> -----Original Message----- > From: Richard Cochran <[email protected]> > Sent: 2021年4月18日 23:06 > To: Y.b. Lu <[email protected]> > Cc: [email protected]; Vladimir Oltean <[email protected]>; > David S . Miller <[email protected]>; Jakub Kicinski <[email protected]>; > Jonathan Corbet <[email protected]>; Kurt Kanzenbach <[email protected]>; > Andrew Lunn <[email protected]>; Vivien Didelot <[email protected]>; > Florian Fainelli <[email protected]>; Claudiu Manoil > <[email protected]>; Alexandre Belloni > <[email protected]>; [email protected]; > [email protected]; [email protected] > Subject: Re: [net-next 1/3] net: dsa: optimize tx timestamp request handling > > On Fri, Apr 16, 2021 at 08:36:53PM +0800, Yangbo Lu wrote: > > Optimization could be done on dsa_skb_tx_timestamp(), and dsa device > > drivers should adapt to it. > > > > - Check SKBTX_HW_TSTAMP request flag at the very beginning, instead of in > > port_txtstamp, so that most skbs not requiring tx timestamp just return. > > > > - No longer to identify PTP packets, and limit tx timestamping only for PTP > > packets. If device driver likes, let device driver do. > > > > - It is a waste to clone skb directly in dsa_skb_tx_timestamp(). > > For one-step timestamping, a clone is not needed. For any failure of > > port_txtstamp (this may usually happen), the skb clone has to be freed. > > So put skb cloning into port_txtstamp where it really needs. > > This patch changes three things ^^^ at once. These are AFAICT independent > changes, and so please break this one patch into three for easier review.
Will split it in next version. Thank you. > > Thanks, > Richard
