[lm-sensors] [PATCH RFC] hwmon: (coretemp) Improve support for TjMax detection on Atom CPUs

[lm-sensors] [PATCH RFC] hwmon: (coretemp) Improve support for TjMax detection on Atom CPUs

[Guenter Roeck]

Atom CPUs don't have a register to retrieve TjMax. Detection so far is
incomplete. Use the X86 model ID to improve it.

Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
Wonder if we can improve TjMax detection for Atom CPUs with this code.
Anyone with Atom CPUs out there for some testing ?

 drivers/hwmon/coretemp.c |   44 ++++++++++++++++++++++++++++++++------------
 1 files changed, 32 insertions(+), 12 deletions(-)

diff --git a/drivers/hwmon/coretemp.c b/drivers/hwmon/coretemp.c
index b9d5123..9689a0d 100644
--- a/drivers/hwmon/coretemp.c
+++ b/drivers/hwmon/coretemp.c
@@ -191,6 +191,29 @@ static ssize_t show_temp(struct device *dev,
 	return tdata->valid ? sprintf(buf, "%d\n", tdata->temp) : -EAGAIN;
 }
 
+struct tjmax {
+    	char const *id;
+	int tjmax;
+};
+
+static struct tjmax atom_tjmax[] = {
+	{ "CPU D410", 100000 },
+	{ "CPU D425", 100000 },
+	{ "CPU D510", 100000 },
+	{ "CPU D525", 100000 },
+	{ "CPU N450", 100000 },
+	{ "CPU N455", 100000 },
+	{ "CPU N470", 100000 },
+	{ "CPU N475", 100000 },
+	{ "CPU 230", 100000 },
+	{ "CPU 330", 125000 },
+	{ "CPU E620T", 110000 },
+	{ "CPU E640T", 110000 },
+	{ "CPU E660T", 110000 },
+	{ "CPU E680T", 110000 },
+	{ },
+};
+
 static int __cpuinit adjust_tjmax(struct cpuinfo_x86 *c, u32 id,
 				  struct device *dev)
 {
@@ -201,7 +224,6 @@ static int __cpuinit adjust_tjmax(struct cpuinfo_x86 *c, u32 id,
 	int usemsr_ee = 1;
 	int err;
 	u32 eax, edx;
-	struct pci_dev *host_bridge;
 
 	/* Early chips have no MSR for TjMax */
 
@@ -211,18 +233,16 @@ static int __cpuinit adjust_tjmax(struct cpuinfo_x86 *c, u32 id,
 	/* Atom CPUs */
 
 	if (c->x86_model = 0x1c) {
-		usemsr_ee = 0;
+		struct tjmax *tj;
 
-		host_bridge = pci_get_bus_and_slot(0, PCI_DEVFN(0, 0));
-
-		if (host_bridge && host_bridge->vendor = PCI_VENDOR_ID_INTEL
-		    && (host_bridge->device = 0xa000	/* NM10 based nettop */
-		    || host_bridge->device = 0xa010))	/* NM10 based netbook */
-			tjmax = 100000;
-		else
-			tjmax = 90000;
-
-		pci_dev_put(host_bridge);
+		usemsr_ee = 0;
+		tjmax = 90000;
+		for (tj = atom_tjmax; tj->tjmax; tj++) {
+			if (strstr(c->x86_model_id, tj->id)) {
+				tjmax = tj->tjmax;
+				break;
+			}
+		}
 	}
 
 	if (c->x86_model > 0xe && usemsr_ee) {
-- 
1.7.5.4


_______________________________________________
lm-sensors mailing list
lm-sensors@lm-sensors.org
http://lists.lm-sensors.org/mailman/listinfo/lm-sensors

Re: [lm-sensors] [PATCH RFC] hwmon: (coretemp) Improve support for TjMax detection on Atom CPUs

[R, Durgadoss]

Hi Guenter,

> -----Original Message-----
> From: lm-sensors-bounces@lm-sensors.org [mailto:lm-sensors-bounces@lm-
> sensors.org] On Behalf Of Guenter Roeck
> Sent: Monday, June 04, 2012 10:08 PM
> To: lm-sensors
> Cc: Guenter Roeck
> Subject: [lm-sensors] [PATCH RFC] hwmon: (coretemp) Improve support for
> TjMax detection on Atom CPUs
> 
> Atom CPUs don't have a register to retrieve TjMax. Detection so far is
> incomplete. Use the X86 model ID to improve it.
> 

Thanks for the patch...

