@@ -103,6 +103,11 @@ VRF device:
or to specify the output device using cmsg and IP_PKTINFO.
+By default the scope of the port bindings for unbound sockets is
+limited to the default VRF. That is, it will not be matched by packets
+arriving on interfaces enslaved to an l3mdev and processes may bind to
+the same port if they bind to an l3mdev.
+
TCP & UDP services running in the default VRF context (ie., not bound
to any VRF device) can work across all VRF domains by enabling the
tcp_l3mdev_accept and udp_l3mdev_accept sysctl options:
@@ -112,10 +117,6 @@ tcp_l3mdev_accept and udp_l3mdev_accept sysctl options:
netfilter rules on the VRF device can be used to limit access to services
running in the default VRF context as well.
-The default VRF does not have limited scope with respect to port bindings.
-That is, if a process does a wildcard bind to a port in the default VRF it
-owns the port across all VRF domains within the network namespace.
-
################################################################################
Using iproute2 for VRFs
@@ -115,9 +115,8 @@ int inet6_hash(struct sock *sk);
((__sk)->sk_family == AF_INET6) && \
ipv6_addr_equal(&(__sk)->sk_v6_daddr, (__saddr)) && \
ipv6_addr_equal(&(__sk)->sk_v6_rcv_saddr, (__daddr)) && \
- (!(__sk)->sk_bound_dev_if || \
- ((__sk)->sk_bound_dev_if == (__dif)) || \
- ((__sk)->sk_bound_dev_if == (__sdif))) && \
+ (((__sk)->sk_bound_dev_if == (__dif)) || \
+ ((__sk)->sk_bound_dev_if == (__sdif))) && \
net_eq(sock_net(__sk), (__net)))
#endif /* _INET6_HASHTABLES_H */
@@ -79,6 +79,7 @@ struct inet_ehash_bucket {
struct inet_bind_bucket {
possible_net_t ib_net;
+ int l3mdev;
unsigned short port;
signed char fastreuse;
signed char fastreuseport;
@@ -188,10 +189,18 @@ static inline void inet_ehash_locks_free(struct inet_hashinfo *hashinfo)
hashinfo->ehash_locks = NULL;
}
+static inline bool inet_sk_bound_dev_eq(struct net *net, int bound_dev_if,
+ int dif, int sdif)
+{
+ if (!bound_dev_if)
+ return !sdif || net->ipv4.sysctl_tcp_l3mdev_accept;
+ return bound_dev_if == dif || bound_dev_if == sdif;
+}
+
struct inet_bind_bucket *
inet_bind_bucket_create(struct kmem_cache *cachep, struct net *net,
struct inet_bind_hashbucket *head,
- const unsigned short snum);
+ const unsigned short snum, int l3mdev);
void inet_bind_bucket_destroy(struct kmem_cache *cachep,
struct inet_bind_bucket *tb);
@@ -282,9 +291,8 @@ static inline struct sock *inet_lookup_listener(struct net *net,
#define INET_MATCH(__sk, __net, __cookie, __saddr, __daddr, __ports, __dif, __sdif) \
(((__sk)->sk_portpair == (__ports)) && \
((__sk)->sk_addrpair == (__cookie)) && \
- (!(__sk)->sk_bound_dev_if || \
- ((__sk)->sk_bound_dev_if == (__dif)) || \
- ((__sk)->sk_bound_dev_if == (__sdif))) && \
+ (((__sk)->sk_bound_dev_if == (__dif)) || \
+ ((__sk)->sk_bound_dev_if == (__sdif))) && \
net_eq(sock_net(__sk), (__net)))
#else /* 32-bit arch */
#define INET_ADDR_COOKIE(__name, __saddr, __daddr) \
@@ -294,9 +302,8 @@ static inline struct sock *inet_lookup_listener(struct net *net,
(((__sk)->sk_portpair == (__ports)) && \
((__sk)->sk_daddr == (__saddr)) && \
((__sk)->sk_rcv_saddr == (__daddr)) && \
- (!(__sk)->sk_bound_dev_if || \
- ((__sk)->sk_bound_dev_if == (__dif)) || \
- ((__sk)->sk_bound_dev_if == (__sdif))) && \
+ (((__sk)->sk_bound_dev_if == (__dif)) || \
