From 4e3c89920cd3a6cfce22c6f537690747c26128dd Mon Sep 17 00:00:00 2001 From: David Ahern Date: Thu, 13 Aug 2015 14:59:00 -0600 Subject: [PATCH 01/11] net: Introduce VRF related flags and helpers Add a VRF_MASTER flag for interfaces and helper functions for determining if a device is a VRF_MASTER. Add link attribute for passing VRF_TABLE id. Add vrf_ptr to netdevice. Add various macros for determining if a device is a VRF device, the index of the master VRF device and table associated with VRF device. Signed-off-by: Shrijeet Mukherjee Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/linux/netdevice.h | 20 +++++ include/net/vrf.h | 139 +++++++++++++++++++++++++++++++++++ include/uapi/linux/if_link.h | 9 +++ 3 files changed, 168 insertions(+) create mode 100644 include/net/vrf.h diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 607b5f41f46f..f7a6ef2fae3a 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1289,6 +1289,7 @@ enum netdev_priv_flags { IFF_XMIT_DST_RELEASE_PERM = 1<<22, IFF_IPVLAN_MASTER = 1<<23, IFF_IPVLAN_SLAVE = 1<<24, + IFF_VRF_MASTER = 1<<25, }; #define IFF_802_1Q_VLAN IFF_802_1Q_VLAN @@ -1316,6 +1317,7 @@ enum netdev_priv_flags { #define IFF_XMIT_DST_RELEASE_PERM IFF_XMIT_DST_RELEASE_PERM #define IFF_IPVLAN_MASTER IFF_IPVLAN_MASTER #define IFF_IPVLAN_SLAVE IFF_IPVLAN_SLAVE +#define IFF_VRF_MASTER IFF_VRF_MASTER /** * struct net_device - The DEVICE structure. @@ -1432,6 +1434,7 @@ enum netdev_priv_flags { * @dn_ptr: DECnet specific data * @ip6_ptr: IPv6 specific data * @ax25_ptr: AX.25 specific data + * @vrf_ptr: VRF specific data * @ieee80211_ptr: IEEE 802.11 specific data, assign before registering * * @last_rx: Time of last Rx @@ -1650,6 +1653,7 @@ struct net_device { struct dn_dev __rcu *dn_ptr; struct inet6_dev __rcu *ip6_ptr; void *ax25_ptr; + struct net_vrf_dev __rcu *vrf_ptr; struct wireless_dev *ieee80211_ptr; struct wpan_dev *ieee802154_ptr; #if IS_ENABLED(CONFIG_MPLS_ROUTING) @@ -3808,6 +3812,22 @@ static inline bool netif_supports_nofcs(struct net_device *dev) return dev->priv_flags & IFF_SUPP_NOFCS; } +static inline bool netif_is_vrf(const struct net_device *dev) +{ + return dev->priv_flags & IFF_VRF_MASTER; +} + +static inline bool netif_index_is_vrf(struct net *net, int ifindex) +{ + struct net_device *dev = dev_get_by_index_rcu(net, ifindex); + bool rc = false; + + if (dev) + rc = netif_is_vrf(dev); + + return rc; +} + /* This device needs to keep skb dst for qdisc enqueue or ndo_start_xmit() */ static inline void netif_keep_dst(struct net_device *dev) { diff --git a/include/net/vrf.h b/include/net/vrf.h new file mode 100644 index 000000000000..0484d29d4589 --- /dev/null +++ b/include/net/vrf.h @@ -0,0 +1,139 @@ +/* + * include/net/net_vrf.h - adds vrf dev structure definitions + * Copyright (c) 2015 Cumulus Networks + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#ifndef __LINUX_NET_VRF_H +#define __LINUX_NET_VRF_H + +struct net_vrf_dev { + struct rcu_head rcu; + int ifindex; /* ifindex of master dev */ + u32 tb_id; /* table id for VRF */ +}; + +struct slave { + struct list_head list; + struct net_device *dev; +}; + +struct slave_queue { + struct list_head all_slaves; + int num_slaves; +}; + +struct net_vrf { + struct slave_queue queue; + struct rtable *rth; + u32 tb_id; +}; + + +#if IS_ENABLED(CONFIG_NET_VRF) +/* called with rcu_read_lock() */ +static inline int vrf_master_ifindex_rcu(const struct net_device *dev) +{ + struct net_vrf_dev *vrf_ptr; + int ifindex = 0; + + if (!dev) + return 0; + + if (netif_is_vrf(dev)) + ifindex = dev->ifindex; + else { + vrf_ptr = rcu_dereference(dev->vrf_ptr); + if (vrf_ptr) + ifindex = vrf_ptr->ifindex; + } + + return ifindex; +} + +/* called with rcu_read_lock */ +static inline int vrf_dev_table_rcu(const struct net_device *dev) +{ + int tb_id = 0; + + if (dev) { + struct net_vrf_dev *vrf_ptr; + + vrf_ptr = rcu_dereference(dev->vrf_ptr); + if (vrf_ptr) + tb_id = vrf_ptr->tb_id; + } + return tb_id; +} + +static inline int vrf_dev_table(const struct net_device *dev) +{ + int tb_id; + + rcu_read_lock(); + tb_id = vrf_dev_table_rcu(dev); + rcu_read_unlock(); + + return tb_id; +} + +/* called with rtnl */ +static inline int vrf_dev_table_rtnl(const struct net_device *dev) +{ + int tb_id = 0; + + if (dev) { + struct net_vrf_dev *vrf_ptr; + + vrf_ptr = rtnl_dereference(dev->vrf_ptr); + if (vrf_ptr) + tb_id = vrf_ptr->tb_id; + } + return tb_id; +} + +/* caller has already checked netif_is_vrf(dev) */ +static inline struct rtable *vrf_dev_get_rth(const struct net_device *dev) +{ + struct rtable *rth = ERR_PTR(-ENETUNREACH); + struct net_vrf *vrf = netdev_priv(dev); + + if (vrf) { + rth = vrf->rth; + atomic_inc(&rth->dst.__refcnt); + } + return rth; +} + +#else +static inline int vrf_master_ifindex_rcu(const struct net_device *dev) +{ + return 0; +} + +static inline int vrf_dev_table_rcu(const struct net_device *dev) +{ + return 0; +} + +static inline int vrf_dev_table(const struct net_device *dev) +{ + return 0; +} + +static inline int vrf_dev_table_rtnl(const struct net_device *dev) +{ + return 0; +} + +static inline struct rtable *vrf_dev_get_rth(const struct net_device *dev) +{ + return ERR_PTR(-ENETUNREACH); +} +#endif + +#endif /* __LINUX_NET_VRF_H */ diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index d450be36add2..313c305fd1ad 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -341,6 +341,15 @@ enum macvlan_macaddr_mode { #define MACVLAN_FLAG_NOPROMISC 1 +/* VRF section */ +enum { + IFLA_VRF_UNSPEC, + IFLA_VRF_TABLE, + __IFLA_VRF_MAX +}; + +#define IFLA_VRF_MAX (__IFLA_VRF_MAX - 1) + /* IPVLAN section */ enum { IFLA_IPVLAN_UNSPEC, From cd2fbe1b6b517ca7c0e80b103c674fdf5bd50f76 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Thu, 13 Aug 2015 14:59:01 -0600 Subject: [PATCH 02/11] net: Use VRF device index for lookups on RX On ingress use index of VRF master device for route lookups if real device is enslaved. Rules are expected to be installed for the VRF device to direct lookups to a specific table. Signed-off-by: Shrijeet Mukherjee Signed-off-by: David Ahern Signed-off-by: David S. Miller --- net/ipv4/fib_frontend.c | 8 +++++++- net/ipv4/route.c | 3 ++- 2 files changed, 9 insertions(+), 2 deletions(-) diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 6b98de0d7949..d8ced1d89f1b 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -45,6 +45,7 @@ #include #include #include +#include #ifndef CONFIG_IP_MULTIPLE_TABLES @@ -309,7 +310,9 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, bool dev_match; fl4.flowi4_oif = 0; - fl4.flowi4_iif = oif ? : LOOPBACK_IFINDEX; + fl4.flowi4_iif = vrf_master_ifindex_rcu(dev); + if (!fl4.flowi4_iif) + fl4.flowi4_iif = oif ? : LOOPBACK_IFINDEX; fl4.daddr = src; fl4.saddr = dst; fl4.flowi4_tos = tos; @@ -339,6 +342,9 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, if (nh->nh_dev == dev) { dev_match = true; break; + } else if (vrf_master_ifindex_rcu(nh->nh_dev) == dev->ifindex) { + dev_match = true; + break; } } #else diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 18fd7c9095c7..c26ff1f7067d 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -112,6 +112,7 @@ #endif #include #include +#include #define RT_FL_TOS(oldflp4) \ ((oldflp4)->flowi4_tos & (IPTOS_RT_MASK | RTO_ONLINK)) @@ -1726,7 +1727,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, * Now we are ready to route packet. */ fl4.flowi4_oif = 0; - fl4.flowi4_iif = dev->ifindex; + fl4.flowi4_iif = vrf_master_ifindex_rcu(dev) ? : dev->ifindex; fl4.flowi4_mark = skb->mark; fl4.flowi4_tos = tos; fl4.flowi4_scope = RT_SCOPE_UNIVERSE; From 613d09b30f8b589d5a9b49775054c8865db95d1c Mon Sep 17 00:00:00 2001 From: David Ahern Date: Thu, 13 Aug 2015 14:59:02 -0600 Subject: [PATCH 03/11] net: Use VRF device index for lookups on TX As with ingress use the index of VRF master device for route lookups on egress. However, the oif should only be used to direct the lookups to a specific table. Routes in the table are not based on the VRF device but rather interfaces that are part of the VRF so do not consider the oif for lookups within the table. The FLOWI_FLAG_VRFSRC is used to control this latter part. Signed-off-by: Shrijeet Mukherjee Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/net/flow.h | 1 + include/net/route.h | 3 +++ net/ipv4/fib_trie.c | 7 +++++-- net/ipv4/icmp.c | 4 ++++ net/ipv4/route.c | 5 +++++ 5 files changed, 18 insertions(+), 2 deletions(-) diff --git a/include/net/flow.h b/include/net/flow.h index 3098ae33a178..f305588fc162 100644 --- a/include/net/flow.h +++ b/include/net/flow.h @@ -33,6 +33,7 @@ struct flowi_common { __u8 flowic_flags; #define FLOWI_FLAG_ANYSRC 0x01 #define FLOWI_FLAG_KNOWN_NH 0x02 +#define FLOWI_FLAG_VRFSRC 0x04 __u32 flowic_secid; struct flowi_tunnel flowic_tun_key; }; diff --git a/include/net/route.h b/include/net/route.h index 2d45f419477f..94189d4bd899 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -251,6 +251,9 @@ static inline void ip_route_connect_init(struct flowi4 *fl4, __be32 dst, __be32 if (inet_sk(sk)->transparent) flow_flags |= FLOWI_FLAG_ANYSRC; + if (netif_index_is_vrf(sock_net(sk), oif)) + flow_flags |= FLOWI_FLAG_VRFSRC; + flowi4_init_output(fl4, oif, sk->sk_mark, tos, RT_SCOPE_UNIVERSE, protocol, flow_flags, dst, src, dport, sport); } diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 37c4bb89a708..1243c79cb5b0 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1423,8 +1423,11 @@ found: nh->nh_flags & RTNH_F_LINKDOWN && !(fib_flags & FIB_LOOKUP_IGNORE_LINKSTATE)) continue; - if (flp->flowi4_oif && flp->flowi4_oif != nh->nh_oif) - continue; + if (!(flp->flowi4_flags & FLOWI_FLAG_VRFSRC)) { + if (flp->flowi4_oif && + flp->flowi4_oif != nh->nh_oif) + continue; + } if (!(fib_flags & FIB_LOOKUP_NOREF)) atomic_inc(&fi->fib_clntref); diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index c0556f1e4bf0..1164fc4ce3bc 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -96,6 +96,7 @@ #include #include #include +#include /* * Build xmit assembly blocks @@ -425,6 +426,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb) fl4.flowi4_mark = mark; fl4.flowi4_tos = RT_TOS(ip_hdr(skb)->tos); fl4.flowi4_proto = IPPROTO_ICMP; + fl4.flowi4_oif = vrf_master_ifindex_rcu(skb->dev) ? : skb->dev->ifindex; security_skb_classify_flow(skb, flowi4_to_flowi(&fl4)); rt = ip_route_output_key(net, &fl4); if (IS_ERR(rt)) @@ -458,6 +460,8 @@ static struct rtable *icmp_route_lookup(struct net *net, fl4->flowi4_proto = IPPROTO_ICMP; fl4->fl4_icmp_type = type; fl4->fl4_icmp_code = code; + fl4->flowi4_oif = vrf_master_ifindex_rcu(skb_in->dev) ? : skb_in->dev->ifindex; + security_skb_classify_flow(skb_in, flowi4_to_flowi(fl4)); rt = __ip_route_output_key(net, fl4); if (IS_ERR(rt)) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index c26ff1f7067d..2c89d294b669 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2131,6 +2131,11 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4) fl4->saddr = inet_select_addr(dev_out, 0, RT_SCOPE_HOST); } + if (netif_is_vrf(dev_out) && + !(fl4->flowi4_flags & FLOWI_FLAG_VRFSRC)) { + rth = vrf_dev_get_rth(dev_out); + goto out; + } } if (!fl4->daddr) { From 9a24abfa42613fefc68963a98c2b7ab7fd7e374c Mon Sep 17 00:00:00 2001 From: David Ahern Date: Thu, 13 Aug 2015 14:59:03 -0600 Subject: [PATCH 04/11] udp: Handle VRF device in sendmsg For unconnected UDP sockets using a VRF device lookup source address based on VRF table. This allows the UDP header to be properly setup before showing up at the VRF device via the dst. Signed-off-by: Shrijeet Mukherjee Signed-off-by: David Ahern Signed-off-by: David S. Miller --- net/ipv4/udp.c | 22 +++++++++++++++++++++- 1 file changed, 21 insertions(+), 1 deletion(-) diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 1b8c5ba7d5f7..c0a15e7f359f 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1013,11 +1013,31 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (!rt) { struct net *net = sock_net(sk); + __u8 flow_flags = inet_sk_flowi_flags(sk); fl4 = &fl4_stack; + + /* unconnected socket. If output device is enslaved to a VRF + * device lookup source address from VRF table. This mimics + * behavior of ip_route_connect{_init}. + */ + if (netif_index_is_vrf(net, ipc.oif)) { + flowi4_init_output(fl4, ipc.oif, sk->sk_mark, tos, + RT_SCOPE_UNIVERSE, sk->sk_protocol, + (flow_flags | FLOWI_FLAG_VRFSRC), + faddr, saddr, dport, + inet->inet_sport); + + rt = ip_route_output_flow(net, fl4, sk); + if (!IS_ERR(rt)) { + saddr = fl4->saddr; + ip_rt_put(rt); + } + } + flowi4_init_output(fl4, ipc.oif, sk->sk_mark, tos, RT_SCOPE_UNIVERSE, sk->sk_protocol, - inet_sk_flowi_flags(sk), + flow_flags, faddr, saddr, dport, inet->inet_sport); security_sk_classify_flow(sk, flowi4_to_flowi(fl4)); From 