[PATCH v3 10/12] drm/xe/pxp: add PXP PM support

John Harrison john.c.harrison at intel.com
Mon Dec 9 19:42:38 UTC 2024


On 11/20/2024 15:43, Daniele Ceraolo Spurio wrote:
> The HW suspend flow kills all PXP HWDRM sessions, so if there was any
> PXP activity before the suspend we need to trigger a full termination on
> suspend.
>
> v2: rebase
+changes about runtime suspend

Reviewed-by: John Harrison <John.C.Harrison at Intel.com>


>
> Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio at intel.com>
> Cc: John Harrison <John.C.Harrison at Intel.com>
> ---
>   drivers/gpu/drm/xe/xe_pm.c        |  40 +++++++---
>   drivers/gpu/drm/xe/xe_pxp.c       | 120 ++++++++++++++++++++++++++++--
>   drivers/gpu/drm/xe/xe_pxp.h       |   3 +
>   drivers/gpu/drm/xe/xe_pxp_types.h |   7 ++
>   4 files changed, 156 insertions(+), 14 deletions(-)
>
> diff --git a/drivers/gpu/drm/xe/xe_pm.c b/drivers/gpu/drm/xe/xe_pm.c
> index 80699dbeb2e9..2fe011a6c6e9 100644
> --- a/drivers/gpu/drm/xe/xe_pm.c
> +++ b/drivers/gpu/drm/xe/xe_pm.c
> @@ -21,6 +21,7 @@
>   #include "xe_guc.h"
>   #include "xe_irq.h"
>   #include "xe_pcode.h"
> +#include "xe_pxp.h"
>   #include "xe_trace.h"
>   #include "xe_wa.h"
>   
> @@ -121,6 +122,10 @@ int xe_pm_suspend(struct xe_device *xe)
>   	drm_dbg(&xe->drm, "Suspending device\n");
>   	trace_xe_pm_suspend(xe, __builtin_return_address(0));
>   
> +	err = xe_pxp_pm_suspend(xe->pxp, false);
> +	if (err)
> +		goto err;
> +
>   	for_each_gt(gt, xe, id)
>   		xe_gt_suspend_prepare(gt);
>   
> @@ -129,14 +134,12 @@ int xe_pm_suspend(struct xe_device *xe)
>   	/* FIXME: Super racey... */
>   	err = xe_bo_evict_all(xe);
>   	if (err)
> -		goto err;
> +		goto err_pxp;
>   
>   	for_each_gt(gt, xe, id) {
>   		err = xe_gt_suspend(gt);
> -		if (err) {
> -			xe_display_pm_resume(xe);
> -			goto err;
> -		}
> +		if (err)
> +			goto err_display;
>   	}
>   
>   	xe_irq_suspend(xe);
> @@ -145,6 +148,11 @@ int xe_pm_suspend(struct xe_device *xe)
>   
>   	drm_dbg(&xe->drm, "Device suspended\n");
>   	return 0;
> +
> +err_display:
> +	xe_display_pm_resume(xe);
> +err_pxp:
> +	xe_pxp_pm_resume(xe->pxp);
>   err:
>   	drm_dbg(&xe->drm, "Device suspend failed %d\n", err);
>   	return err;
> @@ -194,6 +202,8 @@ int xe_pm_resume(struct xe_device *xe)
>   	if (err)
>   		goto err;
>   
> +	xe_pxp_pm_resume(xe->pxp);
> +
>   	drm_dbg(&xe->drm, "Device resumed\n");
>   	return 0;
>   err:
> @@ -388,6 +398,10 @@ int xe_pm_runtime_suspend(struct xe_device *xe)
>   	 */
>   	xe_rpm_lockmap_acquire(xe);
>   
> +	err = xe_pxp_pm_suspend(xe->pxp, true);
> +	if (err)
> +		goto out;
> +
>   	/*
>   	 * Applying lock for entire list op as xe_ttm_bo_destroy and xe_bo_move_notify
>   	 * also checks and delets bo entry from user fault list.
> @@ -403,22 +417,28 @@ int xe_pm_runtime_suspend(struct xe_device *xe)
>   	if (xe->d3cold.allowed) {
>   		err = xe_bo_evict_all(xe);
>   		if (err)
> -			goto out;
> +			goto out_resume;
>   	}
>   
>   	for_each_gt(gt, xe, id) {
>   		err = xe_gt_suspend(gt);
>   		if (err)
> -			goto out;
> +			goto out_resume;
>   	}
>   
>   	xe_irq_suspend(xe);
>   
>   	if (xe->d3cold.allowed)
>   		xe_display_pm_suspend_late(xe);
> +
> +	xe_rpm_lockmap_release(xe);
> +	xe_pm_write_callback_task(xe, NULL);
> +	return 0;
> +
> +out_resume:
> +	xe_display_pm_runtime_resume(xe);
> +	xe_pxp_pm_resume(xe->pxp);
>   out:
> -	if (err)
> -		xe_display_pm_runtime_resume(xe);
>   	xe_rpm_lockmap_release(xe);
>   	xe_pm_write_callback_task(xe, NULL);
>   	return err;
