[1/2] driver core: auxiliary bus: show auxiliary device IRQs

Commit Message

Shay Drori May 3, 2024, 4:31 a.m. UTC

PCI subfunctions (SF) are anchored on the auxiliary bus. PCI physical
and virtual functions are anchored on the PCI bus;  the irq information
of each such function is visible to users via sysfs directory "msi_irqs"
containing file for each irq entry. However, for PCI SFs such information
is unavailable. Due to this users have no visibility on IRQs used by the
SFs.
Secondly, an SF is a multi function device supporting rdma, netdevice
and more. Without irq information at the bus level, the user is unable
to view or use the affinity of the SF IRQs.

Hence to match to the equivalent PCI PFs and VFs, add "irqs" directory,
for supporting auxiliary devices, containing file for each irq entry.

Additionally, the PCI SFs sometimes share the IRQs with peer SFs. This
information is also not available to the users. To overcome this
limitation, each irq sysfs entry shows if irq is exclusive or shared.

For example:
$ ls /sys/bus/auxiliary/devices/mlx5_core.sf.1/irqs/
50  51  52  53  54  55  56  57  58
$ cat /sys/bus/auxiliary/devices/mlx5_core.sf.1/irqs/52
exclusive

Reviewed-by: Parav Pandit <[e-mail]>
Signed-off-by: Shay Drory <[e-mail]>
---
 Documentation/ABI/testing/sysfs-bus-auxiliary |  14 ++
 drivers/base/auxiliary.c                      | 170 +++++++++++++++++-
 include/linux/auxiliary_bus.h                 |  15 +-
 3 files changed, 196 insertions(+), 3 deletions(-)
 create mode 100644 Documentation/ABI/testing/sysfs-bus-auxiliary

Comments

Greg KH May 3, 2024, 5:10 a.m. UTC | #1

On Fri, May 03, 2024 at 07:31:03AM +0300, Shay Drory wrote:
> PCI subfunctions (SF) are anchored on the auxiliary bus. PCI physical
> and virtual functions are anchored on the PCI bus;  the irq information
> of each such function is visible to users via sysfs directory "msi_irqs"
> containing file for each irq entry. However, for PCI SFs such information
> is unavailable. Due to this users have no visibility on IRQs used by the
> SFs.
> Secondly, an SF is a multi function device supporting rdma, netdevice
> and more. Without irq information at the bus level, the user is unable
> to view or use the affinity of the SF IRQs.
> 
> Hence to match to the equivalent PCI PFs and VFs, add "irqs" directory,
> for supporting auxiliary devices, containing file for each irq entry.
> 
> Additionally, the PCI SFs sometimes share the IRQs with peer SFs. This
> information is also not available to the users. To overcome this
> limitation, each irq sysfs entry shows if irq is exclusive or shared.
> 
> For example:
> $ ls /sys/bus/auxiliary/devices/mlx5_core.sf.1/irqs/
> 50  51  52  53  54  55  56  57  58
> $ cat /sys/bus/auxiliary/devices/mlx5_core.sf.1/irqs/52
> exclusive

Not all the world (i.e. not all auxbus users) are PCI devices, right?
So what happens for non-PCI devices?

