linux/drivers/net/macvlan.c

1146 lines
28 KiB
C
Raw Normal View History

/*
* Copyright (c) 2007 Patrick McHardy <kaber@trash.net>
*
* 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.
*
* The code this is based on carried the following copyright notice:
* ---
* (C) Copyright 2001-2006
* Alex Zeffertt, Cambridge Broadband Ltd, ajz@cambridgebroadband.com
* Re-worked by Ben Greear <greearb@candelatech.com>
* ---
*/
#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/errno.h>
#include <linux/slab.h>
#include <linux/string.h>
#include <linux/rculist.h>
#include <linux/notifier.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/ethtool.h>
#include <linux/if_arp.h>
#include <linux/if_vlan.h>
#include <linux/if_link.h>
#include <linux/if_macvlan.h>
#include <linux/hash.h>
#include <linux/workqueue.h>
#include <net/rtnetlink.h>
macvlan: implement bridge, VEPA and private mode This allows each macvlan slave device to be in one of three modes, depending on the use case: MACVLAN_PRIVATE: The device never communicates with any other device on the same upper_dev. This even includes frames coming back from a reflective relay, where supported by the adjacent bridge. MACVLAN_VEPA: The new Virtual Ethernet Port Aggregator (VEPA) mode, we assume that the adjacent bridge returns all frames where both source and destination are local to the macvlan port, i.e. the bridge is set up as a reflective relay. Broadcast frames coming in from the upper_dev get flooded to all macvlan interfaces in VEPA mode. We never deliver any frames locally. MACVLAN_BRIDGE: We provide the behavior of a simple bridge between different macvlan interfaces on the same port. Frames from one interface to another one get delivered directly and are not sent out externally. Broadcast frames get flooded to all other bridge ports and to the external interface, but when they come back from a reflective relay, we don't deliver them again. Since we know all the MAC addresses, the macvlan bridge mode does not require learning or STP like the bridge module does. Based on an earlier patch "macvlan: Reflect macvlan packets meant for other macvlan devices" by Eric Biederman. Signed-off-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Patrick McHardy <kaber@trash.net> Cc: Eric Biederman <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-11-26 06:07:10 +00:00
#include <net/xfrm.h>
#define MACVLAN_HASH_SIZE (1 << BITS_PER_BYTE)
struct macvlan_port {
struct net_device *dev;
struct hlist_head vlan_hash[MACVLAN_HASH_SIZE];
struct list_head vlans;
struct rcu_head rcu;
struct sk_buff_head bc_queue;
struct work_struct bc_work;
bool passthru;
int count;
};
struct macvlan_skb_cb {
const struct macvlan_dev *src;
};
#define MACVLAN_SKB_CB(__skb) ((struct macvlan_skb_cb *)&((__skb)->cb[0]))
static void macvlan_port_destroy(struct net_device *dev);
static struct macvlan_port *macvlan_port_get_rcu(const struct net_device *dev)
{
return rcu_dereference(dev->rx_handler_data);
}
static struct macvlan_port *macvlan_port_get_rtnl(const struct net_device *dev)
{
return rtnl_dereference(dev->rx_handler_data);
}
#define macvlan_port_exists(dev) (dev->priv_flags & IFF_MACVLAN_PORT)
static struct macvlan_dev *macvlan_hash_lookup(const struct macvlan_port *port,
const unsigned char *addr)
{
struct macvlan_dev *vlan;
hlist: drop the node parameter from iterators I'm not sure why, but the hlist for each entry iterators were conceived list_for_each_entry(pos, head, member) The hlist ones were greedy and wanted an extra parameter: hlist_for_each_entry(tpos, pos, head, member) Why did they need an extra pos parameter? I'm not quite sure. Not only they don't really need it, it also prevents the iterator from looking exactly like the list iterator, which is unfortunate. Besides the semantic patch, there was some manual work required: - Fix up the actual hlist iterators in linux/list.h - Fix up the declaration of other iterators based on the hlist ones. - A very small amount of places were using the 'node' parameter, this was modified to use 'obj->member' instead. - Coccinelle didn't handle the hlist_for_each_entry_safe iterator properly, so those had to be fixed up manually. The semantic patch which is mostly the work of Peter Senna Tschudin is here: @@ iterator name hlist_for_each_entry, hlist_for_each_entry_continue, hlist_for_each_entry_from, hlist_for_each_entry_rcu, hlist_for_each_entry_rcu_bh, hlist_for_each_entry_continue_rcu_bh, for_each_busy_worker, ax25_uid_for_each, ax25_for_each, inet_bind_bucket_for_each, sctp_for_each_hentry, sk_for_each, sk_for_each_rcu, sk_for_each_from, sk_for_each_safe, sk_for_each_bound, hlist_for_each_entry_safe, hlist_for_each_entry_continue_rcu, nr_neigh_for_each, nr_neigh_for_each_safe, nr_node_for_each, nr_node_for_each_safe, for_each_gfn_indirect_valid_sp, for_each_gfn_sp, for_each_host; type T; expression a,c,d,e; identifier b; statement S; @@ -T b; <+... when != b ( hlist_for_each_entry(a, - b, c, d) S | hlist_for_each_entry_continue(a, - b, c) S | hlist_for_each_entry_from(a, - b, c) S | hlist_for_each_entry_rcu(a, - b, c, d) S | hlist_for_each_entry_rcu_bh(a, - b, c, d) S | hlist_for_each_entry_continue_rcu_bh(a, - b, c) S | for_each_busy_worker(a, c, - b, d) S | ax25_uid_for_each(a, - b, c) S | ax25_for_each(a, - b, c) S | inet_bind_bucket_for_each(a, - b, c) S | sctp_for_each_hentry(a, - b, c) S | sk_for_each(a, - b, c) S | sk_for_each_rcu(a, - b, c) S | sk_for_each_from -(a, b) +(a) S + sk_for_each_from(a) S | sk_for_each_safe(a, - b, c, d) S | sk_for_each_bound(a, - b, c) S | hlist_for_each_entry_safe(a, - b, c, d, e) S | hlist_for_each_entry_continue_rcu(a, - b, c) S | nr_neigh_for_each(a, - b, c) S | nr_neigh_for_each_safe(a, - b, c, d) S | nr_node_for_each(a, - b, c) S | nr_node_for_each_safe(a, - b, c, d) S | - for_each_gfn_sp(a, c, d, b) S + for_each_gfn_sp(a, c, d) S | - for_each_gfn_indirect_valid_sp(a, c, d, b) S + for_each_gfn_indirect_valid_sp(a, c, d) S | for_each_host(a, - b, c) S | for_each_host_safe(a, - b, c, d) S | for_each_mesh_entry(a, - b, c, d) S ) ...+> [akpm@linux-foundation.org: drop bogus change from net/ipv4/raw.c] [akpm@linux-foundation.org: drop bogus hunk from net/ipv6/raw.c] [akpm@linux-foundation.org: checkpatch fixes] [akpm@linux-foundation.org: fix warnings] [akpm@linux-foudnation.org: redo intrusive kvm changes] Tested-by: Peter Senna Tschudin <peter.senna@gmail.com> Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Sasha Levin <sasha.levin@oracle.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Gleb Natapov <gleb@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-28 01:06:00 +00:00
hlist_for_each_entry_rcu(vlan, &port->vlan_hash[addr[5]], hlist) {
if (ether_addr_equal_64bits(vlan->dev->dev_addr, addr))
return vlan;
}
return NULL;
}
static void macvlan_hash_add(struct macvlan_dev *vlan)
{
struct macvlan_port *port = vlan->port;
const unsigned char *addr = vlan->dev->dev_addr;
hlist_add_head_rcu(&vlan->hlist, &port->vlan_hash[addr[5]]);
}
static void macvlan_hash_del(struct macvlan_dev *vlan, bool sync)
{
hlist_del_rcu(&vlan->hlist);
if (sync)
synchronize_rcu();
}
static void macvlan_hash_change_addr(struct macvlan_dev *vlan,
const unsigned char *addr)
{
macvlan_hash_del(vlan, true);
/* Now that we are unhashed it is safe to change the device
* address without confusing packet delivery.
*/
memcpy(vlan->dev->dev_addr, addr, ETH_ALEN);
macvlan_hash_add(vlan);
}
static int macvlan_addr_busy(const struct macvlan_port *port,
const unsigned char *addr)
{
/* Test to see if the specified multicast address is
* currently in use by the underlying device or
* another macvlan.
