ath10k: report estimated frame transmit airtime to improve fairness

The airtime of a transmitted frame will be estimated from last used tx rate
which the firmware reports with the peer stats feature
(WMI_SERVICE_PEER_STATS). The airtime is computed on the tx path and it
will be reported to mac80211 upon tx completion.

This change is based on Kan's orginal commit in Chromium tree
("CHROMIUM: ath10k: Implementing airtime fairness based TX scheduler")
ref: https://chromium-review.googlesource.com/588190

Tested on QCA4019 with firmware version 10.4-3.2.1.1-00015
Tested on QCA9984 with firmware version 10.4-3.9.0.1-00005
Signed-off-by: Kan Yan <kyan@google.com>
[rmanohar@codeaurora.org: ported only the airtime computation]
Signed-off-by: Rajkumar Manoharan <rmanohar@codeaurora.org>
[toke@redhat.com: Rebase to mac80211-next, add test note]
Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>

drivers/net/wireless/ath/ath10k/core.h

@@ -126,6 +126,7 @@ struct ath10k_skb_cb {
 	u8 flags;
 	u8 eid;
 	u16 msdu_id;
+	u16 airtime_est;
 	struct ieee80211_vif *vif;
 	struct ieee80211_txq *txq;
 } __packed;
@@ -498,6 +499,7 @@ struct ath10k_sta {
 	u16 peer_id;
 	struct rate_info txrate;
 	struct ieee80211_tx_info tx_info;
+	u32 last_tx_bitrate;
 
 	struct work_struct update_wk;
 	u64 rx_duration;

drivers/net/wireless/ath/ath10k/htt_rx.c

@@ -3080,6 +3080,7 @@ ath10k_update_per_peer_tx_stats(struct ath10k *ar,
 
 	arsta->txrate.nss = txrate.nss;
 	arsta->txrate.bw = ath10k_bw_to_mac80211_bw(txrate.bw);
+	arsta->last_tx_bitrate = cfg80211_calculate_bitrate(&arsta->txrate);
 	if (sgi)
 		arsta->txrate.flags |= RATE_INFO_FLAGS_SHORT_GI;
 

drivers/net/wireless/ath/ath10k/mac.c

@@ -3544,7 +3544,7 @@ static void ath10k_tx_h_add_p2p_noa_ie(struct ath10k *ar,
 static void ath10k_mac_tx_h_fill_cb(struct ath10k *ar,
 				    struct ieee80211_vif *vif,
 				    struct ieee80211_txq *txq,
-				    struct sk_buff *skb)
+				    struct sk_buff *skb, u16 airtime)
 {
 	struct ieee80211_hdr *hdr = (void *)skb->data;
 	struct ath10k_skb_cb *cb = ATH10K_SKB_CB(skb);
@@ -3561,6 +3561,7 @@ static void ath10k_mac_tx_h_fill_cb(struct ath10k *ar,
 
 	cb->vif = vif;
 	cb->txq = txq;
+	cb->airtime_est = airtime;
 }
 
 bool ath10k_mac_tx_frm_has_freq(struct ath10k *ar)
@@ -3948,6 +3949,49 @@ static bool ath10k_mac_tx_can_push(struct ieee80211_hw *hw,
 	return false;
 }
 
+/* Return estimated airtime in microsecond, which is calculated using last
+ * reported TX rate. This is just a rough estimation because host driver has no
+ * knowledge of the actual transmit rate, retries or aggregation. If actual
+ * airtime can be reported by firmware, then delta between estimated and actual
+ * airtime can be adjusted from deficit.
+ */
+#define IEEE80211_ATF_OVERHEAD		100	/* IFS + some slot time */
+#define IEEE80211_ATF_OVERHEAD_IFS	16	/* IFS only */
+static u16 ath10k_mac_update_airtime(struct ath10k *ar,
+				     struct ieee80211_txq *txq,
+				     struct sk_buff *skb)
+{
+	struct ath10k_sta *arsta;
+	u32 pktlen;
+	u16 airtime = 0;
+
+	if (!txq || !txq->sta)
+		return airtime;
+
+	spin_lock_bh(&ar->data_lock);
+	arsta = (struct ath10k_sta *)txq->sta->drv_priv;
+
+	pktlen = skb->len + 38; /* Assume MAC header 30, SNAP 8 for most case */
+	if (arsta->last_tx_bitrate) {
+		/* airtime in us, last_tx_bitrate in 100kbps */
+		airtime = (pktlen * 8 * (1000 / 100))
+				/ arsta->last_tx_bitrate;
+		/* overhead for media access time and IFS */
+		airtime += IEEE80211_ATF_OVERHEAD_IFS;
+	} else {
+		/* This is mostly for throttle excessive BC/MC frames, and the
+		 * airtime/rate doesn't need be exact. Airtime of BC/MC frames
+		 * in 2G get some discount, which helps prevent very low rate
+		 * frames from being blocked for too long.
+		 */
+		airtime = (pktlen * 8 * (1000 / 100)) / 60; /* 6M */
+		airtime += IEEE80211_ATF_OVERHEAD;
+	}
+	spin_unlock_bh(&ar->data_lock);
+
+	return airtime;
+}
+
 int ath10k_mac_tx_push_txq(struct ieee80211_hw *hw,
 			   struct ieee80211_txq *txq)
 {
@@ -3963,6 +4007,7 @@ int ath10k_mac_tx_push_txq(struct ieee80211_hw *hw,
 	size_t skb_len;
 	bool is_mgmt, is_presp;
 	int ret;
+	u16 airtime;
 
 	spin_lock_bh(&ar->htt.tx_lock);
 	ret = ath10k_htt_tx_inc_pending(htt);
@@ -3980,7 +4025,8 @@ int ath10k_mac_tx_push_txq(struct ieee80211_hw *hw,
 		return -ENOENT;
 	}
 
-	ath10k_mac_tx_h_fill_cb(ar, vif, txq, skb);
+	airtime = ath10k_mac_update_airtime(ar, txq, skb);
+	ath10k_mac_tx_h_fill_cb(ar, vif, txq, skb, airtime);
 
 	skb_len = skb->len;
 	txmode = ath10k_mac_tx_h_get_txmode(ar, vif, sta, skb);
@@ -4247,8 +4293,10 @@ static void ath10k_mac_op_tx(struct ieee80211_hw *hw,
 	bool is_mgmt;
 	bool is_presp;
 	int ret;
+	u16 airtime;
 
-	ath10k_mac_tx_h_fill_cb(ar, vif, txq, skb);
+	airtime = ath10k_mac_update_airtime(ar, txq, skb);
+	ath10k_mac_tx_h_fill_cb(ar, vif, txq, skb, airtime);
 
 	txmode = ath10k_mac_tx_h_get_txmode(ar, vif, sta, skb);
 	txpath = ath10k_mac_tx_h_get_txpath(ar, skb, txmode);
@@ -8604,6 +8652,9 @@ int ath10k_mac_register(struct ath10k *ar)
 		wiphy_ext_feature_set(ar->hw->wiphy,
 				      NL80211_EXT_FEATURE_ACK_SIGNAL_SUPPORT);
 
+	if (ath10k_peer_stats_enabled(ar))
+		wiphy_ext_feature_set(ar->hw->wiphy,
+				      NL80211_EXT_FEATURE_AIRTIME_FAIRNESS);
 	/*
 	 * on LL hardware queues are managed entirely by the FW
 	 * so we only advertise to mac we can do the queues thing

drivers/net/wireless/ath/ath10k/txrx.c

@@ -95,6 +95,10 @@ int ath10k_txrx_tx_unref(struct ath10k_htt *htt,
 		wake_up(&htt->empty_tx_wq);
 	spin_unlock_bh(&htt->tx_lock);
 
+	if (txq && txq->sta)
+		ieee80211_sta_register_airtime(txq->sta, txq->tid,
+					       skb_cb->airtime_est, 0);
+
 	if (ar->bus_param.dev_type != ATH10K_DEV_TYPE_HL)
 		dma_unmap_single(dev, skb_cb->paddr, msdu->len, DMA_TO_DEVICE);