OpenCloudOS-Kernel/net/ipv4/ip_tunnel_core.c

636 lines
17 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (c) 2013 Nicira, Inc.
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/skbuff.h>
#include <linux/netdevice.h>
#include <linux/in.h>
#include <linux/if_arp.h>
#include <linux/init.h>
#include <linux/in6.h>
#include <linux/inetdevice.h>
#include <linux/netfilter_ipv4.h>
#include <linux/etherdevice.h>
#include <linux/if_ether.h>
#include <linux/if_vlan.h>
#include <linux/static_key.h>
#include <net/ip.h>
#include <net/icmp.h>
#include <net/protocol.h>
#include <net/ip_tunnels.h>
#include <net/ip6_tunnel.h>
#include <net/arp.h>
#include <net/checksum.h>
#include <net/dsfield.h>
#include <net/inet_ecn.h>
#include <net/xfrm.h>
#include <net/net_namespace.h>
#include <net/netns/generic.h>
#include <net/rtnetlink.h>
#include <net/dst_metadata.h>
#include <net/geneve.h>
const struct ip_tunnel_encap_ops __rcu *
iptun_encaps[MAX_IPTUN_ENCAP_OPS] __read_mostly;
EXPORT_SYMBOL(iptun_encaps);
const struct ip6_tnl_encap_ops __rcu *
ip6tun_encaps[MAX_IPTUN_ENCAP_OPS] __read_mostly;
EXPORT_SYMBOL(ip6tun_encaps);
void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb,
__be32 src, __be32 dst, __u8 proto,
__u8 tos, __u8 ttl, __be16 df, bool xnet)
{
int pkt_len = skb->len - skb_inner_network_offset(skb);
struct net *net = dev_net(rt->dst.dev);
struct net_device *dev = skb->dev;
struct iphdr *iph;
int err;
skb_scrub_packet(skb, xnet);
skb_clear_hash_if_not_l4(skb);
skb_dst_set(skb, &rt->dst);
memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
/* Push down and install the IP header. */
skb_push(skb, sizeof(struct iphdr));
skb_reset_network_header(skb);
iph = ip_hdr(skb);
iph->version = 4;
iph->ihl = sizeof(struct iphdr) >> 2;
iph->frag_off = ip_mtu_locked(&rt->dst) ? 0 : df;
iph->protocol = proto;
iph->tos = tos;
iph->daddr = dst;
iph->saddr = src;
iph->ttl = ttl;
__ip_select_ident(net, iph, skb_shinfo(skb)->gso_segs ?: 1);
err = ip_local_out(net, sk, skb);
if (dev) {
if (unlikely(net_xmit_eval(err)))
pkt_len = 0;
iptunnel_xmit_stats(dev, pkt_len);
}
}
EXPORT_SYMBOL_GPL(iptunnel_xmit);
int __iptunnel_pull_header(struct sk_buff *skb, int hdr_len,
__be16 inner_proto, bool raw_proto, bool xnet)
{
if (unlikely(!pskb_may_pull(skb, hdr_len)))
return -ENOMEM;
skb_pull_rcsum(skb, hdr_len);
if (!raw_proto && inner_proto == htons(ETH_P_TEB)) {
struct ethhdr *eh;
if (unlikely(!pskb_may_pull(skb, ETH_HLEN)))
return -ENOMEM;
eh = (struct ethhdr *)skb->data;
if (likely(eth_proto_is_802_3(eh->h_proto)))
skb->protocol = eh->h_proto;
else
skb->protocol = htons(ETH_P_802_2);
} else {
skb->protocol = inner_proto;
}
skb_clear_hash_if_not_l4(skb);
__vlan_hwaccel_clear_tag(skb);
skb_set_queue_mapping(skb, 0);
skb_scrub_packet(skb, xnet);
return iptunnel_pull_offloads(skb);
}
EXPORT_SYMBOL_GPL(__iptunnel_pull_header);
struct metadata_dst *iptunnel_metadata_reply(struct metadata_dst *md,
gfp_t flags)
{
struct metadata_dst *res;
struct ip_tunnel_info *dst, *src;
