From 0617c3de9b4026b87be12b0cb5c35f42c7c66fcb Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Wed, 3 Jan 2024 23:34:58 +0100 Subject: netfilter: nf_tables: reject invalid set policy Report -EINVAL in case userspace provides a unsupported set backend policy. Fixes: c50b960ccc59 ("netfilter: nf_tables: implement proper set selection") Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_tables_api.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'net') diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 8438a8922e4a..a90a364f5be5 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -5048,8 +5048,16 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info, } desc.policy = NFT_SET_POL_PERFORMANCE; - if (nla[NFTA_SET_POLICY] != NULL) + if (nla[NFTA_SET_POLICY] != NULL) { desc.policy = ntohl(nla_get_be32(nla[NFTA_SET_POLICY])); + switch (desc.policy) { + case NFT_SET_POL_PERFORMANCE: + case NFT_SET_POL_MEMORY: + break; + default: + return -EOPNOTSUPP; + } + } if (nla[NFTA_SET_DESC] != NULL) { err = nf_tables_set_desc_parse(&desc, nla[NFTA_SET_DESC]); -- cgit From 65b3bd600e15e00fb9e433bbc8aa55e42b202055 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Sat, 6 Jan 2024 23:52:02 +0100 Subject: netfilter: nf_tables: validate .maxattr at expression registration struct nft_expr_info allows to store up to NFT_EXPR_MAXATTR (16) attributes when parsing netlink attributes. Rise a warning in case there is ever a nft expression whose .maxattr goes beyond this number of expressions, in such case, struct nft_expr_info needs to be updated. Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_tables_api.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'net') diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index a90a364f5be5..2548d7d56408 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -2977,6 +2977,9 @@ static int nf_tables_delchain(struct sk_buff *skb, const struct nfnl_info *info, */ int nft_register_expr(struct nft_expr_type *type) { + if (WARN_ON_ONCE(type->maxattr > NFT_EXPR_MAXATTR)) + return -ENOMEM; + nfnl_lock(NFNL_SUBSYS_NFTABLES); if (type->family == NFPROTO_UNSPEC) list_add_tail_rcu(&type->list, &nf_tables_expressions); -- cgit From 3c13725f43dcf43ad8a9bcd6a9f12add19a8f93e Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Sun, 7 Jan 2024 23:00:15 +0100 Subject: netfilter: nf_tables: bail out if stateful expression provides no .clone All existing NFT_EXPR_STATEFUL provide a .clone interface, remove fallback to copy content of stateful expression since this is never exercised and bail out if .clone interface is not defined. Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_tables_api.c | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) (limited to 'net') diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 2548d7d56408..b3db97440db1 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -3274,14 +3274,13 @@ int nft_expr_clone(struct nft_expr *dst, struct nft_expr *src) { int err; - if (src->ops->clone) { - dst->ops = src->ops; - err = src->ops->clone(dst, src); - if (err < 0) - return err; - } else { - memcpy(dst, src, src->ops->size); - } + if (WARN_ON_ONCE(!src->ops->clone)) + return -EINVAL; + + dst->ops = src->ops; + err = src->ops->clone(dst, src); + if (err < 0) + return err; __module_get(src->ops->type->owner); -- cgit From 91a139cee1202a4599a380810d93c69b5bac6197 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Wed, 10 Jan 2024 00:42:37 +0100 Subject: netfilter: nft_limit: do not ignore unsupported flags Bail out if userspace provides unsupported flags, otherwise future extensions to the limit expression will be silently ignored by the kernel. Fixes: c7862a5f0de5 ("netfilter: nft_limit: allow to invert matching criteria") Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nft_limit.c | 19 ++++++++++++------- 1 file changed, 12 insertions(+), 7 deletions(-) (limited to 'net') diff --git a/net/netfilter/nft_limit.c b/net/netfilter/nft_limit.c index 145dc62c6247..79039afde34e 100644 --- a/net/netfilter/nft_limit.c +++ b/net/netfilter/nft_limit.c @@ -58,6 +58,7 @@ static inline bool nft_limit_eval(struct nft_limit_priv *priv, u64 cost) static int nft_limit_init(struct nft_limit_priv *priv, const struct nlattr * const tb[], bool pkts) { + bool invert = false; u64 unit, tokens; if (tb[NFTA_LIMIT_RATE] == NULL || @@ -90,19 +91,23 @@ static int nft_limit_init(struct nft_limit_priv *priv, priv->rate); } + if (tb[NFTA_LIMIT_FLAGS]) { + u32 flags = ntohl(nla_get_be32(tb[NFTA_LIMIT_FLAGS])); + + if (flags & ~NFT_LIMIT_F_INV) + return -EOPNOTSUPP; + + if (flags & NFT_LIMIT_F_INV) + invert = true; + } + priv->limit = kmalloc(sizeof(*priv->limit), GFP_KERNEL_ACCOUNT); if (!priv->limit) return -ENOMEM; priv->limit->tokens = tokens; priv->tokens_max = priv->limit->tokens; - - if (tb[NFTA_LIMIT_FLAGS]) { - u32 flags = ntohl(nla_get_be32(tb[NFTA_LIMIT_FLAGS])); - - if (flags & NFT_LIMIT_F_INV) - priv->invert = true; - } + priv->invert = invert; priv->limit->last = ktime_get_ns(); spin_lock_init(&priv->limit->lock); -- cgit From c3f9fd54cd87233f53bdf0e191a86b3a5e960e02 Mon Sep 17 00:00:00 2001 From: Pavel Tikhomirov Date: Thu, 11 Jan 2024 23:06:37 +0800 Subject: netfilter: nfnetlink_log: use proper helper for fetching physinif We don't use physindev in __build_packet_message except for getting physinif from it. So let's switch to nf_bridge_get_physinif to get what we want directly. Signed-off-by: Pavel Tikhomirov Reviewed-by: Simon Horman Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nfnetlink_log.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'net') diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index f03f4d4d7d88..134e05d31061 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -508,7 +508,7 @@ __build_packet_message(struct nfnl_log_net *log, htonl(br_port_get_rcu(indev)->br->dev->ifindex))) goto nla_put_failure; } else { - struct net_device *physindev; + int physinif; /* Case 2: indev is bridge group, we need to look for * physical device (when called from ipv4) */ @@ -516,10 +516,10 @@ __build_packet_message(struct nfnl_log_net *log, htonl(indev->ifindex))) goto nla_put_failure; - physindev = nf_bridge_get_physindev(skb); - if (physindev && + physinif = nf_bridge_get_physinif(skb); + if (physinif && nla_put_be32(inst->skb, NFULA_IFINDEX_PHYSINDEV, - htonl(physindev->ifindex))) + htonl(physinif))) goto nla_put_failure; } #endif -- cgit From aeaa44075f8e49e2e0ad4507d925e690b7950145 Mon Sep 17 00:00:00 2001 From: Pavel Tikhomirov Date: Thu, 11 Jan 2024 23:06:38 +0800 Subject: netfilter: nf_queue: remove excess nf_bridge variable We don't really need nf_bridge variable here. And nf_bridge_info_exists is better replacement for nf_bridge_info_get in case we are only checking for existence. Signed-off-by: Pavel Tikhomirov Reviewed-by: Simon Horman Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_queue.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'net') diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c index 63d1516816b1..3dfcb3ac5cb4 100644 --- a/net/netfilter/nf_queue.c +++ b/net/netfilter/nf_queue.c @@ -82,10 +82,8 @@ static void __nf_queue_entry_init_physdevs(struct nf_queue_entry *entry) { #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) const struct sk_buff *skb = entry->skb; - struct nf_bridge_info *nf_bridge; - nf_bridge = nf_bridge_info_get(skb); - if (nf_bridge) { + if (nf_bridge_info_exists(skb)) { entry->physin = nf_bridge_get_physindev(skb); entry->physout = nf_bridge_get_physoutdev(skb); } else { -- cgit From