On (09/28/16 11:08), Alexander Duyck wrote:
> > - then udp_gro_receive -> vxlan_gro_receive pulls up vxlan header
> > into linear part, and then..
>
> This is the point where we need to stop, drop the existing headers,
> call skb_reserve(NET_IP_ALIGN), and then pick back up where we left
> off.
On Wed, Sep 28, 2016 at 10:03 AM, Sowmini Varadhan
wrote:
> On (09/23/16 17:43), Alexander Duyck wrote:
>> > On (09/23/16 10:38), Alexander Duyck wrote:
> ;
>> >> almost think of it as us doing something like the inverse of
>> >> pskb_pull_tail. The general idea here is we want to actua
On (09/23/16 17:43), Alexander Duyck wrote:
> > On (09/23/16 10:38), Alexander Duyck wrote:
;
> >> almost think of it as us doing something like the inverse of
> >> pskb_pull_tail. The general idea here is we want to actually leave
> >> the data in skb->data, but just reference it from f
On Fri, Sep 23, 2016 at 4:41 PM, Sowmini Varadhan
wrote:
> On (09/23/16 10:38), Alexander Duyck wrote:
>>
>> So basically what I was thinking is we do something like reserving
>> NET_IP_ALIGN and continue writing headers to skb->data, but we force
>> the tracking for the inner headers into frag[0]
On (09/23/16 10:38), Alexander Duyck wrote:
>
> So basically what I was thinking is we do something like reserving
> NET_IP_ALIGN and continue writing headers to skb->data, but we force
> the tracking for the inner headers into frag[0] so that we can keep
> the inner headers aligned without messin
On Fri, Sep 23, 2016 at 10:20 AM, Sowmini Varadhan
wrote:
> On (09/23/16 07:17), Alexander Duyck wrote:
>> >> Is this basically about, e.g., putting the vxlanhdr in its own
>> >> skb_frag_t, or something else?
>> >
>> > Yes, and this way skb_header_pointer() is forced to do a memcpy.
> :
>> For
On (09/23/16 07:17), Alexander Duyck wrote:
> >> Is this basically about, e.g., putting the vxlanhdr in its own
> >> skb_frag_t, or something else?
> >
> > Yes, and this way skb_header_pointer() is forced to do a memcpy.
:
> For Tx it all becomes a bit trickier since it would likely require us
>
On Fri, Sep 23, 2016 at 5:06 AM, David Miller wrote:
> From: Sowmini Varadhan
> Date: Thu, 22 Sep 2016 17:30:10 -0400
>
>> On (09/22/16 01:52), David Miller wrote:
>>> Alternatively we can do Alexander Duyck's trick, by pushing
>>> the headers into the frag list, forcing a pull and realignment
>>
From: Sowmini Varadhan
Date: Thu, 22 Sep 2016 17:30:10 -0400
> On (09/22/16 01:52), David Miller wrote:
>> Alternatively we can do Alexander Duyck's trick, by pushing
>> the headers into the frag list, forcing a pull and realignment
>> by the next protocol layer.
>
> What is the "Alexander Duyck
On (09/22/16 01:52), David Miller wrote:
> Alternatively we can do Alexander Duyck's trick, by pushing
> the headers into the frag list, forcing a pull and realignment
> by the next protocol layer.
What is the "Alexander Duyck trick" (hints about module or commit id,
where this can be found, pleas
From: Jiri Benc
Date: Tue, 20 Sep 2016 19:09:29 +0200
> But the point stands, we have much greater problems here than VXLAN.
> And I don't think that wrapping all IP address accesses into
> get/put_unaligned all around the stack is the solution.
Right, and I don't like marking things as packed e
On (09/20/16 19:09), Jiri Benc wrote:
>
> But the point stands, we have much greater problems here than VXLAN.
> And I don't think that wrapping all IP address accesses into
> get/put_unaligned all around the stack is the solution.
>
Agreed, and I think Tom made that point too.
For the immediat
On Tue, Sep 20, 2016 at 10:09 AM, Jiri Benc wrote:
> On Tue, 20 Sep 2016 18:43:33 +0200, Jiri Benc wrote:
>> On Tue, 20 Sep 2016 12:31:08 -0400, Sowmini Varadhan wrote:
>> > The vxlan header is after the ethernet header (14 bytes),
>> > IP header (20 bytes, assuming no options) and udp header (8 b
On Tue, 20 Sep 2016 13:07:42 -0400, Sowmini Varadhan wrote:
> I will try out Hannes' solution (which makes sense) in a moment,
> and report back.
No objections to marking the struct as packed. Will only push the
problem to a different place, though.
Jiri
On Tue, 20 Sep 2016 18:43:33 +0200, Jiri Benc wrote:
> On Tue, 20 Sep 2016 12:31:08 -0400, Sowmini Varadhan wrote:
> > The vxlan header is after the ethernet header (14 bytes),
> > IP header (20 bytes, assuming no options) and udp header (8 bytes).
>
> If the VXLAN header is not aligned to 4 bytes
On (09/20/16 18:43), Jiri Benc wrote:
>
> IPv6 header is certainly not 20 bytes.
vxlan encapsulates an IPv6/ethernet frame in a UDP/IPv4/ethernet packet.
the ipv4 header is 20 bytes (without options).
mld_newpack is dealing with the vxlan net_device in this case,
which has ->hard_header_len of 14
On 20.09.2016 16:27, Sowmini Varadhan wrote:
> The vxlan header is at offset (14 + 20 + 8) into the packet,
> so the vxh is not aligned in vxlan_build_skb. Use [get/put]_unaligned
> functions to modify flags and vni field in the vxh.
>
> Signed-off-by: Sowmini Varadhan
> ---
> drivers/net/vxlan.
On Tue, 20 Sep 2016 12:31:08 -0400, Sowmini Varadhan wrote:
> The vxlan header is after the ethernet header (14 bytes),
> IP header (20 bytes, assuming no options) and udp header (8 bytes).
If the VXLAN header is not aligned to 4 bytes, then IP header is not
aligned to 4 bytes, too, and you have g
On (09/20/16 18:11), Jiri Benc wrote:
> > The vxlan header is at offset (14 + 20 + 8) into the packet,
> > so the vxh is not aligned in vxlan_build_skb. Use [get/put]_unaligned
> > functions to modify flags and vni field in the vxh.
>
> How did you calculate that? IP header should be aligned to 4
On Tue, 20 Sep 2016 10:27:00 -0400, Sowmini Varadhan wrote:
> The vxlan header is at offset (14 + 20 + 8) into the packet,
> so the vxh is not aligned in vxlan_build_skb. Use [get/put]_unaligned
> functions to modify flags and vni field in the vxh.
How did you calculate that? IP header should be a
On (09/20/16 08:31), Tom Herbert wrote:
>
> On Tue, Sep 20, 2016 at 7:27 AM, Sowmini Varadhan
> wrote:
> > The vxlan header is at offset (14 + 20 + 8) into the packet,
> > so the vxh is not aligned in vxlan_build_skb. Use [get/put]_unaligned
> > functions to modify flags and vni field in the vxh.
On Tue, Sep 20, 2016 at 7:27 AM, Sowmini Varadhan
wrote:
> The vxlan header is at offset (14 + 20 + 8) into the packet,
> so the vxh is not aligned in vxlan_build_skb. Use [get/put]_unaligned
> functions to modify flags and vni field in the vxh.
>
I'm wondering if VXLAN is just the tip of the iceb
The vxlan header is at offset (14 + 20 + 8) into the packet,
so the vxh is not aligned in vxlan_build_skb. Use [get/put]_unaligned
functions to modify flags and vni field in the vxh.
Signed-off-by: Sowmini Varadhan
---
drivers/net/vxlan.c | 10 ++
1 files changed, 6 insertions(+), 4 de
23 matches
Mail list logo
