- 19 9月, 2015 12 次提交
-
-
由 Eric W. Biederman 提交于
As gre does not have the srckey in the packet gre_pkt_to_tuple needs to perform a lookup in it's per network namespace tables. Pass in the proper network namespace to all pkt_to_tuple implementations to ensure gre (and any similar protocols) can get this right. Signed-off-by: N"Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: NPablo Neira Ayuso <pablo@netfilter.org>
-
由 Eric W. Biederman 提交于
Stop guessing the struct net instead of remember it. Guessing is just silly and will be problematic in the future when I implement routes between network namespaces. Signed-off-by: N"Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: NPablo Neira Ayuso <pablo@netfilter.org>
-
由 Eric W. Biederman 提交于
This allows them to stop guessing the network namespace with pick_net. Signed-off-by: N"Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: NPablo Neira Ayuso <pablo@netfilter.org>
-
由 Eric W. Biederman 提交于
Signed-off-by: N"Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: NPablo Neira Ayuso <pablo@netfilter.org>
-
由 Eric W. Biederman 提交于
nft_pktinfo is passed on the stack so this does not bloat any in core data structures. By centrally computing this information this makes maintence of the code simpler, and understading of the code easier. Signed-off-by: N"Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: NPablo Neira Ayuso <pablo@netfilter.org>
-
由 Eric W. Biederman 提交于
Signed-off-by: N"Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: NPablo Neira Ayuso <pablo@netfilter.org>
-
由 Eric W. Biederman 提交于
As xt_action_param lives on the stack this does not bloat any persistent data structures. This is a first step in making netfilter code that needs to know which network namespace it is executing in simpler. Signed-off-by: N"Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: NPablo Neira Ayuso <pablo@netfilter.org>
-
由 Eric W. Biederman 提交于
- Add nft_pktinfo.pf to replace ops->pf - Add nft_pktinfo.hook to replace ops->hooknum This simplifies the code, makes it more readable, and likely reduces cache line misses. Maintainability is enhanced as the details of nft_hook_ops are of no concern to the recpients of nft_pktinfo. Signed-off-by: N"Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: NPablo Neira Ayuso <pablo@netfilter.org>
-
由 Eric W. Biederman 提交于
The values of nf_hook_state.hook and nf_hook_ops.hooknum must be the same by definition. We are more likely to access the fields in nf_hook_state over the fields in nf_hook_ops so with a little luck this results in fewer cache line misses, and slightly more consistent code. Signed-off-by: N"Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: NPablo Neira Ayuso <pablo@netfilter.org>
-
由 Eric W. Biederman 提交于
The values of ops->hooknum and state->hook are guaraneted to be equal making the hook argument to ip6t_do_table, arp_do_table, and ipt_do_table is unnecessary. Remove the unnecessary hook argument. In the callers use state->hook instead of ops->hooknum for clarity and to reduce the number of cachelines the callers touch. Signed-off-by: N"Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: NPablo Neira Ayuso <pablo@netfilter.org>
-
由 Eric W. Biederman 提交于
Nearly everything thing of interest to ebt_do_table is already present in nf_hook_state. Simplify ebt_do_table by just passing in the skb, nf_hook_state, and the table. This make the code easier to read and maintenance easier. To support this create an nf_hook_state on the stack in ebt_broute (the only caller without a nf_hook_state already available). This new nf_hook_state adds no new computations to ebt_broute, but does use a few more bytes of stack. Signed-off-by: N"Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: NPablo Neira Ayuso <pablo@netfilter.org>
-
https://git.kernel.org/pub/scm/linux/kernel/git/horms/ipvs-next由 Pablo Neira Ayuso 提交于
Simon Horman says: ==================== IPVS Updates for v4.4 please consider these IPVS Updates for v4.4. The updates include the following from Alex Gartrell: * Scheduling of ICMP * Sysctl to ignore tunneled packets; and hence some packet-looping scenarios ==================== Signed-off-by: NPablo Neira Ayuso <pablo@netfilter.org>
