From 8d985555ddaa6735c5d1f3d6e4d4d9cb47f27878 Mon Sep 17 00:00:00 2001
From: Alagu Sankar <alagusankar@silex-india.com>
Date: Fri, 15 Nov 2019 09:20:58 +0200
Subject: [PATCH] ath10k: enable RX bundle receive for sdio
Git-commit: 8d985555ddaa6735c5d1f3d6e4d4d9cb47f27878
Patch-mainline: v5.6-rc1
References: jsc#SLE-13430
The existing implementation of initiating multiple sdio transfers for
receive bundling is slowing down the receive speed. Combining the
transfers using a bundle method would be ideal.
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
Tested with QCA6174 SDIO with firmware
WLAN.RMH.4.4.1-00017-QCARMSWPZ-1
Signed-off-by: Alagu Sankar <alagusankar@silex-india.com>
Signed-off-by: Wen Gong <wgong@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Acked-by: Takashi Iwai <tiwai@suse.de>
---
drivers/net/wireless/ath/ath10k/sdio.c | 110 +++++++++++++++++++++------------
drivers/net/wireless/ath/ath10k/sdio.h | 11 +++-
2 files changed, 79 insertions(+), 42 deletions(-)
diff --git a/drivers/net/wireless/ath/ath10k/sdio.c b/drivers/net/wireless/ath/ath10k/sdio.c
index 120200a93bcc..7f25079dde2d 100644
--- a/drivers/net/wireless/ath/ath10k/sdio.c
+++ b/drivers/net/wireless/ath/ath10k/sdio.c
@@ -24,6 +24,8 @@
#include "trace.h"
#include "sdio.h"
+#define ATH10K_SDIO_VSG_BUF_SIZE (32 * 1024)
+
/* inlined helper functions */
static inline int ath10k_sdio_calc_txrx_padded_len(struct ath10k_sdio *ar_sdio,
@@ -484,11 +486,11 @@ static int ath10k_sdio_mbox_rx_process_packets(struct ath10k *ar,
return ret;
}
-static int ath10k_sdio_mbox_alloc_pkt_bundle(struct ath10k *ar,
- struct ath10k_sdio_rx_data *rx_pkts,
- struct ath10k_htc_hdr *htc_hdr,
- size_t full_len, size_t act_len,
- size_t *bndl_cnt)
+static int ath10k_sdio_mbox_alloc_bundle(struct ath10k *ar,
+ struct ath10k_sdio_rx_data *rx_pkts,
+ struct ath10k_htc_hdr *htc_hdr,
+ size_t full_len, size_t act_len,
+ size_t *bndl_cnt)
{
int ret, i;
@@ -529,6 +531,7 @@ static int ath10k_sdio_mbox_rx_alloc(struct ath10k *ar,
size_t full_len, act_len;
bool last_in_bundle;
int ret, i;
+ int pkt_cnt = 0;
if (n_lookaheads > ATH10K_SDIO_MAX_RX_MSGS) {
ath10k_warn(ar,
@@ -572,20 +575,19 @@ static int ath10k_sdio_mbox_rx_alloc(struct ath10k *ar,
*/
size_t bndl_cnt;
- ret = ath10k_sdio_mbox_alloc_pkt_bundle(ar,
- &ar_sdio->rx_pkts[i],
- htc_hdr,
- full_len,
- act_len,
- &bndl_cnt);
+ ret = ath10k_sdio_mbox_alloc_bundle(ar,
+ &ar_sdio->rx_pkts[pkt_cnt],
+ htc_hdr,
+ full_len,
+ act_len,
+ &bndl_cnt);
if (ret) {
ath10k_warn(ar, "alloc_bundle error %d\n", ret);
