From: Jesper Dangaard Brouer <brouer@redhat.com>
To: Martin KaFai Lau <kafai@fb.com>
Cc: "Toke Høiland-Jørgensen" <toke@redhat.com>,
"Hangbin Liu" <liuhangbin@gmail.com>,
bpf@vger.kernel.org, netdev@vger.kernel.org,
"Jiri Benc" <jbenc@redhat.com>,
"Eelco Chaudron" <echaudro@redhat.com>,
ast@kernel.org, "Daniel Borkmann" <daniel@iogearbox.net>,
"Lorenzo Bianconi" <lorenzo.bianconi@redhat.com>,
"David Ahern" <dsahern@gmail.com>,
"Andrii Nakryiko" <andrii.nakryiko@gmail.com>,
"Alexei Starovoitov" <alexei.starovoitov@gmail.com>,
"John Fastabend" <john.fastabend@gmail.com>,
"Maciej Fijalkowski" <maciej.fijalkowski@intel.com>,
"Björn Töpel" <bjorn.topel@gmail.com>,
brouer@redhat.com
Subject: Re: [PATCHv7 bpf-next 1/4] bpf: run devmap xdp_prog on flush instead of bulk enqueue
Date: Thu, 15 Apr 2021 20:21:32 +0200 [thread overview]
Message-ID: <20210415202132.7b5e8d0d@carbon> (raw)
In-Reply-To: <20210415173551.7ma4slcbqeyiba2r@kafai-mbp.dhcp.thefacebook.com>
On Thu, 15 Apr 2021 10:35:51 -0700
Martin KaFai Lau <kafai@fb.com> wrote:
> On Thu, Apr 15, 2021 at 11:22:19AM +0200, Toke Høiland-Jørgensen wrote:
> > Hangbin Liu <liuhangbin@gmail.com> writes:
> >
> > > On Wed, Apr 14, 2021 at 05:17:11PM -0700, Martin KaFai Lau wrote:
> > >> > static void bq_xmit_all(struct xdp_dev_bulk_queue *bq, u32 flags)
> > >> > {
> > >> > struct net_device *dev = bq->dev;
> > >> > - int sent = 0, err = 0;
> > >> > + int sent = 0, drops = 0, err = 0;
> > >> > + unsigned int cnt = bq->count;
> > >> > + int to_send = cnt;
> > >> > int i;
> > >> >
> > >> > - if (unlikely(!bq->count))
> > >> > + if (unlikely(!cnt))
> > >> > return;
> > >> >
> > >> > - for (i = 0; i < bq->count; i++) {
> > >> > + for (i = 0; i < cnt; i++) {
> > >> > struct xdp_frame *xdpf = bq->q[i];
> > >> >
> > >> > prefetch(xdpf);
> > >> > }
> > >> >
> > >> > - sent = dev->netdev_ops->ndo_xdp_xmit(dev, bq->count, bq->q, flags);
> > >> > + if (bq->xdp_prog) {
> > >> bq->xdp_prog is used here
> > >>
> > >> > + to_send = dev_map_bpf_prog_run(bq->xdp_prog, bq->q, cnt, dev);
> > >> > + if (!to_send)
> > >> > + goto out;
> > >> > +
> > >> > + drops = cnt - to_send;
> > >> > + }
> > >> > +
> > >>
> > >> [ ... ]
> > >>
> > >> > static void bq_enqueue(struct net_device *dev, struct xdp_frame *xdpf,
> > >> > - struct net_device *dev_rx)
> > >> > + struct net_device *dev_rx, struct bpf_prog *xdp_prog)
> > >> > {
> > >> > struct list_head *flush_list = this_cpu_ptr(&dev_flush_list);
> > >> > struct xdp_dev_bulk_queue *bq = this_cpu_ptr(dev->xdp_bulkq);
> > >> > @@ -412,18 +466,22 @@ static void bq_enqueue(struct net_device *dev, struct xdp_frame *xdpf,
> > >> > /* Ingress dev_rx will be the same for all xdp_frame's in
> > >> > * bulk_queue, because bq stored per-CPU and must be flushed
> > >> > * from net_device drivers NAPI func end.
> > >> > + *
> > >> > + * Do the same with xdp_prog and flush_list since these fields
> > >> > + * are only ever modified together.
> > >> > */
> > >> > - if (!bq->dev_rx)
> > >> > + if (!bq->dev_rx) {
> > >> > bq->dev_rx = dev_rx;
> > >> > + bq->xdp_prog = xdp_prog;
> > >> bp->xdp_prog is assigned here and could be used later in bq_xmit_all().
> > >> How is bq->xdp_prog protected? Are they all under one rcu_read_lock()?
> > >> It is not very obvious after taking a quick look at xdp_do_flush[_map].
> > >>
> > >> e.g. what if the devmap elem gets deleted.
> > >
> > > Jesper knows better than me. From my veiw, based on the description of
> > > __dev_flush():
> > >
> > > On devmap tear down we ensure the flush list is empty before completing to
> > > ensure all flush operations have completed. When drivers update the bpf
> > > program they may need to ensure any flush ops are also complete.
>
> AFAICT, the bq->xdp_prog is not from the dev. It is from a devmap's elem.