+ ((__sk)->sk_bound_dev_if == (__sdif))) && \
net_eq(sock_net(__sk), (__net)))
#endif /* 64-bit arch */
@@ -130,6 +130,19 @@ static inline int inet_request_bound_dev_if(const struct sock *sk,
return sk->sk_bound_dev_if;
}
+static inline int inet_sk_bound_l3mdev(const struct sock *sk)
+{
+#ifdef CONFIG_NET_L3_MASTER_DEV
+ struct net *net = sock_net(sk);
+
+ if (!net->ipv4.sysctl_tcp_l3mdev_accept)
+ return l3mdev_master_ifindex_by_index(net,
+ sk->sk_bound_dev_if);
+#endif
+
+ return 0;
+}
+
static inline struct ip_options_rcu *ireq_opt_deref(const struct inet_request_sock *ireq)
{
return rcu_dereference_check(ireq->ireq_opt,
@@ -567,6 +567,8 @@ static int sock_setbindtodevice(struct sock *sk, char __user *optval,
lock_sock(sk);
sk->sk_bound_dev_if = index;
+ if (sk->sk_prot->rehash)
+ sk->sk_prot->rehash(sk);
sk_dst_reset(sk);
release_sock(sk);
@@ -183,7 +183,9 @@ inet_csk_find_open_port(struct sock *sk, struct inet_bind_bucket **tb_ret, int *
int i, low, high, attempt_half;
struct inet_bind_bucket *tb;
u32 remaining, offset;
+ int l3mdev;
+ l3mdev = inet_sk_bound_l3mdev(sk);
attempt_half = (sk->sk_reuse == SK_CAN_REUSE) ? 1 : 0;
other_half_scan:
inet_get_local_port_range(net, &low, &high);
@@ -219,7 +221,8 @@ inet_csk_find_open_port(struct sock *sk, struct inet_bind_bucket **tb_ret, int *
hinfo->bhash_size)];
spin_lock_bh(&head->lock);
inet_bind_bucket_for_each(tb, &head->chain)
- if (net_eq(ib_net(tb), net) && tb->port == port) {
+ if (net_eq(ib_net(tb), net) && tb->l3mdev == l3mdev &&
+ tb->port == port) {
if (!inet_csk_bind_conflict(sk, tb, false, false))
goto success;
goto next_port;
@@ -293,6 +296,9 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum)
struct net *net = sock_net(sk);
struct inet_bind_bucket *tb = NULL;
kuid_t uid = sock_i_uid(sk);
+ int l3mdev;
+
+ l3mdev = inet_sk_bound_l3mdev(sk);
if (!port) {
head = inet_csk_find_open_port(sk, &tb, &port);
@@ -306,11 +312,12 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum)
hinfo->bhash_size)];
spin_lock_bh(&head->lock);
inet_bind_bucket_for_each(tb, &head->chain)
- if (net_eq(ib_net(tb), net) && tb->port == port)
+ if (net_eq(ib_net(tb), net) && tb->l3mdev == l3mdev &&
+ tb->port == port)
goto tb_found;
tb_not_found:
tb = inet_bind_bucket_create(hinfo->bind_bucket_cachep,
- net, head, port);
+ net, head, port, l3mdev);
if (!tb)
goto fail_unlock;
tb_found:
@@ -65,12 +65,14 @@ static u32 sk_ehashfn(const struct sock *sk)
struct inet_bind_bucket *inet_bind_bucket_create(struct kmem_cache *cachep,
struct net *net,
struct inet_bind_hashbucket *head,
- const unsigned short snum)
+ const unsigned short snum,
+ int l3mdev)
{
struct inet_bind_bucket *tb = kmem_cache_alloc(cachep, GFP_ATOMIC);
if (tb) {
write_pnet(&tb->ib_net, net);
+ tb->l3mdev = l3mdev;
tb->port = snum;
tb->fastreuse = 0;
tb->fastreuseport = 0;
@@ -135,6 +137,7 @@ int __inet_inherit_port(const struct sock *sk, struct sock *child)
table->bhash_size);
struct inet_bind_hashbucket *head = &table->bhash[bhash];
struct inet_bind_bucket *tb;
+ int l3mdev;
spin_lock(&head->lock);
tb = inet_csk(sk)->icsk_bind_hash;
@@ -143,6 +146,8 @@ int __inet_inherit_port(const struct sock *sk, struct sock *child)
return -ENOENT;
}
if (tb->port != port) {
+ l3mdev = inet_sk_bound_l3mdev(sk);
+
/* NOTE: using tproxy and redirecting skbs to a proxy
