Skip to contentSkip to conversation

wifi: rtw89: Lower the timeout in rtw89_fw_read_c2h_reg() for USB

PATCH In review Bitterblue Smith 2 participants 6 messages Jul 15, 2025 – Jul 18, 2025 Realtek wireless driver (rtw89)

lore
Share & tools
lore
#0 lore raw

PATCH v2 1/2 wifi: rtw89: Lower the timeout in rtw89_fw_read_c2h_reg() for USB

This read_poll_timeout_atomic() with a delay of 1 µs and a timeout of 1000000 µs can take ~250 seconds in the worst case because sending a USB control message takes ~250 µs.

Lower the timeout to 4000 for USB in order to reduce the maximum polling time to ~1 second.

This problem was observed with RTL8851BU while suspending to RAM with WOWLAN enabled. The computer sat for 4 minutes with a black screen before suspending.

---
v2:
- Lower the timeout for USB instead of increasing the delay.

---
 drivers/net/wireless/realtek/rtw89/fw.c | 9 +++++++--
 drivers/net/wireless/realtek/rtw89/fw.h | 2 ++
 2 files changed, 9 insertions(+), 2 deletions(-)
drivers/net/wireless/realtek/rtw89/fw.c +7 -2
index 73a4ec988d16..b774a329e7c7 100644
@@ -6755,13 +6755,18 @@ static int rtw89_fw_read_c2h_reg(struct rtw89_dev *rtwdev,
 	const struct rtw89_chip_info *chip = rtwdev->chip;
 	struct rtw89_fw_info *fw_info = &rtwdev->fw;
 	const u32 *c2h_reg = chip->c2h_regs;
-	u32 ret;
+	u32 ret, timeout;
 	u8 i, val;
 
 	info->id = RTW89_FWCMD_C2HREG_FUNC_NULL;
 
+	if (rtwdev->hci.type == RTW89_HCI_TYPE_USB)
+		timeout = RTW89_C2H_TIMEOUT_USB;
+	else
+		timeout = RTW89_C2H_TIMEOUT;
+
 	ret = read_poll_timeout_atomic(rtw89_read8, val, val, 1,
-				       RTW89_C2H_TIMEOUT, false, rtwdev,
+				       timeout, false, rtwdev,
 				       chip->c2h_ctrl_reg);
 	if (ret) {
 		rtw89_warn(rtwdev, "c2h reg timeout\n");
drivers/net/wireless/realtek/rtw89/fw.h +2 -0
index 98be7e72c685..a731c242f389 100644
@@ -115,6 +115,8 @@ struct rtw89_h2creg_sch_tx_en {
 #define RTW89_C2HREG_HDR_LEN 2
 #define RTW89_H2CREG_HDR_LEN 2
 #define RTW89_C2H_TIMEOUT 1000000
+#define RTW89_C2H_TIMEOUT_USB 4000
+
 struct rtw89_mac_c2h_info {
 	u8 id;
 	u8 content_len;
Signature · 1 line
2.50.0
#1 lore raw

PATCH v2 2/2 wifi: rtw89: Lower the timeout in rtw89_fwdl_check_path_ready_ax() for USB

When the chip is not powered on correctly (like during driver development) rtw89_fwdl_check_path_ready_ax() can fail. read_poll_timeout_atomic() with a delay of 1 µs and a timeout of 400000 µs can take 50 seconds with USB because of the time it takes to send a USB control message. The firmware upload is tried 5 times, so in total it takes 250 seconds.

Lower the timeout to 3200 for USB in order to reduce the time rtw89_fwdl_check_path_ready_ax() takes from 50 seconds to less than 1 second.

---
v2:
- Lower the timeout for USB instead of increasing the delay.
- Don't change rtw89_fwdl_check_path_ready_be(). It uses a larger timeout than rtw89_fwdl_check_path_ready_ax(). Leave it for later when I can test it.

