summaryrefslogtreecommitdiff
path: root/net/ipv6
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv6')
-rw-r--r--net/ipv6/addrlabel.c26
-rw-r--r--net/ipv6/af_inet6.c2
-rw-r--r--net/ipv6/ip6_gre.c16
-rw-r--r--net/ipv6/ipv6_sockglue.c2
-rw-r--r--net/ipv6/netfilter/ip6_tables.c14
-rw-r--r--net/ipv6/rpl_iptunnel.c7
-rw-r--r--net/ipv6/seg6_local.c590
-rw-r--r--net/ipv6/tcp_ipv6.c40
8 files changed, 649 insertions, 48 deletions
diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c
index 642fc6ac13d2..8a22486cf270 100644
--- a/net/ipv6/addrlabel.c
+++ b/net/ipv6/addrlabel.c
@@ -306,7 +306,9 @@ static int ip6addrlbl_del(struct net *net,
/* add default label */
static int __net_init ip6addrlbl_net_init(struct net *net)
{
- int err = 0;
+ struct ip6addrlbl_entry *p = NULL;
+ struct hlist_node *n;
+ int err;
int i;
ADDRLABEL(KERN_DEBUG "%s\n", __func__);
@@ -315,14 +317,20 @@ static int __net_init ip6addrlbl_net_init(struct net *net)
INIT_HLIST_HEAD(&net->ipv6.ip6addrlbl_table.head);
for (i = 0; i < ARRAY_SIZE(ip6addrlbl_init_table); i++) {
- int ret = ip6addrlbl_add(net,
- ip6addrlbl_init_table[i].prefix,
- ip6addrlbl_init_table[i].prefixlen,
- 0,
- ip6addrlbl_init_table[i].label, 0);
- /* XXX: should we free all rules when we catch an error? */
- if (ret && (!err || err != -ENOMEM))
- err = ret;
+ err = ip6addrlbl_add(net,
+ ip6addrlbl_init_table[i].prefix,
+ ip6addrlbl_init_table[i].prefixlen,
+ 0,
+ ip6addrlbl_init_table[i].label, 0);
+ if (err)
+ goto err_ip6addrlbl_add;
+ }
+ return 0;
+
+err_ip6addrlbl_add:
+ hlist_for_each_entry_safe(p, n, &net->ipv6.ip6addrlbl_table.head, list) {
+ hlist_del_rcu(&p->list);
+ kfree_rcu(p, rcu);
}
return err;
}
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index e648fbebb167..a7e3d170af51 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -451,7 +451,7 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
/* BPF prog is run before any checks are done so that if the prog
* changes context in a wrong way it will be caught.
*/
- err = BPF_CGROUP_RUN_PROG_INET6_BIND(sk, uaddr);
+ err = BPF_CGROUP_RUN_PROG_INET6_BIND_LOCK(sk, uaddr);
if (err)
return err;
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 8cf659994412..c3bc89b6b1a1 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -1133,8 +1133,13 @@ static void ip6gre_tnl_link_config_route(struct ip6_tnl *t, int set_mtu,
return;
if (rt->dst.dev) {
- dev->needed_headroom = rt->dst.dev->hard_header_len +
- t_hlen;
+ unsigned short dst_len = rt->dst.dev->hard_header_len +
+ t_hlen;
+
+ if (t->dev->header_ops)
+ dev->hard_header_len = dst_len;
+ else
+ dev->needed_headroom = dst_len;
if (set_mtu) {
dev->mtu = rt->dst.dev->mtu - t_hlen;
@@ -1159,7 +1164,12 @@ static int ip6gre_calc_hlen(struct ip6_tnl *tunnel)
tunnel->hlen = tunnel->tun_hlen + tunnel->encap_hlen;
t_hlen = tunnel->hlen + sizeof(struct ipv6hdr);
- tunnel->dev->needed_headroom = LL_MAX_HEADER + t_hlen;
+
+ if (tunnel->dev->header_ops)
+ tunnel->dev->hard_header_len = LL_MAX_HEADER + t_hlen;
+ else
+ tunnel->dev->needed_headroom = LL_MAX_HEADER + t_hlen;
+
return t_hlen;
}
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 43a894bf9a1b..a6804a7e34c1 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -1148,7 +1148,7 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
if (sk->sk_type != SOCK_STREAM)
return -ENOPROTOOPT;
- msg.msg_control = optval;
+ msg.msg_control_user = optval;
msg.msg_controllen = len;
msg.msg_flags = flags;
msg.msg_control_is_user = true;
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index 2e2119bfcf13..c4f532f4d311 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -280,7 +280,7 @@ ip6t_do_table(struct sk_buff *skb,
local_bh_disable();
addend = xt_write_recseq_begin();
- private = READ_ONCE(table->private); /* Address dependency. */
+ private = rcu_access_pointer(table->private);
cpu = smp_processor_id();
table_base = private->entries;
jumpstack = (struct ip6t_entry **)private->jumpstack[cpu];
@@ -807,7 +807,7 @@ static struct xt_counters *alloc_counters(const struct xt_table *table)
{
unsigned int countersize;
struct xt_counters *counters;
