Re: [PATCH v9 09/26] drm/xe/gt: Update handling of xe_force_wake_get return

[Nirmoy Das <nirmoy.das@linux.intel.com>]

On 10/14/2024 9:55 AM, Himal Prasad Ghimiray wrote:
> xe_force_wake_get() now returns the reference count-incremented domain
> mask. If it fails for individual domains, the return value will always
> be 0. However, for XE_FORCEWAKE_ALL, it may return a non-zero value even
> in the event of failure. Use helper xe_force_wake_ref_has_domain to verify
> all domains are initialized or not. Update the return handling of
> xe_force_wake_get() to reflect this behavior, and ensure that the return
> value is passed as input to xe_force_wake_put().
>
> v3
> - return xe_wakeref_t instead of int in xe_force_wake_get()
> - xe_force_wake_put() error doesn't need to be checked. It internally
> WARNS on domain ack failure.
>
> v4
> - Rebase fix
>
> v5
> - return unsigned int for xe_force_wake_get()
> - remove redundant XE_WARN_ON()
>
> v6
> - use helper for checking all initialized domains are awake or not.
>
> v7
> - Fix commit message
>
> v9
> - Remove redundant WARN_ON (Badal)
>
> Cc: Badal Nilawar <badal.nilawar@intel.com>
> Cc: Matthew Brost <matthew.brost@intel.com>
> Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
> Cc: Lucas De Marchi <lucas.demarchi@intel.com>
> Signed-off-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Reviewed-by: Nirmoy Das <nirmoy.das@intel.com>
> ---
>  drivers/gpu/drm/xe/xe_gt.c | 105 ++++++++++++++++++++-----------------
>  1 file changed, 58 insertions(+), 47 deletions(-)
>
> diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c
> index 1c79660fb086..adb51845c21a 100644
> --- a/drivers/gpu/drm/xe/xe_gt.c
> +++ b/drivers/gpu/drm/xe/xe_gt.c
> @@ -97,14 +97,14 @@ void xe_gt_sanitize(struct xe_gt *gt)
>  
>  static void xe_gt_enable_host_l2_vram(struct xe_gt *gt)
>  {
> +	unsigned int fw_ref;
>  	u32 reg;
> -	int err;
>  
>  	if (!XE_WA(gt, 16023588340))
>  		return;
>  
> -	err = xe_force_wake_get(gt_to_fw(gt), XE_FW_GT);
> -	if (WARN_ON(err))
> +	fw_ref = xe_force_wake_get(gt_to_fw(gt), XE_FW_GT);
> +	if (!fw_ref)
>  		return;
>  
>  	if (!xe_gt_is_media_type(gt)) {
> @@ -114,13 +114,13 @@ static void xe_gt_enable_host_l2_vram(struct xe_gt *gt)
>  	}
>  
>  	xe_gt_mcr_multicast_write(gt, XEHPC_L3CLOS_MASK(3), 0x3);
> -	xe_force_wake_put(gt_to_fw(gt), XE_FW_GT);
> +	xe_force_wake_put(gt_to_fw(gt), fw_ref);
>  }
>  
>  static void xe_gt_disable_host_l2_vram(struct xe_gt *gt)
