linux-stable/net/l2tp/l2tp_eth.c
Eric Dumazet 23d3b8bfb8 net: qdisc busylock needs lockdep annotations
It seems we need to provide ability for stacked devices
to use specific lock_class_key for sch->busylock

We could instead default l2tpeth tx_queue_len to 0 (no qdisc), but
a user might use a qdisc anyway.

(So same fixes are probably needed on non LLTX stacked drivers)

Noticed while stressing L2TPV3 setup :

======================================================
 [ INFO: possible circular locking dependency detected ]
 3.6.0-rc3+ #788 Not tainted
 -------------------------------------------------------
 netperf/4660 is trying to acquire lock:
  (l2tpsock){+.-...}, at: [<ffffffffa0208db2>] l2tp_xmit_skb+0x172/0xa50 [l2tp_core]

 but task is already holding lock:
  (&(&sch->busylock)->rlock){+.-...}, at: [<ffffffff81596595>] dev_queue_xmit+0xd75/0xe00

 which lock already depends on the new lock.

 the existing dependency chain (in reverse order) is:

 -> #1 (&(&sch->busylock)->rlock){+.-...}:
        [<ffffffff810a5df0>] lock_acquire+0x90/0x200
        [<ffffffff817499fc>] _raw_spin_lock_irqsave+0x4c/0x60
        [<ffffffff81074872>] __wake_up+0x32/0x70
        [<ffffffff8136d39e>] tty_wakeup+0x3e/0x80
        [<ffffffff81378fb3>] pty_write+0x73/0x80
        [<ffffffff8136cb4c>] tty_put_char+0x3c/0x40
        [<ffffffff813722b2>] process_echoes+0x142/0x330
        [<ffffffff813742ab>] n_tty_receive_buf+0x8fb/0x1230
        [<ffffffff813777b2>] flush_to_ldisc+0x142/0x1c0
        [<ffffffff81062818>] process_one_work+0x198/0x760
        [<ffffffff81063236>] worker_thread+0x186/0x4b0
        [<ffffffff810694d3>] kthread+0x93/0xa0
        [<ffffffff81753e24>] kernel_thread_helper+0x4/0x10

 -> #0 (l2tpsock){+.-...}:
        [<ffffffff810a5288>] __lock_acquire+0x1628/0x1b10
        [<ffffffff810a5df0>] lock_acquire+0x90/0x200
        [<ffffffff817498c1>] _raw_spin_lock+0x41/0x50
        [<ffffffffa0208db2>] l2tp_xmit_skb+0x172/0xa50 [l2tp_core]
        [<ffffffffa021a802>] l2tp_eth_dev_xmit+0x32/0x60 [l2tp_eth]
        [<ffffffff815952b2>] dev_hard_start_xmit+0x502/0xa70
        [<ffffffff815b63ce>] sch_direct_xmit+0xfe/0x290
        [<ffffffff81595a05>] dev_queue_xmit+0x1e5/0xe00
        [<ffffffff815d9d60>] ip_finish_output+0x3d0/0x890
        [<ffffffff815db019>] ip_output+0x59/0xf0
        [<ffffffff815da36d>] ip_local_out+0x2d/0xa0
        [<ffffffff815da5a3>] ip_queue_xmit+0x1c3/0x680
        [<ffffffff815f4192>] tcp_transmit_skb+0x402/0xa60
        [<ffffffff815f4a94>] tcp_write_xmit+0x1f4/0xa30
        [<ffffffff815f5300>] tcp_push_one+0x30/0x40
        [<ffffffff815e6672>] tcp_sendmsg+0xe82/0x1040
        [<ffffffff81614495>] inet_sendmsg+0x125/0x230
        [<ffffffff81576cdc>] sock_sendmsg+0xdc/0xf0
        [<ffffffff81579ece>] sys_sendto+0xfe/0x130
        [<ffffffff81752c92>] system_call_fastpath+0x16/0x1b
  Possible unsafe locking scenario:

