From f307170d6e591a48529425b1ed6ca835790995a9 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 19 Jun 2015 17:23:37 -0500 Subject: [PATCH 1/7] netfilter: nf_queue: Don't recompute the hook_list head If someone sends packets from one of the netdevice ingress hooks to the a userspace queue, and then userspace later accepts the packet, the netfilter code can enter an infinite loop as the list head will never be found. Pass in the saved list_head to avoid this. Signed-off-by: "Eric W. Biederman" Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_queue.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c index cd60d397fe05..8a8b2abc35ff 100644 --- a/net/netfilter/nf_queue.c +++ b/net/netfilter/nf_queue.c @@ -213,7 +213,7 @@ void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict) if (verdict == NF_ACCEPT) { next_hook: - verdict = nf_iterate(&nf_hooks[entry->state.pf][entry->state.hook], + verdict = nf_iterate(entry->state.hook_list, skb, &entry->state, &elem); } From a1bc1b356a9d21bf29bc7c873718b5cacdf119b4 Mon Sep 17 00:00:00 2001 From: Bernhard Thaler Date: Sat, 20 Jun 2015 00:17:50 +0200 Subject: [PATCH 2/7] netfilter: bridge: fix CONFIG_NF_DEFRAG_IPV4/6 related warnings/errors br_nf_ip_fragment() is not needed when neither CONFIG_NF_DEFRAG_IPV4 nor CONFIG_NF_DEFRAG_IPV6 is set. struct brnf_frag_data must be available if either CONFIG_NF_DEFRAG_IPV4 or CONFIG_NF_DEFRAG_IPV6 is set. Fixes: efb6de9b4ba0 ("netfilter: bridge: forward IPv6 fragmented packets") Reported-by: kbuild test robot Signed-off-by: Bernhard Thaler Signed-off-by: Pablo Neira Ayuso --- net/bridge/br_netfilter_hooks.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index d89f4fac0bc5..8a394bd3af83 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -111,7 +111,7 @@ static inline __be16 pppoe_proto(const struct sk_buff *skb) /* largest possible L2 header, see br_nf_dev_queue_xmit() */ #define NF_BRIDGE_MAX_MAC_HEADER_LENGTH (PPPOE_SES_HLEN + ETH_HLEN) -#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV4) +#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV4) || IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) struct brnf_frag_data { char mac[NF_BRIDGE_MAX_MAC_HEADER_LENGTH]; u8 encap_size; @@ -694,6 +694,7 @@ static int br_nf_push_frag_xmit(struct sock *sk, struct sk_buff *skb) } #endif +#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV4) static int br_nf_ip_fragment(struct sock *sk, struct sk_buff *skb, int (*output)(struct sock *, struct sk_buff *)) { @@ -712,6 +713,7 @@ static int br_nf_ip_fragment(struct sock *sk, struct sk_buff *skb, return ip_do_fragment(sk, skb, output); } +#endif static unsigned int nf_bridge_mtu_reduction(const struct sk_buff *skb) { From 3bd229976f64bea64c60803f9fc8d9f0059ba2f2 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 30 Jun 2015 22:21:00 +0200 Subject: [PATCH 3/7] netfilter: arptables: use percpu jumpstack commit 482cfc318559 ("netfilter: xtables: avoid percpu ruleset duplication") Unlike ip and ip6tables, arp tables were never converted to use the percpu jump stack. It still uses the rule blob to store return address, which isn't safe anymore since we now share this blob among all processors. Because there is no TEE support for arptables, we don't need to cope with reentrancy, so we can use loocal variable to hold stack offset. Fixes: 482cfc318559 ("netfilter: xtables: avoid percpu ruleset duplication") Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/ipv4/netfilter/arp_tables.c | 25 ++++++++++++++++--------- 1 file changed, 16 insertions(+), 9 deletions(-) diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 95c9b6eece25..92305a1a021a 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -254,9 +254,10 @@ unsigned int arpt_do_table(struct sk_buff *skb, static const char nulldevname[IFNAMSIZ] __attribute__((aligned(sizeof(long)))); unsigned int verdict = NF_DROP; const struct arphdr *arp; - struct arpt_entry *e, *back; + struct arpt_entry *e, **jumpstack; const char *indev, *outdev; const void *table_base; + unsigned int cpu, stackidx = 0; const struct xt_table_info *private; struct