[PATCH v2] x86/therm_throt.c: Fix error handling in thermal_throttle_add_dev

[PATCH v2] x86/therm_throt.c: Fix error handling in thermal_throttle_add_dev

[Fenghua Yu]

From: Fenghua Yu <fenghua.yu@intel.com>

When sysfs_add_file_to_group fails, thermal_throttle_add_dev removes the
created group and returns with the error code and the driver cleans up and
returns with the error code. Thus the driver either installs all devices
successfully or doesn't install any device at all.

Signed-off-by: Fenghua Yu <fenghua.yu@intel.com>
---
 arch/x86/kernel/cpu/mcheck/therm_throt.c |   36 ++++++++++++++++++++++++++---
 1 files changed, 32 insertions(+), 4 deletions(-)

diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
index c2a8b26..5099e90 100644
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
@@ -211,19 +211,33 @@ static __cpuinit int thermal_throttle_add_dev(struct sys_device *sys_dev)
 	if (err)
 		return err;
 
-	if (cpu_has(c, X86_FEATURE_PLN))
+	if (cpu_has(c, X86_FEATURE_PLN)) {
 		err = sysfs_add_file_to_group(&sys_dev->kobj,
 					      &attr_core_power_limit_count.attr,
 					      thermal_attr_group.name);
-	if (cpu_has(c, X86_FEATURE_PTS))
+		if (err)
+			goto error;
+	}
+
+	if (cpu_has(c, X86_FEATURE_PTS)) {
 		err = sysfs_add_file_to_group(&sys_dev->kobj,
 					      &attr_package_throttle_count.attr,
 					      thermal_attr_group.name);
-		if (cpu_has(c, X86_FEATURE_PLN))
+		if (err)
+			goto error;
+
+		if (cpu_has(c, X86_FEATURE_PLN)) {
 			err = sysfs_add_file_to_group(&sys_dev->kobj,
 					&attr_package_power_limit_count.attr,
 					thermal_attr_group.name);
+			if (err)
+				goto error;
+		}
+	}
 
+	return 0;
+error:
+	sysfs_remove_group(&sys_dev->kobj, &thermal_attr_group);
 	return err;
 }
 
@@ -275,6 +289,7 @@ static struct notifier_block thermal_throttle_cpu_notifier __cpuinitdata =
 static __init int thermal_throttle_init_device(void)
 {
 	unsigned int cpu = 0;
+	int i;
 	int err;
 
 	if (!atomic_read(&therm_throt_en))
@@ -288,13 +303,26 @@ static __init int thermal_throttle_init_device(void)
 	/* connect live CPUs to sysfs */
 	for_each_online_cpu(cpu) {
 		err = thermal_throttle_add_dev(get_cpu_sysdev(cpu));
-		WARN_ON(err);
+		if (err)
+			goto error;
 	}
 #ifdef CONFIG_HOTPLUG_CPU
 	mutex_unlock(&therm_cpu_lock);
 #endif
 
 	return 0;
+error:
+	WARN_ON(err);
+
+	/* cleanup. */
+	for (i = 0; i < cpu; i++)
+		thermal_throttle_remove_dev(get_cpu_sysdev(i));
+#ifdef CONFIG_HOTPLUG_CPU
+	mutex_unlock(&therm_cpu_lock);
+#endif
+	unregister_hotcpu_notifier(&thermal_throttle_cpu_notifier);
+
+	return err;
 }
 device_initcall(thermal_throttle_init_device);
 
-- 
1.6.0.3

Re: [PATCH v2] x86/therm_throt.c: Fix error handling in thermal_throttle_add_dev

[Jean Delvare]

On Tue,  7 Sep 2010 17:25:50 -0700, Fenghua Yu wrote:
> From: Fenghua Yu <fenghua.yu@intel.com>
> 
> When sysfs_add_file_to_group fails, thermal_throttle_add_dev removes the
> created group and returns with the error code and the driver cleans up and
> returns with the error code. Thus the driver either installs all devices
> successfully or doesn't install any device at all.

I don't think this makes any sense. While I generally agree with the
idea that a given device (actually, CPU feature) should either be fully
available or not available at all, I don't get the point of preventing
the driver from loading because one device couldn't be initialized for
whatever reason. I don't know of any other driver behaving this way.

What's the rationale? I think Ingo's wording was inaccurate and when he
wrote "we should either initialize a driver fully - or not intialize it
at all" he really meant "device" not "driver. Ingo?

> 
> Signed-off-by: Fenghua Yu <fenghua.yu@intel.com>
> ---
>  arch/x86/kernel/cpu/mcheck/therm_throt.c |   36 ++++++++++++++++++++++++++---
>  1 files changed, 32 insertions(+), 4 deletions(-)
> 
> diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
> index c2a8b26..5099e90 100644
> --- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
> +++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
> @@ -211,19 +211,33 @@ static __cpuinit int thermal_throttle_add_dev(struct sys_device *sys_dev)
>  	if (err)
>  		return err;
>  
> -	if (cpu_has(c, X86_FEATURE_PLN))
> +	if (cpu_has(c, X86_FEATURE_PLN)) {
>  		err = sysfs_add_file_to_group(&sys_dev->kobj,
>  					      &attr_core_power_limit_count.attr,
>  					      thermal_attr_group.name);
> -	if (cpu_has(c, X86_FEATURE_PTS))
> +		if (err)
> +			goto error;
> +	}
> +
> +	if (cpu_has(c, X86_FEATURE_PTS)) {
>  		err = sysfs_add_file_to_group(&sys_dev->kobj,
>  					      &attr_package_throttle_count.attr,
>  					      thermal_attr_group.name);
> -		if (cpu_has(c, X86_FEATURE_PLN))
> +		if (err)
> +			goto error;
> +
> +		if (cpu_has(c, X86_FEATURE_PLN)) {
>  			err = sysfs_add_file_to_group(&sys_dev->kobj,
>  					&attr_package_power_limit_count.attr,
>  					thermal_attr_group.name);
> +			if (err)
> +				goto error;
> +		}
> +	}
>  
> +	return 0;
> +error:
> +	sysfs_remove_group(&sys_dev->kobj, &thermal_attr_group);
>  	return err;
>  }
>  

I'm fine with the above...

> @@ -275,6 +289,7 @@ static struct notifier_block thermal_throttle_cpu_notifier __cpuinitdata =
>  static __init int thermal_throttle_init_device(void)
>  {
>  	unsigned int cpu = 0;
> +	int i;
>  	int err;
>  
>  	if (!atomic_read(&therm_throt_en))
> @@ -288,13 +303,26 @@ static __init int thermal_throttle_init_device(void)
>  	/* connect live CPUs to sysfs */
>  	for_each_online_cpu(cpu) {
>  		err = thermal_throttle_add_dev(get_cpu_sysdev(cpu));
> -		WARN_ON(err);
> +		if (err)
> +			goto error;
>  	}
>  #ifdef CONFIG_HOTPLUG_CPU
>  	mutex_unlock(&therm_cpu_lock);
>  #endif
>  
>  	return 0;
> +error:
> +	WARN_ON(err);
> +
> +	/* cleanup. */
> +	for (i = 0; i < cpu; i++)
> +		thermal_throttle_remove_dev(get_cpu_sysdev(i));
> +#ifdef CONFIG_HOTPLUG_CPU
> +	mutex_unlock(&therm_cpu_lock);
> +#endif
> +	unregister_hotcpu_notifier(&thermal_throttle_cpu_notifier);
> +
> +	return err;
>  }
>  device_initcall(thermal_throttle_init_device);
>  

... but not with this!