* on a different listener port breaks the assumption
* that the listener socket's icsk_bind_hash is the same
@@ -150,12 +155,13 @@ int __inet_inherit_port(const struct sock *sk, struct sock *child)
* create a new bind bucket for the child here. */
inet_bind_bucket_for_each(tb, &head->chain) {
if (net_eq(ib_net(tb), sock_net(sk)) &&
- tb->port == port)
+ tb->l3mdev == l3mdev && tb->port == port)
break;
}
if (!tb) {
tb = inet_bind_bucket_create(table->bind_bucket_cachep,
- sock_net(sk), head, port);
+ sock_net(sk), head, port,
+ l3mdev);
if (!tb) {
spin_unlock(&head->lock);
return -ENOMEM;
@@ -229,6 +235,7 @@ static inline int compute_score(struct sock *sk, struct net *net,
{
int score = -1;
struct inet_sock *inet = inet_sk(sk);
+ bool dev_match;
if (net_eq(sock_net(sk), net) && inet->inet_num == hnum &&
!ipv6_only_sock(sk)) {
@@ -239,15 +246,12 @@ static inline int compute_score(struct sock *sk, struct net *net,
return -1;
score += 4;
}
- if (sk->sk_bound_dev_if || exact_dif) {
- bool dev_match = (sk->sk_bound_dev_if == dif ||
- sk->sk_bound_dev_if == sdif);
+ dev_match = inet_sk_bound_dev_eq(net, sk->sk_bound_dev_if,
+ dif, sdif);
+ if (!dev_match)
+ return -1;
+ score += 4;
- if (!dev_match)
- return -1;
- if (sk->sk_bound_dev_if)
- score += 4;
- }
if (sk->sk_incoming_cpu == raw_smp_processor_id())
score++;
}
@@ -675,6 +679,7 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
u32 remaining, offset;
int ret, i, low, high;
static u32 hint;
+ int l3mdev;
if (port) {
head = &hinfo->bhash[inet_bhashfn(net, port,
@@ -693,6 +698,8 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
return ret;
}
+ l3mdev = inet_sk_bound_l3mdev(sk);
+
inet_get_local_port_range(net, &low, &high);
high++; /* [32768, 60999] -> [32768, 61000[ */
remaining = high - low;
@@ -719,7 +726,8 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
* the established check is already unique enough.
*/
inet_bind_bucket_for_each(tb, &head->chain) {
- if (net_eq(ib_net(tb), net) && tb->port == port) {
+ if (net_eq(ib_net(tb), net) && tb->l3mdev == l3mdev &&
+ tb->port == port) {
if (tb->fastreuse >= 0 ||
tb->fastreuseport >= 0)
goto next_port;
@@ -732,7 +740,7 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
}
tb = inet_bind_bucket_create(hinfo->bind_bucket_cachep,
- net, head, port);
+ net, head, port, l3mdev);
if (!tb) {
spin_unlock_bh(&head->lock);
return -ENOMEM;
@@ -892,6 +892,9 @@ static int do_ip_setsockopt(struct sock *sk, int level,
dev_put(dev);
err = -EINVAL;
+ if (!sk->sk_bound_dev_if && midx)
+ break;
+
if (sk->sk_bound_dev_if &&
mreq.imr_ifindex != sk->sk_bound_dev_if &&
(!midx || midx != sk->sk_bound_dev_if))
@@ -70,6 +70,7 @@
#include <net/snmp.h>
#include <net/tcp_states.h>
#include <net/inet_common.h>
+#include <net/inet_hashtables.h>
#include <net/checksum.h>
#include <net/xfrm.h>
#include <linux/rtnetlink.h>
@@ -131,8 +132,7 @@ struct sock *__raw_v4_lookup(struct net *net, struct sock *sk,
if (net_eq(sock_net(sk), net) && inet->inet_num == num &&
!(inet->inet_daddr && inet->inet_daddr != raddr) &&
!(inet->inet_rcv_saddr && inet->inet_rcv_saddr != laddr) &&
- !(sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif &&
- sk->sk_bound_dev_if != sdif))
+ inet_sk_bound_dev_eq(net, sk->sk_bound_dev_if, dif, sdif))
goto found; /* gotcha */
}
sk = NULL;
