diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2020-06-03 16:27:18 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2020-06-03 16:27:18 -0700 |
commit | cb8e59cc87201af93dfbb6c3dccc8fcad72a09c2 (patch) | |
tree | a334db9022f89654b777bbce8c4c6632e65b9031 /net/netfilter | |
parent | 2e63f6ce7ed2c4ff83ba30ad9ccad422289a6c63 (diff) | |
parent | 065fcfd49763ec71ae345bb5c5a74f961031e70e (diff) |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next
Pull networking updates from David Miller:
1) Allow setting bluetooth L2CAP modes via socket option, from Luiz
Augusto von Dentz.
2) Add GSO partial support to igc, from Sasha Neftin.
3) Several cleanups and improvements to r8169 from Heiner Kallweit.
4) Add IF_OPER_TESTING link state and use it when ethtool triggers a
device self-test. From Andrew Lunn.
5) Start moving away from custom driver versions, use the globally
defined kernel version instead, from Leon Romanovsky.
6) Support GRO vis gro_cells in DSA layer, from Alexander Lobakin.
7) Allow hard IRQ deferral during NAPI, from Eric Dumazet.
8) Add sriov and vf support to hinic, from Luo bin.
9) Support Media Redundancy Protocol (MRP) in the bridging code, from
Horatiu Vultur.
10) Support netmap in the nft_nat code, from Pablo Neira Ayuso.
11) Allow UDPv6 encapsulation of ESP in the ipsec code, from Sabrina
Dubroca. Also add ipv6 support for espintcp.
12) Lots of ReST conversions of the networking documentation, from Mauro
Carvalho Chehab.
13) Support configuration of ethtool rxnfc flows in bcmgenet driver,
from Doug Berger.
14) Allow to dump cgroup id and filter by it in inet_diag code, from
Dmitry Yakunin.
15) Add infrastructure to export netlink attribute policies to
userspace, from Johannes Berg.
16) Several optimizations to sch_fq scheduler, from Eric Dumazet.
17) Fallback to the default qdisc if qdisc init fails because otherwise
a packet scheduler init failure will make a device inoperative. From
Jesper Dangaard Brouer.
18) Several RISCV bpf jit optimizations, from Luke Nelson.
19) Correct the return type of the ->ndo_start_xmit() method in several
drivers, it's netdev_tx_t but many drivers were using
'int'. From Yunjian Wang.
20) Add an ethtool interface for PHY master/slave config, from Oleksij
Rempel.
21) Add BPF iterators, from Yonghang Song.
22) Add cable test infrastructure, including ethool interfaces, from
Andrew Lunn. Marvell PHY driver is the first to support this
facility.
23) Remove zero-length arrays all over, from Gustavo A. R. Silva.
24) Calculate and maintain an explicit frame size in XDP, from Jesper
Dangaard Brouer.
25) Add CAP_BPF, from Alexei Starovoitov.
26) Support terse dumps in the packet scheduler, from Vlad Buslov.
27) Support XDP_TX bulking in dpaa2 driver, from Ioana Ciornei.
28) Add devm_register_netdev(), from Bartosz Golaszewski.
29) Minimize qdisc resets, from Cong Wang.
30) Get rid of kernel_getsockopt and kernel_setsockopt in order to
eliminate set_fs/get_fs calls. From Christoph Hellwig.
* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2517 commits)
selftests: net: ip_defrag: ignore EPERM
net_failover: fixed rollback in net_failover_open()
Revert "tipc: Fix potential tipc_aead refcnt leak in tipc_crypto_rcv"
Revert "tipc: Fix potential tipc_node refcnt leak in tipc_rcv"
vmxnet3: allow rx flow hash ops only when rss is enabled
hinic: add set_channels ethtool_ops support
selftests/bpf: Add a default $(CXX) value
tools/bpf: Don't use $(COMPILE.c)
bpf, selftests: Use bpf_probe_read_kernel
s390/bpf: Use bcr 0,%0 as tail call nop filler
s390/bpf: Maintain 8-byte stack alignment
selftests/bpf: Fix verifier test
selftests/bpf: Fix sample_cnt shared between two threads
bpf, selftests: Adapt cls_redirect to call csum_level helper
bpf: Add csum_level helper for fixing up csum levels
bpf: Fix up bpf_skb_adjust_room helper's skb csum setting
sfc: add missing annotation for efx_ef10_try_update_nic_stats_vf()
crypto/chtls: IPv6 support for inline TLS
Crypto/chcr: Fixes a coccinile check error
Crypto/chcr: Fixes compilations warnings
...
Diffstat (limited to 'net/netfilter')
-rw-r--r-- | net/netfilter/Kconfig | 2 | ||||
-rw-r--r-- | net/netfilter/ipvs/ip_vs_ctl.c | 6 | ||||
-rw-r--r-- | net/netfilter/nf_conntrack_core.c | 19 | ||||
-rw-r--r-- | net/netfilter/nf_conntrack_netlink.c | 334 | ||||
-rw-r--r-- | net/netfilter/nf_conntrack_proto_icmp.c | 40 | ||||
-rw-r--r-- | net/netfilter/nf_conntrack_proto_icmpv6.c | 42 | ||||
-rw-r--r-- | net/netfilter/nf_conntrack_standalone.c | 6 | ||||
-rw-r--r-- | net/netfilter/nf_flow_table_core.c | 6 | ||||
-rw-r--r-- | net/netfilter/nf_flow_table_offload.c | 88 | ||||
-rw-r--r-- | net/netfilter/nf_internals.h | 17 | ||||
-rw-r--r-- | net/netfilter/nf_log.c | 2 | ||||
-rw-r--r-- | net/netfilter/nf_tables_api.c | 371 | ||||
-rw-r--r-- | net/netfilter/nf_tables_offload.c | 69 | ||||
-rw-r--r-- | net/netfilter/nft_nat.c | 110 |
14 files changed, 808 insertions, 304 deletions
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 468fea1aebba..3a3915d2e1ea 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -1043,7 +1043,7 @@ config NETFILTER_XT_TARGET_TPROXY on Netfilter connection tracking and NAT, unlike REDIRECT. For it to work you will have to configure certain iptables rules and use policy routing. For more information on how to set it up - see Documentation/networking/tproxy.txt. + see Documentation/networking/tproxy.rst. To compile it as a module, choose M here. If unsure, say N. diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 8d14a1acbc37..412656c34f20 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -1736,7 +1736,7 @@ static int three = 3; static int proc_do_defense_mode(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, loff_t *ppos) + void *buffer, size_t *lenp, loff_t *ppos) { struct netns_ipvs *ipvs = table->extra2; int *valp = table->data; @@ -1763,7 +1763,7 @@ proc_do_defense_mode(struct ctl_table *table, int write, static int proc_do_sync_threshold(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, loff_t *ppos) + void *buffer, size_t *lenp, loff_t *ppos) { int *valp = table->data; int val[2]; @@ -1788,7 +1788,7 @@ proc_do_sync_threshold(struct ctl_table *table, int write, static int proc_do_sync_ports(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, loff_t *ppos) + void *buffer, size_t *lenp, loff_t *ppos) { int *valp = table->data; int val = *valp; diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index bb72ca5f3999..79cd9dde457b 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1974,13 +1974,22 @@ const struct nla_policy nf_ct_port_nla_policy[CTA_PROTO_MAX+1] = { EXPORT_SYMBOL_GPL(nf_ct_port_nla_policy); int nf_ct_port_nlattr_to_tuple(struct nlattr *tb[], - struct nf_conntrack_tuple *t) + struct nf_conntrack_tuple *t, + u_int32_t flags) { - if (!tb[CTA_PROTO_SRC_PORT] || !tb[CTA_PROTO_DST_PORT]) - return -EINVAL; + if (flags & CTA_FILTER_FLAG(CTA_PROTO_SRC_PORT)) { + if (!tb[CTA_PROTO_SRC_PORT]) + return -EINVAL; + + t->src.u.tcp.port = nla_get_be16(tb[CTA_PROTO_SRC_PORT]); + } - t->src.u.tcp.port = nla_get_be16(tb[CTA_PROTO_SRC_PORT]); - t->dst.u.tcp.port = nla_get_be16(tb[CTA_PROTO_DST_PORT]); + if (flags & CTA_FILTER_FLAG(CTA_PROTO_DST_PORT)) { + if (!tb[CTA_PROTO_DST_PORT]) + return -EINVAL; + + t->dst.u.tcp.port = nla_get_be16(tb[CTA_PROTO_DST_PORT]); + } return 0; } diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 