        CPU0                    CPU1
        ----                    ----
   lock(&(&sch->busylock)->rlock);
                                lock(l2tpsock);
                                lock(&(&sch->busylock)->rlock);
   lock(l2tpsock);

  *** DEADLOCK ***

 5 locks held by netperf/4660:
  #0:  (sk_lock-AF_INET){+.+.+.}, at: [<ffffffff815e581c>] tcp_sendmsg+0x2c/0x1040
  #1:  (rcu_read_lock){.+.+..}, at: [<ffffffff815da3e0>] ip_queue_xmit+0x0/0x680
  #2:  (rcu_read_lock_bh){.+....}, at: [<ffffffff815d9ac5>] ip_finish_output+0x135/0x890
  #3:  (rcu_read_lock_bh){.+....}, at: [<ffffffff81595820>] dev_queue_xmit+0x0/0xe00
  #4:  (&(&sch->busylock)->rlock){+.-...}, at: [<ffffffff81596595>] dev_queue_xmit+0xd75/0xe00

 stack backtrace:
 Pid: 4660, comm: netperf Not tainted 3.6.0-rc3+ #788
 Call Trace:
  [<ffffffff8173dbf8>] print_circular_bug+0x1fb/0x20c
  [<ffffffff810a5288>] __lock_acquire+0x1628/0x1b10
  [<ffffffff810a334b>] ? check_usage+0x9b/0x4d0
  [<ffffffff810a3f44>] ? __lock_acquire+0x2e4/0x1b10
  [<ffffffff810a5df0>] lock_acquire+0x90/0x200
  [<ffffffffa0208db2>] ? l2tp_xmit_skb+0x172/0xa50 [l2tp_core]
  [<ffffffff817498c1>] _raw_spin_lock+0x41/0x50
  [<ffffffffa0208db2>] ? l2tp_xmit_skb+0x172/0xa50 [l2tp_core]
  [<ffffffffa0208db2>] l2tp_xmit_skb+0x172/0xa50 [l2tp_core]
  [<ffffffffa021a802>] l2tp_eth_dev_xmit+0x32/0x60 [l2tp_eth]
  [<ffffffff815952b2>] dev_hard_start_xmit+0x502/0xa70
  [<ffffffff81594e0e>] ? dev_hard_start_xmit+0x5e/0xa70
  [<ffffffff81595961>] ? dev_queue_xmit+0x141/0xe00
  [<ffffffff815b63ce>] sch_direct_xmit+0xfe/0x290
  [<ffffffff81595a05>] dev_queue_xmit+0x1e5/0xe00
  [<ffffffff81595820>] ? dev_hard_start_xmit+0xa70/0xa70
  [<ffffffff815d9d60>] ip_finish_output+0x3d0/0x890
  [<ffffffff815d9ac5>] ? ip_finish_output+0x135/0x890
  [<ffffffff815db019>] ip_output+0x59/0xf0
  [<ffffffff815da36d>] ip_local_out+0x2d/0xa0
  [<ffffffff815da5a3>] ip_queue_xmit+0x1c3/0x680
  [<ffffffff815da3e0>] ? ip_local_out+0xa0/0xa0
  [<ffffffff815f4192>] tcp_transmit_skb+0x402/0xa60
  [<ffffffff815fa25e>] ? tcp_md5_do_lookup+0x18e/0x1a0
  [<ffffffff815f4a94>] tcp_write_xmit+0x1f4/0xa30
  [<ffffffff815f5300>] tcp_push_one+0x30/0x40
  [<ffffffff815e6672>] tcp_sendmsg+0xe82/0x1040
  [<ffffffff81614495>] inet_sendmsg+0x125/0x230
  [<ffffffff81614370>] ? inet_create+0x6b0/0x6b0
  [<ffffffff8157e6e2>] ? sock_update_classid+0xc2/0x3b0
  [<ffffffff8157e750>] ? sock_update_classid+0x130/0x3b0
  [<ffffffff81576cdc>] sock_sendmsg+0xdc/0xf0
  [<ffffffff81162579>] ? fget_light+0x3f9/0x4f0
  [<ffffffff81579ece>] sys_sendto+0xfe/0x130
  [<ffffffff810a69ad>] ? trace_hardirqs_on+0xd/0x10
  [<ffffffff8174a0b0>] ? _raw_spin_unlock_irq+0x30/0x50
  [<ffffffff810757e3>] ? finish_task_switch+0x83/0xf0
  [<ffffffff810757a6>] ? finish_task_switch+0x46/0xf0
  [<ffffffff81752cb7>] ? sysret_check+0x1b/0x56
  [<ffffffff81752c92>] system_call_fastpath+0x16/0x1b