a54e72197037d2c9bfcd70dddaac8c8ccb5b41ba Mon Sep 17 00:00:00 2001 From: Pavel Tikhomirov Date: Thu, 11 Jan 2024 23:06:39 +0800 Subject: netfilter: propagate net to nf_bridge_get_physindev This is a preparation patch for replacing physindev with physinif on nf_bridge_info structure. We will use dev_get_by_index_rcu to resolve device, when needed, and it requires net to be available. Signed-off-by: Pavel Tikhomirov Reviewed-by: Simon Horman Signed-off-by: Pablo Neira Ayuso --- net/ipv4/netfilter/nf_reject_ipv4.c | 2 +- net/ipv6/netfilter/nf_reject_ipv6.c | 2 +- net/netfilter/ipset/ip_set_hash_netiface.c | 8 ++++---- net/netfilter/nf_log_syslog.c | 13 +++++++------ net/netfilter/nf_queue.c | 2 +- net/netfilter/xt_physdev.c | 2 +- 6 files changed, 15 insertions(+), 14 deletions(-) (limited to 'net') diff --git a/net/ipv4/netfilter/nf_reject_ipv4.c b/net/ipv4/netfilter/nf_reject_ipv4.c index f01b038fc1cd..86e7d390671a 100644 --- a/net/ipv4/netfilter/nf_reject_ipv4.c +++ b/net/ipv4/netfilter/nf_reject_ipv4.c @@ -289,7 +289,7 @@ void nf_send_reset(struct net *net, struct sock *sk, struct sk_buff *oldskb, * build the eth header using the original destination's MAC as the * source, and send the RST packet directly. */ - br_indev = nf_bridge_get_physindev(oldskb); + br_indev = nf_bridge_get_physindev(oldskb, net); if (br_indev) { struct ethhdr *oeth = eth_hdr(oldskb); diff --git a/net/ipv6/netfilter/nf_reject_ipv6.c b/net/ipv6/netfilter/nf_reject_ipv6.c index d45bc54b7ea5..27b2164f4c43 100644 --- a/net/ipv6/netfilter/nf_reject_ipv6.c +++ b/net/ipv6/netfilter/nf_reject_ipv6.c @@ -354,7 +354,7 @@ void nf_send_reset6(struct net *net, struct sock *sk, struct sk_buff *oldskb, * build the eth header using the original destination's MAC as the * source, and send the RST packet directly. */ - br_indev = nf_bridge_get_physindev(oldskb); + br_indev = nf_bridge_get_physindev(oldskb, net); if (br_indev) { struct ethhdr *oeth = eth_hdr(oldskb); diff --git a/net/netfilter/ipset/ip_set_hash_netiface.c b/net/netfilter/ipset/ip_set_hash_netiface.c index 95aeb31c60e0..30a655e5c4fd 100644 --- a/net/netfilter/ipset/ip_set_hash_netiface.c +++ b/net/netfilter/ipset/ip_set_hash_netiface.c @@ -138,9 +138,9 @@ hash_netiface4_data_next(struct hash_netiface4_elem *next, #include "ip_set_hash_gen.h" #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) -static const char *get_physindev_name(const struct sk_buff *skb) +static const char *get_physindev_name(const struct sk_buff *skb, struct net *net) { - struct net_device *dev = nf_bridge_get_physindev(skb); + struct net_device *dev = nf_bridge_get_physindev(skb, net); return dev ? dev->name : NULL; } @@ -177,7 +177,7 @@ hash_netiface4_kadt(struct ip_set *set, const struct sk_buff *skb, if (opt->cmdflags & IPSET_FLAG_PHYSDEV) { #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) - const char *eiface = SRCDIR ? get_physindev_name(skb) : + const char *eiface = SRCDIR ? get_physindev_name(skb, xt_net(par)) : get_physoutdev_name(skb); if (!eiface) @@ -395,7 +395,7 @@ hash_netiface6_kadt(struct ip_set *set, const struct sk_buff *skb, if (opt->cmdflags & IPSET_FLAG_PHYSDEV) { #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) - const char *eiface = SRCDIR ? get_physindev_name(skb) : + const char *eiface = SRCDIR ? get_physindev_name(skb, xt_net(par)) : get_physoutdev_name(skb); if (!eiface) diff --git a/net/netfilter/nf_log_syslog.c b/net/netfilter/nf_log_syslog.c index c66689ad2b49..58402226045e 100644 --- a/net/netfilter/nf_log_syslog.c +++ b/net/netfilter/nf_log_syslog.c @@ -111,7 +111,8 @@ nf_log_dump_packet_common(struct nf_log_buf *m, u8 pf, unsigned int hooknum, const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, - const struct nf_loginfo *loginfo, const char *prefix) + const struct nf_loginfo *loginfo, const char *prefix, + struct net *net) { const struct net_device *physoutdev __maybe_unused; const struct net_device *physindev __maybe_unused; @@ -121,7 +122,7 @@ nf_log_dump_packet_common(struct nf_log_buf *m, u8 pf, in ? in->name : "", out ? out->name : ""); #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) - physindev = nf_bridge_get_physindev(skb); + physindev = nf_bridge_get_physindev(skb, net); if (physindev && in != physindev) nf_log_buf_add(m, "PHYSIN=%s ", physindev->name); physoutdev = nf_bridge_get_physoutdev(skb); @@ -148,7 +149,7 @@ static void nf_log_arp_packet(struct net *net, u_int8_t pf, loginfo = &default_loginfo; nf_log_dump_packet_common(m, pf, hooknum, skb, in, out, loginfo, - prefix); + prefix, net); dump_arp_packet(m, loginfo, skb, skb_network_offset(skb)); nf_log_buf_close(m); @@ -845,7 +846,7 @@ static void nf_log_ip_packet(struct net *net, u_int8_t pf, loginfo = &default_loginfo; nf_log_dump_packet_common(m, pf, hooknum, skb, in, - out, loginfo, prefix); + out, loginfo, prefix, net); if (in) dump_mac_header(m, loginfo, skb); @@ -880,7 +881,7 @@ static void nf_log_ip6_packet(struct net *net, u_int8_t pf, loginfo = &default_loginfo; nf_log_dump_packet_common(m, pf, hooknum, skb, in, out, - loginfo, prefix); + loginfo, prefix, net); if (in) dump_mac_header(m, loginfo, skb); @@ -916,7 +917,7 @@ static void nf_log_unknown_packet(struct net *net, u_int8_t pf, loginfo = &default_loginfo; nf_log_dump_packet_common(m, pf, hooknum, skb, in, out, loginfo, - prefix); + prefix, net); dump_mac_header(m, loginfo, skb); diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c index 3dfcb3ac5cb4..e2f334f70281 100644 --- a/net/netfilter/nf_queue.c +++ b/net/netfilter/nf_queue.c @@ -84,7 +84,7 @@ static void __nf_queue_entry_init_physdevs(struct nf_queue_entry *entry) const struct sk_buff *skb = entry->skb; if (nf_bridge_info_exists(skb)) { - entry->physin = nf_bridge_get_physindev(skb); + entry->physin = nf_bridge_get_physindev(skb, entry->state.net); entry->physout = nf_bridge_get_physoutdev(skb); } else { entry->physin = NULL; diff --git a/net/netfilter/xt_physdev.c b/net/netfilter/xt_physdev.c index ec6ed6fda96c..343e65f377d4 100644 --- a/net/netfilter/xt_physdev.c +++ b/net/netfilter/xt_physdev.c @@ -59,7 +59,7 @@ physdev_mt(const struct sk_buff *skb, struct xt_action_param *par) (!!outdev ^ !(info->invert & XT_PHYSDEV_OP_BRIDGED))) return false; - physdev = nf_bridge_get_physindev(skb); + physdev = nf_bridge_get_physindev(skb, xt_net(par)); indev = physdev ? physdev->name : NULL; if ((info->bitmask & XT_PHYSDEV_OP_ISIN && -- cgit From 9874808878d9eed407e3977fd11fee49de1e1d86 Mon Sep 17 00:00:00 2001 From: Pavel Tikhomirov Date: Thu, 11 Jan 2024 23:06:40 +0800 Subject: netfilter: bridge: replace physindev with physinif in nf_bridge_info An skb can be added to a neigh->arp_queue while waiting for an arp reply. Where original skb's skb->dev can be different to neigh's neigh->dev. For instance in case of bridging dnated skb from one veth to another, the skb would be added to a neigh->arp_queue of the bridge. As skb->dev can be reset back to nf_bridge->physindev and used, and as there is no explicit mechanism that prevents this physindev from been freed under us (for instance neigh_flush_dev doesn't cleanup skbs from different device's neigh queue) we can crash on e.g. this stack: arp_process neigh_update skb = __skb_dequeue(&neigh->arp_queue) neigh_resolve_output(..., skb) ... br_nf_dev_xmit br_nf_pre_routing_finish_bridge_slow skb->dev = nf_bridge->physindev br_handle_frame_finish Let's use plain ifindex instead of net_device link. To peek into the original net_device we will use dev_get_by_index_rcu(). Thus either we get device and are safe to use it or we don't get it and drop