- const struct xt_table_info *private = table->private;
+ const struct xt_table_info *private = xt_table_get_private_protected(table);
/* We need atomic snapshot of counters: rest doesn't change
(other than comefrom, which userspace doesn't care
@@ -831,7 +831,7 @@ copy_entries_to_user(unsigned int total_size,
unsigned int off, num;
const struct ip6t_entry *e;
struct xt_counters *counters;
- const struct xt_table_info *private = table->private;
+ const struct xt_table_info *private = xt_table_get_private_protected(table);
int ret = 0;
const void *loc_cpu_entry;
@@ -980,7 +980,7 @@ static int get_info(struct net *net, void __user *user, const int *len)
t = xt_request_find_table_lock(net, AF_INET6, name);
if (!IS_ERR(t)) {
struct ip6t_getinfo info;
- const struct xt_table_info *private = t->private;
+ const struct xt_table_info *private = xt_table_get_private_protected(t);
#ifdef CONFIG_COMPAT
struct xt_table_info tmp;
@@ -1035,7 +1035,7 @@ get_entries(struct net *net, struct ip6t_get_entries __user *uptr,
t = xt_find_table_lock(net, AF_INET6, get.name);
if (!IS_ERR(t)) {
- struct xt_table_info *private = t->private;
+ struct xt_table_info *private = xt_table_get_private_protected(t);
if (get.size == private->size)
ret = copy_entries_to_user(private->size,
t, uptr->entrytable);
@@ -1189,7 +1189,7 @@ do_add_counters(struct net *net, sockptr_t arg, unsigned int len)
}
local_bh_disable();
- private = t->private;
+ private = xt_table_get_private_protected(t);
if (private->number != tmp.num_counters) {
ret = -EINVAL;
goto unlock_up_free;
@@ -1552,7 +1552,7 @@ compat_copy_entries_to_user(unsigned int total_size, struct xt_table *table,
void __user *userptr)
{
struct xt_counters *counters;
- const struct xt_table_info *private = table->private;
+ const struct xt_table_info *private = xt_table_get_private_protected(table);
void __user *pos;
unsigned int size;
int ret = 0;
diff --git a/net/ipv6/rpl_iptunnel.c b/net/ipv6/rpl_iptunnel.c
index 233da43dd8d7..ff691d9f4a04 100644
--- a/net/ipv6/rpl_iptunnel.c
+++ b/net/ipv6/rpl_iptunnel.c
@@ -190,18 +190,13 @@ static int rpl_do_srh(struct sk_buff *skb, const struct rpl_lwt *rlwt)
{
struct dst_entry *dst = skb_dst(skb);
struct rpl_iptunnel_encap *tinfo;
- int err = 0;
if (skb->protocol != htons(ETH_P_IPV6))
return -EINVAL;
tinfo = rpl_encap_lwtunnel(dst->lwtstate);
- err = rpl_do_srh_inline(skb, rlwt, tinfo->srh);
- if (err)
- return err;
-
- return 0;
+ return rpl_do_srh_inline(skb, rlwt, tinfo->srh);
}
static int rpl_output(struct net *net, struct sock *sk, struct sk_buff *skb)
diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c
index eba23279912d..b07f7c1c82a4 100644
--- a/net/ipv6/seg6_local.c
+++ b/net/ipv6/seg6_local.c
@@ -33,11 +33,35 @@
struct seg6_local_lwt;
+/* callbacks used for customizing the creation and destruction of a behavior */
+struct seg6_local_lwtunnel_ops {
+ int (*build_state)(struct seg6_local_lwt *slwt, const void *cfg,
+ struct netlink_ext_ack *extack);
+ void (*destroy_state)(struct seg6_local_lwt *slwt);
+};
+
struct seg6_action_desc {
int action;
unsigned long attrs;
+
+ /* The optattrs field is used for specifying all the optional
+ * attributes supported by a specific behavior.
+ * It means that if one of these attributes is not provided in the
+ * netlink message during the behavior creation, no errors will be
+ * returned to the userspace.
+ *
+ * Each attribute can be only of two types (mutually exclusive):
+ * 1) required or 2) optional.
+ * Every user MUST obey to this rule! If you set an attribute as
+ * required the same attribute CANNOT be set as optional and vice
+ * versa.
+ */
+ unsigned long optattrs;
+
int (*input)(struct sk_buff *skb, struct seg6_local_lwt *slwt);
int static_headroom;
+
+ struct seg6_local_lwtunnel_ops slwt_ops;
};
struct bpf_lwt_prog {
@@ -45,6 +69,28 @@ struct bpf_lwt_prog {
char *name;
};
+enum seg6_end_dt_mode {
+ DT_INVALID_MODE = -EINVAL,
+ DT_LEGACY_MODE = 0,
+ DT_VRF_MODE = 1,
+};
+
+struct seg6_end_dt_info {
+ enum seg6_end_dt_mode mode;
+
+ struct net *net;
+ /* VRF device associated to the routing table used by the SRv6
+ * End.DT4/DT6 behavior for routing IPv4/IPv6 packets.