net: store port/representator id in metadata_dst Switches and modern SR-IOV enabled NICs may multiplex traffic from Port representators and control messages over single set of hardware queues. Control messages and muxed traffic may need ordered delivery. Those requirements make it hard to comfortably use TC infrastructure today unless we have a way of attaching metadata to skbs at the upper device. Because single set of queues is used for many netdevs stopping TC/sched queues of all of them reliably is impossible and lower device has to retreat to returning NETDEV_TX_BUSY and usually has to take extra locks on the fastpath. This patch attempts to enable port/representative devs to attach metadata to skbs which carry port id. This way representatives can be queueless and all queuing can be performed at the lower netdev in the usual way. Traffic arriving on the port/representative interfaces will be have metadata attached and will subsequently be queued to the lower device for transmission. The lower device should recognize the metadata and translate it to HW specific format which is most likely either a special header inserted before the network headers or descriptor/metadata fields. Metadata is associated with the lower device by storing the netdev pointer along with port id so that if TC decides to redirect or mirror the new netdev will not try to interpret it. This is mostly for SR-IOV devices since switches don't have lower netdevs today. Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com> Signed-off-by: Sridhar Samudrala <sridhar.samudrala@intel.com> Signed-off-by: Simon Horman <horms@verge.net.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-06-24 04:11:58 +08:00
if (!md || md->type != METADATA_IP_TUNNEL ||
md->u.tun_info.mode & IP_TUNNEL_INFO_TX)
return NULL;
src = &md->u.tun_info;
res = metadata_dst_alloc(src->options_len, METADATA_IP_TUNNEL, flags);
if (!res)
return NULL;
dst = &res->u.tun_info;
dst->key.tun_id = src->key.tun_id;
if (src->mode & IP_TUNNEL_INFO_IPV6)
memcpy(&dst->key.u.ipv6.dst, &src->key.u.ipv6.src,
sizeof(struct in6_addr));
else
dst->key.u.ipv4.dst = src->key.u.ipv4.src;
dst->key.tun_flags = src->key.tun_flags;
dst->mode = src->mode | IP_TUNNEL_INFO_TX;
ip_tunnel_info_opts_set(dst, ip_tunnel_info_opts(src),
src->options_len, 0);
return res;
}
EXPORT_SYMBOL_GPL(iptunnel_metadata_reply);
int iptunnel_handle_offloads(struct sk_buff *skb,
int gso_type_mask)
{
int err;
if (likely(!skb->encapsulation)) {
skb_reset_inner_headers(skb);
skb->encapsulation = 1;
}
if (skb_is_gso(skb)) {
err = skb_header_unclone(skb, GFP_ATOMIC);
if (unlikely(err))
return err;
skb_shinfo(skb)->gso_type |= gso_type_mask;
return 0;
}
if (skb->ip_summed != CHECKSUM_PARTIAL) {
skb->ip_summed = CHECKSUM_NONE;
/* We clear encapsulation here to prevent badly-written
* drivers potentially deciding to offload an inner checksum
* if we set CHECKSUM_PARTIAL on the outer header.
* This should go away when the drivers are all fixed.