9ddfcd002d3b..d7bd8b1f27d5 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -54,6 +54,8 @@ #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_conntrack.h> +#include "nf_internals.h" + MODULE_LICENSE("GPL"); static int ctnetlink_dump_tuples_proto(struct sk_buff *skb, @@ -544,14 +546,16 @@ static int ctnetlink_dump_info(struct sk_buff *skb, struct nf_conn *ct) static int ctnetlink_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type, - struct nf_conn *ct, bool extinfo) + struct nf_conn *ct, bool extinfo, unsigned int flags) { const struct nf_conntrack_zone *zone; struct nlmsghdr *nlh; struct nfgenmsg *nfmsg; struct nlattr *nest_parms; - unsigned int flags = portid ? NLM_F_MULTI : 0, event; + unsigned int event; + if (portid) + flags |= NLM_F_MULTI; event = nfnl_msg_type(NFNL_SUBSYS_CTNETLINK, IPCTNL_MSG_CT_NEW); nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nfmsg), flags); if (nlh == NULL) @@ -847,17 +851,70 @@ static int ctnetlink_done(struct netlink_callback *cb) } struct ctnetlink_filter { + u_int32_t cta_flags; u8 family; + + u_int32_t orig_flags; + u_int32_t reply_flags; + + struct nf_conntrack_tuple orig; + struct nf_conntrack_tuple reply; + struct nf_conntrack_zone zone; + struct { u_int32_t val; u_int32_t mask; } mark; }; +static const struct nla_policy cta_filter_nla_policy[CTA_FILTER_MAX + 1] = { + [CTA_FILTER_ORIG_FLAGS] = { .type = NLA_U32 }, + [CTA_FILTER_REPLY_FLAGS] = { .type = NLA_U32 }, +}; + +static int ctnetlink_parse_filter(const struct nlattr *attr, + struct ctnetlink_filter *filter) +{ + struct nlattr *tb[CTA_FILTER_MAX + 1]; + int ret = 0; + + ret = nla_parse_nested(tb, CTA_FILTER_MAX, attr, cta_filter_nla_policy, + NULL); + if (ret) + return ret; + + if (tb[CTA_FILTER_ORIG_FLAGS]) { + filter->orig_flags = nla_get_u32(tb[CTA_FILTER_ORIG_FLAGS]); + if (filter->orig_flags & ~CTA_FILTER_F_ALL) + return -EOPNOTSUPP; + } + + if (tb[CTA_FILTER_REPLY_FLAGS]) { + filter->reply_flags = nla_get_u32(tb[CTA_FILTER_REPLY_FLAGS]); + if (filter->reply_flags & ~CTA_FILTER_F_ALL) + return -EOPNOTSUPP; + } + + return 0; +} + +static int ctnetlink_parse_zone(const struct nlattr *attr, + struct nf_conntrack_zone *zone); +static int ctnetlink_parse_tuple_filter(const struct nlattr * const cda[], + struct nf_conntrack_tuple *tuple, + u32 type, u_int8_t l3num, + struct nf_conntrack_zone *zone, + u_int32_t flags); + +/* applied on filters */ +#define CTA_FILTER_F_CTA_MARK (1 << 0) +#define CTA_FILTER_F_CTA_MARK_MASK (1 << 1) + static struct ctnetlink_filter * ctnetlink_alloc_filter(const struct nlattr * const cda[], u8 family) { struct ctnetlink_filter *filter; + int err; #ifndef CONFIG_NF_CONNTRACK_MARK if (cda[CTA_MARK] || cda[CTA_MARK_MASK]) @@ -871,14 +928,65 @@ ctnetlink_alloc_filter(const struct nlattr * const cda[], u8 family) filter->family = family; #ifdef CONFIG_NF_CONNTRACK_MARK - if (cda[CTA_MARK] && cda[CTA_MARK_MASK]) { + if (cda[CTA_MARK]) { filter->mark.val = ntohl(nla_get_be32(cda[CTA_MARK])); - filter->mark.mask = ntohl(nla_get_be32(cda[CTA_MARK_MASK])); + filter->cta_flags |= CTA_FILTER_FLAG(CTA_MARK); + + if (cda[CTA_MARK_MASK]) { + filter->mark.mask = ntohl(nla_get_be32(cda[CTA_MARK_MASK])); + filter->cta_flags |= CTA_FILTER_FLAG(CTA_MARK_MASK); + } else { + filter->mark.mask = 0xffffffff; + } + } else if (cda[CTA_MARK_MASK]) { + return ERR_PTR(-EINVAL); } #endif + if (!cda[CTA_FILTER]) + return filter; + + err = ctnetlink_parse_zone(cda[CTA_ZONE], &filter->zone); + if (err < 0) + return ERR_PTR(err); + + err = ctnetlink_parse_filter(cda[CTA_FILTER], filter); + if (err < 0) + return ERR_PTR(err); + + if (filter->orig_flags) { + if (!cda[CTA_TUPLE_ORIG]) + return ERR_PTR(-EINVAL); + + err = ctnetlink_parse_tuple_filter(cda, &filter->orig, + CTA_TUPLE_ORIG, + filter->family, + &filter->zone, + filter->orig_flags); + if (err < 0) + return ERR_PTR(err); + } + + if (filter->reply_flags) { + if (!cda[CTA_TUPLE_REPLY]) + return ERR_PTR(-EINVAL); + + err = ctnetlink_parse_tuple_filter(cda, &filter->reply, + CTA_TUPLE_REPLY, + filter->family, + &filter->zone, + filter->orig_flags); + if (err < 0) + return ERR_PTR(err); + } + return filter; } +static bool ctnetlink_needs_filter(u8 family, const struct nlattr * const *cda) +{ + return family || cda[CTA_MARK] || cda[CTA_FILTER]; +} + static int ctnetlink_start(struct netlink_callback *cb) { const struct nlattr * const *cda = cb->data; @@ -886,7 +994,7 @@ static int ctnetlink_start(struct netlink_callback *cb) struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh); u8 family = nfmsg->nfgen_family; - if (family || (cda[CTA_MARK] && cda[CTA_MARK_MASK])) { + if (ctnetlink_needs_filter(family, cda)) { filter = ctnetlink_alloc_filter(cda, family); if (IS_ERR(filter)) return PTR_ERR(filter); @@ -896,9 +1004,79 @@ static int ctnetlink_start(struct netlink_callback *cb) return 0; } +static int ctnetlink_filter_match_tuple(struct nf_conntrack_tuple *filter_tuple, + struct nf_conntrack_tuple *ct_tuple, + u_int32_t flags, int family) +{ + switch (family) { + case NFPROTO_IPV4: + if ((flags & CTA_FILTER_FLAG(CTA_IP_SRC)) && + filter_tuple->src.u3.ip != ct_tuple->src.u3.ip) + return 0; + + if ((flags & CTA_FILTER_FLAG(CTA_IP_DST)) && + filter_tuple->dst.u3.ip != ct_tuple->dst.u3.ip) + return 0; + break; + case NFPROTO_IPV6: + if ((flags & CTA_FILTER_FLAG(CTA_IP_SRC)) && + !ipv6_addr_cmp(&filter_tuple->src.u3.in6, + &ct_tuple->src.u3.in6)) + return 0; + + if ((flags & CTA_FILTER_FLAG(CTA_IP_DST)) && + !ipv6_addr_cmp(&filter_tuple->dst.u3.in6, + &ct_tuple->dst.u3.in6)) + return 0; + break; + } + + if ((flags & CTA_FILTER_FLAG(CTA_PROTO_NUM)) && + filter_tuple->dst.protonum != ct_tuple->dst.protonum) + return 0; + + switch (ct_tuple->dst.protonum) { + case IPPROTO_TCP: + case IPPROTO_UDP: + if ((flags & CTA_FILTER_FLAG(CTA_PROTO_SRC_PORT)) && + filter_tuple->src.u.tcp.port != ct_tuple->src.u.tcp.port) + return 0; + + if ((flags & CTA_FILTER_FLAG(CTA_PROTO_DST_PORT)) && + filter_tuple->dst.u.tcp.port != ct_tuple->dst.u.tcp.port) + return 0; + break; + case IPPROTO_ICMP: + if ((flags & CTA_FILTER_FLAG(CTA_PROTO_ICMP_TYPE)) && + filter_tuple->dst.u.icmp.type != ct_tuple->dst.u.icmp.type) + return 0; + if ((flags & CTA_FILTER_FLAG(CTA_PROTO_ICMP_CODE)) && + filter_tuple->dst.u.icmp.code != ct_tuple->dst.u.icmp.code) + return 0; + if ((flags & CTA_FILTER_FLAG(CTA_PROTO_ICMP_ID)) && + filter_tuple->src.u.icmp.id != ct_tuple->src.u.icmp.id) + return 0; + break; + case IPPROTO_ICMPV6: + if ((flags & CTA_FILTER_FLAG(CTA_PROTO_ICMPV6_TYPE)) && + filter_tuple->dst.u.icmp.type != ct_tuple->dst.u.icmp.type) + return 0; + if ((flags & CTA_FILTER_FLAG(CTA_PROTO_ICMPV6_CODE)) && + filter_tuple->dst.u.icmp.code != ct_tuple->dst.u.icmp.code) + return 0; + if ((flags & CTA_FILTER_FLAG(CTA_PROTO_ICMPV6_ID)) && + filter_tuple->src.u.icmp.id != ct_tuple->src.u.icmp.id) + return 0; + break; + } + + return 1; +} + static int ctnetlink_filter_match(struct nf_conn *ct, void *data) { struct ctnetlink_filter *filter = data; + struct nf_conntrack_tuple *tuple; if (filter == NULL) goto out; @@ -910,8 +1088,28 @@ static int ctnetlink_filter_match(struct nf_conn *ct, void *data) if (filter->family && nf_ct_l3num(ct) != filter->family) goto ignore_entry; + if (filter->orig_flags) { + tuple = nf_ct_tuple(ct, IP_CT_DIR_ORIGINAL); + if (!ctnetlink_filter_match_tuple(&filter->orig, tuple, + filter->orig_flags, + filter->family)) + goto