linux/drivers/net/ifb.c

297 lines
7.1 KiB
C
Raw Normal View History

/* drivers/net/ifb.c:
The purpose of this driver is to provide a device that allows
for sharing of resources:
1) qdiscs/policies that are per device as opposed to system wide.
ifb allows for a device which can be redirected to thus providing
an impression of sharing.
2) Allows for queueing incoming traffic for shaping instead of
dropping.
The original concept is based on what is known as the IMQ
driver initially written by Martin Devera, later rewritten
by Patrick McHardy and then maintained by Andre Correa.
You need the tc action mirror or redirect to feed this device
packets.
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.
Authors: Jamal Hadi Salim (2005)
*/
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/init.h>
#include <linux/moduleparam.h>
#include <net/pkt_sched.h>
[NET]: Make the device list and device lookups per namespace. This patch makes most of the generic device layer network namespace safe. This patch makes dev_base_head a network namespace variable, and then it picks up a few associated variables. The functions: dev_getbyhwaddr dev_getfirsthwbytype dev_get_by_flags dev_get_by_name __dev_get_by_name dev_get_by_index __dev_get_by_index dev_ioctl dev_ethtool dev_load wireless_process_ioctl were modified to take a network namespace argument, and deal with it. vlan_ioctl_set and brioctl_set were modified so their hooks will receive a network namespace argument. So basically anthing in the core of the network stack that was affected to by the change of dev_base was modified to handle multiple network namespaces. The rest of the network stack was simply modified to explicitly use &init_net the initial network namespace. This can be fixed when those components of the network stack are modified to handle multiple network namespaces. For now the ifindex generator is left global. Fundametally ifindex numbers are per namespace, or else we will have corner case problems with migration when we get that far. At the same time there are assumptions in the network stack that the ifindex of a network device won't change. Making the ifindex number global seems a good compromise until the network stack can cope with ifindex changes when you change namespaces, and the like. Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-09-18 02:56:21 +08:00
#include <net/net_namespace.h>
#include <linux/lockdep.h>
#define TX_TIMEOUT (2*HZ)
#define TX_Q_LIMIT 32
struct ifb_private {
struct tasklet_struct ifb_tasklet;
int tasklet_pending;
/* mostly debug stats leave in for now */
unsigned long st_task_enter; /* tasklet entered */
unsigned long st_txq_refl_try; /* transmit queue refill attempt */
unsigned long st_rxq_enter; /* receive queue entered */
unsigned long st_rx2tx_tran; /* receive to trasmit transfers */
unsigned long st_rxq_notenter; /*receiveQ not entered, resched */
unsigned long st_rx_frm_egr; /* received from egress path */
unsigned long st_rx_frm_ing; /* received from ingress path */
unsigned long st_rxq_check;
unsigned long st_rxq_rsch;
struct sk_buff_head rq;
struct sk_buff_head tq;
};
static int numifbs = 2;
static void ri_tasklet(unsigned long dev);
static int ifb_xmit(struct sk_buff *skb, struct net_device *dev);
static int ifb_open(struct net_device *dev);
static int ifb_close(struct net_device *dev);
static void ri_tasklet(unsigned long dev)
{
struct net_device *_dev = (struct net_device *)dev;
struct ifb_private *dp = netdev_priv(_dev);
struct net_device_stats *stats = &_dev->stats;
struct sk_buff *skb;
dp->st_task_enter++;
if ((skb = skb_peek(&dp->tq)) == NULL) {
dp->st_txq_refl_try++;
[NET]: Add netif_tx_lock Various drivers use xmit_lock internally to synchronise with their transmission routines. They do so without setting xmit_lock_owner. This is fine as long as netpoll is not in use. With netpoll it is possible for deadlocks to occur if xmit_lock_owner isn't set. This is because if a printk occurs while xmit_lock is held and xmit_lock_owner is not set can cause netpoll to attempt to take xmit_lock recursively. While it is possible to resolve this by getting netpoll to use trylock, it is suboptimal because netpoll's sole objective is to maximise the chance of getting the printk out on the wire. So delaying or dropping the message is to be avoided as much as possible. So