On Thu, Mar 05, 2020 at 01:59:37PM -0800, Shakeel Butt wrote:
> On Thu, Mar 5, 2020 at 1:17 PM Eric Dumazet <eric.dumazet@xxxxxxxxx> wrote:
> >
> >
> >
> > On 3/5/20 12:55 PM, Shakeel Butt wrote:
> > > If a TCP socket is allocated in IRQ context or cloned from unassociated
> > > (i.e. not associated to a memcg) in IRQ context then it will remain
> > > unassociated for its whole life. Almost half of the TCPs created on the
> > > system are created in IRQ context, so, memory used by such sockets will
> > > not be accounted by the memcg.
> > >
> > > This issue is more widespread in cgroup v1 where network memory
> > > accounting is opt-in but it can happen in cgroup v2 if the source socket
> > > for the cloning was created in root memcg.
> > >
> > > To fix the issue, just do the late association of the unassociated
> > > sockets at accept() time in the process context and then force charge
> > > the memory buffer already reserved by the socket.
> > >
> > > Signed-off-by: Shakeel Butt <shakeelb@xxxxxxxxxx>
> > > ---
> > > Changes since v2:
> > > - Additional check for charging.
> > > - Release the sock after charging.
> > >
> > > Changes since v1:
> > > - added sk->sk_rmem_alloc to initial charging.
> > > - added synchronization to get memory usage and set sk_memcg race-free.
> > >
> > > net/ipv4/inet_connection_sock.c | 20 ++++++++++++++++++++
> > > 1 file changed, 20 insertions(+)
> > >
> > > diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
> > > index a4db79b1b643..5face55cf818 100644
> > > --- a/net/ipv4/inet_connection_sock.c
> > > +++ b/net/ipv4/inet_connection_sock.c
> > > @@ -482,6 +482,26 @@ struct sock *inet_csk_accept(struct sock *sk, int flags, int *err, bool kern)
> > > }
> > > spin_unlock_bh(&queue->fastopenq.lock);
> > > }
> > > +
> > > + if (mem_cgroup_sockets_enabled && !newsk->sk_memcg) {
> > > + int amt;
> > > +
> > > + /* atomically get the memory usage, set and charge the
> > > + * sk->sk_memcg.
> > > + */
> > > + lock_sock(newsk);
> > > +
> > > + /* The sk has not been accepted yet, no need to look at
> > > + * sk->sk_wmem_queued.
> > > + */
> > > + amt = sk_mem_pages(newsk->sk_forward_alloc +
> > > + atomic_read(&sk->sk_rmem_alloc));
> > > + mem_cgroup_sk_alloc(newsk);
> > > + if (newsk->sk_memcg && amt)
> > > + mem_cgroup_charge_skmem(newsk->sk_memcg, amt);
> > > +
> > > + release_sock(newsk);
> > > + }
> > > out:
> > > release_sock(sk);
> > > if (req)
> > >
> >
> > This patch looks fine, but why keeping the mem_cgroup_sk_alloc(newsk);
> > in sk_clone_lock() ?
> >
> > Note that all TCP sk_clone_lock() calls happen in softirq context.
>
> So, basically re-doing something like 9f1c2674b328 ("net: memcontrol:
> defer call to mem_cgroup_sk_alloc()") in this patch. I am fine with
> that.
>
> Roman, any concerns?
Nothing at the moment, I'll try to give some testing to the final patch.
I hope this time it will work better...
Thank you!
