From c9c9b37f8c5505224e8d206184df3bb668ee00cf Mon Sep 17 00:00:00 2001 From: Haoze Xie Date: Mon, 8 Jun 2026 13:43:44 +0800 Subject: netfilter: nf_queue: pin bridge device while NFQUEUE holds fake dst The br_netfilter fake rtable is embedded in struct net_bridge and is attached to bridged packets with skb_dst_set_noref(). If such a packet is queued to NFQUEUE, __nf_queue() upgrades that fake dst with skb_dst_force(). At that point the queued skb can hold a real dst reference after bridge teardown has started. The problem is not that every bridged packet needs its own dst reference. The problem is that NFQUEUE can keep the bridge private fake dst alive after unregister begins. Fix this by keeping the bridge fake dst model unchanged and pinning the bridge master device only while the packet sits in NFQUEUE. Record the bridge device in nf_queue_entry when the queued skb carries a bridge fake dst, take a device reference for the queue lifetime, and drop it when the queue entry is freed. Also make sure queued entries are reaped when that bridge device goes down, and drop the redundant nf_bridge_info_exists() test from the fake dst detection. This keeps netdev_priv(br->dev) alive until verdict completion, so the embedded fake rtable and its metrics backing storage cannot be freed out from under dst_release(). It also avoids the constant refcount bump and avoids using ipv4-specific dst helpers for IPv6 bridge traffic. Fixes: 34666d467cbf ("netfilter: bridge: move br_netfilter out of the core") Cc: stable@kernel.org Reported-by: Yuan Tan Reported-by: Yifan Wu Reported-by: Juefei Pu Reported-by: Xin Liu Signed-off-by: Haoze Xie Signed-off-by: Ren Wei Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_queue.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/netfilter/nf_queue.h b/include/net/netfilter/nf_queue.h index 3978c3174cdb..fc3e81c07364 100644 --- a/include/net/netfilter/nf_queue.h +++ b/include/net/netfilter/nf_queue.h @@ -18,6 +18,7 @@ struct nf_queue_entry { unsigned int id; unsigned int hook_index; /* index in hook_entries->hook[] */ #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) + struct net_device *bridge_dev; struct net_device *physin; struct net_device *physout; #endif -- cgit v1.2.3 From bff1c8b49a9cb5c04af20f4e7d43bf4af5863bc6 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 18 Jun 2026 08:16:18 +0200 Subject: netfilter: nft_meta_bridge: add validate callback for get operations Blamed commit added NFT_META_BRI_IIFHWADDR to the set validate callback, yet this is a get operation. Add a get validate callback and move the NFT_META_BRI_IIFHWADDR key there. AFAICS this is harmless, NFT_META_BRI_IIFHWADDR can deal with a NULL input device and the set handler ignores a NFT_META_BRI_IIFHWADDR operation, but it allows to read 4 bytes off bridge skb->cb[]. Fixes: cbd2257dc96e ("netfilter: nft_meta_bridge: introduce NFT_META_BRI_IIFHWADDR support") Signed-off-by: Florian Westphal Reviewed-by: Fernando Fernandez Mancera Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nft_meta.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/netfilter/nft_meta.h b/include/net/netfilter/nft_meta.h index f74e63290603..6cf1d910bbf8 100644 --- a/include/net/netfilter/nft_meta.h +++ b/include/net/netfilter/nft_meta.h @@ -40,6 +40,8 @@ void nft_meta_set_eval(const struct nft_expr *expr, void nft_meta_set_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr); +int nft_meta_get_validate(const struct nft_ctx *ctx, + const struct nft_expr *expr); int nft_meta_set_validate(const struct nft_ctx *ctx, const struct nft_expr *expr); -- cgit v1.2.3 From b8b09dc2bf35a00d4e0556b5d6308c7b917ebda2 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Thu, 18 Jun 2026 13:56:38 +0200 Subject: netfilter: nf_conntrack_expect: use conntrack GC to reap expectations This patch replaces the timer API by GC worker approach for expectations, as it already happened in many other subsystems. Use the existing conntrack GC worker to iterate over the local list of expectations in the master conntrack to reap expired expectations. Check IPS_HELPER_BIT to run GC for expectations, set it on for nft_ct expectation which