*/
skb->encapsulation = 0;
}
return 0;
}
EXPORT_SYMBOL_GPL(iptunnel_handle_offloads);
/* Often modified stats are per cpu, other are shared (netdev->stats) */
void ip_tunnel_get_stats64(struct net_device *dev,
struct rtnl_link_stats64 *tot)
{
int i;
netdev_stats_to_stats64(tot, &dev->stats);
for_each_possible_cpu(i) {
const struct pcpu_sw_netstats *tstats =
per_cpu_ptr(dev->tstats, i);
u64 rx_packets, rx_bytes, tx_packets, tx_bytes;
unsigned int start;
do {
start = u64_stats_fetch_begin_irq(&tstats->syncp);
rx_packets = tstats->rx_packets;
tx_packets = tstats->tx_packets;
rx_bytes = tstats->rx_bytes;
tx_bytes = tstats->tx_bytes;
} while (u64_stats_fetch_retry_irq(&tstats->syncp, start));
tot->rx_packets += rx_packets;
tot->tx_packets += tx_packets;
tot->rx_bytes += rx_bytes;
tot->tx_bytes += tx_bytes;
}
}
EXPORT_SYMBOL_GPL(ip_tunnel_get_stats64);
static const struct nla_policy ip_tun_policy[LWTUNNEL_IP_MAX + 1] = {
[LWTUNNEL_IP_ID] = { .type = NLA_U64 },
[LWTUNNEL_IP_DST] = { .type = NLA_U32 },
[LWTUNNEL_IP_SRC] = { .type = NLA_U32 },
[LWTUNNEL_IP_TTL] = { .type = NLA_U8 },
[LWTUNNEL_IP_TOS] = { .type = NLA_U8 },
[LWTUNNEL_IP_FLAGS] = { .type = NLA_U16 },
[LWTUNNEL_IP_OPTS] = { .type = NLA_NESTED },
};
static const struct nla_policy ip_opts_policy[LWTUNNEL_IP_OPTS_MAX + 1] = {
[LWTUNNEL_IP_OPTS_GENEVE] = { .type = NLA_NESTED },
};
static const struct nla_policy
geneve_opt_policy[LWTUNNEL_IP_OPT_GENEVE_MAX + 1] = {
[LWTUNNEL_IP_OPT_GENEVE_CLASS] = { .type = NLA_U16 },
[LWTUNNEL_IP_OPT_GENEVE_TYPE] = { .type = NLA_U8 },
[LWTUNNEL_IP_OPT_GENEVE_DATA] = { .type = NLA_BINARY, .len = 128 },
};
static int ip_tun_parse_opts_geneve(struct nlattr *attr,
struct ip_tunnel_info *info,
struct netlink_ext_ack *extack)
{
struct nlattr *tb[LWTUNNEL_IP_OPT_GENEVE_MAX + 1];
int data_len, err;
err = nla_parse_nested_deprecated(tb, LWTUNNEL_IP_OPT_GENEVE_MAX,
attr, geneve_opt_policy, extack);
if (err)
return err;
if (!tb[LWTUNNEL_IP_OPT_GENEVE_CLASS] ||
!tb[LWTUNNEL_IP_OPT_GENEVE_TYPE] ||
!tb[LWTUNNEL_IP_OPT_GENEVE_DATA])
return -EINVAL;
attr = tb[LWTUNNEL_IP_OPT_GENEVE_DATA];
data_len = nla_len(attr);
if (data_len % 4)
return -EINVAL;
if (info) {
struct geneve_opt *opt = ip_tunnel_info_opts(info);
memcpy(opt->opt_data, nla_data(attr), data_len);
opt->length = data_len / 4;
attr = tb[LWTUNNEL_IP_OPT_GENEVE_CLASS];
opt->opt_class = nla_get_be16(attr);
attr = tb[LWTUNNEL_IP_OPT_GENEVE_TYPE];
opt->type = nla_get_u8(attr);
info->key.tun_flags |= TUNNEL_GENEVE_OPT;
}
return sizeof(struct geneve_opt) + data_len;
}
static int ip_tun_parse_opts(struct nlattr *attr, struct ip_tunnel_info *info,
struct netlink_ext_ack *extack)
{
struct nlattr *tb[LWTUNNEL_IP_OPTS_MAX + 1];
int err;
if (!attr)
return 0;
err = nla_parse_nested_deprecated(tb, LWTUNNEL_IP_OPTS_MAX, attr,
ip_opts_policy, extack);
if (err)
return err;
if (tb[LWTUNNEL_IP_OPTS_GENEVE])
err = ip_tun_parse_opts_geneve(tb[LWTUNNEL_IP_OPTS_GENEVE],
info, extack);
else
err = -EINVAL;
return err;
}
static int ip_tun_get_optlen(struct nlattr *attr,