xt_action_param acpar; unsigned int addend; @@ -270,15 +271,16 @@ unsigned int arpt_do_table(struct sk_buff *skb, local_bh_disable(); addend = xt_write_recseq_begin(); private = table->private; + cpu = smp_processor_id(); /* * Ensure we load private-> members after we've fetched the base * pointer. */ smp_read_barrier_depends(); table_base = private->entries; + jumpstack = (struct arpt_entry **)private->jumpstack[cpu]; e = get_entry(table_base, private->hook_entry[hook]); - back = get_entry(table_base, private->underflow[hook]); acpar.in = state->in; acpar.out = state->out; @@ -312,18 +314,23 @@ unsigned int arpt_do_table(struct sk_buff *skb, verdict = (unsigned int)(-v) - 1; break; } - e = back; - back = get_entry(table_base, back->comefrom); + if (stackidx == 0) { + e = get_entry(table_base, + private->underflow[hook]); + } else { + e = jumpstack[--stackidx]; + e = arpt_next_entry(e); + } continue; } if (table_base + v != arpt_next_entry(e)) { - /* Save old back ptr in next entry */ - struct arpt_entry *next = arpt_next_entry(e); - next->comefrom = (void *)back - table_base; - /* set back pointer to next entry */ - back = next; + if (stackidx >= private->stacksize) { + verdict = NF_DROP; + break; + } + jumpstack[stackidx++] = e; } e = get_entry(table_base, v); From dd302b59bde0149c20df7278c0d36c765e66afbd Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 30 Jun 2015 22:27:51 +0200 Subject: [PATCH 4/7] netfilter: bridge: don't leak skb in error paths br_nf_dev_queue_xmit must free skb in its error path. NF_DROP is misleading -- its an okfn, not a netfilter hook. Fixes: 462fb2af9788a ("bridge : Sanitize skb before it enters the IP stack") Fixes: efb6de9b4ba00 ("netfilter: bridge: forward IPv6 fragmented packets") Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/bridge/br_netfilter_hooks.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index 8a394bd3af83..c8b9bcfe997e 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -744,7 +744,7 @@ static int br_nf_dev_queue_xmit(struct sock *sk, struct sk_buff *skb) struct brnf_frag_data *data; if (br_validate_ipv4(skb)) - return NF_DROP; + goto drop; IPCB(skb)->frag_max_size = nf_bridge->frag_max_size; @@ -769,7 +769,7 @@ static int br_nf_dev_queue_xmit(struct sock *sk, struct sk_buff *skb) struct brnf_frag_data *data; if (br_validate_ipv6(skb)) - return NF_DROP; + goto drop; IP6CB(skb)->frag_max_size = nf_bridge->frag_max_size; @@ -784,12 +784,16 @@ static int br_nf_dev_queue_xmit(struct sock *sk, struct sk_buff *skb) if (v6ops) return v6ops->fragment(sk, skb, br_nf_push_frag_xmit); - else - return -EMSGSIZE; + + kfree_skb(skb); + return -EMSGSIZE; } #endif nf_bridge_info_free(skb); return br_dev_queue_push_xmit(sk, skb); + drop: + kfree_skb(skb); + return 0; } /* PF_BRIDGE/POST_ROUTING ********************************************/ From 6742b9e310bcf511b876532846e5302b07b7fedc Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Wed, 1 Jul 2015 16:14:25 +0200 Subject: [PATCH 5/7] netfilter: nfnetlink: keep going batch handling on missing modules After a fresh boot with no modules in place at all and a large rulesets, the existing nfnetlink_rcv_batch() funcion can take long time to commit the ruleset due to the many abort path. This is specifically a problem for the existing client of this code, ie. nf_tables, since it results in several synchronize_rcu() call in a row. This patch changes the policy to keep full batch processing on missing modules errors so we abort only once. Reported-by: Eric Leblond Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nfnetlink.c | 40 +++++++++++++++++++++++++-------------- 1 file changed, 26 insertions(+), 14 deletions(-) diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index 8b117c90ecd7..0c0e8ecf02ab 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -269,6 +269,12 @@ static void nfnl_err_deliver(struct list_head *err_list, struct sk_buff *skb) } } +enum { + NFNL_BATCH_FAILURE = (1 << 0), + NFNL_BATCH_DONE = (1 << 1), + NFNL_BATCH_REPLAY = (1 << 2), +}; + static void nfnetlink_rcv_batch(struct sk_buff *skb, struct nlmsghdr *nlh, u_int16_t