Re: [PATCH v3 2/2] drm/etnaviv: Add GPU reset counters

[Lucas Stach]

Am Freitag, dem 10.07.2026 um 14:03 +0200 schrieb Christian Gmeiner:
> From: Christian Gmeiner <cgmeiner@xxxxxxxxxx>
> 
> The OpenGL and Vulkan robustness extensions let an application detect a
> GPU reset and check if its own context caused it, so the application can
> drop the broken context and build a new one. The kernel knows both
> facts, but etnaviv has no way to report them to userspace.
> 
> Add two counters and a RESET_QUERY ioctl that returns both in one call:
> a per-GPU counter that counts every reset of that GPU, and a per-context
> counter that only counts the resets this context was guilty of.
> Userspace compares the counters with saved values: if the context
> counter moved the context was guilty, if only the GPU counter moved the
> context was an innocent victim.
> 
> The GPU counter is per GPU core and not per device, so a hang on one
> pipe does not look like an innocent reset to contexts that only use
> another pipe.
> 
> The timeout handler updates both counters and the ioctl reads both
> under the GPU lock. Without the lock the query could run between the
> two updates, see only the GPU counter move and report an innocent
> reset to the guilty context.
> 
> Bump the driver minor version so userspace can detect the feature.
> 
> Signed-off-by: Christian Gmeiner <cgmeiner@xxxxxxxxxx>

