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>
The current codes only deal with the case that the skb is dropped, it
may meet one use-after-free issue when NF_HOOK returns 0 that means
the skb is stolen by one netfilter rule or hook.
When one netfilter rule or hook stoles the skb and return NF_STOLEN,
it means the skb is taken by the rule, and other modules should not
touch this skb ever. Maybe the skb is queued or freed directly by the
rule.
Now uses the nf_hook instead of NF_HOOK to get the result of netfilter,
and check the return value of nf_hook. Only when its value equals 1, it
means the skb could go ahead. Or reset the skb as NULL.
BTW, because vrf_rcv_finish is empty function, so needn't invoke it
even though nf_hook returns 1. But we need to modify vrf_rcv_finish
to deal with the NF_STOLEN case.
There are two cases when skb is stolen.
1. The skb is stolen and freed directly.
There is nothing we need to do, and vrf_rcv_finish isn't invoked.
2. The skb is queued and reinjected again.
The vrf_rcv_finish would be invoked as okfn, so need to free the
skb in it.
Signed-off-by: Gao Feng <gfree.wind@vip.163.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Moving the loopback into a VRF breaks networking for the default VRF.
Since the VRF device is the loopback for VRF domains, there is no
reason to move the loopback. Given the repercussions, block attempts
to set lo into a VRF.
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Reviewed-by: Greg Rose <gvrose8192@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
A function in kernel/bpf/syscall.c which got a bug fix in 'net'
was moved to kernel/bpf/verifier.c in 'net-next'.
Signed-off-by: David S. Miller <davem@davemloft.net>
Add netlink_ext_ack arg to rtnl_doit_func. Pass extack arg to nlmsg_parse
for doit functions that call it directly.
This is the first step to using extended error reporting in rtnetlink.
>From here individual subsystems can be updated to set netlink_ext_ack as
needed.
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Only need 1 l3mdev FIB rule. Fix setting NLM_F_EXCL in the nlmsghdr.
Fixes: 1aa6c4f6b8 ("net: vrf: Add l3mdev rules on first device create")
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Conflicts:
drivers/net/ethernet/broadcom/genet/bcmmii.c
drivers/net/hyperv/netvsc.c
kernel/bpf/hashtab.c
Almost entirely overlapping changes.
Signed-off-by: David S. Miller <davem@davemloft.net>
The VRF driver allows users to implement device based features for an
entire domain. For example, a qdisc or netfilter rules can be attached
to a VRF device or tcpdump can be used to view packets for all devices
in the L3 domain.
The device-based features come with a performance penalty, most
notably in the Tx path. The VRF driver uses the l3mdev_l3_out hook
to switch the dst on an skb to its private dst. This allows the skb
to traverse the xmit stack with the device set to the VRF device
which in turn enables the netfilter and qdisc features. The VRF
driver then performs the FIB lookup again and reinserts the packet.
This patch avoids the redirect for IPv6 packets if a qdisc has not
been attached to a VRF device which is the default config. In this
case the netfilter hooks and network taps are directly traversed in
the l3mdev_l3_out handler. If a qdisc is attached to a VRF device,
then the redirect using the vrf dst is done.
Additional overhead is removed by only checking packet taps if a
socket is open on the device (vrf_dev->ptype_all list is not empty).
Packet sockets bound to any device will still get a copy of the
packet via the real ingress or egress interface.
The end result of this change is a decrease in the overhead of VRF
for the default, baseline case (ie., no netfilter rules, no packet
sockets, no qdisc) from a +3% improvement for UDP which has a lookup
per packet (VRF being better than no l3mdev) to ~2% loss for TCP_CRR
which connects a socket for each request-response.
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The VRF driver allows users to implement device based features for an
entire domain. For example, a qdisc or netfilter rules can be attached
to a VRF device or tcpdump can be used to view packets for all devices
in the L3 domain.
The device-based features come with a performance penalty, most
notably in the Tx path. The VRF driver uses the l3mdev_l3_out hook
to switch the dst on an skb to its private dst. This allows the skb
to traverse the xmit stack with the device set to the VRF device
which in turn enables the netfilter and qdisc features. The VRF
driver then performs the FIB lookup again and reinserts the packet.
This patch avoids the redirect for IPv4 packets if a qdisc has not
been attached to a VRF device which is the default config. In this
case the netfilter hooks and network taps are directly traversed in
the l3mdev_l3_out handler. If a qdisc is attached to a VRF device,
then the redirect using the vrf dst is done.
Additional overhead is removed by only checking packet taps if a
socket is open on the device (vrf_dev->ptype_all list is not empty).
Packet sockets bound to any device will still get a copy of the
packet via the real ingress or egress interface.