-- 
Jean Delvare

Re: [PATCH v2] x86/therm_throt.c: Fix error handling in thermal_throttle_add_dev

[Guenter Roeck]

On Fri, Sep 10, 2010 at 04:19:37AM -0400, Jean Delvare wrote:
> On Tue,  7 Sep 2010 17:25:50 -0700, Fenghua Yu wrote:
> > From: Fenghua Yu <fenghua.yu@intel.com>
> > 
> > When sysfs_add_file_to_group fails, thermal_throttle_add_dev removes the
> > created group and returns with the error code and the driver cleans up and
> > returns with the error code. Thus the driver either installs all devices
> > successfully or doesn't install any device at all.
> 
> I don't think this makes any sense. While I generally agree with the
> idea that a given device (actually, CPU feature) should either be fully
> available or not available at all, I don't get the point of preventing
> the driver from loading because one device couldn't be initialized for
> whatever reason. I don't know of any other driver behaving this way.
> 
> What's the rationale? I think Ingo's wording was inaccurate and when he
> wrote "we should either initialize a driver fully - or not intialize it
> at all" he really meant "device" not "driver. Ingo?
> 

Question is what happens if an error is returned from device initialization.
If it causes the driver not to be loaded, it will have to clean up first.
To avoid that, it would have to drop the error from individual device
initializations, like it did before.

As such, it really comes down to philosophy and personal preference.
Mine would be to return the error and fail driver installation (after all,
something must really be wrong for that to happen), but then philosopy
isn't really my field ... so I'll yield to others.

Guenter

> > 
> > Signed-off-by: Fenghua Yu <fenghua.yu@intel.com>
> > ---
> >  arch/x86/kernel/cpu/mcheck/therm_throt.c |   36 ++++++++++++++++++++++++++---
> >  1 files changed, 32 insertions(+), 4 deletions(-)
> > 
> > diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
> > index c2a8b26..5099e90 100644
> > --- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
> > +++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
> > @@ -211,19 +211,33 @@ static __cpuinit int thermal_throttle_add_dev(struct sys_device *sys_dev)
> >  	if (err)
> >  		return err;
> >  
> > -	if (cpu_has(c, X86_FEATURE_PLN))
> > +	if (cpu_has(c, X86_FEATURE_PLN)) {
> >  		err = sysfs_add_file_to_group(&sys_dev->kobj,
> >  					      &attr_core_power_limit_count.attr,
> >  					      thermal_attr_group.name);
> > -	if (cpu_has(c, X86_FEATURE_PTS))
> > +		if (err)
> > +			goto error;
> > +	}
> > +
> > +	if (cpu_has(c, X86_FEATURE_PTS)) {
> >  		err = sysfs_add_file_to_group(&sys_dev->kobj,
> >  					      &attr_package_throttle_count.attr,
> >  					      thermal_attr_group.name);
> > -		if (cpu_has(c, X86_FEATURE_PLN))
> > +		if (err)
> > +			goto error;
> > +
> > +		if (cpu_has(c, X86_FEATURE_PLN)) {
> >  			err = sysfs_add_file_to_group(&sys_dev->kobj,
> >  					&attr_package_power_limit_count.attr,
> >  					thermal_attr_group.name);
> > +			if (err)
> > +				goto error;
> > +		}
> > +	}
> >  
> > +	return 0;
> > +error:
> > +	sysfs_remove_group(&sys_dev->kobj, &thermal_attr_group);
> >  	return err;
> >  }
> >  
> 
> I'm fine with the above...
> 
> > @@ -275,6 +289,7 @@ static struct notifier_block thermal_throttle_cpu_notifier __cpuinitdata =
> >  static __init int thermal_throttle_init_device(void)
> >  {
> >  	unsigned int cpu = 0;
> > +	int i;
> >  	int err;
> >  
> >  	if (!atomic_read(&therm_throt_en))
> > @@ -288,13 +303,26 @@ static __init int thermal_throttle_init_device(void)
> >  	/* connect live CPUs to sysfs */
> >  	for_each_online_cpu(cpu) {
> >  		err = thermal_throttle_add_dev(get_cpu_sysdev(cpu));
> > -		WARN_ON(err);
> > +		if (err)
> > +			goto error;
> >  	}
> >  #ifdef CONFIG_HOTPLUG_CPU
> >  	mutex_unlock(&therm_cpu_lock);
> >  #endif
> >  
> >  	return 0;
> > +error:
> > +	WARN_ON(err);
> > +
> > +	/* cleanup. */
> > +	for (i = 0; i < cpu; i++)
> > +		thermal_throttle_remove_dev(get_cpu_sysdev(i));
> > +#ifdef CONFIG_HOTPLUG_CPU
> > +	mutex_unlock(&therm_cpu_lock);
> > +#endif
> > +	unregister_hotcpu_notifier(&thermal_throttle_cpu_notifier);
> > +
> > +	return err;
> >  }
> >  device_initcall(thermal_throttle_init_device);
> >  
> 
> ... but not with this!
> 
> -- 
> Jean Delvare