goto err;
}
- n_lookaheads += bndl_cnt;
- i += bndl_cnt;
+ pkt_cnt += bndl_cnt;
/*Next buffer will be the last in the bundle */
last_in_bundle = true;
}
@@ -597,7 +599,7 @@ static int ath10k_sdio_mbox_rx_alloc(struct ath10k *ar,
if (htc_hdr->flags & ATH10K_HTC_FLAGS_RECV_1MORE_BLOCK)
full_len += ATH10K_HIF_MBOX_BLOCK_SIZE;
- ret = ath10k_sdio_mbox_alloc_rx_pkt(&ar_sdio->rx_pkts[i],
+ ret = ath10k_sdio_mbox_alloc_rx_pkt(&ar_sdio->rx_pkts[pkt_cnt],
act_len,
full_len,
last_in_bundle,
@@ -606,9 +608,11 @@ static int ath10k_sdio_mbox_rx_alloc(struct ath10k *ar,
ath10k_warn(ar, "alloc_rx_pkt error %d\n", ret);
goto err;
}
+
+ pkt_cnt++;
}
- ar_sdio->n_rx_pkts = i;
+ ar_sdio->n_rx_pkts = pkt_cnt;
return 0;
@@ -622,59 +626,76 @@ static int ath10k_sdio_mbox_rx_alloc(struct ath10k *ar,
return ret;
}
-static int ath10k_sdio_mbox_rx_packet(struct ath10k *ar,
- struct ath10k_sdio_rx_data *pkt)
+static int ath10k_sdio_mbox_rx_fetch(struct ath10k *ar)
{
struct ath10k_sdio *ar_sdio = ath10k_sdio_priv(ar);
+ struct ath10k_sdio_rx_data *pkt = &ar_sdio->rx_pkts[0];
struct sk_buff *skb = pkt->skb;
struct ath10k_htc_hdr *htc_hdr;
int ret;
ret = ath10k_sdio_readsb(ar, ar_sdio->mbox_info.htc_addr,
skb->data, pkt->alloc_len);
- if (ret)
- goto out;
- /* Update actual length. The original length may be incorrect,
- * as the FW will bundle multiple packets as long as their sizes
- * fit within the same aligned length (pkt->alloc_len).
- */
- htc_hdr = (struct ath10k_htc_hdr *)skb->data;
- pkt->act_len = le16_to_cpu(htc_hdr->len) + sizeof(*htc_hdr);
- if (pkt->act_len > pkt->alloc_len) {
- ath10k_warn(ar, "rx packet too large (%zu > %zu)\n",
- pkt->act_len, pkt->alloc_len);
- ret = -EMSGSIZE;
- goto out;
+ if (ret) {
+ ar_sdio->n_rx_pkts = 0;
+ ath10k_sdio_mbox_free_rx_pkt(pkt);
+ return ret;
}
- skb_put(skb, pkt->act_len);
-
-out:
+ htc_hdr = (struct ath10k_htc_hdr *)skb->data;
+ pkt->act_len = le16_to_cpu(htc_hdr->len) + sizeof(*htc_hdr);
pkt->status = ret;
+ skb_put(skb, pkt->act_len);
return ret;
}
-static int ath10k_sdio_mbox_rx_fetch(struct ath10k *ar)
+static int ath10k_sdio_mbox_rx_fetch_bundle(struct ath10k *ar)
{
struct ath10k_sdio *ar_sdio = ath10k_sdio_priv(ar);
+ struct ath10k_sdio_rx_data *pkt;
+ struct ath10k_htc_hdr *htc_hdr;
int ret, i;
+ u32 pkt_offset, virt_pkt_len;
+ virt_pkt_len = 0;
+ for (i = 0; i < ar_sdio->n_rx_pkts; i++)
+ virt_pkt_len += ar_sdio->rx_pkts[i].alloc_len;
+
+ if (virt_pkt_len > ATH10K_SDIO_VSG_BUF_SIZE) {
+ ath10k_warn(ar, "sdio vsg buffer size limit: %d\n", virt_pkt_len);
+ ret = -E2BIG;
