[Intel-xe] [PATCH v2] drm/xe: nuke GuC on unload

[Matthew Brost]

On Thu, Aug 24, 2023 at 05:04:45PM +0100, Matthew Auld wrote:
> On PVC unloading followed by reloading the module often results in a
> completely dead machine (seems to be plaguing CI). Resetting the GuC
> like we do at load seems to cure it at least when locally testing this.
> 
> v2:
>   - Move pc_fini into guc_fini. We want to do the GuC reset just after
>     calling pc_fini, otherwise we encounter communication failures. It
>     also seems like a good idea to do the reset before we start releasing
>     the various other GuC resources. In the case of pc_fini there is an
>     explicit stop, but for other stuff like logs, ads, ctb there is not.
> 
> References: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/542
> References: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/597
> Signed-off-by: Matthew Auld <matthew.auld at intel.com>
> Cc: Matthew Brost <matthew.brost at intel.com>

Reviewed-by: Matthew Brost <matthew.brost at intel.com>

> Cc: Rodrigo Vivi <rodrigo.vivi at intel.com>
> ---
>  drivers/gpu/drm/xe/xe_guc.c    | 17 +++++++++++++++++
>  drivers/gpu/drm/xe/xe_guc_pc.c |  8 +-------
>  drivers/gpu/drm/xe/xe_guc_pc.h |  1 +
>  drivers/gpu/drm/xe/xe_uc.c     |  5 +++++
>  drivers/gpu/drm/xe/xe_uc.h     |  1 +
>  5 files changed, 25 insertions(+), 7 deletions(-)
> 
> diff --git a/drivers/gpu/drm/xe/xe_guc.c b/drivers/gpu/drm/xe/xe_guc.c
> index e102637c0695..3cea4323113f 100644
> --- a/drivers/gpu/drm/xe/xe_guc.c
> +++ b/drivers/gpu/drm/xe/xe_guc.c
> @@ -5,6 +5,8 @@
>  
>  #include "xe_guc.h"
>  
> +#include <drm/drm_managed.h>
> +
>  #include "generated/xe_wa_oob.h"
>  #include "regs/xe_gt_regs.h"
>  #include "regs/xe_guc_regs.h"
> @@ -20,6 +22,7 @@
>  #include "xe_guc_submit.h"
>  #include "xe_mmio.h"
>  #include "xe_platform_types.h"
> +#include "xe_uc.h"
>  #include "xe_uc_fw.h"
>  #include "xe_wa.h"
>  #include "xe_wopcm.h"
> @@ -217,6 +220,16 @@ static void guc_write_params(struct xe_guc *guc)
>  		xe_mmio_write32(gt, SOFT_SCRATCH(1 + i), guc->params[i]);
>  }
>  
> +static void guc_fini(struct drm_device *drm, void *arg)
> +{
> +	struct xe_guc *guc = arg;
> +
> +	xe_force_wake_get(gt_to_fw(guc_to_gt(guc)), XE_FORCEWAKE_ALL);
> +	xe_guc_pc_fini(&guc->pc);
> +	xe_uc_fini_hw(&guc_to_gt(guc)->uc);
> +	xe_force_wake_put(gt_to_fw(guc_to_gt(guc)), XE_FORCEWAKE_ALL);
> +}
> +
>  int xe_guc_init(struct xe_guc *guc)
>  {
>  	struct xe_device *xe = guc_to_xe(guc);
> @@ -244,6 +257,10 @@ int xe_guc_init(struct xe_guc *guc)
>  	if (ret)
>  		goto out;
>  
> +	ret = drmm_add_action_or_reset(&gt_to_xe(gt)->drm, guc_fini, guc);
> +	if (ret)
> +		return ret;
> +
>  	guc_init_params(guc);
>  
>  	if (xe_gt_is_media_type(gt))
> diff --git a/drivers/gpu/drm/xe/xe_guc_pc.c b/drivers/gpu/drm/xe/xe_guc_pc.c
> index c03bb58e7049..87de1ce40e07 100644
> --- a/drivers/gpu/drm/xe/xe_guc_pc.c
> +++ b/drivers/gpu/drm/xe/xe_guc_pc.c
> @@ -884,10 +884,8 @@ int xe_guc_pc_stop(struct xe_guc_pc *pc)
>  	return ret;
>  }
>  
> -static void pc_fini(struct drm_device *drm, void *arg)
> +void xe_guc_pc_fini(struct xe_guc_pc *pc)
>  {
> -	struct xe_guc_pc *pc = arg;
> -
>  	XE_WARN_ON(xe_guc_pc_gucrc_disable(pc));
>  	XE_WARN_ON(xe_guc_pc_stop(pc));
>  	sysfs_remove_files(pc_to_gt(pc)->sysfs, pc_attrs);
> @@ -925,9 +923,5 @@ int xe_guc_pc_init(struct xe_guc_pc *pc)
>  	if (err)
>  		return err;
>  
> -	err = drmm_add_action_or_reset(&xe->drm, pc_fini, pc);
> -	if (err)
> -		return err;
> -
>  	return 0;
>  }
> diff --git a/drivers/gpu/drm/xe/xe_guc_pc.h b/drivers/gpu/drm/xe/xe_guc_pc.h
> index 81833a53b3c9..43ea582545b5 100644
> --- a/drivers/gpu/drm/xe/xe_guc_pc.h
> +++ b/drivers/gpu/drm/xe/xe_guc_pc.h
> @@ -9,6 +9,7 @@
>  #include "xe_guc_pc_types.h"
>  
>  int xe_guc_pc_init(struct xe_guc_pc *pc);
> +void xe_guc_pc_fini(struct xe_guc_pc *pc);
>  int xe_guc_pc_start(struct xe_guc_pc *pc);
>  int xe_guc_pc_stop(struct xe_guc_pc *pc);
>  int xe_guc_pc_gucrc_disable(struct xe_guc_pc *pc);
> diff --git a/drivers/gpu/drm/xe/xe_uc.c b/drivers/gpu/drm/xe/xe_uc.c
> index addd6f2681b9..9c8ce504f4da 100644
> --- a/drivers/gpu/drm/xe/xe_uc.c
> +++ b/drivers/gpu/drm/xe/xe_uc.c
> @@ -167,6 +167,11 @@ int xe_uc_init_hw(struct xe_uc *uc)
>  	return 0;
>  }
>  
> +int xe_uc_fini_hw(struct xe_uc *uc)
> +{
> +	return xe_uc_sanitize_reset(uc);
> +}
> +
>  int xe_uc_reset_prepare(struct xe_uc *uc)
>  {
>  	/* GuC submission not enabled, nothing to do */
> diff --git a/drivers/gpu/drm/xe/xe_uc.h b/drivers/gpu/drm/xe/xe_uc.h
> index 42219b361df5..4109ae7028af 100644
> --- a/drivers/gpu/drm/xe/xe_uc.h
> +++ b/drivers/gpu/drm/xe/xe_uc.h
> @@ -12,6 +12,7 @@ int xe_uc_init(struct xe_uc *uc);
>  int xe_uc_init_hwconfig(struct xe_uc *uc);
>  int xe_uc_init_post_hwconfig(struct xe_uc *uc);
>  int xe_uc_init_hw(struct xe_uc *uc);
> +int xe_uc_fini_hw(struct xe_uc *uc);
>  void xe_uc_gucrc_disable(struct xe_uc *uc);
>  int xe_uc_reset_prepare(struct xe_uc *uc);
>  void xe_uc_stop_prepare(struct xe_uc *uc);
> -- 
> 2.41.0
>