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 2873
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.
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.4.4.1-7-QCARMSWP-1.
Signed-off-by: Wen Gong
---
drivers/net/wireless/ath/ath10k/core.c | 14 +-
drivers/net/wireless/ath/ath10k/core.h | 4 +-
drivers/net/wireless/ath/ath10k/htc.c| 353 ---
drivers/net/wireless/ath/ath10k/htc.h| 21 +-
drivers/net/wireless/ath/ath10k/htt.c| 8 +
drivers/net/wireless/ath/ath10k/htt.h| 5 +
drivers/net/wireless/ath/ath10k/htt_rx.c | 1 +
drivers/net/wireless/ath/ath10k/htt_tx.c | 9 +-
8 files changed, 377 insertions(+), 38 deletions(-)
diff --git a/drivers/net/wireless/ath/ath10k/core.c
b/drivers/net/wireless/ath/ath10k/core.c
index 762bba0..351f4ed 100644
--- a/drivers/net/wireless/ath/ath10k/core.c
+++ b/drivers/net/wireless/ath/ath10k/core.c
@@ -3194,6 +3194,11 @@ struct ath10k *ath10k_core_create(size_t priv_size,
struct device *dev,
if (!ar->workqueue_aux)
goto err_free_wq;
+ ar->workqueue_tx_complete =
+ create_singlethread_workqueue("ath10k_tx_complete_wq");
+ if (!ar->workqueue_tx_complete)
+ goto err_free_aux_wq;
+
mutex_init(&ar->conf_mutex);
mutex_init(&ar->dump_mutex);
spin_lock_init(&ar->data_lock);
@@ -3219,7 +3224,7 @@ struct ath10k *ath10k_core_create(size_t priv_size,
struct device *dev,
ret = ath10k_coredump_create(ar);
if (ret)
- goto err_free_aux_wq;
+ goto err_free_tx_complete;
ret = ath10k_debug_create(ar);
if (ret)
@@ -3229,12 +3234,12 @@ struct ath10k *ath10k_core_create(size_t priv_size,
struct device *dev,
err_free_coredump:
ath10k_coredump_destroy(ar);
-
+err_free_tx_complete:
+ destroy_workqueue(ar->workqueue_tx_complete);
err_free_aux_wq:
destroy_workqueue(ar->workqueue_aux);
err_free_wq:
destroy_workqueue(ar->workqueue);
-
err_free_mac:
ath10k_mac_destroy(ar);
@@ -3250,6 +3255,9 @@ void ath10k_core_destroy(struct ath10k *ar)
flush_workqueue(ar->workqueue_aux);
destroy_workqueue(ar->workqueue_aux);
+ flush_workqueue(ar->workqueue_tx_complete);
+ destroy_workqueue(ar->workqueue_tx_complete);
+
ath10k_debug_destroy(ar);
ath10k_coredump_destroy(ar);
ath10k_htt_tx_destroy(&ar->htt);
diff --git a/drivers/net/wireless/ath/ath10k/core.h
b/drivers/net/wireless/ath/ath10k/core.h
index 4d7db07..be9eb37 100644
--- a/drivers/net/wireless/ath/ath10k/core.h
+++ b/drivers/net/wireless/ath/ath10k/core.h
@@ -1079,7 +1079,7 @@ struct ath10k {
struct workqueue_struct *workqueue;
/* Auxiliary workqueue */
struct workqueue_struct *workqueue_aux;
-
+ struct workqueue_struct *workqueue_tx_complete;
/* prevents concurrent FW reconfiguration */
struct mutex conf_mutex;
@@ -1120,6 +1120,8 @@ struct ath10k {
struct work_struct register_work;
struct work_struct restart_work;
+ struct work_struct bundle_tx_work;
+ struct work_struct tx_complete_work;
/* cycle count is reported twice for each visited channel during scan.
* access protected by data_lock
diff --git a/drivers/net/wireless/ath/ath10k/htc.c
b/drivers/net/wireless/ath/ath10k/htc.c
index 7357a5a..96b620f 100644
--- a/drivers/net/wireless/ath/ath10k/htc.c
+++ b/drivers/net/wireless/ath/ath10k/htc.c
@@ -51,10 +51,12 @@ void ath10k_htc_notify_tx_completion(struct ath10k_htc_ep
*ep,
struct sk_buff *skb)
{
struct ath10k *ar = ep->htc->ar;
+ struct ath10k_htc_hdr *hdr;
ath10k_dbg(ar, ATH10K_DBG_HTC, "%s: ep %d skb %pK\n", __func__,
ep->eid, skb);
+ hdr = (struct ath10k_htc_hdr *)skb->data;
ath10k_htc_restore_tx_skb(ep->htc, skb);
if (!ep->ep_ops.ep_tx_complete) {
@@ -63,6 +65,11 @@ void ath10k_htc_notify_tx_completion(struct ath10k_htc_ep
*ep,
return;
}
+ if (hdr->flags & ATH10K_HTC_FLAG_SEND_BUNDLE)