*/
if (ether_addr_equal_64bits(port->dev->dev_addr, addr))
return 1;
if (macvlan_hash_lookup(port, addr))
return 1;
return 0;
}
static int macvlan_broadcast_one(struct sk_buff *skb,
const struct macvlan_dev *vlan,
macvlan: implement bridge, VEPA and private mode This allows each macvlan slave device to be in one of three modes, depending on the use case: MACVLAN_PRIVATE: The device never communicates with any other device on the same upper_dev. This even includes frames coming back from a reflective relay, where supported by the adjacent bridge. MACVLAN_VEPA: The new Virtual Ethernet Port Aggregator (VEPA) mode, we assume that the adjacent bridge returns all frames where both source and destination are local to the macvlan port, i.e. the bridge is set up as a reflective relay. Broadcast frames coming in from the upper_dev get flooded to all macvlan interfaces in VEPA mode. We never deliver any frames locally. MACVLAN_BRIDGE: We provide the behavior of a simple bridge between different macvlan interfaces on the same port. Frames from one interface to another one get delivered directly and are not sent out externally. Broadcast frames get flooded to all other bridge ports and to the external interface, but when they come back from a reflective relay, we don't deliver them again. Since we know all the MAC addresses, the macvlan bridge mode does not require learning or STP like the bridge module does. Based on an earlier patch "macvlan: Reflect macvlan packets meant for other macvlan devices" by Eric Biederman. Signed-off-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Patrick McHardy <kaber@trash.net> Cc: Eric Biederman <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-11-26 06:07:10 +00:00
const struct ethhdr *eth, bool local)
{
struct net_device *dev = vlan->dev;
macvlan: implement bridge, VEPA and private mode This allows each macvlan slave device to be in one of three modes, depending on the use case: MACVLAN_PRIVATE: The device never communicates with any other device on the same upper_dev. This even includes frames coming back from a reflective relay, where supported by the adjacent bridge. MACVLAN_VEPA: The new Virtual Ethernet Port Aggregator (VEPA) mode, we assume that the adjacent bridge returns all frames where both source and destination are local to the macvlan port, i.e. the bridge is set up as a reflective relay. Broadcast frames coming in from the upper_dev get flooded to all macvlan interfaces in VEPA mode. We never deliver any frames locally. MACVLAN_BRIDGE: We provide the behavior of a simple bridge between different macvlan interfaces on the same port. Frames from one interface to another one get delivered directly and are not sent out externally. Broadcast frames get flooded to all other bridge ports and to the external interface, but when they come back from a reflective relay, we don't deliver them again. Since we know all the MAC addresses, the macvlan bridge mode does not require learning or STP like the bridge module does. Based on an earlier patch "macvlan: Reflect macvlan packets meant for other macvlan devices" by Eric Biederman. Signed-off-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Patrick McHardy <kaber@trash.net> Cc: Eric Biederman <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-11-26 06:07:10 +00:00
if (local)
return __dev_forward_skb(dev, skb);
macvlan: implement bridge, VEPA and private mode This allows each macvlan slave device to be in one of three modes, depending on the use case: MACVLAN_PRIVATE: The device never communicates with any other device on the same upper_dev. This even includes frames coming back from a reflective relay, where supported by the adjacent bridge. MACVLAN_VEPA: The new Virtual Ethernet Port Aggregator (VEPA) mode, we assume that the adjacent bridge returns all frames where both source and destination are local to the macvlan port, i.e. the bridge is set up as a reflective relay. Broadcast frames coming in from the upper_dev get flooded to all macvlan interfaces in VEPA mode. We never deliver any frames locally. MACVLAN_BRIDGE: We provide the behavior of a simple bridge between different macvlan interfaces on the same port. Frames from one interface to another one get delivered directly and are not sent out externally. Broadcast frames get flooded to all other bridge ports and to the external interface, but when they come back from a reflective relay, we don't deliver them again. Since we know all the MAC addresses, the macvlan bridge mode does not require learning or STP like the bridge module does. Based on an earlier patch "macvlan: Reflect macvlan packets meant for other macvlan devices" by Eric Biederman. Signed-off-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Patrick McHardy <kaber@trash.net> Cc: Eric Biederman <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-11-26 06:07:10 +00:00
skb->dev = dev;
if (ether_addr_equal_64bits(eth->h_dest, dev->broadcast))
skb->pkt_type = PACKET_BROADCAST;
else
skb->pkt_type = PACKET_MULTICAST;
return 0;
}
static u32 macvlan_hash_mix(const struct macvlan_dev *vlan)
{
return (u32)(((unsigned long)vlan) >> L1_CACHE_SHIFT);
}
static unsigned int mc_hash(const struct macvlan_dev *vlan,
const unsigned char *addr)
{
u32 val = __get_unaligned_cpu32(addr + 2);
val ^= macvlan_hash_mix(vlan);
return hash_32(val, MACVLAN_MC_FILTER_BITS);
}
static void macvlan_broadcast(struct sk_buff *skb,
macvlan: implement bridge, VEPA and private mode This allows each macvlan slave device to be in one of three modes, depending on the use case: MACVLAN_PRIVATE: The device never communicates with any other device on the same upper_dev. This even includes frames coming back from a reflective relay, where supported by the adjacent bridge. MACVLAN_VEPA: The new Virtual Ethernet Port Aggregator (VEPA) mode, we assume that the adjacent bridge returns all frames where both source and destination are local to the macvlan port, i.e. the bridge is set up as a reflective relay. Broadcast frames coming in from the upper_dev get flooded to all macvlan interfaces in VEPA mode. We never deliver any frames locally. MACVLAN_BRIDGE: We provide the behavior of a simple bridge between different macvlan interfaces on the same port. Frames from one interface to another one get delivered directly and are not sent out externally. Broadcast frames get flooded to all other bridge ports and to the external interface, but when they come back from a reflective relay, we don't deliver them again. Since we know all the MAC addresses, the macvlan bridge mode does not require learning or STP like the bridge module does. Based on an earlier patch "macvlan: Reflect macvlan packets meant for other macvlan devices" by Eric Biederman. Signed-off-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Patrick McHardy <kaber@trash.net> Cc: Eric Biederman <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-11-26 06:07:10 +00:00
const struct macvlan_port *port,
struct net_device *src,
enum macvlan_mode mode)
{
const struct ethhdr *eth = eth_hdr(skb);
const struct macvlan_dev *vlan;
struct sk_buff *nskb;
unsigned int i;
int err;
unsigned int hash;
if (skb->protocol == htons(ETH_P_PAUSE))
return;
for (i = 0; i < MACVLAN_HASH_SIZE; i++) {
hlist: drop the node parameter from iterators I'm not sure why, but the hlist for each entry iterators were conceived list_for_each_entry(pos, head, member) The hlist ones were greedy and wanted an extra parameter: hlist_for_each_entry(tpos, pos, head, member) Why did they need an extra pos parameter? I'm not quite sure. Not only they don't really need it, it also prevents the iterator from looking exactly like the list iterator, which is unfortunate. Besides the semantic patch, there was some manual work required: - Fix up the actual hlist iterators in linux/list.h - Fix up the declaration of other iterators based on the hlist ones. - A very small amount of places were using the 'node' parameter, this was modified to use 'obj->member' instead. - Coccinelle didn't handle the hlist_for_each_entry_safe iterator properly, so those had to be fixed up manually. The semantic patch which is mostly the work of Peter Senna Tschudin is here: @@ iterator name hlist_for_each_entry, hlist_for_each_entry_continue, hlist_for_each_entry_from, hlist_for_each_entry_rcu, hlist_for_each_entry_rcu_bh, hlist_for_each_entry_continue_rcu_bh, for_each_busy_worker, ax25_uid_for_each, ax25_for_each, inet_bind_bucket_for_each, sctp_for_each_hentry, sk_for_each, sk_for_each_rcu, sk_for_each_from, sk_for_each_safe, sk_for_each_bound, hlist_for_each_entry_safe, hlist_for_each_entry_continue_rcu, nr_neigh_for_each, nr_neigh_for_each_safe, nr_node_for_each, nr_node_for_each_safe, for_each_gfn_indirect_valid_sp, for_each_gfn_sp, for_each_host; type T; expression a,c,d,e; identifier b; statement S; @@ -T b; <+... when != b ( hlist_for_each_entry(a, - b, c, d) S | hlist_for_each_entry_continue(a, - b, c) S | hlist_for_each_entry_from(a, - b, c) S | hlist_for_each_entry_rcu(a, - b, c, d) S | hlist_for_each_entry_rcu_bh(a, - b, c, d) S | hlist_for_each_entry_continue_rcu_bh(a, - b, c) S | for_each_busy_worker(a, c, - b, d) S | ax25_uid_for_each(a, - b, c) S | ax25_for_each(a, - b, c) S | inet_bind_bucket_for_each(a, - b, c) S | sctp_for_each_hentry(a, - b, c) S | sk_for_each(a, - b, c) S | sk_for_each_rcu(a, - b, c) S | sk_for_each_from -(a, b) +(a) S + sk_for_each_from(a) S | sk_for_each_safe(a, - b, c, d) S | sk_for_each_bound(a, - b, c) S | hlist_for_each_entry_safe(a, - b, c, d, e) S | hlist_for_each_entry_continue_rcu(a, - b, c) S | nr_neigh_for_each(a, - b, c) S | nr_neigh_for_each_safe(a, - b, c, d) S | nr_node_for_each(a, - b, c) S | nr_node_for_each_safe(a, - b, c, d) S | - for_each_gfn_sp(a, c, d, b) S + for_each_gfn_sp(a, c, d) S | - for_each_gfn_indirect_valid_sp(a, c, d, b) S + for_each_gfn_indirect_valid_sp(a, c, d) S | for_each_host(a, - b, c) S | for_each_host_safe(a, - b, c, d) S | for_each_mesh_entry(a, - b, c, d) S ) ...