> @@ -471,6 +491,8 @@ int xe_pm_runtime_resume(struct xe_device *xe)
>   			goto out;
>   	}
>   
> +	xe_pxp_pm_resume(xe->pxp);
> +
>   out:
>   	xe_rpm_lockmap_release(xe);
>   	xe_pm_write_callback_task(xe, NULL);
> diff --git a/drivers/gpu/drm/xe/xe_pxp.c b/drivers/gpu/drm/xe/xe_pxp.c
> index f39625ae0259..06f025bce5f8 100644
> --- a/drivers/gpu/drm/xe/xe_pxp.c
> +++ b/drivers/gpu/drm/xe/xe_pxp.c
> @@ -123,6 +123,14 @@ static int pxp_wait_for_session_state(struct xe_pxp *pxp, u32 id, bool in_play)
>   
>   static void pxp_invalidate_queues(struct xe_pxp *pxp);
>   
> +static void pxp_invalidate_state(struct xe_pxp *pxp)
> +{
> +	pxp_invalidate_queues(pxp);
> +
> +	if (pxp->status == XE_PXP_ACTIVE)
> +		pxp->key_instance++;
> +}
> +
>   static void pxp_terminate(struct xe_pxp *pxp)
>   {
>   	int ret = 0;
> @@ -132,10 +140,14 @@ static void pxp_terminate(struct xe_pxp *pxp)
>   
>   	lockdep_assert_held(&pxp->mutex);
>   
> -	pxp_invalidate_queues(pxp);
> +	pxp_invalidate_state(pxp);
>   
> -	if (pxp->status == XE_PXP_ACTIVE)
> -		pxp->key_instance++;
> +	/*
> +	 * we'll mark the status as needing termination on resume, so no need to
> +	 * emit a termination now.
> +	 */
> +	if (pxp->status == XE_PXP_SUSPENDED)
> +		return;
>   
>   	/*
>   	 * If we have a termination already in progress, we need to wait for
> @@ -187,17 +199,19 @@ static void pxp_terminate(struct xe_pxp *pxp)
>   static void pxp_terminate_complete(struct xe_pxp *pxp)
>   {
>   	/*
> -	 * We expect PXP to be in one of 2 states when we get here:
> +	 * We expect PXP to be in one of 3 states when we get here:
>   	 * - XE_PXP_TERMINATION_IN_PROGRESS: a single termination event was
>   	 * requested and it is now completing, so we're ready to start.
>   	 * - XE_PXP_NEEDS_TERMINATION: a second termination was requested while
>   	 * the first one was still being processed; we don't update the state
>   	 * in this case so the pxp_start code will automatically issue that
>   	 * second termination.
> +	 * - XE_PXP_SUSPENDED: PXP is now suspended, so we defer everything to
> +	 * when we come back on resume.
>   	 */
>   	if (pxp->status == XE_PXP_TERMINATION_IN_PROGRESS)
>   		pxp->status = XE_PXP_READY_TO_START;
> -	else if (pxp->status != XE_PXP_NEEDS_TERMINATION)
> +	else if (pxp->status != XE_PXP_NEEDS_TERMINATION && pxp->status != XE_PXP_SUSPENDED)
>   		drm_err(&pxp->xe->drm,
>   			"PXP termination complete while status was %u\n",
>   			pxp->status);
> @@ -355,6 +369,7 @@ int xe_pxp_init(struct xe_device *xe)
>   	pxp->gt = gt;
>   
>   	pxp->key_instance = 1;
> +	pxp->last_suspend_key_instance = 1;
>   
>   	/*
>   	 * we'll use the completion to check if there is a termination pending,
> @@ -524,6 +539,7 @@ int xe_pxp_exec_queue_add(struct xe_pxp *pxp, struct xe_exec_queue *q)
>   		pxp_terminate(pxp);
>   		mutex_unlock(&pxp->mutex);
>   		goto wait_for_termination;
> +	case XE_PXP_SUSPENDED:
>   	default:
>   		drm_err(&pxp->xe->drm, "unexpected state during PXP start: %u", pxp->status);
>   		ret = -EIO;
> @@ -674,3 +690,97 @@ int xe_pxp_key_check(struct xe_pxp *pxp, struct xe_bo *bo)
>   	return 0;
>   }
>   
> +/**
> + * xe_pxp_pm_suspend - prepare PXP for HW suspend
> + * @pxp: the xe->pxp pointer (it will be NULL if PXP is disabled)
> + * @runtime: indicates whether this is a runtime suspend or not
> + *
> + * Checks whether a BO was encrypted with the current key or an obsolete one.
> + *
> + * Returns: 0 if successful, a negative errno value otherwise.
> + */
> +int xe_pxp_pm_suspend(struct xe_pxp *pxp, bool runtime)
> +{
> +	int ret = 0;