> 
> Reviewed-by: Parav Pandit <[e-mail]>
> Signed-off-by: Shay Drory <[e-mail]>
> ---
>  Documentation/ABI/testing/sysfs-bus-auxiliary |  14 ++
>  drivers/base/auxiliary.c                      | 170 +++++++++++++++++-
>  include/linux/auxiliary_bus.h                 |  15 +-
>  3 files changed, 196 insertions(+), 3 deletions(-)
>  create mode 100644 Documentation/ABI/testing/sysfs-bus-auxiliary
> 
> diff --git a/Documentation/ABI/testing/sysfs-bus-auxiliary b/Documentation/ABI/testing/sysfs-bus-auxiliary
> new file mode 100644
> index 000000000000..3b8299d49d9e
> --- /dev/null
> +++ b/Documentation/ABI/testing/sysfs-bus-auxiliary
> @@ -0,0 +1,14 @@
> +What:		/sys/bus/auxiliary/devices/.../irqs/
> +Date:		April, 2024
> +Contact:	Shay Drory <[e-mail]>
> +Description:
> +		The /sys/devices/.../irqs directory contains a variable set of
> +		files, with each file is named as irq number similar to PCI PF
> +		or VF's irq number located in msi_irqs directory.
> +
> +What:		/sys/bus/auxiliary/devices/.../irqs/<N>
> +Date:		April, 2024
> +Contact:	Shay Drory <[e-mail]>
> +Description:
> +		auxiliary devices can share IRQs. This attribute indicates if
> +		the irq is shared with other SFs or exclusively used by the SF.
> diff --git a/drivers/base/auxiliary.c b/drivers/base/auxiliary.c
> index d3a2c40c2f12..5c0efa2081b8 100644
> --- a/drivers/base/auxiliary.c
> +++ b/drivers/base/auxiliary.c
> @@ -158,6 +158,167 @@
>   *	};
>   */
>  
> +#ifdef CONFIG_SYSFS
> +/* Xarray of irqs to determine if irq is exclusive or shared. */
> +static DEFINE_XARRAY(irqs);
> +/* Protects insertions into the irtqs xarray. */
> +static DEFINE_MUTEX(irqs_lock);
> +
> +struct auxiliary_irq_info {
> +	struct device_attribute sysfs_attr;
> +	int irq;
> +};
> +
> +static struct attribute *auxiliary_irq_attrs[] = {
> +	NULL
> +};
> +
> +static const struct attribute_group auxiliary_irqs_group = {
> +	.name = "irqs",
> +	.attrs = auxiliary_irq_attrs,
> +};
> +
> +/**
> + * Auxiliary devices can share IRQs. Expose to user whether the provided IRQ is
> + * shared or exclusive.
> + */
> +static ssize_t auxiliary_irq_mode_show(struct device *dev,
> +				       struct device_attribute *attr, char *buf)
> +{
> +	struct auxiliary_irq_info *info =
> +		container_of(attr, struct auxiliary_irq_info, sysfs_attr);
> +
> +	if (refcount_read(xa_load(&irqs, info->irq)) > 1)
> +		return sysfs_emit(buf, "%s\n", "shared");
> +	else
> +		return sysfs_emit(buf, "%s\n", "exclusive");
> +}
> +
> +static void auxiliary_irq_destroy(int irq)
> +{
> +	refcount_t *ref;
> +
> +	xa_lock(&irqs);
> +	ref = xa_load(&irqs, irq);
> +	if (refcount_dec_and_test(ref)) {
> +		__xa_erase(&irqs, irq);
> +		kfree(ref);
> +	}
> +	xa_unlock(&irqs);
> +}
> +
> +static int auxiliary_irq_create(int irq)
> +{
> +	refcount_t *ref;
> +	int ret = 0;
> +
> +	mutex_lock(&irqs_lock);
> +	ref = xa_load(&irqs, irq);
> +	if (ref && refcount_inc_not_zero(ref))
> +		goto out;
> +
> +	ref = kzalloc(sizeof(ref), GFP_KERNEL);
> +	if (!ref) {
> +		ret = -ENOMEM;
> +		goto out;
> +	}
> +
> +	refcount_set(ref, 1);
> +	ret = xa_insert(&irqs, irq, ref, GFP_KERNEL);
> +	if (ret)
> +		kfree(ref);
> +
> +out:
> +	mutex_unlock(&irqs_lock);
> +	return ret;
> +}
> +
> +/**
> + * auxiliary_device_sysfs_irq_add - add a sysfs entry for the given IRQ
> + * @auxdev: auxiliary bus device to add the sysfs entry.
> + * @irq: The associated Linux interrupt number.
> + *
> + * This function should be called after auxiliary device have successfully
> + * received the irq.
> + */
> +int auxiliary_device_sysfs_irq_add(struct auxiliary_device *auxdev, int irq)
> +{
> +	struct device *dev = &auxdev->dev;
> +	struct auxiliary_irq_info *info;
> +	int ret;
> +
> +	ret = auxiliary_irq_create(irq);
> +	if (ret)
> +		return ret;
> +
> +	info = kzalloc(sizeof(*info), GFP_KERNEL);
> +	if (!info) {
> +		ret = -ENOMEM;
> +		goto info_err;
> +	}
> +
> +	sysfs_attr_init(&info->sysfs_attr.attr);
> +	info->sysfs_attr.attr.name = kasprintf(GFP_KERNEL, "%d", irq);
> +	if (!info->sysfs_attr.attr.name) {
> +		ret = -ENOMEM;
> +		goto name_err;
> +	}
> +	info->irq = irq;
> +	info->sysfs_attr.attr.mode = 0444;
> +	info->sysfs_attr.show = auxiliary_irq_mode_show;
> +
> +	ret = xa_insert(&auxdev->irqs, irq, info, GFP_KERNEL);
> +	if (ret)
> +		goto auxdev_xa_err;
> +
> +	ret = sysfs_add_file_to_group(&dev->kobj, &info->sysfs_attr.attr,
> +				      auxiliary_irqs_group.name);
> +	if (ret)
> +		goto sysfs_add_err;
> +
> +	return 0;
> +
> +sysfs_add_err:
> +	xa_erase(&auxdev->irqs, irq);
> +auxdev_xa_err:
> +	kfree(info->sysfs_attr.attr.name);
> +name_err:
> +	kfree(info);
> +info_err:
> +	auxiliary_irq_destroy(irq);
> +	return ret;
> +}
> +EXPORT_SYMBOL(auxiliary_device_sysfs_irq_add);
> +
> +/**
> + * auxiliary_device_sysfs_irq_remove - remove a sysfs entry for the given IRQ
> + * @auxdev: auxiliary bus device to add the sysfs entry.
> + * @irq: the IRQ to remove.
> + *
> + * This function should be called to remove an IRQ sysfs entry.
> + */
> +void auxiliary_device_sysfs_irq_remove(struct auxiliary_device *auxdev, int irq)
> +{
> +	struct auxiliary_irq_info *info = xa_load(&auxdev->irqs, irq);
> +	struct device *dev = &auxdev->dev;
> +
> +	if (WARN_ON(!info))
> +		return;
> +
> +	sysfs_remove_file_from_group(&dev->kobj, &info->sysfs_attr.attr,
> +				     auxiliary_irqs_group.name);
> +	xa_erase(&auxdev->irqs, irq);
> +	kfree(info->sysfs_attr.attr.name);
> +	kfree(info);
> +	auxiliary_irq_destroy(irq);
> +}
> +EXPORT_SYMBOL(auxiliary_device_sysfs_irq_remove);

Any reason this isn't EXPORT_SYMBOL_GPL() like the rest of this file?
Same for the other export.

