1 files changed, 91 insertions, 44 deletions

diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index cd332e3e1134..e0ccee23fbcd 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -214,6 +214,7 @@ ieee80211_tx_h_dynamic_ps(struct ieee80211_tx_data *tx)
 {
 	struct ieee80211_local *local = tx->local;
 	struct ieee80211_if_managed *ifmgd;
+	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(tx->skb);
 
 	/* driver doesn't support power save */
 	if (!ieee80211_hw_check(&local->hw, SUPPORTS_PS))
@@ -242,6 +243,9 @@ ieee80211_tx_h_dynamic_ps(struct ieee80211_tx_data *tx)
 	if (tx->sdata->vif.type != NL80211_IFTYPE_STATION)
 		return TX_CONTINUE;
 
+	if (unlikely(info->flags & IEEE80211_TX_INTFL_OFFCHAN_TX_OK))
+		return TX_CONTINUE;
+
 	ifmgd = &tx->sdata->u.mgd;
 
 	/*
@@ -1249,10 +1253,18 @@ static struct txq_info *ieee80211_get_txq(struct ieee80211_local *local,
 	    (info->control.flags & IEEE80211_TX_CTRL_PS_RESPONSE))
 		return NULL;
 
-	if (!ieee80211_is_data_present(hdr->frame_control))
-		return NULL;
-
-	if (sta) {
+	if (unlikely(!ieee80211_is_data_present(hdr->frame_control))) {
+		if ((!ieee80211_is_mgmt(hdr->frame_control) ||
+		     ieee80211_is_bufferable_mmpdu(hdr->frame_control) ||
+		     vif->type == NL80211_IFTYPE_STATION) &&
+		    sta && sta->uploaded) {
+			/*
+			 * This will be NULL if the driver didn't set the
+			 * opt-in hardware flag.
+			 */
+			txq = sta->sta.txq[IEEE80211_NUM_TIDS];
+		}
+	} else if (sta) {
 		u8 tid = skb->priority & IEEE80211_QOS_CTL_TID_MASK;
 
 		if (!sta->uploaded)
@@ -1440,16 +1452,33 @@ void ieee80211_txq_init(struct ieee80211_sub_if_data *sdata,
 
 	txqi->txq.vif = &sdata->vif;
 
-	if (sta) {
-		txqi->txq.sta = &sta->sta;
-		sta->sta.txq[tid] = &txqi->txq;
-		txqi->txq.tid = tid;
-		txqi->txq.ac = ieee80211_ac_from_tid(tid);
-	} else {
+	if (!sta) {
 		sdata->vif.txq = &txqi->txq;
 		txqi->txq.tid = 0;
 		txqi->txq.ac = IEEE80211_AC_BE;
+
+		return;
+	}
+
+	if (tid == IEEE80211_NUM_TIDS) {
+		if (sdata->vif.type == NL80211_IFTYPE_STATION) {
+			/* Drivers need to opt in to the management MPDU TXQ */
+			if (!ieee80211_hw_check(&sdata->local->hw,
+						STA_MMPDU_TXQ))
+				return;
+		} else if (!ieee80211_hw_check(&sdata->local->hw,
+					       BUFF_MMPDU_TXQ)) {
+			/* Drivers need to opt in to the bufferable MMPDU TXQ */
+			return;
+		}
+		txqi->txq.ac = IEEE80211_AC_VO;
+	} else {
+		txqi->txq.ac = ieee80211_ac_from_tid(tid);
 	}
+
+	txqi->txq.sta = &sta->sta;
+	txqi->txq.tid = tid;
+	sta->sta.txq[tid] = &txqi->txq;
 }
 
 void ieee80211_txq_purge(struct ieee80211_local *local,
@@ -1890,7 +1919,7 @@ static bool ieee80211_tx(struct ieee80211_sub_if_data *sdata,
 			sdata->vif.hw_queue[skb_get_queue_mapping(skb)];
 
 	if (invoke_tx_handlers_early(&tx))
-		return false;
+		return true;
 
 	if (ieee80211_queue_skb(local, sdata, tx.sta, tx.skb))
 		return true;
@@ -2951,6 +2980,10 @@ void ieee80211_check_fast_xmit(struct sta_info *sta)
 		if (!(build.key->flags & KEY_FLAG_UPLOADED_TO_HARDWARE))
 			goto out;
 