---
 drivers/net/wireless/realtek/rtw89/fw.h  | 1 +
 drivers/net/wireless/realtek/rtw89/mac.c | 8 +++++++-
 2 files changed, 8 insertions(+), 1 deletion(-)
drivers/net/wireless/realtek/rtw89/fw.h +1 -0
index a731c242f389..7e07df4beba7 100644
@@ -4697,6 +4697,7 @@ struct rtw89_c2h_rf_tas_info {
 #define RTW89_FW_BACKTRACE_KEY 0xBACEBACE
 
 #define FWDL_WAIT_CNT 400000
+#define FWDL_WAIT_CNT_USB 3200
 
 int rtw89_fw_check_rdy(struct rtw89_dev *rtwdev, enum rtw89_fwdl_check_type type);
 int rtw89_fw_recognize(struct rtw89_dev *rtwdev);
drivers/net/wireless/realtek/rtw89/mac.c +7 -1
index f6bbc796329c..dfaf33173611 100644
@@ -6932,10 +6932,16 @@ int rtw89_fwdl_check_path_ready_ax(struct rtw89_dev *rtwdev,
 				   bool h2c_or_fwdl)
 {
 	u8 check = h2c_or_fwdl ? B_AX_H2C_PATH_RDY : B_AX_FWDL_PATH_RDY;
+	u32 timeout;
 	u8 val;
 
+	if (rtwdev->hci.type == RTW89_HCI_TYPE_USB)
+		timeout = FWDL_WAIT_CNT_USB;
+	else
+		timeout = FWDL_WAIT_CNT;
+
 	return read_poll_timeout_atomic(rtw89_read8, val, val & check,
-					1, FWDL_WAIT_CNT, false,
+					1, timeout, false,
 					rtwdev, R_AX_WCPU_FW_CTRL);
 }
 
Signature · 1 line
2.50.0
maintainer
#2 lore raw
In reply to Bitterblue Smith
Quoted 26 lines · Bitterblue Smith

This read_poll_timeout_atomic() with a delay of 1 µs and a timeout of 1000000 µs can take ~250 seconds in the worst case because sending a USB control message takes ~250 µs.

Lower the timeout to 4000 for USB in order to reduce the maximum polling time to ~1 second.

This problem was observed with RTL8851BU while suspending to RAM with WOWLAN enabled. The computer sat for 4 minutes with a black screen before suspending.

---
v2:
- Lower the timeout for USB instead of increasing the delay.

---
 drivers/net/wireless/realtek/rtw89/fw.c | 9 +++++++--
 drivers/net/wireless/realtek/rtw89/fw.h | 2 ++
 2 files changed, 9 insertions(+), 2 deletions(-)
drivers/net/wireless/realtek/rtw89/fw.c +0 -0
index 73a4ec988d16..b774a329e7c7 100644
@@ -6755,13 +6755,18 @@ static int rtw89_fw_read_c2h_reg(struct rtw89_dev *rtwdev,
        const struct rtw89_chip_info *chip = rtwdev->chip;

drivers/net/wireless/realtek/rtw89/fw.c static int rtw89_fw_read_c2h_reg(struct rtw89_dev *rtwdev, · line 6764

Quoted 10 lines
drivers/net/wireless/realtek/rtw89/fw.c +3 -1
        struct rtw89_fw_info *fw_info = &rtwdev->fw;
        const u32 *c2h_reg = chip->c2h_regs;
-       u32 ret;
+       u32 ret, timeout;
        u8 i, val;
 
        info->id = RTW89_FWCMD_C2HREG_FUNC_NULL;
 
+       if (rtwdev->hci.type == RTW89_HCI_TYPE_USB)
+               timeout = RTW89_C2H_TIMEOUT_USB;

Should we have different timeout times for USB2 and USB3? The same question for patch 2/2.

Otherwise, looks good to me.