Reviewed-by: Lucas Stach <l.stach@xxxxxxxxxxxxxx>

> ---
>  drivers/gpu/drm/etnaviv/etnaviv_drv.c   | 29 ++++++++++++++++++++++++++++-
>  drivers/gpu/drm/etnaviv/etnaviv_drv.h   |  1 +
>  drivers/gpu/drm/etnaviv/etnaviv_gpu.h   |  2 ++
>  drivers/gpu/drm/etnaviv/etnaviv_sched.c |  5 +++++
>  include/uapi/drm/etnaviv_drm.h          | 19 ++++++++++++++++++-
>  5 files changed, 54 insertions(+), 2 deletions(-)
> 
> diff --git a/drivers/gpu/drm/etnaviv/etnaviv_drv.c b/drivers/gpu/drm/etnaviv/etnaviv_drv.c
> index a27ed014fb4e..5c50e5a24408 100644
> --- a/drivers/gpu/drm/etnaviv/etnaviv_drv.c
> +++ b/drivers/gpu/drm/etnaviv/etnaviv_drv.c
> @@ -296,6 +296,32 @@ static int etnaviv_ioctl_get_param(struct drm_device *dev, void *data,
>  	return etnaviv_gpu_get_param(gpu, args->param, &args->value);
>  }
>  
> +static int etnaviv_ioctl_reset_query(struct drm_device *dev, void *data,
> +		struct drm_file *file)
> +{
> +	struct etnaviv_drm_private *priv = dev->dev_private;
> +	struct etnaviv_file_private *ctx = file->driver_priv;
> +	struct drm_etnaviv_reset_query *args = data;
> +	struct etnaviv_gpu *gpu;
> +
> +	if (args->flags)
> +		return -EINVAL;
> +
> +	if (args->pipe >= ETNA_MAX_PIPES)
> +		return -EINVAL;
> +
> +	gpu = priv->gpu[args->pipe];
> +	if (!gpu)
> +		return -ENXIO;
> +
> +	mutex_lock(&gpu->lock);
> +	args->global_reset_counter = gpu->reset_counter;
> +	args->context_reset_counter = ctx->reset_counter;
> +	mutex_unlock(&gpu->lock);
> +
> +	return 0;
> +}
> +
>  static int etnaviv_ioctl_gem_new(struct drm_device *dev, void *data,
>  		struct drm_file *file)
>  {
> @@ -502,6 +528,7 @@ static const struct drm_ioctl_desc etnaviv_ioctls[] = {
>  	ETNA_IOCTL(GEM_WAIT,     gem_wait,     DRM_RENDER_ALLOW),
>  	ETNA_IOCTL(PM_QUERY_DOM, pm_query_dom, DRM_RENDER_ALLOW),
>  	ETNA_IOCTL(PM_QUERY_SIG, pm_query_sig, DRM_RENDER_ALLOW),
> +	ETNA_IOCTL(RESET_QUERY,  reset_query,  DRM_RENDER_ALLOW),
>  };
>  
>  static void etnaviv_show_fdinfo(struct drm_printer *p, struct drm_file *file)
> @@ -530,7 +557,7 @@ static const struct drm_driver etnaviv_drm_driver = {
>  	.name               = "etnaviv",
>  	.desc               = "etnaviv DRM",
>  	.major              = 1,
> -	.minor              = 4,
> +	.minor              = 5,
>  };
>  
>  /*
> diff --git a/drivers/gpu/drm/etnaviv/etnaviv_drv.h b/drivers/gpu/drm/etnaviv/etnaviv_drv.h
> index cba4323ae589..9c348aa7f8d3 100644
> --- a/drivers/gpu/drm/etnaviv/etnaviv_drv.h
> +++ b/drivers/gpu/drm/etnaviv/etnaviv_drv.h
> @@ -34,6 +34,7 @@ struct etnaviv_file_private {
>  	int id;
>  	struct etnaviv_iommu_context	*mmu;
>  	struct drm_sched_entity		sched_entity[ETNA_MAX_PIPES];
> +	u32 reset_counter;
>  };
>  
>  struct etnaviv_drm_private {
> diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.h b/drivers/gpu/drm/etnaviv/etnaviv_gpu.h
> index 5cb46c84e03a..a97780131426 100644
> --- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.h
> +++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.h
> @@ -148,6 +148,8 @@ struct etnaviv_gpu {
>  	u32 hangcheck_primid;
>  	u32 hangcheck_fence;
>  
> +	u32 reset_counter;
> +
>  	void __iomem *mmio;
>  	int irq;
>  
> diff --git a/drivers/gpu/drm/etnaviv/etnaviv_sched.c b/drivers/gpu/drm/etnaviv/etnaviv_sched.c
> index 139e6e38784b..6e9b677122e3 100644
> --- a/drivers/gpu/drm/etnaviv/etnaviv_sched.c
> +++ b/drivers/gpu/drm/etnaviv/etnaviv_sched.c
> @@ -79,6 +79,11 @@ static enum drm_gpu_sched_stat etnaviv_sched_timedout_job(struct drm_sched_job
>  	if(sched_job)
>  		drm_sched_increase_karma(sched_job);
>  
> +	mutex_lock(&gpu->lock);
> +	gpu->reset_counter++;
> +	submit->ctx->reset_counter++;
> +	mutex_unlock(&gpu->lock);
> +
>  	/* get the GPU back into the init state */
>  	etnaviv_core_dump(submit);
>  	etnaviv_gpu_recover_hang(submit);
> diff --git a/include/uapi/drm/etnaviv_drm.h b/include/uapi/drm/etnaviv_drm.h
> index af024d90453d..b50a3a0799e6 100644
> --- a/include/uapi/drm/etnaviv_drm.h
> +++ b/include/uapi/drm/etnaviv_drm.h
> @@ -265,6 +265,21 @@ struct drm_etnaviv_pm_signal {
>  	char  name[64];   /* out, name of domain */
>  };
>  
> +/*
> + * Reset status query:
> + *
> + * Both counters start at zero and only ever increase. Userspace saves
> + * both values and compares them on a later query: if the context
> + * counter moved this context caused a reset, if only the global
> + * counter moved the GPU was reset on behalf of another context.
> + */
> +struct drm_etnaviv_reset_query {
> +	__u32 pipe;			/* in */
> +	__u32 flags;			/* in, must be 0 */
> +	__u32 global_reset_counter;	/* out, all resets of this GPU core */
> +	__u32 context_reset_counter;	/* out, resets caused by this context */
> +};
> +
>  #define DRM_ETNAVIV_GET_PARAM          0x00
>  /* placeholder:
>  #define DRM_ETNAVIV_SET_PARAM          0x01
> @@ -279,7 +294,8 @@ struct drm_etnaviv_pm_signal {
>  #define DRM_ETNAVIV_GEM_WAIT           0x09
>  #define DRM_ETNAVIV_PM_QUERY_DOM       0x0a
>  #define DRM_ETNAVIV_PM_QUERY_SIG       0x0b
> -#define DRM_ETNAVIV_NUM_IOCTLS         0x0c
> +#define DRM_ETNAVIV_RESET_QUERY        0x0c
> +#define DRM_ETNAVIV_NUM_IOCTLS         0x0d
>  
>  #define DRM_IOCTL_ETNAVIV_GET_PARAM    DRM_IOWR(DRM_COMMAND_BASE + DRM_ETNAVIV_GET_PARAM, struct drm_etnaviv_param)
>  #define DRM_IOCTL_ETNAVIV_GEM_NEW      DRM_IOWR(DRM_COMMAND_BASE + DRM_ETNAVIV_GEM_NEW, struct drm_etnaviv_gem_new)
> @@ -292,6 +308,7 @@ struct drm_etnaviv_pm_signal {
>  #define DRM_IOCTL_ETNAVIV_GEM_WAIT     DRM_IOW(DRM_COMMAND_BASE + DRM_ETNAVIV_GEM_WAIT, struct drm_etnaviv_gem_wait)
>  #define DRM_IOCTL_ETNAVIV_PM_QUERY_DOM DRM_IOWR(DRM_COMMAND_BASE + DRM_ETNAVIV_PM_QUERY_DOM, struct drm_etnaviv_pm_domain)
>  #define DRM_IOCTL_ETNAVIV_PM_QUERY_SIG DRM_IOWR(DRM_COMMAND_BASE + DRM_ETNAVIV_PM_QUERY_SIG, struct drm_etnaviv_pm_signal)
> +#define DRM_IOCTL_ETNAVIV_RESET_QUERY  DRM_IOWR(DRM_COMMAND_BASE + DRM_ETNAVIV_RESET_QUERY, struct drm_etnaviv_reset_query)
>  
>  #if defined(__cplusplus)
>  }