nevers sets it. Hold the expectation spinlock while iterating over the master conntrack expectation list to synchronize with nf_ct_remove_expectations(). This also performs runtime packet path garbage collection through the expectation insertion and lookup functions while walking over one of the chains of the global expectation hashtables. Unconfirmed conntrack entries are skipped since ct->ext can be reallocated and dying are skipped since those will be gone soon. Set on IPS_HELPER_BIT if the helper ct extension is added, then the new GC worker does not need to bump the ct refcount to check if the ct->ext helper is available. This removes the extra bump on the refcount for expectation timers, this allows to remove several nf_ct_expect_put() calls after the unlink, after this update only refcount remains at 1 while on the expectation hashes. This patch implicitly addresses a race with the existing timer API allowing an expectation to access a stale exp->master pointer which has been already released when expectation removal loses races with an expiring timer, ie. timer_del() reporting false. Add a new NF_CT_EXPECT_DEAD flag to reap this expectation via GC. This is needed by nf_conntrack_unexpect_related() which is called in error paths to invalidate newly created expectations that has been added into the hashes. These expectactions cannot be inmediately released as GC or nf_ct_remove_expectations() could race to make it. On expectation insert, the runtime GC reaps stale expectations before checking the expectation limit set by policy. Set current timestamp in nf_ct_expect_alloc(), then add the expectation policy timeout (or custom timeout specified added on top of this) to specify the expectation lifetime. Fixes: bffcaad9afdf ("netfilter: ctnetlink: ensure safe access to master conntrack") Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_expect.h | 16 +++++++++++++--- include/uapi/linux/netfilter/nf_conntrack_common.h | 1 + 2 files changed, 14 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_expect.h b/include/net/netfilter/nf_conntrack_expect.h index 80f50fd0f7ad..be4a120d549e 100644 --- a/include/net/netfilter/nf_conntrack_expect.h +++ b/include/net/netfilter/nf_conntrack_expect.h @@ -54,8 +54,8 @@ struct nf_conntrack_expect { /* The conntrack of the master connection */ struct nf_conn *master; - /* Timer function; deletes the expectation. */ - struct timer_list timeout; + /* jiffies32 when this expectation expires */ + u32 timeout; #if IS_ENABLED(CONFIG_NF_NAT) union nf_inet_addr saved_addr; @@ -69,6 +69,14 @@ struct nf_conntrack_expect { struct rcu_head rcu; }; +static inline bool nf_ct_exp_is_expired(const struct nf_conntrack_expect *exp) +{ + if (READ_ONCE(exp->flags) & NF_CT_EXPECT_DEAD) + return true; + + return (__s32)(READ_ONCE(exp->timeout) - nfct_time_stamp) <= 0; +} + static inline struct net *nf_ct_exp_net(struct nf_conntrack_expect *exp) { return read_pnet(&exp->net); @@ -130,7 +138,6 @@ static inline void nf_ct_unlink_expect(struct nf_conntrack_expect *exp) void nf_ct_remove_expectations(struct nf_conn *ct); void nf_ct_unexpect_related(struct nf_conntrack_expect *exp); -bool nf_ct_remove_expect(struct nf_conntrack_expect *exp); void nf_ct_expect_iterate_destroy(bool (*iter)(struct nf_conntrack_expect *e, void *data), void *data); void nf_ct_expect_iterate_net(struct net *net, @@ -153,5 +160,8 @@ static inline int nf_ct_expect_related(struct nf_conntrack_expect *expect, return nf_ct_expect_related_report(expect, 0, 0, flags); } +struct nf_conn_help; +void nf_ct_expectation_gc(struct nf_conn_help *master_help); + #endif /*_NF_CONNTRACK_EXPECT_H*/ diff --git a/include/uapi/linux/netfilter/nf_conntrack_common.h b/include/uapi/linux/netfilter/nf_conntrack_common.h index 56b6b60a814f..ee51045ae1d6 100644 --- a/include/uapi/linux/netfilter/nf_conntrack_common.h +++ b/include/uapi/linux/netfilter/nf_conntrack_common.h @@ -160,6 +160,7 @@ enum ip_conntrack_expect_events { #define NF_CT_EXPECT_USERSPACE 0x4 #ifdef __KERNEL__ +#define NF_CT_EXPECT_DEAD 0x8 #define NF_CT_EXPECT_MASK (NF_CT_EXPECT_PERMANENT | NF_CT_EXPECT_INACTIVE | \ NF_CT_EXPECT_USERSPACE) #endif -- cgit v1.2.3