summaryrefslogtreecommitdiffstats
path: root/drivers/net/ipvlan
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/net/ipvlan')
-rw-r--r--drivers/net/ipvlan/Makefile10
-rw-r--r--drivers/net/ipvlan/ipvlan.h211
-rw-r--r--drivers/net/ipvlan/ipvlan_core.c773
-rw-r--r--drivers/net/ipvlan/ipvlan_l3s.c228
-rw-r--r--drivers/net/ipvlan/ipvlan_main.c1084
-rw-r--r--drivers/net/ipvlan/ipvtap.c241
6 files changed, 2547 insertions, 0 deletions
diff --git a/drivers/net/ipvlan/Makefile b/drivers/net/ipvlan/Makefile
new file mode 100644
index 000000000..2020e9ded
--- /dev/null
+++ b/drivers/net/ipvlan/Makefile
@@ -0,0 +1,10 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# Makefile for the Ethernet Ipvlan driver
+#
+
+obj-$(CONFIG_IPVLAN) += ipvlan.o
+obj-$(CONFIG_IPVTAP) += ipvtap.o
+
+ipvlan-objs-$(CONFIG_IPVLAN_L3S) += ipvlan_l3s.o
+ipvlan-objs := ipvlan_core.o ipvlan_main.o $(ipvlan-objs-y)
diff --git a/drivers/net/ipvlan/ipvlan.h b/drivers/net/ipvlan/ipvlan.h
new file mode 100644
index 000000000..025e0c19e
--- /dev/null
+++ b/drivers/net/ipvlan/ipvlan.h
@@ -0,0 +1,211 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (c) 2014 Mahesh Bandewar <maheshb@google.com>
+ */
+#ifndef __IPVLAN_H
+#define __IPVLAN_H
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/rculist.h>
+#include <linux/notifier.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/if_arp.h>
+#include <linux/if_link.h>
+#include <linux/if_vlan.h>
+#include <linux/ip.h>
+#include <linux/inetdevice.h>
+#include <linux/netfilter.h>
+#include <net/ip.h>
+#include <net/ip6_route.h>
+#include <net/netns/generic.h>
+#include <net/rtnetlink.h>
+#include <net/route.h>
+#include <net/addrconf.h>
+#include <net/l3mdev.h>
+
+#define IPVLAN_DRV "ipvlan"
+#define IPV_DRV_VER "0.1"
+
+#define IPVLAN_HASH_SIZE (1 << BITS_PER_BYTE)
+#define IPVLAN_HASH_MASK (IPVLAN_HASH_SIZE - 1)
+
+#define IPVLAN_MAC_FILTER_BITS 8
+#define IPVLAN_MAC_FILTER_SIZE (1 << IPVLAN_MAC_FILTER_BITS)
+#define IPVLAN_MAC_FILTER_MASK (IPVLAN_MAC_FILTER_SIZE - 1)
+
+#define IPVLAN_QBACKLOG_LIMIT 1000
+
+typedef enum {
+ IPVL_IPV6 = 0,
+ IPVL_ICMPV6,
+ IPVL_IPV4,
+ IPVL_ARP,
+} ipvl_hdr_type;
+
+struct ipvl_pcpu_stats {
+ u64_stats_t rx_pkts;
+ u64_stats_t rx_bytes;
+ u64_stats_t rx_mcast;
+ u64_stats_t tx_pkts;
+ u64_stats_t tx_bytes;
+ struct u64_stats_sync syncp;
+ u32 rx_errs;
+ u32 tx_drps;
+};
+
+struct ipvl_port;
+
+struct ipvl_dev {
+ struct net_device *dev;
+ struct list_head pnode;
+ struct ipvl_port *port;
+ struct net_device *phy_dev;
+ struct list_head addrs;
+ struct ipvl_pcpu_stats __percpu *pcpu_stats;
+ DECLARE_BITMAP(mac_filters, IPVLAN_MAC_FILTER_SIZE);
+ netdev_features_t sfeatures;
+ u32 msg_enable;
+ spinlock_t addrs_lock;
+};
+
+struct ipvl_addr {
+ struct ipvl_dev *master; /* Back pointer to master */
+ union {
+ struct in6_addr ip6; /* IPv6 address on logical interface */
+ struct in_addr ip4; /* IPv4 address on logical interface */
+ } ipu;
+#define ip6addr ipu.ip6
+#define ip4addr ipu.ip4
+ struct hlist_node hlnode; /* Hash-table linkage */
+ struct list_head anode; /* logical-interface linkage */
+ ipvl_hdr_type atype;
+ struct rcu_head rcu;
+};
+
+struct ipvl_port {
+ struct net_device *dev;
+ possible_net_t pnet;
+ struct hlist_head hlhead[IPVLAN_HASH_SIZE];
+ struct list_head ipvlans;
+ u16 mode;
+ u16 flags;
+ u16 dev_id_start;
+ struct work_struct wq;
+ struct sk_buff_head backlog;
+ int count;
+ struct ida ida;
+ netdevice_tracker dev_tracker;
+};
+
+struct ipvl_skb_cb {
+ bool tx_pkt;
+};
+#define IPVL_SKB_CB(_skb) ((struct ipvl_skb_cb *)&((_skb)->cb[0]))
+
+static inline struct ipvl_port *ipvlan_port_get_rcu(const struct net_device *d)
+{
+ return rcu_dereference(d->rx_handler_data);
+}
+
+static inline struct ipvl_port *ipvlan_port_get_rcu_bh(const struct net_device *d)
+{
+ return rcu_dereference_bh(d->rx_handler_data);
+}
+
+static inline struct ipvl_port *ipvlan_port_get_rtnl(const struct net_device *d)
+{
+ return rtnl_dereference(d->rx_handler_data);
+}
+
+static inline bool ipvlan_is_private(const struct ipvl_port *port)
+{
+ return !!(port->flags & IPVLAN_F_PRIVATE);
+}
+
+static inline void ipvlan_mark_private(struct ipvl_port *port)
+{
+ port->flags |= IPVLAN_F_PRIVATE;
+}
+
+static inline void ipvlan_clear_private(struct ipvl_port *port)
+{
+ port->flags &= ~IPVLAN_F_PRIVATE;
+}
+
+static inline bool ipvlan_is_vepa(const struct ipvl_port *port)
+{
+ return !!(port->flags & IPVLAN_F_VEPA);
+}
+
+static inline void ipvlan_mark_vepa(struct ipvl_port *port)
+{
+ port->flags |= IPVLAN_F_VEPA;
+}
+
+static inline void ipvlan_clear_vepa(struct ipvl_port *port)
+{
+ port->flags &= ~IPVLAN_F_VEPA;
+}
+
+void ipvlan_init_secret(void);
+unsigned int ipvlan_mac_hash(const unsigned char *addr);
+rx_handler_result_t ipvlan_handle_frame(struct sk_buff **pskb);
+void ipvlan_process_multicast(struct work_struct *work);
+int ipvlan_queue_xmit(struct sk_buff *skb, struct net_device *dev);
+void ipvlan_ht_addr_add(struct ipvl_dev *ipvlan, struct ipvl_addr *addr);
+struct ipvl_addr *ipvlan_find_addr(const struct ipvl_dev *ipvlan,
+ const void *iaddr, bool is_v6);
+bool ipvlan_addr_busy(struct ipvl_port *port, void *iaddr, bool is_v6);
+void ipvlan_ht_addr_del(struct ipvl_addr *addr);
+struct ipvl_addr *ipvlan_addr_lookup(struct ipvl_port *port, void *lyr3h,
+ int addr_type, bool use_dest);
+void *ipvlan_get_L3_hdr(struct ipvl_port *port, struct sk_buff *skb, int *type);
+void ipvlan_count_rx(const struct ipvl_dev *ipvlan,
+ unsigned int len, bool success, bool mcast);
+int ipvlan_link_new(struct net *src_net, struct net_device *dev,
+ struct nlattr *tb[], struct nlattr *data[],
+ struct netlink_ext_ack *extack);
+void ipvlan_link_delete(struct net_device *dev, struct list_head *head);
+void ipvlan_link_setup(struct net_device *dev);
+int ipvlan_link_register(struct rtnl_link_ops *ops);
+#ifdef CONFIG_IPVLAN_L3S
+int ipvlan_l3s_register(struct ipvl_port *port);
+void ipvlan_l3s_unregister(struct ipvl_port *port);
+void ipvlan_migrate_l3s_hook(struct net *oldnet, struct net *newnet);
+int ipvlan_l3s_init(void);
+void ipvlan_l3s_cleanup(void);
+#else
+static inline int ipvlan_l3s_register(struct ipvl_port *port)
+{
+ return -ENOTSUPP;
+}
+
+static inline void ipvlan_l3s_unregister(struct ipvl_port *port)
+{
+}
+
+static inline void ipvlan_migrate_l3s_hook(struct net *oldnet,
+ struct net *newnet)
+{
+}
+
+static inline int ipvlan_l3s_init(void)
+{
+ return 0;
+}
+
+static inline void ipvlan_l3s_cleanup(void)
+{
+}
+#endif /* CONFIG_IPVLAN_L3S */
+
+static inline bool netif_is_ipvlan_port(const struct net_device *dev)
+{
+ return rcu_access_pointer(dev->rx_handler) == ipvlan_handle_frame;
+}
+
+#endif /* __IPVLAN_H */
diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c
new file mode 100644
index 000000000..d447f3076
--- /dev/null
+++ b/drivers/net/ipvlan/ipvlan_core.c
@@ -0,0 +1,773 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* Copyright (c) 2014 Mahesh Bandewar <maheshb@google.com>
+ */
+
+#include "ipvlan.h"
+
+static u32 ipvlan_jhash_secret __read_mostly;
+
+void ipvlan_init_secret(void)
+{
+ net_get_random_once(&ipvlan_jhash_secret, sizeof(ipvlan_jhash_secret));
+}
+
+void ipvlan_count_rx(const struct ipvl_dev *ipvlan,
+ unsigned int len, bool success, bool mcast)
+{
+ if (likely(success)) {
+ struct ipvl_pcpu_stats *pcptr;
+
+ pcptr = this_cpu_ptr(ipvlan->pcpu_stats);
+ u64_stats_update_begin(&pcptr->syncp);
+ u64_stats_inc(&pcptr->rx_pkts);
+ u64_stats_add(&pcptr->rx_bytes, len);
+ if (mcast)
+ u64_stats_inc(&pcptr->rx_mcast);
+ u64_stats_update_end(&pcptr->syncp);
+ } else {
+ this_cpu_inc(ipvlan->pcpu_stats->rx_errs);
+ }
+}
+EXPORT_SYMBOL_GPL(ipvlan_count_rx);
+
+#if IS_ENABLED(CONFIG_IPV6)
+static u8 ipvlan_get_v6_hash(const void *iaddr)
+{
+ const struct in6_addr *ip6_addr = iaddr;
+
+ return __ipv6_addr_jhash(ip6_addr, ipvlan_jhash_secret) &
+ IPVLAN_HASH_MASK;
+}
+#else
+static u8 ipvlan_get_v6_hash(const void *iaddr)
+{
+ return 0;
+}
+#endif
+
+static u8 ipvlan_get_v4_hash(const void *iaddr)
+{
+ const struct in_addr *ip4_addr = iaddr;
+
+ return jhash_1word(ip4_addr->s_addr, ipvlan_jhash_secret) &
+ IPVLAN_HASH_MASK;
+}
+
+static bool addr_equal(bool is_v6, struct ipvl_addr *addr, const void *iaddr)
+{
+ if (!is_v6 && addr->atype == IPVL_IPV4) {
+ struct in_addr *i4addr = (struct in_addr *)iaddr;
+
+ return addr->ip4addr.s_addr == i4addr->s_addr;
+#if IS_ENABLED(CONFIG_IPV6)
+ } else if (is_v6 && addr->atype == IPVL_IPV6) {
+ struct in6_addr *i6addr = (struct in6_addr *)iaddr;
+
+ return ipv6_addr_equal(&addr->ip6addr, i6addr);
+#endif
+ }
+
+ return false;
+}
+
+static struct ipvl_addr *ipvlan_ht_addr_lookup(const struct ipvl_port *port,
+ const void *iaddr, bool is_v6)
+{
+ struct ipvl_addr *addr;
+ u8 hash;
+
+ hash = is_v6 ? ipvlan_get_v6_hash(iaddr) :
+ ipvlan_get_v4_hash(iaddr);
+ hlist_for_each_entry_rcu(addr, &port->hlhead[hash], hlnode)
+ if (addr_equal(is_v6, addr, iaddr))
+ return addr;
+ return NULL;
+}
+
+void ipvlan_ht_addr_add(struct ipvl_dev *ipvlan, struct ipvl_addr *addr)
+{
+ struct ipvl_port *port = ipvlan->port;
+ u8 hash;
+
+ hash = (addr->atype == IPVL_IPV6) ?