>  {
> +	unsigned int fw_ref;
>  	u32 reg;
> -	int err;
>  
>  	if (!XE_WA(gt, 16023588340))
>  		return;
> @@ -128,15 +128,15 @@ static void xe_gt_disable_host_l2_vram(struct xe_gt *gt)
>  	if (xe_gt_is_media_type(gt))
>  		return;
>  
> -	err = xe_force_wake_get(gt_to_fw(gt), XE_FW_GT);
> -	if (WARN_ON(err))
> +	fw_ref = xe_force_wake_get(gt_to_fw(gt), XE_FW_GT);
> +	if (!fw_ref)
>  		return;
>  
>  	reg = xe_gt_mcr_unicast_read_any(gt, XE2_GAMREQSTRM_CTRL);
>  	reg &= ~CG_DIS_CNTLBUS;
>  	xe_gt_mcr_multicast_write(gt, XE2_GAMREQSTRM_CTRL, reg);
>  
> -	xe_force_wake_put(gt_to_fw(gt), XE_FW_GT);
> +	xe_force_wake_put(gt_to_fw(gt), fw_ref);
>  }
>  
>  /**
> @@ -402,11 +402,14 @@ static void dump_pat_on_error(struct xe_gt *gt)
>  
>  static int gt_fw_domain_init(struct xe_gt *gt)
>  {
> +	unsigned int fw_ref;
>  	int err, i;
>  
> -	err = xe_force_wake_get(gt_to_fw(gt), XE_FW_GT);
> -	if (err)
> +	fw_ref = xe_force_wake_get(gt_to_fw(gt), XE_FW_GT);
> +	if (!fw_ref) {
> +		err = -ETIMEDOUT;
>  		goto err_hw_fence_irq;
> +	}
>  
>  	if (!xe_gt_is_media_type(gt)) {
>  		err = xe_ggtt_init(gt_to_tile(gt)->mem.ggtt);
> @@ -441,14 +444,12 @@ static int gt_fw_domain_init(struct xe_gt *gt)
>  	 */
>  	gt->info.gmdid = xe_mmio_read32(&gt->mmio, GMD_ID);
>  
> -	err = xe_force_wake_put(gt_to_fw(gt), XE_FW_GT);
> -	XE_WARN_ON(err);
> -
> +	xe_force_wake_put(gt_to_fw(gt), fw_ref);
>  	return 0;
>  
>  err_force_wake:
>  	dump_pat_on_error(gt);
> -	xe_force_wake_put(gt_to_fw(gt), XE_FW_GT);
> +	xe_force_wake_put(gt_to_fw(gt), fw_ref);
>  err_hw_fence_irq:
>  	for (i = 0; i < XE_ENGINE_CLASS_MAX; ++i)
>  		xe_hw_fence_irq_finish(&gt->fence_irq[i]);
> @@ -458,11 +459,14 @@ static int gt_fw_domain_init(struct xe_gt *gt)
>  
>  static int all_fw_domain_init(struct xe_gt *gt)
>  {
> +	unsigned int fw_ref;
>  	int err, i;
>  
> -	err = xe_force_wake_get(gt_to_fw(gt), XE_FORCEWAKE_ALL);
> -	if (err)
> -		goto err_hw_fence_irq;
> +	fw_ref = xe_force_wake_get(gt_to_fw(gt), XE_FORCEWAKE_ALL);
> +	if (!xe_force_wake_ref_has_domain(fw_ref, XE_FORCEWAKE_ALL)) {
> +		err = -ETIMEDOUT;
> +		goto err_force_wake;
> +	}
>  
>  	xe_gt_mcr_set_implicit_defaults(gt);
>  	xe_reg_sr_apply_mmio(&gt->reg_sr, gt);
> @@ -526,14 +530,12 @@ static int all_fw_domain_init(struct xe_gt *gt)
>  	if (IS_SRIOV_PF(gt_to_xe(gt)))
>  		xe_gt_sriov_pf_init_hw(gt);
>  
> -	err = xe_force_wake_put(gt_to_fw(gt), XE_FORCEWAKE_ALL);
> -	XE_WARN_ON(err);
> +	xe_force_wake_put(gt_to_fw(gt), fw_ref);