+ */
+ int vrf_ifindex;
+ int vrf_table;
+
+ /* tunneled packet proto and family (IPv4 or IPv6) */
+ __be16 proto;
+ u16 family;
+ int hdrlen;
+};
+
struct seg6_local_lwt {
int action;
struct ipv6_sr_hdr *srh;
@@ -54,9 +100,16 @@ struct seg6_local_lwt {
int iif;
int oif;
struct bpf_lwt_prog bpf;
+#ifdef CONFIG_NET_L3_MASTER_DEV
+ struct seg6_end_dt_info dt_info;
+#endif
int headroom;
struct seg6_action_desc *desc;
+ /* unlike the required attrs, we have to track the optional attributes
+ * that have been effectively parsed.
+ */
+ unsigned long parsed_optattrs;
};
static struct seg6_local_lwt *seg6_local_lwtunnel(struct lwtunnel_state *lwt)
@@ -401,6 +454,248 @@ drop:
return -EINVAL;
}
+#ifdef CONFIG_NET_L3_MASTER_DEV
+static struct net *fib6_config_get_net(const struct fib6_config *fib6_cfg)
+{
+ const struct nl_info *nli = &fib6_cfg->fc_nlinfo;
+
+ return nli->nl_net;
+}
+
+static int __seg6_end_dt_vrf_build(struct seg6_local_lwt *slwt, const void *cfg,
+ u16 family, struct netlink_ext_ack *extack)
+{
+ struct seg6_end_dt_info *info = &slwt->dt_info;
+ int vrf_ifindex;
+ struct net *net;
+
+ net = fib6_config_get_net(cfg);
+
+ /* note that vrf_table was already set by parse_nla_vrftable() */
+ vrf_ifindex = l3mdev_ifindex_lookup_by_table_id(L3MDEV_TYPE_VRF, net,
+ info->vrf_table);
+ if (vrf_ifindex < 0) {
+ if (vrf_ifindex == -EPERM) {
+ NL_SET_ERR_MSG(extack,
+ "Strict mode for VRF is disabled");
+ } else if (vrf_ifindex == -ENODEV) {
+ NL_SET_ERR_MSG(extack,
+ "Table has no associated VRF device");
+ } else {
+ pr_debug("seg6local: SRv6 End.DT* creation error=%d\n",
+ vrf_ifindex);
+ }
+
+ return vrf_ifindex;
+ }
+
+ info->net = net;
+ info->vrf_ifindex = vrf_ifindex;
+
+ switch (family) {
+ case AF_INET:
+ info->proto = htons(ETH_P_IP);
+ info->hdrlen = sizeof(struct iphdr);
+ break;
+ case AF_INET6:
+ info->proto = htons(ETH_P_IPV6);
+ info->hdrlen = sizeof(struct ipv6hdr);
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ info->family = family;
+ info->mode = DT_VRF_MODE;
+
+ return 0;
+}
+
+/* The SRv6 End.DT4/DT6 behavior extracts the inner (IPv4/IPv6) packet and
+ * routes the IPv4/IPv6 packet by looking at the configured routing table.
+ *
+ * In the SRv6 End.DT4/DT6 use case, we can receive traffic (IPv6+Segment
+ * Routing Header packets) from several interfaces and the outer IPv6
+ * destination address (DA) is used for retrieving the specific instance of the
+ * End.DT4/DT6 behavior that should process the packets.
+ *
+ * However, the inner IPv4/IPv6 packet is not really bound to any receiving
+ * interface and thus the End.DT4/DT6 sets the VRF (associated with the
+ * corresponding routing table) as the *receiving* interface.
+ * In other words, the End.DT4/DT6 processes a packet as if it has been received
+ * directly by the VRF (and not by one of its slave devices, if any).
+ * In this way, the VRF interface is used for routing the IPv4/IPv6 packet in
+ * according to the routing table configured by the End.DT4/DT6 instance.
+ *
+ * This design allows you to get some interesting features like:
+ * 1) the statistics on rx packets;
+ * 2) the possibility to install a packet sniffer on the receiving interface
+ * (the VRF one) for looking at the incoming packets;
+ * 3) the possibility to leverage the netfilter prerouting hook for the inner
+ * IPv4 packet.
+ *
+ * This function returns:
+ * - the sk_buff* when the VRF rcv handler has processed the packet correctly;
+ * - NULL when the skb is consumed by the VRF rcv handler;
+ * - a pointer which encodes a negative error number in case of error.
+ * Note that in this case, the function takes care of freeing the skb.
+ */
+static struct sk_buff *end_dt_vrf_rcv(struct sk_buff *skb, u16 family,
+ struct net_device *dev)
+{
+ /* based on l3mdev_ip_rcv; we are only interested in the master */
+ if (unlikely(!netif_is_l3_master(dev) && !netif_has_l3_rx_handler(dev)))
+ goto drop;
+
+ if (unlikely(!dev->l3mdev_ops->l3mdev_l3_rcv))
+ goto drop;
+
+ /* the decap packet IPv4/IPv6 does not come with any mac header info.
+ * We must unset the mac header to allow the VRF device to rebuild it,
+ * just in case there is a sniffer attached on the device.
