![David S. Miller](/assets/img/avatar_default.png)
Network devices can allocate reasources and private memory using netdev_ops->ndo_init(). However, the release of these resources can occur in one of two different places. Either netdev_ops->ndo_uninit() or netdev->destructor(). The decision of which operation frees the resources depends upon whether it is necessary for all netdev refs to be released before it is safe to perform the freeing. netdev_ops->ndo_uninit() presumably can occur right after the NETDEV_UNREGISTER notifier completes and the unicast and multicast address lists are flushed. netdev->destructor(), on the other hand, does not run until the netdev references all go away. Further complicating the situation is that netdev->destructor() almost universally does also a free_netdev(). This creates a problem for the logic in register_netdevice(). Because all callers of register_netdevice() manage the freeing of the netdev, and invoke free_netdev(dev) if register_netdevice() fails. If netdev_ops->ndo_init() succeeds, but something else fails inside of register_netdevice(), it does call ndo_ops->ndo_uninit(). But it is not able to invoke netdev->destructor(). This is because netdev->destructor() will do a free_netdev() and then the caller of register_netdevice() will do the same. However, this means that the resources that would normally be released by netdev->destructor() will not be. Over the years drivers have added local hacks to deal with this, by invoking their destructor parts by hand when register_netdevice() fails. Many drivers do not try to deal with this, and instead we have leaks. Let's close this hole by formalizing the distinction between what private things need to be freed up by netdev->destructor() and whether the driver needs unregister_netdevice() to perform the free_netdev(). netdev->priv_destructor() performs all actions to free up the private resources that used to be freed by netdev->destructor(), except for free_netdev(). netdev->needs_free_netdev is a boolean that indicates whether free_netdev() should be done at the end of unregister_netdevice(). Now, register_netdevice() can sanely release all resources after ndo_ops->ndo_init() succeeds, by invoking both ndo_ops->ndo_uninit() and netdev->priv_destructor(). And at the end of unregister_netdevice(), we invoke netdev->priv_destructor() and optionally call free_netdev(). Signed-off-by: David S. Miller <davem@davemloft.net>
162 lines
3.4 KiB
C
162 lines
3.4 KiB
C
#include <linux/module.h>
|
|
#include <linux/kernel.h>
|
|
#include <linux/netdevice.h>
|
|
#include <linux/netlink.h>
|
|
#include <net/net_namespace.h>
|
|
#include <linux/if_arp.h>
|
|
#include <net/rtnetlink.h>
|
|
|
|
struct pcpu_lstats {
|
|
u64 packets;
|
|
u64 bytes;
|
|
struct u64_stats_sync syncp;
|
|
};
|
|
|
|
static netdev_tx_t nlmon_xmit(struct sk_buff *skb, struct net_device *dev)
|
|
{
|
|
int len = skb->len;
|
|
struct pcpu_lstats *stats = this_cpu_ptr(dev->lstats);
|
|
|
|
u64_stats_update_begin(&stats->syncp);
|
|
stats->bytes += len;
|
|
stats->packets++;
|
|
u64_stats_update_end(&stats->syncp);
|
|
|
|
dev_kfree_skb(skb);
|
|
|
|
return NETDEV_TX_OK;
|
|
}
|
|
|
|
static int nlmon_dev_init(struct net_device *dev)
|
|
{
|
|
