[PATCH stable 1/3] b43: Fix suspend/resume

[PATCH stable 1/3] b43: Fix suspend/resume

[Michael Buesch]

This patch makes suspend/resume work with the b43 driver.
We must not overwrite the MAC addresses in the init function, as this
would also overwrite the MAC on resume. With an all-zero MAC the device
firmware is not able to ACK any received packets anymore.
Fix this by moving the initializion stuff that must be done on init but
not on resume to the start function.
Also zero out filter_flags to make sure we don't have some flags
from a previous instance for a tiny timeframe until mac80211 reconfigures
them.

Signed-off-by: Michael Buesch <mb@bu3sch.de>

---

This patch is upstream inside of the netdev tree.


Index: linux-2.6.24/drivers/net/wireless/b43/main.c
===================================================================
--- linux-2.6.24.orig/drivers/net/wireless/b43/main.c	2008-01-25 11:48:26.000000000 +0100
+++ linux-2.6.24/drivers/net/wireless/b43/main.c	2008-01-25 11:48:28.000000000 +0100
@@ -3395,8 +3395,6 @@ static int b43_wireless_core_init(struct
 	b43_bluetooth_coext_enable(dev);
 
 	ssb_bus_powerup(bus, 1);	/* Enable dynamic PCTL */
-	memset(wl->bssid, 0, ETH_ALEN);
-	memset(wl->mac_addr, 0, ETH_ALEN);
 	b43_upload_card_macaddress(dev);
 	b43_security_init(dev);
 	b43_rng_init(wl);
@@ -3493,6 +3491,13 @@ static int b43_start(struct ieee80211_hw
 	int did_init = 0;
 	int err = 0;
 
+	/* Kill all old instance specific information to make sure
+	 * the card won't use it in the short timeframe between start
+	 * and mac80211 reconfiguring it. */
+	memset(wl->bssid, 0, ETH_ALEN);
+	memset(wl->mac_addr, 0, ETH_ALEN);
+	wl->filter_flags = 0;
+
 	/* First register RFkill.
 	 * LEDs that are registered later depend on it. */
 	b43_rfkill_init(dev);

Re: [stable] [PATCH stable 1/3] b43: Fix suspend/resume

[Greg KH]

On Fri, Jan 25, 2008 at 12:11:45PM +0100, Michael Buesch wrote:
> This patch makes suspend/resume work with the b43 driver.
> We must not overwrite the MAC addresses in the init function, as this
> would also overwrite the MAC on resume. With an all-zero MAC the device
> firmware is not able to ACK any received packets anymore.
> Fix this by moving the initializion stuff that must be done on init but
> not on resume to the start function.
> Also zero out filter_flags to make sure we don't have some flags
> from a previous instance for a tiny timeframe until mac80211 reconfigures
> them.
> 
> Signed-off-by: Michael Buesch <mb@bu3sch.de>
> 
> ---
> 
> This patch is upstream inside of the netdev tree.

Was this series, and the other one, for .24-stable, or .23-stable?

thanks,

greg k-h

Re: [stable] [PATCH stable 1/3] b43: Fix suspend/resume

[Michael Buesch]

On Thursday 07 February 2008 00:14:31 Greg KH wrote:
> On Fri, Jan 25, 2008 at 12:11:45PM +0100, Michael Buesch wrote:
> > This patch makes suspend/resume work with the b43 driver.
> > We must not overwrite the MAC addresses in the init function, as this
> > would also overwrite the MAC on resume. With an all-zero MAC the device
> > firmware is not able to ACK any received packets anymore.
> > Fix this by moving the initializion stuff that must be done on init but
> > not on resume to the start function.
> > Also zero out filter_flags to make sure we don't have some flags
> > from a previous instance for a tiny timeframe until mac80211 reconfigures
> > them.
> > 
> > Signed-off-by: Michael Buesch <mb@bu3sch.de>
> > 
> > ---
> > 
> > This patch is upstream inside of the netdev tree.
> 
> Was this series, and the other one, for .24-stable, or .23-stable?

This was for .24 stable.
.23 stable didn't have the driver, yet.

-- 
Greetings Michael.

Re: [stable] [PATCH stable 1/3] b43: Fix suspend/resume

[Greg KH]

On Thu, Feb 07, 2008 at 12:39:19AM +0100, Michael Buesch wrote:
> On Thursday 07 February 2008 00:14:31 Greg KH wrote:
> > On Fri, Jan 25, 2008 at 12:11:45PM +0100, Michael Buesch wrote:
> > > This patch makes suspend/resume work with the b43 driver.
> > > We must not overwrite the MAC addresses in the init function, as this
> > > would also overwrite the MAC on resume. With an all-zero MAC the device
> > > firmware is not able to ACK any received packets anymore.
> > > Fix this by moving the initializion stuff that must be done on init but
> > > not on resume to the start function.
> > > Also zero out filter_flags to make sure we don't have some flags
> > > from a previous instance for a tiny timeframe until mac80211 reconfigures
> > > them.
> > > 
> > > Signed-off-by: Michael Buesch <mb@bu3sch.de>
> > > 
> > > ---
> > > 
> > > This patch is upstream inside of the netdev tree.
> > 
> > Was this series, and the other one, for .24-stable, or .23-stable?
> 
> This was for .24 stable.
> .23 stable didn't have the driver, yet.

Great, thanks for letting me know.

greg k-h