public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Michal Wajdeczko <michal.wajdeczko@intel.com>
To: "Michał Winiarski" <michal.winiarski@intel.com>,
	"Alex Williamson" <alex.williamson@redhat.com>,
	"Lucas De Marchi" <lucas.demarchi@intel.com>,
	"Thomas Hellström" <thomas.hellstrom@linux.intel.com>,
	"Rodrigo Vivi" <rodrigo.vivi@intel.com>,
	"Jason Gunthorpe" <jgg@ziepe.ca>,
	"Yishai Hadas" <yishaih@nvidia.com>,
	"Kevin Tian" <kevin.tian@intel.com>,
	intel-xe@lists.freedesktop.org, linux-kernel@vger.kernel.org,
	kvm@vger.kernel.org, "Matthew Brost" <matthew.brost@intel.com>
Cc: <dri-devel@lists.freedesktop.org>,
	Jani Nikula <jani.nikula@linux.intel.com>,
	Joonas Lahtinen <joonas.lahtinen@linux.intel.com>,
	Tvrtko Ursulin <tursulin@ursulin.net>,
	David Airlie <airlied@gmail.com>, Simona Vetter <simona@ffwll.ch>,
	"Lukasz Laguna" <lukasz.laguna@intel.com>
Subject: Re: [PATCH v2 03/26] drm/xe/pf: Add save/restore control state stubs and connect to debugfs
Date: Thu, 23 Oct 2025 00:31:47 +0200	[thread overview]
Message-ID: <fdf1ebb7-e8dd-4228-9b13-588e2e617b15@intel.com> (raw)
In-Reply-To: <20251021224133.577765-4-michal.winiarski@intel.com>



On 10/22/2025 12:41 AM, Michał Winiarski wrote:
> The states will be used by upcoming changes to produce (in case of save)
> or consume (in case of resume) the VF migration data.
> 
> Signed-off-by: Michał Winiarski <michal.winiarski@intel.com>
> ---
>  drivers/gpu/drm/xe/xe_gt_sriov_pf_control.c   | 248 ++++++++++++++++++
>  drivers/gpu/drm/xe/xe_gt_sriov_pf_control.h   |   6 +
>  .../gpu/drm/xe/xe_gt_sriov_pf_control_types.h |  14 +
>  drivers/gpu/drm/xe/xe_sriov_pf_control.c      |  96 +++++++
>  drivers/gpu/drm/xe/xe_sriov_pf_control.h      |   4 +
>  drivers/gpu/drm/xe/xe_sriov_pf_debugfs.c      |  38 +++
>  6 files changed, 406 insertions(+)
> 
> diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf_control.c b/drivers/gpu/drm/xe/xe_gt_sriov_pf_control.c
> index 2e6bd3d1fe1da..b770916e88e53 100644
> --- a/drivers/gpu/drm/xe/xe_gt_sriov_pf_control.c
> +++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf_control.c
> @@ -184,6 +184,12 @@ static const char *control_bit_to_string(enum xe_gt_sriov_control_bits bit)
>  	CASE2STR(PAUSE_SAVE_GUC);
>  	CASE2STR(PAUSE_FAILED);
>  	CASE2STR(PAUSED);
> +	CASE2STR(SAVE_WIP);
> +	CASE2STR(SAVE_FAILED);
> +	CASE2STR(SAVED);
> +	CASE2STR(RESTORE_WIP);
> +	CASE2STR(RESTORE_FAILED);
> +	CASE2STR(RESTORED);
>  	CASE2STR(RESUME_WIP);
>  	CASE2STR(RESUME_SEND_RESUME);
>  	CASE2STR(RESUME_FAILED);
> @@ -208,6 +214,8 @@ static unsigned long pf_get_default_timeout(enum xe_gt_sriov_control_bits bit)
>  	case XE_GT_SRIOV_STATE_FLR_WIP:
>  	case XE_GT_SRIOV_STATE_FLR_RESET_CONFIG:
>  		return 5 * HZ;
> +	case XE_GT_SRIOV_STATE_RESTORE_WIP:
> +		return 20 * HZ;
>  	default:
>  		return HZ;
>  	}
> @@ -329,6 +337,8 @@ static void pf_exit_vf_mismatch(struct xe_gt *gt, unsigned int vfid)
>  	pf_exit_vf_state(gt, vfid, XE_GT_SRIOV_STATE_PAUSE_FAILED);
>  	pf_exit_vf_state(gt, vfid, XE_GT_SRIOV_STATE_RESUME_FAILED);
>  	pf_exit_vf_state(gt, vfid, XE_GT_SRIOV_STATE_FLR_FAILED);
> +	pf_exit_vf_state(gt, vfid, XE_GT_SRIOV_STATE_SAVE_FAILED);
> +	pf_exit_vf_state(gt, vfid, XE_GT_SRIOV_STATE_RESTORE_FAILED);
>  }
>  
>  #define pf_enter_vf_state_machine_bug(gt, vfid) ({	\
> @@ -359,6 +369,8 @@ static void pf_queue_vf(struct xe_gt *gt, unsigned int vfid)
>  
>  static void pf_exit_vf_flr_wip(struct xe_gt *gt, unsigned int vfid);
