On Wed, May 8, 2019 at 10:56 AM Ben Pfaff wrote:
> On Wed, May 08, 2019 at 12:14:56AM -0700, Darrell Ball wrote:
> > On Tue, May 7, 2019 at 2:56 PM Ben Pfaff wrote:
> > > I am not confident about destruction ordering here. It appears that
> > > conntrack_destroy() frees 'ct'. I don't see anyth
On Wed, May 08, 2019 at 12:14:56AM -0700, Darrell Ball wrote:
> On Tue, May 7, 2019 at 2:56 PM Ben Pfaff wrote:
> > I am not confident about destruction ordering here. It appears that
> > conntrack_destroy() frees 'ct'. I don't see anything that assures that
> > a grace period has expired before
correction below for 'struct conn' inline comments
On Wed, May 8, 2019 at 12:14 AM Darrell Ball wrote:
> Thanks for the review
>
> On Tue, May 7, 2019 at 2:56 PM Ben Pfaff wrote:
>
>> On Mon, May 06, 2019 at 09:20:53AM -0700, Darrell Ball wrote:
>> > For performance and code simplification rea
Thanks for the review
On Tue, May 7, 2019 at 2:56 PM Ben Pfaff wrote:
> On Mon, May 06, 2019 at 09:20:53AM -0700, Darrell Ball wrote:
> > For performance and code simplification reasons, add rcu support for
> > conntrack. The array of hmaps is replaced by a cmap as part of this
> > conversion.
On Mon, May 06, 2019 at 09:20:53AM -0700, Darrell Ball wrote:
> For performance and code simplification reasons, add rcu support for
> conntrack. The array of hmaps is replaced by a cmap as part of this
> conversion. Using a single map also simplifies the handling of NAT
> and allows the removal o
For performance and code simplification reasons, add rcu support for
conntrack. The array of hmaps is replaced by a cmap as part of this
conversion. Using a single map also simplifies the handling of NAT
and allows the removal of the nat_conn map and friends. Per connection
entry locks are introd