> +#else /* CONFIG_SYSFS */
> +int auxiliary_device_sysfs_irq_add(struct auxiliary_device *auxdev, int irq) {return 0; }
> +void auxiliary_device_sysfs_irq_remove(struct auxiliary_device *auxdev, int irq) {}
> +#endif

Shouldn't the #ifdef stuff be in a .h file?  Why .c?

And again, why do you think that all aux devices have irqs?

thanks,

greg k-h

Shay Drori May 3, 2024, 6:18 a.m. UTC | #2

On 03/05/2024 8:10, Greg KH wrote:
> External email: Use caution opening links or attachments
> 
> 
> On Fri, May 03, 2024 at 07:31:03AM +0300, Shay Drory wrote:
>> PCI subfunctions (SF) are anchored on the auxiliary bus. PCI physical
>> and virtual functions are anchored on the PCI bus;  the irq information
>> of each such function is visible to users via sysfs directory "msi_irqs"
>> containing file for each irq entry. However, for PCI SFs such information
>> is unavailable. Due to this users have no visibility on IRQs used by the
>> SFs.
>> Secondly, an SF is a multi function device supporting rdma, netdevice
>> and more. Without irq information at the bus level, the user is unable
>> to view or use the affinity of the SF IRQs.
>>
>> Hence to match to the equivalent PCI PFs and VFs, add "irqs" directory,
>> for supporting auxiliary devices, containing file for each irq entry.
>>
>> Additionally, the PCI SFs sometimes share the IRQs with peer SFs. This
>> information is also not available to the users. To overcome this
>> limitation, each irq sysfs entry shows if irq is exclusive or shared.
>>
>> For example:
>> $ ls /sys/bus/auxiliary/devices/mlx5_core.sf.1/irqs/
>> 50  51  52  53  54  55  56  57  58
>> $ cat /sys/bus/auxiliary/devices/mlx5_core.sf.1/irqs/52
>> exclusive
> 
> Not all the world (i.e. not all auxbus users) are PCI devices, right?

Right. auxiliary users are PCI sfs and other devices.

> So what happens for non-PCI devices?

The sysfs extension is optional, i.e. only for PCI SFs the sysfs irq 
information is optionally exposed.
Rest of the other users just continue as is without sysfs functionality.


> 
>>
>> Reviewed-by: Parav Pandit <[e-mail]>
>> Signed-off-by: Shay Drory <[e-mail]>
>> ---
>>   Documentation/ABI/testing/sysfs-bus-auxiliary |  14 ++
>>   drivers/base/auxiliary.c                      | 170 +++++++++++++++++-
>>   include/linux/auxiliary_bus.h                 |  15 +-
>>   3 files changed, 196 insertions(+), 3 deletions(-)
>>   create mode 100644 Documentation/ABI/testing/sysfs-bus-auxiliary
>>
>> diff --git a/Documentation/ABI/testing/sysfs-bus-auxiliary b/Documentation/ABI/testing/sysfs-bus-auxiliary
>> new file mode 100644
>> index 000000000000..3b8299d49d9e
>> --- /dev/null
>> +++ b/Documentation/ABI/testing/sysfs-bus-auxiliary
>> @@ -0,0 +1,14 @@
>> +What:                /sys/bus/auxiliary/devices/.../irqs/
>> +Date:                April, 2024
>> +Contact:     Shay Drory <[e-mail]>
>> +Description:
>> +             The /sys/devices/.../irqs directory contains a variable set of
>> +             files, with each file is named as irq number similar to PCI PF
>> +             or VF's irq number located in msi_irqs directory.
>> +
>> +What:                /sys/bus/auxiliary/devices/.../irqs/<N>
>> +Date:                April, 2024
>> +Contact:     Shay Drory <[e-mail]>
>> +Description:
>> +             auxiliary devices can share IRQs. This attribute indicates if
>> +             the irq is shared with other SFs or exclusively used by the SF.
>> diff --git a/drivers/base/auxiliary.c b/drivers/base/auxiliary.c
>> index d3a2c40c2f12..5c0efa2081b8 100644
>> --- a/drivers/base/auxiliary.c
>> +++ b/drivers/base/auxiliary.c
>> @@ -158,6 +158,167 @@
>>    *   };
>>    */
>>
>> +#ifdef CONFIG_SYSFS
>> +/* Xarray of irqs to determine if irq is exclusive or shared. */
>> +static DEFINE_XARRAY(irqs);
>> +/* Protects insertions into the irtqs xarray. */
>> +static DEFINE_MUTEX(irqs_lock);
>> +
>> +struct auxiliary_irq_info {
>> +     struct device_attribute sysfs_attr;
>> +     int irq;
>> +};
>> +
>> +static struct attribute *auxiliary_irq_attrs[] = {
>> +     NULL
>> +};
>> +
>> +static const struct attribute_group auxiliary_irqs_group = {
>> +     .name = "irqs",
>> +     .attrs = auxiliary_irq_attrs,
>> +};
>> +
>> +/**
>> + * Auxiliary devices can share IRQs. Expose to user whether the provided IRQ is
>> + * shared or exclusive.
>> + */
>> +static ssize_t auxiliary_irq_mode_show(struct device *dev,
>> +                                    struct device_attribute *attr, char *buf)
>> +{
>> +     struct auxiliary_irq_info *info =
>> +             container_of(attr, struct auxiliary_irq_info, sysfs_attr);
>> +
>> +     if (refcount_read(xa_load(&irqs, info->irq)) > 1)
>> +             return sysfs_emit(buf, "%s\n", "shared");
>> +     else
>> +             return sysfs_emit(buf, "%s\n", "exclusive");
>> +}
>> +
>> +static void auxiliary_irq_destroy(int irq)
>> +{
>> +     refcount_t *ref;
>> +
>> +     xa_lock(&irqs);
>> +     ref = xa_load(&irqs, irq);
>> +     if (refcount_dec_and_test(ref)) {
>> +             __xa_erase(&irqs, irq);
>> +             kfree(ref);
>> +     }
>> +     xa_unlock(&irqs);
>> +}
>> +
>> +static int auxiliary_irq_create(int irq)
>> +{
>> +     refcount_t *ref;
>> +     int ret = 0;
>> +
>> +     mutex_lock(&irqs_lock);
>> +     ref = xa_load(&irqs, irq);
>> +     if (ref && refcount_inc_not_zero(ref))
>> +             goto out;
>> +
>> +     ref = kzalloc(sizeof(ref), GFP_KERNEL);
>> +     if (!ref) {
>> +             ret = -ENOMEM;
>> +             goto out;
>> +     }
>> +
>> +     refcount_set(ref, 1);
>> +     ret = xa_insert(&irqs, irq, ref, GFP_KERNEL);
>> +     if (ret)
>> +             kfree(ref);
>> +
>> +out:
>> +     mutex_unlock(&irqs_lock);
>> +     return ret;
>> +}
>> +
>> +/**
>> + * auxiliary_device_sysfs_irq_add - add a sysfs entry for the given IRQ
>> + * @auxdev: auxiliary bus device to add the sysfs entry.
>> + * @irq: The associated Linux interrupt number.
>> + *
>> + * This function should be called after auxiliary device have successfully
>> + * received the irq.
>> + */
>> +int auxiliary_device_sysfs_irq_add(struct auxiliary_device *auxdev, int irq)
>> +{
>> +     struct device *dev = &auxdev->dev;
>> +     struct auxiliary_irq_info *info;
>> +     int ret;
>> +
>> +     ret = auxiliary_irq_create(irq);
>> +     if (ret)
>> +             return ret;
>> +
>> +     info = kzalloc(sizeof(*info), GFP_KERNEL);
>> +     if (!info) {
>> +             ret = -ENOMEM;
>> +             goto info_err;
>> +     }
>> +
>> +     sysfs_attr_init(&info->sysfs_attr.attr);
>> +     info->sysfs_attr.attr.name = kasprintf(GFP_KERNEL, "%d", irq);
>> +     if (!info->sysfs_attr.attr.name) {
>> +             ret = -ENOMEM;
>> +             goto name_err;
>> +     }
>> +     info->irq = irq;
>> +     info->sysfs_attr.attr.mode = 0444;
>> +     info->sysfs_attr.show = auxiliary_irq_mode_show;
>> +
>> +     ret = xa_insert(&auxdev->irqs, irq, info, GFP_KERNEL);
>> +     if (ret)
>> +             goto auxdev_xa_err;
>> +
>> +     ret = sysfs_add_file_to_group(&dev->kobj, &info->sysfs_attr.attr,
>> +                                   auxiliary_irqs_group.name);
>> +     if (ret)
>> +             goto sysfs_add_err;
>> +
>> +     return 0;
>> +
>> +sysfs_add_err:
>> +     xa_erase(&auxdev->irqs, irq);
>> +auxdev_xa_err:
>> +     kfree(info->sysfs_attr.attr.name);
>> +name_err:
>> +     kfree(info);
>> +info_err:
>> +     auxiliary_irq_destroy(irq);
>> +     return ret;
>> +}
>> +EXPORT_SYMBOL(auxiliary_device_sysfs_irq_add);
>> +
>> +/**
>> + * auxiliary_device_sysfs_irq_remove - remove a sysfs entry for the given IRQ
>> + * @auxdev: auxiliary bus device to add the sysfs entry.
>> + * @irq: the IRQ to remove.
>> + *
>> + * This function should be called to remove an IRQ sysfs entry.
>> + */
>> +void auxiliary_device_sysfs_irq_remove(struct auxiliary_device *auxdev, int irq)
>> +{
>> +     struct auxiliary_irq_info *info = xa_load(&auxdev->irqs, irq);
>> +     struct device *dev = &auxdev->dev;
>> +
>> +     if (WARN_ON(!info))
>> +             return;
>> +
>> +     sysfs_remove_file_from_group(&dev->kobj, &info->sysfs_attr.attr,
>> +                                  auxiliary_irqs_group.name);
>> +     xa_erase(&auxdev->irqs, irq);
>> +     kfree(info->sysfs_attr.attr.name);
>> +     kfree(info);
>> +     auxiliary_irq_destroy(irq);
>> +}
>> +EXPORT_SYMBOL(auxiliary_device_sysfs_irq_remove);
> 
> Any reason this isn't EXPORT_SYMBOL_GPL() like the rest of this file?
> Same for the other export.

missed that, will fix in v2

> 
>> +#else /* CONFIG_SYSFS */
>> +int auxiliary_device_sysfs_irq_add(struct auxiliary_device *auxdev, int irq) {return 0; }
>> +void auxiliary_device_sysfs_irq_remove(struct auxiliary_device *auxdev, int irq) {}
>> +#endif
> 
> Shouldn't the #ifdef stuff be in a .h file?  Why .c?

missed that, will fix in v2

> 
> And again, why do you think that all aux devices have irqs?

like I mention above, this is optional.
I missed to explain this in the cover letter, I will add it to v2.

