Skip to contentSkip to conversation

ath: add support for special 0x8000 regulatory domain

PATCH New Luis R. Rodriguez 2 participants 3 messages Jul 16, 2009 – Jul 20, 2009 Atheros ath generic utilities

lore
Share & tools
lore
#0 lore raw

PATCH 1/1 ath: add support for special 0x8000 regulatory domain

Two users of ar9170 devices have now reported their cards have been programmed with a regulatory domain of 0x8000. This is not a valid regulatory domain as such these users were unable to use these devices. Since this doesn't seem to be a device EEPROM corruption we must treat it specially.

We default these devices to the default Atheros 0x64 world regulatory domain.

Reported-by DavidFreeman on #linux-wireless
Cc Christian Lamparter <[email protected]>,
Cc Stephen Chen <[email protected]>
Cc David Quan <[email protected]>
Cc Tony Yang <[email protected]>

---

David, or Joerg, can you please test this patch.

 drivers/net/wireless/ath/regd.c |   17 +++++++++++++++++
 1 files changed, 17 insertions(+), 0 deletions(-)
drivers/net/wireless/ath/regd.c +17 -0
index f37c832..62aa270 100644
@@ -474,6 +474,21 @@ ath_regd_init_wiphy(struct ath_regulatory *reg,
 	return 0;
 }
 
+/*
+ * Some users have reported their EEPROM programmed with
+ * 0x8000 set, this is not a supported regulatory domain
+ * but since we have more than one user with it we need
+ * a solution for them. We default to 0x64, which is the
+ * default Atheros world regulatory domain.
+ */
+static void ath_regd_sanitize(struct ath_regulatory *reg)
+{
+	if (reg->current_rd != CTRY_DEFAULT)
+		return;
+	printk(KERN_DEBUG "ath: EEPROM regdomain sanitized\n");
+	reg->current_rd = 0x64;
+}
+
 int
 ath_regd_init(struct ath_regulatory *reg,
 	      struct wiphy *wiphy,
@@ -486,6 +501,8 @@ ath_regd_init(struct ath_regulatory *reg,
 	if (!reg)
 		return -EINVAL;
 
+	ath_regd_sanitize(reg);
+
 	printk(KERN_DEBUG "ath: EEPROM regdomain: 0x%0x\n", reg->current_rd);
 
 	if (!ath_regd_is_eeprom_valid(reg)) {
Signature · 1 line
1.6.3.3
#1 lore raw

PATCH 1/1 ath: add support for special 0x8000 regulatory domain

Quoted 10 lines · Luis R. Rodriguez

Two users of ar9170 devices have now reported their cards have been programmed with a regulatory domain of 0x8000. This is not a valid regulatory domain as such these users were unable to use these devices. Since this doesn't seem to be a device EEPROM corruption we must treat it specially.

We default these devices to the default Atheros 0x64 world regulatory domain.
...
David, or Joerg, can you please test this patch.

Hi Luis,

this patch doesn't work, I still get:

ath: EEPROM regdomain: 0x8000
ath: EEPROM indicates we should expect a country code
ath: No regulatory domain pair found, cannot continue
ar9170usb: probe of 1-1:1.0 failed with error -22

I guess that's due to reg->current_rd == 0x8000, while CTRY_DEFAULT == 0 in ath_regd_sanitize().

Applying

(quoted diff) +0 -0

b/drivers/net/wireless/ath/regd.c
index 62aa270..eae9a58 100644

drivers/net/wireless/ath/regd.c +1 -1
@@ -483,7 +483,7 @@ ath_regd_init_wiphy(struct ath_regulatory *reg,
   */
  static void ath_regd_sanitize(struct ath_regulatory *reg)
  {
-       if (reg->current_rd != CTRY_DEFAULT)
+       if (reg->current_rd != (CTRY_DEFAULT|COUNTRY_ERD_FLAG))
                 return;
         printk(KERN_DEBUG "ath: EEPROM regdomain sanitized\n");
         reg->current_rd = 0x64;

on top of your patch worked:

ath: EEPROM regdomain sanitized
ath: EEPROM regdomain: 0x64
ath: EEPROM indicates we should expect a direct regpair map
ath: Country alpha2 being used: 00
ath: Regpair used: 0x64

Why do we handle a regdomain of 0x8000 differently from a regdomain of 0?
0x8000 leads to regdomain 0x64 in ath_regd_sanitize() while 0 is mapped into country code CTRY_UNITED_STATES.

With the above patch I don't see channels 12,13,100-140 in "iwlist wlan0 channel", which are allowed in DE, but I guess that's due to using regdomain WOR4_WORLD (0x64).

Do calibration data in the EEPROM really depend on the regdomain, i.e. do manufacturers calibrate only for a subset of channels due to the regdomain the device will be programmed with?

BTW, I bought this device refurbished in an U.K. webshop.

#2 lore raw

PATCH 1/1 ath: add support for special 0x8000 regulatory domain

Quoted 32 lines · Joerg Albert
Quoted 10 lines · Luis R. Rodriguez

Two users of ar9170 devices have now reported their cards have been programmed with a regulatory domain of 0x8000. This is not a valid regulatory domain as such these users were unable to use these devices. Since this doesn't seem to be a device EEPROM corruption we must treat it specially.

We default these devices to the default Atheros 0x64 world regulatory domain.
...
David, or Joerg, can you please test this patch.

Hi Luis,

this patch doesn't work, I still get:

ath: EEPROM regdomain: 0x8000
ath: EEPROM indicates we should expect a country code
ath: No regulatory domain pair found, cannot continue
ar9170usb: probe of 1-1:1.0 failed with error -22

I guess that's due to reg->current_rd == 0x8000, while CTRY_DEFAULT == 0 in ath_regd_sanitize().

Applying

drivers/net/wireless/ath/regd.c +0 -0
index 62aa270..eae9a58 100644

drivers/net/wireless/ath/regd.c ath_regd_init_wiphy(struct ath_regulatory *reg, · line 486

Quoted 5 lines
drivers/net/wireless/ath/regd.c +1 -1
@@ -483,7 +483,7 @@ ath_regd_init_wiphy(struct ath_regulatory *reg,
   */
  static void ath_regd_sanitize(struct ath_regulatory *reg)
  {
-       if (reg->current_rd != CTRY_DEFAULT)
+       if (reg->current_rd != (CTRY_DEFAULT|COUNTRY_ERD_FLAG))

Ah yes, it was the ERD flag.. will send another one.

Quoted 6 lines
drivers/net/wireless/ath/regd.c +0 -0
                 return;
         printk(KERN_DEBUG "ath: EEPROM regdomain sanitized\n");
         reg->current_rd = 0x64;

on top of your patch worked:

Quoted 8 lines

ath: EEPROM regdomain sanitized
ath: EEPROM regdomain: 0x64
ath: EEPROM indicates we should expect a direct regpair map
ath: Country alpha2 being used: 00
ath: Regpair used: 0x64

Why do we handle a regdomain of 0x8000 differently from a regdomain of 0?

IMHO we should just be treating it as 0 as I believe that was the manufacturer's intention but since we cannot get confirmation of that in any way we have no other option but to treat this as one of our world regulatory domain SKUs.

Will include this as part of the commit log.

Quoted 2 lines

0x8000 leads to regdomain 0x64 in ath_regd_sanitize() while 0 is mapped into country code CTRY_UNITED_STATES.

Right.

Quoted 3 lines

With the above patch I don't see channels 12,13,100-140 in "iwlist wlan0 channel", which are allowed in DE, but I guess that's due to using regdomain WOR4_WORLD (0x64).

Yeap.

Quoted 3 lines

Do calibration data in the EEPROM really depend on the regdomain, i.e. do manufacturers calibrate only for a subset of channels due to the regdomain the device will be programmed with?

Yeap, that is the idea.

Quoted 1 line

BTW, I bought this device refurbished in an U.K. webshop.

Good to know thanks, if we ever do get some sort of confirmation from the vendor then this can be re-arranged, until then this is what we will have to use.

Luis