Re: [Intel-xe] [PATCH v4 1/7] drm/xe: hold mem_access.ref for CT fast-path

[Matthew Brost <matthew.brost@intel.com>]

On Wed, Jul 05, 2023 at 05:06:04PM +0100, Matthew Auld wrote:
> Just checking xe_device_mem_access_ongoing() is not enough, we also need
> to hold the reference otherwise the ref can transition from 1 -> 0 as we
> enter g2h_read(), leading to warnings. While we can't do a full rpm sync
> in the IRQ, we can keep the device awake if the ref is non-zero.
> Introduce a new helper for this and set it to work in for the CT
> fast-path.
> 
> Signed-off-by: Matthew Auld <matthew.auld@intel.com>
> Cc: Matthew Brost <matthew.brost@intel.com>
> Cc: José Roberto de Souza <jose.souza@intel.com>
> ---
>  drivers/gpu/drm/xe/xe_device.c | 5 +++++
>  drivers/gpu/drm/xe/xe_device.h | 1 +
>  drivers/gpu/drm/xe/xe_guc_ct.c | 5 ++++-
>  3 files changed, 10 insertions(+), 1 deletion(-)
> 
> diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
> index 07ae208af809..94b0089b0dee 100644
> --- a/drivers/gpu/drm/xe/xe_device.c
> +++ b/drivers/gpu/drm/xe/xe_device.c
> @@ -412,6 +412,11 @@ u32 xe_device_ccs_bytes(struct xe_device *xe, u64 size)
>  		DIV_ROUND_UP(size, NUM_BYTES_PER_CCS_BYTE) : 0;
>  }
>  
> +bool xe_device_mem_access_get_if_ongoing(struct xe_device *xe)
> +{
> +	return atomic_inc_not_zero(&xe->mem_access.ref);
> +}
> +
>  void xe_device_mem_access_get(struct xe_device *xe)
>  {
>  	bool resumed = xe_pm_runtime_resume_if_suspended(xe);
> diff --git a/drivers/gpu/drm/xe/xe_device.h b/drivers/gpu/drm/xe/xe_device.h
> index 779f71d066e6..8e01bbadb149 100644
> --- a/drivers/gpu/drm/xe/xe_device.h
> +++ b/drivers/gpu/drm/xe/xe_device.h
> @@ -138,6 +138,7 @@ static inline struct xe_force_wake * gt_to_fw(struct xe_gt *gt)
>  }
>  
>  void xe_device_mem_access_get(struct xe_device *xe);
> +bool xe_device_mem_access_get_if_ongoing(struct xe_device *xe);
>  void xe_device_mem_access_put(struct xe_device *xe);
>  
>  static inline bool xe_device_mem_access_ongoing(struct xe_device *xe)
> diff --git a/drivers/gpu/drm/xe/xe_guc_ct.c b/drivers/gpu/drm/xe/xe_guc_ct.c
> index 22bc9ce846db..b7aecc480098 100644
> --- a/drivers/gpu/drm/xe/xe_guc_ct.c
> +++ b/drivers/gpu/drm/xe/xe_guc_ct.c
> @@ -1038,7 +1038,8 @@ void xe_guc_ct_fast_path(struct xe_guc_ct *ct)
>  	struct xe_device *xe = ct_to_xe(ct);
>  	int len;
>  
> -	if (!xe_device_in_fault_mode(xe) || !xe_device_mem_access_ongoing(xe))
> +	if (!xe_device_in_fault_mode(xe) ||
> +	    !xe_device_mem_access_get_if_ongoing(xe))
>  		return;
>  
>  	spin_lock(&ct->fast_lock);
> @@ -1048,6 +1049,8 @@ void xe_guc_ct_fast_path(struct xe_guc_ct *ct)
>  			g2h_fast_path(ct, ct->fast_msg, len);
>  	} while (len > 0);
>  	spin_unlock(&ct->fast_lock);
> +
> +	xe_device_mem_access_put(xe);

Can't this sleep if would go from 1->0, i.e. can't xe_pm_runtime_put sleep?

Matt

>  }
>  
>  /* Returns less than zero on error, 0 on done, 1 on more available */
> -- 
> 2.41.0
>