drm/xe/pf: Add data structures and handlers for migration rings

Migration data is queued in a per-GT ptr_ring to decouple the worker
responsible for handling the data transfer from the .read() and .write()
syscalls.
Add the data structures and handlers that will be used in future
commits.

Reviewed-by: Michal Wajdeczko <[e-mail]>
Link: https://patch.msgid.link/[e-mail]
Signed-off-by: Michał Winiarski <[e-mail]>

drivers/gpu/drm/xe/xe_gt_sriov_pf_control.c

···
 #include "xe_gt_sriov_printk.h"
 #include "xe_guc_ct.h"
 #include "xe_sriov.h"
+#include "xe_sriov_packet_types.h"
 #include "xe_sriov_pf_control.h"
+#include "xe_sriov_pf_migration.h"
 #include "xe_sriov_pf_service.h"
 #include "xe_tile.h"
 
···
 	CASE2STR(PAUSE_FAILED);
 	CASE2STR(PAUSED);
 	CASE2STR(SAVE_WIP);
+	CASE2STR(SAVE_PROCESS_DATA);
+	CASE2STR(SAVE_WAIT_DATA);
+	CASE2STR(SAVE_DATA_DONE);
 	CASE2STR(SAVE_FAILED);
 	CASE2STR(SAVED);
 	CASE2STR(RESTORE_WIP);
+	CASE2STR(RESTORE_PROCESS_DATA);
+	CASE2STR(RESTORE_WAIT_DATA);
+	CASE2STR(RESTORE_DATA_DONE);
 	CASE2STR(RESTORE_FAILED);
 	CASE2STR(RESTORED);
 	CASE2STR(RESUME_WIP);
···
 	return -ECANCELED;
 }
 
+/**
+ * DOC: The VF SAVE state machine
+ *
+ * SAVE extends the PAUSED state.
+ *
+ * The VF SAVE state machine looks like::
+ *
+ *  ....PAUSED....................................................
+ *  :                                                            :
+ *  :     (O)<---------o                                         :
+ *  :      |            \                                        :
+ *  :    save          (SAVED)    (SAVE_FAILED)                  :
+ *  :      |               ^           ^                         :
+ *  :      |               |           |                         :
+ *  :  ....V...............o...........o......SAVE_WIP.........  :
+ *  :  :   |               |           |                      :  :
+ *  :  :   |             empty         |                      :  :
+ *  :  :   |               |           |                      :  :
+ *  :  :   |               |           |                      :  :
+ *  :  :   |           DATA_DONE       |                      :  :
+ *  :  :   |               ^           |                      :  :
+ *  :  :   |               |        error                     :  :
+ *  :  :   |            no_data       /                       :  :
+ *  :  :   |              /          /                        :  :
+ *  :  :   |             /          /                         :  :
+ *  :  :   |            /          /                          :  :
+ *  :  :   o---------->PROCESS_DATA<----consume               :  :
+ *  :  :                \                      \              :  :
+ *  :  :                 \                      \             :  :
+ *  :  :                  \                      \            :  :
+ *  :  :                   ring_full----->WAIT_DATA           :  :
+ *  :  :                                                      :  :
+ *  :  :......................................................:  :
+ *  :............................................................:
+ *
+ * For the full state machine view, see `The VF state machine`_.
+ */
+
 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);
+	if (pf_exit_vf_state(gt, vfid, XE_GT_SRIOV_STATE_SAVE_WIP)) {
+		pf_escape_vf_state(gt, vfid, XE_GT_SRIOV_STATE_SAVE_PROCESS_DATA);
+		pf_escape_vf_state(gt, vfid, XE_GT_SRIOV_STATE_SAVE_WAIT_DATA);
+		pf_escape_vf_state(gt, vfid, XE_GT_SRIOV_STATE_SAVE_DATA_DONE);
+	}
 }
 
 static void pf_enter_vf_saved(struct xe_gt *gt, unsigned int vfid)
···
 	pf_exit_vf_wip(gt, vfid);
 }
 