+ */
+ skb_unset_mac_header(skb);
+
+ skb = dev->l3mdev_ops->l3mdev_l3_rcv(dev, skb, family);
+ if (!skb)
+ /* the skb buffer was consumed by the handler */
+ return NULL;
+
+ /* when a packet is received by a VRF or by one of its slaves, the
+ * master device reference is set into the skb.
+ */
+ if (unlikely(skb->dev != dev || skb->skb_iif != dev->ifindex))
+ goto drop;
+
+ return skb;
+
+drop:
+ kfree_skb(skb);
+ return ERR_PTR(-EINVAL);
+}
+
+static struct net_device *end_dt_get_vrf_rcu(struct sk_buff *skb,
+ struct seg6_end_dt_info *info)
+{
+ int vrf_ifindex = info->vrf_ifindex;
+ struct net *net = info->net;
+
+ if (unlikely(vrf_ifindex < 0))
+ goto error;
+
+ if (unlikely(!net_eq(dev_net(skb->dev), net)))
+ goto error;
+
+ return dev_get_by_index_rcu(net, vrf_ifindex);
+
+error:
+ return NULL;
+}
+
+static struct sk_buff *end_dt_vrf_core(struct sk_buff *skb,
+ struct seg6_local_lwt *slwt)
+{
+ struct seg6_end_dt_info *info = &slwt->dt_info;
+ struct net_device *vrf;
+
+ vrf = end_dt_get_vrf_rcu(skb, info);
+ if (unlikely(!vrf))
+ goto drop;
+
+ skb->protocol = info->proto;
+
+ skb_dst_drop(skb);
+
+ skb_set_transport_header(skb, info->hdrlen);
+
+ return end_dt_vrf_rcv(skb, info->family, vrf);
+
+drop:
+ kfree_skb(skb);
+ return ERR_PTR(-EINVAL);
+}
+
+static int input_action_end_dt4(struct sk_buff *skb,
+ struct seg6_local_lwt *slwt)
+{
+ struct iphdr *iph;
+ int err;
+
+ if (!decap_and_validate(skb, IPPROTO_IPIP))
+ goto drop;
+
+ if (!pskb_may_pull(skb, sizeof(struct iphdr)))
+ goto drop;
+
+ skb = end_dt_vrf_core(skb, slwt);
+ if (!skb)
+ /* packet has been processed and consumed by the VRF */
+ return 0;
+
+ if (IS_ERR(skb))
+ return PTR_ERR(skb);
+
+ iph = ip_hdr(skb);
+
+ err = ip_route_input(skb, iph->daddr, iph->saddr, 0, skb->dev);
+ if (unlikely(err))
+ goto drop;
+
+ return dst_input(skb);
+
+drop:
+ kfree_skb(skb);
+ return -EINVAL;
+}
+
+static int seg6_end_dt4_build(struct seg6_local_lwt *slwt, const void *cfg,
+ struct netlink_ext_ack *extack)
+{
+ return __seg6_end_dt_vrf_build(slwt, cfg, AF_INET, extack);
+}
+
+static enum
+seg6_end_dt_mode seg6_end_dt6_parse_mode(struct seg6_local_lwt *slwt)
+{
+ unsigned long parsed_optattrs = slwt->parsed_optattrs;
+ bool legacy, vrfmode;
+
+ legacy = !!(parsed_optattrs & (1 << SEG6_LOCAL_TABLE));
+ vrfmode = !!(parsed_optattrs & (1 << SEG6_LOCAL_VRFTABLE));
+
+ if (!(legacy ^ vrfmode))
+ /* both are absent or present: invalid DT6 mode */
+ return DT_INVALID_MODE;
+
+ return legacy ? DT_LEGACY_MODE : DT_VRF_MODE;
+}
+
+static enum seg6_end_dt_mode seg6_end_dt6_get_mode(struct seg6_local_lwt *slwt)
+{
+ struct seg6_end_dt_info *info = &slwt->dt_info;
+
+ return info->mode;
+}
+
+static int seg6_end_dt6_build(struct seg6_local_lwt *slwt, const void *cfg,
+ struct netlink_ext_ack *extack)
+{
+ enum seg6_end_dt_mode mode = seg6_end_dt6_parse_mode(slwt);
+ struct seg6_end_dt_info *info = &slwt->dt_info;
+
+ switch (mode) {
+ case DT_LEGACY_MODE:
+ info->mode = DT_LEGACY_MODE;
+ return 0;
+ case DT_VRF_MODE:
+ return __seg6_end_dt_vrf_build(slwt, cfg, AF_INET6, extack);
+ default:
+ NL_SET_ERR_MSG(extack, "table or vrftable must be specified");
+ return -EINVAL;
+ }
+}
+#endif
+
static int input_action_end_dt6(struct sk_buff *skb,
struct seg6_local_lwt *slwt)
{
@@ -410,6 +705,28 @@ static int input_action_end_dt6(struct sk_buff *skb,
if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
goto drop;
+#ifdef CONFIG_NET_L3_MASTER_DEV
+ if (seg6_end_dt6_get_mode(slwt) == DT_LEGACY_MODE)
+ goto legacy_mode;
+
+ /* DT6_VRF_MODE */
+ skb = end_dt_vrf_core(skb, slwt);
+ if (!skb)
+ /* packet has been processed and consumed by the VRF */
+ return 0;
+
+ if (IS_ERR(skb))
+ return PTR_ERR(skb);
+
+ /* note: this time we do not need to specify the table because the VRF
+ * takes care of selecting the correct table.
