From e2c8d550a973bb34fc28bc8d0ec996f84562fb8a Mon Sep 17 00:00:00 2001 From: Shakeel Butt Date: Wed, 2 Jan 2019 19:14:31 -0800 Subject: netfilter: ebtables: account ebt_table_info to kmemcg The [ip,ip6,arp]_tables use x_tables_info internally and the underlying memory is already accounted to kmemcg. Do the same for ebtables. The syzbot, by using setsockopt(EBT_SO_SET_ENTRIES), was able to OOM the whole system from a restricted memcg, a potential DoS. By accounting the ebt_table_info, the memory used for ebt_table_info can be contained within the memcg of the allocating process. However the lifetime of ebt_table_info is independent of the allocating process and is tied to the network namespace. So, the oom-killer will not be able to relieve the memory pressure due to ebt_table_info memory. The memory for ebt_table_info is allocated through vmalloc. Currently vmalloc does not handle the oom-killed allocating process correctly and one large allocation can bypass memcg limit enforcement. So, with this patch, at least the small allocations will be contained. For large allocations, we need to fix vmalloc. Reported-by: syzbot+7713f3aa67be76b1552c@syzkaller.appspotmail.com Signed-off-by: Shakeel Butt Reviewed-by: Kirill Tkhai Signed-off-by: Pablo Neira Ayuso --- net/bridge/netfilter/ebtables.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'net/bridge') diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 491828713e0b..5e55cef0cec3 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -1137,14 +1137,16 @@ static int do_replace(struct net *net, const void __user *user, tmp.name[sizeof(tmp.name) - 1] = 0; countersize = COUNTER_OFFSET(tmp.nentries) * nr_cpu_ids; - newinfo = vmalloc(sizeof(*newinfo) + countersize); + newinfo = __vmalloc(sizeof(*newinfo) + countersize, GFP_KERNEL_ACCOUNT, + PAGE_KERNEL); if (!newinfo) return -ENOMEM; if (countersize) memset(newinfo->counters, 0, countersize); - newinfo->entries = vmalloc(tmp.entries_size); + newinfo->entries = __vmalloc(tmp.entries_size, GFP_KERNEL_ACCOUNT, + PAGE_KERNEL); if (!newinfo->entries) { ret = -ENOMEM; goto free_newinfo; -- cgit v1.2.3 From 28c1382fa28f2e2d9d0d6f25ae879b5af2ecbd03 Mon Sep 17 00:00:00 2001 From: Yunjian Wang Date: Thu, 17 Jan 2019 09:46:41 +0800 Subject: net: bridge: Fix ethernet header pointer before check skb forwardable The skb header should be set to ethernet header before using is_skb_forwardable. Because the ethernet header length has been considered in is_skb_forwardable(including dev->hard_header_len length). To reproduce the issue: 1, add 2 ports on linux bridge br using following commands: $ brctl addbr br $ brctl addif br eth0 $ brctl addif br eth1 2, the MTU of eth0 and eth1 is 1500 3, send a packet(Data 1480, UDP 8, IP 20, Ethernet 14, VLAN 4) from eth0 to eth1 So the expect result is packet larger than 1500 cannot pass through eth0 and eth1. But currently, the packet passes through success, it means eth1's MTU limit doesn't take effect. Fixes: f6367b4660dd ("bridge: use is_skb_forwardable in forward path") Cc: bridge@lists.linux-foundation.org Cc: Nkolay Aleksandrov Cc: Roopa Prabhu Cc: Stephen Hemminger Signed-off-by: Yunjian Wang Signed-off-by: David S. Miller --- net/bridge/br_forward.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) (limited to 'net/bridge') diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c index 2cb8da465b98..48ddc60b4fbd 100644 --- a/net/bridge/br_forward.c +++ b/net/bridge/br_forward.c @@ -36,10 +36,10 @@ static inline int should_deliver(const struct net_bridge_port *p, int br_dev_queue_push_xmit(struct net *net, struct sock *sk, struct sk_buff *skb) { + skb_push(skb, ETH_HLEN); if (!is_skb_forwardable(skb->dev, skb)) goto drop; - skb_push(skb, ETH_HLEN); br_drop_fake_rtable(skb); if (skb->ip_summed == CHECKSUM_PARTIAL && @@ -98,12 +98,11 @@ static void __br_forward(const struct net_bridge_port *to, net = dev_net(indev); } else { if (unlikely(netpoll_tx_running(to->br->dev))) { - if (!is_skb_forwardable(skb->dev, skb)) { + skb_push(skb, ETH_HLEN); + if (!is_skb_forwardable(skb->dev, skb)) kfree_skb(skb); - } else { - skb_push(skb, ETH_HLEN); + else br_netpoll_send_skb(to, skb); - } return; } br_hook = NF_BR_LOCAL_OUT; -- cgit v1.2.3 From 6c57f0458022298e4da1729c67bd33ce41c14e7a Mon Sep 17 00:00:00 2001 From: Ross Lagerwall Date: Thu, 17 Jan 2019 15:34:38 +0000 Subject: net: Fix usage of pskb_trim_rcsum In certain