Merge: netfilter: stable backport for 9.8 phase 2

CKI KWF Bot · CKI KWF Bot · commit e93c2615d75d · 2025-10-23T14:16:40.000Z
MR: https://gitlab.com/redhat/centos-stream/src/kernel/centos-stream-9/-/merge_requests/7424 JIRA: https://issues.redhat.com/browse/RHEL-115630 This series backports bug fixes from upstream. Signed-off-by: Florian Westphal <fwestpha@redhat.com> Approved-by: Murphy Zhou <xzhou@redhat.com> Approved-by: Phil Sutter <psutter@redhat.com> Approved-by: CKI KWF Bot <cki-ci-bot+kwf-gitlab-com@redhat.com> Merged-by: CKI GitLab Kmaint Pipeline Bot <26919896-cki-kmaint-pipeline-bot@users.noreply.gitlab.com>
diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h
@@ -353,7 +353,7 @@ static inline __be16 __nf_flow_pppoe_proto(const struct sk_buff *skb)
 
 static inline bool nf_flow_pppoe_proto(struct sk_buff *skb, __be16 *inner_proto)
 {
-	if (!pskb_may_pull(skb, PPPOE_SES_HLEN))
+	if (!pskb_may_pull(skb, ETH_HLEN + PPPOE_SES_HLEN))
 		return false;
 
 	*inner_proto = __nf_flow_pppoe_proto(skb);
diff --git a/net/bridge/netfilter/nf_conntrack_bridge.c b/net/bridge/netfilter/nf_conntrack_bridge.c
@@ -60,19 +60,19 @@ static int nf_br_ip_fragment(struct net *net, struct sock *sk,
 		struct ip_fraglist_iter iter;
 		struct sk_buff *frag;
 
-		if (first_len - hlen > mtu ||
-		    skb_headroom(skb) < ll_rs)
+		if (first_len - hlen > mtu)
 			goto blackhole;
 
-		if (skb_cloned(skb))
+		if (skb_cloned(skb) ||
+		    skb_headroom(skb) < ll_rs)
 			goto slow_path;
 
 		skb_walk_frags(skb, frag) {
-			if (frag->len > mtu ||
-			    skb_headroom(frag) < hlen + ll_rs)
+			if (frag->len > mtu)
 				goto blackhole;
 
-			if (skb_shared(frag))
+			if (skb_shared(frag) ||
+			    skb_headroom(frag) < hlen + ll_rs)
 				goto slow_path;
 		}
 
diff --git a/net/ipv4/netfilter/nf_reject_ipv4.c b/net/ipv4/netfilter/nf_reject_ipv4.c
@@ -245,8 +245,7 @@ void nf_send_reset(struct net *net, struct sock *sk, struct sk_buff *oldskb,
 	if (!oth)
 		return;
 
-	if ((hook == NF_INET_PRE_ROUTING || hook == NF_INET_INGRESS) &&
-	    nf_reject_fill_skb_dst(oldskb) < 0)
+	if (!skb_dst(oldskb) && nf_reject_fill_skb_dst(oldskb) < 0)
 		return;
 
 	if (skb_rtable(oldskb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST))
@@ -317,8 +316,7 @@ void nf_send_unreach(struct sk_buff *skb_in, int code, int hook)
 	if (iph->frag_off & htons(IP_OFFSET))
 		return;
 
-	if ((hook == NF_INET_PRE_ROUTING || hook == NF_INET_INGRESS) &&
-	    nf_reject_fill_skb_dst(skb_in) < 0)
+	if (!skb_dst(skb_in) && nf_reject_fill_skb_dst(skb_in) < 0)
 		return;
 
 	if (skb_csum_unnecessary(skb_in) || !nf_reject_verify_csum(proto)) {
diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c
@@ -164,20 +164,20 @@ int br_ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 		struct ip6_fraglist_iter iter;
 		struct sk_buff *frag2;
 
