Skip to contentSkip to conversation

ath10k: improve throughout of TX of sdio

PATCH Superseded Wen Gong 2 participants 22 messages Feb 12, 2020 – Apr 21, 2020 1 message not in the archive Qualcomm Atheros ATH10K wireless driver

v9 of 10 Superseded Latest is v10 →

lore
Share & tools
lore

Wen Gong

author
#0 lore raw

v9 cover ath10k: improve throughout of TX of sdio

v9: change ath10k_htt_htc_tx_complete to fix the use-after-free panic

v8: split out patch "change ATH10K_SDIO_BUS_REQUEST_MAX_NUM from 64 to 1024" from "disable TX complete indication of htt for sdio". merge patch "ath10k: clean bundle tx queue of htt tx stop for sdio" into "add htt TX bundle for sdio"

v7: change a few code style to meet ath10k-check script

v6: remove module parameters disable_tx_comp and alt_data
this is 3 patches of the 7 patches from ath10k: improve throughout of tcp/udp TX/RX of sdio

v5: change ath10k_htc_setup_tx_req to add check bundle_tx to forbidden init 2 times

v4: add macro ATH10K_HTC_MSG_READY_EXT_ALT_DATA_MASK

v3: change some code style

v2: change some code style

The bottleneck of throughout on sdio chip is the bus bandwidth, to the patches are all to increase the use ratio of sdio bus.

These patches only affect sdio bus chip, explanation is mentioned in each patch's commit log.

Wen Gong (4):
ath10k: disable TX complete indication of htt for sdio
ath10k: change ATH10K_SDIO_BUS_REQUEST_MAX_NUM from 64 to 1024
ath10k: add htt TX bundle for sdio
ath10k: enable alt data of TX path for sdio

 drivers/net/wireless/ath/ath10k/core.c   |  27 +-
 drivers/net/wireless/ath/ath10k/core.h   |   4 +-
 drivers/net/wireless/ath/ath10k/hif.h    |   9 +
 drivers/net/wireless/ath/ath10k/htc.c    | 394 +++++++++++++++++++++--
 drivers/net/wireless/ath/ath10k/htc.h    |  40 ++-
 drivers/net/wireless/ath/ath10k/htt.c    |  13 +
 drivers/net/wireless/ath/ath10k/htt.h    |  17 +-
 drivers/net/wireless/ath/ath10k/htt_rx.c |  35 +-
 drivers/net/wireless/ath/ath10k/htt_tx.c |  43 ++-
 drivers/net/wireless/ath/ath10k/hw.h     |   2 +-
 drivers/net/wireless/ath/ath10k/sdio.c   |  23 ++
 drivers/net/wireless/ath/ath10k/sdio.h   |   3 +-
 12 files changed, 557 insertions(+), 53 deletions(-)
Signature · 1 line
2.23.0
author
#1 lore raw

PATCH v9 1/4 ath10k: disable TX complete indication of htt for sdio

For sdio chip, it is high latency bus, all the TX packet's content will be tranferred from HOST memory to firmware memory via sdio bus, then it need much more memory in firmware than low latency bus chip, for low latency chip, such as PCI-E, it only need to transfer the TX descriptor via PCI-E bus to firmware memory. For sdio chip, reduce the complexity of TX logic will help TX efficiency since its memory is limited, and it will reduce the TX circle's time of each packet and then firmware will have more memory for TX since TX complete also need memeory.

This patch disable TX complete indication from firmware for htt data packet, it will not have TX complete indication from firmware to ath10k. It will cut the cost of bus bandwidth of TX complete and make the TX logic of firmware simpler, it results in significant performance improvement on TX path.

Udp TX throughout is 130Mbps without this patch, and it arrives 400Mbps with this patch.

The downside of this patch is the command "iw wlan0 station dump" will show 0 for "tx retries" and "tx failed" since all tx packet's status is success.

This patch only effect sdio chip, it will not effect PCI, SNOC etc.

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

---
 drivers/net/wireless/ath/ath10k/core.c   |  5 +---
 drivers/net/wireless/ath/ath10k/hif.h    |  9 ++++++
 drivers/net/wireless/ath/ath10k/htc.c    | 10 +++++++
 drivers/net/wireless/ath/ath10k/htc.h    |  3 ++
 drivers/net/wireless/ath/ath10k/htt.c    |  5 ++++
 drivers/net/wireless/ath/ath10k/htt.h    | 13 ++++++++-
 drivers/net/wireless/ath/ath10k/htt_rx.c | 34 ++++++++++++++++++++++-
 drivers/net/wireless/ath/ath10k/htt_tx.c | 35 ++++++++++++++++++++++++
 drivers/net/wireless/ath/ath10k/hw.h     |  2 +-
 drivers/net/wireless/ath/ath10k/sdio.c   | 23 ++++++++++++++++
 10 files changed, 132 insertions(+), 7 deletions(-)
drivers/net/wireless/ath/ath10k/core.c +1 -4
index 5ec16ce19b69..b21c5f2fa04b 100644
@@ -696,10 +696,7 @@ static int ath10k_init_sdio(struct ath10k *ar, enum ath10k_firmware_mode mode)
 	if (ret)
 		return ret;
 
-	/* Data transfer is not initiated, when reduced Tx completion
-	 * is used for SDIO. disable it until fixed
-	 */
-	param &= ~HI_ACS_FLAGS_SDIO_REDUCE_TX_COMPL_SET;
+	param |= HI_ACS_FLAGS_SDIO_REDUCE_TX_COMPL_SET;
 
 	/* Alternate credit size of 1544 as used by SDIO firmware is
 	 * not big enough for mac80211 / native wifi frames. disable it
drivers/net/wireless/ath/ath10k/hif.h +9 -0
index 496ee34a4d78..0dd8973d0acf 100644
@@ -56,6 +56,8 @@ struct ath10k_hif_ops {
 
 	int (*swap_mailbox)(struct ath10k *ar);
 
+	int (*get_htt_tx_complete)(struct ath10k *ar);
+
 	int (*map_service_to_pipe)(struct ath10k *ar, u16 service_id,
 				   u8 *ul_pipe, u8 *dl_pipe);
 
@@ -144,6 +146,13 @@ static inline int ath10k_hif_swap_mailbox(struct ath10k *ar)
 	return 0;
 }
 
+static inline int ath10k_hif_get_htt_tx_complete(struct ath10k *ar)
+{
+	if (ar->hif.ops->get_htt_tx_complete)
+		return ar->hif.ops->get_htt_tx_complete(ar);
+	return 0;
+}
+
 static inline int ath10k_hif_map_service_to_pipe(struct ath10k *ar,
 						 u16 service_id,
 						 u8 *ul_pipe, u8 *dl_pipe)
drivers/net/wireless/ath/ath10k/htc.c +10 -0
index 2248d6c022f4..61ee413d902a 100644
@@ -660,6 +660,16 @@ int ath10k_htc_wait_target(struct ath10k_htc *htc)
 	return 0;
 }
 