+ */
+ seg6_lookup_any_nexthop(skb, NULL, 0, true);
+
+ return dst_input(skb);
+
+legacy_mode:
+#endif
skb_set_transport_header(skb, sizeof(struct ipv6hdr));
seg6_lookup_any_nexthop(skb, NULL, slwt->table, true);
@@ -590,8 +907,27 @@ static struct seg6_action_desc seg6_action_table[] = {
.input = input_action_end_dx4,
},
{
+ .action = SEG6_LOCAL_ACTION_END_DT4,
+ .attrs = (1 << SEG6_LOCAL_VRFTABLE),
+#ifdef CONFIG_NET_L3_MASTER_DEV
+ .input = input_action_end_dt4,
+ .slwt_ops = {
+ .build_state = seg6_end_dt4_build,
+ },
+#endif
+ },
+ {
.action = SEG6_LOCAL_ACTION_END_DT6,
+#ifdef CONFIG_NET_L3_MASTER_DEV
+ .attrs = 0,
+ .optattrs = (1 << SEG6_LOCAL_TABLE) |
+ (1 << SEG6_LOCAL_VRFTABLE),
+ .slwt_ops = {
+ .build_state = seg6_end_dt6_build,
+ },
+#else
.attrs = (1 << SEG6_LOCAL_TABLE),
+#endif
.input = input_action_end_dt6,
},
{
@@ -649,6 +985,7 @@ static const struct nla_policy seg6_local_policy[SEG6_LOCAL_MAX + 1] = {
[SEG6_LOCAL_ACTION] = { .type = NLA_U32 },
[SEG6_LOCAL_SRH] = { .type = NLA_BINARY },
[SEG6_LOCAL_TABLE] = { .type = NLA_U32 },
+ [SEG6_LOCAL_VRFTABLE] = { .type = NLA_U32 },
[SEG6_LOCAL_NH4] = { .type = NLA_BINARY,
.len = sizeof(struct in_addr) },
[SEG6_LOCAL_NH6] = { .type = NLA_BINARY,
@@ -710,6 +1047,11 @@ static int cmp_nla_srh(struct seg6_local_lwt *a, struct seg6_local_lwt *b)
return memcmp(a->srh, b->srh, len);
}
+static void destroy_attr_srh(struct seg6_local_lwt *slwt)
+{
+ kfree(slwt->srh);
+}
+
static int parse_nla_table(struct nlattr **attrs, struct seg6_local_lwt *slwt)
{
slwt->table = nla_get_u32(attrs[SEG6_LOCAL_TABLE]);
@@ -733,6 +1075,53 @@ static int cmp_nla_table(struct seg6_local_lwt *a, struct seg6_local_lwt *b)
return 0;
}
+static struct
+seg6_end_dt_info *seg6_possible_end_dt_info(struct seg6_local_lwt *slwt)
+{
+#ifdef CONFIG_NET_L3_MASTER_DEV
+ return &slwt->dt_info;
+#else
+ return ERR_PTR(-EOPNOTSUPP);
+#endif
+}
+
+static int parse_nla_vrftable(struct nlattr **attrs,
+ struct seg6_local_lwt *slwt)
+{
+ struct seg6_end_dt_info *info = seg6_possible_end_dt_info(slwt);
+
+ if (IS_ERR(info))
+ return PTR_ERR(info);
+
+ info->vrf_table = nla_get_u32(attrs[SEG6_LOCAL_VRFTABLE]);
+
+ return 0;
+}
+
+static int put_nla_vrftable(struct sk_buff *skb, struct seg6_local_lwt *slwt)
+{
+ struct seg6_end_dt_info *info = seg6_possible_end_dt_info(slwt);
+
+ if (IS_ERR(info))
+ return PTR_ERR(info);
+
+ if (nla_put_u32(skb, SEG6_LOCAL_VRFTABLE, info->vrf_table))
+ return -EMSGSIZE;
+
+ return 0;
+}
+
+static int cmp_nla_vrftable(struct seg6_local_lwt *a, struct seg6_local_lwt *b)
+{
+ struct seg6_end_dt_info *info_a = seg6_possible_end_dt_info(a);
+ struct seg6_end_dt_info *info_b = seg6_possible_end_dt_info(b);
+
+ if (info_a->vrf_table != info_b->vrf_table)
+ return 1;
+
+ return 0;
+}
+
static int parse_nla_nh4(struct nlattr **attrs, struct seg6_local_lwt *slwt)
{
memcpy(&slwt->nh4, nla_data(attrs[SEG6_LOCAL_NH4]),
@@ -901,16 +1290,30 @@ static int cmp_nla_bpf(struct seg6_local_lwt *a, struct seg6_local_lwt *b)
return strcmp(a->bpf.name, b->bpf.name);
}
+static void destroy_attr_bpf(struct seg6_local_lwt *slwt)
+{
+ kfree(slwt->bpf.name);
+ if (slwt->bpf.prog)
+ bpf_prog_put(slwt->bpf.prog);
+}
+
struct seg6_action_param {
int (*parse)(struct nlattr **attrs, struct seg6_local_lwt *slwt);
int (*put)(struct sk_buff *skb, struct seg6_local_lwt *slwt);
int (*cmp)(struct seg6_local_lwt *a, struct seg6_local_lwt *b);
+
+ /* optional destroy() callback useful for releasing resources which
+ * have been previously acquired in the corresponding parse()
+ * function.
