netdev - Re: [CRIU] linux-next: WARNING: CPU: 0 PID: 2825 at net/ipv4/tcp_input.c:3078 tcp

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]

Message-ID: <1407772520.10122.38.camel@edumazet-glaptop2.roam.corp.google.com>
Date:	Mon, 11 Aug 2014 17:55:20 +0200
From:	Eric Dumazet <eric.dumazet@...il.com>
To:	Andrew Vagin <avagin@...allels.com>
Cc:	Andrey Wagin <avagin@...il.com>,
	"criu@...nvz.org" <criu@...nvz.org>, netdev@...r.kernel.org,
	Pavel Emelyanov <xemul@...allels.com>
Subject: Re: [CRIU] linux-next: WARNING: CPU: 0 PID: 2825 at
 net/ipv4/tcp_input.c:3078 tcp_ack+0x11f5/0x1380()

On Mon, 2014-08-11 at 19:37 +0400, Andrew Vagin wrote:

> Yes, it does. We hope that tcp code will fix rtt according with next
> packages.

I don't think its the right way.

You only used cubic, but some congestion modules heavily depends on rtt.

Cleaner way would be to not try to use wrong RTT estimations in the
first place.

skb_mstamp being NULL is exactly the mark of skb that should not
participate in the rtt estimations.

(or use a new flag , included in TCPCB_RETRANS )


--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html