>  
>  	return 0;
>  
>  err_force_wake:
> -	xe_force_wake_put(gt_to_fw(gt), XE_FORCEWAKE_ALL);
> -err_hw_fence_irq:
> +	xe_force_wake_put(gt_to_fw(gt), fw_ref);
>  	for (i = 0; i < XE_ENGINE_CLASS_MAX; ++i)
>  		xe_hw_fence_irq_finish(&gt->fence_irq[i]);
>  
> @@ -546,11 +548,12 @@ static int all_fw_domain_init(struct xe_gt *gt)
>   */
>  int xe_gt_init_hwconfig(struct xe_gt *gt)
>  {
> +	unsigned int fw_ref;
>  	int err;
>  
> -	err = xe_force_wake_get(gt_to_fw(gt), XE_FW_GT);
> -	if (err)
> -		goto out;
> +	fw_ref = xe_force_wake_get(gt_to_fw(gt), XE_FW_GT);
> +	if (!fw_ref)
> +		return -ETIMEDOUT;
>  
>  	xe_gt_mcr_init_early(gt);
>  	xe_pat_init(gt);
> @@ -568,8 +571,7 @@ int xe_gt_init_hwconfig(struct xe_gt *gt)
>  	xe_gt_enable_host_l2_vram(gt);
>  
>  out_fw:
> -	xe_force_wake_put(gt_to_fw(gt), XE_FW_GT);
> -out:
> +	xe_force_wake_put(gt_to_fw(gt), fw_ref);
>  	return err;
>  }
>  
> @@ -764,6 +766,7 @@ static int do_gt_restart(struct xe_gt *gt)
>  
>  static int gt_reset(struct xe_gt *gt)
>  {
> +	unsigned int fw_ref;
>  	int err;
>  
>  	if (xe_device_wedged(gt_to_xe(gt)))
> @@ -784,9 +787,11 @@ static int gt_reset(struct xe_gt *gt)
>  
>  	xe_gt_sanitize(gt);
>  
> -	err = xe_force_wake_get(gt_to_fw(gt), XE_FORCEWAKE_ALL);
> -	if (err)
> -		goto err_msg;
> +	fw_ref = xe_force_wake_get(gt_to_fw(gt), XE_FORCEWAKE_ALL);
> +	if (!xe_force_wake_ref_has_domain(fw_ref, XE_FORCEWAKE_ALL)) {
> +		err = -ETIMEDOUT;
> +		goto err_out;
> +	}
>  
>  	xe_uc_gucrc_disable(&gt->uc);
>  	xe_uc_stop_prepare(&gt->uc);
> @@ -804,8 +809,7 @@ static int gt_reset(struct xe_gt *gt)
>  	if (err)
>  		goto err_out;
>  
> -	err = xe_force_wake_put(gt_to_fw(gt), XE_FORCEWAKE_ALL);
> -	XE_WARN_ON(err);
> +	xe_force_wake_put(gt_to_fw(gt), fw_ref);
>  	xe_pm_runtime_put(gt_to_xe(gt));
>  
>  	xe_gt_info(gt, "reset done\n");
> @@ -813,8 +817,7 @@ static int gt_reset(struct xe_gt *gt)
>  	return 0;
>  
>  err_out:
> -	XE_WARN_ON(xe_force_wake_put(gt_to_fw(gt), XE_FORCEWAKE_ALL));
> -err_msg:
> +	xe_force_wake_put(gt_to_fw(gt), fw_ref);
>  	XE_WARN_ON(xe_uc_start(&gt->uc));
>  err_fail:
>  	xe_gt_err(gt, "reset failed (%pe)\n", ERR_PTR(err));
> @@ -846,22 +849,25 @@ void xe_gt_reset_async(struct xe_gt *gt)
>  
>  void xe_gt_suspend_prepare(struct xe_gt *gt)
>  {
> -	XE_WARN_ON(xe_force_wake_get(gt_to_fw(gt), XE_FORCEWAKE_ALL));
> +	unsigned int fw_ref;
> +
> +	fw_ref = xe_force_wake_get(gt_to_fw(gt), XE_FORCEWAKE_ALL);
>  
