[RFC PATCH v2 0/4] wifi: rtl8xxxu: implement AP mode for 8188EU

[RFC PATCH v2 0/4] wifi: rtl8xxxu: implement AP mode for 8188EU

[Georg Müller]

This series tries to implement AP mode for Realtek RTL8188EU chips.

This is not final. I still have issues connecting to the AP, searching for some
input on what may be the reason or how to further debug issues.

Patch 1 could be picked independently as it shouldn't change anything for the
non-AP mode.

---
Changes in v2:
- add patch to move dynamic_tx_rpt_timing_counter from ra_info to priv
- convert ra_info to a dynamic array
- update max report mac id after station add/remove

---
Georg Müller (4):
  wifi: rtl8xxxu: move dynamic_tx_rpt_timing_counter from ra_info to
    priv
  wifi: rtl8xxxu: handle rate control for 8188e a per mac_id
  wifi: rtl8xxxu: update max report mac id on station add / remove for
    8188e chips
  wifi: rtl8xxxu: Enable AP mode for RTL8188EU

 drivers/net/wireless/realtek/rtl8xxxu/8188e.c | 22 +++++-----
 drivers/net/wireless/realtek/rtl8xxxu/core.c  | 41 ++++++++++++++++---
 .../net/wireless/realtek/rtl8xxxu/rtl8xxxu.h  |  5 ++-
 3 files changed, 50 insertions(+), 18 deletions(-)

-- 
2.53.0

[RFC PATCH v2 1/4] wifi: rtl8xxxu: move dynamic_tx_rpt_timing_counter from ra_info to priv

[Georg Müller]

dynamic_tx_rpt_timing_counter is not per mac_id, but used across all
mac_ids.
---
 drivers/net/wireless/realtek/rtl8xxxu/8188e.c    | 8 ++++----
 drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.h | 2 +-
 2 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtl8xxxu/8188e.c b/drivers/net/wireless/realtek/rtl8xxxu/8188e.c
index 766a7a7c7d28..de2837a91bbe 100644
--- a/drivers/net/wireless/realtek/rtl8xxxu/8188e.c
+++ b/drivers/net/wireless/realtek/rtl8xxxu/8188e.c
@@ -1550,14 +1550,14 @@ static void rtl8188e_rate_decision(struct rtl8xxxu_ra_info *ra)
 	}
 
 	if (ra->decision_rate == ra->pre_rate)
-		ra->dynamic_tx_rpt_timing_counter++;
+		priv->dynamic_tx_rpt_timing_counter++;
 	else
-		ra->dynamic_tx_rpt_timing_counter = 0;
+		priv->dynamic_tx_rpt_timing_counter = 0;
 
-	if (ra->dynamic_tx_rpt_timing_counter >= 4) {
+	if (priv->dynamic_tx_rpt_timing_counter >= 4) {
 		/* Rate didn't change 4 times, extend RPT timing */
 		rtl8188e_set_tx_rpt_timing(ra, INCREASE_TIMING);
-		ra->dynamic_tx_rpt_timing_counter = 0;
+		priv->dynamic_tx_rpt_timing_counter = 0;
 	}
 
 	ra->pre_rate = ra->decision_rate;
diff --git a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.h b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.h
index 9fb2583ffffc..4a744b5c1aec 100644
--- a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.h
+++ b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.h
@@ -1756,7 +1756,6 @@ struct rtl8xxxu_ra_info {
 	u16 drop;
 	u16 rpt_time;
 	u16 pre_min_rpt_time;
-	u8 dynamic_tx_rpt_timing_counter;
 	u8 ra_waiting_counter;
 	u8 ra_pending_counter;
 	u8 ra_drop_after_down;
@@ -1917,6 +1916,7 @@ struct rtl8xxxu_priv {
 	struct rtl8xxxu_ra_report ra_report;
 	struct rtl8xxxu_cfo_tracking cfo_tracking;
 	struct rtl8xxxu_ra_info ra_info;
+	u8 dynamic_tx_rpt_timing_counter; // 8188e specific
 
 	bool led_registered;
 	char led_name[32];
-- 
2.53.0

[RFC PATCH v2 2/4] wifi: rtl8xxxu: handle rate control for 8188e a per mac_id

[Georg Müller]

convert member ra_info to an array with one entry per mac id. This
allows having different rate control settings per connected station
in ap mode.

