4.4-rc7 failure report
Subsystems (2)
Hi Dave,
The 4.4-rc7 kernel is failing for me. In my case, all of my vlan interfaces are failing to obtain a dhcp address using dhclient. I've tried a hand built 4.4-rc7, and the Fedora rawhide 4.4-rc7 kernel, both failed. I've tried NetworkManager and the old SysV network service, both fail. I tried a working dhclient from rhel7 on the Fedora rawhide install and it failed too. Running tcpdump on the interface shows the dhcp request going out, and a dhcp response coming back in. Running strace on dhclient shows that it writes the dhcp request, but it never recvs a dhcp response. If I manually bring the interface up with a static IP address then I'm able to run typical IP traffic across the link (aka, ping). It would seem that when dhclient registers a packet filter on the socket, that filter is preventing it from ever getting the dhcp response. The same dhclient works on any non-vlan interfaces in the system, so the filter must work for non-vlan interfaces. Aside from the fact that the interface is a vlan, we also use a priority egress map on the interface, and we use PFC flow control. Let me know if you need anymore to debug the issue, or email me off list and I can get you logins to my reproducer machines.
Signature · 2 lines
Doug Ledford <[email protected]> GPG KeyID: 0E572FDD
Quoted 10 lines · Doug Ledford
The 4.4-rc7 kernel is failing for me. In my case, all of my vlan interfaces are failing to obtain a dhcp address using dhclient. I've tried a hand built 4.4-rc7, and the Fedora rawhide 4.4-rc7 kernel, both failed. I've tried NetworkManager and the old SysV network service, both fail. I tried a working dhclient from rhel7 on the Fedora rawhide install and it failed too. Running tcpdump on the interface shows the dhcp request going out, and a dhcp response coming back in. Running strace on dhclient shows that it writes the dhcp request, but it never recvs a dhcp response. If I manually bring the interface up with a static IP address then I'm able to run typical IP traffic across the
Quoted 8 lines
link (aka, ping). It would seem that when dhclient registers a packet filter on the socket, that filter is preventing it from ever getting the dhcp response. The same dhclient works on any non-vlan interfaces in the system, so the filter must work for non-vlan interfaces. Aside from the fact that the interface is a vlan, we also use a priority egress map on the interface, and we use PFC flow control. Let me know if you need anymore to debug the issue, or email me off list and I can get you logins to my reproducer machines.
When you say 4.4-rc7 kernel is failing for you, what latest kernel version was working, where the socket filter was properly receiving the response on your vlan iface? Are you reasonably sure that the skb is dropped at the BPF filter attached to the dhcp's packet socket? Can you dump the BPF code of the filter? Are there any vlan offloading settings the filter is not taking into account (in the sense of classic BPF extensions, tcpdump/libpcap finally managed to cope with this)?
Quoted 20 lines · Daniel Borkmann
Quoted 10 lines · Doug Ledford
The 4.4-rc7 kernel is failing for me. In my case, all of my vlan interfaces are failing to obtain a dhcp address using dhclient. I've tried a hand built 4.4-rc7, and the Fedora rawhide 4.4-rc7 kernel, both failed. I've tried NetworkManager and the old SysV network service, both fail. I tried a working dhclient from rhel7 on the Fedora rawhide install and it failed too. Running tcpdump on the interface shows the dhcp request going out, and a dhcp response coming back in. Running strace on dhclient shows that it writes the dhcp request, but it never recvs a dhcp response. If I manually bring the interface up with a static IP address then I'm able to run typical IP traffic across the
Quoted 8 lines
link (aka, ping). It would seem that when dhclient registers a packet filter on the socket, that filter is preventing it from ever getting the dhcp response. The same dhclient works on any non-vlan interfaces in the system, so the filter must work for non-vlan interfaces. Aside from the fact that the interface is a vlan, we also use a priority egress map on the interface, and we use PFC flow control. Let me know if you need anymore to debug the issue, or email me off list and I can get you logins to my reproducer machines.
Quoted 3 lines
When you say 4.4-rc7 kernel is failing for you, what latest kernel version was working, where the socket filter was properly receiving the response on your vlan iface?
v4.3 final works. I haven't bisected where in the 4.4 series it quits working. I can do that tomorrow.
