On Wed, 2009-03-25 at 16:49 +0530, Vasanthakumar Thiagarajan wrote: > On Wed, Mar 25, 2009 at 04:32:53PM +0530, Johannes Berg wrote: > > On Wed, 2009-03-25 at 16:23 +0530, Vasanthakumar Thiagarajan wrote: > > > Currently rx status for frames which are completed from reorder buffer > > > is taken from it's cb area which is wrong, cb is not holding the rx status. > > > This results in dropping almost all frames from reorder buffer when security > > > is enabled by doing double decryption (first in hw, second in sw because of wrong > > > rx status). This patch copies rx status into cb area before the frame is put > > > into reorder buffer. After this patch, there is a significant improvement in > > > throughput with ath9k + WPA2(AES). > > > > Interesting. For ieee80211_rx_irqsafe() packets this is already in the > > cb area. > > right. I will change the commit log. No worries -- just pointing it out -- this is the reason it worked ok with iwlwifi. > This is while completing reorder buffer on reception of BAR. ok... this code is a little convoluted, so I didn't see that at first, thanks. johannes
Attachment:
signature.asc
Description: This is a digitally signed message part