+ */
+ void (*destroy)(struct seg6_local_lwt *slwt);
};
static struct seg6_action_param seg6_action_params[SEG6_LOCAL_MAX + 1] = {
[SEG6_LOCAL_SRH] = { .parse = parse_nla_srh,
.put = put_nla_srh,
- .cmp = cmp_nla_srh },
+ .cmp = cmp_nla_srh,
+ .destroy = destroy_attr_srh },
[SEG6_LOCAL_TABLE] = { .parse = parse_nla_table,
.put = put_nla_table,
@@ -934,14 +1337,130 @@ static struct seg6_action_param seg6_action_params[SEG6_LOCAL_MAX + 1] = {
[SEG6_LOCAL_BPF] = { .parse = parse_nla_bpf,
.put = put_nla_bpf,
- .cmp = cmp_nla_bpf },
+ .cmp = cmp_nla_bpf,
+ .destroy = destroy_attr_bpf },
+
+ [SEG6_LOCAL_VRFTABLE] = { .parse = parse_nla_vrftable,
+ .put = put_nla_vrftable,
+ .cmp = cmp_nla_vrftable },
};
+/* call the destroy() callback (if available) for each set attribute in
+ * @parsed_attrs, starting from the first attribute up to the @max_parsed
+ * (excluded) attribute.
+ */
+static void __destroy_attrs(unsigned long parsed_attrs, int max_parsed,
+ struct seg6_local_lwt *slwt)
+{
+ struct seg6_action_param *param;
+ int i;
+
+ /* Every required seg6local attribute is identified by an ID which is
+ * encoded as a flag (i.e: 1 << ID) in the 'attrs' bitmask;
+ *
+ * We scan the 'parsed_attrs' bitmask, starting from the first attribute
+ * up to the @max_parsed (excluded) attribute.
+ * For each set attribute, we retrieve the corresponding destroy()
+ * callback. If the callback is not available, then we skip to the next
+ * attribute; otherwise, we call the destroy() callback.
+ */
+ for (i = 0; i < max_parsed; ++i) {
+ if (!(parsed_attrs & (1 << i)))
+ continue;
+
+ param = &seg6_action_params[i];
+
+ if (param->destroy)
+ param->destroy(slwt);
+ }
+}
+
+/* release all the resources that may have been acquired during parsing
+ * operations.
+ */
+static void destroy_attrs(struct seg6_local_lwt *slwt)
+{
+ unsigned long attrs = slwt->desc->attrs | slwt->parsed_optattrs;
+
+ __destroy_attrs(attrs, SEG6_LOCAL_MAX + 1, slwt);
+}
+
+static int parse_nla_optional_attrs(struct nlattr **attrs,
+ struct seg6_local_lwt *slwt)
+{
+ struct seg6_action_desc *desc = slwt->desc;
+ unsigned long parsed_optattrs = 0;
+ struct seg6_action_param *param;
+ int err, i;
+
+ for (i = 0; i < SEG6_LOCAL_MAX + 1; ++i) {
+ if (!(desc->optattrs & (1 << i)) || !attrs[i])
+ continue;
+
+ /* once here, the i-th attribute is provided by the
+ * userspace AND it is identified optional as well.
+ */
+ param = &seg6_action_params[i];
+
+ err = param->parse(attrs, slwt);
+ if (err < 0)
+ goto parse_optattrs_err;
+
+ /* current attribute has been correctly parsed */
+ parsed_optattrs |= (1 << i);
+ }
+
+ /* store in the tunnel state all the optional attributed successfully
+ * parsed.
+ */
+ slwt->parsed_optattrs = parsed_optattrs;
+
+ return 0;
+
+parse_optattrs_err:
+ __destroy_attrs(parsed_optattrs, i, slwt);
+
+ return err;
+}
+
+/* call the custom constructor of the behavior during its initialization phase
+ * and after that all its attributes have been parsed successfully.
+ */
+static int
+seg6_local_lwtunnel_build_state(struct seg6_local_lwt *slwt, const void *cfg,
+ struct netlink_ext_ack *extack)
+{
+ struct seg6_action_desc *desc = slwt->desc;
+ struct seg6_local_lwtunnel_ops *ops;
+
+ ops = &desc->slwt_ops;
+ if (!ops->build_state)
+ return 0;
+
+ return ops->build_state(slwt, cfg, extack);
+}
+
+/* call the custom destructor of the behavior which is invoked before the
+ * tunnel is going to be destroyed.