+> [akpm@linux-foundation.org: drop bogus change from net/ipv4/raw.c] [akpm@linux-foundation.org: drop bogus hunk from net/ipv6/raw.c] [akpm@linux-foundation.org: checkpatch fixes] [akpm@linux-foundation.org: fix warnings] [akpm@linux-foudnation.org: redo intrusive kvm changes] Tested-by: Peter Senna Tschudin <peter.senna@gmail.com> Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Sasha Levin <sasha.levin@oracle.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Gleb Natapov <gleb@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-28 01:06:00 +00:00
hlist_for_each_entry_rcu(vlan, &port->vlan_hash[i], hlist) {
macvlan: implement bridge, VEPA and private mode This allows each macvlan slave device to be in one of three modes, depending on the use case: MACVLAN_PRIVATE: The device never communicates with any other device on the same upper_dev. This even includes frames coming back from a reflective relay, where supported by the adjacent bridge. MACVLAN_VEPA: The new Virtual Ethernet Port Aggregator (VEPA) mode, we assume that the adjacent bridge returns all frames where both source and destination are local to the macvlan port, i.e. the bridge is set up as a reflective relay. Broadcast frames coming in from the upper_dev get flooded to all macvlan interfaces in VEPA mode. We never deliver any frames locally. MACVLAN_BRIDGE: We provide the behavior of a simple bridge between different macvlan interfaces on the same port. Frames from one interface to another one get delivered directly and are not sent out externally. Broadcast frames get flooded to all other bridge ports and to the external interface, but when they come back from a reflective relay, we don't deliver them again. Since we know all the MAC addresses, the macvlan bridge mode does not require learning or STP like the bridge module does. Based on an earlier patch "macvlan: Reflect macvlan packets meant for other macvlan devices" by Eric Biederman. Signed-off-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Patrick McHardy <kaber@trash.net> Cc: Eric Biederman <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-11-26 06:07:10 +00:00
if (vlan->dev == src || !(vlan->mode & mode))
continue;
hash = mc_hash(vlan, eth->h_dest);
if (!test_bit(hash, vlan->mc_filter))
continue;
err = NET_RX_DROP;
nskb = skb_clone(skb, GFP_ATOMIC);
if (likely(nskb))
err = macvlan_broadcast_one(
nskb, vlan, eth,
mode == MACVLAN_MODE_BRIDGE) ?:
netif_rx_ni(nskb);
macvlan_count_rx(vlan, skb->len + ETH_HLEN,
err == NET_RX_SUCCESS, 1);
}
}
}
static void macvlan_process_broadcast(struct work_struct *w)
{
struct macvlan_port *port = container_of(w, struct macvlan_port,
bc_work);
struct sk_buff *skb;
struct sk_buff_head list;
skb_queue_head_init(&list);
spin_lock_bh(&port->bc_queue.lock);
skb_queue_splice_tail_init(&port->bc_queue, &list);
spin_unlock_bh(&port->bc_queue.lock);
while ((skb = __skb_dequeue(&list))) {
const struct macvlan_dev *src = MACVLAN_SKB_CB(skb)->src;
rcu_read_lock();
macvlan: implement bridge, VEPA and private mode This allows each macvlan slave device to be in one of three modes, depending on the use case: MACVLAN_PRIVATE: The device never communicates with any other device on the same upper_dev. This even includes frames coming back from a reflective relay, where supported by the adjacent bridge. MACVLAN_VEPA: The new Virtual Ethernet Port Aggregator (VEPA) mode, we assume that the adjacent bridge returns all frames where both source and destination are local to the macvlan port, i.e. the bridge is set up as a reflective relay. Broadcast frames coming in from the upper_dev get flooded to all macvlan interfaces in VEPA mode. We never deliver any frames locally. MACVLAN_BRIDGE: We provide the behavior of a simple bridge between different macvlan interfaces on the same port. Frames from one interface to another one get delivered directly and are not sent out externally. Broadcast frames get flooded to all other bridge ports and to the external interface, but when they come back from a reflective relay, we don't deliver them again. Since we know all the MAC addresses, the macvlan bridge mode does not require learning or STP like the bridge module does. Based on an earlier patch "macvlan: Reflect macvlan packets meant for other macvlan devices" by Eric Biederman. Signed-off-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Patrick McHardy <kaber@trash.net> Cc: Eric Biederman <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-11-26 06:07:10 +00:00
if (!src)
/* frame comes from an external address */
macvlan_broadcast(skb, port, NULL,
MACVLAN_MODE_PRIVATE |
MACVLAN_MODE_VEPA |
MACVLAN_MODE_PASSTHRU|
macvlan: implement bridge, VEPA and private mode This allows each macvlan slave device to be in one of three modes, depending on the use case: MACVLAN_PRIVATE: The device never communicates with any other device on the same upper_dev. This even includes frames coming back from a reflective relay, where supported by the adjacent bridge. MACVLAN_VEPA: The new Virtual Ethernet Port Aggregator (VEPA) mode, we assume that the adjacent bridge returns all frames where both source and destination are local to the macvlan port, i.e. the bridge is set up as a reflective relay. Broadcast frames coming in from the upper_dev get flooded to all macvlan interfaces in VEPA mode. We never deliver any frames locally. MACVLAN_BRIDGE: We provide the behavior of a simple bridge between different macvlan interfaces on the same port. Frames from one interface to another one get delivered directly and are not sent out externally. Broadcast frames get flooded to all other bridge ports and to the external interface, but when they come back from a reflective relay, we don't deliver them again. Since we know all the MAC addresses, the macvlan bridge mode does not require learning or STP like the bridge module does. Based on an earlier patch "macvlan: Reflect macvlan packets meant for other macvlan devices" by Eric Biederman. Signed-off-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Patrick McHardy <kaber@trash.net> Cc: Eric Biederman <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-11-26 06:07:10 +00:00
MACVLAN_MODE_BRIDGE);
else if (src->mode == MACVLAN_MODE_VEPA)
/* flood to everyone except source */
macvlan_broadcast(skb, port, src->dev,
MACVLAN_MODE_VEPA |
MACVLAN_MODE_BRIDGE);
else
macvlan: implement bridge, VEPA and private mode This allows each macvlan slave device to be in one of three modes, depending on the use case: MACVLAN_PRIVATE: The device never communicates with any other device on the same upper_dev. This even includes frames coming back from a reflective relay, where supported by the adjacent bridge. MACVLAN_VEPA: The new Virtual Ethernet Port Aggregator (VEPA) mode, we assume that the adjacent bridge returns all frames where both source and destination are local to the macvlan port, i.e. the bridge is set up as a reflective relay. Broadcast frames coming in from the upper_dev get flooded to all macvlan interfaces in VEPA mode. We never deliver any frames locally. MACVLAN_BRIDGE: We provide the behavior of a simple bridge between different macvlan interfaces on the same port. Frames from one interface to another one get delivered directly and are not sent out externally. Broadcast frames get flooded to all other bridge ports and to the external interface, but when they come back from a reflective relay, we don't deliver them again. Since we know all the MAC addresses, the macvlan bridge mode does not require learning or STP like the bridge module does. Based on an earlier patch "macvlan: Reflect macvlan packets meant for other macvlan devices" by Eric Biederman. Signed-off-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Patrick McHardy <kaber@trash.net> Cc: Eric Biederman <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-11-26 06:07:10 +00:00
/*
* flood only to VEPA ports, bridge ports
* already saw the frame on the way out.
*/
macvlan_broadcast(skb, port, src->dev,
MACVLAN_MODE_VEPA);
rcu_read_unlock();
kfree_skb(skb);
}
}
static void macvlan_broadcast_enqueue(struct macvlan_port *port,
struct sk_buff *skb)
{
struct sk_buff *nskb;
int err = -ENOMEM;
nskb = skb_clone(skb, GFP_ATOMIC);
if (!nskb)
goto err;
spin_lock(&port->bc_queue.lock);
if (skb_queue_len(&port->bc_queue) < skb->dev->tx_queue_len) {
__skb_queue_tail(&port->bc_queue, nskb);
err = 0;
}
spin_unlock(&port->bc_queue.lock);
if (err)
goto free_nskb;
schedule_work(&port->bc_work);
return;
free_nskb:
kfree_skb(nskb);
err:
atomic_long_inc(&skb->dev->rx_dropped);
}
/* called under rcu_read_lock() from netif_receive_skb */
static rx_handler_result_t macvlan_handle_frame(struct sk_buff **pskb)
{
struct macvlan_port *port;
struct sk_buff *skb = *pskb;
const struct ethhdr *eth = eth_hdr(skb);
const struct macvlan_dev *vlan;
const struct macvlan_dev *src;
struct net_device *dev;
unsigned int len = 0;
int ret = NET_RX_DROP;
port = macvlan_port_get_rcu(skb->dev);
if (is_multicast_ether_addr(eth->h_dest)) {
skb = ip_check_defrag(skb, IP_DEFRAG_MACVLAN);
if (!skb)
return RX_HANDLER_CONSUMED;
eth = eth_hdr(skb);
src = macvlan_hash_lookup(port, eth->h_source);
if (src && src->mode != MACVLAN_MODE_VEPA &&
src->mode != MACVLAN_MODE_BRIDGE) {
/* forward to original port. */
vlan = src;
ret = macvlan_broadcast_one(skb, vlan, eth, 0) ?:
netif_rx(skb);
goto out;
}
MACVLAN_SKB_CB(skb)->src = src;
macvlan_broadcast_enqueue(port, skb);
return RX_HANDLER_PASS;
}
if (port->passthru)
vlan = list_first_or_null_rcu(&port->vlans,
struct macvlan_dev, list);
else
vlan = macvlan_hash_lookup(port, eth->h_dest);
if (vlan == NULL)
return RX_HANDLER_PASS;
dev = vlan->dev;
if (unlikely(!(dev->flags & IFF_UP))) {
kfree_skb(skb);
return RX_HANDLER_CONSUMED;
}
len = skb->len + ETH_HLEN;
skb = skb_share_check(skb, GFP_ATOMIC);
if (!skb)
goto out;
skb->dev = dev;
skb->pkt_type = PACKET_HOST;
ret = netif_rx(skb);
out:
macvlan_count_rx(vlan, len, ret == NET_RX_SUCCESS, 0);
return RX_HANDLER_CONSUMED;
}
macvlan: implement bridge, VEPA and private mode This allows each macvlan slave device to be in one of three modes, depending on the use case: MACVLAN_PRIVATE: The device never communicates with any other device on the same upper_dev. This even includes frames coming back from a reflective relay, where supported by the adjacent bridge. MACVLAN_VEPA: The new Virtual Ethernet Port Aggregator (VEPA) mode, we assume that the adjacent bridge returns all frames where both source and destination are local to the macvlan port, i.e. the bridge is set up as a reflective relay. Broadcast frames coming in from the upper_dev get flooded to all macvlan interfaces in VEPA mode. We never deliver any frames locally. MACVLAN_BRIDGE: We provide the behavior of a simple bridge between different macvlan interfaces on the same port. Frames from one interface to another one get delivered directly and are not sent out externally. Broadcast frames get flooded to all other bridge ports and to the external interface, but when they come back from a reflective relay, we don't deliver them again. Since we know all the MAC addresses, the macvlan bridge mode does not require learning or STP like the bridge module does. Based on an earlier patch "macvlan: Reflect macvlan packets meant for other macvlan devices" by Eric Biederman. Signed-off-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Patrick McHardy <kaber@trash.net> Cc: Eric Biederman <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-11-26 06:07:10 +00:00
static int macvlan_queue_xmit(struct sk_buff *skb, struct net_device *dev)
{
const struct macvlan_dev *vlan = netdev_priv(dev);
const struct macvlan_port *port = vlan->port;
const struct macvlan_dev *dest;
__u8 ip_summed = skb->ip_summed;
macvlan: implement bridge, VEPA and private mode This allows each macvlan slave device to be in one of three modes, depending on the use case: MACVLAN_PRIVATE: The device never communicates with any other device on the same upper_dev. This even includes frames coming back from a reflective relay, where supported by the adjacent bridge. MACVLAN_VEPA: The new Virtual Ethernet Port Aggregator (VEPA) mode, we assume that the adjacent bridge returns all frames where both source and destination are local to the macvlan port, i.e. the bridge is set up as a reflective relay. Broadcast frames coming in from the upper_dev get flooded to all macvlan interfaces in VEPA mode. We never deliver any frames locally. MACVLAN_BRIDGE: We provide the behavior of a simple bridge between different macvlan interfaces on the same port. Frames from one interface to another one get delivered directly and are not sent out externally. Broadcast frames get flooded to all other bridge ports and to the external interface, but when they come back from a reflective relay, we don't deliver them again. Since we know all the MAC addresses, the macvlan bridge mode does not require learning or STP like the bridge module does. Based on an earlier patch "macvlan: Reflect macvlan packets meant for other macvlan devices" by Eric Biederman. Signed-off-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Patrick McHardy <kaber@trash.net> Cc: Eric Biederman <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-11-26 06:07:10 +00:00
if (vlan->mode == MACVLAN_MODE_BRIDGE) {
const struct ethhdr *eth = (void *)skb->data;
skb->ip_summed = CHECKSUM_UNNECESSARY;
macvlan: implement bridge, VEPA and private mode This allows each macvlan slave device to be in one of three modes, depending on the use case: MACVLAN_PRIVATE: The device never communicates with any other device on the same upper_dev. This even includes frames coming back from a reflective relay, where supported by the adjacent bridge. MACVLAN_VEPA: The new Virtual Ethernet Port Aggregator (VEPA) mode, we assume that the adjacent bridge returns all frames where both source and destination are local to the macvlan port, i.e. the bridge is set up as a reflective relay. Broadcast frames coming in from the upper_dev get flooded to all macvlan interfaces in VEPA mode. We never deliver any frames locally. MACVLAN_BRIDGE: We provide the behavior of a simple bridge between different macvlan interfaces on the same port. Frames from one interface to another one get delivered directly and are not sent out externally. Broadcast frames get flooded to all other bridge ports and to the external interface, but when they come back from a reflective relay, we don't deliver them again. Since we know all the MAC addresses, the macvlan bridge mode does not require learning or STP like the bridge module does. Based on an earlier patch "macvlan: Reflect macvlan packets meant for other macvlan devices" by Eric Biederman. Signed-off-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Patrick McHardy <kaber@trash.net> Cc: Eric Biederman <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-11-26 06:07:10 +00:00
/* send to other bridge ports directly */
if (is_multicast_ether_addr(eth->h_dest)) {
macvlan_broadcast(skb, port, dev, MACVLAN_MODE_BRIDGE);
goto xmit_world;
}
dest = macvlan_hash_lookup(port, eth->h_dest);
if (dest && dest->mode == MACVLAN_MODE_BRIDGE) {
/* send to lowerdev first for its network taps */
dev_forward_skb(vlan->lowerdev, skb);
macvlan: implement bridge, VEPA and private mode This allows each macvlan slave device to be in one of three modes, depending on the use case: MACVLAN_PRIVATE: The device never communicates with any other device on the same upper_dev. This even includes frames coming back from a reflective relay, where supported by the adjacent bridge. MACVLAN_VEPA: The new Virtual Ethernet Port Aggregator (VEPA) mode, we assume that the adjacent bridge returns all frames where both source and destination are local to the macvlan port, i.e. the bridge is set up as a reflective relay. Broadcast frames coming in from the upper_dev get flooded to all macvlan interfaces in VEPA mode. We never deliver any frames locally. MACVLAN_BRIDGE: We provide the behavior of a simple bridge between different macvlan interfaces on the same port. Frames from one interface to another one get delivered directly and are not sent out externally. Broadcast frames get flooded to all other bridge ports and to the external interface, but when they come back from a reflective relay, we don't deliver them again. Since we know all the MAC addresses, the macvlan bridge mode does not require learning or STP like the bridge module does. Based on an earlier patch "macvlan: Reflect macvlan packets meant for other macvlan devices" by Eric Biederman. Signed-off-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Patrick McHardy <kaber@trash.net> Cc: Eric Biederman <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-11-26 06:07:10 +00:00
return NET_XMIT_SUCCESS;
}
}
xmit_world:
skb->ip_summed = ip_summed;
skb->dev = vlan->lowerdev;
