[PATCH] mac80211: don't drop frames where skb->len < 24 in ieee80211_scan_rx()

[PATCH] mac80211: don't drop frames where skb->len < 24 in ieee80211_scan_rx()

[Luciano Coelho]

This seems to be a leftover from the old days, when we didn't support
any frames that didn't contain the full ieee802.11 header.  This is
not the case anymore.  It does not cause problems now, because they
are only dropped during scan.  But when scheduled scans get merged,
this would become a problem because we would drop all small frames
while scheduled scan is running.

Cc: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: Luciano Coelho <coelho@ti.com>
---
 net/mac80211/scan.c |    3 ---
 1 files changed, 0 insertions(+), 3 deletions(-)

diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c
index 489b6ad..b7a39c4 100644
--- a/net/mac80211/scan.c
+++ b/net/mac80211/scan.c
@@ -169,9 +169,6 @@ ieee80211_scan_rx(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb)
 	if (ieee80211_is_ctl(fc))
 		return RX_CONTINUE;
 
-	if (skb->len < 24)
-		return RX_DROP_MONITOR;
-
 	presp = ieee80211_is_probe_resp(fc);
 	if (presp) {
 		/* ignore ProbeResp to foreign address */
-- 
1.7.1

Re: [PATCH] mac80211: don't drop frames where skb->len < 24 in ieee80211_scan_rx()

[Johannes Berg]

On Mon, 2011-05-09 at 17:19 +0300, Luciano Coelho wrote:
> This seems to be a leftover from the old days, when we didn't support
> any frames that didn't contain the full ieee802.11 header.  This is
> not the case anymore.  It does not cause problems now, because they
> are only dropped during scan.  But when scheduled scans get merged,
> this would become a problem because we would drop all small frames
> while scheduled scan is running.
> 
> Cc: Johannes Berg <johannes@sipsolutions.net>
> Signed-off-by: Luciano Coelho <coelho@ti.com>
> ---
>  net/mac80211/scan.c |    3 ---
>  1 files changed, 0 insertions(+), 3 deletions(-)
> 
> diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c
> index 489b6ad..b7a39c4 100644
> --- a/net/mac80211/scan.c
> +++ b/net/mac80211/scan.c
> @@ -169,9 +169,6 @@ ieee80211_scan_rx(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb)
>  	if (ieee80211_is_ctl(fc))
>  		return RX_CONTINUE;
>  
> -	if (skb->len < 24)
> -		return RX_DROP_MONITOR;
> -

You can't just delete it, we use mgmt->da at least in this code path.
You should just change RX_DROP_MONITOR to RX_CONTINUe here I think.

johannes

Re: [PATCH] mac80211: don't drop frames where skb->len < 24 in ieee80211_scan_rx()

[Luciano Coelho]

On Mon, 2011-05-09 at 16:46 +0200, Johannes Berg wrote:
> On Mon, 2011-05-09 at 17:19 +0300, Luciano Coelho wrote:
> > This seems to be a leftover from the old days, when we didn't support
> > any frames that didn't contain the full ieee802.11 header.  This is
> > not the case anymore.  It does not cause problems now, because they
> > are only dropped during scan.  But when scheduled scans get merged,
> > this would become a problem because we would drop all small frames
> > while scheduled scan is running.
> > 
> > Cc: Johannes Berg <johannes@sipsolutions.net>
> > Signed-off-by: Luciano Coelho <coelho@ti.com>
> > ---
> >  net/mac80211/scan.c |    3 ---
> >  1 files changed, 0 insertions(+), 3 deletions(-)
> > 
> > diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c
> > index 489b6ad..b7a39c4 100644
> > --- a/net/mac80211/scan.c
> > +++ b/net/mac80211/scan.c
> > @@ -169,9 +169,6 @@ ieee80211_scan_rx(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb)
> >  	if (ieee80211_is_ctl(fc))
> >  		return RX_CONTINUE;
> >  
> > -	if (skb->len < 24)
> > -		return RX_DROP_MONITOR;
> > -
> 
> You can't just delete it, we use mgmt->da at least in this code path.
> You should just change RX_DROP_MONITOR to RX_CONTINUe here I think.

Oops! I did this in a hurry and didn't think.  I'm sending v2 in a sec.

-- 
Cheers,
Luca.

[PATCH v2] mac80211: don't drop frames where skb->len < 24 in ieee80211_scan_rx()

[Luciano Coelho]

This seems to be a leftover from the old days, when we didn't support
any frames that didn't contain the full ieee802.11 header.  This is
not the case anymore.  It does not cause problems now, because they
are only dropped during scan.  But when scheduled scans get merged,
this would become a problem because we would drop all small frames
while scheduled scan is running.

To fix this, return RX_CONTINUE instead of RX_DROP_MONITOR.

Cc: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: Luciano Coelho <coelho@ti.com>
---
 net/mac80211/scan.c |    2 +-
 1 files changed, 1 insertions(+), 1 deletions(-)

diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c
index 489b6ad..8acce72 100644
--- a/net/mac80211/scan.c
+++ b/net/mac80211/scan.c
@@ -170,7 +170,7 @@ ieee80211_scan_rx(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb)
 		return RX_CONTINUE;
 
 	if (skb->len < 24)
-		return RX_DROP_MONITOR;
+		return RX_CONTINUE;
 
 	presp = ieee80211_is_probe_resp(fc);
 	if (presp) {
-- 
1.7.1