+ ipvlan_get_v6_hash(&addr->ip6addr) :
+ ipvlan_get_v4_hash(&addr->ip4addr);
+ if (hlist_unhashed(&addr->hlnode))
+ hlist_add_head_rcu(&addr->hlnode, &port->hlhead[hash]);
+}
+
+void ipvlan_ht_addr_del(struct ipvl_addr *addr)
+{
+ hlist_del_init_rcu(&addr->hlnode);
+}
+
+struct ipvl_addr *ipvlan_find_addr(const struct ipvl_dev *ipvlan,
+ const void *iaddr, bool is_v6)
+{
+ struct ipvl_addr *addr, *ret = NULL;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(addr, &ipvlan->addrs, anode) {
+ if (addr_equal(is_v6, addr, iaddr)) {
+ ret = addr;
+ break;
+ }
+ }
+ rcu_read_unlock();
+ return ret;
+}
+
+bool ipvlan_addr_busy(struct ipvl_port *port, void *iaddr, bool is_v6)
+{
+ struct ipvl_dev *ipvlan;
+ bool ret = false;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(ipvlan, &port->ipvlans, pnode) {
+ if (ipvlan_find_addr(ipvlan, iaddr, is_v6)) {
+ ret = true;
+ break;
+ }
+ }
+ rcu_read_unlock();
+ return ret;
+}
+
+void *ipvlan_get_L3_hdr(struct ipvl_port *port, struct sk_buff *skb, int *type)
+{
+ void *lyr3h = NULL;
+
+ switch (skb->protocol) {
+ case htons(ETH_P_ARP): {
+ struct arphdr *arph;
+
+ if (unlikely(!pskb_may_pull(skb, arp_hdr_len(port->dev))))
+ return NULL;
+
+ arph = arp_hdr(skb);
+ *type = IPVL_ARP;
+ lyr3h = arph;
+ break;
+ }
+ case htons(ETH_P_IP): {
+ u32 pktlen;
+ struct iphdr *ip4h;
+
+ if (unlikely(!pskb_may_pull(skb, sizeof(*ip4h))))
+ return NULL;
+
+ ip4h = ip_hdr(skb);
+ pktlen = ntohs(ip4h->tot_len);
+ if (ip4h->ihl < 5 || ip4h->version != 4)
+ return NULL;
+ if (skb->len < pktlen || pktlen < (ip4h->ihl * 4))
+ return NULL;
+
+ *type = IPVL_IPV4;
+ lyr3h = ip4h;
+ break;
+ }
+#if IS_ENABLED(CONFIG_IPV6)
+ case htons(ETH_P_IPV6): {
+ struct ipv6hdr *ip6h;
+
+ if (unlikely(!pskb_may_pull(skb, sizeof(*ip6h))))
+ return NULL;
+
+ ip6h = ipv6_hdr(skb);
+ if (ip6h->version != 6)
+ return NULL;
+
+ *type = IPVL_IPV6;
+ lyr3h = ip6h;
+ /* Only Neighbour Solicitation pkts need different treatment */
+ if (ipv6_addr_any(&ip6h->saddr) &&
+ ip6h->nexthdr == NEXTHDR_ICMP) {
+ struct icmp6hdr *icmph;
+
+ if (unlikely(!pskb_may_pull(skb, sizeof(*ip6h) + sizeof(*icmph))))
+ return NULL;
+
+ ip6h = ipv6_hdr(skb);
+ icmph = (struct icmp6hdr *)(ip6h + 1);
+
+ if (icmph->icmp6_type == NDISC_NEIGHBOUR_SOLICITATION) {
+ /* Need to access the ipv6 address in body */
+ if (unlikely(!pskb_may_pull(skb, sizeof(*ip6h) + sizeof(*icmph)
+ + sizeof(struct in6_addr))))
+ return NULL;
+
+ ip6h = ipv6_hdr(skb);
+ icmph = (struct icmp6hdr *)(ip6h + 1);
+ }
+
+ *type = IPVL_ICMPV6;
+ lyr3h = icmph;
+ }
+ break;
+ }
+#endif
+ default:
+ return NULL;
+ }
+
+ return lyr3h;
+}
+
+unsigned int ipvlan_mac_hash(const unsigned char *addr)
+{
+ u32 hash = jhash_1word(__get_unaligned_cpu32(addr+2),
+ ipvlan_jhash_secret);
+
+ return hash & IPVLAN_MAC_FILTER_MASK;
+}
+
+void ipvlan_process_multicast(struct work_struct *work)
+{
+ struct ipvl_port *port = container_of(work, struct ipvl_port, wq);
+ struct ethhdr *ethh;
+ struct ipvl_dev *ipvlan;
+ struct sk_buff *skb, *nskb;
+ struct sk_buff_head list;
+ unsigned int len;
+ unsigned int mac_hash;
+ int ret;
+ u8 pkt_type;
+ bool tx_pkt;
+
+ __skb_queue_head_init(&list);
+
+ spin_lock_bh(&port->backlog.lock);
+ skb_queue_splice_tail_init(&port->backlog, &list);
+ spin_unlock_bh(&port->backlog.lock);
+
+ while ((skb = __skb_dequeue(&list)) != NULL) {
+ struct net_device *dev = skb->dev;
+ bool consumed = false;
+
+ ethh = eth_hdr(skb);
+ tx_pkt = IPVL_SKB_CB(skb)->tx_pkt;
+ mac_hash = ipvlan_mac_hash(ethh->h_dest);
+
+ if (ether_addr_equal(ethh->h_dest, port->dev->broadcast))
+ pkt_type = PACKET_BROADCAST;
+ else
+ pkt_type = PACKET_MULTICAST;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(ipvlan, &port->ipvlans, pnode) {
+ if (tx_pkt && (ipvlan->dev == skb->dev))
+ continue;
+ if (!test_bit(mac_hash, ipvlan->mac_filters))
+ continue;
+ if (!(ipvlan->dev->flags & IFF_UP))
+ continue;
+ ret = NET_RX_DROP;
+ len = skb->len + ETH_HLEN;
+ nskb = skb_clone(skb, GFP_ATOMIC);
+ local_bh_disable();
+ if (nskb) {
+ consumed = true;
+ nskb->pkt_type = pkt_type;
+ nskb->dev = ipvlan->dev;
+ if (tx_pkt)
+ ret = dev_forward_skb(ipvlan->dev, nskb);
+ else
+ ret = netif_rx(nskb);
+ }
+ ipvlan_count_rx(ipvlan, len, ret == NET_RX_SUCCESS, true);
+ local_bh_enable();
+ }
+ rcu_read_unlock();
+
+ if (tx_pkt) {
+ /* If the packet originated here, send it out. */
+ skb->dev = port->dev;
+ skb->pkt_type = pkt_type;
+ dev_queue_xmit(skb);
+ } else {
+ if (consumed)
+ consume_skb(skb);
+ else
+ kfree_skb(skb);
+ }
+ dev_put(dev);
+ cond_resched();
+ }
+}
+
+static void ipvlan_skb_crossing_ns(struct sk_buff *skb, struct net_device *dev)
+{
+ bool xnet = true;
+
+ if (dev)
+ xnet = !net_eq(dev_net(skb->dev), dev_net(dev));
+
+ skb_scrub_packet(skb, xnet);
+ if (dev)
+ skb->dev = dev;
+}
+
+static int ipvlan_rcv_frame(struct ipvl_addr *addr, struct sk_buff **pskb,
+ bool local)
+{
+ struct ipvl_dev *ipvlan = addr->master;
+ struct net_device *dev = ipvlan->dev;
+ unsigned int len;
+ rx_handler_result_t ret = RX_HANDLER_CONSUMED;
+ bool success = false;
+ struct sk_buff *skb = *pskb;
+
+ len = skb->len + ETH_HLEN;
+ /* Only packets exchanged between two local slaves need to have
+ * device-up check as well as skb-share check.
+ */
+ if (local) {
+ if (unlikely(!(dev->flags & IFF_UP))) {
+ kfree_skb(skb);
+ goto out;
+ }
+
+ skb = skb_share_check(skb, GFP_ATOMIC);
+ if (!skb)
+ goto out;
+
+ *pskb = skb;
+ }
+
+ if (local) {
+ skb->pkt_type = PACKET_HOST;
+ if (dev_forward_skb(ipvlan->dev, skb) == NET_RX_SUCCESS)
+ success = true;
+ } else {
+ skb->dev = dev;
+ ret = RX_HANDLER_ANOTHER;
+ success = true;
+ }
+
+out:
+ ipvlan_count_rx(ipvlan, len, success, false);
+ return ret;
+}
+
+struct ipvl_addr *ipvlan_addr_lookup(struct ipvl_port *port, void *lyr3h,
+ int addr_type, bool use_dest)
+{
+ struct ipvl_addr *addr = NULL;
+
+ switch (addr_type) {
+#if IS_ENABLED(CONFIG_IPV6)
+ case IPVL_IPV6: {
+ struct ipv6hdr *ip6h;
+ struct in6_addr *i6addr;
+
+ ip6h = (struct ipv6hdr *)lyr3h;
+ i6addr = use_dest ? &ip6h->daddr : &ip6h->saddr;
+ addr = ipvlan_ht_addr_lookup(port, i6addr, true);
+ break;
+ }
+ case IPVL_ICMPV6: {
+ struct nd_msg *ndmh;
+ struct in6_addr *i6addr;
+
+ /* Make sure that the NeighborSolicitation ICMPv6 packets
+ * are handled to avoid DAD issue.