macvlan: implement bridge, VEPA and private mode This allows each macvlan slave device to be in one of three modes, depending on the use case: MACVLAN_PRIVATE: The device never communicates with any other device on the same upper_dev. This even includes frames coming back from a reflective relay, where supported by the adjacent bridge. MACVLAN_VEPA: The new Virtual Ethernet Port Aggregator (VEPA) mode, we assume that the adjacent bridge returns all frames where both source and destination are local to the macvlan port, i.e. the bridge is set up as a reflective relay. Broadcast frames coming in from the upper_dev get flooded to all macvlan interfaces in VEPA mode. We never deliver any frames locally. MACVLAN_BRIDGE: We provide the behavior of a simple bridge between different macvlan interfaces on the same port. Frames from one interface to another one get delivered directly and are not sent out externally. Broadcast frames get flooded to all other bridge ports and to the external interface, but when they come back from a reflective relay, we don't deliver them again. Since we know all the MAC addresses, the macvlan bridge mode does not require learning or STP like the bridge module does. Based on an earlier patch "macvlan: Reflect macvlan packets meant for other macvlan devices" by Eric Biederman. Signed-off-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Patrick McHardy <kaber@trash.net> Cc: Eric Biederman <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-11-26 06:07:10 +00:00
return dev_queue_xmit(skb);
}
static netdev_tx_t macvlan_start_xmit(struct sk_buff *skb,
struct net_device *dev)
{
unsigned int len = skb->len;
int ret;
const struct macvlan_dev *vlan = netdev_priv(dev);
if (vlan->fwd_priv) {
skb->dev = vlan->lowerdev;
net: core: explicitly select a txq before doing l2 forwarding Currently, the tx queue were selected implicitly in ndo_dfwd_start_xmit(). The will cause several issues: - NETIF_F_LLTX were removed for macvlan, so txq lock were done for macvlan instead of lower device which misses the necessary txq synchronization for lower device such as txq stopping or frozen required by dev watchdog or control path. - dev_hard_start_xmit() was called with NULL txq which bypasses the net device watchdog. - dev_hard_start_xmit() does not check txq everywhere which will lead a crash when tso is disabled for lower device. Fix this by explicitly introducing a new param for .ndo_select_queue() for just selecting queues in the case of l2 forwarding offload. netdev_pick_tx() was also extended to accept this parameter and dev_queue_xmit_accel() was used to do l2 forwarding transmission. With this fixes, NETIF_F_LLTX could be preserved for macvlan and there's no need to check txq against NULL in dev_hard_start_xmit(). Also there's no need to keep a dedicated ndo_dfwd_start_xmit() and we can just reuse the code of dev_queue_xmit() to do the transmission. In the future, it was also required for macvtap l2 forwarding support since it provides a necessary synchronization method. Cc: John Fastabend <john.r.fastabend@intel.com> Cc: Neil Horman <nhorman@tuxdriver.com> Cc: e1000-devel@lists.sourceforge.net Signed-off-by: Jason Wang <jasowang@redhat.com> Acked-by: Neil Horman <nhorman@tuxdriver.com> Acked-by: John Fastabend <john.r.fastabend@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-01-10 08:18:26 +00:00
ret = dev_queue_xmit_accel(skb, vlan->fwd_priv);
} else {
ret = macvlan_queue_xmit(skb, dev);
}
if (likely(ret == NET_XMIT_SUCCESS || ret == NET_XMIT_CN)) {
struct vlan_pcpu_stats *pcpu_stats;
pcpu_stats = this_cpu_ptr(vlan->pcpu_stats);
u64_stats_update_begin(&pcpu_stats->syncp);
pcpu_stats->tx_packets++;
pcpu_stats->tx_bytes += len;
u64_stats_update_end(&pcpu_stats->syncp);
} else {
this_cpu_inc(vlan->pcpu_stats->tx_dropped);
}
return ret;
}
static int macvlan_hard_header(struct sk_buff *skb, struct net_device *dev,
unsigned short type, const void *daddr,
const void *saddr, unsigned len)
{
const struct macvlan_dev *vlan = netdev_priv(dev);
struct net_device *lowerdev = vlan->lowerdev;
return dev_hard_header(skb, lowerdev, type, daddr,
saddr ? : dev->dev_addr, len);
}
static const struct header_ops macvlan_hard_header_ops = {
.create = macvlan_hard_header,
.rebuild = eth_rebuild_header,
.parse = eth_header_parse,
.cache = eth_header_cache,
.cache_update = eth_header_cache_update,
};
static struct rtnl_link_ops macvlan_link_ops;
static int macvlan_open(struct net_device *dev)
{
struct macvlan_dev *vlan = netdev_priv(dev);
struct net_device *lowerdev = vlan->lowerdev;
int err;
if (vlan->port->passthru) {
if (!(vlan->flags & MACVLAN_FLAG_NOPROMISC)) {
err = dev_set_promiscuity(lowerdev, 1);
if (err < 0)
goto out;
}
goto hash_add;
}
if (lowerdev->features & NETIF_F_HW_L2FW_DOFFLOAD &&
dev->rtnl_link_ops == &macvlan_link_ops) {
vlan->fwd_priv =
lowerdev->netdev_ops->ndo_dfwd_add_station(lowerdev, dev);
/* If we get a NULL pointer back, or if we get an error
* then we should just fall through to the non accelerated path
*/
if (IS_ERR_OR_NULL(vlan->fwd_priv)) {
vlan->fwd_priv = NULL;
net: core: explicitly select a txq before doing l2 forwarding Currently, the tx queue were selected implicitly in ndo_dfwd_start_xmit(). The will cause several issues: - NETIF_F_LLTX were removed for macvlan, so txq lock were done for macvlan instead of lower device which misses the necessary txq synchronization for lower device such as txq stopping or frozen required by dev watchdog or control path. - dev_hard_start_xmit() was called with NULL txq which bypasses the net device watchdog. - dev_hard_start_xmit() does not check txq everywhere which will lead a crash when tso is disabled for lower device. Fix this by explicitly introducing a new param for .ndo_select_queue() for just selecting queues in the case of l2 forwarding offload. netdev_pick_tx() was also extended to accept this parameter and dev_queue_xmit_accel() was used to do l2 forwarding transmission. With this fixes, NETIF_F_LLTX could be preserved for macvlan and there's no need to check txq against NULL in dev_hard_start_xmit(). Also there's no need to keep a dedicated ndo_dfwd_start_xmit() and we can just reuse the code of dev_queue_xmit() to do the transmission. In the future, it was also required for macvtap l2 forwarding support since it provides a necessary synchronization method. Cc: John Fastabend <john.r.fastabend@intel.com> Cc: Neil Horman <nhorman@tuxdriver.com> Cc: e1000-devel@lists.sourceforge.net Signed-off-by: Jason Wang <jasowang@redhat.com> Acked-by: Neil Horman <nhorman@tuxdriver.com> Acked-by: John Fastabend <john.r.fastabend@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-01-10 08:18:26 +00:00
} else
return 0;
}
err = -EBUSY;
if (macvlan_addr_busy(vlan->port, dev->dev_addr))
goto out;
err = dev_uc_add(lowerdev, dev->dev_addr);
if (err < 0)
goto out;
if (dev->flags & IFF_ALLMULTI) {
err = dev_set_allmulti(lowerdev, 1);
if (err < 0)
goto del_unicast;
}
hash_add:
macvlan_hash_add(vlan);
return 0;
del_unicast:
dev_uc_del(lowerdev, dev->dev_addr);
out:
if (vlan->fwd_priv) {
lowerdev->netdev_ops->ndo_dfwd_del_station(lowerdev,
vlan->fwd_priv);
vlan->fwd_priv = NULL;
}
return err;
}
static int macvlan_stop(struct net_device *dev)
{
struct macvlan_dev *vlan = netdev_priv(dev);
struct net_device *lowerdev = vlan->lowerdev;
if (vlan->fwd_priv) {
lowerdev->netdev_ops->ndo_dfwd_del_station(lowerdev,
vlan->fwd_priv);
vlan->fwd_priv = NULL;
return 0;
}
dev_uc_unsync(lowerdev, dev);
dev_mc_unsync(lowerdev, dev);
if (vlan->port->passthru) {
if (!(vlan->flags & MACVLAN_FLAG_NOPROMISC))
dev_set_promiscuity(lowerdev, -1);
goto hash_del;
}
if (dev->flags & IFF_ALLMULTI)
dev_set_allmulti(lowerdev, -1);
dev_uc_del(lowerdev, dev->dev_addr);
hash_del:
macvlan_hash_del(vlan, !dev->dismantle);
return 0;
}
static int macvlan_set_mac_address(struct net_device *dev, void *p)
{
struct macvlan_dev *vlan = netdev_priv(dev);
struct net_device *lowerdev = vlan->lowerdev;
struct sockaddr *addr = p;
int err;
if (!is_valid_ether_addr(addr->sa_data))
return -EADDRNOTAVAIL;
if (!(dev->flags & IFF_UP)) {
/* Just copy in the new address */
memcpy(dev->dev_addr, addr->sa_data, ETH_ALEN);
} else {
/* Rehash and update the device filters */
if (macvlan_addr_busy(vlan->port, addr->sa_data))
return -EBUSY;
err = dev_uc_add(lowerdev, addr->sa_data);
if (err)
return err;
dev_uc_del(lowerdev, dev->dev_addr);
macvlan_hash_change_addr(vlan, addr->sa_data);
}
return 0;
}
static void macvlan_change_rx_flags(struct net_device *dev, int change)
{
struct macvlan_dev *vlan = netdev_priv(dev);
struct net_device *lowerdev = vlan->lowerdev;
if (change & IFF_ALLMULTI)
dev_set_allmulti(lowerdev, dev->flags & IFF_ALLMULTI ? 1 : -1);
}
static void macvlan_set_mac_lists(struct net_device *dev)
{
struct macvlan_dev *vlan = netdev_priv(dev);
if (dev->flags & (IFF_PROMISC | IFF_ALLMULTI)) {
bitmap_fill(vlan->mc_filter, MACVLAN_MC_FILTER_SZ);
} else {
struct netdev_hw_addr *ha;
DECLARE_BITMAP(filter, MACVLAN_MC_FILTER_SZ);
bitmap_zero(filter, MACVLAN_MC_FILTER_SZ);
netdev_for_each_mc_addr(ha, dev) {
__set_bit(mc_hash(vlan, ha->addr), filter);
}
__set_bit(mc_hash(vlan, dev->broadcast), filter);
bitmap_copy(vlan->mc_filter, filter, MACVLAN_MC_FILTER_SZ);
}
dev_uc_sync(vlan->lowerdev, dev);
dev_mc_sync(vlan->lowerdev, dev);
}
static int macvlan_change_mtu(struct net_device *dev, int new_mtu)
{
struct macvlan_dev *vlan = netdev_priv(dev);
if (new_mtu < 68 || vlan->lowerdev->mtu < new_mtu)
return -EINVAL;
dev->mtu = new_mtu;
return 0;
}
/*
* macvlan network devices have devices nesting below it and are a special
* "super class" of normal network devices; split their locks off into a
* separate class since they always nest.