+		/* Key is being removed */
+		if (build.key->flags & KEY_FLAG_TAINTED)
+			goto out;
+
 		switch (build.key->conf.cipher) {
 		case WLAN_CIPHER_SUITE_CCMP:
 		case WLAN_CIPHER_SUITE_CCMP_256:
@@ -3078,27 +3111,18 @@ void ieee80211_clear_fast_xmit(struct sta_info *sta)
 }
 
 static bool ieee80211_amsdu_realloc_pad(struct ieee80211_local *local,
-					struct sk_buff *skb, int headroom,
-					int *subframe_len)
+					struct sk_buff *skb, int headroom)
 {
-	int amsdu_len = *subframe_len + sizeof(struct ethhdr);
-	int padding = (4 - amsdu_len) & 3;
-
-	if (skb_headroom(skb) < headroom || skb_tailroom(skb) < padding) {
+	if (skb_headroom(skb) < headroom) {
 		I802_DEBUG_INC(local->tx_expand_skb_head);
 
-		if (pskb_expand_head(skb, headroom, padding, GFP_ATOMIC)) {
+		if (pskb_expand_head(skb, headroom, 0, GFP_ATOMIC)) {
 			wiphy_debug(local->hw.wiphy,
 				    "failed to reallocate TX buffer\n");
 			return false;
 		}
 	}
 
-	if (padding) {
-		*subframe_len += padding;
-		skb_put_zero(skb, padding);
-	}
-
 	return true;
 }
 
@@ -3122,8 +3146,7 @@ static bool ieee80211_amsdu_prepare_head(struct ieee80211_sub_if_data *sdata,
 	if (info->control.flags & IEEE80211_TX_CTRL_AMSDU)
 		return true;
 
-	if (!ieee80211_amsdu_realloc_pad(local, skb, sizeof(*amsdu_hdr),
-					 &subframe_len))
+	if (!ieee80211_amsdu_realloc_pad(local, skb, sizeof(*amsdu_hdr)))
 		return false;
 
 	data = skb_push(skb, sizeof(*amsdu_hdr));
@@ -3189,7 +3212,8 @@ static bool ieee80211_amsdu_aggregate(struct ieee80211_sub_if_data *sdata,
 	void *data;
 	bool ret = false;
 	unsigned int orig_len;
-	int n = 1, nfrags;
+	int n = 2, nfrags, pad = 0;
+	u16 hdrlen;
 
 	if (!ieee80211_hw_check(&local->hw, TX_AMSDU))
 		return false;
@@ -3205,6 +3229,10 @@ static bool ieee80211_amsdu_aggregate(struct ieee80211_sub_if_data *sdata,
 		max_amsdu_len = min_t(int, max_amsdu_len,
 				      sta->sta.max_rc_amsdu_len);
 
+	if (sta->sta.max_tid_amsdu_len[tid])
+		max_amsdu_len = min_t(int, max_amsdu_len,
+				      sta->sta.max_tid_amsdu_len[tid]);
+
 	spin_lock_bh(&fq->lock);
 
 	/* TODO: Ideally aggregation should be done on dequeue to remain
@@ -3222,9 +3250,6 @@ static bool ieee80211_amsdu_aggregate(struct ieee80211_sub_if_data *sdata,
 	if (skb->len + head->len > max_amsdu_len)
 		goto out;
 
-	if (!ieee80211_amsdu_prepare_head(sdata, fast_tx, head))
-		goto out;
-
 	nfrags = 1 + skb_shinfo(skb)->nr_frags;
 	nfrags += 1 + skb_shinfo(head)->nr_frags;
 	frag_tail = &skb_shinfo(head)->frag_list;
@@ -3240,10 +3265,27 @@ static bool ieee80211_amsdu_aggregate(struct ieee80211_sub_if_data *sdata,
 	if (max_frags && nfrags > max_frags)
 		goto out;
 
-	if (!ieee80211_amsdu_realloc_pad(local, skb, sizeof(rfc1042_header) + 2,
-					 &subframe_len))
+	if (!drv_can_aggregate_in_amsdu(local, head, skb))
+		goto out;
+
+	if (!ieee80211_amsdu_prepare_head(sdata, fast_tx, head))
 		goto out;
 
+	/*
+	 * Pad out the previous subframe to a multiple of 4 by adding the
+	 * padding to the next one, that's being added. Note that head->len
+	 * is the length of the full A-MSDU, but that works since each time
+	 * we add a new subframe we pad out the previous one to a multiple
+	 * of 4 and thus it no longer matters in the next round.
+	 */
+	hdrlen = fast_tx->hdr_len - sizeof(rfc1042_header);
+	if ((head->len - hdrlen) & 3)
+		pad = 4 - ((head->len - hdrlen) & 3);
+
+	if (!ieee80211_amsdu_realloc_pad(local, skb, sizeof(rfc1042_header) +
+						     2 + pad))
+		goto out_recalc;
+
 	ret = true;
 	data = skb_push(skb, ETH_ALEN + 2);
 	memmove(data, data + ETH_ALEN + 2, 2 * ETH_ALEN);
@@ -3253,15 +3295,19 @@ static bool ieee80211_amsdu_aggregate(struct ieee80211_sub_if_data *sdata,
 	memcpy(data, &len, 2);
 	memcpy(data + 2, rfc1042_header, sizeof(rfc1042_header));
 
+	memset(skb_push(skb, pad), 0, pad);
+
 	head->len += skb->len;
 	head->data_len += skb->len;
 	*frag_tail = skb;
 
-	flow->backlog += head->len - orig_len;
-	tin->backlog_bytes += head->len - orig_len;
-
-	fq_recalc_backlog(fq, tin, flow);
+out_recalc:
+	if (head->len != orig_len) {
+		flow->backlog += head->len - orig_len;
+		tin->backlog_bytes += head->len - orig_len;
 
+		fq_recalc_backlog(fq, tin, flow);
+	}
 out:
 	spin_unlock_bh(&fq->lock);
 
@@ -3466,12 +3512,18 @@ struct sk_buff *ieee80211_tx_dequeue(struct ieee80211_hw *hw,
 	struct ieee80211_tx_info *info;
 	struct ieee80211_tx_data tx;
 	ieee80211_tx_result r;
-	struct ieee80211_vif *vif;
+	struct ieee80211_vif *vif = txq->vif;
 
 	spin_lock_bh(&fq->lock);
 
-	if (test_bit(IEEE80211_TXQ_STOP, &txqi->flags))
+	if (test_bit(IEEE80211_TXQ_STOP, &txqi->flags) ||
+	    test_bit(IEEE80211_TXQ_STOP_NETIF_TX, &txqi->flags))
+		goto out;
+
+	if (vif->txqs_stopped[ieee80211_ac_from_tid(txq->tid)]) {
+		set_bit(IEEE80211_TXQ_STOP_NETIF_TX, &txqi->flags);
 		goto out;
+	}
 
 	/* Make sure fragments stay together. */
 	skb = __skb_dequeue(&txqi->frags);
@@ -3567,6 +3619,7 @@ begin:
 	}
 
 	IEEE80211_SKB_CB(skb)->control.vif = vif;
+
 out:
 	spin_unlock_bh(&fq->lock);
 
@@ -3595,13 +3648,7 @@ void __ieee80211_subif_start_xmit(struct sk_buff *skb,
 	if (!IS_ERR_OR_NULL(sta)) {
 		struct ieee80211_fast_tx *fast_tx;
 
-		/* We need a bit of data queued to build aggregates properly, so
-		 * instruct the TCP stack to allow more than a single ms of data
-		 * to be queued in the stack. The value is a bit-shift of 1
-		 * second, so 8 is ~4ms of queued data. Only affects local TCP
-		 * sockets.
-		 */
-		sk_pacing_shift_update(skb->sk, 8);
+		sk_pacing_shift_update(skb->sk, sdata->local->hw.tx_sk_pacing_shift);
 
 		fast_tx = rcu_dereference(sta->fast_tx);