+ */
+static void seg6_local_lwtunnel_destroy_state(struct seg6_local_lwt *slwt)
+{
+ struct seg6_action_desc *desc = slwt->desc;
+ struct seg6_local_lwtunnel_ops *ops;
+
+ ops = &desc->slwt_ops;
+ if (!ops->destroy_state)
+ return;
+
+ ops->destroy_state(slwt);
+}
+
static int parse_nla_action(struct nlattr **attrs, struct seg6_local_lwt *slwt)
{
struct seg6_action_param *param;
struct seg6_action_desc *desc;
+ unsigned long invalid_attrs;
int i, err;
desc = __get_action_desc(slwt->action);
@@ -954,6 +1473,26 @@ static int parse_nla_action(struct nlattr **attrs, struct seg6_local_lwt *slwt)
slwt->desc = desc;
slwt->headroom += desc->static_headroom;
+ /* Forcing the desc->optattrs *set* and the desc->attrs *set* to be
+ * disjoined, this allow us to release acquired resources by optional
+ * attributes and by required attributes independently from each other
+ * without any interfarence.
+ * In other terms, we are sure that we do not release some the acquired
+ * resources twice.
+ *
+ * Note that if an attribute is configured both as required and as
+ * optional, it means that the user has messed something up in the
+ * seg6_action_table. Therefore, this check is required for SRv6
+ * behaviors to work properly.
+ */
+ invalid_attrs = desc->attrs & desc->optattrs;
+ if (invalid_attrs) {
+ WARN_ONCE(1,
+ "An attribute cannot be both required AND optional");
+ return -EINVAL;
+ }
+
+ /* parse the required attributes */
for (i = 0; i < SEG6_LOCAL_MAX + 1; i++) {
if (desc->attrs & (1 << i)) {
if (!attrs[i])
@@ -963,11 +1502,24 @@ static int parse_nla_action(struct nlattr **attrs, struct seg6_local_lwt *slwt)
err = param->parse(attrs, slwt);
if (err < 0)
- return err;
+ goto parse_attrs_err;
}
}
+ /* parse the optional attributes, if any */
+ err = parse_nla_optional_attrs(attrs, slwt);
+ if (err < 0)
+ goto parse_attrs_err;
+
return 0;
+
+parse_attrs_err:
+ /* release any resource that may have been acquired during the i-1
+ * parse() operations.
+ */
+ __destroy_attrs(desc->attrs, i, slwt);
+
+ return err;
}
static int seg6_local_build_state(struct net *net, struct nlattr *nla,
@@ -1003,6 +1555,10 @@ static int seg6_local_build_state(struct net *net, struct nlattr *nla,
if (err < 0)
goto out_free;
+ err = seg6_local_lwtunnel_build_state(slwt, cfg, extack);
+ if (err < 0)
+ goto out_destroy_attrs;
+
newts->type = LWTUNNEL_ENCAP_SEG6_LOCAL;
newts->flags = LWTUNNEL_STATE_INPUT_REDIRECT;
newts->headroom = slwt->headroom;
@@ -1011,8 +1567,9 @@ static int seg6_local_build_state(struct net *net, struct nlattr *nla,
return 0;
+out_destroy_attrs:
+ destroy_attrs(slwt);
out_free:
- kfree(slwt->srh);
kfree(newts);
return err;
}
@@ -1021,12 +1578,9 @@ static void seg6_local_destroy_state(struct lwtunnel_state *lwt)
{
struct seg6_local_lwt *slwt = seg6_local_lwtunnel(lwt);
- kfree(slwt->srh);
+ seg6_local_lwtunnel_destroy_state(slwt);
- if (slwt->desc->attrs & (1 << SEG6_LOCAL_BPF)) {
- kfree(slwt->bpf.name);
- bpf_prog_put(slwt->bpf.prog);
- }
+ destroy_attrs(slwt);
return;
}
@@ -1036,13 +1590,16 @@ static int seg6_local_fill_encap(struct sk_buff *skb,
{
struct seg6_local_lwt *slwt = seg6_local_lwtunnel(lwt);
struct seg6_action_param *param;
+ unsigned long attrs;
int i, err;
if (nla_put_u32(skb, SEG6_LOCAL_ACTION, slwt->action))
return -EMSGSIZE;
+ attrs = slwt->desc->attrs | slwt->parsed_optattrs;
+
for (i = 0; i < SEG6_LOCAL_MAX + 1; i++) {
- if (slwt->desc->attrs & (1 << i)) {
+ if (attrs & (1 << i)) {
param = &seg6_action_params[i];
err = param->put(skb, slwt);
if (err < 0)
@@ -1061,7 +1618,7 @@ static int seg6_local_get_encap_size(struct lwtunnel_state *lwt)
nlsize = nla_total_size(4); /* action */
- attrs = slwt->desc->attrs;
+ attrs = slwt->desc->attrs | slwt->parsed_optattrs;
if (attrs & (1 << SEG6_LOCAL_SRH))
nlsize += nla_total_size((slwt->srh->hdrlen + 1) << 3);
@@ -1086,6 +1643,9 @@ static int seg6_local_get_encap_size(struct lwtunnel_state *lwt)