+void ath10k_htc_change_tx_credit_flow(struct ath10k_htc *htc,
+				      enum ath10k_htc_ep_id eid,
+				      bool enable)
+{
+	struct ath10k *ar = htc->ar;
+	struct ath10k_htc_ep *ep = &ar->htc.endpoint[eid];
+
+	ep->tx_credit_flow_enabled = enable;
+}
+
 int ath10k_htc_connect_service(struct ath10k_htc *htc,
 			       struct ath10k_htc_svc_conn_req *conn_req,
 			       struct ath10k_htc_svc_conn_resp *conn_resp)
drivers/net/wireless/ath/ath10k/htc.h +3 -0
index 065c82d9d689..14e5c3f712c1 100644
@@ -386,6 +386,9 @@ 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,
 			       struct ath10k_htc_svc_conn_resp *conn_resp);
+void ath10k_htc_change_tx_credit_flow(struct ath10k_htc *htc,
+				      enum ath10k_htc_ep_id eid,
+				      bool enable);
 int ath10k_htc_send(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);
drivers/net/wireless/ath/ath10k/htt.c +5 -0
index c32ab07d2586..b07f14b53e72 100644
@@ -10,6 +10,7 @@
 #include "htt.h"
 #include "core.h"
 #include "debug.h"
+#include "hif.h"
 
 static const enum htt_t2h_msg_type htt_main_t2h_msg_types[] = {
 	[HTT_MAIN_T2H_MSG_TYPE_VERSION_CONF] = HTT_T2H_MSG_TYPE_VERSION_CONF,
@@ -155,6 +156,10 @@ int ath10k_htt_connect(struct ath10k_htt *htt)
 
 	htt->eid = conn_resp.eid;
 
+	htt->disable_tx_comp = ath10k_hif_get_htt_tx_complete(htt->ar);
+	if (htt->disable_tx_comp)
+		ath10k_htc_change_tx_credit_flow(&htt->ar->htc, htt->eid, true);
+
 	return 0;
 }
 
drivers/net/wireless/ath/ath10k/htt.h +12 -1
index d09ba4a550cc..2b3f32c929d1 100644
@@ -150,9 +150,19 @@ enum htt_data_tx_desc_flags1 {
 	HTT_DATA_TX_DESC_FLAGS1_MORE_IN_BATCH    = 1 << 12,
 	HTT_DATA_TX_DESC_FLAGS1_CKSUM_L3_OFFLOAD = 1 << 13,
 	HTT_DATA_TX_DESC_FLAGS1_CKSUM_L4_OFFLOAD = 1 << 14,
-	HTT_DATA_TX_DESC_FLAGS1_RSVD1            = 1 << 15
+	HTT_DATA_TX_DESC_FLAGS1_TX_COMPLETE      = 1 << 15
 };
 
+#define HTT_TX_CREDIT_DELTA_ABS_M      0xffff0000
+#define HTT_TX_CREDIT_DELTA_ABS_S      16
+#define HTT_TX_CREDIT_DELTA_ABS_GET(word) \
+	    (((word) & HTT_TX_CREDIT_DELTA_ABS_M) >> HTT_TX_CREDIT_DELTA_ABS_S)
+
+#define HTT_TX_CREDIT_SIGN_BIT_M       0x00000100
+#define HTT_TX_CREDIT_SIGN_BIT_S       8
+#define HTT_TX_CREDIT_SIGN_BIT_GET(word) \
+	    (((word) & HTT_TX_CREDIT_SIGN_BIT_M) >> HTT_TX_CREDIT_SIGN_BIT_S)
+
 enum htt_data_tx_ext_tid {
 	HTT_DATA_TX_EXT_TID_NON_QOS_MCAST_BCAST = 16,
 	HTT_DATA_TX_EXT_TID_MGMT                = 17,
@@ -2051,6 +2061,7 @@ struct ath10k_htt {
 	bool tx_mem_allocated;
 	const struct ath10k_htt_tx_ops *tx_ops;
 	const struct ath10k_htt_rx_ops *rx_ops;
+	bool disable_tx_comp;
 };
 
 struct ath10k_htt_tx_ops {
drivers/net/wireless/ath/ath10k/htt_rx.c +33 -1
index 22e78413fd44..2427adda4d9a 100644
@@ -3929,6 +3929,9 @@ bool ath10k_htt_t2h_msg_handler(struct ath10k *ar, struct sk_buff *skb)
 	}
 	case HTT_T2H_MSG_TYPE_MGMT_TX_COMPLETION: {
 		struct htt_tx_done tx_done = {};
+		struct ath10k_htt *htt = &ar->htt;
+		struct ath10k_htc *htc = &ar->htc;
+		struct ath10k_htc_ep *ep = &ar->htc.endpoint[htt->eid];
 		int status = __le32_to_cpu(resp->mgmt_tx_completion.status);
 		int info = __le32_to_cpu(resp->mgmt_tx_completion.info);
 
@@ -3954,6 +3957,12 @@ bool ath10k_htt_t2h_msg_handler(struct ath10k *ar, struct sk_buff *skb)
 			break;
 		}
 
+		if (htt->disable_tx_comp) {
+			spin_lock_bh(&htc->tx_lock);
+			ep->tx_credits++;
+			spin_unlock_bh(&htc->tx_lock);
+		}
+
 		status = ath10k_txrx_tx_unref(htt, &tx_done);
 		if (!status) {
 			spin_lock_bh(&htt->tx_lock);
@@ -4028,8 +4037,31 @@ bool ath10k_htt_t2h_msg_handler(struct ath10k *ar, struct sk_buff *skb)
 		skb_queue_tail(&htt->rx_in_ord_compl_q, skb);
 		return false;
 	}
-	case HTT_T2H_MSG_TYPE_TX_CREDIT_UPDATE_IND:
+	case HTT_T2H_MSG_TYPE_TX_CREDIT_UPDATE_IND: {
+		struct ath10k_htt *htt = &ar->htt;
+		struct ath10k_htc *htc = &ar->htc;
+		struct ath10k_htc_ep *ep = &ar->htc.endpoint[htt->eid];
+		u32 msg_word = __le32_to_cpu(*(__le32 *)resp);
+		int htt_credit_delta;
+
+		htt_credit_delta = HTT_TX_CREDIT_DELTA_ABS_GET(msg_word);
+		if (HTT_TX_CREDIT_SIGN_BIT_GET(msg_word))
+			htt_credit_delta = -htt_credit_delta;
+
+		ath10k_dbg(ar, ATH10K_DBG_HTT,
+			   "credit update: delta:%d\n",
+			   htt_credit_delta);
+
+		if (htt->disable_tx_comp) {
+			spin_lock_bh(&htc->tx_lock);
+			ep->tx_credits += htt_credit_delta;
+			spin_unlock_bh(&htc->tx_lock);
+			ath10k_dbg(ar, ATH10K_DBG_HTT,
+				   "credit total:%d\n",
+				   ep->tx_credits);
+		}
 		break;
+	}
 	case HTT_T2H_MSG_TYPE_CHAN_CHANGE: {
 		u32 phymode = __le32_to_cpu(resp->chan_change.phymode);
 		u32 freq = __le32_to_cpu(resp->chan_change.freq);
drivers/net/wireless/ath/ath10k/htt_tx.c +35 -0
index a182c0944cc7..8f2fda382b6b 100644
@@ -543,7 +543,39 @@ void ath10k_htt_tx_free(struct ath10k_htt *htt)
 
 void ath10k_htt_htc_tx_complete(struct ath10k *ar, struct sk_buff *skb)
 {
+	struct ath10k_htt *htt = &ar->htt;
+	struct htt_tx_done tx_done = {0};
+	struct htt_cmd_hdr *htt_hdr;
+	struct htt_data_tx_desc *desc_hdr;
+	u16 flags1;
+	u8 msg_type;
+
+	if (htt->disable_tx_comp) {
+		htt_hdr = (struct htt_cmd_hdr *)skb->data;
+		msg_type = htt_hdr->msg_type;
+
+		if (msg_type == HTT_H2T_MSG_TYPE_TX_FRM) {
+			desc_hdr = (struct htt_data_tx_desc *)
+				(skb->data + sizeof(*htt_hdr));
+			flags1 = __le16_to_cpu(desc_hdr->flags1);
+		}
+	}
+
 	dev_kfree_skb_any(skb);
+
+	if ((!htt->disable_tx_comp) || (msg_type != HTT_H2T_MSG_TYPE_TX_FRM))
+		return;
+
+	ath10k_dbg(ar, ATH10K_DBG_HTT,
+		   "htt tx complete msdu id:%u ,flags1:%x\n",
+		   __le16_to_cpu(desc_hdr->id), flags1);
+
+	if (flags1 & HTT_DATA_TX_DESC_FLAGS1_TX_COMPLETE)
+		return;
+
+	tx_done.status = HTT_TX_COMPL_STATE_ACK;
+	tx_done.msdu_id = __le16_to_cpu(desc_hdr->id);
+	ath10k_txrx_tx_unref(&ar->htt, &tx_done);
 }
 
 void ath10k_htt_hif_tx_complete(struct ath10k *ar, struct sk_buff *skb)
@@ -1269,6 +1301,9 @@ static int ath10k_htt_tx_hl(struct ath10k_htt *htt, enum ath10k_hw_txrx_mode txm
 		flags0 |= SM(ATH10K_HW_TXRX_MGMT,
 			     HTT_DATA_TX_DESC_FLAGS0_PKT_TYPE);
 		flags0 |= HTT_DATA_TX_DESC_FLAGS0_MAC_HDR_PRESENT;
+
+		if (htt->disable_tx_comp)
+			flags1 |= HTT_DATA_TX_DESC_FLAGS1_TX_COMPLETE;
 		break;
 	}
 
drivers/net/wireless/ath/ath10k/hw.h +1 -1
index 21b7a2a873b0..54176a0c0479 100644
@@ -765,7 +765,7 @@ ath10k_is_rssi_enable(struct ath10k_hw_params *hw,
 #define TARGET_TLV_NUM_TDLS_VDEVS		1
 #define TARGET_TLV_NUM_TIDS			((TARGET_TLV_NUM_PEERS) * 2)
 #define TARGET_TLV_NUM_MSDU_DESC		(1024 + 32)
-#define TARGET_TLV_NUM_MSDU_DESC_HL		64
+#define TARGET_TLV_NUM_MSDU_DESC_HL		1024
 #define TARGET_TLV_NUM_WOW_PATTERNS		22
 #define TARGET_TLV_MGMT_NUM_MSDU_DESC		(50)
 
drivers/net/wireless/ath/ath10k/sdio.c +23 -0
index 6fdf71b8b676..7b894dcaad2e 100644
@@ -1727,6 +1727,28 @@ static int ath10k_sdio_hif_swap_mailbox(struct ath10k *ar)
 	return 0;
 }
 
+static int ath10k_sdio_get_htt_tx_complete(struct ath10k *ar)
+{
+	u32 addr, val;
+	int ret;
+
+	addr = host_interest_item_address(HI_ITEM(hi_acs_flags));
+
+	ret = ath10k_sdio_hif_diag_read32(ar, addr, &val);
+	if (ret) {
+		ath10k_warn(ar,
+			    "unable to read hi_acs_flags for htt tx comple : %d\n", ret);
+		return ret;
+	}
+
+	ret = (val & HI_ACS_FLAGS_SDIO_REDUCE_TX_COMPL_FW_ACK);
+
+	ath10k_dbg(ar, ATH10K_DBG_SDIO, "sdio reduce tx complete fw%sack\n",
+		   ret ? " " : " not ");
+
+	return ret;
+}
+
 /* HIF start/stop */
 
 static int ath10k_sdio_hif_start(struct ath10k *ar)
@@ -2001,6 +2023,7 @@ static const struct ath10k_hif_ops ath10k_sdio_hif_ops = {
 	.start			= ath10k_sdio_hif_start,
 	.stop			= ath10k_sdio_hif_stop,
 	.swap_mailbox		= ath10k_sdio_hif_swap_mailbox,
+	.get_htt_tx_complete	= ath10k_sdio_get_htt_tx_complete,
 	.map_service_to_pipe	= ath10k_sdio_hif_map_service_to_pipe,
 	.get_default_pipe	= ath10k_sdio_hif_get_default_pipe,
 	.send_complete_check	= ath10k_sdio_hif_send_complete_check,
Signature · 6 lines
2.23.0

_______________________________________________
ath10k mailing list
[email protected]
http://lists.infradead.org/mailman/listinfo/ath10k
#2 lore raw

Re: [PATCH v9 1/4] ath10k: disable TX complete indication of htt for sdio

Quoted 22 lines · Wen Gong

For sdio chip, it is high latency bus, all the TX packet's content will be tranferred from HOST memory to firmware memory via sdio bus, then it need much more memory in firmware than low latency bus chip, for low latency chip, such as PCI-E, it only need to transfer the TX descriptor via PCI-E bus to firmware memory. For sdio chip, reduce the complexity of TX logic will help TX efficiency since its memory is limited, and it will reduce the TX circle's time of each packet and then firmware will have more memory for TX since TX complete also need memeory.

This patch disable TX complete indication from firmware for htt data packet, it will not have TX complete indication from firmware to ath10k. It will cut the cost of bus bandwidth of TX complete and make the TX logic of firmware simpler, it results in significant performance improvement on TX path.

Udp TX throughout is 130Mbps without this patch, and it arrives 400Mbps with this patch.

The downside of this patch is the command "iw wlan0 station dump" will show 0 for "tx retries" and "tx failed" since all tx packet's status is success.

Quoted 7 lines

This patch only effect sdio chip, it will not effect PCI, SNOC etc.

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

This has new warnings:

drivers/net/wireless/ath/ath10k/htt_tx.c: In function 'ath10k_htt_htc_tx_complete':
drivers/net/wireless/ath/ath10k/htt_tx.c:566:30: warning: 'msg_type' may be used uninitialized in this function [-Wmaybe-uninitialized] drivers/net/wireless/ath/ath10k/htt_tx.c:573:6: warning: 'flags1' may be used uninitialized in this function [-Wmaybe-uninitialized] drivers/net/wireless/ath/ath10k/htt_tx.c:577:42: warning: 'desc_hdr' may be used uninitialized in this function [-Wmaybe-uninitialized]

Quoted 1 line

From what I can see these are false positives, but please do double check that. In

the pending branch I solved it like this:

drivers/net/wireless/ath/ath10k/htt_tx.c +3 -3
@@ -546,9 +546,9 @@ void ath10k_htt_htc_tx_complete(struct ath10k *ar, struct sk_buff *skb)
        struct ath10k_htt *htt = &ar->htt;
        struct htt_tx_done tx_done = {0};
        struct htt_cmd_hdr *htt_hdr;
-       struct htt_data_tx_desc *desc_hdr;
-       u16 flags1;
-       u8 msg_type;
+       struct htt_data_tx_desc *desc_hdr = NULL;
+       u16 flags1 = 0;
+       u8 msg_type = 0;
 
        if (htt->disable_tx_comp) {
                htt_hdr = (struct htt_cmd_hdr *)skb->data;
Signature · 3 lines
https://patchwork.kernel.org/patch/11377827/

https://wireless.wiki.kernel.org/en/developers/documentation/submittingpatches
#3 lore raw

Re: [PATCH v9 1/4] ath10k: disable TX complete indication of htt for sdio

In reply to Wen Gong
Quoted 22 lines · Wen Gong

For sdio chip, it is high latency bus, all the TX packet's content will be tranferred from HOST memory to firmware memory via sdio bus, then it need much more memory in firmware than low latency bus chip, for low latency chip, such as PCI-E, it only need to transfer the TX descriptor via PCI-E bus to firmware memory. For sdio chip, reduce the complexity of TX logic will help TX efficiency since its memory is limited, and it will reduce the TX circle's time of each packet and then firmware will have more memory for TX since TX complete also need memeory.

