hollalinux
/
linux-sg2042
mirror of https://github.com/sophgo/linux-riscv.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

net: allow binding socket in a VRF when there's an unbound socket 

Change the inet socket lookup to avoid packets arriving on a device
enslaved to an l3mdev from matching unbound sockets by removing the
wildcard for non sk_bound_dev_if and instead relying on check against
the secondary device index, which will be 0 when the input device is
not enslaved to an l3mdev and so match against an unbound socket and
not match when the input device is enslaved.

Change the socket binding to take the l3mdev into account to allow an
unbound socket to not conflict sockets bound to an l3mdev given the
datapath isolation now guaranteed.

Signed-off-by: Robert Shearman <rshearma@vyatta.att-mail.com>
Signed-off-by: Mike Manning <mmanning@vyatta.att-mail.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Tested-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This commit is contained in:
Robert Shearman 2018-11-07 15:36:02 +00:00 committed by David S. Miller
parent f601a85bd7
commit 3c82a21f43
6 changed files with 51 additions and 22 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
Documentation/networking/vrf.txt
View File

@ -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

3
include/net/inet6_hashtables.h
View File

@ -115,8 +115,7 @@ 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 == (__dif)) || \
((__sk)->sk_bound_dev_if == (__sdif))) && \
net_eq(sock_net(__sk), (__net)))

9
include/net/inet_hashtables.h
View File

@ -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;
@ -191,7 +192,7 @@ static inline void inet_ehash_locks_free(struct inet_hashinfo *hashinfo)
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);
@ -282,8 +283,7 @@ 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 == (__dif)) || \
((__sk)->sk_bound_dev_if == (__sdif))) && \
net_eq(sock_net(__sk), (__net)))
#else /* 32-bit arch */
@ -294,8 +294,7 @@ 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 == (__dif)) || \
((__sk)->sk_bound_dev_if == (__sdif))) && \
net_eq(sock_net(__sk), (__net)))
#endif /* 64-bit arch */

13
include/net/inet_sock.h
View File

@ -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;
}
struct inet_cork {
unsigned int flags;
__be32 addr;

13
net/ipv4/inet_connection_sock.c
View File

@ -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 @@ other_parity_scan:
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:

20
net/ipv4/inet_hashtables.c
View File

@ -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;
@ -675,6 +681,7 @@ 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 +700,8 @@ 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 +728,8 @@ other_parity_scan:
* 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 +742,7 @@ other_parity_scan:
}
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;