-
- 18 9月, 2015 28 次提交
-
-
由 Eric Dumazet 提交于
Memory placement in sch_dsmark is silly : Better place mask/value in the same cache line. Also, we can embed small arrays in the first cache line and remove a potential cache miss. Signed-off-by: NEric Dumazet <edumazet@google.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 David S. Miller 提交于
Florian Fainelli says: ==================== net: bcmgenet: Interrupt coalescing This patch series adds support for interrupt coalescing for GENET adapters. ==================== Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Florian Fainelli 提交于
Add support for the ethtool rx-frames coalescing parameter which allows defining the number of RX interrupts per frames received. The RDMA engine supports a configurable timeout with a resolution of approximately 8.192 us. We can no longer enable the BDONE/PDONE interrupts as those would fire for each packet/buffer received, which would defeat the MBDONE interrupt purpose. The MBDONE interrupt is guaranteed to correspond to a PDONE/BDONE interrupt when the threshold is set to 1. Signed-off-by: NFlorian Fainelli <f.fainelli@gmail.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Florian Fainelli 提交于
Configuring the ethtool tx-frames property, which translates into N packets before a TX interrupt is the simplest configuration scheme because it requires no locking neither at the softare nor hardware level, and is completely indepedent from the link speed. Since ethtool does not allow per-tx queue coalescing parameters, we apply the same setting to any transmit queue. We can no longer enable the BDONE/PDONE interrupts as those would fire for each packet/buffer received, which would defeat the MBDONE interrupt purpose. The MBDONE interrupt is guaranteed to correspond to a PDONE/BDONE interrupt when the threshold is set to 1, but offers interrupt coalescing when the value is > 1. Since the HW is configured to generate an interrupt when the ring becomes emtpy, we have to deny any timeout/timer settings coming from user-space to indicate we can only generate an interrupt very <N> packets. While we are at it, fix the DMA_INTR_THRESHOLD_MASK value which was off by one bit (0xff vs. 0x1ff). Signed-off-by: NFlorian Fainelli <f.fainelli@gmail.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
Remove not defined MAC_CR_GMII_EN_ bit from MAC_CR. Signed-off-by: NWoojung Huh <woojung.huh@microchip.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
Create lan78xx_get_mdix_status() and lan78xx_set_mdix_status() for MDIX control. Signed-off-by: NWoojung Huh <woojung.huh@microchip.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
Remove phy defines in lan78xx.h and use defines in include/linux/microchipphy.h. Signed-off-by: NWoojung Huh <woojung.huh@microchip.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
Update to use phylib instead of mii_if_info. Signed-off-by: NWoojung Huh <woojung.huh@microchip.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
Add PHYLIB and MICROCHIP_PHY as default configuration for lan78xx. Signed-off-by: NWoojung Huh <woojung.huh@microchip.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
Check device ready bit (PMT_CTL_READY_) after reset the PHY. Device may not be ready even if PHY_RST_ is cleared depends on configuration. Signed-off-by: NWoojung Huh <woojung.huh@microchip.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 David Ahern 提交于