This patch disable TX complete indication from firmware for htt data packet, it will not have TX complete indication from firmware to ath10k. It will cut the cost of bus bandwidth of TX complete and make the TX logic of firmware simpler, it results in significant performance improvement on TX path.

Udp TX throughout is 130Mbps without this patch, and it arrives 400Mbps with this patch.

The downside of this patch is the command "iw wlan0 station dump" will show 0 for "tx retries" and "tx failed" since all tx packet's status is success.

Quoted 7 lines

This patch only effect sdio chip, it will not effect PCI, SNOC etc.

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

This has new warnings:

drivers/net/wireless/ath/ath10k/htt_tx.c: In function 'ath10k_htt_htc_tx_complete':
drivers/net/wireless/ath/ath10k/htt_tx.c:566:30: warning: 'msg_type' may be used uninitialized in this function [-Wmaybe-uninitialized] drivers/net/wireless/ath/ath10k/htt_tx.c:573:6: warning: 'flags1' may be used uninitialized in this function [-Wmaybe-uninitialized] drivers/net/wireless/ath/ath10k/htt_tx.c:577:42: warning: 'desc_hdr' may be used uninitialized in this function [-Wmaybe-uninitialized]

From what I can see these are false positives, but please do double check that. In the pending branch I solved it like this:

drivers/net/wireless/ath/ath10k/htt_tx.c +3 -3
@@ -546,9 +546,9 @@ void ath10k_htt_htc_tx_complete(struct ath10k *ar, struct sk_buff *skb)
        struct ath10k_htt *htt = &ar->htt;
        struct htt_tx_done tx_done = {0};
        struct htt_cmd_hdr *htt_hdr;
-       struct htt_data_tx_desc *desc_hdr;
-       u16 flags1;
-       u8 msg_type;
+       struct htt_data_tx_desc *desc_hdr = NULL;
+       u16 flags1 = 0;
+       u8 msg_type = 0;
 
        if (htt->disable_tx_comp) {
                htt_hdr = (struct htt_cmd_hdr *)skb->data;
Signature · 8 lines
https://patchwork.kernel.org/patch/11377827/

https://wireless.wiki.kernel.org/en/developers/documentation/submittingpatches

_______________________________________________
ath10k mailing list
[email protected]
http://lists.infradead.org/mailman/listinfo/ath10k

A message that is not in the archive (sent off-list or not yet received): [email protected]

author
#5 lore raw

Re: [PATCH v9 1/4] ath10k: disable TX complete indication of htt for sdio

Quoted 11 lines · Kalle Valo

This has new warnings:

drivers/net/wireless/ath/ath10k/htt_tx.c: In function 'ath10k_htt_htc_tx_complete':
drivers/net/wireless/ath/ath10k/htt_tx.c:566:30: warning: 'msg_type' may be used uninitialized in this function [-Wmaybe-uninitialized] drivers/net/wireless/ath/ath10k/htt_tx.c:573:6: warning: 'flags1' may be used uninitialized in this function [-Wmaybe-uninitialized] drivers/net/wireless/ath/ath10k/htt_tx.c:577:42: warning: 'desc_hdr' may be used uninitialized in this function [-Wmaybe-uninitialized]

I already run ath10k-check, but not see these warnings. my gcc: gcc (Ubuntu 4.8.4-2ubuntu1~14.04.4) 4.8.4 so is it because my gcc too version too low?

Quoted 18 lines
Quoted 1 line

From what I can see these are false positives, but please do double check that. In

the pending branch I solved it like this:

drivers/net/wireless/ath/ath10k/htt_tx.c +3 -3
@@ -546,9 +546,9 @@ void ath10k_htt_htc_tx_complete(struct ath10k *ar,
 struct sk_buff *skb)
        struct ath10k_htt *htt = &ar->htt;
        struct htt_tx_done tx_done = {0};
        struct htt_cmd_hdr *htt_hdr;
-       struct htt_data_tx_desc *desc_hdr;
-       u16 flags1;
-       u8 msg_type;
+       struct htt_data_tx_desc *desc_hdr = NULL;
+       u16 flags1 = 0;
+       u8 msg_type = 0;
 
        if (htt->disable_tx_comp) {
Quoted 1 line
                htt_hdr = (struct htt_cmd_hdr *)skb->data;

_______________________________________________
ath10k mailing list
[email protected]
http://lists.infradead.org/mailman/listinfo/ath10k

#6 lore raw

Re: [PATCH v9 1/4] ath10k: disable TX complete indication of htt for sdio

Quoted 14 lines · Wen Gong
Quoted 11 lines · Kalle Valo

This has new warnings:

drivers/net/wireless/ath/ath10k/htt_tx.c: In function 'ath10k_htt_htc_tx_complete':
drivers/net/wireless/ath/ath10k/htt_tx.c:566:30: warning: 'msg_type' may be used uninitialized in this function [-Wmaybe-uninitialized] drivers/net/wireless/ath/ath10k/htt_tx.c:573:6: warning: 'flags1' may be used uninitialized in this function [-Wmaybe-uninitialized] drivers/net/wireless/ath/ath10k/htt_tx.c:577:42: warning: 'desc_hdr' may be used uninitialized in this function [-Wmaybe-uninitialized]

Quoted 3 lines

I already run ath10k-check, but not see these warnings. my gcc: gcc (Ubuntu 4.8.4-2ubuntu1~14.04.4) 4.8.4 so is it because my gcc too version too low?

Most likely, I'm using 9.2 from crosstool:

x86_64-linux-gcc (GCC) 9.2.0

crosstool is a handy way to install GCC for kernel compilations, here are my notes:

listings: https://www.kernel.org/pub/tools/crosstool/

wget https://www.kernel.org/pub/tools/crosstool/files/bin/x86_64/8.1.0/x86_64-gcc-8.1.0-nolibc-x86_64-linux.tar.xz
pushd /opt/cross/
tar -xf ~/tmp/crosstool/x86_64-gcc-8.1.0-nolibc-x86_64-linux.tar.xz

In top level create GNUMakefile:

CROSS_COMPILE=/opt/cross/gcc-8.1.0-nolibc/x86_64-linux/bin/x86_64-linux- include Makefile

Signature · 1 line
https://wireless.wiki.kernel.org/en/developers/documentation/submittingpatches
#7 lore raw

Re: [PATCH v9 1/4] ath10k: disable TX complete indication of htt for sdio

In reply to Wen Gong
Quoted 22 lines · Wen Gong

For sdio chip, it is high latency bus, all the TX packet's content will be tranferred from HOST memory to firmware memory via sdio bus, then it need much more memory in firmware than low latency bus chip, for low latency chip, such as PCI-E, it only need to transfer the TX descriptor via PCI-E bus to firmware memory. For sdio chip, reduce the complexity of TX logic will help TX efficiency since its memory is limited, and it will reduce the TX circle's time of each packet and then firmware will have more memory for TX since TX complete also need memeory.

This patch disable TX complete indication from firmware for htt data packet, it will not have TX complete indication from firmware to ath10k. It will cut the cost of bus bandwidth of TX complete and make the TX logic of firmware simpler, it results in significant performance improvement on TX path.

Udp TX throughout is 130Mbps without this patch, and it arrives 400Mbps with this patch.

The downside of this patch is the command "iw wlan0 station dump" will show 0 for "tx retries" and "tx failed" since all tx packet's status is success.

Quoted 7 lines

This patch only effect sdio chip, it will not effect PCI, SNOC etc.