-		if (first_len - hlen > mtu ||
-		    skb_headroom(skb) < (hroom + sizeof(struct frag_hdr)))
+		if (first_len - hlen > mtu)
 			goto blackhole;
 
-		if (skb_cloned(skb))
+		if (skb_cloned(skb) ||
+		    skb_headroom(skb) < (hroom + sizeof(struct frag_hdr)))
 			goto slow_path;
 
 		skb_walk_frags(skb, frag2) {
-			if (frag2->len > mtu ||
-			    skb_headroom(frag2) < (hlen + hroom + sizeof(struct frag_hdr)))
+			if (frag2->len > mtu)
 				goto blackhole;
 
 			/* Partially cloned skb? */
-			if (skb_shared(frag2))
+			if (skb_shared(frag2) ||
+			    skb_headroom(frag2) < (hlen + hroom + sizeof(struct frag_hdr)))
 				goto slow_path;
 		}
 
diff --git a/net/ipv6/netfilter/nf_reject_ipv6.c b/net/ipv6/netfilter/nf_reject_ipv6.c
@@ -293,7 +293,7 @@ void nf_send_reset6(struct net *net, struct sock *sk, struct sk_buff *oldskb,
 	fl6.fl6_sport = otcph->dest;
 	fl6.fl6_dport = otcph->source;
 
-	if (hook == NF_INET_PRE_ROUTING || hook == NF_INET_INGRESS) {
+	if (!skb_dst(oldskb)) {
 		nf_ip6_route(net, &dst, flowi6_to_flowi(&fl6), false);
 		if (!dst)
 			return;
@@ -396,8 +396,7 @@ void nf_send_unreach6(struct net *net, struct sk_buff *skb_in,
 	if (hooknum == NF_INET_LOCAL_OUT && skb_in->dev == NULL)
 		skb_in->dev = net->loopback_dev;
 
-	if ((hooknum == NF_INET_PRE_ROUTING || hooknum == NF_INET_INGRESS) &&
-	    nf_reject6_fill_skb_dst(skb_in) < 0)
+	if (!skb_dst(skb_in) && nf_reject6_fill_skb_dst(skb_in) < 0)
 		return;
 
 	icmpv6_send(skb_in, ICMPV6_DEST_UNREACH, code, 0);
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -119,13 +119,12 @@ __mtu_check_toobig_v6(const struct sk_buff *skb, u32 mtu)
 	return false;
 }
 
-/* Get route to daddr, update *saddr, optionally bind route to saddr */
+/* Get route to daddr, optionally bind route to saddr */
 static struct rtable *do_output_route4(struct net *net, __be32 daddr,
-				       int rt_mode, __be32 *saddr)
+				       int rt_mode, __be32 *ret_saddr)
 {
 	struct flowi4 fl4;
 	struct rtable *rt;
-	bool loop = false;
 
 	memset(&fl4, 0, sizeof(fl4));
 	fl4.daddr = daddr;
@@ -135,23 +134,17 @@ static struct rtable *do_output_route4(struct net *net, __be32 daddr,
 retry:
 	rt = ip_route_output_key(net, &fl4);
 	if (IS_ERR(rt)) {
-		/* Invalid saddr ? */
-		if (PTR_ERR(rt) == -EINVAL && *saddr &&
-		    rt_mode & IP_VS_RT_MODE_CONNECT && !loop) {
-			*saddr = 0;
-			flowi4_update_output(&fl4, 0, 0, daddr, 0);
-			goto retry;
-		}
 		IP_VS_DBG_RL("ip_route_output error, dest: %pI4\n", &daddr);
 		return NULL;
-	} else if (!*saddr && rt_mode & IP_VS_RT_MODE_CONNECT && fl4.saddr) {
+	}
+	if (rt_mode & IP_VS_RT_MODE_CONNECT && fl4.saddr) {
 		ip_rt_put(rt);
-		*saddr = fl4.saddr;
 		flowi4_update_output(&fl4, 0, 0, daddr, fl4.saddr);
-		loop = true;
+		rt_mode = 0;
 		goto retry;
 	}
-	*saddr = fl4.saddr;
+	if (ret_saddr)
+		*ret_saddr = fl4.saddr;
 	return rt;
 }
 