>  static void pf_exit_vf_stop_wip(struct xe_gt *gt, unsigned int vfid);
> +static void pf_exit_vf_save_wip(struct xe_gt *gt, unsigned int vfid);
> +static void pf_exit_vf_restore_wip(struct xe_gt *gt, unsigned int vfid);
>  static void pf_exit_vf_pause_wip(struct xe_gt *gt, unsigned int vfid);
>  static void pf_exit_vf_resume_wip(struct xe_gt *gt, unsigned int vfid);
>  
> @@ -380,6 +392,8 @@ static void pf_exit_vf_wip(struct xe_gt *gt, unsigned int vfid)
>  
>  		pf_exit_vf_flr_wip(gt, vfid);
>  		pf_exit_vf_stop_wip(gt, vfid);
> +		pf_exit_vf_save_wip(gt, vfid);
> +		pf_exit_vf_restore_wip(gt, vfid);
>  		pf_exit_vf_pause_wip(gt, vfid);
>  		pf_exit_vf_resume_wip(gt, vfid);
>  
> @@ -399,6 +413,8 @@ static void pf_enter_vf_ready(struct xe_gt *gt, unsigned int vfid)
>  	pf_exit_vf_state(gt, vfid, XE_GT_SRIOV_STATE_PAUSED);
>  	pf_exit_vf_state(gt, vfid, XE_GT_SRIOV_STATE_STOPPED);
>  	pf_exit_vf_state(gt, vfid, XE_GT_SRIOV_STATE_RESUMED);
> +	pf_exit_vf_state(gt, vfid, XE_GT_SRIOV_STATE_SAVED);
> +	pf_exit_vf_state(gt, vfid, XE_GT_SRIOV_STATE_RESTORED);
>  	pf_exit_vf_mismatch(gt, vfid);
>  	pf_exit_vf_wip(gt, vfid);
>  }
> @@ -675,6 +691,8 @@ static void pf_enter_vf_resumed(struct xe_gt *gt, unsigned int vfid)
>  {
>  	pf_enter_vf_state(gt, vfid, XE_GT_SRIOV_STATE_RESUMED);
>  	pf_exit_vf_state(gt, vfid, XE_GT_SRIOV_STATE_PAUSED);
> +	pf_exit_vf_state(gt, vfid, XE_GT_SRIOV_STATE_SAVED);
> +	pf_exit_vf_state(gt, vfid, XE_GT_SRIOV_STATE_RESTORED);
>  	pf_exit_vf_mismatch(gt, vfid);
>  	pf_exit_vf_wip(gt, vfid);
>  }
> @@ -753,6 +771,16 @@ int xe_gt_sriov_pf_control_resume_vf(struct xe_gt *gt, unsigned int vfid)
>  		return -EPERM;
>  	}
>  
> +	if (pf_check_vf_state(gt, vfid, XE_GT_SRIOV_STATE_SAVE_WIP)) {
> +		xe_gt_sriov_dbg(gt, "VF%u save is in progress!\n", vfid);
> +		return -EBUSY;
> +	}
> +
> +	if (pf_check_vf_state(gt, vfid, XE_GT_SRIOV_STATE_RESTORE_WIP)) {
> +		xe_gt_sriov_dbg(gt, "VF%u restore is in progress!\n", vfid);
> +		return -EBUSY;
> +	}
> +
>  	if (!pf_enter_vf_resume_wip(gt, vfid)) {
>  		xe_gt_sriov_dbg(gt, "VF%u resume already in progress!\n", vfid);
>  		return -EALREADY;
> @@ -776,6 +804,218 @@ int xe_gt_sriov_pf_control_resume_vf(struct xe_gt *gt, unsigned int vfid)
>  	return -ECANCELED;
>  }
>  
> +static void pf_exit_vf_save_wip(struct xe_gt *gt, unsigned int vfid)
> +{
> +	pf_exit_vf_state(gt, vfid, XE_GT_SRIOV_STATE_SAVE_WIP);
> +}
> +
> +static void pf_enter_vf_saved(struct xe_gt *gt, unsigned int vfid)
> +{
> +	if (!pf_enter_vf_state(gt, vfid, XE_GT_SRIOV_STATE_SAVED))
> +		pf_enter_vf_state_machine_bug(gt, vfid);
> +
> +	xe_gt_sriov_dbg(gt, "VF%u saved!\n", vfid);

nit: you can move expect(PAUSED) here

> +
> +	pf_exit_vf_mismatch(gt, vfid);
> +	pf_exit_vf_wip(gt, vfid);
> +	pf_expect_vf_state(gt, vfid, XE_GT_SRIOV_STATE_PAUSED);
> +}
> +
> +static bool pf_handle_vf_save(struct xe_gt *gt, unsigned int vfid)
> +{
> +	if (!pf_exit_vf_state(gt, vfid, XE_GT_SRIOV_STATE_SAVE_WIP))
> +		return false;
> +
> +	pf_enter_vf_saved(gt, vfid);
> +
> +	return true;
> +}
> +
> +static bool pf_enter_vf_save_wip(struct xe_gt *gt, unsigned int vfid)
> +{
> +	if (pf_enter_vf_state(gt, vfid, XE_GT_SRIOV_STATE_SAVE_WIP)) {
> +		pf_enter_vf_wip(gt, vfid);
> +		pf_queue_vf(gt, vfid);
> +		return true;
> +	}
> +
> +	return false;
> +}
> +
> +/**
> + * xe_gt_sriov_pf_control_trigger_save_vf() - Start an SR-IOV VF migration data save sequence.