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-09-05 17:49:27 -04:00

357 lines
8.3 KiB
C

/*
* L2TPv3 ethernet pseudowire driver
*
* Copyright (c) 2008,2009,2010 Katalix Systems Ltd
*
* 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.
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/module.h>
#include <linux/skbuff.h>
#include <linux/socket.h>
#include <linux/hash.h>
#include <linux/l2tp.h>
#include <linux/in.h>
#include <linux/etherdevice.h>
#include <linux/spinlock.h>
#include <net/sock.h>
#include <net/ip.h>
#include <net/icmp.h>
#include <net/udp.h>
#include <net/inet_common.h>
#include <net/inet_hashtables.h>
#include <net/tcp_states.h>
#include <net/protocol.h>
#include <net/xfrm.h>
#include <net/net_namespace.h>
#include <net/netns/generic.h>
#include "l2tp_core.h"
/* Default device name. May be overridden by name specified by user */
#define L2TP_ETH_DEV_NAME "l2tpeth%d"
/* via netdev_priv() */
struct l2tp_eth {
struct net_device *dev;
struct sock *tunnel_sock;
struct l2tp_session *session;
struct list_head list;
atomic_long_t tx_bytes;
atomic_long_t tx_packets;
atomic_long_t tx_dropped;
atomic_long_t rx_bytes;
atomic_long_t rx_packets;
atomic_long_t rx_errors;
};
/* via l2tp_session_priv() */
struct l2tp_eth_sess {
struct net_device *dev;
};
/* per-net private data for this module */
static unsigned int l2tp_eth_net_id;
struct l2tp_eth_net {
struct list_head l2tp_eth_dev_list;
spinlock_t l2tp_eth_lock;
};
static inline struct l2tp_eth_net *l2tp_eth_pernet(struct net *net)
{
return net_generic(net, l2tp_eth_net_id);
}
static struct lock_class_key l2tp_eth_tx_busylock;
static int l2tp_eth_dev_init(struct net_device *dev)
{
struct l2tp_eth *priv = netdev_priv(dev);
priv->dev = dev;
eth_hw_addr_random(dev);
memset(&dev->broadcast[0], 0xff, 6);
dev->qdisc_tx_busylock = &l2tp_eth_tx_busylock;
return 0;
}
static void l2tp_eth_dev_uninit(struct net_device *dev)
{
struct l2tp_eth *priv = netdev_priv(dev);
struct l2tp_eth_net *pn = l2tp_eth_pernet(dev_net(dev));
spin_lock(&pn->l2tp_eth_lock);
list_del_init(&priv->list);
spin_unlock(&pn->l2tp_eth_lock);
dev_put(dev);
}
static int l2tp_eth_dev_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct l2tp_eth *priv = netdev_priv(dev);
struct l2tp_session *session = priv->session;
unsigned int len = skb->len;
int ret = l2tp_xmit_skb(session, skb, session->hdr_len);
if (likely(ret == NET_XMIT_SUCCESS)) {
atomic_long_add(len, &priv->tx_bytes);
atomic_long_inc(&priv->tx_packets);
} else {
atomic_long_inc(&priv->tx_dropped);
}
return NETDEV_TX_OK;
}
static struct rtnl_link_stats64 *l2tp_eth_get_stats64(struct net_device *dev,
struct rtnl_link_stats64 *stats)
{