The max_macid_num is conservative. The old driver used 32 [1], some
other sources said 64 [2]. I have not enough adapters to test any of the
higher values. Given the usage of this chipset in nano dongles, I think
the 16 might be high enough.

[1] https://github.com/lwfinger/rtl8188eu/blob/f5d1c8df2e2d8b217ea0113bf2cf3e37df8cb716/include/sta_info.h#L28
[2] https://lore.kernel.org/linux-wireless/27e83382-4c84-1841-c428-d1e5143ea20c@gmail.com/

Signed-off-by: Georg Müller <georgmueller@gmx.net>
---
 drivers/net/wireless/realtek/rtl8xxxu/8188e.c | 12 ++++++------
 drivers/net/wireless/realtek/rtl8xxxu/core.c  | 19 ++++++++++++++-----
 .../net/wireless/realtek/rtl8xxxu/rtl8xxxu.h  |  3 ++-
 3 files changed, 22 insertions(+), 12 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtl8xxxu/8188e.c b/drivers/net/wireless/realtek/rtl8xxxu/8188e.c
index de2837a91bbe..607ca62194fc 100644
--- a/drivers/net/wireless/realtek/rtl8xxxu/8188e.c
+++ b/drivers/net/wireless/realtek/rtl8xxxu/8188e.c
@@ -1468,9 +1468,8 @@ static void rtl8188e_reset_ra_counter(struct rtl8xxxu_ra_info *ra)
 	ra->nsc_down = (n_threshold_high[rate_id] + n_threshold_low[rate_id]) >> 1;
 }
 
-static void rtl8188e_rate_decision(struct rtl8xxxu_ra_info *ra)
+static void rtl8188e_rate_decision(struct rtl8xxxu_priv *priv, struct rtl8xxxu_ra_info *ra)
 {
-	struct rtl8xxxu_priv *priv = container_of(ra, struct rtl8xxxu_priv, ra_info);
 	const u8 *retry_penalty_idx_0;
 	const u8 *retry_penalty_idx_1;
 	const u8 *retry_penalty_up_idx;
@@ -1669,7 +1668,7 @@ void rtl8188e_handle_ra_tx_report2(struct rtl8xxxu_priv *priv, struct sk_buff *s
 	u32 *_rx_desc = (u32 *)(skb->data - sizeof(struct rtl8xxxu_rxdesc16));
 	struct rtl8xxxu_rxdesc16 *rx_desc = (struct rtl8xxxu_rxdesc16 *)_rx_desc;
 	struct device *dev = &priv->udev->dev;
-	struct rtl8xxxu_ra_info *ra = &priv->ra_info;
+	struct rtl8xxxu_ra_info *ra;
 	u32 tx_rpt_len = rx_desc->pktlen & 0x3ff;
 	u32 items = tx_rpt_len / TX_RPT2_ITEM_SIZE;
 	u64 macid_valid = ((u64)_rx_desc[5] << 32) | _rx_desc[4];
@@ -1688,6 +1687,7 @@ void rtl8188e_handle_ra_tx_report2(struct rtl8xxxu_priv *priv, struct sk_buff *s
 
 	for (macid = 0; macid < items; macid++) {
 		valid = false;
+		ra = &priv->ra_info[macid];
 
 		if (macid < 64)
 			valid = macid_valid & BIT(macid);
@@ -1704,7 +1704,7 @@ void rtl8188e_handle_ra_tx_report2(struct rtl8xxxu_priv *priv, struct sk_buff *s
 
 			if (ra->total > 0) {
 				if (ra->ra_stage < 5)
-					rtl8188e_rate_decision(ra);
+					rtl8188e_rate_decision(priv, ra);
 				else if (ra->ra_stage == 5)
 					rtl8188e_power_training_try_state(ra);
 				else /* ra->ra_stage == 6 */
@@ -1781,7 +1781,7 @@ rtl8188e_update_rate_mask(struct rtl8xxxu_priv *priv,
 			  u32 ramask, u8 rateid, int sgi, int txbw_40mhz,
 			  u8 macid)
 {
-	struct rtl8xxxu_ra_info *ra = &priv->ra_info;
+	struct rtl8xxxu_ra_info *ra = &priv->ra_info[macid];
 
 	ra->rate_id = rateid;
 	ra->rate_mask = ramask;
@@ -1792,7 +1792,7 @@ rtl8188e_update_rate_mask(struct rtl8xxxu_priv *priv,
 
 static void rtl8188e_ra_set_rssi(struct rtl8xxxu_priv *priv, u8 macid, u8 rssi)
 {
-	priv->ra_info.rssi_sta_ra = rssi;
+	priv->ra_info[macid].rssi_sta_ra = rssi;
 }
 
 void rtl8188e_ra_info_init_all(struct rtl8xxxu_ra_info *ra)
diff --git a/drivers/net/wireless/realtek/rtl8xxxu/core.c b/drivers/net/wireless/realtek/rtl8xxxu/core.c
index 794187d28caa..ea4dcca9d22a 100644
--- a/drivers/net/wireless/realtek/rtl8xxxu/core.c
+++ b/drivers/net/wireless/realtek/rtl8xxxu/core.c
@@ -3921,6 +3921,7 @@ static int rtl8xxxu_init_device(struct ieee80211_hw *hw)
 	struct device *dev = &priv->udev->dev;
 	struct rtl8xxxu_fileops *fops = priv->fops;
 	bool macpower;
+	u16 mac_id;
 	int ret;
 	u8 val8;
 	u16 val16;
@@ -4393,9 +4394,16 @@ static int rtl8xxxu_init_device(struct ieee80211_hw *hw)
 		priv->cfo_tracking.crystal_cap = priv->default_crystal_cap;
 	}
 
-	if (priv->rtl_chip == RTL8188E)
-		rtl8188e_ra_info_init_all(&priv->ra_info);
-
+	if (priv->rtl_chip == RTL8188E)	{
+		priv->ra_info = kmalloc_array(RTL8188E_MAX_MAC_ID_NUM, sizeof(*priv->ra_info));
+		if (!priv->ra_info) {
+			ret = -ENOMEM;
+			goto exit;
+		}
+		for (mac_id = 0; mac_id < RTL8188E_MAX_MAC_ID_NUM; mac_id++) {
+			rtl8188e_ra_info_init_all(&priv->ra_info[mac_id]);
+		}
+	}
 	set_bit(RTL8XXXU_BC_MC_MACID, priv->mac_id_map);
 	set_bit(RTL8XXXU_BC_MC_MACID1, priv->mac_id_map);
 
@@ -5338,7 +5346,7 @@ rtl8xxxu_fill_txdesc_v3(struct ieee80211_hw *hw, struct ieee80211_hdr *hdr,
 {
 	struct rtl8xxxu_priv *priv = hw->priv;
 	struct device *dev = &priv->udev->dev;
-	struct rtl8xxxu_ra_info *ra = &priv->ra_info;
+	struct rtl8xxxu_ra_info *ra = &priv->ra_info[macid];
 	u8 *qc = ieee80211_get_qos_ctl(hdr);
 	u8 tid = qc[0] & IEEE80211_QOS_CTL_TID_MASK;
 	u32 rate = 0;
@@ -7895,6 +7903,7 @@ static int rtl8xxxu_probe(struct usb_interface *interface,
 err_set_intfdata:
 	usb_set_intfdata(interface, NULL);
 
