netdev - Re: [RFC PATCH 1/2] [TCP]: Add highest_sack seqno, points to globally highest SACK

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [day] [month] [year] [list]

Date:	Thu, 8 Mar 2007 16:58:00 +0200 (EET)
From:	"Ilpo Järvinen" <ilpo.jarvinen@...sinki.fi>
To:	Baruch Even <baruch@...en.org>
cc:	David Miller <davem@...emloft.net>, netdev@...r.kernel.org
Subject: Re: [RFC PATCH 1/2] [TCP]: Add highest_sack seqno, points to globally
 highest SACK

On Thu, 8 Mar 2007, Ilpo Järvinen wrote:

> It is maintained only in during slowpath of tcp_ack().

I think I'll change this to do the forced synchronization of the 
highest_sack to snd_una in sacktag_write_queue when tp->sacked_out is zero 
during entry, which should be much simpler than the current approach.
...and then use if (!tp->sacked_out) to select between snd_una and 
highest_sack entry in the scoreboard updater...

-- 
 i.