ignore_entry; + } + + if (filter->reply_flags) { + tuple = nf_ct_tuple(ct, IP_CT_DIR_REPLY); + if (!ctnetlink_filter_match_tuple(&filter->reply, tuple, + filter->reply_flags, + filter->family)) + goto ignore_entry; + } + #ifdef CONFIG_NF_CONNTRACK_MARK - if ((ct->mark & filter->mark.mask) != filter->mark.val) + if ((filter->cta_flags & CTA_FILTER_FLAG(CTA_MARK_MASK)) && + (ct->mark & filter->mark.mask) != filter->mark.val) + goto ignore_entry; + else if ((filter->cta_flags & CTA_FILTER_FLAG(CTA_MARK)) && + ct->mark != filter->mark.val) goto ignore_entry; #endif @@ -925,6 +1123,7 @@ ignore_entry: static int ctnetlink_dump_table(struct sk_buff *skb, struct netlink_callback *cb) { + unsigned int flags = cb->data ? NLM_F_DUMP_FILTERED : 0; struct net *net = sock_net(skb->sk); struct nf_conn *ct, *last; struct nf_conntrack_tuple_hash *h; @@ -979,7 +1178,7 @@ restart: ctnetlink_fill_info(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NFNL_MSG_TYPE(cb->nlh->nlmsg_type), - ct, true); + ct, true, flags); if (res < 0) { nf_conntrack_get(&ct->ct_general); cb->args[1] = (unsigned long)ct; @@ -1014,31 +1213,50 @@ out: } static int ipv4_nlattr_to_tuple(struct nlattr *tb[], - struct nf_conntrack_tuple *t) + struct nf_conntrack_tuple *t, + u_int32_t flags) { - if (!tb[CTA_IP_V4_SRC] || !tb[CTA_IP_V4_DST]) - return -EINVAL; + if (flags & CTA_FILTER_FLAG(CTA_IP_SRC)) { + if (!tb[CTA_IP_V4_SRC]) + return -EINVAL; + + t->src.u3.ip = nla_get_in_addr(tb[CTA_IP_V4_SRC]); + } + + if (flags & CTA_FILTER_FLAG(CTA_IP_DST)) { + if (!tb[CTA_IP_V4_DST]) + return -EINVAL; - t->src.u3.ip = nla_get_in_addr(tb[CTA_IP_V4_SRC]); - t->dst.u3.ip = nla_get_in_addr(tb[CTA_IP_V4_DST]); + t->dst.u3.ip = nla_get_in_addr(tb[CTA_IP_V4_DST]); + } return 0; } static int ipv6_nlattr_to_tuple(struct nlattr *tb[], - struct nf_conntrack_tuple *t) + struct nf_conntrack_tuple *t, + u_int32_t flags) { - if (!tb[CTA_IP_V6_SRC] || !tb[CTA_IP_V6_DST]) - return -EINVAL; + if (flags & CTA_FILTER_FLAG(CTA_IP_SRC)) { + if (!tb[CTA_IP_V6_SRC]) + return -EINVAL; - t->src.u3.in6 = nla_get_in6_addr(tb[CTA_IP_V6_SRC]); - t->dst.u3.in6 = nla_get_in6_addr(tb[CTA_IP_V6_DST]); + t->src.u3.in6 = nla_get_in6_addr(tb[CTA_IP_V6_SRC]); + } + + if (flags & CTA_FILTER_FLAG(CTA_IP_DST)) { + if (!tb[CTA_IP_V6_DST]) + return -EINVAL; + + t->dst.u3.in6 = nla_get_in6_addr(tb[CTA_IP_V6_DST]); + } return 0; } static int ctnetlink_parse_tuple_ip(struct nlattr *attr, - struct nf_conntrack_tuple *tuple) + struct nf_conntrack_tuple *tuple, + u_int32_t flags) { struct nlattr *tb[CTA_IP_MAX+1]; int ret = 0; @@ -1054,10 +1272,10 @@ static int ctnetlink_parse_tuple_ip(struct nlattr *attr, switch (tuple->src.l3num) { case NFPROTO_IPV4: - ret = ipv4_nlattr_to_tuple(tb, tuple); + ret = ipv4_nlattr_to_tuple(tb, tuple, flags); break; case NFPROTO_IPV6: - ret = ipv6_nlattr_to_tuple(tb, tuple); + ret = ipv6_nlattr_to_tuple(tb, tuple, flags); break; } @@ -1069,7 +1287,8 @@ static const struct nla_policy proto_nla_policy[CTA_PROTO_MAX+1] = { }; static int ctnetlink_parse_tuple_proto(struct nlattr *attr, - struct nf_conntrack_tuple *tuple) + struct nf_conntrack_tuple *tuple, + u_int32_t flags) { const struct nf_conntrack_l4proto *l4proto; struct nlattr *tb[CTA_PROTO_MAX+1]; @@ -1080,8 +1299,12 @@ static int ctnetlink_parse_tuple_proto(struct nlattr *attr, if (ret < 0) return ret; + if (!(flags & CTA_FILTER_FLAG(CTA_PROTO_NUM))) + return 0; + if (!tb[CTA_PROTO_NUM]) return -EINVAL; + tuple->dst.protonum = nla_get_u8(tb[CTA_PROTO_NUM]); rcu_read_lock(); @@ -1092,7 +1315,7 @@ static int ctnetlink_parse_tuple_proto(struct nlattr *attr, l4proto->nla_policy, NULL); if (ret == 0) - ret = l4proto->nlattr_to_tuple(tb, tuple); + ret = l4proto->nlattr_to_tuple(tb, tuple, flags); } rcu_read_unlock(); @@ -1143,10 +1366,21 @@ static const struct nla_policy tuple_nla_policy[CTA_TUPLE_MAX+1] = { [CTA_TUPLE_ZONE] = { .type = NLA_U16 }, }; +#define CTA_FILTER_F_ALL_CTA_PROTO \ + (CTA_FILTER_F_CTA_PROTO_SRC_PORT | \ + CTA_FILTER_F_CTA_PROTO_DST_PORT | \ + CTA_FILTER_F_CTA_PROTO_ICMP_TYPE | \ + CTA_FILTER_F_CTA_PROTO_ICMP_CODE | \ + CTA_FILTER_F_CTA_PROTO_ICMP_ID | \ + CTA_FILTER_F_CTA_PROTO_ICMPV6_TYPE | \ + CTA_FILTER_F_CTA_PROTO_ICMPV6_CODE | \ + CTA_FILTER_F_CTA_PROTO_ICMPV6_ID) + static int -ctnetlink_parse_tuple(const struct nlattr * const cda[], - struct nf_conntrack_tuple *tuple, u32 type, - u_int8_t l3num, struct nf_conntrack_zone *zone) +ctnetlink_parse_tuple_filter(const struct nlattr * const cda[], + struct nf_conntrack_tuple *tuple, u32 type, + u_int8_t l3num, struct nf_conntrack_zone *zone, + u_int32_t flags) { struct nlattr *tb[CTA_TUPLE_MAX+1]; int err; @@ -1158,23 +1392,32 @@ ctnetlink_parse_tuple(const struct nlattr * const cda[], if (err < 0) return err; - if (!tb[CTA_TUPLE_IP]) - return -EINVAL; tuple->src.l3num = l3num; - err = ctnetlink_parse_tuple_ip(tb[CTA_TUPLE_IP], tuple); - if (err < 0) - return err; + if (flags & CTA_FILTER_FLAG(CTA_IP_DST) || + flags & CTA_FILTER_FLAG(CTA_IP_SRC)) { + if (!tb[CTA_TUPLE_IP]) + return -EINVAL; - if (!tb[CTA_TUPLE_PROTO]) - return -EINVAL; + err = ctnetlink_parse_tuple_ip(tb[CTA_TUPLE_IP], tuple, flags); + if (err < 0) + return err; + } - err = ctnetlink_parse_tuple_proto(tb[CTA_TUPLE_PROTO], tuple); - if (err < 0) - return err; + if (flags & CTA_FILTER_FLAG(CTA_PROTO_NUM)) { + if (!tb[CTA_TUPLE_PROTO]) + return -EINVAL; - if (tb[CTA_TUPLE_ZONE]) { + err = ctnetlink_parse_tuple_proto(tb[CTA_TUPLE_PROTO], tuple, flags); + if (err < 0) + return err; + } else if (flags & CTA_FILTER_FLAG(ALL_CTA_PROTO)) { + /* Can't manage proto flags without a protonum */ + return -EINVAL; + } + + if ((flags & CTA_FILTER_FLAG(CTA_TUPLE_ZONE)) && tb[CTA_TUPLE_ZONE]) { if (!zone) return -EINVAL; @@ -1193,6 +1436,15 @@ ctnetlink_parse_tuple(const struct nlattr * const cda[], return 0; } +static int +ctnetlink_parse_tuple(const struct nlattr * const cda[], + struct nf_conntrack_tuple *tuple, u32 type, + u_int8_t l3num, struct nf_conntrack_zone *zone) +{ + return ctnetlink_parse_tuple_filter(cda, tuple, type, l3num, zone, + CTA_FILTER_FLAG(ALL)); +} + static const struct nla_policy help_nla_policy[CTA_HELP_MAX+1] = { [CTA_HELP_NAME] = { .type = NLA_NUL_STRING, .len = NF_CT_HELPER_NAME_LEN - 1 }, @@ -1240,6 +1492,7 @@ static const struct nla_policy ct_nla_policy[CTA_MAX+1] = { .len = NF_CT_LABELS_MAX_SIZE }, [CTA_LABELS_MASK] = { .type = NLA_BINARY, .len = NF_CT_LABELS_MAX_SIZE }, + [CTA_FILTER] = { .type = NLA_NESTED }, }; static int ctnetlink_flush_iterate(struct nf_conn *ct, void *data) @@ -1256,7 +1509,10 @@ static int ctnetlink_flush_conntrack(struct net *net, { struct ctnetlink_filter *filter = NULL; - if (family || (cda[CTA_MARK] && cda[CTA_MARK_MASK])) { + if (ctnetlink_needs_filter(family, cda)) { + if (cda[CTA_FILTER]) + return -EOPNOTSUPP; + filter = ctnetlink_alloc_filter(cda, family); if (IS_ERR(filter)) return PTR_ERR(filter); @@ -1385,7 +1641,7 @@ static int ctnetlink_get_conntrack(struct net *net, struct sock *ctnl, } err = ctnetlink_fill_info(skb2, NETLINK_CB(skb).portid, nlh->nlmsg_seq, - NFNL_MSG_TYPE(nlh->nlmsg_type), ct, true); + NFNL_MSG_TYPE(nlh->nlmsg_type), ct, true, 0); nf_ct_put(ct); if (err <= 0) goto free; @@ -1458,7 +1714,7 @@ restart: res = ctnetlink_fill_info(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NFNL_MSG_TYPE(cb->nlh->nlmsg_type), - ct, dying ? true : false); + ct, dying ? true : false, 0); if (res < 0) { if (!atomic_inc_not_zero(&ct->ct_general.use)) continue; diff --git a/net/netfilter/nf_conntrack_proto_icmp.c b/net/netfilter/nf_conntrack_proto_icmp.c index c2e3dff773bc..4efd8741c105 100644 --- a/net/netfilter/nf_conntrack_proto_icmp.c +++ b/net/netfilter/nf_conntrack_proto_icmp.c @@ -20,6 +20,8 @@ #include <net/netfilter/nf_conntrack_zones.h> #include <net/netfilter/nf_log.h> +#include "nf_internals.h" + static const unsigned int nf_ct_icmp_timeout = 30*HZ; bool icmp_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, @@ -271,20 +273,32 @@ static const struct nla_policy icmp_nla_policy[CTA_PROTO_MAX+1] = { }; static int icmp_nlattr_to_tuple(struct nlattr *tb[], - struct nf_conntrack_tuple *tuple) + struct nf_conntrack_tuple *tuple, + u_int32_t flags) { - if (!tb[CTA_PROTO_ICMP_TYPE] || - !tb[CTA_PROTO_ICMP_CODE] || - !tb[CTA_PROTO_ICMP_ID]) - return -EINVAL; - - tuple->dst.u.icmp.type = nla_get_u8(tb[CTA_PROTO_ICMP_TYPE]); - tuple->dst.u.icmp.code = nla_get_u8(tb[CTA_PROTO_ICMP_CODE]); - tuple->src.u.icmp.id = nla_get_be16(tb[CTA_PROTO_ICMP_ID]); - - if (tuple->dst.u.icmp.type >= sizeof(invmap) || - !invmap[tuple->dst.u.icmp.type]) - return -EINVAL; + if (flags & CTA_FILTER_FLAG(CTA_PROTO_ICMP_TYPE)) { + if (!tb[CTA_PROTO_ICMP_TYPE]) + return -EINVAL; + + tuple->dst.u.icmp.type = nla_get_u8(tb[CTA_PROTO_ICMP_TYPE]); + if (tuple->dst.u.icmp.type >= sizeof(invmap) || + !invmap[tuple->dst.u.icmp.type]) + return -EINVAL; + } + + if (flags & CTA_FILTER_FLAG(CTA_PROTO_ICMP_CODE)) { + if (!tb[CTA_PROTO_ICMP_CODE]) + return -EINVAL; + + tuple->dst.u.icmp.code = nla_get_u8(tb[CTA_PROTO_ICMP_CODE]); + } + + if (flags & CTA_FILTER_FLAG(CTA_PROTO_ICMP_ID)) { + if (!tb[CTA_PROTO_ICMP_ID]) + return -EINVAL; + + tuple->src.u.icmp.id = nla_get_be16(tb[CTA_PROTO_ICMP_ID]); + } return 0; } diff --git a/net/netfilter/nf_conntrack_proto_icmpv6.c b/net/netfilter/nf_conntrack_proto_icmpv6.c index 6f9144e1f1c1..facd8c64ec4e 100644 --- a/net/netfilter/nf_conntrack_proto_icmpv6.c +++ b/net/netfilter/nf_conntrack_proto_icmpv6.c @@ -24,6 +24,8 @@ #include <net/netfilter/nf_conntrack_zones.h> #include <net/netfilter/nf_log.h> +#include "nf_internals.h" + static const unsigned int nf_ct_icmpv6_timeout = 30*HZ; bool icmpv6_pkt_to_tuple(const struct sk_buff *skb, @@ -193,21 +195,33 @@ static const struct nla_policy icmpv6_nla_policy[CTA_PROTO_MAX+1] = { }; static int icmpv6_nlattr_to_tuple(struct nlattr *tb[], - struct nf_conntrack_tuple *tuple) + struct nf_conntrack_tuple *tuple, + u_int32_t flags) { - if (!tb[CTA_PROTO_ICMPV6_TYPE] || - !tb[CTA_PROTO_ICMPV6_CODE] || - !tb[CTA_PROTO_ICMPV6_ID]) - return -EINVAL; - - tuple->dst.u.icmp.type = nla_get_u8(tb[CTA_PROTO_ICMPV6_TYPE]); - tuple->dst.u.icmp.code = nla_get_u8(tb[CTA_PROTO_ICMPV6_CODE]); - tuple->src.u.icmp.id = nla_get_be16(tb[CTA_PROTO_ICMPV6_ID]); - - if (tuple->dst.u.icmp.type < 128 || - tuple->dst.u.icmp.type - 128 >= sizeof(invmap) || - !invmap[tuple->dst.u.icmp.type - 128]) - return -EINVAL; + if (flags & CTA_FILTER_FLAG(CTA_PROTO_ICMPV6_TYPE)) { + if (!tb[CTA_PROTO_ICMPV6_TYPE]) + return -EINVAL; + + tuple->dst.u.icmp.type = nla_get_u8(tb[CTA_PROTO_ICMPV6_TYPE]); + if (tuple->dst.u.icmp.type < 128 || + tuple->dst.u.icmp.type - 128 >= sizeof(invmap) || + !invmap[tuple->dst.u.icmp.type - 128]) + return -EINVAL; + } + + if (flags & CTA_FILTER_FLAG(CTA_PROTO_ICMPV6_CODE)) { + if (!tb[CTA_PROTO_ICMPV6_CODE]) + return -EINVAL; + + tuple->dst.u.icmp.code = nla_get_u8(tb[CTA_PROTO_ICMPV6_CODE]); + } + + if (flags & CTA_FILTER_FLAG(CTA_PROTO_ICMPV6_ID)) { + if (!tb[CTA_PROTO_ICMPV6_ID]) + return -EINVAL; + + tuple->src.u.icmp.id = nla_get_be16(tb[CTA_PROTO_ICMPV6_ID]); + } return 0; } diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 9b57330c81f8..6a26299cb064 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -348,7 +348,9 @@ static int ct_seq_show(struct seq_file *s, void *v) if (seq_print_acct(s, ct, IP_CT_DIR_REPLY)) goto release; - if (test_bit(IPS_OFFLOAD_BIT, &ct->status)) + if (test_bit(IPS_HW_OFFLOAD_BIT, &ct->status)) + seq_puts(s, "[HW_OFFLOAD] "); + else if (test_bit(IPS_OFFLOAD_BIT, &ct->status)) seq_puts(s, "[OFFLOAD] "); else if (test_bit(IPS_ASSURED_BIT, &ct->status)) seq_puts(s, "[ASSURED] "); @@ -517,7 +519,7 @@ static unsigned int nf_conntrack_htable_size_user __read_mostly; static int nf_conntrack_hash_sysctl(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, loff_t *ppos) + void *buffer, size_t *lenp, loff_t *ppos) { int ret; diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index 42da6e337276..6a3034f84ab6 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -588,8 +588,8 @@ static void nf_flow_table_do_cleanup(struct flow_offload *flow, void *data) flow_offload_teardown(flow); } -static void nf_flow_table_iterate_cleanup(struct nf_flowtable *flowtable, - struct net_device *dev) +void nf_flow_table_gc_cleanup(struct nf_flowtable *flowtable, + struct net_device *dev) { nf_flow_table_iterate(flowtable, nf_flow_table_do_cleanup, dev); flush_delayed_work(&flowtable->gc_work); @@ -602,7 +602,7 @@ void nf_flow_table_cleanup(struct net_device *dev) mutex_lock(&flowtable_lock); list_for_each_entry(flowtable, &flowtables, list) - nf_flow_table_iterate_cleanup(flowtable, dev); + nf_flow_table_gc_cleanup(flowtable, dev); mutex_unlock(&flowtable_lock); } EXPORT_SYMBOL_GPL(nf_flow_table_cleanup); diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c index 2276a73ccba2..62651e6683f6 100644 --- a/net/netfilter/nf_flow_table_offload.c +++ b/net/netfilter/nf_flow_table_offload.c @@ -754,12 +754,15 @@ static void flow_offload_work_add(struct flow_offload_work *offload) err = flow_offload_rule_add(offload, flow_rule); if (err < 0) set_bit(NF_FLOW_HW_REFRESH, &offload->flow->flags); + else + set_bit(IPS_HW_OFFLOAD_BIT, &offload->flow->ct->status); nf_flow_offload_destroy(flow_rule); } static void flow_offload_work_del(struct flow_offload_work *offload) { + clear_bit(IPS_HW_OFFLOAD_BIT, &offload->flow->ct->status); flow_offload_tuple_del(offload, FLOW_OFFLOAD_DIR_ORIGINAL); flow_offload_tuple_del(offload, FLOW_OFFLOAD_DIR_REPLY); set_bit(NF_FLOW_HW_DEAD, &offload->flow->flags); @@ -939,6 +942,18 @@ static void nf_flow_table_block_offload_init(struct flow_block_offload *bo, INIT_LIST_HEAD(&bo->cb_list); } +static void nf_flow_table_indr_cleanup(struct flow_block_cb *block_cb) +{ + struct nf_flowtable *flowtable = block_cb->indr.data; + struct net_device *dev = block_cb->indr.dev; + + nf_flow_table_gc_cleanup(flowtable, dev); + down_write(&flowtable->flow_block_lock); + list_del(&block_cb->list); + flow_block_cb_free(block_cb); + up_write(&flowtable->flow_block_lock); +} + static int nf_flow_table_indr_offload_cmd(struct flow_block_offload *bo, struct nf_flowtable *flowtable, struct net_device *dev, @@ -947,12 +962,9 @@ static int nf_flow_table_indr_offload_cmd(struct flow_block_offload *bo, { nf_flow_table_block_offload_init(bo, dev_net(dev), cmd, flowtable, extack); - flow_indr_block_call(dev, bo, cmd, TC_SETUP_FT); - if (list_empty(&bo->cb_list)) - return -EOPNOTSUPP; - - return 0; + return flow_indr_dev_setup_offload(dev, TC_SETUP_FT, flowtable, bo, + nf_flow_table_indr_cleanup); } static int nf_flow_table_offload_cmd(struct flow_block_offload *bo, @@ -996,69 +1008,6 @@ int nf_flow_table_offload_setup(struct nf_flowtable *flowtable, } EXPORT_SYMBOL_GPL(nf_flow_table_offload_setup); -static void nf_flow_table_indr_block_ing_cmd(struct net_device *dev, - struct nf_flowtable *flowtable, - flow_indr_block_bind_cb_t *cb, - void *cb_priv, - enum flow_block_command cmd) -{ - struct netlink_ext_ack extack = {}; - struct flow_block_offload bo; - - if (!flowtable) - return; - - nf_flow_table_block_offload_init(&bo, dev_net(dev), cmd, flowtable, - &extack); - - cb(dev, cb_priv, TC_SETUP_FT, &bo); - - nf_flow_table_block_setup(flowtable, &bo, cmd); -} - -static void nf_flow_table_indr_block_cb_cmd(struct nf_flowtable *flowtable, - struct net_device *dev, - flow_indr_block_bind_cb_t *cb, - void *cb_priv, - enum flow_block_command cmd) -{ - if (!