Re: [PATCH v4] drm/xe: Poll GT for C6 before D3

[Raag Jadav <raag.jadav@intel.com>]

On Tue, Sep 15, 2026 at 12:11:45AM -0700, Vinay Belgaumkar wrote:
> Ensure GT C6 state before D3 transition in runtime suspend flow.
> This avoids the scenario where GT is being accessed after D3 state
> is programmed. If the check for C6 fails, resume the device so it is
> not stuck in an intermediate state.
> 
> v2: Force resume when we cancel suspend due to C6 check (Sashiko)
> v3: Abort the suspend properly when idle check fails (Sashiko)
> v4: Only check for C6 during suspend (Rodrigo). Have check in
> xe_pci_runtime_suspend() instead of xe_pci_suspend().
> 
> Cc: Badal Nilawar <badal.nilawar@intel.com>
> Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
> Signed-off-by: Vinay Belgaumkar <vinay.belgaumkar@intel.com>
> ---
>  drivers/gpu/drm/xe/xe_gt_idle.c | 36 +++++++++++++++++++++++++++++++++
>  drivers/gpu/drm/xe/xe_gt_idle.h |  1 +
>  drivers/gpu/drm/xe/xe_pci.c     | 13 +++++++++++-
>  drivers/gpu/drm/xe/xe_pm.c      | 21 +++++++++++++++++++
>  drivers/gpu/drm/xe/xe_pm.h      |  1 +
>  5 files changed, 71 insertions(+), 1 deletion(-)
> 
> diff --git a/drivers/gpu/drm/xe/xe_gt_idle.c b/drivers/gpu/drm/xe/xe_gt_idle.c
> index c208d7563e36..8242feede1dd 100644
> --- a/drivers/gpu/drm/xe/xe_gt_idle.c
> +++ b/drivers/gpu/drm/xe/xe_gt_idle.c
> @@ -8,10 +8,12 @@
>  #include <drm/drm_managed.h>
>  
>  #include <generated/xe_wa_oob.h>
> +#include <linux/iopoll.h>
>  #include "xe_force_wake.h"
>  #include "xe_device.h"
>  #include "xe_gt.h"
>  #include "xe_gt_idle.h"
> +#include "xe_gt_printk.h"
>  #include "xe_gt_sysfs.h"
>  #include "xe_guc_pc.h"
>  #include "regs/xe_gt_regs.h"
> @@ -451,3 +453,37 @@ int xe_gt_idle_disable_c6(struct xe_gt *gt)
>  
>  	return 0;
>  }
> +
> +static int wait_for_gt_c6_state(struct xe_gt *gt, u32 timeout_ms)
> +{
> +	struct xe_guc_pc *pc = &gt->uc.guc.pc;
> +	enum xe_gt_idle_state state;
> +
> +	return poll_timeout_us(state = gt->gtidle.idle_status(pc),
> +			       state == GT_IDLE_C6,
> +			       20,
> +			       timeout_ms * USEC_PER_MSEC,
> +			       false);
> +}
> +
> +/**
> + * xe_gt_idle_wait_for_c6 - Poll for GT C6
> + * @gt: GT object
> + * @timeout_ms: wait time in ms
> + *
> + * This function waits for GT to enter C6.
> + *
> + * Return: 0 on success, -EAGAIN otherwise
> + */
> +int xe_gt_idle_wait_for_c6(struct xe_gt *gt, u32 timeout_ms)
> +{
> +	if (IS_SRIOV_VF(gt_to_xe(gt)))
> +		return 0;
> +
> +	if (wait_for_gt_c6_state(gt, timeout_ms)) {
> +		xe_gt_dbg(gt, "GT is not in C6\n");
> +		return -EAGAIN;
> +	}
> +
> +	return 0;
> +}
> diff --git a/drivers/gpu/drm/xe/xe_gt_idle.h b/drivers/gpu/drm/xe/xe_gt_idle.h
> index 9c34a155e102..2c8e9adf4a68 100644
> --- a/drivers/gpu/drm/xe/xe_gt_idle.h
> +++ b/drivers/gpu/drm/xe/xe_gt_idle.h
> @@ -18,5 +18,6 @@ void xe_gt_idle_enable_pg(struct xe_gt *gt);
>  void xe_gt_idle_disable_pg(struct xe_gt *gt);
>  int xe_gt_idle_pg_print(struct xe_gt *gt, struct drm_printer *p);
>  u64 xe_gt_idle_residency_msec(struct xe_gt_idle *gtidle);
> +int xe_gt_idle_wait_for_c6(struct xe_gt *gt, u32 timeout_ms);
>  
>  #endif /* _XE_GT_IDLE_H_ */
> diff --git a/drivers/gpu/drm/xe/xe_pci.c b/drivers/gpu/drm/xe/xe_pci.c
> index ab4da1d9a9f1..379795ac5e7b 100644
> --- a/drivers/gpu/drm/xe/xe_pci.c
> +++ b/drivers/gpu/drm/xe/xe_pci.c
> @@ -1381,7 +1381,7 @@ static int xe_pci_runtime_suspend(struct device *dev)
>  {
>  	struct pci_dev *pdev = to_pci_dev(dev);
>  	struct xe_device *xe = pdev_to_xe_device(pdev);
> -	int err;
> +	int err, ret;
>  
>  	/*
>  	 * We hold an additional reference to the runtime PM to keep PF in D0
> @@ -1396,6 +1396,17 @@ static int xe_pci_runtime_suspend(struct device *dev)
>  	if (err)
>  		return err;
>  
> +	err = xe_pm_check_device_idle(xe);

