From 3c82a21f4320c8d54cf6456b27c8d49e5ffb722e Mon Sep 17 00:00:00 2001 From: Robert Shearman Date: Wed, 7 Nov 2018 15:36:02 +0000 Subject: 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 Signed-off-by: Mike Manning Reviewed-by: David Ahern Tested-by: David Ahern Signed-off-by: David S. Miller --- Documentation/networking/vrf.txt | 9 +++++---- include/net/inet6_hashtables.h | 5 ++--- include/net/inet_hashtables.h | 13 ++++++------- include/net/inet_sock.h | 13 +++++++++++++ net/ipv4/inet_connection_sock.c | 13 ++++++++++--- net/ipv4/inet_hashtables.c | 20 +++++++++++++++----- 6 files changed, 51 insertions(+), 22 deletions(-) diff --git a/Documentation/networking/vrf.txt b/Documentation/networking/vrf.txt index 8ff7b4c8f91b..d4b129402d57 100644 --- a/Documentation/networking/vrf.txt +++ b/Documentation/networking/vrf.txt @@ -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 diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h index 6e91e38a31da..9db98af46985 100644 --- a/include/net/inet6_hashtables.h +++ b/include/net/inet6_hashtables.h @@ -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 */ diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index 9141e95529e7..4ae060b4bac2 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_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; @@ -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); @@ -282,9 +283,8 @@ 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 +294,8 @@ 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 */ diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index a80fd0ac4563..ed3f723af00b 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -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; diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 15e7f7915a21..5c63449130d9 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -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: diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 411dd7a90046..40d722ab1738 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -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; -- cgit v1.2.3 From e78190581aff7c96fbd6324aa633170934650b65 Mon Sep 17 00:00:00 2001 From: Mike Manning Date: Wed, 7 Nov 2018 15:36:03 +0000 Subject: net: ensure unbound stream socket to be chosen when not in a VRF The commit a04a480d4392 ("net: Require exact match for TCP socket lookups if dif is l3mdev") only ensures that the correct socket is selected for packets in a VRF. However, there is no guarantee that the unbound socket will be selected for packets when not in a VRF. By checking for a device match in compute_score() also for the case when there is no bound device and attaching a score to this, the unbound socket is selected. And if a failure is returned when there is no device match, this ensures that bound sockets are never selected, even if there is no unbound socket. Signed-off-by: Mike Manning Reviewed-by: David Ahern Tested-by: David Ahern Signed-off-by: David S. Miller --- include/net/inet_hashtables.h | 11 +++++++++++ include/net/inet_sock.h | 8 ++++++++ net/ipv4/inet_hashtables.c | 14 ++++++-------- net/ipv6/inet6_hashtables.c | 14 ++++++-------- 4 files changed, 31 insertions(+), 16 deletions(-) diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index 4ae060b4bac2..0ce460e93dc4 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -189,6 +189,17 @@ 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 IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) + return inet_bound_dev_eq(!!net->ipv4.sysctl_tcp_l3mdev_accept, + bound_dev_if, dif, sdif); +#else + return inet_bound_dev_eq(true, bound_dev_if, dif, sdif); +#endif +} + struct inet_bind_bucket * inet_bind_bucket_create(struct kmem_cache *cachep, struct net *net, struct inet_bind_hashbucket *head, diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index ed3f723af00b..e8eef85006aa 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -143,6 +143,14 @@ static inline int inet_sk_bound_l3mdev(const struct sock *sk) return 0; } +static inline bool inet_bound_dev_eq(bool l3mdev_accept, int bound_dev_if, + int dif, int sdif) +{ + if (!bound_dev_if) + return !sdif || l3mdev_accept; + return bound_dev_if == dif || bound_dev_if == sdif; +} + struct inet_cork { unsigned int flags; __be32 addr; diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 40d722ab1738..13890d5bfc34 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -235,6 +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)) { @@ -245,15 +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++; } diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index 3d7c7460a0c5..5eeeba7181a1 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -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++; } -- cgit v1.2.3 From 6da5b0f027a825df2aebc1927a27bda185dc03d4 Mon Sep 17 00:00:00 2001 From: Mike Manning Date: Wed, 7 Nov 2018 15:36:04 +0000 Subject: net: ensure unbound datagram socket to be chosen when not in a VRF Ensure an unbound datagram skt is chosen when not in a VRF. The check for a device match in compute_score() for UDP must be performed when there is no device match. For this, a failure is returned when there is no device match. This ensures that bound sockets are never selected, even if there is no unbound socket. Allow IPv6 packets to be sent over a datagram skt bound to a VRF. These packets are currently blocked, as flowi6_oif was set to that of the master vrf device, and the ipi6_ifindex is that of the slave device. Allow these packets to be sent by checking the device with ipi6_ifindex has the same L3 scope as that of the bound device of the skt, which is the master vrf device. Note that this check always succeeds if the skt is unbound. Even though the right datagram skt is now selected by compute_score(), a different skt is being returned that is bound to the wrong vrf. The difference between these and stream sockets is the handling of the skt option for SO_REUSEPORT. While the handling when adding a skt for reuse correctly checks that the bound device of the skt is a match, the skts in the hashslot are already incorrect. So for the same hash, a skt for the wrong vrf may be selected for the required port. The root cause is that the skt is immediately placed into a slot when it is created, but when the skt is then bound using SO_BINDTODEVICE, it remains in the same slot. The solution is to move the skt to the correct slot by forcing a rehash. Signed-off-by: Mike Manning Reviewed-by: David Ahern Tested-by: David Ahern Signed-off-by: David S. Miller --- include/net/udp.h | 11 +++++++++++ net/core/sock.c | 2 ++ net/ipv4/udp.c | 15 ++++++--------- net/ipv6/datagram.c | 10 +++++++--- net/ipv6/udp.c | 14 +++++--------- 5 files changed, 31 insertions(+), 21 deletions(-) diff --git a/include/net/udp.h b/include/net/udp.h index 9e82cb391dea..a496e441645e 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -252,6 +252,17 @@ static inline int udp_rqueue_get(struct sock *sk) return sk_rmem_alloc_get(sk) - READ_ONCE(udp_sk(sk)->forward_deficit); } +static inline bool udp_sk_bound_dev_eq(struct net *net, int bound_dev_if, + int dif, int sdif) +{ +#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) + return inet_bound_dev_eq(!!net->ipv4.sysctl_udp_l3mdev_accept, + bound_dev_if, dif, sdif); +#else + return inet_bound_dev_eq(true, bound_dev_if, dif, sdif); +#endif +} + /* net/ipv4/udp.c */ void udp_destruct_sock(struct sock *sk); void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len); diff --git a/net/core/sock.c b/net/core/sock.c index 080a880a1761..7b304e454a38 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -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); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 1976fddb9e00..cf73c9194bb6 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -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 = udp_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++; diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 1ede7a16a0be..bde08aa549f3 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -772,6 +772,7 @@ int ip6_datagram_send_ctl(struct net *net, struct sock *sk, case IPV6_2292PKTINFO: { struct net_device *dev = NULL; + int src_idx; if (cmsg->cmsg_len < CMSG_LEN(sizeof(struct in6_pktinfo))) { err = -EINVAL; @@ -779,12 +780,15 @@ int ip6_datagram_send_ctl(struct net *net, struct sock *sk, } src_info = (struct in6_pktinfo *)CMSG_DATA(cmsg); + src_idx = src_info->ipi6_ifindex; - if (src_info->ipi6_ifindex) { + if (src_idx) { if (fl6->flowi6_oif && - src_info->ipi6_ifindex != fl6->flowi6_oif) + src_idx != fl6->flowi6_oif && + (sk->sk_bound_dev_if != fl6->flowi6_oif || + !sk_dev_equal_l3scope(sk, src_idx))) return -EINVAL; - fl6->flowi6_oif = src_info->ipi6_ifindex; + fl6->flowi6_oif = src_idx; } addr_type = __ipv6_addr_type(&src_info->ipi6_addr); diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index d2d97d07ef27..0559adc2f357 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -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 = udp_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++; -- cgit v1.2.3 From 6897445fb194c8ad046df4a13e1ee9f080a5a21e Mon Sep 17 00:00:00 2001 From: Mike Manning Date: Wed, 7 Nov 2018 15:36:05 +0000 Subject: net: provide a sysctl raw_l3mdev_accept for raw socket lookup with VRFs Add a sysctl raw_l3mdev_accept to control raw socket lookup in a manner similar to use of tcp_l3mdev_accept for stream and of udp_l3mdev_accept for datagram sockets. Have this default to enabled for reasons of backwards compatibility. This is so as to specify the output device with cmsg and IP_PKTINFO, but using a socket not bound to the corresponding VRF. This allows e.g. older ping implementations to be run with specifying the device but without executing it in the VRF. If the option is disabled, packets received in a VRF context are only handled by a raw socket bound to the VRF, and correspondingly packets in the default VRF are only handled by a socket not bound to any VRF. Signed-off-by: Mike Manning Reviewed-by: David Ahern Tested-by: David Ahern Signed-off-by: David S. Miller --- Documentation/networking/ip-sysctl.txt | 12 ++++++++++++ Documentation/networking/vrf.txt | 13 +++++++++++++ include/net/netns/ipv4.h | 3 +++ include/net/raw.h | 1 + net/ipv4/af_inet.c | 2 ++ net/ipv4/raw.c | 28 ++++++++++++++++++++++++++-- net/ipv4/sysctl_net_ipv4.c | 11 +++++++++++ 7 files changed, 68 insertions(+), 2 deletions(-) diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index 32b21571adfe..aa9e6a331679 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -370,6 +370,7 @@ tcp_l3mdev_accept - BOOLEAN derived from the listen socket to be bound to the L3 domain in which the packets originated. Only valid when the kernel was compiled with CONFIG_NET_L3_MASTER_DEV. + Default: 0 (disabled) tcp_low_latency - BOOLEAN This is a legacy option, it has no effect anymore. @@ -773,6 +774,7 @@ udp_l3mdev_accept - BOOLEAN being received regardless of the L3 domain in which they originated. Only valid when the kernel was compiled with CONFIG_NET_L3_MASTER_DEV. + Default: 0 (disabled) udp_mem - vector of 3 INTEGERs: min, pressure, max Number of pages allowed for queueing by all UDP sockets. @@ -799,6 +801,16 @@ udp_wmem_min - INTEGER