ath10k: add htt TX bundle for sdio

The transmission utilization ratio for sdio bus for small packet is
slow, because the space and time cost for sdio bus is same for large
length packet and small length packet. So the speed of data for large
length packet is higher than small length.

Test result of different length of data:

data packet(byte)   cost time(us)   calculated rate(Mbps)
      256               28                73
      512               33               124
     1024               35               234
     1792               45               318
    14336              168               682
    28672              333               688
    57344              660               695

This patch change the TX packet from single packet to a large length
bundle packet, max size is 32, it results in significant performance
improvement on TX path.

Also there's a fourth thread "ath10k_tx_complete_wq" added to ath10k as it
improves TCP RX throughput (values in Mbps):

                                       TCP-RX    TCP-TX    UDP-RX      UDP-TX
use workqueue_tx_complete              423       357       448         412
change it to ar->workqueue             410       360       449         414
change it to ar->workqueue_aux         405       339       446         401

This patch only effect sdio chip, it will not effect PCI, SNOC etc.
It only enable bundle for sdio chip.

Tested with QCA6174 SDIO with firmware
WLAN.RMH.4.4.1-00017-QCARMSWP-1.

Signed-off-by: Wen Gong <wgong@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/20200410061400.14231-2-wgong@codeaurora.org

1 files changed, 22 insertions, 2 deletions

diff --git a/drivers/net/wireless/ath/ath10k/htc.h b/drivers/net/wireless/ath/ath10k/htc.h
index 14e5c3f712c1..d045dbc42158 100644
--- a/drivers/net/wireless/ath/ath10k/htc.h
+++ b/drivers/net/wireless/ath/ath10k/htc.h
@@ -83,8 +83,14 @@ struct ath10k_htc_hdr {
 		u8 seq_no; /* for tx */
 		u8 control_byte1;
 	} __packed;
-	u8 pad0;
-	u8 pad1;
+	union {
+		__le16 pad_len;
+		struct {
+			u8 pad0;
+			u8 pad1;
+		} __packed;
+	} __packed;
+
 } __packed __aligned(4);
 
 enum ath10k_ath10k_htc_msg_id {
@@ -121,6 +127,10 @@ enum ath10k_htc_conn_svc_status {
 	ATH10K_HTC_CONN_SVC_STATUS_NO_MORE_EP   = 4
 };
 
+#define ATH10K_MAX_MSG_PER_HTC_TX_BUNDLE        32
+#define ATH10K_MIN_MSG_PER_HTC_TX_BUNDLE        2
+#define ATH10K_MIN_CREDIT_PER_HTC_TX_BUNDLE     2
+
 enum ath10k_htc_setup_complete_flags {
 	ATH10K_HTC_SETUP_COMPLETE_FLAGS_RX_BNDL_EN = 1
 };
@@ -353,7 +363,12 @@ struct ath10k_htc_ep {
 
 	u8 seq_no; /* for debugging */
 	int tx_credits;
+	int tx_credit_size;
 	bool tx_credit_flow_enabled;
+	bool bundle_tx;
+	struct sk_buff_head tx_req_head;
+	struct sk_buff_head tx_complete_head;
+
 };
 
 struct ath10k_htc_svc_tx_credits {
@@ -382,6 +397,7 @@ struct ath10k_htc {
 
 int ath10k_htc_init(struct ath10k *ar);
 int ath10k_htc_wait_target(struct ath10k_htc *htc);
+void ath10k_htc_setup_tx_req(struct ath10k_htc_ep *ep);
 int ath10k_htc_start(struct ath10k_htc *htc);
 int ath10k_htc_connect_service(struct ath10k_htc *htc,
 			       struct ath10k_htc_svc_conn_req  *conn_req,
@@ -391,6 +407,10 @@ void ath10k_htc_change_tx_credit_flow(struct ath10k_htc *htc,
 				      bool enable);
 int ath10k_htc_send(struct ath10k_htc *htc, enum ath10k_htc_ep_id eid,
 		    struct sk_buff *packet);
+void ath10k_htc_stop_hl(struct ath10k *ar);
+
+int ath10k_htc_send_hl(struct ath10k_htc *htc, enum ath10k_htc_ep_id eid,
+		       struct sk_buff *packet);
 struct sk_buff *ath10k_htc_alloc_skb(struct ath10k *ar, int size);
 void ath10k_htc_tx_completion_handler(struct ath10k *ar, struct sk_buff *skb);
 void ath10k_htc_rx_completion_handler(struct ath10k *ar, struct sk_buff *skb);