Quoted 2 lines
Are you reasonably sure that the skb is dropped at the BPF filter attached to the dhcp's packet socket?
No. I'm only reasonably sure that without a filter it works, I don't know if it gets dropped at the BPF filter or something else when the filter is added. It could be an interaction between the filter and PFC or vlan or anything else for all I know. But I figured the level of detail I gave should make it easy to reproduce locally by interested parties.
Quoted 2 lines
Can you dump the BPF code of
the filter?
It's whatever the filter is that dhclient uses. I'm pretty sure that's a pretty standard filter. And I tried known working dhclients in order to make sure it wasn't the latest dhclient's fault.
Quoted 4 lines
Are there any vlan offloading settings the filter is not taking into account (in the sense of classic BPF extensions, tcpdump/libpcap finally
managed to cope with this)?
Have no clue.
Signature · 2 lines
Doug Ledford <[email protected]> GPG KeyID: 0E572FDD
Quoted 21 lines · Doug Ledford
Quoted 20 lines · Daniel Borkmann
Quoted 18 lines · Doug Ledford
The 4.4-rc7 kernel is failing for me. In my case, all of my vlan interfaces are failing to obtain a dhcp address using dhclient. I've tried a hand built 4.4-rc7, and the Fedora rawhide 4.4-rc7 kernel, both failed. I've tried NetworkManager and the old SysV network service, both fail. I tried a working dhclient from rhel7 on the Fedora rawhide install and it failed too. Running tcpdump on the interface shows the dhcp request going out, and a dhcp response coming back in. Running strace on dhclient shows that it writes the dhcp request, but it never recvs a dhcp response. If I manually bring the interface up with a static IP address then I'm able to run typical IP traffic across the link (aka, ping). It would seem that when dhclient registers a packet filter on the socket, that filter is preventing it from ever getting the dhcp response. The same dhclient works on any non-vlan interfaces in the system, so the filter must work for non-vlan interfaces. Aside from the fact that the interface is a vlan, we also use a priority egress map on the interface, and we use PFC flow control. Let me know if you need anymore to debug the issue, or email me off list and I can get you logins to my reproducer machines.
Quoted 6 lines
Quoted 3 lines
When you say 4.4-rc7 kernel is failing for you, what latest kernel version was working, where the socket filter was properly receiving the response on your vlan iface?
v4.3 final works. I haven't bisected where in the 4.4 series it quits working. I can do that tomorrow.
I've tried to reproduce, but cannot seem to make dnsmasq work properly over vlan, so bisect would be great.
Quoted 26 lines · Alexei Starovoitov
Quoted 25 lines · Doug Ledford
Quoted 23 lines · Daniel Borkmann
Quoted 10 lines · Doug Ledford
The 4.4-rc7 kernel is failing for me. In my case, all of my vlan interfaces are failing to obtain a dhcp address using dhclient. I've tried a hand built 4.4-rc7, and the Fedora rawhide 4.4-rc7 kernel, both failed. I've tried NetworkManager and the old SysV network service, both fail. I tried a working dhclient from rhel7 on the Fedora rawhide install and it failed too. Running tcpdump on the interface shows the dhcp request going out, and a dhcp response coming back in. Running strace on dhclient shows that it writes the dhcp request, but it never recvs a dhcp response. If I manually bring the interface up with a static IP address then I'm able to run typical IP traffic across the
Quoted 8 lines
link (aka, ping). It would seem that when dhclient registers a packet filter on the socket, that filter is preventing it from ever getting the dhcp response. The same dhclient works on any non-vlan interfaces in the system, so the filter must work for non-vlan interfaces. Aside from the fact that the interface is a vlan, we also use a priority egress map on the interface, and we use PFC flow control. Let me know if you need anymore to debug the issue, or email me off list and I can get you logins to my reproducer machines.
When you say 4.4-rc7 kernel is failing for you, what latest kernel version was working, where the socket filter was properly receiving the response on your vlan iface?
Quoted 6 lines
Quoted 2 lines
v4.3 final works. I haven't bisected where in the 4.4 series it quits working. I can do that tomorrow.
I've tried to reproduce, but cannot seem to make dnsmasq work properly over vlan, so bisect would be great.