@@ -344,19 +337,15 @@ __ip_vs_get_out_rt(struct netns_ipvs *ipvs, int skb_af, struct sk_buff *skb,
 		if (ret_saddr)
 			*ret_saddr = dest_dst->dst_saddr.ip;
 	} else {
-		__be32 saddr = htonl(INADDR_ANY);
-
 		noref = 0;
 
 		/* For such unconfigured boxes avoid many route lookups
 		 * for performance reasons because we do not remember saddr
 		 */
 		rt_mode &= ~IP_VS_RT_MODE_CONNECT;
-		rt = do_output_route4(net, daddr, rt_mode, &saddr);
+		rt = do_output_route4(net, daddr, rt_mode, ret_saddr);
 		if (!rt)
 			goto err_unreach;
-		if (ret_saddr)
-			*ret_saddr = saddr;
 	}
 
 	local = (rt->rt_flags & RTCF_LOCAL) ? 1 : 0;
diff --git a/net/netfilter/nf_bpf_link.c b/net/netfilter/nf_bpf_link.c
@@ -15,7 +15,7 @@ static unsigned int nf_hook_run_bpf(void *bpf_prog, struct sk_buff *skb,
 		.skb = skb,
 	};
 
-	return bpf_prog_run(prog, &ctx);
+	return bpf_prog_run_pin_on_cpu(prog, &ctx);
 }
 
 struct bpf_nf_link {
@@ -200,6 +200,9 @@ static bool nf_is_valid_access(int off, int size, enum bpf_access_type type,
 	if (off < 0 || off >= sizeof(struct bpf_nf_ctx))
 		return false;
 
+	if (off % size != 0)
+		return false;
+
 	if (type == BPF_WRITE)
 		return false;
 
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
@@ -862,8 +862,6 @@ ctnetlink_conntrack_event(unsigned int events, const struct nf_ct_event *item)
 
 static int ctnetlink_done(struct netlink_callback *cb)
 {
-	if (cb->args[1])
-		nf_ct_put((struct nf_conn *)cb->args[1]);
 	kfree(cb->data);
 	return 0;
 }
@@ -1178,19 +1176,26 @@ static int ctnetlink_filter_match(struct nf_conn *ct, void *data)
 	return 0;
 }
 
+static unsigned long ctnetlink_get_id(const struct nf_conn *ct)
+{
+	unsigned long id = nf_ct_get_id(ct);
+
+	return id ? id : 1;
+}
+
 static int
 ctnetlink_dump_table(struct sk_buff *skb, struct netlink_callback *cb)
 {
 	unsigned int flags = cb->data ? NLM_F_DUMP_FILTERED : 0;
 	struct net *net = sock_net(skb->sk);
-	struct nf_conn *ct, *last;
+	unsigned long last_id = cb->args[1];
 	struct nf_conntrack_tuple_hash *h;
 	struct hlist_nulls_node *n;
 	struct nf_conn *nf_ct_evict[8];
+	struct nf_conn *ct;
 	int res, i;
 	spinlock_t *lockp;
 