> Signed-off-by: Guenter Roeck <linux@roeck-us.net>
> ---
> Wonder if we can improve TjMax detection for Atom CPUs with this code.
> Anyone with Atom CPUs out there for some testing ?

I can test it out on the Medfield platform (Atom based).
But its Tjmax is 90 C. I don't see any 90 C values in your array.
is there a reason behind it ?
Or we can add as we find more models ?

Thanks,
Durga

_______________________________________________
lm-sensors mailing list
lm-sensors@lm-sensors.org
http://lists.lm-sensors.org/mailman/listinfo/lm-sensors

Re: [lm-sensors] [PATCH RFC] hwmon: (coretemp) Improve support for TjMax detection on Atom CPUs

[linux]

Quoting "R, Durgadoss" <durgadoss.r@intel.com>:

> Hi Guenter,
>
>> -----Original Message-----
>> From: lm-sensors-bounces@lm-sensors.org [mailto:lm-sensors-bounces@lm-
>> sensors.org] On Behalf Of Guenter Roeck
>> Sent: Monday, June 04, 2012 10:08 PM
>> To: lm-sensors
>> Cc: Guenter Roeck
>> Subject: [lm-sensors] [PATCH RFC] hwmon: (coretemp) Improve support for
>> TjMax detection on Atom CPUs
>>
>> Atom CPUs don't have a register to retrieve TjMax. Detection so far is
>> incomplete. Use the X86 model ID to improve it.
>>
>
> Thanks for the patch...
>
>> Signed-off-by: Guenter Roeck <linux@roeck-us.net>
>> ---
>> Wonder if we can improve TjMax detection for Atom CPUs with this code.
>> Anyone with Atom CPUs out there for some testing ?
>
> I can test it out on the Medfield platform (Atom based).

You will need Jean's pending patch for that, to detect the new Atom CPU model.

> But its Tjmax is 90 C. I don't see any 90 C values in your array.
> is there a reason behind it ?

Hi Durga,

If you look closely at the patch, you will notice that the Atom code  
starts with

     tjmax = 90000;

90 degrees C is thus the default case. The table only includes values  
for CPUs with a different tjmax. That keeps the table a bit smaller.

> Or we can add as we find more models ?
>
Definitely ...

Thanks,
Guenter


_______________________________________________
lm-sensors mailing list
lm-sensors@lm-sensors.org
http://lists.lm-sensors.org/mailman/listinfo/lm-sensors

Re: [lm-sensors] [PATCH RFC] hwmon: (coretemp) Improve support for TjMax detection on Atom CPUs

[R, Durgadoss]

Hi Guenter,

[big cut.]
> 
> If you look closely at the patch, you will notice that the Atom code
> starts with
> 
>      tjmax = 90000;
> 
> 90 degrees C is thus the default case. The table only includes values
> for CPUs with a different tjmax. That keeps the table a bit smaller.
> 

Oh got it...and it makes sense. I will try in a couple of days and reply here.

Thanks,
Durga

_______________________________________________
lm-sensors mailing list
lm-sensors@lm-sensors.org
http://lists.lm-sensors.org/mailman/listinfo/lm-sensors

Re: [lm-sensors] [PATCH RFC] hwmon: (coretemp) Improve support for TjMax detection on Atom CPUs

[Jean Delvare]

Hi Guenter,

On Mon,  4 Jun 2012 09:37:31 -0700, Guenter Roeck wrote:
> Atom CPUs don't have a register to retrieve TjMax. Detection so far is
> incomplete. Use the X86 model ID to improve it.
> 
> Signed-off-by: Guenter Roeck <linux@roeck-us.net>
> ---
> Wonder if we can improve TjMax detection for Atom CPUs with this code.
> Anyone with Atom CPUs out there for some testing ?