+static void pf_enter_vf_save_failed(struct xe_gt *gt, unsigned int vfid)
+{
+	if (!pf_enter_vf_state(gt, vfid, XE_GT_SRIOV_STATE_SAVE_FAILED))
+		pf_enter_vf_state_machine_bug(gt, vfid);
+
+	wake_up_all(xe_sriov_pf_migration_waitqueue(gt_to_xe(gt), vfid));
+
+	pf_exit_vf_wip(gt, vfid);
+}
+
+static int pf_handle_vf_save_data(struct xe_gt *gt, unsigned int vfid)
+{
+	return 0;
+}
+
 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))
+	int ret;
+
+	if (!pf_exit_vf_state(gt, vfid, XE_GT_SRIOV_STATE_SAVE_PROCESS_DATA))
 		return false;
 
-	pf_enter_vf_saved(gt, vfid);
+	if (xe_gt_sriov_pf_migration_ring_full(gt, vfid)) {
+		pf_enter_vf_state(gt, vfid, XE_GT_SRIOV_STATE_SAVE_WAIT_DATA);
+		return true;
+	}
+
+	ret = pf_handle_vf_save_data(gt, vfid);
+	if (ret == -EAGAIN)
+		pf_enter_vf_state(gt, vfid, XE_GT_SRIOV_STATE_SAVE_PROCESS_DATA);
+	else if (ret)
+		pf_enter_vf_save_failed(gt, vfid);
+	else
+		pf_enter_vf_state(gt, vfid, XE_GT_SRIOV_STATE_SAVE_DATA_DONE);
 
 	return true;
+}
+
+static void pf_exit_vf_save_wait_data(struct xe_gt *gt, unsigned int vfid)
+{
+	if (!pf_exit_vf_state(gt, vfid, XE_GT_SRIOV_STATE_SAVE_WAIT_DATA))
+		return;
+
+	pf_enter_vf_state(gt, vfid, XE_GT_SRIOV_STATE_SAVE_PROCESS_DATA);
+	pf_queue_vf(gt, vfid);
 }
 
 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_enter_vf_state(gt, vfid, XE_GT_SRIOV_STATE_SAVE_PROCESS_DATA);
 		pf_queue_vf(gt, vfid);
 		return true;
 	}
 
 	return false;
+}
+
+/**
+ * xe_gt_sriov_pf_control_check_save_data_done() - Check if all save migration data was produced.
+ * @gt: the &xe_gt
+ * @vfid: the VF identifier
+ *
+ * This function is for PF only.
+ *
+ * Return: true if all migration data was produced, false otherwise.
+ */
+bool xe_gt_sriov_pf_control_check_save_data_done(struct xe_gt *gt, unsigned int vfid)
+{
+	return pf_check_vf_state(gt, vfid, XE_GT_SRIOV_STATE_SAVE_DATA_DONE);
+}
+
+/**
+ * xe_gt_sriov_pf_control_check_save_failed() - Check if save processing has failed.
+ * @gt: the &xe_gt
+ * @vfid: the VF identifier
+ *
+ * This function is for PF only.
+ *
+ * Return: true if save processing failed, false otherwise.
+ */
+bool xe_gt_sriov_pf_control_check_save_failed(struct xe_gt *gt, unsigned int vfid)
+{
+	return pf_check_vf_state(gt, vfid, XE_GT_SRIOV_STATE_SAVE_FAILED);
+}
+
+/**
+ * xe_gt_sriov_pf_control_process_save_data() - Queue VF save migration data processing.
+ * @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_process_save_data(struct xe_gt *gt, unsigned int vfid)
+{
+	if (!pf_expect_vf_not_state(gt, vfid, XE_GT_SRIOV_STATE_SAVE_FAILED))
+		return -EIO;
+
+	pf_exit_vf_save_wait_data(gt, vfid);
+
+	return 0;
 }
 