Quoted 24 lines
drivers/net/wireless/realtek/rtw89/fw.c +4 -1
+       else
+               timeout = RTW89_C2H_TIMEOUT;
+
        ret = read_poll_timeout_atomic(rtw89_read8, val, val, 1,
-                                      RTW89_C2H_TIMEOUT, false, rtwdev,
+                                      timeout, false, rtwdev,
                                       chip->c2h_ctrl_reg);
        if (ret) {
                rtw89_warn(rtwdev, "c2h reg timeout\n");
drivers/net/wireless/realtek/rtw89/fw.h +2 -1
index 98be7e72c685..a731c242f389 100644
@@ -115,6 +115,8 @@ struct rtw89_h2creg_sch_tx_en {
 #define RTW89_C2HREG_HDR_LEN 2
 #define RTW89_H2CREG_HDR_LEN 2
 #define RTW89_C2H_TIMEOUT 1000000
+#define RTW89_C2H_TIMEOUT_USB 4000
+
 struct rtw89_mac_c2h_info {
        u8 id;
        u8 content_len;
--

2.50.0

#3 lore raw
Quoted 33 lines · Ping-Ke Shih
Quoted 32 lines · Bitterblue Smith

This read_poll_timeout_atomic() with a delay of 1 µs and a timeout of 1000000 µs can take ~250 seconds in the worst case because sending a USB control message takes ~250 µs.

Lower the timeout to 4000 for USB in order to reduce the maximum polling time to ~1 second.

This problem was observed with RTL8851BU while suspending to RAM with WOWLAN enabled. The computer sat for 4 minutes with a black screen before suspending.

---
v2:
- Lower the timeout for USB instead of increasing the delay.

---
 drivers/net/wireless/realtek/rtw89/fw.c | 9 +++++++--
 drivers/net/wireless/realtek/rtw89/fw.h | 2 ++
 2 files changed, 9 insertions(+), 2 deletions(-)
drivers/net/wireless/realtek/rtw89/fw.c +1 -1
index 73a4ec988d16..b774a329e7c7 100644
@@ -6755,13 +6755,18 @@ static int rtw89_fw_read_c2h_reg(struct rtw89_dev *rtwdev,
        const struct rtw89_chip_info *chip = rtwdev->chip;
        struct rtw89_fw_info *fw_info = &rtwdev->fw;
        const u32 *c2h_reg = chip->c2h_regs;
-       u32 ret;
+       u32 ret, timeout;
        u8 i, val;
 
Quoted 8 lines

drivers/net/wireless/realtek/rtw89/fw.c static int rtw89_fw_read_c2h_reg(struct rtw89_dev *rtwdev, · line 6764

Quoted 4 lines
drivers/net/wireless/realtek/rtw89/fw.c +2 -0
        info->id = RTW89_FWCMD_C2HREG_FUNC_NULL;
 
+       if (rtwdev->hci.type == RTW89_HCI_TYPE_USB)
+               timeout = RTW89_C2H_TIMEOUT_USB;

Should we have different timeout times for USB2 and USB3? The same question for patch 2/2.

I measured the time it takes to read R_AX_WCPU_FW_CTRL (patch 2/2):

		USB 2		USB 3

RTL8851BU 125 µs not supported
RTL8852BU 250 µs 40 µs
RTL8852CU 375 µs 40 µs

In my setup the same timeout works for both. Even with the faster reads it still waits long enough.

Quoted 28 lines

Otherwise, looks good to me.