Sergey, Richard and Fabio reported an oops in ip_route_input_noref. e.g., from Richard: [ 0.877040] BUG: unable to handle kernel NULL pointer dereference at 0000000000000056 [ 0.877597] IP: [<ffffffff8155b5e2>] ip_route_input_noref+0x1a2/0xb00 [ 0.877597] PGD 3fa14067 PUD 3fa6e067 PMD 0 [ 0.877597] Oops: 0000 [#1] SMP [ 0.877597] Modules linked in: virtio_net virtio_pci virtio_ring virtio [ 0.877597] CPU: 1 PID: 119 Comm: ifconfig Not tainted 4.2.0+ #1 [ 0.877597] Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011 [ 0.877597] task: ffff88003fab0bc0 ti: ffff88003faa8000 task.ti: ffff88003faa8000 [ 0.877597] RIP: 0010:[<ffffffff8155b5e2>] [<ffffffff8155b5e2>] ip_route_input_noref+0x1a2/0xb00 [ 0.877597] RSP: 0018:ffff88003ed03ba0 EFLAGS: 00010202 [ 0.877597] RAX: 0000000000000046 RBX: 00000000ffffff8f RCX: 0000000000000020 [ 0.877597] RDX: ffff88003fab50b8 RSI: 0000000000000200 RDI: ffffffff8152b4b8 [ 0.877597] RBP: ffff88003ed03c50 R08: 0000000000000000 R09: 0000000000000000 [ 0.877597] R10: 0000000000000000 R11: 0000000000000000 R12: ffff88003fab6f00 [ 0.877597] R13: ffff88003fab5000 R14: 0000000000000000 R15: ffffffff81cb5600 [ 0.877597] FS: 00007f6de5751700(0000) GS:ffff88003ed00000(0000) knlGS:0000000000000000 [ 0.877597] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 0.877597] CR2: 0000000000000056 CR3: 000000003fa6d000 CR4: 00000000000006e0 [ 0.877597] Stack: [ 0.877597] 0000000000000000 0000000000000046 ffff88003fffa600 ffff88003ed03be0 [ 0.877597] ffff88003f9e2c00 697da8c0017da8c0 ffff880000000000 000000000007fd00 [ 0.877597] 0000000000000000 0000000000000046 0000000000000000 0000000400000000 [ 0.877597] Call Trace: [ 0.877597] <IRQ> [ 0.877597] [<ffffffff812bfa1f>] ? cpumask_next_and+0x2f/0x40 [ 0.877597] [<ffffffff8158e13c>] arp_process+0x39c/0x690 [ 0.877597] [<ffffffff8158e57e>] arp_rcv+0x13e/0x170 [ 0.877597] [<ffffffff8151feec>] __netif_receive_skb_core+0x60c/0xa00 [ 0.877597] [<ffffffff81515795>] ? __build_skb+0x25/0x100 [ 0.877597] [<ffffffff81515795>] ? __build_skb+0x25/0x100 [ 0.877597] [<ffffffff81521ff6>] __netif_receive_skb+0x16/0x70 [ 0.877597] [<ffffffff81522078>] netif_receive_skb_internal+0x28/0x90 [ 0.877597] [<ffffffff8152288f>] napi_gro_receive+0x7f/0xd0 [ 0.877597] [<ffffffffa0017906>] virtnet_receive+0x256/0x910 [virtio_net] [ 0.877597] [<ffffffffa0017fd8>] virtnet_poll+0x18/0x80 [virtio_net] [ 0.877597] [<ffffffff815234cd>] net_rx_action+0x1dd/0x2f0 [ 0.877597] [<ffffffff81053228>] __do_softirq+0x98/0x260 [ 0.877597] [<ffffffff8164969c>] do_softirq_own_stack+0x1c/0x30 The root cause is use of res.table uninitialized. Thanks to Nikolay for noticing the uninitialized use amongst the maze of gotos. As Nikolay pointed out the second initialization is not required to fix the oops, but rather to fix a related problem where a valid lookup should be invalidated before creating the rth entry. Fixes: b7503e0c ("net: Add FIB table id to rtable") Reported-by: NSergey Senozhatsky <sergey.senozhatsky.work@gmail.com> Reported-by: NRichard Alpe <richard.alpe@ericsson.com> Reported-by: NFabio Estevam <festevam@gmail.com> Tested-by: NFabio Estevam <fabio.estevam@freescale.com> Signed-off-by: NDavid Ahern <dsa@cumulusnetworks.com> Signed-off-by: NNikolay Aleksandrov <nikolay@cumulusnetworks.com> Tested-by: NSergey Senozhatsky <sergey.senozhatsky@gmail.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 David S. Miller 提交于
Alexei Starovoitov says: ==================== bpf: performance improvements v1->v2: dropped redundant iff_up check in patch 2 At plumbers we discussed different options on how to get rid of skb_clone from bpf_clone_redirect(), the patch 2 implements the best option. Patch 1 adds 'integrated exts' to cls_bpf to improve performance by combining simple actions into bpf classifier. ==================== Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Alexei Starovoitov 提交于
Existing bpf_clone_redirect() helper clones skb before redirecting it to RX or TX of destination netdev. Introduce bpf_redirect() helper that does that without cloning. Benchmarked with two hosts using 10G ixgbe NICs. One host is doing line rate pktgen. Another host is configured as: $ tc qdisc add dev $dev ingress $ tc filter add dev $dev root pref 10 u32 match u32 0 0 flowid 1:2 \ action bpf run object-file tcbpf1_kern.o section clone_redirect_xmit drop so it receives the packet on $dev and immediately xmits it on $dev + 1 The section 'clone_redirect_xmit' in tcbpf1_kern.o file has the program that does bpf_clone_redirect() and performance is 2.0 