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

2 patches applied to ath-next branch of ath.git, thanks.

d81686d33356 ath10k: disable TX complete indication of htt for sdio c61a74837043 ath10k: change ATH10K_SDIO_BUS_REQUEST_MAX_NUM from 64 to 1024

Signature · 8 lines
https://patchwork.kernel.org/patch/11377827/

https://wireless.wiki.kernel.org/en/developers/documentation/submittingpatches

_______________________________________________
ath10k mailing list
[email protected]
http://lists.infradead.org/mailman/listinfo/ath10k
#8 lore raw

Re: [PATCH v9 1/4] ath10k: disable TX complete indication of htt for sdio

In reply to Wen Gong
Quoted 22 lines · Wen Gong

For sdio chip, it is high latency bus, all the TX packet's content will be tranferred from HOST memory to firmware memory via sdio bus, then it need much more memory in firmware than low latency bus chip, for low latency chip, such as PCI-E, it only need to transfer the TX descriptor via PCI-E bus to firmware memory. For sdio chip, reduce the complexity of TX logic will help TX efficiency since its memory is limited, and it will reduce the TX circle's time of each packet and then firmware will have more memory for TX since TX complete also need memeory.

This patch disable TX complete indication from firmware for htt data packet, it will not have TX complete indication from firmware to ath10k. It will cut the cost of bus bandwidth of TX complete and make the TX logic of firmware simpler, it results in significant performance improvement on TX path.

Udp TX throughout is 130Mbps without this patch, and it arrives 400Mbps with this patch.

The downside of this patch is the command "iw wlan0 station dump" will show 0 for "tx retries" and "tx failed" since all tx packet's status is success.

Quoted 7 lines

This patch only effect sdio chip, it will not effect PCI, SNOC etc.

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

2 patches applied to ath-next branch of ath.git, thanks.

d81686d33356 ath10k: disable TX complete indication of htt for sdio c61a74837043 ath10k: change ATH10K_SDIO_BUS_REQUEST_MAX_NUM from 64 to 1024

Signature · 3 lines
https://patchwork.kernel.org/patch/11377827/

https://wireless.wiki.kernel.org/en/developers/documentation/submittingpatches
author
#9 lore raw

PATCH v9 2/4 ath10k: change ATH10K_SDIO_BUS_REQUEST_MAX_NUM from 64 to 1024

In reply to Wen Gong

sdio bus bandwidth is low, sometimes for high performance TX test, it will lack of ath10k_sdio_bus_request, it will print message:
ath10k_sdio mmc1:0001:1: unable to allocate bus request for async request

change the num from 64 to 1024 will not happen it.

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

---
 drivers/net/wireless/ath/ath10k/sdio.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)
drivers/net/wireless/ath/ath10k/sdio.h +2 -1
index 33195f49acab..1c987494ad22 100644
@@ -37,7 +37,7 @@
 	(ATH10K_SDIO_MAX_BUFFER_SIZE - sizeof(struct ath10k_htc_hdr))
 
 #define ATH10K_HIF_MBOX_NUM_MAX                 4
-#define ATH10K_SDIO_BUS_REQUEST_MAX_NUM         64
+#define ATH10K_SDIO_BUS_REQUEST_MAX_NUM         1024
 
 #define ATH10K_SDIO_HIF_COMMUNICATION_TIMEOUT_HZ (100 * HZ)
 
@@ -98,6 +98,7 @@
 #define ATH10K_FIFO_TIMEOUT_AND_CHIP_CONTROL_DISABLE_SLEEP_OFF 0xFFFEFFFF
 #define ATH10K_FIFO_TIMEOUT_AND_CHIP_CONTROL_DISABLE_SLEEP_ON 0x10000
 
+/* TODO: remove this and use skb->cb instead, much cleaner approach */
 struct ath10k_sdio_bus_request {
 	struct list_head list;
 
Signature · 6 lines
2.23.0

_______________________________________________
ath10k mailing list
[email protected]
http://lists.infradead.org/mailman/listinfo/ath10k
author
#10 lore raw

PATCH v9 3/4 ath10k: add htt TX bundle for sdio

In reply to Wen Gong

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.

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.

---
 drivers/net/wireless/ath/ath10k/core.c   |  14 +-
 drivers/net/wireless/ath/ath10k/core.h   |   4 +-
 drivers/net/wireless/ath/ath10k/htc.c    | 372 +++++++++++++++++++++--
 drivers/net/wireless/ath/ath10k/htc.h    |  24 +-
 drivers/net/wireless/ath/ath10k/htt.c    |   8 +
 drivers/net/wireless/ath/ath10k/htt.h    |   4 +
 drivers/net/wireless/ath/ath10k/htt_rx.c |   1 +
 drivers/net/wireless/ath/ath10k/htt_tx.c |   8 +-
 8 files changed, 398 insertions(+), 37 deletions(-)
drivers/net/wireless/ath/ath10k/core.c +11 -3
index b21c5f2fa04b..8663abaa71d1 100644
@@ -3208,6 +3208,11 @@ 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);
@@ -3235,7 +3240,7 @@ 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)
@@ -3245,12 +3250,12 @@ 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);
 
@@ -3266,6 +3271,9 @@ 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);
drivers/net/wireless/ath/ath10k/core.h +3 -1
index 5101bf2b5b15..e57b2e7235e3 100644
@@ -1089,7 +1089,7 @@ 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;
 
@@ -1130,6 +1130,8 @@ 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
drivers/net/wireless/ath/ath10k/htc.c +342 -30

437 lines not on this page · raw message

drivers/net/wireless/ath/ath10k/htc.h +22 -2
index 14e5c3f712c1..d045dbc42158 100644
@@ -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);
drivers/net/wireless/ath/ath10k/htt.c +8 -0
index b07f14b53e72..eac9a27f1a54 100644
@@ -137,6 +137,8 @@ int ath10k_htt_connect(struct ath10k_htt *htt)
 {
 	struct ath10k_htc_svc_conn_req conn_req;
 	struct ath10k_htc_svc_conn_resp conn_resp;
+	struct ath10k *ar = htt->ar;
+	struct ath10k_htc_ep *ep;
 	int status;
 
 	memset(&conn_req, 0, sizeof(conn_req));
@@ -144,6 +146,7 @@ int ath10k_htt_connect(struct ath10k_htt *htt)
 
 	conn_req.ep_ops.ep_tx_complete = ath10k_htt_htc_tx_complete;
 	conn_req.ep_ops.ep_rx_complete = ath10k_htt_htc_t2h_msg_handler;
+	conn_req.ep_ops.ep_tx_credits = ath10k_htt_op_ep_tx_credits;
 
 	/* connect to control service */
 	conn_req.service_id = ATH10K_HTC_SVC_ID_HTT_DATA_MSG;
@@ -156,6 +159,11 @@ int ath10k_htt_connect(struct ath10k_htt *htt)
 
 	htt->eid = conn_resp.eid;
 
