Re: [PATCH v3 08/10] vfio-pci/zdev: Add a device feature for error information

[Farhan Ali <alifm@linux.ibm.com>]

On 9/13/2025 2:04 AM, Alex Williamson wrote:
> On Thu, 11 Sep 2025 11:33:05 -0700
> Farhan Ali <alifm@linux.ibm.com> wrote:
>
>> For zPCI devices, we have platform specific error information. The platform
>> firmware provides this error information to the operating system in an
>> architecture specific mechanism. To enable recovery from userspace for
>> these devices, we want to expose this error information to userspace. Add a
>> new device feature to expose this information.
>>
>> Signed-off-by: Farhan Ali <alifm@linux.ibm.com>
>> ---
>>   drivers/vfio/pci/vfio_pci_core.c |  2 ++
>>   drivers/vfio/pci/vfio_pci_priv.h |  8 ++++++++
>>   drivers/vfio/pci/vfio_pci_zdev.c | 34 ++++++++++++++++++++++++++++++++
>>   include/uapi/linux/vfio.h        | 14 +++++++++++++
>>   4 files changed, 58 insertions(+)
>>
>> diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c
>> index 7dcf5439dedc..378adb3226db 100644
>> --- a/drivers/vfio/pci/vfio_pci_core.c
>> +++ b/drivers/vfio/pci/vfio_pci_core.c
>> @@ -1514,6 +1514,8 @@ int vfio_pci_core_ioctl_feature(struct vfio_device *device, u32 flags,
>>   		return vfio_pci_core_pm_exit(device, flags, arg, argsz);
>>   	case VFIO_DEVICE_FEATURE_PCI_VF_TOKEN:
>>   		return vfio_pci_core_feature_token(device, flags, arg, argsz);
>> +	case VFIO_DEVICE_FEATURE_ZPCI_ERROR:
>> +		return vfio_pci_zdev_feature_err(device, flags, arg, argsz);
>>   	default:
>>   		return -ENOTTY;
>>   	}
>> diff --git a/drivers/vfio/pci/vfio_pci_priv.h b/drivers/vfio/pci/vfio_pci_priv.h
>> index a9972eacb293..a4a7f97fdc2e 100644
>> --- a/drivers/vfio/pci/vfio_pci_priv.h
>> +++ b/drivers/vfio/pci/vfio_pci_priv.h
>> @@ -86,6 +86,8 @@ int vfio_pci_info_zdev_add_caps(struct vfio_pci_core_device *vdev,
>>   				struct vfio_info_cap *caps);
>>   int vfio_pci_zdev_open_device(struct vfio_pci_core_device *vdev);
>>   void vfio_pci_zdev_close_device(struct vfio_pci_core_device *vdev);
>> +int vfio_pci_zdev_feature_err(struct vfio_device *device, u32 flags,
>> +			      void __user *arg, size_t argsz);
>>   #else
>>   static inline int vfio_pci_info_zdev_add_caps(struct vfio_pci_core_device *vdev,
>>   					      struct vfio_info_cap *caps)
>> @@ -100,6 +102,12 @@ static inline int vfio_pci_zdev_open_device(struct vfio_pci_core_device *vdev)
>>   
>>   static inline void vfio_pci_zdev_close_device(struct vfio_pci_core_device *vdev)
>>   {}
>> +
>> +static int vfio_pci_zdev_feature_err(struct vfio_device *device, u32 flags,
>> +				     void __user *arg, size_t argsz);
>> +{
>> +	return -ENODEV;
>> +}
>>   #endif
>>   
>>   static inline bool vfio_pci_is_vga(struct pci_dev *pdev)
>> diff --git a/drivers/vfio/pci/vfio_pci_zdev.c b/drivers/vfio/pci/vfio_pci_zdev.c
>> index 2be37eab9279..261954039aa9 100644
>> --- a/drivers/vfio/pci/vfio_pci_zdev.c
>> +++ b/drivers/vfio/pci/vfio_pci_zdev.c
>> @@ -141,6 +141,40 @@ int vfio_pci_info_zdev_add_caps(struct vfio_pci_core_device *vdev,
>>   	return ret;
>>   }
>>   
>> +int vfio_pci_zdev_feature_err(struct vfio_device *device, u32 flags,
>> +			      void __user *arg, size_t argsz)
>> +{
>> +	struct vfio_device_feature_zpci_err err;
>> +	struct vfio_pci_core_device *vdev =
>> +		container_of(device, struct vfio_pci_core_device, vdev);
>> +	struct zpci_dev *zdev = to_zpci(vdev->pdev);
>> +	int ret;
>> +	int head = 0;
>> +
>> +	if (!zdev)
>> +		return -ENODEV;
>> +
>> +	ret = vfio_check_feature(flags, argsz, VFIO_DEVICE_FEATURE_GET,
>> +				 sizeof(err));
>> +	if (ret != 1)
>> +		return ret;
>> +
>> +	mutex_lock(&zdev->pending_errs_lock);
>> +	if (zdev->pending_errs.count) {
>> +		head = zdev->pending_errs.head % ZPCI_ERR_PENDING_MAX;
>> +		err.pec = zdev->pending_errs.err[head].pec;
>> +		zdev->pending_errs.head++;
>> +		zdev->pending_errs.count--;
>> +		err.pending_errors = zdev->pending_errs.count;
>> +	}
>> +	mutex_unlock(&zdev->pending_errs_lock);
>> +
>> +	if (copy_to_user(arg, &err, sizeof(err)))
>> +		return -EFAULT;
>> +
>> +	return 0;
>> +}
>> +
>>   int vfio_pci_zdev_open_device(struct vfio_pci_core_device *vdev)
>>   {
>>   	struct zpci_dev *zdev = to_zpci(vdev->pdev);
>> diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
>> index 75100bf009ba..a950c341602d 100644
>> --- a/include/uapi/linux/vfio.h
>> +++ b/include/uapi/linux/vfio.h
>> @@ -1478,6 +1478,20 @@ struct vfio_device_feature_bus_master {
>>   };
>>   #define VFIO_DEVICE_FEATURE_BUS_MASTER 10
>>   
>> +/**
>> + * VFIO_DEVICE_FEATURE_ZPCI_ERROR feature provides PCI error information to
>> + * userspace for vfio-pci devices on s390x. On s390x PCI error recovery involves
>> + * platform firmware and notification to operating system is done by
>> + * architecture specific mechanism.  Exposing this information to userspace
>> + * allows userspace to take appropriate actions to handle an error on the
>> + * device.
>> + */
>> +struct vfio_device_feature_zpci_err {
>> +	__u16 pec;
>> +	int pending_errors;
>> +};
> This should have some explicit alignment.  Thanks,
>
> Alex
>
Sure, would something like this be sufficient?

struct vfio_device_feature_zpci_err {
	__u16 pec;
	__u8 pending_errors;
	__u8 __pad;
};

Based on some discussion with Niklas (patch 7) we can reduce the 
pending_errors to u8.

Thanks
Farhan

>
>> +#define VFIO_DEVICE_FEATURE_ZPCI_ERROR 11
>> +
>>   /* -------- API for Type1 VFIO IOMMU -------- */
>>   
>>   /**