The end result of this change is a decrease in the overhead of VRF
for the default, baseline case (ie., no netfilter rules, no packet
sockets, no qdisc) to ~3% for UDP which has a lookup per packet and
< 1% overhead for connected sockets that leverage early demux and
avoid FIB lookups.
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The VRF driver takes a reference to the inet6_dev on the VRF device for
its rt6_local dst when handling local traffic through the VRF device as
a loopback. When the device is deleted the driver does a put on the idev
but does not reset rt6i_idev in the rt6_info struct. When the dst is
destroyed, dst_destroy calls ip6_dst_destroy which does a second put for
what is essentially the same reference causing it to be prematurely freed.
Reset rt6i_idev after the put in the vrf driver.
Fixes: b4869aa2f8 ("net: vrf: ipv6 support for local traffic to
local addresses")
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Allow listeners of the subsequent CHANGEUPPER notification to retrieve
the VRF's table ID by calling l3mdev_fib_table() with the slave netdev.
Without this change, the netdev won't be considered an L3 slave and the
function would return 0.
This is consistent with other master device such as bridge and bond that
set the slave's private flag before linking. It also makes
do_vrf_{add,del}_slave() symmetric.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Acked-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
After the dst->pending_confirm flag was removed, we do not
need anymore to provide dst arg to dst_neigh_output.
So, rename it to neigh_output as before commit 5110effee8
("net: Do delayed neigh confirmation.").
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add new skbuff flag to allow protocols to confirm neighbour.
When same struct dst_entry can be used for many different
neighbours we can not use it for pending confirmations.
Add sock_confirm_neigh() helper to confirm the neighbour and
use it for IPv4, IPv6 and VRF before dst_neigh_output.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Frank reported that vrf devices can be created with a table id of 0.
This breaks many of the run time table id checks and should not be
allowed. Detect this condition at create time and fail with EINVAL.
Fixes: 193125dbd8 ("net: Introduce VRF device driver")
Reported-by: Frank Kellermann <frank.kellermann@atos.net>
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
fib_select_path does not call fib_select_multipath if oif is set in the
flow struct. For VRF use cases oif is always set, so multipath route
selection is bypassed. Use the FLOWI_FLAG_SKIP_NH_OIF to skip the oif
check similar to what is done in fib_table_lookup.
Add saddr and proto to the flow struct for the fib lookup done by the
VRF driver to better match hash computation for a flow.
Fixes: 613d09b30f ("net: Use VRF device index for lookups on TX")
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The network device operation for reading statistics is only called
in one place, and it ignores the return value. Having a structure
return value is potentially confusing because some future driver could
incorrectly assume that the return value was used.
Fix all drivers with ndo_get_stats64 to have a void function.
Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The move from rx-handler to L3 receive handler inadvertantly dropped the
rx counters. Restore them.
Fixes: 74b20582ac ("net: l3mdev: Add hook in ip and ipv6")
Reported-by: Dinesh Dutt <ddutt@cumulusnetworks.com>
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Locally originated traffic in a VRF fails in the presence of a POSTROUTING
rule. For example,
$ iptables -t nat -A POSTROUTING -s 11.1.1.0/24 -j MASQUERADE
$ ping -I red -c1 11.1.1.3
ping: Warning: source address might be selected on device other than red.
PING 11.1.1.3 (11.1.1.3) from 11.1.1.2 red: 56(84) bytes of data.
ping: sendmsg: Operation not permitted
Worse, the above causes random corruption resulting in a panic in random
places (I have not seen a consistent backtrace).
Call nf_reset to drop the conntrack info following the pass through the
VRF device. The nf_reset is needed on Tx but not Rx because of the order
in which NF_HOOK's are hit: on Rx the VRF device is after the real ingress
device and on Tx it is is before the real egress device. Connection
tracking should be tied to the real egress device and not the VRF device.
Fixes: 8f58336d3f ("net: Add ethernet header for pass through VRF device")
Fixes: 35402e3136 ("net: Add IPv6 support to VRF device")
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Connection tracking with VRF is broken because the pass through the VRF
device drops the connection tracking info. Removing the call to nf_reset
allows DNAT and MASQUERADE to work across interfaces within a VRF.
Fixes: 73e20b761a ("net: vrf: Add support for PREROUTING rules on vrf device")
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Enable support for IPv4 multicast:
- similar to unicast the flow struct is updated to L3 master device
if relevant prior to calling fib_rules_lookup. The table id is saved
to the lookup arg so the rule action for ipmr can return the table
associated with the device.
- ip_mr_forward needs to check for master device mismatch as well
since the skb->dev is set to it
- allow multicast address on VRF device for Rx by checking for the
daddr in the VRF device as well as the original ingress device
- on Tx need to drop to __mkroute_output when FIB lookup fails for
multicast destination address.