total pages of UDP sockets exceed udp_mem pressure. The unit is byte. Default: 4K +RAW variables: + +raw_l3mdev_accept - BOOLEAN + Enabling this option allows a "global" bound socket to work + across L3 master domains (e.g., VRFs) with packets capable of + being received regardless of the L3 domain in which they + originated. Only valid when the kernel was compiled with + CONFIG_NET_L3_MASTER_DEV. + Default: 1 (enabled) + CIPSOv4 Variables: cipso_cache_enable - BOOLEAN diff --git a/Documentation/networking/vrf.txt b/Documentation/networking/vrf.txt index d4b129402d57..a5f103b083a0 100644 --- a/Documentation/networking/vrf.txt +++ b/Documentation/networking/vrf.txt @@ -111,9 +111,22 @@ 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: + sysctl -w net.ipv4.tcp_l3mdev_accept=1 sysctl -w net.ipv4.udp_l3mdev_accept=1 +These options are disabled by default so that a socket in a VRF is only +selected for packets in that VRF. There is a similar option for RAW +sockets, which is enabled by default for reasons of backwards compatibility. +This is so as to specify the output device with cmsg and IP_PKTINFO, but +using a socket not bound to the corresponding VRF. This allows e.g. older ping +implementations to be run with specifying the device but without executing it +in the VRF. This option can be disabled so that packets received in a VRF +context are only handled by a raw socket bound to the VRF, and packets in the +default VRF are only handled by a socket not bound to any VRF: + + sysctl -w net.ipv4.raw_l3mdev_accept=0 + netfilter rules on the VRF device can be used to limit access to services running in the default VRF context as well. diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index e47503b4e4d1..104a6669e344 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -103,6 +103,9 @@ struct netns_ipv4 { /* Shall we try to damage output packets if routing dev changes? */ int sysctl_ip_dynaddr; int sysctl_ip_early_demux; +#ifdef CONFIG_NET_L3_MASTER_DEV + int sysctl_raw_l3mdev_accept; +#endif int sysctl_tcp_early_demux; int sysctl_udp_early_demux; diff --git a/include/net/raw.h b/include/net/raw.h index 9c9fa98a91a4..20ebf0b3dfa8 100644 --- a/include/net/raw.h +++ b/include/net/raw.h @@ -61,6 +61,7 @@ void raw_seq_stop(struct seq_file *seq, void *v); int raw_hash_sk(struct sock *sk); void raw_unhash_sk(struct sock *sk); +void raw_init(void); struct raw_sock { /* inet_sock has to be the first member */ diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 1fbe2f815474..07749c5b0a50 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1964,6 +1964,8 @@ static int __init inet_init(void) /* Add UDP-Lite (RFC 3828) */ udplite4_register(); + raw_init(); + ping_init(); /* diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 8ca3eb06ba04..1ebd29abe79c 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -805,7 +805,7 @@ out: return copied; } -static int raw_init(struct sock *sk) +static int raw_sk_init(struct sock *sk) { struct raw_sock *rp = raw_sk(sk); @@ -970,7 +970,7 @@ struct proto raw_prot = { .connect = ip4_datagram_connect, .disconnect = __udp_disconnect, .ioctl = raw_ioctl, - .init = raw_init, + .init = raw_sk_init, .setsockopt = raw_setsockopt, .getsockopt = raw_getsockopt, .sendmsg = raw_sendmsg, @@ -1133,4 +1133,28 @@ void __init raw_proc_exit(void) { unregister_pernet_subsys(&raw_net_ops); } + +static void raw_sysctl_init_net(struct net *net) +{ +#ifdef CONFIG_NET_L3_MASTER_DEV + net->ipv4.sysctl_raw_l3mdev_accept = 1; +#endif +} + +static int __net_init raw_sysctl_init(struct net *net) +{ + raw_sysctl_init_net(net); + return 0; +} + +static struct pernet_operations __net_initdata raw_sysctl_ops = { + .init = raw_sysctl_init, +}; + +void __init raw_init(void) +{ + raw_sysctl_init_net(&init_net); + if (register_pernet_subsys(&raw_sysctl_ops)) + panic("RAW: failed to init sysctl parameters.