kernel_optimize_test/drivers/net/vsockmon.c
David S. Miller cf124db566 net: Fix inconsistent teardown and release of private netdev state.
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>
2017-06-07 15:53:24 -04:00

171 lines
3.6 KiB
C

#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/if_arp.h>
#include <net/rtnetlink.h>
#include <net/sock.h>
#include <net/af_vsock.h>
#include <uapi/linux/vsockmon.h>
#include <linux/virtio_vsock.h>
/* Virtio transport max packet size plus header */
#define DEFAULT_MTU (VIRTIO_VSOCK_MAX_PKT_BUF_SIZE + \
sizeof(struct af_vsockmon_hdr))
struct pcpu_lstats {
u64 rx_packets;
u64 rx_bytes;
struct u64_stats_sync syncp;
};
static int vsockmon_dev_init(struct net_device *dev)
{
dev->lstats = netdev_alloc_pcpu_stats(struct pcpu_lstats);
if (!dev->lstats)
return -ENOMEM;
return 0;
}
static void vsockmon_dev_uninit(struct net_device *dev)
{
free_percpu(dev->lstats);
}
struct vsockmon {
struct vsock_tap vt;
};
static int vsockmon_open(struct net_device *dev)
{
struct vsockmon *vsockmon = netdev_priv(dev);
vsockmon->vt.dev = dev;
vsockmon->vt.module = THIS_MODULE;
return vsock_add_tap(&vsockmon->vt);
}
static int vsockmon_close(struct net_device *dev)
{
struct vsockmon *vsockmon = netdev_priv(dev);
return vsock_remove_tap(&vsockmon->vt);
}
static netdev_tx_t vsockmon_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->rx_bytes += len;
stats->rx_packets++;
u64_stats_update_end(&stats->syncp);
dev_kfree_skb(skb);
return NETDEV_TX_OK;
}
static void
vsockmon_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 *vstats;
u64 tbytes, tpackets;
unsigned int start;
vstats = per_cpu_ptr(dev->lstats, i);
do {
start = u64_stats_fetch_begin_irq(&vstats->syncp);
tbytes = vstats->rx_bytes;
tpackets = vstats->rx_packets;
} while (u64_stats_fetch_retry_irq(&vstats->syncp, start));
packets += tpackets;
bytes += tbytes;
}
stats->rx_packets = packets;
stats->tx_packets = 0;
stats->rx_bytes = bytes;
stats->tx_bytes = 0;
}
static int vsockmon_is_valid_mtu(int new_mtu)
{
return new_mtu >= (int)sizeof(struct af_vsockmon_hdr);
}
static int vsockmon_change_mtu(struct net_device *dev, int new_mtu)
{
if (!vsockmon_is_valid_mtu(new_mtu))
return -EINVAL;
dev->mtu = new_mtu;
return 0;
}
static const struct net_device_ops vsockmon_ops = {
.ndo_init = vsockmon_dev_init,
.ndo_uninit = vsockmon_dev_uninit,
.ndo_open = vsockmon_open,
.ndo_stop = vsockmon_close,
.ndo_start_xmit = vsockmon_xmit,
.ndo_get_stats64 = vsockmon_get_stats64,
.ndo_change_mtu = vsockmon_change_mtu,
};
static u32 always_on(struct net_device *dev)
{
return 1;
}
static const struct ethtool_ops vsockmon_ethtool_ops = {
.get_link = always_on,
};
static void vsockmon_setup(struct net_device *dev)
{
dev->type = ARPHRD_VSOCKMON;
dev->priv_flags |= IFF_NO_QUEUE;
dev->netdev_ops = &vsockmon_ops;
dev->ethtool_ops = &vsockmon_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;
dev->mtu = DEFAULT_MTU;
}
static struct rtnl_link_ops vsockmon_link_ops __read_mostly = {
.kind = "vsockmon",
.priv_size = sizeof(struct vsockmon),
.setup = vsockmon_setup,
};
static __init int vsockmon_register(void)
{
return rtnl_link_register(&vsockmon_link_ops);
}
static __exit void vsockmon_unregister(void)
{
rtnl_link_unregister(&vsockmon_link_ops);
}
module_init(vsockmon_register);
module_exit(vsockmon_unregister);
MODULE_LICENSE("GPL v2");
MODULE_AUTHOR("Gerard Garcia <ggarcia@deic.uab.cat>");
MODULE_DESCRIPTION("Vsock monitoring device. Based on nlmon device.");
MODULE_ALIAS_RTNL_LINK("vsockmon");