For RX, it has two parts, one is to read data from sdio, another
is to indicate the packets to upper stack. Recently it has only
one thread to do all RX things, it results that it is sequential
for RX and low throughout, change RX to parallel for the two parts
will increase throughout.
This patch move the indication to a workqueue, it results in
significant performance improvement on RX path.
Udp rx throughout is 200Mbps without this patch, and it arrives
400Mbps with this patch.
Tested with QCA6174 SDIO with firmware
WLAN.RMH.4.4.1-00017-QCARMSWPZ-1
Signed-off-by: Wen Gong <wgong@xxxxxxxxxxxxxx>
---
drivers/net/wireless/ath/ath10k/sdio.c | 35 +++++++++++++++++++++++++++++++---
drivers/net/wireless/ath/ath10k/sdio.h | 11 +++++++++++
2 files changed, 43 insertions(+), 3 deletions(-)
diff --git a/drivers/net/wireless/ath/ath10k/sdio.c b/drivers/net/wireless/ath/ath10k/sdio.c
index a510101..ff02833 100644
--- a/drivers/net/wireless/ath/ath10k/sdio.c
+++ b/drivers/net/wireless/ath/ath10k/sdio.c
@@ -419,6 +419,7 @@ static int ath10k_sdio_mbox_rx_process_packets(struct ath10k *ar,
struct ath10k_htc *htc = &ar->htc;
struct ath10k_sdio_rx_data *pkt;
struct ath10k_htc_ep *ep;
+ struct ath10k_skb_cb *cb;
enum ath10k_htc_ep_id id;
int ret, i, *n_lookahead_local;
u32 *lookaheads_local;
@@ -464,10 +465,16 @@ static int ath10k_sdio_mbox_rx_process_packets(struct ath10k *ar,
if (ret)
goto out;
- if (!pkt->trailer_only)
- ep->ep_ops.ep_rx_complete(ar_sdio->ar, pkt->skb);
- else
+ if (!pkt->trailer_only) {
+ cb = ATH10K_SKB_CB(pkt->skb);
+ cb->eid = id;
+
+ skb_queue_tail(&ar_sdio->rx_head, pkt->skb);
+ queue_work(ar->workqueue_aux,
+ &ar_sdio->async_work_rx);
+ } else {
kfree_skb(pkt->skb);
+ }
/* The RX complete handler now owns the skb...*/
pkt->skb = NULL;
@@ -1317,6 +1324,25 @@ static void __ath10k_sdio_write_async(struct ath10k *ar,
ath10k_sdio_free_bus_req(ar, req);
}
+static void ath10k_rx_indication_async_work(struct work_struct *work)
+{
+ struct ath10k_sdio *ar_sdio = container_of(work, struct ath10k_sdio,
+ async_work_rx);
+ struct ath10k *ar = ar_sdio->ar;
+ struct ath10k_htc_ep *ep;
+ struct ath10k_skb_cb *cb;
+ struct sk_buff *skb;
+
+ while (true) {
+ skb = skb_dequeue(&ar_sdio->rx_head);
+ if (!skb)
+ break;
+ cb = ATH10K_SKB_CB(skb);
+ ep = &ar->htc.endpoint[cb->eid];
+ ep->ep_ops.ep_rx_complete(ar, skb);
+ }
+}
+
static void ath10k_sdio_write_async_work(struct work_struct *work)
{
struct ath10k_sdio *ar_sdio = container_of(work, struct ath10k_sdio,
@@ -2087,6 +2113,9 @@ static int ath10k_sdio_probe(struct sdio_func *func,
for (i = 0; i < ATH10K_SDIO_BUS_REQUEST_MAX_NUM; i++)
ath10k_sdio_free_bus_req(ar, &ar_sdio->bus_req[i]);
+ skb_queue_head_init(&ar_sdio->rx_head);
+ INIT_WORK(&ar_sdio->async_work_rx, ath10k_rx_indication_async_work);
+
dev_id_base = FIELD_GET(QCA_MANUFACTURER_ID_BASE, id->device);
switch (dev_id_base) {
case QCA_MANUFACTURER_ID_AR6005_BASE:
diff --git a/drivers/net/wireless/ath/ath10k/sdio.h b/drivers/net/wireless/ath/ath10k/sdio.h
index 00bd4ca..8aa0dbc 100644
--- a/drivers/net/wireless/ath/ath10k/sdio.h
+++ b/drivers/net/wireless/ath/ath10k/sdio.h
@@ -98,6 +98,12 @@
#define ATH10K_FIFO_TIMEOUT_AND_CHIP_CONTROL_DISABLE_SLEEP_OFF 0xFFFEFFFF
#define ATH10K_FIFO_TIMEOUT_AND_CHIP_CONTROL_DISABLE_SLEEP_ON 0x10000
+struct ath10k_sdio_rx_request {
+ struct list_head list;
+ struct sk_buff *skb;
+ struct ath10k_htc_ep *ep;
+};
+
struct ath10k_sdio_bus_request {
struct list_head list;
@@ -187,6 +193,9 @@ struct ath10k_sdio {
struct ath10k_sdio_bus_request bus_req[ATH10K_SDIO_BUS_REQUEST_MAX_NUM];
/* free list of bus requests */
struct list_head bus_req_freeq;
+
+ struct sk_buff_head rx_head;
+
/* protects access to bus_req_freeq */
spinlock_t lock;
@@ -213,6 +222,8 @@ struct ath10k_sdio {
struct list_head wr_asyncq;
/* protects access to wr_asyncq */
spinlock_t wr_async_lock;
+
+ struct work_struct async_work_rx;
};
static inline struct ath10k_sdio *ath10k_sdio_priv(struct ath10k *ar)
--
1.9.1
