diff options
author | David S. Miller <davem@davemloft.net> | 2019-09-13 14:22:43 +0100 |
---|---|---|
committer | David S. Miller <davem@davemloft.net> | 2019-09-13 14:22:43 +0100 |
commit | 022c10d6c73b0a4e67a0294e55b2310626f17f75 (patch) | |
tree | 7f735a8eac0ddd1166a8533d66da8036f4a7fb4b /net | |
parent | 172ca8308b0517ca2522a8c885755fd5c20294e7 (diff) | |
parent | 0d32e7048d927418300b9f5415ca546e44621ef1 (diff) |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/pablo/nf-next
Pablo Neira Ayuso says:
====================
Netfilter updates for net-next
The following patchset contains Netfilter updates for net-next:
1) Fix error path of nf_tables_updobj(), from Dan Carpenter.
2) Move large structure away from stack in the nf_tables offload
infrastructure, from Arnd Bergmann.
3) Move indirect flow_block logic to nf_tables_offload.
4) Support for synproxy objects, from Fernando Fernandez Mancera.
5) Support for fwd and dup offload.
6) Add __nft_offload_get_chain() helper, this implicitly fixes missing
mutex and check for offload flags in the indirect block support,
patch from wenxu.
7) Remove rules on device unregistration, from wenxu. This includes
two preparation patches to reuse nft_flow_offload_chain() and
nft_flow_offload_rule().
Large batch from Jeremy Sowden to make a second pass to the
CONFIG_HEADER_TEST support and a bit of housekeeping:
8) Missing include guard in conntrack label header, from Jeremy Sowden.
9) A few coding style errors: trailing whitespace, incorrect indent in
Kconfig, and semicolons at the end of function definitions.
10) Remove unused ipt_init() and ip6t_init() declarations.
11) Inline xt_hashlimit, ebt_802_3 and xt_physdev headers. They are
only used once.
12) Update include directive in several netfilter files.
13) Remove unused include/net/netfilter/ipv6/nf_conntrack_icmpv6.h.
14) Move nf_ip6_ext_hdr() to include/linux/netfilter_ipv6.h
15) Move several synproxy structure definitions to nf_synproxy.h
16) Move nf_bridge_frag_data structure to include/linux/netfilter_bridge.h
17) Clean up static inline definitions in nf_conntrack_ecache.h.
18) Replace defined(CONFIG...) || defined(CONFIG...MODULE) with IS_ENABLED(CONFIG...).
19) Missing inline function conditional definitions based on Kconfig
preferences in synproxy and nf_conntrack_timeout.
20) Update br_nf_pre_routing_ipv6() definition.
21) Move conntrack code in linux/skbuff.h to nf_conntrack headers.
22) Several patches to remove superfluous CONFIG_NETFILTER and
CONFIG_NF_CONNTRACK checks in headers, coming from the initial batch
support for CONFIG_HEADER_TEST for netfilter.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net')
29 files changed, 380 insertions, 112 deletions
diff --git a/net/bridge/netfilter/ebt_802_3.c b/net/bridge/netfilter/ebt_802_3.c index 2c8fe24400e5..68c2519bdc52 100644 --- a/net/bridge/netfilter/ebt_802_3.c +++ b/net/bridge/netfilter/ebt_802_3.c @@ -11,7 +11,13 @@ #include <linux/module.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter_bridge/ebtables.h> -#include <linux/netfilter_bridge/ebt_802_3.h> +#include <linux/skbuff.h> +#include <uapi/linux/netfilter_bridge/ebt_802_3.h> + +static struct ebt_802_3_hdr *ebt_802_3_hdr(const struct sk_buff *skb) +{ + return (struct ebt_802_3_hdr *)skb_mac_header(skb); +} static bool ebt_802_3_mt(const struct sk_buff *skb, struct xt_action_param *par) diff --git a/net/bridge/netfilter/nf_conntrack_bridge.c b/net/bridge/netfilter/nf_conntrack_bridge.c index 4f5444d2a526..8842798c29e6 100644 --- a/net/bridge/netfilter/nf_conntrack_bridge.c +++ b/net/bridge/netfilter/nf_conntrack_bridge.c @@ -17,7 +17,6 @@ #include <net/netfilter/nf_conntrack_bridge.h> #include <linux/netfilter/nf_tables.h> -#include <net/netfilter/ipv6/nf_defrag_ipv6.h> #include <net/netfilter/nf_tables.h> #include "../br_private.h" @@ -27,9 +26,9 @@ */ static int nf_br_ip_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, - struct nf_ct_bridge_frag_data *data, + struct nf_bridge_frag_data *data, int (*output)(struct net *, struct sock *sk, - const struct nf_ct_bridge_frag_data *data, + const struct nf_bridge_frag_data *data, struct sk_buff *)) { int frag_max_size = BR_INPUT_SKB_CB(skb)->frag_max_size; @@ -279,7 +278,7 @@ static unsigned int nf_ct_bridge_pre(void *priv, struct sk_buff *skb, } static void nf_ct_bridge_frag_save(struct sk_buff *skb, - struct nf_ct_bridge_frag_data *data) + struct nf_bridge_frag_data *data) { if (skb_vlan_tag_present(skb)) { data->vlan_present = true; @@ -294,10 +293,10 @@ static void nf_ct_bridge_frag_save(struct sk_buff *skb, static unsigned int nf_ct_bridge_refrag(struct sk_buff *skb, const struct nf_hook_state *state, int (*output)(struct net *, struct sock *sk, - const struct nf_ct_bridge_frag_data *data, + const struct nf_bridge_frag_data *data, struct sk_buff *)) { - struct nf_ct_bridge_frag_data data; + struct nf_bridge_frag_data data; if (!BR_INPUT_SKB_CB(skb)->frag_max_size) return NF_ACCEPT; @@ -320,7 +319,7 @@ nf_ct_bridge_refrag(struct sk_buff *skb, const struct nf_hook_state *state, /* Actually only slow path refragmentation needs this. */ static int nf_ct_bridge_frag_restore(struct sk_buff *skb, - const struct nf_ct_bridge_frag_data *data) + const struct nf_bridge_frag_data *data) { int err; @@ -341,7 +340,7 @@ static int nf_ct_bridge_frag_restore(struct sk_buff *skb, } static int nf_ct_bridge_refrag_post(struct net *net, struct sock *sk, - const struct nf_ct_bridge_frag_data *data, + const struct nf_bridge_frag_data *data, struct sk_buff *skb) { int err; diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index 69e76d677f9e..f17b402111ce 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -272,7 +272,7 @@ config IP_NF_TARGET_CLUSTERIP The CLUSTERIP target allows you to build load-balancing clusters of network servers without having a dedicated load-balancing router/server/switch. - + To compile it as a module, choose M here. If unsure, say N. config IP_NF_TARGET_ECN @@ -281,7 +281,7 @@ config IP_NF_TARGET_ECN depends on NETFILTER_ADVANCED ---help--- This option adds a `ECN' target, which can be used in the iptables mangle - table. + table. You can use this target to remove the ECN bits from the IPv4 header of an IP packet. This is particularly useful, if you need to work around @@ -306,7 +306,7 @@ config IP_NF_RAW This option adds a `raw' table to iptables. This table is the very first in the netfilter framework and hooks in at the PREROUTING and OUTPUT chains. - + If you want to compile it as a module, say M here and read <file:Documentation/kbuild/modules.rst>. If unsure, say `N'. @@ -318,7 +318,7 @@ config IP_NF_SECURITY help This option adds a `security' table to iptables, for use with Mandatory Access Control (MAC) policy. - + If unsure, say N. endif # IP_NF_IPTABLES diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile index c50e0ec095d2..7c497c78105f 100644 --- a/net/ipv4/netfilter/Makefile +++ b/net/ipv4/netfilter/Makefile @@ -31,7 +31,7 @@ obj-$(CONFIG_NFT_DUP_IPV4) += nft_dup_ipv4.o # flow table support obj-$(CONFIG_NF_FLOW_TABLE_IPV4) += nf_flow_table_ipv4.o -# generic IP tables +# generic IP tables obj-$(CONFIG_IP_NF_IPTABLES) += ip_tables.o # the three instances of ip_tables diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index 