(flowtable->flags & NF_FLOWTABLE_HW_OFFLOAD)) - return; - - nf_flow_table_indr_block_ing_cmd(dev, flowtable, cb, cb_priv, cmd); -} - -static void nf_flow_table_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_flowtable *nft_ft; - struct nft_table *table; - struct nft_hook *hook; - - mutex_lock(&net->nft.commit_mutex); - list_for_each_entry(table, &net->nft.tables, list) { - list_for_each_entry(nft_ft, &table->flowtables, list) { - list_for_each_entry(hook, &nft_ft->hook_list, list) { - if (hook->ops.dev != dev) - continue; - - nf_flow_table_indr_block_cb_cmd(&nft_ft->data, - dev, cb, - cb_priv, cmd); - } - } - } - mutex_unlock(&net->nft.commit_mutex); -} - -static struct flow_indr_block_entry block_ing_entry = { - .cb = nf_flow_table_indr_block_cb, - .list = LIST_HEAD_INIT(block_ing_entry.list), -}; - int nf_flow_table_offload_init(void) { nf_flow_offload_wq = alloc_workqueue("nf_flow_table_offload", @@ -1066,13 +1015,10 @@ int nf_flow_table_offload_init(void) if (!nf_flow_offload_wq) return -ENOMEM; - flow_indr_add_block_cb(&block_ing_entry); - return 0; } void nf_flow_table_offload_exit(void) { - flow_indr_del_block_cb(&block_ing_entry); destroy_workqueue(nf_flow_offload_wq); } diff --git a/net/netfilter/nf_internals.h b/net/netfilter/nf_internals.h index d6c43902ebd7..832ae64179f0 100644 --- a/net/netfilter/nf_internals.h +++ b/net/netfilter/nf_internals.h @@ -6,6 +6,23 @@ #include <linux/skbuff.h> #include <linux/netdevice.h> +/* nf_conntrack_netlink.c: applied on tuple filters */ +#define CTA_FILTER_F_CTA_IP_SRC (1 << 0) +#define CTA_FILTER_F_CTA_IP_DST (1 << 1) +#define CTA_FILTER_F_CTA_TUPLE_ZONE (1 << 2) +#define CTA_FILTER_F_CTA_PROTO_NUM (1 << 3) +#define CTA_FILTER_F_CTA_PROTO_SRC_PORT (1 << 4) +#define CTA_FILTER_F_CTA_PROTO_DST_PORT (1 << 5) +#define CTA_FILTER_F_CTA_PROTO_ICMP_TYPE (1 << 6) +#define CTA_FILTER_F_CTA_PROTO_ICMP_CODE (1 << 7) +#define CTA_FILTER_F_CTA_PROTO_ICMP_ID (1 << 8) +#define CTA_FILTER_F_CTA_PROTO_ICMPV6_TYPE (1 << 9) +#define CTA_FILTER_F_CTA_PROTO_ICMPV6_CODE (1 << 10) +#define CTA_FILTER_F_CTA_PROTO_ICMPV6_ID (1 << 11) +#define CTA_FILTER_F_MAX (1 << 12) +#define CTA_FILTER_F_ALL (CTA_FILTER_F_MAX-1) +#define CTA_FILTER_FLAG(ctattr) CTA_FILTER_F_ ## ctattr + /* nf_queue.c */ void nf_queue_nf_hook_drop(struct net *net); diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c index bb25d4c794c7..6cb9f9474b05 100644 --- a/net/netfilter/nf_log.c +++ b/net/netfilter/nf_log.c @@ -414,7 +414,7 @@ static struct ctl_table nf_log_sysctl_ftable[] = { }; static int nf_log_proc_dostring(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, loff_t *ppos) + void *buffer, size_t *lenp, loff_t *ppos) { const struct nf_logger *logger; char buf[NFLOGGER_NAME_LEN]; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 9780bd93b7e4..073aa1051d43 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -1669,6 +1669,7 @@ static struct nft_hook *nft_netdev_hook_alloc(struct net *net, goto err_hook_dev; } hook->ops.dev = dev; + hook->inactive = false; return hook; @@ -1678,17 +1679,17 @@ err_hook_alloc: return ERR_PTR(err); } -static bool nft_hook_list_find(struct list_head *hook_list, - const struct nft_hook *this) +static struct nft_hook *nft_hook_list_find(struct list_head *hook_list, + const struct nft_hook *this) { struct nft_hook *hook; list_for_each_entry(hook, hook_list, list) { if (this->ops.dev == hook->ops.dev) - return true; + return hook; } - return false; + return NULL; } static int nf_tables_parse_netdev_hooks(struct net *net, @@ -1723,8 +1724,6 @@ static int nf_tables_parse_netdev_hooks(struct net *net, goto err_hook; } } - if (!n) - return -EINVAL; return 0; @@ -1761,6 +1760,9 @@ static int nft_chain_parse_netdev(struct net *net, hook_list); if (err < 0) return err; + + if (list_empty(hook_list)) + return -EINVAL; } else { return -EINVAL; } @@ -4669,6 +4671,25 @@ static int nft_setelem_parse_key(struct nft_ctx *ctx, struct nft_set *set, return 0; } +static int nft_setelem_parse_data(struct nft_ctx *ctx, struct nft_set *set, + struct nft_data_desc *desc, + struct nft_data *data, + struct nlattr *attr) +{ + int err; + + err = nft_data_init(ctx, data, NFT_DATA_VALUE_MAXLEN, desc, attr); + if (err < 0) + return err; + + if (desc->type != NFT_DATA_VERDICT && desc->len != set->dlen) { + nft_data_release(data, desc->type); + return -EINVAL; + } + + return 0; +} + static int nft_get_set_elem(struct nft_ctx *ctx, struct nft_set *set, const struct nlattr *attr) { @@ -4946,7 +4967,6 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, struct nft_expr *expr = NULL; struct nft_userdata *udata; struct nft_data_desc desc; - struct nft_data data; enum nft_registers dreg; struct nft_trans *trans; u32 flags = 0; @@ -5072,15 +5092,11 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, } if (nla[NFTA_SET_ELEM_DATA] != NULL) { - err = nft_data_init(ctx, &data, sizeof(data), &desc, - nla[NFTA_SET_ELEM_DATA]); + err = nft_setelem_parse_data(ctx, set, &desc, &elem.data.val, + nla[NFTA_SET_ELEM_DATA]); if (err < 0) goto err_parse_key_end; - err = -EINVAL; - if (set->dtype != NFT_DATA_VERDICT && desc.len != set->dlen) - goto err_parse_data; - dreg = nft_type_to_reg(set->dtype); list_for_each_entry(binding, &set->bindings, list) { struct nft_ctx bind_ctx = { @@ -5094,14 +5110,14 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, continue; err = nft_validate_register_store(&bind_ctx, dreg, - &data, + &elem.data.val, desc.type, desc.len); if (err < 0) goto err_parse_data; if (desc.type == NFT_DATA_VERDICT && - (data.verdict.code == NFT_GOTO || - data.verdict.code == NFT_JUMP)) + (elem.data.val.verdict.code == NFT_GOTO || + elem.data.val.verdict.code == NFT_JUMP)) nft_validate_state_update(ctx->net, NFT_VALIDATE_NEED); } @@ -5123,7 +5139,7 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, err = -ENOMEM; elem.priv = nft_set_elem_init(set, &tmpl, elem.key.val.data, - elem.key_end.val.data, data.data, + elem.key_end.val.data, elem.data.val.data, timeout, expiration, GFP_KERNEL); if (elem.priv == NULL) goto err_parse_data; @@ -5201,7 +5217,7 @@ err_trans: nf_tables_set_elem_destroy(ctx, set, elem.priv); err_parse_data: if (nla[NFTA_SET_ELEM_DATA] != NULL) - nft_data_release(&data, desc.type); + nft_data_release(&elem.data.val, desc.type); err_parse_key_end: nft_data_release(&elem.key_end.val, NFT_DATA_VALUE); err_parse_key: @@ -6164,50 +6180,77 @@ nft_flowtable_lookup_byhandle(const struct nft_table *table, return ERR_PTR(-ENOENT); } +struct nft_flowtable_hook { + u32 num; + int priority; + struct list_head list; +}; + static const struct nla_policy nft_flowtable_hook_policy[NFTA_FLOWTABLE_HOOK_MAX + 1] = { [NFTA_FLOWTABLE_HOOK_NUM] = { .type = NLA_U32 }, [NFTA_FLOWTABLE_HOOK_PRIORITY] = { .type = NLA_U32 }, [NFTA_FLOWTABLE_HOOK_DEVS] = { .type = NLA_NESTED }, }; -static int nf_tables_flowtable_parse_hook(const struct nft_ctx *ctx, - const struct nlattr *attr, - struct nft_flowtable *flowtable) +static int nft_flowtable_parse_hook(const struct nft_ctx *ctx, + const struct nlattr *attr, + struct nft_flowtable_hook *flowtable_hook, + struct nft_flowtable *flowtable, bool add) { struct nlattr *tb[NFTA_FLOWTABLE_HOOK_MAX + 1]; struct nft_hook *hook; int hooknum, priority; int err; + INIT_LIST_HEAD(&flowtable_hook->list); + err = nla_parse_nested_deprecated(tb, NFTA_FLOWTABLE_HOOK_MAX, attr, nft_flowtable_hook_policy, NULL); if (err < 0) return err; - if (!tb[NFTA_FLOWTABLE_HOOK_NUM] || - !tb[NFTA_FLOWTABLE_HOOK_PRIORITY] || - !tb[NFTA_FLOWTABLE_HOOK_DEVS]) - return -EINVAL; + if (add) { + if (!tb[NFTA_FLOWTABLE_HOOK_NUM] || + !tb[NFTA_FLOWTABLE_HOOK_PRIORITY]) + return -EINVAL; - hooknum = ntohl(nla_get_be32(tb[NFTA_FLOWTABLE_HOOK_NUM])); - if (hooknum != NF_NETDEV_INGRESS) - return -EINVAL; + hooknum = ntohl(nla_get_be32(tb[NFTA_FLOWTABLE_HOOK_NUM])); + if (hooknum != NF_NETDEV_INGRESS) + return -EOPNOTSUPP; - priority = ntohl(nla_get_be32(tb[NFTA_FLOWTABLE_HOOK_PRIORITY])); + priority = ntohl(nla_get_be32(tb[NFTA_FLOWTABLE_HOOK_PRIORITY])); - err = nf_tables_parse_netdev_hooks(ctx->net, - tb[NFTA_FLOWTABLE_HOOK_DEVS], - &flowtable->hook_list); - if (err < 0) - return err; + flowtable_hook->priority = priority; + flowtable_hook->num = hooknum; + } else { + if (tb[NFTA_FLOWTABLE_HOOK_NUM]) { + hooknum = ntohl(nla_get_be32(tb[NFTA_FLOWTABLE_HOOK_NUM])); + if (hooknum != flowtable->hooknum) + return -EOPNOTSUPP; + } - flowtable->hooknum = hooknum; - flowtable->data.priority = priority; + if (tb[NFTA_FLOWTABLE_HOOK_PRIORITY]) { + priority = ntohl(nla_get_be32(tb[NFTA_FLOWTABLE_HOOK_PRIORITY])); + if (priority != flowtable->data.priority) + return -EOPNOTSUPP; + } - list_for_each_entry(hook, &flowtable->hook_list, list) { + flowtable_hook->priority = flowtable->data.priority; + flowtable_hook->num = flowtable->hooknum; + } + + if (tb[NFTA_FLOWTABLE_HOOK_DEVS]) { + err = nf_tables_parse_netdev_hooks(ctx->net, + tb[NFTA_FLOWTABLE_HOOK_DEVS], + &flowtable_hook->list); + if (err < 0) + return err; + } + + list_for_each_entry(hook, &flowtable_hook->list, list) { hook->ops.pf = NFPROTO_NETDEV; - hook->ops.hooknum = hooknum; - hook->ops.priority = priority; + hook->ops.hooknum = flowtable_hook->num; + hook->ops.priority = flowtable_hook->priority; hook->ops.priv = &flowtable->data; hook->ops.hook = flowtable->data.type->hook; } @@ -6256,23 +6299,24 @@ static void nft_unregister_flowtable_hook(struct net *net, } static void nft_unregister_flowtable_net_hooks(struct net *net, - struct nft_flowtable *flowtable) + struct list_head *hook_list) { struct nft_hook *hook; - list_for_each_entry(hook, &flowtable->hook_list, list) + list_for_each_entry(hook, hook_list, list) nf_unregister_net_hook(net, &hook->ops); } static int nft_register_flowtable_net_hooks(struct net *net, struct nft_table *table, + struct list_head *hook_list, struct nft_flowtable *flowtable) { struct nft_hook *hook, *hook2, *next; struct nft_flowtable *ft; int err, i = 0; - list_for_each_entry(hook, &flowtable->hook_list, list) { + list_for_each_entry(hook, hook_list, list) { list_for_each_entry(ft, &table->flowtables, list) { list_for_each_entry(hook2, &ft->hook_list, list) { if (hook->ops.dev == hook2->ops.dev && @@ -6303,7 +6347,7 @@ static int nft_register_flowtable_net_hooks(struct net *net, return 0; err_unregister_net_hooks: - list_for_each_entry_safe(hook, next, &flowtable->hook_list, list) { + list_for_each_entry_safe(hook, next, hook_list, list) { if (i-- <= 0) break; @@ -6315,6 +6359,72 @@ err_unregister_net_hooks: return err; } +static void nft_flowtable_hooks_destroy(struct list_head *hook_list) +{ + struct nft_hook *hook, *next; + + list_for_each_entry_safe(hook, next, hook_list, list) { + list_del_rcu(&hook->list); + kfree_rcu(hook, rcu); + } +} + +static int nft_flowtable_update(struct nft_ctx *ctx, const struct nlmsghdr *nlh, + struct nft_flowtable *flowtable) +{ + const struct nlattr * const *nla = ctx->nla; + struct nft_flowtable_hook flowtable_hook; + struct nft_hook *hook, *next; + struct nft_trans *trans; + bool unregister = false; + int err; + + err = nft_flowtable_parse_hook(ctx, nla[NFTA_FLOWTABLE_HOOK], + &flowtable_hook, flowtable, false); + if (err < 0) + return err; + + list_for_each_entry_safe(hook, next, &flowtable_hook.list, list) { + if (nft_hook_list_find(&flowtable->hook_list, hook)) { + list_del(&hook->list); + kfree(hook); + } + } + + err = nft_register_flowtable_net_hooks(ctx->net, ctx->table, + &flowtable_hook.list, flowtable); + if (err < 0) + goto err_flowtable_update_hook; + + trans = nft_trans_alloc(ctx, NFT_MSG_NEWFLOWTABLE, + sizeof(struct nft_trans_flowtable)); + if (!trans) { + unregister = true; + err = -ENOMEM; + goto err_flowtable_update_hook; + } + + nft_trans_flowtable(trans) = flowtable; + nft_trans_flowtable_update(trans) = true; + INIT_LIST_HEAD(&nft_trans_flowtable_hooks(trans)); + list_splice(&flowtable_hook.list, &nft_trans_flowtable_hooks(trans)); + + list_add_tail(&trans->list, &ctx->net->nft.commit_list); + + return 0; + +err_flowtable_update_hook: + list_for_each_entry_safe(hook, next, &flowtable_hook.list, list) { + if (unregister) + nft_unregister_flowtable_hook(ctx->net, flowtable, hook); + list_del_rcu(&hook->list); + kfree_rcu(hook, rcu); + } + + return err; + +} + static int nf_tables_newflowtable(struct net *net, struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, @@ -6322,6 +6432,7 @@ static int nf_tables_newflowtable(struct net *net, struct sock *nlsk, struct netlink_ext_ack *extack) { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); + struct nft_flowtable_hook flowtable_hook; const struct nf_flowtable_type *type; u8 genmask = nft_genmask_next(net); int family = nfmsg->nfgen_family; @@ -6357,7 +6468,9 @@ static int nf_tables_newflowtable(struct net *net, struct sock *nlsk, return -EEXIST; } - return 0; + nft_ctx_init(&ctx, net, skb, nlh, family, table, NULL, nla); + + return nft_flowtable_update(&ctx, nlh, flowtable); } nft_ctx_init(&ctx, net, skb, nlh, family, table, NULL, nla); @@ -6395,17 +6508,20 @@ static int nf_tables_newflowtable(struct net *net, struct sock *nlsk, if (err < 0) goto err3; - err = nf_tables_flowtable_parse_hook(&ctx, nla[NFTA_FLOWTABLE_HOOK], - flowtable); + err = nft_flowtable_parse_hook(&ctx, nla[NFTA_FLOWTABLE_HOOK], + &flowtable_hook, flowtable, true); if (err < 0) goto err4; - err = nft_register_flowtable_net_hooks(ctx.net, table, flowtable); + list_splice(&flowtable_hook.list, &flowtable->hook_list); + flowtable->data.priority = flowtable_hook.priority; + flowtable->hooknum = flowtable_hook.num; + + err = nft_register_flowtable_net_hooks(ctx.net, table, + &flowtable->hook_list, + flowtable); if (err < 0) { - list_for_each_entry_safe(hook, next, &flowtable->hook_list, list) { - list_del_rcu(&hook->list); - kfree_rcu(hook, rcu); - } + nft_flowtable_hooks_destroy(&flowtable->hook_list); goto err4; } @@ -6434,6 +6550,51 @@ err1: return err; } +static int nft_delflowtable_hook(struct nft_ctx *ctx, + struct nft_flowtable *flowtable) +{ + const struct nlattr * const *nla = ctx->nla; + struct nft_flowtable_hook