- if CONFIG_IP_MROUTE_MULTIPLE_TABLES is enabled VRF driver creates
IPMR FIB rules on first device create similar to FIB rules. In
addition the VRF driver does not divert IPv4 multicast packets:
it breaks on Tx since the fib lookup fails on the mcast address.
With this patch, ipmr forwarding and local rx/tx work.
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Currently, socket lookups for l3mdev (vrf) use cases can match a socket
that is bound to a port but not a device (ie., a global socket). If the
sysctl tcp_l3mdev_accept is not set this leads to ack packets going out
based on the main table even though the packet came in from an L3 domain.
The end result is that the connection does not establish creating
confusion for users since the service is running and a socket shows in
ss output. Fix by requiring an exact dif to sk_bound_dev_if match if the
skb came through an interface enslaved to an l3mdev device and the
tcp_l3mdev_accept is not set.
skb's through an l3mdev interface are marked by setting a flag in
inet{6}_skb_parm. The IPv6 variant is already set; this patch adds the
flag for IPv4. Using an skb flag avoids a device lookup on the dif. The
flag is set in the VRF driver using the IP{6}CB macros. For IPv4, the
inet_skb_parm struct is moved in the cb per commit 971f10eca1, so the
match function in the TCP stack needs to use TCP_SKB_CB. For IPv6, the
move is done after the socket lookup, so IP6CB is used.
The flags field in inet_skb_parm struct needs to be increased to add
another flag. There is currently a 1-byte hole following the flags,
so it can be expanded to u16 without increasing the size of the struct.
Fixes: 193125dbd8 ("net: Introduce VRF device driver")
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
No longer used after d66f6c0a8f ("net: ipv4: Remove l3mdev_get_saddr")
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Flip the IPv6 output path to use the l3mdev tx out hook. The VRF dst
is not returned on the first FIB lookup. Instead, the dst on the
skb is switched at the beginning of the IPv6 output processing to
send the packet to the VRF driver on xmit.
Link scope addresses (linklocal and multicast) need special handling:
specifically the oif the flow struct can not be changed because we
want the lookup tied to the enslaved interface. ie., the source address
and the returned route MUST point to the interface scope passed in.
Convert the existing vrf_get_rt6_dst to handle only link scope addresses.
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Flip the IPv4 output path to use the l3mdev tx out hook. The VRF dst
is not returned on the first FIB lookup. Instead, the dst on the
skb is switched at the beginning of the IPv4 output processing to
send the packet to the VRF driver on xmit.
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add support for PREROUTING rules with skb->dev set to the vrf device.
INPUT rules are already allowed. Provides symmetry with the output path
which allows POSTROUTING rules.
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
IPv6 source address selection needs to consider the real egress route.
Similar to IPv4 implement a get_saddr6 method which is called if
source address has not been set. The get_saddr6 method does a full
lookup which means pulling a route from the VRF FIB table and properly
considering linklocal/multicast destination addresses. Lookup failures
(eg., unreachable) then cause the source address selection to fail
which gets propagated back to the caller.
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Attempting to delete a VRF device with a socket bound to it can stall:
unregister_netdevice: waiting for red to become free. Usage count = 1
The unregister is waiting for the dst to be released and with it
references to the vrf device. Similar to dst_ifdown switch the dst
dev to loopback on delete for all of the dst's for the vrf device
and release the references to the vrf device.
Fixes: 193125dbd8 ("net: Introduce VRF device driver")
Fixes: 35402e3136 ("net: Add IPv6 support to VRF device")
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
1. Default VRF devices to not having a qdisc (IFF_NO_QUEUE). Users
can add one as desired.
2. Disable adding a VLAN to a VRF device.
3. Enable offloads and hardware features similar to other logical
devices (e.g., dummy, veth)
Change provides a significant boost in TCP stream Tx performance,
from ~2,700 Mbps to ~18,100 Mbps and makes throughput close to the
performance without a VRF (18,500 Mbps). netperf TCP_STREAM benchmark
using qemu with virtio+vhost for the NICs
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
IPv6 multicast and link-local addresses require special handling by the
VRF driver:
1. Rather than using the VRF device index and full FIB lookups,
packets to/from these addresses should use direct FIB lookups based on
the VRF device table.
2. fail sends/receives on a VRF device to/from a multicast address
(e.g, make ping6 ff02::1%<vrf> fail)
3. move the setting of the flow oif to the first dst lookup and revert
the change in icmpv6_echo_reply made in ca254490c8 ("net: Add VRF
support to IPv6 stack"). Linklocal/mcast addresses require use of the
skb->dev.