> + * @gt: the &xe_gt
> + * @vfid: the VF identifier
> + *
> + * This function is for PF only.
> + *
> + * Return: 0 on success or a negative error code on failure.
> + */
> +int xe_gt_sriov_pf_control_trigger_save_vf(struct xe_gt *gt, unsigned int vfid)
> +{
> +	if (pf_check_vf_state(gt, vfid, XE_GT_SRIOV_STATE_STOPPED)) {
> +		xe_gt_sriov_dbg(gt, "VF%u is stopped!\n", vfid);
> +		return -EPERM;
> +	}
> +
> +	if (!pf_check_vf_state(gt, vfid, XE_GT_SRIOV_STATE_PAUSED)) {
> +		xe_gt_sriov_dbg(gt, "VF%u is not paused!\n", vfid);
> +		return -EPERM;
> +	}
> +
> +	if (pf_check_vf_state(gt, vfid, XE_GT_SRIOV_STATE_RESTORE_WIP)) {
> +		xe_gt_sriov_dbg(gt, "VF%u restore is in progress!\n", vfid);
> +		return -EBUSY;
> +	}
> +
> +	if (!pf_enter_vf_save_wip(gt, vfid)) {
> +		xe_gt_sriov_dbg(gt, "VF%u save already in progress!\n", vfid);
> +		return -EALREADY;
> +	}
> +
> +	return 0;
> +}
> +
> +/**
> + * xe_gt_sriov_pf_control_finish_save_vf() - Complete a VF migration data save sequence.
> + * @gt: the &xe_gt
> + * @vfid: the VF identifier
> + *
> + * This function is for PF only.
> + *
> + * Return: 0 on success or a negative error code on failure.
> + */
> +int xe_gt_sriov_pf_control_finish_save_vf(struct xe_gt *gt, unsigned int vfid)
> +{
> +	if (!pf_expect_vf_state(gt, vfid, XE_GT_SRIOV_STATE_SAVED)) {
> +		pf_enter_vf_mismatch(gt, vfid);
> +		return -EIO;
> +	}
> +
> +	pf_expect_vf_state(gt, vfid, XE_GT_SRIOV_STATE_PAUSED);
> +
> +	return 0;
> +}
> +
> +static void pf_exit_vf_restore_wip(struct xe_gt *gt, unsigned int vfid)
> +{
> +	pf_exit_vf_state(gt, vfid, XE_GT_SRIOV_STATE_RESTORE_WIP);
> +}
> +
> +static void pf_enter_vf_restored(struct xe_gt *gt, unsigned int vfid)
> +{
> +	if (!pf_enter_vf_state(gt, vfid, XE_GT_SRIOV_STATE_RESTORED))
> +		pf_enter_vf_state_machine_bug(gt, vfid);
> +
> +	xe_gt_sriov_dbg(gt, "VF%u restored!\n", vfid);
> +
> +	pf_exit_vf_mismatch(gt, vfid);
> +	pf_exit_vf_wip(gt, vfid);
> +	pf_expect_vf_state(gt, vfid, XE_GT_SRIOV_STATE_PAUSED);
> +}
> +
> +static bool pf_handle_vf_restore(struct xe_gt *gt, unsigned int vfid)
> +{
> +	if (!pf_exit_vf_state(gt, vfid, XE_GT_SRIOV_STATE_RESTORE_WIP))
> +		return false;
> +
> +	pf_enter_vf_restored(gt, vfid);
> +
> +	return true;
> +}
> +
> +static bool pf_enter_vf_restore_wip(struct xe_gt *gt, unsigned int vfid)
> +{
> +	if (pf_enter_vf_state(gt, vfid, XE_GT_SRIOV_STATE_RESTORE_WIP)) {
> +		pf_enter_vf_wip(gt, vfid);
> +		pf_queue_vf(gt, vfid);
> +		return true;
> +	}
> +
> +	return false;
> +}
> +
> +/**
> + * xe_gt_sriov_pf_control_trigger restore_vf() - Start an SR-IOV VF migration data restore sequence.
> + * @gt: the &xe_gt
> + * @vfid: the VF identifier
> + *
> + * This function is for PF only.
> + *
> + * Return: 0 on success or a negative error code on failure.
