linux-stable/net/openvswitch/vport-internal_dev.c
Hillf Danton 9464cc37f3 net: openvswitch: free vport unless register_netdevice() succeeds
syzbot found the following crash on:

HEAD commit:    1e78030e Merge tag 'mmc-v5.3-rc1' of git://git.kernel.org/..
git tree:       upstream
console output: https://syzkaller.appspot.com/x/log.txt?x=148d3d1a600000
kernel config:  https://syzkaller.appspot.com/x/.config?x=30cef20daf3e9977
dashboard link: https://syzkaller.appspot.com/bug?extid=13210896153522fe1ee5
compiler:       gcc (GCC) 9.0.0 20181231 (experimental)
syz repro:      https://syzkaller.appspot.com/x/repro.syz?x=136aa8c4600000
C reproducer:   https://syzkaller.appspot.com/x/repro.c?x=109ba792600000

=====================================================================
BUG: memory leak
unreferenced object 0xffff8881207e4100 (size 128):
   comm "syz-executor032", pid 7014, jiffies 4294944027 (age 13.830s)
   hex dump (first 32 bytes):
     00 70 16 18 81 88 ff ff 80 af 8c 22 81 88 ff ff  .p........."....
     00 b6 23 17 81 88 ff ff 00 00 00 00 00 00 00 00  ..#.............
   backtrace:
     [<000000000eb78212>] kmemleak_alloc_recursive  include/linux/kmemleak.h:43 [inline]
     [<000000000eb78212>] slab_post_alloc_hook mm/slab.h:522 [inline]
     [<000000000eb78212>] slab_alloc mm/slab.c:3319 [inline]
     [<000000000eb78212>] kmem_cache_alloc_trace+0x145/0x2c0 mm/slab.c:3548
     [<00000000006ea6c6>] kmalloc include/linux/slab.h:552 [inline]
     [<00000000006ea6c6>] kzalloc include/linux/slab.h:748 [inline]
     [<00000000006ea6c6>] ovs_vport_alloc+0x37/0xf0  net/openvswitch/vport.c:130
     [<00000000f9a04a7d>] internal_dev_create+0x24/0x1d0  net/openvswitch/vport-internal_dev.c:164
     [<0000000056ee7c13>] ovs_vport_add+0x81/0x190  net/openvswitch/vport.c:199
     [<000000005434efc7>] new_vport+0x19/0x80 net/openvswitch/datapath.c:194
     [<00000000b7b253f1>] ovs_dp_cmd_new+0x22f/0x410  net/openvswitch/datapath.c:1614
     [<00000000e0988518>] genl_family_rcv_msg+0x2ab/0x5b0  net/netlink/genetlink.c:629
     [<00000000d0cc9347>] genl_rcv_msg+0x54/0x9c net/netlink/genetlink.c:654
     [<000000006694b647>] netlink_rcv_skb+0x61/0x170  net/netlink/af_netlink.c:2477
     [<0000000088381f37>] genl_rcv+0x29/0x40 net/netlink/genetlink.c:665
     [<00000000dad42a47>] netlink_unicast_kernel  net/netlink/af_netlink.c:1302 [inline]
     [<00000000dad42a47>] netlink_unicast+0x1ec/0x2d0  net/netlink/af_netlink.c:1328
     [<0000000067e6b079>] netlink_sendmsg+0x270/0x480  net/netlink/af_netlink.c:1917
     [<00000000aab08a47>] sock_sendmsg_nosec net/socket.c:637 [inline]
     [<00000000aab08a47>] sock_sendmsg+0x54/0x70 net/socket.c:657
     [<000000004cb7c11d>] ___sys_sendmsg+0x393/0x3c0 net/socket.c:2311
     [<00000000c4901c63>] __sys_sendmsg+0x80/0xf0 net/socket.c:2356
     [<00000000c10abb2d>] __do_sys_sendmsg net/socket.c:2365 [inline]
     [<00000000c10abb2d>] __se_sys_sendmsg net/socket.c:2363 [inline]
     [<00000000c10abb2d>] __x64_sys_sendmsg+0x23/0x30 net/socket.c:2363