dev->lstats = netdev_alloc_pcpu_stats(struct pcpu_lstats);
|
|
return dev->lstats == NULL ? -ENOMEM : 0;
|
|
}
|
|
|
|
static void nlmon_dev_uninit(struct net_device *dev)
|
|
{
|
|
free_percpu(dev->lstats);
|
|
}
|
|
|
|
struct nlmon {
|
|
struct netlink_tap nt;
|
|
};
|
|
|
|
static int nlmon_open(struct net_device *dev)
|
|
{
|
|
struct nlmon *nlmon = netdev_priv(dev);
|
|
|
|
nlmon->nt.dev = dev;
|
|
nlmon->nt.module = THIS_MODULE;
|
|
return netlink_add_tap(&nlmon->nt);
|
|
}
|
|
|
|
static int nlmon_close(struct net_device *dev)
|
|
{
|
|
struct nlmon *nlmon = netdev_priv(dev);
|
|
|
|
return netlink_remove_tap(&nlmon->nt);
|
|
}
|
|
|
|
static void
|
|
nlmon_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats)
|
|
{
|
|
int i;
|
|
u64 bytes = 0, packets = 0;
|
|
|
|
for_each_possible_cpu(i) {
|
|
const struct pcpu_lstats *nl_stats;
|
|
u64 tbytes, tpackets;
|
|
unsigned int start;
|
|
|
|
nl_stats = per_cpu_ptr(dev->lstats, i);
|
|
|
|
do {
|
|
start = u64_stats_fetch_begin_irq(&nl_stats->syncp);
|
|
tbytes = nl_stats->bytes;
|
|
tpackets = nl_stats->packets;
|
|
} while (u64_stats_fetch_retry_irq(&nl_stats->syncp, start));
|
|
|
|
packets += tpackets;
|
|
bytes += tbytes;
|
|
}
|
|
|
|
stats->rx_packets = packets;
|
|
stats->tx_packets = 0;
|
|
|
|
stats->rx_bytes = bytes;
|
|
stats->tx_bytes = 0;
|
|
}
|
|
|
|
static u32 always_on(struct net_device *dev)
|
|
{
|
|
return 1;
|
|
}
|
|
|
|
static const struct ethtool_ops nlmon_ethtool_ops = {
|
|
.get_link = always_on,
|
|
};
|
|
|
|
static const struct net_device_ops nlmon_ops = {
|
|
.ndo_init = nlmon_dev_init,
|
|
.ndo_uninit = nlmon_dev_uninit,
|
|
.ndo_open = nlmon_open,
|
|
.ndo_stop = nlmon_close,
|
|
.ndo_start_xmit = nlmon_xmit,
|
|
.ndo_get_stats64 = nlmon_get_stats64,
|
|
};
|
|
|
|
static void nlmon_setup(struct net_device *dev)
|
|
{
|
|
dev->type = ARPHRD_NETLINK;
|
|
dev->priv_flags |= IFF_NO_QUEUE;
|
|
|
|
dev->netdev_ops = &nlmon_ops;
|
|
dev->ethtool_ops = &nlmon_ethtool_ops;
|
|
dev->needs_free_netdev = true;
|
|
|
|
dev->features = NETIF_F_SG | NETIF_F_FRAGLIST |
|
|
NETIF_F_HIGHDMA | NETIF_F_LLTX;
|
|
dev->flags = IFF_NOARP;
|
|
|
|
/* That's rather a softlimit here, which, of course,
|
|
* can be altered. Not a real MTU, but what is to be
|
|
* expected in most cases.
|
|
*/
|
|
dev->mtu = NLMSG_GOODSIZE;
|
|
dev->min_mtu = sizeof(struct nlmsghdr);
|
|
}
|
|
|
|
static int nlmon_validate(struct nlattr *tb[], struct nlattr *data[])
|
|
{
|
|
if (tb[IFLA_ADDRESS])
|
|
return -EINVAL;
|
|
return 0;
|
|
}
|
|
|
|
static struct rtnl_link_ops nlmon_link_ops __read_mostly = {
|
|
.kind = "nlmon",
|
|
.priv_size = sizeof(struct nlmon),
|
|
.setup = nlmon_setup,
|
|
.validate = nlmon_validate,
|
|
};
|
|
|
|
static __init int nlmon_register(void)
|
|
{
|
|
return rtnl_link_register(&nlmon_link_ops);
|
|
}
|
|
|
|
static __exit void nlmon_unregister(void)
|
|
{
|
|
rtnl_link_unregister(&nlmon_link_ops);
|
|
}
|
|
|
|
module_init(nlmon_register);
|
|
module_exit(nlmon_unregister);
|
|
|
|
MODULE_LICENSE("GPL v2");
|
|
MODULE_AUTHOR("Daniel Borkmann <dborkman@redhat.com>");
|
|
MODULE_AUTHOR("Mathieu Geli <geli@enseirb.fr>");
|
|
MODULE_DESCRIPTION("Netlink monitoring device");
|
|
MODULE_ALIAS_RTNL_LINK("nlmon");
|