[PATCH 3/4] drm/xe: Force wedged state and block GT reset upon any GPU hang

[Rodrigo Vivi]

On Wed, Apr 24, 2024 at 08:50:45AM +0530, Ghimiray, Himal Prasad wrote:
>                                                                                 
>    Hi Rodrigo,                                                                  
>                                                                                 
>    The debugfs entry introduced in [PATCH 4/4] of the series offers the same    
>    functionality as the modparams provided. Do you perceive any additional      
>    value in using this modparam?                                                
>                                                                                 
>    The behavior of loading the module without using modparams and setting       
>    debugfs mode to 2 before executing the workload is identical to loading      
>    the driver module with the modparam xe_modparam.wedged_mode = 2.             

yes, they are.
But there are situations where the hang could be happening at boot time.
That's what the modparam is for. SV teams wouldn't have a way to debug
the hangs on boot. But in general the debugfs is enough for most of the
cases and better because it is per device and not for all devices driven
by the module.

>                                                                                 
>    BR                                                                           
>                                                                                 
>    Himal                                                                        
>                                                                                 
>     struct init_funcs {                                                         
>            int (*init)(void);                                                   
>            void (*exit)(void);                                                  
>    diff --git a/drivers/gpu/drm/xe/xe_module.h b/drivers/gpu/drm/xe/xe_module.h 
>    index b369984f08ec..61a0d28a28c8 100644                                      
>    --- a/drivers/gpu/drm/xe/xe_module.h                                         
>    +++ b/drivers/gpu/drm/xe/xe_module.h                                         
>    @@ -21,6 +21,7 @@ struct xe_modparam {                                       
>     #ifdef CONFIG_PCI_IOV                                                       
>            unsigned int max_vfs;                                                
>     #endif                                                                      
>    +       int wedged_mode;                                                     
>     };                                                                          
>                                                                                 
>     extern struct xe_modparam xe_modparam;                                      
> 
> References
> 
>    Visible links
>    1. mailto:matthew.brost at intel.com
>    2. mailto:dhirschfeld at habana.ai
>    3. mailto:lucas.demarchi at intel.com
>    4. mailto:alan.previn.teres.alexis at intel.com
>    5. mailto:himanshu.somaiya at intel.com
>    6. mailto:lucas.demarchi at intel.com
>    7. mailto:rodrigo.vivi at intel.com
>    8. https://gitlab.freedesktop.org/drm/xe/kernel/issues/new\n
>    9. https://gitlab.freedesktop.org/drm/xe/kernel/issues/new\n