diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2016-01-12 18:57:02 -0800 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2016-01-12 18:57:02 -0800 |
commit | aee3bfa3307cd0da2126bdc0ea359dabea5ee8f7 (patch) | |
tree | 3d35c69e8fa835098bb90f77f30abed120681651 /net/netfilter/nf_tables_trace.c | |
parent | Merge branch 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6 (diff) | |
parent | net: bnxt: always return values from _bnxt_get_max_rings (diff) | |
download | linux-dev-aee3bfa3307cd0da2126bdc0ea359dabea5ee8f7.tar.xz linux-dev-aee3bfa3307cd0da2126bdc0ea359dabea5ee8f7.zip |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from Davic Miller:
1) Support busy polling generically, for all NAPI drivers. From Eric
Dumazet.
2) Add byte/packet counter support to nft_ct, from Floriani Westphal.
3) Add RSS/XPS support to mvneta driver, from Gregory Clement.
4) Implement IPV6_HDRINCL socket option for raw sockets, from Hannes
Frederic Sowa.
5) Add support for T6 adapter to cxgb4 driver, from Hariprasad Shenai.
6) Add support for VLAN device bridging to mlxsw switch driver, from
Ido Schimmel.
7) Add driver for Netronome NFP4000/NFP6000, from Jakub Kicinski.
8) Provide hwmon interface to mlxsw switch driver, from Jiri Pirko.
9) Reorganize wireless drivers into per-vendor directories just like we
do for ethernet drivers. From Kalle Valo.
10) Provide a way for administrators "destroy" connected sockets via the
SOCK_DESTROY socket netlink diag operation. From Lorenzo Colitti.
11) Add support to add/remove multicast routes via netlink, from Nikolay
Aleksandrov.
12) Make TCP keepalive settings per-namespace, from Nikolay Borisov.
13) Add forwarding and packet duplication facilities to nf_tables, from
Pablo Neira Ayuso.
14) Dead route support in MPLS, from Roopa Prabhu.
15) TSO support for thunderx chips, from Sunil Goutham.
16) Add driver for IBM's System i/p VNIC protocol, from Thomas Falcon.
17) Rationalize, consolidate, and more completely document the checksum
offloading facilities in the networking stack. From Tom Herbert.
18) Support aborting an ongoing scan in mac80211/cfg80211, from
Vidyullatha Kanchanapally.
19) Use per-bucket spinlock for bpf hash facility, from Tom Leiming.
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1375 commits)
net: bnxt: always return values from _bnxt_get_max_rings
net: bpf: reject invalid shifts
phonet: properly unshare skbs in phonet_rcv()
dwc_eth_qos: Fix dma address for multi-fragment skbs
phy: remove an unneeded condition
mdio: remove an unneed condition
mdio_bus: NULL dereference on allocation error
net: Fix typo in netdev_intersect_features
net: freescale: mac-fec: Fix build error from phy_device API change
net: freescale: ucc_geth: Fix build error from phy_device API change
bonding: Prevent IPv6 link local address on enslaved devices
IB/mlx5: Add flow steering support
net/mlx5_core: Export flow steering API
net/mlx5_core: Make ipv4/ipv6 location more clear
net/mlx5_core: Enable flow steering support for the IB driver
net/mlx5_core: Initialize namespaces only when supported by device
net/mlx5_core: Set priority attributes
net/mlx5_core: Connect flow tables
net/mlx5_core: Introduce modify flow table command
net/mlx5_core: Managing root flow table
...
