[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <PAXPR04MB9185B9A02BBC7A861C6B75BA89579@PAXPR04MB9185.eurprd04.prod.outlook.com>
Date: Thu, 29 Sep 2022 13:35:05 +0000
From: Shenwei Wang <shenwei.wang@....com>
To: Andrew Lunn <andrew@...n.ch>
CC: Joakim Zhang <qiangqing.zhang@....com>,
"David S. Miller" <davem@...emloft.net>,
Eric Dumazet <edumazet@...gle.com>,
Jakub Kicinski <kuba@...nel.org>,
Paolo Abeni <pabeni@...hat.com>,
Alexei Starovoitov <ast@...nel.org>,
Daniel Borkmann <daniel@...earbox.net>,
Jesper Dangaard Brouer <hawk@...nel.org>,
John Fastabend <john.fastabend@...il.com>,
"netdev@...r.kernel.org" <netdev@...r.kernel.org>,
"linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
"imx@...ts.linux.dev" <imx@...ts.linux.dev>
Subject: RE: [EXT] Re: [PATCH 1/1] net: fec: add initial XDP support
> -----Original Message-----
> From: Andrew Lunn <andrew@...n.ch>
> Sent: Thursday, September 29, 2022 8:24 AM
> To: Shenwei Wang <shenwei.wang@....com>
> Cc: Joakim Zhang <qiangqing.zhang@....com>; David S. Miller
> <davem@...emloft.net>; Eric Dumazet <edumazet@...gle.com>; Jakub
> Kicinski <kuba@...nel.org>; Paolo Abeni <pabeni@...hat.com>; Alexei
> Starovoitov <ast@...nel.org>; Daniel Borkmann <daniel@...earbox.net>;
> Jesper Dangaard Brouer <hawk@...nel.org>; John Fastabend
> <john.fastabend@...il.com>; netdev@...r.kernel.org; linux-
> kernel@...r.kernel.org; imx@...ts.linux.dev
> Subject: Re: [EXT] Re: [PATCH 1/1] net: fec: add initial XDP support
>
> Caution: EXT Email
>
> > > > +struct fec_enet_xdp_stats {
> > > > + u64 xdp_pass;
> > > > + u64 xdp_drop;
> > > > + u64 xdp_xmit;
> > > > + u64 xdp_redirect;
> > > > + u64 xdp_xmit_err;
> > > > + u64 xdp_tx;
> > > > + u64 xdp_tx_err;
> > > > +};
> > > > +
> > > > + switch (act) {
> > > > + case XDP_PASS:
> > > > + rxq->stats.xdp_pass++;
> > >
> > > Since the stats are u64, and most machines using the FEC are 32 bit,
> > > you cannot just do an increment. Took a look at u64_stats_sync.h.
> > >
> >
>
> > As this increment is only executed under the NAPI kthread context, is
> > the protection still required?
>
> Are the statistics values read by ethtool under NAPI kthread context?
>
You are right. The read is not under NAPI context.
Thanks,
Shenwei
> Andrew
Powered by blists - more mailing lists