From: Johannes Berg
Date: Sun, 09 Apr 2017 09:04:07 +0200
> On Sun, 2017-04-09 at 08:25 +0200, Johannes Berg wrote:
>> That would also let you use rcu_assign_pointer() which seems like the
>> right thing to do here, along with marking the xdp_prog pointer as
>> __rcu? That'd also let you use rcu_
From: Andy Gospodarek
Date: Sun, 9 Apr 2017 01:17:26 -0400
> I should be able to run this on Monday and see how the performance
> compares to the driver/native XDP case on some bnxt_en-based hardware.
Thanks in advance for testing Andy.
From: Andrew Lunn
Date: Sun, 9 Apr 2017 15:46:55 +0200
>> +switch (act) {
>> +case XDP_PASS:
>> +case XDP_TX:
>> +break;
>> +
>> +default:
>> +bpf_warn_invalid_xdp_action(act);
>
> Hi David
>
> You might want to put a /* fall through */ comment here, just
> + switch (act) {
> + case XDP_PASS:
> + case XDP_TX:
> + break;
> +
> + default:
> + bpf_warn_invalid_xdp_action(act);
Hi David
You might want to put a /* fall through */ comment here, just to
prevent newbies from submitting patches moving the default cla
On Sun, 2017-04-09 at 08:25 +0200, Johannes Berg wrote:
> That would also let you use rcu_assign_pointer() which seems like the
> right thing to do here, along with marking the xdp_prog pointer as
> __rcu? That'd also let you use rcu_dereference() instead of
> READ_ONCE() which seems like the bette
On Sat, 2017-04-08 at 20:07 -0700, David Miller wrote:
> +static int generic_xdp_install(struct net_device *dev, struct
> netdev_xdp *xdp)
> +{
> + struct bpf_prog *new = xdp->prog;
> + int ret = 0;
> +
> + switch (xdp->command) {
> + case XDP_SETUP_PROG: {
> +
On Sat, Apr 8, 2017 at 11:07 PM, David Miller wrote:
>
> This provides a generic non-optimized XDP implementation when the
> device driver does not provide an optimized one.
>
> It is arguable that perhaps I should have required something like
> this as part of the initial XDP feature merge.
>
> I
This provides a generic non-optimized XDP implementation when the
device driver does not provide an optimized one.
It is arguable that perhaps I should have required something like
this as part of the initial XDP feature merge.
I believe this is critical for two reasons:
1) Accessibility. More
