On Thu, 2009-01-29 at 22:57 -0800, Herbert Xu wrote: > Roland Dreier <[email protected]> wrote: > > > > OK, thanks... what confused me is that several other drivers also do > > skb_linearize() in their hard_start_xmit method... eg bnx2x, > > via-velocity, mv643xx_eth. So there are several other lurking bugs to > > deal with here I guess. > > I don't know about the rest but bnx2x is certainly OK since it > only does so with IRQ enabled. It is legal to call skb_linearize > as long as you're sure that IRQs are enabled, which is always the > case for hard_start_xmit upon entry. > > So the only time you can't call it in hard_start_xmit is if you've > just disabled IRQs yourself. > Thanks Herbert,
That was my conclusion too and even though I was still looking at it since this report yesterday - it still looks OK to me. The bnx2x is getting into this flow when using SAMBA and it was tested on few systems for days under traffic - this does not mean that the code is right and it is not a prove that there is no bug - but it makes me feel better... I would appreciate some comments if someone still thinks this is a bug. Thanks, Eilon _______________________________________________ general mailing list [email protected] http://lists.openfabrics.org/cgi-bin/mailman/listinfo/general To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general