61819ed858b1..a9bff556d3b2 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -113,9 +113,9 @@ int __nf_ip6_route(struct net *net, struct dst_entry **dst, EXPORT_SYMBOL_GPL(__nf_ip6_route); int br_ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, - struct nf_ct_bridge_frag_data *data, + struct nf_bridge_frag_data *data, int (*output)(struct net *, struct sock *sk, - const struct nf_ct_bridge_frag_data *data, + const struct nf_bridge_frag_data *data, struct sk_buff *)) { int frag_max_size = BR_INPUT_SKB_CB(skb)->frag_max_size; diff --git a/net/ipv6/netfilter/ip6t_ipv6header.c b/net/ipv6/netfilter/ip6t_ipv6header.c index 0fc6326ef499..c52ff929c93b 100644 --- a/net/ipv6/netfilter/ip6t_ipv6header.c +++ b/net/ipv6/netfilter/ip6t_ipv6header.c @@ -16,7 +16,7 @@ #include <net/ipv6.h> #include <linux/netfilter/x_tables.h> -#include <linux/netfilter_ipv6/ip6_tables.h> +#include <linux/netfilter_ipv6.h> #include <linux/netfilter_ipv6/ip6t_ipv6header.h> MODULE_LICENSE("GPL"); @@ -42,7 +42,7 @@ ipv6header_mt6(const struct sk_buff *skb, struct xt_action_param *par) len = skb->len - ptr; temp = 0; - while (ip6t_ext_hdr(nexthdr)) { + while (nf_ip6_ext_hdr(nexthdr)) { const struct ipv6_opt_hdr *hp; struct ipv6_opt_hdr _hdr; int hdrlen; diff --git a/net/ipv6/netfilter/nf_log_ipv6.c b/net/ipv6/netfilter/nf_log_ipv6.c index f53bd8f01219..22b80db6d882 100644 --- a/net/ipv6/netfilter/nf_log_ipv6.c +++ b/net/ipv6/netfilter/nf_log_ipv6.c @@ -18,7 +18,7 @@ #include <net/route.h> #include <linux/netfilter.h> -#include <linux/netfilter_ipv6/ip6_tables.h> +#include <linux/netfilter_ipv6.h> #include <linux/netfilter/xt_LOG.h> #include <net/netfilter/nf_log.h> @@ -70,7 +70,7 @@ static void dump_ipv6_packet(struct net *net, struct nf_log_buf *m, fragment = 0; ptr = ip6hoff + sizeof(struct ipv6hdr); currenthdr = ih->nexthdr; - while (currenthdr != NEXTHDR_NONE && ip6t_ext_hdr(currenthdr)) { + while (currenthdr != NEXTHDR_NONE && nf_ip6_ext_hdr(currenthdr)) { struct ipv6_opt_hdr _hdr; const struct ipv6_opt_hdr *hp; diff --git a/net/ipv6/netfilter/nf_socket_ipv6.c b/net/ipv6/netfilter/nf_socket_ipv6.c index 437d95545c31..b9df879c48d3 100644 --- a/net/ipv6/netfilter/nf_socket_ipv6.c +++ b/net/ipv6/netfilter/nf_socket_ipv6.c @@ -12,7 +12,6 @@ #include <net/sock.h> #include <net/inet_sock.h> #include <net/inet6_hashtables.h> -#include <net/netfilter/ipv6/nf_defrag_ipv6.h> #include <net/netfilter/nf_socket.h> #if IS_ENABLED(CONFIG_NF_CONNTRACK) #include <net/netfilter/nf_conntrack.h> diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 0d65f4d39494..34ec7afec116 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -20,7 +20,7 @@ config NETFILTER_FAMILY_ARP bool config NETFILTER_NETLINK_ACCT -tristate "Netfilter NFACCT over NFNETLINK interface" + tristate "Netfilter NFACCT over NFNETLINK interface" depends on NETFILTER_ADVANCED select NETFILTER_NETLINK help @@ -34,7 +34,7 @@ config NETFILTER_NETLINK_QUEUE help If this option is enabled, the kernel will include support for queueing packets via NFNETLINK. - + config NETFILTER_NETLINK_LOG tristate "Netfilter LOG over NFNETLINK interface" default m if NETFILTER_ADVANCED=n @@ -1502,7 +1502,7 @@ config NETFILTER_XT_MATCH_REALM This option adds a `realm' match, which allows you to use the realm key from the routing subsystem inside iptables. - This match pretty much resembles the CONFIG_NET_CLS_ROUTE4 option + This match pretty much resembles the CONFIG_NET_CLS_ROUTE4 option in tc world. If you want to compile it as a module, say M here and read @@ -1523,7 +1523,7 @@ config NETFILTER_XT_MATCH_SCTP depends on NETFILTER_ADVANCED