>
> >
> > Yeah, drivers call xdp_do_flush() before exiting their NAPI poll loop,
> > which also runs under one big rcu_read_lock(). So the storage in the
> > bulk queue is quite temporary, it's just used for bulking to increase
> > performance :)
>
> I am missing the one big rcu_read_lock() part. For example, in i40e_txrx.c,
> i40e_run_xdp() has its own rcu_read_lock/unlock(). dst->xdp_prog used to run
> in i40e_run_xdp() and it is fine.
>
> In this patch, dst->xdp_prog is run outside of i40e_run_xdp() where the
> rcu_read_unlock() has already done. It is now run in xdp_do_flush_map().
> or I missed the big rcu_read_lock() in i40e_napi_poll()?
>
> I do see the big rcu_read_lock() in mlx5e_napi_poll().
I believed/assumed xdp_do_flush_map() was already protected under an
rcu_read_lock. As the devmap and cpumap, which get called via
__dev_flush() and __cpu_map_flush(), have multiple RCU objects that we
are operating on.
Perhaps it is a bug in i40e?
We are running in softirq in NAPI context, when xdp_do_flush_map() is
call, which I think means that this CPU will not go-through a RCU grace
period before we exit softirq, so in-practice it should be safe. But
to be correct I do think we need a rcu_read_lock() around this call.
--
Best regards,
Jesper Dangaard Brouer
MSc.CS, Principal Kernel Engineer at Red Hat
LinkedIn: http://www.linkedin.com/in/brouer
next prev parent reply other threads:[~2021-04-15 18:21 UTC|newest]
Thread overview: 39+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-04-14 12:26 [PATCHv7 bpf-next 0/4] xdp: extend xdp_redirect_map with broadcast support Hangbin Liu
2021-04-14 12:26 ` [PATCHv7 bpf-next 1/4] bpf: run devmap xdp_prog on flush instead of bulk enqueue Hangbin Liu
2021-04-15 0:17 ` Martin KaFai Lau
2021-04-15 2:37 ` Hangbin Liu
2021-04-15 9:22 ` Toke Høiland-Jørgensen
2021-04-15 17:35 ` Martin KaFai Lau
2021-04-15 18:21 ` Jesper Dangaard Brouer [this message]
2021-04-15 20:29 ` Toke Høiland-Jørgensen
2021-04-16 0:39 ` Martin KaFai Lau
2021-04-16 10:03 ` Toke Høiland-Jørgensen
2021-04-16 18:20 ` Martin KaFai Lau
2021-04-16 13:45 ` Jesper Dangaard Brouer
2021-04-16 14:35 ` Toke Høiland-Jørgensen
2021-04-16 18:22 ` Martin KaFai Lau
2021-04-17 0:23 ` Paul E. McKenney
2021-04-17 12:27 ` Toke Høiland-Jørgensen
2021-04-19 16:58 ` Paul E. McKenney
2021-04-19 18:12 ` Toke Høiland-Jørgensen
2021-04-19 18:32 ` Paul E. McKenney
2021-04-19 21:21 ` Toke Høiland-Jørgensen
2021-04-19 21:41 ` Paul E. McKenney
2021-04-19 22:16 ` Toke Høiland-Jørgensen
2021-04-19 22:31 ` Paul E. McKenney
2021-04-21 14:24 ` Toke Høiland-Jørgensen
2021-04-21 14:59 ` Paul E. McKenney
2021-04-21 19:59 ` Toke Høiland-Jørgensen
2021-04-21 20:51 ` Paul E. McKenney
2021-04-21 21:10 ` Toke Høiland-Jørgensen
2021-04-21 21:30 ` Paul E. McKenney
2021-04-21 22:00 ` Toke Høiland-Jørgensen
2021-04-21 22:31 ` Paul E. McKenney
2021-04-22 14:30 ` Toke Høiland-Jørgensen
2021-04-14 12:26 ` [PATCHv7 bpf-next 2/4] xdp: extend xdp_redirect_map with broadcast support Hangbin Liu
2021-04-15 0:23 ` Martin KaFai Lau
2021-04-15 2:21 ` Hangbin Liu
2021-04-15 9:29 ` Toke Høiland-Jørgensen
2021-04-14 12:26 ` [PATCHv7 bpf-next 3/4] sample/bpf: add xdp_redirect_map_multi for redirect_map broadcast test Hangbin Liu
2021-04-14 12:26 ` [PATCHv7 bpf-next 4/4] selftests/bpf: add xdp_redirect_multi test Hangbin Liu
2021-04-14 14:16 ` [PATCHv7 bpf-next 0/4] xdp: extend xdp_redirect_map with broadcast support Toke Høiland-Jørgensen
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20210415202132.7b5e8d0d@carbon \
--to=brouer@redhat.com \
--cc=alexei.starovoitov@gmail.com \
--cc=andrii.nakryiko@gmail.com \
--cc=ast@kernel.org \
--cc=bjorn.topel@gmail.com \
--cc=bpf@vger.kernel.org \
--cc=daniel@iogearbox.net \
--cc=dsahern@gmail.com \
--cc=echaudro@redhat.com \
--cc=jbenc@redhat.com \
--cc=john.fastabend@gmail.com \
--cc=kafai@fb.com \
--cc=liuhangbin@gmail.com \
--cc=lorenzo.bianconi@redhat.com \
--cc=maciej.fijalkowski@intel.com \
--cc=netdev@vger.kernel.org \
--cc=toke@redhat.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).