+ */
+ ndmh = (struct nd_msg *)lyr3h;
+ if (ndmh->icmph.icmp6_type == NDISC_NEIGHBOUR_SOLICITATION) {
+ i6addr = &ndmh->target;
+ addr = ipvlan_ht_addr_lookup(port, i6addr, true);
+ }
+ break;
+ }
+#endif
+ case IPVL_IPV4: {
+ struct iphdr *ip4h;
+ __be32 *i4addr;
+
+ ip4h = (struct iphdr *)lyr3h;
+ i4addr = use_dest ? &ip4h->daddr : &ip4h->saddr;
+ addr = ipvlan_ht_addr_lookup(port, i4addr, false);
+ break;
+ }
+ case IPVL_ARP: {
+ struct arphdr *arph;
+ unsigned char *arp_ptr;
+ __be32 dip;
+
+ arph = (struct arphdr *)lyr3h;
+ arp_ptr = (unsigned char *)(arph + 1);
+ if (use_dest)
+ arp_ptr += (2 * port->dev->addr_len) + 4;
+ else
+ arp_ptr += port->dev->addr_len;
+
+ memcpy(&dip, arp_ptr, 4);
+ addr = ipvlan_ht_addr_lookup(port, &dip, false);
+ break;
+ }
+ }
+
+ return addr;
+}
+
+static noinline_for_stack int ipvlan_process_v4_outbound(struct sk_buff *skb)
+{
+ const struct iphdr *ip4h = ip_hdr(skb);
+ struct net_device *dev = skb->dev;
+ struct net *net = dev_net(dev);
+ struct rtable *rt;
+ int err, ret = NET_XMIT_DROP;
+ struct flowi4 fl4 = {
+ .flowi4_oif = dev->ifindex,
+ .flowi4_tos = RT_TOS(ip4h->tos),
+ .flowi4_flags = FLOWI_FLAG_ANYSRC,
+ .flowi4_mark = skb->mark,
+ .daddr = ip4h->daddr,
+ .saddr = ip4h->saddr,
+ };
+
+ rt = ip_route_output_flow(net, &fl4, NULL);
+ if (IS_ERR(rt))
+ goto err;
+
+ if (rt->rt_type != RTN_UNICAST && rt->rt_type != RTN_LOCAL) {
+ ip_rt_put(rt);
+ goto err;
+ }
+ skb_dst_set(skb, &rt->dst);
+
+ memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
+
+ err = ip_local_out(net, skb->sk, skb);
+ if (unlikely(net_xmit_eval(err)))
+ DEV_STATS_INC(dev, tx_errors);
+ else
+ ret = NET_XMIT_SUCCESS;
+ goto out;
+err:
+ DEV_STATS_INC(dev, tx_errors);
+ kfree_skb(skb);
+out:
+ return ret;
+}
+
+#if IS_ENABLED(CONFIG_IPV6)
+
+static noinline_for_stack int
+ipvlan_route_v6_outbound(struct net_device *dev, struct sk_buff *skb)
+{
+ const struct ipv6hdr *ip6h = ipv6_hdr(skb);
+ struct flowi6 fl6 = {
+ .flowi6_oif = dev->ifindex,
+ .daddr = ip6h->daddr,
+ .saddr = ip6h->saddr,
+ .flowi6_flags = FLOWI_FLAG_ANYSRC,
+ .flowlabel = ip6_flowinfo(ip6h),
+ .flowi6_mark = skb->mark,
+ .flowi6_proto = ip6h->nexthdr,
+ };
+ struct dst_entry *dst;
+ int err;
+
+ dst = ip6_route_output(dev_net(dev), NULL, &fl6);
+ err = dst->error;
+ if (err) {
+ dst_release(dst);
+ return err;
+ }
+ skb_dst_set(skb, dst);
+ return 0;
+}
+
+static int ipvlan_process_v6_outbound(struct sk_buff *skb)
+{
+ struct net_device *dev = skb->dev;
+ int err, ret = NET_XMIT_DROP;
+
+ err = ipvlan_route_v6_outbound(dev, skb);
+ if (unlikely(err)) {
+ DEV_STATS_INC(dev, tx_errors);
+ kfree_skb(skb);
+ return err;
+ }
+
+ memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
+
+ err = ip6_local_out(dev_net(dev), skb->sk, skb);
+ if (unlikely(net_xmit_eval(err)))
+ DEV_STATS_INC(dev, tx_errors);
+ else
+ ret = NET_XMIT_SUCCESS;
+ return ret;
+}
+#else
+static int ipvlan_process_v6_outbound(struct sk_buff *skb)
+{
+ return NET_XMIT_DROP;
+}
+#endif
+
+static int ipvlan_process_outbound(struct sk_buff *skb)
+{
+ int ret = NET_XMIT_DROP;
+
+ /* The ipvlan is a pseudo-L2 device, so the packets that we receive
+ * will have L2; which need to discarded and processed further
+ * in the net-ns of the main-device.
+ */
+ if (skb_mac_header_was_set(skb)) {
+ /* In this mode we dont care about
+ * multicast and broadcast traffic */
+ struct ethhdr *ethh = eth_hdr(skb);
+
+ if (is_multicast_ether_addr(ethh->h_dest)) {
+ pr_debug_ratelimited(
+ "Dropped {multi|broad}cast of type=[%x]\n",
+ ntohs(skb->protocol));
+ kfree_skb(skb);
+ goto out;
+ }
+
+ skb_pull(skb, sizeof(*ethh));
+ skb->mac_header = (typeof(skb->mac_header))~0U;
+ skb_reset_network_header(skb);
+ }
+
+ if (skb->protocol == htons(ETH_P_IPV6))
+ ret = ipvlan_process_v6_outbound(skb);
+ else if (skb->protocol == htons(ETH_P_IP))
+ ret = ipvlan_process_v4_outbound(skb);
+ else {
+ pr_warn_ratelimited("Dropped outbound packet type=%x\n",
+ ntohs(skb->protocol));
+ kfree_skb(skb);
+ }
+out:
+ return ret;
+}
+
+static void ipvlan_multicast_enqueue(struct ipvl_port *port,
+ struct sk_buff *skb, bool tx_pkt)
+{
+ if (skb->protocol == htons(ETH_P_PAUSE)) {
+ kfree_skb(skb);
+ return;
+ }
+
+ /* Record that the deferred packet is from TX or RX path. By
+ * looking at mac-addresses on packet will lead to erronus decisions.
+ * (This would be true for a loopback-mode on master device or a
+ * hair-pin mode of the switch.)
+ */
+ IPVL_SKB_CB(skb)->tx_pkt = tx_pkt;
+
+ spin_lock(&port->backlog.lock);
+ if (skb_queue_len(&port->backlog) < IPVLAN_QBACKLOG_LIMIT) {
+ if (skb->dev)
+ dev_hold(skb->dev);
+ __skb_queue_tail(&port->backlog, skb);
+ spin_unlock(&port->backlog.lock);
+ schedule_work(&port->wq);
+ } else {
+ spin_unlock(&port->backlog.lock);
+ dev_core_stats_rx_dropped_inc(skb->dev);
+ kfree_skb(skb);
+ }
+}
+
+static int ipvlan_xmit_mode_l3(struct sk_buff *skb, struct net_device *dev)
+{
+ const struct ipvl_dev *ipvlan = netdev_priv(dev);
+ void *lyr3h;
+ struct ipvl_addr *addr;
+ int addr_type;
+
+ lyr3h = ipvlan_get_L3_hdr(ipvlan->port, skb, &addr_type);
+ if (!lyr3h)
+ goto out;
+
+ if (!ipvlan_is_vepa(ipvlan->port)) {
+ addr = ipvlan_addr_lookup(ipvlan->port, lyr3h, addr_type, true);
+ if (addr) {
+ if (ipvlan_is_private(ipvlan->port)) {
+ consume_skb(skb);
+ return NET_XMIT_DROP;
+ }
+ ipvlan_rcv_frame(addr, &skb, true);
+ return NET_XMIT_SUCCESS;
+ }
+ }
+out:
+ ipvlan_skb_crossing_ns(skb, ipvlan->phy_dev);
+ return ipvlan_process_outbound(skb);
+}
+
+static int ipvlan_xmit_mode_l2(struct sk_buff *skb, struct net_device *dev)
+{
+ const struct ipvl_dev *ipvlan = netdev_priv(dev);
+ struct ethhdr *eth = skb_eth_hdr(skb);
+ struct ipvl_addr *addr;
+ void *lyr3h;
+ int addr_type;
+
+ if (!ipvlan_is_vepa(ipvlan->port) &&
+ ether_addr_equal(eth->h_dest, eth->h_source)) {
+ lyr3h = ipvlan_get_L3_hdr(ipvlan->port, skb, &addr_type);
+ if (lyr3h) {
+ addr = ipvlan_addr_lookup(ipvlan->port, lyr3h, addr_type, true);
+ if (addr) {
+ if (ipvlan_is_private(ipvlan->port)) {
+ consume_skb(skb);
+ return NET_XMIT_DROP;
+ }
+ ipvlan_rcv_frame(addr, &skb, true);
+ return NET_XMIT_SUCCESS;
+ }
+ }
+ skb = skb_share_check(skb, GFP_ATOMIC);
+ if (!skb)
+ return NET_XMIT_DROP;
+
+ /* Packet definitely does not belong to any of the
+ * virtual devices, but the dest is local. So forward
+ * the skb for the main-dev. At the RX side we just return
+ * RX_PASS for it to be processed further on the stack.
+ */
+ dev_forward_skb(ipvlan->phy_dev, skb);
+ return NET_XMIT_SUCCESS;
+
+ } else if (is_multicast_ether_addr(eth->h_dest)) {
+ skb_reset_mac_header(skb);
+ ipvlan_skb_crossing_ns(skb, NULL);
+ ipvlan_multicast_enqueue(ipvlan->port, skb, true);
+ return NET_XMIT_SUCCESS;
+ }
+
+ skb->dev = ipvlan->phy_dev;
+ return dev_queue_xmit(skb);
+}
+
+int ipvlan_queue_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+ struct ipvl_dev *ipvlan = netdev_priv(dev);
+ struct ipvl_port *port = ipvlan_port_get_rcu_bh(ipvlan->phy_dev);
+
+ if (!port)
+ goto out;
+
+ if (unlikely(!pskb_may_pull(skb, sizeof(struct ethhdr))))
+ goto out;
+
+ switch(port->mode) {
+ case IPVLAN_MODE_L2:
+ return ipvlan_xmit_mode_l2(skb, dev);
+ case IPVLAN_MODE_L3:
+#ifdef CONFIG_IPVLAN_L3S
+ case IPVLAN_MODE_L3S:
+#endif
+ return ipvlan_xmit_mode_l3(skb, dev);
+ }
+
+ /* Should not reach here */
+ WARN_ONCE(true, "%s called for mode = [%x]\n", __func__, port->mode);
+out:
+ kfree_skb(skb);
+ return NET_XMIT_DROP;
+}
+
+static bool ipvlan_external_frame(struct sk_buff *skb, struct ipvl_port *port)
+{
+ struct ethhdr *eth = eth_hdr(skb);
+ struct ipvl_addr *addr;
+ void *lyr3h;
+ int addr_type;
+
+ if (ether_addr_equal(eth->h_source, skb->dev->dev_addr)) {
+ lyr3h = ipvlan_get_L3_hdr(port, skb, &addr_type);
+ if (!lyr3h)
+ return true;
+
+ addr = ipvlan_addr_lookup(port, lyr3h, addr_type, false);
+ if (addr)
+ return false;
+ }
+
+ return true;
+}
+
+static rx_handler_result_t ipvlan_handle_mode_l3(struct sk_buff **pskb,
+ struct ipvl_port *port)
+{
+ void *lyr3h;
+ int addr_type;
+ struct ipvl_addr *addr;
+ struct sk_buff *skb = *pskb;
+ rx_handler_result_t ret = RX_HANDLER_PASS;
+
+ lyr3h = ipvlan_get_L3_hdr(port, skb, &addr_type);
+ if (!lyr3h)
+ goto out;
+
+ addr = ipvlan_addr_lookup(port, lyr3h, addr_type, true);
+ if (addr)
+ ret = ipvlan_rcv_frame(addr, pskb, false);
+
+out:
+ return ret;
+}
+
+static rx_handler_result_t ipvlan_handle_mode_l2(struct sk_buff **pskb,
+ struct ipvl_port *port)
+{
+ struct sk_buff *skb = *pskb;
+ struct ethhdr *eth = eth_hdr(skb);
+ rx_handler_result_t ret = RX_HANDLER_PASS;
+
+ if (is_multicast_ether_addr(eth->h_dest)) {
+ if (ipvlan_external_frame(skb, port)) {
+ struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC);
+
+ /* External frames are queued for device local
+ * distribution, but a copy is given to master
+ * straight away to avoid sending duplicates later
+ * when work-queue processes this frame. This is
+ * achieved by returning RX_HANDLER_PASS.