the only alternative is to always set xmit_lock_owner. The following patch does this by introducing the netif_tx_lock family of functions that take care of setting/unsetting xmit_lock_owner. I renamed xmit_lock to _xmit_lock to indicate that it should not be used directly. I didn't provide irq versions of the netif_tx_lock functions since xmit_lock is meant to be a BH-disabling lock. This is pretty much a straight text substitution except for a small bug fix in winbond. It currently uses netif_stop_queue/spin_unlock_wait to stop transmission. This is unsafe as an IRQ can potentially wake up the queue. So it is safer to use netif_tx_disable. The hamradio bits used spin_lock_irq but it is unnecessary as xmit_lock must never be taken in an IRQ handler. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-06-10 03:20:56 +08:00
if (netif_tx_trylock(_dev)) {
dp->st_rxq_enter++;
while ((skb = skb_dequeue(&dp->rq)) != NULL) {
skb_queue_tail(&dp->tq, skb);
dp->st_rx2tx_tran++;
}
[NET]: Add netif_tx_lock Various drivers use xmit_lock internally to synchronise with their transmission routines. They do so without setting xmit_lock_owner. This is fine as long as netpoll is not in use. With netpoll it is possible for deadlocks to occur if xmit_lock_owner isn't set. This is because if a printk occurs while xmit_lock is held and xmit_lock_owner is not set can cause netpoll to attempt to take xmit_lock recursively. While it is possible to resolve this by getting netpoll to use trylock, it is suboptimal because netpoll's sole objective is to maximise the chance of getting the printk out on the wire. So delaying or dropping the message is to be avoided as much as possible. So the only alternative is to always set xmit_lock_owner. The following patch does this by introducing the netif_tx_lock family of functions that take care of setting/unsetting xmit_lock_owner. I renamed xmit_lock to _xmit_lock to indicate that it should not be used directly. I didn't provide irq versions of the netif_tx_lock functions since xmit_lock is meant to be a BH-disabling lock. This is pretty much a straight text substitution except for a small bug fix in winbond. It currently uses netif_stop_queue/spin_unlock_wait to stop transmission. This is unsafe as an IRQ can potentially wake up the queue. So it is safer to use netif_tx_disable. The hamradio bits used spin_lock_irq but it is unnecessary as xmit_lock must never be taken in an IRQ handler. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-06-10 03:20:56 +08:00
netif_tx_unlock(_dev);
} else {
/* reschedule */
dp->st_rxq_notenter++;
goto resched;
}
}
while ((skb = skb_dequeue(&dp->tq)) != NULL) {
u32 from = G_TC_FROM(skb->tc_verd);
skb->tc_verd = 0;
skb->tc_verd = SET_TC_NCLS(skb->tc_verd);
stats->tx_packets++;
stats->tx_bytes +=skb->len;
[NET]: Make the device list and device lookups per namespace. This patch makes most of the generic device layer network namespace safe. This patch makes dev_base_head a network namespace variable, and then it picks up a few associated variables. The functions: dev_getbyhwaddr dev_getfirsthwbytype dev_get_by_flags dev_get_by_name __dev_get_by_name dev_get_by_index __dev_get_by_index dev_ioctl dev_ethtool dev_load wireless_process_ioctl were modified to take a network namespace argument, and deal with it. vlan_ioctl_set and brioctl_set were modified so their hooks will receive a network namespace argument. So basically anthing in the core of the network stack that was affected to by the change of dev_base was modified to handle multiple network namespaces. The rest of the network stack was simply modified to explicitly use &init_net the initial network namespace. This can be fixed when those components of the network stack are modified to handle multiple network namespaces. For now the ifindex generator is left global. Fundametally ifindex numbers are per namespace, or else we will have corner case problems with migration when we get that far. At the same time there are assumptions in the network stack that the ifindex of a network device won't change. Making the ifindex number global seems a good compromise until the network stack can cope with ifindex changes when you change namespaces, and the like. Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-09-18 02:56:21 +08:00
skb->dev = __dev_get_by_index(&init_net, skb->iif);
