- Kernel - mailweb.openeuler.org

[PATCH OLK-5.10] netfilter: nf_conntrack: destroy stale expectfn expectations
by superdcc97＠163.com 04 Jul '26

04 Jul '26

From: Weiming Shi <bestswngs(a)gmail.com> mainline inclusion from mainline-v7.2-rc1 commit c3009418f9fa1dcb3eb86f4d8c92583537b5faa3 category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/16058 CVE: CVE-2026-53349 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- NAT helpers such as nf_nat_h323 store a raw pointer to module text in exp->expectfn (e.g. ip_nat_q931_expect). nf_ct_helper_expectfn_unregister() only unlinks the callback descriptor and never walks the expectation table, so an expectation pending at module removal survives with a dangling exp->expectfn into freed module text. When the expected connection arrives, init_conntrack() invokes exp->expectfn(), now a stale pointer into the unloaded module. Reproduced on a KASAN build by loading the H.323 helpers, creating a Q.931 expectation, unloading nf_nat_h323, then connecting to the expected port: Oops: int3: 0000 [#1] SMP KASAN NOPTI RIP: 0010:0xffffffffa06102d1 init_conntrack.isra.0 (net/netfilter/nf_conntrack_core.c:1862) nf_conntrack_in (net/netfilter/nf_conntrack_core.c:2049) ipv4_conntrack_local (net/netfilter/nf_conntrack_proto.c:223) nf_hook_slow (net/netfilter/core.c:619) __ip_local_out (net/ipv4/ip_output.c:120) __tcp_transmit_skb (net/ipv4/tcp_output.c:1715) tcp_connect (net/ipv4/tcp_output.c:4374) tcp_v4_connect (net/ipv4/tcp_ipv4.c:345) __sys_connect (net/socket.c:2167) Modules linked in: nf_conntrack_h323 [last unloaded: nf_nat_h323] Reaching the dangling state requires CAP_SYS_MODULE in the initial user namespace to remove a NAT helper that still has live expectations, so this is a robustness fix; leaving an expectation pointing at freed text is wrong regardless. Add nf_ct_helper_expectfn_destroy(), which walks the expectation table and drops every expectation whose ->expectfn matches the descriptor being torn down. Call it from each NAT helper's exit path after the existing RCU grace period, so no expectation outlives the code it points at and no extra synchronize_rcu() is introduced. With the fix, the same reproducer runs to completion without the Oops. Fixes: f587de0e2feb ("[NETFILTER]: nf_conntrack/nf_nat: add H.323 helper port") Reported-by: Xiang Mei <xmei5(a)asu.edu> Assisted-by: Claude:claude-opus-4-8 Signed-off-by: Weiming Shi <bestswngs(a)gmail.com> Signed-off-by: Pablo Neira Ayuso <pablo(a)netfilter.org> Conflicts: net/ipv4/netfilter/nf_nat_h323.c net/netfilter/nf_nat_core.c [commit cbc1dd5b659f is not backport, which lead to conflicts. - net/netfilter/nf_nat_core.c init error path: register_nf_nat_bpf() does not exist on OLK-5.10, so the corresponding nf_ct_helper_expectfn_destroy() call in that dead path was omitted (this path does not exist on target branch).] Signed-off-by: Dong Chenchen <dongchenchen2(a)huawei.com> --- include/net/netfilter/nf_conntrack_helper.h | 1 + net/ipv4/netfilter/nf_nat_h323.c | 2 ++ net/netfilter/nf_conntrack_helper.c | 19 +++++++++++++++++++ net/netfilter/nf_nat_core.c | 1 + net/netfilter/nf_nat_sip.c | 1 + 5 files changed, 24 insertions(+) diff --git a/include/net/netfilter/nf_conntrack_helper.h b/include/net/netfilter/nf_conntrack_helper.h index 37f0fbefb060..3932f09f8801 100644 --- a/include/net/netfilter/nf_conntrack_helper.h +++ b/include/net/netfilter/nf_conntrack_helper.h @@ -152,6 +152,7 @@ void nf_ct_helper_log(struct sk_buff *skb, const struct nf_conn *ct, void nf_ct_helper_expectfn_register(struct nf_ct_helper_expectfn *n); void nf_ct_helper_expectfn_unregister(struct nf_ct_helper_expectfn *n); +void nf_ct_helper_expectfn_destroy(const struct nf_ct_helper_expectfn *n); struct nf_ct_helper_expectfn * nf_ct_helper_expectfn_find_by_name(const char *name); struct nf_ct_helper_expectfn * diff --git a/net/ipv4/netfilter/nf_nat_h323.c b/net/ipv4/netfilter/nf_nat_h323.c index 3e2685c120c7..d028cbae11e8 100644 --- a/net/ipv4/netfilter/nf_nat_h323.c +++ b/net/ipv4/netfilter/nf_nat_h323.c @@ -621,6 +621,8 @@ static void __exit fini(void) nf_ct_helper_expectfn_unregister(&q931_nat); nf_ct_helper_expectfn_unregister(&callforwarding_nat); synchronize_rcu(); + nf_ct_helper_expectfn_destroy(&q931_nat); + nf_ct_helper_expectfn_destroy(&callforwarding_nat); } /****************************************************************************/ diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index 862a782ec931..24a945cfb2e8 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -332,6 +332,25 @@ void nf_ct_helper_expectfn_unregister(struct nf_ct_helper_expectfn *n) } EXPORT_SYMBOL_GPL(nf_ct_helper_expectfn_unregister); +static bool expect_iter_expectfn(struct nf_conntrack_expect *exp, void *data) +{ + const struct nf_ct_helper_expectfn *n = data; + + /* Relies on registered expectfn descriptors having unique ->expectfn + * pointers, which holds for the in-tree NAT helpers. + */ + return exp->expectfn == n->expectfn; +} + +/* Destroy expectations still pointing at @n->expectfn; call after the + * caller's RCU grace period so none outlives the (often modular) callback. + */ +void nf_ct_helper_expectfn_destroy(const struct nf_ct_helper_expectfn *n) +{ + nf_ct_expect_iterate_destroy(expect_iter_expectfn, (void *)n); +} +EXPORT_SYMBOL_GPL(nf_ct_helper_expectfn_destroy); + /* Caller should hold the rcu lock */ struct nf_ct_helper_expectfn * nf_ct_helper_expectfn_find_by_name(const char *name) diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index b7c3c902290f..62356dcd694b 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -1197,6 +1197,7 @@ static void __exit nf_nat_cleanup(void) RCU_INIT_POINTER(nf_nat_hook, NULL); synchronize_net(); + nf_ct_helper_expectfn_destroy(&follow_master_nat); kvfree(nf_nat_bysource); unregister_pernet_subsys(&nat_net_ops); } diff --git a/net/netfilter/nf_nat_sip.c b/net/netfilter/nf_nat_sip.c index 15d4267cf49f..71e75a751c09 100644 --- a/net/netfilter/nf_nat_sip.c +++ b/net/netfilter/nf_nat_sip.c @@ -666,6 +666,7 @@ static void __exit nf_nat_sip_fini(void) RCU_INIT_POINTER(nf_nat_sip_hooks, NULL); nf_ct_helper_expectfn_unregister(&sip_nat); synchronize_rcu(); + nf_ct_helper_expectfn_destroy(&sip_nat); } static const struct nf_nat_sip_hooks sip_hooks = { -- 2.43.0

2 1

[PATCH OLK-6.6] net/sched: act_api: use RCU with deferred freeing for action lifecycle
by superdcc97＠163.com 04 Jul '26

04 Jul '26

From: Jamal Hadi Salim <jhs(a)mojatatu.com> stable inclusion from stable-v6.6.143 commit 8b136f18ac4b2ace5aaad3305b3f8a5d8165a009 category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/15950 CVE: CVE-2026-53264 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 5057e1aca011e51ef51498c940ef96f3d3e8a305 ] When NEWTFILTER and DELFILTER are run concurrently it is possible to create a race with an associated action. Let's illustrate with CPU0 running NEWTFILTER and CPU1 running DELFILTER: 0: mutex_lock() <-- holds the idr lock 0: rcu_read_lock() 0: p = idr_find(idr, index) <-- action p is valid (RCU protects IDR) 0: mutex_unlock() <-- releases the idr lock 1: refcount_dec_and_mutex_lock() <-- refcnt 1->0, mutex held 1: idr_remove(idr, index) <-- Action removed from IDR 1: mutex_unlock() <-- mutex released allowing us to delete the action 1: tcf_action_cleanup(p); kfree(p) <-- Kfrees p immediately, no deferral 0: refcount_inc_not_zero(&p->tcfa_refcnt) <-- ouch, UAF p points to freed memory This patch fixes the race condition between NEWTFILTER and DELFILTER by adding struct rcu_head to tc_action used in the deferral and introducing a call_rcu() in the delete path to defer the final kfree(). Note: this is a revert of commit d7fb60b9cafb ("net_sched: get rid of tcfa_rcu") but also modernization/simplification to directly use kfree_rcu(). Let's illustrate the new restored code path: 0: rcu_read_lock() 1: refcount_dec_and_mutex_lock() <-- refcnt 1->0, mutex held 1: idr_remove(idr, index) 1: mutex_unlock() 1: call_rcu(&p->tcfa_rcu, tcf_action_rcu_free) <-- defer kfree after grace period 0: p = idr_find(idr, index) 0: refcount_inc_not_zero(&p->tcfa_refcnt) <-- fails, refcnt already 0 1: rcu_read_unlock() <-- release so freeing can run after grace period After CPU1 calls idr_remove(), the object is no longer reachable through the IDR. CPU0's subsequent idr_find() will return NULL, and even if it still held a stale pointer, the immediate kfree() is now deferred until after the RCU grace period, so no UAF can occur. Fixes: d7fb60b9cafb ("net_sched: get rid of tcfa_rcu") Suggested-by: Jakub Kicinski <kuba(a)kernel.org> Reported-by: Kyle Zeng <kylebot(a)openai.com> Tested-by: Victor Nogueira <victor(a)mojatatu.com> Tested-by: syzbot(a)syzkaller.appspotmail.com Signed-off-by: Jamal Hadi Salim <jhs(a)mojatatu.com> Tested-by: Kyle Zeng <kylebot(a)openai.com> Reviewed-by: Pedro Tammela <pctammela(a)mojatatu.com> Reviewed-by: Eric Dumazet <edumazet(a)google.com> Reviewed-by: Victor Nogueira <victor(a)mojatatu.com> Link: https://patch.msgid.link/20260531160812.68020-1-jhs@mojatatu.com Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Dong Chenchen <dongchenchen2(a)huawei.com> --- include/net/act_api.h | 1 + net/sched/act_api.c | 7 +------ 2 files changed, 2 insertions(+), 6 deletions(-) diff --git a/include/net/act_api.h b/include/net/act_api.h index 8db6994c90ee..56f49351fd51 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -42,6 +42,7 @@ struct tc_action { struct tc_cookie __rcu *user_cookie; struct tcf_chain __rcu *goto_chain; u32 tcfa_flags; + struct rcu_head tcfa_rcu; u8 hw_stats; u8 used_hw_stats; bool used_hw_stats_valid; diff --git a/net/sched/act_api.c b/net/sched/act_api.c index e509ac28c492..bed04ae3003c 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -112,11 +112,6 @@ struct tcf_chain *tcf_action_set_ctrlact(struct tc_action *a, int action, } EXPORT_SYMBOL(tcf_action_set_ctrlact); -/* XXX: For standalone actions, we don't need a RCU grace period either, because - * actions are always connected to filters and filters are already destroyed in - * RCU callbacks, so after a RCU grace period actions are already disconnected - * from filters. Readers later can not find us. - */ static void free_tcf(struct tc_action *p) { struct tcf_chain *chain = rcu_dereference_protected(p->goto_chain, 1); @@ -129,7 +124,7 @@ static void free_tcf(struct tc_action *p) if (chain) tcf_chain_put_by_act(chain); - kfree(p); + kfree_rcu(p, tcfa_rcu); } static void offload_action_hw_count_set(struct tc_action *act, -- 2.43.0