subsys_id) { @@ -276,13 +282,15 @@ static void nfnetlink_rcv_batch(struct sk_buff *skb, struct nlmsghdr *nlh, struct net *net = sock_net(skb->sk); const struct nfnetlink_subsystem *ss; const struct nfnl_callback *nc; - bool success = true, done = false; static LIST_HEAD(err_list); + u32 status; int err; if (subsys_id >= NFNL_SUBSYS_COUNT) return netlink_ack(skb, nlh, -EINVAL); replay: + status = 0; + skb = netlink_skb_clone(oskb, GFP_KERNEL); if (!skb) return netlink_ack(oskb, nlh, -ENOMEM); @@ -336,10 +344,10 @@ replay: if (type == NFNL_MSG_BATCH_BEGIN) { /* Malformed: Batch begin twice */ nfnl_err_reset(&err_list); - success = false; + status |= NFNL_BATCH_FAILURE; goto done; } else if (type == NFNL_MSG_BATCH_END) { - done = true; + status |= NFNL_BATCH_DONE; goto done; } else if (type < NLMSG_MIN_TYPE) { err = -EINVAL; @@ -382,11 +390,8 @@ replay: * original skb. */ if (err == -EAGAIN) { - nfnl_err_reset(&err_list); - ss->abort(oskb); - nfnl_unlock(subsys_id); - kfree_skb(skb); - goto replay; + status |= NFNL_BATCH_REPLAY; + goto next; } } ack: @@ -402,7 +407,7 @@ ack: */ nfnl_err_reset(&err_list); netlink_ack(skb, nlmsg_hdr(oskb), -ENOMEM); - success = false; + status |= NFNL_BATCH_FAILURE; goto done; } /* We don't stop processing the batch on errors, thus, @@ -410,19 +415,26 @@ ack: * triggers. */ if (err) - success = false; + status |= NFNL_BATCH_FAILURE; } - +next: msglen = NLMSG_ALIGN(nlh->nlmsg_len); if (msglen > skb->len) msglen = skb->len; skb_pull(skb, msglen); } done: - if (success && done) - ss->commit(oskb); - else + if (status & NFNL_BATCH_REPLAY) { ss->abort(oskb); + nfnl_err_reset(&err_list); + nfnl_unlock(subsys_id); + kfree_skb(skb); + goto replay; + } else if (status == NFNL_BATCH_DONE) { + ss->commit(oskb); + } else { + ss->abort(oskb); + } nfnl_err_deliver(&err_list, oskb); nfnl_unlock(subsys_id); From 91c269a0d3eadd63f7112411ee812fbc170dc488 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 6 Jul 2015 20:55:35 +0200 Subject: [PATCH 6/7] MAINTAINER: add bridge netfilter So scripts/get_maintainer.pl shows the Netfilter mailing lists. Reported-by: Julien Grall Signed-off-by: Pablo Neira Ayuso --- MAINTAINERS | 1 + 1 file changed, 1 insertion(+) diff --git a/MAINTAINERS b/MAINTAINERS index 993d4cfd5aa0..8183b4659a4d 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -6996,6 +6996,7 @@ F: include/uapi/linux/netfilter/ F: net/*/netfilter.c F: net/*/netfilter/ F: net/netfilter/ +F: net/bridge/br_netfilter*.c NETLABEL M: Paul Moore From 86e8971800381c3a8d8d9327f83b1f97ccb04a4f Mon Sep 17 00:00:00 2001 From: Julien Grall Date: Tue, 7 Jul 2015 15:55:21 +0100 Subject: [PATCH 7/7] netfilter: bridge: Use __in6_dev_get rather than in6_dev_get in br_validate_ipv6 The commit efb6de9b4ba0092b2c55f6a52d16294a8a698edd "netfilter: bridge: forward IPv6 fragmented packets" introduced a new function br_validate_ipv6 which take a reference on the inet6 device. Although, the reference is not released at the end. This will result to the impossibility to destroy any netdevice using ipv6 and bridge. It's possible to directly retrieve the inet6 device without taking a reference as all netfilter hooks are protected by rcu_read_lock via nf_hook_slow. Spotted while trying to destroy a Xen guest on the upstream Linux: "unregister_netdevice: waiting for vif1.0 to become free. Usage count = 1" Signed-off-by: Julien Grall Cc: Bernhard Thaler Cc: Pablo Neira Ayuso Cc: fw@strlen.de Cc: ian.campbell@citrix.com Cc: wei.liu2@citrix.com Cc: Bob Liu Acked-by: Stephen Hemminger Signed-off-by: Pablo Neira Ayuso --- net/bridge/br_netfilter_ipv6.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/bridge/br_netfilter_ipv6.c b/net/bridge/br_netfilter_ipv6.c index 6d12d2675c80..13b7d1e3d185 100644 --- a/net/bridge/br_netfilter_ipv6.c +++ b/net/bridge/br_netfilter_ipv6.c @@ -104,7 +104,7 @@ int br_validate_ipv6(struct sk_buff *skb) { const struct ipv6hdr *hdr; struct net_device *dev = skb->dev; - struct inet6_dev *idev = in6_dev_get(skb->dev); + struct inet6_dev *idev = __in6_dev_get(skb->dev); u32 pkt_len; u8 ip6h_len = sizeof(struct ipv6hdr);