15be405eb2ea943ac5fa2aab7d0ba282e9ef1301 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Thu, 13 Aug 2015 14:59:04 -0600 Subject: [PATCH 05/11] net: Add inet_addr lookup by table Currently inet_addr_type and inet_dev_addr_type expect local addresses to be in the local table. With the VRF device local routes for devices associated with a VRF will be in the table associated with the VRF. Provide an alternate inet_addr lookup to use a specific table rather than defaulting to the local table. Signed-off-by: Shrijeet Mukherjee Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/net/route.h | 1 + net/ipv4/fib_frontend.c | 22 +++++++++++++++------- 2 files changed, 16 insertions(+), 7 deletions(-) diff --git a/include/net/route.h b/include/net/route.h index 94189d4bd899..6ba681f0b98d 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -189,6 +189,7 @@ void ipv4_sk_redirect(struct sk_buff *skb, struct sock *sk); void ip_rt_send_redirect(struct sk_buff *skb); unsigned int inet_addr_type(struct net *net, __be32 addr); +unsigned int inet_addr_type_table(struct net *net, __be32 addr, int tb_id); unsigned int inet_dev_addr_type(struct net *net, const struct net_device *dev, __be32 addr); void ip_rt_multicast_event(struct in_device *); diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index d8ced1d89f1b..b11321a8e58d 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -212,12 +212,12 @@ void fib_flush_external(struct net *net) */ static inline unsigned int __inet_dev_addr_type(struct net *net, const struct net_device *dev, - __be32 addr) + __be32 addr, int tb_id) { struct flowi4 fl4 = { .daddr = addr }; struct fib_result res; unsigned int ret = RTN_BROADCAST; - struct fib_table *local_table; + struct fib_table *table; if (ipv4_is_zeronet(addr) || ipv4_is_lbcast(addr)) return RTN_BROADCAST; @@ -226,10 +226,10 @@ static inline unsigned int __inet_dev_addr_type(struct net *net, rcu_read_lock(); - local_table = fib_get_table(net, RT_TABLE_LOCAL); - if (local_table) { + table = fib_get_table(net, tb_id); + if (table) { ret = RTN_UNICAST; - if (!fib_table_lookup(local_table, &fl4, &res, FIB_LOOKUP_NOREF)) { + if (!fib_table_lookup(table, &fl4, &res, FIB_LOOKUP_NOREF)) { if (!dev || dev == res.fi->fib_dev) ret = res.type; } @@ -239,16 +239,24 @@ static inline unsigned int __inet_dev_addr_type(struct net *net, return ret; } +unsigned int inet_addr_type_table(struct net *net, __be32 addr, int tb_id) +{ + return __inet_dev_addr_type(net, NULL, addr, tb_id); +} +EXPORT_SYMBOL(inet_addr_type_table); + unsigned int inet_addr_type(struct net *net, __be32 addr) { - return __inet_dev_addr_type(net, NULL, addr); + return __inet_dev_addr_type(net, NULL, addr, RT_TABLE_LOCAL); } EXPORT_SYMBOL(inet_addr_type); unsigned int inet_dev_addr_type(struct net *net, const struct net_device *dev, __be32 addr) { - return __inet_dev_addr_type(net, dev, addr); + int rt_table = vrf_dev_table(dev) ? : RT_TABLE_LOCAL; + + return __inet_dev_addr_type(net, dev, addr, rt_table); } EXPORT_SYMBOL(inet_dev_addr_type); From 30bbaa19500559d7625c65632195413f639b3b97 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Thu, 13 Aug 2015 14:59:05 -0600 Subject: [PATCH 06/11] net: Fix up inet_addr_type checks Currently inet_addr_type and inet_dev_addr_type expect local addresses to be in the local table. With the VRF device local routes for devices associated with a VRF will be in the table associated with the VRF. Provide an alternate inet_addr lookup to use a specific table rather than defaulting to the local table. inet_addr_type_dev_table keeps the same semantics as inet_addr_type but if the passed in device is enslaved to a VRF then the table for that VRF is used for the lookup. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/net/route.h | 3 +++ net/ipv4/af_inet.c | 13 ++++++++++++- net/ipv4/arp.c | 15 +++++++++------ net/ipv4/fib_frontend.c | 25 ++++++++++++++++++++++--- net/ipv4/fib_semantics.c | 6 ++++-- net/ipv4/icmp.c | 5 +++-- 6 files changed, 53 insertions(+), 14 deletions(-) diff --git a/include/net/route.h b/include/net/route.h index 6ba681f0b98d..6dda2c1bf8c6 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -192,6 +192,9 @@ unsigned int inet_addr_type(struct net *net, __be32 addr); unsigned int inet_addr_type_table(struct net *net, __be32 addr, int tb_id); unsigned int inet_dev_addr_type(struct net *net, const struct net_device *dev, __be32 addr); +unsigned int inet_addr_type_dev_table(struct net *net, + const struct net_device *dev, + __be32 addr); void ip_rt_multicast_event(struct in_device *); int ip_rt_ioctl(struct net *, unsigned int cmd, void __user *arg); void ip_rt_get_source(u8 *src, struct sk_buff *skb, struct rtable *rt); diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index cc4e498a0ccf..c8b855882fa5 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -119,6 +119,7 @@ #ifdef CONFIG_IP_MROUTE #include #endif +#include /* The inetsw table contains everything that inet_create needs to @@ -427,6 +428,7 @@ int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) struct net *net = sock_net(sk); unsigned short snum; int chk_addr_ret; + int tb_id = RT_TABLE_LOCAL; int err; /* If the socket has its own bind function then use it. (RAW) */ @@ -448,7 +450,16 @@ int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) goto out; } - chk_addr_ret = inet_addr_type(net, addr->sin_addr.s_addr); + if (sk->sk_bound_dev_if) { + struct net_device *dev; + + rcu_read_lock(); + dev = dev_get_by_index_rcu(net, sk->sk_bound_dev_if); + if (dev) + tb_id = vrf_dev_table_rcu(dev) ? : tb_id; + rcu_read_unlock(); + } + chk_addr_ret = inet_addr_type_table(net, addr->sin_addr.s_addr, tb_id); /* Not specified by any standard per-se, however it breaks too * many applications when removed. It is unfortunate since diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 34a308573f4b..30409b75e925 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -233,7 +233,7 @@ static int arp_constructor(struct neighbour *neigh) return -EINVAL; } - neigh->type = inet_addr_type(dev_net(dev), addr); + neigh->type = inet_addr_type_dev_table(dev_net(dev), dev, addr); parms = in_dev->arp_parms; __neigh_parms_put(neigh->parms); @@ -343,7 +343,7 @@ static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb) switch (IN_DEV_ARP_ANNOUNCE(in_dev)) { default: case 0: /* By default announce any local IP */ - if (skb && inet_addr_type(dev_net(dev), + if (skb && inet_addr_type_dev_table(dev_net(dev), dev, ip_hdr(skb)->saddr) == RTN_LOCAL) saddr = ip_hdr(skb)->saddr; break; @@ -351,7 +351,8 @@ static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb) if (!skb) break; saddr = ip_hdr(skb)->saddr; - if (inet_addr_type(dev_net(dev), saddr) == RTN_LOCAL) { + if (inet_addr_type_dev_table(dev_net(dev), dev, + saddr) == RTN_LOCAL) { /* saddr should be known to target */ if (inet_addr_onlink(in_dev, target, saddr)) break; @@ -751,7 +752,7 @@ static int arp_process(struct sock *sk, struct sk_buff *skb) /* Special case: IPv4 duplicate address detection packet (RFC2131) */ if (sip == 0) { if (arp->ar_op == htons(ARPOP_REQUEST) && - inet_addr_type(net, tip) == RTN_LOCAL && + inet_addr_type_dev_table(net, dev, tip) == RTN_LOCAL && !arp_ignore(in_dev, sip, tip)) arp_send(ARPOP_REPLY, ETH_P_ARP, sip, dev, tip, sha, dev->dev_addr, sha); @@ -811,16 +812,18 @@ static int arp_process(struct sock *sk, struct sk_buff *skb) n = __neigh_lookup(&arp_tbl, &sip, dev, 0); if (IN_DEV_ARP_ACCEPT(in_dev)) { + unsigned int addr_type = inet_addr_type_dev_table(net, dev, sip); + /* Unsolicited ARP is not accepted by default. It is possible, that this option should be enabled for some devices (strip is candidate) */ is_garp = arp->ar_op == htons(ARPOP_REQUEST) && tip == sip && - inet_addr_type(net, sip) == RTN_UNICAST; + addr_type == RTN_UNICAST; if (!n && ((arp->ar_op == htons(ARPOP_REPLY) && - inet_addr_type(net, sip) == RTN_UNICAST) || is_garp)) + addr_type == RTN_UNICAST) || is_garp)) n = __neigh_lookup(&arp_tbl, &sip, dev, 1); } diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index b11321a8e58d..c55723ec4c3e 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -260,6 +260,19 @@ unsigned int inet_dev_addr_type(struct net *net, const struct net_device *dev, } EXPORT_SYMBOL(inet_dev_addr_type); +/* inet_addr_type with dev == NULL but using the table from a dev + * if one is associated + */ +unsigned int inet_addr_type_dev_table(struct net *net, + const struct net_device *dev, + __be32 addr) +{ + int rt_table = vrf_dev_table(dev) ? : RT_TABLE_LOCAL; + + return __inet_dev_addr_type(net, NULL, addr, rt_table); +} +EXPORT_SYMBOL(inet_addr_type_dev_table); + __be32 fib_compute_spec_dst(struct sk_buff *skb) { struct net_device *dev = skb->dev; @@ -510,9 +523,12 @@ static int rtentry_to_fib_config(struct net *net, int cmd, struct rtentry *rt, addr = sk_extract_addr(&rt->rt_gateway); if (rt->rt_gateway.sa_family == AF_INET && addr) { + unsigned int addr_type; + cfg->fc_gw = addr; + addr_type = inet_addr_type_table(net, addr, cfg->fc_table); if (rt->rt_flags & RTF_GATEWAY && - inet_addr_type(net, addr) == RTN_UNICAST) + addr_type == RTN_UNICAST) cfg->fc_scope = RT_SCOPE_UNIVERSE; } @@ -984,11 +1000,14 @@ void fib_del_ifaddr(struct in_ifaddr *ifa, struct in_ifaddr *iprim) fib_magic(RTM_DELROUTE, RTN_BROADCAST, any, 32, prim); } if (!(ok & LOCAL_OK)) { + unsigned int addr_type; + fib_magic(RTM_DELROUTE, RTN_LOCAL, ifa->ifa_local, 32, prim); /* Check, that this local address finally disappeared. */ - if (gone && - inet_addr_type(dev_net(dev), ifa->ifa_local) != RTN_LOCAL) { + addr_type = inet_addr_type_dev_table(dev_net(dev), dev, + ifa->ifa_local); + if (gone && addr_type != RTN_LOCAL) { /* And the last, but not the least thing. * We must flush stray FIB entries. * diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 558e196bae0f..410ddb67221e 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -670,16 +670,18 @@ static int fib_check_nh(struct fib_config *cfg, struct fib_info *fi, struct fib_result res; if (nh->nh_flags & RTNH_F_ONLINK) { + unsigned int addr_type; if (cfg->fc_scope >= RT_SCOPE_LINK) return -EINVAL; - if (inet_addr_type(net, nh->nh_gw) != RTN_UNICAST) - return -EINVAL; dev = __dev_get_by_index(net, nh->nh_oif); if (!dev) return -ENODEV; if (!(dev->flags & IFF_UP)) return -ENETDOWN; + addr_type = inet_addr_type_dev_table(net, dev, nh->nh_gw); + if (addr_type != RTN_UNICAST) + return -EINVAL; if (!netif_carrier_ok(dev)) nh->nh_flags |= RTNH_F_LINKDOWN; nh->nh_dev = dev; diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 1164fc4ce3bc..c6f1ce149ffb 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -484,7 +484,8 @@ static struct rtable *icmp_route_lookup(struct net *net, if (err) goto relookup_failed; - if (inet_addr_type(net, fl4_dec.saddr) == RTN_LOCAL) { + if (inet_addr_type_dev_table(net, skb_in->dev, + fl4_dec.saddr) == RTN_LOCAL) { rt2 = __ip_route_output_key(net, &fl4_dec); if (IS_ERR(rt2)) err = PTR_ERR(rt2); @@ -833,7 +834,7 @@ static bool icmp_unreach(struct sk_buff *skb) */ if (!net->ipv4.sysctl_icmp_ignore_bogus_error_responses && - inet_addr_type(net, iph->daddr) == RTN_BROADCAST) { + inet_addr_type_dev_table(net, skb->dev, iph->daddr) == RTN_BROADCAST) { net_warn_ratelimited("%pI4 sent an invalid ICMP type %u, code %u error to a broadcast: %pI4 on %s\n", &ip_hdr(skb)->saddr, icmph->type, icmph->code, From 021dd3b8a142d482cb65a27bf6644e3764001460 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Thu, 13 Aug 2015 14:59:06 -0600 Subject: [PATCH 07/11] net: Add routes to the table associated with the device When a device associated with a VRF is brought up or down routes should be added to/removed from the table associated with the VRF. fib_magic defaults to using the main or local tables. Have it use the table with the device if there is one. A part of this is directing prefsrc validations to the correct table as well. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- net/ipv4/fib_frontend.c | 8 ++++---- net/ipv4/fib_semantics.c | 25 +++++++++++++++++++------ 2 files changed, 23 insertions(+), 10 deletions(-) diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index c55723ec4c3e..7fa277176c33 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -800,6 +800,7 @@ out: static void fib_magic(int cmd, int type, __be32 dst, int dst_len, struct in_ifaddr *ifa) { struct net *net = dev_net(ifa->ifa_dev->dev); + int tb_id = vrf_dev_table_rtnl(ifa->ifa_dev->dev); struct fib_table *tb; struct fib_config cfg = { .fc_protocol = RTPROT_KERNEL, @@ -814,11 +815,10 @@ static void fib_magic(int cmd, int type, __be32 dst, int dst_len, struct in_ifad }, }; - if (type == RTN_UNICAST) - tb = fib_new_table(net, RT_TABLE_MAIN); - else - tb = fib_new_table(net, RT_TABLE_LOCAL); + if (!tb_id) + tb_id = (type == RTN_UNICAST) ? RT_TABLE_MAIN : RT_TABLE_LOCAL; + tb = fib_new_table(net, tb_id); if (!tb) return; diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 410ddb67221e..85e9a8abf15c 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -838,6 +838,23 @@ __be32 fib_info_update_nh_saddr(struct net *net, struct fib_nh *nh) return nh->nh_saddr; } +static bool fib_valid_prefsrc(struct fib_config *cfg, __be32 fib_prefsrc) +{ + if (cfg->fc_type != RTN_LOCAL || !cfg->fc_dst || + fib_prefsrc != cfg->fc_dst) { + int tb_id = cfg->fc_table; + + if (tb_id == RT_TABLE_MAIN) + tb_id = RT_TABLE_LOCAL; + + if (inet_addr_type_table(cfg->fc_nlinfo.nl_net, + fib_prefsrc, tb_id) != RTN_LOCAL) { + return false; + } + } + return true; +} + struct fib_info *fib_create_info(struct fib_config *cfg) { int err; @@ -1033,12 +1050,8 @@ struct fib_info *fib_create_info(struct fib_config *cfg) fi->fib_flags |= RTNH_F_LINKDOWN; } - if (fi->fib_prefsrc) { - if (cfg->fc_type != RTN_LOCAL || !cfg->fc_dst || - fi->fib_prefsrc != cfg->fc_dst) - if (inet_addr_type(net, fi->fib_prefsrc) != RTN_LOCAL) - goto err_inval; - } + if (fi->fib_prefsrc && !fib_valid_prefsrc(cfg, fi->fib_prefsrc)) + goto err_inval; change_nexthops(fi) { fib_info_update_nh_saddr(net, nexthop_nh); From 3bfd847203c6d89532f836ad3f5b4ff4ced26dd9 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Thu, 13 Aug 2015 14:59:07 -0600 Subject: [PATCH 08/11] net: Use passed in table for nexthop lookups If a user passes in a table for new routes use that table for nexthop lookups. Specifically, this solves the case where a connected route does not exist in the main table, but only another table and then a subsequent route is added with a next hop using the connected route. ie., $ ip route ls default via 10.0.2.2 dev eth0 10.0.2.0/24 dev eth0 proto kernel scope link src 10.0.2.15 169.254.0.0/16 dev eth0 scope link metric 1003 192.168.56.0/24 dev eth1 proto kernel scope link src 192.168.56.51 $ ip route ls table 10 1.1.1.0/24 dev eth2 scope link Without this patch adding a nexthop route fails: $ ip route add table 10 2.2.2.0/24 via 1.1.1.10 RTNETLINK answers: Network is unreachable With this patch the route is added successfully. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- net/ipv4/fib_semantics.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 85e9a8abf15c..b7f1d20a9615 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -691,6 +691,7 @@ static int fib_check_nh(struct fib_config *cfg, struct fib_info *fi, } rcu_read_lock(); { + struct fib_table *tbl = NULL; struct flowi4 fl4 = { .daddr = nh->nh_gw, .flowi4_scope = cfg->fc_scope + 1, @@ -701,8 +702,16 @@ static int fib_check_nh(struct fib_config *cfg, struct fib_info *fi, /* It is not necessary, but requires a bit of thinking */ if (fl4.flowi4_scope < RT_SCOPE_LINK) fl4.flowi4_scope = RT_SCOPE_LINK; - err = fib_lookup(net, &fl4, &res, - FIB_LOOKUP_IGNORE_LINKSTATE); + + if (cfg->fc_table) + tbl = fib_get_table(net, cfg->fc_table); + + if (tbl) + err = fib_table_lookup(tbl, &fl4, &res, + FIB_LOOKUP_IGNORE_LINKSTATE); + else + err = fib_lookup(net, &fl4, &res, + FIB_LOOKUP_IGNORE_LINKSTATE); if (err) { rcu_read_unlock(); return err; From f7ba868b71bc858cf06de11fc8150c4552cfad81 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Thu, 13 Aug 2015 14:59:08 -0600 Subject: [PATCH 09/11] net: Use VRF index for oif in ip_send_unicast_reply If output device is not specified use VRF device if input device is enslaved. This is needed to ensure tcp acks and resets go out VRF device. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- net/ipv4/ip_output.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 6bf89a6312bc..0138fada0951 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -1542,6 +1542,7 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb, struct net *net = sock_net(sk); struct sk_buff *nskb; int err; + int oif; if (__ip_options_echo(&replyopts.opt.opt, skb, sopt)) return; @@ -1559,7 +1560,11 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb, daddr = replyopts.opt.opt.faddr; } - flowi4_init_output(&fl4, arg->bound_dev_if, + oif = arg->bound_dev_if; + if (!oif && netif_index_is_vrf(net, skb->skb_iif)) + oif = skb->skb_iif; + + flowi4_init_output(&fl4, oif, IP4_REPLY_MARK(net, skb->mark), RT_TOS(arg->tos), RT_SCOPE_UNIVERSE, ip_hdr(skb)->protocol, From 9972f134a273d6dc52d912a3513fa06b426de9b4 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Thu, 13 Aug 2015 14:59:09 -0600 Subject: [PATCH 10/11] net: frags: Add VRF device index to cache and lookup Fragmentation cache uses information from the IP header to reassemble packets. That information can be duplicated across VRFs -- same source and destination addresses, protocol and id. Handle fragmentation with VRFs by adding the VRF device index to entries in the cache and the lookup arg. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- net/ipv4/ip_fragment.c | 18 +++++++++++++----- 1 file changed, 13 insertions(+), 5 deletions(-) diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index d96722ae8979..15762e758861 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -48,6 +48,7 @@ #include #include #include +#include /* NOTE. Logic of IP defragmentation is parallel to corresponding IPv6 * code now. If you change something here, _PLEASE_ update ipv6/reassembly.c @@ -77,6 +78,7 @@ struct ipq { u8 ecn; /* RFC3168 support */ u16 max_df_size; /* largest frag with DF set seen */ int iif; + int vif; /* VRF device index */ unsigned int rid; struct inet_peer *peer; }; @@ -99,6 +101,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev, struct ip4_create_arg { struct iphdr *iph; u32 user; + int vif; }; static unsigned int ipqhashfn(__be16 id, __be32 saddr, __be32 daddr, u8 prot) @@ -127,7 +130,8 @@ static bool ip4_frag_match(const struct inet_frag_queue *q, const void *a) qp->saddr == arg->iph->saddr && qp->daddr == arg->iph->daddr && qp->protocol == arg->iph->protocol && - qp->user == arg->user; + qp->user == arg->user && + qp->vif == arg->vif; } static void ip4_frag_init(struct inet_frag_queue *q, const void *a) @@ -144,6 +148,7 @@ static void ip4_frag_init(struct inet_frag_queue *q, const void *a) qp->ecn = ip4_frag_ecn(arg->iph->tos); qp->saddr = arg->iph->saddr; qp->daddr = arg->iph->daddr; + qp->vif = arg->vif; qp->user = arg->user; qp->peer = sysctl_ipfrag_max_dist ? inet_getpeer_v4(net->ipv4.peers, arg->iph->saddr, 1) : NULL; @@ -244,7 +249,8 @@ out: /* Find the correct entry in the "incomplete datagrams" queue for * this IP datagram, and create new one, if nothing is found. */ -static struct ipq *ip_find(struct net *net, struct iphdr *iph, u32 user) +static struct ipq *ip_find(struct net *net, struct iphdr *iph, + u32 user, int vif) { struct inet_frag_queue *q; struct ip4_create_arg arg; @@ -252,6 +258,7 @@ static struct ipq *ip_find(struct net *net, struct iphdr *iph, u32 user) arg.iph = iph; arg.user = user; + arg.vif = vif; hash = ipqhashfn(iph->id, iph->saddr, iph->daddr, iph->protocol); @@ -648,14 +655,15 @@ out_fail: /* Process an incoming IP datagram fragment. */ int ip_defrag(struct sk_buff *skb, u32 user) { + struct net_device *dev = skb->dev ? : skb_dst(skb)->dev; + int vif = vrf_master_ifindex_rcu(dev); + struct net *net = dev_net(dev); struct ipq *qp; - struct net *net; - net = skb->dev ? dev_net(skb->dev) : dev_net(skb_dst(skb)->dev); IP_INC_STATS_BH(net, IPSTATS_MIB_REASMREQDS); /* Lookup (or create) queue header */ - qp = ip_find(net, ip_hdr(skb), user); + qp = ip_find(net, ip_hdr(skb), user, vif); if (qp) { int ret; From 193125dbd8eb292d88feb201f030889b488b0a02 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Thu, 13 Aug 2015 14:59:10 -0600 Subject: [PATCH 11/11] net: Introduce VRF device driver This driver borrows heavily from IPvlan and teaming drivers. Routing domains (VRF-lite) are created by instantiating a VRF master device with an associated table and enslaving all routed interfaces that participate in the domain. As part of the enslavement, all connected routes for the enslaved devices are moved to the table associated with the VRF device. Outgoing sockets must bind to the VRF device to function. Standard FIB rules bind the VRF device to tables and regular fib rule processing is followed. Routed traffic through the box, is forwarded by using the VRF device as the IIF and following the IIF rule to a table that is mated with the VRF. Example: Create vrf 1: ip link add vrf1 type vrf table 5 ip rule add iif vrf1 table 5 ip rule add oif vrf1 table 5 ip route add table 5 prohibit default ip link set vrf1 up Add interface to vrf 1: ip link set eth1 master vrf1 Signed-off-by: Shrijeet Mukherjee Signed-off-by: David Ahern Signed-off-by: David S. Miller --- drivers/net/Kconfig | 7 + drivers/net/Makefile | 1 + drivers/net/vrf.c | 685 +++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 693 insertions(+) create mode 100644 drivers/net/vrf.c diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig index c18f9e62a9fa..e58468b02987 100644 --- a/drivers/net/Kconfig +++ b/drivers/net/Kconfig @@ -297,6 +297,13 @@ config NLMON diagnostics, etc. This is mostly intended for developers or support to debug netlink issues. If unsure, say N. +config NET_VRF + tristate "Virtual Routing and Forwarding (Lite)" + depends on IP_MULTIPLE_TABLES && IPV6_MULTIPLE_TABLES + ---help--- + This option enables the support for mapping interfaces into VRF's. The + support enables VRF devices. + endif # NET_CORE config SUNGEM_PHY diff --git a/drivers/net/Makefile b/drivers/net/Makefile index c12cb22478a7..ca16dd689b36 100644 --- a/drivers/net/Makefile +++ b/drivers/net/Makefile @@ -25,6 +25,7 @@ obj-$(CONFIG_VIRTIO_NET) += virtio_net.o obj-$(CONFIG_VXLAN) += vxlan.o obj-$(CONFIG_GENEVE) += geneve.o obj-$(CONFIG_NLMON) += nlmon.o +obj-$(CONFIG_NET_VRF) += vrf.o # # Networking Drivers diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c new file mode 100644 index 000000000000..95097cb79354 --- /dev/null +++ b/drivers/net/vrf.c @@ -0,0 +1,685 @@ +/* + * vrf.c: device driver to encapsulate a VRF space + * + * Copyright (c) 2015 Cumulus Networks. All rights reserved. + * Copyright (c) 2015 Shrijeet Mukherjee + * Copyright (c) 2015 David Ahern + * + * Based on dummy, team and ipvlan drivers + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include +#include +#include + +#define DRV_NAME "vrf" +#define DRV_VERSION "1.0" + +#define vrf_is_slave(dev) ((dev)->flags & IFF_SLAVE) + +#define vrf_master_get_rcu(dev) \ + ((struct net_device *)rcu_dereference(dev->rx_handler_data)) + +struct pcpu_dstats { + u64 tx_pkts; + u64 tx_bytes; + u64 tx_drps; + u64 rx_pkts; + u64 rx_bytes; + struct u64_stats_sync syncp; +}; + +static struct dst_entry *vrf_ip_check(struct dst_entry *dst, u32 cookie) +{ + return dst; +} + +static int vrf_ip_local_out(struct sk_buff *skb) +{ + return ip_local_out(skb); +} + +static unsigned int vrf_v4_mtu(const struct dst_entry *dst) +{ + /* TO-DO: return max ethernet size? */ + return dst->dev->mtu; +} + +static void vrf_dst_destroy(struct dst_entry *dst) +{ + /* our dst lives forever - or until the device is closed */ +} + +static unsigned int vrf_default_advmss(const struct dst_entry *dst) +{ + return 65535 - 40; +} + +static struct dst_ops vrf_dst_ops = { + .family = AF_INET, + .local_out = vrf_ip_local_out, + .check = vrf_ip_check, + .mtu = vrf_v4_mtu, + .destroy = vrf_dst_destroy, + .default_advmss = vrf_default_advmss, +}; + +static bool is_ip_rx_frame(struct sk_buff *skb) +{ + switch (skb->protocol) { + case htons(ETH_P_IP): + case htons(ETH_P_IPV6): + return true; + } + return false; +} + +/* note: already called with rcu_read_lock */ +static rx_handler_result_t vrf_handle_frame(struct sk_buff **pskb) +{ + struct sk_buff *skb = *pskb; + + if (is_ip_rx_frame(skb)) { + struct net_device *dev = vrf_master_get_rcu(skb->dev); + struct pcpu_dstats *dstats = this_cpu_ptr(dev->dstats); + + u64_stats_update_begin(&dstats->syncp); + dstats->rx_pkts++; + dstats->rx_bytes += skb->len; + u64_stats_update_end(&dstats->syncp); + + skb->dev = dev; + + return RX_HANDLER_ANOTHER; + } + return RX_HANDLER_PASS; +} + +static struct rtnl_link_stats64 *vrf_get_stats64(struct net_device *dev, + struct rtnl_link_stats64 *stats) +{ + int i; + + for_each_possible_cpu(i) { + const struct pcpu_dstats *dstats; + u64 tbytes, tpkts, tdrops, rbytes, rpkts; + unsigned int start; + + dstats = per_cpu_ptr(dev->dstats, i); + do { + start = u64_stats_fetch_begin_irq(&dstats->syncp); + tbytes = dstats->tx_bytes; + tpkts = dstats->tx_pkts; + tdrops = dstats->tx_drps; + rbytes = dstats->rx_bytes; + rpkts = dstats->rx_pkts; + } while (u64_stats_fetch_retry_irq(&dstats->syncp, start)); + stats->tx_bytes += tbytes; + stats->tx_packets += tpkts; + stats->tx_dropped += tdrops; + stats->rx_bytes += rbytes; + stats->rx_packets += rpkts; + } + return stats; +} + +static netdev_tx_t vrf_process_v6_outbound(struct sk_buff *skb, + struct net_device *dev) +{ + return 0; +} + +static int vrf_send_v4_prep(struct sk_buff *skb, struct flowi4 *fl4, + struct net_device *vrf_dev) +{ + struct rtable *rt; + int err = 1; + + rt = ip_route_output_flow(dev_net(vrf_dev), fl4, NULL); + if (IS_ERR(rt)) + goto out; + + /* TO-DO: what about broadcast ? */ + if (rt->rt_type != RTN_UNICAST && rt->rt_type != RTN_LOCAL) { + ip_rt_put(rt); + goto out; + } + + skb_dst_drop(skb); + skb_dst_set(skb, &rt->dst); + err = 0; +out: + return err; +} + +static netdev_tx_t vrf_process_v4_outbound(struct sk_buff *skb, + struct net_device *vrf_dev) +{ + struct iphdr *ip4h = ip_hdr(skb); + int ret = NET_XMIT_DROP; + struct flowi4 fl4 = { + /* needed to match OIF rule */ + .flowi4_oif = vrf_dev->ifindex, + .flowi4_iif = LOOPBACK_IFINDEX, + .flowi4_tos = RT_TOS(ip4h->tos), + .flowi4_flags = FLOWI_FLAG_ANYSRC | FLOWI_FLAG_VRFSRC, + .daddr = ip4h->daddr, + }; + + if (vrf_send_v4_prep(skb, &fl4, vrf_dev)) + goto err; + + if (!ip4h->saddr) { + ip4h->saddr = inet_select_addr(skb_dst(skb)->dev, 0, + RT_SCOPE_LINK); + } + + ret = ip_local_out(skb); + if (unlikely(net_xmit_eval(ret))) + vrf_dev->stats.tx_errors++; + else + ret = NET_XMIT_SUCCESS; + +out: + return ret; +err: + vrf_dev->stats.tx_errors++; + kfree_skb(skb); + goto out; +} + +static netdev_tx_t is_ip_tx_frame(struct sk_buff *skb, struct net_device *dev) +{ + switch (skb->protocol) { + case htons(ETH_P_IP): + return vrf_process_v4_outbound(skb, dev); + case htons(ETH_P_IPV6): + return vrf_process_v6_outbound(skb, dev); + default: + return NET_XMIT_DROP; + } +} + +static netdev_tx_t vrf_xmit(struct sk_buff *skb, struct net_device *dev) +{ + netdev_tx_t ret = is_ip_tx_frame(skb, dev); + + if (likely(ret == NET_XMIT_SUCCESS || ret == NET_XMIT_CN)) { + struct pcpu_dstats *dstats = this_cpu_ptr(dev->dstats); + + u64_stats_update_begin(&dstats->syncp); + dstats->tx_pkts++; + dstats->tx_bytes += skb->len; + u64_stats_update_end(&dstats->syncp); + } else { + this_cpu_inc(dev->dstats->tx_drps); + } + + return ret; +} + +static netdev_tx_t vrf_finish(struct sock *sk, struct sk_buff *skb) +{ + return dev_queue_xmit(skb); +} + +static int vrf_output(struct sock *sk, struct sk_buff *skb) +{ + struct net_device *dev = skb_dst(skb)->dev; + + IP_UPD_PO_STATS(dev_net(dev), IPSTATS_MIB_OUT, skb->len); + + skb->dev = dev; + skb->protocol = htons(ETH_P_IP); + + return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, sk, skb, + NULL, dev, + vrf_finish, + !(IPCB(skb)->flags & IPSKB_REROUTED)); +} + +static void vrf_rtable_destroy(struct net_vrf *vrf) +{ + struct dst_entry *dst = (struct dst_entry *)vrf->rth; + + if (dst) + dst_destroy(dst); + vrf->rth = NULL; +} + +static struct rtable *vrf_rtable_create(struct net_device *dev) +{ + struct rtable *rth; + + rth = dst_alloc(&vrf_dst_ops, dev, 2, + DST_OBSOLETE_NONE, + (DST_HOST | DST_NOPOLICY | DST_NOXFRM)); + if (rth) { + rth->dst.output = vrf_output; + rth->rt_genid = rt_genid_ipv4(dev_net(dev)); + rth->rt_flags = 0; + rth->rt_type = RTN_UNICAST; + rth->rt_is_input = 0; + rth->rt_iif = 0; + rth->rt_pmtu = 0; + rth->rt_gateway = 0; + rth->rt_uses_gateway = 0; + INIT_LIST_HEAD(&rth->rt_uncached); + rth->rt_uncached_list = NULL; + rth->rt_lwtstate = NULL; + } + + return rth; +} + +/**************************** device handling ********************/ + +/* cycle interface to flush neighbor cache and move routes across tables */ +static void cycle_netdev(struct net_device *dev) +{ + unsigned int flags = dev->flags; + int ret; + + if (!netif_running(dev)) + return; + + ret = dev_change_flags(dev, flags & ~IFF_UP); + if (ret >= 0) + ret = dev_change_flags(dev, flags); + + if (ret < 0) { + netdev_err(dev, + "Failed to cycle device %s; route tables might be wrong!\n", + dev->name); + } +} + +static struct slave *__vrf_find_slave_dev(struct slave_queue *queue, + struct net_device *dev) +{ + struct list_head *head = &queue->all_slaves; + struct slave *slave; + + list_for_each_entry(slave, head, list) { + if (slave->dev == dev) + return slave; + } + + return NULL; +} + +/* inverse of __vrf_insert_slave */ +static void __vrf_remove_slave(struct slave_queue *queue, struct slave *slave) +{ + dev_put(slave->dev); + list_del(&slave->list); + queue->num_slaves--; +} + +static void __vrf_insert_slave(struct slave_queue *queue, struct slave *slave) +{ + dev_hold(slave->dev); + list_add(&slave->list, &queue->all_slaves); + queue->num_slaves++; +} + +static int do_vrf_add_slave(struct net_device *dev, struct net_device *port_dev) +{ + struct net_vrf_dev *vrf_ptr = kmalloc(sizeof(*vrf_ptr), GFP_KERNEL); + struct slave *slave = kzalloc(sizeof(*slave), GFP_KERNEL); + struct slave *duplicate_slave; + struct net_vrf *vrf = netdev_priv(dev); + struct slave_queue *queue = &vrf->queue; + int ret = -ENOMEM; + + if (!slave || !vrf_ptr) + goto out_fail; + + slave->dev = port_dev; + + vrf_ptr->ifindex = dev->ifindex; + vrf_ptr->tb_id = vrf->tb_id; + + duplicate_slave = __vrf_find_slave_dev(queue, port_dev); + if (duplicate_slave) { + ret = -EBUSY; + goto out_fail; + } + + __vrf_insert_slave(queue, slave); + + /* register the packet handler for slave ports */ + ret = netdev_rx_handler_register(port_dev, vrf_handle_frame, dev); + if (ret) { + netdev_err(port_dev, + "Device %s failed to register rx_handler\n", + port_dev->name); + goto out_remove; + } + + ret = netdev_master_upper_dev_link(port_dev, dev); + if (ret < 0) + goto out_unregister; + + port_dev->flags |= IFF_SLAVE; + + rcu_assign_pointer(port_dev->vrf_ptr, vrf_ptr); + cycle_netdev(port_dev); + + return 0; + +out_unregister: + netdev_rx_handler_unregister(port_dev); +out_remove: + __vrf_remove_slave(queue, slave); +out_fail: + kfree(vrf_ptr); + kfree(slave); + return ret; +} + +static int vrf_add_slave(struct net_device *dev, struct net_device *port_dev) +{ + if (!netif_is_vrf(dev) || netif_is_vrf(port_dev) || + vrf_is_slave(port_dev)) + return -EINVAL; + + return do_vrf_add_slave(dev, port_dev); +} + +/* inverse of do_vrf_add_slave */ +static int do_vrf_del_slave(struct net_device *dev, struct net_device *port_dev) +{ + struct net_vrf_dev *vrf_ptr = rtnl_dereference(port_dev->vrf_ptr); + struct net_vrf *vrf = netdev_priv(dev); + struct slave_queue *queue = &vrf->queue; + struct slave *slave; + + RCU_INIT_POINTER(port_dev->vrf_ptr, NULL); + + netdev_upper_dev_unlink(port_dev, dev); + port_dev->flags &= ~IFF_SLAVE; + + netdev_rx_handler_unregister(port_dev); + + /* after netdev_rx_handler_unregister for synchronize_rcu */ + kfree(vrf_ptr); + + cycle_netdev(port_dev); + + slave = __vrf_find_slave_dev(queue, port_dev); + if (slave) + __vrf_remove_slave(queue, slave); + + kfree(slave); + + return 0; +} + +static int vrf_del_slave(struct net_device *dev, struct net_device *port_dev) +{ + if (!netif_is_vrf(dev)) + return -EINVAL; + + return do_vrf_del_slave(dev, port_dev); +} + +static void vrf_dev_uninit(struct net_device *dev) +{ + struct net_vrf *vrf = netdev_priv(dev); + struct slave_queue *queue = &vrf->queue; + struct list_head *head = &queue->all_slaves; + struct slave *slave, *next; + + vrf_rtable_destroy(vrf); + + list_for_each_entry_safe(slave, next, head, list) + vrf_del_slave(dev, slave->dev); + + if (dev->dstats) + free_percpu(dev->dstats); + dev->dstats = NULL; +} + +static int vrf_dev_init(struct net_device *dev) +{ + struct net_vrf *vrf = netdev_priv(dev); + + INIT_LIST_HEAD(&vrf->queue.all_slaves); + + dev->dstats = netdev_alloc_pcpu_stats(struct pcpu_dstats); + if (!dev->dstats) + goto out_nomem; + + /* create the default dst which points back to us */ + vrf->rth = vrf_rtable_create(dev); + if (!vrf->rth) + goto out_stats; + + dev->flags = IFF_MASTER | IFF_NOARP; + + return 0; + +out_stats: + free_percpu(dev->dstats); + dev->dstats = NULL; +out_nomem: + return -ENOMEM; +} + +static const struct net_device_ops vrf_netdev_ops = { + .ndo_init = vrf_dev_init, + .ndo_uninit = vrf_dev_uninit, + .ndo_start_xmit = vrf_xmit, + .ndo_get_stats64 = vrf_get_stats64, + .ndo_add_slave = vrf_add_slave, + .ndo_del_slave = vrf_del_slave, +}; + +static void vrf_get_drvinfo(struct net_device *dev, + struct ethtool_drvinfo *info) +{ + strlcpy(info->driver, DRV_NAME, sizeof(info->driver)); + strlcpy(info->version, DRV_VERSION, sizeof(info->version)); +} + +static const struct ethtool_ops vrf_ethtool_ops = { + .get_drvinfo = vrf_get_drvinfo, +}; + +static void vrf_setup(struct net_device *dev) +{ + ether_setup(dev); + + /* Initialize the device structure. */ + dev->netdev_ops = &vrf_netdev_ops; + dev->ethtool_ops = &vrf_ethtool_ops; + dev->destructor = free_netdev; + + /* Fill in device structure with ethernet-generic values. */ + eth_hw_addr_random(dev); + + /* don't acquire vrf device's netif_tx_lock when transmitting */ + dev->features |= NETIF_F_LLTX; + + /* don't allow vrf devices to change network namespaces. */ + dev->features |= NETIF_F_NETNS_LOCAL; +} + +static int vrf_validate(struct nlattr *tb[], struct nlattr *data[]) +{ + if (tb[IFLA_ADDRESS]) { + if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN) + return -EINVAL; + if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS]))) + return -EADDRNOTAVAIL; + } + return 0; +} + +static void vrf_dellink(struct net_device *dev, struct list_head *head) +{ + struct net_vrf_dev *vrf_ptr = rtnl_dereference(dev->vrf_ptr); + + RCU_INIT_POINTER(dev->vrf_ptr, NULL); + kfree_rcu(vrf_ptr, rcu); + unregister_netdevice_queue(dev, head); +} + +static int vrf_newlink(struct net *src_net, struct net_device *dev, + struct nlattr *tb[], struct nlattr *data[]) +{ + struct net_vrf *vrf = netdev_priv(dev); + struct net_vrf_dev *vrf_ptr; + int err; + + if (!data || !data[IFLA_VRF_TABLE]) + return -EINVAL; + + vrf->tb_id = nla_get_u32(data[IFLA_VRF_TABLE]); + + dev->priv_flags |= IFF_VRF_MASTER; + + err = -ENOMEM; + vrf_ptr = kmalloc(sizeof(*dev->vrf_ptr), GFP_KERNEL); + if (!vrf_ptr) + goto out_fail; + + vrf_ptr->ifindex = dev->ifindex; + vrf_ptr->tb_id = vrf->tb_id; + + err = register_netdevice(dev); + if (err < 0) + goto out_fail; + + rcu_assign_pointer(dev->vrf_ptr, vrf_ptr); + + return 0; + +out_fail: + kfree(vrf_ptr); + free_netdev(dev); + return err; +} + +static size_t vrf_nl_getsize(const struct net_device *dev) +{ + return nla_total_size(sizeof(u32)); /* IFLA_VRF_TABLE */ +} + +static int vrf_fillinfo(struct sk_buff *skb, + const struct net_device *dev) +{ + struct net_vrf *vrf = netdev_priv(dev); + + return nla_put_u32(skb, IFLA_VRF_TABLE, vrf->tb_id); +} + +static const struct nla_policy vrf_nl_policy[IFLA_VRF_MAX + 1] = { + [IFLA_VRF_TABLE] = { .type = NLA_U32 }, +}; + +static struct rtnl_link_ops vrf_link_ops __read_mostly = { + .kind = DRV_NAME, + .priv_size = sizeof(struct net_vrf), + + .get_size = vrf_nl_getsize, + .policy = vrf_nl_policy, + .validate = vrf_validate, + .fill_info = vrf_fillinfo, + + .newlink = vrf_newlink, + .dellink = vrf_dellink, + .setup = vrf_setup, + .maxtype = IFLA_VRF_MAX, +}; + +static int vrf_device_event(struct notifier_block *unused, + unsigned long event, void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + + /* only care about unregister events to drop slave references */ + if (event == NETDEV_UNREGISTER) { + struct net_vrf_dev *vrf_ptr = rtnl_dereference(dev->vrf_ptr); + struct net_device *vrf_dev; + + if (!vrf_ptr || netif_is_vrf(dev)) + goto out; + + vrf_dev = __dev_get_by_index(dev_net(dev), vrf_ptr->ifindex); + if (vrf_dev) + vrf_del_slave(vrf_dev, dev); + } +out: + return NOTIFY_DONE; +} + +static struct notifier_block vrf_notifier_block __read_mostly = { + .notifier_call = vrf_device_event, +}; + +static int __init vrf_init_module(void) +{ + int rc; + + vrf_dst_ops.kmem_cachep = + kmem_cache_create("vrf_ip_dst_cache", + sizeof(struct rtable), 0, + SLAB_HWCACHE_ALIGN | SLAB_PANIC, + NULL); + + if (!vrf_dst_ops.kmem_cachep) + return -ENOMEM; + + register_netdevice_notifier(&vrf_notifier_block); + + rc = rtnl_link_register(&vrf_link_ops); + if (rc < 0) + goto error; + + return 0; + +error: + unregister_netdevice_notifier(&vrf_notifier_block); + kmem_cache_destroy(vrf_dst_ops.kmem_cachep); + return rc; +} + +static void __exit vrf_cleanup_module(void) +{ + rtnl_link_unregister(&vrf_link_ops); + unregister_netdevice_notifier(&vrf_notifier_block); + kmem_cache_destroy(vrf_dst_ops.kmem_cachep); +} + +module_init(vrf_init_module); +module_exit(vrf_cleanup_module); +MODULE_AUTHOR("Shrijeet Mukherjee, David Ahern"); +MODULE_DESCRIPTION("Device driver to instantiate VRF domains"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS_RTNL_LINK(DRV_NAME); +MODULE_VERSION(DRV_VERSION);