+	if (ar->bus_param.dev_type == ATH10K_DEV_TYPE_HL) {
+		ep = &ar->htc.endpoint[htt->eid];
+		ath10k_htc_setup_tx_req(ep);
+	}
+
 	htt->disable_tx_comp = ath10k_hif_get_htt_tx_complete(htt->ar);
 	if (htt->disable_tx_comp)
 		ath10k_htc_change_tx_credit_flow(&htt->ar->htc, htt->eid, true);
drivers/net/wireless/ath/ath10k/htt.h +4 -0
index 2b3f32c929d1..3c2096d0766b 100644
@@ -2062,6 +2062,9 @@ struct ath10k_htt {
 	const struct ath10k_htt_tx_ops *tx_ops;
 	const struct ath10k_htt_rx_ops *rx_ops;
 	bool disable_tx_comp;
+	bool bundle_tx;
+	struct sk_buff_head tx_req_head;
+	struct sk_buff_head tx_complete_head;
 };
 
 struct ath10k_htt_tx_ops {
@@ -2308,6 +2311,7 @@ int ath10k_htt_tx_fetch_resp(struct ath10k *ar,
 			     __le16 fetch_seq_num,
 			     struct htt_tx_fetch_record *records,
 			     size_t num_records);
+void ath10k_htt_op_ep_tx_credits(struct ath10k *ar);
 
 void ath10k_htt_tx_txq_update(struct ieee80211_hw *hw,
 			      struct ieee80211_txq *txq);
drivers/net/wireless/ath/ath10k/htt_rx.c +1 -0
index 2427adda4d9a..283ffac56b1a 100644
@@ -4059,6 +4059,7 @@ bool ath10k_htt_t2h_msg_handler(struct ath10k *ar, struct sk_buff *skb)
 			ath10k_dbg(ar, ATH10K_DBG_HTT,
 				   "credit total:%d\n",
 				   ep->tx_credits);
+			ep->ep_ops.ep_tx_credits(htc->ar);
 		}
 		break;
 	}
drivers/net/wireless/ath/ath10k/htt_tx.c +7 -1
index 8f2fda382b6b..0beb73aecaac 100644
@@ -531,6 +531,7 @@ void ath10k_htt_tx_destroy(struct ath10k_htt *htt)
 
 void ath10k_htt_tx_stop(struct ath10k_htt *htt)
 {
+	ath10k_htc_stop_hl(htt->ar);
 	idr_for_each(&htt->pending_tx, ath10k_htt_tx_clean_up_pending, htt->ar);
 	idr_destroy(&htt->pending_tx);
 }
@@ -541,6 +542,11 @@ void ath10k_htt_tx_free(struct ath10k_htt *htt)
 	ath10k_htt_tx_destroy(htt);
 }
 
+void ath10k_htt_op_ep_tx_credits(struct ath10k *ar)
+{
+	queue_work(ar->workqueue, &ar->bundle_tx_work);
+}
+
 void ath10k_htt_htc_tx_complete(struct ath10k *ar, struct sk_buff *skb)
 {
 	struct ath10k_htt *htt = &ar->htt;
@@ -1369,7 +1375,7 @@ static int ath10k_htt_tx_hl(struct ath10k_htt *htt, enum ath10k_hw_txrx_mode txm
 	 */
 	tx_desc->peerid = __cpu_to_le32(HTT_INVALID_PEERID);
 
-	res = ath10k_htc_send(&htt->ar->htc, htt->eid, msdu);
+	res = ath10k_htc_send_hl(&htt->ar->htc, htt->eid, msdu);
 
 out:
 	return res;
Signature · 1 line
2.23.0
#11 lore raw

Re: [PATCH v9 3/4] ath10k: add htt TX bundle for sdio

Quoted 27 lines · Wen Gong

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.

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.

[...]

drivers/net/wireless/ath/ath10k/core.c struct ath10k *ath10k_core_create(size_t priv_size, struct device *dev, · line 3214

Quoted 10 lines
drivers/net/wireless/ath/ath10k/core.c +4 -0
@@ -3208,6 +3208,11 @@ 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;

We already have three threads:

ath/ath10k/core.c:      ar->workqueue = create_singlethread_workqueue("ath10k_wq");
ath/ath10k/core.c:      ar->workqueue_aux = create_singlethread_workqueue("ath10k_aux_wq");
ath/ath10k/sdio.c:      ar_sdio->workqueue = create_singlethread_workqueue("ath10k_sdio_wq");

Do we really need a fourth one? For example, why can't we use ar->workqueue_aux?

Signature · 6 lines
https://wireless.wiki.kernel.org/en/developers/documentation/submittingpatches

_______________________________________________
ath10k mailing list
[email protected]
http://lists.infradead.org/mailman/listinfo/ath10k
author
#12 lore raw

Re: [PATCH v9 3/4] ath10k: add htt TX bundle for sdio

Quoted 16 lines · Kalle Valo

drivers/net/wireless/ath/ath10k/core.c struct ath10k *ath10k_core_create(size_t priv_size, struct device *dev, · line 3214

Quoted 4 lines · Wen Gong
drivers/net/wireless/ath/ath10k/core.c +4 -0
+	ar->workqueue_tx_complete =
+		create_singlethread_workqueue("ath10k_tx_complete_wq");
+	if (!ar->workqueue_tx_complete)
+		goto err_free_aux_wq;

We already have three threads:

ath/ath10k/core.c: ar->workqueue =
create_singlethread_workqueue("ath10k_wq");
ath/ath10k/core.c: ar->workqueue_aux =
create_singlethread_workqueue("ath10k_aux_wq");
ath/ath10k/sdio.c: ar_sdio->workqueue =
create_singlethread_workqueue("ath10k_sdio_wq");

Quoted 2 lines

Do we really need a fourth one? For example, why can't we use ar->workqueue_aux?

For tcp test, it has 4 thread work meanwhile:
tx_bundle_skbs(ar->workqueue),
rx_indication(ar->workqueue_aux),
sdio_async_tx_request(ar_sdio->workqueue),
tx_bundle_complete(ar->workqueue_tx_complete)

It has 4+ cpu/core in system, if reduced to 3 threads, then tcp throughput will drop. only when it only has 1/2/3 cpu/core in system, then reduced to 3 threads will not drop.

_______________________________________________
ath10k mailing list
[email protected]
http://lists.infradead.org/mailman/listinfo/ath10k

#13 lore raw

Re: [PATCH v9 3/4] ath10k: add htt TX bundle for sdio

Quoted 26 lines · Wen Gong
Quoted 16 lines · Kalle Valo

drivers/net/wireless/ath/ath10k/core.c struct ath10k *ath10k_core_create(size_t priv_size, struct device *dev, · line 3214

Quoted 4 lines · Wen Gong
drivers/net/wireless/ath/ath10k/core.c +4 -0
+	ar->workqueue_tx_complete =
+		create_singlethread_workqueue("ath10k_tx_complete_wq");
+	if (!ar->workqueue_tx_complete)
+		goto err_free_aux_wq;

We already have three threads:

ath/ath10k/core.c: ar->workqueue =
create_singlethread_workqueue("ath10k_wq");
ath/ath10k/core.c: ar->workqueue_aux =
create_singlethread_workqueue("ath10k_aux_wq");
ath/ath10k/sdio.c: ar_sdio->workqueue =
create_singlethread_workqueue("ath10k_sdio_wq");

Quoted 2 lines

Do we really need a fourth one? For example, why can't we use ar->workqueue_aux?

For tcp test, it has 4 thread work meanwhile:
tx_bundle_skbs(ar->workqueue),
rx_indication(ar->workqueue_aux),
sdio_async_tx_request(ar_sdio->workqueue),
tx_bundle_complete(ar->workqueue_tx_complete)

Quoted 3 lines

It has 4+ cpu/core in system, if reduced to 3 threads, then tcp throughput will drop. only when it only has 1/2/3 cpu/core in system, then reduced to 3 threads will not drop.

How much does it drop? Please add the justification (with numbers) for the new thread to the commit log, so that the reason is properly documented.

Signature · 6 lines
https://wireless.wiki.kernel.org/en/developers/documentation/submittingpatches

_______________________________________________
ath10k mailing list
[email protected]
http://lists.infradead.org/mailman/listinfo/ath10k
#14 lore raw

Re: [PATCH v9 3/4] ath10k: add htt TX bundle for sdio

Quoted 28 lines · Kalle Valo
Quoted 26 lines · Wen Gong
Quoted 16 lines · Kalle Valo

drivers/net/wireless/ath/ath10k/core.c struct ath10k *ath10k_core_create(size_t priv_size, struct device *dev, · line 3214

Quoted 4 lines · Wen Gong
drivers/net/wireless/ath/ath10k/core.c +4 -0
+	ar->workqueue_tx_complete =
+		create_singlethread_workqueue("ath10k_tx_complete_wq");
+	if (!ar->workqueue_tx_complete)
+		goto err_free_aux_wq;

We already have three threads:

ath/ath10k/core.c: ar->workqueue =
create_singlethread_workqueue("ath10k_wq");
ath/ath10k/core.c: ar->workqueue_aux =
create_singlethread_workqueue("ath10k_aux_wq");
ath/ath10k/sdio.c: ar_sdio->workqueue =
create_singlethread_workqueue("ath10k_sdio_wq");

Quoted 2 lines

Do we really need a fourth one? For example, why can't we use ar->workqueue_aux?