+ */
+ if (nskb) {
+ ipvlan_skb_crossing_ns(nskb, NULL);
+ ipvlan_multicast_enqueue(port, nskb, false);
+ }
+ }
+ } else {
+ /* Perform like l3 mode for non-multicast packet */
+ ret = ipvlan_handle_mode_l3(pskb, port);
+ }
+
+ return ret;
+}
+
+rx_handler_result_t ipvlan_handle_frame(struct sk_buff **pskb)
+{
+ struct sk_buff *skb = *pskb;
+ struct ipvl_port *port = ipvlan_port_get_rcu(skb->dev);
+
+ if (!port)
+ return RX_HANDLER_PASS;
+
+ switch (port->mode) {
+ case IPVLAN_MODE_L2:
+ return ipvlan_handle_mode_l2(pskb, port);
+ case IPVLAN_MODE_L3:
+ return ipvlan_handle_mode_l3(pskb, port);
+#ifdef CONFIG_IPVLAN_L3S
+ case IPVLAN_MODE_L3S:
+ return RX_HANDLER_PASS;
+#endif
+ }
+
+ /* Should not reach here */
+ WARN_ONCE(true, "%s called for mode = [%x]\n", __func__, port->mode);
+ kfree_skb(skb);
+ return RX_HANDLER_CONSUMED;
+}
diff --git a/drivers/net/ipvlan/ipvlan_l3s.c b/drivers/net/ipvlan/ipvlan_l3s.c
new file mode 100644
index 000000000..d5b05e803
--- /dev/null
+++ b/drivers/net/ipvlan/ipvlan_l3s.c
@@ -0,0 +1,228 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* Copyright (c) 2014 Mahesh Bandewar <maheshb@google.com>
+ */
+
+#include "ipvlan.h"
+
+static unsigned int ipvlan_netid __read_mostly;
+
+struct ipvlan_netns {
+ unsigned int ipvl_nf_hook_refcnt;
+};
+
+static struct ipvl_addr *ipvlan_skb_to_addr(struct sk_buff *skb,
+ struct net_device *dev)
+{
+ struct ipvl_addr *addr = NULL;
+ struct ipvl_port *port;
+ int addr_type;
+ void *lyr3h;
+
+ if (!dev || !netif_is_ipvlan_port(dev))
+ goto out;
+
+ port = ipvlan_port_get_rcu(dev);
+ if (!port || port->mode != IPVLAN_MODE_L3S)
+ goto out;
+
+ lyr3h = ipvlan_get_L3_hdr(port, skb, &addr_type);
+ if (!lyr3h)
+ goto out;
+
+ addr = ipvlan_addr_lookup(port, lyr3h, addr_type, true);
+out:
+ return addr;
+}
+
+static struct sk_buff *ipvlan_l3_rcv(struct net_device *dev,
+ struct sk_buff *skb, u16 proto)
+{
+ struct ipvl_addr *addr;
+ struct net_device *sdev;
+
+ addr = ipvlan_skb_to_addr(skb, dev);
+ if (!addr)
+ goto out;
+
+ sdev = addr->master->dev;
+ switch (proto) {
+ case AF_INET:
+ {
+ struct iphdr *ip4h = ip_hdr(skb);
+ int err;
+
+ err = ip_route_input_noref(skb, ip4h->daddr, ip4h->saddr,
+ ip4h->tos, sdev);
+ if (unlikely(err))
+ goto out;
+ break;
+ }
+#if IS_ENABLED(CONFIG_IPV6)
+ case AF_INET6:
+ {
+ struct dst_entry *dst;
+ struct ipv6hdr *ip6h = ipv6_hdr(skb);
+ int flags = RT6_LOOKUP_F_HAS_SADDR;
+ struct flowi6 fl6 = {
+ .flowi6_iif = sdev->ifindex,
+ .daddr = ip6h->daddr,
+ .saddr = ip6h->saddr,
+ .flowlabel = ip6_flowinfo(ip6h),
+ .flowi6_mark = skb->mark,
+ .flowi6_proto = ip6h->nexthdr,
+ };
+
+ skb_dst_drop(skb);
+ dst = ip6_route_input_lookup(dev_net(sdev), sdev, &fl6,
+ skb, flags);
+ skb_dst_set(skb, dst);
+ break;
+ }
+#endif
+ default:
+ break;
+ }
+out:
+ return skb;
+}
+
+static const struct l3mdev_ops ipvl_l3mdev_ops = {
+ .l3mdev_l3_rcv = ipvlan_l3_rcv,
+};
+
+static unsigned int ipvlan_nf_input(void *priv, struct sk_buff *skb,
+ const struct nf_hook_state *state)
+{
+ struct ipvl_addr *addr;
+ unsigned int len;
+
+ addr = ipvlan_skb_to_addr(skb, skb->dev);
+ if (!addr)
+ goto out;
+
+ skb->dev = addr->master->dev;
+ skb->skb_iif = skb->dev->ifindex;
+#if IS_ENABLED(CONFIG_IPV6)
+ if (addr->atype == IPVL_IPV6)
+ IP6CB(skb)->iif = skb->dev->ifindex;
+#endif
+ len = skb->len + ETH_HLEN;
+ ipvlan_count_rx(addr->master, len, true, false);
+out:
+ return NF_ACCEPT;
+}
+
+static const struct nf_hook_ops ipvl_nfops[] = {
+ {
+ .hook = ipvlan_nf_input,
+ .pf = NFPROTO_IPV4,
+ .hooknum = NF_INET_LOCAL_IN,
+ .priority = INT_MAX,
+ },
+#if IS_ENABLED(CONFIG_IPV6)
+ {
+ .hook = ipvlan_nf_input,
+ .pf = NFPROTO_IPV6,
+ .hooknum = NF_INET_LOCAL_IN,
+ .priority = INT_MAX,
+ },
+#endif
+};
+
+static int ipvlan_register_nf_hook(struct net *net)
+{
+ struct ipvlan_netns *vnet = net_generic(net, ipvlan_netid);
+ int err = 0;
+
+ if (!vnet->ipvl_nf_hook_refcnt) {
+ err = nf_register_net_hooks(net, ipvl_nfops,
+ ARRAY_SIZE(ipvl_nfops));
+ if (!err)
+ vnet->ipvl_nf_hook_refcnt = 1;
+ } else {
+ vnet->ipvl_nf_hook_refcnt++;
+ }
+
+ return err;
+}
+
+static void ipvlan_unregister_nf_hook(struct net *net)
+{
+ struct ipvlan_netns *vnet = net_generic(net, ipvlan_netid);
+
+ if (WARN_ON(!vnet->ipvl_nf_hook_refcnt))
+ return;
+
+ vnet->ipvl_nf_hook_refcnt--;
+ if (!vnet->ipvl_nf_hook_refcnt)
+ nf_unregister_net_hooks(net, ipvl_nfops,
+ ARRAY_SIZE(ipvl_nfops));
+}
+
+void ipvlan_migrate_l3s_hook(struct net *oldnet, struct net *newnet)
+{
+ struct ipvlan_netns *old_vnet;
+
+ ASSERT_RTNL();
+
+ old_vnet = net_generic(oldnet, ipvlan_netid);
+ if (!old_vnet->ipvl_nf_hook_refcnt)
+ return;
+
+ ipvlan_register_nf_hook(newnet);
+ ipvlan_unregister_nf_hook(oldnet);
+}
+
+static void ipvlan_ns_exit(struct net *net)
+{
+ struct ipvlan_netns *vnet = net_generic(net, ipvlan_netid);
+
+ if (WARN_ON_ONCE(vnet->ipvl_nf_hook_refcnt)) {
+ vnet->ipvl_nf_hook_refcnt = 0;
+ nf_unregister_net_hooks(net, ipvl_nfops,
+ ARRAY_SIZE(ipvl_nfops));
+ }
+}
+
+static struct pernet_operations ipvlan_net_ops = {
+ .id = &ipvlan_netid,
+ .size = sizeof(struct ipvlan_netns),
+ .exit = ipvlan_ns_exit,
+};
+
+int ipvlan_l3s_init(void)
+{
+ return register_pernet_subsys(&ipvlan_net_ops);
+}
+
+void ipvlan_l3s_cleanup(void)
+{
+ unregister_pernet_subsys(&ipvlan_net_ops);
+}
+
+int ipvlan_l3s_register(struct ipvl_port *port)
+{
+ struct net_device *dev = port->dev;
+ int ret;
+
+ ASSERT_RTNL();
+
+ ret = ipvlan_register_nf_hook(read_pnet(&port->pnet));
+ if (!ret) {
+ dev->l3mdev_ops = &ipvl_l3mdev_ops;
+ dev->priv_flags |= IFF_L3MDEV_RX_HANDLER;
+ }
+
+ return ret;
+}
+
+void ipvlan_l3s_unregister(struct ipvl_port *port)
+{
+ struct net_device *dev = port->dev;
+
+ ASSERT_RTNL();
+
+ dev->priv_flags &= ~IFF_L3MDEV_RX_HANDLER;
+ ipvlan_unregister_nf_hook(read_pnet(&port->pnet));
+ dev->l3mdev_ops = NULL;
+}
diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c
new file mode 100644
index 000000000..fbf2d5b67
--- /dev/null
+++ b/drivers/net/ipvlan/ipvlan_main.c
@@ -0,0 +1,1084 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* Copyright (c) 2014 Mahesh Bandewar <maheshb@google.com>
+ */
+
+#include <linux/ethtool.h>
+
+#include "ipvlan.h"
+
+static int ipvlan_set_port_mode(struct ipvl_port *port, u16 nval,
+ struct netlink_ext_ack *extack)
+{
+ struct ipvl_dev *ipvlan;
+ unsigned int flags;
+ int err;
+
+ ASSERT_RTNL();
+ if (port->mode != nval) {
+ list_for_each_entry(ipvlan, &port->ipvlans, pnode) {
+ flags = ipvlan->dev->flags;
+ if (nval == IPVLAN_MODE_L3 || nval == IPVLAN_MODE_L3S) {
+ err = dev_change_flags(ipvlan->dev,
+ flags | IFF_NOARP,
+ extack);
+ } else {
+ err = dev_change_flags(ipvlan->dev,
+ flags & ~IFF_NOARP,
+ extack);
+ }
+ if (unlikely(err))
+ goto fail;
+ }
+ if (nval == IPVLAN_MODE_L3S) {
+ /* New mode is L3S */
+ err = ipvlan_l3s_register(port);
+ if (err)
+ goto fail;
+ } else if (port->mode == IPVLAN_MODE_L3S) {
+ /* Old mode was L3S */
+ ipvlan_l3s_unregister(port);
+ }
+ port->mode = nval;
+ }
+ return 0;
+
+fail:
+ /* Undo the flags changes that have been done so far. */
+ list_for_each_entry_continue_reverse(ipvlan, &port->ipvlans, pnode) {
+ flags = ipvlan->dev->flags;
+ if (port->mode == IPVLAN_MODE_L3 ||
+ port->mode == IPVLAN_MODE_L3S)
+ dev_change_flags(ipvlan->dev, flags | IFF_NOARP,
+ NULL);
+ else
+ dev_change_flags(ipvlan->dev, flags & ~IFF_NOARP,
+ NULL);
+ }
+
+ return err;
+}
+
+static int ipvlan_port_create(struct net_device *dev)
+{
+ struct ipvl_port *port;
+ int err, idx;
+
+ port = kzalloc(sizeof(struct ipvl_port), GFP_KERNEL);
+ if (!port)
+ return -ENOMEM;
+
+ write_pnet(&port->pnet, dev_net(dev));
+ port->dev = dev;
+ port->mode = IPVLAN_MODE_L3;
+ INIT_LIST_HEAD(&port->ipvlans);
+ for (idx = 0; idx < IPVLAN_HASH_SIZE; idx++)
+ INIT_HLIST_HEAD(&port->hlhead[idx]);
+
+ skb_queue_head_init(&port->backlog);
+ INIT_WORK(&port->wq, ipvlan_process_multicast);
+ ida_init(&port->ida);
+ port->dev_id_start = 1;
+
+ err = netdev_rx_handler_register(dev, ipvlan_handle_frame, port);
+ if (err)
+ goto err;
+
+ netdev_hold(dev, &port->dev_tracker, GFP_KERNEL);
+ return 0;
+
+err:
+ kfree(port);
+ return err;
+}
+