\n"); +} #endif /* CONFIG_PROC_FS */ diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 891ed2f91467..ba0fc4b18465 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -602,6 +602,17 @@ static struct ctl_table ipv4_net_table[] = { .mode = 0644, .proc_handler = ipv4_ping_group_range, }, +#ifdef CONFIG_NET_L3_MASTER_DEV + { + .procname = "raw_l3mdev_accept", + .data = &init_net.ipv4.sysctl_raw_l3mdev_accept, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &one, + }, +#endif { .procname = "tcp_ecn", .data = &init_net.ipv4.sysctl_tcp_ecn, -- cgit v1.2.3 From 7055420fb6a1cb754a64be99ddcabd45bd902d99 Mon Sep 17 00:00:00 2001 From: Duncan Eastoe Date: Wed, 7 Nov 2018 15:36:06 +0000 Subject: net: fix raw socket lookup device bind matching with VRFs When there exist a pair of raw sockets one unbound and one bound to a VRF but equal in all other respects, when a packet is received in the VRF context, __raw_v4_lookup() matches on both sockets. This results in the packet being delivered over both sockets, instead of only the raw socket bound to the VRF. The bound device checks in __raw_v4_lookup() are replaced with a call to raw_sk_bound_dev_eq() which correctly handles whether the packet should be delivered over the unbound socket in such cases. In __raw_v6_lookup() the match on the device binding of the socket is similarly updated to use raw_sk_bound_dev_eq() which matches the handling in __raw_v4_lookup(). Importantly raw_sk_bound_dev_eq() takes the raw_l3mdev_accept sysctl into account. Signed-off-by: Duncan Eastoe Signed-off-by: Mike Manning Reviewed-by: David Ahern Tested-by: David Ahern Signed-off-by: David S. Miller --- include/net/raw.h | 13 ++++++++++++- net/ipv4/raw.c | 3 +-- net/ipv6/raw.c | 5 ++--- 3 files changed, 15 insertions(+), 6 deletions(-) diff --git a/include/net/raw.h b/include/net/raw.h index 20ebf0b3dfa8..821ff4887f77 100644 --- a/include/net/raw.h +++ b/include/net/raw.h @@ -17,7 +17,7 @@ #ifndef _RAW_H #define _RAW_H - +#include #include #include @@ -75,4 +75,15 @@ static inline struct raw_sock *raw_sk(const struct sock *sk) return (struct raw_sock *)sk; } +static inline bool raw_sk_bound_dev_eq(struct net *net, int bound_dev_if, + int dif, int sdif) +{ +#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) + return inet_bound_dev_eq(!!net->ipv4.sysctl_raw_l3mdev_accept, + bound_dev_if, dif, sdif); +#else + return inet_bound_dev_eq(true, bound_dev_if, dif, sdif); +#endif +} + #endif /* _RAW_H */ diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 1ebd29abe79c..fb1f02015a15 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -131,8 +131,7 @@ 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)) + raw_sk_bound_dev_eq(net, sk->sk_bound_dev_if, dif, sdif)) goto found; /* gotcha */ } sk = NULL; diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 5e0efd3954e9..aed7eb5c2123 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -86,9 +86,8 @@ 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 (!raw_sk_bound_dev_eq(net, sk->sk_bound_dev_if, + dif, sdif)) continue; if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr)) { -- cgit v1.2.3 From 6f12fa775530195a501fb090d092c637f32d0cc5 Mon Sep 17 00:00:00 2001 From: Mike Manning Date: Wed, 7 Nov 2018 15:36:07 +0000 Subject: vrf: mark skb for multicast or link-local as enslaved to VRF The skb for packets that are multicast or to a link-local address are not marked as being enslaved to a VRF, if they are received on a socket bound to the VRF. This is needed for ND and it is preferable for the kernel not to have to deal with the additional use-cases if ll or mcast packets are handled as enslaved. However, this does not