2 1

[PATCH OLK-6.6] netfilter: revalidate bridge ports
by superdcc97＠163.com 04 Jul '26

04 Jul '26

From: Florian Westphal <fw(a)strlen.de> mainline inclusion from mainline-v7.2-rc1 commit ccb9fd4b87538ccf19ccff78ee26700526d94867 category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/15906 CVE: CVE-2026-53220 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- ebt_redirect_tg() dereferences br_port_get_rcu() return without a NULL check, causing a kernel panic when the bridge port has been removed between the original hook invocation and an NFQUEUE reinject. A mere NULL check isn't sufficient, however. As sashiko review points out userspace can not only remove the port from the bridge, it could also place the device in a different virtual device, e.g. macvlan. If this happens, we must drop the packet, there is no way for us to reinject it into the bridge path. Switch to _upper API, we don't need the bridge port structure. Also, this fix keeps another bug intact: Both nfnetlink_log and nfnetlink_queue use CONFIG_BRIDGE_NETFILTER too aggressive, which prevents certain logging features when queueing in bridge family: NETFILTER_FAMILY_BRIDGE can be enabled while the old CONFIG_BRIDGE_NETFILTER cruft is off. Fixes tag is a common ancestor, this was always broken. Fixes: f350a0a87374 ("bridge: use rx_handler_data pointer to store net_bridge_port pointer") Reported-by: Ji'an Zhou <eilaimemedsnaimel(a)gmail.com> Assisted-by: Claude:claude-sonnet-4-6 Signed-off-by: Florian Westphal <fw(a)strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo(a)netfilter.org> Signed-off-by: Dong Chenchen <dongchenchen2(a)huawei.com> --- net/bridge/netfilter/ebt_dnat.c | 4 +- net/bridge/netfilter/ebt_redirect.c | 16 +++++--- net/netfilter/nfnetlink_log.c | 23 +++++++++-- net/netfilter/nfnetlink_queue.c | 60 +++++++++++++++++++++++++++-- 4 files changed, 89 insertions(+), 14 deletions(-) diff --git a/net/bridge/netfilter/ebt_dnat.c b/net/bridge/netfilter/ebt_dnat.c index 3fda71a8579d..73f185cccd63 100644 --- a/net/bridge/netfilter/ebt_dnat.c +++ b/net/bridge/netfilter/ebt_dnat.c @@ -39,7 +39,9 @@ ebt_dnat_tg(struct sk_buff *skb, const struct xt_action_param *par) dev = xt_in(par); break; case NF_BR_PRE_ROUTING: - dev = br_port_get_rcu(xt_in(par))->br->dev; + dev = netdev_master_upper_dev_get_rcu(xt_in(par)); + if (!dev) /* bridge port removed? */ + return EBT_DROP; break; default: dev = NULL; diff --git a/net/bridge/netfilter/ebt_redirect.c b/net/bridge/netfilter/ebt_redirect.c index 307790562b49..83486cd4d564 100644 --- a/net/bridge/netfilter/ebt_redirect.c +++ b/net/bridge/netfilter/ebt_redirect.c @@ -24,12 +24,18 @@ ebt_redirect_tg(struct sk_buff *skb, const struct xt_action_param *par) if (skb_ensure_writable(skb, 0)) return EBT_DROP; - if (xt_hooknum(par) != NF_BR_BROUTING) - /* rcu_read_lock()ed by nf_hook_thresh */ - ether_addr_copy(eth_hdr(skb)->h_dest, - br_port_get_rcu(xt_in(par))->br->dev->dev_addr); - else + if (xt_hooknum(par) != NF_BR_BROUTING) { + const struct net_device *dev; + + dev = netdev_master_upper_dev_get_rcu(xt_in(par)); + if (!dev) + return EBT_DROP; + + ether_addr_copy(eth_hdr(skb)->h_dest, dev->dev_addr); + } else { ether_addr_copy(eth_hdr(skb)->h_dest, xt_in(par)->dev_addr); + } + skb->pkt_type = PACKET_HOST; return info->target; } diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index 3da32d2f68e0..cfd68bc005d2 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -450,6 +450,23 @@ static int nfulnl_put_bridge(struct nfulnl_instance *inst, const struct sk_buff return -1; } +#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) +static int nflog_put_master_ifindex(struct sk_buff *nlskb, int attr, + const struct net_device *dev) +{ + const struct net_device *upper; + + if (dev && !netif_is_bridge_port(dev)) + return 0; + + upper = netdev_master_upper_dev_get_rcu((struct net_device *)dev); + if (upper && nla_put_be32(nlskb, attr, htonl(upper->ifindex))) + return -EMSGSIZE; + + return 0; +} +#endif + /* This is an inline function, we don't really care about a long * list of arguments */ static inline int @@ -504,8 +521,7 @@ __build_packet_message(struct nfnl_log_net *log, /* rcu_read_lock()ed by nf_hook_thresh or * nf_log_packet. */ - nla_put_be32(inst->skb, NFULA_IFINDEX_INDEV, - htonl(br_port_get_rcu(indev)->br->dev->ifindex))) + nflog_put_master_ifindex(inst->skb, NFULA_IFINDEX_INDEV, indev)) goto nla_put_failure; } else { int physinif; @@ -541,8 +557,7 @@ __build_packet_message(struct nfnl_log_net *log, /* rcu_read_lock()ed by nf_hook_thresh or * nf_log_packet. */ - nla_put_be32(inst->skb, NFULA_IFINDEX_OUTDEV, - htonl(br_port_get_rcu(outdev)->br->dev->ifindex))) + nflog_put_master_ifindex(inst->skb, NFULA_IFINDEX_OUTDEV, outdev)) goto nla_put_failure; } else { struct net_device *physoutdev; diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index 38ab16b71c21..574c62a451ce 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -255,11 +255,48 @@ static bool nf_ct_drop_unconfirmed(const struct nf_queue_entry *entry, bool *is_ return false; } +static bool nf_bridge_port_valid(const struct net_device *dev) +{ + if (!dev) + return true; + + return netif_is_bridge_port(dev); +} + +/* queued skbs leave rcu protection. We bump device refcount so that + * the device cannot go away. However, while packet was out the port + * could have been removed from the bridge. + * + * Ensure in+outdev are still part of a bridge at reinject time. + * + * The device rx_handler_data could even be pointing at data that is + * not a net_bridge_port structure. + */ +static bool nf_bridge_ports_valid(const struct nf_queue_entry *entry) +{ +#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) + if (!nf_bridge_port_valid(entry->physin) || + !nf_bridge_port_valid(entry->physout)) + return false; +#endif + if (entry->state.pf != PF_BRIDGE) + return true; + + if (!nf_bridge_port_valid(entry->state.in) || + !nf_bridge_port_valid(entry->state.out)) + return false; + + return true; +} + static void nfqnl_reinject(struct nf_queue_entry *entry, unsigned int verdict) { const struct nf_ct_hook *ct_hook; int err; + if (!nf_bridge_ports_valid(entry)) + verdict = NF_DROP; + if (verdict == NF_ACCEPT || verdict == NF_REPEAT || verdict == NF_STOP) { @@ -434,6 +471,23 @@ static int nfqnl_put_bridge(struct nf_queue_entry *entry, struct sk_buff *skb) return -1; } +#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) +static int nfqnl_put_master_ifindex(struct sk_buff *nlskb, int attr, + const struct net_device *dev) +{ + const struct net_device *upper; + + if (dev && !netif_is_bridge_port(dev)) + return 0; + + upper = netdev_master_upper_dev_get_rcu((struct net_device *)dev); + if (upper && nla_put_be32(nlskb, attr, htonl(upper->ifindex))) + return -EMSGSIZE; + + return 0; +} +#endif + static struct sk_buff * nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, struct nf_queue_entry *entry, @@ -569,8 +623,7 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, htonl(indev->ifindex)) || /* this is the bridge group "brX" */ /* rcu_read_lock()ed by __nf_queue */ - nla_put_be32(skb, NFQA_IFINDEX_INDEV, - htonl(br_port_get_rcu(indev)->br->dev->ifindex))) + nfqnl_put_master_ifindex(skb, NFQA_IFINDEX_INDEV, indev)) goto nla_put_failure; } else { int physinif; @@ -603,8 +656,7 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, htonl(outdev->ifindex)) || /* this is the bridge group "brX" */ /* rcu_read_lock()ed by __nf_queue */ - nla_put_be32(skb, NFQA_IFINDEX_OUTDEV, - htonl(br_port_get_rcu(outdev)->br->dev->ifindex))) + nfqnl_put_master_ifindex(skb, NFQA_IFINDEX_OUTDEV, outdev)) goto nla_put_failure; } else { int physoutif; -- 2.43.0

2 1

[PATCH OLK-5.10] netfilter: revalidate bridge ports
by superdcc97＠163.com 04 Jul '26