skb. Fixes: c4e70a87d975 ("netfilter: bridge: rename br_netfilter.c to br_netfilter_hooks.c") Suggested-by: Florian Westphal Signed-off-by: Pavel Tikhomirov Signed-off-by: Pablo Neira Ayuso --- net/bridge/br_netfilter_hooks.c | 42 ++++++++++++++++++++++++++++++------- net/bridge/br_netfilter_ipv6.c | 14 +++++++++---- net/ipv4/netfilter/nf_reject_ipv4.c | 9 +++++--- net/ipv6/netfilter/nf_reject_ipv6.c | 11 +++++++--- 4 files changed, 58 insertions(+), 18 deletions(-) (limited to 'net') diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index 6adcb45bca75..ed1720890757 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -279,8 +279,17 @@ int br_nf_pre_routing_finish_bridge(struct net *net, struct sock *sk, struct sk_ if ((READ_ONCE(neigh->nud_state) & NUD_CONNECTED) && READ_ONCE(neigh->hh.hh_len)) { + struct net_device *br_indev; + + br_indev = nf_bridge_get_physindev(skb, net); + if (!br_indev) { + neigh_release(neigh); + goto free_skb; + } + neigh_hh_bridge(&neigh->hh, skb); - skb->dev = nf_bridge->physindev; + skb->dev = br_indev; + ret = br_handle_frame_finish(net, sk, skb); } else { /* the neighbour function below overwrites the complete @@ -352,12 +361,18 @@ br_nf_ipv4_daddr_was_changed(const struct sk_buff *skb, */ static int br_nf_pre_routing_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { - struct net_device *dev = skb->dev; + struct net_device *dev = skb->dev, *br_indev; struct iphdr *iph = ip_hdr(skb); struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb); struct rtable *rt; int err; + br_indev = nf_bridge_get_physindev(skb, net); + if (!br_indev) { + kfree_skb(skb); + return 0; + } + nf_bridge->frag_max_size = IPCB(skb)->frag_max_size; if (nf_bridge->pkt_otherhost) { @@ -397,7 +412,7 @@ free_skb: } else { if (skb_dst(skb)->dev == dev) { bridged_dnat: - skb->dev = nf_bridge->physindev; + skb->dev = br_indev; nf_bridge_update_protocol(skb); nf_bridge_push_encap_header(skb); br_nf_hook_thresh(NF_BR_PRE_ROUTING, @@ -410,7 +425,7 @@ bridged_dnat: skb->pkt_type = PACKET_HOST; } } else { - rt = bridge_parent_rtable(nf_bridge->physindev); + rt = bridge_parent_rtable(br_indev); if (!rt) { kfree_skb(skb); return 0; @@ -419,7 +434,7 @@ bridged_dnat: skb_dst_set_noref(skb, &rt->dst); } - skb->dev = nf_bridge->physindev; + skb->dev = br_indev; nf_bridge_update_protocol(skb); nf_bridge_push_encap_header(skb); br_nf_hook_thresh(NF_BR_PRE_ROUTING, net, sk, skb, skb->dev, NULL, @@ -456,7 +471,7 @@ struct net_device *setup_pre_routing(struct sk_buff *skb, const struct net *net) } nf_bridge->in_prerouting = 1; - nf_bridge->physindev = skb->dev; + nf_bridge->physinif = skb->dev->ifindex; skb->dev = brnf_get_logical_dev(skb, skb->dev, net); if (skb->protocol == htons(ETH_P_8021Q)) @@ -553,7 +568,11 @@ static int br_nf_forward_finish(struct net *net, struct sock *sk, struct sk_buff if (skb->protocol == htons(ETH_P_IPV6)) nf_bridge->frag_max_size = IP6CB(skb)->frag_max_size; - in = nf_bridge->physindev; + in = nf_bridge_get_physindev(skb, net); + if (!in) { + kfree_skb(skb); + return 0; + } if (nf_bridge->pkt_otherhost) { skb->pkt_type = PACKET_OTHERHOST; nf_bridge->pkt_otherhost = false; @@ -899,6 +918,13 @@ static unsigned int ip_sabotage_in(void *priv, static void br_nf_pre_routing_finish_bridge_slow(struct sk_buff *skb) { struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb); + struct net_device *br_indev; + + br_indev = nf_bridge_get_physindev(skb, dev_net(skb->dev)); + if (!br_indev) { + kfree_skb(skb); + return; + } skb_pull(skb, ETH_HLEN); nf_bridge->bridged_dnat = 0; @@ -908,7 +934,7 @@ static void br_nf_pre_routing_finish_bridge_slow(struct sk_buff *skb) skb_copy_to_linear_data_offset(skb, -(ETH_HLEN - ETH_ALEN), nf_bridge->neigh_header, ETH_HLEN - ETH_ALEN); - skb->dev = nf_bridge->physindev; + skb->dev = br_indev; nf_bridge->physoutdev = NULL; br_handle_frame_finish(dev_net(skb->dev), NULL, skb); diff --git a/net/bridge/br_netfilter_ipv6.c b/net/bridge/br_netfilter_ipv6.c index 2e24a743f917..e0421eaa3abc 100644 --- a/net/bridge/br_netfilter_ipv6.c +++ b/net/bridge/br_netfilter_ipv6.c @@ -102,9 +102,15 @@ static int br_nf_pre_routing_finish_ipv6(struct net *net, struct sock *sk, struc { struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb); struct rtable *rt; - struct net_device *dev = skb->dev; + struct net_device *dev = skb->dev, *br_indev; const struct nf_ipv6_ops *v6ops = nf_get_ipv6_ops(); + br_indev = nf_bridge_get_physindev(skb, net); + if (!br_indev) { + kfree_skb(skb); + return 0; + } + nf_bridge->frag_max_size = IP6CB(skb)->frag_max_size; if (nf_bridge->pkt_otherhost) { @@ -122,7 +128,7 @@ static int br_nf_pre_routing_finish_ipv6(struct net *net, struct sock *sk, struc } if (skb_dst(skb)->dev == dev) { - skb->dev = nf_bridge->physindev; + skb->dev = br_indev; nf_bridge_update_protocol(skb); nf_bridge_push_encap_header(skb); br_nf_hook_thresh(NF_BR_PRE_ROUTING, @@ -133,7 +139,7 @@ static int br_nf_pre_routing_finish_ipv6(struct net *net, struct sock *sk, struc ether_addr_copy(eth_hdr(skb)->h_dest, dev->dev_addr); skb->pkt_type = PACKET_HOST; } else { - rt = bridge_parent_rtable(nf_bridge->physindev); + rt = bridge_parent_rtable(br_indev); if (!rt) { kfree_skb(skb); return 0; @@ -142,7 +148,7 @@ static int br_nf_pre_routing_finish_ipv6(struct net *net, struct sock *sk, struc skb_dst_set_noref(skb, &rt->dst); } - skb->dev = nf_bridge->physindev; + skb->dev = br_indev; nf_bridge_update_protocol(skb); nf_bridge_push_encap_header(skb); br_nf_hook_thresh(NF_BR_PRE_ROUTING, net, sk, skb, diff --git a/net/ipv4/netfilter/nf_reject_ipv4.c b/net/ipv4/netfilter/nf_reject_ipv4.c index 86e7d390671a..04504b2b51df 100644 --- a/net/ipv4/netfilter/nf_reject_ipv4.c +++ b/net/ipv4/netfilter/nf_reject_ipv4.c @@ -239,7 +239,6 @@ static int nf_reject_fill_skb_dst(struct sk_buff *skb_in) void nf_send_reset(struct net *net, struct sock *sk, struct sk_buff *oldskb, int hook) { - struct net_device *br_indev __maybe_unused; struct sk_buff *nskb; struct iphdr *niph; const struct tcphdr *oth; @@ -289,9 +288,13 @@ void nf_send_reset(struct net *net, struct sock *sk, struct sk_buff *oldskb, * build the eth header using the original destination's MAC as the * source, and send the RST packet directly. */ - br_indev = nf_bridge_get_physindev(oldskb, net); - if (br_indev) { + if (nf_bridge_info_exists(oldskb)) { struct ethhdr *oeth = eth_hdr(oldskb); + struct net_device *br_indev; + + br_indev = nf_bridge_get_physindev(oldskb, net); + if (!br_indev) + goto free_nskb; nskb->dev = br_indev; niph->tot_len = htons(nskb->len); diff --git a/net/ipv6/netfilter/nf_reject_ipv6.c b/net/ipv6/netfilter/nf_reject_ipv6.c index 27b2164f4c43..196dd4ecb5e2 100644 --- a/net/ipv6/netfilter/nf_reject_ipv6.c +++ b/net/ipv6/netfilter/nf_reject_ipv6.c @@ -278,7 +278,6 @@ static int nf_reject6_fill_skb_dst(struct sk_buff *skb_in) void nf_send_reset6(struct net *net, struct sock *sk, struct sk_buff *oldskb, int hook) { - struct net_device *br_indev __maybe_unused; struct sk_buff *nskb; struct tcphdr _otcph; const struct tcphdr *otcph; @@ -354,9 +353,15 @@ void nf_send_reset6(struct net *net, struct sock *sk, struct sk_buff *oldskb, * build the eth header using the original destination's MAC as the * source, and send the RST packet directly. */ - br_indev = nf_bridge_get_physindev(oldskb, net); - if (br_indev) { + if (nf_bridge_info_exists(oldskb)) { struct ethhdr *oeth = eth_hdr(oldskb); + struct net_device *br_indev; + + br_indev = nf_bridge_get_physindev(oldskb, net); + if (!br_indev) { + kfree_skb(nskb); + return; + } nskb->dev = br_indev; nskb->protocol = htons(ETH_P_IPV6); -- cgit From b1db244ffd041a49ecc9618e8feb6b5c1afcdaa7 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Fri, 12 Jan 2024 23:28:45 +0100 Subject: netfilter: nf_tables: check if catch-all set element is active in next generation When deactivating the catch-all set element, check the state in the next generation that represents this transaction. This bug uncovered after the recent removal of the element busy mark a2dd0233cbc4 ("netfilter: nf_tables: remove busy mark and gc batch API"). Fixes: aaa31047a6d2 ("netfilter: nftables: add catch-all set element support") Cc: stable@vger.kernel.org Reported-by: lonial con Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_tables_api.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index b3db97440db1..50b595ef6389 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -6578,7 +6578,7 @@ static int nft_setelem_catchall_deactivate(const struct net *net, list_for_each_entry(catchall, &set->catchall_list, list) { ext = nft_set_elem_ext(set, catchall->elem); - if (!nft_is_active(net, ext)) + if (!nft_is_active_next(net, ext)) continue; kfree(elem->priv); -- cgit From 3ce67e3793f48c1b9635beb9bb71116ca1e51b58 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Sun, 14 Jan 2024 23:53:39 +0100 Subject: netfilter: nf_tables: do not allow mismatch field size and set key length The set description provides the size of each field in the set whose sum should not mismatch the set key length, bail out otherwise. I did not manage to crash nft_set_pipapo with mismatch fields and set key length so far, but this is UB which must be disallowed. Fixes: f3a2181e16f1 ("netfilter: nf_tables: Support for sets with multiple ranged fields") Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_tables_api.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'net') diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 50b595ef6389..e9fa4a32c093 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -4813,8 +4813,8 @@ static int nft_set_desc_concat_parse(const struct nlattr *attr, static int nft_set_desc_concat(struct nft_set_desc *desc, const struct nlattr *nla) { + u32 num_regs = 0, key_num_regs = 0; struct nlattr *attr; - u32 num_regs = 0; int rem, err, i; nla_for_each_nested(attr, nla, rem) { @@ -4829,6 +4829,10 @@ static int nft_set_desc_concat(struct nft_set_desc *desc, for (i = 0; i < desc->field_count; i++) num_regs += DIV_ROUND_UP(desc->field_len[i], sizeof(u32)); + key_num_regs = DIV_ROUND_UP(desc->klen, sizeof(u32)); + if (key_num_regs != num_regs) + return -EINVAL; + if (num_regs > NFT_REG32_COUNT) return -E2BIG; -- cgit From 6b1ca88e4bb63673dc9f9c7f23c899f22c3cb17a Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 15 Jan 2024 00:14:38 +0100 Subject: netfilter: nf_tables: skip dead set elements in netlink dump Delete from packet path relies on the garbage collector to purge elements with NFT_SET_ELEM_DEAD_BIT on. Skip these dead elements from nf_tables_dump_setelem() path, I very rarely see tests/shell/testcases/maps/typeof_maps_add_delete reports [DUMP FAILED] showing a mismatch in the expected output with an element that should not be there. If the netlink dump happens before GC worker run, it might show dead elements in the ruleset listing. nft_rhash_get() already skips dead elements in nft_rhash_cmp(), therefore, it already does not show the element when getting a single element via netlink control plane. Fixes: 5f68718b34a5 ("netfilter: nf_tables: GC transaction API to avoid race with control plane") Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_tables_api.