Mpps $ tc filter add dev $dev root pref 10 u32 match u32 0 0 flowid 1:2 \ action bpf run object-file tcbpf1_kern.o section redirect_xmit drop which is using bpf_redirect() - 2.4 Mpps and using cls_bpf with integrated actions as: $ tc filter add dev $dev root pref 10 \ bpf run object-file tcbpf1_kern.o section redirect_xmit integ_act classid 1 performance is 2.5 Mpps To summarize: u32+act_bpf using clone_redirect - 2.0 Mpps u32+act_bpf using redirect - 2.4 Mpps cls_bpf using redirect - 2.5 Mpps For comparison linux bridge in this setup is doing 2.1 Mpps and ixgbe rx + drop in ip_rcv - 7.8 Mpps Signed-off-by: NAlexei Starovoitov <ast@plumgrid.com> Acked-by: NDaniel Borkmann <daniel@iogearbox.net> Acked-by: NJohn Fastabend <john.r.fastabend@intel.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Daniel Borkmann 提交于
Often cls_bpf classifier is used with single action drop attached. Optimize this use case and let cls_bpf return both classid and action. For backwards compatibility reasons enable this feature under TCA_BPF_FLAG_ACT_DIRECT flag. Then more interesting programs like the following are easier to write: int cls_bpf_prog(struct __sk_buff *skb) { /* classify arp, ip, ipv6 into different traffic classes * and drop all other packets */ switch (skb->protocol) { case htons(ETH_P_ARP): skb->tc_classid = 1; break; case htons(ETH_P_IP): skb->tc_classid = 2; break; case htons(ETH_P_IPV6): skb->tc_classid = 3; break; default: return TC_ACT_SHOT; } return TC_ACT_OK; } Joint work with Daniel Borkmann. Signed-off-by: NDaniel Borkmann <daniel@iogearbox.net> Signed-off-by: NAlexei Starovoitov <ast@plumgrid.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Junwei Zhang 提交于
The permanent protocol nodes are at the head of the list, So only need check all these nodes. No matter the new node is permanent or not, insert the new node after the last permanent protocol node, If the new node conflicts with existing permanent node, return error. Signed-off-by: NMartin Zhang <martinbj2008@gmail.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Eric Dumazet 提交于
If skb carries a l4 hash, no need to perform a flow dissection. Performance is slightly better : lpaa5:~# ./super_netperf 200 -H lpaa6 -t TCP_RR -l 100 2.39012e+06 lpaa5:~# ./super_netperf 200 -H lpaa6 -t TCP_RR -l 100 2.39393e+06 lpaa5:~# ./super_netperf 200 -H lpaa6 -t TCP_RR -l 100 2.39988e+06 After patch : lpaa5:~# ./super_netperf 200 -H lpaa6 -t TCP_RR -l 100 2.43579e+06 lpaa5:~# ./super_netperf 200 -H lpaa6 -t TCP_RR -l 100 2.44304e+06 lpaa5:~# ./super_netperf 200 -H lpaa6 -t TCP_RR -l 100 2.44312e+06 Signed-off-by: NEric Dumazet <edumazet@google.com> Cc: Tom Herbert <tom@herbertland.com> Cc: Mahesh Bandewar <maheshb@google.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Eric Dumazet 提交于
In commit b73c3d0e ("net: Save TX flow hash in sock and set in skbuf on xmit"), Tom provided a l4 hash to most outgoing TCP packets. We'd like to provide one as well for SYNACK packets, so that all packets of a given flow share same txhash, to later enable bonding driver to also use skb->hash to perform slave selection. Note that a SYNACK retransmit shuffles the tx hash, as Tom did in commit 265f94ff ("net: Recompute sk_txhash on negative routing advice") for established sockets. This has nice effect making TCP flows resilient to some kind of black holes, even at connection establish phase. Signed-off-by: NEric Dumazet <edumazet@google.com> Cc: Tom Herbert <tom@herbertland.com> Cc: Mahesh Bandewar <maheshb@google.com> Acked-by: NTom Herbert <tom@herbertland.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 David S. Miller 提交于
Eric W. Biederman says: ==================== Passing net through the netfilter hooks My primary goal with this patchset and it's follow ups is to cleanup the network routing paths so that we do not look at the output device to derive the network namespace. My plan is to pass the network namespace of the transmitting socket through the output path, to replace code that looks at the output network device today. Once that is done we can have routes with output devices outside of the current network namespace. Which should allow reception and transmission of packets in network namespaces to be as fast as normal packet reception and transmission with early demux disabled, because it will same code path. Once skb_dst(skb)->dev is a little better under control I think it will also be possible to use rcu to cleanup the ancient hack that sets dst->dev to loopback_dev when a network device is removed. The work to get there is a series of code cleanups. I am starting with passing net into the netfilter hooks and into the functions that are called after the netfilter hooks. This removes from netfilter the need to guess which network namespace it is working on. To get there I perform a series of minor prep patches so the big changes at the end are possible to audit without getting lost in the noise. In particular I have a lot of patches computing net into a local variable and then using it through out the function. So this patchset encompases removing dead code, sorting out the _sk functions that were added last time someone pushed a prototype change through the post netfilter functions. Cleaning up individual functions use of the network namespace. Passing net into the netfilter hooks. Passing net into the post netfilter functions. Using state->net in the netfilter code where it is available and trivially usable. Pablo, Dave I don't know whose tree this makes more sense to go through. I am assuming at least initially Pablos as netfilter is involved. From what I have seen there will be a lot of back and forth between the netfilter code paths and the routing code paths. The patches are also available (against 4.3-rc1) at: git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/net-next.git master ==================== Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Eric W. Biederman 提交于
In code review it was noticed that I had failed to add some blank lines in places where they are customarily used. Taking a second look at the code I have to agree blank lines would be nice so I have added them here. Reported-by: NNicolas Dichtel <nicolas.dichtel@6wind.com> Signed-off-by: N"Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Eric W. Biederman 提交于
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: N"Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Eric W. Biederman 提交于
Instead of saying "net = dev_net(state->in?state->in:state->out)" just say "state->net". As that information is now availabe, much less confusing and much less error prone. Signed-off-by: N"Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Eric W. Biederman 提交于
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: N"Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Eric W. Biederman 提交于
netif_receive_skb_sk is only called once in the bridge code, replace it with a bridge specific function that calls netif_receive_skb. Signed-off-by: N"Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Eric W. Biederman 提交于
This is prep work for passing net to the netfilter hooks. Signed-off-by: N"Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Eric W. Biederman 提交于
When struct net starts being passed through the ipv4 and ipv6 fragment routines br_nf_push_frag_xmit will need to take a net parameter. Prepare br_nf_push_frag_xmit before that is needed and introduce br_nf_push_frag_xmit_sk for the call sites that still need the old calling conventions. Signed-off-by: N"Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Eric W. Biederman 提交于
This is a prep work for passing struct net through ip_do_fragment and later the netfilter okfn. Doing this independently makes the later code changes clearer. Signed-off-by: N"Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Eric W. Biederman 提交于
Signed-off-by: N"Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Eric W. Biederman 提交于
Keep net in a local variable so I can use it in NF_HOOK_COND when I pass struct net to all of the netfilter hooks. Signed-off-by: N"Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-