struct l2tp_eth *priv = netdev_priv(dev);
stats->tx_bytes = atomic_long_read(&priv->tx_bytes);
stats->tx_packets = atomic_long_read(&priv->tx_packets);
stats->tx_dropped = atomic_long_read(&priv->tx_dropped);
stats->rx_bytes = atomic_long_read(&priv->rx_bytes);
stats->rx_packets = atomic_long_read(&priv->rx_packets);
stats->rx_errors = atomic_long_read(&priv->rx_errors);
return stats;
}
static struct net_device_ops l2tp_eth_netdev_ops = {
.ndo_init = l2tp_eth_dev_init,
.ndo_uninit = l2tp_eth_dev_uninit,
.ndo_start_xmit = l2tp_eth_dev_xmit,
.ndo_get_stats64 = l2tp_eth_get_stats64,
};
static void l2tp_eth_dev_setup(struct net_device *dev)
{
ether_setup(dev);
dev->priv_flags &= ~IFF_TX_SKB_SHARING;
dev->features |= NETIF_F_LLTX;
dev->netdev_ops = &l2tp_eth_netdev_ops;
dev->destructor = free_netdev;
}
static void l2tp_eth_dev_recv(struct l2tp_session *session, struct sk_buff *skb, int data_len)
{
struct l2tp_eth_sess *spriv = l2tp_session_priv(session);
struct net_device *dev = spriv->dev;
struct l2tp_eth *priv = netdev_priv(dev);
if (session->debug & L2TP_MSG_DATA) {
unsigned int length;
length = min(32u, skb->len);
if (!pskb_may_pull(skb, length))
goto error;
pr_debug("%s: eth recv\n", session->name);
print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, skb->data, length);
}
if (!pskb_may_pull(skb, sizeof(ETH_HLEN)))
goto error;
secpath_reset(skb);
/* checksums verified by L2TP */
skb->ip_summed = CHECKSUM_NONE;
skb_dst_drop(skb);
nf_reset(skb);
if (dev_forward_skb(dev, skb) == NET_RX_SUCCESS) {
atomic_long_inc(&priv->rx_packets);
atomic_long_add(data_len, &priv->rx_bytes);
} else {
atomic_long_inc(&priv->rx_errors);
}
return;
error:
atomic_long_inc(&priv->rx_errors);
kfree_skb(skb);
}
static void l2tp_eth_delete(struct l2tp_session *session)
{
struct l2tp_eth_sess *spriv;
struct net_device *dev;
if (session) {
spriv = l2tp_session_priv(session);
dev = spriv->dev;
if (dev) {
unregister_netdev(dev);
spriv->dev = NULL;
module_put(THIS_MODULE);
}
}
}
#if defined(CONFIG_L2TP_DEBUGFS) || defined(CONFIG_L2TP_DEBUGFS_MODULE)
static void l2tp_eth_show(struct seq_file *m, void *arg)
{
struct l2tp_session *session = arg;
struct l2tp_eth_sess *spriv = l2tp_session_priv(session);
struct net_device *dev = spriv->dev;
seq_printf(m, " interface %s\n", dev->name);
}
#endif
static int l2tp_eth_create(struct net *net, u32 tunnel_id, u32 session_id, u32 peer_session_id, struct l2tp_session_cfg *cfg)
{
struct net_device *dev;
char name[IFNAMSIZ];
struct l2tp_tunnel *tunnel;
struct l2tp_session *session;
struct l2tp_eth *priv;
struct l2tp_eth_sess *spriv;
int rc;
struct l2tp_eth_net *pn;
tunnel = l2tp_tunnel_find(net, tunnel_id);
if (!tunnel) {
rc = -ENODEV;
goto out;