default IP_SCTP help - With this option enabled, you will be able to use the + With this option enabled, you will be able to use the `sctp' match in order to match on SCTP source/destination ports and SCTP chunk types. diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index 9270a7fae484..4fc075b612fe 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -124,7 +124,7 @@ nf_flow_table-objs := nf_flow_table_core.o nf_flow_table_ip.o obj-$(CONFIG_NF_FLOW_TABLE_INET) += nf_flow_table_inet.o -# generic X tables +# generic X tables obj-$(CONFIG_NETFILTER_XTABLES) += x_tables.o xt_tcpudp.o # combos diff --git a/net/netfilter/nf_conntrack_ecache.c b/net/netfilter/nf_conntrack_ecache.c index 5e2812ee2149..6fba74b5aaf7 100644 --- a/net/netfilter/nf_conntrack_ecache.c +++ b/net/netfilter/nf_conntrack_ecache.c @@ -24,6 +24,7 @@ #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_core.h> +#include <net/netfilter/nf_conntrack_ecache.h> #include <net/netfilter/nf_conntrack_extend.h> static DEFINE_MUTEX(nf_ct_ecache_mutex); diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index 65364de915d1..42557d2b6a90 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -25,8 +25,10 @@ #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_core.h> +#include <net/netfilter/nf_conntrack_ecache.h> #include <net/netfilter/nf_conntrack_expect.h> #include <net/netfilter/nf_conntrack_helper.h> +#include <net/netfilter/nf_conntrack_l4proto.h> #include <net/netfilter/nf_conntrack_tuple.h> #include <net/netfilter/nf_conntrack_zones.h> diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index 8d729e7c36ff..118f415928ae 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -21,10 +21,11 @@ #include <linux/rtnetlink.h> #include <net/netfilter/nf_conntrack.h> -#include <net/netfilter/nf_conntrack_l4proto.h> -#include <net/netfilter/nf_conntrack_helper.h> #include <net/netfilter/nf_conntrack_core.h> +#include <net/netfilter/nf_conntrack_ecache.h> #include <net/netfilter/nf_conntrack_extend.h> +#include <net/netfilter/nf_conntrack_helper.h> +#include <net/netfilter/nf_conntrack_l4proto.h> #include <net/netfilter/nf_log.h> static DEFINE_MUTEX(nf_ct_helper_mutex); diff --git a/net/netfilter/nf_conntrack_proto_icmpv6.c b/net/netfilter/nf_conntrack_proto_icmpv6.c index 7e317e6698ba..6f9144e1f1c1 100644 --- a/net/netfilter/nf_conntrack_proto_icmpv6.c +++ b/net/netfilter/nf_conntrack_proto_icmpv6.c @@ -22,7 +22,6 @@ #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/nf_conntrack_timeout.h> #include <net/netfilter/nf_conntrack_zones.h> -#include <net/netfilter/ipv6/nf_conntrack_icmpv6.h> #include <net/netfilter/nf_log.h> static const unsigned int nf_ct_icmpv6_timeout = 30*HZ; diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 88d4127df863..410809c669e1 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -1167,7 +1167,6 @@ static int __init nf_conntrack_standalone_init(void) if (ret < 0) goto out_start; - BUILD_BUG_ON(SKB_NFCT_PTRMASK != NFCT_PTRMASK); BUILD_BUG_ON(NFCT_INFOMASK <= IP_CT_NUMBER); #ifdef CONFIG_SYSCTL diff --git a/net/netfilter/nf_conntrack_timeout.c b/net/netfilter/nf_conntrack_timeout.c index 13d0f4a92647..14387e0b8008 100644 --- a/net/netfilter/nf_conntrack_timeout.c +++ b/net/netfilter/nf_conntrack_timeout.c @@ -19,6 +19,7 @@ #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/nf_conntrack_extend.h> +#include <net/netfilter/nf_conntrack_l4proto.h> #include <net/netfilter/nf_conntrack_timeout.h> struct nf_ct_timeout * diff --git a/net/netfilter/nf_dup_netdev.c b/net/netfilter/nf_dup_netdev.c index 5a35ef08c3cb..f108a76925dd 100644 --- a/net/netfilter/nf_dup_netdev.c +++ b/net/netfilter/nf_dup_netdev.c @@ -10,6 +10,7 @@ #include <linux/netfilter.h> #include <linux/netfilter/nf_tables.h> #include <net/netfilter/nf_tables.h> +#include <net/netfilter/nf_tables_offload.h> #include <net/netfilter/nf_dup_netdev.h> static void nf_do_netdev_egress(struct sk_buff *skb, struct net_device *dev) @@ -50,5 +51,25 @@ void nf_dup_netdev_egress(const struct nft_pktinfo *pkt, int oif) } EXPORT_SYMBOL_GPL(nf_dup_netdev_egress); +int nft_fwd_dup_netdev_offload(struct nft_offload_ctx *ctx, + struct nft_flow_rule *flow, + enum flow_action_id id, int oif) +{ + struct flow_action_entry *entry; + struct net_device *dev; + + /* nft_flow_rule_destroy() releases the reference on this device. */ + dev = dev_get_by_index(ctx->net, oif); + if (!dev) + return -EOPNOTSUPP; + + entry = &flow->rule->action.entries[ctx->num_actions++]; + entry->id = id; + entry->dev = dev; + + return 0; +} +EXPORT_SYMBOL_GPL(nft_fwd_dup_netdev_offload); + MODULE_LICENSE("GPL"); MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>"); diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index 80a8f9ae4c93..09310a1bd91f 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -11,6 +11,7 @@ #include <net/netfilter/nf_flow_table.h> #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_core.h> +#include <net/netfilter/nf_conntrack_l4proto.h> #include <net/netfilter/nf_conntrack_tuple.h> struct flow_offload_entry { diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index 3f6023ed4966..bfc555fcbc72 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -18,12 +18,12 @@ #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_core.h> -#include <net/netfilter/nf_nat.h> -#include <net/netfilter/nf_nat_helper.h> #include <net/netfilter/nf_conntrack_helper.h> #include <net/netfilter/nf_conntrack_seqadj.h> #include <net/netfilter/nf_conntrack_zones.h> -#include <linux/netfilter/nf_nat.h> +#include <net/netfilter/nf_nat.h> +#include <net/netfilter/nf_nat_helper.h> +#include <uapi/linux/netfilter/nf_nat.h> #include "nf_internals.h" diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 013d28899cab..e4a68dc42694 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -2853,7 +2853,7 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk, return nft_table_validate(net, table); if (chain->flags & NFT_CHAIN_HW_OFFLOAD) { - flow = nft_flow_rule_create(rule); + flow = nft_flow_rule_create(net, rule); if (IS_ERR(flow)) return PTR_ERR(flow); @@ -5151,7 +5151,7 @@ static int nf_tables_updobj(const struct nft_ctx *ctx, newobj = nft_obj_init(ctx, type, attr); if (IS_ERR(newobj)) { err = PTR_ERR(newobj); - goto err1; + goto err_free_trans; } nft_trans_obj(trans) = obj; @@ -5160,9 +5160,9 @@ static int nf_tables_updobj(const struct nft_ctx *ctx, list_add_tail(&trans->list, &ctx->net->nft.commit_list); return 0; -err1: + +err_free_trans: kfree(trans); - kfree(newobj); return err; } @@ -7669,11 +7669,6 @@ static struct pernet_operations nf_tables_net_ops = { .exit = nf_tables_exit_net, }; -static struct flow_indr_block_ing_entry block_ing_entry = { - .cb = nft_indr_block_get_and_ing_cmd, - .list = LIST_HEAD_INIT(block_ing_entry.list), -}; - static int __init nf_tables_module_init(void) { int err; @@ -7699,14 +7694,20 @@ static int __init nf_tables_module_init(void) if (err < 0) goto err4; + err = nft_offload_init(); + if (err < 0) + goto err5; + /* must be last */ err = nfnetlink_subsys_register(&nf_tables_subsys); if (err < 0) - goto err5; + goto err6; nft_chain_route_init(); - flow_indr_add_block_ing_cb(&block_ing_entry); + return err; +err6: + nft_offload_exit(); err5: rhltable_destroy(&nft_objname_ht); err4: @@ -7722,8 +7723,8 @@ err1: static void __exit nf_tables_module_exit(void) { - flow_indr_del_block_ing_cb(&block_ing_entry); nfnetlink_subsys_unregister(&nf_tables_subsys); + nft_offload_exit(); unregister_netdevice_notifier(&nf_tables_flowtable_notifier); nft_chain_filter_fini(); nft_chain_route_fini(); diff --git a/net/netfilter/nf_tables_offload.c b/net/netfilter/nf_tables_offload.c index 3c2725ade61b..21bb772cb4b7 100644 --- a/net/netfilter/nf_tables_offload.c +++ b/net/netfilter/nf_tables_offload.c @@ -28,13 +28,10 @@ static struct nft_flow_rule *nft_flow_rule_alloc(int num_actions) return flow; } -struct nft_flow_rule *nft_flow_rule_create(const struct nft_rule *rule) +struct nft_flow_rule *nft_flow_rule_create(struct net *net, + const struct nft_rule *rule) { - struct nft_offload_ctx ctx = { - .dep = { - .type = NFT_OFFLOAD_DEP_UNSPEC, - }, - }; + struct nft_offload_ctx *ctx; struct nft_flow_rule *flow; int num_actions = 0, err; struct nft_expr *expr; @@ -52,21 +49,32 @@ struct nft_flow_rule *nft_flow_rule_create(const struct nft_rule *rule) return ERR_PTR(-ENOMEM); expr = nft_expr_first(rule); + + ctx = kzalloc(sizeof(struct nft_offload_ctx), GFP_KERNEL); + if (!ctx) { + err = -ENOMEM; + goto err_out; + } + ctx->net = net; + ctx->dep.type = NFT_OFFLOAD_DEP_UNSPEC; + while (expr->ops && expr != nft_expr_last(rule)) { if (!expr->ops->offload) { err = -EOPNOTSUPP; goto err_out; } - err = expr->ops->offload(&ctx, flow, expr); + err = expr->ops->offload(ctx, flow, expr); if (err < 0) goto err_out; expr = nft_expr_next(expr); } - flow->proto = ctx.dep.l3num; + flow->proto = ctx->dep.l3num; + kfree(ctx); return flow; err_out: + kfree(ctx); nft_flow_rule_destroy(flow); return ERR_PTR(err); @@ -74,6 +82,19 @@ err_out: void nft_flow_rule_destroy(struct nft_flow_rule *flow) { + struct flow_action_entry *entry; + int i; + + flow_action_for_each(i, entry, &flow->rule->action) { + switch (entry->id) { + case FLOW_ACTION_REDIRECT: + case FLOW_ACTION_MIRRED: + dev_put(entry->dev); + break; + default: + break; + } + } kfree(flow->rule); kfree(flow); } @@ -134,20 +155,20 @@ int nft_chain_offload_priority(struct nft_base_chain *basechain) return 0; } -static int nft_flow_offload_rule(struct nft_trans *trans, +static int nft_flow_offload_rule(struct nft_chain *chain, + struct nft_rule *rule, + struct nft_flow_rule *flow, enum flow_cls_command command) { - struct nft_flow_rule *flow = nft_trans_flow_rule(trans); - struct nft_rule *rule = nft_trans_rule(trans); struct flow_cls_offload cls_flow = {}; struct nft_base_chain *basechain; struct netlink_ext_ack extack; __be16 proto = ETH_P_ALL; - if (!nft_is_base_chain(trans->ctx.chain)) + if (!nft_is_base_chain(chain)) return -EOPNOTSUPP; - basechain = nft_base_chain(trans->ctx.chain); + basechain = nft_base_chain(chain); if (flow) proto = flow->proto; @@ -273,12 +294,13 @@ static int nft_indr_block_offload_cmd(struct nft_base_chain *chain, #define FLOW_SETUP_BLOCK TC_SETUP_BLOCK -static int nft_flow_offload_chain(struct nft_trans *trans, +static int nft_flow_offload_chain(struct nft_chain *chain, + u8 *ppolicy, enum flow_block_command cmd) { - struct nft_chain *chain = trans->ctx.chain; struct nft_base_chain *basechain; struct net_device *dev; + u8 policy; if (!nft_is_base_chain(chain)) return -EOPNOTSUPP; @@ -288,10 +310,10 @@ static int nft_flow_offload_chain(struct nft_trans *trans, if (!dev) return -EOPNOTSUPP; + policy = ppolicy ? *ppolicy : basechain->policy; + /* Only default policy to accept is supported for now. */ - if (cmd == FLOW_BLOCK_BIND && - nft_trans_chain_policy(trans) != -1 && - nft_trans_chain_policy(trans) != NF_ACCEPT) + if (cmd == FLOW_BLOCK_BIND && policy != -1 && policy != NF_ACCEPT) return -EOPNOTSUPP; if (dev->netdev_ops->ndo_setup_tc) @@ -304,6 +326,7 @@ int nft_flow_rule_offload_commit(struct net *net) { struct nft_trans *trans; int err = 0; + u8 policy; list_for_each_entry(trans, &net->nft.commit_list, list) { if (trans->ctx.family != NFPROTO_NETDEV) @@ -314,13 +337,17 @@ int nft_flow_rule_offload_commit(struct net *net) if (!(trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD)) continue; - err = nft_flow_offload_chain(trans, FLOW_BLOCK_BIND); + policy = nft_trans_chain_policy(trans); + err = nft_flow_offload_chain(trans->ctx.chain, &policy, + FLOW_BLOCK_BIND); break; case NFT_MSG_DELCHAIN: if (!(trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD)) continue; - err = nft_flow_offload_chain(trans, FLOW_BLOCK_UNBIND); + policy = nft_trans_chain_policy(trans); + err = nft_flow_offload_chain(trans->ctx.chain, &policy, + FLOW_BLOCK_BIND); break; case NFT_MSG_NEWRULE: if (!(trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD)) @@ -330,14 +357,20 @@ int nft_flow_rule_offload_commit(struct net *net) !(trans->ctx.flags & NLM_F_APPEND)) return -EOPNOTSUPP; - err = nft_flow_offload_rule(trans, FLOW_CLS_REPLACE); + err = nft_flow_offload_rule(trans->ctx.chain, + nft_trans_rule(trans), + nft_trans_flow_rule(trans), + FLOW_CLS_REPLACE); nft_flow_rule_destroy(nft_trans_flow_rule(trans)); break; case NFT_MSG_DELRULE: if (!(trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD)) continue; - err = nft_flow_offload_rule(trans, FLOW_CLS_DESTROY); + err = nft_flow_offload_rule(trans->ctx.chain, + nft_trans_rule(trans), + nft_trans_flow_rule(trans), + FLOW_CLS_DESTROY); break; } @@ -348,32 +381,103 @@ int nft_flow_rule_offload_commit(struct net *net) return err; } -void nft_indr_block_get_and_ing_cmd(struct net_device *dev, - flow_indr_block_bind_cb_t *cb, - void *cb_priv, - enum flow_block_command command) +static struct nft_chain *__nft_offload_get_chain(struct net_device *dev) { + struct nft_base_chain *basechain; struct net *net = dev_net(dev); const struct nft_table *table; - const struct nft_chain *chain; + struct nft_chain *chain; - list_for_each_entry_rcu(table, &net->nft.tables, list) { + list_for_each_entry(table, &net->nft.tables, list) { if (table->family != NFPROTO_NETDEV) continue; - list_for_each_entry_rcu(chain, &table->chains, list) { - if (nft_is_base_chain(chain)) { - struct nft_base_chain *basechain; - - basechain = nft_base_chain(chain); - if (!strncmp(basechain->dev_name, dev->name, - IFNAMSIZ)) { - nft_indr_block_ing_cmd(dev, basechain, - cb, cb_priv, - command); - return; - } - } + list_for_each_entry(chain, &table->chains, list) { + if (!nft_is_base_chain(chain) || + !(chain->flags & NFT_CHAIN_HW_OFFLOAD)) + continue; + + basechain = nft_base_chain(chain); + if (strncmp(basechain->dev_name, dev->name, IFNAMSIZ)) + continue; + + return chain; } } + + return NULL; +} + +static void nft_indr_block_cb(struct net_device *dev, + flow_indr_block_bind_cb_t *cb, void *cb_priv, + enum flow_block_command cmd) +{ + struct net *net = dev_net(dev); + struct nft_chain *chain; + + mutex_lock(&net->nft.commit_mutex); + chain = __nft_offload_get_chain(dev); + if (chain) { + struct nft_base_chain *basechain; + + basechain = nft_base_chain(chain); + nft_indr_block_ing_cmd(dev, basechain, cb, cb_priv, cmd); + } + mutex_unlock(&net->nft.commit_mutex); +} + +static void nft_offload_chain_clean(struct nft_chain *chain) +{ + struct nft_rule *rule; + + list_for_each_entry(rule, &chain->rules, list) { + nft_flow_offload_rule(chain, rule, + N |