@@ -371,6 +371,7 @@ static int compute_score(struct sock *sk, struct net *net,
{
int score;
struct inet_sock *inet;
+ bool dev_match;
if (!net_eq(sock_net(sk), net) ||
udp_sk(sk)->udp_port_hash != hnum ||
@@ -398,15 +399,11 @@ static int compute_score(struct sock *sk, struct net *net,
score += 4;
}
- if (sk->sk_bound_dev_if || exact_dif) {
- bool dev_match = (sk->sk_bound_dev_if == dif ||
- sk->sk_bound_dev_if == sdif);
-
- if (!dev_match)
- return -1;
- if (sk->sk_bound_dev_if)
- score += 4;
- }
+ dev_match = inet_sk_bound_dev_eq(net, sk->sk_bound_dev_if,
+ dif, sdif);
+ if (!dev_match)
+ return -1;
+ score += 4;
if (sk->sk_incoming_cpu == raw_smp_processor_id())
score++;
@@ -782,7 +782,10 @@ int ip6_datagram_send_ctl(struct net *net, struct sock *sk,
if (src_info->ipi6_ifindex) {
if (fl6->flowi6_oif &&
- src_info->ipi6_ifindex != fl6->flowi6_oif)
+ src_info->ipi6_ifindex != fl6->flowi6_oif &&
+ (sk->sk_bound_dev_if != fl6->flowi6_oif ||
+ !sk_dev_equal_l3scope(
+ sk, src_info->ipi6_ifindex)))
return -EINVAL;
fl6->flowi6_oif = src_info->ipi6_ifindex;
}
@@ -99,6 +99,7 @@ static inline int compute_score(struct sock *sk, struct net *net,
const int dif, const int sdif, bool exact_dif)
{
int score = -1;
+ bool dev_match;
if (net_eq(sock_net(sk), net) && inet_sk(sk)->inet_num == hnum &&
sk->sk_family == PF_INET6) {
@@ -109,15 +110,12 @@ static inline int compute_score(struct sock *sk, struct net *net,
return -1;
score++;
}
- if (sk->sk_bound_dev_if || exact_dif) {
- bool dev_match = (sk->sk_bound_dev_if == dif ||
- sk->sk_bound_dev_if == sdif);
+ dev_match = inet_sk_bound_dev_eq(net, sk->sk_bound_dev_if,
+ dif, sdif);
+ if (!dev_match)
+ return -1;
+ score++;
- if (!dev_match)
- return -1;
- if (sk->sk_bound_dev_if)
- score++;
- }
if (sk->sk_incoming_cpu == raw_smp_processor_id())
score++;
}
@@ -626,6 +626,9 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
rcu_read_unlock();
+ if (!sk->sk_bound_dev_if && midx)
+ goto e_inval;
+
if (sk->sk_bound_dev_if &&
sk->sk_bound_dev_if != val &&
(!midx || midx != sk->sk_bound_dev_if))
@@ -49,6 +49,7 @@
#include <net/transp_v6.h>
#include <net/udp.h>
#include <net/inet_common.h>
+#include <net/inet_hashtables.h>
#include <net/tcp_states.h>
#if IS_ENABLED(CONFIG_IPV6_MIP6)
#include <net/mip6.h>
@@ -86,9 +87,8 @@ struct sock *__raw_v6_lookup(struct net *net, struct sock *sk,
!ipv6_addr_equal(&sk->sk_v6_daddr, rmt_addr))
continue;
- if (sk->sk_bound_dev_if &&
- sk->sk_bound_dev_if != dif &&
- sk->sk_bound_dev_if != sdif)
+ if (!inet_sk_bound_dev_eq(net, sk->sk_bound_dev_if,
+ dif, sdif))
continue;
if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr)) {
@@ -117,6 +117,7 @@ static int compute_score(struct sock *sk, struct net *net,
{
int score;
struct inet_sock *inet;
+ bool dev_match;
if (!net_eq(sock_net(sk), net) ||
udp_sk(sk)->udp_port_hash != hnum ||
@@ -144,15 +145,10 @@ static int compute_score(struct sock *sk, struct net *net,
score++;
}
- if (sk->sk_bound_dev_if || exact_dif) {
- bool dev_match = (sk->sk_bound_dev_if == dif ||
- sk->sk_bound_dev_if == sdif);
-
- if (!dev_match)
- return -1;
- if (sk->sk_bound_dev_if)
- score++;
- }
+ dev_match = inet_sk_bound_dev_eq(net, sk->sk_bound_dev_if, dif, sdif);
+ if (!dev_match)
+ return -1;
+ score++;
if (sk->sk_incoming_cpu == raw_smp_processor_id())
score++;