With this change connections into and out of a VRF enslaved device work
for multicast and link-local addresses work (icmp, tcp, and udp)
e.g.,
1. packets into VM with VRF config:
ping6 -c3 fe80::e0:f9ff:fe1c:b974%br1
ping6 -c3 ff02::1%br1
ssh -6 fe80::e0:f9ff:fe1c:b974%br1
2. packets going out a VRF enslaved device:
ping6 -c3 fe80::18f8:83ff:fe4b:7a2e%eth1
ping6 -c3 ff02::1%eth1
ssh -6 root@fe80::18f8:83ff:fe4b:7a2e%eth1
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Allow drivers to pass flow arg to functions where the arg is not const
and allow the driver to make updates as needed (eg., setting oif).
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Frank Kellermann reported a kernel crash with 4.5.0 when IPv6 is
disabled at boot using the kernel option ipv6.disable=1. Using
current net-next with the boot option:
$ ip link add red type vrf table 1001
Generates:
[12210.919584] BUG: unable to handle kernel NULL pointer dereference at 0000000000000748
[12210.921341] IP: [<ffffffff814b30e3>] fib6_get_table+0x2c/0x5a
[12210.922537] PGD b79e3067 PUD bb32b067 PMD 0
[12210.923479] Oops: 0000 [#1] SMP
[12210.924001] Modules linked in: ipvlan 8021q garp mrp stp llc
[12210.925130] CPU: 3 PID: 1177 Comm: ip Not tainted 4.7.0-rc1+ #235
[12210.926168] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.7.5-20140531_083030-gandalf 04/01/2014
[12210.928065] task: ffff8800b9ac4640 ti: ffff8800bacac000 task.ti: ffff8800bacac000
[12210.929328] RIP: 0010:[<ffffffff814b30e3>] [<ffffffff814b30e3>] fib6_get_table+0x2c/0x5a
[12210.930697] RSP: 0018:ffff8800bacaf888 EFLAGS: 00010202
[12210.931563] RAX: 0000000000000748 RBX: ffffffff81a9e280 RCX: ffff8800b9ac4e28
[12210.932688] RDX: 00000000000000e9 RSI: 0000000000000002 RDI: 0000000000000286
[12210.933820] RBP: ffff8800bacaf898 R08: ffff8800b9ac4df0 R09: 000000000052001b
[12210.934941] R10: 00000000657c0000 R11: 000000000000c649 R12: 00000000000003e9
[12210.936032] R13: 00000000000003e9 R14: ffff8800bace7800 R15: ffff8800bb3ec000
[12210.937103] FS: 00007faa1766c700(0000) GS:ffff88013ac00000(0000) knlGS:0000000000000000
[12210.938321] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[12210.939166] CR2: 0000000000000748 CR3: 00000000b79d6000 CR4: 00000000000406e0
[12210.940278] Stack:
[12210.940603] ffff8800bb3ec000 ffffffff81a9e280 ffff8800bacaf8c8 ffffffff814b3135
[12210.941818] ffff8800bb3ec000 ffffffff81a9e280 ffffffff81a9e280 ffff8800bace7800
[12210.943040] ffff8800bacaf8f0 ffffffff81397c88 ffff8800bb3ec000 ffffffff81a9e280
[12210.944288] Call Trace:
[12210.944688] [<ffffffff814b3135>] fib6_new_table+0x24/0x8a
[12210.945516] [<ffffffff81397c88>] vrf_dev_init+0xd4/0x162
[12210.946328] [<ffffffff814091e1>] register_netdevice+0x100/0x396
[12210.947209] [<ffffffff8139823d>] vrf_newlink+0x40/0xb3
[12210.948001] [<ffffffff814187f0>] rtnl_newlink+0x5d3/0x6d5
...
The problem above is due to the fact that the fib hash table is not
allocated when IPv6 is disabled at boot.
As for the VRF driver it should not do any IPv6 initializations if IPv6
is disabled, so it needs to know if IPv6 is disabled at boot. The disable
parameter is private to the IPv6 module, so provide an accessor for
modules to determine if IPv6 was disabled at boot time.
Fixes: 35402e3136 ("net: Add IPv6 support to VRF device")
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In case a qdisc is used on a vrf device, we need to use different
lockdep classes to avoid false positives.
Use the new netdev_lockdep_set_classes() generic helper.
Reported-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Tested-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add l3mdev rule per address family when the first VRF device is
created. The rules are installed with a default preference of 1000.
Users can replace the default rule as desired.
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add support for locally originated traffic to VRF-local IPv6 addresses.