> +
> +	if (!xe_pxp_is_enabled(pxp))
> +		return 0;
> +
> +	mutex_lock(&pxp->mutex);
> +
> +	/* if a termination is already in progress, no need to do additional cleanup */
> +	if (!completion_done(&pxp->termination))
> +		goto mark_suspended;
> +
> +	switch (pxp->status) {
> +	case XE_PXP_ERROR:
> +	case XE_PXP_READY_TO_START:
> +	case XE_PXP_SUSPENDED:
> +		/* nothing to cleanup */
> +		break;
> +	case XE_PXP_NEEDS_TERMINATION:
> +		/* If PXP was never used we can skip the cleanup */
> +		if (pxp->key_instance == pxp->last_suspend_key_instance)
> +			break;
> +		fallthrough;
> +	case XE_PXP_ACTIVE:
> +		if (runtime)
> +			pxp_invalidate_state(pxp);
> +		else
> +			pxp_terminate(pxp);
> +		break;
> +	default:
> +		drm_err(&pxp->xe->drm, "unexpected state during PXP suspend: %u",
> +			pxp->status);
> +		ret = -EIO;
> +		goto out;
> +	}
> +
> +mark_suspended:
> +	/*
> +	 * We set this even if we were in error state, hoping the suspend clears
> +	 * the error. Worse case we fail again and go in error state again.
> +	 */
> +	pxp->status = XE_PXP_SUSPENDED;
> +
> +	mutex_unlock(&pxp->mutex);
> +
> +	/*
> +	 * if there is a termination in progress, wait for it.
> +	 * We need to wait outside the lock because the completion is done from
> +	 * within the lock
> +	 */
> +	if (!wait_for_completion_timeout(&pxp->termination,
> +					 msecs_to_jiffies(PXP_TERMINATION_TIMEOUT_MS)))
> +		ret = -ETIMEDOUT;
> +
> +	pxp->last_suspend_key_instance = pxp->key_instance;
> +
> +out:
> +	return ret;
> +}
> +
> +/**
> + * xe_pxp_pm_resume - re-init PXP after HW suspend
> + * @pxp: the xe->pxp pointer (it will be NULL if PXP is disabled)
> + */
> +void xe_pxp_pm_resume(struct xe_pxp *pxp)
> +{
> +	int err;
> +
> +	if (!xe_pxp_is_enabled(pxp))
> +		return;
> +
> +	err = kcr_pxp_enable(pxp);
> +
> +	mutex_lock(&pxp->mutex);
> +
> +	xe_assert(pxp->xe, pxp->status == XE_PXP_SUSPENDED);
> +
> +	if (err)
> +		pxp->status = XE_PXP_ERROR;
> +	else
> +		pxp->status = XE_PXP_NEEDS_TERMINATION;
> +
> +	mutex_unlock(&pxp->mutex);
> +}
> diff --git a/drivers/gpu/drm/xe/xe_pxp.h b/drivers/gpu/drm/xe/xe_pxp.h
> index 2d22a6e6ab27..0477bb46d49f 100644
> --- a/drivers/gpu/drm/xe/xe_pxp.h
> +++ b/drivers/gpu/drm/xe/xe_pxp.h
> @@ -20,6 +20,9 @@ int xe_pxp_get_readiness_status(struct xe_pxp *pxp);
>   int xe_pxp_init(struct xe_device *xe);
>   void xe_pxp_irq_handler(struct xe_device *xe, u16 iir);
>   
> +int xe_pxp_pm_suspend(struct xe_pxp *pxp, bool runtime);
> +void xe_pxp_pm_resume(struct xe_pxp *pxp);
> +
>   int xe_pxp_exec_queue_set_type(struct xe_pxp *pxp, struct xe_exec_queue *q, u8 type);
>   int xe_pxp_exec_queue_add(struct xe_pxp *pxp, struct xe_exec_queue *q);
>   void xe_pxp_exec_queue_remove(struct xe_pxp *pxp, struct xe_exec_queue *q);
> diff --git a/drivers/gpu/drm/xe/xe_pxp_types.h b/drivers/gpu/drm/xe/xe_pxp_types.h
> index 9c2d2b9a850d..fa40b039e26f 100644
> --- a/drivers/gpu/drm/xe/xe_pxp_types.h
> +++ b/drivers/gpu/drm/xe/xe_pxp_types.h
> @@ -25,6 +25,7 @@ enum xe_pxp_status {
>   	XE_PXP_TERMINATION_IN_PROGRESS,
>   	XE_PXP_READY_TO_START,
>   	XE_PXP_ACTIVE,
> +	XE_PXP_SUSPENDED,
>   };
>   
>   /**
> @@ -119,6 +120,12 @@ struct xe_pxp {
>   	 * that case in the code.
>   	 */
>   	u32 key_instance;
> +	/**
> +	 * @last_suspend_key_instance: value of key_instance at the last
> +	 * suspend. Used to check if any PXP session has been created between
> +	 * suspend cycles.
> +	 */
> +	u32 last_suspend_key_instance;
>   };
>   
>   #endif /* __XE_PXP_TYPES_H__ */



More information about the Intel-xe mailing list