> + */
> +int xe_gt_sriov_pf_control_trigger_restore_vf(struct xe_gt *gt, unsigned int vfid)
> +{
> +	if (pf_check_vf_state(gt, vfid, XE_GT_SRIOV_STATE_STOPPED)) {
> +		xe_gt_sriov_dbg(gt, "VF%u is stopped!\n", vfid);
> +		return -EPERM;
> +	}
> +
> +	if (!pf_check_vf_state(gt, vfid, XE_GT_SRIOV_STATE_PAUSED)) {
> +		xe_gt_sriov_dbg(gt, "VF%u is not paused!\n", vfid);
> +		return -EPERM;
> +	}
> +
> +	if (pf_check_vf_state(gt, vfid, XE_GT_SRIOV_STATE_SAVE_WIP)) {
> +		xe_gt_sriov_dbg(gt, "VF%u save is in progress!\n", vfid);
> +		return -EBUSY;
> +	}
> +
> +	if (!pf_enter_vf_restore_wip(gt, vfid)) {
> +		xe_gt_sriov_dbg(gt, "VF%u restore already in progress!\n", vfid);
> +		return -EALREADY;
> +	}
> +
> +	return 0;
> +}
> +
> +static int pf_wait_vf_restore_done(struct xe_gt *gt, unsigned int vfid)
> +{
> +	unsigned long timeout = pf_get_default_timeout(XE_GT_SRIOV_STATE_RESTORE_WIP);
> +	int err;
> +
> +	err = pf_wait_vf_wip_done(gt, vfid, timeout);
> +	if (err) {
> +		xe_gt_sriov_notice(gt, "VF%u RESTORE didn't finish in %u ms (%pe)\n",
> +				   vfid, jiffies_to_msecs(timeout), ERR_PTR(err));
> +		return err;
> +	}
> +
> +	if (!pf_expect_vf_not_state(gt, vfid, XE_GT_SRIOV_STATE_RESTORE_FAILED))
> +		return -EIO;
> +
> +	return 0;
> +}
> +
> +/**
> + * xe_gt_sriov_pf_control_finish_restore_vf() - Complete a VF migration data restore sequence.
> + * @gt: the &xe_gt
> + * @vfid: the VF identifier
> + *
> + * This function is for PF only.
> + *
> + * Return: 0 on success or a negative error code on failure.
> + */
> +int xe_gt_sriov_pf_control_finish_restore_vf(struct xe_gt *gt, unsigned int vfid)
> +{
> +	int ret;
> +
> +	if (pf_check_vf_state(gt, vfid, XE_GT_SRIOV_STATE_RESTORE_WIP)) {
> +		ret = pf_wait_vf_restore_done(gt, vfid);
> +		if (ret)
> +			return ret;
> +	}
> +
> +	if (!pf_expect_vf_state(gt, vfid, XE_GT_SRIOV_STATE_RESTORED)) {
> +		pf_enter_vf_mismatch(gt, vfid);
> +		return -EIO;
> +	}
> +
> +	pf_expect_vf_state(gt, vfid, XE_GT_SRIOV_STATE_PAUSED);
> +
> +	return 0;
> +}
> +
>  /**
>   * DOC: The VF STOP state machine
>   *
> @@ -817,6 +1057,8 @@ static void pf_enter_vf_stopped(struct xe_gt *gt, unsigned int vfid)
>  
>  	pf_exit_vf_state(gt, vfid, XE_GT_SRIOV_STATE_RESUMED);
>  	pf_exit_vf_state(gt, vfid, XE_GT_SRIOV_STATE_PAUSED);
> +	pf_exit_vf_state(gt, vfid, XE_GT_SRIOV_STATE_SAVED);
> +	pf_exit_vf_state(gt, vfid, XE_GT_SRIOV_STATE_RESTORED);
>  	pf_exit_vf_mismatch(gt, vfid);
>  	pf_exit_vf_wip(gt, vfid);
>  }
> @@ -1461,6 +1703,12 @@ static bool pf_process_vf_state_machine(struct xe_gt *gt, unsigned int vfid)
>  	if (pf_exit_vf_pause_save_guc(gt, vfid))
>  		return true;
>  
> +	if (pf_handle_vf_save(gt, vfid))
> +		return true;
> +
> +	if (pf_handle_vf_restore(gt, vfid))
> +		return true;
> +
>  	if (pf_exit_vf_resume_send_resume(gt, vfid))
>  		return true;
>  
> diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf_control.h b/drivers/gpu/drm/xe/xe_gt_sriov_pf_control.h
> index 8a72ef3778d47..abc233f6302ed 100644
> --- a/drivers/gpu/drm/xe/xe_gt_sriov_pf_control.h
> +++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf_control.h
> @@ -14,8 +14,14 @@ struct xe_gt;
>  int xe_gt_sriov_pf_control_init(struct xe_gt *gt);
>  void xe_gt_sriov_pf_control_restart(struct xe_gt *gt);
>  
> +bool xe_gt_sriov_pf_control_check_vf_data_wip(struct xe_gt *gt, unsigned int vfid);
> +
>  int xe_gt_sriov_pf_control_pause_vf(struct xe_gt *gt, unsigned int vfid);
>  int xe_gt_sriov_pf_control_resume_vf(struct xe_gt *gt, unsigned int vfid);
> +int xe_gt_sriov_pf_control_trigger_save_vf(struct xe_gt *gt, unsigned int vfid);
> +int xe_gt_sriov_pf_control_finish_save_vf(struct xe_gt *gt, unsigned int vfid);
> +int xe_gt_sriov_pf_control_trigger_restore_vf(struct xe_gt *gt, unsigned int vfid);
> +int xe_gt_sriov_pf_control_finish_restore_vf(struct xe_gt *gt, unsigned int vfid);
>  int xe_gt_sriov_pf_control_stop_vf(struct xe_gt *gt, unsigned int vfid);
>  int xe_gt_sriov_pf_control_trigger_flr(struct xe_gt *gt, unsigned int vfid);
>  int xe_gt_sriov_pf_control_sync_flr(struct xe_gt *gt, unsigned int vfid, bool sync);
> diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf_control_types.h b/drivers/gpu/drm/xe/xe_gt_sriov_pf_control_types.h
> index c80b7e77f1ad2..e113dc98b33ce 100644
> --- a/drivers/gpu/drm/xe/xe_gt_sriov_pf_control_types.h
> +++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf_control_types.h
> @@ -31,6 +31,12 @@
>   * @XE_GT_SRIOV_STATE_PAUSE_SAVE_GUC: indicates that the PF needs to save the VF GuC state.