struct netlink_ext_ack *extack)
{
return ip_tun_parse_opts(attr, NULL, extack);
}
static int ip_tun_set_opts(struct nlattr *attr, struct ip_tunnel_info *info,
struct netlink_ext_ack *extack)
{
return ip_tun_parse_opts(attr, info, extack);
}
static int ip_tun_build_state(struct nlattr *attr,
unsigned int family, const void *cfg,
struct lwtunnel_state **ts,
struct netlink_ext_ack *extack)
{
struct nlattr *tb[LWTUNNEL_IP_MAX + 1];
struct lwtunnel_state *new_state;
struct ip_tunnel_info *tun_info;
int err, opt_len;
netlink: make validation more configurable for future strictness We currently have two levels of strict validation: 1) liberal (default) - undefined (type >= max) & NLA_UNSPEC attributes accepted - attribute length >= expected accepted - garbage at end of message accepted 2) strict (opt-in) - NLA_UNSPEC attributes accepted - attribute length >= expected accepted Split out parsing strictness into four different options: * TRAILING - check that there's no trailing data after parsing attributes (in message or nested) * MAXTYPE - reject attrs > max known type * UNSPEC - reject attributes with NLA_UNSPEC policy entries * STRICT_ATTRS - strictly validate attribute size The default for future things should be *everything*. The current *_strict() is a combination of TRAILING and MAXTYPE, and is renamed to _deprecated_strict(). The current regular parsing has none of this, and is renamed to *_parse_deprecated(). Additionally it allows us to selectively set one of the new flags even on old policies. Notably, the UNSPEC flag could be useful in this case, since it can be arranged (by filling in the policy) to not be an incompatible userspace ABI change, but would then going forward prevent forgetting attribute entries. Similar can apply to the POLICY flag. We end up with the following renames: * nla_parse -> nla_parse_deprecated * nla_parse_strict -> nla_parse_deprecated_strict * nlmsg_parse -> nlmsg_parse_deprecated * nlmsg_parse_strict -> nlmsg_parse_deprecated_strict * nla_parse_nested -> nla_parse_nested_deprecated * nla_validate_nested -> nla_validate_nested_deprecated Using spatch, of course: @@ expression TB, MAX, HEAD, LEN, POL, EXT; @@ -nla_parse(TB, MAX, HEAD, LEN, POL, EXT) +nla_parse_deprecated(TB, MAX, HEAD, LEN, POL, EXT) @@ expression NLH, HDRLEN, TB, MAX, POL, EXT; @@ -nlmsg_parse(NLH, HDRLEN, TB, MAX, POL, EXT) +nlmsg_parse_deprecated(NLH, HDRLEN, TB, MAX, POL, EXT) @@ expression NLH, HDRLEN, TB, MAX, POL, EXT; @@ -nlmsg_parse_strict(NLH, HDRLEN, TB, MAX, POL, EXT) +nlmsg_parse_deprecated_strict(NLH, HDRLEN, TB, MAX, POL, EXT) @@ expression TB, MAX, NLA, POL, EXT; @@ -nla_parse_nested(TB, MAX, NLA, POL, EXT) +nla_parse_nested_deprecated(TB, MAX, NLA, POL, EXT) @@ expression START, MAX, POL, EXT; @@ -nla_validate_nested(START, MAX, POL, EXT) +nla_validate_nested_deprecated(START, MAX, POL, EXT) @@ expression NLH, HDRLEN, MAX, POL, EXT; @@ -nlmsg_validate(NLH, HDRLEN, MAX, POL, EXT) +nlmsg_validate_deprecated(NLH, HDRLEN, MAX, POL, EXT) For this