For tcp test, it has 4 thread work meanwhile:
tx_bundle_skbs(ar->workqueue),
rx_indication(ar->workqueue_aux),
sdio_async_tx_request(ar_sdio->workqueue),
tx_bundle_complete(ar->workqueue_tx_complete)

Quoted 7 lines
Quoted 3 lines

It has 4+ cpu/core in system, if reduced to 3 threads, then tcp throughput will drop. only when it only has 1/2/3 cpu/core in system, then reduced to 3 threads will not drop.

How much does it drop? Please add the justification (with numbers) for the new thread to the commit log, so that the reason is properly documented.

I see that you already submitted v10. If you can give the numbers I can add them to the commit log.

Signature · 6 lines
https://wireless.wiki.kernel.org/en/developers/documentation/submittingpatches

_______________________________________________
ath10k mailing list
[email protected]
http://lists.infradead.org/mailman/listinfo/ath10k
author
#15 lore raw

Re: [PATCH v9 3/4] ath10k: add htt TX bundle for sdio

Quoted 9 lines · Kalle Valo
Quoted 3 lines · Kalle Valo

How much does it drop? Please add the justification (with numbers) for the new thread to the commit log, so that the reason is properly documented.

I see that you already submitted v10. If you can give the numbers I can add them to the commit log.

I tested for VHT80 mode for 3 thread config:
result:
TCP-RX TCP-TX UDP-RX
UDP-TX

use workqueue_tx_complete(Mbps)        423       357       448       412
change it to ar->workqueue(Mbps)       410       360       449       414
change it to ar->workqueue_aux(Mbps)   405       339       446       401

each thread role:
tx_bundle_skbs(ar->workqueue),
rx_indication(ar->workqueue_aux),
sdio_async_tx_request(ar_sdio->workqueue),
tx_bundle_complete(ar->workqueue_tx_complete)

_______________________________________________
ath10k mailing list
[email protected]
http://lists.infradead.org/mailman/listinfo/ath10k

#16 lore raw

Re: [PATCH v9 3/4] ath10k: add htt TX bundle for sdio

Quoted 11 lines · Wen Gong
Quoted 9 lines · Kalle Valo
Quoted 3 lines · Kalle Valo

How much does it drop? Please add the justification (with numbers) for the new thread to the commit log, so that the reason is properly documented.

I see that you already submitted v10. If you can give the numbers I can add them to the commit log.

Quoted 7 lines

I tested for VHT80 mode for 3 thread config:
result:
TCP-RX TCP-TX UDP-RX
UDP-TX

use workqueue_tx_complete(Mbps)        423       357       448       412
change it to ar->workqueue(Mbps)       410       360       449       414
change it to ar->workqueue_aux(Mbps)   405       339       446       401

Thanks, I added the table to the commit log.

Signature · 1 line
https://wireless.wiki.kernel.org/en/developers/documentation/submittingpatches
#17 lore raw

Re: [PATCH v9 3/4] ath10k: add htt TX bundle for sdio

In reply to Wen Gong
Quoted 27 lines · Wen Gong

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.

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.

[...]

drivers/net/wireless/ath/ath10k/htc.c static void ath10k_htc_prepare_tx_skb(struct ath10k_htc_ep *ep, · line 122

Quoted 12 lines
drivers/net/wireless/ath/ath10k/htc.c +12 -0
+	if (ep->tx_credits < credits) {
+		ath10k_dbg(ar, ATH10K_DBG_HTC,
+			   "htc insufficient credits ep %d required %d available %d consume %d\n",
+			   eid, credits, ep->tx_credits, consume);
+		ret = -EAGAIN;
+		goto unlock;
+	}
+
+	if (consume) {
+		ep->tx_credits -= credits;
+		ath10k_dbg(ar, ATH10K_DBG_HTC,
+			   "htc ep %d consumed %d credits (total %d)\n",

"htc ep %d consumed %d credits total %d\n"

[...]

drivers/net/wireless/ath/ath10k/htc.c static u8 ath10k_htc_get_credit_allocation(struct ath10k_htc *htc, · line 636

Quoted 1 line
drivers/net/wireless/ath/ath10k/htc.c +1 -0
+	ath10k_dbg(ar, ATH10K_DBG_HTC, "bundle skb: len:%d\n", bundle_skb->len);

"htc bundle skb len %d\n"

In other words, start with "htc" and don't use colons or parenthesis. This applies to most of debug messages in this patch.

Signature · 1 line
https://wireless.wiki.kernel.org/en/developers/documentation/submittingpatches
author
#18 lore raw

Re: [PATCH v9 3/4] ath10k: add htt TX bundle for sdio

Quoted 8 lines · Kalle Valo

drivers/net/wireless/ath/ath10k/htc.c static void ath10k_htc_prepare_tx_skb(struct ath10k_htc_ep *ep, · line 122

Quoted 3 lines
drivers/net/wireless/ath/ath10k/htc.c +3 -0
+		ep->tx_credits -= credits;
+		ath10k_dbg(ar, ATH10K_DBG_HTC,
+			   "htc ep %d consumed %d credits (total %d)\n",

"htc ep %d consumed %d credits total %d\n"

[...]

Quoted 7 lines
Quoted 2 lines
(quoted diff) +1 -0
+	ath10k_dbg(ar, ATH10K_DBG_HTC, "bundle skb: len:%d\n", 

bundle_skb->len);

"htc bundle skb len %d\n"

In other words, start with "htc" and don't use colons or parenthesis. This applies to most of debug messages in this patch.

I will change the log and other log and sent v10.
but "ath10k: disable TX complete indication of htt for sdio" and
"ath10k: change ATH10K_SDIO_BUS_REQUEST_MAX_NUM from 64 to 1024" has appied to ath-next, so I only need to send the left 2 patches:
"ath10k: add htt TX bundle for sdio" and "ath10k: enable alt data of TX path for sdio", right?

#19 lore raw

Re: [PATCH v9 3/4] ath10k: add htt TX bundle for sdio

Quoted 18 lines · Wen Gong
Quoted 8 lines · Kalle Valo

drivers/net/wireless/ath/ath10k/htc.c static void ath10k_htc_prepare_tx_skb(struct ath10k_htc_ep *ep, · line 122

Quoted 3 lines
drivers/net/wireless/ath/ath10k/htc.c +3 -0
+		ep->tx_credits -= credits;
+		ath10k_dbg(ar, ATH10K_DBG_HTC,
+			   "htc ep %d consumed %d credits (total %d)\n",

"htc ep %d consumed %d credits total %d\n"

[...]

Quoted 7 lines
Quoted 2 lines
(quoted diff) +1 -0
+	ath10k_dbg(ar, ATH10K_DBG_HTC, "bundle skb: len:%d\n",

bundle_skb->len);

"htc bundle skb len %d\n"

In other words, start with "htc" and don't use colons or parenthesis. This applies to most of debug messages in this patch.

Quoted 7 lines

I will change the log and other log and sent v10.
but "ath10k: disable TX complete indication of htt for sdio" and "ath10k: change ATH10K_SDIO_BUS_REQUEST_MAX_NUM from 64 to 1024" has appied to ath-next,
so I only need to send the left 2 patches:
"ath10k: add htt TX bundle for sdio" and "ath10k: enable alt data of TX path for sdio", right?

