[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <1358262467.8744.5772.camel@edumazet-glaptop>
Date: Tue, 15 Jan 2013 07:07:47 -0800
From: Eric Dumazet <eric.dumazet@...il.com>
To: Yuval Mintz <yuvalmin@...adcom.com>
Cc: davem@...emloft.net, netdev@...r.kernel.org, eilong@...adcom.com,
ariele@...adcom.com
Subject: Re: [PATCH net-next 09/10] bnx2x: Added FW GRO bridging support
On Tue, 2013-01-15 at 16:02 +0200, Yuval Mintz wrote:
> >>> bnx2x not setting gso_segs means that qdisc accounting on ingress is
> >>> completely wrong.
> >>
> >> Notice this behaviour was not introduced in this patch -
> >>
> >> ...
> >>
> >> We could either:
> >> 1. Continue with this patch, later sending a patch correcting gso_segs,
> >> as this is not a new issue.
> >> 2. Send a V2 patch-series which will also set gso_segs correctly.
> >
> > I am fine with any solution, as long as we fix the problem.
>
> Eric - Thanks.
> Just to be certain - gso_segs should hold the number of non-aggregated packets
> contained in the skb's frags, right?
Thats right
If the FW doesnt provide the info, you could for example do :
shinfo->gso_segs = DIV_ROUND_UP(skb->len - hdr_len, shinfo->gso_size);
(hdr_len being the length of all headers (ethernet+network+TCP))
--
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
Powered by blists - more mailing lists