Similar to IPv4 a local dst is set on the skb and the packet is
reinserted with a call to netif_rx. With this patch, ping, tcp and udp
packets to a local IPv6 address are successfully routed:
$ ip addr show dev eth1
4: eth1: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc pfifo_fast master red state UP group default qlen 1000
link/ether 02:e0:f9:1c:b9:74 brd ff:ff:ff:ff:ff:ff
inet 10.100.1.1/24 brd 10.100.1.255 scope global eth1
valid_lft forever preferred_lft forever
inet6 2100:1::1/120 scope global
valid_lft forever preferred_lft forever
inet6 fe80::e0:f9ff:fe1c:b974/64 scope link
valid_lft forever preferred_lft forever
$ ping6 -c1 -I red 2100:1::1
ping6: Warning: source address might be selected on device other than red.
PING 2100:1::1(2100:1::1) from 2100:1::1 red: 56 data bytes
64 bytes from 2100:1::1: icmp_seq=1 ttl=64 time=0.098 ms
ip6_input is exported so the VRF driver can use it for the dst input
function. The dst_alloc function for IPv4 defaults to setting the input and
output functions; IPv6's does not. VRF does not need to duplicate the Rx path
so just export the ipv6 input function.
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add support for locally originated traffic to VRF-local addresses. If
destination device for an skb is the loopback or VRF device then set
its dst to a local version of the VRF cached dst_entry and call netif_rx
to insert the packet onto the rx queue - similar to what is done for
loopback. This patch handles IPv4 support; follow on patch handles IPv6.
With this patch, ping, tcp and udp packets to a local IPv4 address are
successfully routed:
$ ip addr show dev eth1
4: eth1: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc pfifo_fast master red state UP group default qlen 1000
link/ether 02:e0:f9:1c:b9:74 brd ff:ff:ff:ff:ff:ff
inet 10.100.1.1/24 brd 10.100.1.255 scope global eth1
valid_lft forever preferred_lft forever
inet6 2100:1::1/120 scope global
valid_lft forever preferred_lft forever
inet6 fe80::e0:f9ff:fe1c:b974/64 scope link
valid_lft forever preferred_lft forever
$ ping -c1 -I red 10.100.1.1
ping: Warning: source address might be selected on device other than red.
PING 10.100.1.1 (10.100.1.1) from 10.100.1.1 red: 56(84) bytes of data.
64 bytes from 10.100.1.1: icmp_seq=1 ttl=64 time=0.057 ms
This patch also enables use of IPv4 loopback address on the VRF device:
$ ip addr add dev red 127.0.0.1/8
$ ping -c1 -I red 127.0.0.1
PING 127.0.0.1 (127.0.0.1) from 127.0.0.1 red: 56(84) bytes of data.
64 bytes from 127.0.0.1: icmp_seq=1 ttl=64 time=0.058 ms
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Move the stripping of the ethernet header from is_ip_tx_frame into the
ipv4 and ipv6 outbound functions and collapse vrf_send_v4_prep into
vrf_process_v4_outbound.
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This reverts commit 2fb7ea455d.
It results in build errors because ip6_input is not a
symbol exported to modules.
Signed-off-by: David S. Miller <davem@davemloft.net>
Add support for locally originated traffic to VRF-local IPv6 addresses.
Similar to IPv4 a local dst is set on the skb and the packet is
reinserted with a call to netif_rx. With this patch, ping, tcp and udp
packets to a local IPv6 address are successfully routed:
$ ip addr show dev eth1
4: eth1: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc pfifo_fast master red state UP group default qlen 1000
link/ether 02:e0:f9:1c:b9:74 brd ff:ff:ff:ff:ff:ff
inet 10.100.1.1/24 brd 10.100.1.255 scope global eth1
valid_lft forever preferred_lft forever
inet6 2100:1::1/120 scope global
valid_lft forever preferred_lft forever
inet6 fe80::e0:f9ff:fe1c:b974/64 scope link
valid_lft forever preferred_lft forever
$ ping6 -c1 -I red 2100:1::1
ping6: Warning: source address might be selected on device other than red.
PING 2100:1::1(2100:1::1) from 2100:1::1 red: 56 data bytes
64 bytes from 2100:1::1: icmp_seq=1 ttl=64 time=0.098 ms
ip6_input is exported so the VRF driver can use it for the dst input
function. The dst_alloc function for IPv4 defaults to setting the input and
output functions; IPv6's does not. VRF does not need to duplicate the Rx path
so just export the ipv6 input function.
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add support for locally originated traffic to VRF-local addresses. If
destination device for an skb is the loopback or VRF device then set
its dst to a local version of the VRF cached dst_entry and call netif_rx
to insert the packet onto the rx queue - similar to what is done for
loopback. This patch handles IPv4 support; follow on patch handles IPv6.
With this patch, ping, tcp and udp packets to a local IPv4 address are
successfully routed:
$ ip addr show dev eth1
4: eth1: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc pfifo_fast master red state UP group default qlen 1000
link/ether 02:e0:f9:1c:b9:74 brd ff:ff:ff:ff:ff:ff
inet 10.100.1.1/24 brd 10.100.1.255 scope global eth1
valid_lft forever preferred_lft forever
inet6 2100:1::1/120 scope global
valid_lft forever preferred_lft forever
inet6 fe80::e0:f9ff:fe1c:b974/64 scope link
valid_lft forever preferred_lft forever
$ ping -c1 -I red 10.100.1.1
ping: Warning: source address might be selected on device other than red.
PING 10.100.1.1 (10.100.1.1) from 10.100.1.1 red: 56(84) bytes of data.
64 bytes from 10.100.1.1: icmp_seq=1 ttl=64 time=0.057 ms
This patch also enables use of IPv4 loopback address on the VRF device:
$ ip addr add dev red 127.0.0.1/8
$ ping -c1 -I red 127.0.0.1
PING 127.0.0.1 (127.0.0.1) from 127.0.0.1 red: 56(84) bytes of data.
64 bytes from 127.0.0.1: icmp_seq=1 ttl=64 time=0.058 ms
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Move the stripping of the ethernet header from is_ip_tx_frame into the
ipv4 and ipv6 outbound functions. If the packet is destined to a local
address the header is retained since the packet is sent back to netif_rx.
Collapse vrf_send_v4_prep into vrf_process_v4_outbound.
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The VRF device exists to define L3 domains and guide FIB lookups. As
such its operstate is not relevant. Seeing 'state UNKNOWN' in the
output of 'ip link show' can be confusing, so set operstate at link
create.
Similarly, the MTU for a VRF device is not used; any fragmentation
of the payload is done on the output path based on the real egress
device. An MTU of 1500 on the VRF device while enslaved devices
have a higher MTU can lead to confusion. Since the VRF MTU is not
relevant set to 64k similar to what is done for loopback.
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
One cpu can be processing packets which includes using the cached route
entries in the vrf device's private data and on another cpu the device
gets deleted which releases the routes and sets the pointers in net_vrf
to NULL. This results in datapath dereferencing a NULL pointer.
Fix by protecting access to dst's with rcu.
Fixes: 193125dbd8 ("net: Introduce VRF device driver")
Fixes: 35402e3136 ("net: Add IPv6 support to VRF device")
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Currently the VRF driver uses the rx_handler to switch the skb device
to the VRF device. Switching the dev prior to the ip / ipv6 layer
means the VRF driver has to duplicate IP/IPv6 processing which adds
overhead and makes features such as retaining the ingress device index
more complicated than necessary.
This patch moves the hook to the L3 layer just after the first NF_HOOK
for PRE_ROUTING. This location makes exposing the original ingress device
trivial (next patch) and allows adding other NF_HOOKs to the VRF driver
in the future.
dev_queue_xmit_nit is exported so that the VRF driver can cycle the skb
with the switched device through the packet taps to maintain current
behavior (tcpdump can be used on either the vrf device or the enslaved
devices).
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Allow udp and raw sockets to send by oif that is an enslaved interface
versus the l3mdev/VRF device. For example, this allows BFD to use ifindex
from IP_PKTINFO on a receive to send a response without the need to
convert to the VRF index. It also allows ping and ping6 to work when
specifying an enslaved interface (e.g., ping -I swp1 <ip>) which is
a natural use case.
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Tables have to exist for VRFs to function. Ensure they exist
when VRF device is created.
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Vivek reported a kernel exception deleting a VRF with an active
connection through it. The root cause is that the socket has a cached
reference to a dst that is destroyed. Converting the dst_destroy to
dst_release and letting proper reference counting kick in does not
work as the dst has a reference to the device which needs to be released
as well.
I talked to Hannes about this at netdev and he pointed out the ipv4 and
ipv6 dst handling has dst_ifdown for just this scenario. Rather than
continuing with the reinvented dst wheel in VRF just remove it and
leverage the ipv4 and ipv6 versions.
Fixes: 193125dbd8 ("net: Introduce VRF device driver")
Fixes: 35402e3136 ("net: Add IPv6 support to VRF device")
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Several cases of overlapping changes, as well as one instance
(vxlan) of a bug fix in 'net' overlapping with code movement
in 'net-next'.
Signed-off-by: David S. Miller <davem@davemloft.net>
Nik pointed that the VRF driver should be using skb_header_pointer
instead of accessing skb->data and bits beyond directly which can
be garbage.
Fixes: 35402e3136 ("net: Add IPv6 support to VRF device")
Cc: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Allows userspace to have direct access to VRF table association
versus looking up master device and its table.
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Commands run in a vrf context are not failing as expected on a route lookup:
root@kenny:~# ip ro ls table vrf-red
unreachable default
root@kenny:~# ping -I vrf-red -c1 -w1 10.100.1.254
ping: Warning: source address might be selected on device other than vrf-red.