Considering driver has no control over C state here, is there a guarantee
that GT will remain in C6 after this point?

Raag

> +	if (err) {
> +		drm_dbg(&xe->drm, "Resuming - Device idle check failed!");
> +		ret = xe_pm_runtime_resume(xe);
> +		if (ret) {
> +			drm_err(&xe->drm, "Resume failed after suspend was canceled");
> +			return ret;
> +		}
> +		return err;
> +	}
> +
>  	pci_save_state(pdev);
>  
>  	if (xe->d3cold.allowed) {
> diff --git a/drivers/gpu/drm/xe/xe_pm.c b/drivers/gpu/drm/xe/xe_pm.c
> index f517bf453b54..678afd7a1d08 100644
> --- a/drivers/gpu/drm/xe/xe_pm.c
> +++ b/drivers/gpu/drm/xe/xe_pm.c
> @@ -1030,6 +1030,27 @@ void xe_pm_d3cold_allowed_toggle(struct xe_device *xe)
>  	mutex_unlock(&xe->d3cold.lock);
>  }
>  
> +/**
> + * xe_pm_check_device_idle() - Check if all GTs are idle.
> + * @xe: xe device instance
> + *
> + * One of the ways to do this is to check for GT C6 state. This check
> + * will fail if some component is holding a forcewake, for example.
> + *
> + * Return: 0 on success, -EAGAIN on failure
> + */
> +int xe_pm_check_device_idle(struct xe_device *xe)
> +{
> +	struct xe_gt *gt;
> +	u8 id;
> +
> +	for_each_gt(gt, xe, id)
> +		if (xe_gt_idle_wait_for_c6(gt, 200))
> +			return -EAGAIN;
> +
> +	return 0;
> +}
> +
>  /**
>   * xe_pm_module_init() - Perform xe_pm specific module initialization.
>   *
> diff --git a/drivers/gpu/drm/xe/xe_pm.h b/drivers/gpu/drm/xe/xe_pm.h
> index 6d5ab09cb769..a4fdc9c5cb10 100644
> --- a/drivers/gpu/drm/xe/xe_pm.h
> +++ b/drivers/gpu/drm/xe/xe_pm.h
> @@ -36,6 +36,7 @@ void xe_pm_d3cold_allowed_toggle(struct xe_device *xe);
>  bool xe_rpm_reclaim_safe(const struct xe_device *xe);
>  struct task_struct *xe_pm_read_callback_task(struct xe_device *xe);
>  int xe_pm_block_on_suspend(struct xe_device *xe);
> +int xe_pm_check_device_idle(struct xe_device *xe);
>  void xe_pm_might_block_on_suspend(void);
>  int xe_pm_module_init(void);
>  
> -- 
> 2.38.1
>