flowtable_hook; + struct nft_hook *this, *next, *hook; + struct nft_trans *trans; + int err; + + err = nft_flowtable_parse_hook(ctx, nla[NFTA_FLOWTABLE_HOOK], + &flowtable_hook, flowtable, false); + if (err < 0) + return err; + + list_for_each_entry_safe(this, next, &flowtable_hook.list, list) { + hook = nft_hook_list_find(&flowtable->hook_list, this); + if (!hook) { + err = -ENOENT; + goto err_flowtable_del_hook; + } + hook->inactive = true; + list_del(&this->list); + kfree(this); + } + + trans = nft_trans_alloc(ctx, NFT_MSG_DELFLOWTABLE, + sizeof(struct nft_trans_flowtable)); + if (!trans) + return -ENOMEM; + + nft_trans_flowtable(trans) = flowtable; + nft_trans_flowtable_update(trans) = true; + INIT_LIST_HEAD(&nft_trans_flowtable_hooks(trans)); + + list_add_tail(&trans->list, &ctx->net->nft.commit_list); + + return 0; + +err_flowtable_del_hook: + list_for_each_entry(hook, &flowtable_hook.list, list) + hook->inactive = false; + + return err; +} + static int nf_tables_delflowtable(struct net *net, struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, @@ -6472,20 +6633,25 @@ static int nf_tables_delflowtable(struct net *net, struct sock *nlsk, NL_SET_BAD_ATTR(extack, attr); return PTR_ERR(flowtable); } + + nft_ctx_init(&ctx, net, skb, nlh, family, table, NULL, nla); + + if (nla[NFTA_FLOWTABLE_HOOK]) + return nft_delflowtable_hook(&ctx, flowtable); + if (flowtable->use > 0) { NL_SET_BAD_ATTR(extack, attr); return -EBUSY; } - nft_ctx_init(&ctx, net, skb, nlh, family, table, NULL, nla); - return nft_delflowtable(&ctx, flowtable); } static int nf_tables_fill_flowtable_info(struct sk_buff *skb, struct net *net, u32 portid, u32 seq, int event, u32 flags, int family, - struct nft_flowtable *flowtable) + struct nft_flowtable *flowtable, + struct list_head *hook_list) { struct nlattr *nest, *nest_devs; struct nfgenmsg *nfmsg; @@ -6521,7 +6687,7 @@ static int nf_tables_fill_flowtable_info(struct sk_buff *skb, struct net *net, if (!nest_devs) goto nla_put_failure; - list_for_each_entry_rcu(hook, &flowtable->hook_list, list) { + list_for_each_entry_rcu(hook, hook_list, list) { if (nla_put_string(skb, NFTA_DEVICE_NAME, hook->ops.dev->name)) goto nla_put_failure; } @@ -6574,7 +6740,9 @@ static int nf_tables_dump_flowtable(struct sk_buff *skb, cb->nlh->nlmsg_seq, NFT_MSG_NEWFLOWTABLE, NLM_F_MULTI | NLM_F_APPEND, - table->family, flowtable) < 0) + table->family, + flowtable, + &flowtable->hook_list) < 0) goto done; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); @@ -6671,7 +6839,7 @@ static int nf_tables_getflowtable(struct net *net, struct sock *nlsk, err = nf_tables_fill_flowtable_info(skb2, net, NETLINK_CB(skb).portid, nlh->nlmsg_seq, NFT_MSG_NEWFLOWTABLE, 0, family, - flowtable); + flowtable, &flowtable->hook_list); if (err < 0) goto err; @@ -6683,6 +6851,7 @@ err: static void nf_tables_flowtable_notify(struct nft_ctx *ctx, struct nft_flowtable *flowtable, + struct list_head *hook_list, int event) { struct sk_buff *skb; @@ -6698,7 +6867,7 @@ static void nf_tables_flowtable_notify(struct nft_ctx *ctx, err = nf_tables_fill_flowtable_info(skb, ctx->net, ctx->portid, ctx->seq, event, 0, - ctx->family, flowtable); + ctx->family, flowtable, hook_list); if (err < 0) { kfree_skb(skb); goto err; @@ -7084,7 +7253,10 @@ static void nft_commit_release(struct nft_trans *trans) nft_obj_destroy(&trans->ctx, nft_trans_obj(trans)); break; case NFT_MSG_DELFLOWTABLE: - nf_tables_flowtable_destroy(nft_trans_flowtable(trans)); + if (nft_trans_flowtable_update(trans)) + nft_flowtable_hooks_destroy(&nft_trans_flowtable_hooks(trans)); + else + nf_tables_flowtable_destroy(nft_trans_flowtable(trans)); break; } @@ -7245,6 +7417,17 @@ static void nft_chain_del(struct nft_chain *chain) list_del_rcu(&chain->list); } +static void nft_flowtable_hooks_del(struct nft_flowtable *flowtable, + struct list_head *hook_list) +{ + struct nft_hook *hook, *next; + + list_for_each_entry_safe(hook, next, &flowtable->hook_list, list) { + if (hook->inactive) + list_move(&hook->list, hook_list); + } +} + static void nf_tables_module_autoload_cleanup(struct net *net) { struct nft_module_request *req, *next; @@ -7453,19 +7636,41 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) NFT_MSG_DELOBJ); break; case NFT_MSG_NEWFLOWTABLE: - nft_clear(net, nft_trans_flowtable(trans)); - nf_tables_flowtable_notify(&trans->ctx, - nft_trans_flowtable(trans), - NFT_MSG_NEWFLOWTABLE); + if (nft_trans_flowtable_update(trans)) { + nf_tables_flowtable_notify(&trans->ctx, + nft_trans_flowtable(trans), + &nft_trans_flowtable_hooks(trans), + NFT_MSG_NEWFLOWTABLE); + list_splice(&nft_trans_flowtable_hooks(trans), + &nft_trans_flowtable(trans)->hook_list); + } else { + nft_clear(net, nft_trans_flowtable(trans)); + nf_tables_flowtable_notify(&trans->ctx, + nft_trans_flowtable(trans), + &nft_trans_flowtable(trans)->hook_list, + NFT_MSG_NEWFLOWTABLE); + } nft_trans_destroy(trans); break; case NFT_MSG_DELFLOWTABLE: - list_del_rcu(&nft_trans_flowtable(trans)->list); - nf_tables_flowtable_notify(&trans->ctx, - nft_trans_flowtable(trans), - NFT_MSG_DELFLOWTABLE); - nft_unregister_flowtable_net_hooks(net, - nft_trans_flowtable(trans)); + if (nft_trans_flowtable_update(trans)) { + nft_flowtable_hooks_del(nft_trans_flowtable(trans), + &nft_trans_flowtable_hooks(trans)); + nf_tables_flowtable_notify(&trans->ctx, + nft_trans_flowtable(trans), + &nft_trans_flowtable_hooks(trans), + NFT_MSG_DELFLOWTABLE); + nft_unregister_flowtable_net_hooks(net, + &nft_trans_flowtable_hooks(trans)); + } else { + list_del_rcu(&nft_trans_flowtable(trans)->list); + nf_tables_flowtable_notify(&trans->ctx, + nft_trans_flowtable(trans), + &nft_trans_flowtable(trans)->hook_list, + NFT_MSG_DELFLOWTABLE); + nft_unregister_flowtable_net_hooks(net, + &nft_trans_flowtable(trans)->hook_list); + } break; } } @@ -7514,7 +7719,10 @@ static void nf_tables_abort_release(struct nft_trans *trans) nft_obj_destroy(&trans->ctx, nft_trans_obj(trans)); break; case NFT_MSG_NEWFLOWTABLE: - nf_tables_flowtable_destroy(nft_trans_flowtable(trans)); + if (nft_trans_flowtable_update(trans)) + nft_flowtable_hooks_destroy(&nft_trans_flowtable_hooks(trans)); + else + nf_tables_flowtable_destroy(nft_trans_flowtable(trans)); break; } kfree(trans); @@ -7524,6 +7732,7 @@ static int __nf_tables_abort(struct net *net, bool autoload) { struct nft_trans *trans, *next; struct nft_trans_elem *te; + struct nft_hook *hook; list_for_each_entry_safe_reverse(trans, next, &net->nft.commit_list, list) { @@ -7621,14 +7830,24 @@ static int __nf_tables_abort(struct net *net, bool autoload) nft_trans_destroy(trans); break; case NFT_MSG_NEWFLOWTABLE: - trans->ctx.table->use--; - list_del_rcu(&nft_trans_flowtable(trans)->list); - nft_unregister_flowtable_net_hooks(net, - nft_trans_flowtable(trans)); + if (nft_trans_flowtable_update(trans)) { + nft_unregister_flowtable_net_hooks(net, + &nft_trans_flowtable_hooks(trans)); + } else { + trans->ctx.table->use--; + list_del_rcu(&nft_trans_flowtable(trans)->list); + nft_unregister_flowtable_net_hooks(net, + &nft_trans_flowtable(trans)->hook_list); + } break; case NFT_MSG_DELFLOWTABLE: - trans->ctx.table->use++; - nft_clear(trans->ctx.net, nft_trans_flowtable(trans)); + if (nft_trans_flowtable_update(trans)) { + list_for_each_entry(hook, &nft_trans_flowtable(trans)->hook_list, list) + hook->inactive = false; + } else { + trans->ctx.table->use++; + nft_clear(trans->ctx.net, nft_trans_flowtable(trans)); + } nft_trans_destroy(trans); break; } diff --git a/net/netfilter/nf_tables_offload.c b/net/netfilter/nf_tables_offload.c index 954bccb7f32a..185fc82c99aa 100644 --- a/net/netfilter/nf_tables_offload.c +++ b/net/netfilter/nf_tables_offload.c @@ -285,40 +285,41 @@ static int nft_block_offload_cmd(struct nft_base_chain *chain, return nft_block_setup(chain, &bo, cmd); } -static void nft_indr_block_ing_cmd(struct net_device *dev, - struct nft_base_chain *chain, - flow_indr_block_bind_cb_t *cb, - void *cb_priv, - enum flow_block_command cmd) +static void nft_indr_block_cleanup(struct flow_block_cb *block_cb) { + struct nft_base_chain *basechain = block_cb->indr.data; + struct net_device *dev = block_cb->indr.dev; struct netlink_ext_ack extack = {}; + struct net *net = dev_net(dev); struct flow_block_offload bo; - if (!chain) - return; - - nft_flow_block_offload_init(&bo, dev_net(dev), cmd, chain, &extack); - - cb(dev, cb_priv, TC_SETUP_BLOCK, &bo); - - nft_block_setup(chain, &bo, cmd); + nft_flow_block_offload_init(&bo, dev_net(dev), FLOW_BLOCK_UNBIND, + basechain, &extack); + mutex_lock(&net->nft.commit_mutex); + list_move(&block_cb->list, &bo.cb_list); + nft_flow_offload_unbind(&bo, basechain); + mutex_unlock(&net->nft.commit_mutex); } -static int nft_indr_block_offload_cmd(struct nft_base_chain *chain, +static int nft_indr_block_offload_cmd(struct nft_base_chain *basechain, struct net_device *dev, enum flow_block_command cmd) { struct netlink_ext_ack extack = {}; struct flow_block_offload bo; + int err; - nft_flow_block_offload_init(&bo, dev_net(dev), cmd, chain, &extack); + nft_flow_block_offload_init(&bo, dev_net(dev), cmd, basechain, &extack); - flow_indr_block_call(dev, &bo, cmd, TC_SETUP_BLOCK); + err = flow_indr_dev_setup_offload(dev, TC_SETUP_BLOCK, basechain, &bo, + nft_indr_block_cleanup); + if (err < 0) + return err; if (list_empty(&bo.cb_list)) return -EOPNOTSUPP; - return nft_block_setup(chain, &bo, cmd); + return nft_block_setup(basechain, &bo, cmd); } #define FLOW_SETUP_BLOCK TC_SETUP_BLOCK @@ -555,24 +556,6 @@ static struct nft_chain *__nft_offload_get_chain(struct net_device *dev) 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 && chain->flags & NFT_CHAIN_HW_OFFLOAD) { - 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 int nft_offload_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { @@ -594,30 +577,16 @@ static int nft_offload_netdev_event(struct notifier_block *this, return NOTIFY_DONE; } -static struct flow_indr_block_entry block_ing_entry = { - .cb = nft_indr_block_cb, - .list = LIST_HEAD_INIT(block_ing_entry.list), -}; - static struct notifier_block nft_offload_netdev_notifier = { .notifier_call = nft_offload_netdev_event, }; int nft_offload_init(void) { - int err; - - err = register_netdevice_notifier(&nft_offload_netdev_notifier); - if (err < 0) - return err; - - flow_indr_add_block_cb(&block_ing_entry); - - return 0; + return register_netdevice_notifier(&nft_offload_netdev_notifier); } void nft_offload_exit(void) { - flow_indr_del_block_cb(&block_ing_entry); unregister_netdevice_notifier(&nft_offload_netdev_notifier); } diff --git a/net/netfilter/nft_nat.c b/net/netfilter/nft_nat.c index 8b44a4de5329..23a7bfd10521 100644 --- a/net/netfilter/nft_nat.c +++ b/net/netfilter/nft_nat.c @@ -30,6 +30,76 @@ struct nft_nat { u16 flags; }; +static void nft_nat_setup_addr(struct nf_nat_range2 *range, + const struct nft_regs *regs, + const struct nft_nat *priv) +{ + switch (priv->family) { + case AF_INET: + range->min_addr.ip = (__force __be32) + regs->data[priv->sreg_addr_min]; + range->max_addr.ip = (__force __be32) + regs->data[priv->sreg_addr_max]; + break; + case AF_INET6: + memcpy(range->min_addr.ip6, ®s->data[priv->sreg_addr_min], + sizeof(range->min_addr.ip6)); + memcpy(range->max_addr.ip6, ®s->data[priv->sreg_addr_max], + sizeof(range->max_addr.ip6)); + break; + } +} + +static void nft_nat_setup_proto(struct nf_nat_range2 *range, + const struct nft_regs *regs, + const struct nft_nat *priv) +{ + range->min_proto.all = (__force __be16) + nft_reg_load16(®s->data[priv->sreg_proto_min]); + range->max_proto.all = (__force __be16) + nft_reg_load16(®s->data[priv->sreg_proto_max]); +} + +static void nft_nat_setup_netmap(struct nf_nat_range2 *range, + const struct nft_pktinfo *pkt, + const struct nft_nat *priv) +{ + struct sk_buff *skb = pkt->skb; + union nf_inet_addr new_addr; + __be32 netmask; + int i, len = 0; + + switch (priv->type) { + case NFT_NAT_SNAT: + if (nft_pf(pkt) == NFPROTO_IPV4) { + new_addr.ip = ip_hdr(skb)->saddr; + len = sizeof(struct in_addr); + } else { + new_addr.in6 = ipv6_hdr(skb)->saddr; + len = sizeof(struct in6_addr); + } + break; + case NFT_NAT_DNAT: + if (nft_pf(pkt) == NFPROTO_IPV4) { + new_addr.ip = ip_hdr(skb)->daddr; + len = sizeof(struct in_addr); + } else { + new_addr.in6 = ipv6_hdr(skb)->daddr; + len = sizeof(struct in6_addr); + } + break; + } + + for (i = 0; i < len / sizeof(__be32); i++) { + netmask = ~(range->min_addr.ip6[i] ^ range->max_addr.ip6[i]); + new_addr.ip6[i] &= ~netmask; + new_addr.ip6[i] |= range->min_addr.ip6[i] & netmask; + } + + range->min_addr = new_addr; + range->max_addr = new_addr; +} + static void nft_nat_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) @@ -40,33 +110,17 @@ static void nft_nat_eval(const struct nft_expr *expr, struct nf_nat_range2 range; memset(&range, 0, sizeof(range)); - if (priv->sreg_addr_min) { - if (priv->family == AF_INET) { - range.min_addr.ip = (__force __be32) - regs->data[priv->sreg_addr_min]; - range.max_addr.ip = (__force __be32) - regs->data[priv->sreg_addr_max]; - } else { - memcpy(range.min_addr.ip6, - ®s->data[priv->sreg_addr_min], - sizeof(range.min_addr.ip6)); - memcpy(range.max_addr.ip6, - ®s->data[priv->sreg_addr_max], - sizeof(range.max_addr.ip6)); - } - range.flags |= NF_NAT_RANGE_MAP_IPS; + if (priv->sreg_addr_min) { + nft_nat_setup_addr(&range, regs, priv); + if (priv->flags & NF_NAT_RANGE_NETMAP) + nft_nat_setup_netmap(&range, pkt, priv); } - if (priv->sreg_proto_min) { - range.min_proto.all = (__force __be16)nft_reg_load16( - ®s->data[priv->sreg_proto_min]); - range.max_proto.all = (__force __be16)nft_reg_load16( - ®s->data[priv->sreg_proto_max]); - range.flags |= NF_NAT_RANGE_PROTO_SPECIFIED; - } + if (priv->sreg_proto_min) + nft_nat_setup_proto(&range, regs, priv); - range.flags |= priv->flags; + range.flags = priv->flags; regs->verdict.code = nf_nat_setup_info(ct, &range, priv->type); } @@ -129,7 +183,7 @@ static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr, priv->type = NF_NAT_MANIP_DST; break; default: - return -EINVAL; + return -EOPNOTSUPP; } if (tb[NFTA_NAT_FAMILY] == NULL) @@ -169,6 +223,8 @@ static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr, } else { priv->sreg_addr_max = priv->sreg_addr_min; } + + priv->flags |= NF_NAT_RANGE_MAP_IPS; } plen = sizeof_field(struct nf_nat_range, min_addr.all); @@ -191,12 +247,14 @@ static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr, } else { priv->sreg_proto_max = priv->sreg_proto_min; } + + priv->flags |= NF_NAT_RANGE_PROTO_SPECIFIED; } if (tb[NFTA_NAT_FLAGS]) { - priv->flags = ntohl(nla_get_be32(tb[NFTA_NAT_FLAGS])); + priv->flags |= ntohl(nla_get_be32(tb[NFTA_NAT_FLAGS])); if (priv->flags & ~NF_NAT_RANGE_MASK) - return -EINVAL; + return -EOPNOTSUPP; } return nf_ct_netns_get(ctx->net, family); |