+static void ipvlan_port_destroy(struct net_device *dev)
+{
+ struct ipvl_port *port = ipvlan_port_get_rtnl(dev);
+ struct sk_buff *skb;
+
+ netdev_put(dev, &port->dev_tracker);
+ if (port->mode == IPVLAN_MODE_L3S)
+ ipvlan_l3s_unregister(port);
+ netdev_rx_handler_unregister(dev);
+ cancel_work_sync(&port->wq);
+ while ((skb = __skb_dequeue(&port->backlog)) != NULL) {
+ dev_put(skb->dev);
+ kfree_skb(skb);
+ }
+ ida_destroy(&port->ida);
+ kfree(port);
+}
+
+#define IPVLAN_ALWAYS_ON_OFLOADS \
+ (NETIF_F_SG | NETIF_F_HW_CSUM | \
+ NETIF_F_GSO_ROBUST | NETIF_F_GSO_SOFTWARE | NETIF_F_GSO_ENCAP_ALL)
+
+#define IPVLAN_ALWAYS_ON \
+ (IPVLAN_ALWAYS_ON_OFLOADS | NETIF_F_LLTX | NETIF_F_VLAN_CHALLENGED)
+
+#define IPVLAN_FEATURES \
+ (NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST | \
+ NETIF_F_GSO | NETIF_F_ALL_TSO | NETIF_F_GSO_ROBUST | \
+ NETIF_F_GRO | NETIF_F_RXCSUM | \
+ NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_STAG_FILTER)
+
+ /* NETIF_F_GSO_ENCAP_ALL NETIF_F_GSO_SOFTWARE Newly added */
+
+#define IPVLAN_STATE_MASK \
+ ((1<<__LINK_STATE_NOCARRIER) | (1<<__LINK_STATE_DORMANT))
+
+static int ipvlan_init(struct net_device *dev)
+{
+ struct ipvl_dev *ipvlan = netdev_priv(dev);
+ struct net_device *phy_dev = ipvlan->phy_dev;
+ struct ipvl_port *port;
+ int err;
+
+ dev->state = (dev->state & ~IPVLAN_STATE_MASK) |
+ (phy_dev->state & IPVLAN_STATE_MASK);
+ dev->features = phy_dev->features & IPVLAN_FEATURES;
+ dev->features |= IPVLAN_ALWAYS_ON;
+ dev->vlan_features = phy_dev->vlan_features & IPVLAN_FEATURES;
+ dev->vlan_features |= IPVLAN_ALWAYS_ON_OFLOADS;
+ dev->hw_enc_features |= dev->features;
+ netif_inherit_tso_max(dev, phy_dev);
+ dev->hard_header_len = phy_dev->hard_header_len;
+
+ netdev_lockdep_set_classes(dev);
+
+ ipvlan->pcpu_stats = netdev_alloc_pcpu_stats(struct ipvl_pcpu_stats);
+ if (!ipvlan->pcpu_stats)
+ return -ENOMEM;
+
+ if (!netif_is_ipvlan_port(phy_dev)) {
+ err = ipvlan_port_create(phy_dev);
+ if (err < 0) {
+ free_percpu(ipvlan->pcpu_stats);
+ return err;
+ }
+ }
+ port = ipvlan_port_get_rtnl(phy_dev);
+ port->count += 1;
+ return 0;
+}
+
+static void ipvlan_uninit(struct net_device *dev)
+{
+ struct ipvl_dev *ipvlan = netdev_priv(dev);
+ struct net_device *phy_dev = ipvlan->phy_dev;
+ struct ipvl_port *port;
+
+ free_percpu(ipvlan->pcpu_stats);
+
+ port = ipvlan_port_get_rtnl(phy_dev);
+ port->count -= 1;
+ if (!port->count)
+ ipvlan_port_destroy(port->dev);
+}
+
+static int ipvlan_open(struct net_device *dev)
+{
+ struct ipvl_dev *ipvlan = netdev_priv(dev);
+ struct ipvl_addr *addr;
+
+ if (ipvlan->port->mode == IPVLAN_MODE_L3 ||
+ ipvlan->port->mode == IPVLAN_MODE_L3S)
+ dev->flags |= IFF_NOARP;
+ else
+ dev->flags &= ~IFF_NOARP;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(addr, &ipvlan->addrs, anode)
+ ipvlan_ht_addr_add(ipvlan, addr);
+ rcu_read_unlock();
+
+ return 0;
+}
+
+static int ipvlan_stop(struct net_device *dev)
+{
+ struct ipvl_dev *ipvlan = netdev_priv(dev);
+ struct net_device *phy_dev = ipvlan->phy_dev;
+ struct ipvl_addr *addr;
+
+ dev_uc_unsync(phy_dev, dev);
+ dev_mc_unsync(phy_dev, dev);
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(addr, &ipvlan->addrs, anode)
+ ipvlan_ht_addr_del(addr);
+ rcu_read_unlock();
+
+ return 0;
+}
+
+static netdev_tx_t ipvlan_start_xmit(struct sk_buff *skb,
+ struct net_device *dev)
+{
+ const struct ipvl_dev *ipvlan = netdev_priv(dev);
+ int skblen = skb->len;
+ int ret;
+
+ ret = ipvlan_queue_xmit(skb, dev);
+ if (likely(ret == NET_XMIT_SUCCESS || ret == NET_XMIT_CN)) {
+ struct ipvl_pcpu_stats *pcptr;
+
+ pcptr = this_cpu_ptr(ipvlan->pcpu_stats);
+
+ u64_stats_update_begin(&pcptr->syncp);
+ u64_stats_inc(&pcptr->tx_pkts);
+ u64_stats_add(&pcptr->tx_bytes, skblen);
+ u64_stats_update_end(&pcptr->syncp);
+ } else {
+ this_cpu_inc(ipvlan->pcpu_stats->tx_drps);
+ }
+ return ret;
+}
+
+static netdev_features_t ipvlan_fix_features(struct net_device *dev,
+ netdev_features_t features)
+{
+ struct ipvl_dev *ipvlan = netdev_priv(dev);
+
+ features |= NETIF_F_ALL_FOR_ALL;
+ features &= (ipvlan->sfeatures | ~IPVLAN_FEATURES);
+ features = netdev_increment_features(ipvlan->phy_dev->features,
+ features, features);
+ features |= IPVLAN_ALWAYS_ON;
+ features &= (IPVLAN_FEATURES | IPVLAN_ALWAYS_ON);
+
+ return features;
+}
+
+static void ipvlan_change_rx_flags(struct net_device *dev, int change)
+{
+ struct ipvl_dev *ipvlan = netdev_priv(dev);
+ struct net_device *phy_dev = ipvlan->phy_dev;
+
+ if (change & IFF_ALLMULTI)
+ dev_set_allmulti(phy_dev, dev->flags & IFF_ALLMULTI? 1 : -1);
+}
+
+static void ipvlan_set_multicast_mac_filter(struct net_device *dev)
+{
+ struct ipvl_dev *ipvlan = netdev_priv(dev);
+
+ if (dev->flags & (IFF_PROMISC | IFF_ALLMULTI)) {
+ bitmap_fill(ipvlan->mac_filters, IPVLAN_MAC_FILTER_SIZE);
+ } else {
+ struct netdev_hw_addr *ha;
+ DECLARE_BITMAP(mc_filters, IPVLAN_MAC_FILTER_SIZE);
+
+ bitmap_zero(mc_filters, IPVLAN_MAC_FILTER_SIZE);
+ netdev_for_each_mc_addr(ha, dev)
+ __set_bit(ipvlan_mac_hash(ha->addr), mc_filters);
+
+ /* Turn-on broadcast bit irrespective of address family,
+ * since broadcast is deferred to a work-queue, hence no
+ * impact on fast-path processing.
+ */
+ __set_bit(ipvlan_mac_hash(dev->broadcast), mc_filters);
+
+ bitmap_copy(ipvlan->mac_filters, mc_filters,
+ IPVLAN_MAC_FILTER_SIZE);
+ }
+ dev_uc_sync(ipvlan->phy_dev, dev);
+ dev_mc_sync(ipvlan->phy_dev, dev);
+}
+
+static void ipvlan_get_stats64(struct net_device *dev,
+ struct rtnl_link_stats64 *s)
+{
+ struct ipvl_dev *ipvlan = netdev_priv(dev);
+
+ if (ipvlan->pcpu_stats) {
+ struct ipvl_pcpu_stats *pcptr;
+ u64 rx_pkts, rx_bytes, rx_mcast, tx_pkts, tx_bytes;
+ u32 rx_errs = 0, tx_drps = 0;
+ u32 strt;
+ int idx;
+
+ for_each_possible_cpu(idx) {
+ pcptr = per_cpu_ptr(ipvlan->pcpu_stats, idx);
+ do {
+ strt= u64_stats_fetch_begin_irq(&pcptr->syncp);
+ rx_pkts = u64_stats_read(&pcptr->rx_pkts);
+ rx_bytes = u64_stats_read(&pcptr->rx_bytes);
+ rx_mcast = u64_stats_read(&pcptr->rx_mcast);
+ tx_pkts = u64_stats_read(&pcptr->tx_pkts);
+ tx_bytes = u64_stats_read(&pcptr->tx_bytes);
+ } while (u64_stats_fetch_retry_irq(&pcptr->syncp,
+ strt));
+
+ s->rx_packets += rx_pkts;
+ s->rx_bytes += rx_bytes;
+ s->multicast += rx_mcast;
+ s->tx_packets += tx_pkts;
+ s->tx_bytes += tx_bytes;
+
+ /* u32 values are updated without syncp protection. */
+ rx_errs += READ_ONCE(pcptr->rx_errs);
+ tx_drps += READ_ONCE(pcptr->tx_drps);
+ }
+ s->rx_errors = rx_errs;
+ s->rx_dropped = rx_errs;
+ s->tx_dropped = tx_drps;
+ }
+ s->tx_errors = DEV_STATS_READ(dev, tx_errors);
+}
+
+static int ipvlan_vlan_rx_add_vid(struct net_device *dev, __be16 proto, u16 vid)
+{
+ struct ipvl_dev *ipvlan = netdev_priv(dev);
+ struct net_device *phy_dev = ipvlan->phy_dev;
+
+ return vlan_vid_add(phy_dev, proto, vid);
+}
+
+static int ipvlan_vlan_rx_kill_vid(struct net_device *dev, __be16 proto,
+ u16 vid)
+{
+ struct ipvl_dev *ipvlan = netdev_priv(dev);
+ struct net_device *phy_dev = ipvlan->phy_dev;
+
+ vlan_vid_del(phy_dev, proto, vid);
+ return 0;
+}
+
+static int ipvlan_get_iflink(const struct net_device *dev)
+{
+ struct ipvl_dev *ipvlan = netdev_priv(dev);
+
+ return ipvlan->phy_dev->ifindex;
+}
+
+static const struct net_device_ops ipvlan_netdev_ops = {
+ .ndo_init = ipvlan_init,
+ .ndo_uninit = ipvlan_uninit,
+ .ndo_open = ipvlan_open,
+ .ndo_stop = ipvlan_stop,
+ .ndo_start_xmit = ipvlan_start_xmit,
+ .ndo_fix_features = ipvlan_fix_features,
+ .ndo_change_rx_flags = ipvlan_change_rx_flags,
+ .ndo_set_rx_mode = ipvlan_set_multicast_mac_filter,
+ .ndo_get_stats64 = ipvlan_get_stats64,
+ .ndo_vlan_rx_add_vid = ipvlan_vlan_rx_add_vid,
+ .ndo_vlan_rx_kill_vid = ipvlan_vlan_rx_kill_vid,
+ .ndo_get_iflink = ipvlan_get_iflink,
+};
+
+static int ipvlan_hard_header(struct sk_buff *skb, struct net_device *dev,
+ unsigned short type, const void *daddr,
+ const void *saddr, unsigned len)
+{
+ const struct ipvl_dev *ipvlan = netdev_priv(dev);
+ struct net_device *phy_dev = ipvlan->phy_dev;
+
+ /* TODO Probably use a different field than dev_addr so that the
+ * mac-address on the virtual device is portable and can be carried
+ * while the packets use the mac-addr on the physical device.
