rtnetlink: delay RTM_DELLINK notification until after ndo_uninit()
The commit 56bfa7ee7c ("unregister_netdevice : move RTM_DELLINK to
until after ndo_uninit") tried to do this ealier but while doing so
it created a problem. Unfortunately the delayed rtmsg_ifinfo() also
delayed call to fill_info(). So this translated into asking driver
to remove private state and then query it's private state. This
could have catastropic consequences.
This change breaks the rtmsg_ifinfo() into two parts - one takes the
precise snapshot of the device by called fill_info() before calling
the ndo_uninit() and the second part sends the notification using
collected snapshot.
It was brought to notice when last link is deleted from an ipvlan device
when it has free-ed the port and the subsequent .fill_info() call is
trying to get the info from the port.
kernel: [ 255.139429] ------------[ cut here ]------------
kernel: [ 255.139439] WARNING: CPU: 12 PID: 11173 at net/core/rtnetlink.c:2238 rtmsg_ifinfo+0x100/0x110()
kernel: [ 255.139493] Modules linked in: ipvlan bonding w1_therm ds2482 wire cdc_acm ehci_pci ehci_hcd i2c_dev i2c_i801 i2c_core msr cpuid bnx2x ptp pps_core mdio libcrc32c
kernel: [ 255.139513] CPU: 12 PID: 11173 Comm: ip Not tainted 3.18.0-smp-DEV #167
kernel: [ 255.139514] Hardware name: Intel RML,PCH/Ibis_QC_18, BIOS 1.0.10 05/15/2012
kernel: [ 255.139515] 0000000000000009 ffff880851b6b828 ffffffff815d87f4 00000000000000e0
kernel: [ 255.139516] 0000000000000000 ffff880851b6b868 ffffffff8109c29c 0000000000000000
kernel: [ 255.139518] 00000000ffffffa6 00000000000000d0 ffffffff81aaf580 0000000000000011
kernel: [ 255.139520] Call Trace:
kernel: [ 255.139527] [<ffffffff815d87f4>] dump_stack+0x46/0x58
kernel: [ 255.139531] [<ffffffff8109c29c>] warn_slowpath_common+0x8c/0xc0
kernel: [ 255.139540] [<ffffffff8109c2ea>] warn_slowpath_null+0x1a/0x20
kernel: [ 255.139544] [<ffffffff8150d570>] rtmsg_ifinfo+0x100/0x110
kernel: [ 255.139547] [<ffffffff814f78b5>] rollback_registered_many+0x1d5/0x2d0
kernel: [ 255.139549] [<ffffffff814f79cf>] unregister_netdevice_many+0x1f/0xb0
kernel: [ 255.139551] [<ffffffff8150acab>] rtnl_dellink+0xbb/0x110
kernel: [ 255.139553] [<ffffffff8150da90>] rtnetlink_rcv_msg+0xa0/0x240
kernel: [ 255.139557] [<ffffffff81329283>] ? rhashtable_lookup_compare+0x43/0x80
kernel: [ 255.139558] [<ffffffff8150d9f0>] ? __rtnl_unlock+0x20/0x20
kernel: [ 255.139562] [<ffffffff8152cb11>] netlink_rcv_skb+0xb1/0xc0
kernel: [ 255.139563] [<ffffffff8150a495>] rtnetlink_rcv+0x25/0x40
kernel: [ 255.139565] [<ffffffff8152c398>] netlink_unicast+0x178/0x230
kernel: [ 255.139567] [<ffffffff8152c75f>] netlink_sendmsg+0x30f/0x420
kernel: [ 255.139571] [<ffffffff814e0b0c>] sock_sendmsg+0x9c/0xd0
kernel: [ 255.139575] [<ffffffff811d1d7f>] ? rw_copy_check_uvector+0x6f/0x130
kernel: [ 255.139577] [<ffffffff814e11c9>] ? copy_msghdr_from_user+0x139/0x1b0
kernel: [ 255.139578] [<ffffffff814e1774>] ___sys_sendmsg+0x304/0x310