allow service instances listening on unbound and bound to VRF sockets to distinguish the VRF used, if packets are sent as multicast or to a link-local address. The fix is for the VRF driver to also mark these skb as being enslaved to the VRF. Signed-off-by: Mike Manning Reviewed-by: David Ahern Tested-by: David Ahern Signed-off-by: David S. Miller --- drivers/net/vrf.c | 19 +++++++++---------- 1 file changed, 9 insertions(+), 10 deletions(-) diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index 69b7227c637e..21ad4b1d7f03 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -981,24 +981,23 @@ static struct sk_buff *vrf_ip6_rcv(struct net_device *vrf_dev, struct sk_buff *skb) { int orig_iif = skb->skb_iif; - bool need_strict; + bool need_strict = rt6_need_strict(&ipv6_hdr(skb)->daddr); + bool is_ndisc = ipv6_ndisc_frame(skb); - /* loopback traffic; do not push through packet taps again. - * Reset pkt_type for upper layers to process skb + /* loopback, multicast & non-ND link-local traffic; do not push through + * packet taps again. Reset pkt_type for upper layers to process skb */ - if (skb->pkt_type == PACKET_LOOPBACK) { + if (skb->pkt_type == PACKET_LOOPBACK || (need_strict && !is_ndisc)) { skb->dev = vrf_dev; skb->skb_iif = vrf_dev->ifindex; IP6CB(skb)->flags |= IP6SKB_L3SLAVE; - skb->pkt_type = PACKET_HOST; + if (skb->pkt_type == PACKET_LOOPBACK) + skb->pkt_type = PACKET_HOST; goto out; } - /* if packet is NDISC or addressed to multicast or link-local - * then keep the ingress interface - */ - need_strict = rt6_need_strict(&ipv6_hdr(skb)->daddr); - if (!ipv6_ndisc_frame(skb) && !need_strict) { + /* if packet is NDISC then keep the ingress interface */ + if (!is_ndisc) { vrf_rx_stats(vrf_dev, skb->len); skb->dev = vrf_dev; skb->skb_iif = vrf_dev->ifindex; -- cgit v1.2.3 From d839a0ebeb4e81a4f2923f581c28b41e1238bdfe Mon Sep 17 00:00:00 2001 From: Mike Manning Date: Wed, 7 Nov 2018 15:36:08 +0000 Subject: ipv6: allow ping to link-local address in VRF If link-local packets are marked as enslaved to a VRF, then to allow ping to the link-local from a vrf, the error handling for IPV6_PKTINFO needs to be relaxed to also allow the pkt ipi6_ifindex to be that of a slave device to the vrf. Note that the real device also needs to be retrieved in icmp6_iif() to set the ipv6 flow oif to this for icmp echo reply handling. The recent commit 24b711edfc34 ("net/ipv6: Fix linklocal to global address with VRF") takes care of this, so the sdif does not need checking here. This fix makes ping to link-local consistent with that to global addresses, in that this can now be done from within the same VRF that the address is in. Signed-off-by: Mike Manning Reviewed-by: David Ahern Tested-by: David Ahern Signed-off-by: David S. Miller --- net/ipv6/ipv6_sockglue.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 381ce38940ae..973e215c3114 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -486,7 +486,7 @@ sticky_done: retv = -EFAULT; break; } - if (sk->sk_bound_dev_if && pkt.ipi6_ifindex != sk->sk_bound_dev_if) + if (!sk_dev_equal_l3scope(sk, pkt.ipi6_ifindex)) goto e_inval; np->sticky_pktinfo.ipi6_ifindex = pkt.ipi6_ifindex; -- cgit v1.2.3 From 5226b6a920ba78d9fbcbb843388d2a844a1fa1c8 Mon Sep 17 00:00:00 2001 From: Mike Manning Date: Wed, 7 Nov 2018 15:36:09 +0000 Subject: ipv6: handling of multicast packets received in VRF If the skb for multicast packets marked as enslaved to a VRF are received, then the secondary device index should be used to obtain the real device. And verify the multicast address against the enslaved rather than the l3mdev device. Signed-off-by: Dewi Morgan Signed-off-by: Mike Manning Reviewed-by: David Ahern Tested-by: David Ahern Signed-off-by: David S. Miller --- net/ipv6/ip6_input.c | 