>   * @XE_GT_SRIOV_STATE_PAUSE_FAILED: indicates that a VF pause operation has failed.
>   * @XE_GT_SRIOV_STATE_PAUSED: indicates that the VF is paused.
> + * @XE_GT_SRIOV_STATE_SAVE_WIP: indicates that VF save operation is in progress.
> + * @XE_GT_SRIOV_STATE_SAVE_FAILED: indicates that VF save operation has failed.
> + * @XE_GT_SRIOV_STATE_SAVED: indicates that VF data is saved.
> + * @XE_GT_SRIOV_STATE_RESTORE_WIP: indicates that VF restore operation is in progress.
> + * @XE_GT_SRIOV_STATE_RESTORE_FAILED: indicates that VF restore operation has failed.
> + * @XE_GT_SRIOV_STATE_RESTORED: indicates that VF data is restored.
>   * @XE_GT_SRIOV_STATE_RESUME_WIP: indicates the a VF resume operation is in progress.
>   * @XE_GT_SRIOV_STATE_RESUME_SEND_RESUME: indicates that the PF is about to send RESUME command.
>   * @XE_GT_SRIOV_STATE_RESUME_FAILED: indicates that a VF resume operation has failed.
> @@ -63,6 +69,14 @@ enum xe_gt_sriov_control_bits {
>  	XE_GT_SRIOV_STATE_PAUSE_FAILED,
>  	XE_GT_SRIOV_STATE_PAUSED,
>  
> +	XE_GT_SRIOV_STATE_SAVE_WIP,
> +	XE_GT_SRIOV_STATE_SAVE_FAILED,
> +	XE_GT_SRIOV_STATE_SAVED,
> +
> +	XE_GT_SRIOV_STATE_RESTORE_WIP,
> +	XE_GT_SRIOV_STATE_RESTORE_FAILED,
> +	XE_GT_SRIOV_STATE_RESTORED,
> +
>  	XE_GT_SRIOV_STATE_RESUME_WIP,
>  	XE_GT_SRIOV_STATE_RESUME_SEND_RESUME,
>  	XE_GT_SRIOV_STATE_RESUME_FAILED,

it is easier to understand those states after patch 04/26 with diagrams,
and while there are small and hard to avoid overlaps between 03/26 and 04/26
the patch itself LGTM, so

Reviewed-by: Michal Wajdeczko <michal.wajdeczko@intel.com>

> diff --git a/drivers/gpu/drm/xe/xe_sriov_pf_control.c b/drivers/gpu/drm/xe/xe_sriov_pf_control.c
> index 416d00a03fbb7..8d8a01faf5291 100644
> --- a/drivers/gpu/drm/xe/xe_sriov_pf_control.c
> +++ b/drivers/gpu/drm/xe/xe_sriov_pf_control.c
> @@ -149,3 +149,99 @@ int xe_sriov_pf_control_sync_flr(struct xe_device *xe, unsigned int vfid)
>  
>  	return 0;
>  }
> +
> +/**
> + * xe_sriov_pf_control_trigger_save_vf - Start a VF migration data SAVE sequence on all GTs.
> + * @xe: the &xe_device
> + * @vfid: the VF identifier
> + *
> + * This function is for PF only.
> + *
> + * Return: 0 on success or a negative error code on failure.
> + */
> +int xe_sriov_pf_control_trigger_save_vf(struct xe_device *xe, unsigned int vfid)
> +{
> +	struct xe_gt *gt;
> +	unsigned int id;
> +	int ret;
> +
> +	for_each_gt(gt, xe, id) {
> +		ret = xe_gt_sriov_pf_control_trigger_save_vf(gt, vfid);
> +		if (ret)
> +			return ret;
> +	}
> +
> +	return 0;
> +}
> +
> +/**
> + * xe_sriov_pf_control_finish_save_vf - Complete a VF migration data SAVE sequence on all GTs.