> 
> thanks,
> 
> greg k-h

kernel test robot May 3, 2024, 5:14 p.m. UTC | #3

Hi Shay,

kernel test robot noticed the following build warnings:

[auto build test WARNING on driver-core/driver-core-testing]
[also build test WARNING on driver-core/driver-core-next driver-core/driver-core-linus net/main net-next/main linus/master v6.9-rc6 next-20240503]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]

url:    https://github.com/intel-lab-lkp/linux/commits/Shay-Drory/driver-core-auxiliary-bus-show-auxiliary-device-IRQs/20240503-123319
base:   driver-core/driver-core-testing
patch link:    https://lore.kernel.org/r/20240503043104.381938-2-shayd%40nvidia.com
patch subject: [PATCH 1/2] driver core: auxiliary bus: show auxiliary device IRQs
config: s390-randconfig-r081-20240503 (https://download.01.org/0day-ci/archive/20240504/[e-mail]/config)
compiler: s390-linux-gcc (GCC) 13.2.0
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20240504/[e-mail]/reproduce)

If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <[e-mail]>
| Closes: https://lore.kernel.org/oe-kbuild-all/[e-mail]/

All warnings (new ones prefixed by >>):

>> drivers/base/auxiliary.c:182: warning: This comment starts with '/**', but isn't a kernel-doc comment. Refer Documentation/doc-guide/kernel-doc.rst
    * Auxiliary devices can share IRQs. Expose to user whether the provided IRQ is


vim +182 drivers/base/auxiliary.c

   180	
   181	/**
 > 182	 * Auxiliary devices can share IRQs. Expose to user whether the provided IRQ is
   183	 * shared or exclusive.
   184	 */
   185	static ssize_t auxiliary_irq_mode_show(struct device *dev,
   186					       struct device_attribute *attr, char *buf)
   187	{
   188		struct auxiliary_irq_info *info =
   189			container_of(attr, struct auxiliary_irq_info, sysfs_attr);
   190	
   191		if (refcount_read(xa_load(&irqs, info->irq)) > 1)
   192			return sysfs_emit(buf, "%s\n", "shared");
   193		else
   194			return sysfs_emit(buf, "%s\n", "exclusive");
   195	}
   196

Simon Horman May 4, 2024, 5:50 p.m. UTC | #4

On Fri, May 03, 2024 at 07:31:03AM +0300, Shay Drory wrote:
> PCI subfunctions (SF) are anchored on the auxiliary bus. PCI physical
> and virtual functions are anchored on the PCI bus;  the irq information
> of each such function is visible to users via sysfs directory "msi_irqs"
> containing file for each irq entry. However, for PCI SFs such information
> is unavailable. Due to this users have no visibility on IRQs used by the
> SFs.
> Secondly, an SF is a multi function device supporting rdma, netdevice
> and more. Without irq information at the bus level, the user is unable
> to view or use the affinity of the SF IRQs.
> 
> Hence to match to the equivalent PCI PFs and VFs, add "irqs" directory,
> for supporting auxiliary devices, containing file for each irq entry.
> 
> Additionally, the PCI SFs sometimes share the IRQs with peer SFs. This
> information is also not available to the users. To overcome this
> limitation, each irq sysfs entry shows if irq is exclusive or shared.
> 
> For example:
> $ ls /sys/bus/auxiliary/devices/mlx5_core.sf.1/irqs/
> 50  51  52  53  54  55  56  57  58
> $ cat /sys/bus/auxiliary/devices/mlx5_core.sf.1/irqs/52
> exclusive
> 
> Reviewed-by: Parav Pandit <[e-mail]>
> Signed-off-by: Shay Drory <[e-mail]>

...

> diff --git a/drivers/base/auxiliary.c b/drivers/base/auxiliary.c

...

> +static int auxiliary_irq_create(int irq)
> +{
> +	refcount_t *ref;
> +	int ret = 0;
> +
> +	mutex_lock(&irqs_lock);
> +	ref = xa_load(&irqs, irq);
> +	if (ref && refcount_inc_not_zero(ref))
> +		goto out;
> +
> +	ref = kzalloc(sizeof(ref), GFP_KERNEL);

Hi Shay,

Should this be sizeof(*ref) ?

Flagged by Coccinelle.

> +	if (!ref) {
> +		ret = -ENOMEM;
> +		goto out;
> +	}
> +
> +	refcount_set(ref, 1);
> +	ret = xa_insert(&irqs, irq, ref, GFP_KERNEL);
> +	if (ret)
> +		kfree(ref);
> +
> +out:
> +	mutex_unlock(&irqs_lock);
> +	return ret;
> +}
> +
> +/**
> + * auxiliary_device_sysfs_irq_add - add a sysfs entry for the given IRQ
> + * @auxdev: auxiliary bus device to add the sysfs entry.
> + * @irq: The associated Linux interrupt number.
> + *
> + * This function should be called after auxiliary device have successfully
> + * received the irq.

It would be nice to include a Return section to this kernel doc.

Flagged by ./scripts/kernel-doc -none -Wall

> + */
> +int auxiliary_device_sysfs_irq_add(struct auxiliary_device *auxdev, int irq)

...

Shay Drori May 5, 2024, 5:16 a.m. UTC | #5

On 04/05/2024 20:50, Simon Horman wrote:
> External email: Use caution opening links or attachments
> 
> 
> On Fri, May 03, 2024 at 07:31:03AM +0300, Shay Drory wrote:
>> PCI subfunctions (SF) are anchored on the auxiliary bus. PCI physical
>> and virtual functions are anchored on the PCI bus;  the irq information
>> of each such function is visible to users via sysfs directory "msi_irqs"
>> containing file for each irq entry. However, for PCI SFs such information
>> is unavailable. Due to this users have no visibility on IRQs used by the
>> SFs.
>> Secondly, an SF is a multi function device supporting rdma, netdevice
>> and more. Without irq information at the bus level, the user is unable
>> to view or use the affinity of the SF IRQs.
>>
>> Hence to match to the equivalent PCI PFs and VFs, add "irqs" directory,
>> for supporting auxiliary devices, containing file for each irq entry.
>>
>> Additionally, the PCI SFs sometimes share the IRQs with peer SFs. This
>> information is also not available to the users. To overcome this
>> limitation, each irq sysfs entry shows if irq is exclusive or shared.
>>
>> For example:
>> $ ls /sys/bus/auxiliary/devices/mlx5_core.sf.1/irqs/
>> 50  51  52  53  54  55  56  57  58
>> $ cat /sys/bus/auxiliary/devices/mlx5_core.sf.1/irqs/52
>> exclusive
>>
>> Reviewed-by: Parav Pandit <[e-mail]>
>> Signed-off-by: Shay Drory <[e-mail]>
> 
> ...
> 
>> diff --git a/drivers/base/auxiliary.c b/drivers/base/auxiliary.c
> 
> ...
> 
>> +static int auxiliary_irq_create(int irq)
>> +{
>> +     refcount_t *ref;
>> +     int ret = 0;
>> +
>> +     mutex_lock(&irqs_lock);
>> +     ref = xa_load(&irqs, irq);
>> +     if (ref && refcount_inc_not_zero(ref))
>> +             goto out;
>> +
>> +     ref = kzalloc(sizeof(ref), GFP_KERNEL);
> 
> Hi Shay,
> 
> Should this be sizeof(*ref) ?

yes, will fix in v2

> 
> Flagged by Coccinelle.
> 
>> +     if (!ref) {
>> +             ret = -ENOMEM;
>> +             goto out;
>> +     }
>> +
>> +     refcount_set(ref, 1);
>> +     ret = xa_insert(&irqs, irq, ref, GFP_KERNEL);
>> +     if (ret)
>> +             kfree(ref);
>> +
>> +out:
>> +     mutex_unlock(&irqs_lock);
>> +     return ret;
>> +}
>> +
>> +/**
>> + * auxiliary_device_sysfs_irq_add - add a sysfs entry for the given IRQ
>> + * @auxdev: auxiliary bus device to add the sysfs entry.
>> + * @irq: The associated Linux interrupt number.
>> + *
>> + * This function should be called after auxiliary device have successfully
>> + * received the irq.
> 
> It would be nice to include a Return section to this kernel doc.
> 
> Flagged by ./scripts/kernel-doc -none -Wall

will add in v2

> 
>> + */
>> +int auxiliary_device_sysfs_irq_add(struct auxiliary_device *auxdev, int irq)
> 
> ...

Zhu Yanjun May 5, 2024, 8:43 a.m. UTC | #6

在 2024/5/3 19:14, kernel test robot 写道:
> Hi Shay,
> 
> kernel test robot noticed the following build warnings:
> 
> [auto build test WARNING on driver-core/driver-core-testing]
> [also build test WARNING on driver-core/driver-core-next driver-core/driver-core-linus net/main net-next/main linus/master v6.9-rc6 next-20240503]
> [If your patch is applied to the wrong git tree, kindly drop us a note.
> And when submitting patch, we suggest to use '--base' as documented in
> https://git-scm.com/docs/git-format-patch#_base_tree_information]
> 
> url:    https://github.com/intel-lab-lkp/linux/commits/Shay-Drory/driver-core-auxiliary-bus-show-auxiliary-device-IRQs/20240503-123319
> base:   driver-core/driver-core-testing
> patch link:    https://lore.kernel.org/r/20240503043104.381938-2-shayd%40nvidia.com
> patch subject: [PATCH 1/2] driver core: auxiliary bus: show auxiliary device IRQs
> config: s390-randconfig-r081-20240503 (https://download.01.org/0day-ci/archive/20240504/[e-mail]/config)
> compiler: s390-linux-gcc (GCC) 13.2.0
> reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20240504/[e-mail]/reproduce)
> 
> If you fix the issue in a separate patch/commit (i.e. not just a new version of
> the same patch/commit), kindly add following tags
> | Reported-by: kernel test robot <[e-mail]>
> | Closes: https://lore.kernel.org/oe-kbuild-all/[e-mail]/
> 
> All warnings (new ones prefixed by >>):
> 
>>> drivers/base/auxiliary.c:182: warning: This comment starts with '/**', but isn't a kernel-doc comment. Refer Documentation/doc-guide/kernel-doc.rst
>      * Auxiliary devices can share IRQs. Expose to user whether the provided IRQ is
> 
> 
> vim +182 drivers/base/auxiliary.c
> 
>     180	
>     181	/**
 From the above, "/**" should be "/*"?

Zhu Yanjun
>   > 182	 * Auxiliary devices can share IRQs. Expose to user whether the provided IRQ is
>     183	 * shared or exclusive.
>     184	 */
>     185	static ssize_t auxiliary_irq_mode_show(struct device *dev,
>     186					       struct device_attribute *attr, char *buf)
>     187	{
>     188		struct auxiliary_irq_info *info =
>     189			container_of(attr, struct auxiliary_irq_info, sysfs_attr);
>     190	
>     191		if (refcount_read(xa_load(&irqs, info->irq)) > 1)
>     192			return sysfs_emit(buf, "%s\n", "shared");
>     193		else
>     194			return sysfs_emit(buf, "%s\n", "exclusive");
>     195	}
>     196	
>

Patch

diff --git a/Documentation/ABI/testing/sysfs-bus-auxiliary b/Documentation/ABI/testing/sysfs-bus-auxiliary
new file mode 100644
index 000000000000..3b8299d49d9e
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-bus-auxiliary
@@ -0,0 +1,14 @@ 
+What:		/sys/bus/auxiliary/devices/.../irqs/
+Date:		April, 2024
+Contact:	Shay Drory <[e-mail]>
+Description:
+		The /sys/devices/.../irqs directory contains a variable set of
+		files, with each file is named as irq number similar to PCI PF
+		or VF's irq number located in msi_irqs directory.
+
+What:		/sys/bus/auxiliary/devices/.../irqs/<N>
+Date:		April, 2024
+Contact:	Shay Drory <[e-mail]>
+Description:
+		auxiliary devices can share IRQs. This attribute indicates if
+		the irq is shared with other SFs or exclusively used by the SF.
diff --git a/drivers/base/auxiliary.c b/drivers/base/auxiliary.c
index d3a2c40c2f12..5c0efa2081b8 100644
--- a/drivers/base/auxiliary.c
+++ b/drivers/base/auxiliary.c
@@ -158,6 +158,167 @@ 
  *	};
  */
 
+#ifdef CONFIG_SYSFS
+/* Xarray of irqs to determine if irq is exclusive or shared. */
+static DEFINE_XARRAY(irqs);
+/* Protects insertions into the irtqs xarray. */
+static DEFINE_MUTEX(irqs_lock);
+
+struct auxiliary_irq_info {
+	struct device_attribute sysfs_attr;
+	int irq;
+};
+
+static struct attribute *auxiliary_irq_attrs[] = {
+	NULL
+};
+
+static const struct attribute_group auxiliary_irqs_group = {
+	.name = "irqs",
+	.attrs = auxiliary_irq_attrs,
+};
+
+/**
+ * Auxiliary devices can share IRQs. Expose to user whether the provided IRQ is
+ * shared or exclusive.
+ */
+static ssize_t auxiliary_irq_mode_show(struct device *dev,
+				       struct device_attribute *attr, char *buf)
+{
+	struct auxiliary_irq_info *info =
+		container_of(attr, struct auxiliary_irq_info, sysfs_attr);
+
+	if (refcount_read(xa_load(&irqs, info->irq)) > 1)
+		return sysfs_emit(buf, "%s\n", "shared");
+	else
+		return sysfs_emit(buf, "%s\n", "exclusive");
+}
+
+static void auxiliary_irq_destroy(int irq)
+{
+	refcount_t *ref;
+
+	xa_lock(&irqs);
+	ref = xa_load(&irqs, irq);
+	if (refcount_dec_and_test(ref)) {
+		__xa_erase(&irqs, irq);
+		kfree(ref);
+	}
+	xa_unlock(&irqs);
+}
+
+static int auxiliary_irq_create(int irq)
+{
+	refcount_t *ref;
+	int ret = 0;
+
+	mutex_lock(&irqs_lock);
+	ref = xa_load(&irqs, irq);
+	if (ref && refcount_inc_not_zero(ref))
+		goto out;
+
+	ref = kzalloc(sizeof(ref), GFP_KERNEL);
+	if (!ref) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	refcount_set(ref, 1);
+	ret = xa_insert(&irqs, irq, ref, GFP_KERNEL);
+	if (ret)
+		kfree(ref);
+
+out:
+	mutex_unlock(&irqs_lock);
+	return ret;
+}
+
+/**
+ * auxiliary_device_sysfs_irq_add - add a sysfs entry for the given IRQ
+ * @auxdev: auxiliary bus device to add the sysfs entry.
+ * @irq: The associated Linux interrupt number.
+ *
+ * This function should be called after auxiliary device have successfully
+ * received the irq.
+ */
+int auxiliary_device_sysfs_irq_add(struct auxiliary_device *auxdev, int irq)
+{
+	struct device *dev = &auxdev->dev;
+	struct auxiliary_irq_info *info;
+	int ret;
+
+	ret = auxiliary_irq_create(irq);
+	if (ret)
+		return ret;
+
+	info = kzalloc(sizeof(*info), GFP_KERNEL);
+	if (!info) {
+		ret = -ENOMEM;
+		goto info_err;
+	}
+
+	sysfs_attr_init(&info->sysfs_attr.attr);
+	info->sysfs_attr.attr.name = kasprintf(GFP_KERNEL, "%d", irq);
+	if (!info->sysfs_attr.attr.name) {
+		ret = -ENOMEM;
+		goto name_err;
+	}
+	info->irq = irq;
+	info->sysfs_attr.attr.mode = 0444;
+	info->sysfs_attr.show = auxiliary_irq_mode_show;
+
+	ret = xa_insert(&auxdev->irqs, irq, info, GFP_KERNEL);
+	if (ret)
+		goto auxdev_xa_err;
+
+	ret = sysfs_add_file_to_group(&dev->kobj, &info->sysfs_attr.attr,
+				      auxiliary_irqs_group.name);
+	if (ret)
+		goto sysfs_add_err;
+
+	return 0;
+
+sysfs_add_err:
+	xa_erase(&auxdev->irqs, irq);
+auxdev_xa_err:
+	kfree(info->sysfs_attr.attr.name);
+name_err:
+	kfree(info);
+info_err:
+	auxiliary_irq_destroy(irq);
+	return ret;
+}
+EXPORT_SYMBOL(auxiliary_device_sysfs_irq_add);
+
+/**
+ * auxiliary_device_sysfs_irq_remove - remove a sysfs entry for the given IRQ
+ * @auxdev: auxiliary bus device to add the sysfs entry.
+ * @irq: the IRQ to remove.
+ *
+ * This function should be called to remove an IRQ sysfs entry.
+ */
+void auxiliary_device_sysfs_irq_remove(struct auxiliary_device *auxdev, int irq)
+{
+	struct auxiliary_irq_info *info = xa_load(&auxdev->irqs, irq);
+	struct device *dev = &auxdev->dev;
+
+	if (WARN_ON(!info))
+		return;
+
+	sysfs_remove_file_from_group(&dev->kobj, &info->sysfs_attr.attr,
+				     auxiliary_irqs_group.name);
+	xa_erase(&auxdev->irqs, irq);
+	kfree(info->sysfs_attr.attr.name);
+	kfree(info);
+	auxiliary_irq_destroy(irq);
+}
+EXPORT_SYMBOL(auxiliary_device_sysfs_irq_remove);
+
+#else /* CONFIG_SYSFS */
+int auxiliary_device_sysfs_irq_add(struct auxiliary_device *auxdev, int irq) {return 0; }
+void auxiliary_device_sysfs_irq_remove(struct auxiliary_device *auxdev, int irq) {}
+#endif
+
 static const struct auxiliary_device_id *auxiliary_match_id(const struct auxiliary_device_id *id,
 							    const struct auxiliary_device *auxdev)
 {
@@ -295,6 +456,7 @@  EXPORT_SYMBOL_GPL(auxiliary_device_init);
  * __auxiliary_device_add - add an auxiliary bus device
  * @auxdev: auxiliary bus device to add to the bus
  * @modname: name of the parent device's driver module
+ * @irqs_sysfs_enable: whether to enable IRQs sysfs
  *
  * This is the third step in the three-step process to register an
  * auxiliary_device.
@@ -310,7 +472,8 @@  EXPORT_SYMBOL_GPL(auxiliary_device_init);
  * parameter.  Only if a user requires a custom name would this version be
  * called directly.
  */
-int __auxiliary_device_add(struct auxiliary_device *auxdev, const char *modname)
+int __auxiliary_device_add(struct auxiliary_device *auxdev, const char *modname,
+			   bool irqs_sysfs_enable)
 {
 	struct device *dev = &auxdev->dev;
 	int ret;
@@ -325,6 +488,11 @@  int __auxiliary_device_add(struct auxiliary_device *auxdev, const char *modname)
 		dev_err(dev, "auxiliary device dev_set_name failed: %d\n", ret);
 		return ret;
 	}
+	if (irqs_sysfs_enable) {
+		auxdev->groups[0] = &auxiliary_irqs_group;
+		xa_init(&auxdev->irqs);
+		dev->groups = auxdev->groups;
+	}
 
 	ret = device_add(dev);
 	if (ret)
diff --git a/include/linux/auxiliary_bus.h b/include/linux/auxiliary_bus.h
index de21d9d24a95..c95c46bacfc7 100644
--- a/include/linux/auxiliary_bus.h
+++ b/include/linux/auxiliary_bus.h
@@ -58,6 +58,9 @@ 
  *       in
  * @name: Match name found by the auxiliary device driver,
  * @id: unique identitier if multiple devices of the same name are exported,
+ * @irqs: irqs xarray contains irq indices which are used by the device,
+ * @groups: first group is for irqs sysfs directory; it is a NULL terminated
+ *          array,
  *
  * An auxiliary_device represents a part of its parent device's functionality.
  * It is given a name that, combined with the registering drivers
@@ -138,6 +141,8 @@ 
 struct auxiliary_device {
 	struct device dev;
 	const char *name;
+	struct xarray irqs;
+	const struct attribute_group *groups[2];
 	u32 id;
 };
 
@@ -209,8 +214,14 @@  static inline struct auxiliary_driver *to_auxiliary_drv(struct device_driver *dr
 }
 
 int auxiliary_device_init(struct auxiliary_device *auxdev);
-int __auxiliary_device_add(struct auxiliary_device *auxdev, const char *modname);
-#define auxiliary_device_add(auxdev) __auxiliary_device_add(auxdev, KBUILD_MODNAME)
+int __auxiliary_device_add(struct auxiliary_device *auxdev, const char *modname,
+			   bool irqs_sysfs_enable);
+#define auxiliary_device_add(auxdev) __auxiliary_device_add(auxdev, KBUILD_MODNAME, false)
+#define auxiliary_device_add_with_irqs(auxdev) \
+	__auxiliary_device_add(auxdev, KBUILD_MODNAME, true)
+
+int auxiliary_device_sysfs_irq_add(struct auxiliary_device *auxdev, int irq);
+void auxiliary_device_sysfs_irq_remove(struct auxiliary_device *auxdev, int irq);
 
 static inline void auxiliary_device_uninit(struct auxiliary_device *auxdev)
 {