On Fri, Jan 13, 2012 at 11:29:09AM +0100, Stanislaw Gruszka wrote: > On Thu, Jan 12, 2012 at 09:34:50AM +0300, Dan Carpenter wrote: > > This is basically just a cleanup. Large positive numbers get counted as > > negative but then get implicitly cast to positive again for the checks > > that matter. > > > > This does make a small difference in ipw_handle_promiscuous_rx() when we > > test "if (unlikely((len + IPW_RX_FRAME_SIZE) > skb_tailroom(rxb->skb)))" > > It should return there, but we don't return until a couple lines later > > when we test "if (len > IPW_RX_BUF_SIZE - sizeof(struct ipw_rt_hdr)) {". > > The difference is that in the second test the sizeof() means that there > > is an implied cast to unsigned. > > Signed-off-by: Dan Carpenter <dan.carpenter@xxxxxxxxxx> > > Not sure if making it "unsinged int" would be better, but this change is > fine to me as is too. Yeah. You're probably right... Next time, I'll do it that way. ;) regards, dan carpenter
Attachment:
signature.asc
Description: Digital signature