+	kfree(priv->ra_info);
 	kfree(priv->fw_data);
 	mutex_destroy(&priv->usb_buf_mutex);
 	mutex_destroy(&priv->syson_indirect_access_mutex);
@@ -7924,7 +7933,7 @@ static void rtl8xxxu_disconnect(struct usb_interface *interface)
 	usb_set_intfdata(interface, NULL);
 
 	dev_info(&priv->udev->dev, "disconnecting\n");
-
+	kfree(priv->ra_info);
 	kfree(priv->fw_data);
 	mutex_destroy(&priv->usb_buf_mutex);
 	mutex_destroy(&priv->syson_indirect_access_mutex);
diff --git a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.h b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.h
index 4a744b5c1aec..9ce820ff4793 100644
--- a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.h
+++ b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.h
@@ -76,6 +76,7 @@
 #define RTL_FW_PAGE_SIZE		4096
 #define RTL8XXXU_FIRMWARE_POLL_MAX	1000
 
+#define RTL8188E_MAX_MAC_ID_NUM		16
 #define RTL8723A_CHANNEL_GROUPS		3
 #define RTL8723A_MAX_RF_PATHS		2
 #define RTL8723B_CHANNEL_GROUPS		6
@@ -1915,7 +1916,7 @@ struct rtl8xxxu_priv {
 	struct rtl8xxxu_btcoex bt_coex;
 	struct rtl8xxxu_ra_report ra_report;
 	struct rtl8xxxu_cfo_tracking cfo_tracking;
-	struct rtl8xxxu_ra_info ra_info;
+	struct rtl8xxxu_ra_info *ra_info;
 	u8 dynamic_tx_rpt_timing_counter; // 8188e specific
 
 	bool led_registered;
-- 
2.53.0

[RFC PATCH v2 3/4] wifi: rtl8xxxu: update max report mac id on station add / remove for 8188e chips

[Georg Müller]

---
 drivers/net/wireless/realtek/rtl8xxxu/core.c | 22 +++++++++++++++++++-
 1 file changed, 21 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/realtek/rtl8xxxu/core.c b/drivers/net/wireless/realtek/rtl8xxxu/core.c
index ea4dcca9d22a..6d97bb212f75 100644
--- a/drivers/net/wireless/realtek/rtl8xxxu/core.c
+++ b/drivers/net/wireless/realtek/rtl8xxxu/core.c
@@ -3884,6 +3884,15 @@ void rtl8xxxu_init_burst(struct rtl8xxxu_priv *priv)
 	rtl8xxxu_write8(priv, REG_RSV_CTRL, val8);
 }
 
+static u8 rtl8xxxu_max_acquired_macid(struct rtl8xxxu_priv *priv)
+{
+	u8 macid;
+
+	macid = find_last_bit(priv->mac_id_map, RTL8XXXU_MAX_MAC_ID_NUM);
+
+	return macid;
+}
+
 static u8 rtl8xxxu_acquire_macid(struct rtl8xxxu_priv *priv)
 {
 	u8 macid;
@@ -7499,6 +7508,7 @@ static int rtl8xxxu_sta_add(struct ieee80211_hw *hw,
 	struct rtl8xxxu_sta_info *sta_info = (struct rtl8xxxu_sta_info *)sta->drv_priv;
 	struct rtl8xxxu_vif *rtlvif = (struct rtl8xxxu_vif *)vif->drv_priv;
 	struct rtl8xxxu_priv *priv = hw->priv;
+	u8 max_mac_id;
 
 	mutex_lock(&priv->sta_mutex);
 	ewma_rssi_init(&sta_info->avg_rssi);
@@ -7510,6 +7520,11 @@ static int rtl8xxxu_sta_add(struct ieee80211_hw *hw,
 			return -ENOSPC;
 		}
 