*/
static struct lock_class_key macvlan_netdev_xmit_lock_key;
static struct lock_class_key macvlan_netdev_addr_lock_key;
macvlan: Add support for 'always_on' offload features Macvlan currently inherits all of its features from the lower device. When lower device disables offload support, this causes macvlan to disable offload support as well. This causes performance regression when using macvlan/macvtap in bridge mode. It can be easily demonstrated by creating 2 namespaces using macvlan in bridge mode and running netperf between them: MIGRATED TCP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 10.0.0.1 () port 0 AF_INET Recv Send Send Socket Socket Message Elapsed Size Size Size Time Throughput bytes bytes bytes secs. 10^6bits/sec 87380 16384 16384 20.00 1204.61 To restore the performance, we add software offload features to the list of "always_on" features for macvlan. This way when a namespace or a guest using macvtap initially sends a packet, this packet will not be segmented at macvlan level. It will only be segmented when macvlan sends the packet to the lower device. MIGRATED TCP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 10.0.0.1 () port 0 AF_INET Recv Send Send Socket Socket Message Elapsed Size Size Size Time Throughput bytes bytes bytes secs. 10^6bits/sec 87380 16384 16384 20.00 5507.35 Fixes: 6acf54f1cf0a6747bac9fea26f34cfc5a9029523 (macvtap: Add support of packet capture on macvtap device.) Fixes: 797f87f83b60685ff8a13fa0572d2f10393c50d3 (macvlan: fix netdev feature propagation from lower device) CC: Florian Westphal <fw@strlen.de> CC: Christian Borntraeger <borntraeger@de.ibm.com> CC: Jason Wang <jasowang@redhat.com> CC: Michael S. Tsirkin <mst@redhat.com> Tested-by: Christian Borntraeger <borntraeger@de.ibm.com> Signed-off-by: Vlad Yasevich <vyasevic@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-03-03 20:33:53 +00:00
#define ALWAYS_ON_FEATURES \
(NETIF_F_SG | NETIF_F_GEN_CSUM | NETIF_F_GSO_SOFTWARE | NETIF_F_LLTX)
#define MACVLAN_FEATURES \
(NETIF_F_SG | NETIF_F_ALL_CSUM | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST | \
NETIF_F_GSO | NETIF_F_TSO | NETIF_F_UFO | NETIF_F_GSO_ROBUST | \
NETIF_F_TSO_ECN | NETIF_F_TSO6 | NETIF_F_GRO | NETIF_F_RXCSUM | \
NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_STAG_FILTER)
#define MACVLAN_STATE_MASK \
((1<<__LINK_STATE_NOCARRIER) | (1<<__LINK_STATE_DORMANT))
static void macvlan_set_lockdep_class_one(struct net_device *dev,
struct netdev_queue *txq,
void *_unused)
{
lockdep_set_class(&txq->_xmit_lock,
&macvlan_netdev_xmit_lock_key);
}
static void macvlan_set_lockdep_class(struct net_device *dev)
{
lockdep_set_class(&dev->addr_list_lock,
&macvlan_netdev_addr_lock_key);
netdev_for_each_tx_queue(dev, macvlan_set_lockdep_class_one, NULL);
}
static int macvlan_init(struct net_device *dev)
{
struct macvlan_dev *vlan = netdev_priv(dev);
const struct net_device *lowerdev = vlan->lowerdev;
dev->state = (dev->state & ~MACVLAN_STATE_MASK) |
(lowerdev->state & MACVLAN_STATE_MASK);
dev->features = lowerdev->features & MACVLAN_FEATURES;
macvlan: Add support for 'always_on' offload features Macvlan currently inherits all of its features from the lower device. When lower device disables offload support, this causes macvlan to disable offload support as well. This causes performance regression when using macvlan/macvtap in bridge mode. It can be easily demonstrated by creating 2 namespaces using macvlan in bridge mode and running netperf between them: MIGRATED TCP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 10.0.0.1 () port 0 AF_INET Recv Send Send Socket Socket Message Elapsed Size Size Size Time Throughput bytes bytes bytes secs. 10^6bits/sec 87380 16384 16384 20.00 1204.61 To restore the performance, we add software offload features to the list of "always_on" features for macvlan. This way when a namespace or a guest using macvtap initially sends a packet, this packet will not be segmented at macvlan level. It will only be segmented when macvlan sends the packet to the lower device. MIGRATED TCP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 10.0.0.1 () port 0 AF_INET Recv Send Send Socket Socket Message Elapsed Size Size Size Time Throughput bytes bytes bytes secs. 10^6bits/sec 87380 16384 16384 20.00 5507.35 Fixes: 6acf54f1cf0a6747bac9fea26f34cfc5a9029523 (macvtap: Add support of packet capture on macvtap device.) Fixes: 797f87f83b60685ff8a13fa0572d2f10393c50d3 (macvlan: fix netdev feature propagation from lower device) CC: Florian Westphal <fw@strlen.de> CC: Christian Borntraeger <borntraeger@de.ibm.com> CC: Jason Wang <jasowang@redhat.com> CC: Michael S. Tsirkin <mst@redhat.com> Tested-by: Christian Borntraeger <borntraeger@de.ibm.com> Signed-off-by: Vlad Yasevich <vyasevic@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-03-03 20:33:53 +00:00
dev->features |= ALWAYS_ON_FEATURES;
dev->gso_max_size = lowerdev->gso_max_size;
dev->iflink = lowerdev->ifindex;
drivers/net/macvlan.c: fix cloning of tagged VLAN interfaces Addresses http://bugzilla.kernel.org/show_bug.cgi?id=13348 akpm: the reporter disappeared, so I typed it in again. It is not possible to make clone of tagged VLAN interface to be used as mac-based vlan interfave. How reproducible: Use any 802.1q tagged vlan interface, e.g. eth2.700 and clone it: ip link add link eth2.700 address 00:04:75:cb:38:09 macvlan0 type macvlan ip link set dev macvlan0 up ip addr add 10.195.1.1/24 dev macvlan0 So far, so good. Now try to ping anything via macvlan0: ping 10.195.1.2 Actual results: For every attempted packet tx kernel writes to console: ------------[ cut here ]------------ WARNING: at net/8021q/vlan_dev.c:254 vlan_dev_hard_header+0x36/0x126 [8021q]() Hardware name: M22ES Modules linked in: arptable_filter arp_tables bridge veth macvlan arc4 ecb ppp_mppe ppp_async crc_ccitt ppp_generic slhc autofs4 sunrpc 8021q garp stp ipt_REJECT nf_conntrack_ipv4 nf_defrag_ipv4 xt_state nf_conntrack xt_tcpudp x_tables dm_mirror dm_region_hash dm_log dm_multipath dm_mod sbs sbshc lp floppy snd_intel8x0 joydev snd_seq_dummy snd_intel8x0m snd_ac97_codec ide_cd_mod ac97_bus snd_seq_oss cdrom snd_seq_midi_event serio_raw snd_seq snd_seq_device snd_pcm_oss snd_mixer_oss parport_pc snd_pcm parport battery 8139cp snd_timer i2c_sis96x ac button snd rtc_cmos rtc_core 8139too soundcore rtc_lib mii i2c_core pcspkr snd_page_alloc pata_sis libata sd_mod scsi_mod ext3 jbd ehci_hcd ohci_hcd uhci_hcd [last unloaded: ip_tables] Pid: 0, comm: swapper Tainted: G W 2.6.29.3 #1 Call Trace: [<c0425f48>] warn_slowpath+0x60/0x9f [<c0425f6f>] warn_slowpath+0x87/0x9f [<dffb850d>] vlan_dev_hard_header+0x0/0x126 [8021q] [<dffb8543>] vlan_dev_hard_header+0x36/0x126 [8021q] [<dffb850d>] vlan_dev_hard_header+0x0/0x126 [8021q] [<df83155d>] macvlan_hard_header+0x3c/0x47 [macvlan] [<df831521>] macvlan_hard_header+0x0/0x47 [macvlan] [<c062bf3f>] arp_create+0xef/0x1ff [<c062c08c>] arp_send+0x3d/0x54 [<c062c916>] arp_solicit+0x16c/0x177 [<c05fadd2>] neigh_timer_handler+0x227/0x269 [<c05fabab>] neigh_timer_handler+0x0/0x269 [<c042ce4d>] run_timer_softirq+0xf0/0x141 [<c0429e5a>] __do_softirq+0x76/0xf8 [<c0429de4>] __do_softirq+0x0/0xf8 <IRQ> [<c044fb67>] handle_level_irq+0x0/0xad [<c0429db7>] irq_exit+0x35/0x62 [<c04046bb>] do_IRQ+0xdf/0xf4 [<c04035a7>] common_interrupt+0x27/0x2c [<c04079c5>] default_idle+0x2a/0x3d [<c0401bb6>] cpu_idle+0x57/0x70 Macvlan driver always uses standard ethernet header length for all types of interface to which it is linked. This patch fixes this problem. Reported-by: <sg.tweak@gmail.com> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: "Rafael J. Wysocki" <rjw@sisk.pl> Cc: "David S. Miller" <davem@davemloft.net> Cc: Stephen Hemminger <shemminger@vyatta.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-06-10 09:55:02 +00:00
dev->hard_header_len = lowerdev->hard_header_len;
macvlan_set_lockdep_class(dev);
vlan->pcpu_stats = netdev_alloc_pcpu_stats(struct vlan_pcpu_stats);
if (!vlan->pcpu_stats)
return -ENOMEM;
return 0;
}
static void macvlan_uninit(struct net_device *dev)
{
struct macvlan_dev *vlan = netdev_priv(dev);
struct macvlan_port *port = vlan->port;
free_percpu(vlan->pcpu_stats);
port->count -= 1;
if (!port->count)
macvlan_port_destroy(port->dev);
}
static struct rtnl_link_stats64 *macvlan_dev_get_stats64(struct net_device *dev,
struct rtnl_link_stats64 *stats)
{
struct macvlan_dev *vlan = netdev_priv(dev);
if (vlan->pcpu_stats) {
struct vlan_pcpu_stats *p;
u64 rx_packets, rx_bytes, rx_multicast, tx_packets, tx_bytes;
u32 rx_errors = 0, tx_dropped = 0;
unsigned int start;
int i;
for_each_possible_cpu(i) {
p = per_cpu_ptr(vlan->pcpu_stats, i);
do {
start = u64_stats_fetch_begin_irq(&p->syncp);
rx_packets = p->rx_packets;
rx_bytes = p->rx_bytes;
rx_multicast = p->rx_multicast;
tx_packets = p->tx_packets;
tx_bytes = p->tx_bytes;
} while (u64_stats_fetch_retry_irq(&p->syncp, start));
stats->rx_packets += rx_packets;
stats->rx_bytes += rx_bytes;
stats->multicast += rx_multicast;
stats->tx_packets += tx_packets;
stats->tx_bytes += tx_bytes;
/* rx_errors & tx_dropped are u32, updated
* without syncp protection.
