netdev
[Top] [All Lists]

Re: [PATCH] PKT_SCHED: dsmark must take care of shared/cloned skbs

To: Patrick McHardy <kaber@xxxxxxxxx>
Subject: Re: [PATCH] PKT_SCHED: dsmark must take care of shared/cloned skbs
From: jamal <hadi@xxxxxxxxxx>
Date: 20 Dec 2004 09:13:46 -0500
Cc: Thomas Graf <tgraf@xxxxxxx>, "David S. Miller" <davem@xxxxxxxxxxxxx>, netdev@xxxxxxxxxxx
In-reply-to: <41C687EE.1090205@trash.net>
Organization: jamalopolous
References: <20041218170017.GH17998@postel.suug.ch> <1103487827.1048.188.camel@jzny.localdomain> <20041219203641.GL17998@postel.suug.ch> <41C687EE.1090205@trash.net>
Reply-to: hadi@xxxxxxxxxx
Sender: netdev-bounce@xxxxxxxxxxx
On Mon, 2004-12-20 at 03:06, Patrick McHardy wrote:

> You shouldn't care about IMQ, but we still need to copy the packet
> before modifying it if the data is shared. Otherwise we have a race
> on SMP with AF_PACKET sockets, depending on when the packet is read
> it can be either modified or not.

Certainly not a big deal; shouldnt care if once in a while tcpdump
actually gets to see the real packet that went out the wire.

> Converting dsmark to an action sounds like the best long-term solution.

Indeed; hence my comment to talk to Werner.

cheers,
jamal


<Prev in Thread] Current Thread [Next in Thread>