From: Alexei Starovoitov
Date: Fri, 30 Nov 2018 15:33:08 -0800
> On Wed, Nov 28, 2018 at 11:02:00AM -0800, David Miller wrote:
>> From: Daniel Borkmann
>> Date: Wed, 28 Nov 2018 11:34:55 +0100
>>
>> > Yeah fully agree. Thinking diff below should address it, do you
>> > have a chance to give thi
On 12/01/2018 12:33 AM, Alexei Starovoitov wrote:
> On Wed, Nov 28, 2018 at 11:02:00AM -0800, David Miller wrote:
>> From: Daniel Borkmann
>> Date: Wed, 28 Nov 2018 11:34:55 +0100
>>
>>> Yeah fully agree. Thinking diff below should address it, do you
>>> have a chance to give this a spin for sparc
On Wed, Nov 28, 2018 at 11:02:00AM -0800, David Miller wrote:
> From: Daniel Borkmann
> Date: Wed, 28 Nov 2018 11:34:55 +0100
>
> > Yeah fully agree. Thinking diff below should address it, do you
> > have a chance to give this a spin for sparc / 32 bit to check if
> > test_verifier still explodes
From: Daniel Borkmann
Date: Wed, 28 Nov 2018 11:34:55 +0100
> Yeah fully agree. Thinking diff below should address it, do you
> have a chance to give this a spin for sparc / 32 bit to check if
> test_verifier still explodes?
Great, let me play with this.
I did something simpler yesterday, just
On 11/27/2018 11:25 PM, David Miller wrote:
>
> In the linux/bpf.h UAPI header, we must absolutely avoid any
> non-fixed-sized types.
>
> Otherwise we have serious problems on 32-bit.
>
> Unfortunately I discovered today that we have take on two such cases,
> sk_msg_md and sk_reuseport_md, both
In the linux/bpf.h UAPI header, we must absolutely avoid any
non-fixed-sized types.
Otherwise we have serious problems on 32-bit.
Unfortunately I discovered today that we have take on two such cases,
sk_msg_md and sk_reuseport_md, both of which start with two void
pointers.
I hit this because