BUG: memory leak
unreferenced object 0xffff88811723b600 (size 64):
   comm "syz-executor032", pid 7014, jiffies 4294944027 (age 13.830s)
   hex dump (first 32 bytes):
     01 00 00 00 01 00 00 00 00 00 00 00 00 00 00 00  ................
     00 00 00 00 00 00 00 00 02 00 00 00 05 35 82 c1  .............5..
   backtrace:
     [<00000000352f46d8>] kmemleak_alloc_recursive  include/linux/kmemleak.h:43 [inline]
     [<00000000352f46d8>] slab_post_alloc_hook mm/slab.h:522 [inline]
     [<00000000352f46d8>] slab_alloc mm/slab.c:3319 [inline]
     [<00000000352f46d8>] __do_kmalloc mm/slab.c:3653 [inline]
     [<00000000352f46d8>] __kmalloc+0x169/0x300 mm/slab.c:3664
     [<000000008e48f3d1>] kmalloc include/linux/slab.h:557 [inline]
     [<000000008e48f3d1>] ovs_vport_set_upcall_portids+0x54/0xd0  net/openvswitch/vport.c:343
     [<00000000541e4f4a>] ovs_vport_alloc+0x7f/0xf0  net/openvswitch/vport.c:139
     [<00000000f9a04a7d>] internal_dev_create+0x24/0x1d0  net/openvswitch/vport-internal_dev.c:164
     [<0000000056ee7c13>] ovs_vport_add+0x81/0x190  net/openvswitch/vport.c:199
     [<000000005434efc7>] new_vport+0x19/0x80 net/openvswitch/datapath.c:194
     [<00000000b7b253f1>] ovs_dp_cmd_new+0x22f/0x410  net/openvswitch/datapath.c:1614
     [<00000000e0988518>] genl_family_rcv_msg+0x2ab/0x5b0  net/netlink/genetlink.c:629
     [<00000000d0cc9347>] genl_rcv_msg+0x54/0x9c net/netlink/genetlink.c:654
     [<000000006694b647>] netlink_rcv_skb+0x61/0x170  net/netlink/af_netlink.c:2477
     [<0000000088381f37>] genl_rcv+0x29/0x40 net/netlink/genetlink.c:665
     [<00000000dad42a47>] netlink_unicast_kernel  net/netlink/af_netlink.c:1302 [inline]
     [<00000000dad42a47>] netlink_unicast+0x1ec/0x2d0  net/netlink/af_netlink.c:1328
     [<0000000067e6b079>] netlink_sendmsg+0x270/0x480  net/netlink/af_netlink.c:1917
     [<00000000aab08a47>] sock_sendmsg_nosec net/socket.c:637 [inline]
     [<00000000aab08a47>] sock_sendmsg+0x54/0x70 net/socket.c:657
     [<000000004cb7c11d>] ___sys_sendmsg+0x393/0x3c0 net/socket.c:2311
     [<00000000c4901c63>] __sys_sendmsg+0x80/0xf0 net/socket.c:2356