kernel: [ 255.139581] [<ffffffff81198723>] ? handle_mm_fault+0xca3/0xde0
kernel: [ 255.139585] [<ffffffff811ebc4c>] ? destroy_inode+0x3c/0x70
kernel: [ 255.139589] [<ffffffff8108e6ec>] ? __do_page_fault+0x20c/0x500
kernel: [ 255.139597] [<ffffffff811e8336>] ? dput+0xb6/0x190
kernel: [ 255.139606] [<ffffffff811f05f6>] ? mntput+0x26/0x40
kernel: [ 255.139611] [<ffffffff811d2b94>] ? __fput+0x174/0x1e0
kernel: [ 255.139613] [<ffffffff814e2129>] __sys_sendmsg+0x49/0x90
kernel: [ 255.139615] [<ffffffff814e2182>] SyS_sendmsg+0x12/0x20
kernel: [ 255.139617] [<ffffffff815df092>] system_call_fastpath+0x12/0x17
kernel: [ 255.139619] ---[ end trace 5e6703e87d984f6b ]---
Signed-off-by: Mahesh Bandewar <maheshb@google.com>
Reported-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Roopa Prabhu <roopa@cumulusnetworks.com>
Cc: David S. Miller <davem@davemloft.net>
Acked-by: Eric Dumazet <edumazet@google.com>
Acked-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/net/core/dev.c b/net/core/dev.c
index 0814a56..dd3bf58 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5925,6 +5925,8 @@
synchronize_net();
list_for_each_entry(dev, head, unreg_list) {
+ struct sk_buff *skb = NULL;
+
/* Shutdown queueing discipline. */
dev_shutdown(dev);
@@ -5934,6 +5936,11 @@
*/
call_netdevice_notifiers(NETDEV_UNREGISTER, dev);
+ if (!dev->rtnl_link_ops ||
+ dev->rtnl_link_state == RTNL_LINK_INITIALIZED)
+ skb = rtmsg_ifinfo_build_skb(RTM_DELLINK, dev, ~0U,
+ GFP_KERNEL);
+
/*
* Flush the unicast and multicast chains
*/
@@ -5943,9 +5950,8 @@
if (dev->netdev_ops->ndo_uninit)
dev->netdev_ops->ndo_uninit(dev);
- if (!dev->rtnl_link_ops ||
- dev->rtnl_link_state == RTNL_LINK_INITIALIZED)
- rtmsg_ifinfo(RTM_DELLINK, dev, ~0U, GFP_KERNEL);
+ if (skb)
+ rtmsg_ifinfo_send(skb, dev, GFP_KERNEL);
/* Notifier chain MUST detach us all upper devices. */
WARN_ON(netdev_has_any_upper_dev(dev));
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 61cb7e7..a9be2c1 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2245,8 +2245,8 @@
return skb->len;
}
-void rtmsg_ifinfo(int type, struct net_device *dev, unsigned int change,
- gfp_t flags)
+struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev,
+ unsigned int change, gfp_t flags)
{
struct net *net = dev_net(dev);
struct sk_buff *skb;
@@ -2264,11 +2264,28 @@
kfree_skb(skb);
goto errout;
}
- rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, flags);
- return;
+ return skb;
errout:
if (err < 0)
rtnl_set_sk_err(net, RTNLGRP_LINK, err);
+ return NULL;
+}
+
+void rtmsg_ifinfo_send(struct sk_buff *skb, struct net_device *dev, gfp_t flags)
+{
+ struct net *net = dev_net(dev);
+
+ rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, flags);
+}
+
+void rtmsg_ifinfo(int type, struct net_device *dev, unsigned int change,
+ gfp_t flags)
+{
+ struct sk_buff *skb;
+
+ skb = rtmsg_ifinfo_build_skb(type, dev, change, flags);
+ if (skb)
+ rtmsg_ifinfo_send(skb, dev, flags);
}
EXPORT_SYMBOL(rtmsg_ifinfo);