Quoted 24 lines
drivers/net/wireless/realtek/rtw89/fw.c +4 -1
+       else
+               timeout = RTW89_C2H_TIMEOUT;
+
        ret = read_poll_timeout_atomic(rtw89_read8, val, val, 1,
-                                      RTW89_C2H_TIMEOUT, false, rtwdev,
+                                      timeout, false, rtwdev,
                                       chip->c2h_ctrl_reg);
        if (ret) {
                rtw89_warn(rtwdev, "c2h reg timeout\n");
drivers/net/wireless/realtek/rtw89/fw.h +2 -1
index 98be7e72c685..a731c242f389 100644
@@ -115,6 +115,8 @@ struct rtw89_h2creg_sch_tx_en {
 #define RTW89_C2HREG_HDR_LEN 2
 #define RTW89_H2CREG_HDR_LEN 2
 #define RTW89_C2H_TIMEOUT 1000000
+#define RTW89_C2H_TIMEOUT_USB 4000
+
 struct rtw89_mac_c2h_info {
        u8 id;
        u8 content_len;
--

2.50.0

maintainer
#4 lore raw
Quoted 45 lines · Bitterblue Smith
Quoted 33 lines · Ping-Ke Shih
Quoted 32 lines · Bitterblue Smith

This read_poll_timeout_atomic() with a delay of 1 µs and a timeout of 1000000 µs can take ~250 seconds in the worst case because sending a USB control message takes ~250 µs.

Lower the timeout to 4000 for USB in order to reduce the maximum polling time to ~1 second.

This problem was observed with RTL8851BU while suspending to RAM with WOWLAN enabled. The computer sat for 4 minutes with a black screen before suspending.

---
v2:
- Lower the timeout for USB instead of increasing the delay.

---
 drivers/net/wireless/realtek/rtw89/fw.c | 9 +++++++--
 drivers/net/wireless/realtek/rtw89/fw.h | 2 ++
 2 files changed, 9 insertions(+), 2 deletions(-)
drivers/net/wireless/realtek/rtw89/fw.c +1 -1
index 73a4ec988d16..b774a329e7c7 100644
@@ -6755,13 +6755,18 @@ static int rtw89_fw_read_c2h_reg(struct rtw89_dev *rtwdev,
        const struct rtw89_chip_info *chip = rtwdev->chip;
        struct rtw89_fw_info *fw_info = &rtwdev->fw;
        const u32 *c2h_reg = chip->c2h_regs;
-       u32 ret;
+       u32 ret, timeout;
        u8 i, val;
 
Quoted 8 lines

drivers/net/wireless/realtek/rtw89/fw.c static int rtw89_fw_read_c2h_reg(struct rtw89_dev *rtwdev, · line 6764

Quoted 4 lines
drivers/net/wireless/realtek/rtw89/fw.c +2 -0
        info->id = RTW89_FWCMD_C2HREG_FUNC_NULL;
 
+       if (rtwdev->hci.type == RTW89_HCI_TYPE_USB)
+               timeout = RTW89_C2H_TIMEOUT_USB;

Should we have different timeout times for USB2 and USB3? The same question for patch 2/2.

I measured the time it takes to read R_AX_WCPU_FW_CTRL (patch 2/2):

Quoted 7 lines

USB 2 USB 3

RTL8851BU       125 µs          not supported
RTL8852BU       250 µs          40 µs
RTL8852CU       375 µs          40 µs

In my setup the same timeout works for both. Even with the faster reads it still waits long enough.

Thanks for the info.

maintainer
#5 lore raw
In reply to Bitterblue Smith
Quoted 4 lines · Bitterblue Smith

This read_poll_timeout_atomic() with a delay of 1 µs and a timeout of 1000000 µs can take ~250 seconds in the worst case because sending a USB control message takes ~250 µs.

Quoted 8 lines

Lower the timeout to 4000 for USB in order to reduce the maximum polling time to ~1 second.

This problem was observed with RTL8851BU while suspending to RAM with WOWLAN enabled. The computer sat for 4 minutes with a black screen before suspending.

2 patch(es) applied to rtw-next branch of rtw.git, thanks.

671be46afd1f wifi: rtw89: Lower the timeout in rtw89_fw_read_c2h_reg() for USB 12322a026030 wifi: rtw89: Lower the timeout in rtw89_fwdl_check_path_ready_ax() for USB

---
https://github.com/pkshih/rtw.git