cases, pskb_trim_rcsum() may change skb pointers. Reinitialize header pointers afterwards to avoid potential use-after-frees. Add a note in the documentation of pskb_trim_rcsum(). Found by KASAN. Signed-off-by: Ross Lagerwall Signed-off-by: David S. Miller --- drivers/net/ppp/pppoe.c | 1 + include/linux/skbuff.h | 1 + net/bridge/br_netfilter_ipv6.c | 1 + net/bridge/netfilter/nft_reject_bridge.c | 1 + net/ipv4/ip_input.c | 1 + 5 files changed, 5 insertions(+) (limited to 'net/bridge') diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c index 62dc564b251d..f22639f0116a 100644 --- a/drivers/net/ppp/pppoe.c +++ b/drivers/net/ppp/pppoe.c @@ -445,6 +445,7 @@ static int pppoe_rcv(struct sk_buff *skb, struct net_device *dev, if (pskb_trim_rcsum(skb, len)) goto drop; + ph = pppoe_hdr(skb); pn = pppoe_pernet(dev_net(dev)); /* Note that get_item does a sock_hold(), so sk_pppox(po) diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 93f56fddd92a..95d25b010a25 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3218,6 +3218,7 @@ int pskb_trim_rcsum_slow(struct sk_buff *skb, unsigned int len); * * This is exactly the same as pskb_trim except that it ensures the * checksum of received packets are still valid after the operation. + * It can change skb pointers. */ static inline int pskb_trim_rcsum(struct sk_buff *skb, unsigned int len) diff --git a/net/bridge/br_netfilter_ipv6.c b/net/bridge/br_netfilter_ipv6.c index 94039f588f1d..564710f88f93 100644 --- a/net/bridge/br_netfilter_ipv6.c +++ b/net/bridge/br_netfilter_ipv6.c @@ -131,6 +131,7 @@ int br_validate_ipv6(struct net *net, struct sk_buff *skb) IPSTATS_MIB_INDISCARDS); goto drop; } + hdr = ipv6_hdr(skb); } if (hdr->nexthdr == NEXTHDR_HOP && br_nf_check_hbh_len(skb)) goto drop; diff --git a/net/bridge/netfilter/nft_reject_bridge.c b/net/bridge/netfilter/nft_reject_bridge.c index 08cbed7d940e..419e8edf23ba 100644 --- a/net/bridge/netfilter/nft_reject_bridge.c +++ b/net/bridge/netfilter/nft_reject_bridge.c @@ -229,6 +229,7 @@ static bool reject6_br_csum_ok(struct sk_buff *skb, int hook) pskb_trim_rcsum(skb, ntohs(ip6h->payload_len) + sizeof(*ip6h))) return false; + ip6h = ipv6_hdr(skb); thoff = ipv6_skip_exthdr(skb, ((u8*)(ip6h+1) - skb->data), &proto, &fo); if (thoff < 0 || thoff >= skb->len || (fo & htons(~0x7)) != 0) return false; diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index 26921f6b3b92..51d8efba6de2 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -488,6 +488,7 @@ static struct sk_buff *ip_rcv_core(struct sk_buff *skb, struct net *net) goto drop; } + iph = ip_hdr(skb); skb->transport_header = skb->network_header + iph->ihl*4; /* Remove any debris in the socket control block */ -- cgit v1.2.3 From 710ae72877378e7cde611efd30fe90502a6e5b30 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Fri, 18 Jan 2019 15:58:00 +0000 Subject: net: bridge: Mark FDB entries that were added by user as such Externally learned entries can be added by a user or by a switch driver that is notifying the bridge driver about entries that were learned in hardware. In the first case, the entries are not marked with the 'added_by_user' flag, which causes switch drivers to ignore them and not offload them. The 'added_by_user' flag can be set on externally learned FDB entries based on the 'swdev_notify' parameter in br_fdb_external_learn_add(), which effectively means if the created / updated FDB entry was added by a user or not. Fixes: 816a3bed9549 ("switchdev: Add fdb.added_by_user to switchdev notifications") Signed-off-by: Ido Schimmel Reported-by: Alexander Petrovskiy Reviewed-by: Petr Machata Cc: Roopa Prabhu Cc: Nikolay Aleksandrov Cc: bridge@lists.linux-foundation.org Signed-off-by: David S. Miller --- net/bridge/br_fdb.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'net/bridge') diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index fe3c758791ca..9e14767500ea 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -1128,6 +1128,8 @@ int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p, err = -ENOMEM; goto err_unlock; } + if (swdev_notify) + fdb->added_by_user = 1; fdb->added_by_external_learn = 1; fdb_notify(br, fdb, RTM_NEWNEIGH, swdev_notify); } else { @@ -1147,6 +1149,9 @@ int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p, modified = true; } + if (swdev_notify) + fdb->added_by_user = 1; + if (modified) fdb_notify(br, fdb, RTM_NEWNEIGH, swdev_notify); } -- cgit v1.2.3