[Make-wifi-fast] [PATCH v2] mac80211: Move crypto IV generation to after TXQ dequeue.

[Noah Causin]

Hi,

Thank you and others for all the work you all have done.

I have a question:
How do I apply this to Felix Fietkaus's lede staging branch?

Thank you,

Noah Causin

On 8/17/2016 10:45 AM, Toke Høiland-Jørgensen wrote:
> The FQ portion of the intermediate queues will reorder packets, which
> means that crypto IV generation needs to happen after dequeue when they
> are enabled, or the receiver will throw packets away when receiving
> them.
>
> This fixes the performance regression introduced by enabling softq in
> ath9k.
>
> Cc: Felix Fietkau <nbd at nbd.name>
> Tested-by: Dave Taht <dave at taht.net>
> Signed-off-by: Toke Høiland-Jørgensen <toke at toke.dk>
> ---
> Changes since v1:
>    - Recalculate pn_offs when needed instead of storing it.
>
>   net/mac80211/sta_info.h |  3 +-
>   net/mac80211/tx.c       | 85 +++++++++++++++++++++++++++++++++++++------------
>   2 files changed, 66 insertions(+), 22 deletions(-)
>
> diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h
> index 0556be3..c9d4d69 100644
> --- a/net/mac80211/sta_info.h
> +++ b/net/mac80211/sta_info.h
> @@ -266,7 +266,6 @@ struct sta_ampdu_mlme {
>    * @hdr_len: actual 802.11 header length
>    * @sa_offs: offset of the SA
>    * @da_offs: offset of the DA
> - * @pn_offs: offset where to put PN for crypto (or 0 if not needed)
>    * @band: band this will be transmitted on, for tx_info
>    * @rcu_head: RCU head to free this struct
>    *
> @@ -277,7 +276,7 @@ struct sta_ampdu_mlme {
>   struct ieee80211_fast_tx {
>   	struct ieee80211_key *key;
>   	u8 hdr_len;
> -	u8 sa_offs, da_offs, pn_offs;
> +	u8 sa_offs, da_offs;
>   	u8 band;
>   	u8 hdr[30 + 2 + IEEE80211_FAST_XMIT_MAX_IV +
>   	       sizeof(rfc1042_header)] __aligned(2);
> diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
> index 1d0746d..9caf75f 100644
> --- a/net/mac80211/tx.c
> +++ b/net/mac80211/tx.c
> @@ -1074,6 +1074,64 @@ ieee80211_tx_h_calculate_duration(struct ieee80211_tx_data *tx)
>   	return TX_CONTINUE;
>   }
>   
> +static void ieee80211_gen_crypto_iv(struct ieee80211_key_conf *conf,
> +					   struct sta_info *sta, struct sk_buff *skb)
> +{
> +	struct ieee80211_sub_if_data *sdata;
> +	u64 pn;
> +	u8 *crypto_hdr;
> +	u8 pn_offs = 0;
> +
> +	if (!conf || !sta || !(conf->flags & IEEE80211_KEY_FLAG_GENERATE_IV))
> +		return;
> +
> +	sdata = sta->sdata;
> +
> +	switch (sdata->vif.type) {
> +	case NL80211_IFTYPE_STATION:
> +		if (sdata->u.mgd.use_4addr) {
> +			pn_offs = 30;
> +			break;
> +		}
> +		pn_offs = 24;
> +		break;
> +	case NL80211_IFTYPE_AP_VLAN:
> +		if (sdata->wdev.use_4addr) {
> +			pn_offs = 30;
> +			break;
> +		}
> +		/* fall through */
> +	case NL80211_IFTYPE_ADHOC:
> +	case NL80211_IFTYPE_AP:
> +		pn_offs = 24;
> +		break;
> +	default:
> +		return;
> +	}
> +
> +	if (sta->sta.wme) {
> +		pn_offs += 2;
> +	}
> +
> +	crypto_hdr = skb->data + pn_offs;
> +	switch (conf->cipher) {
> +	case WLAN_CIPHER_SUITE_CCMP:
> +	case WLAN_CIPHER_SUITE_CCMP_256:
> +	case WLAN_CIPHER_SUITE_GCMP:
> +	case WLAN_CIPHER_SUITE_GCMP_256:
> +		pn = atomic64_inc_return(&conf->tx_pn);
> +		crypto_hdr[0] = pn;
> +		crypto_hdr[1] = pn >> 8;
> +		crypto_hdr[4] = pn >> 16;
> +		crypto_hdr[5] = pn >> 24;
> +		crypto_hdr[6] = pn >> 32;
> +		crypto_hdr[7] = pn >> 40;
> +		break;
> +	}
> +}
> +
> +
> +
>   /* actual transmit path */
>   
>   static bool ieee80211_tx_prep_agg(struct ieee80211_tx_data *tx,
> @@ -1503,6 +1561,11 @@ struct sk_buff *ieee80211_tx_dequeue(struct ieee80211_hw *hw,
>   						    sta);
>   		struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
>   
> +		if (info->control.hw_key) {
> +			ieee80211_gen_crypto_iv(info->control.hw_key,
> +			container_of(txq->sta, struct sta_info, sta), skb);
> +		}
> +
>   		hdr->seq_ctrl = ieee80211_tx_next_seq(sta, txq->tid);
>   		if (test_bit(IEEE80211_TXQ_AMPDU, &txqi->flags))
>   			info->flags |= IEEE80211_TX_CTL_AMPDU;
> @@ -2874,7 +2937,6 @@ void ieee80211_check_fast_xmit(struct sta_info *sta)
>   			if (gen_iv) {
>   				(build.hdr + build.hdr_len)[3] =
>   					0x20 | (build.key->conf.keyidx << 6);
> -				build.pn_offs = build.hdr_len;
>   			}
>   			if (gen_iv || iv_spc)
>   				build.hdr_len += IEEE80211_CCMP_HDR_LEN;
> @@ -2885,7 +2947,6 @@ void ieee80211_check_fast_xmit(struct sta_info *sta)
>   			if (gen_iv) {
>   				(build.hdr + build.hdr_len)[3] =
>   					0x20 | (build.key->conf.keyidx << 6);
> -				build.pn_offs = build.hdr_len;
>   			}
>   			if (gen_iv || iv_spc)
>   				build.hdr_len += IEEE80211_GCMP_HDR_LEN;
> @@ -3289,24 +3350,8 @@ static bool ieee80211_xmit_fast(struct ieee80211_sub_if_data *sdata,
>   	sta->tx_stats.bytes[skb_get_queue_mapping(skb)] += skb->len;
>   	sta->tx_stats.packets[skb_get_queue_mapping(skb)]++;
>   
> -	if (fast_tx->pn_offs) {
> -		u64 pn;
> -		u8 *crypto_hdr = skb->data + fast_tx->pn_offs;
> -
> -		switch (fast_tx->key->conf.cipher) {
> -		case WLAN_CIPHER_SUITE_CCMP:
> -		case WLAN_CIPHER_SUITE_CCMP_256:
> -		case WLAN_CIPHER_SUITE_GCMP:
> -		case WLAN_CIPHER_SUITE_GCMP_256:
> -			pn = atomic64_inc_return(&fast_tx->key->conf.tx_pn);
> -			crypto_hdr[0] = pn;
> -			crypto_hdr[1] = pn >> 8;
> -			crypto_hdr[4] = pn >> 16;
> -			crypto_hdr[5] = pn >> 24;
> -			crypto_hdr[6] = pn >> 32;
> -			crypto_hdr[7] = pn >> 40;
> -			break;
> -		}
> +	if (fast_tx->key && !local->ops->wake_tx_queue) {
> +		ieee80211_gen_crypto_iv(&fast_tx->key->conf, sta, skb);
>   	}
>   
>   	if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN)