct ovs_ct_limit_info *info; u16 zone; + int rem; rem = NLA_ALIGN(nla_len(nla_zone_limit)); zone_limit = (struct ovs_zone_limit *)nla_data(nla_zone_limit); @@ -1723,6 +1745,7 @@ static int ovs_ct_limit_del_zone_limit(struct nlattr *nla_zone_limit, if (unlikely(zone_limit->zone_id == OVS_ZONE_LIMIT_DEFAULT_ZONE)) { ovs_lock(); + info = ovsl_dereference(ovs_net->ct_limit_info); info->default_limit = OVS_CT_LIMIT_DEFAULT; ovs_unlock(); } else if (unlikely(!check_zone_id( @@ -1730,6 +1753,7 @@ static int ovs_ct_limit_del_zone_limit(struct nlattr *nla_zone_limit, OVS_NLERR(true, "zone id is out of range"); } else { ovs_lock(); + info = ovsl_dereference(ovs_net->ct_limit_info); ct_limit_del(info, zone); ovs_unlock(); } @@ -1773,6 +1797,7 @@ static int __ovs_ct_limit_get_zone_limit(struct net *net, return nla_put_nohdr(reply, sizeof(zone_limit), &zone_limit); } +/* Called with RCU read lock held. */ static int ovs_ct_limit_get_zone_limit(struct net *net, struct nlattr *nla_zone_limit, struct ovs_ct_limit_info *info, @@ -1796,12 +1821,10 @@ static int ovs_ct_limit_get_zone_limit(struct net *net, &zone))) { OVS_NLERR(true, "zone id is out of range"); } else { - rcu_read_lock(); limit = ct_limit_get(info, zone); err = __ovs_ct_limit_get_zone_limit( net, info->data, zone, limit, reply); - rcu_read_unlock(); if (err) return err; } @@ -1816,6 +1839,7 @@ static int ovs_ct_limit_get_zone_limit(struct net *net, return 0; } +/* Called with RCU read lock held. */ static int ovs_ct_limit_get_all_zone_limit(struct net *net, struct ovs_ct_limit_info *info, struct sk_buff *reply) @@ -1828,19 +1852,16 @@ static int ovs_ct_limit_get_all_zone_limit(struct net *net, if (err) return err; - rcu_read_lock(); for (i = 0; i < CT_LIMIT_HASH_BUCKETS; ++i) { head = &info->limits[i]; hlist_for_each_entry_rcu(ct_limit, head, hlist_node) { err = __ovs_ct_limit_get_zone_limit(net, info->data, ct_limit->zone, ct_limit->limit, reply); if (err) - goto exit_err; + return err; } } -exit_err: - rcu_read_unlock(); return err; } @@ -1850,7 +1871,6 @@ static int ovs_ct_limit_cmd_set(struct sk_buff *skb, struct genl_info *info) struct sk_buff *reply; struct ovs_header *ovs_reply_header; struct ovs_net *ovs_net = net_generic(sock_net(skb->sk), ovs_net_id); - struct ovs_ct_limit_info *ct_limit_info = ovs_net->ct_limit_info; int err; reply = ovs_ct_limit_cmd_reply_start(info, OVS_CT_LIMIT_CMD_SET, @@ -1863,8 +1883,8 @@ static int ovs_ct_limit_cmd_set(struct sk_buff *skb, struct genl_info *info) goto exit_err; } - err = ovs_ct_limit_set_zone_limit(a[OVS_CT_LIMIT_ATTR_ZONE_LIMIT], - ct_limit_info); + err = ovs_ct_limit_set_zone_limit(ovs_net, + a[OVS_CT_LIMIT_ATTR_ZONE_LIMIT]); if (err) goto exit_err; @@ -1884,7 +1904,6 @@ static int ovs_ct_limit_cmd_del(struct sk_buff *skb, struct genl_info *info) struct sk_buff *reply; struct ovs_header *ovs_reply_header; struct ovs_net *ovs_net = net_generic(sock_net(skb->sk), ovs_net_id); - struct ovs_ct_limit_info *ct_limit_info = ovs_net->ct_limit_info; int err; reply = ovs_ct_limit_cmd_reply_start(info, OVS_CT_LIMIT_CMD_DEL, @@ -1897,8 +1916,8 @@ static int ovs_ct_limit_cmd_del(struct sk_buff *skb, struct genl_info *info) goto exit_err; } - err = ovs_ct_limit_del_zone_limit(a[OVS_CT_LIMIT_ATTR_ZONE_LIMIT], - ct_limit_info); + err = ovs_ct_limit_del_zone_limit(ovs_net, + a[OVS_CT_LIMIT_ATTR_ZONE_LIMIT]); if (err) goto exit_err; @@ -1918,7 +1937,7 @@ static int ovs_ct_limit_cmd_get(struct sk_buff *skb, struct genl_info *info) struct ovs_header *ovs_reply_header; struct net *net = sock_net(skb->sk); struct ovs_net *ovs_net = net_generic(net, ovs_net_id); - struct ovs_ct_limit_info *ct_limit_info = ovs_net->ct_limit_info; + struct ovs_ct_limit_info *ct_limit_info; int err; reply = ovs_ct_limit_cmd_reply_start(info, OVS_CT_LIMIT_CMD_GET, @@ -1932,18 +1951,19 @@ static int ovs_ct_limit_cmd_get(struct sk_buff *skb, struct genl_info *info) goto exit_err; } + rcu_read_lock(); + ct_limit_info = rcu_dereference(ovs_net->ct_limit_info); if (a[OVS_CT_LIMIT_ATTR_ZONE_LIMIT]) { err = ovs_ct_limit_get_zone_limit( net, a[OVS_CT_LIMIT_ATTR_ZONE_LIMIT], ct_limit_info, reply); - if (err) - goto exit_err; } else { err = ovs_ct_limit_get_all_zone_limit(net, ct_limit_info, reply); - if (err) - goto exit_err; } + rcu_read_unlock(); + if (err) + goto exit_err; nla_nest_end(reply, nla_reply); genlmsg_end(reply, ovs_reply_header); @@ -2016,12 +2036,27 @@ int ovs_ct_init(struct net *net) #endif } -void ovs_ct_exit(struct net *net) +/* Must be called with ovs_mutex held. Detaches RCU-protected ct_limit_info + * and returns an opaque handle for ovs_ct_exit_finish() to complete teardown + * after the mutex is released. + */ +void *ovs_ct_exit_start(struct net *net __maybe_unused) +{ +#if IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT) + return ovs_ct_limit_exit_start(net_generic(net, ovs_net_id)); +#endif + return NULL; +} + +/* Must be called without ovs_mutex held. @data must be the opaque pointer + * returned by ovs_ct_exit_start(). + */ +void ovs_ct_exit_finish(struct net *net, void *data __maybe_unused) { struct ovs_net *ovs_net = net_generic(net, ovs_net_id); #if IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT) - ovs_ct_limit_exit(net, ovs_net); + ovs_ct_limit_exit_finish(net, data); #endif if (ovs_net->xt_label) diff --git a/net/openvswitch/conntrack.h b/net/openvswitch/conntrack.h index 317e525c8a11..2363ce56d7ec 100644 --- a/net/openvswitch/conntrack.h +++ b/net/openvswitch/conntrack.h @@ -14,7 +14,8 @@ enum ovs_key_attr; #if IS_ENABLED(CONFIG_NF_CONNTRACK) int ovs_ct_init(struct net *); -void ovs_ct_exit(struct net *); +void *ovs_ct_exit_start(struct net *net); +void ovs_ct_exit_finish(struct net *net, void *data); bool ovs_ct_verify(struct net *, enum ovs_key_attr attr); int ovs_ct_copy_action(struct net *, const struct nlattr *, const struct sw_flow_key *, struct sw_flow_actions **, @@ -40,7 +41,8 @@ void ovs_ct_free_action(const struct nlattr *a); static inline int ovs_ct_init(struct net *net) { return 0; } -static inline void ovs_ct_exit(struct net *net) { } +static inline void *ovs_ct_exit_start(struct net *net) { return NULL; } +static inline void ovs_ct_exit_finish(struct net *net, void *data) { } static inline bool ovs_ct_verify(struct net *net, int attr) { diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index ae69b2cabab9..c18dafa920b7 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -2758,15 +2758,16 @@ static void __net_exit list_vports_from_net(struct net *net, struct net *dnet, static void __net_exit ovs_exit_net(struct net *dnet) { - struct datapath *dp, *dp_next; struct ovs_net *ovs_net = net_generic(dnet, ovs_net_id); struct vport *vport, *vport_next; + struct datapath *dp, *dp_next; + void *ct_exit_data; struct net *net; LIST_HEAD(head); ovs_lock(); - ovs_ct_exit(dnet); + ct_exit_data = ovs_ct_exit_start(dnet); list_for_each_entry_safe(dp, dp_next, &ovs_net->dps, list_node) __dp_destroy(dp); @@ -2784,6 +2785,8 @@ static void __net_exit ovs_exit_net(struct net *dnet) ovs_unlock(); + ovs_ct_exit_finish(dnet, ct_exit_data); + cancel_delayed_work_sync(&ovs_net->masks_rebalance); cancel_work_sync(&ovs_net->dp_notify_work); } diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h index 696640e88fa7..06c6956fb1dc 100644 --- a/net/openvswitch/datapath.h +++ b/net/openvswitch/datapath.h @@ -164,7 +164,9 @@ struct dp_upcall_info { * Protected by genl_mutex. * @dp_notify_work: A work notifier to handle port unregistering. * @masks_rebalance: A work to periodically optimize flow table caches. - * @ct_limit_info: A hash table of conntrack zone connection limits. + * @ct_limit_info: Hash table of conntrack zone connection limits. Protected + * by RCU; updates and teardown are serialized by ovs_mutex. May be NULL during + * netns teardown. * @xt_label: Whether connlables are configured for the network or not. */ struct ovs_net { @@ -172,7 +174,7 @@ struct ovs_net { struct work_struct dp_notify_work; struct delayed_work masks_rebalance; #if IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT) - struct ovs_ct_limit_info *ct_limit_info; + struct ovs_ct_limit_info __rcu *ct_limit_info; #endif bool xt_label; };