> + * @xe: the &xe_device
> + * @vfid: the VF identifier
> + *
> + * This function is for PF only.
> + *
> + * Return: 0 on success or a negative error code on failure.
> + */
> +int xe_sriov_pf_control_finish_save_vf(struct xe_device *xe, unsigned int vfid)
> +{
> +	struct xe_gt *gt;
> +	unsigned int id;
> +	int ret;
> +
> +	for_each_gt(gt, xe, id) {
> +		ret = xe_gt_sriov_pf_control_finish_save_vf(gt, vfid);
> +		if (ret)
> +			break;
> +	}
> +
> +	return ret;
> +}
> +
> +/**
> + * xe_sriov_pf_control_trigger_restore_vf - Start a VF migration data RESTORE sequence on all GTs.
> + * @xe: the &xe_device
> + * @vfid: the VF identifier
> + *
> + * This function is for PF only.
> + *
> + * Return: 0 on success or a negative error code on failure.
> + */
> +int xe_sriov_pf_control_trigger_restore_vf(struct xe_device *xe, unsigned int vfid)
> +{
> +	struct xe_gt *gt;
> +	unsigned int id;
> +	int ret;
> +
> +	for_each_gt(gt, xe, id) {
> +		ret = xe_gt_sriov_pf_control_trigger_restore_vf(gt, vfid);
> +		if (ret)
> +			return ret;
> +	}
> +
> +	return ret;
> +}
> +
> +/**
> + * xe_sriov_pf_control_wait_restore_vf - Complete a VF migration data RESTORE sequence in all GTs.
> + * @xe: the &xe_device
> + * @vfid: the VF identifier
> + *
> + * This function is for PF only.
> + *
> + * Return: 0 on success or a negative error code on failure.
> + */
> +int xe_sriov_pf_control_finish_restore_vf(struct xe_device *xe, unsigned int vfid)
> +{
> +	struct xe_gt *gt;
> +	unsigned int id;
> +	int ret;
> +
> +	for_each_gt(gt, xe, id) {
> +		ret = xe_gt_sriov_pf_control_finish_restore_vf(gt, vfid);
> +		if (ret)
> +			break;
> +	}
> +
> +	return ret;
> +}
> diff --git a/drivers/gpu/drm/xe/xe_sriov_pf_control.h b/drivers/gpu/drm/xe/xe_sriov_pf_control.h
> index 2d52d0ac1b28f..30318c1fba34e 100644
> --- a/drivers/gpu/drm/xe/xe_sriov_pf_control.h
> +++ b/drivers/gpu/drm/xe/xe_sriov_pf_control.h
> @@ -13,5 +13,9 @@ int xe_sriov_pf_control_resume_vf(struct xe_device *xe, unsigned int vfid);
>  int xe_sriov_pf_control_stop_vf(struct xe_device *xe, unsigned int vfid);
>  int xe_sriov_pf_control_reset_vf(struct xe_device *xe, unsigned int vfid);
>  int xe_sriov_pf_control_sync_flr(struct xe_device *xe, unsigned int vfid);
> +int xe_sriov_pf_control_trigger_save_vf(struct xe_device *xe, unsigned int vfid);
> +int xe_sriov_pf_control_finish_save_vf(struct xe_device *xe, unsigned int vfid);
> +int xe_sriov_pf_control_trigger_restore_vf(struct xe_device *xe, unsigned int vfid);
> +int xe_sriov_pf_control_finish_restore_vf(struct xe_device *xe, unsigned int vfid);
>  
>  #endif
> diff --git a/drivers/gpu/drm/xe/xe_sriov_pf_debugfs.c b/drivers/gpu/drm/xe/xe_sriov_pf_debugfs.c
> index a81aa05c55326..e0e6340c49106 100644
> --- a/drivers/gpu/drm/xe/xe_sriov_pf_debugfs.c
> +++ b/drivers/gpu/drm/xe/xe_sriov_pf_debugfs.c
> @@ -136,11 +136,31 @@ static void pf_populate_pf(struct xe_device *xe, struct dentry *pfdent)
>   *      │   │   ├── reset
>   *      │   │   ├── resume
>   *      │   │   ├── stop
> + *      │   │   ├── save
> + *      │   │   ├── restore
>   *      │   │   :
>   *      │   ├── vf2
>   *      │   │   ├── ...