Not here, sorry.

>  drivers/hwmon/coretemp.c |   44 ++++++++++++++++++++++++++++++++------------
>  1 files changed, 32 insertions(+), 12 deletions(-)
> 
> diff --git a/drivers/hwmon/coretemp.c b/drivers/hwmon/coretemp.c
> index b9d5123..9689a0d 100644
> --- a/drivers/hwmon/coretemp.c
> +++ b/drivers/hwmon/coretemp.c
> @@ -191,6 +191,29 @@ static ssize_t show_temp(struct device *dev,
>  	return tdata->valid ? sprintf(buf, "%d\n", tdata->temp) : -EAGAIN;
>  }
>  
> +struct tjmax {
> +    	char const *id;
> +	int tjmax;
> +};
> +
> +static struct tjmax atom_tjmax[] = {
> +	{ "CPU D410", 100000 },
> +	{ "CPU D425", 100000 },
> +	{ "CPU D510", 100000 },
> +	{ "CPU D525", 100000 },
> +	{ "CPU N450", 100000 },
> +	{ "CPU N455", 100000 },
> +	{ "CPU N470", 100000 },
> +	{ "CPU N475", 100000 },
> +	{ "CPU 230", 100000 },
> +	{ "CPU 330", 125000 },

I suspect this won't work, there seems to be a double space between
"CPU" and the number. See:
http://lists.lm-sensors.org/pipermail/lm-sensors/2010-May/028544.html
http://lists.lm-sensors.org/pipermail/lm-sensors/2012-June/036236.html

Oh, this is fixed in v2, ignore.

> +	{ "CPU E620T", 110000 },
> +	{ "CPU E640T", 110000 },
> +	{ "CPU E660T", 110000 },
> +	{ "CPU E680T", 110000 },

This probably won't work either, as for an unknown reason Intel did not
encode the model number for at least some of these Atom CPUs:
http://lists.lm-sensors.org/pipermail/lm-sensors/2011-June/033010.html
This is even the reason why we did not use the processor name strings
back then.

> +	{ },
> +};
> +
>  static int __cpuinit adjust_tjmax(struct cpuinfo_x86 *c, u32 id,
>  				  struct device *dev)
>  {
> @@ -201,7 +224,6 @@ static int __cpuinit adjust_tjmax(struct cpuinfo_x86 *c, u32 id,
>  	int usemsr_ee = 1;
>  	int err;
>  	u32 eax, edx;
> -	struct pci_dev *host_bridge;
>  
>  	/* Early chips have no MSR for TjMax */
>  
> @@ -211,18 +233,16 @@ static int __cpuinit adjust_tjmax(struct cpuinfo_x86 *c, u32 id,
>  	/* Atom CPUs */
>  
>  	if (c->x86_model = 0x1c) {
> -		usemsr_ee = 0;
> +		struct tjmax *tj;
>  
> -		host_bridge = pci_get_bus_and_slot(0, PCI_DEVFN(0, 0));
> -
> -		if (host_bridge && host_bridge->vendor = PCI_VENDOR_ID_INTEL
> -		    && (host_bridge->device = 0xa000	/* NM10 based nettop */
> -		    || host_bridge->device = 0xa010))	/* NM10 based netbook */
> -			tjmax = 100000;
> -		else
> -			tjmax = 90000;
> -
> -		pci_dev_put(host_bridge);

You are dropping a known-to-work heuristic for one which hasn't been
tested on these models. Don't get me wrong, I'd be very happy to get
rid of this code, I just don't want us to introduce a regression.

> +		usemsr_ee = 0;
> +		tjmax = 90000;
> +		for (tj = atom_tjmax; tj->tjmax; tj++) {

Any reason for not using a regular array and ARRAY_SIZE?

