netdev - Re: [PATCH net-next] net: netdev_alloc_skb() use build

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

Date:	Mon, 04 Jun 2012 22:05:17 +0200
From:	Eric Dumazet <eric.dumazet@...il.com>
To:	"Michael S. Tsirkin" <mst@...hat.com>
Cc:	Willy Tarreau <w@....eu>, David Miller <davem@...emloft.net>,
	netdev@...r.kernel.org
Subject: Re: [PATCH net-next] net: netdev_alloc_skb() use build_skb()

On Mon, 2012-06-04 at 22:56 +0300, Michael S. Tsirkin wrote:

> And just to explain why I'm asking, if it's OK to
> declare 2K when you use 4K, we can do (effectively):
> 
> +       skb->truesize += PAGE_SIZE * nfrags;
> -       skb->truesize += min(1500, skb->data_len);
> 
> which means with 1500 byte packets we can use
> as much memory as we did before
> 4b727361f0bc7ee7378298941066d8aa15023ffb
> 

How are you sure data_len is >= 1500 ?

If you know that you use a full page for a fragment, then PAGE_SIZE is
better than 1500


If you share a page with 2/4 frames (But not one hundred), you can
assume risk of underestimation is really low.



--
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