Re: [PATCH v2] x86/therm_throt.c: Fix error handling in thermal_throttle_add_dev

[Jean Delvare]

Hi Guenter,

On Fri, 10 Sep 2010 06:56:57 -0700, Guenter Roeck wrote:
> On Fri, Sep 10, 2010 at 04:19:37AM -0400, Jean Delvare wrote:
> > On Tue,  7 Sep 2010 17:25:50 -0700, Fenghua Yu wrote:
> > > From: Fenghua Yu <fenghua.yu@intel.com>
> > > 
> > > When sysfs_add_file_to_group fails, thermal_throttle_add_dev removes the
> > > created group and returns with the error code and the driver cleans up and
> > > returns with the error code. Thus the driver either installs all devices
> > > successfully or doesn't install any device at all.
> > 
> > I don't think this makes any sense. While I generally agree with the
> > idea that a given device (actually, CPU feature) should either be fully
> > available or not available at all, I don't get the point of preventing
> > the driver from loading because one device couldn't be initialized for
> > whatever reason. I don't know of any other driver behaving this way.
> > 
> > What's the rationale? I think Ingo's wording was inaccurate and when he
> > wrote "we should either initialize a driver fully - or not intialize it
> > at all" he really meant "device" not "driver. Ingo?
> 
> Question is what happens if an error is returned from device initialization.
> If it causes the driver not to be loaded, it will have to clean up first.
> To avoid that, it would have to drop the error from individual device
> initializations, like it did before.
> 
> As such, it really comes down to philosophy and personal preference.
> Mine would be to return the error and fail driver installation (after all,
> something must really be wrong for that to happen), but then philosopy
> isn't really my field ... so I'll yield to others.

I beg to disagree. The Linux 2.6 device driver model focuses on clear
separation between device instantiation and driver initialization. When
you properly stick to the model, both steps are totally separate, and
even happen in different modules, so device instantiation and
initialization can have no effect on the driver, which can even
pre-exist.

The code we have here is different because there's no device instances
being created, and no device driver binding taking place. But following
the spirit of the model, device initialization should still not affect
the success of driver loading.

Note BTW: Fenghua's patch will have to be rebased, as the following fix
went in the way meanwhile:
http://git.kernel.org/?p=linux/kernel/git/torvalds/linux-2.6.git;a=commitdiff;h=51e3c1b558b31b11bf5fc66d3c6f5adacf3573f7

-- 
Jean Delvare

Re: [PATCH v2] x86/therm_throt.c: Fix error handling in thermal_throttle_add_dev

[Jean Delvare]

On Tue,  7 Sep 2010 17:25:50 -0700, Fenghua Yu wrote:
> From: Fenghua Yu <fenghua.yu@intel.com>
> 
> When sysfs_add_file_to_group fails, thermal_throttle_add_dev removes the
> created group and returns with the error code and the driver cleans up and
> returns with the error code. Thus the driver either installs all devices
> successfully or doesn't install any device at all.
> 
> Signed-off-by: Fenghua Yu <fenghua.yu@intel.com>
> ---
>  arch/x86/kernel/cpu/mcheck/therm_throt.c |   36 ++++++++++++++++++++++++++---
>  1 files changed, 32 insertions(+), 4 deletions(-)
> 

Ingo, Fenghua, what happened to this patch? There was so much
discussion about it about the details that in the end nothing was done
and the actual bug in the code (missing curly braces) is still not
fixed while kernel 2.6.36 is about to be released. This is no good.

The original fix for the main bug was sent by Jin Dongming on August
26th, 2010:
http://lkml.org/lkml/2010/8/26/67

If we can't agree on how to handle errors, at least this easy patch (which
fixes the _success_ path) should be applied immediately.

> diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
> index c2a8b26..5099e90 100644
> --- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
> +++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
> @@ -211,19 +211,33 @@ static __cpuinit int thermal_throttle_add_dev(struct sys_device *sys_dev)
>  	if (err)
>  		return err;
>  
> -	if (cpu_has(c, X86_FEATURE_PLN))
> +	if (cpu_has(c, X86_FEATURE_PLN)) {
>  		err = sysfs_add_file_to_group(&sys_dev->kobj,
>  					      &attr_core_power_limit_count.attr,
>  					      thermal_attr_group.name);
> -	if (cpu_has(c, X86_FEATURE_PTS))
> +		if (err)
> +			goto error;
> +	}
> +
> +	if (cpu_has(c, X86_FEATURE_PTS)) {
>  		err = sysfs_add_file_to_group(&sys_dev->kobj,
>  					      &attr_package_throttle_count.attr,
>  					      thermal_attr_group.name);
> -		if (cpu_has(c, X86_FEATURE_PLN))
> +		if (err)
> +			goto error;
> +
> +		if (cpu_has(c, X86_FEATURE_PLN)) {
>  			err = sysfs_add_file_to_group(&sys_dev->kobj,
>  					&attr_package_power_limit_count.attr,
>  					thermal_attr_group.name);
> +			if (err)
> +				goto error;
> +		}
> +	}
>  
> +	return 0;
> +error:
> +	sysfs_remove_group(&sys_dev->kobj, &thermal_attr_group);
>  	return err;
>  }
>  
> @@ -275,6 +289,7 @@ static struct notifier_block thermal_throttle_cpu_notifier __cpuinitdata =
>  static __init int thermal_throttle_init_device(void)
>  {
>  	unsigned int cpu = 0;
> +	int i;
>  	int err;
>  
>  	if (!atomic_read(&therm_throt_en))
> @@ -288,13 +303,26 @@ static __init int thermal_throttle_init_device(void)
>  	/* connect live CPUs to sysfs */
>  	for_each_online_cpu(cpu) {
>  		err = thermal_throttle_add_dev(get_cpu_sysdev(cpu));
> -		WARN_ON(err);
> +		if (err)
> +			goto error;
>  	}
>  #ifdef CONFIG_HOTPLUG_CPU
>  	mutex_unlock(&therm_cpu_lock);
>  #endif
>  
>  	return 0;
> +error:
> +	WARN_ON(err);
> +
> +	/* cleanup. */
> +	for (i = 0; i < cpu; i++)
> +		thermal_throttle_remove_dev(get_cpu_sysdev(i));
> +#ifdef CONFIG_HOTPLUG_CPU
> +	mutex_unlock(&therm_cpu_lock);
> +#endif
> +	unregister_hotcpu_notifier(&thermal_throttle_cpu_notifier);
> +
> +	return err;
>  }
>  device_initcall(thermal_throttle_init_device);
>  


-- 
Jean Delvare

Re: [PATCH v2] x86/therm_throt.c: Fix error handling in thermal_throttle_add_dev

[Ingo Molnar]

* Fenghua Yu <fenghua.yu@intel.com> wrote:

>  #ifdef CONFIG_HOTPLUG_CPU
>  	mutex_unlock(&therm_cpu_lock);
>  #endif

> +#ifdef CONFIG_HOTPLUG_CPU
> +	mutex_unlock(&therm_cpu_lock);
> +#endif

That's all very ugly.

Thanks,

	Ingo