> +			if (strstr(c->x86_model_id, tj->id)) {
> +				tjmax = tj->tjmax;
> +				break;
> +			}
> +		}
>  	}
>  
>  	if (c->x86_model > 0xe && usemsr_ee) {


-- 
Jean Delvare

_______________________________________________
lm-sensors mailing list
lm-sensors@lm-sensors.org
http://lists.lm-sensors.org/mailman/listinfo/lm-sensors

Re: [lm-sensors] [PATCH RFC] hwmon: (coretemp) Improve support for TjMax detection on Atom CPUs

[Guenter Roeck]

On Tue, 2012-06-05 at 04:02 -0400, Jean Delvare wrote:
> Hi Guenter,
> 
> On Mon,  4 Jun 2012 09:37:31 -0700, Guenter Roeck wrote:
> > Atom CPUs don't have a register to retrieve TjMax. Detection so far is
> > incomplete. Use the X86 model ID to improve it.
> > 
> > Signed-off-by: Guenter Roeck <linux@roeck-us.net>
> > ---
> > Wonder if we can improve TjMax detection for Atom CPUs with this code.
> > Anyone with Atom CPUs out there for some testing ?
> 
> Not here, sorry.
> 
> >  drivers/hwmon/coretemp.c |   44 ++++++++++++++++++++++++++++++++------------
> >  1 files changed, 32 insertions(+), 12 deletions(-)
> > 
> > diff --git a/drivers/hwmon/coretemp.c b/drivers/hwmon/coretemp.c
> > index b9d5123..9689a0d 100644
> > --- a/drivers/hwmon/coretemp.c
> > +++ b/drivers/hwmon/coretemp.c
> > @@ -191,6 +191,29 @@ static ssize_t show_temp(struct device *dev,
> >  	return tdata->valid ? sprintf(buf, "%d\n", tdata->temp) : -EAGAIN;
> >  }
> >  
> > +struct tjmax {
> > +    	char const *id;
> > +	int tjmax;
> > +};
> > +
> > +static struct tjmax atom_tjmax[] = {
> > +	{ "CPU D410", 100000 },
> > +	{ "CPU D425", 100000 },
> > +	{ "CPU D510", 100000 },
> > +	{ "CPU D525", 100000 },
> > +	{ "CPU N450", 100000 },
> > +	{ "CPU N455", 100000 },
> > +	{ "CPU N470", 100000 },
> > +	{ "CPU N475", 100000 },
> > +	{ "CPU 230", 100000 },
> > +	{ "CPU 330", 125000 },
> 
> I suspect this won't work, there seems to be a double space between
> "CPU" and the number. See:
> http://lists.lm-sensors.org/pipermail/lm-sensors/2010-May/028544.html
> http://lists.lm-sensors.org/pipermail/lm-sensors/2012-June/036236.html
> 
> Oh, this is fixed in v2, ignore.
> 
> > +	{ "CPU E620T", 110000 },
> > +	{ "CPU E640T", 110000 },
> > +	{ "CPU E660T", 110000 },
> > +	{ "CPU E680T", 110000 },
> 
> This probably won't work either, as for an unknown reason Intel did not
> encode the model number for at least some of these Atom CPUs:
> http://lists.lm-sensors.org/pipermail/lm-sensors/2011-June/033010.html
> This is even the reason why we did not use the processor name strings
> back then.
> 
Ah, now I remember. That explains why I didn't find any online logs with
those IDs. Would be great to find PCI bridge ID we could use instead ...

> > +	{ },
> > +};
> > +
> >  static int __cpuinit adjust_tjmax(struct cpuinfo_x86 *c, u32 id,
> >  				  struct device *dev)
> >  {
> > @@ -201,7 +224,6 @@ static int __cpuinit adjust_tjmax(struct cpuinfo_x86 *c, u32 id,
> >  	int usemsr_ee = 1;
> >  	int err;
> >  	u32 eax, edx;
> > -	struct pci_dev *host_bridge;
> >  
> >  	/* Early chips have no MSR for TjMax */
> >  
> > @@ -211,18 +233,16 @@ static int __cpuinit adjust_tjmax(struct cpuinfo_x86 *c, u32 id,
> >  	/* Atom CPUs */
> >  
> >  	if (c->x86_model = 0x1c) {
> > -		usemsr_ee = 0;
> > +		struct tjmax *tj;
> >  
> > -		host_bridge = pci_get_bus_and_slot(0, PCI_DEVFN(0, 0));
> > -
> > -		if (host_bridge && host_bridge->vendor = PCI_VENDOR_ID_INTEL
> > -		    && (host_bridge->device = 0xa000	/* NM10 based nettop */
> > -		    || host_bridge->device = 0xa010))	/* NM10 based netbook */
> > -			tjmax = 100000;
> > -		else
> > -			tjmax = 90000;
> > -
> > -		pci_dev_put(host_bridge);
> 
> You are dropping a known-to-work heuristic for one which hasn't been
> tested on these models. Don't get me wrong, I'd be very happy to get
> rid of this code, I just don't want us to introduce a regression.
> 
Good point. I'll keep it.

