Commit ed46ff0d authored by Michał Winiarski's avatar Michał Winiarski
Browse files

drm/xe/pf: Add save/restore control state stubs and connect to debugfs 



The states will be used by upcoming changes to produce (in case of save)
or consume (in case of resume) the VF migration data.

Reviewed-by: default avatarMichal Wajdeczko <michal.wajdeczko@intel.com>
Link: https://patch.msgid.link/20251112132220.516975-5-michal.winiarski@intel.com


Signed-off-by: default avatarMichał Winiarski <michal.winiarski@intel.com>
parent cd0ffc8d

drivers/gpu/drm/xe/xe_gt_sriov_pf_control.c

+248 −0
Original line number Diff line number Diff line
@@ -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);



	pf_expect_vf_state(gt, vfid, XE_GT_SRIOV_STATE_PAUSED);

	pf_exit_vf_mismatch(gt, vfid);

	pf_exit_vf_wip(gt, vfid);

}



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_expect_vf_state(gt, vfid, XE_GT_SRIOV_STATE_PAUSED);

	pf_exit_vf_mismatch(gt, vfid);

	pf_exit_vf_wip(gt, vfid);

}



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);

}
@@ -1463,6 +1705,12 @@ 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;

drivers/gpu/drm/xe/xe_gt_sriov_pf_control.h

+4 −0
Original line number Diff line number Diff line
@@ -16,6 +16,10 @@ void xe_gt_sriov_pf_control_restart(struct xe_gt *gt); 


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);

drivers/gpu/drm/xe/xe_gt_sriov_pf_control_types.h

+14 −0
Original line number Diff line number Diff line
@@ -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,

drivers/gpu/drm/xe/xe_sriov_pf_control.c

+96 −0
Original line number Diff line number Diff line
@@ -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 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 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 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_finish_restore_vf() - Complete 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_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;

}

drivers/gpu/drm/xe/xe_sriov_pf_control.h

+4 −0
Original line number Diff line number Diff line
@@ -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