Diffstat (limited to 'net/netfilter/nf_tables_trace.c')
-rw-r--r-- | net/netfilter/nf_tables_trace.c | 275 |
1 files changed, 275 insertions, 0 deletions
diff --git a/net/netfilter/nf_tables_trace.c b/net/netfilter/nf_tables_trace.c new file mode 100644 index 000000000000..e9e959f65d91 --- /dev/null +++ b/net/netfilter/nf_tables_trace.c @@ -0,0 +1,275 @@ +/* + * (C) 2015 Red Hat GmbH + * Author: Florian Westphal <fw@strlen.de> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/module.h> +#include <linux/static_key.h> +#include <linux/hash.h> +#include <linux/jhash.h> +#include <linux/if_vlan.h> +#include <linux/init.h> +#include <linux/skbuff.h> +#include <linux/netlink.h> +#include <linux/netfilter.h> +#include <linux/netfilter/nfnetlink.h> +#include <linux/netfilter/nf_tables.h> +#include <net/netfilter/nf_tables_core.h> +#include <net/netfilter/nf_tables.h> + +#define NFT_TRACETYPE_LL_HSIZE 20 +#define NFT_TRACETYPE_NETWORK_HSIZE 40 +#define NFT_TRACETYPE_TRANSPORT_HSIZE 20 + +DEFINE_STATIC_KEY_FALSE(nft_trace_enabled); +EXPORT_SYMBOL_GPL(nft_trace_enabled); + +static int trace_fill_id(struct sk_buff *nlskb, struct sk_buff *skb) +{ + __be32 id; + + /* using skb address as ID results in a limited number of + * values (and quick reuse). + * + * So we attempt to use as many skb members that will not + * change while skb is with netfilter. + */ + id = (__be32)jhash_2words(hash32_ptr(skb), skb_get_hash(skb), + skb->skb_iif); + + return nla_put_be32(nlskb, NFTA_TRACE_ID, id); +} + +static int trace_fill_header(struct sk_buff *nlskb, u16 type, + const struct sk_buff *skb, + int off, unsigned int len) +{ + struct nlattr *nla; + + if (len == 0) + return 0; + + nla = nla_reserve(nlskb, type, len); + if (!nla || skb_copy_bits(skb, off, nla_data(nla), len)) + return -1; + + return 0; +} + +static int nf_trace_fill_ll_header(struct sk_buff *nlskb, + const struct sk_buff *skb) +{ + struct vlan_ethhdr veth; + int off; + + BUILD_BUG_ON(sizeof(veth) > NFT_TRACETYPE_LL_HSIZE); + + off = skb_mac_header(skb) - skb->data; + if (off != -ETH_HLEN) + return -1; + + if (skb_copy_bits(skb, off, &veth, ETH_HLEN)) + return -1; + + veth.h_vlan_proto = skb->vlan_proto; + veth.h_vlan_TCI = htons(skb_vlan_tag_get(skb)); + veth.h_vlan_encapsulated_proto = skb->protocol; + + return nla_put(nlskb, NFTA_TRACE_LL_HEADER, sizeof(veth), &veth); +} + +static int nf_trace_fill_dev_info(struct sk_buff *nlskb, + const struct net_device *indev, + const struct net_device *outdev) +{ + if (indev) { + if (nla_put_be32(nlskb, NFTA_TRACE_IIF, + htonl(indev->ifindex))) + return -1; + + if (nla_put_be16(nlskb, NFTA_TRACE_IIFTYPE, + htons(indev->type))) + return -1; + } + + if (outdev) { + if (nla_put_be32(nlskb, NFTA_TRACE_OIF, + htonl(outdev->ifindex))) + return -1; + + if (nla_put_be16(nlskb, NFTA_TRACE_OIFTYPE, + htons(outdev->type))) + return -1; + } + + return 0; +} + +static int nf_trace_fill_pkt_info(struct sk_buff *nlskb, + const struct nft_pktinfo *pkt) +{ + const struct sk_buff *skb = pkt->skb; + unsigned int len = min_t(unsigned int, + pkt->xt.thoff - skb_network_offset(skb), + NFT_TRACETYPE_NETWORK_HSIZE); + int off = skb_network_offset(skb); + + if (trace_fill_header(nlskb, NFTA_TRACE_NETWORK_HEADER, skb, off, len)) + return -1; + + len = min_t(unsigned int, skb->len - pkt->xt.thoff, + NFT_TRACETYPE_TRANSPORT_HSIZE); + + if (trace_fill_header(nlskb, NFTA_TRACE_TRANSPORT_HEADER, skb, + pkt->xt.thoff, len)) + return -1; + + if (!skb_mac_header_was_set(skb)) + return 0; + + if (skb_vlan_tag_get(skb)) + return nf_trace_fill_ll_header(nlskb, skb); + + off = skb_mac_header(skb) - skb->data; + len = min_t(unsigned int, -off, NFT_TRACETYPE_LL_HSIZE); + return trace_fill_header(nlskb, NFTA_TRACE_LL_HEADER, + skb, off, len); +} + +static