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index e9fa4a32c093..88a6a858383b 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -5718,7 +5718,7 @@ static int nf_tables_dump_setelem(const struct nft_ctx *ctx, const struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); struct nft_set_dump_args *args; - if (nft_set_elem_expired(ext)) + if (nft_set_elem_expired(ext) || nft_set_elem_is_dead(ext)) return 0; args = container_of(iter, struct nft_set_dump_args, iter); -- cgit From 113661e07460a6604aacc8ae1b23695a89e7d4b3 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 15 Jan 2024 12:50:29 +0100 Subject: netfilter: nf_tables: reject NFT_SET_CONCAT with not field length description It is still possible to set on the NFT_SET_CONCAT flag by specifying a set size and no field description, report EINVAL in such case. Fixes: 1b6345d4160e ("netfilter: nf_tables: check NFT_SET_CONCAT flag if field_count is specified") Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_tables_api.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'net') diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 88a6a858383b..4b55533ce5ca 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -5070,8 +5070,12 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info, if (err < 0) return err; - if (desc.field_count > 1 && !(flags & NFT_SET_CONCAT)) + if (desc.field_count > 1) { + if (!(flags & NFT_SET_CONCAT)) + return -EINVAL; + } else if (flags & NFT_SET_CONCAT) { return -EINVAL; + } } else if (flags & NFT_SET_CONCAT) { return -EINVAL; } -- cgit From d6938c1c76c64f42363d0d1f051e1b4641c2ad40 Mon Sep 17 00:00:00 2001 From: Fedor Pchelkin Date: Mon, 15 Jan 2024 17:39:22 +0300 Subject: ipvs: avoid stat macros calls from preemptible context Inside decrement_ttl() upon discovering that the packet ttl has exceeded, __IP_INC_STATS and __IP6_INC_STATS macros can be called from preemptible context having the following backtrace: check_preemption_disabled: 48 callbacks suppressed BUG: using __this_cpu_add() in preemptible [00000000] code: curl/1177 caller is decrement_ttl+0x217/0x830 CPU: 5 PID: 1177 Comm: curl Not tainted 6.7.0+ #34 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 04/01/2014 Call Trace: dump_stack_lvl+0xbd/0xe0 check_preemption_disabled+0xd1/0xe0 decrement_ttl+0x217/0x830 __ip_vs_get_out_rt+0x4e0/0x1ef0 ip_vs_nat_xmit+0x205/0xcd0 ip_vs_in_hook+0x9b1/0x26a0 nf_hook_slow+0xc2/0x210 nf_hook+0x1fb/0x770 __ip_local_out+0x33b/0x640 ip_local_out+0x2a/0x490 __ip_queue_xmit+0x990/0x1d10 __tcp_transmit_skb+0x288b/0x3d10 tcp_connect+0x3466/0x5180 tcp_v4_connect+0x1535/0x1bb0 __inet_stream_connect+0x40d/0x1040 inet_stream_connect+0x57/0xa0 __sys_connect_file+0x162/0x1a0 __sys_connect+0x137/0x160 __x64_sys_connect+0x72/0xb0 do_syscall_64+0x6f/0x140 entry_SYSCALL_64_after_hwframe+0x6e/0x76 RIP: 0033:0x7fe6dbbc34e0 Use the corresponding preemption-aware variants: IP_INC_STATS and IP6_INC_STATS. Found by Linux Verification Center (linuxtesting.org). Fixes: 8d8e20e2d7bb ("ipvs: Decrement ttl") Signed-off-by: Fedor Pchelkin Acked-by: Julian Anastasov Acked-by: Simon Horman Signed-off-by: Pablo Neira Ayuso --- net/netfilter/ipvs/ip_vs_xmit.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 9193e109e6b3..65e0259178da 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -271,7 +271,7 @@ static inline bool decrement_ttl(struct netns_ipvs *ipvs, skb->dev = dst->dev; icmpv6_send(skb, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT, 0); - __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); + IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); return false; } @@ -286,7 +286,7 @@ static inline bool decrement_ttl(struct netns_ipvs *ipvs, { if (ip_hdr(skb)->ttl <= 1) { /* Tell the sender its packet died... */ - __IP_INC_STATS(net, IPSTATS_MIB_INHDRERRORS); + IP_INC_STATS(net, IPSTATS_MIB_INHDRERRORS); icmp_send(skb, ICMP_TIME_EXCEEDED, ICMP_EXC_TTL, 0); return false; } -- cgit