+ */
+ return dev_hard_header(skb, phy_dev, type, daddr,
+ saddr ? : phy_dev->dev_addr, len);
+}
+
+static const struct header_ops ipvlan_header_ops = {
+ .create = ipvlan_hard_header,
+ .parse = eth_header_parse,
+ .cache = eth_header_cache,
+ .cache_update = eth_header_cache_update,
+};
+
+static void ipvlan_adjust_mtu(struct ipvl_dev *ipvlan, struct net_device *dev)
+{
+ ipvlan->dev->mtu = dev->mtu;
+}
+
+static bool netif_is_ipvlan(const struct net_device *dev)
+{
+ /* both ipvlan and ipvtap devices use the same netdev_ops */
+ return dev->netdev_ops == &ipvlan_netdev_ops;
+}
+
+static int ipvlan_ethtool_get_link_ksettings(struct net_device *dev,
+ struct ethtool_link_ksettings *cmd)
+{
+ const struct ipvl_dev *ipvlan = netdev_priv(dev);
+
+ return __ethtool_get_link_ksettings(ipvlan->phy_dev, cmd);
+}
+
+static void ipvlan_ethtool_get_drvinfo(struct net_device *dev,
+ struct ethtool_drvinfo *drvinfo)
+{
+ strscpy(drvinfo->driver, IPVLAN_DRV, sizeof(drvinfo->driver));
+ strscpy(drvinfo->version, IPV_DRV_VER, sizeof(drvinfo->version));
+}
+
+static u32 ipvlan_ethtool_get_msglevel(struct net_device *dev)
+{
+ const struct ipvl_dev *ipvlan = netdev_priv(dev);
+
+ return ipvlan->msg_enable;
+}
+
+static void ipvlan_ethtool_set_msglevel(struct net_device *dev, u32 value)
+{
+ struct ipvl_dev *ipvlan = netdev_priv(dev);
+
+ ipvlan->msg_enable = value;
+}
+
+static const struct ethtool_ops ipvlan_ethtool_ops = {
+ .get_link = ethtool_op_get_link,
+ .get_link_ksettings = ipvlan_ethtool_get_link_ksettings,
+ .get_drvinfo = ipvlan_ethtool_get_drvinfo,
+ .get_msglevel = ipvlan_ethtool_get_msglevel,
+ .set_msglevel = ipvlan_ethtool_set_msglevel,
+};
+
+static int ipvlan_nl_changelink(struct net_device *dev,
+ struct nlattr *tb[], struct nlattr *data[],
+ struct netlink_ext_ack *extack)
+{
+ struct ipvl_dev *ipvlan = netdev_priv(dev);
+ struct ipvl_port *port = ipvlan_port_get_rtnl(ipvlan->phy_dev);
+ int err = 0;
+
+ if (!data)
+ return 0;
+ if (!ns_capable(dev_net(ipvlan->phy_dev)->user_ns, CAP_NET_ADMIN))
+ return -EPERM;
+
+ if (data[IFLA_IPVLAN_MODE]) {
+ u16 nmode = nla_get_u16(data[IFLA_IPVLAN_MODE]);
+
+ err = ipvlan_set_port_mode(port, nmode, extack);
+ }
+
+ if (!err && data[IFLA_IPVLAN_FLAGS]) {
+ u16 flags = nla_get_u16(data[IFLA_IPVLAN_FLAGS]);
+
+ if (flags & IPVLAN_F_PRIVATE)
+ ipvlan_mark_private(port);
+ else
+ ipvlan_clear_private(port);
+
+ if (flags & IPVLAN_F_VEPA)
+ ipvlan_mark_vepa(port);
+ else
+ ipvlan_clear_vepa(port);
+ }
+
+ return err;
+}
+
+static size_t ipvlan_nl_getsize(const struct net_device *dev)
+{
+ return (0
+ + nla_total_size(2) /* IFLA_IPVLAN_MODE */
+ + nla_total_size(2) /* IFLA_IPVLAN_FLAGS */
+ );
+}
+
+static int ipvlan_nl_validate(struct nlattr *tb[], struct nlattr *data[],
+ struct netlink_ext_ack *extack)
+{
+ if (!data)
+ return 0;
+
+ if (data[IFLA_IPVLAN_MODE]) {
+ u16 mode = nla_get_u16(data[IFLA_IPVLAN_MODE]);
+
+ if (mode >= IPVLAN_MODE_MAX)
+ return -EINVAL;
+ }
+ if (data[IFLA_IPVLAN_FLAGS]) {
+ u16 flags = nla_get_u16(data[IFLA_IPVLAN_FLAGS]);
+
+ /* Only two bits are used at this moment. */
+ if (flags & ~(IPVLAN_F_PRIVATE | IPVLAN_F_VEPA))
+ return -EINVAL;
+ /* Also both flags can't be active at the same time. */
+ if ((flags & (IPVLAN_F_PRIVATE | IPVLAN_F_VEPA)) ==
+ (IPVLAN_F_PRIVATE | IPVLAN_F_VEPA))
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int ipvlan_nl_fillinfo(struct sk_buff *skb,
+ const struct net_device *dev)
+{
+ struct ipvl_dev *ipvlan = netdev_priv(dev);
+ struct ipvl_port *port = ipvlan_port_get_rtnl(ipvlan->phy_dev);
+ int ret = -EINVAL;
+
+ if (!port)
+ goto err;
+
+ ret = -EMSGSIZE;
+ if (nla_put_u16(skb, IFLA_IPVLAN_MODE, port->mode))
+ goto err;
+ if (nla_put_u16(skb, IFLA_IPVLAN_FLAGS, port->flags))
+ goto err;
+
+ return 0;
+
+err:
+ return ret;
+}
+
+int ipvlan_link_new(struct net *src_net, struct net_device *dev,
+ struct nlattr *tb[], struct nlattr *data[],
+ struct netlink_ext_ack *extack)
+{
+ struct ipvl_dev *ipvlan = netdev_priv(dev);
+ struct ipvl_port *port;
+ struct net_device *phy_dev;
+ int err;
+ u16 mode = IPVLAN_MODE_L3;
+
+ if (!tb[IFLA_LINK])
+ return -EINVAL;
+
+ phy_dev = __dev_get_by_index(src_net, nla_get_u32(tb[IFLA_LINK]));
+ if (!phy_dev)
+ return -ENODEV;
+
+ if (netif_is_ipvlan(phy_dev)) {
+ struct ipvl_dev *tmp = netdev_priv(phy_dev);
+
+ phy_dev = tmp->phy_dev;
+ if (!ns_capable(dev_net(phy_dev)->user_ns, CAP_NET_ADMIN))
+ return -EPERM;
+ } else if (!netif_is_ipvlan_port(phy_dev)) {
+ /* Exit early if the underlying link is invalid or busy */
+ if (phy_dev->type != ARPHRD_ETHER ||
+ phy_dev->flags & IFF_LOOPBACK) {
+ netdev_err(phy_dev,
+ "Master is either lo or non-ether device\n");
+ return -EINVAL;
+ }
+
+ if (netdev_is_rx_handler_busy(phy_dev)) {
+ netdev_err(phy_dev, "Device is already in use.\n");
+ return -EBUSY;
+ }
+ }
+
+ ipvlan->phy_dev = phy_dev;
+ ipvlan->dev = dev;
+ ipvlan->sfeatures = IPVLAN_FEATURES;
+ if (!tb[IFLA_MTU])
+ ipvlan_adjust_mtu(ipvlan, phy_dev);
+ INIT_LIST_HEAD(&ipvlan->addrs);
+ spin_lock_init(&ipvlan->addrs_lock);
+
+ /* TODO Probably put random address here to be presented to the
+ * world but keep using the physical-dev address for the outgoing
+ * packets.
+ */
+ eth_hw_addr_set(dev, phy_dev->dev_addr);
+
+ dev->priv_flags |= IFF_NO_RX_HANDLER;
+
+ err = register_netdevice(dev);
+ if (err < 0)
+ return err;
+
+ /* ipvlan_init() would have created the port, if required */
+ port = ipvlan_port_get_rtnl(phy_dev);
+ ipvlan->port = port;
+
+ /* If the port-id base is at the MAX value, then wrap it around and
+ * begin from 0x1 again. This may be due to a busy system where lots
+ * of slaves are getting created and deleted.
+ */
+ if (port->dev_id_start == 0xFFFE)
+ port->dev_id_start = 0x1;
+
+ /* Since L2 address is shared among all IPvlan slaves including
+ * master, use unique 16 bit dev-ids to diffentiate among them.
+ * Assign IDs between 0x1 and 0xFFFE (used by the master) to each
+ * slave link [see addrconf_ifid_eui48()].
+ */
+ err = ida_simple_get(&port->ida, port->dev_id_start, 0xFFFE,
+ GFP_KERNEL);
+ if (err < 0)
+ err = ida_simple_get(&port->ida, 0x1, port->dev_id_start,
+ GFP_KERNEL);
+ if (err < 0)
+ goto unregister_netdev;
+ dev->dev_id = err;
+
+ /* Increment id-base to the next slot for the future assignment */
+ port->dev_id_start = err + 1;
+
+ err = netdev_upper_dev_link(phy_dev, dev, extack);
+ if (err)
+ goto remove_ida;
+
+ /* Flags are per port and latest update overrides. User has
+ * to be consistent in setting it just like the mode attribute.