>   */
>  
> +static int from_file_read_to_vf_call(struct seq_file *s,
> +				     int (*call)(struct xe_device *, unsigned int))
> +{
> +	struct dentry *dent = file_dentry(s->file)->d_parent;
> +	struct xe_device *xe = extract_xe(dent);
> +	unsigned int vfid = extract_vfid(dent);
> +	int ret;
> +
> +	xe_pm_runtime_get(xe);
> +	ret = call(xe, vfid);
> +	xe_pm_runtime_put(xe);
> +
> +	if (ret < 0)
> +		return ret;
> +
> +	return 0;
> +}
> +
>  static ssize_t from_file_write_to_vf_call(struct file *file, const char __user *userbuf,
>  					  size_t count, loff_t *ppos,
>  					  int (*call)(struct xe_device *, unsigned int))
> @@ -179,10 +199,26 @@ static ssize_t OP##_write(struct file *file, const char __user *userbuf,	\
>  }										\
>  DEFINE_SHOW_STORE_ATTRIBUTE(OP)
>  
> +#define DEFINE_VF_CONTROL_ATTRIBUTE_RW(OP)					\
> +static int OP##_show(struct seq_file *s, void *unused)				\
> +{										\
> +	return from_file_read_to_vf_call(s,					\
> +					 xe_sriov_pf_control_finish_##OP);	\
> +}										\
> +static ssize_t OP##_write(struct file *file, const char __user *userbuf,	\
> +			  size_t count, loff_t *ppos)				\
> +{										\
> +	return from_file_write_to_vf_call(file, userbuf, count, ppos,		\
> +					  xe_sriov_pf_control_trigger_##OP);	\
> +}										\
> +DEFINE_SHOW_STORE_ATTRIBUTE(OP)
> +
>  DEFINE_VF_CONTROL_ATTRIBUTE(pause_vf);
>  DEFINE_VF_CONTROL_ATTRIBUTE(resume_vf);
>  DEFINE_VF_CONTROL_ATTRIBUTE(stop_vf);
>  DEFINE_VF_CONTROL_ATTRIBUTE(reset_vf);
> +DEFINE_VF_CONTROL_ATTRIBUTE_RW(save_vf);
> +DEFINE_VF_CONTROL_ATTRIBUTE_RW(restore_vf);
>  
>  static void pf_populate_vf(struct xe_device *xe, struct dentry *vfdent)
>  {
> @@ -190,6 +226,8 @@ static void pf_populate_vf(struct xe_device *xe, struct dentry *vfdent)
>  	debugfs_create_file("resume", 0200, vfdent, xe, &resume_vf_fops);
>  	debugfs_create_file("stop", 0200, vfdent, xe, &stop_vf_fops);
>  	debugfs_create_file("reset", 0200, vfdent, xe, &reset_vf_fops);
> +	debugfs_create_file("save", 0600, vfdent, xe, &save_vf_fops);
> +	debugfs_create_file("restore", 0600, vfdent, xe, &restore_vf_fops);
>  }
>  
>  static void pf_populate_with_tiles(struct xe_device *xe, struct dentry *dent, unsigned int vfid)


  reply	other threads:[~2025-10-22 22:31 UTC|newest]

Thread overview: 72+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-10-21 22:41 [PATCH v2 00/26] vfio/xe: Add driver variant for Xe VF migration Michał Winiarski
2025-10-21 22:41 ` [PATCH v2 01/26] drm/xe/pf: Remove GuC version check for migration support Michał Winiarski
2025-10-28  2:33   ` Tian, Kevin
2025-10-28  8:06     ` Winiarski, Michal
2025-10-21 22:41 ` [PATCH v2 02/26] drm/xe: Move migration support to device-level struct Michał Winiarski
2025-10-21 22:41 ` [PATCH v2 03/26] drm/xe/pf: Add save/restore control state stubs and connect to debugfs Michał Winiarski
2025-10-22 22:31   ` Michal Wajdeczko [this message]
2025-10-27 12:02     ` Michał Winiarski
2025-10-28  3:06   ` Tian, Kevin
2025-10-28  8:02     ` Michal Wajdeczko
2025-10-21 22:41 ` [PATCH v2 04/26] drm/xe/pf: Add data structures and handlers for migration rings Michał Winiarski
2025-10-22 22:06   ` Michal Wajdeczko
2025-10-27 12:33     ` Michał Winiarski
2025-10-21 22:41 ` [PATCH v2 05/26] drm/xe/pf: Add helpers for migration data allocation / free Michał Winiarski
2025-10-22 22:18   ` Michal Wajdeczko
2025-10-27 12:47     ` Michał Winiarski
2025-10-21 22:41 ` [PATCH v2 06/26] drm/xe/pf: Add support for encap/decap of bitstream to/from packet Michał Winiarski
2025-10-22 22:34   ` Michal Wajdeczko
2025-10-27 13:27     ` Michał Winiarski
2025-10-21 22:41 ` [PATCH v2 07/26] drm/xe/pf: Add minimalistic migration descriptor Michał Winiarski
2025-10-22 22:49   ` Michal Wajdeczko
2025-10-27 14:52     ` Michał Winiarski
2025-10-21 22:41 ` [PATCH v2 08/26] drm/xe/pf: Expose VF migration data size over debugfs Michał Winiarski
2025-10-22 23:02   ` Michal Wajdeczko