Yeah, I've been working on it. Issues with available machines that reproduce combined with what hardware they have and whether or not that hardware works at various steps in the bisection :-/
Signature · 2 lines
Doug Ledford <[email protected]> GPG KeyID: 0E572FDD
Quoted 30 lines · Doug Ledford
Quoted 29 lines · Alexei Starovoitov
Quoted 27 lines · Doug Ledford
Quoted 20 lines · Daniel Borkmann
Quoted 10 lines · Doug Ledford
The 4.4-rc7 kernel is failing for me. In my case, all of my vlan interfaces are failing to obtain a dhcp address using dhclient. I've tried a hand built 4.4-rc7, and the Fedora rawhide 4.4-rc7 kernel, both failed. I've tried NetworkManager and the old SysV network service, both fail. I tried a working dhclient from rhel7 on the Fedora rawhide install and it failed too. Running tcpdump on the interface shows the dhcp request going out, and a dhcp response coming back in. Running strace on dhclient shows that it writes the dhcp request, but it never recvs a dhcp response. If I manually bring the interface up with a static IP address then I'm able to run typical IP traffic across the
Quoted 8 lines
link (aka, ping). It would seem that when dhclient registers a packet filter on the socket, that filter is preventing it from ever getting the dhcp response. The same dhclient works on any non-vlan interfaces in the system, so the filter must work for non-vlan interfaces. Aside from the fact that the interface is a vlan, we also use a priority egress map on the interface, and we use PFC flow control. Let me know if you need anymore to debug the issue, or email me off list and I can get you logins to my reproducer machines.
Quoted 3 lines
When you say 4.4-rc7 kernel is failing for you, what latest kernel version was working, where the socket filter was properly receiving the response on your vlan iface?
v4.3 final works. I haven't bisected where in the 4.4 series it quits working. I can do that tomorrow.
Quoted 7 lines
Quoted 3 lines
I've tried to reproduce, but cannot seem to make dnsmasq work properly over vlan, so bisect would be great.
Yeah, I've been working on it. Issues with available machines that reproduce combined with what hardware they have and whether or not that hardware works at various steps in the bisection :-/
I've looked through all bpf related commits between v4.3..HEAD and don't see anything suspicious. Could it be that your setup exploited a bug that was fixed by 28f9ee22bcdd ("vlan: Do not put vlan headers back on bridge and macvlan ports")
Could you also provide more details on vlan+dhcp setup to help narrow it down if bisect is taking too long.
Quoted 34 lines · Alexei Starovoitov
Quoted 33 lines · Doug Ledford
Quoted 31 lines · Alexei Starovoitov
Quoted 21 lines · Doug Ledford
Quoted 20 lines · Daniel Borkmann
Quoted 18 lines · Doug Ledford
The 4.4-rc7 kernel is failing for me. In my case, all of my vlan interfaces are failing to obtain a dhcp address using dhclient. I've tried a hand built 4.4-rc7, and the Fedora rawhide 4.4-rc7 kernel, both failed. I've tried NetworkManager and the old SysV network service, both fail. I tried a working dhclient from rhel7 on the Fedora rawhide install and it failed too. Running tcpdump on the interface shows the dhcp request going out, and a dhcp response coming back in. Running strace on dhclient shows that it writes the dhcp request, but it never recvs a dhcp response. If I manually bring the interface up with a static IP address then I'm able to run typical IP traffic across the link (aka, ping). It would seem that when dhclient registers a packet filter on the socket, that filter is preventing it from ever getting the dhcp response. The same dhclient works on any non-vlan interfaces in the system, so the filter must work for non-vlan interfaces. Aside from the fact that the interface is a vlan, we also use a priority egress map on the interface, and we use PFC flow control. Let me know if you need anymore to debug the issue, or email me off list and I can get you logins to my reproducer machines.
Quoted 6 lines
Quoted 3 lines
When you say 4.4-rc7 kernel is failing for you, what latest kernel version was working, where the socket filter was properly receiving the response on your vlan iface?
v4.3 final works. I haven't bisected where in the 4.4 series it quits working. I can do that tomorrow.
I've tried to reproduce, but cannot seem to make dnsmasq work properly over vlan, so bisect would be great.