patch, don't actually add the strict, non-renamed versions yet so that it breaks compile if I get it wrong. Also, while at it, make nla_validate and nla_parse go down to a common __nla_validate_parse() function to avoid code duplication. Ultimately, this allows us to have very strict validation for every new caller of nla_parse()/nlmsg_parse() etc as re-introduced in the next patch, while existing things will continue to work as is. In effect then, this adds fully strict validation for any new command. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-26 20:07:28 +08:00
err = nla_parse_nested_deprecated(tb, LWTUNNEL_IP_MAX, attr,
ip_tun_policy, extack);
if (err < 0)
return err;
opt_len = ip_tun_get_optlen(tb[LWTUNNEL_IP_OPTS], extack);
if (opt_len < 0)
return opt_len;
new_state = lwtunnel_state_alloc(sizeof(*tun_info) + opt_len);
if (!new_state)
return -ENOMEM;
new_state->type = LWTUNNEL_ENCAP_IP;
tun_info = lwt_tun_info(new_state);
err = ip_tun_set_opts(tb[LWTUNNEL_IP_OPTS], tun_info, extack);
if (err < 0) {
lwtstate_free(new_state);
return err;
}
#ifdef CONFIG_DST_CACHE
err = dst_cache_init(&tun_info->dst_cache, GFP_KERNEL);
if (err) {
lwtstate_free(new_state);
return err;
}
#endif
if (tb[LWTUNNEL_IP_ID])
tun_info->key.tun_id = nla_get_be64(tb[LWTUNNEL_IP_ID]);
if (tb[LWTUNNEL_IP_DST])
tun_info->key.u.ipv4.dst = nla_get_in_addr(tb[LWTUNNEL_IP_DST]);
if (tb[LWTUNNEL_IP_SRC])
tun_info->key.u.ipv4.src = nla_get_in_addr(tb[LWTUNNEL_IP_SRC]);
if (tb[LWTUNNEL_IP_TTL])
tun_info->key.ttl = nla_get_u8(tb[LWTUNNEL_IP_TTL]);
if (tb[LWTUNNEL_IP_TOS])
tun_info->key.tos = nla_get_u8(tb[LWTUNNEL_IP_TOS]);
if (tb[LWTUNNEL_IP_FLAGS])
tun_info->key.tun_flags |= nla_get_be16(tb[LWTUNNEL_IP_FLAGS]);
tun_info->mode = IP_TUNNEL_INFO_TX;
tun_info->options_len = opt_len;
*ts = new_state;
return 0;
}
static void ip_tun_destroy_state(struct lwtunnel_state *lwtstate)
{
#ifdef CONFIG_DST_CACHE
struct ip_tunnel_info *tun_info = lwt_tun_info(lwtstate);
dst_cache_destroy(&tun_info->dst_cache);
#endif
}
static int ip_tun_fill_encap_opts_geneve(struct sk_buff *skb,
struct ip_tunnel_info *tun_info)
{
struct geneve_opt *opt;
struct nlattr *nest;
nest = nla_nest_start_noflag(skb, LWTUNNEL_IP_OPTS_GENEVE);
if (!nest)
return -ENOMEM;
opt = ip_tunnel_info_opts(tun_info);
if (nla_put_be16(skb, LWTUNNEL_IP_OPT_GENEVE_CLASS, opt->opt_class) ||
nla_put_u8(skb, LWTUNNEL_IP_OPT_GENEVE_TYPE, opt->type) ||
nla_put(skb, LWTUNNEL_IP_OPT_GENEVE_DATA, opt->length * 4,
opt->opt_data)) {
nla_nest_cancel(skb, nest);
return -ENOMEM;
}
nla_nest_end(skb, nest);
return 0;
}
static int ip_tun_fill_encap_opts(struct sk_buff *skb, int type,
struct ip_tunnel_info *tun_info)
{
struct nlattr *nest;
int err = 0;
if (!(tun_info->key.tun_flags & TUNNEL_GENEVE_OPT))
return 0;
nest = nla_nest_start_noflag(skb, type);
if (!nest)
return -ENOMEM;
if (tun_info->key.tun_flags & TUNNEL_GENEVE_OPT)
err = ip_tun_fill_encap_opts_geneve(skb, tun_info);
if (err) {
nla_nest_cancel(skb, nest);
return err;
}
nla_nest_end(skb, nest);
return 0;
}
static int ip_tun_fill_encap_info(struct sk_buff *skb,
struct lwtunnel_state *lwtstate)
{
struct ip_tunnel_info *tun_info = lwt_tun_info(lwtstate);
if (nla_put_be64(skb, LWTUNNEL_IP_ID, tun_info->key.tun_id,
LWTUNNEL_IP_PAD) ||
nla_put_in_addr(skb, LWTUNNEL_IP_DST, tun_info->key.u.ipv4.dst) ||
nla_put_in_addr(skb, LWTUNNEL_IP_SRC, tun_info->key.u.ipv4.src) ||
nla_put_u8(skb, LWTUNNEL_IP_TOS, tun_info->key.tos) ||
nla_put_u8(skb, LWTUNNEL_IP_TTL, tun_info->key.ttl) ||
nla_put_be16(skb, LWTUNNEL_IP_FLAGS, tun_info->key.tun_flags) ||
ip_tun_fill_encap_opts(skb, LWTUNNEL_IP_OPTS, tun_info))
return -ENOMEM;
return 0;
}
static int ip_tun_opts_nlsize(struct ip_tunnel_info *info)
{
int opt_len;
if (!(info->key.tun_flags & TUNNEL_GENEVE_OPT))
return 0;
opt_len = nla_total_size(0); /* LWTUNNEL_IP_OPTS */
if (info->key.tun_flags & TUNNEL_GENEVE_OPT) {
struct geneve_opt *opt = ip_tunnel_info_opts(info);
opt_len += nla_total_size(0) /* LWTUNNEL_IP_OPTS_GENEVE */
+ nla_total_size(2) /* OPT_GENEVE_CLASS */
+ nla_total_size(1) /* OPT_GENEVE_TYPE */
+ nla_total_size(opt->length * 4);
/* OPT_GENEVE_DATA */
}
return opt_len;
}
static int ip_tun_encap_nlsize(struct lwtunnel_state *lwtstate)
{
return nla_total_size_64bit(8) /* LWTUNNEL_IP_ID */
+ nla_total_size(4) /* LWTUNNEL_IP_DST */
+ nla_total_size(4) /* LWTUNNEL_IP_SRC */
+ nla_total_size(1) /* LWTUNNEL_IP_TOS */
+ nla_total_size(1) /* LWTUNNEL_IP_TTL */
+ nla_total_size(2) /* LWTUNNEL_IP_FLAGS */
+ ip_tun_opts_nlsize(lwt_tun_info(lwtstate));
/* LWTUNNEL_IP_OPTS */
}
static int ip_tun_cmp_encap(struct lwtunnel_state *a, struct lwtunnel_state *b)
{
struct ip_tunnel_info *info_a = lwt_tun_info(a);
struct ip_tunnel_info *info_b = lwt_tun_info(b);
return memcmp(info_a, info_b, sizeof(info_a->key)) ||
info_a->mode != info_b->mode ||
info_a->options_len != info_b->options_len ||
memcmp(ip_tunnel_info_opts(info_a),
ip_tunnel_info_opts(info_b), info_a->options_len);
}
static const struct lwtunnel_encap_ops ip_tun_lwt_ops = {
.build_state = ip_tun_build_state,
.destroy_state = ip_tun_destroy_state,
.fill_encap = ip_tun_fill_encap_info,
.get_encap_size = ip_tun_encap_nlsize,
.cmp_encap = ip_tun_cmp_encap,
.owner = THIS_MODULE,
};
static const struct nla_policy ip6_tun_policy[LWTUNNEL_IP6_MAX + 1] = {
[LWTUNNEL_IP6_ID] = { .type = NLA_U64 },
[LWTUNNEL_IP6_DST] = { .len = sizeof(struct in6_addr) },
[LWTUNNEL_IP6_SRC] = { .len = sizeof(struct in6_addr) },
[LWTUNNEL_IP6_HOPLIMIT] = { .type = NLA_U8 },
[LWTUNNEL_IP6_TC] = { .type = NLA_U8 },
[LWTUNNEL_IP6_FLAGS] = { .type = NLA_U16 },
};
static int ip6_tun_build_state(struct nlattr *attr,
unsigned int family, const void *cfg,
struct lwtunnel_state **ts,
struct netlink_ext_ack *extack)
{
struct nlattr *tb[LWTUNNEL_IP6_MAX + 1];
struct lwtunnel_state *new_state;
struct ip_tunnel_info *tun_info;
int err, opt_len;
netlink: make validation more configurable for future strictness We currently have two levels of strict validation: 1) liberal (default) - undefined (type >= max) & NLA_UNSPEC attributes accepted - attribute length >= expected accepted - garbage at end of message accepted 2) strict (opt-in) - NLA_UNSPEC attributes accepted - attribute length >= expected accepted Split out parsing strictness into four different options: * TRAILING - check that there's no trailing data after parsing attributes (in message or nested) * MAXTYPE - reject attrs > max known type * UNSPEC - reject attributes with NLA_UNSPEC policy entries * STRICT_ATTRS - strictly validate attribute size The default for future things should be *everything*. The current *_strict() is a combination of TRAILING and MAXTYPE, and is renamed to _deprecated_strict(). The current regular parsing has none of this, and is renamed to *_parse_deprecated(). Additionally it allows us to selectively set one of the new flags even on old policies. Notably, the UNSPEC flag could be useful in this case, since it can be arranged (by filling in the policy) to not be an incompatible userspace ABI change, but would then going forward prevent forgetting attribute entries. Similar can apply to the POLICY flag. We end up with the following renames: * nla_parse -> nla_parse_deprecated * nla_parse_strict -> nla_parse_deprecated_strict * nlmsg_parse -> nlmsg_parse_deprecated * nlmsg_parse_strict -> nlmsg_parse_deprecated_strict * nla_parse_nested -> nla_parse_nested_deprecated * nla_validate_nested -> nla_validate_nested_deprecated Using spatch, of course: @@ expression TB, MAX, HEAD, LEN, POL, EXT; @@ -nla_parse(TB, MAX, HEAD, LEN, POL, EXT) +nla_parse_deprecated(TB, MAX, HEAD, LEN, POL, EXT) @@ expression NLH, HDRLEN, TB, MAX, POL, EXT; @@ -nlmsg_parse(NLH, HDRLEN, TB, MAX, POL, EXT) +nlmsg_parse_deprecated(NLH, HDRLEN, TB, MAX, POL, EXT) @@ expression NLH, HDRLEN, TB, MAX, POL, EXT; @@ -nlmsg_parse_strict(NLH, HDRLEN, TB, MAX, POL, EXT) +nlmsg_parse_deprecated_strict(NLH, HDRLEN, TB, MAX, POL, EXT) @@ expression TB, MAX, NLA, POL, EXT; @@ -nla_parse_nested(TB, MAX, NLA, POL, EXT) +nla_parse_nested_deprecated(TB, MAX, NLA, POL, EXT) @@ expression START, MAX, POL, EXT; @@ -nla_validate_nested(START, MAX, POL, EXT) +nla_validate_nested_deprecated(START, MAX, POL, EXT) @@ expression NLH, HDRLEN, MAX, POL, EXT; @@ -nlmsg_validate(NLH, HDRLEN, MAX, POL, EXT) +nlmsg_validate_deprecated(NLH, HDRLEN, MAX, POL, EXT) For this patch, don't actually add the strict, non-renamed versions yet so that it breaks compile if I get it wrong. Also, while at it, make nla_validate and nla_parse go down to a common __nla_validate_parse() function to avoid code duplication. Ultimately, this allows us to have very strict validation for every new caller of nla_parse()/nlmsg_parse() etc as re-introduced in the next patch, while existing things will continue to work as is. In effect then, this adds fully strict validation for any new command. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-26 20:07:28 +08:00
err = nla_parse_nested_deprecated(tb, LWTUNNEL_IP6_MAX, attr,
ip6_tun_policy, extack);
if (err < 0)
return err;