+		if (priv->rtl_chip == RTL8188E) {
+			max_mac_id = rtl8xxxu_max_acquired_macid(priv);
+			rtl8xxxu_write8(priv, REG_TX_REPORT_CTRL + 1, max_mac_id + 1);
+		}
+
 		rtl8xxxu_refresh_rate_mask(priv, 0, sta, true);
 		priv->fops->report_connect(priv, sta_info->macid, H2C_MACID_ROLE_STA, true);
 	} else {
@@ -7537,8 +7552,13 @@ static int rtl8xxxu_sta_remove(struct ieee80211_hw *hw,
 	struct rtl8xxxu_priv *priv = hw->priv;
 
 	mutex_lock(&priv->sta_mutex);
-	if (vif->type == NL80211_IFTYPE_AP)
+	if (vif->type == NL80211_IFTYPE_AP) {
 		rtl8xxxu_release_macid(priv, sta_info->macid);
+		if (priv->rtl_chip == RTL8188E) {
+			max_mac_id = rtl8xxxu_max_acquired_macid(priv);
+			rtl8xxxu_write8(priv, REG_TX_REPORT_CTRL + 1, max_mac_id + 1);
+		}
+	}
 	mutex_unlock(&priv->sta_mutex);
 
 	return 0;
-- 
2.53.0

Re: [RFC PATCH v2 3/4] wifi: rtl8xxxu: update max report mac id on station add / remove for 8188e chips

[Georg Müller]

Am 13.03.26 um 14:18 schrieb Georg Müller:
> ---
>   drivers/net/wireless/realtek/rtl8xxxu/core.c | 22 +++++++++++++++++++-
>   1 file changed, 21 insertions(+), 1 deletion(-)
> 
> diff --git a/drivers/net/wireless/realtek/rtl8xxxu/core.c b/drivers/net/wireless/realtek/rtl8xxxu/core.c
> index ea4dcca9d22a..6d97bb212f75 100644
> --- a/drivers/net/wireless/realtek/rtl8xxxu/core.c
> +++ b/drivers/net/wireless/realtek/rtl8xxxu/core.c
> @@ -3884,6 +3884,15 @@ void rtl8xxxu_init_burst(struct rtl8xxxu_priv *priv)
>   	rtl8xxxu_write8(priv, REG_RSV_CTRL, val8);
>   }
>   
> +static u8 rtl8xxxu_max_acquired_macid(struct rtl8xxxu_priv *priv)
> +{
> +	u8 macid;
> +
> +	macid = find_last_bit(priv->mac_id_map, RTL8XXXU_MAX_MAC_ID_NUM);
> +
> +	return macid;
> +}
> +
>   static u8 rtl8xxxu_acquire_macid(struct rtl8xxxu_priv *priv)
>   {
>   	u8 macid;
> @@ -7499,6 +7508,7 @@ static int rtl8xxxu_sta_add(struct ieee80211_hw *hw,
>   	struct rtl8xxxu_sta_info *sta_info = (struct rtl8xxxu_sta_info *)sta->drv_priv;
>   	struct rtl8xxxu_vif *rtlvif = (struct rtl8xxxu_vif *)vif->drv_priv;
>   	struct rtl8xxxu_priv *priv = hw->priv;
> +	u8 max_mac_id;
>   
>   	mutex_lock(&priv->sta_mutex);
>   	ewma_rssi_init(&sta_info->avg_rssi);
> @@ -7510,6 +7520,11 @@ static int rtl8xxxu_sta_add(struct ieee80211_hw *hw,
>   			return -ENOSPC;
>   		}
>   
> +		if (priv->rtl_chip == RTL8188E) {
> +			max_mac_id = rtl8xxxu_max_acquired_macid(priv);
> +			rtl8xxxu_write8(priv, REG_TX_REPORT_CTRL + 1, max_mac_id + 1);
> +		}
> +
>   		rtl8xxxu_refresh_rate_mask(priv, 0, sta, true);
>   		priv->fops->report_connect(priv, sta_info->macid, H2C_MACID_ROLE_STA, true);
>   	} else {
> @@ -7537,8 +7552,13 @@ static int rtl8xxxu_sta_remove(struct ieee80211_hw *hw,
>   	struct rtl8xxxu_priv *priv = hw->priv;

sorry: declaration "u8 max_mac_id;" is missing here. This was lost when copying back from my test VM.