Quoted 6 lines
Quoted 3 lines
Yeah, I've been working on it. Issues with available machines that reproduce combined with what hardware they have and whether or not that hardware works at various steps in the bisection :-/
I've looked through all bpf related commits between v4.3..HEAD and don't see anything suspicious. Could it be that your setup exploited a bug that was fixed by
Agreed, also went over the bpf history yesterday and didn't find anything that could be related to this issue between the two tags.
The filter that dhclient seems to be using is (common/bpf.c):
struct bpf_insn dhcp_bpf_filter [] = {
/* Make sure this is an IP packet... */
BPF_STMT (BPF_LD + BPF_H + BPF_ABS, 12),
BPF_JUMP (BPF_JMP + BPF_JEQ + BPF_K, ETHERTYPE_IP, 0, 8),
/* Make sure it's a UDP packet... */
BPF_STMT (BPF_LD + BPF_B + BPF_ABS, 23),
BPF_JUMP (BPF_JMP + BPF_JEQ + BPF_K, IPPROTO_UDP, 0, 6),
/* Make sure this isn't a fragment... */
BPF_STMT(BPF_LD + BPF_H + BPF_ABS, 20),
BPF_JUMP(BPF_JMP + BPF_JSET + BPF_K, 0x1fff, 4, 0),
/* Get the IP header length... */
BPF_STMT (BPF_LDX + BPF_B + BPF_MSH, 14),
/* Make sure it's to the right port... */
BPF_STMT (BPF_LD + BPF_H + BPF_IND, 16),
BPF_JUMP (BPF_JMP + BPF_JEQ + BPF_K, 67, 0, 1), /* patch */
/* If we passed all the tests, ask for the whole packet. */
BPF_STMT(BPF_RET+BPF_K, (u_int)-1),
/* Otherwise, drop it. */
BPF_STMT(BPF_RET+BPF_K, 0),
};Given that this drop doesn't strictly need to be caused by filter code, it would be nice if you could pin the location down where the packet gets dropped exactly. Perhaps dropwatch or perf with '-e skb:kfree_skb -a -g dhclient <iface>', etc could help to get a first overview to dig into details then.
Quoted 4 lines
28f9ee22bcdd("vlan: Do not put vlan headers back on bridge and macvlan ports")Could you also provide more details on vlan+dhcp setup to help narrow it down if bisect is taking too long.
Quoted 5 lines · Daniel Borkmann
Given that this drop doesn't strictly need to be caused by filter code, it would be nice if you could pin the location down where the packet gets dropped exactly. Perhaps dropwatch or perf with '-e skb:kfree_skb -a -g dhclient <iface>', etc could help to get a first overview to dig into details then.
Wild stab in the dark, but..
Could this bug be another symptom fixed by http://article.gmane.org/gmane.linux.network/392885 ?
Dave
Quoted 10 lines · Dave Jones
Quoted 5 lines · Daniel Borkmann
Given that this drop doesn't strictly need to be caused by filter code, it would be nice if you could pin the location down where the packet gets dropped exactly. Perhaps dropwatch or perf with '-e skb:kfree_skb -a -g dhclient <iface>', etc could help to get a first overview to dig into details then.
Wild stab in the dark, but..
Could this bug be another symptom fixed by http://article.gmane.org/gmane.linux.network/392885 ?
dhclient does not use async io
David Miller
maintainerFrom: Eric Dumazet <[email protected]>
Date: Wed, 30 Dec 2015 11:55:25 -0500
Quoted 9 lines · Dave Jones
Quoted 8 lines · Daniel Borkmann
Quoted 6 lines
Given that this drop doesn't strictly need to be caused by filter code, it would be nice if you could pin the location down where the packet gets dropped exactly. Perhaps dropwatch or perf with '-e skb:kfree_skb -a -g dhclient <iface>', etc could help to get a first overview to dig into details then.
Quoted 4 lines
Quoted 2 lines
Wild stab in the dark, but..
Could this bug be another symptom fixed by http://article.gmane.org/gmane.linux.network/392885 ?dhclient does not use async io
But the bug causes requests to "LOOK" like async I/O, right?
Quoted 12 lines · David Miller
From: Eric Dumazet <[email protected]>
Date: Wed, 30 Dec 2015 11:55:25 -0500Quoted 9 lines · Dave Jones
Quoted 8 lines · Daniel Borkmann
Quoted 6 lines
Given that this drop doesn't strictly need to be caused by filter code, it would be nice if you could pin the location down where the packet gets dropped exactly. Perhaps dropwatch or perf with '-e skb:kfree_skb -a -g dhclient <iface>', etc could help to get a first overview to dig into details then.