-	last = (struct nf_conn *)cb->args[1];
 	i = 0;
 
 	local_bh_disable();
@@ -1227,7 +1232,7 @@ ctnetlink_dump_table(struct sk_buff *skb, struct netlink_callback *cb)
 				continue;
 
 			if (cb->args[1]) {
-				if (ct != last)
+				if (ctnetlink_get_id(ct) != last_id)
 					continue;
 				cb->args[1] = 0;
 			}
@@ -1240,8 +1245,7 @@ ctnetlink_dump_table(struct sk_buff *skb, struct netlink_callback *cb)
 					    NFNL_MSG_TYPE(cb->nlh->nlmsg_type),
 					    ct, true, flags);
 			if (res < 0) {
-				nf_conntrack_get(&ct->ct_general);
-				cb->args[1] = (unsigned long)ct;
+				cb->args[1] = ctnetlink_get_id(ct);
 				spin_unlock(lockp);
 				goto out;
 			}
@@ -1254,12 +1258,10 @@ ctnetlink_dump_table(struct sk_buff *skb, struct netlink_callback *cb)
 	}
 out:
 	local_bh_enable();
-	if (last) {
+	if (last_id) {
 		/* nf ct hash resize happened, now clear the leftover. */
-		if ((struct nf_conn *)cb->args[1] == last)
+		if (cb->args[1] == last_id)
 			cb->args[1] = 0;
-
-		nf_ct_put(last);
 	}
 
 	while (i) {
@@ -3153,23 +3155,27 @@ ctnetlink_expect_event(unsigned int events, const struct nf_exp_event *item)
 	return 0;
 }
 #endif
-static int ctnetlink_exp_done(struct netlink_callback *cb)
+
+static unsigned long ctnetlink_exp_id(const struct nf_conntrack_expect *exp)
 {
-	if (cb->args[1])
-		nf_ct_expect_put((struct nf_conntrack_expect *)cb->args[1]);
-	return 0;
+	unsigned long id = (unsigned long)exp;
+
+	id += nf_ct_get_id(exp->master);
+	id += exp->class;
+
+	return id ? id : 1;
 }
 
 static int
 ctnetlink_exp_dump_table(struct sk_buff *skb, struct netlink_callback *cb)
 {
 	struct net *net = sock_net(skb->sk);
-	struct nf_conntrack_expect *exp, *last;
 	struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh);
 	u_int8_t l3proto = nfmsg->nfgen_family;
+	unsigned long last_id = cb->args[1];
+	struct nf_conntrack_expect *exp;
 
 	rcu_read_lock();
-	last = (struct nf_conntrack_expect *)cb->args[1];
 	for (; cb->args[0] < nf_ct_expect_hsize; cb->args[0]++) {
 restart:
 		hlist_for_each_entry_rcu(exp, &nf_ct_expect_hash[cb->args[0]],
@@ -3181,7 +3187,7 @@ ctnetlink_exp_dump_table(struct sk_buff *skb, struct netlink_callback *cb)
 				continue;
 
 			if (cb->args[1]) {
-				if (exp != last)
+				if (ctnetlink_exp_id(exp) != last_id)
 					continue;
 				cb->args[1] = 0;
 			}
@@ -3190,9 +3196,7 @@ ctnetlink_exp_dump_table(struct sk_buff *skb, struct netlink_callback *cb)
 						    cb->nlh->nlmsg_seq,
 						    IPCTNL_MSG_EXP_NEW,
 						    exp) < 0) {
-				if (!refcount_inc_not_zero(&exp->use))
-					continue;
-				cb->args[1] = (unsigned long)exp;
+				cb->args[1] = ctnetlink_exp_id(exp);
 				goto out;
 			}
 		}
@@ -3203,42 +3207,38 @@ ctnetlink_exp_dump_table(struct sk_buff *skb, struct netlink_callback *cb)
 	}
 out:
 	rcu_read_unlock();
-	if (last)
-		nf_ct_expect_put(last);
-
 	return skb->len;
 }
 
 static int
 ctnetlink_exp_ct_dump_table(struct sk_buff *skb, struct netlink_callback *cb)
 {
-	struct nf_conntrack_expect *exp, *last;
 	struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh);
 	struct nf_conn *ct = cb->data;
 	struct nf_conn_help *help = nfct_help(ct);
 	u_int8_t l3proto = nfmsg->nfgen_family;
+	unsigned long last_id = cb->args[1];
+	struct nf_conntrack_expect *exp;
 