Correct, I already applied patches 1 and 2. But before you resend patches 3-4 did you see my question about creating a new thread, is it really necessary?

Signature · 6 lines
https://wireless.wiki.kernel.org/en/developers/documentation/submittingpatches

_______________________________________________
ath10k mailing list
[email protected]
http://lists.infradead.org/mailman/listinfo/ath10k
author
#20 lore raw

Re: [PATCH v9 3/4] ath10k: add htt TX bundle for sdio

Quoted 28 lines · Kalle Valo
Quoted 18 lines · Wen Gong
Quoted 8 lines · Kalle Valo

drivers/net/wireless/ath/ath10k/htc.c static void ath10k_htc_prepare_tx_skb(struct ath10k_htc_ep *ep, · line 122

Quoted 3 lines
drivers/net/wireless/ath/ath10k/htc.c +3 -0
+		ep->tx_credits -= credits;
+		ath10k_dbg(ar, ATH10K_DBG_HTC,
+			   "htc ep %d consumed %d credits (total %d)\n",

"htc ep %d consumed %d credits total %d\n"

[...]

Quoted 7 lines
Quoted 2 lines
(quoted diff) +1 -0
+	ath10k_dbg(ar, ATH10K_DBG_HTC, "bundle skb: len:%d\n",

bundle_skb->len);

"htc bundle skb len %d\n"

In other words, start with "htc" and don't use colons or parenthesis. This applies to most of debug messages in this patch.

Quoted 7 lines

I will change the log and other log and sent v10.
but "ath10k: disable TX complete indication of htt for sdio" and "ath10k: change ATH10K_SDIO_BUS_REQUEST_MAX_NUM from 64 to 1024" has appied to ath-next,
so I only need to send the left 2 patches:
"ath10k: add htt TX bundle for sdio" and "ath10k: enable alt data of TX path for sdio", right?

Quoted 3 lines

Correct, I already applied patches 1 and 2. But before you resend patches 3-4 did you see my question about creating a new thread, is it really necessary?

already replied.

_______________________________________________
ath10k mailing list
[email protected]
http://lists.infradead.org/mailman/listinfo/ath10k

author
#21 lore raw

PATCH v9 4/4 ath10k: enable alt data of TX path for sdio

In reply to Wen Gong

The default credit size is 1792 bytes, but the IP mtu is 1500 bytes, then it has about 290 bytes's waste for each data packet on sdio transfer path for TX bundle, it will reduce the transmission utilization ratio for data packet.

This patch enable the small credit size in firmware, firmware will use the new credit size 1556 bytes, it will increase the transmission utilization ratio for data packet on TX patch. It results in significant performance improvement on TX path.

This patch only effect sdio chip, it will not effect PCI, SNOC etc.

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

---
 drivers/net/wireless/ath/ath10k/core.c |  8 ++++----
 drivers/net/wireless/ath/ath10k/htc.c  | 12 ++++++++++--
 drivers/net/wireless/ath/ath10k/htc.h  | 13 +++++++++++--
 3 files changed, 25 insertions(+), 8 deletions(-)
drivers/net/wireless/ath/ath10k/core.c +4 -4
index 8663abaa71d1..91f131b87efc 100644
@@ -698,10 +698,10 @@ static int ath10k_init_sdio(struct ath10k *ar, enum ath10k_firmware_mode mode)
 
 	param |= HI_ACS_FLAGS_SDIO_REDUCE_TX_COMPL_SET;
 
-	/* Alternate credit size of 1544 as used by SDIO firmware is
-	 * not big enough for mac80211 / native wifi frames. disable it
-	 */
-	param &= ~HI_ACS_FLAGS_ALT_DATA_CREDIT_SIZE;
+	if (mode == ATH10K_FIRMWARE_MODE_NORMAL)
+		param |= HI_ACS_FLAGS_ALT_DATA_CREDIT_SIZE;
+	else
+		param &= ~HI_ACS_FLAGS_ALT_DATA_CREDIT_SIZE;
 
 	if (mode == ATH10K_FIRMWARE_MODE_UTF)
 		param &= ~HI_ACS_FLAGS_SDIO_SWAP_MAILBOX_SET;
drivers/net/wireless/ath/ath10k/htc.c +10 -2
index cc6a8cb6db77..78fc1695ec37 100644
@@ -957,12 +957,16 @@ int ath10k_htc_wait_target(struct ath10k_htc *htc)
 	 */
 	if (htc->control_resp_len >=
 	    sizeof(msg->hdr) + sizeof(msg->ready_ext)) {
+		htc->alt_data_credit_size =
+			__le16_to_cpu(msg->ready_ext.reserved) &
+			ATH10K_HTC_MSG_READY_EXT_ALT_DATA_MASK;
 		htc->max_msgs_per_htc_bundle =
 			min_t(u8, msg->ready_ext.max_msgs_per_htc_bundle,
 			      HTC_HOST_MAX_MSG_PER_RX_BUNDLE);
 		ath10k_dbg(ar, ATH10K_DBG_HTC,
-			   "Extended ready message. RX bundle size: %d\n",
-			   htc->max_msgs_per_htc_bundle);
+			   "Extended ready message. RX bundle size: %d, alt size:%d\n",
+			   htc->max_msgs_per_htc_bundle,
+			   htc->alt_data_credit_size);
 	}
 
 	INIT_WORK(&ar->bundle_tx_work, ath10k_htc_bundle_tx_work);
@@ -1114,6 +1118,10 @@ int ath10k_htc_connect_service(struct ath10k_htc *htc,
 	ep->tx_credits = tx_alloc;
 	ep->tx_credit_size = htc->target_credit_size;
 
+	if (conn_req->service_id == ATH10K_HTC_SVC_ID_HTT_DATA_MSG &&
+	    htc->alt_data_credit_size != 0)
+		ep->tx_credit_size = htc->alt_data_credit_size;
+
 	/* copy all the callbacks */
 	ep->ep_ops = conn_req->ep_ops;
 
drivers/net/wireless/ath/ath10k/htc.h +11 -2
index d045dbc42158..0d180faf3b77 100644
@@ -119,6 +119,8 @@ enum ath10k_htc_conn_flags {
 #define ATH10K_HTC_CONN_FLAGS_RECV_ALLOC_LSB  8
 };
 
+#define ATH10K_HTC_MSG_READY_EXT_ALT_DATA_MASK 0xFFF
+
 enum ath10k_htc_conn_svc_status {
 	ATH10K_HTC_CONN_SVC_STATUS_SUCCESS      = 0,
 	ATH10K_HTC_CONN_SVC_STATUS_NOT_FOUND    = 1,
@@ -155,8 +157,14 @@ struct ath10k_htc_ready_extended {
 	struct ath10k_htc_ready base;
 	u8 htc_version; /* @enum ath10k_htc_version */
 	u8 max_msgs_per_htc_bundle;
-	u8 pad0;
-	u8 pad1;
+	union {
+		__le16 reserved;
+		struct {
+			u8 pad0;
+			u8 pad1;
+		} __packed;
+	} __packed;
+
 } __packed;
 
 struct ath10k_htc_conn_svc {
@@ -393,6 +401,7 @@ struct ath10k_htc {
 	int total_transmit_credits;
 	int target_credit_size;
 	u8 max_msgs_per_htc_bundle;
+	int alt_data_credit_size;
 };
 
 int ath10k_htc_init(struct ath10k *ar);
Signature · 6 lines
2.23.0

_______________________________________________
ath10k mailing list
[email protected]
http://lists.infradead.org/mailman/listinfo/ath10k