>   	mutex_lock(&priv->sta_mutex);
> -	if (vif->type == NL80211_IFTYPE_AP)
> +	if (vif->type == NL80211_IFTYPE_AP) {
>   		rtl8xxxu_release_macid(priv, sta_info->macid);
> +		if (priv->rtl_chip == RTL8188E) {
> +			max_mac_id = rtl8xxxu_max_acquired_macid(priv);
> +			rtl8xxxu_write8(priv, REG_TX_REPORT_CTRL + 1, max_mac_id + 1);
> +		}
> +	}
>   	mutex_unlock(&priv->sta_mutex);
>   
>   	return 0;

[RFC PATCH v2 4/4] wifi: rtl8xxxu: Enable AP mode for RTL8188EU

[Georg Müller]

Allow devices with this driver to be used as a wireless access point.

Signed-off-by: Georg Müller <georgmueller@gmx.net>
---
 drivers/net/wireless/realtek/rtl8xxxu/8188e.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/wireless/realtek/rtl8xxxu/8188e.c b/drivers/net/wireless/realtek/rtl8xxxu/8188e.c
index 607ca62194fc..67fd77944d67 100644
--- a/drivers/net/wireless/realtek/rtl8xxxu/8188e.c
+++ b/drivers/net/wireless/realtek/rtl8xxxu/8188e.c
@@ -1867,6 +1867,8 @@ struct rtl8xxxu_fileops rtl8188eu_fops = {
 	.init_reg_pkt_life_time = 1,
 	.gen2_thermal_meter = 1,
 	.max_sec_cam_num = 32,
+	.supports_ap = 1,
+	.max_macid_num = RTL8188E_MAX_MAC_ID_NUM,
 	.adda_1t_init = 0x0b1b25a0,
 	.adda_1t_path_on = 0x0bdb25a0,
 	/*
-- 
2.53.0

Re: [RFC PATCH v3 0/4] wifi: rtl8xxxu: implement AP mode for 8188EU

[Mehmet Fide]

Hi Georg,

Is there any progress on this series since v3? We are very interested in
seeing AP mode land for the 8188EU and can offer testing and debugging
help.

Our situation: we ship embedded ARM devices (i.MX/Vybrid based) that use
the Edimax EW-7811Un V2 (USB 7392:b811, RTL8188EU) as a WiFi AP dongle
with hostapd. On our older kernel we run the out-of-tree vendor rtl8188eu
driver, where multi-client AP mode works reliably with its per-MACID rate
adaptation. On recent kernels we had to drop this dongle because rtl8xxxu
has no AP support for this chip, so your series is exactly what we are
missing.

What we can offer:
- Testing on the exact hardware (EW-7811Un V2), both single and
  multi-client scenarios, with iOS/Windows/Linux clients.
- A/B comparison against the working vendor driver on the same board
  (register-level or behavioral differences, e.g. beacon/rsvd page setup,
  RA behavior), which may help pinpoint why clients fail to associate in
  your setup.
- Over-the-air sniffer captures and hostapd/driver debug logs from both
  drivers.

If you share your current WIP branch (or v4 draft) and describe how the
connection failure manifests on your side (no auth response? assoc
timeout? works open but fails WPA2?), we can try to reproduce it here and
compare against the vendor driver behavior.

Happy to provide Tested-by tags once it works.

Best regards,
Mehmet Fide
Screening Eagle Technologies

[RFC PATCH v3 0/4] wifi: rtl8xxxu: implement AP mode for 8188EU

[Georg Müller]

This series tries to implement AP mode for Realtek RTL8188EU chips.

This is not final. I still have issues connecting to the AP, searching for some
input on what may be the reason or how to further debug issues.

Patch 1 could be picked independently as it shouldn't change anything for the
non-AP mode.

---
Changes in v3:
- fix compile errors caused by testing on machine with older kernel
Changes in v2:
- add patch to move dynamic_tx_rpt_timing_counter from ra_info to priv
- convert ra_info to a dynamic array
- update max report mac id after station add/remove

---
Georg Müller (4):
  wifi: rtl8xxxu: move dynamic_tx_rpt_timing_counter from ra_info to
    priv
  wifi: rtl8xxxu: handle rate control for 8188e a per mac_id
  wifi: rtl8xxxu: update max report mac id on station add / remove for
    8188e chips
  wifi: rtl8xxxu: Enable AP mode for RTL8188EU

 drivers/net/wireless/realtek/rtl8xxxu/8188e.c | 22 +++++-----
 drivers/net/wireless/realtek/rtl8xxxu/core.c  | 41 ++++++++++++++++---
 .../net/wireless/realtek/rtl8xxxu/rtl8xxxu.h  |  5 ++-
 3 files changed, 50 insertions(+), 18 deletions(-)

-- 
2.53.0

Re: [RFC PATCH v3 0/4] wifi: rtl8xxxu: implement AP mode for 8188EU

[Bitterblue Smith]

On 13/03/2026 15:53, Georg Müller wrote:
> This series tries to implement AP mode for Realtek RTL8188EU chips.
> 
> This is not final. I still have issues connecting to the AP, searching for some
> input on what may be the reason or how to further debug issues.
> 

What are the issues? Were they happening with your original patch
which only added supports_ap and max_macid_num?

Another thing still missing is the macid in the TX descriptor
(rtl8xxxu_fill_txdesc_v3).

> Patch 1 could be picked independently as it shouldn't change anything for the
> non-AP mode.
> 
> ---
> Changes in v3:
> - fix compile errors caused by testing on machine with older kernel
> Changes in v2:
> - add patch to move dynamic_tx_rpt_timing_counter from ra_info to priv
> - convert ra_info to a dynamic array
> - update max report mac id after station add/remove
> 
> ---
> Georg Müller (4):
>   wifi: rtl8xxxu: move dynamic_tx_rpt_timing_counter from ra_info to
>     priv
>   wifi: rtl8xxxu: handle rate control for 8188e a per mac_id
>   wifi: rtl8xxxu: update max report mac id on station add / remove for
>     8188e chips
>   wifi: rtl8xxxu: Enable AP mode for RTL8188EU
> 
>  drivers/net/wireless/realtek/rtl8xxxu/8188e.c | 22 +++++-----
>  drivers/net/wireless/realtek/rtl8xxxu/core.c  | 41 ++++++++++++++++---
>  .../net/wireless/realtek/rtl8xxxu/rtl8xxxu.h  |  5 ++-
>  3 files changed, 50 insertions(+), 18 deletions(-)
> 

Re: [RFC PATCH v3 0/4] wifi: rtl8xxxu: implement AP mode for 8188EU

[Georg Müller]

Just to give a litte update:

Am 14.03.26 um 00:14 schrieb Bitterblue Smith:
> What are the issues? Were they happening with your original patch
> which only added supports_ap and max_macid_num?
> 
> Another thing still missing is the macid in the TX descriptor
> (rtl8xxxu_fill_txdesc_v3).

I added setting the macid in rtl8xxxu_fill_txdesc_v3 and the other comments to the
patches.

There are still some issues:

In a test setup, I connected 5 different devices to a host running with a 8188eu wifi dongle
running in AP mode and a web server running on it.

All were able to fetch a web page served by the host.

Sometimes the connection was a bit stuck, but this recovered after some time.

In the logs of the server with the 8188eu dongle, I sometimes observed the following messages
in dmesg (with debug messages turned on):

   C2H TX report type 2
   rtl8188e_handle_ra_tx_report2: len: 24 items: 3
   rtl8188e_handle_ra_tx_report2: TX report item 0 not valid
   rtl8188e_handle_ra_tx_report2:  valid: 0 retry: 0 0 0 0 0 drop: 0
   rtl8188e_handle_ra_tx_report2:  valid: 0 retry: 0 0 0 0 0 drop: 0
   rtl8188e_handle_ra_tx_report2:  valid: 1 retry: 5 0 0 0 0 drop: 0

another thing which sometimes occurred:

   rtl8xxxu_read8(020a)   = 0x00, len 1   # <- repeated 50-70 times
   rtl8xxxu_send_beacon_frame: Failed to read beacon valid bit


What I observed on one of the clients was DUP ping responses. I will try to debug this with
a wifi capture device.

Best regards,
Georg