[PATCH] mac80211: Minor optimization in ieee80211_rx_h_data

[PATCH] mac80211: Minor optimization in ieee80211_rx_h_data

[Helmut Schaa]

Remove a superfluous ieee80211_is_data check as that was checked a few
lines before already and we wont't get here for non-data frames at all.

Second, the frame was already converted to 802.3 header format and
reading the fc and addr1 fields was only possible because the 802.3
header is short enough and didn't overwrite the relevant parts of the
802.11 header. Make the code more obvious by checking the ethernet
header's h_dest field.

Furthermore reorder the conditions to reduce the number of checks
when dynamic powersave is not needed (AP mode for example).

Cc: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: Helmut Schaa <helmut.schaa@googlemail.com>
---

Found via code review, compile tested only.

 net/mac80211/rx.c |    5 ++---
 1 files changed, 2 insertions(+), 3 deletions(-)

diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 9dd60a7..9e44fbf 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -1871,9 +1871,8 @@ ieee80211_rx_h_data(struct ieee80211_rx_data *rx)
 	dev->stats.rx_packets++;
 	dev->stats.rx_bytes += rx->skb->len;
 
-	if (ieee80211_is_data(hdr->frame_control) &&
-	    !is_multicast_ether_addr(hdr->addr1) &&
-	    local->hw.conf.dynamic_ps_timeout > 0 && local->ps_sdata) {
+	if (local->ps_sdata && local->hw.conf.dynamic_ps_timeout > 0 && 
+	    !is_multicast_ether_addr(((struct ethhdr *)rx->skb->data)->h_dest)) {
 			mod_timer(&local->dynamic_ps_timer, jiffies +
 			 msecs_to_jiffies(local->hw.conf.dynamic_ps_timeout));
 	}
-- 
1.7.1

Re: [PATCH] mac80211: Minor optimization in ieee80211_rx_h_data

[Johannes Berg]

On Tue, 2010-11-30 at 12:19 +0100, Helmut Schaa wrote:
> Remove a superfluous ieee80211_is_data check as that was checked a few
> lines before already and we wont't get here for non-data frames at all.
> 
> Second, the frame was already converted to 802.3 header format and
> reading the fc and addr1 fields was only possible because the 802.3
> header is short enough and didn't overwrite the relevant parts of the
> 802.11 header. Make the code more obvious by checking the ethernet
> header's h_dest field.
> 
> Furthermore reorder the conditions to reduce the number of checks
> when dynamic powersave is not needed (AP mode for example).
> 
> Cc: Johannes Berg <johannes@sipsolutions.net>
> Signed-off-by: Helmut Schaa <helmut.schaa@googlemail.com>

Looks sane to me. Indeed if the check was required it should use the
"fc" variable, but clearly it's pointless. Must be some code that got
moved during PS code restructuring...

Reviewed-by: Johannes Berg <johannes@sipsolutions.net>

> ---
> 
> Found via code review, compile tested only.
> 
>  net/mac80211/rx.c |    5 ++---
>  1 files changed, 2 insertions(+), 3 deletions(-)
> 
> diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
> index 9dd60a7..9e44fbf 100644
> --- a/net/mac80211/rx.c
> +++ b/net/mac80211/rx.c
> @@ -1871,9 +1871,8 @@ ieee80211_rx_h_data(struct ieee80211_rx_data *rx)
>  	dev->stats.rx_packets++;
>  	dev->stats.rx_bytes += rx->skb->len;
>  
> -	if (ieee80211_is_data(hdr->frame_control) &&
> -	    !is_multicast_ether_addr(hdr->addr1) &&
> -	    local->hw.conf.dynamic_ps_timeout > 0 && local->ps_sdata) {
> +	if (local->ps_sdata && local->hw.conf.dynamic_ps_timeout > 0 && 
> +	    !is_multicast_ether_addr(((struct ethhdr *)rx->skb->data)->h_dest)) {
>  			mod_timer(&local->dynamic_ps_timer, jiffies +
>  			 msecs_to_jiffies(local->hw.conf.dynamic_ps_timeout));
>  	}