nla_total_size(MAX_PROG_NAME) +
nla_total_size(4);
+ if (attrs & (1 << SEG6_LOCAL_VRFTABLE))
+ nlsize += nla_total_size(4);
+
return nlsize;
}
@@ -1094,6 +1654,7 @@ static int seg6_local_cmp_encap(struct lwtunnel_state *a,
{
struct seg6_local_lwt *slwt_a, *slwt_b;
struct seg6_action_param *param;
+ unsigned long attrs_a, attrs_b;
int i;
slwt_a = seg6_local_lwtunnel(a);
@@ -1102,11 +1663,14 @@ static int seg6_local_cmp_encap(struct lwtunnel_state *a,
if (slwt_a->action != slwt_b->action)
return 1;
- if (slwt_a->desc->attrs != slwt_b->desc->attrs)
+ attrs_a = slwt_a->desc->attrs | slwt_a->parsed_optattrs;
+ attrs_b = slwt_b->desc->attrs | slwt_b->parsed_optattrs;
+
+ if (attrs_a != attrs_b)
return 1;
for (i = 0; i < SEG6_LOCAL_MAX + 1; i++) {
- if (slwt_a->desc->attrs & (1 << i)) {
+ if (attrs_a & (1 << i)) {
param = &seg6_action_params[i];
if (param->cmp(slwt_a, slwt_b))
return 1;
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 8db59f4e5f13..e254569a3005 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -527,15 +527,21 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst,
if (np->repflow && ireq->pktopts)
fl6->flowlabel = ip6_flowlabel(ipv6_hdr(ireq->pktopts));
+ tclass = sock_net(sk)->ipv4.sysctl_tcp_reflect_tos ?
+ (tcp_rsk(req)->syn_tos & ~INET_ECN_MASK) |
+ (np->tclass & INET_ECN_MASK) :
+ np->tclass;
+
+ if (!INET_ECN_is_capable(tclass) &&
+ tcp_bpf_ca_needs_ecn((struct sock *)req))
+ tclass |= INET_ECN_ECT_0;
+
rcu_read_lock();
opt = ireq->ipv6_opt;
- tclass = sock_net(sk)->ipv4.sysctl_tcp_reflect_tos ?
- tcp_rsk(req)->syn_tos : np->tclass;
if (!opt)
opt = rcu_dereference(np->opt);
err = ip6_xmit(sk, skb, fl6, sk->sk_mark, opt,
- tclass & ~INET_ECN_MASK,
- sk->sk_priority);
+ tclass, sk->sk_priority);
rcu_read_unlock();
err = net_xmit_eval(err);
}
@@ -823,9 +829,15 @@ static void tcp_v6_init_req(struct request_sock *req,
}
static struct dst_entry *tcp_v6_route_req(const struct sock *sk,
+ struct sk_buff *skb,
struct flowi *fl,
- const struct request_sock *req)
+ struct request_sock *req)
{
+ tcp_v6_init_req(req, sk, skb);
+
+ if (security_inet_conn_request(sk, skb, req))
+ return NULL;
+
return inet6_csk_route_req(sk, &fl->u.ip6, req, IPPROTO_TCP);
}
@@ -846,7 +858,6 @@ const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = {
.req_md5_lookup = tcp_v6_md5_lookup,
.calc_md5_hash = tcp_v6_md5_hash_skb,
#endif
- .init_req = tcp_v6_init_req,
#ifdef CONFIG_SYN_COOKIES
.cookie_init_seq = cookie_v6_init_sequence,
#endif
@@ -1193,6 +1204,7 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
const struct ipv6_pinfo *np = tcp_inet6_sk(sk);
struct ipv6_txoptions *opt;
struct inet_sock *newinet;
+ bool found_dup_sk = false;
struct tcp_sock *newtp;
struct sock *newsk;
#ifdef CONFIG_TCP_MD5SIG
@@ -1314,7 +1326,9 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
if (np->repflow)
newnp->flow_label = ip6_flowlabel(ipv6_hdr(skb));
- /* Set ToS of the new socket based upon the value of incoming SYN. */
+ /* Set ToS of the new socket based upon the value of incoming SYN.
+ * ECT bits are set later in tcp_init_transfer().
+ */
if (sock_net(sk)->ipv4.sysctl_tcp_reflect_tos)
newnp->tclass = tcp_rsk(req)->syn_tos & ~INET_ECN_MASK;
@@ -1368,7 +1382,8 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
tcp_done(newsk);
goto out;
}
- *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash));
+ *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash),
+ &found_dup_sk);
if (*own_req) {
tcp_move_syn(newtp, req);
@@ -1383,6 +1398,15 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
skb_set_owner_r(newnp->pktoptions, newsk);
}
}
+ } else {
+ if (!req_unhash && found_dup_sk) {
+ /* This code path should only be executed in the
+ * syncookie case only
+ */
+ bh_unlock_sock(newsk);
+ sock_put(newsk);
+ newsk = NULL;
+ }
}
return newsk;
generated by cgit v1.2.3 (git 2.39.0) at 2024-11-25 11:55:37 +0300