+ */
+ if (data && data[IFLA_IPVLAN_FLAGS])
+ port->flags = nla_get_u16(data[IFLA_IPVLAN_FLAGS]);
+
+ if (data && data[IFLA_IPVLAN_MODE])
+ mode = nla_get_u16(data[IFLA_IPVLAN_MODE]);
+
+ err = ipvlan_set_port_mode(port, mode, extack);
+ if (err)
+ goto unlink_netdev;
+
+ list_add_tail_rcu(&ipvlan->pnode, &port->ipvlans);
+ netif_stacked_transfer_operstate(phy_dev, dev);
+ return 0;
+
+unlink_netdev:
+ netdev_upper_dev_unlink(phy_dev, dev);
+remove_ida:
+ ida_simple_remove(&port->ida, dev->dev_id);
+unregister_netdev:
+ unregister_netdevice(dev);
+ return err;
+}
+EXPORT_SYMBOL_GPL(ipvlan_link_new);
+
+void ipvlan_link_delete(struct net_device *dev, struct list_head *head)
+{
+ struct ipvl_dev *ipvlan = netdev_priv(dev);
+ struct ipvl_addr *addr, *next;
+
+ spin_lock_bh(&ipvlan->addrs_lock);
+ list_for_each_entry_safe(addr, next, &ipvlan->addrs, anode) {
+ ipvlan_ht_addr_del(addr);
+ list_del_rcu(&addr->anode);
+ kfree_rcu(addr, rcu);
+ }
+ spin_unlock_bh(&ipvlan->addrs_lock);
+
+ ida_simple_remove(&ipvlan->port->ida, dev->dev_id);
+ list_del_rcu(&ipvlan->pnode);
+ unregister_netdevice_queue(dev, head);
+ netdev_upper_dev_unlink(ipvlan->phy_dev, dev);
+}
+EXPORT_SYMBOL_GPL(ipvlan_link_delete);
+
+void ipvlan_link_setup(struct net_device *dev)
+{
+ ether_setup(dev);
+
+ dev->max_mtu = ETH_MAX_MTU;
+ dev->priv_flags &= ~(IFF_XMIT_DST_RELEASE | IFF_TX_SKB_SHARING);
+ dev->priv_flags |= IFF_UNICAST_FLT | IFF_NO_QUEUE;
+ dev->netdev_ops = &ipvlan_netdev_ops;
+ dev->needs_free_netdev = true;
+ dev->header_ops = &ipvlan_header_ops;
+ dev->ethtool_ops = &ipvlan_ethtool_ops;
+}
+EXPORT_SYMBOL_GPL(ipvlan_link_setup);
+
+static const struct nla_policy ipvlan_nl_policy[IFLA_IPVLAN_MAX + 1] =
+{
+ [IFLA_IPVLAN_MODE] = { .type = NLA_U16 },
+ [IFLA_IPVLAN_FLAGS] = { .type = NLA_U16 },
+};
+
+static struct net *ipvlan_get_link_net(const struct net_device *dev)
+{
+ struct ipvl_dev *ipvlan = netdev_priv(dev);
+
+ return dev_net(ipvlan->phy_dev);
+}
+
+static struct rtnl_link_ops ipvlan_link_ops = {
+ .kind = "ipvlan",
+ .priv_size = sizeof(struct ipvl_dev),
+
+ .setup = ipvlan_link_setup,
+ .newlink = ipvlan_link_new,
+ .dellink = ipvlan_link_delete,
+ .get_link_net = ipvlan_get_link_net,
+};
+
+int ipvlan_link_register(struct rtnl_link_ops *ops)
+{
+ ops->get_size = ipvlan_nl_getsize;
+ ops->policy = ipvlan_nl_policy;
+ ops->validate = ipvlan_nl_validate;
+ ops->fill_info = ipvlan_nl_fillinfo;
+ ops->changelink = ipvlan_nl_changelink;
+ ops->maxtype = IFLA_IPVLAN_MAX;
+ return rtnl_link_register(ops);
+}
+EXPORT_SYMBOL_GPL(ipvlan_link_register);
+
+static int ipvlan_device_event(struct notifier_block *unused,
+ unsigned long event, void *ptr)
+{
+ struct netlink_ext_ack *extack = netdev_notifier_info_to_extack(ptr);
+ struct netdev_notifier_pre_changeaddr_info *prechaddr_info;
+ struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+ struct ipvl_dev *ipvlan, *next;
+ struct ipvl_port *port;
+ LIST_HEAD(lst_kill);
+ int err;
+
+ if (!netif_is_ipvlan_port(dev))
+ return NOTIFY_DONE;
+
+ port = ipvlan_port_get_rtnl(dev);
+
+ switch (event) {
+ case NETDEV_UP:
+ case NETDEV_CHANGE:
+ list_for_each_entry(ipvlan, &port->ipvlans, pnode)
+ netif_stacked_transfer_operstate(ipvlan->phy_dev,
+ ipvlan->dev);
+ break;
+
+ case NETDEV_REGISTER: {
+ struct net *oldnet, *newnet = dev_net(dev);
+
+ oldnet = read_pnet(&port->pnet);
+ if (net_eq(newnet, oldnet))
+ break;
+
+ write_pnet(&port->pnet, newnet);
+
+ if (port->mode == IPVLAN_MODE_L3S)
+ ipvlan_migrate_l3s_hook(oldnet, newnet);
+ break;
+ }
+ case NETDEV_UNREGISTER:
+ if (dev->reg_state != NETREG_UNREGISTERING)
+ break;
+
+ list_for_each_entry_safe(ipvlan, next, &port->ipvlans, pnode)
+ ipvlan->dev->rtnl_link_ops->dellink(ipvlan->dev,
+ &lst_kill);
+ unregister_netdevice_many(&lst_kill);
+ break;
+
+ case NETDEV_FEAT_CHANGE:
+ list_for_each_entry(ipvlan, &port->ipvlans, pnode) {
+ netif_inherit_tso_max(ipvlan->dev, dev);
+ netdev_update_features(ipvlan->dev);
+ }
+ break;
+
+ case NETDEV_CHANGEMTU:
+ list_for_each_entry(ipvlan, &port->ipvlans, pnode)
+ ipvlan_adjust_mtu(ipvlan, dev);
+ break;
+
+ case NETDEV_PRE_CHANGEADDR:
+ prechaddr_info = ptr;
+ list_for_each_entry(ipvlan, &port->ipvlans, pnode) {
+ err = dev_pre_changeaddr_notify(ipvlan->dev,
+ prechaddr_info->dev_addr,
+ extack);
+ if (err)
+ return notifier_from_errno(err);
+ }
+ break;
+
+ case NETDEV_CHANGEADDR:
+ list_for_each_entry(ipvlan, &port->ipvlans, pnode) {
+ eth_hw_addr_set(ipvlan->dev, dev->dev_addr);
+ call_netdevice_notifiers(NETDEV_CHANGEADDR, ipvlan->dev);
+ }
+ break;
+
+ case NETDEV_PRE_TYPE_CHANGE:
+ /* Forbid underlying device to change its type. */
+ return NOTIFY_BAD;
+ }
+ return NOTIFY_DONE;
+}
+
+/* the caller must held the addrs lock */
+static int ipvlan_add_addr(struct ipvl_dev *ipvlan, void *iaddr, bool is_v6)
+{
+ struct ipvl_addr *addr;
+
+ addr = kzalloc(sizeof(struct ipvl_addr), GFP_ATOMIC);
+ if (!addr)
+ return -ENOMEM;
+
+ addr->master = ipvlan;
+ if (!is_v6) {
+ memcpy(&addr->ip4addr, iaddr, sizeof(struct in_addr));
+ addr->atype = IPVL_IPV4;
+#if IS_ENABLED(CONFIG_IPV6)
+ } else {
+ memcpy(&addr->ip6addr, iaddr, sizeof(struct in6_addr));
+ addr->atype = IPVL_IPV6;
+#endif
+ }
+
+ list_add_tail_rcu(&addr->anode, &ipvlan->addrs);
+
+ /* If the interface is not up, the address will be added to the hash
+ * list by ipvlan_open.
+ */
+ if (netif_running(ipvlan->dev))
+ ipvlan_ht_addr_add(ipvlan, addr);
+
+ return 0;
+}
+
+static void ipvlan_del_addr(struct ipvl_dev *ipvlan, void *iaddr, bool is_v6)
+{
+ struct ipvl_addr *addr;
+
+ spin_lock_bh(&ipvlan->addrs_lock);
+ addr = ipvlan_find_addr(ipvlan, iaddr, is_v6);
+ if (!addr) {
+ spin_unlock_bh(&ipvlan->addrs_lock);
+ return;
+ }
+
+ ipvlan_ht_addr_del(addr);
+ list_del_rcu(&addr->anode);
+ spin_unlock_bh(&ipvlan->addrs_lock);
+ kfree_rcu(addr, rcu);
+}
+
+static bool ipvlan_is_valid_dev(const struct net_device *dev)
+{
+ struct ipvl_dev *ipvlan = netdev_priv(dev);
+
+ if (!netif_is_ipvlan(dev))
+ return false;
+
+ if (!ipvlan || !ipvlan->port)
+ return false;
+
+ return true;
+}
+
+#if IS_ENABLED(CONFIG_IPV6)
+static int ipvlan_add_addr6(struct ipvl_dev *ipvlan, struct in6_addr *ip6_addr)
+{
+ int ret = -EINVAL;
+
+ spin_lock_bh(&ipvlan->addrs_lock);
+ if (ipvlan_addr_busy(ipvlan->port, ip6_addr, true))
+ netif_err(ipvlan, ifup, ipvlan->dev,
+ "Failed to add IPv6=%pI6c addr for %s intf\n",
+ ip6_addr, ipvlan->dev->name);
+ else
+ ret = ipvlan_add_addr(ipvlan, ip6_addr, true);
+ spin_unlock_bh(&ipvlan->addrs_lock);
+ return ret;
+}
+
+static void ipvlan_del_addr6(struct ipvl_dev *ipvlan, struct in6_addr *ip6_addr)
+{
+ return ipvlan_del_addr(ipvlan, ip6_addr, true);
+}
+
+static int ipvlan_addr6_event(struct notifier_block *unused,
+ unsigned long event, void *ptr)
+{
+ struct inet6_ifaddr *if6 = (struct inet6_ifaddr *)ptr;
+ struct net_device *dev = (struct net_device *)if6->idev->dev;
+ struct ipvl_dev *ipvlan = netdev_priv(dev);
+
+ if (!ipvlan_is_valid_dev(dev))
+ return NOTIFY_DONE;
+
+ switch (event) {
+ case NETDEV_UP:
+ if (ipvlan_add_addr6(ipvlan, &if6->addr))
+ return NOTIFY_BAD;
+ break;
+
+ case NETDEV_DOWN:
+ ipvlan_del_addr6(ipvlan, &if6->addr);
+ break;
+ }
+
+ return NOTIFY_OK;
+}
+
+static int ipvlan_addr6_validator_event(struct notifier_block *unused,
+ unsigned long event, void *ptr)
+{
+ struct in6_validator_info *i6vi = (struct in6_validator_info *)ptr;
+ struct net_device *dev = (struct net_device *)i6vi->i6vi_dev->dev;
+ struct ipvl_dev *ipvlan = netdev_priv(dev);
+
+ if (!ipvlan_is_valid_dev(dev))
+ return NOTIFY_DONE;
+
+ switch (event) {
+ case NETDEV_UP:
+ if (ipvlan_addr_busy(ipvlan->port, &i6vi->i6vi_addr, true)) {
+ NL_SET_ERR_MSG(i6vi->extack,
+ "Address already assigned to an ipvlan device");
+ return notifier_from_errno(-EADDRINUSE);
+ }
+ break;
+ }
+
+ return NOTIFY_OK;
+}
+#endif
+
+static int ipvlan_add_addr4(struct ipvl_dev *ipvlan, struct in_addr *ip4_addr)
+{
+ int ret = -EINVAL;
+
+ spin_lock_bh(&ipvlan->addrs_lock);
+ if (ipvlan_addr_busy(ipvlan->port, ip4_addr, false))
+ netif_err(ipvlan, ifup, ipvlan->dev,
+ "Failed to add IPv4=%pI4 on %s intf.\n",
+ ip4_addr, ipvlan->dev->name);
+ else
+ ret = ipvlan_add_addr(ipvlan, ip4_addr, false);
+ spin_unlock_bh(&ipvlan->addrs_lock);
+ return ret;
+}
+
+static void ipvlan_del_addr4(struct ipvl_dev *ipvlan, struct in_addr *ip4_addr)
+{
+ return ipvlan_del_addr(ipvlan, ip4_addr, false);
+}
+
+static int ipvlan_addr4_event(struct notifier_block *unused,
+ unsigned long event, void *ptr)
+{
+ struct in_ifaddr *if4 = (struct in_ifaddr *)ptr;
+ struct net_device *dev = (struct net_device *)if4->ifa_dev->dev;
+ struct ipvl_dev *ipvlan = netdev_priv(dev);
+ struct in_addr ip4_addr;
+
+ if (!ipvlan_is_valid_dev(dev))
+ return NOTIFY_DONE;
+
+ switch (event) {
+ case NETDEV_UP:
+ ip4_addr.s_addr = if4->ifa_address;
+ if (ipvlan_add_addr4(ipvlan, &ip4_addr))
+ return NOTIFY_BAD;
+ break;
+
+ case NETDEV_DOWN:
+ ip4_addr.s_addr = if4->ifa_address;
+ ipvlan_del_addr4(ipvlan, &ip4_addr);
+ break;
+ }
+
+ return NOTIFY_OK;
+}
+
+static int ipvlan_addr4_validator_event(struct notifier_block *unused,
+ unsigned long event, void *ptr)
+{
+ struct in_validator_info *ivi = (struct in_validator_info *)ptr;