>  	xe_uc_stop_prepare(&gt->uc);
>  
> -	XE_WARN_ON(xe_force_wake_put(gt_to_fw(gt), XE_FORCEWAKE_ALL));
> +	xe_force_wake_put(gt_to_fw(gt), fw_ref);
>  }
>  
>  int xe_gt_suspend(struct xe_gt *gt)
>  {
> +	unsigned int fw_ref;
>  	int err;
>  
>  	xe_gt_dbg(gt, "suspending\n");
>  	xe_gt_sanitize(gt);
>  
> -	err = xe_force_wake_get(gt_to_fw(gt), XE_FORCEWAKE_ALL);
> -	if (err)
> +	fw_ref = xe_force_wake_get(gt_to_fw(gt), XE_FORCEWAKE_ALL);
> +	if (!xe_force_wake_ref_has_domain(fw_ref, XE_FORCEWAKE_ALL))
>  		goto err_msg;
>  
>  	err = xe_uc_suspend(&gt->uc);
> @@ -872,14 +878,15 @@ int xe_gt_suspend(struct xe_gt *gt)
>  
>  	xe_gt_disable_host_l2_vram(gt);
>  
> -	XE_WARN_ON(xe_force_wake_put(gt_to_fw(gt), XE_FORCEWAKE_ALL));
> +	xe_force_wake_put(gt_to_fw(gt), fw_ref);
>  	xe_gt_dbg(gt, "suspended\n");
>  
>  	return 0;
>  
> -err_force_wake:
> -	XE_WARN_ON(xe_force_wake_put(gt_to_fw(gt), XE_FORCEWAKE_ALL));
>  err_msg:
> +	err = -ETIMEDOUT;
> +err_force_wake:
> +	xe_force_wake_put(gt_to_fw(gt), fw_ref);
>  	xe_gt_err(gt, "suspend failed (%pe)\n", ERR_PTR(err));
>  
>  	return err;
> @@ -887,9 +894,11 @@ int xe_gt_suspend(struct xe_gt *gt)
>  
>  void xe_gt_shutdown(struct xe_gt *gt)
>  {
> -	xe_force_wake_get(gt_to_fw(gt), XE_FORCEWAKE_ALL);
> +	unsigned int fw_ref;
> +
> +	fw_ref = xe_force_wake_get(gt_to_fw(gt), XE_FORCEWAKE_ALL);
>  	do_gt_reset(gt);
> -	xe_force_wake_put(gt_to_fw(gt), XE_FORCEWAKE_ALL);
> +	xe_force_wake_put(gt_to_fw(gt), fw_ref);
>  }
>  
>  /**
> @@ -914,11 +923,12 @@ int xe_gt_sanitize_freq(struct xe_gt *gt)
>  
>  int xe_gt_resume(struct xe_gt *gt)
>  {
> +	unsigned int fw_ref;
>  	int err;
>  
>  	xe_gt_dbg(gt, "resuming\n");
> -	err = xe_force_wake_get(gt_to_fw(gt), XE_FORCEWAKE_ALL);
> -	if (err)
> +	fw_ref = xe_force_wake_get(gt_to_fw(gt), XE_FORCEWAKE_ALL);
> +	if (!xe_force_wake_ref_has_domain(fw_ref, XE_FORCEWAKE_ALL))
>  		goto err_msg;
>  
>  	err = do_gt_restart(gt);
> @@ -927,14 +937,15 @@ int xe_gt_resume(struct xe_gt *gt)
>  
>  	xe_gt_idle_enable_pg(gt);
>  
> -	XE_WARN_ON(xe_force_wake_put(gt_to_fw(gt), XE_FORCEWAKE_ALL));
> +	xe_force_wake_put(gt_to_fw(gt), fw_ref);
>  	xe_gt_dbg(gt, "resumed\n");
>  
>  	return 0;
>  
> -err_force_wake:
> -	XE_WARN_ON(xe_force_wake_put(gt_to_fw(gt), XE_FORCEWAKE_ALL));
>  err_msg:
> +	err = -ETIMEDOUT;
> +err_force_wake:
> +	xe_force_wake_put(gt_to_fw(gt), fw_ref);
>  	xe_gt_err(gt, "resume failed (%pe)\n", ERR_PTR(err));
>  
>  	return err;