PING 10.100.1.254 (10.100.1.254) from 0.0.0.0 vrf-red: 56(84) bytes of data.
--- 10.100.1.254 ping statistics ---
2 packets transmitted, 0 received, 100% packet loss, time 999ms
Since the vrf table does not have a route for 10.100.1.254 the ping
should have failed. The saddr lookup causes a full VRF table lookup.
Propogating a lookup failure to the user allows the command to fail as
expected:
root@kenny:~# ping -I vrf-red -c1 -w1 10.100.1.254
connect: No route to host
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Conflicts:
drivers/net/ethernet/renesas/ravb_main.c
kernel/bpf/syscall.c
net/ipv4/ipmr.c
All three conflicts were cases of overlapping changes.
Signed-off-by: David S. Miller <davem@davemloft.net>
Sometimes the drivers and other code would find it handy to know some
internal information about upper device being changed. So allow upper-code
to pass information down to notifier listeners during linking.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Eliminate netdev_master_upper_dev_link_private and pass priv directly as
a parameter of netdev_master_upper_dev_link.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The private slave queue and slave struct haven't been used for anything
and aren't needed, this allows to reduce memory usage and simplify
enslave/release. We can use netdev_for_each_lower_dev() to free the vrf
ports when deleting a vrf device. Also if in the future a private struct
is needed for each slave, it can be implemented via lower devices'
private member (similar to how bonding does it).
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add support for IPv6 to VRF device driver. Implemenation parallels what
has been done for IPv4.
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The network namespace is already passed into dst_output pass it into
dst->output lwt->output and friends.
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
It is confusing and silly hiding a parameter so modify all of
the callers to pass in the appropriate socket or skb->sk if
no socket is known.
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
For consistency with the other similar methods in the kernel pass a
struct sock into the dst_ops .local_out method.
Simplifying the socket passing case is needed a prequel to passing a
struct net reference into .local_out.
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add operation to l3mdev to lookup source address for a given flow.
Add support for the operation to VRF driver and convert existing
IPv4 hooks to use the new lookup.
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
IPv6 addrconf keys off of IFF_SLAVE so can not use it for L3 slave.
Add a new private flag and add netif_is_l3_slave function for checking
it.
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Move remaining structs to VRF driver and delete the vrf header file.
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Rename IFF_VRF_MASTER to IFF_L3MDEV_MASTER and update the name of the
netif_is_vrf and netif_index_is_vrf macros.
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Conflicts:
net/ipv4/arp.c
The net/ipv4/arp.c conflict was one commit adding a new
local variable while another commit was deleting one.
Signed-off-by: David S. Miller <davem@davemloft.net>
This is immediately motivated by the bridge code that chains functions that
call into netfilter. Without passing net into the okfns the bridge code would
need to guess about the best expression for the network namespace to process
packets in.
As net is frequently one of the first things computed in continuation functions
after netfilter has done it's job passing in the desired network namespace is in
many cases a code simplification.
To support this change the function dst_output_okfn is introduced to
simplify passing dst_output as an okfn. For the moment dst_output_okfn
just silently drops the struct net.
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Pass a network namespace parameter into the netfilter hooks. At the
call site of the netfilter hooks the path a packet is taking through
the network stack is well known which allows the network namespace to
be easily and reliabily.
This allows the replacement of magic code like
"dev_net(state->in?:state->out)" that appears at the start of most
netfilter hooks with "state->net".
In almost all cases the network namespace passed in is derived
from the first network device passed in, guaranteeing those
paths will not see any changes in practice.
The exceptions are:
xfrm/xfrm_output.c:xfrm_output_resume() xs_net(skb_dst(skb)->xfrm)
ipvs/ip_vs_xmit.c:ip_vs_nat_send_or_cont() ip_vs_conn_net(cp)
ipvs/ip_vs_xmit.c:ip_vs_send_or_cont() ip_vs_conn_net(cp)
ipv4/raw.c:raw_send_hdrinc() sock_net(sk)
ipv6/ip6_output.c:ip6_xmit() sock_net(sk)
ipv6/ndisc.c:ndisc_send_skb() dev_net(skb->dev) not dev_net(dst->dev)
ipv6/raw.c:raw6_send_hdrinc() sock_net(sk)
br_netfilter_hooks.c:br_nf_pre_routing_finish() dev_net(skb->dev) before skb->dev is set to nf_bridge->physindev
In all cases these exceptions seem to be a better expression for the
network namespace the packet is being processed in then the historic
"dev_net(in?in:out)". I am documenting them in case something odd
pops up and someone starts trying to track down what happened.