 	if (cb->args[0])
 		return 0;
 
 	rcu_read_lock();
-	last = (struct nf_conntrack_expect *)cb->args[1];
+
 restart:
 	hlist_for_each_entry_rcu(exp, &help->expectations, lnode) {
 		if (l3proto && exp->tuple.src.l3num != l3proto)
 			continue;
 		if (cb->args[1]) {
-			if (exp != last)
+			if (ctnetlink_exp_id(exp) != last_id)
 				continue;
 			cb->args[1] = 0;
 		}
 		if (ctnetlink_exp_fill_info(skb, NETLINK_CB(cb->skb).portid,
 					    cb->nlh->nlmsg_seq,
 					    IPCTNL_MSG_EXP_NEW,
 					    exp) < 0) {
-			if (!refcount_inc_not_zero(&exp->use))
-				continue;
-			cb->args[1] = (unsigned long)exp;
+			cb->args[1] = ctnetlink_exp_id(exp);
 			goto out;
 		}
 	}
@@ -3249,9 +3249,6 @@ ctnetlink_exp_ct_dump_table(struct sk_buff *skb, struct netlink_callback *cb)
 	cb->args[0] = 1;
 out:
 	rcu_read_unlock();
-	if (last)
-		nf_ct_expect_put(last);
-
 	return skb->len;
 }
 
@@ -3270,7 +3267,6 @@ static int ctnetlink_dump_exp_ct(struct net *net, struct sock *ctnl,
 	struct nf_conntrack_zone zone;
 	struct netlink_dump_control c = {
 		.dump = ctnetlink_exp_ct_dump_table,
-		.done = ctnetlink_exp_done,
 	};
 
 	err = ctnetlink_parse_tuple(cda, &tuple, CTA_EXPECT_MASTER,
@@ -3320,7 +3316,6 @@ static int ctnetlink_get_expect(struct sk_buff *skb,
 		else {
 			struct netlink_dump_control c = {
 				.dump = ctnetlink_exp_dump_table,
-				.done = ctnetlink_exp_done,
 			};
 			return netlink_dump_start(info->sk, skb, info->nlh, &c);
 		}
diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c
@@ -544,8 +544,11 @@ static void nf_nat_l4proto_unique_tuple(struct nf_conntrack_tuple *tuple,
 find_free_id:
 	if (range->flags & NF_NAT_RANGE_PROTO_OFFSET)
 		off = (ntohs(*keyptr) - ntohs(range->base_proto.all));
-	else
+	else if ((range->flags & NF_NAT_RANGE_PROTO_RANDOM_ALL) ||
+		 maniptype != NF_NAT_MANIP_DST)
 		off = prandom_u32();
+	else
+		off = 0;
 
 	attempts = range_size;
 	if (attempts > NF_NAT_MAX_ATTEMPTS)
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
diff --git a/net/netfilter/nft_set_pipapo_avx2.c b/net/netfilter/nft_set_pipapo_avx2.c
diff --git a/net/netfilter/nft_socket.c b/net/netfilter/nft_socket.c
diff --git a/net/netfilter/xt_nfacct.c b/net/netfilter/xt_nfacct.c

Original file line number	Diff line number	Diff line change
`@@ -353,7 +353,7 @@ static inline __be16 __nf_flow_pppoe_proto(const struct sk_buff *skb)`
`353`	`353`
`354`	`354`	`static inline bool nf_flow_pppoe_proto(struct sk_buff skb, __be16 inner_proto)`
`355`	`355`	`{`
`356`		`- if (!pskb_may_pull(skb, PPPOE_SES_HLEN))`
	`356`	`+ if (!pskb_may_pull(skb, ETH_HLEN + PPPOE_SES_HLEN))`
`357`	`357`	`return false;`
`358`	`358`
`359`	`359`	`*inner_proto = __nf_flow_pppoe_proto(skb);`