35 ++++++++++++++++++++++++++++++++--- 1 file changed, 32 insertions(+), 3 deletions(-) diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index 96577e742afd..df58e1100226 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -359,6 +359,8 @@ resubmit_final: } } else if (ipprot->flags & INET6_PROTO_FINAL) { const struct ipv6hdr *hdr; + int sdif = inet6_sdif(skb); + struct net_device *dev; /* Only do this once for first final protocol */ have_final = true; @@ -371,9 +373,19 @@ resubmit_final: skb_postpull_rcsum(skb, skb_network_header(skb), skb_network_header_len(skb)); hdr = ipv6_hdr(skb); + + /* skb->dev passed may be master dev for vrfs. */ + if (sdif) { + dev = dev_get_by_index_rcu(net, sdif); + if (!dev) + goto discard; + } else { + dev = skb->dev; + } + if (ipv6_addr_is_multicast(&hdr->daddr) && - !ipv6_chk_mcast_addr(skb->dev, &hdr->daddr, - &hdr->saddr) && + !ipv6_chk_mcast_addr(dev, &hdr->daddr, + &hdr->saddr) && !ipv6_is_mld(skb, nexthdr, skb_network_header_len(skb))) goto discard; } @@ -432,15 +444,32 @@ EXPORT_SYMBOL_GPL(ip6_input); int ip6_mc_input(struct sk_buff *skb) { + int sdif = inet6_sdif(skb); const struct ipv6hdr *hdr; + struct net_device *dev; bool deliver; __IP6_UPD_PO_STATS(dev_net(skb_dst(skb)->dev), __in6_dev_get_safely(skb->dev), IPSTATS_MIB_INMCAST, skb->len); + /* skb->dev passed may be master dev for vrfs. */ + if (sdif) { + rcu_read_lock(); + dev = dev_get_by_index_rcu(dev_net(skb->dev), sdif); + if (!dev) { + rcu_read_unlock(); + kfree_skb(skb); + return -ENODEV; + } + } else { + dev = skb->dev; + } + hdr = ipv6_hdr(skb); - deliver = ipv6_chk_mcast_addr(skb->dev, &hdr->daddr, NULL); + deliver = ipv6_chk_mcast_addr(dev, &hdr->daddr, NULL); + if (sdif) + rcu_read_unlock(); #ifdef CONFIG_IPV6_MROUTE /* -- cgit v1.2.3 From 7bd2db404efa3daff700e8c88561b435611d07a5 Mon Sep 17 00:00:00 2001 From: Dewi Morgan Date: Wed, 7 Nov 2018 15:36:10 +0000 Subject: ipv6: do not drop vrf udp multicast packets For bound udp sockets in a vrf, also check the sdif to get the index for ingress devices enslaved to an l3mdev. Signed-off-by: Dewi Morgan Signed-off-by: Mike Manning Reviewed-by: David Ahern Tested-by: David Ahern Signed-off-by: David S. Miller --- net/ipv6/udp.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 0559adc2f357..a25571c12a8a 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -637,7 +637,7 @@ drop: static bool __udp_v6_is_mcast_sock(struct net *net, struct sock *sk, __be16 loc_port, const struct in6_addr *loc_addr, __be16 rmt_port, const struct in6_addr *rmt_addr, - int dif, unsigned short hnum) + int dif, int sdif, unsigned short hnum) { struct inet_sock *inet = inet_sk(sk); @@ -649,7 +649,7 @@ static bool __udp_v6_is_mcast_sock(struct net *net, struct sock *sk, (inet->inet_dport && inet->inet_dport != rmt_port) || (!ipv6_addr_any(&sk->sk_v6_daddr) && !ipv6_addr_equal(&sk->sk_v6_daddr, rmt_addr)) || - (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif) || + !udp_sk_bound_dev_eq(net, sk->sk_bound_dev_if, dif, sdif) || (!ipv6_addr_any(&sk->sk_v6_rcv_saddr) && !ipv6_addr_equal(&sk->sk_v6_rcv_saddr, loc_addr))) return false; @@ -683,6 +683,7 @@ static int __udp6_lib_mcast_deliver(struct net *net, struct sk_buff *skb, unsigned int offset = offsetof(typeof(*sk), sk_node); unsigned int hash2 = 0, hash2_any = 0, use_hash2 = (hslot->count > 10); int dif = inet6_iif(skb); + int sdif = inet6_sdif(skb); struct hlist_node *node; struct sk_buff *nskb; @@ -697,7 +698,8 @@ start_lookup: sk_for_each_entry_offset_rcu(sk, node, &hslot->head, offset) { if (!__udp_v6_is_mcast_sock(net, sk, uh->dest, daddr, - uh->source, saddr, dif, hnum)) + uh->source, saddr, dif, sdif, + hnum)) continue; /* If zero checksum and no_check is not on for * the socket then skip it. -- cgit v1.2.3