Quoted 7 lines
Quoted 4 lines
Quoted 2 lines
Wild stab in the dark, but..
Could this bug be another symptom fixed by http://article.gmane.org/gmane.linux.network/392885 ?dhclient does not use async io
But the bug causes requests to "LOOK" like async I/O, right?
I got my hands on a machine that's reliable, so the bisecting is finally progressing again. The machines with ocrdma devices can have link issues, the machines with mlx5 devices don't support vlans in all kernel versions, and some of my machines with mlx4 devices simply didn't have their Ethernet port plugged in. I managed to check out a machine with mlx4 in IB/Eth mode that is otherwise reliable on all of the kernel versions the bisection covers and modified its setup to show me at a glance if the dhcp on vlan is working and now I'm probably over half down with the bisection.
Signature · 2 lines
Doug Ledford <[email protected]> GPG KeyID: 0E572FDD
Quoted 12 lines · David Miller
From: Eric Dumazet <[email protected]>
Date: Wed, 30 Dec 2015 11:55:25 -0500Quoted 9 lines · Dave Jones
Quoted 8 lines · Daniel Borkmann
Quoted 6 lines
Given that this drop doesn't strictly need to be caused by filter code, it would be nice if you could pin the location down where the packet gets dropped exactly. Perhaps dropwatch or perf with '-e skb:kfree_skb -a -g dhclient <iface>', etc could help to get a first overview to dig into details then.
Quoted 6 lines
Quoted 4 lines
Quoted 2 lines
Wild stab in the dark, but..
Could this bug be another symptom fixed by http://article.gmane.org/gmane.linux.network/392885 ?dhclient does not use async io
But the bug causes requests to "LOOK" like async I/O, right?
This is not how I understood the bug.
By having a bit set (because we lacked a clear of wq->flags), we have :
sock_wake_async()
...
case SOCK_WAKE_WAITD:
if (test_bit(SOCKWQ_ASYNC_WAITDATA, &wq->flags)) break;
So we never call kill_fasync()
Quoted 39 lines · Alexei Starovoitov
Quoted 30 lines · Doug Ledford
Quoted 29 lines · Alexei Starovoitov
Quoted 27 lines · Doug Ledford
Quoted 20 lines · Daniel Borkmann
Quoted 10 lines · Doug Ledford
The 4.4-rc7 kernel is failing for me. In my case, all of my vlan interfaces are failing to obtain a dhcp address using dhclient. I've tried a hand built 4.4-rc7, and the Fedora rawhide 4.4-rc7 kernel, both failed. I've tried NetworkManager and the old SysV network service, both fail. I tried a working dhclient from rhel7 on the Fedora rawhide install and it failed too. Running tcpdump on the interface shows the dhcp request going out, and a dhcp response coming back in. Running strace on dhclient shows that it writes the dhcp request, but it never recvs a dhcp response. If I manually bring the interface up with a static IP address then I'm able to run typical IP traffic across the
Quoted 8 lines
link (aka, ping). It would seem that when dhclient registers a packet filter on the socket, that filter is preventing it from ever getting the dhcp response. The same dhclient works on any non-vlan interfaces in the system, so the filter must work for non-vlan interfaces. Aside from the fact that the interface is a vlan, we also use a priority egress map on the interface, and we use PFC flow control. Let me know if you need anymore to debug the issue, or email me off list and I can get you logins to my reproducer machines.
Quoted 3 lines
When you say 4.4-rc7 kernel is failing for you, what latest kernel version was working, where the socket filter was properly receiving the response on your vlan iface?
v4.3 final works. I haven't bisected where in the 4.4 series it quits working. I can do that tomorrow.
Quoted 7 lines
Quoted 3 lines
I've tried to reproduce, but cannot seem to make dnsmasq work properly over vlan, so bisect would be great.
Yeah, I've been working on it. Issues with available machines that reproduce combined with what hardware they have and whether or not that hardware works at various steps in the bisection :-/
Quoted 7 lines
I've looked through all bpf related commits between v4.3..HEAD and don't see anything suspicious. Could it be that your setup exploited a bug that was fixed by
28f9ee22bcdd("vlan: Do not put vlan headers back on bridge and macvlan ports")Could you also provide more details on vlan+dhcp setup to help narrow it down if bisect is taking too long.
My bisection got down to the last few steps and just didn't make sense.
So, I ended up starting it over. I'm not sure how/why I saw that v4.3
worked the first time around, but the second time around it failed. So I also tried a pre-made 4.2.8-300 kernel from Fedora 23 and it failed as well. The problem at least spans 4.2 through 4.4, so it's been a while.
I'll continue searching more kernels tomorrow, but I've been doing this
while I still have company in town for the holidays so I'm gonna go be with them when I'm done writing this.
I've recently made some changes to my network setup here, so that might be related to why I'm seeing it now. I'll provide details on my test setup in case any of it helps people on this:
Ethernet network is used for RDMA testing. Switches are Mellanox 56GigE switches. The ports with multiple vlans are all set in hybrid mode, untagged frames to vlan 40, tagged frames for vlans 43 and 45 allowed. Switch has DCB enabled, priority 5 is no-drop, ports are set to use PFC and MTU 9216 and LLDP is enabled on the ports as well.
The head node of the cluster runs dhcpd on the vlans (as well as the InfiniBand ports). The test machine has a static IP address configured for each port/vlan in the server's config.
On the client, I've set the base interface to dhcp, vlan 43 to static IP assignment, and vlan 45 to dhcp. This allows me to see at a glance if things are working since I know if the base device gets an IP and vlan 45 doesn't and instead times out and goes away, then the dhcp on the vlan failed. (I needed to set one vlan to static so the vlan creation didn't depend on dhcp success because with some kernel versions and some hardware types, namely mlx5, vlans weren't working at all and you could mistake no vlans made for a problem with dhcp when it was really a problem with vlans on mlx5 hardware).
This is the failing device's config:
[root@rdma-perf-00 ~]$ more /etc/sysconfig/network-scripts/ifcfg-mlx4_roce.45 DEVICE=mlx4_roce.45
VLAN=yes
VLAN_ID=45
REORDER_HDR=0 VLAN_EGRESS_PRIORITY_MAP=0:5,1:5,2:5,3:5,4:5,5:5,6:5,7:5 TYPE=Vlan
ONBOOT=yes
BOOTPROTO=dhcp
DEFROUTE=no
PEERDNS=no
PEERROUTES=yes
IPV4_FAILURE_FATAL=yes
IPV6INIT=yes
IPV6_AUTOCONF=yes
IPV6_DEFROUTE=no
IPV6_PEERDNS=no
IPV6_PEERROUTES=yes
IPV6_FAILURE_FATAL=no
NAME=mlx4_roce.45
And if the interface actually comes up, there is this NetworkManager dispatcher script:
[root@rdma-perf-00 ~]$ more /etc/NetworkManager/dispatcher.d/98-mlx4_roce.45-egress.conf #!/bin/sh
interface=$1
status=$2
[ "$interface" = mlx4_roce.45 ] || exit 0
case $status in
up)
tc qdisc add dev mlx4_roce root mqprio num_tc 8 map 5 5 5 5 5 5 5 5 5 5
5 5 5 5 5 5 queues 32@0 32@32 32@64 32@96 32@128 32@160 32@192 32@224
# tc_wrap.py -i mlx4_roce -u 5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5 ;; esac
The base device's config file is this:
[root@rdma-perf-00 ~]$ more /etc/sysconfig/network-scripts/ifcfg-mlx4_roce DEVICE=mlx4_roce
TYPE=Ethernet
ONBOOT=yes
HWADDR=00:02:c9:31:77:91
BOOTPROTO=dhcp
DEFROUTE=no
PEERDNS=no
PEERROUTES=yes
IPV4_FAILURE_FATAL=yes
IPV6INIT=yes
IPV6_AUTOCONF=yes
IPV6_DEFROUTE=no
IPV6_PEERDNS=no
IPV6_PEERROUTES=yes
IPV6_FAILURE_FATAL=no
MTU=9000
NAME=mlx4_roce
Let me know if you need any more details on the setup. I'll report back when I've actually *really* identified when the bug appeared.
Signature · 2 lines
Doug Ledford <[email protected]> GPG KeyID: 0E572FDD