+ struct net_device *dev = (struct net_device *)ivi->ivi_dev->dev;
+ struct ipvl_dev *ipvlan = netdev_priv(dev);
+
+ if (!ipvlan_is_valid_dev(dev))
+ return NOTIFY_DONE;
+
+ switch (event) {
+ case NETDEV_UP:
+ if (ipvlan_addr_busy(ipvlan->port, &ivi->ivi_addr, false)) {
+ NL_SET_ERR_MSG(ivi->extack,
+ "Address already assigned to an ipvlan device");
+ return notifier_from_errno(-EADDRINUSE);
+ }
+ break;
+ }
+
+ return NOTIFY_OK;
+}
+
+static struct notifier_block ipvlan_addr4_notifier_block __read_mostly = {
+ .notifier_call = ipvlan_addr4_event,
+};
+
+static struct notifier_block ipvlan_addr4_vtor_notifier_block __read_mostly = {
+ .notifier_call = ipvlan_addr4_validator_event,
+};
+
+static struct notifier_block ipvlan_notifier_block __read_mostly = {
+ .notifier_call = ipvlan_device_event,
+};
+
+#if IS_ENABLED(CONFIG_IPV6)
+static struct notifier_block ipvlan_addr6_notifier_block __read_mostly = {
+ .notifier_call = ipvlan_addr6_event,
+};
+
+static struct notifier_block ipvlan_addr6_vtor_notifier_block __read_mostly = {
+ .notifier_call = ipvlan_addr6_validator_event,
+};
+#endif
+
+static int __init ipvlan_init_module(void)
+{
+ int err;
+
+ ipvlan_init_secret();
+ register_netdevice_notifier(&ipvlan_notifier_block);
+#if IS_ENABLED(CONFIG_IPV6)
+ register_inet6addr_notifier(&ipvlan_addr6_notifier_block);
+ register_inet6addr_validator_notifier(
+ &ipvlan_addr6_vtor_notifier_block);
+#endif
+ register_inetaddr_notifier(&ipvlan_addr4_notifier_block);
+ register_inetaddr_validator_notifier(&ipvlan_addr4_vtor_notifier_block);
+
+ err = ipvlan_l3s_init();
+ if (err < 0)
+ goto error;
+
+ err = ipvlan_link_register(&ipvlan_link_ops);
+ if (err < 0) {
+ ipvlan_l3s_cleanup();
+ goto error;
+ }
+
+ return 0;
+error:
+ unregister_inetaddr_notifier(&ipvlan_addr4_notifier_block);
+ unregister_inetaddr_validator_notifier(
+ &ipvlan_addr4_vtor_notifier_block);
+#if IS_ENABLED(CONFIG_IPV6)
+ unregister_inet6addr_notifier(&ipvlan_addr6_notifier_block);
+ unregister_inet6addr_validator_notifier(
+ &ipvlan_addr6_vtor_notifier_block);
+#endif
+ unregister_netdevice_notifier(&ipvlan_notifier_block);
+ return err;
+}
+
+static void __exit ipvlan_cleanup_module(void)
+{
+ rtnl_link_unregister(&ipvlan_link_ops);
+ ipvlan_l3s_cleanup();
+ unregister_netdevice_notifier(&ipvlan_notifier_block);
+ unregister_inetaddr_notifier(&ipvlan_addr4_notifier_block);
+ unregister_inetaddr_validator_notifier(
+ &ipvlan_addr4_vtor_notifier_block);
+#if IS_ENABLED(CONFIG_IPV6)
+ unregister_inet6addr_notifier(&ipvlan_addr6_notifier_block);
+ unregister_inet6addr_validator_notifier(
+ &ipvlan_addr6_vtor_notifier_block);
+#endif
+}
+
+module_init(ipvlan_init_module);
+module_exit(ipvlan_cleanup_module);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Mahesh Bandewar <maheshb@google.com>");
+MODULE_DESCRIPTION("Driver for L3 (IPv6/IPv4) based VLANs");
+MODULE_ALIAS_RTNL_LINK("ipvlan");
diff --git a/drivers/net/ipvlan/ipvtap.c b/drivers/net/ipvlan/ipvtap.c
new file mode 100644
index 000000000..cbabca167
--- /dev/null
+++ b/drivers/net/ipvlan/ipvtap.c
@@ -0,0 +1,241 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <linux/etherdevice.h>
+#include "ipvlan.h"
+#include <linux/if_vlan.h>
+#include <linux/if_tap.h>
+#include <linux/interrupt.h>
+#include <linux/nsproxy.h>
+#include <linux/compat.h>
+#include <linux/if_tun.h>
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <linux/cache.h>
+#include <linux/sched.h>
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <linux/wait.h>
+#include <linux/cdev.h>
+#include <linux/idr.h>
+#include <linux/fs.h>
+#include <linux/uio.h>
+
+#include <net/net_namespace.h>
+#include <net/rtnetlink.h>
+#include <net/sock.h>
+#include <linux/virtio_net.h>
+
+#define TUN_OFFLOADS (NETIF_F_HW_CSUM | NETIF_F_TSO_ECN | NETIF_F_TSO | \
+ NETIF_F_TSO6)
+
+static dev_t ipvtap_major;
+static struct cdev ipvtap_cdev;
+
+static const void *ipvtap_net_namespace(struct device *d)
+{
+ struct net_device *dev = to_net_dev(d->parent);
+ return dev_net(dev);
+}
+
+static struct class ipvtap_class = {
+ .name = "ipvtap",
+ .owner = THIS_MODULE,
+ .ns_type = &net_ns_type_operations,
+ .namespace = ipvtap_net_namespace,
+};
+
+struct ipvtap_dev {
+ struct ipvl_dev vlan;
+ struct tap_dev tap;
+};
+
+static void ipvtap_count_tx_dropped(struct tap_dev *tap)
+{
+ struct ipvtap_dev *vlantap = container_of(tap, struct ipvtap_dev, tap);
+ struct ipvl_dev *vlan = &vlantap->vlan;
+
+ this_cpu_inc(vlan->pcpu_stats->tx_drps);
+}
+
+static void ipvtap_count_rx_dropped(struct tap_dev *tap)
+{
+ struct ipvtap_dev *vlantap = container_of(tap, struct ipvtap_dev, tap);
+ struct ipvl_dev *vlan = &vlantap->vlan;
+
+ ipvlan_count_rx(vlan, 0, 0, 0);
+}
+
+static void ipvtap_update_features(struct tap_dev *tap,
+ netdev_features_t features)
+{
+ struct ipvtap_dev *vlantap = container_of(tap, struct ipvtap_dev, tap);
+ struct ipvl_dev *vlan = &vlantap->vlan;
+
+ vlan->sfeatures = features;
+ netdev_update_features(vlan->dev);
+}
+
+static int ipvtap_newlink(struct net *src_net, struct net_device *dev,
+ struct nlattr *tb[], struct nlattr *data[],
+ struct netlink_ext_ack *extack)
+{
+ struct ipvtap_dev *vlantap = netdev_priv(dev);
+ int err;
+
+ INIT_LIST_HEAD(&vlantap->tap.queue_list);
+
+ /* Since macvlan supports all offloads by default, make
+ * tap support all offloads also.
+ */
+ vlantap->tap.tap_features = TUN_OFFLOADS;
+ vlantap->tap.count_tx_dropped = ipvtap_count_tx_dropped;
+ vlantap->tap.update_features = ipvtap_update_features;
+ vlantap->tap.count_rx_dropped = ipvtap_count_rx_dropped;
+
+ err = netdev_rx_handler_register(dev, tap_handle_frame, &vlantap->tap);
+ if (err)
+ return err;
+
+ /* Don't put anything that may fail after macvlan_common_newlink
+ * because we can't undo what it does.
+ */
+ err = ipvlan_link_new(src_net, dev, tb, data, extack);
+ if (err) {
+ netdev_rx_handler_unregister(dev);
+ return err;
+ }
+
+ vlantap->tap.dev = vlantap->vlan.dev;
+
+ return err;
+}
+
+static void ipvtap_dellink(struct net_device *dev,
+ struct list_head *head)
+{
+ struct ipvtap_dev *vlan = netdev_priv(dev);
+
+ netdev_rx_handler_unregister(dev);
+ tap_del_queues(&vlan->tap);
+ ipvlan_link_delete(dev, head);
+}
+
+static void ipvtap_setup(struct net_device *dev)
+{
+ ipvlan_link_setup(dev);
+ dev->tx_queue_len = TUN_READQ_SIZE;
+ dev->priv_flags &= ~IFF_NO_QUEUE;
+}
+
+static struct rtnl_link_ops ipvtap_link_ops __read_mostly = {
+ .kind = "ipvtap",
+ .setup = ipvtap_setup,
+ .newlink = ipvtap_newlink,
+ .dellink = ipvtap_dellink,
+ .priv_size = sizeof(struct ipvtap_dev),
+};
+
+static int ipvtap_device_event(struct notifier_block *unused,
+ unsigned long event, void *ptr)
+{
+ struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+ struct ipvtap_dev *vlantap;
+ struct device *classdev;
+ dev_t devt;
+ int err;
+ char tap_name[IFNAMSIZ];
+
+ if (dev->rtnl_link_ops != &ipvtap_link_ops)
+ return NOTIFY_DONE;
+
+ snprintf(tap_name, IFNAMSIZ, "tap%d", dev->ifindex);
+ vlantap = netdev_priv(dev);
+
+ switch (event) {
+ case NETDEV_REGISTER:
+ /* Create the device node here after the network device has
+ * been registered but before register_netdevice has
+ * finished running.
+ */
+ err = tap_get_minor(ipvtap_major, &vlantap->tap);
+ if (err)
+ return notifier_from_errno(err);
+
+ devt = MKDEV(MAJOR(ipvtap_major), vlantap->tap.minor);
+ classdev = device_create(&ipvtap_class, &dev->dev, devt,
+ dev, "%s", tap_name);
+ if (IS_ERR(classdev)) {
+ tap_free_minor(ipvtap_major, &vlantap->tap);
+ return notifier_from_errno(PTR_ERR(classdev));
+ }
+ err = sysfs_create_link(&dev->dev.kobj, &classdev->kobj,
+ tap_name);
+ if (err)
+ return notifier_from_errno(err);
+ break;
+ case NETDEV_UNREGISTER:
+ /* vlan->minor == 0 if NETDEV_REGISTER above failed */
+ if (vlantap->tap.minor == 0)
+ break;
+ sysfs_remove_link(&dev->dev.kobj, tap_name);
+ devt = MKDEV(MAJOR(ipvtap_major), vlantap->tap.minor);
+ device_destroy(&ipvtap_class, devt);
+ tap_free_minor(ipvtap_major, &vlantap->tap);
+ break;
+ case NETDEV_CHANGE_TX_QUEUE_LEN:
+ if (tap_queue_resize(&vlantap->tap))
+ return NOTIFY_BAD;
+ break;
+ }
+
+ return NOTIFY_DONE;
+}
+
+static struct notifier_block ipvtap_notifier_block __read_mostly = {
+ .notifier_call = ipvtap_device_event,
+};
+
+static int __init ipvtap_init(void)
+{
+ int err;
+
+ err = tap_create_cdev(&ipvtap_cdev, &ipvtap_major, "ipvtap",
+ THIS_MODULE);
+ if (err)
+ goto out1;
+
+ err = class_register(&ipvtap_class);
+ if (err)
+ goto out2;
+
+ err = register_netdevice_notifier(&ipvtap_notifier_block);
+ if (err)
+ goto out3;
+
+ err = ipvlan_link_register(&ipvtap_link_ops);
+ if (err)
+ goto out4;
+
+ return 0;
+
+out4:
+ unregister_netdevice_notifier(&ipvtap_notifier_block);
+out3:
+ class_unregister(&ipvtap_class);
+out2:
+ tap_destroy_cdev(ipvtap_major, &ipvtap_cdev);
+out1:
+ return err;
+}
+module_init(ipvtap_init);
+
+static void __exit ipvtap_exit(void)
+{
+ rtnl_link_unregister(&ipvtap_link_ops);
+ unregister_netdevice_notifier(&ipvtap_notifier_block);
+ class_unregister(&ipvtap_class);
+ tap_destroy_cdev(ipvtap_major, &ipvtap_cdev);
+}
+module_exit(ipvtap_exit);
+MODULE_ALIAS_RTNL_LINK("ipvtap");
+MODULE_AUTHOR("Sainath Grandhi <sainath.grandhi@intel.com>");
+MODULE_LICENSE("GPL");