* Re: [PATCH 2/2] man/send(2): document a long standing bug that can cause spurious EPERM errors
From: Pablo Neira Ayuso @ 2013-03-19 10:12 UTC (permalink / raw)
To: Fernando Luis Vázquez Cao
Cc: Michael Kerrisk, linux-man-u79uwXL29TY76Z2rM5mHXA,
netdev-u79uwXL29TY76Z2rM5mHXA,
netfilter-devel-u79uwXL29TY76Z2rM5mHXA, Patrick McHardy,
Hirotaka Sasaki
In-Reply-To: <1363675960.4767.10.camel@nexus>
On Tue, Mar 19, 2013 at 03:52:40PM +0900, Fernando Luis Vázquez Cao wrote:
> Subject: [PATCH 2/2] man/send(2): document a long standing bug that can cause spurious EPERM errors
>
> This bug has been known since early 2009 (the latest) and discussed in
> netdev before:
>
> http://marc.info/?l=linux-netdev&w=2&r=1&s=Possible+race+condition+in+conntracking+&q=b
>
> It seems that a proper fix would be non trivial, so document the bug
> in the meantime.
>
> Reported-by: Hirotaka Sasaki <sasaki.hirotaka-Zyj7fXuS5i5L9jVzuh4AOg@public.gmane.org>
> Signed-off-by: Fernando Luis Vazquez Cao <fernando-gVGce1chcLdL9jVzuh4AOg@public.gmane.org>
> ---
>
> diff -urNp man-pages-3.50-orig/man2/send.2 man-pages-3.50/man2/send.2
> --- man-pages-3.50-orig/man2/send.2 2013-03-19 15:18:03.784306647 +0900
> +++ man-pages-3.50/man2/send.2 2013-03-19 15:30:40.788060426 +0900
> @@ -420,6 +420,11 @@ Linux may return
> .B EPIPE
> instead of
> .BR ENOTCONN .
> +
> +Linux may return spurious
> +.B EPERM
> +errors when netfilter's conntrack module is loaded and two or more
> +UDP packets belonging to the same connection are processed in parallel.
The Connection tracking system may drop packets for different reasons
under rare circunstances, not only in this case.
I'd prefer if you only apply patch 1/2.
--
To unsubscribe from this list: send the line "unsubscribe linux-man" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* RE: [Xen-devel] [PATCH 1/4] xen-netfront: remove unused variable `extra'
From: Paul Durrant @ 2013-03-19 10:03 UTC (permalink / raw)
To: annie li
Cc: Ian Campbell, netdev@vger.kernel.org, konrad.wilk@oracle.com,
Wei Liu, xen-devel@lists.xen.org
In-Reply-To: <5148359C.8040906@oracle.com>
> -----Original Message-----
[snip]
> For TCPv4 GSO, it seems one extra info request(NETTXF_extra_info) is
> enough in my winpv driver, and I did not process the
> XEN_NETIF_EXTRA_MORE.
> Do you create two extra info requests for bothTCPv4 and TCPv6 GSO like
> following?
>
> * [Request 2: netif_tx_extra] (only if request 1 has NETTXF_extra_info)
> * [Request 3: netif_tx_extra] (only if request 2 has
> XEN_NETIF_EXTRA_MORE)
>
No, I just use one. I don't use XEN_NETIF_EXTRA_FLAG_MORE. I thought you were questioning the existence of extra segments rather than this flag. I guess I got the wrong end of the stick.
I've not seen anything use XEN_NETIF_EXTRA_FLAG_MORE, but that's not to say nothing will use it in the future. Clearly something is needed to indicate subsequent extra segments should they ever be needed.
Paul
>
> > Extra segments are certainly not redundant; the Citrix Windows PV drivers
> send TSOs using them and handle LRO using them too.
>
> About the LRO, upstream netback does not create any response with
> XEN_NETIF_EXTRA_MORE, so I assume your dom0 did such process?
>
> Thanks
> Annie
^ permalink raw reply
* Re: [Xen-devel] [PATCH 1/4] xen-netfront: remove unused variable `extra'
From: annie li @ 2013-03-19 9:53 UTC (permalink / raw)
To: Paul Durrant
Cc: Ian Campbell, netdev@vger.kernel.org, konrad.wilk@oracle.com,
Wei Liu, xen-devel@lists.xen.org
In-Reply-To: <291EDFCB1E9E224A99088639C4762022013F7D2D3543@LONPMAILBOX01.citrite.net>
On 2013-3-19 17:28, Paul Durrant wrote:
>> -----Original Message-----
>> From: xen-devel-bounces@lists.xen.org [mailto:xen-devel-
>> bounces@lists.xen.org] On Behalf Of annie li
>> Sent: 19 March 2013 02:39
>> To: Ian Campbell
>> Cc: netdev@vger.kernel.org; konrad.wilk@oracle.com; Wei Liu; xen-
>> devel@lists.xen.org
>> Subject: Re: [Xen-devel] [PATCH 1/4] xen-netfront: remove unused variable
>> `extra'
>>
>>
>> On 2013-3-18 20:14, Ian Campbell wrote:
>>> On Mon, 2013-03-18 at 12:04 +0000, Wei Liu wrote:
>>>> On Mon, 2013-03-18 at 11:42 +0000, Ian Campbell wrote:
>>>>> On Mon, 2013-03-18 at 10:35 +0000, Wei Liu wrote:
>>>>>
>>>>> I think a few more words are needed here since from the code you are
>>>>> removing it seems very much like gso is used for something. If you have
>>>>> a proof that the "extra = gso" case is never hit then please explain it.
>>>>> Perhaps a reference to the removal of the last user?
>>>>>
>>>>> Or maybe it is the case that it should be used and the bug is that it
>>>>> isn't?
>>>>>
>>>> Looks like the latter one. 'extra' field should be used to get hold of
>>>> the last extra info in the ring. ;-)
>>>>
>>>> But, the only extra info in upstream kernel is
>> XEN_NETIF_EXTRA_TYPE_GSO,
>>>> so there's really no other extra info in the ring at that point. Could
>>>> it be possible that it is something from classic Xen kernel?
>>> The classic kernel netfront has exactly the same code it seems and
>>> netif_extra_type_gso is the only one I've ever heard of.
>>>
>>> Maybe this extra thing is just redundant unless/until a second extra
>>> comes along.
>> In our windows pv driver, we do not process this for GSO in tx path
>> either. Maybe we ignored processing for some special GSO?
>>
>> BTW, what is XEN_NETIF_EXTRA_FLAG_MORE actually for? Backend only
>> processes it in xen_netback_tx_build_gops, but netfront xmit path does
>> not really set this flag. I did process it in rx path of my windows pv
>> driver(linux netfront did that too), but it seems unnecessary since
>> netback does not set this flag at all.
>>
> The flag is there to denote the existence of an 'extra' segment in the packet. The 'extra' segment goes after the 1st segment and specifies metadata such as the GSO type (TCPv4 is the only one at the moment but we'll need TCPv6 very shortly) and the MSS.
For TCPv4 GSO, it seems one extra info request(NETTXF_extra_info) is
enough in my winpv driver, and I did not process the XEN_NETIF_EXTRA_MORE.
Do you create two extra info requests for bothTCPv4 and TCPv6 GSO like
following?
* [Request 2: netif_tx_extra] (only if request 1 has NETTXF_extra_info)
* [Request 3: netif_tx_extra] (only if request 2 has XEN_NETIF_EXTRA_MORE)
> Extra segments are certainly not redundant; the Citrix Windows PV drivers send TSOs using them and handle LRO using them too.
About the LRO, upstream netback does not create any response with
XEN_NETIF_EXTRA_MORE, so I assume your dom0 did such process?
Thanks
Annie
^ permalink raw reply
* Re: [GIT PULL nf] IPVS fixes for v3.9
From: Pablo Neira Ayuso @ 2013-03-19 9:45 UTC (permalink / raw)
To: Simon Horman
Cc: lvs-devel, netdev, netfilter-devel, Wensong Zhang,
Julian Anastasov
In-Reply-To: <1363657198-5333-1-git-send-email-horms@verge.net.au>
Hi Simon,
I proposed this:
> I think that these three fixes:
>
> ipvs: add backup_only flag to avoid loops
> ipvs: remove extra rcu lock
> ipvs: fix sctp chunk length order
>
> should find their path to the net tree.
>
> The remaining two sparse fixes should go to net-next.
But you sent me these for net:
ipvs: fix sctp chunk length order
ipvs: fix hashing in ip_vs_svc_hashkey
ipvs: fix some sparse warnings
that doesn't match.
Can you resolve this? Thanks.
On Tue, Mar 19, 2013 at 10:39:55AM +0900, Simon Horman wrote:
> Hi Pablo,
>
> The following changes since commit a82783c91d5dce680dbd290ebf301a520b0e72a5:
>
> netfilter: ip6t_NPT: restrict to mangle table (2013-03-15 12:58:21 +0100)
>
> are available in the git repository at:
>
> git://git.kernel.org/pub/scm/linux/kernel/git/horms/ipvs.git tags/ipvs-fixes-for-v3.9
>
> for you to fetch changes up to 1804ac13ac3d9d39b94f3074f303b286e90632ba:
>
> ipvs: fix some sparse warnings (2013-03-19 09:37:37 +0900)
>
> ----------------------------------------------------------------
> IPVS fixes for v3.9 from Julian Anastasov
>
> ----------------------------------------------------------------
> Julian Anastasov (3):
> ipvs: fix sctp chunk length order
> ipvs: fix hashing in ip_vs_svc_hashkey
> ipvs: fix some sparse warnings
>
> include/net/ip_vs.h | 2 +-
> net/netfilter/ipvs/ip_vs_core.c | 8 +-------
> net/netfilter/ipvs/ip_vs_ctl.c | 8 +++++---
> net/netfilter/ipvs/ip_vs_est.c | 2 +-
> net/netfilter/ipvs/ip_vs_proto_sctp.c | 16 +++++++++-------
> 5 files changed, 17 insertions(+), 19 deletions(-)
^ permalink raw reply
* RE: [Xen-devel] [PATCH 1/4] xen-netfront: remove unused variable `extra'
From: Paul Durrant @ 2013-03-19 9:28 UTC (permalink / raw)
To: annie li, Ian Campbell
Cc: netdev@vger.kernel.org, konrad.wilk@oracle.com, Wei Liu,
xen-devel@lists.xen.org
In-Reply-To: <5147CFD2.8040803@oracle.com>
> -----Original Message-----
> From: xen-devel-bounces@lists.xen.org [mailto:xen-devel-
> bounces@lists.xen.org] On Behalf Of annie li
> Sent: 19 March 2013 02:39
> To: Ian Campbell
> Cc: netdev@vger.kernel.org; konrad.wilk@oracle.com; Wei Liu; xen-
> devel@lists.xen.org
> Subject: Re: [Xen-devel] [PATCH 1/4] xen-netfront: remove unused variable
> `extra'
>
>
> On 2013-3-18 20:14, Ian Campbell wrote:
> > On Mon, 2013-03-18 at 12:04 +0000, Wei Liu wrote:
> >> On Mon, 2013-03-18 at 11:42 +0000, Ian Campbell wrote:
> >>> On Mon, 2013-03-18 at 10:35 +0000, Wei Liu wrote:
> >>>
> >>> I think a few more words are needed here since from the code you are
> >>> removing it seems very much like gso is used for something. If you have
> >>> a proof that the "extra = gso" case is never hit then please explain it.
> >>> Perhaps a reference to the removal of the last user?
> >>>
> >>> Or maybe it is the case that it should be used and the bug is that it
> >>> isn't?
> >>>
> >> Looks like the latter one. 'extra' field should be used to get hold of
> >> the last extra info in the ring. ;-)
> >>
> >> But, the only extra info in upstream kernel is
> XEN_NETIF_EXTRA_TYPE_GSO,
> >> so there's really no other extra info in the ring at that point. Could
> >> it be possible that it is something from classic Xen kernel?
> > The classic kernel netfront has exactly the same code it seems and
> > netif_extra_type_gso is the only one I've ever heard of.
> >
> > Maybe this extra thing is just redundant unless/until a second extra
> > comes along.
>
> In our windows pv driver, we do not process this for GSO in tx path
> either. Maybe we ignored processing for some special GSO?
>
> BTW, what is XEN_NETIF_EXTRA_FLAG_MORE actually for? Backend only
> processes it in xen_netback_tx_build_gops, but netfront xmit path does
> not really set this flag. I did process it in rx path of my windows pv
> driver(linux netfront did that too), but it seems unnecessary since
> netback does not set this flag at all.
>
The flag is there to denote the existence of an 'extra' segment in the packet. The 'extra' segment goes after the 1st segment and specifies metadata such as the GSO type (TCPv4 is the only one at the moment but we'll need TCPv6 very shortly) and the MSS.
Extra segments are certainly not redundant; the Citrix Windows PV drivers send TSOs using them and handle LRO using them too.
Paul
^ permalink raw reply
* Re: [PATCH net-next 2/2] net: reset transport header if it was not set before transmission
From: Jason Wang @ 2013-03-19 9:26 UTC (permalink / raw)
To: David Miller; +Cc: eric.dumazet, netdev, linux-kernel, mst, edumazet
In-Reply-To: <20130317.121318.1869489921021513474.davem@davemloft.net>
On 03/18/2013 12:13 AM, David Miller wrote:
> From: Eric Dumazet <eric.dumazet@gmail.com>
> Date: Fri, 15 Mar 2013 19:10:51 -0700
>
>> Any way we can avoid adding this to fast path, for people not using
>> macvtap and ixgbe ?
> Likewise I'd rather see macvtap be responsible for fixing this up by
> setting the transport header properly, and therfore sending well
> formed packets to the rest of the stack.
Ok, haven't checked all other possibility but looks like packet needs to
be fixed also.
^ permalink raw reply
* Re: [PATCH net-next 1/2] net_sched: don't do precise pkt_len computation for untrusted packets
From: Jason Wang @ 2013-03-19 9:25 UTC (permalink / raw)
To: David Miller; +Cc: netdev, linux-kernel, mst, edumazet
In-Reply-To: <20130317.121026.733329595817911776.davem@davemloft.net>
On 03/18/2013 12:10 AM, David Miller wrote:
> From: Jason Wang <jasowang@redhat.com>
> Date: Fri, 15 Mar 2013 15:41:44 +0800
>
>> Commit 1def9238d4aa2 (net_sched: more precise pkt_len computation) tries to do
>> precise packet len computation for GSO packets, but it does not check whether
>> the packets were from untrusted source. This is wrong since: we haven't done
>> header check before so both gso_segs and headers may not be correct. So this
>> patch just bypass the precise pkt_len computation for packet from untrusted
>> source (SKB_GSO_DODGY).
>>
>> Cc: Eric Dumazet <edumazet@google.com>
>> Signed-off-by: Jason Wang <jasowang@redhat.com>
> I do not think this is appropriate or even necessary.
>
> All the user can do by reporting an incorrect header size or GSO segs
> is hurt himself, by making his traffic take more packet scheduler
> quota.
I believe before doing header check for untrusted packets, the only
thing we can trust is skb->len and that's we've used before
1def9238d4aa2. But after that, we're trying to use unchecked or
meaningless value (e.g gso_segs were reset to zero in
tun/macvtap/packet), and guest then can utilize this to result a very
huge (-1U) pkt_len by filling evil value in the header. Can all kinds of
packet scheduler survive this kinds of possible DOS?
>
> When we do precise accounting, it increases, never decreases, the
> amount that a packet "costs" as far as the packet scheduler is
> concerned.
> --
> To unsubscribe from this list: send the line "unsubscribe netdev" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* RE: [PATCH 1/1] connector: Added coredumping event to the process connector
From: Jesper Derehag @ 2013-03-19 9:21 UTC (permalink / raw)
To: netdev@vger.kernel.org
In-Reply-To: <DUB002-W153FA7D4CB9EB6CFF1689B3DDE90@phx.gbl>
> From: jderehag@hotmail.com
> To: netdev@vger.kernel.org
> Subject: RE: [PATCH 1/1] connector: Added coredumping event to the process connector
> Date: Sat, 16 Mar 2013 19:08:03 +0000
>
> ----------------------------------------
> > Date: Sat, 16 Mar 2013 19:40:36 +0100
> > From: hannes@stressinduktion.org
> > To: jderehag@hotmail.com
> > CC: zbr@ioremap.net; netdev@vger.kernel.org
> > Subject: Re: [PATCH 1/1] connector: Added coredumping event to the process connector
> >
> > On Sat, Mar 16, 2013 at 05:57:20PM +0000, Jesper Derehag wrote:
> > >
> > >
> > > > Date: Sat, 16 Mar 2013 18:03:48 +0100
> > > > From: hannes@stressinduktion.org
> > > > To: jderehag@hotmail.com
> > > > CC: zbr@ioremap.net; netdev@vger.kernel.org
> > > > Subject: Re: [PATCH 1/1] connector: Added coredumping event to the process connector
> > > >
> > > > On Sat, Mar 16, 2013 at 11:50:50AM +0100, Jesper Derehag wrote:
> > > > > + ev->event_data.exit.exit_code = task->exit_code;
> > > > > + ev->event_data.exit.exit_signal = task->exit_signal;
> > > >
> > > > Do these already contain meaningful values?
> > > >
> > >
> > > I have to admit that they dont.And you are correct, I should add a new event struct specific for the coredump event instead of piggybacking on the exit struct.Will re-submit a patch..
> >
> > Hm, I am still unsure if such a patch is needed. Couldn't you test for
> > coredump by inspecting exit_code on PROC_EVENT_EXIT?
>
> *** resubmitted message due to it got dropped by vger.kernel.org ***
>
> Well, what this patch adds I think is more a question of timing.
> As an example, say you want to quickly detect process failures. In that case if we would only have the EXIT event, that would mean that we get notified after the dump is done, which could take minutes depending on how large the dump is.
> If we instead watch for both EXIT & COREDUMP events, it would mean that we would quickly catch any failing process, regardless of if its actually starting to coredump or if its exited for some other reason.
Any other comments on this before I send a v2 patch with the exit vs the coredump event struct change?
Regards,
Jesper
^ permalink raw reply
* Re: [PATCH net-next 2/2] bnx2x: add RSS capability for GRE traffic
From: Maciej Żenczykowski @ 2013-03-19 9:18 UTC (permalink / raw)
To: Dmitry Kravkov
Cc: Eric Dumazet, davem@davemloft.net, netdev@vger.kernel.org,
Eilon Greenstein, Tom Herbert
In-Reply-To: <504C9EFCA2D0054393414C9CB605C37F20BE935B@SJEXCHMB06.corp.ad.broadcom.com>
Can the HW calculate and return a 1s complement sum of the entire
packet (or a large portion there-of)?
Fixing that up to be only of the outer IPv4, inner IPv4 and inner TCP
relevant portions should still be simpler (well faster) than
calculating the TCP checksum.
I'm pretty sure that some relationship between 1s complement sum of
all bytes, outer IPv4 checksum, inner IPv4 checksum and TCP checksum
could be pulled out of a hat with some deeper thought. (similarly for
IPv4/GRE/IPv6/TCP and other combinations)
What portions of the packet can the HW/FW [partially] checksum - and
return the value to the driver for further processing?
Can it return 1s complement sum of data portion of outer IPv4 (ie. in
IPv4/GRE/IPv4/TCP return a 1s complement sum of GRE/IPv4/TCP bytes)
Maciej Żenczykowski, Kernel Networking Developer @ Google
On Mon, Mar 18, 2013 at 11:30 PM, Dmitry Kravkov <dmitry@broadcom.com> wrote:
>> -----Original Message-----
>> From: netdev-owner@vger.kernel.org [mailto:netdev-owner@vger.kernel.org] On Behalf Of Eric Dumazet
>> Sent: Tuesday, March 19, 2013 2:08 AM
>> To: Dmitry Kravkov
>> Cc: davem@davemloft.net; netdev@vger.kernel.org; Eilon Greenstein; Tom Herbert; Maciej Żenczykowski
>> Subject: Re: [PATCH net-next 2/2] bnx2x: add RSS capability for GRE traffic
>>
>> On Mon, 2013-03-18 at 18:51 +0200, Dmitry Kravkov wrote:
>> > The patch drives FW to perform RSS for GRE traffic,
>> > based on inner headers.
>> >
>> > Signed-off-by: Dmitry Kravkov <dmitry@broadcom.com>
>> > Signed-off-by: Eilon Greenstein <eilong@broadcom.com>
>> > ---
>> > drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h | 3 +++
>> > drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c | 23 ++++++++++++-----------
>> > drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.h | 9 +++++++++
>> > 3 files changed, 24 insertions(+), 11 deletions(-)
>>
>> This works very well.
>>
>> Problem is we skb_set_queue_mapping(skb, 0); in __skb_tunnel_rx()
>>
>> (this was a patch from Tom Herbert, commit
>> 693019e90ca45d881109d32c0c6d29adf03f6447 (net: reset skb queue mapping
>> when rx'ing over tunnel )
>>
>> Meaning we hit a single cpu for the GRO stuff in ip_gre.
>>
>> I have to think about it.
>>
>>
>> Another question is :
>>
>> Can bnx2x check the tcp checksum if GRE encapsulated ?
>>
> Current HW can't provide this. Probably, it's possible to separate CSUM from GRO/TPA then stack will have to handle CSUM validation for huge packets. Is it worth?
>
^ permalink raw reply
* Re: hv_netvsc: WARNING in softirq.c
From: Richard Genoud @ 2013-03-19 8:36 UTC (permalink / raw)
To: Haiyang Zhang
Cc: devel@linuxdriverproject.org, linux-kernel@vger.kernel.org,
netdev@vger.kernel.org
In-Reply-To: <CACQ1gAi1NNwJ_QDp7ipjwdYCskENGN=N-j+TFD5aHX8DHnoBQA@mail.gmail.com>
2013/3/7 Richard Genoud <richard.genoud@gmail.com>:
> 2013/3/6 Haiyang Zhang <haiyangz@microsoft.com>:
>> I have found a simple way to reproduce this kind of warning:
>> 1) reboot the VM (because this warning can be displayed only once.)
>> 2) login to the host and open the VM [Settings]
>> 3) Temporarily change the Network adapter's option [Virtual Switch] to "Not connected".
>> 4) run dmesg, you should see the warning.
>>
>> The reason for the warning is -- netif_tx_disable() is called when the NIC
>> is disconnected. And it's called within irq context. netif_tx_disable()
>> calls local_bh_enable() which displays warning if in irq.
>>
>> The fix is to remove the unnecessary netif_tx_disable() in the netvsc_linkstatus_callback().
>> I attached a patch. Would you like to test it on your side as well?
I installed the patched kernel today.
here are the stats of the warings until today :
kern.log.1:Mar 12 22:32:10 devlabo kernel: [30114.506299]
------------[ cut here ]------------
kern.log.2:Mar 5 22:30:48 devlabo kernel: [10455.098586]
------------[ cut here ]------------
kern.log.2:Mar 6 22:31:25 devlabo kernel: [85552.645480]
------------[ cut here ]------------
kern.log.3:Feb 26 22:35:14 devlabo kernel: [37398.788119]
------------[ cut here ]------------
kern.log.3:Feb 27 22:34:37 devlabo kernel: [10688.187196]
------------[ cut here ]------------
kern.log.4:Feb 22 22:32:22 devlabo kernel: [40399.795364]
------------[ cut here ]------------
So, I'll wait for one or two weeks before sending some feedback.
Regards,
Richard
^ permalink raw reply
* 3.7.10 and net_namespace_list oops - a known issue?
From: Arkadiusz Miskiewicz @ 2013-03-19 8:29 UTC (permalink / raw)
To: netdev
Hello.
I have one machine with 3.7.10 kernel and vserver patch
(http://vserver.13thfloor.at/Experimental/patch-3.7.10-vs2.3.5.6.diff).
It oopses at net_namespace_list.
Is such thing a known issue in vanilla kernel? Googling shows no similar reports unfortunately.
vserver people think it's vserver unrelated (but who knows).
containers are not used here, network namespace is also not used.
Sometimes it oopses early, sometimes few days after, exim was always involved in several
such oopses I saw.
[ 90.663896] BUG: unable to handle kernel paging request at 00000000f2fa46bb
[ 90.668765] IP: [<ffffffff818661c2>] net_namespace_list+0x2/0x20
[ 90.668765] PGD 1c0e13067 PUD 1c0f24067 PMD 0
[ 90.703789] Oops: 0002 [#1] SMP
[ 90.703789] Modules linked in: ipmi_watchdog sch_sfq dm_mod ipmi_devintf ipmi_si ipmi_msghandler ide_cd_mod cdrom ata_generic pata_acpi ses enclosure pata_amd evdev
sata_nv libata pcspkr serio_raw k8temp hwmon amd64_edac_mod edac_core edac_mce_amd floppy i2c_nforce2 hid_generic forcedeth processor shpchp pci_hotplug kvm_amd kvm
ide_pci_generic amd74xx ide_core i2c_core button xfs sd_mod crc_t10dif aacraid scsi_mod usbhid hid ohci_hcd ehci_hcd usbcore usb_common
[ 90.703789] CPU 1
[ 90.703789] Pid: 3847, xid: #1600, comm: exim Not tainted 3.7.10-1 #1 Supermicro H8SMU/H8SMU
[ 90.703789] RIP: 0010:[<ffffffff818661c2>] [<ffffffff818661c2>] net_namespace_list+0x2/0x20
[ 90.703789] RSP: 0018:ffff8801c0c65b68 EFLAGS: 00210246
[ 90.703789] RAX: ffffffff81865480 RBX: ffff8801f4d99700 RCX: 00000000f2fa46bc
[ 90.703789] RDX: 0000000000000001 RSI: 0000000000000000 RDI: ffff8801d467b840
[ 90.703789] RBP: ffff8801c0c65be8 R08: ffff8801c0c65fd8 R09: 0000000000000000
[ 90.703789] R10: ffff88020d37ab80 R11: 0000000000000003 R12: ffff88020d37ab80
[ 90.703789] R13: ffff8801d467b840 R14: ffff8801be8e484e R15: ffff8801be8e485a
[ 90.703789] FS: 00007f0b663a6700(0000) GS:ffff88021fd00000(0063) knlGS:00000000f6717700
[ 90.703789] CS: 0010 DS: 002b ES: 002b CR0: 000000008005003b
[ 90.703789] CR2: 00000000f2fa46bb CR3: 00000001c0e14000 CR4: 00000000000007e0
[ 90.703789] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[ 90.703789] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400
[ 90.703789] Process exim (pid: 3847, threadinfo ffff8801c0c64000, task ffff88021247da30)
[ 90.703789] Stack:
[ 90.703789] ffff8801c0c65b70 ffffffff8142be7c 0000000000000000 0000000000200246
[ 90.703789] ffff8801c0c65ba8 ffff8801be8e4862 0000000000000000 ffff8801c0c65c80
[ 90.703789] ffff8801c0c65c08 00000000287eac5f ffff8801c0c65bc8 ffff88020d37ab80
[ 90.703789] Call Trace:
[ 90.703789] [<ffffffff8142be7c>] ? tcp_v4_do_rcv+0x2cc/0x4c0
[ 90.703789] [<ffffffff81416d07>] tcp_prequeue_process+0x67/0xb0
[ 90.703789] [<ffffffff8141a8ff>] tcp_recvmsg+0xa8f/0xd70
[ 90.703789] [<ffffffff8143fcda>] inet_recvmsg+0x4a/0x80
[ 90.703789] [<ffffffff814407c5>] ? inet_sendmsg+0x45/0xb0
[ 90.703789] [<ffffffff813bffa2>] sock_aio_read.part.9+0x142/0x1c0
[ 90.703789] [<ffffffff813c0041>] sock_aio_read+0x21/0x30
[ 90.703789] [<ffffffff8117a7f7>] do_sync_read+0xa7/0xe0
[ 90.703789] [<ffffffff8117afed>] vfs_read+0x15d/0x180
[ 90.703789] [<ffffffff8117b05d>] sys_read+0x4d/0xa0
[ 90.703789] [<ffffffff8118ed26>] ? sys_poll+0x66/0x100
[ 90.703789] [<ffffffff814ea6ec>] cstar_dispatch+0x7/0x21
[ 90.703789] Code: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 90 54 <86> 81 ff ff ff ff 90 54 86 81 ff
ff ff ff 00 00 00 00 00 00 00
[ 90.703789] RIP [<ffffffff818661c2>] net_namespace_list+0x2/0x20
[ 90.703789] RSP <ffff8801c0c65b68>
[ 90.703789] CR2: 00000000f2fa46bb
[ 91.531561] ---[ end trace f29e53e8c0132ced ]---
[ 91.545398] Kernel panic - not syncing: Fatal exception in interrupt
[ 91.548728] Rebooting in 60 seconds..
http://pastebin.com/cSCfFgcy
http://pastebin.com/3XtkMbR5
--
Arkadiusz Miśkiewicz, arekm / maven.pl
^ permalink raw reply
* [PATCH v3 net-next 3/5] VXLAN: Fix vxlan stats handling.
