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 <dan.carpenter@oracle.com>
Reviewed-by: Stanislaw Gruszka <sgruszka@redhat.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>

diff --git a/drivers/net/wireless/ipw2x00/ipw2200.c b/drivers/net/wireless/ipw2x00/ipw2200.c
index 018a8deb88a83b5b2ab2febcc2487b89eeb4ba4f..4fcdac63a3007aff3822e8dd17ccd5db57ce69a6 100644 (file)
--- a/drivers/net/wireless/ipw2x00/ipw2200.c
+++ b/drivers/net/wireless/ipw2x00/ipw2200.c
@@ -7848,7 +7848,7 @@ static void ipw_handle_data_packet_monitor(struct ipw_priv *priv,
         * 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;
@@ -8023,7 +8023,7 @@ static void ipw_handle_promiscuous_rx(struct ipw_priv *priv,
        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;