2025-10-21 22:41 ` [PATCH v2 09/26] drm/xe: Add sa/guc_buf_cache sync interface Michał Winiarski
2025-10-22 23:05   ` Michal Wajdeczko
2025-10-21 22:41 ` [PATCH v2 10/26] drm/xe: Allow the caller to pass guc_buf_cache size Michał Winiarski
2025-10-22 23:13   ` Michal Wajdeczko
2025-10-21 22:41 ` [PATCH v2 11/26] drm/xe/pf: Increase PF GuC Buffer Cache size and use it for VF migration Michał Winiarski
2025-10-23 17:37   ` Michal Wajdeczko
2025-10-28 10:46     ` Michał Winiarski
2025-10-21 22:41 ` [PATCH v2 12/26] drm/xe/pf: Remove GuC migration data save/restore from GT debugfs Michał Winiarski
2025-10-21 22:41 ` [PATCH v2 13/26] drm/xe/pf: Don't save GuC VF migration data on pause Michał Winiarski
2025-10-21 22:41 ` [PATCH v2 14/26] drm/xe/pf: Switch VF migration GuC save/restore to struct migration data Michał Winiarski
2025-10-21 22:41 ` [PATCH v2 15/26] drm/xe/pf: Handle GuC migration data as part of PF control Michał Winiarski
2025-10-23 20:39   ` Michal Wajdeczko
2025-10-28 13:04     ` Michał Winiarski
2025-10-21 22:41 ` [PATCH v2 16/26] drm/xe/pf: Add helpers for VF GGTT migration data handling Michał Winiarski
2025-10-23 21:50   ` Michal Wajdeczko
2025-10-28 17:03     ` Michał Winiarski
2025-10-28  3:22   ` Tian, Kevin
2025-10-28  7:38     ` Michal Wajdeczko
2025-10-21 22:41 ` [PATCH v2 17/26] drm/xe/pf: Handle GGTT migration data as part of PF control Michał Winiarski
2025-10-21 22:41 ` [PATCH v2 18/26] drm/xe/pf: Add helpers for VF MMIO migration data handling Michał Winiarski
2025-10-23 22:10   ` Michal Wajdeczko
2025-10-28 23:37     ` Michał Winiarski
2025-10-21 22:41 ` [PATCH v2 19/26] drm/xe/pf: Handle MMIO migration data as part of PF control Michał Winiarski
2025-10-21 22:41 ` [PATCH v2 20/26] drm/xe/pf: Add helper to retrieve VF's LMEM object Michał Winiarski
2025-10-23 20:25   ` Michal Wajdeczko
2025-10-28 23:40     ` Michał Winiarski
2025-10-21 22:41 ` [PATCH v2 21/26] drm/xe/migrate: Add function to copy of VRAM data in chunks Michał Winiarski
2025-10-23 19:29   ` Michal Wajdeczko
2025-10-30  6:07     ` Laguna, Lukasz
2025-10-21 22:41 ` [PATCH v2 22/26] drm/xe/pf: Handle VRAM migration data as part of PF control Michał Winiarski
2025-10-23 11:44   ` kernel test robot
2025-10-23 19:54   ` Michal Wajdeczko
2025-10-29  8:54     ` Michał Winiarski
2025-10-21 22:41 ` [PATCH v2 23/26] drm/xe/pf: Add wait helper for VF FLR Michał Winiarski
2025-10-21 22:41 ` [PATCH v2 24/26] drm/xe/pf: Enable SR-IOV VF migration for PTL and BMG Michał Winiarski
2025-10-23 20:15   ` Michal Wajdeczko
2025-10-21 22:41 ` [PATCH v2 25/26] drm/xe/pf: Export helpers for VFIO Michał Winiarski
2025-10-28  3:28   ` Tian, Kevin
2025-10-21 22:41 ` [PATCH v2 26/26] vfio/xe: Add vendor-specific vfio_pci driver for Intel graphics Michał Winiarski
2025-10-22  7:12   ` Christoph Hellwig
2025-10-22  8:52     ` Michał Winiarski
2025-10-22  8:54       ` Christoph Hellwig
2025-10-22  9:12         ` Michał Winiarski
2025-10-22 11:33           ` Jason Gunthorpe
2025-10-22 13:27             ` Michał Winiarski
2025-10-27  7:24   ` Tian, Kevin
2025-10-29 20:46     ` Winiarski, Michal
2025-10-27  7:26   ` Tian, Kevin

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=fdf1ebb7-e8dd-4228-9b13-588e2e617b15@intel.com \
    --to=michal.wajdeczko@intel.com \
    --cc=airlied@gmail.com \
    --cc=alex.williamson@redhat.com \
    --cc=dri-devel@lists.freedesktop.org \
    --cc=intel-xe@lists.freedesktop.org \
    --cc=jani.nikula@linux.intel.com \
    --cc=jgg@ziepe.ca \
    --cc=joonas.lahtinen@linux.intel.com \
    --cc=kevin.tian@intel.com \
    --cc=kvm@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=lucas.demarchi@intel.com \
    --cc=lukasz.laguna@intel.com \
    --cc=matthew.brost@intel.com \
    --cc=michal.winiarski@intel.com \
    --cc=rodrigo.vivi@intel.com \
    --cc=simona@ffwll.ch \
    --cc=thomas.hellstrom@linux.intel.com \
    --cc=tursulin@ursulin.net \
    --cc=yishaih@nvidia.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox