public inbox for netdev@vger.kernel.org 
 help / color / mirror / Atom feed
From: "Toke Høiland-Jørgensen" <toke@redhat•com>
To: Hangbin Liu <liuhangbin@gmail•com>, Martin KaFai Lau <kafai@fb•com>
Cc: bpf@vger•kernel.org, netdev@vger•kernel.org,
	"Jiri Benc" <jbenc@redhat•com>,
	"Jesper Dangaard Brouer" <brouer@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>
Subject: Re: [PATCHv7 bpf-next 1/4] bpf: run devmap xdp_prog on flush instead of bulk enqueue
Date: Thu, 15 Apr 2021 11:22:19 +0200	[thread overview]
Message-ID: <87o8efkilw.fsf@toke.dk> (raw)
In-Reply-To: <20210415023746.GR2900@Leo-laptop-t470s>

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.

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 :)

-Toke


  reply	other threads:[~2021-04-15  9:22 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 [this message]
2021-04-15 17:35         ` Martin KaFai Lau
2021-04-15 18:21           ` Jesper Dangaard Brouer
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=87o8efkilw.fsf@toke.dk \
    --to=toke@redhat$(echo .)com \
    --cc=alexei.starovoitov@gmail$(echo .)com \
    --cc=andrii.nakryiko@gmail$(echo .)com \
    --cc=ast@kernel$(echo .)org \
    --cc=bjorn.topel@gmail$(echo .)com \
    --cc=bpf@vger$(echo .)kernel.org \
    --cc=brouer@redhat$(echo .)com \
    --cc=daniel@iogearbox$(echo .)net \
    --cc=dsahern@gmail$(echo .)com \
    --cc=echaudro@redhat$(echo .)com \
    --cc=jbenc@redhat$(echo .)com \
    --cc=john.fastabend@gmail$(echo .)com \
    --cc=kafai@fb$(echo .)com \
    --cc=liuhangbin@gmail$(echo .)com \
    --cc=lorenzo.bianconi@redhat$(echo .)com \
    --cc=maciej.fijalkowski@intel$(echo .)com \
    --cc=netdev@vger$(echo .)kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html
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