On Mon, Sep 23, 2024 at 09:28:23AM +0530, Raag Jadav wrote:
> Introduce device wedged event, which will notify userspace of wedged
> (hanged/unusable) state of the DRM device through a uevent. This is
> useful especially in cases where the device is no longer operating as
> expected and has become unrecoverable from driver context.
>
> Purpose of this implementation is to provide drivers a way to recover
> through userspace intervention. Different drivers may have different
> ideas of a "wedged device" depending on their hardware implementation,
> and hence the vendor agnostic nature of the event. It is up to the drivers
> to decide when they see the need for recovery and how they want to recover
> from the available methods.
>
> Current implementation defines three recovery methods, out of which,
> drivers can choose to support any one or multiple of them. Preferred
> recovery method will be sent in the uevent environment as WEDGED=<method>.
> Userspace consumers (sysadmin) can define udev rules to parse this event
> and take respective action to recover the device.
>
> Method | Consumer expectations
> -----------|-----------------------------------
> rebind | unbind + rebind driver
> bus-reset | unbind + reset bus device + rebind
> reboot | reboot system
>
> v4: s/drm_dev_wedged/drm_dev_wedged_event
> Use drm_info() (Jani)
> Kernel doc adjustment (Aravind)
> v5: Send recovery method with uevent (Lina)
> v6: Access wedge_recovery_opts[] using helper function (Jani)
> Use snprintf() (Jani)
>
> Signed-off-by: Raag Jadav <raag.jadav@xxxxxxxxx>
Finally caught up on mail, so dropping this here again: Please also add a
small section to drm-uapi.rst, pointing at these functions. Just the
kerneldoc for developers is kinda not enough I think.
Also maybe link to an example udev script which handles this would be
neat.
Cheers, Sima
> ---
> drivers/gpu/drm/drm_drv.c | 41 +++++++++++++++++++++++++++++++++++++++
> include/drm/drm_device.h | 24 +++++++++++++++++++++++
> include/drm/drm_drv.h | 18 +++++++++++++++++
> 3 files changed, 83 insertions(+)
>
> diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c
> index ac30b0ec9d93..03a5d9009689 100644
> --- a/drivers/gpu/drm/drm_drv.c
> +++ b/drivers/gpu/drm/drm_drv.c
> @@ -70,6 +70,18 @@ static struct dentry *drm_debugfs_root;
>
> DEFINE_STATIC_SRCU(drm_unplug_srcu);
>
> +/*
> + * Available recovery methods for wedged device. To be sent along with device
> + * wedged uevent.
> + */
> +#define WEDGE_LEN 32 /* Need 16+ */
> +
> +const char *const wedge_recovery_opts[] = {
> + [DRM_WEDGE_RECOVERY_REBIND] = "rebind",
> + [DRM_WEDGE_RECOVERY_BUS_RESET] = "bus-reset",
> + [DRM_WEDGE_RECOVERY_REBOOT] = "reboot",
> +};
> +
> /*
> * DRM Minors
> * A DRM device can provide several char-dev interfaces on the DRM-Major. Each
> @@ -497,6 +509,35 @@ void drm_dev_unplug(struct drm_device *dev)
> }
> EXPORT_SYMBOL(drm_dev_unplug);
>
> +/**
> + * drm_dev_wedged_event - generate a device wedged uevent
> + * @dev: DRM device
> + * @method: method to be used for recovery
> + *
> + * This generates a device wedged uevent for the DRM device specified by @dev.
> + * Recovery @method from wedge_recovery_opts[] (if supprted by the device) is
> + * sent in the uevent environment as WEDGED=<method>, on the basis of which,
> + * userspace may take respective action to recover the device.
> + *
> + * Returns: 0 on success, or negative error code otherwise.
> + */
> +int drm_dev_wedged_event(struct drm_device *dev, enum wedge_recovery_method method)
> +{
> + char event_string[WEDGE_LEN] = {};
> + char *envp[] = { event_string, NULL };
> +
> + if (!test_bit(method, &dev->wedge_recovery)) {
> + drm_err(dev, "device wedged, recovery method not supported\n");
> + return -EOPNOTSUPP;
> + }
> +
> + snprintf(event_string, sizeof(event_string), "WEDGED=%s", recovery_method_name(method));
> +
> + drm_info(dev, "device wedged, generating uevent\n");
> + return kobject_uevent_env(&dev->primary->kdev->kobj, KOBJ_CHANGE, envp);
> +}
> +EXPORT_SYMBOL(drm_dev_wedged_event);
> +
> /*
> * DRM internal mount
> * We want to be able to allocate our own "struct address_space" to control
> diff --git a/include/drm/drm_device.h b/include/drm/drm_device.h
> index c91f87b5242d..f1a71763c22a 100644
> --- a/include/drm/drm_device.h
> +++ b/include/drm/drm_device.h
> @@ -40,6 +40,27 @@ enum switch_power_state {
> DRM_SWITCH_POWER_DYNAMIC_OFF = 3,
> };
>
> +/**
> + * enum wedge_recovery_method - Recovery method for wedged device in order
> + * of severity. To be set as bit fields in drm_device.wedge_recovery variable.
> + * Drivers can choose to support any one or multiple of them depending on their
> + * needs.
> + */
> +
> +enum wedge_recovery_method {
> + /** @DRM_WEDGE_RECOVERY_REBIND: unbind + rebind driver */
> + DRM_WEDGE_RECOVERY_REBIND,
> +
> + /** @DRM_WEDGE_RECOVERY_BUS_RESET: unbind + reset bus device + rebind */
> + DRM_WEDGE_RECOVERY_BUS_RESET,
> +
> + /** @DRM_WEDGE_RECOVERY_REBOOT: reboot system */
> + DRM_WEDGE_RECOVERY_REBOOT,
> +
> + /** @DRM_WEDGE_RECOVERY_MAX: for bounds checking, do not use */
> + DRM_WEDGE_RECOVERY_MAX
> +};
> +
> /**
> * struct drm_device - DRM device structure
> *
> @@ -317,6 +338,9 @@ struct drm_device {
> * Root directory for debugfs files.
> */
> struct dentry *debugfs_root;
> +
> + /** @wedge_recovery: Supported recovery methods for wedged device */
> + unsigned long wedge_recovery;
> };
>
> #endif
> diff --git a/include/drm/drm_drv.h b/include/drm/drm_drv.h
> index 02ea4e3248fd..83d44e153557 100644
> --- a/include/drm/drm_drv.h
> +++ b/include/drm/drm_drv.h
> @@ -45,6 +45,8 @@ struct drm_mode_create_dumb;
> struct drm_printer;
> struct sg_table;
>
> +extern const char *const wedge_recovery_opts[];
> +
> /**
> * enum drm_driver_feature - feature flags
> *
> @@ -461,6 +463,7 @@ void drm_put_dev(struct drm_device *dev);
> bool drm_dev_enter(struct drm_device *dev, int *idx);
> void drm_dev_exit(int idx);
> void drm_dev_unplug(struct drm_device *dev);
> +int drm_dev_wedged_event(struct drm_device *dev, enum wedge_recovery_method method);
>
> /**
> * drm_dev_is_unplugged - is a DRM device unplugged
> @@ -551,4 +554,19 @@ static inline void drm_debugfs_dev_init(struct drm_device *dev, struct dentry *r
> }
> #endif
>
> +static inline bool recovery_method_is_valid(enum wedge_recovery_method method)
> +{
> + if (method >= DRM_WEDGE_RECOVERY_REBIND && method < DRM_WEDGE_RECOVERY_MAX)
> + return true;
> +
> + return false;
> +}
> +
> +static inline const char *recovery_method_name(enum wedge_recovery_method method)
> +{
> + if (recovery_method_is_valid(method))
> + return wedge_recovery_opts[method];
> +
> + return NULL;
> +}
> #endif
> --
> 2.34.1
>
--
Simona Vetter
Software Engineer, Intel Corporation
http://blog.ffwll.ch