if (!skb->dev) {
dev_kfree_skb(skb);
stats->tx_dropped++;
break;
}
skb->iif = _dev->ifindex;
if (from & AT_EGRESS) {
dp->st_rx_frm_egr++;
dev_queue_xmit(skb);
} else if (from & AT_INGRESS) {
dp->st_rx_frm_ing++;
skb_pull(skb, skb->dev->hard_header_len);
netif_rx(skb);
} else
BUG();
}
[NET]: Add netif_tx_lock Various drivers use xmit_lock internally to synchronise with their transmission routines. They do so without setting xmit_lock_owner. This is fine as long as netpoll is not in use. With netpoll it is possible for deadlocks to occur if xmit_lock_owner isn't set. This is because if a printk occurs while xmit_lock is held and xmit_lock_owner is not set can cause netpoll to attempt to take xmit_lock recursively. While it is possible to resolve this by getting netpoll to use trylock, it is suboptimal because netpoll's sole objective is to maximise the chance of getting the printk out on the wire. So delaying or dropping the message is to be avoided as much as possible. So the only alternative is to always set xmit_lock_owner. The following patch does this by introducing the netif_tx_lock family of functions that take care of setting/unsetting xmit_lock_owner. I renamed xmit_lock to _xmit_lock to indicate that it should not be used directly. I didn't provide irq versions of the netif_tx_lock functions since xmit_lock is meant to be a BH-disabling lock. This is pretty much a straight text substitution except for a small bug fix in winbond. It currently uses netif_stop_queue/spin_unlock_wait to stop transmission. This is unsafe as an IRQ can potentially wake up the queue. So it is safer to use netif_tx_disable. The hamradio bits used spin_lock_irq but it is unnecessary as xmit_lock must never be taken in an IRQ handler. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-06-10 03:20:56 +08:00
if (netif_tx_trylock(_dev)) {
dp->st_rxq_check++;
if ((skb = skb_peek(&dp->rq)) == NULL) {
dp->tasklet_pending = 0;
if (netif_queue_stopped(_dev))
netif_wake_queue(_dev);
} else {
dp->st_rxq_rsch++;
[NET]: Add netif_tx_lock Various drivers use xmit_lock internally to synchronise with their transmission routines. They do so without setting xmit_lock_owner. This is fine as long as netpoll is not in use. With netpoll it is possible for deadlocks to occur if xmit_lock_owner isn't set. This is because if a printk occurs while xmit_lock is held and xmit_lock_owner is not set can cause netpoll to attempt to take xmit_lock recursively. While it is possible to resolve this by getting netpoll to use trylock, it is suboptimal because netpoll's sole objective is to maximise the chance of getting the printk out on the wire. So delaying or dropping the message is to be avoided as much as possible. So the only alternative is to always set xmit_lock_owner. The following patch does this by introducing the netif_tx_lock family of functions that take care of setting/unsetting xmit_lock_owner. I renamed xmit_lock to _xmit_lock to indicate that it should not be used directly. I didn't provide irq versions of the netif_tx_lock functions since xmit_lock is meant to be a BH-disabling lock. This is pretty much a straight text substitution except for a small bug fix in winbond. It currently uses netif_stop_queue/spin_unlock_wait to stop transmission. This is unsafe as an IRQ can potentially wake up the queue. So it is safer to use netif_tx_disable. The hamradio bits used spin_lock_irq but it is unnecessary as xmit_lock must never be taken in an IRQ handler. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-06-10 03:20:56 +08:00
netif_tx_unlock(_dev);
goto resched;
}
[NET]: Add netif_tx_lock Various drivers use xmit_lock internally to synchronise with their transmission routines. They do so without setting xmit_lock_owner. This is fine as long as netpoll is not in use. With netpoll it is possible for deadlocks to occur if xmit_lock_owner isn't set. This is because if a printk occurs while xmit_lock is held and xmit_lock_owner is not set can cause netpoll to attempt to take xmit_lock recursively. While it is possible to resolve this by getting netpoll to use trylock, it is suboptimal because netpoll's sole objective is to maximise the chance of getting the printk out on the wire. So delaying or dropping the message is to be avoided as much as possible. So the only alternative is to always set