> > +		usemsr_ee = 0;
> > +		tjmax = 90000;
> > +		for (tj = atom_tjmax; tj->tjmax; tj++) {
> 
> Any reason for not using a regular array and ARRAY_SIZE?
> 
No.

Guenter



_______________________________________________
lm-sensors mailing list
lm-sensors@lm-sensors.org
http://lists.lm-sensors.org/mailman/listinfo/lm-sensors

Re: [lm-sensors] [PATCH RFC] hwmon: (coretemp) Improve support for TjMax detection on Atom CPUs

[Jean Delvare]

On Tue, 5 Jun 2012 09:29:22 -0700, Guenter Roeck wrote:
> On Tue, 2012-06-05 at 04:02 -0400, Jean Delvare wrote:
> > On Mon,  4 Jun 2012 09:37:31 -0700, Guenter Roeck wrote:
> > > +	{ "CPU E620T", 110000 },
> > > +	{ "CPU E640T", 110000 },
> > > +	{ "CPU E660T", 110000 },
> > > +	{ "CPU E680T", 110000 },
> > 
> > This probably won't work either, as for an unknown reason Intel did not
> > encode the model number for at least some of these Atom CPUs:
> > http://lists.lm-sensors.org/pipermail/lm-sensors/2011-June/033010.html
> > This is even the reason why we did not use the processor name strings
> > back then.
> > 
> Ah, now I remember. That explains why I didn't find any online logs with
> those IDs. Would be great to find PCI bridge ID we could use instead ...

You can read the whole thread, to see if this was already discussed. I
seem to recall we did and concluded it wasn't an option, but I could
remember wrongly.

-- 
Jean Delvare

_______________________________________________
lm-sensors mailing list
lm-sensors@lm-sensors.org
http://lists.lm-sensors.org/mailman/listinfo/lm-sensors

Re: [lm-sensors] [PATCH RFC] hwmon: (coretemp) Improve support for TjMax detection on Atom CPUs

[Guenter Roeck]

On Tue, 2012-06-05 at 14:04 -0400, Jean Delvare wrote:
> On Tue, 5 Jun 2012 09:29:22 -0700, Guenter Roeck wrote:
> > On Tue, 2012-06-05 at 04:02 -0400, Jean Delvare wrote:
> > > On Mon,  4 Jun 2012 09:37:31 -0700, Guenter Roeck wrote:
> > > > +	{ "CPU E620T", 110000 },
> > > > +	{ "CPU E640T", 110000 },
> > > > +	{ "CPU E660T", 110000 },
> > > > +	{ "CPU E680T", 110000 },
> > > 
> > > This probably won't work either, as for an unknown reason Intel did not
> > > encode the model number for at least some of these Atom CPUs:
> > > http://lists.lm-sensors.org/pipermail/lm-sensors/2011-June/033010.html
> > > This is even the reason why we did not use the processor name strings
> > > back then.
> > > 
> > Ah, now I remember. That explains why I didn't find any online logs with
> > those IDs. Would be great to find PCI bridge ID we could use instead ...
> 
> You can read the whole thread, to see if this was already discussed. I
> seem to recall we did and concluded it wasn't an option, but I could
> remember wrongly.
> 
It doesn't cover all CPUs, but it should cover all Atoms except for the
E6xx series. I did find model name info for all other Atom CPUs on the
web - this is how I noticed the N2000 and D2000 series. The N2000 and
D2000 series all have a TjMax of 100 degrees C, so we don't need a table
for those. I changed the code to handle model ID 0x36 separately and set
TjMax for those directly to 100 degrees C.