}
session = l2tp_session_find(net, tunnel, session_id);
if (session) {
rc = -EEXIST;
goto out;
}
if (cfg->ifname) {
dev = dev_get_by_name(net, cfg->ifname);
if (dev) {
dev_put(dev);
rc = -EEXIST;
goto out;
}
strlcpy(name, cfg->ifname, IFNAMSIZ);
} else
strcpy(name, L2TP_ETH_DEV_NAME);
session = l2tp_session_create(sizeof(*spriv), tunnel, session_id,
peer_session_id, cfg);
if (!session) {
rc = -ENOMEM;
goto out;
}
dev = alloc_netdev(sizeof(*priv), name, l2tp_eth_dev_setup);
if (!dev) {
rc = -ENOMEM;
goto out_del_session;
}
dev_net_set(dev, net);
if (session->mtu == 0)
session->mtu = dev->mtu - session->hdr_len;
dev->mtu = session->mtu;
dev->needed_headroom += session->hdr_len;
priv = netdev_priv(dev);
priv->dev = dev;
priv->session = session;
INIT_LIST_HEAD(&priv->list);
priv->tunnel_sock = tunnel->sock;
session->recv_skb = l2tp_eth_dev_recv;
session->session_close = l2tp_eth_delete;
#if defined(CONFIG_L2TP_DEBUGFS) || defined(CONFIG_L2TP_DEBUGFS_MODULE)
session->show = l2tp_eth_show;
#endif
spriv = l2tp_session_priv(session);
spriv->dev = dev;
rc = register_netdev(dev);
if (rc < 0)
goto out_del_dev;
__module_get(THIS_MODULE);
/* Must be done after register_netdev() */
strlcpy(session->ifname, dev->name, IFNAMSIZ);
dev_hold(dev);
pn = l2tp_eth_pernet(dev_net(dev));
spin_lock(&pn->l2tp_eth_lock);
list_add(&priv->list, &pn->l2tp_eth_dev_list);
spin_unlock(&pn->l2tp_eth_lock);
return 0;
out_del_dev:
free_netdev(dev);
out_del_session:
l2tp_session_delete(session);
out:
return rc;
}
static __net_init int l2tp_eth_init_net(struct net *net)
{
struct l2tp_eth_net *pn = net_generic(net, l2tp_eth_net_id);
INIT_LIST_HEAD(&pn->l2tp_eth_dev_list);
spin_lock_init(&pn->l2tp_eth_lock);
return 0;
}
static struct pernet_operations l2tp_eth_net_ops = {
.init = l2tp_eth_init_net,
.id = &l2tp_eth_net_id,
.size = sizeof(struct l2tp_eth_net),
};
static const struct l2tp_nl_cmd_ops l2tp_eth_nl_cmd_ops = {
.session_create = l2tp_eth_create,
.session_delete = l2tp_session_delete,
};
static int __init l2tp_eth_init(void)
{
int err = 0;
err = l2tp_nl_register_ops(L2TP_PWTYPE_ETH, &l2tp_eth_nl_cmd_ops);
if (err)
goto out;
err = register_pernet_device(&l2tp_eth_net_ops);
if (err)
goto out_unreg;
pr_info("L2TP ethernet pseudowire support (L2TPv3)\n");
return 0;
out_unreg:
l2tp_nl_unregister_ops(L2TP_PWTYPE_ETH);
out:
return err;
}
static void __exit l2tp_eth_exit(void)
{
unregister_pernet_device(&l2tp_eth_net_ops);
l2tp_nl_unregister_ops(L2TP_PWTYPE_ETH);
}
module_init(l2tp_eth_init);
module_exit(l2tp_eth_exit);
MODULE_LICENSE("GPL");
MODULE_AUTHOR("James Chapman <jchapman@katalix.com>");
MODULE_DESCRIPTION("L2TP ethernet pseudowire driver");
MODULE_VERSION("1.0");