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

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 <redacted>

Not sure if making it "unsinged int" would be better, but this change is
fine to me as is too.

Reviewed-by: Stanislaw Gruszka <redacted>