+ goto err;
+ }
+
+ ret = ath10k_sdio_readsb(ar, ar_sdio->mbox_info.htc_addr,
+ ar_sdio->vsg_buffer, virt_pkt_len);
+ if (ret) {
+ ath10k_warn(ar, "failed to read bundle packets: %d", ret);
+ goto err;
+ }
+
+ pkt_offset = 0;
for (i = 0; i < ar_sdio->n_rx_pkts; i++) {
- ret = ath10k_sdio_mbox_rx_packet(ar,
- &ar_sdio->rx_pkts[i]);
- if (ret)
- goto err;
+ pkt = &ar_sdio->rx_pkts[i];
+ htc_hdr = (struct ath10k_htc_hdr *)(ar_sdio->vsg_buffer + pkt_offset);
+ pkt->act_len = le16_to_cpu(htc_hdr->len) + sizeof(*htc_hdr);
+
+ skb_put_data(pkt->skb, htc_hdr, pkt->act_len);
+ pkt->status = 0;
+ pkt_offset += pkt->alloc_len;
}
return 0;
err:
/* Free all packets that was not successfully fetched. */
- for (; i < ar_sdio->n_rx_pkts; i++)
+ for (i = 0; i < ar_sdio->n_rx_pkts; i++)
ath10k_sdio_mbox_free_rx_pkt(&ar_sdio->rx_pkts[i]);
+ ar_sdio->n_rx_pkts = 0;
+
return ret;
}
@@ -717,7 +738,10 @@ static int ath10k_sdio_mbox_rxmsg_pending_handler(struct ath10k *ar,
*/
*done = false;
- ret = ath10k_sdio_mbox_rx_fetch(ar);
+ if (ar_sdio->n_rx_pkts > 1)
+ ret = ath10k_sdio_mbox_rx_fetch_bundle(ar);
+ else
+ ret = ath10k_sdio_mbox_rx_fetch(ar);
/* Process fetched packets. This will potentially update
* n_lookaheads depending on if the packets contain lookahead
@@ -2020,6 +2044,12 @@ static int ath10k_sdio_probe(struct sdio_func *func,
goto err_core_destroy;
}
+ ar_sdio->vsg_buffer = devm_kmalloc(ar->dev, ATH10K_SDIO_VSG_BUF_SIZE, GFP_KERNEL);
+ if (!ar_sdio->vsg_buffer) {
+ ret = -ENOMEM;
+ goto err_core_destroy;
+ }
+
ar_sdio->irq_data.irq_en_reg =
devm_kzalloc(ar->dev, sizeof(struct ath10k_sdio_irq_enable_regs),
GFP_KERNEL);
diff --git a/drivers/net/wireless/ath/ath10k/sdio.h b/drivers/net/wireless/ath/ath10k/sdio.h
index b8c7ac0330bd..8d5b09f8b4f3 100644
--- a/drivers/net/wireless/ath/ath10k/sdio.h
+++ b/drivers/net/wireless/ath/ath10k/sdio.h
@@ -138,8 +138,8 @@ struct ath10k_sdio_irq_proc_regs {
u8 rx_lookahead_valid;
u8 host_int_status2;
u8 gmbox_rx_avail;
- __le32 rx_lookahead[2];
- __le32 rx_gmbox_lookahead_alias[2];
+ __le32 rx_lookahead[2 * ATH10K_HIF_MBOX_NUM_MAX];
+ __le32 int_status_enable;
};
struct ath10k_sdio_irq_enable_regs {
@@ -196,6 +196,13 @@ struct ath10k_sdio {
struct ath10k *ar;
struct ath10k_sdio_irq_data irq_data;
+ /* temporary buffer for sdio read.
+ * It is allocated when probe, and used for receive bundled packets,
+ * the read for bundled packets is not parallel, so it does not need
+ * protected.
+ */
+ u8 *vsg_buffer;
+
/* temporary buffer for BMI requests */
u8 *bmi_buf;
--
2.16.4