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Steffen reported that the recent change to add oif to dst lookups breaks
the VTI use case. The problem is that with the oif set in the flow struct
the comparison to the nh_oif is triggered. Fix by splitting the
FLOWI_FLAG_VRFSRC into 2 flags -- one that triggers the vrf device cache
bypass (FLOWI_FLAG_VRFSRC) and another telling the lookup to not compare
nh oif (FLOWI_FLAG_SKIP_NH_OIF).
Fixes: 42a7b32b73 ("xfrm: Add oif to dst lookups")
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Acked-by: Steffen Klassert <steffen.klassert@secunet.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add the FIB table id to rtable to make the information available for
IPv4 as it is for IPv6.
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The change to use a custom dst broke tcpdump captures on the VRF device:
$ tcpdump -n -i vrf10
...
05:32:29.009362 IP 10.2.1.254 > 10.2.1.2: ICMP echo request, id 21989, seq 1, length 64
05:32:29.009855 00:00:40:01:8d:36 > 45:00:00:54:d6:6f, ethertype Unknown (0x0a02), length 84:
0x0000: 0102 0a02 01fe 0000 9181 55e5 0001 bd11 ..........U.....
0x0010: da55 0000 0000 bb5d 0700 0000 0000 1011 .U.....]........
0x0020: 1213 1415 1617 1819 1a1b 1c1d 1e1f 2021 ...............!
0x0030: 2223 2425 2627 2829 2a2b 2c2d 2e2f 3031 "#$%&'()*+,-./01
0x0040: 3233 3435 3637 234567
Local packets going through the VRF device are missing an ethernet header.
Fix by adding one and then stripping it off before pushing back to the IP
stack. With this patch you get the expected dumps:
...
05:36:15.713944 IP 10.2.1.254 > 10.2.1.2: ICMP echo request, id 23795, seq 1, length 64
05:36:15.714160 IP 10.2.1.2 > 10.2.1.254: ICMP echo reply, id 23795, seq 1, length 64
...
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Currently, the lwtunnel state resides in per-protocol data. This is
a problem if we encapsulate ipv6 traffic in an ipv4 tunnel (or vice versa).
The xmit function of the tunnel does not know whether the packet has been
routed to it by ipv4 or ipv6, yet it needs the lwtstate data. Moving the
lwtstate data to dst_entry makes such inter-protocol tunneling possible.
As a bonus, this brings a nice diffstat.
Signed-off-by: Jiri Benc <jbenc@redhat.com>
Acked-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Acked-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
When ndo_add|del_slave ops are used, they're taken from the respective
master device's netdev ops, so if the master device is a VRF only then
the VRF ops will get called thus no need to check the type of the
master.
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We can simplify do_vrf_add_slave by moving vrf_insert_slave in the end
of the enslaving and thus eliminate an error goto label. It always
succeeds and isn't needed before that anyway.
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The upper/lower functions already check for duplicate slaves so no need
to do it again.
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
It's pointless to panic on cache create failure when that case is handled
and even more so since it's not a kernel-wide fatal problem so don't
panic.
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Currently whenever a packet different from ETH_P_IP is sent through the
VRF device it is leaked so plug the leaks and properly drop these
packets.
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Acked-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We can drop the check because if vrf_ptr is present then we must have
the vrf device as a master and since we're running with rtnl it can't go
away.
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
dstats and rth are always present because we fail the device registration
if they can't be allocated in vrf_init() (ndo_init) so drop the unnecessary
checks.
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
slave_queue has a num_slaves member which is unused, drop it.
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
netdev_master_upper_dev_link/unlink already do a dev_hold/put on the
devices being linked, so no need to take another reference.
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This driver borrows heavily from IPvlan and teaming drivers.
Routing domains (VRF-lite) are created by instantiating a VRF master
device with an associated table and enslaving all routed interfaces that
participate in the domain. As part of the enslavement, all connected
routes for the enslaved devices are moved to the table associated with
the VRF device. Outgoing sockets must bind to the VRF device to function.
Standard FIB rules bind the VRF device to tables and regular fib rule
processing is followed. Routed traffic through the box, is forwarded by
using the VRF device as the IIF and following the IIF rule to a table
that is mated with the VRF.
Example:
Create vrf 1:
ip link add vrf1 type vrf table 5
ip rule add iif vrf1 table 5
ip rule add oif vrf1 table 5
ip route add table 5 prohibit default
ip link set vrf1 up
Add interface to vrf 1:
ip link set eth1 master vrf1
Signed-off-by: Shrijeet Mukherjee <shm@cumulusnetworks.com>
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller
Gao Feng
David Ahern
Ido Schimmel
Julian Anastasov
stephen hemminger
Eric Dumazet
stephen hemminger
Jiri Pirko
Nikolay Aleksandrov
Eric W. Biederman
WANG Cong
Jiri Benc