BUG: memory leak
unreferenced object 0xffff8881228ca500 (size 128):
   comm "syz-executor032", pid 7015, jiffies 4294944622 (age 7.880s)
   hex dump (first 32 bytes):
     00 f0 27 18 81 88 ff ff 80 ac 8c 22 81 88 ff ff  ..'........"....
     40 b7 23 17 81 88 ff ff 00 00 00 00 00 00 00 00  @.#.............
   backtrace:
     [<000000000eb78212>] kmemleak_alloc_recursive  include/linux/kmemleak.h:43 [inline]
     [<000000000eb78212>] slab_post_alloc_hook mm/slab.h:522 [inline]
     [<000000000eb78212>] slab_alloc mm/slab.c:3319 [inline]
     [<000000000eb78212>] kmem_cache_alloc_trace+0x145/0x2c0 mm/slab.c:3548
     [<00000000006ea6c6>] kmalloc include/linux/slab.h:552 [inline]
     [<00000000006ea6c6>] kzalloc include/linux/slab.h:748 [inline]
     [<00000000006ea6c6>] ovs_vport_alloc+0x37/0xf0  net/openvswitch/vport.c:130
     [<00000000f9a04a7d>] internal_dev_create+0x24/0x1d0  net/openvswitch/vport-internal_dev.c:164
     [<0000000056ee7c13>] ovs_vport_add+0x81/0x190  net/openvswitch/vport.c:199
     [<000000005434efc7>] new_vport+0x19/0x80 net/openvswitch/datapath.c:194
     [<00000000b7b253f1>] ovs_dp_cmd_new+0x22f/0x410  net/openvswitch/datapath.c:1614
     [<00000000e0988518>] genl_family_rcv_msg+0x2ab/0x5b0  net/netlink/genetlink.c:629
     [<00000000d0cc9347>] genl_rcv_msg+0x54/0x9c net/netlink/genetlink.c:654
     [<000000006694b647>] netlink_rcv_skb+0x61/0x170  net/netlink/af_netlink.c:2477
     [<0000000088381f37>] genl_rcv+0x29/0x40 net/netlink/genetlink.c:665
     [<00000000dad42a47>] netlink_unicast_kernel  net/netlink/af_netlink.c:1302 [inline]
     [<00000000dad42a47>] netlink_unicast+0x1ec/0x2d0  net/netlink/af_netlink.c:1328
     [<0000000067e6b079>] netlink_sendmsg+0x270/0x480  net/netlink/af_netlink.c:1917
     [<00000000aab08a47>] sock_sendmsg_nosec net/socket.c:637 [inline]
     [<00000000aab08a47>] sock_sendmsg+0x54/0x70 net/socket.c:657
     [<000000004cb7c11d>] ___sys_sendmsg+0x393/0x3c0 net/socket.c:2311
     [<00000000c4901c63>] __sys_sendmsg+0x80/0xf0 net/socket.c:2356
     [<00000000c10abb2d>] __do_sys_sendmsg net/socket.c:2365 [inline]
     [<00000000c10abb2d>] __se_sys_sendmsg net/socket.c:2363 [inline]
     [<00000000c10abb2d>] __x64_sys_sendmsg+0x23/0x30 net/socket.c:2363
=====================================================================

The function in net core, register_netdevice(), may fail with vport's
destruction callback either invoked or not. After commit 309b66970e
("net: openvswitch: do not free vport if register_netdevice() is failed."),
the duty to destroy vport is offloaded from the driver OTOH, which ends
up in the memory leak reported.

It is fixed by releasing vport unless device is registered successfully.
To do that, the callback assignment is defered until device is registered.

Reported-by: syzbot+13210896153522fe1ee5@syzkaller.appspotmail.com
Fixes: 309b66970e ("net: openvswitch: do not free vport if register_netdevice() is failed.")
Cc: Taehee Yoo <ap420073@gmail.com>
Cc: Greg Rose <gvrose8192@gmail.com>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Cc: Ying Xue <ying.xue@windriver.com>
Cc: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: Hillf Danton <hdanton@sina.com>
Acked-by: Pravin B Shelar <pshelar@ovn.org>
[sbrivio: this was sent to dev@openvswitch.org and never made its way
 to netdev -- resending original patch]
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Reviewed-by: Greg Rose <gvrose8192@gmail.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
2019-10-22 14:45:08 -07:00

293 lines
6.9 KiB
C

// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (c) 2007-2012 Nicira, Inc.
*/
#include <linux/if_vlan.h>
#include <linux/kernel.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/ethtool.h>
#include <linux/skbuff.h>
#include <net/dst.h>
#include <net/xfrm.h>
#include <net/rtnetlink.h>
#include "datapath.h"
#include "vport-internal_dev.h"
#include "vport-netdev.h"
struct internal_dev {
struct vport *vport;
};
static struct vport_ops ovs_internal_vport_ops;
static struct internal_dev *internal_dev_priv(struct net_device *netdev)
{
return netdev_priv(netdev);
}
/* Called with rcu_read_lock_bh. */
static netdev_tx_t
internal_dev_xmit(struct sk_buff *skb, struct net_device *netdev)
{
int len, err;
len = skb->len;
rcu_read_lock();
err = ovs_vport_receive(internal_dev_priv(netdev)->vport, skb, NULL);
rcu_read_unlock();
if (likely(!err)) {
struct pcpu_sw_netstats *tstats = this_cpu_ptr(netdev->tstats);
u64_stats_update_begin(&tstats->syncp);
tstats->tx_bytes += len;
tstats->tx_packets++;
u64_stats_update_end(&tstats->syncp);
} else {
netdev->stats.tx_errors++;
}
return NETDEV_TX_OK;
}
static int internal_dev_open(struct net_device *netdev)
{
netif_start_queue(netdev);
return 0;
}
static int internal_dev_stop(struct net_device *netdev)
{
netif_stop_queue(netdev);
return 0;
}
static void internal_dev_getinfo(struct net_device *netdev,
struct ethtool_drvinfo *info)
{
strlcpy(info->driver, "openvswitch", sizeof(info->driver));
}
static const struct ethtool_ops internal_dev_ethtool_ops = {
.get_drvinfo = internal_dev_getinfo,
.get_link = ethtool_op_get_link,
};
static void internal_dev_destructor(struct net_device *dev)
{
struct vport *vport = ovs_internal_dev_get_vport(dev);
ovs_vport_free(vport);
}
static void
internal_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats)
{
int i;
memset(stats, 0, sizeof(*stats));
stats->rx_errors = dev->stats.rx_errors;
stats->tx_errors = dev->stats.tx_errors;
stats->tx_dropped = dev->stats.tx_dropped;
stats->rx_dropped = dev->stats.rx_dropped;
for_each_possible_cpu(i) {
const struct pcpu_sw_netstats *percpu_stats;
struct pcpu_sw_netstats local_stats;
unsigned int start;
percpu_stats = per_cpu_ptr(dev->tstats, i);
do {
start = u64_stats_fetch_begin_irq(&percpu_stats->syncp);
local_stats = *percpu_stats;
} while (u64_stats_fetch_retry_irq(&percpu_stats->syncp, start));
stats->rx_bytes += local_stats.rx_bytes;
stats->rx_packets += local_stats.rx_packets;
stats->tx_bytes += local_stats.tx_bytes;
stats->tx_packets += local_stats.tx_packets;
}
}
static const struct net_device_ops internal_dev_netdev_ops = {
.ndo_open = internal_dev_open,
.ndo_stop = internal_dev_stop,
.ndo_start_xmit = internal_dev_xmit,
.ndo_set_mac_address = eth_mac_addr,
.ndo_get_stats64 = internal_get_stats,
};
static struct rtnl_link_ops internal_dev_link_ops __read_mostly = {
.kind = "openvswitch",
};
static void do_setup(struct net_device *netdev)
{
ether_setup(netdev);
netdev->max_mtu = ETH_MAX_MTU;
netdev->netdev_ops = &internal_dev_netdev_ops;
netdev->priv_flags &= ~IFF_TX_SKB_SHARING;
netdev->priv_flags |= IFF_LIVE_ADDR_CHANGE | IFF_OPENVSWITCH |
IFF_NO_QUEUE;
netdev->needs_free_netdev = true;
netdev->priv_destructor = NULL;
netdev->ethtool_ops = &internal_dev_ethtool_ops;
netdev->rtnl_link_ops = &internal_dev_link_ops;
netdev->features = NETIF_F_LLTX | NETIF_F_SG | NETIF_F_FRAGLIST |
