Skip to contentSkip to conversation

rtlwifi: 8192de: correct checking of IQK reload

PATCH In review Ping-Ke Shih 2 participants 3 messages May 24, 2022 Realtek wireless driver (rtlwifi family)

lore
Share & tools
lore

Ping-Ke Shih

author maintainer
#0 lore raw

PATCH 1/1 rtlwifi: 8192de: correct checking of IQK reload

This mistake is existing since initial commit, and I recall the vendor driver to find correctness.

Fixes ee3db469dd31 ("wifi: rtlwifi: remove always-true condition pointed out by GCC 12")
Cc Jakub Kicinski <[email protected]>

---
This patch should go through net-next tree, because this one is going to fix "wifi: rtlwifi: remove always-true condition pointed out by GCC 12" that only exits in that tree.

---
 drivers/net/wireless/realtek/rtlwifi/rtl8192de/phy.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)
drivers/net/wireless/realtek/rtlwifi/rtl8192de/phy.c +4 -1
index 15e6a6aded319..f6ff32658863d 100644
@@ -2386,7 +2386,10 @@ void rtl92d_phy_reload_iqk_setting(struct ieee80211_hw *hw, u8 channel)
 			rtl_dbg(rtlpriv, COMP_SCAN, DBG_LOUD,
 				"Just Read IQK Matrix reg for channel:%d....\n",
 				channel);
-			_rtl92d_phy_patha_fill_iqk_matrix(hw, true,
+			if ((rtlphy->iqk_matrix[indexforchannel].
+			     value[0][0] != 0)
+				/*&&(regea4 != 0) */)
+				_rtl92d_phy_patha_fill_iqk_matrix(hw, true,
 					rtlphy->iqk_matrix[
 					indexforchannel].value,	0,
 					(rtlphy->iqk_matrix[
Signature · 1 line
2.25.1
#1 lore raw
Quoted 4 lines · On Tue, 24 May 2022 08:37:50 +0800 Ping-Ke Shih wrote:

This mistake is existing since initial commit, and I recall the vendor driver to find correctness.

Fixes ee3db469dd31 ("wifi: rtlwifi: remove always-true condition pointed out by GCC 12")

Not fair, I did not break this code. My change did not alter the functionality.

Quoted 6 lines
Cc Jakub Kicinski <[email protected]>

---
This patch should go through net-next tree, because this one is going to fix "wifi: rtlwifi: remove always-true condition pointed out by GCC 12" that only exits in that tree.

If you want it to go via net-next you must CC netdev@.

But I don't see any reason to rush it, AFAICS the code was added in 2011 - commit 7274a8c22980 ("rtlwifi: rtl8192de: Merge phy routines") or so. We waited 11 years to notice, we can wait a few weeks for the patch to propagate thru wireless tree.

drivers/net/wireless/realtek/rtlwifi/rtl8192de/phy.c void rtl92d_phy_reload_iqk_setting(struct ieee80211_hw *hw, u8 channel) · line 2391

Quoted 12 lines
drivers/net/wireless/realtek/rtlwifi/rtl8192de/phy.c +3 -1
index 15e6a6aded319..f6ff32658863d 100644
@@ -2386,7 +2386,10 @@ void rtl92d_phy_reload_iqk_setting(struct ieee80211_hw *hw, u8 channel)
 			rtl_dbg(rtlpriv, COMP_SCAN, DBG_LOUD,
 				"Just Read IQK Matrix reg for channel:%d....\n",
 				channel);
-			_rtl92d_phy_patha_fill_iqk_matrix(hw, true,
+			if ((rtlphy->iqk_matrix[indexforchannel].
+			     value[0][0] != 0)
+				/*&&(regea4 != 0) */)

Please don't add the extra brackets around the condition and the commented out code back in.

Quoted 4 lines
drivers/net/wireless/realtek/rtlwifi/rtl8192de/phy.c +1 -0
+				_rtl92d_phy_patha_fill_iqk_matrix(hw, true,
 					rtlphy->iqk_matrix[
 					indexforchannel].value,	0,
 					(rtlphy->iqk_matrix[
author maintainer
#2 lore raw
Quoted 8 lines

-----Original Message-----
From: Jakub Kicinski <[email protected]>
Sent: Tuesday, May 24, 2022 9:41 AM
To: Ping-Ke Shih <[email protected]>
Cc: [email protected]; [email protected]
Subject: Re: [PATCH net-next] rtlwifi: 8192de: correct checking of IQK reload

Quoted 8 lines
Quoted 4 lines · On Tue, 24 May 2022 08:37:50 +0800 Ping-Ke Shih wrote:

This mistake is existing since initial commit, and I recall the vendor driver to find correctness.

Fixes ee3db469dd31 ("wifi: rtlwifi: remove always-true condition pointed out by GCC 12")

Not fair, I did not break this code. My change did not alter the functionality.

Will annotate the commit 11 years ago.

Quoted 17 lines
Quoted 7 lines
Cc Jakub Kicinski <[email protected]>

---
This patch should go through net-next tree, because this one is going to fix "wifi: rtlwifi: remove always-true condition pointed out by GCC 12" that only exits in that tree.

If you want it to go via net-next you must CC netdev@.

But I don't see any reason to rush it, AFAICS the code was added in 2011 - commit 7274a8c22980 ("rtlwifi: rtl8192de: Merge phy routines") or so. We waited 11 years to notice, we can wait a few weeks for the patch to propagate thru wireless tree.

Review

Quoted 1 line
(quoted diff) +0 -0

b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/phy.c

Quoted 14 lines

drivers/net/wireless/realtek/rtlwifi/rtl8192de/phy.c void rtl92d_phy_reload_iqk_setting(struct ieee80211_hw *hw, u8 channel) · line 2391

Quoted 11 lines

index 15e6a6aded319..f6ff32658863d 100644

drivers/net/wireless/realtek/rtlwifi/rtl8192de/phy.c +3 -1
@@ -2386,7 +2386,10 @@ void rtl92d_phy_reload_iqk_setting(struct ieee80211_hw *hw, u8 channel)
 			rtl_dbg(rtlpriv, COMP_SCAN, DBG_LOUD,
 				"Just Read IQK Matrix reg for channel:%d....\n",
 				channel);
-			_rtl92d_phy_patha_fill_iqk_matrix(hw, true,
+			if ((rtlphy->iqk_matrix[indexforchannel].
+			     value[0][0] != 0)
+				/*&&(regea4 != 0) */)

Please don't add the extra brackets around the condition and the commented out code back in.

My patch is to revert your patch and correct single one line. I will correct the strange coding style as well until your patch appears in wireless-next.

Quoted 6 lines

drivers/net/wireless/realtek/rtlwifi/rtl8192de/phy.c void rtl92d_phy_reload_iqk_setting(struct ieee80211_hw *hw, u8 channel) · line 2395

Quoted 5 lines
drivers/net/wireless/realtek/rtlwifi/rtl8192de/phy.c +1 -0
+				_rtl92d_phy_patha_fill_iqk_matrix(hw, true,
 					rtlphy->iqk_matrix[
 					indexforchannel].value,	0,
 					(rtlphy->iqk_matrix[

------Please consider the environment before printing this e-mail.