Do you have access to the Medfield Atom (Z2640) specification ? I did
not find anything on the Intel web site. It would be interesting to know
its TjMax. Same for the CE4100 - Intel seems to closely guard those
specifications.

Thanks,
Guenter



_______________________________________________
lm-sensors mailing list
lm-sensors@lm-sensors.org
http://lists.lm-sensors.org/mailman/listinfo/lm-sensors

Re: [lm-sensors] [PATCH RFC] hwmon: (coretemp) Improve support for TjMax detection on Atom CPUs

[Jean Delvare]

On Tue, 5 Jun 2012 11:19:15 -0700, Guenter Roeck wrote:
> Do you have access to the Medfield Atom (Z2640) specification ? I did
> not find anything on the Intel web site. It would be interesting to know
> its TjMax. Same for the CE4100 - Intel seems to closely guard those
> specifications.

I don't. Durga or Fenghua maybe?

-- 
Jean Delvare

_______________________________________________
lm-sensors mailing list
lm-sensors@lm-sensors.org
http://lists.lm-sensors.org/mailman/listinfo/lm-sensors

Re: [lm-sensors] [PATCH RFC] hwmon: (coretemp) Improve support for TjMax detection on Atom CPUs

[R, Durgadoss]

Hi Guenter/Jean,

> 
> On Tue, 5 Jun 2012 11:19:15 -0700, Guenter Roeck wrote:
> > Do you have access to the Medfield Atom (Z2640) specification ? I did
> > not find anything on the Intel web site. It would be interesting to know
> > its TjMax. Same for the CE4100 - Intel seems to closely guard those
> > specifications.
> 
> I don't. Durga or Fenghua maybe?

I don't have any public specification as such. I use the same platform for testing.
There it says TjMax is 90 (which corresponds to cpu model 0x27).
This is the patch that Jean has submitted a couple of days ago.

Guenter, Could you please give me website link where you are getting details on
TjMax for other platforms ? I will try and see if I can make people add the
'Atom platform' details also there.

BTW, my Medfield platform's /proc/cpuinfo says model as Z2460 whereas you
are saying Z2640. Is it a typo or actually reported as Z2640 somewhere ?

Thanks,
Durga

_______________________________________________
lm-sensors mailing list
lm-sensors@lm-sensors.org
http://lists.lm-sensors.org/mailman/listinfo/lm-sensors

Re: [lm-sensors] [PATCH RFC] hwmon: (coretemp) Improve support for TjMax detection on Atom CPUs

[Guenter Roeck]

On Tue, Jun 05, 2012 at 11:20:05PM -0400, R, Durgadoss wrote:
> Hi Guenter/Jean,
> 
> > 
> > On Tue, 5 Jun 2012 11:19:15 -0700, Guenter Roeck wrote:
> > > Do you have access to the Medfield Atom (Z2640) specification ? I did
> > > not find anything on the Intel web site. It would be interesting to know
> > > its TjMax. Same for the CE4100 - Intel seems to closely guard those
> > > specifications.
> > 
> > I don't. Durga or Fenghua maybe?
> 
> I don't have any public specification as such. I use the same platform for testing.
> There it says TjMax is 90 (which corresponds to cpu model 0x27).
> This is the patch that Jean has submitted a couple of days ago.
> 
Hi Durga,

sorry, you lost me. What do you mean with "there" ? If it is what coretemp reports,
it is just a wild guess, unless you or Jean know better from some document.

> Guenter, Could you please give me website link where you are getting details on
> TjMax for other platforms ? I will try and see if I can make people add the
> 'Atom platform' details also there.
> 

Usually it is in the device datasheet / specification or the device thermal guide
if it exists. I don't think there is a single web site with all the information,
or at least I don't know one. Problem is that no such documentation seems to exist,
at least not in public, for the Z2460 (or CE4100, for that matter). Only reason
for mentioning CE4100 is that someone suggested a patch for it a couple of years ago,
but it went nowhere, presumably since tjmax (supposedly 110 C) was never confirmed,
nor are there well defined means to detect it.

> BTW, my Medfield platform's /proc/cpuinfo says model as Z2460 whereas you
> are saying Z2640. Is it a typo or actually reported as Z2640 somewhere ?
> 
Typo, sorry.

Guenter

_______________________________________________
lm-sensors mailing list
lm-sensors@lm-sensors.org
http://lists.lm-sensors.org/mailman/listinfo/lm-sensors

Re: [lm-sensors] [PATCH RFC] hwmon: (coretemp) Improve support for TjMax detection on Atom CPUs

[R, Durgadoss]

Hi Guenter,

[snip.]
> > I don't have any public specification as such. I use the same platform for testing.
> > There it says TjMax is 90 (which corresponds to cpu model 0x27).
> > This is the patch that Jean has submitted a couple of days ago.
> >
> Hi Durga,
> 
> sorry, you lost me. What do you mean with "there" ? If it is what coretemp
> reports,
> it is just a wild guess, unless you or Jean know better from some document.

It is what coretemp reports.
I know it is 90C, from an internal document, though :-(
That's why was asking is there a place where I can ask folks to update.

> 
> > Guenter, Could you please give me website link where you are getting details
> on
> > TjMax for other platforms ? I will try and see if I can make people add the
> > 'Atom platform' details also there.
> >
> 
> Usually it is in the device datasheet / specification or the device thermal guide
> if it exists. I don't think there is a single web site with all the information,
> or at least I don't know one. Problem is that no such documentation seems to
> exist,
> at least not in public, for the Z2460 (or CE4100, for that matter). Only reason
> for mentioning CE4100 is that someone suggested a patch for it a couple of years
> ago,
> but it went nowhere, presumably since tjmax (supposedly 110 C) was never
> confirmed,
> nor are there well defined means to detect it.
> 

I will see if I can talk to people to see what can be done better here.
I will try & try & try.. :-)

Thanks,
Durga

_______________________________________________
lm-sensors mailing list
lm-sensors@lm-sensors.org
http://lists.lm-sensors.org/mailman/listinfo/lm-sensors

Re: [lm-sensors] [PATCH RFC] hwmon: (coretemp) Improve support for TjMax detection on Atom CPUs

[Guenter Roeck]

On Wed, Jun 06, 2012 at 12:15:52AM -0400, R, Durgadoss wrote:
> Hi Guenter,
> 
> [snip.]
> > > I don't have any public specification as such. I use the same platform for testing.
> > > There it says TjMax is 90 (which corresponds to cpu model 0x27).
> > > This is the patch that Jean has submitted a couple of days ago.
> > >
> > Hi Durga,
> > 
> > sorry, you lost me. What do you mean with "there" ? If it is what coretemp
> > reports,
> > it is just a wild guess, unless you or Jean know better from some document.
> 
> It is what coretemp reports.
> I know it is 90C, from an internal document, though :-(
> That's why was asking is there a place where I can ask folks to update.
> 
That is easy - we can add it to Documentation/hwmon/coretemp. I'll do that with my
series of patches.

> > 
> > > Guenter, Could you please give me website link where you are getting details
> > on
> > > TjMax for other platforms ? I will try and see if I can make people add the
> > > 'Atom platform' details also there.
> > >
> > 
> > Usually it is in the device datasheet / specification or the device thermal guide
> > if it exists. I don't think there is a single web site with all the information,
> > or at least I don't know one. Problem is that no such documentation seems to
> > exist,
> > at least not in public, for the Z2460 (or CE4100, for that matter). Only reason
> > for mentioning CE4100 is that someone suggested a patch for it a couple of years
> > ago,
> > but it went nowhere, presumably since tjmax (supposedly 110 C) was never
> > confirmed,
> > nor are there well defined means to detect it.
> > 
> 
> I will see if I can talk to people to see what can be done better here.
> I will try & try & try.. :-)
> 
Thanks!

Guenter

_______________________________________________
lm-sensors mailing list
lm-sensors@lm-sensors.org
http://lists.lm-sensors.org/mailman/listinfo/lm-sensors