Re: [patch] ipw2x00: signedness bug handling frame length

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:

quoted

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 <redacted>

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