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>
This commit is contained in:
parent
ccde8a45cb
commit
92c1ff1fa7
1 changed files with 2 additions and 2 deletions
|
@ -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;
|
||||
|
|
Loading…
Reference in a new issue