int nf_trace_fill_rule_info(struct sk_buff *nlskb, + const struct nft_traceinfo *info) +{ + if (!info->rule) + return 0; + + /* a continue verdict with ->type == RETURN means that this is + * an implicit return (end of chain reached). + * + * Since no rule matched, the ->rule pointer is invalid. + */ + if (info->type == NFT_TRACETYPE_RETURN && + info->verdict->code == NFT_CONTINUE) + return 0; + + return nla_put_be64(nlskb, NFTA_TRACE_RULE_HANDLE, + cpu_to_be64(info->rule->handle)); +} + +void nft_trace_notify(struct nft_traceinfo *info) +{ + const struct nft_pktinfo *pkt = info->pkt; + struct nfgenmsg *nfmsg; + struct nlmsghdr *nlh; + struct sk_buff *skb; + unsigned int size; + int event = (NFNL_SUBSYS_NFTABLES << 8) | NFT_MSG_TRACE; + + if (!nfnetlink_has_listeners(pkt->net, NFNLGRP_NFTRACE)) + return; + + size = nlmsg_total_size(sizeof(struct nfgenmsg)) + + nla_total_size(NFT_TABLE_MAXNAMELEN) + + nla_total_size(NFT_CHAIN_MAXNAMELEN) + + nla_total_size(sizeof(__be64)) + /* rule handle */ + nla_total_size(sizeof(__be32)) + /* trace type */ + nla_total_size(0) + /* VERDICT, nested */ + nla_total_size(sizeof(u32)) + /* verdict code */ + nla_total_size(NFT_CHAIN_MAXNAMELEN) + /* jump target */ + nla_total_size(sizeof(u32)) + /* id */ + nla_total_size(NFT_TRACETYPE_LL_HSIZE) + + nla_total_size(NFT_TRACETYPE_NETWORK_HSIZE) + + nla_total_size(NFT_TRACETYPE_TRANSPORT_HSIZE) + + nla_total_size(sizeof(u32)) + /* iif */ + nla_total_size(sizeof(__be16)) + /* iiftype */ + nla_total_size(sizeof(u32)) + /* oif */ + nla_total_size(sizeof(__be16)) + /* oiftype */ + nla_total_size(sizeof(u32)) + /* mark */ + nla_total_size(sizeof(u32)) + /* nfproto */ + nla_total_size(sizeof(u32)); /* policy */ + + skb = nlmsg_new(size, GFP_ATOMIC); + if (!skb) + return; + + nlh = nlmsg_put(skb, 0, 0, event, sizeof(struct nfgenmsg), 0); + if (!nlh) + goto nla_put_failure; + + nfmsg = nlmsg_data(nlh); + nfmsg->nfgen_family = info->basechain->type->family; + nfmsg->version = NFNETLINK_V0; + nfmsg->res_id = 0; + + if (nla_put_be32(skb, NFTA_TRACE_NFPROTO, htonl(pkt->pf))) + goto nla_put_failure; + + if (nla_put_be32(skb, NFTA_TRACE_TYPE, htonl(info->type))) + goto nla_put_failure; + + if (trace_fill_id(skb, pkt->skb)) + goto nla_put_failure; + + if (info->chain) { + if (nla_put_string(skb, NFTA_TRACE_CHAIN, + info->chain->name)) + goto nla_put_failure; + if (nla_put_string(skb, NFTA_TRACE_TABLE, + info->chain->table->name)) + goto nla_put_failure; + } + + if (nf_trace_fill_rule_info(skb, info)) + goto nla_put_failure; + + switch (info->type) { + case NFT_TRACETYPE_UNSPEC: + case __NFT_TRACETYPE_MAX: + break; + case NFT_TRACETYPE_RETURN: + case NFT_TRACETYPE_RULE: + if (nft_verdict_dump(skb, NFTA_TRACE_VERDICT, info->verdict)) + goto nla_put_failure; + break; + case NFT_TRACETYPE_POLICY: + if (nla_put_be32(skb, NFTA_TRACE_POLICY, + info->basechain->policy)) + goto nla_put_failure; + break; + } + + if (pkt->skb->mark && + nla_put_be32(skb, NFTA_TRACE_MARK, htonl(pkt->skb->mark))) + goto nla_put_failure; + + if (!info->packet_dumped) { + if (nf_trace_fill_dev_info(skb, pkt->in, pkt->out)) + goto nla_put_failure; + + if (nf_trace_fill_pkt_info(skb, pkt)) + goto nla_put_failure; + info->packet_dumped = true; + } + + nlmsg_end(skb, nlh); + nfnetlink_send(skb, pkt->net, 0, NFNLGRP_NFTRACE, 0, GFP_ATOMIC); + return; + + nla_put_failure: + WARN_ON_ONCE(1); + kfree_skb(skb); +} + +void nft_trace_init(struct nft_traceinfo *info, const struct nft_pktinfo *pkt, + const struct nft_verdict *verdict, + const struct nft_chain *chain) +{ + info->basechain = nft_base_chain(chain); + info->trace = true; + info->packet_dumped = false; + info->pkt = pkt; + info->verdict = verdict; +} |