From: Pravin B Shelar @ 2013-03-19 8:10 UTC (permalink / raw)
To: davem; +Cc: stephen, xiyou.wangcong, netdev, jesse, Pravin B Shelar
Fixes bug in VXLAN code where is iptunnel_xmit() called with NULL
dev->tstats.
This bug was introduced in commit 6aed0c8bf7d2f389b (tunnel: use
iptunnel_xmit() again).
Following patch fixes bug by setting dev->tstats. It uses ip_tunnel
module code to share stats function.
CC: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: Pravin B Shelar <pshelar@nicira.com>
Acked-by: Stephen Hemminger <stephen@networkplumber.org>
---
drivers/net/Kconfig | 1 +
drivers/net/vxlan.c | 72 +++++----------------------------------------------
2 files changed, 8 insertions(+), 65 deletions(-)
diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index 87f1d39..3835321 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -151,6 +151,7 @@ config MACVTAP
config VXLAN
tristate "Virtual eXtensible Local Area Network (VXLAN)"
depends on INET
+ select NET_IP_TUNNEL
---help---
This allows one to create vxlan virtual interfaces that provide
Layer 2 Networks over Layer 3 Networks. VXLAN is often used
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index fe9ea7d..e532b2a 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -101,20 +101,10 @@ struct vxlan_fdb {
u8 eth_addr[ETH_ALEN];
};
-/* Per-cpu network traffic stats */
-struct vxlan_stats {
- u64 rx_packets;
- u64 rx_bytes;
- u64 tx_packets;
- u64 tx_bytes;
- struct u64_stats_sync syncp;
-};
-
/* Pseudo network device */
struct vxlan_dev {
struct hlist_node hlist;
struct net_device *dev;
- struct vxlan_stats __percpu *stats;
__u32 vni; /* virtual network id */
__be32 gaddr; /* multicast group */
__be32 saddr; /* source address */
@@ -667,7 +657,7 @@ static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
struct iphdr *oip;
struct vxlanhdr *vxh;
struct vxlan_dev *vxlan;
- struct vxlan_stats *stats;
+ struct pcpu_tstats *stats;
__u32 vni;
int err;
@@ -743,7 +733,7 @@ static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
}
}
- stats = this_cpu_ptr(vxlan->stats);
+ stats = this_cpu_ptr(vxlan->dev->tstats);
u64_stats_update_begin(&stats->syncp);
stats->rx_packets++;
stats->rx_bytes += skb->len;
@@ -974,8 +964,7 @@ static netdev_tx_t vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
/* short-circuited back to local bridge */
if (netif_rx(skb) == NET_RX_SUCCESS) {
- struct vxlan_stats *stats =
- this_cpu_ptr(vxlan->stats);
+ struct pcpu_tstats *stats = this_cpu_ptr(dev->tstats);
u64_stats_update_begin(&stats->syncp);
stats->tx_packets++;
@@ -1183,10 +1172,8 @@ static void vxlan_cleanup(unsigned long arg)
/* Setup stats when device is created */
static int vxlan_init(struct net_device *dev)
{
- struct vxlan_dev *vxlan = netdev_priv(dev);
-
- vxlan->stats = alloc_percpu(struct vxlan_stats);
- if (!vxlan->stats)
+ dev->tstats = alloc_percpu(struct pcpu_tstats);
+ if (!dev->tstats)
return -ENOMEM;
return 0;
@@ -1242,49 +1229,6 @@ static int vxlan_stop(struct net_device *dev)
return 0;
}
-/* Merge per-cpu statistics */
-static struct rtnl_link_stats64 *vxlan_stats64(struct net_device *dev,
- struct rtnl_link_stats64 *stats)
-{
- struct vxlan_dev *vxlan = netdev_priv(dev);
- struct vxlan_stats tmp, sum = { 0 };
- unsigned int cpu;
-
- for_each_possible_cpu(cpu) {
- unsigned int start;
- const struct vxlan_stats *stats
- = per_cpu_ptr(vxlan->stats, cpu);
-
- do {
- start = u64_stats_fetch_begin_bh(&stats->syncp);
- memcpy(&tmp, stats, sizeof(tmp));
- } while (u64_stats_fetch_retry_bh(&stats->syncp, start));
-
- sum.tx_bytes += tmp.tx_bytes;
- sum.tx_packets += tmp.tx_packets;
- sum.rx_bytes += tmp.rx_bytes;
- sum.rx_packets += tmp.rx_packets;
- }
-
- stats->tx_bytes = sum.tx_bytes;
- stats->tx_packets = sum.tx_packets;
- stats->rx_bytes = sum.rx_bytes;
- stats->rx_packets = sum.rx_packets;
-
- stats->multicast = dev->stats.multicast;
- stats->rx_length_errors = dev->stats.rx_length_errors;
- stats->rx_frame_errors = dev->stats.rx_frame_errors;
- stats->rx_errors = dev->stats.rx_errors;
-
- stats->tx_dropped = dev->stats.tx_dropped;
- stats->tx_carrier_errors = dev->stats.tx_carrier_errors;
- stats->tx_aborted_errors = dev->stats.tx_aborted_errors;
- stats->collisions = dev->stats.collisions;
- stats->tx_errors = dev->stats.tx_errors;
-
- return stats;
-}
-
/* Stub, nothing needs to be done. */
static void vxlan_set_multicast_list(struct net_device *dev)
{
@@ -1295,7 +1239,7 @@ static const struct net_device_ops vxlan_netdev_ops = {
.ndo_open = vxlan_open,
.ndo_stop = vxlan_stop,
.ndo_start_xmit = vxlan_xmit,
- .ndo_get_stats64 = vxlan_stats64,
+ .ndo_get_stats64 = ip_tunnel_get_stats64,
.ndo_set_rx_mode = vxlan_set_multicast_list,
.ndo_change_mtu = eth_change_mtu,
.ndo_validate_addr = eth_validate_addr,
@@ -1312,9 +1256,7 @@ static struct device_type vxlan_type = {
static void vxlan_free(struct net_device *dev)
{
- struct vxlan_dev *vxlan = netdev_priv(dev);
-
- free_percpu(vxlan->stats);
+ free_percpu(dev->tstats);
free_netdev(dev);
}
--
1.7.1
^ permalink raw reply related
* [PATCH v3 net-next 5/5] Tunneling: use IP Tunnel stats APIs.
From: Pravin B Shelar @ 2013-03-19 8:10 UTC (permalink / raw)
To: davem; +Cc: netdev, jesse, Pravin B Shelar
Use common function get calculate rtnl_link_stats64 stats.
Signed-off-by: Pravin B Shelar <pshelar@nicira.com>
---
net/ipv4/Kconfig | 1 +
net/ipv4/ip_vti.c | 40 +---------------------------------------
net/ipv6/Kconfig | 2 ++
net/ipv6/ip6_gre.c | 42 +-----------------------------------------
net/ipv6/sit.c | 37 +------------------------------------
5 files changed, 6 insertions(+), 116 deletions(-)
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index 6f04073..91c9dd7 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -319,6 +319,7 @@ config SYN_COOKIES
config NET_IPVTI
tristate "Virtual (secure) IP: tunneling"
select INET_TUNNEL
+ select NET_IP_TUNNEL
depends on INET_XFRM_MODE_TUNNEL
---help---
Tunneling means encapsulating data of one protocol type within
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 6a628fb..9d2bdb2 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -82,44 +82,6 @@ static int vti_tunnel_bind_dev(struct net_device *dev);
} while (0)
-static struct rtnl_link_stats64 *vti_get_stats64(struct net_device *dev,
- struct rtnl_link_stats64 *tot)
-{
- int i;
-
- for_each_possible_cpu(i) {
- const struct pcpu_tstats *tstats = per_cpu_ptr(dev->tstats, i);
- u64 rx_packets, rx_bytes, tx_packets, tx_bytes;
- unsigned int start;
-
- do {
- start = u64_stats_fetch_begin_bh(&tstats->syncp);
- rx_packets = tstats->rx_packets;
- tx_packets = tstats->tx_packets;
- rx_bytes = tstats->rx_bytes;
- tx_bytes = tstats->tx_bytes;
- } while (u64_stats_fetch_retry_bh(&tstats->syncp, start));
-
- tot->rx_packets += rx_packets;
- tot->tx_packets += tx_packets;
- tot->rx_bytes += rx_bytes;
- tot->tx_bytes += tx_bytes;
- }
-
- tot->multicast = dev->stats.multicast;
- tot->rx_crc_errors = dev->stats.rx_crc_errors;
- tot->rx_fifo_errors = dev->stats.rx_fifo_errors;
- tot->rx_length_errors = dev->stats.rx_length_errors;
- tot->rx_errors = dev->stats.rx_errors;
- tot->tx_fifo_errors = dev->stats.tx_fifo_errors;
- tot->tx_carrier_errors = dev->stats.tx_carrier_errors;
- tot->tx_dropped = dev->stats.tx_dropped;
- tot->tx_aborted_errors = dev->stats.tx_aborted_errors;
- tot->tx_errors = dev->stats.tx_errors;
-
- return tot;
-}
-
static struct ip_tunnel *vti_tunnel_lookup(struct net *net,
__be32 remote, __be32 local)
{
@@ -597,7 +559,7 @@ static const struct net_device_ops vti_netdev_ops = {
.ndo_start_xmit = vti_tunnel_xmit,
.ndo_do_ioctl = vti_tunnel_ioctl,
.ndo_change_mtu = vti_tunnel_change_mtu,
- .ndo_get_stats64 = vti_get_stats64,
+ .ndo_get_stats64 = ip_tunnel_get_stats64,
};
static void vti_dev_free(struct net_device *dev)
diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig
index ed0b9e2..11b13ea 100644
--- a/net/ipv6/Kconfig
+++ b/net/ipv6/Kconfig
@@ -156,6 +156,7 @@ config INET6_XFRM_MODE_ROUTEOPTIMIZATION
config IPV6_SIT
tristate "IPv6: IPv6-in-IPv4 tunnel (SIT driver)"
select INET_TUNNEL
+ select NET_IP_TUNNEL
select IPV6_NDISC_NODETYPE
default y
---help---
@@ -201,6 +202,7 @@ config IPV6_TUNNEL
config IPV6_GRE
tristate "IPv6: GRE tunnel"
select IPV6_TUNNEL
+ select NET_IP_TUNNEL
---help---
Tunneling means encapsulating data of one protocol type within
another protocol and sending it over a channel that understands the
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index af4a5e2..499a545 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -111,46 +111,6 @@ static u32 HASH_ADDR(const struct in6_addr *addr)
#define tunnels_l tunnels[1]
#define tunnels_wc tunnels[0]
-static struct rtnl_link_stats64 *ip6gre_get_stats64(struct net_device *dev,
- struct rtnl_link_stats64 *tot)
-{
- int i;
-
- for_each_possible_cpu(i) {
- const struct pcpu_tstats *tstats = per_cpu_ptr(dev->tstats, i);
- u64 rx_packets, rx_bytes, tx_packets, tx_bytes;
- unsigned int start;
-
- do {
- start = u64_stats_fetch_begin_bh(&tstats->syncp);
- rx_packets = tstats->rx_packets;
- tx_packets = tstats->tx_packets;
- rx_bytes = tstats->rx_bytes;
- tx_bytes = tstats->tx_bytes;
- } while (u64_stats_fetch_retry_bh(&tstats->syncp, start));
-
- tot->rx_packets += rx_packets;
- tot->tx_packets += tx_packets;
- tot->rx_bytes += rx_bytes;
- tot->tx_bytes += tx_bytes;
- }
-
- tot->multicast = dev->stats.multicast;
- tot->rx_crc_errors = dev->stats.rx_crc_errors;
- tot->rx_fifo_errors = dev->stats.rx_fifo_errors;
- tot->rx_length_errors = dev->stats.rx_length_errors;
- tot->rx_frame_errors = dev->stats.rx_frame_errors;
- tot->rx_errors = dev->stats.rx_errors;
-
- tot->tx_fifo_errors = dev->stats.tx_fifo_errors;
- tot->tx_carrier_errors = dev->stats.tx_carrier_errors;
- tot->tx_dropped = dev->stats.tx_dropped;
- tot->tx_aborted_errors = dev->stats.tx_aborted_errors;
- tot->tx_errors = dev->stats.tx_errors;
-
- return tot;
-}
-
/* Given src, dst and key, find appropriate for input tunnel. */
static struct ip6_tnl *ip6gre_tunnel_lookup(struct net_device *dev,
@@ -1257,7 +1217,7 @@ static const struct net_device_ops ip6gre_netdev_ops = {
.ndo_start_xmit = ip6gre_tunnel_xmit,
.ndo_do_ioctl = ip6gre_tunnel_ioctl,
.ndo_change_mtu = ip6gre_tunnel_change_mtu,
- .ndo_get_stats64 = ip6gre_get_stats64,
+ .ndo_get_stats64 = ip_tunnel_get_stats64,
};
static void ip6gre_dev_free(struct net_device *dev)
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index ee4fc57..3353634 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -87,41 +87,6 @@ struct sit_net {
struct net_device *fb_tunnel_dev;
};
-static struct rtnl_link_stats64 *ipip6_get_stats64(struct net_device *dev,
- struct rtnl_link_stats64 *tot)
-{
- int i;
-
- for_each_possible_cpu(i) {
- const struct pcpu_tstats *tstats = per_cpu_ptr(dev->tstats, i);
- u64 rx_packets, rx_bytes, tx_packets, tx_bytes;
- unsigned int start;
-
- do {
- start = u64_stats_fetch_begin_bh(&tstats->syncp);
- rx_packets = tstats->rx_packets;
- tx_packets = tstats->tx_packets;
- rx_bytes = tstats->rx_bytes;
- tx_bytes = tstats->tx_bytes;
- } while (u64_stats_fetch_retry_bh(&tstats->syncp, start));
-
- tot->rx_packets += rx_packets;
- tot->tx_packets += tx_packets;
- tot->rx_bytes += rx_bytes;
- tot->tx_bytes += tx_bytes;
- }
-
- tot->rx_errors = dev->stats.rx_errors;
- tot->rx_frame_errors = dev->stats.rx_frame_errors;
- tot->tx_fifo_errors = dev->stats.tx_fifo_errors;
- tot->tx_carrier_errors = dev->stats.tx_carrier_errors;
- tot->tx_dropped = dev->stats.tx_dropped;
- tot->tx_aborted_errors = dev->stats.tx_aborted_errors;
- tot->tx_errors = dev->stats.tx_errors;
-
- return tot;
-}
-
/*
* Must be invoked with rcu_read_lock
*/
@@ -1202,7 +1167,7 @@ static const struct net_device_ops ipip6_netdev_ops = {
.ndo_start_xmit = ipip6_tunnel_xmit,
.ndo_do_ioctl = ipip6_tunnel_ioctl,
.ndo_change_mtu = ipip6_tunnel_change_mtu,
- .ndo_get_stats64= ipip6_get_stats64,
+ .ndo_get_stats64 = ip_tunnel_get_stats64,
};
static void ipip6_dev_free(struct net_device *dev)
--
1.7.1
^ permalink raw reply related
* [PATCH v3 net-next 4/5] VXLAN: Use IP Tunnels tunnel ENC encap API
From: Pravin B Shelar @ 2013-03-19 8:10 UTC (permalink / raw)
To: davem; +Cc: stephen, netdev, jesse, Pravin B Shelar
Use common ecn_encap functions from ip_tunnel module.
Signed-off-by: Pravin B Shelar <pshelar@nicira.com>
Acked-by: Stephen Hemminger <stephen@networkplumber.org>
---
drivers/net/vxlan.c | 26 ++------------------------
1 files changed, 2 insertions(+), 24 deletions(-)
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index e532b2a..7624ab1 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -864,28 +864,6 @@ static bool route_shortcircuit(struct net_device *dev, struct sk_buff *skb)
return false;
}
-/* Extract dsfield from inner protocol */
-static inline u8 vxlan_get_dsfield(const struct iphdr *iph,
- const struct sk_buff *skb)
-{
- if (skb->protocol == htons(ETH_P_IP))
- return iph->tos;
- else if (skb->protocol == htons(ETH_P_IPV6))
- return ipv6_get_dsfield((const struct ipv6hdr *)iph);
- else
- return 0;
-}
-
-/* Propogate ECN bits out */
-static inline u8 vxlan_ecn_encap(u8 tos,
- const struct iphdr *iph,
- const struct sk_buff *skb)
-{
- u8 inner = vxlan_get_dsfield(iph, skb);
-
- return INET_ECN_encapsulate(tos, inner);
-}
-
static void vxlan_sock_free(struct sk_buff *skb)
{
sock_put(skb->sk);
@@ -996,7 +974,7 @@ static netdev_tx_t vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
tos = vxlan->tos;
if (tos == 1)
- tos = vxlan_get_dsfield(old_iph, skb);
+ tos = ip_tunnel_get_dsfield(old_iph, skb);
src_port = vxlan_src_port(vxlan, skb);
@@ -1047,7 +1025,7 @@ static netdev_tx_t vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
iph->ihl = sizeof(struct iphdr) >> 2;
iph->frag_off = df;
iph->protocol = IPPROTO_UDP;
- iph->tos = vxlan_ecn_encap(tos, old_iph, skb);
+ iph->tos = ip_tunnel_ecn_encap(tos, old_iph, skb);
iph->daddr = dst;
iph->saddr = fl4.saddr;
iph->ttl = ttl ? : ip4_dst_hoplimit(&rt->dst);
--
1.7.1
^ permalink raw reply related
* [PATCH v3 net-next 2/5] IPIP: Use ip-tunneling code.
From: Pravin B Shelar @ 2013-03-19 8:10 UTC (permalink / raw)
To: davem; +Cc: netdev, jesse, Pravin B Shelar
Reuse common ip-tunneling code which is re-factored from GRE
module.
Signed-off-by: Pravin B Shelar <pshelar@nicira.com>
---
net/ipv4/Kconfig | 1 +
net/ipv4/ipip.c | 747 ++++-------------------------------------------------
2 files changed, 58 insertions(+), 690 deletions(-)
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index 7d3c240..6f04073 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -166,6 +166,7 @@ config IP_PNP_RARP
config NET_IPIP
tristate "IP: tunneling"
select INET_TUNNEL
+ select NET_IP_TUNNEL
---help---
Tunneling means encapsulating data of one protocol type within
another protocol and sending it over a channel that understands the
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index a557d6a..94aee53 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -117,221 +117,15 @@
#include <net/net_namespace.h>
#include <net/netns/generic.h>
-#define HASH_SIZE 16
-#define HASH(addr) (((__force u32)addr^((__force u32)addr>>4))&0xF)
-
static bool log_ecn_error = true;
module_param(log_ecn_error, bool, 0644);
MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN");
static int ipip_net_id __read_mostly;
-struct ipip_net {
- struct ip_tunnel __rcu *tunnels_r_l[HASH_SIZE];
- struct ip_tunnel __rcu *tunnels_r[HASH_SIZE];
- struct ip_tunnel __rcu *tunnels_l[HASH_SIZE];
- struct ip_tunnel __rcu *tunnels_wc[1];
- struct ip_tunnel __rcu **tunnels[4];
-
- struct net_device *fb_tunnel_dev;
-};
static int ipip_tunnel_init(struct net_device *dev);
-static void ipip_tunnel_setup(struct net_device *dev);
-static void ipip_dev_free(struct net_device *dev);
static struct rtnl_link_ops ipip_link_ops __read_mostly;
-static struct rtnl_link_stats64 *ipip_get_stats64(struct net_device *dev,
- struct rtnl_link_stats64 *tot)
-{
- int i;
-
- for_each_possible_cpu(i) {
- const struct pcpu_tstats *tstats = per_cpu_ptr(dev->tstats, i);
- u64 rx_packets, rx_bytes, tx_packets, tx_bytes;
- unsigned int start;
-
- do {
- start = u64_stats_fetch_begin_bh(&tstats->syncp);
- rx_packets = tstats->rx_packets;
- tx_packets = tstats->tx_packets;
- rx_bytes = tstats->rx_bytes;
- tx_bytes = tstats->tx_bytes;
- } while (u64_stats_fetch_retry_bh(&tstats->syncp, start));
-
- tot->rx_packets += rx_packets;
- tot->tx_packets += tx_packets;
- tot->rx_bytes += rx_bytes;
- tot->tx_bytes += tx_bytes;
- }
-
- tot->tx_fifo_errors = dev->stats.tx_fifo_errors;
- tot->tx_carrier_errors = dev->stats.tx_carrier_errors;
- tot->tx_dropped = dev->stats.tx_dropped;
- tot->tx_aborted_errors = dev->stats.tx_aborted_errors;
- tot->tx_errors = dev->stats.tx_errors;
- tot->collisions = dev->stats.collisions;
-
- return tot;
-}
-
-static struct ip_tunnel *ipip_tunnel_lookup(struct net *net,
- __be32 remote, __be32 local)
-{
- unsigned int h0 = HASH(remote);
- unsigned int h1 = HASH(local);
- struct ip_tunnel *t;
- struct ipip_net *ipn = net_generic(net, ipip_net_id);
-
- for_each_ip_tunnel_rcu(t, ipn->tunnels_r_l[h0 ^ h1])
- if (local == t->parms.iph.saddr &&
- remote == t->parms.iph.daddr && (t->dev->flags&IFF_UP))
- return t;
-
- for_each_ip_tunnel_rcu(t, ipn->tunnels_r[h0])
- if (remote == t->parms.iph.daddr && (t->dev->flags&IFF_UP))
- return t;
-
- for_each_ip_tunnel_rcu(t, ipn->tunnels_l[h1])
- if (local == t->parms.iph.saddr && (t->dev->flags&IFF_UP))
- return t;
-
- t = rcu_dereference(ipn->tunnels_wc[0]);
- if (t && (t->dev->flags&IFF_UP))
- return t;
- return NULL;
-}
-
-static struct ip_tunnel __rcu **__ipip_bucket(struct ipip_net *ipn,
- struct ip_tunnel_parm *parms)
-{
- __be32 remote = parms->iph.daddr;
- __be32 local = parms->iph.saddr;
- unsigned int h = 0;
- int prio = 0;
-
- if (remote) {
- prio |= 2;
- h ^= HASH(remote);
- }
- if (local) {
- prio |= 1;
- h ^= HASH(local);
- }
- return &ipn->tunnels[prio][h];
-}
-
-static inline struct ip_tunnel __rcu **ipip_bucket(struct ipip_net *ipn,
- struct ip_tunnel *t)
-{
- return __ipip_bucket(ipn, &t->parms);
-}
-
-static void ipip_tunnel_unlink(struct ipip_net *ipn, struct ip_tunnel *t)
-{
- struct ip_tunnel __rcu **tp;
- struct ip_tunnel *iter;
-
- for (tp = ipip_bucket(ipn, t);
- (iter = rtnl_dereference(*tp)) != NULL;
- tp = &iter->next) {
- if (t == iter) {
- rcu_assign_pointer(*tp, t->next);
- break;
- }
- }
-}
-
-static void ipip_tunnel_link(struct ipip_net *ipn, struct ip_tunnel *t)
-{
- struct ip_tunnel __rcu **tp = ipip_bucket(ipn, t);
-
- rcu_assign_pointer(t->next, rtnl_dereference(*tp));
- rcu_assign_pointer(*tp, t);
-}
-
-static int ipip_tunnel_create(struct net_device *dev)
-{
- struct ip_tunnel *t = netdev_priv(dev);
- struct net *net = dev_net(dev);
- struct ipip_net *ipn = net_generic(net, ipip_net_id);
- int err;
-
- err = ipip_tunnel_init(dev);
- if (err < 0)
- goto out;
-
- err = register_netdevice(dev);
- if (err < 0)
- goto out;
-
- strcpy(t->parms.name, dev->name);
- dev->rtnl_link_ops = &ipip_link_ops;
-
- dev_hold(dev);
- ipip_tunnel_link(ipn, t);
- return 0;
-
-out:
- return err;
-}
-
-static struct ip_tunnel *ipip_tunnel_locate(struct net *net,
- struct ip_tunnel_parm *parms, int create)
-{
- __be32 remote = parms->iph.daddr;
- __be32 local = parms->iph.saddr;
- struct ip_tunnel *t, *nt;
- struct ip_tunnel __rcu **tp;
- struct net_device *dev;
- char name[IFNAMSIZ];
- struct ipip_net *ipn = net_generic(net, ipip_net_id);
-
- for (tp = __ipip_bucket(ipn, parms);
- (t = rtnl_dereference(*tp)) != NULL;
- tp = &t->next) {
- if (local == t->parms.iph.saddr && remote == t->parms.iph.daddr)
- return t;
- }
- if (!create)
- return NULL;
-
- if (parms->name[0])
- strlcpy(name, parms->name, IFNAMSIZ);
- else
- strcpy(name, "tunl%d");
-
- dev = alloc_netdev(sizeof(*t), name, ipip_tunnel_setup);
- if (dev == NULL)
- return NULL;
-
- dev_net_set(dev, net);
-
- nt = netdev_priv(dev);
- nt->parms = *parms;
-
- if (ipip_tunnel_create(dev) < 0)
- goto failed_free;
-
- return nt;
-
-failed_free:
- ipip_dev_free(dev);
- return NULL;
-}
-
-/* called with RTNL */
-static void ipip_tunnel_uninit(struct net_device *dev)
-{
- struct net *net = dev_net(dev);
- struct ipip_net *ipn = net_generic(net, ipip_net_id);
-
- if (dev == ipn->fb_tunnel_dev)
- RCU_INIT_POINTER(ipn->tunnels_wc[0], NULL);
- else
- ipip_tunnel_unlink(ipn, netdev_priv(dev));
- dev_put(dev);
-}
-
static int ipip_err(struct sk_buff *skb, u32 info)
{
@@ -339,41 +133,17 @@ static int ipip_err(struct sk_buff *skb, u32 info)
8 bytes of packet payload. It means, that precise relaying of
ICMP in the real Internet is absolutely infeasible.
*/
+ struct net *net = dev_net(skb->dev);
+ struct ip_tunnel_net *itn = net_generic(net, ipip_net_id);
const struct iphdr *iph = (const struct iphdr *)skb->data;
- const int type = icmp_hdr(skb)->type;
- const int code = icmp_hdr(skb)->code;
struct ip_tunnel *t;
int err;
-
- switch (type) {
- default:
- case ICMP_PARAMETERPROB:
- return 0;
-
- case ICMP_DEST_UNREACH:
- switch (code) {
- case ICMP_SR_FAILED:
- case ICMP_PORT_UNREACH:
- /* Impossible event. */
- return 0;
- default:
- /* All others are translated to HOST_UNREACH.
- rfc2003 contains "deep thoughts" about NET_UNREACH,
- I believe they are just ether pollution. --ANK
- */
- break;
- }
- break;
- case ICMP_TIME_EXCEEDED:
- if (code != ICMP_EXC_TTL)
- return 0;
- break;
- case ICMP_REDIRECT:
- break;
- }
+ const int type = icmp_hdr(skb)->type;
+ const int code = icmp_hdr(skb)->code;
err = -ENOENT;
- t = ipip_tunnel_lookup(dev_net(skb->dev), iph->daddr, iph->saddr);
+ t = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY,
+ iph->daddr, iph->saddr, 0);
if (t == NULL)
goto out;
@@ -403,53 +173,29 @@ static int ipip_err(struct sk_buff *skb, u32 info)
else
t->err_count = 1;
t->err_time = jiffies;
-out:
+out:
return err;
}
+static const struct tnl_ptk_info tpi = {
+ /* no tunnel info required for ipip. */
+ .proto = htons(ETH_P_IP),
+};
+
static int ipip_rcv(struct sk_buff *skb)
{
+ struct net *net = dev_net(skb->dev);
+ struct ip_tunnel_net *itn = net_generic(net, ipip_net_id);
struct ip_tunnel *tunnel;
const struct iphdr *iph = ip_hdr(skb);
- int err;
-
- tunnel = ipip_tunnel_lookup(dev_net(skb->dev), iph->saddr, iph->daddr);
- if (tunnel != NULL) {
- struct pcpu_tstats *tstats;
+ tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY,
+ iph->saddr, iph->daddr, 0);
+ if (tunnel) {
if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
goto drop;
-
- secpath_reset(skb);
-
- skb->mac_header = skb->network_header;
- skb_reset_network_header(skb);
- skb->protocol = htons(ETH_P_IP);
- skb->pkt_type = PACKET_HOST;
-
- __skb_tunnel_rx(skb, tunnel->dev);
-
- err = IP_ECN_decapsulate(iph, skb);
- if (unlikely(err)) {
- if (log_ecn_error)
- net_info_ratelimited("non-ECT from %pI4 with TOS=%#x\n",
- &iph->saddr, iph->tos);
- if (err > 1) {
- ++tunnel->dev->stats.rx_frame_errors;
- ++tunnel->dev->stats.rx_errors;
- goto drop;
- }
- }
-
- tstats = this_cpu_ptr(tunnel->dev->tstats);
- u64_stats_update_begin(&tstats->syncp);
- tstats->rx_packets++;
- tstats->rx_bytes += skb->len;
- u64_stats_update_end(&tstats->syncp);
-
- netif_rx(skb);
- return 0;
+ return ip_tunnel_rcv(tunnel, skb, &tpi, log_ecn_error);
}
return -1;
@@ -463,333 +209,65 @@ drop:
* This function assumes it is being called from dev_queue_xmit()
* and that skb is filled properly by that function.
*/
-
static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
const struct iphdr *tiph = &tunnel->parms.iph;
- u8 tos = tunnel->parms.iph.tos;
- __be16 df = tiph->frag_off;
- struct rtable *rt; /* Route to the other host */
- struct net_device *tdev; /* Device to other host */
- const struct iphdr *old_iph;
- struct iphdr *iph; /* Our new IP header */
- unsigned int max_headroom; /* The extra header space needed */
- __be32 dst = tiph->daddr;
- struct flowi4 fl4;
- int mtu;
-
- if (skb->protocol != htons(ETH_P_IP))
- goto tx_error;
- old_iph = ip_hdr(skb);
-
- if (tos & 1)
- tos = old_iph->tos;
-
- if (!dst) {
- /* NBMA tunnel */
- if ((rt = skb_rtable(skb)) == NULL) {
- dev->stats.tx_fifo_errors++;
- goto tx_error;
- }
- dst = rt_nexthop(rt, old_iph->daddr);
- }
- rt = ip_route_output_ports(dev_net(dev), &fl4, NULL,
- dst, tiph->saddr,
- 0, 0,
- IPPROTO_IPIP, RT_TOS(tos),
- tunnel->parms.link);
- if (IS_ERR(rt)) {
- dev->stats.tx_carrier_errors++;
- goto tx_error_icmp;
- }
- tdev = rt->dst.dev;
-
- if (tdev == dev) {
- ip_rt_put(rt);
- dev->stats.collisions++;
+ if (unlikely(skb->protocol != htons(ETH_P_IP)))
goto tx_error;
- }
-
- df |= old_iph->frag_off & htons(IP_DF);
-
- if (df) {
- mtu = dst_mtu(&rt->dst) - sizeof(struct iphdr);
-
- if (mtu < 68) {
- dev->stats.collisions++;
- ip_rt_put(rt);
- goto tx_error;
- }
-
- if (skb_dst(skb))
- skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
- if ((old_iph->frag_off & htons(IP_DF)) &&
- mtu < ntohs(old_iph->tot_len)) {
- icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
- htonl(mtu));
- ip_rt_put(rt);
- goto tx_error;
- }
- }
-
- if (tunnel->err_count > 0) {
- if (time_before(jiffies,
- tunnel->err_time + IPTUNNEL_ERR_TIMEO)) {
- tunnel->err_count--;
- dst_link_failure(skb);
- } else
- tunnel->err_count = 0;
- }
-
- /*
- * Okay, now see if we can stuff it in the buffer as-is.
- */
- max_headroom = (LL_RESERVED_SPACE(tdev)+sizeof(struct iphdr));
-
- if (skb_headroom(skb) < max_headroom || skb_shared(skb) ||
- (skb_cloned(skb) && !skb_clone_writable(skb, 0))) {
- struct sk_buff *new_skb = skb_realloc_headroom(skb, max_headroom);
- if (!new_skb) {
- ip_rt_put(rt);
- dev->stats.tx_dropped++;
- dev_kfree_skb(skb);
- return NETDEV_TX_OK;
- }
- if (skb->sk)
- skb_set_owner_w(new_skb, skb->sk);
- dev_kfree_skb(skb);
- skb = new_skb;
- old_iph = ip_hdr(skb);
- }
-
- if (!skb->encapsulation) {
+ if (likely(!skb->encapsulation)) {
skb_reset_inner_headers(skb);
skb->encapsulation = 1;
}
- if (skb->ip_summed != CHECKSUM_PARTIAL)
- skb->ip_summed = CHECKSUM_NONE;
-
- skb->transport_header = skb->network_header;
- skb_push(skb, sizeof(struct iphdr));
- skb_reset_network_header(skb);
- memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
- IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED |
- IPSKB_REROUTED);
- skb_dst_drop(skb);
- skb_dst_set(skb, &rt->dst);
-
- /*
- * Push down and install the IPIP header.
- */
-
- iph = ip_hdr(skb);
- iph->version = 4;
- iph->ihl = sizeof(struct iphdr)>>2;
- iph->frag_off = df;
- iph->protocol = IPPROTO_IPIP;
- iph->tos = INET_ECN_encapsulate(tos, old_iph->tos);
- iph->daddr = fl4.daddr;
- iph->saddr = fl4.saddr;
- tunnel_ip_select_ident(skb, old_iph, &rt->dst);
-
- if ((iph->ttl = tiph->ttl) == 0)
- iph->ttl = old_iph->ttl;
-
- iptunnel_xmit(skb, dev);
+ ip_tunnel_xmit(skb, dev, tiph);
return NETDEV_TX_OK;
-tx_error_icmp:
- dst_link_failure(skb);
tx_error:
dev->stats.tx_errors++;
dev_kfree_skb(skb);
return NETDEV_TX_OK;
}
-static void ipip_tunnel_bind_dev(struct net_device *dev)
-{
- struct net_device *tdev = NULL;
- struct ip_tunnel *tunnel;
- const struct iphdr *iph;
-
- tunnel = netdev_priv(dev);
- iph = &tunnel->parms.iph;
-
- if (iph->daddr) {
- struct rtable *rt;
- struct flowi4 fl4;
-
- rt = ip_route_output_ports(dev_net(dev), &fl4, NULL,
- iph->daddr, iph->saddr,
- 0, 0,
- IPPROTO_IPIP,
- RT_TOS(iph->tos),
- tunnel->parms.link);
- if (!IS_ERR(rt)) {
- tdev = rt->dst.dev;
- ip_rt_put(rt);
- }
- dev->flags |= IFF_POINTOPOINT;
- }
-
- if (!tdev && tunnel->parms.link)
- tdev = __dev_get_by_index(dev_net(dev), tunnel->parms.link);
-
- if (tdev) {
- dev->hard_header_len = tdev->hard_header_len + sizeof(struct iphdr);
- dev->mtu = tdev->mtu - sizeof(struct iphdr);
- }
- dev->iflink = tunnel->parms.link;
-}
-
-static void ipip_tunnel_update(struct ip_tunnel *t, struct ip_tunnel_parm *p)
-{
- struct net *net = dev_net(t->dev);
- struct ipip_net *ipn = net_generic(net, ipip_net_id);
-
- ipip_tunnel_unlink(ipn, t);
- synchronize_net();
- t->parms.iph.saddr = p->iph.saddr;
- t->parms.iph.daddr = p->iph.daddr;
- memcpy(t->dev->dev_addr, &p->iph.saddr, 4);
- memcpy(t->dev->broadcast, &p->iph.daddr, 4);
- ipip_tunnel_link(ipn, t);
- t->parms.iph.ttl = p->iph.ttl;
- t->parms.iph.tos = p->iph.tos;
- t->parms.iph.frag_off = p->iph.frag_off;
- if (t->parms.link != p->link) {
- t->parms.link = p->link;
- ipip_tunnel_bind_dev(t->dev);
- }
- netdev_state_change(t->dev);
-}
-
static int
-ipip_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd)
+ipip_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
{
int err = 0;
struct ip_tunnel_parm p;
- struct ip_tunnel *t;
- struct net *net = dev_net(dev);
- struct ipip_net *ipn = net_generic(net, ipip_net_id);
-
- switch (cmd) {
- case SIOCGETTUNNEL:
- t = NULL;
- if (dev == ipn->fb_tunnel_dev) {
- if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) {
- err = -EFAULT;
- break;
- }
- t = ipip_tunnel_locate(net, &p, 0);
- }
- if (t == NULL)
- t = netdev_priv(dev);
- memcpy(&p, &t->parms, sizeof(p));
- if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p)))
- err = -EFAULT;
- break;
-
- case SIOCADDTUNNEL:
- case SIOCCHGTUNNEL:
- err = -EPERM;
- if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
- goto done;
-
- err = -EFAULT;
- if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p)))
- goto done;
-
- err = -EINVAL;
- if (p.iph.version != 4 || p.iph.protocol != IPPROTO_IPIP ||
- p.iph.ihl != 5 || (p.iph.frag_off&htons(~IP_DF)))
- goto done;
- if (p.iph.ttl)
- p.iph.frag_off |= htons(IP_DF);
-
- t = ipip_tunnel_locate(net, &p, cmd == SIOCADDTUNNEL);
-
- if (dev != ipn->fb_tunnel_dev && cmd == SIOCCHGTUNNEL) {
- if (t != NULL) {
- if (t->dev != dev) {
- err = -EEXIST;
- break;
- }
- } else {
- if (((dev->flags&IFF_POINTOPOINT) && !p.iph.daddr) ||
- (!(dev->flags&IFF_POINTOPOINT) && p.iph.daddr)) {
- err = -EINVAL;
- break;
- }
- t = netdev_priv(dev);
- }
-
- ipip_tunnel_update(t, &p);
- }
-
- if (t) {
- err = 0;
- if (copy_to_user(ifr->ifr_ifru.ifru_data, &t->parms, sizeof(p)))
- err = -EFAULT;
- } else
- err = (cmd == SIOCADDTUNNEL ? -ENOBUFS : -ENOENT);
- break;
-
- case SIOCDELTUNNEL:
- err = -EPERM;
- if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
- goto done;
-
- if (dev == ipn->fb_tunnel_dev) {
- err = -EFAULT;
- if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p)))
- goto done;
- err = -ENOENT;
- if ((t = ipip_tunnel_locate(net, &p, 0)) == NULL)
- goto done;
- err = -EPERM;
- if (t->dev == ipn->fb_tunnel_dev)
- goto done;
- dev = t->dev;
- }
- unregister_netdevice(dev);
- err = 0;
- break;
- default:
- err = -EINVAL;
- }
+ if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p)))
+ return -EFAULT;
-done:
- return err;
-}
-
-static int ipip_tunnel_change_mtu(struct net_device *dev, int new_mtu)
-{
- if (new_mtu < 68 || new_mtu > 0xFFF8 - sizeof(struct iphdr))
+ if (p.iph.version != 4 || p.iph.protocol != IPPROTO_IPIP ||
+ p.iph.ihl != 5 || (p.iph.frag_off&htons(~IP_DF)))
return -EINVAL;
- dev->mtu = new_mtu;
+ if (p.i_key || p.o_key || p.i_flags || p.o_flags)
+ return -EINVAL;
+ if (p.iph.ttl)
+ p.iph.frag_off |= htons(IP_DF);
+
+
+ err = ip_tunnel_ioctl(dev, &p, cmd);
+ if (err)
+ return err;
+
+ if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p)))
+ return -EFAULT;
+
return 0;
}
static const struct net_device_ops ipip_netdev_ops = {
- .ndo_uninit = ipip_tunnel_uninit,
+ .ndo_init = ipip_tunnel_init,
+ .ndo_uninit = ip_tunnel_uninit,
.ndo_start_xmit = ipip_tunnel_xmit,
.ndo_do_ioctl = ipip_tunnel_ioctl,
- .ndo_change_mtu = ipip_tunnel_change_mtu,
- .ndo_get_stats64 = ipip_get_stats64,
+ .ndo_change_mtu = ip_tunnel_change_mtu,
+ .ndo_get_stats64 = ip_tunnel_get_stats64,
};
-static void ipip_dev_free(struct net_device *dev)
-{
- free_percpu(dev->tstats);
- free_netdev(dev);
-}
-
#define IPIP_FEATURES (NETIF_F_SG | \
NETIF_F_FRAGLIST | \
NETIF_F_HIGHDMA | \
@@ -798,11 +276,8 @@ static void ipip_dev_free(struct net_device *dev)
static void ipip_tunnel_setup(struct net_device *dev)
{
dev->netdev_ops = &ipip_netdev_ops;
- dev->destructor = ipip_dev_free;
dev->type = ARPHRD_TUNNEL;
- dev->hard_header_len = LL_MAX_HEADER + sizeof(struct iphdr);
- dev->mtu = ETH_DATA_LEN - sizeof(struct iphdr);
dev->flags = IFF_NOARP;
dev->iflink = 0;
dev->addr_len = 4;
@@ -812,46 +287,19 @@ static void ipip_tunnel_setup(struct net_device *dev)
dev->features |= IPIP_FEATURES;
dev->hw_features |= IPIP_FEATURES;
+ ip_tunnel_setup(dev, ipip_net_id);
}
static int ipip_tunnel_init(struct net_device *dev)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
- tunnel->dev = dev;
-
memcpy(dev->dev_addr, &tunnel->parms.iph.saddr, 4);
memcpy(dev->broadcast, &tunnel->parms.iph.daddr, 4);
- ipip_tunnel_bind_dev(dev);
-
- dev->tstats = alloc_percpu(struct pcpu_tstats);
- if (!dev->tstats)
- return -ENOMEM;
-
- return 0;
-}
-
-static int __net_init ipip_fb_tunnel_init(struct net_device *dev)
-{
- struct ip_tunnel *tunnel = netdev_priv(dev);
- struct iphdr *iph = &tunnel->parms.iph;
- struct ipip_net *ipn = net_generic(dev_net(dev), ipip_net_id);
-
- tunnel->dev = dev;
- strcpy(tunnel->parms.name, dev->name);
-
- iph->version = 4;
- iph->protocol = IPPROTO_IPIP;
- iph->ihl = 5;
-
- dev->tstats = alloc_percpu(struct pcpu_tstats);
- if (!dev->tstats)
- return -ENOMEM;
-
- dev_hold(dev);
- rcu_assign_pointer(ipn->tunnels_wc[0], tunnel);
- return 0;
+ tunnel->hlen = 0;
+ tunnel->parms.iph.protocol = IPPROTO_IPIP;
+ return ip_tunnel_init(dev);
}
static void ipip_netlink_parms(struct nlattr *data[],
@@ -891,28 +339,16 @@ static void ipip_netlink_parms(struct nlattr *data[],
static int ipip_newlink(struct net *src_net, struct net_device *dev,
struct nlattr *tb[], struct nlattr *data[])
{
- struct net *net = dev_net(dev);
- struct ip_tunnel *nt;
-
- nt = netdev_priv(dev);
- ipip_netlink_parms(data, &nt->parms);
-
- if (ipip_tunnel_locate(net, &nt->parms, 0))
- return -EEXIST;
+ struct ip_tunnel_parm p;
- return ipip_tunnel_create(dev);
+ ipip_netlink_parms(data, &p);
+ return ip_tunnel_newlink(dev, tb, &p);
}
static int ipip_changelink(struct net_device *dev, struct nlattr *tb[],
struct nlattr *data[])
{
- struct ip_tunnel *t;
struct ip_tunnel_parm p;
- struct net *net = dev_net(dev);
- struct ipip_net *ipn = net_generic(net, ipip_net_id);
-
- if (dev == ipn->fb_tunnel_dev)
- return -EINVAL;
ipip_netlink_parms(data, &p);
@@ -920,16 +356,7 @@ static int ipip_changelink(struct net_device *dev, struct nlattr *tb[],
(!(dev->flags & IFF_POINTOPOINT) && p.iph.daddr))
return -EINVAL;
- t = ipip_tunnel_locate(net, &p, 0);
-
- if (t) {
- if (t->dev != dev)
- return -EEXIST;
- } else
- t = netdev_priv(dev);
-
- ipip_tunnel_update(t, &p);
- return 0;
+ return ip_tunnel_changelink(dev, tb, &p);
}
static size_t ipip_get_size(const struct net_device *dev)
@@ -986,6 +413,7 @@ static struct rtnl_link_ops ipip_link_ops __read_mostly = {
.setup = ipip_tunnel_setup,
.newlink = ipip_newlink,
.changelink = ipip_changelink,
+ .dellink = ip_tunnel_dellink,
.get_size = ipip_get_size,
.fill_info = ipip_fill_info,
};
@@ -996,90 +424,29 @@ static struct xfrm_tunnel ipip_handler __read_mostly = {
.priority = 1,
};
-static const char banner[] __initconst =
- KERN_INFO "IPv4 over IPv4 tunneling driver\n";
-
-static void ipip_destroy_tunnels(struct ipip_net *ipn, struct list_head *head)
-{
- int prio;
-
- for (prio = 1; prio < 4; prio++) {
- int h;
- for (h = 0; h < HASH_SIZE; h++) {
- struct ip_tunnel *t;
-
- t = rtnl_dereference(ipn->tunnels[prio][h]);
- while (t != NULL) {
- unregister_netdevice_queue(t->dev, head);
- t = rtnl_dereference(t->next);
- }
- }
- }
-}
-
static int __net_init ipip_init_net(struct net *net)
{
- struct ipip_net *ipn = net_generic(net, ipip_net_id);
- struct ip_tunnel *t;
- int err;
-
- ipn->tunnels[0] = ipn->tunnels_wc;
- ipn->tunnels[1] = ipn->tunnels_l;
- ipn->tunnels[2] = ipn->tunnels_r;
- ipn->tunnels[3] = ipn->tunnels_r_l;
-
- ipn->fb_tunnel_dev = alloc_netdev(sizeof(struct ip_tunnel),
- "tunl0",
- ipip_tunnel_setup);
- if (!ipn->fb_tunnel_dev) {
- err = -ENOMEM;
- goto err_alloc_dev;
- }
- dev_net_set(ipn->fb_tunnel_dev, net);
-
- err = ipip_fb_tunnel_init(ipn->fb_tunnel_dev);
- if (err)
- goto err_reg_dev;
-
- if ((err = register_netdev(ipn->fb_tunnel_dev)))
- goto err_reg_dev;
-
- t = netdev_priv(ipn->fb_tunnel_dev);
-
- strcpy(t->parms.name, ipn->fb_tunnel_dev->name);
- return 0;
-
-err_reg_dev:
- ipip_dev_free(ipn->fb_tunnel_dev);
-err_alloc_dev:
- /* nothing */
- return err;
+ return ip_tunnel_init_net(net, ipip_net_id, &ipip_link_ops, "tunl0");
}
static void __net_exit ipip_exit_net(struct net *net)
{
- struct ipip_net *ipn = net_generic(net, ipip_net_id);
- LIST_HEAD(list);
-
- rtnl_lock();
- ipip_destroy_tunnels(ipn, &list);
- unregister_netdevice_queue(ipn->fb_tunnel_dev, &list);
- unregister_netdevice_many(&list);
- rtnl_unlock();
+ struct ip_tunnel_net *itn = net_generic(net, ipip_net_id);
+ ip_tunnel_delete_net(itn);
}
static struct pernet_operations ipip_net_ops = {
.init = ipip_init_net,
.exit = ipip_exit_net,
.id = &ipip_net_id,
- .size = sizeof(struct ipip_net),
+ .size = sizeof(struct ip_tunnel_net),
};
static int __init ipip_init(void)
{
int err;
- printk(banner);
+ pr_info("ipip: IPv4 over IPv4 tunneling driver\n");
err = register_pernet_device(&ipip_net_ops);
if (err < 0)
--
1.7.1
^ permalink raw reply related
* [PATCH v3 net-next 1/5] GRE: Refactor GRE tunneling code.
From: Pravin B Shelar @ 2013-03-19 8:10 UTC (permalink / raw)
To: davem; +Cc: netdev, jesse, Pravin B Shelar
Following patch refactors GRE code into ip tunneling code and GRE
specific code. Common tunneling code is moved to ip_tunnel module.
ip_tunnel module is written as generic library which can be used
by different tunneling implementations.
ip_tunnel module contains following components:
- packet xmit and rcv generic code. xmit flow looks like
(gre_xmit/ipip_xmit)->ip_tunnel_xmit->ip_local_out.
- hash table of all devices.
- lookup for tunnel devices.
- control plane operations like device create, destroy, ioctl, netlink
operations code.
- registration for tunneling modules, like gre, ipip etc.
- define single pcpu_tstats dev->tstats.
- struct tnl_ptk_info added to pass parsed tunnel packet parameters.
ipip.h header is renamed to ip_tunnel.h
Signed-off-by: Pravin B Shelar <pshelar@nicira.com>
---
drivers/net/vxlan.c | 2 +-
include/net/gre.h | 51 ++
include/net/ip_tunnels.h | 169 ++++++
include/net/ipip.h | 88 ---
net/ipv4/Kconfig | 5 +
net/ipv4/Makefile | 1 +
net/ipv4/af_inet.c | 1 -
net/ipv4/gre.c | 5 -
net/ipv4/ip_gre.c | 1503 ++++++++++------------------------------------
net/ipv4/ip_tunnel.c | 1035 +++++++++++++++++++++++++++++++
net/ipv4/ip_vti.c | 2 +-
net/ipv4/ipip.c | 2 +-
net/ipv4/ipmr.c | 2 +-
net/ipv6/af_inet6.c | 1 -
net/ipv6/ip6_gre.c | 1 +
net/ipv6/ip6_tunnel.c | 1 +
net/ipv6/sit.c | 2 +-
17 files changed, 1580 insertions(+), 1291 deletions(-)
create mode 100644 include/net/ip_tunnels.h
delete mode 100644 include/net/ipip.h
create mode 100644 net/ipv4/ip_tunnel.c
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 33427fd..fe9ea7d 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -33,7 +33,7 @@
#include <net/arp.h>
#include <net/ndisc.h>
#include <net/ip.h>
-#include <net/ipip.h>
+#include <net/ip_tunnels.h>
#include <net/icmp.h>
#include <net/udp.h>
#include <net/rtnetlink.h>
diff --git a/include/net/gre.h b/include/net/gre.h
index 8266547..9f03a39 100644
--- a/include/net/gre.h
+++ b/include/net/gre.h
@@ -2,6 +2,7 @@
#define __LINUX_GRE_H
#include <linux/skbuff.h>
+#include <net/ip_tunnels.h>
#define GREPROTO_CISCO 0
#define GREPROTO_PPTP 1
@@ -12,7 +13,57 @@ struct gre_protocol {
void (*err_handler)(struct sk_buff *skb, u32 info);
};
+struct gre_base_hdr {
+ __be16 flags;
+ __be16 protocol;
+};
+#define GRE_HEADER_SECTION 4
+
int gre_add_protocol(const struct gre_protocol *proto, u8 version);
int gre_del_protocol(const struct gre_protocol *proto, u8 version);
+static inline __be16 gre_flags_to_tnl_flags(__be16 flags)
+{
+ __be16 tflags = 0;
+
+ if (flags & GRE_CSUM)
+ tflags |= TUNNEL_CSUM;
+ if (flags & GRE_ROUTING)
+ tflags |= TUNNEL_ROUTING;
+ if (flags & GRE_KEY)
+ tflags |= TUNNEL_KEY;
+ if (flags & GRE_SEQ)
+ tflags |= TUNNEL_SEQ;
+ if (flags & GRE_STRICT)
+ tflags |= TUNNEL_STRICT;
+ if (flags & GRE_REC)
+ tflags |= TUNNEL_REC;
+ if (flags & GRE_VERSION)
+ tflags |= TUNNEL_VERSION;
+
+ return tflags;
+}
+
+static inline __be16 tnl_flags_to_gre_flags(__be16 tflags)
+{
+ __be16 flags = 0;
+
+ if (tflags & TUNNEL_CSUM)
+ flags |= GRE_CSUM;
+ if (tflags & TUNNEL_ROUTING)
+ flags |= GRE_ROUTING;
+ if (tflags & TUNNEL_KEY)
+ flags |= GRE_KEY;
+ if (tflags & TUNNEL_SEQ)
+ flags |= GRE_SEQ;
+ if (tflags & TUNNEL_STRICT)
+ flags |= GRE_STRICT;
+ if (tflags & TUNNEL_REC)
+ flags |= GRE_REC;
+ if (tflags & TUNNEL_VERSION)
+ flags |= GRE_VERSION;
+
+ return flags;
+}
+
#endif
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
new file mode 100644
index 0000000..0799d7a
--- /dev/null
+++ b/include/net/ip_tunnels.h
@@ -0,0 +1,169 @@
+#ifndef __NET_IP_TUNNELS_H
+#define __NET_IP_TUNNELS_H 1
+
+#include <linux/if_tunnel.h>
+#include <net/dsfield.h>
+#include <net/gro_cells.h>
+#include <net/inet_ecn.h>
+#include <net/ip.h>
+
+/* Keep error state on tunnel for 30 sec */
+#define IPTUNNEL_ERR_TIMEO (30*HZ)
+
+/* 6rd prefix/relay information */
+struct ip_tunnel_6rd_parm {
+ struct in6_addr prefix;
+ __be32 relay_prefix;
+ u16 prefixlen;
+ u16 relay_prefixlen;
+};
+
+struct ip_tunnel {
+ struct ip_tunnel __rcu *next;
+ struct hlist_node hash_node;
+ struct net_device *dev;
+
+ int err_count; /* Number of arrived ICMP errors */
+ unsigned long err_time; /* Time when the last ICMP error
+ * arrived */
+
+ /* These four fields used only by GRE */
+ __u32 i_seqno; /* The last seen seqno */
+ __u32 o_seqno; /* The last output seqno */
+ int hlen; /* Precalculated header length */
+ int mlink;
+
+ struct ip_tunnel_parm parms;
+
+ /* for SIT */
+#ifdef CONFIG_IPV6_SIT_6RD
+ struct ip_tunnel_6rd_parm ip6rd;
+#endif
+ struct ip_tunnel_prl_entry __rcu *prl; /* potential router list */
+ unsigned int prl_count; /* # of entries in PRL */
+ int ip_tnl_net_id;
+ struct gro_cells gro_cells;
+};
+
+#define TUNNEL_CSUM __cpu_to_be16(0x01)
+#define TUNNEL_ROUTING __cpu_to_be16(0x02)
+#define TUNNEL_KEY __cpu_to_be16(0x04)
+#define TUNNEL_SEQ __cpu_to_be16(0x08)
+#define TUNNEL_STRICT __cpu_to_be16(0x10)
+#define TUNNEL_REC __cpu_to_be16(0x20)
+#define TUNNEL_VERSION __cpu_to_be16(0x40)
+#define TUNNEL_NO_KEY __cpu_to_be16(0x80)
+
+struct tnl_ptk_info {
+ __be16 flags;
+ __be16 proto;
+ __be32 key;
+ __be32 seq;
+};
+
+struct ip_tunnel_prl_entry {
+ struct ip_tunnel_prl_entry __rcu *next;
+ __be32 addr;
+ u16 flags;
+ struct rcu_head rcu_head;
+};
+
+#define PACKET_RCVD 0
+#define PACKET_REJECT 1
+
+#define IP_TNL_HASH_BITS 10
+#define IP_TNL_HASH_SIZE (1 << IP_TNL_HASH_BITS)
+
+struct ip_tunnel_net {
+ struct hlist_head *tunnels;
+ struct net_device *fb_tunnel_dev;
+};
+
+int ip_tunnel_init(struct net_device *dev);
+void ip_tunnel_uninit(struct net_device *dev);
+void ip_tunnel_dellink(struct net_device *dev, struct list_head *head);
+int __net_init ip_tunnel_init_net(struct net *net, int ip_tnl_net_id,
+ struct rtnl_link_ops *ops, char *devname);
+
+void __net_exit ip_tunnel_delete_net(struct ip_tunnel_net *itn);
+
+void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
+ const struct iphdr *tnl_params);
+int ip_tunnel_ioctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd);
+int ip_tunnel_change_mtu(struct net_device *dev, int new_mtu);
+
+struct rtnl_link_stats64 *ip_tunnel_get_stats64(struct net_device *dev,
+ struct rtnl_link_stats64 *tot);
+struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn,
+ int link, __be16 flags,
+ __be32 remote, __be32 local,
+ __be32 key);
+
+int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb,
+ const struct tnl_ptk_info *tpi, bool log_ecn_error);
+int ip_tunnel_changelink(struct net_device *dev, struct nlattr *tb[],
+ struct ip_tunnel_parm *p);
+int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[],
+ struct ip_tunnel_parm *p);
+void ip_tunnel_setup(struct net_device *dev, int net_id);
+
+/* Extract dsfield from inner protocol */
+static inline u8 ip_tunnel_get_dsfield(const struct iphdr *iph,
+ const struct sk_buff *skb)
+{
+ if (skb->protocol == htons(ETH_P_IP))
+ return iph->tos;
+ else if (skb->protocol == htons(ETH_P_IPV6))
+ return ipv6_get_dsfield((const struct ipv6hdr *)iph);
+ else
+ return 0;
+}
+
+/* Propogate ECN bits out */
+static inline u8 ip_tunnel_ecn_encap(u8 tos,
+ const struct iphdr *iph,
+ const struct sk_buff *skb)
+{
+ u8 inner = ip_tunnel_get_dsfield(iph, skb);
+
+ return INET_ECN_encapsulate(tos, inner);
+}
+
+static inline void tunnel_ip_select_ident(struct sk_buff *skb,
+ const struct iphdr *old_iph,
+ struct dst_entry *dst)
+{
+ struct iphdr *iph = ip_hdr(skb);
+
+ if (iph->frag_off & htons(IP_DF))
+ iph->id = 0;
+ else {
+ /* Use inner packet iph-id if possible. */
+ if (skb->protocol == htons(ETH_P_IP) && old_iph->id)
+ iph->id = old_iph->id;
+ else
+ __ip_select_ident(iph, dst,
+ (skb_shinfo(skb)->gso_segs ?: 1) - 1);
+ }
+}
+
+static inline void iptunnel_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+ int err;
+ int pkt_len = skb->len - skb_transport_offset(skb);
+ struct pcpu_tstats *tstats = this_cpu_ptr(dev->tstats);
+
+ nf_reset(skb);
+
+ err = ip_local_out(skb);
+ if (likely(net_xmit_eval(err) == 0)) {
+ u64_stats_update_begin(&tstats->syncp);
+ tstats->tx_bytes += pkt_len;
+ tstats->tx_packets++;
+ u64_stats_update_end(&tstats->syncp);
+ } else {
+ dev->stats.tx_errors++;
+ dev->stats.tx_aborted_errors++;
+ }
+}
+#endif /* __NET_IP_TUNNELS_H */
diff --git a/include/net/ipip.h b/include/net/ipip.h
deleted file mode 100644
index 0c046e3..0000000
--- a/include/net/ipip.h
+++ /dev/null
@@ -1,88 +0,0 @@
-#ifndef __NET_IPIP_H
-#define __NET_IPIP_H 1
-
-#include <linux/if_tunnel.h>
-#include <net/gro_cells.h>
-#include <net/ip.h>
-
-/* Keep error state on tunnel for 30 sec */
-#define IPTUNNEL_ERR_TIMEO (30*HZ)
-
-/* 6rd prefix/relay information */
-struct ip_tunnel_6rd_parm {
- struct in6_addr prefix;
- __be32 relay_prefix;
- u16 prefixlen;
- u16 relay_prefixlen;
-};
-
-struct ip_tunnel {
- struct ip_tunnel __rcu *next;
- struct net_device *dev;
-
- int err_count; /* Number of arrived ICMP errors */
- unsigned long err_time; /* Time when the last ICMP error arrived */
-
- /* These four fields used only by GRE */
- __u32 i_seqno; /* The last seen seqno */
- __u32 o_seqno; /* The last output seqno */
- int hlen; /* Precalculated GRE header length */
- int mlink;
-
- struct ip_tunnel_parm parms;
-
- /* for SIT */
-#ifdef CONFIG_IPV6_SIT_6RD
- struct ip_tunnel_6rd_parm ip6rd;
-#endif
- struct ip_tunnel_prl_entry __rcu *prl; /* potential router list */
- unsigned int prl_count; /* # of entries in PRL */
-
- struct gro_cells gro_cells;
-};
-
-struct ip_tunnel_prl_entry {
- struct ip_tunnel_prl_entry __rcu *next;
- __be32 addr;
- u16 flags;
- struct rcu_head rcu_head;
-};
-
-static inline void iptunnel_xmit(struct sk_buff *skb, struct net_device *dev)
-{
- int err;
- int pkt_len = skb->len - skb_transport_offset(skb);
- struct pcpu_tstats *tstats = this_cpu_ptr(dev->tstats);
-
- nf_reset(skb);
-
- err = ip_local_out(skb);
- if (likely(net_xmit_eval(err) == 0)) {
- u64_stats_update_begin(&tstats->syncp);
- tstats->tx_bytes += pkt_len;
- tstats->tx_packets++;
- u64_stats_update_end(&tstats->syncp);
- } else {
- dev->stats.tx_errors++;
- dev->stats.tx_aborted_errors++;
- }
-}
-
-static inline void tunnel_ip_select_ident(struct sk_buff *skb,
- const struct iphdr *old_iph,
- struct dst_entry *dst)
-{
- struct iphdr *iph = ip_hdr(skb);
-
- if (iph->frag_off & htons(IP_DF))
- iph->id = 0;
- else {
- /* Use inner packet iph-id if possible. */
- if (skb->protocol == htons(ETH_P_IP) && old_iph->id)
- iph->id = old_iph->id;
- else
- __ip_select_ident(iph, dst,
- (skb_shinfo(skb)->gso_segs ?: 1) - 1);
- }
-}
-#endif
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index 7944df7..7d3c240 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -186,9 +186,14 @@ config NET_IPGRE_DEMUX
This is helper module to demultiplex GRE packets on GRE version field criteria.
Required by ip_gre and pptp modules.
+config NET_IP_TUNNEL
+ tristate
+ default m
+
config NET_IPGRE
tristate "IP: GRE tunnels over IP"
depends on (IPV6 || IPV6=n) && NET_IPGRE_DEMUX
+ select NET_IP_TUNNEL
help
Tunneling means encapsulating data of one protocol type within
another protocol and sending it over a channel that understands the
diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile
index 15ca63e..089cb9f 100644
--- a/net/ipv4/Makefile
+++ b/net/ipv4/Makefile
@@ -13,6 +13,7 @@ obj-y := route.o inetpeer.o protocol.o \
fib_frontend.o fib_semantics.o fib_trie.o \
inet_fragment.o ping.o
+obj-$(CONFIG_NET_IP_TUNNEL) += ip_tunnel.o
obj-$(CONFIG_SYSCTL) += sysctl_net_ipv4.o
obj-$(CONFIG_PROC_FS) += proc.o
obj-$(CONFIG_IP_MULTIPLE_TABLES) += fib_rules.o
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 9e5882c..a1fca33 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -111,7 +111,6 @@
#include <net/sock.h>
#include <net/raw.h>
#include <net/icmp.h>
-#include <net/ipip.h>
#include <net/inet_common.h>
#include <net/xfrm.h>
#include <net/net_namespace.h>
diff --git a/net/ipv4/gre.c b/net/ipv4/gre.c
index 7a4c710..d2d5a99 100644
--- a/net/ipv4/gre.c
+++ b/net/ipv4/gre.c
@@ -27,11 +27,6 @@
static const struct gre_protocol __rcu *gre_proto[GREPROTO_MAX] __read_mostly;
static DEFINE_SPINLOCK(gre_proto_lock);
-struct gre_base_hdr {
- __be16 flags;
- __be16 protocol;
-};
-#define GRE_HEADER_SECTION 4
int gre_add_protocol(const struct gre_protocol *proto, u8 version)
{
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index a13a097..7da061f 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -37,7 +37,7 @@
#include <net/ip.h>
#include <net/icmp.h>
#include <net/protocol.h>
-#include <net/ipip.h>
+#include <net/ip_tunnels.h>
#include <net/arp.h>
#include <net/checksum.h>
#include <net/dsfield.h>
@@ -108,15 +108,6 @@
fatal route to network, even if it were you who configured
fatal static route: you are innocent. :-)
-
-
- 3. Really, ipv4/ipip.c, ipv4/ip_gre.c and ipv6/sit.c contain
- practically identical code. It would be good to glue them
- together, but it is not very evident, how to make them modular.
- sit is integral part of IPv6, ipip and gre are naturally modular.
- We could extract common parts (hash table, ioctl etc)
- to a separate module (ip_tunnel.c).
-
Alexey Kuznetsov.
*/
@@ -126,400 +117,129 @@ MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN");
static struct rtnl_link_ops ipgre_link_ops __read_mostly;
static int ipgre_tunnel_init(struct net_device *dev);
-static void ipgre_tunnel_setup(struct net_device *dev);
-static int ipgre_tunnel_bind_dev(struct net_device *dev);
-
-/* Fallback tunnel: no source, no destination, no key, no options */
-
-#define HASH_SIZE 16
static int ipgre_net_id __read_mostly;
-struct ipgre_net {
- struct ip_tunnel __rcu *tunnels[4][HASH_SIZE];
-
- struct net_device *fb_tunnel_dev;
-};
-
-/* Tunnel hash table */
-
-/*
- 4 hash tables:
-
- 3: (remote,local)
- 2: (remote,*)
- 1: (*,local)
- 0: (*,*)
+static int gre_tap_net_id __read_mostly;
- We require exact key match i.e. if a key is present in packet
- it will match only tunnel with the same key; if it is not present,
- it will match only keyless tunnel.
-
- All keysless packets, if not matched configured keyless tunnels
- will match fallback tunnel.
- */
-
-#define HASH(addr) (((__force u32)addr^((__force u32)addr>>4))&0xF)
-
-#define tunnels_r_l tunnels[3]
-#define tunnels_r tunnels[2]
-#define tunnels_l tunnels[1]
-#define tunnels_wc tunnels[0]
-
-static struct rtnl_link_stats64 *ipgre_get_stats64(struct net_device *dev,
- struct rtnl_link_stats64 *tot)
+static __sum16 check_checksum(struct sk_buff *skb)
{
- int i;
-
- for_each_possible_cpu(i) {
- const struct pcpu_tstats *tstats = per_cpu_ptr(dev->tstats, i);
- u64 rx_packets, rx_bytes, tx_packets, tx_bytes;
- unsigned int start;
-
- do {
- start = u64_stats_fetch_begin_bh(&tstats->syncp);
- rx_packets = tstats->rx_packets;
- tx_packets = tstats->tx_packets;
- rx_bytes = tstats->rx_bytes;
- tx_bytes = tstats->tx_bytes;
- } while (u64_stats_fetch_retry_bh(&tstats->syncp, start));
-
- tot->rx_packets += rx_packets;
- tot->tx_packets += tx_packets;
- tot->rx_bytes += rx_bytes;
- tot->tx_bytes += tx_bytes;
- }
+ __sum16 csum = 0;
- tot->multicast = dev->stats.multicast;
- tot->rx_crc_errors = dev->stats.rx_crc_errors;
- tot->rx_fifo_errors = dev->stats.rx_fifo_errors;
- tot->rx_length_errors = dev->stats.rx_length_errors;
- tot->rx_frame_errors = dev->stats.rx_frame_errors;
- tot->rx_errors = dev->stats.rx_errors;
+ switch (skb->ip_summed) {
+ case CHECKSUM_COMPLETE:
+ csum = csum_fold(skb->csum);
- tot->tx_fifo_errors = dev->stats.tx_fifo_errors;
- tot->tx_carrier_errors = dev->stats.tx_carrier_errors;
- tot->tx_dropped = dev->stats.tx_dropped;
- tot->tx_aborted_errors = dev->stats.tx_aborted_errors;
- tot->tx_errors = dev->stats.tx_errors;
+ if (!csum)
+ break;
+ /* Fall through. */
- return tot;
-}
+ case CHECKSUM_NONE:
+ skb->csum = 0;
+ csum = __skb_checksum_complete(skb);
+ skb->ip_summed = CHECKSUM_COMPLETE;
+ break;
+ }
-/* Does key in tunnel parameters match packet */
-static bool ipgre_key_match(const struct ip_tunnel_parm *p,
- __be16 flags, __be32 key)
-{
- if (p->i_flags & GRE_KEY) {
- if (flags & GRE_KEY)
- return key == p->i_key;
- else
- return false; /* key expected, none present */
- } else
- return !(flags & GRE_KEY);
+ return csum;
}
-/* Given src, dst and key, find appropriate for input tunnel. */
-
-static struct ip_tunnel *ipgre_tunnel_lookup(struct net_device *dev,
- __be32 remote, __be32 local,
- __be16 flags, __be32 key,
- __be16 gre_proto)
+static int ip_gre_calc_hlen(__be16 o_flags)
{
- struct net *net = dev_net(dev);
- int link = dev->ifindex;
- unsigned int h0 = HASH(remote);
- unsigned int h1 = HASH(key);
- struct ip_tunnel *t, *cand = NULL;
- struct ipgre_net *ign = net_generic(net, ipgre_net_id);
- int dev_type = (gre_proto == htons(ETH_P_TEB)) ?
- ARPHRD_ETHER : ARPHRD_IPGRE;
- int score, cand_score = 4;
-
- for_each_ip_tunnel_rcu(t, ign->tunnels_r_l[h0 ^ h1]) {
- if (local != t->parms.iph.saddr ||
- remote != t->parms.iph.daddr ||
- !(t->dev->flags & IFF_UP))
- continue;
-
- if (!ipgre_key_match(&t->parms, flags, key))
- continue;
-
- if (t->dev->type != ARPHRD_IPGRE &&
- t->dev->type != dev_type)
- continue;
-
- score = 0;
- if (t->parms.link != link)
- score |= 1;
- if (t->dev->type != dev_type)
- score |= 2;
- if (score == 0)
- return t;
-
- if (score < cand_score) {
- cand = t;
- cand_score = score;
- }
- }
-
- for_each_ip_tunnel_rcu(t, ign->tunnels_r[h0 ^ h1]) {
- if (remote != t->parms.iph.daddr ||
- !(t->dev->flags & IFF_UP))
- continue;
-
- if (!ipgre_key_match(&t->parms, flags, key))
- continue;
-
- if (t->dev->type != ARPHRD_IPGRE &&
- t->dev->type != dev_type)
- continue;
-
- score = 0;
- if (t->parms.link != link)
- score |= 1;
- if (t->dev->type != dev_type)
- score |= 2;
- if (score == 0)
- return t;
-
- if (score < cand_score) {
- cand = t;
- cand_score = score;
- }
- }
-
- for_each_ip_tunnel_rcu(t, ign->tunnels_l[h1]) {
- if ((local != t->parms.iph.saddr &&
- (local != t->parms.iph.daddr ||
- !ipv4_is_multicast(local))) ||
- !(t->dev->flags & IFF_UP))
- continue;
-
- if (!ipgre_key_match(&t->parms, flags, key))
- continue;
-
- if (t->dev->type != ARPHRD_IPGRE &&
- t->dev->type != dev_type)
- continue;
-
- score = 0;
- if (t->parms.link != link)
- score |= 1;
- if (t->dev->type != dev_type)
- score |= 2;
- if (score == 0)
- return t;
-
- if (score < cand_score) {
- cand = t;
- cand_score = score;
- }
- }
-
- for_each_ip_tunnel_rcu(t, ign->tunnels_wc[h1]) {
- if (t->parms.i_key != key ||
- !(t->dev->flags & IFF_UP))
- continue;
-
- if (t->dev->type != ARPHRD_IPGRE &&
- t->dev->type != dev_type)
- continue;
-
- score = 0;
- if (t->parms.link != link)
- score |= 1;
- if (t->dev->type != dev_type)
- score |= 2;
- if (score == 0)
- return t;
-
- if (score < cand_score) {
- cand = t;
- cand_score = score;
- }
- }
-
- if (cand != NULL)
- return cand;
+ int addend = 4;
- dev = ign->fb_tunnel_dev;
- if (dev->flags & IFF_UP)
- return netdev_priv(dev);
-
- return NULL;
+ if (o_flags&TUNNEL_CSUM)
+ addend += 4;
+ if (o_flags&TUNNEL_KEY)
+ addend += 4;
+ if (o_flags&TUNNEL_SEQ)
+ addend += 4;
+ return addend;
}
-static struct ip_tunnel __rcu **__ipgre_bucket(struct ipgre_net *ign,
- struct ip_tunnel_parm *parms)
+static int parse_gre_header(struct sk_buff *skb, struct tnl_ptk_info *tpi,
+ bool *csum_err, int *hdr_len)
{
- __be32 remote = parms->iph.daddr;
- __be32 local = parms->iph.saddr;
- __be32 key = parms->i_key;
- unsigned int h = HASH(key);
- int prio = 0;
-
- if (local)
- prio |= 1;
- if (remote && !ipv4_is_multicast(remote)) {
- prio |= 2;
- h ^= HASH(remote);
- }
+ struct gre_base_hdr *greh = (struct gre_base_hdr *)skb->data;
+ __be32 *options = (__be32 *)(greh + 1);
- return &ign->tunnels[prio][h];
-}
+ if (unlikely(greh->flags & (GRE_VERSION | GRE_ROUTING)))
+ return -EINVAL;
-static inline struct ip_tunnel __rcu **ipgre_bucket(struct ipgre_net *ign,
- struct ip_tunnel *t)
-{
- return __ipgre_bucket(ign, &t->parms);
-}
+ tpi->flags = gre_flags_to_tnl_flags(greh->flags);
+ *hdr_len = ip_gre_calc_hlen(tpi->flags);
-static void ipgre_tunnel_link(struct ipgre_net *ign, struct ip_tunnel *t)
-{
- struct ip_tunnel __rcu **tp = ipgre_bucket(ign, t);
+ if (!pskb_may_pull(skb, *hdr_len))
+ return -EINVAL;
- rcu_assign_pointer(t->next, rtnl_dereference(*tp));
- rcu_assign_pointer(*tp, t);
-}
+ tpi->proto = greh->protocol;
-static void ipgre_tunnel_unlink(struct ipgre_net *ign, struct ip_tunnel *t)
-{
- struct ip_tunnel __rcu **tp;
- struct ip_tunnel *iter;
-
- for (tp = ipgre_bucket(ign, t);
- (iter = rtnl_dereference(*tp)) != NULL;
- tp = &iter->next) {
- if (t == iter) {
- rcu_assign_pointer(*tp, t->next);
- break;
+ if (greh->flags & GRE_CSUM) {
+ if (check_checksum(skb)) {
+ *csum_err = true;
+ return -EINVAL;
}
+ options++;
}
-}
-
-static struct ip_tunnel *ipgre_tunnel_find(struct net *net,
- struct ip_tunnel_parm *parms,
- int type)
-{
- __be32 remote = parms->iph.daddr;
- __be32 local = parms->iph.saddr;
- __be32 key = parms->i_key;
- int link = parms->link;
- struct ip_tunnel *t;
- struct ip_tunnel __rcu **tp;
- struct ipgre_net *ign = net_generic(net, ipgre_net_id);
-
- for (tp = __ipgre_bucket(ign, parms);
- (t = rtnl_dereference(*tp)) != NULL;
- tp = &t->next)
- if (local == t->parms.iph.saddr &&
- remote == t->parms.iph.daddr &&
- key == t->parms.i_key &&
- link == t->parms.link &&
- type == t->dev->type)
- break;
-
- return t;
-}
-
-static struct ip_tunnel *ipgre_tunnel_locate(struct net *net,
- struct ip_tunnel_parm *parms, int create)
-{
- struct ip_tunnel *t, *nt;
- struct net_device *dev;
- char name[IFNAMSIZ];
- struct ipgre_net *ign = net_generic(net, ipgre_net_id);
-
- t = ipgre_tunnel_find(net, parms, ARPHRD_IPGRE);
- if (t || !create)
- return t;
-
- if (parms->name[0])
- strlcpy(name, parms->name, IFNAMSIZ);
- else
- strcpy(name, "gre%d");
-
- dev = alloc_netdev(sizeof(*t), name, ipgre_tunnel_setup);
- if (!dev)
- return NULL;
-
- dev_net_set(dev, net);
-
- nt = netdev_priv(dev);
- nt->parms = *parms;
- dev->rtnl_link_ops = &ipgre_link_ops;
-
- dev->mtu = ipgre_tunnel_bind_dev(dev);
-
- if (register_netdevice(dev) < 0)
- goto failed_free;
-
- /* Can use a lockless transmit, unless we generate output sequences */
- if (!(nt->parms.o_flags & GRE_SEQ))
- dev->features |= NETIF_F_LLTX;
- dev_hold(dev);
- ipgre_tunnel_link(ign, nt);
- return nt;
+ if (greh->flags & GRE_KEY) {
+ tpi->key = *options;
+ options++;
+ } else
+ tpi->key = 0;
-failed_free:
- free_netdev(dev);
- return NULL;
-}
+ if (unlikely(greh->flags & GRE_SEQ)) {
+ tpi->seq = *options;
+ options++;
+ } else
+ tpi->seq = 0;
-static void ipgre_tunnel_uninit(struct net_device *dev)
-{
- struct net *net = dev_net(dev);
- struct ipgre_net *ign = net_generic(net, ipgre_net_id);
+ /* WCCP version 1 and 2 protocol decoding.
+ * - Change protocol to IP
+ * - When dealing with WCCPv2, Skip extra 4 bytes in GRE header
+ */
+ if (greh->flags == 0 && tpi->proto == htons(ETH_P_WCCP)) {
+ tpi->proto = htons(ETH_P_IP);
+ if ((*(u8 *)options & 0xF0) != 0x40) {
+ *hdr_len += 4;
+ if (!pskb_may_pull(skb, *hdr_len))
+ return -EINVAL;
+ }
+ }
- ipgre_tunnel_unlink(ign, netdev_priv(dev));
- dev_put(dev);
+ return 0;
}
-
static void ipgre_err(struct sk_buff *skb, u32 info)
{
-/* All the routers (except for Linux) return only
- 8 bytes of packet payload. It means, that precise relaying of
- ICMP in the real Internet is absolutely infeasible.
+ /* All the routers (except for Linux) return only
+ 8 bytes of packet payload. It means, that precise relaying of
+ ICMP in the real Internet is absolutely infeasible.
- Moreover, Cisco "wise men" put GRE key to the third word
- in GRE header. It makes impossible maintaining even soft state for keyed
- GRE tunnels with enabled checksum. Tell them "thank you".
-
- Well, I wonder, rfc1812 was written by Cisco employee,
- what the hell these idiots break standards established
- by themselves???
- */
+ Moreover, Cisco "wise men" put GRE key to the third word
+ in GRE header. It makes impossible maintaining even soft
+ state for keyed GRE tunnels with enabled checksum. Tell
+ them "thank you".
+ Well, I wonder, rfc1812 was written by Cisco employee,
+ what the hell these idiots break standards established
+ by themselves???
+ */
+ struct net *net = dev_net(skb->dev);
+ struct ip_tunnel_net *itn;
const struct iphdr *iph = (const struct iphdr *)skb->data;
- __be16 *p = (__be16 *)(skb->data+(iph->ihl<<2));
- int grehlen = (iph->ihl<<2) + 4;
const int type = icmp_hdr(skb)->type;
const int code = icmp_hdr(skb)->code;
struct ip_tunnel *t;
- __be16 flags;
- __be32 key = 0;
+ struct tnl_ptk_info tpi;
+ int hdr_len;
+ bool csum_err = false;
- flags = p[0];
- if (flags&(GRE_CSUM|GRE_KEY|GRE_SEQ|GRE_ROUTING|GRE_VERSION)) {
- if (flags&(GRE_VERSION|GRE_ROUTING))
+ if (parse_gre_header(skb, &tpi, &csum_err, &hdr_len)) {
+ if (!csum_err) /* ignore csum errors. */
return;
- if (flags&GRE_KEY) {
- grehlen += 4;
- if (flags&GRE_CSUM)
- grehlen += 4;
- }
}
- /* If only 8 bytes returned, keyed message will be dropped here */
- if (skb_headlen(skb) < grehlen)
- return;
-
- if (flags & GRE_KEY)
- key = *(((__be32 *)p) + (grehlen / 4) - 1);
-
switch (type) {
default:
case ICMP_PARAMETERPROB:
@@ -548,8 +268,13 @@ static void ipgre_err(struct sk_buff *skb, u32 info)
break;
}
- t = ipgre_tunnel_lookup(skb->dev, iph->daddr, iph->saddr,
- flags, key, p[1]);
+ if (tpi.proto == htons(ETH_P_TEB))
+ itn = net_generic(net, gre_tap_net_id);
+ else
+ itn = net_generic(net, ipgre_net_id);
+
+ t = ip_tunnel_lookup(itn, skb->dev->ifindex, tpi.flags,
+ iph->daddr, iph->saddr, tpi.key);
if (t == NULL)
return;
@@ -578,158 +303,33 @@ static void ipgre_err(struct sk_buff *skb, u32 info)
t->err_time = jiffies;
}
-static inline u8
-ipgre_ecn_encapsulate(u8 tos, const struct iphdr *old_iph, struct sk_buff *skb)
-{
- u8 inner = 0;
- if (skb->protocol == htons(ETH_P_IP))
- inner = old_iph->tos;
- else if (skb->protocol == htons(ETH_P_IPV6))
- inner = ipv6_get_dsfield((const struct ipv6hdr *)old_iph);
- return INET_ECN_encapsulate(tos, inner);
-}
-
static int ipgre_rcv(struct sk_buff *skb)
{
+ struct net *net = dev_net(skb->dev);
+ struct ip_tunnel_net *itn;
const struct iphdr *iph;
- u8 *h;
- __be16 flags;
- __sum16 csum = 0;
- __be32 key = 0;
- u32 seqno = 0;
struct ip_tunnel *tunnel;
- int offset = 4;
- __be16 gre_proto;
- int err;
+ struct tnl_ptk_info tpi;
+ int hdr_len;
+ bool csum_err = false;
- if (!pskb_may_pull(skb, 16))
+ if (parse_gre_header(skb, &tpi, &csum_err, &hdr_len) < 0)
goto drop;
- iph = ip_hdr(skb);
- h = skb->data;
- flags = *(__be16 *)h;
-
- if (flags&(GRE_CSUM|GRE_KEY|GRE_ROUTING|GRE_SEQ|GRE_VERSION)) {
- /* - Version must be 0.
- - We do not support routing headers.
- */
- if (flags&(GRE_VERSION|GRE_ROUTING))
- goto drop;
-
- if (flags&GRE_CSUM) {
- switch (skb->ip_summed) {
- case CHECKSUM_COMPLETE:
- csum = csum_fold(skb->csum);
- if (!csum)
- break;
- /* fall through */
- case CHECKSUM_NONE:
- skb->csum = 0;
- csum = __skb_checksum_complete(skb);
- skb->ip_summed = CHECKSUM_COMPLETE;
- }
- offset += 4;
- }
- if (flags&GRE_KEY) {
- key = *(__be32 *)(h + offset);
- offset += 4;
- }
- if (flags&GRE_SEQ) {
- seqno = ntohl(*(__be32 *)(h + offset));
- offset += 4;
- }
- }
+ if (tpi.proto == htons(ETH_P_TEB))
+ itn = net_generic(net, gre_tap_net_id);
+ else
+ itn = net_generic(net, ipgre_net_id);
- gre_proto = *(__be16 *)(h + 2);
+ iph = ip_hdr(skb);
+ tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, tpi.flags,
+ iph->saddr, iph->daddr, tpi.key);
- tunnel = ipgre_tunnel_lookup(skb->dev,
- iph->saddr, iph->daddr, flags, key,
- gre_proto);
if (tunnel) {
- struct pcpu_tstats *tstats;
-
- secpath_reset(skb);
-
- skb->protocol = gre_proto;
- /* WCCP version 1 and 2 protocol decoding.
- * - Change protocol to IP
- * - When dealing with WCCPv2, Skip extra 4 bytes in GRE header
- */
- if (flags == 0 && gre_proto == htons(ETH_P_WCCP)) {
- skb->protocol = htons(ETH_P_IP);
- if ((*(h + offset) & 0xF0) != 0x40)
- offset += 4;
- }
-
- skb->mac_header = skb->network_header;
- __pskb_pull(skb, offset);
- skb_postpull_rcsum(skb, skb_transport_header(skb), offset);
- skb->pkt_type = PACKET_HOST;
-#ifdef CONFIG_NET_IPGRE_BROADCAST
- if (ipv4_is_multicast(iph->daddr)) {
- /* Looped back packet, drop it! */
- if (rt_is_output_route(skb_rtable(skb)))
- goto drop;
- tunnel->dev->stats.multicast++;
- skb->pkt_type = PACKET_BROADCAST;
- }
-#endif
-
- if (((flags&GRE_CSUM) && csum) ||
- (!(flags&GRE_CSUM) && tunnel->parms.i_flags&GRE_CSUM)) {
- tunnel->dev->stats.rx_crc_errors++;
- tunnel->dev->stats.rx_errors++;
- goto drop;
- }
- if (tunnel->parms.i_flags&GRE_SEQ) {
- if (!(flags&GRE_SEQ) ||
- (tunnel->i_seqno && (s32)(seqno - tunnel->i_seqno) < 0)) {
- tunnel->dev->stats.rx_fifo_errors++;
- tunnel->dev->stats.rx_errors++;
- goto drop;
- }
- tunnel->i_seqno = seqno + 1;
- }
-
- /* Warning: All skb pointers will be invalidated! */
- if (tunnel->dev->type == ARPHRD_ETHER) {
- if (!pskb_may_pull(skb, ETH_HLEN)) {
- tunnel->dev->stats.rx_length_errors++;
- tunnel->dev->stats.rx_errors++;
- goto drop;
- }
-
- iph = ip_hdr(skb);
- skb->protocol = eth_type_trans(skb, tunnel->dev);
- skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
- }
-
- __skb_tunnel_rx(skb, tunnel->dev);
-
- skb_reset_network_header(skb);
- err = IP_ECN_decapsulate(iph, skb);
- if (unlikely(err)) {
- if (log_ecn_error)
- net_info_ratelimited("non-ECT from %pI4 with TOS=%#x\n",
- &iph->saddr, iph->tos);
- if (err > 1) {
- ++tunnel->dev->stats.rx_frame_errors;
- ++tunnel->dev->stats.rx_errors;
- goto drop;
- }
- }
-
- tstats = this_cpu_ptr(tunnel->dev->tstats);
- u64_stats_update_begin(&tstats->syncp);
- tstats->rx_packets++;
- tstats->rx_bytes += skb->len;
- u64_stats_update_end(&tstats->syncp);
-
- gro_cells_receive(&tunnel->gro_cells, skb);
+ ip_tunnel_rcv(tunnel, skb, &tpi, log_ecn_error);
return 0;
}
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0);
-
drop:
kfree_skb(skb);
return 0;
@@ -746,7 +346,7 @@ static struct sk_buff *handle_offloads(struct ip_tunnel *tunnel, struct sk_buff
skb_shinfo(skb)->gso_type |= SKB_GSO_GRE;
return skb;
} else if (skb->ip_summed == CHECKSUM_PARTIAL &&
- tunnel->parms.o_flags&GRE_CSUM) {
+ tunnel->parms.o_flags&TUNNEL_CSUM) {
err = skb_checksum_help(skb);
if (unlikely(err))
goto error;
@@ -760,483 +360,157 @@ error:
return ERR_PTR(err);
}
-static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
+static struct sk_buff *gre_build_header(struct sk_buff *skb,
+ const struct tnl_ptk_info *tpi,
+ int hdr_len)
{
- struct ip_tunnel *tunnel = netdev_priv(dev);
- const struct iphdr *old_iph;
- const struct iphdr *tiph;
- struct flowi4 fl4;
- u8 tos;
- __be16 df;
- struct rtable *rt; /* Route to the other host */
- struct net_device *tdev; /* Device to other host */
- struct iphdr *iph; /* Our new IP header */
- unsigned int max_headroom; /* The extra header space needed */
- int gre_hlen;
- __be32 dst;
- int mtu;
- u8 ttl;
- int err;
-
- skb = handle_offloads(tunnel, skb);
- if (IS_ERR(skb)) {
- dev->stats.tx_dropped++;
- return NETDEV_TX_OK;
- }
+ struct gre_base_hdr *greh;
- if (!skb->encapsulation) {
- skb_reset_inner_headers(skb);
- skb->encapsulation = 1;
- }
+ skb_push(skb, hdr_len);
- old_iph = ip_hdr(skb);
+ greh = (struct gre_base_hdr *)skb->data;
+ greh->flags = tnl_flags_to_gre_flags(tpi->flags);
+ greh->protocol = tpi->proto;
- if (dev->type == ARPHRD_ETHER)
- IPCB(skb)->flags = 0;
+ if (tpi->flags&(TUNNEL_KEY|TUNNEL_CSUM|TUNNEL_SEQ)) {
+ __be32 *ptr = (__be32 *)(((u8 *)greh) + hdr_len - 4);
- if (dev->header_ops && dev->type == ARPHRD_IPGRE) {
- gre_hlen = 0;
- if (skb->protocol == htons(ETH_P_IP))
- tiph = (const struct iphdr *)skb->data;
- else
- tiph = &tunnel->parms.iph;
- } else {
- gre_hlen = tunnel->hlen;
- tiph = &tunnel->parms.iph;
- }
-
- if ((dst = tiph->daddr) == 0) {
- /* NBMA tunnel */
-
- if (skb_dst(skb) == NULL) {
- dev->stats.tx_fifo_errors++;
- goto tx_error;
+ if (tpi->flags&TUNNEL_SEQ) {
+ *ptr = tpi->seq;
+ ptr--;
}
-
- if (skb->protocol == htons(ETH_P_IP)) {
- rt = skb_rtable(skb);
- dst = rt_nexthop(rt, old_iph->daddr);
+ if (tpi->flags&TUNNEL_KEY) {
+ *ptr = tpi->key;
+ ptr--;
}
-#if IS_ENABLED(CONFIG_IPV6)
- else if (skb->protocol == htons(ETH_P_IPV6)) {
- const struct in6_addr *addr6;
- struct neighbour *neigh;
- bool do_tx_error_icmp;
- int addr_type;
-
- neigh = dst_neigh_lookup(skb_dst(skb), &ipv6_hdr(skb)->daddr);
- if (neigh == NULL)
- goto tx_error;
-
- addr6 = (const struct in6_addr *)&neigh->primary_key;
- addr_type = ipv6_addr_type(addr6);
-
- if (addr_type == IPV6_ADDR_ANY) {
- addr6 = &ipv6_hdr(skb)->daddr;
- addr_type = ipv6_addr_type(addr6);
- }
-
- if ((addr_type & IPV6_ADDR_COMPATv4) == 0)
- do_tx_error_icmp = true;
- else {
- do_tx_error_icmp = false;
- dst = addr6->s6_addr32[3];
- }
- neigh_release(neigh);
- if (do_tx_error_icmp)
- goto tx_error_icmp;
+ if (tpi->flags&TUNNEL_CSUM &&
+ !(skb_shinfo(skb)->gso_type & SKB_GSO_GRE)) {
+ *(__sum16 *)ptr = 0;
+ *(__sum16 *)ptr = csum_fold(skb_checksum(skb, 0,
+ skb->len, 0));
}
-#endif
- else
- goto tx_error;
}
- ttl = tiph->ttl;
- tos = tiph->tos;
- if (tos & 0x1) {
- tos &= ~0x1;
- if (skb->protocol == htons(ETH_P_IP))
- tos = old_iph->tos;
- else if (skb->protocol == htons(ETH_P_IPV6))
- tos = ipv6_get_dsfield((const struct ipv6hdr *)old_iph);
- }
+ return skb;
+}
- rt = ip_route_output_gre(dev_net(dev), &fl4, dst, tiph->saddr,
- tunnel->parms.o_key, RT_TOS(tos),
- tunnel->parms.link);
- if (IS_ERR(rt)) {
- dev->stats.tx_carrier_errors++;
- goto tx_error;
- }
- tdev = rt->dst.dev;
+static void __gre_xmit(struct sk_buff *skb, struct net_device *dev,
+ const struct iphdr *tnl_params,
+ __be16 proto)
+{
+ struct ip_tunnel *tunnel = netdev_priv(dev);
+ struct tnl_ptk_info tpi;
- if (tdev == dev) {
- ip_rt_put(rt);
- dev->stats.collisions++;
- goto tx_error;
+ if (likely(!skb->encapsulation)) {
+ skb_reset_inner_headers(skb);
+ skb->encapsulation = 1;
}
- df = tiph->frag_off;
- if (df)
- mtu = dst_mtu(&rt->dst) - dev->hard_header_len - tunnel->hlen;
- else
- mtu = skb_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu;
-
- if (skb_dst(skb))
- skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
-
- if (skb->protocol == htons(ETH_P_IP)) {
- df |= (old_iph->frag_off&htons(IP_DF));
+ tpi.flags = tunnel->parms.o_flags;
+ tpi.proto = proto;
+ tpi.key = tunnel->parms.o_key;
+ if (tunnel->parms.o_flags & TUNNEL_SEQ)
+ tunnel->o_seqno++;
+ tpi.seq = htonl(tunnel->o_seqno);
- if (!skb_is_gso(skb) &&
- (old_iph->frag_off&htons(IP_DF)) &&
- mtu < ntohs(old_iph->tot_len)) {
- icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu));
- ip_rt_put(rt);
- goto tx_error;
- }
+ /* Push GRE header. */
+ skb = gre_build_header(skb, &tpi, tunnel->hlen);
+ if (unlikely(!skb)) {
+ dev->stats.tx_dropped++;
+ return;
}
-#if IS_ENABLED(CONFIG_IPV6)
- else if (skb->protocol == htons(ETH_P_IPV6)) {
- struct rt6_info *rt6 = (struct rt6_info *)skb_dst(skb);
-
- if (rt6 && mtu < dst_mtu(skb_dst(skb)) && mtu >= IPV6_MIN_MTU) {
- if ((tunnel->parms.iph.daddr &&
- !ipv4_is_multicast(tunnel->parms.iph.daddr)) ||
- rt6->rt6i_dst.plen == 128) {
- rt6->rt6i_flags |= RTF_MODIFIED;
- dst_metric_set(skb_dst(skb), RTAX_MTU, mtu);
- }
- }
- if (!skb_is_gso(skb) &&
- mtu >= IPV6_MIN_MTU &&
- mtu < skb->len - tunnel->hlen + gre_hlen) {
- icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
- ip_rt_put(rt);
- goto tx_error;
- }
- }
-#endif
+ ip_tunnel_xmit(skb, dev, tnl_params);
+}
- if (tunnel->err_count > 0) {
- if (time_before(jiffies,
- tunnel->err_time + IPTUNNEL_ERR_TIMEO)) {
- tunnel->err_count--;
+static netdev_tx_t ipgre_xmit(struct sk_buff *skb,
+ struct net_device *dev)
+{
+ struct ip_tunnel *tunnel = netdev_priv(dev);
+ const struct iphdr *tnl_params;
- dst_link_failure(skb);
- } else
- tunnel->err_count = 0;
- }
+ skb = handle_offloads(tunnel, skb);
+ if (IS_ERR(skb))
+ goto out;
- max_headroom = LL_RESERVED_SPACE(tdev) + gre_hlen + rt->dst.header_len;
-
- if (skb_headroom(skb) < max_headroom || skb_shared(skb)||
- (skb_cloned(skb) && !skb_clone_writable(skb, 0))) {
- struct sk_buff *new_skb = skb_realloc_headroom(skb, max_headroom);
- if (max_headroom > dev->needed_headroom)
- dev->needed_headroom = max_headroom;
- if (!new_skb) {
- ip_rt_put(rt);
- dev->stats.tx_dropped++;
- dev_kfree_skb(skb);
- return NETDEV_TX_OK;
- }
- if (skb->sk)
- skb_set_owner_w(new_skb, skb->sk);
- dev_kfree_skb(skb);
- skb = new_skb;
- old_iph = ip_hdr(skb);
- /* Warning : tiph value might point to freed memory */
- }
+ if (dev->header_ops) {
+ /* Need space for new headers */
+ if (skb_cow_head(skb, dev->needed_headroom -
+ (tunnel->hlen + sizeof(struct iphdr))));
+ goto free_skb;
- skb_push(skb, gre_hlen);
- skb_reset_network_header(skb);
- skb_set_transport_header(skb, sizeof(*iph));
- memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
- IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED |
- IPSKB_REROUTED);
- skb_dst_drop(skb);
- skb_dst_set(skb, &rt->dst);
-
- /*
- * Push down and install the IPIP header.
- */
+ tnl_params = (const struct iphdr *)skb->data;
- iph = ip_hdr(skb);
- iph->version = 4;
- iph->ihl = sizeof(struct iphdr) >> 2;
- iph->frag_off = df;
- iph->protocol = IPPROTO_GRE;
- iph->tos = ipgre_ecn_encapsulate(tos, old_iph, skb);
- iph->daddr = fl4.daddr;
- iph->saddr = fl4.saddr;
- iph->ttl = ttl;
-
- tunnel_ip_select_ident(skb, old_iph, &rt->dst);
-
- if (ttl == 0) {
- if (skb->protocol == htons(ETH_P_IP))
- iph->ttl = old_iph->ttl;
-#if IS_ENABLED(CONFIG_IPV6)
- else if (skb->protocol == htons(ETH_P_IPV6))
- iph->ttl = ((const struct ipv6hdr *)old_iph)->hop_limit;
-#endif
- else
- iph->ttl = ip4_dst_hoplimit(&rt->dst);
- }
-
- ((__be16 *)(iph + 1))[0] = tunnel->parms.o_flags;
- ((__be16 *)(iph + 1))[1] = (dev->type == ARPHRD_ETHER) ?
- htons(ETH_P_TEB) : skb->protocol;
-
- if (tunnel->parms.o_flags&(GRE_KEY|GRE_CSUM|GRE_SEQ)) {
- __be32 *ptr = (__be32 *)(((u8 *)iph) + tunnel->hlen - 4);
+ /* Pull skb since ip_tunnel_xmit() needs skb->data pointing
+ * to gre header.
+ */
+ skb_pull(skb, tunnel->hlen + sizeof(struct iphdr));
+ } else {
+ if (skb_cow_head(skb, dev->needed_headroom))
+ goto free_skb;
- if (tunnel->parms.o_flags&GRE_SEQ) {
- ++tunnel->o_seqno;
- *ptr = htonl(tunnel->o_seqno);
- ptr--;
- }
- if (tunnel->parms.o_flags&GRE_KEY) {
- *ptr = tunnel->parms.o_key;
- ptr--;
- }
- /* Skip GRE checksum if skb is getting offloaded. */
- if (!(skb_shinfo(skb)->gso_type & SKB_GSO_GRE) &&
- (tunnel->parms.o_flags&GRE_CSUM)) {
- int offset = skb_transport_offset(skb);
-
- if (skb_has_shared_frag(skb)) {
- err = __skb_linearize(skb);
- if (err)
- goto tx_error;
- }
-
- *ptr = 0;
- *(__sum16 *)ptr = csum_fold(skb_checksum(skb, offset,
- skb->len - offset,
- 0));
- }
+ tnl_params = &tunnel->parms.iph;
}
- iptunnel_xmit(skb, dev);
+ __gre_xmit(skb, dev, tnl_params, skb->protocol);
+
return NETDEV_TX_OK;
-#if IS_ENABLED(CONFIG_IPV6)
-tx_error_icmp:
- dst_link_failure(skb);
-#endif
-tx_error:
- dev->stats.tx_errors++;
+free_skb:
dev_kfree_skb(skb);
+out:
+ dev->stats.tx_dropped++;
return NETDEV_TX_OK;
}
-static int ipgre_tunnel_bind_dev(struct net_device *dev)
+static netdev_tx_t gre_tap_xmit(struct sk_buff *skb,
+ struct net_device *dev)
{
- struct net_device *tdev = NULL;
- struct ip_tunnel *tunnel;
- const struct iphdr *iph;
- int hlen = LL_MAX_HEADER;
- int mtu = ETH_DATA_LEN;
- int addend = sizeof(struct iphdr) + 4;
-
- tunnel = netdev_priv(dev);
- iph = &tunnel->parms.iph;
-
- /* Guess output device to choose reasonable mtu and needed_headroom */
-
- if (iph->daddr) {
- struct flowi4 fl4;
- struct rtable *rt;
-
- rt = ip_route_output_gre(dev_net(dev), &fl4,
- iph->daddr, iph->saddr,
- tunnel->parms.o_key,
- RT_TOS(iph->tos),
- tunnel->parms.link);
- if (!IS_ERR(rt)) {
- tdev = rt->dst.dev;
- ip_rt_put(rt);
- }
-
- if (dev->type != ARPHRD_ETHER)
- dev->flags |= IFF_POINTOPOINT;
- }
+ struct ip_tunnel *tunnel = netdev_priv(dev);
- if (!tdev && tunnel->parms.link)
- tdev = __dev_get_by_index(dev_net(dev), tunnel->parms.link);
+ skb = handle_offloads(tunnel, skb);
+ if (IS_ERR(skb))
+ goto out;
- if (tdev) {
- hlen = tdev->hard_header_len + tdev->needed_headroom;
- mtu = tdev->mtu;
- }
- dev->iflink = tunnel->parms.link;
-
- /* Precalculate GRE options length */
- if (tunnel->parms.o_flags&(GRE_CSUM|GRE_KEY|GRE_SEQ)) {
- if (tunnel->parms.o_flags&GRE_CSUM)
- addend += 4;
- if (tunnel->parms.o_flags&GRE_KEY)
- addend += 4;
- if (tunnel->parms.o_flags&GRE_SEQ)
- addend += 4;
- }
- dev->needed_headroom = addend + hlen;
- mtu -= dev->hard_header_len + addend;
+ if (skb_cow_head(skb, dev->needed_headroom))
+ goto free_skb;
- if (mtu < 68)
- mtu = 68;
+ __gre_xmit(skb, dev, &tunnel->parms.iph, htons(ETH_P_TEB));
- tunnel->hlen = addend;
- /* TCP offload with GRE SEQ is not supported. */
- if (!(tunnel->parms.o_flags & GRE_SEQ)) {
- dev->features |= NETIF_F_GSO_SOFTWARE;
- dev->hw_features |= NETIF_F_GSO_SOFTWARE;
- }
+ return NETDEV_TX_OK;
- return mtu;
+free_skb:
+ dev_kfree_skb(skb);
+out:
+ dev->stats.tx_dropped++;
+ return NETDEV_TX_OK;
}
-static int
-ipgre_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd)
+static int ipgre_tunnel_ioctl(struct net_device *dev,
+ struct ifreq *ifr, int cmd)
{
int err = 0;
struct ip_tunnel_parm p;
- struct ip_tunnel *t;
- struct net *net = dev_net(dev);
- struct ipgre_net *ign = net_generic(net, ipgre_net_id);
-
- switch (cmd) {
- case SIOCGETTUNNEL:
- t = NULL;
- if (dev == ign->fb_tunnel_dev) {
- if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) {
- err = -EFAULT;
- break;
- }
- t = ipgre_tunnel_locate(net, &p, 0);
- }
- if (t == NULL)
- t = netdev_priv(dev);
- memcpy(&p, &t->parms, sizeof(p));
- if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p)))
- err = -EFAULT;
- break;
-
- case SIOCADDTUNNEL:
- case SIOCCHGTUNNEL:
- err = -EPERM;
- if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
- goto done;
-
- err = -EFAULT;
- if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p)))
- goto done;
-
- err = -EINVAL;
- if (p.iph.version != 4 || p.iph.protocol != IPPROTO_GRE ||
- p.iph.ihl != 5 || (p.iph.frag_off&htons(~IP_DF)) ||
- ((p.i_flags|p.o_flags)&(GRE_VERSION|GRE_ROUTING)))
- goto done;
- if (p.iph.ttl)
- p.iph.frag_off |= htons(IP_DF);
-
- if (!(p.i_flags&GRE_KEY))
- p.i_key = 0;
- if (!(p.o_flags&GRE_KEY))
- p.o_key = 0;
-
- t = ipgre_tunnel_locate(net, &p, cmd == SIOCADDTUNNEL);
-
- if (dev != ign->fb_tunnel_dev && cmd == SIOCCHGTUNNEL) {
- if (t != NULL) {
- if (t->dev != dev) {
- err = -EEXIST;
- break;
- }
- } else {
- unsigned int nflags = 0;
-
- t = netdev_priv(dev);
-
- if (ipv4_is_multicast(p.iph.daddr))
- nflags = IFF_BROADCAST;
- else if (p.iph.daddr)
- nflags = IFF_POINTOPOINT;
-
- if ((dev->flags^nflags)&(IFF_POINTOPOINT|IFF_BROADCAST)) {
- err = -EINVAL;
- break;
- }
- ipgre_tunnel_unlink(ign, t);
- synchronize_net();
- t->parms.iph.saddr = p.iph.saddr;
- t->parms.iph.daddr = p.iph.daddr;
- t->parms.i_key = p.i_key;
- t->parms.o_key = p.o_key;
- memcpy(dev->dev_addr, &p.iph.saddr, 4);
- memcpy(dev->broadcast, &p.iph.daddr, 4);
- ipgre_tunnel_link(ign, t);
- netdev_state_change(dev);
- }
- }
- if (t) {
- err = 0;
- if (cmd == SIOCCHGTUNNEL) {
- t->parms.iph.ttl = p.iph.ttl;
- t->parms.iph.tos = p.iph.tos;
- t->parms.iph.frag_off = p.iph.frag_off;
- if (t->parms.link != p.link) {
- t->parms.link = p.link;
- dev->mtu = ipgre_tunnel_bind_dev(dev);
- netdev_state_change(dev);
- }
- }
- if (copy_to_user(ifr->ifr_ifru.ifru_data, &t->parms, sizeof(p)))
- err = -EFAULT;
- } else
- err = (cmd == SIOCADDTUNNEL ? -ENOBUFS : -ENOENT);
- break;
-
- case SIOCDELTUNNEL:
- err = -EPERM;
- if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
- goto done;
-
- if (dev == ign->fb_tunnel_dev) {
- err = -EFAULT;
- if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p)))
- goto done;
- err = -ENOENT;
- if ((t = ipgre_tunnel_locate(net, &p, 0)) == NULL)
- goto done;
- err = -EPERM;
- if (t == netdev_priv(ign->fb_tunnel_dev))
- goto done;
- dev = t->dev;
- }
- unregister_netdevice(dev);
- err = 0;
- break;
-
- default:
- err = -EINVAL;
+ if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p)))
+ return -EFAULT;
+ if (p.iph.version != 4 || p.iph.protocol != IPPROTO_GRE ||
+ p.iph.ihl != 5 || (p.iph.frag_off&htons(~IP_DF)) ||
+ ((p.i_flags|p.o_flags)&(GRE_VERSION|GRE_ROUTING))) {
+ return -EINVAL;
}
+ p.i_flags = gre_flags_to_tnl_flags(p.i_flags);
+ p.o_flags = gre_flags_to_tnl_flags(p.o_flags);
-done:
- return err;
-}
+ err = ip_tunnel_ioctl(dev, &p, cmd);
+ if (err)
+ return err;
-static int ipgre_tunnel_change_mtu(struct net_device *dev, int new_mtu)
-{
- struct ip_tunnel *tunnel = netdev_priv(dev);
- if (new_mtu < 68 ||
- new_mtu > 0xFFF8 - dev->hard_header_len - tunnel->hlen)
- return -EINVAL;
- dev->mtu = new_mtu;
+ p.i_flags = tnl_flags_to_gre_flags(p.i_flags);
+ p.o_flags = tnl_flags_to_gre_flags(p.o_flags);
+
+ if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p)))
+ return -EFAULT;
return 0;
}
@@ -1266,25 +540,23 @@ static int ipgre_tunnel_change_mtu(struct net_device *dev, int new_mtu)
...
ftp fec0:6666:6666::193.233.7.65
...
-
*/
-
static int ipgre_header(struct sk_buff *skb, struct net_device *dev,
unsigned short type,
const void *daddr, const void *saddr, unsigned int len)
{
struct ip_tunnel *t = netdev_priv(dev);
- struct iphdr *iph = (struct iphdr *)skb_push(skb, t->hlen);
- __be16 *p = (__be16 *)(iph+1);
+ struct iphdr *iph;
+ struct gre_base_hdr *greh;
- memcpy(iph, &t->parms.iph, sizeof(struct iphdr));
- p[0] = t->parms.o_flags;
- p[1] = htons(type);
+ iph = (struct iphdr *)skb_push(skb, t->hlen + sizeof(*iph));
+ greh = (struct gre_base_hdr *)(iph+1);
+ greh->flags = tnl_flags_to_gre_flags(t->parms.o_flags);
+ greh->protocol = htons(type);
- /*
- * Set the source hardware address.
- */
+ memcpy(iph, &t->parms.iph, sizeof(struct iphdr));
+ /* Set the source hardware address. */
if (saddr)
memcpy(&iph->saddr, saddr, 4);
if (daddr)
@@ -1292,7 +564,7 @@ static int ipgre_header(struct sk_buff *skb, struct net_device *dev,
if (iph->daddr)
return t->hlen;
- return -t->hlen;
+ return -(t->hlen + sizeof(*iph));
}
static int ipgre_header_parse(const struct sk_buff *skb, unsigned char *haddr)
@@ -1346,31 +618,21 @@ static int ipgre_close(struct net_device *dev)
}
return 0;
}
-
#endif
static const struct net_device_ops ipgre_netdev_ops = {
.ndo_init = ipgre_tunnel_init,
- .ndo_uninit = ipgre_tunnel_uninit,
+ .ndo_uninit = ip_tunnel_uninit,
#ifdef CONFIG_NET_IPGRE_BROADCAST
.ndo_open = ipgre_open,
.ndo_stop = ipgre_close,
#endif
- .ndo_start_xmit = ipgre_tunnel_xmit,
+ .ndo_start_xmit = ipgre_xmit,
.ndo_do_ioctl = ipgre_tunnel_ioctl,
- .ndo_change_mtu = ipgre_tunnel_change_mtu,
- .ndo_get_stats64 = ipgre_get_stats64,
+ .ndo_change_mtu = ip_tunnel_change_mtu,
+ .ndo_get_stats64 = ip_tunnel_get_stats64,
};
-static void ipgre_dev_free(struct net_device *dev)
-{
- struct ip_tunnel *tunnel = netdev_priv(dev);
-
- gro_cells_destroy(&tunnel->gro_cells);
- free_percpu(dev->tstats);
- free_netdev(dev);
-}
-
#define GRE_FEATURES (NETIF_F_SG | \
NETIF_F_FRAGLIST | \
NETIF_F_HIGHDMA | \
@@ -1379,35 +641,49 @@ static void ipgre_dev_free(struct net_device *dev)
static void ipgre_tunnel_setup(struct net_device *dev)
{
dev->netdev_ops = &ipgre_netdev_ops;
- dev->destructor = ipgre_dev_free;
+ ip_tunnel_setup(dev, ipgre_net_id);
+}
- dev->type = ARPHRD_IPGRE;
- dev->needed_headroom = LL_MAX_HEADER + sizeof(struct iphdr) + 4;
+static void __gre_tunnel_init(struct net_device *dev)
+{
+ struct ip_tunnel *tunnel;
+
+ tunnel = netdev_priv(dev);
+ tunnel->hlen = ip_gre_calc_hlen(tunnel->parms.o_flags);
+ tunnel->parms.iph.protocol = IPPROTO_GRE;
+
+ dev->needed_headroom = LL_MAX_HEADER + sizeof(struct iphdr) + 4;
dev->mtu = ETH_DATA_LEN - sizeof(struct iphdr) - 4;
- dev->flags = IFF_NOARP;
dev->iflink = 0;
- dev->addr_len = 4;
- dev->features |= NETIF_F_NETNS_LOCAL;
- dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
- dev->features |= GRE_FEATURES;
+ dev->features |= NETIF_F_NETNS_LOCAL | GRE_FEATURES;
dev->hw_features |= GRE_FEATURES;
+
+ if (!(tunnel->parms.o_flags & TUNNEL_SEQ)) {
+ /* TCP offload with GRE SEQ is not supported. */
+ dev->features |= NETIF_F_GSO_SOFTWARE;
+ dev->hw_features |= NETIF_F_GSO_SOFTWARE;
+ /* Can use a lockless transmit, unless we generate
+ * output sequences
+ */
+ dev->features |= NETIF_F_LLTX;
+ }
}
static int ipgre_tunnel_init(struct net_device *dev)
{
- struct ip_tunnel *tunnel;
- struct iphdr *iph;
- int err;
+ struct ip_tunnel *tunnel = netdev_priv(dev);
+ struct iphdr *iph = &tunnel->parms.iph;
- tunnel = netdev_priv(dev);
- iph = &tunnel->parms.iph;
+ __gre_tunnel_init(dev);
- tunnel->dev = dev;
- strcpy(tunnel->parms.name, dev->name);
+ memcpy(dev->dev_addr, &iph->saddr, 4);
+ memcpy(dev->broadcast, &iph->daddr, 4);
- memcpy(dev->dev_addr, &tunnel->parms.iph.saddr, 4);
- memcpy(dev->broadcast, &tunnel->parms.iph.daddr, 4);
+ dev->type = ARPHRD_IPGRE;
+ dev->flags = IFF_NOARP;
+ dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
+ dev->addr_len = 4;
if (iph->daddr) {
#ifdef CONFIG_NET_IPGRE_BROADCAST
@@ -1421,106 +697,30 @@ static int ipgre_tunnel_init(struct net_device *dev)
} else
dev->header_ops = &ipgre_header_ops;
- dev->tstats = alloc_percpu(struct pcpu_tstats);
- if (!dev->tstats)
- return -ENOMEM;
-
- err = gro_cells_init(&tunnel->gro_cells, dev);
- if (err) {
- free_percpu(dev->tstats);
- return err;
- }
-
- return 0;
+ return ip_tunnel_init(dev);
}
-static void ipgre_fb_tunnel_init(struct net_device *dev)
-{
- struct ip_tunnel *tunnel = netdev_priv(dev);
- struct iphdr *iph = &tunnel->parms.iph;
-
- tunnel->dev = dev;
- strcpy(tunnel->parms.name, dev->name);
-
- iph->version = 4;
- iph->protocol = IPPROTO_GRE;
- iph->ihl = 5;
- tunnel->hlen = sizeof(struct iphdr) + 4;
-
- dev_hold(dev);
-}
-
-
static const struct gre_protocol ipgre_protocol = {
.handler = ipgre_rcv,
.err_handler = ipgre_err,
};
-static void ipgre_destroy_tunnels(struct ipgre_net *ign, struct list_head *head)
-{
- int prio;
-
- for (prio = 0; prio < 4; prio++) {
- int h;
- for (h = 0; h < HASH_SIZE; h++) {
- struct ip_tunnel *t;
-
- t = rtnl_dereference(ign->tunnels[prio][h]);
-
- while (t != NULL) {
- unregister_netdevice_queue(t->dev, head);
- t = rtnl_dereference(t->next);
- }
- }
- }
-}
-
static int __net_init ipgre_init_net(struct net *net)
{
- struct ipgre_net *ign = net_generic(net, ipgre_net_id);
- int err;
-
- ign->fb_tunnel_dev = alloc_netdev(sizeof(struct ip_tunnel), "gre0",
- ipgre_tunnel_setup);
- if (!ign->fb_tunnel_dev) {
- err = -ENOMEM;
- goto err_alloc_dev;
- }
- dev_net_set(ign->fb_tunnel_dev, net);
-
- ipgre_fb_tunnel_init(ign->fb_tunnel_dev);
- ign->fb_tunnel_dev->rtnl_link_ops = &ipgre_link_ops;
-
- if ((err = register_netdev(ign->fb_tunnel_dev)))
- goto err_reg_dev;
-
- rcu_assign_pointer(ign->tunnels_wc[0],
- netdev_priv(ign->fb_tunnel_dev));
- return 0;
-
-err_reg_dev:
- ipgre_dev_free(ign->fb_tunnel_dev);
-err_alloc_dev:
- return err;
+ return ip_tunnel_init_net(net, ipgre_net_id, &ipgre_link_ops, NULL);
}
static void __net_exit ipgre_exit_net(struct net *net)
{
- struct ipgre_net *ign;
- LIST_HEAD(list);
-
- ign = net_generic(net, ipgre_net_id);
- rtnl_lock();
- ipgre_destroy_tunnels(ign, &list);
- unregister_netdevice_many(&list);
- rtnl_unlock();
+ struct ip_tunnel_net *itn = net_generic(net, ipgre_net_id);
+ ip_tunnel_delete_net(itn);
}
static struct pernet_operations ipgre_net_ops = {
.init = ipgre_init_net,
.exit = ipgre_exit_net,
.id = &ipgre_net_id,
- .size = sizeof(struct ipgre_net),
+ .size = sizeof(struct ip_tunnel_net),
};
static int ipgre_tunnel_validate(struct nlattr *tb[], struct nlattr *data[])
@@ -1565,8 +765,8 @@ out:
return ipgre_tunnel_validate(tb, data);
}
-static void ipgre_netlink_parms(struct nlattr *data[],
- struct ip_tunnel_parm *parms)
+static void ipgre_netlink_parms(struct nlattr *data[], struct nlattr *tb[],
+ struct ip_tunnel_parm *parms)
{
memset(parms, 0, sizeof(*parms));
@@ -1579,10 +779,10 @@ static void ipgre_netlink_parms(struct nlattr *data[],
parms->link = nla_get_u32(data[IFLA_GRE_LINK]);
if (data[IFLA_GRE_IFLAGS])
- parms->i_flags = nla_get_be16(data[IFLA_GRE_IFLAGS]);
+ parms->i_flags = gre_flags_to_tnl_flags(nla_get_be16(data[IFLA_GRE_IFLAGS]));
if (data[IFLA_GRE_OFLAGS])
- parms->o_flags = nla_get_be16(data[IFLA_GRE_OFLAGS]);
+ parms->o_flags = gre_flags_to_tnl_flags(nla_get_be16(data[IFLA_GRE_OFLAGS]));
if (data[IFLA_GRE_IKEY])
parms->i_key = nla_get_be32(data[IFLA_GRE_IKEY]);
@@ -1606,148 +806,46 @@ static void ipgre_netlink_parms(struct nlattr *data[],
parms->iph.frag_off = htons(IP_DF);
}
-static int ipgre_tap_init(struct net_device *dev)
+static int gre_tap_init(struct net_device *dev)
{
- struct ip_tunnel *tunnel;
-
- tunnel = netdev_priv(dev);
-
- tunnel->dev = dev;
- strcpy(tunnel->parms.name, dev->name);
-
- ipgre_tunnel_bind_dev(dev);
+ __gre_tunnel_init(dev);
- dev->tstats = alloc_percpu(struct pcpu_tstats);
- if (!dev->tstats)
- return -ENOMEM;
-
- return 0;
+ return ip_tunnel_init(dev);
}
-static const struct net_device_ops ipgre_tap_netdev_ops = {
- .ndo_init = ipgre_tap_init,
- .ndo_uninit = ipgre_tunnel_uninit,
- .ndo_start_xmit = ipgre_tunnel_xmit,
+static const struct net_device_ops gre_tap_netdev_ops = {
+ .ndo_init = gre_tap_init,
+ .ndo_uninit = ip_tunnel_uninit,
+ .ndo_start_xmit = gre_tap_xmit,
.ndo_set_mac_address = eth_mac_addr,
.ndo_validate_addr = eth_validate_addr,
- .ndo_change_mtu = ipgre_tunnel_change_mtu,
- .ndo_get_stats64 = ipgre_get_stats64,
+ .ndo_change_mtu = ip_tunnel_change_mtu,
+ .ndo_get_stats64 = ip_tunnel_get_stats64,
};
static void ipgre_tap_setup(struct net_device *dev)
{
-
ether_setup(dev);
-
- dev->netdev_ops = &ipgre_tap_netdev_ops;
- dev->destructor = ipgre_dev_free;
-
- dev->iflink = 0;
- dev->features |= NETIF_F_NETNS_LOCAL;
-
- dev->features |= GRE_FEATURES;
- dev->hw_features |= GRE_FEATURES;
+ dev->netdev_ops = &gre_tap_netdev_ops;
+ ip_tunnel_setup(dev, gre_tap_net_id);
}
-static int ipgre_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[],
- struct nlattr *data[])
+static int ipgre_newlink(struct net *src_net, struct net_device *dev,
+ struct nlattr *tb[], struct nlattr *data[])
{
- struct ip_tunnel *nt;
- struct net *net = dev_net(dev);
- struct ipgre_net *ign = net_generic(net, ipgre_net_id);
- int mtu;
- int err;
-
- nt = netdev_priv(dev);
- ipgre_netlink_parms(data, &nt->parms);
-
- if (ipgre_tunnel_find(net, &nt->parms, dev->type))
- return -EEXIST;
-
- if (dev->type == ARPHRD_ETHER && !tb[IFLA_ADDRESS])
- eth_hw_addr_random(dev);
-
- mtu = ipgre_tunnel_bind_dev(dev);
- if (!tb[IFLA_MTU])
- dev->mtu = mtu;
-
- /* Can use a lockless transmit, unless we generate output sequences */
- if (!(nt->parms.o_flags & GRE_SEQ))
- dev->features |= NETIF_F_LLTX;
-
- err = register_netdevice(dev);
- if (err)
- goto out;
-
- dev_hold(dev);
- ipgre_tunnel_link(ign, nt);
+ struct ip_tunnel_parm p;
-out:
- return err;
+ ipgre_netlink_parms(data, tb, &p);
+ return ip_tunnel_newlink(dev, tb, &p);
}
static int ipgre_changelink(struct net_device *dev, struct nlattr *tb[],
struct nlattr *data[])
{
- struct ip_tunnel *t, *nt;
- struct net *net = dev_net(dev);
- struct ipgre_net *ign = net_generic(net, ipgre_net_id);
struct ip_tunnel_parm p;
- int mtu;
-
- if (dev == ign->fb_tunnel_dev)
- return -EINVAL;
-
- nt = netdev_priv(dev);
- ipgre_netlink_parms(data, &p);
-
- t = ipgre_tunnel_locate(net, &p, 0);
-
- if (t) {
- if (t->dev != dev)
- return -EEXIST;
- } else {
- t = nt;
-
- if (dev->type != ARPHRD_ETHER) {
- unsigned int nflags = 0;
-
- if (ipv4_is_multicast(p.iph.daddr))
- nflags = IFF_BROADCAST;
- else if (p.iph.daddr)
- nflags = IFF_POINTOPOINT;
-
- if ((dev->flags ^ nflags) &
- (IFF_POINTOPOINT | IFF_BROADCAST))
- return -EINVAL;
- }
- ipgre_tunnel_unlink(ign, t);
- t->parms.iph.saddr = p.iph.saddr;
- t->parms.iph.daddr = p.iph.daddr;
- t->parms.i_key = p.i_key;
- if (dev->type != ARPHRD_ETHER) {
- memcpy(dev->dev_addr, &p.iph.saddr, 4);
- memcpy(dev->broadcast, &p.iph.daddr, 4);
- }
- ipgre_tunnel_link(ign, t);
- netdev_state_change(dev);
- }
-
- t->parms.o_key = p.o_key;
- t->parms.iph.ttl = p.iph.ttl;
- t->parms.iph.tos = p.iph.tos;
- t->parms.iph.frag_off = p.iph.frag_off;
-
- if (t->parms.link != p.link) {
- t->parms.link = p.link;
- mtu = ipgre_tunnel_bind_dev(dev);
- if (!tb[IFLA_MTU])
- dev->mtu = mtu;
- netdev_state_change(dev);
- }
-
- return 0;
+ ipgre_netlink_parms(data, tb, &p);
+ return ip_tunnel_changelink(dev, tb, &p);
}
static size_t ipgre_get_size(const struct net_device *dev)
@@ -1782,8 +880,8 @@ static int ipgre_fill_info(struct sk_buff *skb, const struct net_device *dev)
struct ip_tunnel_parm *p = &t->parms;
if (nla_put_u32(skb, IFLA_GRE_LINK, p->link) ||
- nla_put_be16(skb, IFLA_GRE_IFLAGS, p->i_flags) ||
- nla_put_be16(skb, IFLA_GRE_OFLAGS, p->o_flags) ||
+ nla_put_be16(skb, IFLA_GRE_IFLAGS, tnl_flags_to_gre_flags(p->i_flags)) ||
+ nla_put_be16(skb, IFLA_GRE_OFLAGS, tnl_flags_to_gre_flags(p->o_flags)) ||
nla_put_be32(skb, IFLA_GRE_IKEY, p->i_key) ||
nla_put_be32(skb, IFLA_GRE_OKEY, p->o_key) ||
nla_put_be32(skb, IFLA_GRE_LOCAL, p->iph.saddr) ||
@@ -1821,6 +919,7 @@ static struct rtnl_link_ops ipgre_link_ops __read_mostly = {
.validate = ipgre_tunnel_validate,
.newlink = ipgre_newlink,
.changelink = ipgre_changelink,
+ .dellink = ip_tunnel_dellink,
.get_size = ipgre_get_size,
.fill_info = ipgre_fill_info,
};
@@ -1834,13 +933,28 @@ static struct rtnl_link_ops ipgre_tap_ops __read_mostly = {
.validate = ipgre_tap_validate,
.newlink = ipgre_newlink,
.changelink = ipgre_changelink,
+ .dellink = ip_tunnel_dellink,
.get_size = ipgre_get_size,
.fill_info = ipgre_fill_info,
};
-/*
- * And now the modules code and kernel interface.
- */
+static int __net_init ipgre_tap_init_net(struct net *net)
+{
+ return ip_tunnel_init_net(net, gre_tap_net_id, &ipgre_tap_ops, NULL);
+}
+
+static void __net_exit ipgre_tap_exit_net(struct net *net)
+{
+ struct ip_tunnel_net *itn = net_generic(net, gre_tap_net_id);
+ ip_tunnel_delete_net(itn);
+}
+
+static struct pernet_operations ipgre_tap_net_ops = {
+ .init = ipgre_tap_init_net,
+ .exit = ipgre_tap_exit_net,
+ .id = &gre_tap_net_id,
+ .size = sizeof(struct ip_tunnel_net),
+};
static int __init ipgre_init(void)
{
@@ -1852,6 +966,10 @@ static int __init ipgre_init(void)
if (err < 0)
return err;
+ err = register_pernet_device(&ipgre_tap_net_ops);
+ if (err < 0)
+ goto pnet_tap_faied;
+
err = gre_add_protocol(&ipgre_protocol, GREPROTO_CISCO);
if (err < 0) {
pr_info("%s: can't add protocol\n", __func__);
@@ -1866,16 +984,17 @@ static int __init ipgre_init(void)
if (err < 0)
goto tap_ops_failed;
-out:
- return err;
+ return 0;
tap_ops_failed:
rtnl_link_unregister(&ipgre_link_ops);
rtnl_link_failed:
gre_del_protocol(&ipgre_protocol, GREPROTO_CISCO);
add_proto_failed:
+ unregister_pernet_device(&ipgre_tap_net_ops);
+pnet_tap_faied:
unregister_pernet_device(&ipgre_net_ops);
- goto out;
+ return err;
}
static void __exit ipgre_fini(void)
@@ -1884,6 +1003,7 @@ static void __exit ipgre_fini(void)
rtnl_link_unregister(&ipgre_link_ops);
if (gre_del_protocol(&ipgre_protocol, GREPROTO_CISCO) < 0)
pr_info("%s: can't remove protocol\n", __func__);
+ unregister_pernet_device(&ipgre_tap_net_ops);
unregister_pernet_device(&ipgre_net_ops);
}
@@ -1893,3 +1013,4 @@ MODULE_LICENSE("GPL");
MODULE_ALIAS_RTNL_LINK("gre");
MODULE_ALIAS_RTNL_LINK("gretap");
MODULE_ALIAS_NETDEV("gre0");
+MODULE_ALIAS_NETDEV("gretap0");
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
new file mode 100644
index 0000000..dc1d19d
--- /dev/null
+++ b/net/ipv4/ip_tunnel.c
@@ -0,0 +1,1035 @@
+/*
+ * Copyright (c) 2013 Nicira, Inc.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/capability.h>
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+#include <linux/skbuff.h>
+#include <linux/netdevice.h>
+#include <linux/in.h>
+#include <linux/tcp.h>
+#include <linux/udp.h>
+#include <linux/if_arp.h>
+#include <linux/mroute.h>
+#include <linux/init.h>
+#include <linux/in6.h>
+#include <linux/inetdevice.h>
+#include <linux/igmp.h>
+#include <linux/netfilter_ipv4.h>
+#include <linux/etherdevice.h>
+#include <linux/if_ether.h>
+#include <linux/if_vlan.h>
+#include <linux/rculist.h>
+
+#include <net/sock.h>
+#include <net/ip.h>
+#include <net/icmp.h>
+#include <net/protocol.h>
+#include <net/ip_tunnels.h>
+#include <net/arp.h>
+#include <net/checksum.h>
+#include <net/dsfield.h>
+#include <net/inet_ecn.h>
+#include <net/xfrm.h>
+#include <net/net_namespace.h>
+#include <net/netns/generic.h>
+#include <net/rtnetlink.h>
+
+#if IS_ENABLED(CONFIG_IPV6)
+#include <net/ipv6.h>
+#include <net/ip6_fib.h>
+#include <net/ip6_route.h>
+#endif
+
+static unsigned int ip_tunnel_hash(struct ip_tunnel_net *itn,
+ __be32 key, __be32 remote)
+{
+ return hash_32((__force u32)key ^ (__force u32)remote,
+ IP_TNL_HASH_BITS);
+}
+
+/* Often modified stats are per cpu, other are shared (netdev->stats) */
+struct rtnl_link_stats64 *ip_tunnel_get_stats64(struct net_device *dev,
+ struct rtnl_link_stats64 *tot)
+{
+ int i;
+
+ for_each_possible_cpu(i) {
+ const struct pcpu_tstats *tstats = per_cpu_ptr(dev->tstats, i);
+ u64 rx_packets, rx_bytes, tx_packets, tx_bytes;
+ unsigned int start;
+
+ do {
+ start = u64_stats_fetch_begin_bh(&tstats->syncp);
+ rx_packets = tstats->rx_packets;
+ tx_packets = tstats->tx_packets;
+ rx_bytes = tstats->rx_bytes;
+ tx_bytes = tstats->tx_bytes;
+ } while (u64_stats_fetch_retry_bh(&tstats->syncp, start));
+
+ tot->rx_packets += rx_packets;
+ tot->tx_packets += tx_packets;
+ tot->rx_bytes += rx_bytes;
+ tot->tx_bytes += tx_bytes;
+ }
+
+ tot->multicast = dev->stats.multicast;
+
+ tot->rx_crc_errors = dev->stats.rx_crc_errors;
+ tot->rx_fifo_errors = dev->stats.rx_fifo_errors;
+ tot->rx_length_errors = dev->stats.rx_length_errors;
+ tot->rx_frame_errors = dev->stats.rx_frame_errors;
+ tot->rx_errors = dev->stats.rx_errors;
+
+ tot->tx_fifo_errors = dev->stats.tx_fifo_errors;
+ tot->tx_carrier_errors = dev->stats.tx_carrier_errors;
+ tot->tx_dropped = dev->stats.tx_dropped;
+ tot->tx_aborted_errors = dev->stats.tx_aborted_errors;
+ tot->tx_errors = dev->stats.tx_errors;
+
+ tot->collisions = dev->stats.collisions;
+
+ return tot;
+}
+EXPORT_SYMBOL_GPL(ip_tunnel_get_stats64);
+
+static bool ip_tunnel_key_match(const struct ip_tunnel_parm *p,
+ __be16 flags, __be32 key)
+{
+ if (p->i_flags & TUNNEL_KEY) {
+ if (flags & TUNNEL_KEY)
+ return key == p->i_key;
+ else
+ /* key expected, none present */
+ return false;
+ } else
+ return !(flags & TUNNEL_KEY);
+}
+
+/* Fallback tunnel: no source, no destination, no key, no options
+
+ Tunnel hash table:
+ We require exact key match i.e. if a key is present in packet
+ it will match only tunnel with the same key; if it is not present,
+ it will match only keyless tunnel.
+
+ All keysless packets, if not matched configured keyless tunnels
+ will match fallback tunnel.
+ Given src, dst and key, find appropriate for input tunnel.
+*/
+struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn,
+ int link, __be16 flags,
+ __be32 remote, __be32 local,
+ __be32 key)
+{
+ unsigned int hash;
+ struct ip_tunnel *t, *cand = NULL;
+ struct hlist_head *head;
+
+ hash = ip_tunnel_hash(itn, key, remote);
+ head = &itn->tunnels[hash];
+
+ hlist_for_each_entry_rcu(t, head, hash_node) {
+ if (local != t->parms.iph.saddr ||
+ remote != t->parms.iph.daddr ||
+ !(t->dev->flags & IFF_UP))
+ continue;
+
+ if (!ip_tunnel_key_match(&t->parms, flags, key))
+ continue;
+
+ if (t->parms.link == link)
+ return t;
+ else
+ cand = t;
+ }
+
+ hlist_for_each_entry_rcu(t, head, hash_node) {
+ if (remote != t->parms.iph.daddr ||
+ !(t->dev->flags & IFF_UP))
+ continue;
+
+ if (!ip_tunnel_key_match(&t->parms, flags, key))
+ continue;
+
+ if (t->parms.link == link)
+ return t;
+ else if (!cand)
+ cand = t;
+ }
+
+ hash = ip_tunnel_hash(itn, key, 0);
+ head = &itn->tunnels[hash];
+
+ hlist_for_each_entry_rcu(t, head, hash_node) {
+ if ((local != t->parms.iph.saddr &&
+ (local != t->parms.iph.daddr ||
+ !ipv4_is_multicast(local))) ||
+ !(t->dev->flags & IFF_UP))
+ continue;
+
+ if (!ip_tunnel_key_match(&t->parms, flags, key))
+ continue;
+
+ if (t->parms.link == link)
+ return t;
+ else if (!cand)
+ cand = t;
+ }
+
+ if (flags & TUNNEL_NO_KEY)
+ goto skip_key_lookup;
+
+ hlist_for_each_entry_rcu(t, head, hash_node) {
+ if (t->parms.i_key != key ||
+ !(t->dev->flags & IFF_UP))
+ continue;
+
+ if (t->parms.link == link)
+ return t;
+ else if (!cand)
+ cand = t;
+ }
+
+skip_key_lookup:
+ if (cand)
+ return cand;
+
+ if (itn->fb_tunnel_dev && itn->fb_tunnel_dev->flags & IFF_UP)
+ return netdev_priv(itn->fb_tunnel_dev);
+
+
+ return NULL;
+}
+EXPORT_SYMBOL_GPL(ip_tunnel_lookup);
+
+static struct hlist_head *ip_bucket(struct ip_tunnel_net *itn,
+ struct ip_tunnel_parm *parms)
+{
+ unsigned int h;
+ __be32 remote;
+
+ if (parms->iph.daddr && !ipv4_is_multicast(parms->iph.daddr))
+ remote = parms->iph.daddr;
+ else
+ remote = 0;
+
+ h = ip_tunnel_hash(itn, parms->i_key, remote);
+ return &itn->tunnels[h];
+}
+
+static void ip_tunnel_add(struct ip_tunnel_net *itn, struct ip_tunnel *t)
+{
+ struct hlist_head *head = ip_bucket(itn, &t->parms);
+
+ hlist_add_head_rcu(&t->hash_node, head);
+}
+
+static void ip_tunnel_del(struct ip_tunnel_net *itn, struct ip_tunnel *t)
+{
+ hlist_del_init_rcu(&t->hash_node);
+}
+
+static struct ip_tunnel *ip_tunnel_find(struct ip_tunnel_net *itn,
+ struct ip_tunnel_parm *parms,
+ int type)
+{
+ __be32 remote = parms->iph.daddr;
+ __be32 local = parms->iph.saddr;
+ __be32 key = parms->i_key;
+ int link = parms->link;
+ struct ip_tunnel *t = NULL;
+ struct hlist_head *head = ip_bucket(itn, parms);
+
+ hlist_for_each_entry_rcu(t, head, hash_node) {
+ if (local == t->parms.iph.saddr &&
+ remote == t->parms.iph.daddr &&
+ key == t->parms.i_key &&
+ link == t->parms.link &&
+ type == t->dev->type)
+ break;
+ }
+ return t;
+}
+
+static struct net_device *__ip_tunnel_create(struct net *net,
+ const struct rtnl_link_ops *ops,
+ struct ip_tunnel_parm *parms)
+{
+ int err;
+ struct ip_tunnel *tunnel;
+ struct net_device *dev;
+ char name[IFNAMSIZ];
+
+ if (parms->name[0])
+ strlcpy(name, parms->name, IFNAMSIZ);
+ else {
+ if (strlen(ops->kind) + 3 >= IFNAMSIZ) {
+ err = -E2BIG;
+ goto failed;
+ }
+ strlcpy(name, ops->kind, IFNAMSIZ);
+ strncat(name, "%d", 2);
+ }
+
+ ASSERT_RTNL();
+ dev = alloc_netdev(ops->priv_size, name, ops->setup);
+ if (!dev) {
+ err = -ENOMEM;
+ goto failed;
+ }
+ dev_net_set(dev, net);
+
+ dev->rtnl_link_ops = ops;
+
+ tunnel = netdev_priv(dev);
+ tunnel->parms = *parms;
+
+ err = register_netdevice(dev);
+ if (err)
+ goto failed_free;
+
+ return dev;
+
+failed_free:
+ free_netdev(dev);
+failed:
+ return ERR_PTR(err);
+}
+
+static inline struct rtable *ip_route_output_tunnel(struct net *net,
+ struct flowi4 *fl4,
+ int proto,
+ __be32 daddr, __be32 saddr,
+ __be32 key, __u8 tos, int oif)
+{
+ memset(fl4, 0, sizeof(*fl4));
+ fl4->flowi4_oif = oif;
+ fl4->daddr = daddr;
+ fl4->saddr = saddr;
+ fl4->flowi4_tos = tos;
+ fl4->flowi4_proto = proto;
+ fl4->fl4_gre_key = key;
+ return ip_route_output_key(net, fl4);
+}
+
+static int ip_tunnel_bind_dev(struct net_device *dev)
+{
+ struct net_device *tdev = NULL;
+ struct ip_tunnel *tunnel = netdev_priv(dev);
+ const struct iphdr *iph;
+ int hlen = LL_MAX_HEADER;
+ int mtu = ETH_DATA_LEN;
+ int t_hlen = tunnel->hlen + sizeof(struct iphdr);
+
+ iph = &tunnel->parms.iph;
+
+ /* Guess output device to choose reasonable mtu and needed_headroom */
+ if (iph->daddr) {
+ struct flowi4 fl4;
+ struct rtable *rt;
+
+ rt = ip_route_output_tunnel(dev_net(dev), &fl4,
+ tunnel->parms.iph.protocol,
+ iph->daddr, iph->saddr,
+ tunnel->parms.o_key,
+ RT_TOS(iph->tos),
+ tunnel->parms.link);
+ if (!IS_ERR(rt)) {
+ tdev = rt->dst.dev;
+ ip_rt_put(rt);
+ }
+ if (dev->type != ARPHRD_ETHER)
+ dev->flags |= IFF_POINTOPOINT;
+ }
+
+ if (!tdev && tunnel->parms.link)
+ tdev = __dev_get_by_index(dev_net(dev), tunnel->parms.link);
+
+ if (tdev) {
+ hlen = tdev->hard_header_len + tdev->needed_headroom;
+ mtu = tdev->mtu;
+ }
+ dev->iflink = tunnel->parms.link;
+
+ dev->needed_headroom = t_hlen + hlen;
+ mtu -= (dev->hard_header_len + t_hlen);
+
+ if (mtu < 68)
+ mtu = 68;
+
+ return mtu;
+}
+
+static struct ip_tunnel *ip_tunnel_create(struct net *net,
+ struct ip_tunnel_net *itn,
+ struct ip_tunnel_parm *parms)
+{
+ struct ip_tunnel *nt, *fbt;
+ struct net_device *dev;
+
+ BUG_ON(!itn->fb_tunnel_dev);
+ fbt = netdev_priv(itn->fb_tunnel_dev);
+ dev = __ip_tunnel_create(net, itn->fb_tunnel_dev->rtnl_link_ops, parms);
+ if (IS_ERR(dev))
+ return NULL;
+
+ dev->mtu = ip_tunnel_bind_dev(dev);
+
+ nt = netdev_priv(dev);
+ ip_tunnel_add(itn, nt);
+ return nt;
+}
+
+int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb,
+ const struct tnl_ptk_info *tpi, bool log_ecn_error)
+{
+ struct pcpu_tstats *tstats;
+ const struct iphdr *iph = ip_hdr(skb);
+ int err;
+
+ secpath_reset(skb);
+
+ skb->protocol = tpi->proto;
+
+ skb->mac_header = skb->network_header;
+ __pskb_pull(skb, tunnel->hlen);
+ skb_postpull_rcsum(skb, skb_transport_header(skb), tunnel->hlen);
+#ifdef CONFIG_NET_IPGRE_BROADCAST
+ if (ipv4_is_multicast(iph->daddr)) {
+ /* Looped back packet, drop it! */
+ if (rt_is_output_route(skb_rtable(skb)))
+ goto drop;
+ tunnel->dev->stats.multicast++;
+ skb->pkt_type = PACKET_BROADCAST;
+ }
+#endif
+
+ if ((!(tpi->flags&TUNNEL_CSUM) && (tunnel->parms.i_flags&TUNNEL_CSUM)) ||
+ ((tpi->flags&TUNNEL_CSUM) && !(tunnel->parms.i_flags&TUNNEL_CSUM))) {
+ tunnel->dev->stats.rx_crc_errors++;
+ tunnel->dev->stats.rx_errors++;
+ goto drop;
+ }
+
+ if (tunnel->parms.i_flags&TUNNEL_SEQ) {
+ if (!(tpi->flags&TUNNEL_SEQ) ||
+ (tunnel->i_seqno && (s32)(ntohl(tpi->seq) - tunnel->i_seqno) < 0)) {
+ tunnel->dev->stats.rx_fifo_errors++;
+ tunnel->dev->stats.rx_errors++;
+ goto drop;
+ }
+ tunnel->i_seqno = ntohl(tpi->seq) + 1;
+ }
+
+ /* Warning: All skb pointers will be invalidated! */
+ if (tunnel->dev->type == ARPHRD_ETHER) {
+ if (!pskb_may_pull(skb, ETH_HLEN)) {
+ tunnel->dev->stats.rx_length_errors++;
+ tunnel->dev->stats.rx_errors++;
+ goto drop;
+ }
+
+ iph = ip_hdr(skb);
+ skb->protocol = eth_type_trans(skb, tunnel->dev);
+ skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
+ }
+
+ skb->pkt_type = PACKET_HOST;
+ __skb_tunnel_rx(skb, tunnel->dev);
+
+ skb_reset_network_header(skb);
+ err = IP_ECN_decapsulate(iph, skb);
+ if (unlikely(err)) {
+ if (log_ecn_error)
+ net_info_ratelimited("non-ECT from %pI4 with TOS=%#x\n",
+ &iph->saddr, iph->tos);
+ if (err > 1) {
+ ++tunnel->dev->stats.rx_frame_errors;
+ ++tunnel->dev->stats.rx_errors;
+ goto drop;
+ }
+ }
+
+ tstats = this_cpu_ptr(tunnel->dev->tstats);
+ u64_stats_update_begin(&tstats->syncp);
+ tstats->rx_packets++;
+ tstats->rx_bytes += skb->len;
+ u64_stats_update_end(&tstats->syncp);
+
+ gro_cells_receive(&tunnel->gro_cells, skb);
+
+ return 0;
+
+drop:
+ kfree_skb(skb);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(ip_tunnel_rcv);
+
+void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
+ const struct iphdr *tnl_params)
+{
+ struct ip_tunnel *tunnel = netdev_priv(dev);
+ const struct iphdr *inner_iph;
+ struct iphdr *iph;
+ struct flowi4 fl4;
+ u8 tos, ttl;
+ __be16 df;
+ struct rtable *rt; /* Route to the other host */
+ struct net_device *tdev; /* Device to other host */
+ unsigned int max_headroom; /* The extra header space needed */
+ __be32 dst;
+ int mtu;
+
+ inner_iph = (const struct iphdr *)skb_inner_network_header(skb);
+
+ dst = tnl_params->daddr;
+ if (dst == 0) {
+ /* NBMA tunnel */
+
+ if (skb_dst(skb) == NULL) {
+ dev->stats.tx_fifo_errors++;
+ goto tx_error;
+ }
+
+ if (skb->protocol == htons(ETH_P_IP)) {
+ rt = skb_rtable(skb);
+ dst = rt_nexthop(rt, inner_iph->daddr);
+ }
+#if IS_ENABLED(CONFIG_IPV6)
+ else if (skb->protocol == htons(ETH_P_IPV6)) {
+ const struct in6_addr *addr6;
+ struct neighbour *neigh;
+ bool do_tx_error_icmp;
+ int addr_type;
+
+ neigh = dst_neigh_lookup(skb_dst(skb),
+ &ipv6_hdr(skb)->daddr);
+ if (neigh == NULL)
+ goto tx_error;
+
+ addr6 = (const struct in6_addr *)&neigh->primary_key;
+ addr_type = ipv6_addr_type(addr6);
+
+ if (addr_type == IPV6_ADDR_ANY) {
+ addr6 = &ipv6_hdr(skb)->daddr;
+ addr_type = ipv6_addr_type(addr6);
+ }
+
+ if ((addr_type & IPV6_ADDR_COMPATv4) == 0)
+ do_tx_error_icmp = true;
+ else {
+ do_tx_error_icmp = false;
+ dst = addr6->s6_addr32[3];
+ }
+ neigh_release(neigh);
+ if (do_tx_error_icmp)
+ goto tx_error_icmp;
+ }
+#endif
+ else
+ goto tx_error;
+ }
+
+ tos = tnl_params->tos;
+ if (tos & 0x1) {
+ tos &= ~0x1;
+ if (skb->protocol == htons(ETH_P_IP))
+ tos = inner_iph->tos;
+ else if (skb->protocol == htons(ETH_P_IPV6))
+ tos = ipv6_get_dsfield((const struct ipv6hdr *)inner_iph);
+ }
+
+ rt = ip_route_output_tunnel(dev_net(dev), &fl4,
+ tunnel->parms.iph.protocol,
+ dst, tnl_params->saddr,
+ tunnel->parms.o_key,
+ RT_TOS(tos),
+ tunnel->parms.link);
+ if (IS_ERR(rt)) {
+ dev->stats.tx_carrier_errors++;
+ goto tx_error;
+ }
+ tdev = rt->dst.dev;
+
+ if (tdev == dev) {
+ ip_rt_put(rt);
+ dev->stats.collisions++;
+ goto tx_error;
+ }
+
+ df = tnl_params->frag_off;
+
+ if (df)
+ mtu = dst_mtu(&rt->dst) - dev->hard_header_len
+ - sizeof(struct iphdr);
+ else
+ mtu = skb_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu;
+
+ if (skb_dst(skb))
+ skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
+
+ if (skb->protocol == htons(ETH_P_IP)) {
+ df |= (inner_iph->frag_off&htons(IP_DF));
+
+ if (!skb_is_gso(skb) &&
+ (inner_iph->frag_off&htons(IP_DF)) &&
+ mtu < ntohs(inner_iph->tot_len)) {
+ icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu));
+ ip_rt_put(rt);
+ goto tx_error;
+ }
+ }
+#if IS_ENABLED(CONFIG_IPV6)
+ else if (skb->protocol == htons(ETH_P_IPV6)) {
+ struct rt6_info *rt6 = (struct rt6_info *)skb_dst(skb);
+
+ if (rt6 && mtu < dst_mtu(skb_dst(skb)) &&
+ mtu >= IPV6_MIN_MTU) {
+ if ((tunnel->parms.iph.daddr &&
+ !ipv4_is_multicast(tunnel->parms.iph.daddr)) ||
+ rt6->rt6i_dst.plen == 128) {
+ rt6->rt6i_flags |= RTF_MODIFIED;
+ dst_metric_set(skb_dst(skb), RTAX_MTU, mtu);
+ }
+ }
+
+ if (!skb_is_gso(skb) && mtu >= IPV6_MIN_MTU &&
+ mtu < skb->len) {
+ icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
+ ip_rt_put(rt);
+ goto tx_error;
+ }
+ }
+#endif
+
+ if (tunnel->err_count > 0) {
+ if (time_before(jiffies,
+ tunnel->err_time + IPTUNNEL_ERR_TIMEO)) {
+ tunnel->err_count--;
+
+ dst_link_failure(skb);
+ } else
+ tunnel->err_count = 0;
+ }
+
+ ttl = tnl_params->ttl;
+ if (ttl == 0) {
+ if (skb->protocol == htons(ETH_P_IP))
+ ttl = inner_iph->ttl;
+#if IS_ENABLED(CONFIG_IPV6)
+ else if (skb->protocol == htons(ETH_P_IPV6))
+ ttl = ((const struct ipv6hdr *)inner_iph)->hop_limit;
+#endif
+ else
+ ttl = ip4_dst_hoplimit(&rt->dst);
+ }
+
+ max_headroom = LL_RESERVED_SPACE(tdev) + sizeof(struct iphdr)
+ + rt->dst.header_len;
+ if (max_headroom > dev->needed_headroom) {
+ dev->needed_headroom = max_headroom;
+ if (skb_cow_head(skb, dev->needed_headroom)) {
+ dev->stats.tx_dropped++;
+ dev_kfree_skb(skb);
+ return;
+ }
+ }
+
+ skb_dst_drop(skb);
+ skb_dst_set(skb, &rt->dst);
+ memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
+
+ /* Push down and install the IP header. */
+ skb_push(skb, sizeof(struct iphdr));
+ skb_reset_network_header(skb);
+
+ iph = ip_hdr(skb);
+ inner_iph = (const struct iphdr *)skb_inner_network_header(skb);
+
+ iph->version = 4;
+ iph->ihl = sizeof(struct iphdr) >> 2;
+ iph->frag_off = df;
+ iph->protocol = tnl_params->protocol;
+ iph->tos = ip_tunnel_ecn_encap(tos, inner_iph, skb);
+ iph->daddr = fl4.daddr;
+ iph->saddr = fl4.saddr;
+ iph->ttl = ttl;
+ tunnel_ip_select_ident(skb, inner_iph, &rt->dst);
+
+ iptunnel_xmit(skb, dev);
+ return;
+
+#if IS_ENABLED(CONFIG_IPV6)
+tx_error_icmp:
+ dst_link_failure(skb);
+#endif
+tx_error:
+ dev->stats.tx_errors++;
+ dev_kfree_skb(skb);
+}
+EXPORT_SYMBOL_GPL(ip_tunnel_xmit);
+
+static void ip_tunnel_update(struct ip_tunnel_net *itn,
+ struct ip_tunnel *t,
+ struct net_device *dev,
+ struct ip_tunnel_parm *p,
+ bool set_mtu)
+{
+ ip_tunnel_del(itn, t);
+ t->parms.iph.saddr = p->iph.saddr;
+ t->parms.iph.daddr = p->iph.daddr;
+ t->parms.i_key = p->i_key;
+ t->parms.o_key = p->o_key;
+ if (dev->type != ARPHRD_ETHER) {
+ memcpy(dev->dev_addr, &p->iph.saddr, 4);
+ memcpy(dev->broadcast, &p->iph.daddr, 4);
+ }
+ ip_tunnel_add(itn, t);
+
+ t->parms.iph.ttl = p->iph.ttl;
+ t->parms.iph.tos = p->iph.tos;
+ t->parms.iph.frag_off = p->iph.frag_off;
+
+ if (t->parms.link != p->link) {
+ int mtu;
+
+ t->parms.link = p->link;
+ mtu = ip_tunnel_bind_dev(dev);
+ if (set_mtu)
+ dev->mtu = mtu;
+ }
+ netdev_state_change(dev);
+}
+
+int ip_tunnel_ioctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd)
+{
+ int err = 0;
+ struct ip_tunnel *t;
+ struct net *net = dev_net(dev);
+ struct ip_tunnel *tunnel = netdev_priv(dev);
+ struct ip_tunnel_net *itn = net_generic(net, tunnel->ip_tnl_net_id);
+
+ BUG_ON(!itn->fb_tunnel_dev);
+ switch (cmd) {
+ case SIOCGETTUNNEL:
+ t = NULL;
+ if (dev == itn->fb_tunnel_dev)
+ t = ip_tunnel_find(itn, p, itn->fb_tunnel_dev->type);
+ if (t == NULL)
+ t = netdev_priv(dev);
+ memcpy(p, &t->parms, sizeof(*p));
+ break;
+
+ case SIOCADDTUNNEL:
+ case SIOCCHGTUNNEL:
+ err = -EPERM;
+ if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
+ goto done;
+ if (p->iph.ttl)
+ p->iph.frag_off |= htons(IP_DF);
+ if (!(p->i_flags&TUNNEL_KEY))
+ p->i_key = 0;
+ if (!(p->o_flags&TUNNEL_KEY))
+ p->o_key = 0;
+
+ t = ip_tunnel_find(itn, p, itn->fb_tunnel_dev->type);
+
+ if (!t && (cmd == SIOCADDTUNNEL))
+ t = ip_tunnel_create(net, itn, p);
+
+ if (dev != itn->fb_tunnel_dev && cmd == SIOCCHGTUNNEL) {
+ if (t != NULL) {
+ if (t->dev != dev) {
+ err = -EEXIST;
+ break;
+ }
+ } else {
+ unsigned int nflags = 0;
+
+ if (ipv4_is_multicast(p->iph.daddr))
+ nflags = IFF_BROADCAST;
+ else if (p->iph.daddr)
+ nflags = IFF_POINTOPOINT;
+
+ if ((dev->flags^nflags)&(IFF_POINTOPOINT|IFF_BROADCAST)) {
+ err = -EINVAL;
+ break;
+ }
+
+ t = netdev_priv(dev);
+ }
+ }
+
+ if (t) {
+ err = 0;
+ ip_tunnel_update(itn, t, dev, p, true);
+ } else
+ err = (cmd == SIOCADDTUNNEL ? -ENOBUFS : -ENOENT);
+ break;
+
+ case SIOCDELTUNNEL:
+ err = -EPERM;
+ if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
+ goto done;
+
+ if (dev == itn->fb_tunnel_dev) {
+ err = -ENOENT;
+ t = ip_tunnel_find(itn, p, itn->fb_tunnel_dev->type);
+ if (t == NULL)
+ goto done;
+ err = -EPERM;
+ if (t == netdev_priv(itn->fb_tunnel_dev))
+ goto done;
+ dev = t->dev;
+ }
+ unregister_netdevice(dev);
+ err = 0;
+ break;
+
+ default:
+ err = -EINVAL;
+ }
+
+done:
+ return err;
+}
+EXPORT_SYMBOL_GPL(ip_tunnel_ioctl);
+
+int ip_tunnel_change_mtu(struct net_device *dev, int new_mtu)
+{
+ struct ip_tunnel *tunnel = netdev_priv(dev);
+ int t_hlen = tunnel->hlen + sizeof(struct iphdr);
+
+ if (new_mtu < 68 ||
+ new_mtu > 0xFFF8 - dev->hard_header_len - t_hlen)
+ return -EINVAL;
+ dev->mtu = new_mtu;
+ return 0;
+}
+EXPORT_SYMBOL_GPL(ip_tunnel_change_mtu);
+
+static void ip_tunnel_dev_free(struct net_device *dev)
+{
+ struct ip_tunnel *tunnel = netdev_priv(dev);
+
+ gro_cells_destroy(&tunnel->gro_cells);
+ free_percpu(dev->tstats);
+ free_netdev(dev);
+}
+
+void ip_tunnel_dellink(struct net_device *dev, struct list_head *head)
+{
+ struct net *net = dev_net(dev);
+ struct ip_tunnel *tunnel = netdev_priv(dev);
+ struct ip_tunnel_net *itn;
+
+ itn = net_generic(net, tunnel->ip_tnl_net_id);
+
+ if (itn->fb_tunnel_dev != dev) {
+ ip_tunnel_del(itn, netdev_priv(dev));
+ unregister_netdevice_queue(dev, head);
+ }
+}
+EXPORT_SYMBOL_GPL(ip_tunnel_dellink);
+
+int __net_init ip_tunnel_init_net(struct net *net, int ip_tnl_net_id,
+ struct rtnl_link_ops *ops, char *devname)
+{
+ struct ip_tunnel_net *itn = net_generic(net, ip_tnl_net_id);
+ struct ip_tunnel_parm parms;
+
+ itn->tunnels = kzalloc(IP_TNL_HASH_SIZE * sizeof(struct hlist_head), GFP_KERNEL);
+ if (!itn->tunnels)
+ return -ENOMEM;
+
+ if (!ops) {
+ itn->fb_tunnel_dev = NULL;
+ return 0;
+ }
+ memset(&parms, 0, sizeof(parms));
+ if (devname)
+ strlcpy(parms.name, devname, IFNAMSIZ);
+
+ rtnl_lock();
+ itn->fb_tunnel_dev = __ip_tunnel_create(net, ops, &parms);
+ rtnl_unlock();
+ if (IS_ERR(itn->fb_tunnel_dev)) {
+ kfree(itn->tunnels);
+ return PTR_ERR(itn->fb_tunnel_dev);
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(ip_tunnel_init_net);
+
+static void ip_tunnel_destroy(struct ip_tunnel_net *itn, struct list_head *head)
+{
+ int h;
+
+ for (h = 0; h < IP_TNL_HASH_SIZE; h++) {
+ struct ip_tunnel *t;
+ struct hlist_node *n;
+ struct hlist_head *thead = &itn->tunnels[h];
+
+ hlist_for_each_entry_safe(t, n, thead, hash_node)
+ unregister_netdevice_queue(t->dev, head);
+ }
+ if (itn->fb_tunnel_dev)
+ unregister_netdevice_queue(itn->fb_tunnel_dev, head);
+}
+
+void __net_exit ip_tunnel_delete_net(struct ip_tunnel_net *itn)
+{
+ LIST_HEAD(list);
+
+ rtnl_lock();
+ ip_tunnel_destroy(itn, &list);
+ unregister_netdevice_many(&list);
+ rtnl_unlock();
+ kfree(itn->tunnels);
+}
+EXPORT_SYMBOL_GPL(ip_tunnel_delete_net);
+
+int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[],
+ struct ip_tunnel_parm *p)
+{
+ struct ip_tunnel *nt;
+ struct net *net = dev_net(dev);
+ struct ip_tunnel_net *itn;
+ int mtu;
+ int err;
+
+ nt = netdev_priv(dev);
+ itn = net_generic(net, nt->ip_tnl_net_id);
+
+ if (ip_tunnel_find(itn, p, dev->type))
+ return -EEXIST;
+
+ nt->parms = *p;
+ err = register_netdevice(dev);
+ if (err)
+ goto out;
+
+ if (dev->type == ARPHRD_ETHER && !tb[IFLA_ADDRESS])
+ eth_hw_addr_random(dev);
+
+ mtu = ip_tunnel_bind_dev(dev);
+ if (!tb[IFLA_MTU])
+ dev->mtu = mtu;
+
+ ip_tunnel_add(itn, nt);
+
+out:
+ return err;
+}
+EXPORT_SYMBOL_GPL(ip_tunnel_newlink);
+
+int ip_tunnel_changelink(struct net_device *dev, struct nlattr *tb[],
+ struct ip_tunnel_parm *p)
+{
+ struct ip_tunnel *t, *nt;
+ struct net *net = dev_net(dev);
+ struct ip_tunnel *tunnel = netdev_priv(dev);
+ struct ip_tunnel_net *itn = net_generic(net, tunnel->ip_tnl_net_id);
+
+ if (dev == itn->fb_tunnel_dev)
+ return -EINVAL;
+
+ nt = netdev_priv(dev);
+
+ t = ip_tunnel_find(itn, p, dev->type);
+
+ if (t) {
+ if (t->dev != dev)
+ return -EEXIST;
+ } else {
+ t = nt;
+
+ if (dev->type != ARPHRD_ETHER) {
+ unsigned int nflags = 0;
+
+ if (ipv4_is_multicast(p->iph.daddr))
+ nflags = IFF_BROADCAST;
+ else if (p->iph.daddr)
+ nflags = IFF_POINTOPOINT;
+
+ if ((dev->flags ^ nflags) &
+ (IFF_POINTOPOINT | IFF_BROADCAST))
+ return -EINVAL;
+ }
+ }
+
+ ip_tunnel_update(itn, t, dev, p, !tb[IFLA_MTU]);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(ip_tunnel_changelink);
+
+int ip_tunnel_init(struct net_device *dev)
+{
+ struct ip_tunnel *tunnel = netdev_priv(dev);
+ struct iphdr *iph = &tunnel->parms.iph;
+ int err;
+
+ dev->destructor = ip_tunnel_dev_free;
+ dev->tstats = alloc_percpu(struct pcpu_tstats);
+ if (!dev->tstats)
+ return -ENOMEM;
+
+ err = gro_cells_init(&tunnel->gro_cells, dev);
+ if (err) {
+ free_percpu(dev->tstats);
+ return err;
+ }
+
+ tunnel->dev = dev;
+ strcpy(tunnel->parms.name, dev->name);
+ iph->version = 4;
+ iph->ihl = 5;
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(ip_tunnel_init);
+
+void ip_tunnel_uninit(struct net_device *dev)
+{
+ struct net *net = dev_net(dev);
+ struct ip_tunnel *tunnel = netdev_priv(dev);
+ struct ip_tunnel_net *itn;
+
+ itn = net_generic(net, tunnel->ip_tnl_net_id);
+ /* fb_tunnel_dev will be unregisted in net-exit call. */
+ if (itn->fb_tunnel_dev != dev)
+ ip_tunnel_del(itn, netdev_priv(dev));
+}
+EXPORT_SYMBOL_GPL(ip_tunnel_uninit);
+
+void ip_tunnel_setup(struct net_device *dev, int net_id)
+{
+ struct ip_tunnel *tunnel = netdev_priv(dev);
+ tunnel->ip_tnl_net_id = net_id;
+}
+EXPORT_SYMBOL_GPL(ip_tunnel_setup);
+
+MODULE_LICENSE("GPL");
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index c3a4233..6a628fb 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -38,7 +38,7 @@
#include <net/sock.h>
#include <net/ip.h>
#include <net/icmp.h>
-#include <net/ipip.h>
+#include <net/ip_tunnels.h>
#include <net/inet_ecn.h>
#include <net/xfrm.h>
#include <net/net_namespace.h>
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index 34e006f..a557d6a 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -111,7 +111,7 @@
#include <net/sock.h>
#include <net/ip.h>
#include <net/icmp.h>
-#include <net/ipip.h>
+#include <net/ip_tunnels.h>
#include <net/inet_ecn.h>
#include <net/xfrm.h>
#include <net/net_namespace.h>
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 5f95b3a..fd61fe1 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -61,7 +61,7 @@
#include <linux/netfilter_ipv4.h>
#include <linux/compat.h>
#include <linux/export.h>
-#include <net/ipip.h>
+#include <net/ip_tunnels.h>
#include <net/checksum.h>
#include <net/netlink.h>
#include <net/fib_rules.h>
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index f56277f..ab5c7ad 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -49,7 +49,6 @@
#include <net/udp.h>
#include <net/udplite.h>
#include <net/tcp.h>
-#include <net/ipip.h>
#include <net/protocol.h>
#include <net/inet_common.h>
#include <net/route.h>
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 6a6ba73..af4a5e2 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -38,6 +38,7 @@
#include <net/sock.h>
#include <net/ip.h>
+#include <net/ip_tunnel.h>
#include <net/icmp.h>
#include <net/protocol.h>
#include <net/addrconf.h>
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index bef3fed..1e55866 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -47,6 +47,7 @@
#include <net/icmp.h>
#include <net/ip.h>
+#include <net/ip_tunnels.h>
#include <net/ipv6.h>
#include <net/ip6_route.h>
#include <net/addrconf.h>
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 898e671..ee4fc57 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -49,7 +49,7 @@
#include <net/ip.h>
#include <net/udp.h>
#include <net/icmp.h>
-#include <net/ipip.h>
+#include <net/ip_tunnels.h>
#include <net/inet_ecn.h>
#include <net/xfrm.h>
#include <net/dsfield.h>
--
1.7.1
^ permalink raw reply related
* [PATCH v3 net-next 0/5] Tunneling: Tunnel restructuring.
From: Pravin B Shelar @ 2013-03-19 8:10 UTC (permalink / raw)
To: davem; +Cc: netdev, jesse, Pravin B Shelar
Following patch series restructure GRE and IPIP tunneling code
to make it modular. It adds ip_tunnel module which acts as
generic tunneling layer which has common code.
These patches do not change any functionality.
v2-v3:
- Use GPL exports for all export symbols.
- Set default config NET_IP_TUNNEL to m.
v1-v2:
- Dropped patch to convert gre_proto_lock to rtnl lock.
Pravin B Shelar (5):
GRE: Refactor GRE tunneling code.
IPIP: Use ip-tunneling code.
VXLAN: Fix vxlan stats handling.
VXLAN: Use IP Tunnels tunnel ENC encap API
Tunneling: use IP Tunnel stats APIs.
drivers/net/Kconfig | 1 +
drivers/net/vxlan.c | 100 +---
include/net/gre.h | 51 ++
include/net/ip_tunnels.h | 169 ++++++
include/net/ipip.h | 88 ---
net/ipv4/Kconfig | 7 +
net/ipv4/Makefile | 1 +
net/ipv4/af_inet.c | 1 -
net/ipv4/gre.c | 5 -
net/ipv4/ip_gre.c | 1503 ++++++++++------------------------------------
net/ipv4/ip_tunnel.c | 1035 +++++++++++++++++++++++++++++++
net/ipv4/ip_vti.c | 42 +--
net/ipv4/ipip.c | 749 ++---------------------
net/ipv4/ipmr.c | 2 +-
net/ipv6/Kconfig | 2 +
net/ipv6/af_inet6.c | 1 -
net/ipv6/ip6_gre.c | 43 +--
net/ipv6/ip6_tunnel.c | 1 +
net/ipv6/sit.c | 39 +--
19 files changed, 1654 insertions(+), 2186 deletions(-)
create mode 100644 include/net/ip_tunnels.h
delete mode 100644 include/net/ipip.h
create mode 100644 net/ipv4/ip_tunnel.c
^ permalink raw reply
* [PATCH 1/1] net/smsc911x: Use NULL instead of integer for pointer
From: Sachin Kamat @ 2013-03-19 7:01 UTC (permalink / raw)
To: netdev; +Cc: steve.glendinning, davem, sachin.kamat
Silences the following sparse warning:
drivers/net/ethernet/smsc/smsc911x.c:2145:30:
warning: Using plain integer as NULL pointer
Signed-off-by: Sachin Kamat <sachin.kamat@linaro.org>
---
drivers/net/ethernet/smsc/smsc911x.c | 2 +-
1 files changed, 1 insertions(+), 1 deletions(-)
diff --git a/drivers/net/ethernet/smsc/smsc911x.c b/drivers/net/ethernet/smsc/smsc911x.c
index df77df1..3663b9e 100644
--- a/drivers/net/ethernet/smsc/smsc911x.c
+++ b/drivers/net/ethernet/smsc/smsc911x.c
@@ -2142,7 +2142,7 @@ static int smsc911x_init(struct net_device *dev)
spin_lock_init(&pdata->dev_lock);
spin_lock_init(&pdata->mac_lock);
- if (pdata->ioaddr == 0) {
+ if (pdata->ioaddr == NULL) {
SMSC_WARN(pdata, probe, "pdata->ioaddr: 0x00000000");
return -ENODEV;
}
--
1.7.4.1
^ permalink raw reply related
* [PATCH 2/2] man/send(2): document a long standing bug that can cause spurious EPERM errors
From: Fernando Luis Vázquez Cao @ 2013-03-19 6:52 UTC (permalink / raw)
To: Michael Kerrisk
Cc: linux-man-u79uwXL29TY76Z2rM5mHXA, netdev-u79uwXL29TY76Z2rM5mHXA,
netfilter-devel-u79uwXL29TY76Z2rM5mHXA, Pablo Neira Ayuso,
Patrick McHardy, Hirotaka Sasaki
In-Reply-To: <1363675513.4767.6.camel@nexus>
Subject: [PATCH 2/2] man/send(2): document a long standing bug that can cause spurious EPERM errors
This bug has been known since early 2009 (the latest) and discussed in
netdev before:
http://marc.info/?l=linux-netdev&w=2&r=1&s=Possible+race+condition+in+conntracking+&q=b
It seems that a proper fix would be non trivial, so document the bug
in the meantime.
Reported-by: Hirotaka Sasaki <sasaki.hirotaka-Zyj7fXuS5i5L9jVzuh4AOg@public.gmane.org>
Signed-off-by: Fernando Luis Vazquez Cao <fernando-gVGce1chcLdL9jVzuh4AOg@public.gmane.org>
---
diff -urNp man-pages-3.50-orig/man2/send.2 man-pages-3.50/man2/send.2
--- man-pages-3.50-orig/man2/send.2 2013-03-19 15:18:03.784306647 +0900
+++ man-pages-3.50/man2/send.2 2013-03-19 15:30:40.788060426 +0900
@@ -420,6 +420,11 @@ Linux may return
.B EPIPE
instead of
.BR ENOTCONN .
+
+Linux may return spurious
+.B EPERM
+errors when netfilter's conntrack module is loaded and two or more
+UDP packets belonging to the same connection are processed in parallel.
.SH EXAMPLE
An example of the use of
.BR sendto ()
--
To unsubscribe from this list: send the line "unsubscribe linux-man" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* [PATCH 1/2] man/send(2): add EPERM to the list of possible errors
From: Fernando Luis Vázquez Cao @ 2013-03-19 6:45 UTC (permalink / raw)
To: Michael Kerrisk
Cc: linux-man-u79uwXL29TY76Z2rM5mHXA, netdev-u79uwXL29TY76Z2rM5mHXA,
netfilter-devel-u79uwXL29TY76Z2rM5mHXA, Pablo Neira Ayuso,
Patrick McHardy, Hirotaka Sasaki
Subject: [PATCH 1/2] man/send(2): add EPERM to the list of possible errors
System policy (for example netfilter rule) can cause a send* operation
to fail with EPERM.
Reported-by: Hirotaka Sasaki <sasaki.hirotaka-Zyj7fXuS5i5L9jVzuh4AOg@public.gmane.org>
Signed-off-by: Fernando Luis Vazquez Cao <fernando-gVGce1chcLdL9jVzuh4AOg@public.gmane.org>
---
diff -urNp man-pages-3.50-orig/man2/send.2 man-pages-3.50/man2/send.2
--- man-pages-3.50-orig/man2/send.2 2013-03-15 16:17:32.000000000 +0900
+++ man-pages-3.50/man2/send.2 2013-03-19 15:17:03.616008275 +0900
@@ -357,6 +357,10 @@ Some bit in the
.I flags
argument is inappropriate for the socket type.
.TP
+.B EPERM
+System policy (for example a netfilter rule) does not permit the requested
+operation.
+.TP
.B EPIPE
The local end has been shut down on a connection oriented socket.
In this case the process
--
To unsubscribe from this list: send the line "unsubscribe linux-man" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* [PATCH v6] net: sh_eth: Add support of device tree probe
From: Nobuhiro Iwamatsu @ 2013-03-19 6:39 UTC (permalink / raw)
To: netdev
Cc: devicetree-discuss, magnus.damm, kda, horms+renesas, mark.rutland,
grant.likely, Nobuhiro Iwamatsu
This adds support of device tree probe for Renesas sh-ether driver.
Signed-off-by: Nobuhiro Iwamatsu <nobuhiro.iwamatsu.yj@renesas.com>
V6: - Add renesas,sh-eth-gigabit, renesas,sh-eth-sh4 and
renesas,sh-eth-sh3-sh2 to compatible string.
- Remove sh-eth,register-type. This is supplemented by the
compatible string.
- Use the of_property_read_bool instead of of_find_property.
- Add sanity chheck for of_property_read_u32.
- Update document.
V5: - Rewrite sh_eth_parse_dt().
Remove of_device_is_available() and CONFIG_OF from support OF
checking function and re-add empty sh_eth_parse_dt().
- Add CONFIG_PM to definition of dev_pm_ops.
- Add CONFIG_OF to definition of of_device_id.
V4: - Remove empty sh_eth_parse_dt().
V3: - Remove empty sh_eth_parse_dt().
V3: - Removed sentnece of "needs-init" from document.
V2: - Removed ether_setup().
- Fixed typo from "sh-etn" to "sh-eth".
- Removed "needs-init" and sh-eth,endian from definition of DT.
- Changed "sh-eth,edmac-endian" instead of "sh-eth,edmac-big-endain"
in definition of DT.
---
Documentation/devicetree/bindings/net/sh_ether.txt | 48 +++++++
drivers/net/ethernet/renesas/sh_eth.c | 145 ++++++++++++++++----
2 files changed, 168 insertions(+), 25 deletions(-)
create mode 100644 Documentation/devicetree/bindings/net/sh_ether.txt
diff --git a/Documentation/devicetree/bindings/net/sh_ether.txt b/Documentation/devicetree/bindings/net/sh_ether.txt
new file mode 100644
index 0000000..d1f961c
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/sh_ether.txt
@@ -0,0 +1,48 @@
+* Renesas Electronics SuperH EMAC
+
+This file provides information, what the device node
+for the sh_eth interface contains.
+
+Required properties:
+- compatible: "renesas,sh-eth-gigabit": If a device has
+ a function of gigabit, you should
+ set this.
+ "renesas,sh-eth-sh4": If this is provided by
+ SH4, you should set this.
+ "renesas,sh-eth-sh3-sh2": If this is provided
+ by SH3 or SH2, you should set this.
+
+- interrupt-parent: The phandle for the interrupt controller that
+ services interrupts for this device.
+
+- reg: Offset and length of the register set for the
+ device. If device has TSU registers, you need
+ to set up two register information here.
+
+- interrupts: Interrupt mapping for the sh_eth interrupt
+ sources (vector id). You can set one value.
+
+- phy-mode: String, operation mode of the PHY interface
+ (a string that of_get_phy_mode() can understand).
+
+- sh-eth,phy-id: PHY id.
+
+Optional properties:
+- local-mac-address: 6 bytes, mac address
+- sh-eth,no-ether-link: Set link control by software. When device does
+ not support ether-link, set.
+- sh-eth,ether-link-active-low: Set link check method.
+ When detection of link is treated as active-low,
+ set.
+- sh-eth,edmac-big-endian: Set big endian for sh_eth dmac.
+ It work as little endian when this is not set.
+
+Example (armadillo800eva):
+ sh-eth@e9a00000 {
+ compatible = "renesas,sh-eth-gigabit";
+ interrupt-parent = <&intca>;
+ reg = <0xe9a00000 0x800>, <0xe9a01800 0x800>;
+ interrupts = <0x500>;
+ phy-mode = "mii";
+ sh-eth,phy-id = <0>;
+ };
diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c
index 7a6471d..d9df68e 100644
--- a/drivers/net/ethernet/renesas/sh_eth.c
+++ b/drivers/net/ethernet/renesas/sh_eth.c
@@ -1,7 +1,7 @@
/*
* SuperH Ethernet device driver
*
- * Copyright (C) 2006-2012 Nobuhiro Iwamatsu
+ * Copyright (C) 2006-2013 Nobuhiro Iwamatsu
* Copyright (C) 2008-2012 Renesas Solutions Corp.
*
* This program is free software; you can redistribute it and/or modify it
@@ -31,6 +31,12 @@
#include <linux/platform_device.h>
#include <linux/mdio-bitbang.h>
#include <linux/netdevice.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/of_platform.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/of_net.h>
#include <linux/phy.h>
#include <linux/cache.h>
#include <linux/io.h>
@@ -2340,26 +2346,88 @@ static const struct net_device_ops sh_eth_netdev_ops = {
.ndo_change_mtu = eth_change_mtu,
};
+#ifdef CONFIG_OF
+static struct sh_eth_plat_data *
+sh_eth_parse_dt(struct device *dev, struct net_device *ndev,
+ struct device_node *np)
+{
+ struct sh_eth_plat_data *pdata;
+
+ pdata = devm_kzalloc(dev, sizeof(struct sh_eth_plat_data),
+ GFP_KERNEL);
+ if (!pdata) {
+ dev_err(dev, "%s: failed to allocate config data\n", __func__);
+ return NULL;
+ }
+
+ pdata->phy_interface = of_get_phy_mode(np);
+
+ if (of_property_read_u32(np, "sh-eth,phy-id", &pdata->phy))
+ goto error;
+
+ pdata->edmac_endian =
+ of_property_read_bool(np, "sh-eth,edmac-big-endian");
+
+ pdata->no_ether_link =
+ of_property_read_bool(np, "sh-eth,no-ether-link");
+
+ pdata->ether_link_active_low =
+ of_property_read_bool(np, "sh-eth,ether-link-active-low");
+
+ if (of_device_is_compatible(np, "renesas,sh-eth-gigabit"))
+ pdata->register_type = SH_ETH_REG_GIGABIT;
+ else if (of_device_is_compatible(np, "renesas,sh-eth-sh4"))
+ pdata->register_type = SH_ETH_REG_FAST_SH4;
+ else if (of_device_is_compatible(np, "renesas,sh-eth-sh3-sh2"))
+ pdata->register_type = SH_ETH_REG_FAST_SH3_SH2;
+ else
+ pdata->register_type = -EINVAL;
+
+#ifdef CONFIG_OF_NET
+ if (!is_valid_ether_addr(ndev->dev_addr)) {
+ const char *macaddr = of_get_mac_address(np);
+ if (macaddr)
+ memcpy(pdata->mac_addr, macaddr, ETH_ALEN);
+ }
+#endif
+
+ return pdata;
+
+error:
+ devm_kfree(dev, pdata);
+ return NULL;
+}
+#else
+static inline struct sh_eth_plat_data *
+sh_eth_parse_dt(struct device *dev, struct net_device *ndev,
+ struct device_node *np)
+{
+ return NULL;
+}
+#endif
+
static int sh_eth_drv_probe(struct platform_device *pdev)
{
- int ret, devno = 0;
+ int ret = 0, devno = 0;
struct resource *res;
struct net_device *ndev = NULL;
struct sh_eth_private *mdp = NULL;
struct sh_eth_plat_data *pd;
+ struct device_node *np = pdev->dev.of_node;
+
+ ndev = alloc_etherdev(sizeof(struct sh_eth_private));
+ if (!ndev) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ mdp = netdev_priv(ndev);
/* get base addr */
res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
if (unlikely(res == NULL)) {
dev_err(&pdev->dev, "invalid resource\n");
ret = -EINVAL;
- goto out;
- }
-
- ndev = alloc_etherdev(sizeof(struct sh_eth_private));
- if (!ndev) {
- ret = -ENOMEM;
- goto out;
+ goto out_release;
}
/* The sh Ether-specific entries in the device structure. */
@@ -2376,14 +2444,6 @@ static int sh_eth_drv_probe(struct platform_device *pdev)
}
ndev->irq = ret;
- SET_NETDEV_DEV(ndev, &pdev->dev);
-
- /* Fill in the fields of the device structure with ethernet values. */
- ether_setup(ndev);
-
- mdp = netdev_priv(ndev);
- mdp->num_tx_ring = TX_RING_SIZE;
- mdp->num_rx_ring = RX_RING_SIZE;
mdp->addr = ioremap(res->start, resource_size(res));
if (mdp->addr == NULL) {
ret = -ENOMEM;
@@ -2391,12 +2451,33 @@ static int sh_eth_drv_probe(struct platform_device *pdev)
goto out_release;
}
+ if (np) {
+ pd = sh_eth_parse_dt(&pdev->dev, ndev, np);
+ if (pdev->dev.platform_data && pd) {
+ struct sh_eth_plat_data *tmp =
+ pdev->dev.platform_data;
+ pd->set_mdio_gate = tmp->set_mdio_gate;
+ pd->needs_init = tmp->needs_init;
+ }
+ } else
+ pd = pdev->dev.platform_data;
+
+ if (!pd) {
+ dev_err(&pdev->dev, "no setup data defined\n");
+ ret = -EINVAL;
+ goto out_release;
+ }
+
+ SET_NETDEV_DEV(ndev, &pdev->dev);
+
+ mdp->num_tx_ring = TX_RING_SIZE;
+ mdp->num_rx_ring = RX_RING_SIZE;
+
spin_lock_init(&mdp->lock);
mdp->pdev = pdev;
pm_runtime_enable(&pdev->dev);
pm_runtime_resume(&pdev->dev);
- pd = (struct sh_eth_plat_data *)(pdev->dev.platform_data);
/* get PHY ID */
mdp->phy_id = pd->phy;
mdp->phy_interface = pd->phy_interface;
@@ -2405,6 +2486,8 @@ static int sh_eth_drv_probe(struct platform_device *pdev)
mdp->no_ether_link = pd->no_ether_link;
mdp->ether_link_active_low = pd->ether_link_active_low;
mdp->reg_offset = sh_eth_get_register_offset(pd->register_type);
+ /* read and set MAC address */
+ read_mac_address(ndev, pd->mac_addr);
/* set cpu data */
#if defined(SH_ETH_HAS_BOTH_MODULES)
@@ -2422,20 +2505,16 @@ static int sh_eth_drv_probe(struct platform_device *pdev)
/* debug message level */
mdp->msg_enable = SH_ETH_DEF_MSG_ENABLE;
- /* read and set MAC address */
- read_mac_address(ndev, pd->mac_addr);
-
/* ioremap the TSU registers */
if (mdp->cd->tsu) {
struct resource *rtsu;
rtsu = platform_get_resource(pdev, IORESOURCE_MEM, 1);
if (!rtsu) {
dev_err(&pdev->dev, "Not found TSU resource\n");
- ret = -ENODEV;
goto out_release;
}
mdp->tsu_addr = ioremap(rtsu->start,
- resource_size(rtsu));
+ resource_size(rtsu));
mdp->port = devno % 2;
ndev->features = NETIF_F_HW_VLAN_FILTER;
}
@@ -2502,6 +2581,7 @@ static int sh_eth_drv_remove(struct platform_device *pdev)
return 0;
}
+#ifdef CONFIG_PM
static int sh_eth_runtime_nop(struct device *dev)
{
/*
@@ -2515,17 +2595,32 @@ static int sh_eth_runtime_nop(struct device *dev)
return 0;
}
-static struct dev_pm_ops sh_eth_dev_pm_ops = {
+static const struct dev_pm_ops sh_eth_dev_pm_ops = {
.runtime_suspend = sh_eth_runtime_nop,
.runtime_resume = sh_eth_runtime_nop,
};
+#define SH_ETH_PM_OPS (&sh_eth_dev_pm_ops)
+#else
+#define SH_ETH_PM_OPS NULL
+#endif
+
+#ifdef CONFIG_OF
+static const struct of_device_id sh_eth_match[] = {
+ { .compatible = "renesas,sh-eth-gigabit", },
+ { .compatible = "renesas,sh-eth-sh4", },
+ { .compatible = "renesas,sh-eth-sh3-sh2", },
+ {},
+};
+MODULE_DEVICE_TABLE(of, sh_eth_match);
+#endif
static struct platform_driver sh_eth_driver = {
.probe = sh_eth_drv_probe,
.remove = sh_eth_drv_remove,
.driver = {
.name = CARDNAME,
- .pm = &sh_eth_dev_pm_ops,
+ .pm = SH_ETH_PM_OPS,
+ .of_match_table = of_match_ptr(sh_eth_match),
},
};
--
1.7.10.4
^ permalink raw reply related
* RE: [PATCH net-next 2/2] bnx2x: add RSS capability for GRE traffic
From: Dmitry Kravkov @ 2013-03-19 6:30 UTC (permalink / raw)
To: Eric Dumazet
Cc: davem@davemloft.net, netdev@vger.kernel.org, Eilon Greenstein,
Tom Herbert, Maciej Żenczykowski
In-Reply-To: <1363651672.21184.17.camel@edumazet-glaptop>
> -----Original Message-----
> From: netdev-owner@vger.kernel.org [mailto:netdev-owner@vger.kernel.org] On Behalf Of Eric Dumazet
> Sent: Tuesday, March 19, 2013 2:08 AM
> To: Dmitry Kravkov
> Cc: davem@davemloft.net; netdev@vger.kernel.org; Eilon Greenstein; Tom Herbert; Maciej Żenczykowski
> Subject: Re: [PATCH net-next 2/2] bnx2x: add RSS capability for GRE traffic
>
> On Mon, 2013-03-18 at 18:51 +0200, Dmitry Kravkov wrote:
> > The patch drives FW to perform RSS for GRE traffic,
> > based on inner headers.
> >
> > Signed-off-by: Dmitry Kravkov <dmitry@broadcom.com>
> > Signed-off-by: Eilon Greenstein <eilong@broadcom.com>
> > ---
> > drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h | 3 +++
> > drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c | 23 ++++++++++++-----------
> > drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.h | 9 +++++++++
> > 3 files changed, 24 insertions(+), 11 deletions(-)
>
> This works very well.
>
> Problem is we skb_set_queue_mapping(skb, 0); in __skb_tunnel_rx()
>
> (this was a patch from Tom Herbert, commit
> 693019e90ca45d881109d32c0c6d29adf03f6447 (net: reset skb queue mapping
> when rx'ing over tunnel )
>
> Meaning we hit a single cpu for the GRO stuff in ip_gre.
>
> I have to think about it.
>
>
> Another question is :
>
> Can bnx2x check the tcp checksum if GRE encapsulated ?
>
Current HW can't provide this. Probably, it's possible to separate CSUM from GRO/TPA then stack will have to handle CSUM validation for huge packets. Is it worth?
^ permalink raw reply
* [patch 1/3] qeth: delay feature trace
From: frank.blaschka @ 2013-03-19 6:04 UTC (permalink / raw)
To: davem; +Cc: netdev, linux-s390, Stefan Raspl
In-Reply-To: <20130319060441.956271217@de.ibm.com>
[-- Attachment #1: 600-qeth-delay-trace.diff --]
[-- Type: text/plain, Size: 874 bytes --]
From: Stefan Raspl <raspl@linux.vnet.ibm.com>
Delay tracing of the card features until the optional commands have been
enabled.
Signed-off-by: Stefan Raspl <raspl@linux.vnet.ibm.com>
Signed-off-by: Frank Blaschka <blaschka@linux.vnet.ibm.com>
---
drivers/s390/net/qeth_l3_main.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -3348,7 +3348,6 @@ static int __qeth_l3_set_online(struct c
rc = -ENODEV;
goto out_remove;
}
- qeth_trace_features(card);
if (!card->dev && qeth_l3_setup_netdev(card)) {
rc = -ENODEV;
@@ -3425,6 +3424,7 @@ contin:
qeth_l3_set_multicast_list(card->dev);
rtnl_unlock();
}
+ qeth_trace_features(card);
/* let user_space know that device is online */
kobject_uevent(&gdev->dev.kobj, KOBJ_CHANGE);
mutex_unlock(&card->conf_mutex);
^ permalink raw reply
* [patch 2/3] qeth: Fix invalid router settings handling
From: frank.blaschka @ 2013-03-19 6:04 UTC (permalink / raw)
To: davem; +Cc: netdev, linux-s390, Stefan Raspl
In-Reply-To: <20130319060441.956271217@de.ibm.com>
[-- Attachment #1: 601-qeth-router-setting.diff --]
[-- Type: text/plain, Size: 2643 bytes --]
From: Stefan Raspl <raspl@linux.vnet.ibm.com>
Give a bad return code when specifying a router setting that is either
invalid or not support on the respective device type. In addition, fall back
the previous setting instead of silently switching back to 'no routing'.
Signed-off-by: Stefan Raspl <raspl@linux.vnet.ibm.com>
Signed-off-by: Frank Blaschka <blaschka@linux.vnet.ibm.com>
---
drivers/s390/net/qeth_l3_main.c | 17 +++++++++++------
drivers/s390/net/qeth_l3_sys.c | 2 ++
2 files changed, 13 insertions(+), 6 deletions(-)
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -623,7 +623,7 @@ static int qeth_l3_send_setrouting(struc
return rc;
}
-static void qeth_l3_correct_routing_type(struct qeth_card *card,
+static int qeth_l3_correct_routing_type(struct qeth_card *card,
enum qeth_routing_types *type, enum qeth_prot_versions prot)
{
if (card->info.type == QETH_CARD_TYPE_IQD) {
@@ -632,7 +632,7 @@ static void qeth_l3_correct_routing_type
case PRIMARY_CONNECTOR:
case SECONDARY_CONNECTOR:
case MULTICAST_ROUTER:
- return;
+ return 0;
default:
goto out_inval;
}
@@ -641,17 +641,18 @@ static void qeth_l3_correct_routing_type
case NO_ROUTER:
case PRIMARY_ROUTER:
case SECONDARY_ROUTER:
- return;
+ return 0;
case MULTICAST_ROUTER:
if (qeth_is_ipafunc_supported(card, prot,
IPA_OSA_MC_ROUTER))
- return;
+ return 0;
default:
goto out_inval;
}
}
out_inval:
*type = NO_ROUTER;
+ return -EINVAL;
}
int qeth_l3_setrouting_v4(struct qeth_card *card)
@@ -660,8 +661,10 @@ int qeth_l3_setrouting_v4(struct qeth_ca
QETH_CARD_TEXT(card, 3, "setrtg4");
- qeth_l3_correct_routing_type(card, &card->options.route4.type,
+ rc = qeth_l3_correct_routing_type(card, &card->options.route4.type,
QETH_PROT_IPV4);
+ if (rc)
+ return rc;
rc = qeth_l3_send_setrouting(card, card->options.route4.type,
QETH_PROT_IPV4);
@@ -683,8 +686,10 @@ int qeth_l3_setrouting_v6(struct qeth_ca
if (!qeth_is_supported(card, IPA_IPV6))
return 0;
- qeth_l3_correct_routing_type(card, &card->options.route6.type,
+ rc = qeth_l3_correct_routing_type(card, &card->options.route6.type,
QETH_PROT_IPV6);
+ if (rc)
+ return rc;
rc = qeth_l3_send_setrouting(card, card->options.route6.type,
QETH_PROT_IPV6);
--- a/drivers/s390/net/qeth_l3_sys.c
+++ b/drivers/s390/net/qeth_l3_sys.c
@@ -87,6 +87,8 @@ static ssize_t qeth_l3_dev_route_store(s
rc = qeth_l3_setrouting_v6(card);
}
out:
+ if (rc)
+ route->type = old_route_type;
mutex_unlock(&card->conf_mutex);
return rc ? rc : count;
}
^ permalink raw reply
* [patch 3/3] qeth: Fix scatter-gather regression
From: frank.blaschka @ 2013-03-19 6:04 UTC (permalink / raw)
To: davem; +Cc: netdev, linux-s390
In-Reply-To: <20130319060441.956271217@de.ibm.com>
[-- Attachment #1: 603-qeth-scatter-gather.diff --]
[-- Type: text/plain, Size: 3723 bytes --]
From: Frank Blaschka <blaschka@linux.vnet.ibm.com>
This patch fixes a scatter-gather regression introduced with
commit 5640f768 net: use a per task frag allocator
Now the qeth driver can cope with bigger framents and split a fragment in
sub framents if required.
Signed-off-by: Frank Blaschka <blaschka@linux.vnet.ibm.com>
---
drivers/s390/net/qeth_core.h | 1
drivers/s390/net/qeth_core_main.c | 45 ++++++++++++++++++++++++++++++++------
drivers/s390/net/qeth_l3_main.c | 4 ++-
3 files changed, 42 insertions(+), 8 deletions(-)
--- a/drivers/s390/net/qeth_core.h
+++ b/drivers/s390/net/qeth_core.h
@@ -916,6 +916,7 @@ int qeth_send_control_data(struct qeth_c
void *reply_param);
int qeth_get_priority_queue(struct qeth_card *, struct sk_buff *, int, int);
int qeth_get_elements_no(struct qeth_card *, void *, struct sk_buff *, int);
+int qeth_get_elements_for_frags(struct sk_buff *);
int qeth_do_send_packet_fast(struct qeth_card *, struct qeth_qdio_out_q *,
struct sk_buff *, struct qeth_hdr *, int, int, int);
int qeth_do_send_packet(struct qeth_card *, struct qeth_qdio_out_q *,
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -3679,6 +3679,25 @@ int qeth_get_priority_queue(struct qeth_
}
EXPORT_SYMBOL_GPL(qeth_get_priority_queue);
+int qeth_get_elements_for_frags(struct sk_buff *skb)
+{
+ int cnt, length, e, elements = 0;
+ struct skb_frag_struct *frag;
+ char *data;
+
+ for (cnt = 0; cnt < skb_shinfo(skb)->nr_frags; cnt++) {
+ frag = &skb_shinfo(skb)->frags[cnt];
+ data = (char *)page_to_phys(skb_frag_page(frag)) +
+ frag->page_offset;
+ length = frag->size;
+ e = PFN_UP((unsigned long)data + length - 1) -
+ PFN_DOWN((unsigned long)data);
+ elements += e;
+ }
+ return elements;
+}
+EXPORT_SYMBOL_GPL(qeth_get_elements_for_frags);
+
int qeth_get_elements_no(struct qeth_card *card, void *hdr,
struct sk_buff *skb, int elems)
{
@@ -3686,7 +3705,8 @@ int qeth_get_elements_no(struct qeth_car
int elements_needed = PFN_UP((unsigned long)skb->data + dlen - 1) -
PFN_DOWN((unsigned long)skb->data);
- elements_needed += skb_shinfo(skb)->nr_frags;
+ elements_needed += qeth_get_elements_for_frags(skb);
+
if ((elements_needed + elems) > QETH_MAX_BUFFER_ELEMENTS(card)) {
QETH_DBF_MESSAGE(2, "Invalid size of IP packet "
"(Number=%d / Length=%d). Discarded.\n",
@@ -3771,12 +3791,23 @@ static inline void __qeth_fill_buffer(st
for (cnt = 0; cnt < skb_shinfo(skb)->nr_frags; cnt++) {
frag = &skb_shinfo(skb)->frags[cnt];
- buffer->element[element].addr = (char *)
- page_to_phys(skb_frag_page(frag))
- + frag->page_offset;
- buffer->element[element].length = frag->size;
- buffer->element[element].eflags = SBAL_EFLAGS_MIDDLE_FRAG;
- element++;
+ data = (char *)page_to_phys(skb_frag_page(frag)) +
+ frag->page_offset;
+ length = frag->size;
+ while (length > 0) {
+ length_here = PAGE_SIZE -
+ ((unsigned long) data % PAGE_SIZE);
+ if (length < length_here)
+ length_here = length;
+
+ buffer->element[element].addr = data;
+ buffer->element[element].length = length_here;
+ buffer->element[element].eflags =
+ SBAL_EFLAGS_MIDDLE_FRAG;
+ length -= length_here;
+ data += length_here;
+ element++;
+ }
}
if (buffer->element[element - 1].eflags)
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -2903,7 +2903,9 @@ static inline int qeth_l3_tso_elements(s
tcp_hdr(skb)->doff * 4;
int tcpd_len = skb->len - (tcpd - (unsigned long)skb->data);
int elements = PFN_UP(tcpd + tcpd_len - 1) - PFN_DOWN(tcpd);
- elements += skb_shinfo(skb)->nr_frags;
+
+ elements += qeth_get_elements_for_frags(skb);
+
return elements;
}
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox