Re: [net-next] tcp: add TCP_INFO status for failed client TFO

[Eric Dumazet]

On 10/21/19 11:49 AM, William Dauchy wrote:
 
> I'm curious what would be the arguments compared to creating a new
> getsockopt() to fetch this data?

Reporting tsval/tsecr values were not well defined and seemed quite 
experimental to me.

TCP fastopen would use 2 unused bits, not real extra cost here.

This is persistent information after the connect(), while your tsval/tsecr 
report
seems quite dynamic stuff can be stale as soon as the info is fetched from the 
kernel.