ath10k: decouple HTT TX completions

Until now the all MSDU transfer related structures
were freed when all resources were unreferenced.

Now HTC transfer is freed independently and HTT
transfer is so too.

This yields a way more simpler ath10k_skb_cb and
should possibly enable parallel pipe processing
(which is now serialized in
ath10k_pci_process_ce routine).
Signed-off-by: Michal Kazior <michal.kazior@tieto.com>
Signed-off-by: Kalle Valo <kvalo@qca.qualcomm.com>

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

@@ -52,18 +52,10 @@ struct ath10k_skb_cb {
 
 	struct {
 		u8 vdev_id;
-		u16 msdu_id;
 		u8 tid;
 		bool is_offchan;
-		bool is_conf;
-		bool discard;
-		bool no_ack;
-		u8 refcount;
 		struct sk_buff *txfrag;
-		struct sk_buff *msdu;
 	} __packed htt;
-
-	/* 4 bytes left on 64bit arch */
 } __packed;
 
 static inline struct ath10k_skb_cb *ATH10K_SKB_CB(struct sk_buff *skb)

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

@@ -1140,7 +1140,7 @@ void ath10k_htt_t2h_msg_handler(struct ath10k *ar, struct sk_buff *skb)
 			break;
 		}
 
-		ath10k_txrx_tx_completed(htt, &tx_done);
+		ath10k_txrx_tx_unref(htt, &tx_done);
 		break;
 	}
 	case HTT_T2H_MSG_TYPE_TX_COMPL_IND: {
@@ -1174,7 +1174,7 @@ void ath10k_htt_t2h_msg_handler(struct ath10k *ar, struct sk_buff *skb)
 		for (i = 0; i < resp->data_tx_completion.num_msdus; i++) {
 			msdu_id = resp->data_tx_completion.msdus[i];
 			tx_done.msdu_id = __le16_to_cpu(msdu_id);
-			ath10k_txrx_tx_completed(htt, &tx_done);
+			ath10k_txrx_tx_unref(htt, &tx_done);
 		}
 		break;
 	}

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

@@ -117,7 +117,7 @@ int ath10k_htt_tx_attach(struct ath10k_htt *htt)
 
 static void ath10k_htt_tx_cleanup_pending(struct ath10k_htt *htt)
 {
-	struct sk_buff *txdesc;
+	struct htt_tx_done tx_done = {0};
 	int msdu_id;
 
 	/* No locks needed. Called after communication with the device has
@@ -127,18 +127,13 @@ static void ath10k_htt_tx_cleanup_pending(struct ath10k_htt *htt)
 		if (!test_bit(msdu_id, htt->used_msdu_ids))
 			continue;
 
-		txdesc = htt->pending_tx[msdu_id];
-		if (!txdesc)
-			continue;
-
 		ath10k_dbg(ATH10K_DBG_HTT, "force cleanup msdu_id %hu\n",
 			   msdu_id);
 
-		if (ATH10K_SKB_CB(txdesc)->htt.refcount > 0)
-			ATH10K_SKB_CB(txdesc)->htt.refcount = 1;
+		tx_done.discard = 1;
+		tx_done.msdu_id = msdu_id;
 
-		ATH10K_SKB_CB(txdesc)->htt.discard = true;
-		ath10k_txrx_tx_unref(htt, txdesc);
+		ath10k_txrx_tx_unref(htt, &tx_done);
 	}
 }
 
@@ -152,26 +147,7 @@ void ath10k_htt_tx_detach(struct ath10k_htt *htt)
 
 void ath10k_htt_htc_tx_complete(struct ath10k *ar, struct sk_buff *skb)
 {
-	struct ath10k_skb_cb *skb_cb = ATH10K_SKB_CB(skb);
-	struct ath10k_htt *htt = &ar->htt;
-
-	if (skb_cb->htt.is_conf) {
 	dev_kfree_skb_any(skb);
-		return;
-	}
-
-	if (skb_cb->is_aborted) {
-		skb_cb->htt.discard = true;
-
-		/* if the skbuff is aborted we need to make sure we'll free up
-		 * the tx resources, we can't simply run tx_unref() 2 times
-		 * because if htt tx completion came in earlier we'd access
-		 * unallocated memory */
-		if (skb_cb->htt.refcount > 1)
-			skb_cb->htt.refcount = 1;
-	}
-
-	ath10k_txrx_tx_unref(htt, skb);
 }
 
 int ath10k_htt_h2t_ver_req_msg(struct ath10k_htt *htt)
@@ -192,8 +168,6 @@ int ath10k_htt_h2t_ver_req_msg(struct ath10k_htt *htt)
 	cmd = (struct htt_cmd *)skb->data;
 	cmd->hdr.msg_type = HTT_H2T_MSG_TYPE_VERSION_REQ;
 
-	ATH10K_SKB_CB(skb)->htt.is_conf = true;
-
 	ret = ath10k_htc_send(&htt->ar->htc, htt->eid, skb);
 	if (ret) {
 		dev_kfree_skb_any(skb);
@@ -233,8 +207,6 @@ int ath10k_htt_h2t_stats_req(struct ath10k_htt *htt, u8 mask, u64 cookie)
 	req->cookie_lsb = cpu_to_le32(cookie & 0xffffffff);
 	req->cookie_msb = cpu_to_le32((cookie & 0xffffffff00000000ULL) >> 32);
 
-	ATH10K_SKB_CB(skb)->htt.is_conf = true;
-
 	ret = ath10k_htc_send(&htt->ar->htc, htt->eid, skb);
 	if (ret) {
 		ath10k_warn("failed to send htt type stats request: %d", ret);
@@ -321,8 +293,6 @@ int ath10k_htt_send_rx_ring_cfg_ll(struct ath10k_htt *htt)
 
 #undef desc_offset
 
-	ATH10K_SKB_CB(skb)->htt.is_conf = true;
-
 	ret = ath10k_htc_send(&htt->ar->htc, htt->eid, skb);
 	if (ret) {
 		dev_kfree_skb_any(skb);
@@ -335,7 +305,6 @@ int ath10k_htt_send_rx_ring_cfg_ll(struct ath10k_htt *htt)
 int ath10k_htt_mgmt_tx(struct ath10k_htt *htt, struct sk_buff *msdu)
 {
 	struct device *dev = htt->ar->dev;
-	struct ath10k_skb_cb *skb_cb;
 	struct sk_buff *txdesc = NULL;
 	struct htt_cmd *cmd;
 	u8 vdev_id = ATH10K_SKB_CB(msdu)->htt.vdev_id;
@@ -364,7 +333,7 @@ int ath10k_htt_mgmt_tx(struct ath10k_htt *htt, struct sk_buff *msdu)
 		res = msdu_id;
 		goto err;
 	}
-	htt->pending_tx[msdu_id] = txdesc;
+	htt->pending_tx[msdu_id] = msdu;
 	spin_unlock_bh(&htt->tx_lock);
 
 	res = ath10k_skb_map(dev, msdu);
@@ -381,15 +350,6 @@ int ath10k_htt_mgmt_tx(struct ath10k_htt *htt, struct sk_buff *msdu)
 	memcpy(cmd->mgmt_tx.hdr, msdu->data,
 	       min_t(int, msdu->len, HTT_MGMT_FRM_HDR_DOWNLOAD_LEN));
 
