ipw2x00: signedness bug handling frame length

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 <[e-mail]>
Reviewed-by: Stanislaw Gruszka <[e-mail]>
Signed-off-by: John W. Linville <[e-mail]>

drivers/net/wireless/ipw2x00/ipw2200.c

···
 	 * more efficiently than we can parse it. ORDER MATTERS HERE */
 	struct ipw_rt_hdr *ipw_rt;
 
-	short len = le16_to_cpu(pkt->u.frame.length);
+	unsigned short len = le16_to_cpu(pkt->u.frame.length);
 
 	/* We received data from the HW, so stop the watchdog */
 	dev->trans_start = jiffies;
···
 	s8 signal = frame->rssi_dbm - IPW_RSSI_TO_DBM;
 	s8 noise = (s8) le16_to_cpu(frame->noise);
 	u8 rate = frame->rate;
-	short len = le16_to_cpu(pkt->u.frame.length);
+	unsigned short len = le16_to_cpu(pkt->u.frame.length);
 	struct sk_buff *skb;
 	int hdr_only = 0;
 	u16 filter = priv->prom_priv->filter;