NETIF_F_HIGHDMA | NETIF_F_HW_CSUM |
NETIF_F_GSO_SOFTWARE | NETIF_F_GSO_ENCAP_ALL;
netdev->vlan_features = netdev->features;
netdev->hw_enc_features = netdev->features;
netdev->features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX;
netdev->hw_features = netdev->features & ~NETIF_F_LLTX;
eth_hw_addr_random(netdev);
}
static struct vport *internal_dev_create(const struct vport_parms *parms)
{
struct vport *vport;
struct internal_dev *internal_dev;
struct net_device *dev;
int err;
vport = ovs_vport_alloc(0, &ovs_internal_vport_ops, parms);
if (IS_ERR(vport)) {
err = PTR_ERR(vport);
goto error;
}
dev = alloc_netdev(sizeof(struct internal_dev),
parms->name, NET_NAME_USER, do_setup);
vport->dev = dev;
if (!vport->dev) {
err = -ENOMEM;
goto error_free_vport;
}
vport->dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
if (!vport->dev->tstats) {
err = -ENOMEM;
goto error_free_netdev;
}
dev_net_set(vport->dev, ovs_dp_get_net(vport->dp));
internal_dev = internal_dev_priv(vport->dev);
internal_dev->vport = vport;
/* Restrict bridge port to current netns. */
if (vport->port_no == OVSP_LOCAL)
vport->dev->features |= NETIF_F_NETNS_LOCAL;
rtnl_lock();
err = register_netdevice(vport->dev);
if (err)
goto error_unlock;
vport->dev->priv_destructor = internal_dev_destructor;
dev_set_promiscuity(vport->dev, 1);
rtnl_unlock();
netif_start_queue(vport->dev);
return vport;
error_unlock:
rtnl_unlock();
free_percpu(dev->tstats);
error_free_netdev:
free_netdev(dev);
error_free_vport:
ovs_vport_free(vport);
error:
return ERR_PTR(err);
}
static void internal_dev_destroy(struct vport *vport)
{
netif_stop_queue(vport->dev);
rtnl_lock();
dev_set_promiscuity(vport->dev, -1);
/* unregister_netdevice() waits for an RCU grace period. */
unregister_netdevice(vport->dev);
free_percpu(vport->dev->tstats);
rtnl_unlock();
}
static netdev_tx_t internal_dev_recv(struct sk_buff *skb)
{
struct net_device *netdev = skb->dev;
struct pcpu_sw_netstats *stats;
if (unlikely(!(netdev->flags & IFF_UP))) {
kfree_skb(skb);
netdev->stats.rx_dropped++;
return NETDEV_TX_OK;
}
skb_dst_drop(skb);
nf_reset_ct(skb);
secpath_reset(skb);
skb->pkt_type = PACKET_HOST;
skb->protocol = eth_type_trans(skb, netdev);
skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
stats = this_cpu_ptr(netdev->tstats);
u64_stats_update_begin(&stats->syncp);
stats->rx_packets++;
stats->rx_bytes += skb->len;
u64_stats_update_end(&stats->syncp);
netif_rx(skb);
return NETDEV_TX_OK;
}
static struct vport_ops ovs_internal_vport_ops = {
.type = OVS_VPORT_TYPE_INTERNAL,
.create = internal_dev_create,
.destroy = internal_dev_destroy,
.send = internal_dev_recv,
};
int ovs_is_internal_dev(const struct net_device *netdev)
{
return netdev->netdev_ops == &internal_dev_netdev_ops;
}
struct vport *ovs_internal_dev_get_vport(struct net_device *netdev)
{
if (!ovs_is_internal_dev(netdev))
return NULL;
return internal_dev_priv(netdev)->vport;
}
int ovs_internal_dev_rtnl_link_register(void)
{
int err;
err = rtnl_link_register(&internal_dev_link_ops);
if (err < 0)
return err;
err = ovs_vport_ops_register(&ovs_internal_vport_ops);
if (err < 0)
rtnl_link_unregister(&internal_dev_link_ops);
return err;
}
void ovs_internal_dev_rtnl_link_unregister(void)
{
ovs_vport_ops_unregister(&ovs_internal_vport_ops);
rtnl_link_unregister(&internal_dev_link_ops);
}