*/
rx_errors += p->rx_errors;
tx_dropped += p->tx_dropped;
}
stats->rx_errors = rx_errors;
stats->rx_dropped = rx_errors;
stats->tx_dropped = tx_dropped;
}
return stats;
}
static int macvlan_vlan_rx_add_vid(struct net_device *dev,
__be16 proto, u16 vid)
{
struct macvlan_dev *vlan = netdev_priv(dev);
struct net_device *lowerdev = vlan->lowerdev;
return vlan_vid_add(lowerdev, proto, vid);
}
static int macvlan_vlan_rx_kill_vid(struct net_device *dev,
__be16 proto, u16 vid)
{
struct macvlan_dev *vlan = netdev_priv(dev);
struct net_device *lowerdev = vlan->lowerdev;
vlan_vid_del(lowerdev, proto, vid);
return 0;
}
static int macvlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
struct net_device *dev,
const unsigned char *addr,
u16 flags)
{
struct macvlan_dev *vlan = netdev_priv(dev);
int err = -EINVAL;
if (!vlan->port->passthru)
return -EOPNOTSUPP;
if (flags & NLM_F_REPLACE)
return -EOPNOTSUPP;
if (is_unicast_ether_addr(addr))
err = dev_uc_add_excl(dev, addr);
else if (is_multicast_ether_addr(addr))
err = dev_mc_add_excl(dev, addr);
return err;
}
static int macvlan_fdb_del(struct ndmsg *ndm, struct nlattr *tb[],
struct net_device *dev,
const unsigned char *addr)
{
struct macvlan_dev *vlan = netdev_priv(dev);
int err = -EINVAL;
if (!vlan->port->passthru)
return -EOPNOTSUPP;
if (is_unicast_ether_addr(addr))
err = dev_uc_del(dev, addr);
else if (is_multicast_ether_addr(addr))
err = dev_mc_del(dev, addr);
return err;
}
static void macvlan_ethtool_get_drvinfo(struct net_device *dev,
struct ethtool_drvinfo *drvinfo)
{
strlcpy(drvinfo->driver, "macvlan", sizeof(drvinfo->driver));
strlcpy(drvinfo->version, "0.1", sizeof(drvinfo->version));
}
static int macvlan_ethtool_get_settings(struct net_device *dev,
struct ethtool_cmd *cmd)
{
const struct macvlan_dev *vlan = netdev_priv(dev);
return __ethtool_get_settings(vlan->lowerdev, cmd);
}
static netdev_features_t macvlan_fix_features(struct net_device *dev,
netdev_features_t features)
{
struct macvlan_dev *vlan = netdev_priv(dev);
netdev_features_t mask;
features |= NETIF_F_ALL_FOR_ALL;
features &= (vlan->set_features | ~MACVLAN_FEATURES);
mask = features;
features = netdev_increment_features(vlan->lowerdev->features,
features,
mask);
macvlan: Add support for 'always_on' offload features Macvlan currently inherits all of its features from the lower device. When lower device disables offload support, this causes macvlan to disable offload support as well. This causes performance regression when using macvlan/macvtap in bridge mode. It can be easily demonstrated by creating 2 namespaces using macvlan in bridge mode and running netperf between them: MIGRATED TCP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 10.0.0.1 () port 0 AF_INET Recv Send Send Socket Socket Message Elapsed Size Size Size Time Throughput bytes bytes bytes secs. 10^6bits/sec 87380 16384 16384 20.00 1204.61 To restore the performance, we add software offload features to the list of "always_on" features for macvlan. This way when a namespace or a guest using macvtap initially sends a packet, this packet will not be segmented at macvlan level. It will only be segmented when macvlan sends the packet to the lower device. MIGRATED TCP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 10.0.0.1 () port 0 AF_INET Recv Send Send Socket Socket Message Elapsed Size Size Size Time Throughput bytes bytes bytes secs. 10^6bits/sec 87380 16384 16384 20.00 5507.35 Fixes: 6acf54f1cf0a6747bac9fea26f34cfc5a9029523 (macvtap: Add support of packet capture on macvtap device.) Fixes: 797f87f83b60685ff8a13fa0572d2f10393c50d3 (macvlan: fix netdev feature propagation from lower device) CC: Florian Westphal <fw@strlen.de> CC: Christian Borntraeger <borntraeger@de.ibm.com> CC: Jason Wang <jasowang@redhat.com> CC: Michael S. Tsirkin <mst@redhat.com> Tested-by: Christian Borntraeger <borntraeger@de.ibm.com> Signed-off-by: Vlad Yasevich <vyasevic@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-03-03 20:33:53 +00:00
features |= ALWAYS_ON_FEATURES;
return features;
}
static const struct ethtool_ops macvlan_ethtool_ops = {
.get_link = ethtool_op_get_link,
.get_settings = macvlan_ethtool_get_settings,
.get_drvinfo = macvlan_ethtool_get_drvinfo,
};
static const struct net_device_ops macvlan_netdev_ops = {
.ndo_init = macvlan_init,
.ndo_uninit = macvlan_uninit,
.ndo_open = macvlan_open,
.ndo_stop = macvlan_stop,
.ndo_start_xmit = macvlan_start_xmit,
.ndo_change_mtu = macvlan_change_mtu,
.ndo_fix_features = macvlan_fix_features,
.ndo_change_rx_flags = macvlan_change_rx_flags,
.ndo_set_mac_address = macvlan_set_mac_address,
.ndo_set_rx_mode = macvlan_set_mac_lists,
.ndo_get_stats64 = macvlan_dev_get_stats64,
.ndo_validate_addr = eth_validate_addr,
.ndo_vlan_rx_add_vid = macvlan_vlan_rx_add_vid,
.ndo_vlan_rx_kill_vid = macvlan_vlan_rx_kill_vid,
.ndo_fdb_add = macvlan_fdb_add,
.ndo_fdb_del = macvlan_fdb_del,
.ndo_fdb_dump = ndo_dflt_fdb_dump,
};
macvtap: Limit packet queue length Mark Wagner reported OOM symptoms when sending UDP traffic over a macvtap link to a kvm receiver. This appears to be caused by the fact that macvtap packet queues are unlimited in length. This means that if the receiver can't keep up with the rate of flow, then we will hit OOM. Of course it gets worse if the OOM killer then decides to kill the receiver. This patch imposes a cap on the packet queue length, in the same way as the tuntap driver, using the device TX queue length. Please note that macvtap currently has no way of giving congestion notification, that means the software device TX queue cannot be used and packets will always be dropped once the macvtap driver queue fills up. This shouldn't be a great problem for the scenario where macvtap is used to feed a kvm receiver, as the traffic is most likely external in origin so congestion notification can't be applied anyway. Of course, if anybody decides to complain about guest-to-guest UDP packet loss down the track, then we may have to revisit this. Incidentally, this patch also fixes a real memory leak when macvtap_get_queue fails. Chris Wright noticed that for this patch to work, we need a non-zero TX queue length. This patch includes his work to change the default macvtap TX queue length to 500. Reported-by: Mark Wagner <mwagner@redhat.com> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Acked-by: Chris Wright <chrisw@sous-sol.org> Acked-by: Arnd Bergmann <arnd@arndb.de> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-07-21 21:44:31 +00:00
void macvlan_common_setup(struct net_device *dev)
{
ether_setup(dev);
dev->priv_flags &= ~(IFF_XMIT_DST_RELEASE | IFF_TX_SKB_SHARING);
dev->priv_flags |= IFF_UNICAST_FLT;
dev->netdev_ops = &macvlan_netdev_ops;
dev->destructor = free_netdev;
dev->header_ops = &macvlan_hard_header_ops;
dev->ethtool_ops = &macvlan_ethtool_ops;
macvtap: Limit packet queue length Mark Wagner reported OOM symptoms when sending UDP traffic over a macvtap link to a kvm receiver. This appears to be caused by the fact that macvtap packet queues are unlimited in length. This means that if the receiver can't keep up with the rate of flow, then we will hit OOM. Of course it gets worse if the OOM killer then decides to kill the receiver. This patch imposes a cap on the packet queue length, in the same way as the tuntap driver, using the device TX queue length. Please note that macvtap currently has no way of giving congestion notification, that means the software device TX queue cannot be used and packets will always be dropped once the macvtap driver queue fills up. This shouldn't be a great problem for the scenario where macvtap is used to feed a kvm receiver, as the traffic is most likely external in origin so congestion notification can't be applied anyway. Of course, if anybody decides to complain about guest-to-guest UDP packet loss down the track, then we may have to revisit this. Incidentally, this patch also fixes a real memory leak when macvtap_get_queue fails. Chris Wright noticed that for this patch to work, we need a non-zero TX queue length. This patch includes his work to change the default macvtap TX queue length to 500. Reported-by: Mark Wagner <mwagner@redhat.com> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Acked-by: Chris Wright <chrisw@sous-sol.org> Acked-by: Arnd Bergmann <arnd@arndb.de> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-07-21 21:44:31 +00:00
}
EXPORT_SYMBOL_GPL(macvlan_common_setup);
static void macvlan_setup(struct net_device *dev)
{
macvlan_common_setup(dev);
dev->tx_queue_len = 0;
}
static int macvlan_port_create(struct net_device *dev)
{
struct macvlan_port *port;
unsigned int i;
int err;
if (dev->type != ARPHRD_ETHER || dev->flags & IFF_LOOPBACK)
return -EINVAL;
port = kzalloc(sizeof(*port), GFP_KERNEL);
if (port == NULL)
return -ENOMEM;
port->passthru = false;
port->dev = dev;
INIT_LIST_HEAD(&port->vlans);
for (i = 0; i < MACVLAN_HASH_SIZE; i++)
INIT_HLIST_HEAD(&port->vlan_hash[i]);
skb_queue_head_init(&port->bc_queue);
INIT_WORK(&port->bc_work, macvlan_process_broadcast);
err = netdev_rx_handler_register(dev, macvlan_handle_frame, port);
if (err)
kfree(port);
else
dev->priv_flags |= IFF_MACVLAN_PORT;
return err;
}
static void macvlan_port_destroy(struct net_device *dev)
{
struct macvlan_port *port = macvlan_port_get_rtnl(dev);
cancel_work_sync(&port->bc_work);
dev->priv_flags &= ~IFF_MACVLAN_PORT;
netdev_rx_handler_unregister(dev);
kfree_rcu(port, rcu);
}
static int macvlan_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;
}
if (data && data[IFLA_MACVLAN_FLAGS] &&
nla_get_u16(data[IFLA_MACVLAN_FLAGS]) & ~MACVLAN_FLAG_NOPROMISC)
return -EINVAL;
if (data && data[IFLA_MACVLAN_MODE]) {
switch (nla_get_u32(data[IFLA_MACVLAN_MODE])) {
case MACVLAN_MODE_PRIVATE:
case MACVLAN_MODE_VEPA:
case MACVLAN_MODE_BRIDGE:
case MACVLAN_MODE_PASSTHRU:
break;
default:
return -EINVAL;
}
}
return 0;
}
int macvlan_common_newlink(struct net *src_net, struct net_device *dev,
struct nlattr *tb[], struct nlattr *data[])
{
struct macvlan_dev *vlan = netdev_priv(dev);
struct macvlan_port *port;
struct net_device *lowerdev;
int err;
if (!tb[IFLA_LINK])
return -EINVAL;
lowerdev = __dev_get_by_index(src_net, nla_get_u32(tb[IFLA_LINK]));
if (lowerdev == NULL)
return -ENODEV;
/* When creating macvlans or macvtaps on top of other macvlans - use
* the real device as the lowerdev.
*/
if (netif_is_macvlan(lowerdev))
lowerdev = macvlan_dev_real_dev(lowerdev);
if (!tb[IFLA_MTU])
dev->mtu = lowerdev->mtu;
else if (dev->mtu > lowerdev->mtu)
return -EINVAL;
if (!tb[IFLA_ADDRESS])
eth_hw_addr_random(dev);
if (!macvlan_port_exists(lowerdev)) {
err = macvlan_port_create(lowerdev);
if (err < 0)
return err;
}
port = macvlan_port_get_rtnl(lowerdev);
/* Only 1 macvlan device can be created in passthru mode */
if (port->passthru)
return -EINVAL;
vlan->lowerdev = lowerdev;
vlan->dev = dev;
vlan->port = port;
vlan->set_features = MACVLAN_FEATURES;
vlan->mode = MACVLAN_MODE_VEPA;
if (data && data[IFLA_MACVLAN_MODE])
vlan->mode = nla_get_u32(data[IFLA_MACVLAN_MODE]);
if (data && data[IFLA_MACVLAN_FLAGS])
vlan->flags = nla_get_u16(data[IFLA_MACVLAN_FLAGS]);
if (vlan->mode == MACVLAN_MODE_PASSTHRU) {
if (port->count)
return -EINVAL;
port->passthru = true;
eth_hw_addr_inherit(dev, lowerdev);
}
port->count += 1;
err = register_netdevice(dev);
if (err < 0)
goto destroy_port;
dev->priv_flags |= IFF_MACVLAN;
err = netdev_upper_dev_link(lowerdev, dev);
if (err)
goto unregister_netdev;
list_add_tail_rcu(&vlan->list, &port->vlans);
netif_stacked_transfer_operstate(lowerdev, dev);
return 0;
unregister_netdev:
unregister_netdevice(dev);
destroy_port:
port->count -= 1;
if (!port->count)
macvlan_port_destroy(lowerdev);
return err;
}
EXPORT_SYMBOL_GPL(macvlan_common_newlink);
static int macvlan_newlink(struct net *src_net, struct net_device *dev,
struct nlattr *tb[], struct nlattr *data[])
{
return macvlan_common_newlink(src_net, dev, tb, data);
}
void macvlan_dellink(struct net_device *dev, struct list_head *head)
{
struct macvlan_dev *vlan = netdev_priv(dev);
list_del_rcu(&vlan->list);
unregister_netdevice_queue(dev, head);
netdev_upper_dev_unlink(vlan->lowerdev, dev);
}
EXPORT_SYMBOL_GPL(macvlan_dellink);
static int macvlan_changelink(struct net_device *dev,
struct nlattr *tb[], struct nlattr *data[])
{
struct macvlan_dev *vlan = netdev_priv(dev);
enum macvlan_mode mode;
bool set_mode = false;
/* Validate mode, but don't set yet: setting flags may fail. */
if (data && data[IFLA_MACVLAN_MODE]) {
set_mode = true;
mode = nla_get_u32(data[IFLA_MACVLAN_MODE]);
/* Passthrough mode can't be set or cleared dynamically */
if ((mode == MACVLAN_MODE_PASSTHRU) !=
(vlan->mode == MACVLAN_MODE_PASSTHRU))
return -EINVAL;
}
if (data && data[IFLA_MACVLAN_FLAGS]) {
__u16 flags = nla_get_u16(data[IFLA_MACVLAN_FLAGS]);
bool promisc = (flags ^ vlan->flags) & MACVLAN_FLAG_NOPROMISC;
if (vlan->port->passthru && promisc) {
int err;
if (flags & MACVLAN_FLAG_NOPROMISC)
err = dev_set_promiscuity(vlan->lowerdev, -1);
else
err = dev_set_promiscuity(vlan->lowerdev, 1);
if (err < 0)
return err;
}
vlan->flags = flags;
}
if (set_mode)
vlan->mode = mode;
return 0;
}
static size_t macvlan_get_size(const struct net_device *dev)
{
return (0
+ nla_total_size(4) /* IFLA_MACVLAN_MODE */
+ nla_total_size(2) /* IFLA_MACVLAN_FLAGS */
);
}
static int macvlan_fill_info(struct sk_buff *skb,
const struct net_device *dev)
{
struct macvlan_dev *vlan = netdev_priv(dev);
if (nla_put_u32(skb, IFLA_MACVLAN_MODE, vlan->mode))
goto nla_put_failure;
if (nla_put_u16(skb, IFLA_MACVLAN_FLAGS, vlan->flags))
goto nla_put_failure;
return 0;
nla_put_failure:
return -EMSGSIZE;
}
static const struct nla_policy macvlan_policy[IFLA_MACVLAN_MAX + 1] = {
[IFLA_MACVLAN_MODE] = { .type = NLA_U32 },
[IFLA_MACVLAN_FLAGS] = { .type = NLA_U16 },
};
int macvlan_link_register(struct rtnl_link_ops *ops)
{
/* common fields */
ops->priv_size = sizeof(struct macvlan_dev);
ops->validate = macvlan_validate;
ops->maxtype = IFLA_MACVLAN_MAX;
ops->policy = macvlan_policy;
ops->changelink = macvlan_changelink;
ops->get_size = macvlan_get_size;
ops->fill_info = macvlan_fill_info;
return rtnl_link_register(ops);
};
EXPORT_SYMBOL_GPL(macvlan_link_register);
static struct rtnl_link_ops macvlan_link_ops = {
.kind = "macvlan",
macvtap: Limit packet queue length Mark Wagner reported OOM symptoms when sending UDP traffic over a macvtap link to a kvm receiver. This appears to be caused by the fact that macvtap packet queues are unlimited in length. This means that if the receiver can't keep up with the rate of flow, then we will hit OOM. Of course it gets worse if the OOM killer then decides to kill the receiver. This patch imposes a cap on the packet queue length, in the same way as the tuntap driver, using the device TX queue length. Please note that macvtap currently has no way of giving congestion notification, that means the software device TX queue cannot be used and packets will always be dropped once the macvtap driver queue fills up. This shouldn't be a great problem for the scenario where macvtap is used to feed a kvm receiver, as the traffic is most likely external in origin so congestion notification can't be applied anyway. Of course, if anybody decides to complain about guest-to-guest UDP packet loss down the track, then we may have to revisit this. Incidentally, this patch also fixes a real memory leak when macvtap_get_queue fails. Chris Wright noticed that for this patch to work, we need a non-zero TX queue length. This patch includes his work to change the default macvtap TX queue length to 500. Reported-by: Mark Wagner <mwagner@redhat.com> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Acked-by: Chris Wright <chrisw@sous-sol.org> Acked-by: Arnd Bergmann <arnd@arndb.de> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-07-21 21:44:31 +00:00
.setup = macvlan_setup,
.newlink = macvlan_newlink,
.dellink = macvlan_dellink,
};
static int macvlan_device_event(struct notifier_block *unused,
unsigned long event, void *ptr)
{
struct net_device *dev = netdev_notifier_info_to_dev(ptr);
struct macvlan_dev *vlan, *next;
struct macvlan_port *port;
LIST_HEAD(list_kill);
if (!macvlan_port_exists(dev))
return NOTIFY_DONE;
port = macvlan_port_get_rtnl(dev);
switch (event) {
case NETDEV_CHANGE:
list_for_each_entry(vlan, &port->vlans, list)
netif_stacked_transfer_operstate(vlan->lowerdev,
vlan->dev);
break;
case NETDEV_FEAT_CHANGE:
list_for_each_entry(vlan, &port->vlans, list) {
vlan->dev->gso_max_size = dev->gso_max_size;
netdev_update_features(vlan->dev);
}
break;
case NETDEV_UNREGISTER:
/* twiddle thumbs on netns device moves */
if (dev->reg_state != NETREG_UNREGISTERING)
break;
list_for_each_entry_safe(vlan, next, &port->vlans, list)
vlan->dev->rtnl_link_ops->dellink(vlan->dev, &list_kill);
unregister_netdevice_many(&list_kill);
list_del(&list_kill);
break;
case NETDEV_PRE_TYPE_CHANGE:
/* Forbid underlaying device to change its type. */
return NOTIFY_BAD;
}
return NOTIFY_DONE;
}
static struct notifier_block macvlan_notifier_block __read_mostly = {
.notifier_call = macvlan_device_event,
};
static int __init macvlan_init_module(void)
{
int err;
register_netdevice_notifier(&macvlan_notifier_block);
err = macvlan_link_register(&macvlan_link_ops);
if (err < 0)
goto err1;
return 0;
err1:
unregister_netdevice_notifier(&macvlan_notifier_block);
return err;
}
static void __exit macvlan_cleanup_module(void)
{
rtnl_link_unregister(&macvlan_link_ops);
unregister_netdevice_notifier(&macvlan_notifier_block);
}
module_init(macvlan_init_module);
module_exit(macvlan_cleanup_module);
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
MODULE_DESCRIPTION("Driver for MAC address based VLANs");
MODULE_ALIAS_RTNL_LINK("macvlan");