04 Jul '26

From: Florian Westphal <fw(a)strlen.de> mainline inclusion from mainline-v7.2-rc1 commit ccb9fd4b87538ccf19ccff78ee26700526d94867 category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/15906 CVE: CVE-2026-53220 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- ebt_redirect_tg() dereferences br_port_get_rcu() return without a NULL check, causing a kernel panic when the bridge port has been removed between the original hook invocation and an NFQUEUE reinject. A mere NULL check isn't sufficient, however. As sashiko review points out userspace can not only remove the port from the bridge, it could also place the device in a different virtual device, e.g. macvlan. If this happens, we must drop the packet, there is no way for us to reinject it into the bridge path. Switch to _upper API, we don't need the bridge port structure. Also, this fix keeps another bug intact: Both nfnetlink_log and nfnetlink_queue use CONFIG_BRIDGE_NETFILTER too aggressive, which prevents certain logging features when queueing in bridge family: NETFILTER_FAMILY_BRIDGE can be enabled while the old CONFIG_BRIDGE_NETFILTER cruft is off. Fixes tag is a common ancestor, this was always broken. Fixes: f350a0a87374 ("bridge: use rx_handler_data pointer to store net_bridge_port pointer") Reported-by: Ji'an Zhou <eilaimemedsnaimel(a)gmail.com> Assisted-by: Claude:claude-sonnet-4-6 Signed-off-by: Florian Westphal <fw(a)strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo(a)netfilter.org> Conflicts: net/netfilter/nfnetlink_queue.c [commit ccb9fd4b8753 ("netfilter: revalidate bridge ports") is not backport, which lead to conflicts] Signed-off-by: Dong Chenchen <dongchenchen2(a)huawei.com> --- net/bridge/netfilter/ebt_dnat.c | 4 +- net/bridge/netfilter/ebt_redirect.c | 16 +++++--- net/netfilter/nfnetlink_log.c | 23 +++++++++-- net/netfilter/nfnetlink_queue.c | 64 +++++++++++++++++++++++++---- 4 files changed, 89 insertions(+), 18 deletions(-) diff --git a/net/bridge/netfilter/ebt_dnat.c b/net/bridge/netfilter/ebt_dnat.c index 3fda71a8579d..73f185cccd63 100644 --- a/net/bridge/netfilter/ebt_dnat.c +++ b/net/bridge/netfilter/ebt_dnat.c @@ -39,7 +39,9 @@ ebt_dnat_tg(struct sk_buff *skb, const struct xt_action_param *par) dev = xt_in(par); break; case NF_BR_PRE_ROUTING: - dev = br_port_get_rcu(xt_in(par))->br->dev; + dev = netdev_master_upper_dev_get_rcu(xt_in(par)); + if (!dev) /* bridge port removed? */ + return EBT_DROP; break; default: dev = NULL; diff --git a/net/bridge/netfilter/ebt_redirect.c b/net/bridge/netfilter/ebt_redirect.c index 307790562b49..83486cd4d564 100644 --- a/net/bridge/netfilter/ebt_redirect.c +++ b/net/bridge/netfilter/ebt_redirect.c @@ -24,12 +24,18 @@ ebt_redirect_tg(struct sk_buff *skb, const struct xt_action_param *par) if (skb_ensure_writable(skb, 0)) return EBT_DROP; - if (xt_hooknum(par) != NF_BR_BROUTING) - /* rcu_read_lock()ed by nf_hook_thresh */ - ether_addr_copy(eth_hdr(skb)->h_dest, - br_port_get_rcu(xt_in(par))->br->dev->dev_addr); - else + if (xt_hooknum(par) != NF_BR_BROUTING) { + const struct net_device *dev; + + dev = netdev_master_upper_dev_get_rcu(xt_in(par)); + if (!dev) + return EBT_DROP; + + ether_addr_copy(eth_hdr(skb)->h_dest, dev->dev_addr); + } else { ether_addr_copy(eth_hdr(skb)->h_dest, xt_in(par)->dev_addr); + } + skb->pkt_type = PACKET_HOST; return info->target; } diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index ff01afe1bc60..e5daece618f2 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -435,6 +435,23 @@ static int nfulnl_put_bridge(struct nfulnl_instance *inst, const struct sk_buff return -1; } +#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) +static int nflog_put_master_ifindex(struct sk_buff *nlskb, int attr, + const struct net_device *dev) +{ + const struct net_device *upper; + + if (dev && !netif_is_bridge_port(dev)) + return 0; + + upper = netdev_master_upper_dev_get_rcu((struct net_device *)dev); + if (upper && nla_put_be32(nlskb, attr, htonl(upper->ifindex))) + return -EMSGSIZE; + + return 0; +} +#endif + /* This is an inline function, we don't really care about a long * list of arguments */ static inline int @@ -489,8 +506,7 @@ __build_packet_message(struct nfnl_log_net *log, /* rcu_read_lock()ed by nf_hook_thresh or * nf_log_packet. */ - nla_put_be32(inst->skb, NFULA_IFINDEX_INDEV, - htonl(br_port_get_rcu(indev)->br->dev->ifindex))) + nflog_put_master_ifindex(inst->skb, NFULA_IFINDEX_INDEV, indev)) goto nla_put_failure; } else { int physinif; @@ -526,8 +542,7 @@ __build_packet_message(struct nfnl_log_net *log, /* rcu_read_lock()ed by nf_hook_thresh or * nf_log_packet. */ - nla_put_be32(inst->skb, NFULA_IFINDEX_OUTDEV, - htonl(br_port_get_rcu(outdev)->br->dev->ifindex))) + nflog_put_master_ifindex(inst->skb, NFULA_IFINDEX_OUTDEV, outdev)) goto nla_put_failure; } else { struct net_device *physoutdev; diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index dc6af1919dea..6a79287f33c3 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -225,11 +225,48 @@ find_dequeue_entry(struct nfqnl_instance *queue, unsigned int id) return entry; } +static bool nf_bridge_port_valid(const struct net_device *dev) +{ + if (!dev) + return true; + + return netif_is_bridge_port(dev); +} + +/* queued skbs leave rcu protection. We bump device refcount so that + * the device cannot go away. However, while packet was out the port + * could have been removed from the bridge. + * + * Ensure in+outdev are still part of a bridge at reinject time. + * + * The device rx_handler_data could even be pointing at data that is + * not a net_bridge_port structure. + */ +static bool nf_bridge_ports_valid(const struct nf_queue_entry *entry) +{ +#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) + if (!nf_bridge_port_valid(entry->physin) || + !nf_bridge_port_valid(entry->physout)) + return false; +#endif + if (entry->state.pf != PF_BRIDGE) + return true; + + if (!nf_bridge_port_valid(entry->state.in) || + !nf_bridge_port_valid(entry->state.out)) + return false; + + return true; +} + static void nfqnl_reinject(struct nf_queue_entry *entry, unsigned int verdict) { struct nf_ct_hook *ct_hook; int err; + if (!nf_bridge_ports_valid(entry)) + verdict = NF_DROP; + if (verdict == NF_ACCEPT || verdict == NF_REPEAT || verdict == NF_STOP) { @@ -373,6 +410,23 @@ static int nfqnl_put_bridge(struct nf_queue_entry *entry, struct sk_buff *skb) return -1; } +#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) +static int nfqnl_put_master_ifindex(struct sk_buff *nlskb, int attr, + const struct net_device *dev) +{ + const struct net_device *upper; + + if (dev && !netif_is_bridge_port(dev)) + return 0; + + upper = netdev_master_upper_dev_get_rcu((struct net_device *)dev); + if (upper && nla_put_be32(nlskb, attr, htonl(upper->ifindex))) + return -EMSGSIZE; + + return 0; +} +#endif + static struct sk_buff * nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, struct nf_queue_entry *entry, @@ -498,10 +552,7 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, * netfilter_bridge) */ if (nla_put_be32(skb, NFQA_IFINDEX_PHYSINDEV, htonl(indev->ifindex)) || - /* this is the bridge group "brX" */ - /* rcu_read_lock()ed by __nf_queue */ - nla_put_be32(skb, NFQA_IFINDEX_INDEV, - htonl(br_port_get_rcu(indev)->br->dev->ifindex))) + nfqnl_put_master_ifindex(skb, NFQA_IFINDEX_INDEV, indev)) goto nla_put_failure; } else { int physinif; @@ -532,10 +583,7 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, * netfilter_bridge) */ if (nla_put_be32(skb, NFQA_IFINDEX_PHYSOUTDEV, htonl(outdev->ifindex)) || - /* this is the bridge group "brX" */ - /* rcu_read_lock()ed by __nf_queue */ - nla_put_be32(skb, NFQA_IFINDEX_OUTDEV, - htonl(br_port_get_rcu(outdev)->br->dev->ifindex))) + nfqnl_put_master_ifindex(skb, NFQA_IFINDEX_OUTDEV, outdev)) goto nla_put_failure; } else { int physoutif; -- 2.43.0

2 1

[PATCH OLK-5.10] net: pull headers in qdisc_pkt_len_segs_init()
by superdcc97＠163.com 04 Jul '26

04 Jul '26

From: Eric Dumazet <edumazet(a)google.com> mainline inclusion from mainline-v7.1-rc1 commit 7fb4c19670110f052c04e1ec1d2b953b9f4f57e4 category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/15794 CVE: CVE-2026-53091 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- Most ndo_start_xmit() methods expects headers of gso packets to be already in skb->head. net/core/tso.c users are particularly at risk, because tso_build_hdr() does a memcpy(hdr, skb->data, hdr_len); qdisc_pkt_len_segs_init() already does a dissection of gso packets. Use pskb_may_pull() instead of skb_header_pointer() to make sure drivers do not have to reimplement this. Some malicious packets could be fed, detect them so that we can drop them sooner with a new SKB_DROP_REASON_SKB_BAD_GSO drop_reason. Fixes: e876f208af18 ("net: Add a software TSO helper API") Signed-off-by: Eric Dumazet <edumazet(a)google.com> Reviewed-by: Joe Damato <joe(a)dama.to> Link: https://patch.msgid.link/20260403221540.3297753-3-edumazet@google.com Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Conflicts: include/net/dropreason-core.h net/core/dev.c [commit c504e5c2f964 ("net: skb: introduce kfree_skb_reason()") introduced skb_drop_reason enum and kfree_skb_reason(); later commit ff8372a467fa ("net: skb: move enum skb_drop_reason to standalone header file") and 5b8285cca6fe ("net: move dropreason.h to dropreason-core.h") moved it to include/net/dropreason-core.h. These are not present in OLK-5.10, so the SKB_DROP_REASON_SKB_BAD_GSO drop reason is omitted and the malicious GSO packet is dropped using kfree_skb() and atomic_long_inc(&dev->tx_dropped) instead. commit 874c1928d372 ("net_sched: initialize qdisc_skb_cb(skb)->pkt_segs in qdisc_pkt_len_init()") renamed qdisc_pkt_len_init() to qdisc_pkt_len_segs_init() and added pkt_segs initialization; this is not backported to OLK-5.10, so the fix is applied to the existing qdisc_pkt_len_init() function and the function returns -EINVAL on error. commit 625788b58445 ("net: add per-cpu storage and net->core_stats") introduced dev_core_stats_tx_dropped_inc(), which is not present in OLK-5.10; the existing atomic_long_inc(&dev->tx_dropped) is used instead.] Signed-off-by: Dong Chenchen <dongchenchen2(a)huawei.com> --- net/core/dev.c | 39 +++++++++++++++++++++++++-------------- 1 file changed, 25 insertions(+), 14 deletions(-) diff --git a/net/core/dev.c b/net/core/dev.c index d6dc66b2960d..8d2a00851eb7 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3748,7 +3748,7 @@ struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *d } EXPORT_SYMBOL_GPL(validate_xmit_skb_list); -static void qdisc_pkt_len_init(struct sk_buff *skb) +static int qdisc_pkt_len_init(struct sk_buff *skb) { const struct skb_shared_info *shinfo = skb_shinfo(skb); @@ -3758,7 +3758,7 @@ static void qdisc_pkt_len_init(struct sk_buff *skb) * we add to pkt_len the headers size of all segments */ if (shinfo->gso_size && skb_transport_header_was_set(skb)) { - unsigned int hdr_len; + unsigned int hdr_len, tlen; u16 gso_segs = shinfo->gso_segs; /* mac layer + network layer */ @@ -3767,30 +3767,36 @@ static void qdisc_pkt_len_init(struct sk_buff *skb) /* + transport layer */ if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))) { const struct tcphdr *th; - struct tcphdr _tcphdr; - th = skb_header_pointer(skb, skb_transport_offset(skb), - sizeof(_tcphdr), &_tcphdr); - if (likely(th)) - hdr_len += __tcp_hdrlen(th); - } else if (shinfo->gso_type & SKB_GSO_UDP_L4) { - struct udphdr _udphdr; + if (!pskb_may_pull(skb, hdr_len + sizeof(struct tcphdr))) + return -EINVAL; - if (skb_header_pointer(skb, skb_transport_offset(skb), - sizeof(_udphdr), &_udphdr)) - hdr_len += sizeof(struct udphdr); + th = (const struct tcphdr *)(skb->data + hdr_len); + tlen = __tcp_hdrlen(th); + if (tlen < sizeof(*th)) + return -EINVAL; + hdr_len += tlen; + if (!pskb_may_pull(skb, hdr_len)) + return -EINVAL; + } else if (shinfo->gso_type & SKB_GSO_UDP_L4) { + if (!pskb_may_pull(skb, hdr_len + sizeof(struct udphdr))) + return -EINVAL; + hdr_len += sizeof(struct udphdr); } + /* prior pskb_may_pull() might have changed skb->head. */ + shinfo = skb_shinfo(skb); if (unlikely(shinfo->gso_type & SKB_GSO_DODGY)) { int payload = skb->len - hdr_len; /* Malicious packet. */ if (payload <= 0) - return; + return -EINVAL; gso_segs = DIV_ROUND_UP(payload, shinfo->gso_size); } qdisc_skb_cb(skb)->pkt_len += (gso_segs - 1) * hdr_len; } + return 0; } static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, @@ -4145,7 +4151,12 @@ static int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev) skb_update_prio(skb); - qdisc_pkt_len_init(skb); + if (unlikely(qdisc_pkt_len_init(skb))) { + atomic_long_inc(&dev->tx_dropped); + kfree_skb(skb); + rc = -EINVAL; + goto out; + } #ifdef CONFIG_NET_CLS_ACT skb->tc_at_ingress = 0; # ifdef CONFIG_NET_EGRESS -- 2.43.0

2 1

[PATCH OLK-5.10 v2] netfilter: nf_tables: use list_del_rcu for netlink hooks
by superdcc97＠163.com 04 Jul '26

04 Jul '26

From: Florian Westphal <fw(a)strlen.de> mainline inclusion from mainline-v7.1-rc2 commit f3224ee463f8f6f6ced7dcdf6081add4f8128527 category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/15588 CVE: CVE-2026-46324 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- nft_netdev_unregister_hooks and __nft_unregister_flowtable_net_hooks need to use list_del_rcu(), this list can be walked by concurrent dumpers. Add a new helper and use it consistently. Fixes: f9a43007d3f7 ("netfilter: nf_tables: double hook unregistration in netns path") Signed-off-by: Florian Westphal <fw(a)strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo(a)netfilter.org> Conflicts: net/netfilter/nf_tables_api.c [1.The nf_tables_updchain() hook-list teardown path present in mainline (where hook.list lives on the stack and uses list_del() / nft_netdev_hook_free_rcu()) does not exist in OLK-5.10, so that hunk was skipped. 2. nf_tables_flowtable_destroy() in OLK-5.10 still performs flowtable->data.type->setup(..., FLOW_BLOCK_UNBIND) for each hook before removing it, a pattern that was refactored out upstream; the helper replacement from mainline therefore could not be used here. The existing list_del_rcu() call is retained, and the immediate kfree(hook) was changed to kfree_rcu(hook, rcu) to match the RCU-safe freeing used by the new helper. 3. Other hunks were applied manually by introducing the nft_netdev_hook_unlink_free_rcu() helper and using it consistently wherever OLK-5.10 already performed list_del_rcu()/kfree_rcu() on a netdev/flowtable hook, and by converting the two list_del() callers (nft_netdev_unregister_hooks and __nft_unregister_flowtable_net_hooks) to list_del_rcu() as required by the CVE fix. ] Signed-off-by: Dong Chenchen <dongchenchen2(a)huawei.com> --- net/netfilter/nf_tables_api.c | 38 ++++++++++++++++------------------- 1 file changed, 17 insertions(+), 21 deletions(-) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 2beef989cced..b97c4d0cf1d9 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -303,6 +303,12 @@ static int nft_netdev_register_hooks(struct net *net, return err; } +static void nft_netdev_hook_unlink_free_rcu(struct nft_hook *hook) +{ + list_del_rcu(&hook->list); + kfree_rcu(hook, rcu); +} + static void nft_netdev_unregister_hooks(struct net *net, struct list_head *hook_list, bool release_netdev) @@ -311,10 +317,8 @@ static void nft_netdev_unregister_hooks(struct net *net, list_for_each_entry_safe(hook, next, hook_list, list) { nf_unregister_net_hook(net, &hook->ops); - if (release_netdev) { - list_del(&hook->list); - kfree_rcu(hook, rcu); - } + if (release_netdev) + nft_netdev_hook_unlink_free_rcu(hook); } } @@ -1932,10 +1936,8 @@ void nf_tables_chain_destroy(struct nft_ctx *ctx) if (nft_base_chain_netdev(ctx->family, basechain->ops.hooknum)) { list_for_each_entry_safe(hook, next, - &basechain->hook_list, list) { - list_del_rcu(&hook->list); - kfree_rcu(hook, rcu); - } + &basechain->hook_list, list) + nft_netdev_hook_unlink_free_rcu(hook); } module_put(basechain->type->owner); if (rcu_access_pointer(basechain->stats)) { @@ -7004,10 +7006,8 @@ static void __nft_unregister_flowtable_net_hooks(struct net *net, list_for_each_entry_safe(hook, next, hook_list, list) { nf_unregister_net_hook(net, &hook->ops); - if (release_netdev) { - list_del(&hook->list); - kfree_rcu(hook, rcu); - } + if (release_netdev) + nft_netdev_hook_unlink_free_rcu(hook); } } @@ -7065,8 +7065,7 @@ static int nft_register_flowtable_net_hooks(struct net *net, break; nft_unregister_flowtable_hook(net, flowtable, hook); - list_del_rcu(&hook->list); - kfree_rcu(hook, rcu); + nft_netdev_hook_unlink_free_rcu(hook); } return err; @@ -7076,10 +7075,8 @@ static void nft_flowtable_hooks_destroy(struct list_head *hook_list) { struct nft_hook *hook, *next; - list_for_each_entry_safe(hook, next, hook_list, list) { - list_del_rcu(&hook->list); - kfree_rcu(hook, rcu); - } + list_for_each_entry_safe(hook, next, hook_list, list) + nft_netdev_hook_unlink_free_rcu(hook); } static int nft_flowtable_update(struct nft_ctx *ctx, const struct nlmsghdr *nlh, @@ -7147,8 +7144,7 @@ static int nft_flowtable_update(struct nft_ctx *ctx, const struct nlmsghdr *nlh, list_for_each_entry_safe(hook, next, &flowtable_hook.list, list) { if (unregister) nft_unregister_flowtable_hook(ctx->net, flowtable, hook); - list_del_rcu(&hook->list); - kfree_rcu(hook, rcu); + nft_netdev_hook_unlink_free_rcu(hook); } return err; @@ -7639,7 +7635,7 @@ static void nf_tables_flowtable_destroy(struct nft_flowtable *flowtable) flowtable->data.type->setup(&flowtable->data, hook->ops.dev, FLOW_BLOCK_UNBIND); list_del_rcu(&hook->list); - kfree(hook); + kfree_rcu(hook, rcu); } kfree(flowtable->name); module_put(flowtable->data.type->owner); -- 2.43.0

2 1

[PATCH OLK-6.6] af_unix: Drop all SCM attributes for SOCKMAP.
by superdcc97＠163.com 04 Jul '26

04 Jul '26

From: Kuniyuki Iwashima <kuniyu(a)google.com> mainline inclusion from mainline-v7.1-rc1 commit 965dc93481d1b80d341bdd16c27b16fe197175ee category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/15707 CVE: CVE-2026-53005 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- SOCKMAP can hide inflight fd from AF_UNIX GC. When a socket in SOCKMAP receives skb with inflight fd, sk_psock_verdict_data_ready() looks up the mapped socket and enqueue skb to its psock->ingress_skb. Since neither the old nor the new GC can inspect the psock queue, the hidden skb leaks the inflight sockets. Note that this cannot be detected via kmemleak because inflight sockets are linked to a global list. In addition, SOCKMAP redirect breaks the Tarjan-based GC's assumption that unix_edge.successor is always alive, which is no longer true once skb is redirected, resulting in use-after-free below. [0] Moreover, SOCKMAP does not call scm_stat_del() properly, so unix_show_fdinfo() could report an incorrect fd count. sk_msg_recvmsg() does not support any SCM attributes in the first place. Let's drop all SCM attributes before passing skb to the SOCKMAP layer. [0]: BUG: KASAN: slab-use-after-free in unix_del_edges (net/unix/garbage.c:118 net/unix/garbage.c:181 net/unix/garbage.c:251) Read of size 8 at addr ffff888125362670 by task kworker/56:1/496 CPU: 56 UID: 0 PID: 496 Comm: kworker/56:1 Not tainted 7.0.0-rc7-00263-gb9d8b856689d #3 PREEMPT(lazy) Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.17.0-debian-1.17.0-1 04/01/2014 Workqueue: events sk_psock_backlog Call Trace: <TASK> dump_stack_lvl (lib/dump_stack.c:122) print_report (mm/kasan/report.c:379) kasan_report (mm/kasan/report.c:597) unix_del_edges (net/unix/garbage.c:118 net/unix/garbage.c:181 net/unix/garbage.c:251) unix_destroy_fpl (net/unix/garbage.c:317) unix_destruct_scm (./include/net/scm.h:80 ./include/net/scm.h:86 net/unix/af_unix.c:1976) sk_psock_backlog (./include/linux/skbuff.h:?) process_scheduled_works (kernel/workqueue.c:?) worker_thread (kernel/workqueue.c:?) kthread (kernel/kthread.c:438) ret_from_fork (arch/x86/kernel/process.c:164) ret_from_fork_asm (arch/x86/entry/entry_64.S:258) </TASK> Allocated by task 955: kasan_save_track (mm/kasan/common.c:58 mm/kasan/common.c:78) __kasan_slab_alloc (mm/kasan/common.c:369) kmem_cache_alloc_noprof (mm/slub.c:4539) sk_prot_alloc (net/core/sock.c:2240) sk_alloc (net/core/sock.c:2301) unix_create1 (net/unix/af_unix.c:1099) unix_create (net/unix/af_unix.c:1169) __sock_create (net/socket.c:1606) __sys_socketpair (net/socket.c:1811) __x64_sys_socketpair (net/socket.c:1863 net/socket.c:1860 net/socket.c:1860) do_syscall_64 (arch/x86/entry/syscall_64.c:?) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:130) Freed by task 496: kasan_save_track (mm/kasan/common.c:58 mm/kasan/common.c:78) kasan_save_free_info (mm/kasan/generic.c:587) __kasan_slab_free (mm/kasan/common.c:287) kmem_cache_free (mm/slub.c:6165) __sk_destruct (net/core/sock.c:2282 net/core/sock.c:2384) sk_psock_destroy (./include/net/sock.h:?) process_scheduled_works (kernel/workqueue.c:?) worker_thread (kernel/workqueue.c:?) kthread (kernel/kthread.c:438) ret_from_fork (arch/x86/kernel/process.c:164) ret_from_fork_asm (arch/x86/entry/entry_64.S:258) Fixes: c63829182c37 ("af_unix: Implement ->psock_update_sk_prot()") Fixes: 77462de14a43 ("af_unix: Add read_sock for stream socket types") Reported-by: Xingyu Jin <xingyuj(a)google.com> Signed-off-by: Kuniyuki Iwashima <kuniyu(a)google.com> Link: https://patch.msgid.link/20260415184830.3988432-1-kuniyu@google.com Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Conflicts: net/unix/af_unix.c [commit d0aac85449de ("af_unix: Don't use skb_recv_datagram() in unix_stream_read_skb().") and commit 2b9996417e4e ("af_unix/scm: fix whitespace errors") are not backported, which lead to conflicts] Signed-off-by: Dong Chenchen <dongchenchen2(a)huawei.com> --- net/unix/af_unix.c | 32 ++++++++++++++++++++++++-------- 1 file changed, 24 insertions(+), 8 deletions(-) diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index d20b43a13ffc..da0e477b96a7 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1854,16 +1854,18 @@ static void unix_peek_fds(struct scm_cookie *scm, struct sk_buff *skb) static void unix_destruct_scm(struct sk_buff *skb) { - struct scm_cookie scm; + struct scm_cookie scm = {}; - memset(&scm, 0, sizeof(scm)); - scm.pid = UNIXCB(skb).pid; + swap(scm.pid, UNIXCB(skb).pid); if (UNIXCB(skb).fp) unix_detach_fds(&scm, skb); - /* Alas, it calls VFS */ - /* So fscking what? fput() had been SMP-safe since the last Summer */ scm_destroy(&scm); +} + +static void unix_wfree(struct sk_buff *skb) +{ + unix_destruct_scm(skb); sock_wfree(skb); } @@ -1879,7 +1881,7 @@ static int unix_scm_to_skb(struct scm_cookie *scm, struct sk_buff *skb, bool sen if (scm->fp && send_fds) err = unix_attach_fds(scm, skb); - skb->destructor = unix_destruct_scm; + skb->destructor = unix_wfree; return err; } @@ -1940,6 +1942,13 @@ static void scm_stat_del(struct sock *sk, struct sk_buff *skb) } } +static void unix_orphan_scm(struct sock *sk, struct sk_buff *skb) +{ + scm_stat_del(sk, skb); + unix_destruct_scm(skb); + skb->destructor = sock_wfree; +} + /* * Send AF_UNIX data. */ @@ -2517,9 +2526,14 @@ static int unix_read_skb(struct sock *sk, skb_read_actor_t recv_actor) mutex_lock(&u->iolock); skb = skb_recv_datagram(sk, MSG_DONTWAIT, &err); - mutex_unlock(&u->iolock); - if (!skb) + if (!skb) { + mutex_unlock(&u->iolock); return err; + } + + unix_orphan_scm(sk, skb); + + mutex_unlock(&u->iolock); return recv_actor(sk, skb); } @@ -2708,6 +2722,8 @@ static int unix_stream_read_skb(struct sock *sk, skb_read_actor_t recv_actor) } #endif + unix_orphan_scm(sk, skb); + return recv_actor(sk, skb); } -- 2.43.0

2 1

[PATCH OLK-5.10] bonding: 3ad: implement proper RCU rules for port->aggregator
by superdcc97＠163.com 04 Jul '26

04 Jul '26

From: Eric Dumazet <edumazet(a)google.com> mainline inclusion from mainline-v7.1-rc2 commit c4f050ce06c56cfb5993268af4a5cb66ed1cd04e category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/15677 CVE: CVE-2026-52975 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- syzbot found a data-race in bond_3ad_get_active_agg_info / bond_3ad_state_machine_handler [1] which hints at lack of proper RCU implementation. Add __rcu qualifier to port->aggregator, and add proper RCU API. [1] BUG: KCSAN: data-race in bond_3ad_get_active_agg_info / bond_3ad_state_machine_handler write to 0xffff88813cf5c4b0 of 8 bytes by task 36 on cpu 0: ad_port_selection_logic drivers/net/bonding/bond_3ad.c:1659 [inline] bond_3ad_state_machine_handler+0x9d5/0x2d60 drivers/net/bonding/bond_3ad.c:2569 process_one_work kernel/workqueue.c:3302 [inline] process_scheduled_works+0x4f0/0x9c0 kernel/workqueue.c:3385 worker_thread+0x58a/0x780 kernel/workqueue.c:3466 kthread+0x22a/0x280 kernel/kthread.c:436 ret_from_fork+0x146/0x330 arch/x86/kernel/process.c:158 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:245 read to 0xffff88813cf5c4b0 of 8 bytes by task 22063 on cpu 1: __bond_3ad_get_active_agg_info drivers/net/bonding/bond_3ad.c:2858 [inline] bond_3ad_get_active_agg_info+0x8c/0x230 drivers/net/bonding/bond_3ad.c:2881 bond_fill_info+0xe0f/0x10f0 drivers/net/bonding/bond_netlink.c:853 rtnl_link_info_fill net/core/rtnetlink.c:906 [inline] rtnl_link_fill+0x1d7/0x4e0 net/core/rtnetlink.c:927 rtnl_fill_ifinfo+0xf8e/0x1380 net/core/rtnetlink.c:2168 rtmsg_ifinfo_build_skb+0x11c/0x1b0 net/core/rtnetlink.c:4453 rtmsg_ifinfo_event net/core/rtnetlink.c:4486 [inline] rtmsg_ifinfo+0x6d/0x110 net/core/rtnetlink.c:4495 __dev_notify_flags+0x76/0x390 net/core/dev.c:9790 netif_change_flags+0xac/0xd0 net/core/dev.c:9823 do_setlink+0x905/0x2950 net/core/rtnetlink.c:3180 rtnl_group_changelink net/core/rtnetlink.c:3813 [inline] __rtnl_newlink net/core/rtnetlink.c:3981 [inline] rtnl_newlink+0xf55/0x1400 net/core/rtnetlink.c:4109 rtnetlink_rcv_msg+0x64b/0x720 net/core/rtnetlink.c:6995 netlink_rcv_skb+0x123/0x220 net/netlink/af_netlink.c:2550 rtnetlink_rcv+0x1c/0x30 net/core/rtnetlink.c:7022 netlink_unicast_kernel net/netlink/af_netlink.c:1318 [inline] netlink_unicast+0x5a8/0x680 net/netlink/af_netlink.c:1344 netlink_sendmsg+0x5c8/0x6f0 net/netlink/af_netlink.c:1894 sock_sendmsg_nosec net/socket.c:787 [inline] __sock_sendmsg net/socket.c:802 [inline] ____sys_sendmsg+0x563/0x5b0 net/socket.c:2698 ___sys_sendmsg+0x195/0x1e0 net/socket.c:2752 __sys_sendmsg net/socket.c:2784 [inline] __do_sys_sendmsg net/socket.c:2789 [inline] __se_sys_sendmsg net/socket.c:2787 [inline] __x64_sys_sendmsg+0xd4/0x160 net/socket.c:2787 x64_sys_call+0x194c/0x3020 arch/x86/include/generated/asm/syscalls_64.h:47 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0x12c/0x3b0 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x77/0x7f value changed: 0x0000000000000000 -> 0xffff88813cf5c400 Reported by Kernel Concurrency Sanitizer on: CPU: 1 UID: 0 PID: 22063 Comm: syz.0.31122 Tainted: G W syzkaller #0 PREEMPT(full) Tainted: [W]=WARN Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 04/18/2026 Fixes: 47e91f56008b ("bonding: use RCU protection for 3ad xmit path") Reported-by: syzbot+9bb2ff2a4ab9e17307e1(a)syzkaller.appspotmail.com Closes: https://lore.kernel.org/netdev/69f0a82f.050a0220.3aadc4.0000.GAE@google.com/ Signed-off-by: Eric Dumazet <edumazet(a)google.com> Cc: Jay Vosburgh <jv(a)jvosburgh.net> Cc: Andrew Lunn <andrew+netdev(a)lunn.ch> Link: https://patch.msgid.link/20260428123207.3809211-1-edumazet@google.com Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Conflicts: drivers/net/bonding/bond_3ad.c drivers/net/bonding/bond_netlink.c drivers/net/bonding/bond_procfs.c drivers/net/bonding/bond_sysfs_slave.c [commit 240fd405528b and 4440873f3655 are not backport, which lead to conflicts] Signed-off-by: Dong Chenchen <dongchenchen2(a)huawei.com> --- drivers/net/bonding/bond_3ad.c | 97 ++++++++++++++------------ drivers/net/bonding/bond_main.c | 8 ++- drivers/net/bonding/bond_netlink.c | 12 ++-- drivers/net/bonding/bond_procfs.c | 3 +- drivers/net/bonding/bond_sysfs_slave.c | 27 ++++--- include/net/bond_3ad.h | 2 +- 6 files changed, 83 insertions(+), 66 deletions(-) diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c index 7278f3d44a68..724c98247894 100644 --- a/drivers/net/bonding/bond_3ad.c +++ b/drivers/net/bonding/bond_3ad.c @@ -923,6 +923,7 @@ static int ad_marker_send(struct port *port, struct bond_marker *marker) */ static void ad_mux_machine(struct port *port, bool *update_slave_arr) { + struct aggregator *aggregator; mux_states_t last_state; /* keep current State Machine state to compare later if it was @@ -930,6 +931,7 @@ static void ad_mux_machine(struct port *port, bool *update_slave_arr) */ last_state = port->sm_mux_state; + aggregator = rcu_dereference(port->aggregator); if (port->sm_vars & AD_PORT_BEGIN) { port->sm_mux_state = AD_MUX_DETACHED; } else { @@ -949,7 +951,7 @@ static void ad_mux_machine(struct port *port, bool *update_slave_arr) * cycle to update ready variable, we check * READY_N and update READY here */ - __set_agg_ports_ready(port->aggregator, __agg_ports_are_ready(port->aggregator)); + __set_agg_ports_ready(aggregator, __agg_ports_are_ready(aggregator)); port->sm_mux_state = AD_MUX_DETACHED; break; } @@ -964,7 +966,7 @@ static void ad_mux_machine(struct port *port, bool *update_slave_arr) * update ready variable, we check READY_N and update * READY here */ - __set_agg_ports_ready(port->aggregator, __agg_ports_are_ready(port->aggregator)); + __set_agg_ports_ready(aggregator, __agg_ports_are_ready(aggregator)); /* if the wait_while_timer expired, and the port is * in READY state, move to ATTACHED state @@ -980,7 +982,7 @@ static void ad_mux_machine(struct port *port, bool *update_slave_arr) if ((port->sm_vars & AD_PORT_SELECTED) && (port->partner_oper.port_state & LACP_STATE_SYNCHRONIZATION) && !__check_agg_selection_timer(port)) { - if (port->aggregator->is_active) + if (aggregator->is_active) port->sm_mux_state = AD_MUX_COLLECTING_DISTRIBUTING; } else if (!(port->sm_vars & AD_PORT_SELECTED) || @@ -992,9 +994,9 @@ static void ad_mux_machine(struct port *port, bool *update_slave_arr) * cycle to update ready variable, we check * READY_N and update READY here */ - __set_agg_ports_ready(port->aggregator, __agg_ports_are_ready(port->aggregator)); + __set_agg_ports_ready(aggregator, __agg_ports_are_ready(aggregator)); port->sm_mux_state = AD_MUX_DETACHED; - } else if (port->aggregator->is_active) { + } else if (aggregator->is_active) { port->actor_oper_port_state |= LACP_STATE_SYNCHRONIZATION; } @@ -1010,8 +1012,8 @@ static void ad_mux_machine(struct port *port, bool *update_slave_arr) * sure that a collecting distributing * port in an active aggregator is enabled */ - if (port->aggregator && - port->aggregator->is_active && + if (aggregator && + aggregator->is_active && !__port_is_enabled(port)) { __enable_port(port); *update_slave_arr = true; @@ -1043,7 +1045,7 @@ static void ad_mux_machine(struct port *port, bool *update_slave_arr) port->sm_mux_timer_counter = __ad_timer_to_ticks(AD_WAIT_WHILE_TIMER, 0); break; case AD_MUX_ATTACHED: - if (port->aggregator->is_active) + if (aggregator->is_active) port->actor_oper_port_state |= LACP_STATE_SYNCHRONIZATION; else @@ -1397,9 +1399,9 @@ static void ad_port_selection_logic(struct port *port, bool *update_slave_arr) bond = __get_bond_by_port(port); /* if the port is connected to other aggregator, detach it */ - if (port->aggregator) { + temp_aggregator = rcu_dereference(port->aggregator); + if (temp_aggregator) { /* detach the port from its former aggregator */ - temp_aggregator = port->aggregator; for (curr_port = temp_aggregator->lag_ports; curr_port; last_port = curr_port, curr_port = curr_port->next_port_in_aggregator) { @@ -1422,7 +1424,7 @@ static void ad_port_selection_logic(struct port *port, bool *update_slave_arr) /* clear the port's relations to this * aggregator */ - port->aggregator = NULL; + RCU_INIT_POINTER(port->aggregator, NULL); port->next_port_in_aggregator = NULL; port->actor_port_aggregator_identifier = 0; @@ -1445,7 +1447,7 @@ static void ad_port_selection_logic(struct port *port, bool *update_slave_arr) port->slave->bond->dev->name, port->slave->dev->name, port->actor_port_number, - port->aggregator->aggregator_identifier); + temp_aggregator->aggregator_identifier); } } /* search on all aggregators for a suitable aggregator for this port */ @@ -1469,15 +1471,15 @@ static void ad_port_selection_logic(struct port *port, bool *update_slave_arr) ) ) { /* attach to the founded aggregator */ - port->aggregator = aggregator; + rcu_assign_pointer(port->aggregator, aggregator); port->actor_port_aggregator_identifier = - port->aggregator->aggregator_identifier; + aggregator->aggregator_identifier; port->next_port_in_aggregator = aggregator->lag_ports; - port->aggregator->num_of_ports++; + aggregator->num_of_ports++; aggregator->lag_ports = port; slave_dbg(bond->dev, slave->dev, "Port %d joined LAG %d (existing LAG)\n", port->actor_port_number, - port->aggregator->aggregator_identifier); + aggregator->aggregator_identifier); /* mark this port as selected */ port->sm_vars |= AD_PORT_SELECTED; @@ -1492,39 +1494,40 @@ static void ad_port_selection_logic(struct port *port, bool *update_slave_arr) if (!found) { if (free_aggregator) { /* assign port a new aggregator */ - port->aggregator = free_aggregator; port->actor_port_aggregator_identifier = - port->aggregator->aggregator_identifier; + free_aggregator->aggregator_identifier; /* update the new aggregator's parameters * if port was responsed from the end-user */ if (port->actor_oper_port_key & AD_DUPLEX_KEY_MASKS) /* if port is full duplex */ - port->aggregator->is_individual = false; + free_aggregator->is_individual = false; else - port->aggregator->is_individual = true; + free_aggregator->is_individual = true; - port->aggregator->actor_admin_aggregator_key = + free_aggregator->actor_admin_aggregator_key = port->actor_admin_port_key; - port->aggregator->actor_oper_aggregator_key = + free_aggregator->actor_oper_aggregator_key = port->actor_oper_port_key; - port->aggregator->partner_system = + free_aggregator->partner_system = port->partner_oper.system; - port->aggregator->partner_system_priority = + free_aggregator->partner_system_priority = port->partner_oper.system_priority; - port->aggregator->partner_oper_aggregator_key = port->partner_oper.key; - port->aggregator->receive_state = 1; - port->aggregator->transmit_state = 1; - port->aggregator->lag_ports = port; - port->aggregator->num_of_ports++; + free_aggregator->partner_oper_aggregator_key = port->partner_oper.key; + free_aggregator->receive_state = 1; + free_aggregator->transmit_state = 1; + free_aggregator->lag_ports = port; + free_aggregator->num_of_ports++; + + rcu_assign_pointer(port->aggregator, free_aggregator); /* mark this port as selected */ port->sm_vars |= AD_PORT_SELECTED; slave_dbg(bond->dev, port->slave->dev, "Port %d joined LAG %d (new LAG)\n", port->actor_port_number, - port->aggregator->aggregator_identifier); + free_aggregator->aggregator_identifier); } else { slave_err(bond->dev, port->slave->dev, "Port %d did not find a suitable aggregator\n", @@ -1536,13 +1539,12 @@ static void ad_port_selection_logic(struct port *port, bool *update_slave_arr) * in all aggregator's ports, else set ready=FALSE in all * aggregator's ports */ - __set_agg_ports_ready(port->aggregator, - __agg_ports_are_ready(port->aggregator)); + aggregator = rcu_dereference(port->aggregator); + __set_agg_ports_ready(aggregator, __agg_ports_are_ready(aggregator)); - aggregator = __get_first_agg(port); - ad_agg_selection_logic(aggregator, update_slave_arr); + ad_agg_selection_logic(__get_first_agg(port), update_slave_arr); - if (!port->aggregator->is_active) + if (!aggregator->is_active) port->actor_oper_port_state &= ~LACP_STATE_SYNCHRONIZATION; } @@ -1871,7 +1873,7 @@ static void ad_initialize_port(struct port *port, int lacp_fast) port->sm_mux_state = 0; port->sm_mux_timer_counter = 0; port->sm_tx_state = 0; - port->aggregator = NULL; + RCU_INIT_POINTER(port->aggregator, NULL); port->next_port_in_aggregator = NULL; port->transaction_id = 0; @@ -1896,11 +1898,13 @@ static void ad_initialize_port(struct port *port, int lacp_fast) static void ad_enable_collecting_distributing(struct port *port, bool *update_slave_arr) { - if (port->aggregator->is_active) { + struct aggregator *aggregator = rcu_dereference(port->aggregator); + + if (aggregator->is_active) { slave_dbg(port->slave->bond->dev, port->slave->dev, "Enabling port %d (LAG %d)\n", port->actor_port_number, - port->aggregator->aggregator_identifier); + aggregator->aggregator_identifier); __enable_port(port); /* Slave array needs update */ *update_slave_arr = true; @@ -1915,13 +1919,13 @@ static void ad_enable_collecting_distributing(struct port *port, static void ad_disable_collecting_distributing(struct port *port, bool *update_slave_arr) { - if (port->aggregator && - !MAC_ADDRESS_EQUAL(&(port->aggregator->partner_system), - &(null_mac_addr))) { + struct aggregator *aggregator = rcu_dereference(port->aggregator); + + if (aggregator && __agg_has_partner(aggregator)) { slave_dbg(port->slave->bond->dev, port->slave->dev, "Disabling port %d (LAG %d)\n", port->actor_port_number, - port->aggregator->aggregator_identifier); + aggregator->aggregator_identifier); __disable_port(port); /* Slave array needs an update */ *update_slave_arr = true; @@ -2164,7 +2168,7 @@ void bond_3ad_unbind_slave(struct slave *slave) */ for (temp_port = aggregator->lag_ports; temp_port; temp_port = temp_port->next_port_in_aggregator) { - temp_port->aggregator = new_aggregator; + rcu_assign_pointer(temp_port->aggregator, new_aggregator); temp_port->actor_port_aggregator_identifier = new_aggregator->aggregator_identifier; } @@ -2633,15 +2637,16 @@ int bond_3ad_set_carrier(struct bonding *bond) int __bond_3ad_get_active_agg_info(struct bonding *bond, struct ad_info *ad_info) { - struct aggregator *aggregator = NULL; + struct aggregator *aggregator = NULL, *tmp; struct list_head *iter; struct slave *slave; struct port *port; bond_for_each_slave_rcu(bond, slave, iter) { port = &(SLAVE_AD_INFO(slave)->port); - if (port->aggregator && port->aggregator->is_active) { - aggregator = port->aggregator; + tmp = rcu_dereference(port->aggregator); + if (tmp && tmp->is_active) { + aggregator = tmp; break; } } diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index c6e625ef6d34..2ba313997dbb 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1282,7 +1282,7 @@ static void bond_poll_controller(struct net_device *bond_dev) if (BOND_MODE(bond) == BOND_MODE_8023AD) { struct aggregator *agg = - SLAVE_AD_INFO(slave)->port.aggregator; + rcu_dereference(SLAVE_AD_INFO(slave)->port.aggregator); if (agg && agg->aggregator_identifier != ad_info.aggregator_id) @@ -4712,15 +4712,16 @@ int bond_update_slave_arr(struct bonding *bond, struct slave *skipslave) spin_unlock_bh(&bond->mode_lock); agg_id = ad_info.aggregator_id; } + rcu_read_lock(); bond_for_each_slave(bond, slave, iter) { if (skipslave == slave) continue; all_slaves->arr[all_slaves->count++] = slave; if (BOND_MODE(bond) == BOND_MODE_8023AD) { - struct aggregator *agg; + const struct aggregator *agg; - agg = SLAVE_AD_INFO(slave)->port.aggregator; + agg = rcu_dereference(SLAVE_AD_INFO(slave)->port.aggregator); if (!agg || agg->aggregator_identifier != agg_id) continue; } @@ -4732,6 +4733,7 @@ int bond_update_slave_arr(struct bonding *bond, struct slave *skipslave) usable_slaves->arr[usable_slaves->count++] = slave; } + rcu_read_unlock(); bond_set_slave_arr(bond, usable_slaves, all_slaves); return ret; diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c index f0f9138e967f..a53fbf6035ed 100644 --- a/drivers/net/bonding/bond_netlink.c +++ b/drivers/net/bonding/bond_netlink.c @@ -57,24 +57,28 @@ static int bond_fill_slave_info(struct sk_buff *skb, const struct port *ad_port; ad_port = &SLAVE_AD_INFO(slave)->port; - agg = SLAVE_AD_INFO(slave)->port.aggregator; + rcu_read_lock(); + agg = rcu_dereference(SLAVE_AD_INFO(slave)->port.aggregator); if (agg) { if (nla_put_u16(skb, IFLA_BOND_SLAVE_AD_AGGREGATOR_ID, agg->aggregator_identifier)) - goto nla_put_failure; + goto nla_put_failure_rcu; if (nla_put_u8(skb, IFLA_BOND_SLAVE_AD_ACTOR_OPER_PORT_STATE, ad_port->actor_oper_port_state)) - goto nla_put_failure; + goto nla_put_failure_rcu; if (nla_put_u16(skb, IFLA_BOND_SLAVE_AD_PARTNER_OPER_PORT_STATE, ad_port->partner_oper.port_state)) - goto nla_put_failure; + goto nla_put_failure_rcu; } + rcu_read_unlock(); } return 0; +nla_put_failure_rcu: + rcu_read_unlock(); nla_put_failure: return -EMSGSIZE; } diff --git a/drivers/net/bonding/bond_procfs.c b/drivers/net/bonding/bond_procfs.c index fd5c9cbe45b1..0b22785bacbf 100644 --- a/drivers/net/bonding/bond_procfs.c +++ b/drivers/net/bonding/bond_procfs.c @@ -166,6 +166,7 @@ static void bond_info_show_master(struct seq_file *seq) } } +/* Note: runs under rcu_read_lock() */ static void bond_info_show_slave(struct seq_file *seq, const struct slave *slave) { @@ -192,7 +193,7 @@ static void bond_info_show_slave(struct seq_file *seq, if (BOND_MODE(bond) == BOND_MODE_8023AD) { const struct port *port = &SLAVE_AD_INFO(slave)->port; - const struct aggregator *agg = port->aggregator; + const struct aggregator *agg = rcu_dereference(port->aggregator); if (agg) { seq_printf(seq, "Aggregator ID: %d\n", diff --git a/drivers/net/bonding/bond_sysfs_slave.c b/drivers/net/bonding/bond_sysfs_slave.c index 6a6cdd0bb258..d11a7b3ca335 100644 --- a/drivers/net/bonding/bond_sysfs_slave.c +++ b/drivers/net/bonding/bond_sysfs_slave.c @@ -68,13 +68,18 @@ static ssize_t ad_aggregator_id_show(struct slave *slave, char *buf) const struct aggregator *agg; if (BOND_MODE(slave->bond) == BOND_MODE_8023AD) { - agg = SLAVE_AD_INFO(slave)->port.aggregator; - if (agg) - return sprintf(buf, "%d\n", - agg->aggregator_identifier); + rcu_read_lock(); + agg = rcu_dereference(SLAVE_AD_INFO(slave)->port.aggregator); + if (agg) { + ssize_t res = sysfs_emit(buf, "%d\n", + agg->aggregator_identifier); + rcu_read_unlock(); + return res; + } + rcu_read_unlock(); } - return sprintf(buf, "N/A\n"); + return sysfs_emit(buf, "N/A\n"); } static SLAVE_ATTR_RO(ad_aggregator_id); @@ -84,12 +89,12 @@ static ssize_t ad_actor_oper_port_state_show(struct slave *slave, char *buf) if (BOND_MODE(slave->bond) == BOND_MODE_8023AD) { ad_port = &SLAVE_AD_INFO(slave)->port; - if (ad_port->aggregator) - return sprintf(buf, "%u\n", + if (rcu_access_pointer(ad_port->aggregator)) + return sysfs_emit(buf, "%u\n", ad_port->actor_oper_port_state); } - return sprintf(buf, "N/A\n"); + return sysfs_emit(buf, "N/A\n"); } static SLAVE_ATTR_RO(ad_actor_oper_port_state); @@ -99,12 +104,12 @@ static ssize_t ad_partner_oper_port_state_show(struct slave *slave, char *buf) if (BOND_MODE(slave->bond) == BOND_MODE_8023AD) { ad_port = &SLAVE_AD_INFO(slave)->port; - if (ad_port->aggregator) - return sprintf(buf, "%u\n", + if (rcu_access_pointer(ad_port->aggregator)) + return sysfs_emit(buf, "%u\n", ad_port->partner_oper.port_state); } - return sprintf(buf, "N/A\n"); + return sysfs_emit(buf, "N/A\n"); } static SLAVE_ATTR_RO(ad_partner_oper_port_state); diff --git a/include/net/bond_3ad.h b/include/net/bond_3ad.h index 895eae18271f..f9b2855753c7 100644 --- a/include/net/bond_3ad.h +++ b/include/net/bond_3ad.h @@ -237,7 +237,7 @@ typedef struct port { churn_state_t sm_churn_actor_state; churn_state_t sm_churn_partner_state; struct slave *slave; /* pointer to the bond slave that this port belongs to */ - struct aggregator *aggregator; /* pointer to an aggregator that this port related to */ + struct aggregator __rcu *aggregator; /* pointer to an aggregator that this port related to */ struct port *next_port_in_aggregator; /* Next port on the linked list of the parent aggregator */ u32 transaction_id; /* continuous number for identification of Marker PDU's; */ struct lacpdu lacpdu; /* the lacpdu that will be sent for this port */ -- 2.43.0

2 1

[PATCH OLK-5.10] bpf: Free reuseport cBPF prog after RCU grace period.
by superdcc97＠163.com 04 Jul '26

04 Jul '26

From: Kuniyuki Iwashima <kuniyu(a)google.com> stable inclusion from stable-v5.10.259 commit 08264d5bba0bdd3a79bc2984fee09286aba0c4eb category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/15607 CVE: CVE-2026-52910 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 18fc650ccd7fe3376eca89203668cfb8268f60df ] Eulgyu Kim reported the splat below with a repro. [0] The repro sets up a UDP reuseport group with a cBPF prog and replaces it with a new one while another thread is sending a UDP packet to the group. The reuseport prog is freed by sk_reuseport_prog_free(). bpf_prog_put() is called for "e"BPF prog to destruct through multiple stages while cBPF prog is freed immediately by bpf_release_orig_filter() and bpf_prog_free(). If a reuseport prog is detached from the setsockopt() path (reuseport_attach_prog() or reuseport_detach_prog()), sk_reuseport_prog_free() is called without waiting for RCU readers to complete, resulting in various bugs. Let's defer freeing the reuseport cBPF prog after one RCU grace period. Note "e"BPF prog is safe as is unless the fast path starts to touch fields destroyed in bpf_prog_put_deferred() and __bpf_prog_put_noref(). [0]: BUG: KASAN: vmalloc-out-of-bounds in reuseport_select_sock+0xedc/0x1220 net/core/sock_reuseport.c:596 Read of size 4 at addr ffffc9000051e004 by task slowme/10208 CPU: 6 UID: 1000 PID: 10208 Comm: slowme Not tainted 7.0.0-geb7ac95ff75e #32 PREEMPT(full) Hardware name: QEMU Ubuntu 24.04 PC v2 (i440FX + PIIX, arch_caps fix, 1996), BIOS 1.16.3-debian-1.16.3-2 04/01/2014 Call Trace: <IRQ> dump_stack_lvl+0xe8/0x150 lib/dump_stack.c:120 print_address_description mm/kasan/report.c:378 [inline] print_report+0xca/0x240 mm/kasan/report.c:482 kasan_report+0x118/0x150 mm/kasan/report.c:595 reuseport_select_sock+0xedc/0x1220 net/core/sock_reuseport.c:596 udp4_lib_lookup2+0x3bc/0x950 net/ipv4/udp.c:495 __udp4_lib_lookup+0x768/0xe20 net/ipv4/udp.c:723 __udp4_lib_lookup_skb+0x297/0x390 net/ipv4/udp.c:752 __udp4_lib_rcv+0x1312/0x2620 net/ipv4/udp.c:2752 ip_protocol_deliver_rcu+0x282/0x440 net/ipv4/ip_input.c:207 ip_local_deliver_finish+0x3bb/0x6f0 net/ipv4/ip_input.c:241 NF_HOOK+0x30c/0x3a0 include/linux/netfilter.h:318 NF_HOOK+0x30c/0x3a0 include/linux/netfilter.h:318 __netif_receive_skb_one_core net/core/dev.c:6181 [inline] __netif_receive_skb net/core/dev.c:6294 [inline] process_backlog+0xaa4/0x1960 net/core/dev.c:6645 __napi_poll+0xae/0x340 net/core/dev.c:7709 napi_poll net/core/dev.c:7772 [inline] net_rx_action+0x5d7/0xf50 net/core/dev.c:7929 handle_softirqs+0x22b/0x870 kernel/softirq.c:622 do_softirq+0x76/0xd0 kernel/softirq.c:523 </IRQ> <TASK> __local_bh_enable_ip+0xf8/0x130 kernel/softirq.c:450 local_bh_enable include/linux/bottom_half.h:33 [inline] rcu_read_unlock_bh include/linux/rcupdate.h:924 [inline] __dev_queue_xmit+0x1dd7/0x3710 net/core/dev.c:4890 neigh_output include/net/neighbour.h:556 [inline] ip_finish_output2+0xca9/0x1070 net/ipv4/ip_output.c:237 NF_HOOK_COND include/linux/netfilter.h:307 [inline] ip_output+0x29f/0x450 net/ipv4/ip_output.c:438 ip_send_skb+0x45/0xc0 net/ipv4/ip_output.c:1508 udp_send_skb+0xb04/0x1510 net/ipv4/udp.c:1195 udp_sendmsg+0x1a71/0x2350 net/ipv4/udp.c:1485 sock_sendmsg_nosec net/socket.c:727 [inline] __sock_sendmsg net/socket.c:742 [inline] __sys_sendto+0x554/0x680 net/socket.c:2206 __do_sys_sendto net/socket.c:2213 [inline] __se_sys_sendto net/socket.c:2209 [inline] __x64_sys_sendto+0xde/0x100 net/socket.c:2209 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0x160/0xf80 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x415a2d Code: b3 66 2e 0f 1f 84 00 00 00 00 00 66 90 f3 0f 1e fa 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 b8 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007f6bc31e41e8 EFLAGS: 00000212 ORIG_RAX: 000000000000002c RAX: ffffffffffffffda RBX: 00007f6bc31e4cdc RCX: 0000000000415a2d RDX: 0000000000000001 RSI: 00007f6bc31e421f RDI: 0000000000000003 RBP: 00007f6bc31e4240 R08: 00007f6bc31e4220 R09: 0000000000000010 R10: 0000000000000000 R11: 0000000000000212 R12: 00007f6bc31e46c0 R13: ffffffffffffffb8 R14: 0000000000000000 R15: 00007ffc9b0d70b0 </TASK> Fixes: 538950a1b752 ("soreuseport: setsockopt SO_ATTACH_REUSEPORT_[CE]BPF") Reported-by: Eulgyu Kim <eulgyukim(a)snu.ac.kr> Reported-by: Taeyang Lee <0wn(a)theori.io> Signed-off-by: Kuniyuki Iwashima <kuniyu(a)google.com> Signed-off-by: Daniel Borkmann <daniel(a)iogearbox.net> Acked-by: Daniel Borkmann <daniel(a)iogearbox.net> Link: https://lore.kernel.org/bpf/20260426012647.3233119-1-kuniyu@google.com Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Dong Chenchen <dongchenchen2(a)huawei.com> --- net/core/filter.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) diff --git a/net/core/filter.c b/net/core/filter.c index e28857036d90..4587692710fc 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1629,15 +1629,24 @@ int sk_reuseport_attach_bpf(u32 ufd, struct sock *sk) return err; } +static void sk_reuseport_prog_free_rcu(struct rcu_head *rcu) +{ + struct bpf_prog_aux *aux = container_of(rcu, struct bpf_prog_aux, rcu); + struct bpf_prog *prog = aux->prog; + + bpf_release_orig_filter(prog); + bpf_prog_free(prog); +} + void sk_reuseport_prog_free(struct bpf_prog *prog) { if (!prog) return; - if (prog->type == BPF_PROG_TYPE_SK_REUSEPORT) - bpf_prog_put(prog); + if (bpf_prog_was_classic(prog)) + call_rcu(&prog->aux->rcu, sk_reuseport_prog_free_rcu); else - bpf_prog_destroy(prog); + bpf_prog_put(prog); } struct bpf_scratchpad { -- 2.43.0

2 1

[PATCH OLK-5.10] netfilter: nf_tables: use list_del_rcu for netlink hooks
by superdcc97＠163.com 04 Jul '26

04 Jul '26

From: Dong Chenchen <dongchenchen2(a)huawei.com> mainline inclusion from mainline-v7.1-rc2 commit f3224ee463f8f6f6ced7dcdf6081add4f8128527 category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/15588 CVE: CVE-2026-46324 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- nft_netdev_unregister_hooks and __nft_unregister_flowtable_net_hooks need to use list_del_rcu(), this list can be walked by concurrent dumpers. Add a new helper and use it consistently. Fixes: f9a43007d3f7 ("netfilter: nf_tables: double hook unregistration in netns path") Signed-off-by: Florian Westphal <fw(a)strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo(a)netfilter.org> Conflicts: net/netfilter/nf_tables_api.c [1.The nf_tables_updchain() hook-list teardown path present in mainline (where hook.list lives on the stack and uses list_del() / nft_netdev_hook_free_rcu()) does not exist in OLK-5.10, so that hunk was skipped. 2. nf_tables_flowtable_destroy() in OLK-5.10 still performs flowtable->data.type->setup(..., FLOW_BLOCK_UNBIND) for each hook before removing it, a pattern that was refactored out upstream; the helper replacement from mainline therefore could not be used here. The existing list_del_rcu() call is retained, and the immediate kfree(hook) was changed to kfree_rcu(hook, rcu) to match the RCU-safe freeing used by the new helper. 3. Other hunks were applied manually by introducing the nft_netdev_hook_unlink_free_rcu() helper and using it consistently wherever OLK-5.10 already performed list_del_rcu()/kfree_rcu() on a netdev/flowtable hook, and by converting the two list_del() callers (nft_netdev_unregister_hooks and __nft_unregister_flowtable_net_hooks) to list_del_rcu() as required by the CVE fix. ] Signed-off-by: Dong Chenchen <dongchenchen2(a)huawei.com> --- net/netfilter/nf_tables_api.c | 38 ++++++++++++++++------------------- 1 file changed, 17 insertions(+), 21 deletions(-) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 2beef989cced..b97c4d0cf1d9 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -303,6 +303,12 @@ static int nft_netdev_register_hooks(struct net *net, return err; } +static void nft_netdev_hook_unlink_free_rcu(struct nft_hook *hook) +{ + list_del_rcu(&hook->list); + kfree_rcu(hook, rcu); +} + static void nft_netdev_unregister_hooks(struct net *net, struct list_head *hook_list, bool release_netdev) @@ -311,10 +317,8 @@ static void nft_netdev_unregister_hooks(struct net *net, list_for_each_entry_safe(hook, next, hook_list, list) { nf_unregister_net_hook(net, &hook->ops); - if (release_netdev) { - list_del(&hook->list); - kfree_rcu(hook, rcu); - } + if (release_netdev) + nft_netdev_hook_unlink_free_rcu(hook); } } @@ -1932,10 +1936,8 @@ void nf_tables_chain_destroy(struct nft_ctx *ctx) if (nft_base_chain_netdev(ctx->family, basechain->ops.hooknum)) { list_for_each_entry_safe(hook, next, - &basechain->hook_list, list) { - list_del_rcu(&hook->list); - kfree_rcu(hook, rcu); - } + &basechain->hook_list, list) + nft_netdev_hook_unlink_free_rcu(hook); } module_put(basechain->type->owner); if (rcu_access_pointer(basechain->stats)) { @@ -7004,10 +7006,8 @@ static void __nft_unregister_flowtable_net_hooks(struct net *net, list_for_each_entry_safe(hook, next, hook_list, list) { nf_unregister_net_hook(net, &hook->ops); - if (release_netdev) { - list_del(&hook->list); - kfree_rcu(hook, rcu); - } + if (release_netdev) + nft_netdev_hook_unlink_free_rcu(hook); } } @@ -7065,8 +7065,7 @@ static int nft_register_flowtable_net_hooks(struct net *net, break; nft_unregister_flowtable_hook(net, flowtable, hook); - list_del_rcu(&hook->list); - kfree_rcu(hook, rcu); + nft_netdev_hook_unlink_free_rcu(hook); } return err; @@ -7076,10 +7075,8 @@ static void nft_flowtable_hooks_destroy(struct list_head *hook_list) { struct nft_hook *hook, *next; - list_for_each_entry_safe(hook, next, hook_list, list) { - list_del_rcu(&hook->list); - kfree_rcu(hook, rcu); - } + list_for_each_entry_safe(hook, next, hook_list, list) + nft_netdev_hook_unlink_free_rcu(hook); } static int nft_flowtable_update(struct nft_ctx *ctx, const struct nlmsghdr *nlh, @@ -7147,8 +7144,7 @@ static int nft_flowtable_update(struct nft_ctx *ctx, const struct nlmsghdr *nlh, list_for_each_entry_safe(hook, next, &flowtable_hook.list, list) { if (unregister) nft_unregister_flowtable_hook(ctx->net, flowtable, hook); - list_del_rcu(&hook->list); - kfree_rcu(hook, rcu); + nft_netdev_hook_unlink_free_rcu(hook); } return err; @@ -7639,7 +7635,7 @@ static void nf_tables_flowtable_destroy(struct nft_flowtable *flowtable) flowtable->data.type->setup(&flowtable->data, hook->ops.dev, FLOW_BLOCK_UNBIND); list_del_rcu(&hook->list); - kfree(hook); + kfree_rcu(hook, rcu); } kfree(flowtable->name); module_put(flowtable->data.type->owner); -- 2.43.0

2 1