opt_len = ip_tun_get_optlen(tb[LWTUNNEL_IP6_OPTS], extack);
if (opt_len < 0)
return opt_len;
new_state = lwtunnel_state_alloc(sizeof(*tun_info) + opt_len);
if (!new_state)
return -ENOMEM;
new_state->type = LWTUNNEL_ENCAP_IP6;
tun_info = lwt_tun_info(new_state);
err = ip_tun_set_opts(tb[LWTUNNEL_IP6_OPTS], tun_info, extack);
if (err < 0) {
lwtstate_free(new_state);
return err;
}
if (tb[LWTUNNEL_IP6_ID])
tun_info->key.tun_id = nla_get_be64(tb[LWTUNNEL_IP6_ID]);
if (tb[LWTUNNEL_IP6_DST])
tun_info->key.u.ipv6.dst = nla_get_in6_addr(tb[LWTUNNEL_IP6_DST]);
if (tb[LWTUNNEL_IP6_SRC])
tun_info->key.u.ipv6.src = nla_get_in6_addr(tb[LWTUNNEL_IP6_SRC]);
if (tb[LWTUNNEL_IP6_HOPLIMIT])
tun_info->key.ttl = nla_get_u8(tb[LWTUNNEL_IP6_HOPLIMIT]);
if (tb[LWTUNNEL_IP6_TC])
tun_info->key.tos = nla_get_u8(tb[LWTUNNEL_IP6_TC]);
if (tb[LWTUNNEL_IP6_FLAGS])
tun_info->key.tun_flags |= nla_get_be16(tb[LWTUNNEL_IP6_FLAGS]);
tun_info->mode = IP_TUNNEL_INFO_TX | IP_TUNNEL_INFO_IPV6;
tun_info->options_len = opt_len;
*ts = new_state;
return 0;
}
static int ip6_tun_fill_encap_info(struct sk_buff *skb,
struct lwtunnel_state *lwtstate)
{
struct ip_tunnel_info *tun_info = lwt_tun_info(lwtstate);
if (nla_put_be64(skb, LWTUNNEL_IP6_ID, tun_info->key.tun_id,
LWTUNNEL_IP6_PAD) ||
nla_put_in6_addr(skb, LWTUNNEL_IP6_DST, &tun_info->key.u.ipv6.dst) ||
nla_put_in6_addr(skb, LWTUNNEL_IP6_SRC, &tun_info->key.u.ipv6.src) ||
nla_put_u8(skb, LWTUNNEL_IP6_TC, tun_info->key.tos) ||
nla_put_u8(skb, LWTUNNEL_IP6_HOPLIMIT, tun_info->key.ttl) ||
nla_put_be16(skb, LWTUNNEL_IP6_FLAGS, tun_info->key.tun_flags) ||
ip_tun_fill_encap_opts(skb, LWTUNNEL_IP6_OPTS, tun_info))
return -ENOMEM;
return 0;
}
static int ip6_tun_encap_nlsize(struct lwtunnel_state *lwtstate)
{
return nla_total_size_64bit(8) /* LWTUNNEL_IP6_ID */
+ nla_total_size(16) /* LWTUNNEL_IP6_DST */
+ nla_total_size(16) /* LWTUNNEL_IP6_SRC */
+ nla_total_size(1) /* LWTUNNEL_IP6_HOPLIMIT */
+ nla_total_size(1) /* LWTUNNEL_IP6_TC */
+ nla_total_size(2) /* LWTUNNEL_IP6_FLAGS */
+ ip_tun_opts_nlsize(lwt_tun_info(lwtstate));
/* LWTUNNEL_IP6_OPTS */
}
static const struct lwtunnel_encap_ops ip6_tun_lwt_ops = {
.build_state = ip6_tun_build_state,
.fill_encap = ip6_tun_fill_encap_info,
.get_encap_size = ip6_tun_encap_nlsize,
.cmp_encap = ip_tun_cmp_encap,
.owner = THIS_MODULE,
};
void __init ip_tunnel_core_init(void)
{
/* If you land here, make sure whether increasing ip_tunnel_info's
* options_len is a reasonable choice with its usage in front ends
* (f.e., it's part of flow keys, etc).
*/
BUILD_BUG_ON(IP_TUNNEL_OPTS_MAX != 255);
lwtunnel_encap_add_ops(&ip_tun_lwt_ops, LWTUNNEL_ENCAP_IP);
lwtunnel_encap_add_ops(&ip6_tun_lwt_ops, LWTUNNEL_ENCAP_IP6);
}
DEFINE_STATIC_KEY_FALSE(ip_tunnel_metadata_cnt);
EXPORT_SYMBOL(ip_tunnel_metadata_cnt);
void ip_tunnel_need_metadata(void)
{
static_branch_inc(&ip_tunnel_metadata_cnt);
}
EXPORT_SYMBOL_GPL(ip_tunnel_need_metadata);
void ip_tunnel_unneed_metadata(void)
{
static_branch_dec(&ip_tunnel_metadata_cnt);
}
EXPORT_SYMBOL_GPL(ip_tunnel_unneed_metadata);