xmit_lock_owner. The following patch does this by introducing the netif_tx_lock family of functions that take care of setting/unsetting xmit_lock_owner. I renamed xmit_lock to _xmit_lock to indicate that it should not be used directly. I didn't provide irq versions of the netif_tx_lock functions since xmit_lock is meant to be a BH-disabling lock. This is pretty much a straight text substitution except for a small bug fix in winbond. It currently uses netif_stop_queue/spin_unlock_wait to stop transmission. This is unsafe as an IRQ can potentially wake up the queue. So it is safer to use netif_tx_disable. The hamradio bits used spin_lock_irq but it is unnecessary as xmit_lock must never be taken in an IRQ handler. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-06-10 03:20:56 +08:00
netif_tx_unlock(_dev);
} else {
resched:
dp->tasklet_pending = 1;
tasklet_schedule(&dp->ifb_tasklet);
}
}
static void ifb_setup(struct net_device *dev)
{
/* Initialize the device structure. */
dev->hard_start_xmit = ifb_xmit;
dev->open = &ifb_open;
dev->stop = &ifb_close;
dev->destructor = free_netdev;
/* Fill in device structure with ethernet-generic values. */
ether_setup(dev);
dev->tx_queue_len = TX_Q_LIMIT;
dev->change_mtu = NULL;
dev->flags |= IFF_NOARP;
dev->flags &= ~IFF_MULTICAST;
random_ether_addr(dev->dev_addr);
}
static int ifb_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct ifb_private *dp = netdev_priv(dev);
struct net_device_stats *stats = &dev->stats;
int ret = 0;
u32 from = G_TC_FROM(skb->tc_verd);
stats->rx_packets++;
stats->rx_bytes+=skb->len;
if (!(from & (AT_INGRESS|AT_EGRESS)) || !skb->iif) {
dev_kfree_skb(skb);
stats->rx_dropped++;
return ret;
}
if (skb_queue_len(&dp->rq) >= dev->tx_queue_len) {
netif_stop_queue(dev);
}
dev->trans_start = jiffies;
skb_queue_tail(&dp->rq, skb);
if (!dp->tasklet_pending) {
dp->tasklet_pending = 1;
tasklet_schedule(&dp->ifb_tasklet);
}
return ret;
}
static int ifb_close(struct net_device *dev)
{
struct ifb_private *dp = netdev_priv(dev);
tasklet_kill(&dp->ifb_tasklet);
netif_stop_queue(dev);
skb_queue_purge(&dp->rq);
skb_queue_purge(&dp->tq);
return 0;
}
static int ifb_open(struct net_device *dev)
{
struct ifb_private *dp = netdev_priv(dev);
tasklet_init(&dp->ifb_tasklet, ri_tasklet, (unsigned long)dev);
skb_queue_head_init(&dp->rq);
skb_queue_head_init(&dp->tq);
netif_start_queue(dev);
return 0;
}
static int ifb_validate(struct nlattr *tb[], struct nlattr *data[])
{
if (tb[IFLA_ADDRESS]) {
if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN)
return -EINVAL;
if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS])))
return -EADDRNOTAVAIL;
}
return 0;
}
static struct rtnl_link_ops ifb_link_ops __read_mostly = {
.kind = "ifb",
.priv_size = sizeof(struct ifb_private),
.setup = ifb_setup,
.validate = ifb_validate,
};
/* Number of ifb devices to be set up by this module. */
module_param(numifbs, int, 0);
MODULE_PARM_DESC(numifbs, "Number of ifb devices");
/*
* dev_ifb->queue_lock is usually taken after dev->ingress_lock,
* reversely to e.g. qdisc_lock_tree(). It should be safe until
* ifb doesn't take dev->queue_lock with dev_ifb->ingress_lock.
* But lockdep should know that ifb has different locks from dev.
*/
static struct lock_class_key ifb_queue_lock_key;
static struct lock_class_key ifb_ingress_lock_key;
static int __init ifb_init_one(int index)
{
struct net_device *dev_ifb;
int err;
dev_ifb = alloc_netdev(sizeof(struct ifb_private),
"ifb%d", ifb_setup);
if (!dev_ifb)
return -ENOMEM;
err = dev_alloc_name(dev_ifb, dev_ifb->name);
if (err < 0)
goto err;
dev_ifb->rtnl_link_ops = &ifb_link_ops;
err = register_netdevice(dev_ifb);
if (err < 0)
goto err;
lockdep_set_class(&dev_ifb->queue_lock, &ifb_queue_lock_key);
lockdep_set_class(&dev_ifb->ingress_lock, &ifb_ingress_lock_key);
return 0;
err:
free_netdev(dev_ifb);
return err;
}
static int __init ifb_init_module(void)
{
int i, err;
rtnl_lock();
err = __rtnl_link_register(&ifb_link_ops);
for (i = 0; i < numifbs && !err; i++)
err = ifb_init_one(i);
if (err)
__rtnl_link_unregister(&ifb_link_ops);
rtnl_unlock();
return err;
}
static void __exit ifb_cleanup_module(void)
{
rtnl_link_unregister(&ifb_link_ops);
}
module_init(ifb_init_module);
module_exit(ifb_cleanup_module);
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Jamal Hadi Salim");
MODULE_ALIAS_RTNL_LINK("ifb");