-	/* refcount is decremented by HTC and HTT completions until it reaches
-	 * zero and is freed */
-	skb_cb = ATH10K_SKB_CB(txdesc);
-	skb_cb->htt.is_conf = false;
-	skb_cb->htt.msdu_id = msdu_id;
-	skb_cb->htt.refcount = 2;
-	skb_cb->htt.msdu = msdu;
-	skb_cb->htt.txfrag = NULL;
-
 	res = ath10k_htc_send(&htt->ar->htc, htt->eid, txdesc);
 	if (res)
 		goto err;
@@ -417,7 +377,6 @@ int ath10k_htt_tx(struct ath10k_htt *htt, struct sk_buff *msdu)
 	struct htt_cmd *cmd;
 	struct htt_data_tx_desc_frag *tx_frags;
 	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)msdu->data;
-	struct ath10k_skb_cb *skb_cb;
 	struct sk_buff *txdesc = NULL;
 	struct sk_buff *txfrag = NULL;
 	u8 vdev_id = ATH10K_SKB_CB(msdu)->htt.vdev_id;
@@ -470,7 +429,7 @@ int ath10k_htt_tx(struct ath10k_htt *htt, struct sk_buff *msdu)
 		res = msdu_id;
 		goto err;
 	}
-	htt->pending_tx[msdu_id] = txdesc;
+	htt->pending_tx[msdu_id] = msdu;
 	spin_unlock_bh(&htt->tx_lock);
 
 	res = ath10k_skb_map(dev, msdu);
@@ -553,15 +512,6 @@ int ath10k_htt_tx(struct ath10k_htt *htt, struct sk_buff *msdu)
 
 	memcpy(cmd->data_tx.prefetch, msdu->data, prefetch_len);
 
-	/* refcount is decremented by HTC and HTT completions until it reaches
-	 * zero and is freed */
-	skb_cb = ATH10K_SKB_CB(txdesc);
-	skb_cb->htt.is_conf = false;
-	skb_cb->htt.msdu_id = msdu_id;
-	skb_cb->htt.refcount = 2;
-	skb_cb->htt.txfrag = txfrag;
-	skb_cb->htt.msdu = msdu;
-
 	res = ath10k_htc_send(&htt->ar->htc, htt->eid, txdesc);
 	if (res)
 		goto err;

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

@@ -1757,8 +1757,6 @@ static void ath10k_tx(struct ieee80211_hw *hw,
 		ath10k_tx_h_seq_no(skb);
 	}
 
-	ATH10K_SKB_CB(skb)->is_mapped = false;
-	ATH10K_SKB_CB(skb)->is_aborted = false;
 	ATH10K_SKB_CB(skb)->htt.is_offchan = false;
 	ATH10K_SKB_CB(skb)->htt.vdev_id = vdev_id;
 	ATH10K_SKB_CB(skb)->htt.tid = tid;

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

@@ -44,21 +44,25 @@ static void ath10k_report_offchan_tx(struct ath10k *ar, struct sk_buff *skb)
 	spin_unlock_bh(&ar->data_lock);
 }
 
-void ath10k_txrx_tx_unref(struct ath10k_htt *htt, struct sk_buff *txdesc)
+void ath10k_txrx_tx_unref(struct ath10k_htt *htt,
+			  const struct htt_tx_done *tx_done)
 {
 	struct device *dev = htt->ar->dev;
 	struct ieee80211_tx_info *info;
-	struct sk_buff *txfrag = ATH10K_SKB_CB(txdesc)->htt.txfrag;
-	struct sk_buff *msdu = ATH10K_SKB_CB(txdesc)->htt.msdu;
+	struct sk_buff *msdu, *txfrag;
 	int ret;
 
-	if (ATH10K_SKB_CB(txdesc)->htt.refcount == 0)
-		return;
-
-	ATH10K_SKB_CB(txdesc)->htt.refcount--;
+	ath10k_dbg(ATH10K_DBG_HTT, "htt tx completion msdu_id %u discard %d no_ack %d\n",
+		   tx_done->msdu_id, !!tx_done->discard, !!tx_done->no_ack);
 
-	if (ATH10K_SKB_CB(txdesc)->htt.refcount > 0)
+	if (tx_done->msdu_id >= htt->max_num_pending_tx) {
+		ath10k_warn("warning: msdu_id %d too big, ignoring\n",
+			    tx_done->msdu_id);
 		return;
+	}
+
+	msdu = htt->pending_tx[tx_done->msdu_id];
+	txfrag = ATH10K_SKB_CB(msdu)->htt.txfrag;
 
 	if (txfrag) {
 		ret = ath10k_skb_unmap(dev, txfrag);
@@ -76,7 +80,7 @@ void ath10k_txrx_tx_unref(struct ath10k_htt *htt, struct sk_buff *txdesc)
 
 	info = IEEE80211_SKB_CB(msdu);
 
-	if (ATH10K_SKB_CB(txdesc)->htt.discard) {
+	if (tx_done->discard) {
 		ieee80211_free_txskb(htt->ar->hw, msdu);
 		goto exit;
 	}
@@ -84,7 +88,7 @@ void ath10k_txrx_tx_unref(struct ath10k_htt *htt, struct sk_buff *txdesc)
 	if (!(info->flags & IEEE80211_TX_CTL_NO_ACK))
 		info->flags |= IEEE80211_TX_STAT_ACK;
 
-	if (ATH10K_SKB_CB(txdesc)->htt.no_ack)
+	if (tx_done->no_ack)
 		info->flags &= ~IEEE80211_TX_STAT_ACK;
 
 	ieee80211_tx_status(htt->ar->hw, msdu);
@@ -92,36 +96,12 @@ void ath10k_txrx_tx_unref(struct ath10k_htt *htt, struct sk_buff *txdesc)
 
 exit:
 	spin_lock_bh(&htt->tx_lock);
-	htt->pending_tx[ATH10K_SKB_CB(txdesc)->htt.msdu_id] = NULL;
-	ath10k_htt_tx_free_msdu_id(htt, ATH10K_SKB_CB(txdesc)->htt.msdu_id);
+	htt->pending_tx[tx_done->msdu_id] = NULL;
+	ath10k_htt_tx_free_msdu_id(htt, tx_done->msdu_id);
 	__ath10k_htt_tx_dec_pending(htt);
 	if (htt->num_pending_tx == 0)
 		wake_up(&htt->empty_tx_wq);
 	spin_unlock_bh(&htt->tx_lock);
-
-	dev_kfree_skb_any(txdesc);
-}
-
-void ath10k_txrx_tx_completed(struct ath10k_htt *htt,
-			      const struct htt_tx_done *tx_done)
-{
-	struct sk_buff *txdesc;
-
-	ath10k_dbg(ATH10K_DBG_HTT, "htt tx completion msdu_id %u discard %d no_ack %d\n",
-		   tx_done->msdu_id, !!tx_done->discard, !!tx_done->no_ack);
-
-	if (tx_done->msdu_id >= htt->max_num_pending_tx) {
-		ath10k_warn("warning: msdu_id %d too big, ignoring\n",
-			    tx_done->msdu_id);
-		return;
-	}
-
-	txdesc = htt->pending_tx[tx_done->msdu_id];
-
-	ATH10K_SKB_CB(txdesc)->htt.discard = tx_done->discard;
-	ATH10K_SKB_CB(txdesc)->htt.no_ack = tx_done->no_ack;
-
-	ath10k_txrx_tx_unref(htt, txdesc);
 }
 
 static const u8 rx_legacy_rate_idx[] = {

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

@@ -19,8 +19,7 @@
 
 #include "htt.h"
 
-void ath10k_txrx_tx_unref(struct ath10k_htt *htt, struct sk_buff *txdesc);
-void ath10k_txrx_tx_completed(struct ath10k_htt *htt,
+void ath10k_txrx_tx_unref(struct ath10k_htt *htt,
 			  const struct htt_tx_done *tx_done);
 void ath10k_process_rx(struct ath10k *ar, struct htt_rx_info *info);