 /**
···
  */
 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);
+	if (!pf_check_vf_state(gt, vfid, XE_GT_SRIOV_STATE_SAVE_DATA_DONE)) {
+		xe_gt_sriov_err(gt, "VF%u save is still in progress!\n", vfid);
 		return -EIO;
 	}
 
 	pf_expect_vf_state(gt, vfid, XE_GT_SRIOV_STATE_PAUSED);
+	pf_exit_vf_state(gt, vfid, XE_GT_SRIOV_STATE_SAVE_DATA_DONE);
+	pf_enter_vf_saved(gt, vfid);
 
 	return 0;
 }
 
+/**
+ * DOC: The VF RESTORE state machine
+ *
+ * RESTORE extends the PAUSED state.
+ *
+ * The VF RESTORE state machine looks like::
+ *
+ *  ....PAUSED....................................................
+ *  :                                                            :
+ *  :     (O)<---------o                                         :
+ *  :      |            \                                        :
+ *  :    restore      (RESTORED)  (RESTORE_FAILED)               :
+ *  :      |               ^           ^                         :
+ *  :      |               |           |                         :
+ *  :  ....V...............o...........o......RESTORE_WIP......  :
+ *  :  :   |               |           |                      :  :
+ *  :  :   |             empty         |                      :  :
+ *  :  :   |               |           |                      :  :
+ *  :  :   |               |           |                      :  :
+ *  :  :   |           DATA_DONE       |                      :  :
+ *  :  :   |               ^           |                      :  :
+ *  :  :   |               |        error                     :  :
+ *  :  :   |           trailer        /                       :  :
+ *  :  :   |              /          /                        :  :
+ *  :  :   |             /          /                         :  :
+ *  :  :   |            /          /                          :  :
+ *  :  :   o---------->PROCESS_DATA<----produce               :  :
+ *  :  :                \                      \              :  :
+ *  :  :                 \                      \             :  :
+ *  :  :                  \                      \            :  :
+ *  :  :                   ring_empty---->WAIT_DATA           :  :
+ *  :  :                                                      :  :
+ *  :  :......................................................:  :
+ *  :............................................................:
+ *
+ * For the full state machine view, see `The VF state machine`_.
+ */
+
 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);
+	if (pf_exit_vf_state(gt, vfid, XE_GT_SRIOV_STATE_RESTORE_WIP)) {
+		pf_escape_vf_state(gt, vfid, XE_GT_SRIOV_STATE_RESTORE_PROCESS_DATA);
+		pf_escape_vf_state(gt, vfid, XE_GT_SRIOV_STATE_RESTORE_WAIT_DATA);
+		pf_escape_vf_state(gt, vfid, XE_GT_SRIOV_STATE_RESTORE_DATA_DONE);
+	}
 }
 
 static void pf_enter_vf_restored(struct xe_gt *gt, unsigned int vfid)
···
 	pf_exit_vf_wip(gt, vfid);
 }
 
+static void pf_enter_vf_restore_failed(struct xe_gt *gt, unsigned int vfid)
+{
+	if (!pf_enter_vf_state(gt, vfid, XE_GT_SRIOV_STATE_RESTORE_FAILED))
+		pf_enter_vf_state_machine_bug(gt, vfid);
+
+	wake_up_all(xe_sriov_pf_migration_waitqueue(gt_to_xe(gt), vfid));
+
+	pf_exit_vf_wip(gt, vfid);
+}
+
+static int pf_handle_vf_restore_data(struct xe_gt *gt, unsigned int vfid)
+{
+	struct xe_sriov_packet *data = xe_gt_sriov_pf_migration_restore_consume(gt, vfid);
+
+	xe_gt_sriov_notice(gt, "Skipping VF%u unknown data type: %d\n", vfid, data->hdr.type);
+
+	return 0;
+}
+
 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))
+	int ret;
+
+	if (!pf_exit_vf_state(gt, vfid, XE_GT_SRIOV_STATE_RESTORE_PROCESS_DATA))
 		return false;
 
-	pf_enter_vf_restored(gt, vfid);
+	if (xe_gt_sriov_pf_migration_ring_empty(gt, vfid)) {
+		if (pf_exit_vf_state(gt, vfid, XE_GT_SRIOV_STATE_RESTORE_DATA_DONE))
+			pf_enter_vf_restored(gt, vfid);
+		else
+			pf_enter_vf_state(gt, vfid, XE_GT_SRIOV_STATE_RESTORE_WAIT_DATA);
+
+		return true;
+	}
+
+	ret = pf_handle_vf_restore_data(gt, vfid);
+	if (ret)
+		pf_enter_vf_restore_failed(gt, vfid);
+	else
+		pf_enter_vf_state(gt, vfid, XE_GT_SRIOV_STATE_RESTORE_PROCESS_DATA);
 
 	return true;
+}
+
+static void pf_exit_vf_restore_wait_data(struct xe_gt *gt, unsigned int vfid)
+{
+	if (!pf_exit_vf_state(gt, vfid, XE_GT_SRIOV_STATE_RESTORE_WAIT_DATA))
+		return;
+
+	pf_enter_vf_state(gt, vfid, XE_GT_SRIOV_STATE_RESTORE_PROCESS_DATA);
+	pf_queue_vf(gt, vfid);
 }
 
 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_enter_vf_state(gt, vfid, XE_GT_SRIOV_STATE_RESTORE_PROCESS_DATA);
 		pf_queue_vf(gt, vfid);
 		return true;
 	}
 
 	return false;
+}
+
+/**
+ * xe_gt_sriov_pf_control_check_restore_failed() - Check if restore processing has failed.
+ * @gt: the &xe_gt
+ * @vfid: the VF identifier
+ *
+ * This function is for PF only.
+ *
+ * Return: true if restore processing failed, false otherwise.
+ */
+bool xe_gt_sriov_pf_control_check_restore_failed(struct xe_gt *gt, unsigned int vfid)
+{
+	return pf_check_vf_state(gt, vfid, XE_GT_SRIOV_STATE_RESTORE_FAILED);
+}
+
+/**
+ * xe_gt_sriov_pf_control_restore_data_done() - Indicate the end of VF migration data stream.
+ * @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_restore_data_done(struct xe_gt *gt, unsigned int vfid)
+{
+	if (!pf_enter_vf_state(gt, vfid, XE_GT_SRIOV_STATE_RESTORE_DATA_DONE)) {
+		pf_enter_vf_state_machine_bug(gt, vfid);
+		return -EIO;
+	}
+
+	return xe_gt_sriov_pf_control_process_restore_data(gt, vfid);
+}
+
+/**
+ * xe_gt_sriov_pf_control_process_restore_data() - Queue VF restore migration data processing.
+ * @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_process_restore_data(struct xe_gt *gt, unsigned int vfid)
+{
+	if (!pf_expect_vf_not_state(gt, vfid, XE_GT_SRIOV_STATE_RESTORE_FAILED))
+		return -EIO;
+
+	pf_exit_vf_restore_wait_data(gt, vfid);
+
+	return 0;
 }
 
 /**
···
 {
 	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;
-	}
+	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);
···
 	if (pf_exit_vf_pause_save_guc(gt, vfid))
 		return true;
 
+	if (pf_check_vf_state(gt, vfid, XE_GT_SRIOV_STATE_SAVE_WAIT_DATA)) {
+		xe_gt_sriov_dbg_verbose(gt, "VF%u in %s\n", vfid,
+					control_bit_to_string(XE_GT_SRIOV_STATE_SAVE_WAIT_DATA));
+		return false;
+	}
+
 	if (pf_handle_vf_save(gt, vfid))
 		return true;
+
+	if (pf_check_vf_state(gt, vfid, XE_GT_SRIOV_STATE_RESTORE_WAIT_DATA)) {
+		xe_gt_sriov_dbg_verbose(gt, "VF%u in %s\n", vfid,
+					control_bit_to_string(XE_GT_SRIOV_STATE_RESTORE_WAIT_DATA));
+		return false;
+	}
 
 	if (pf_handle_vf_restore(gt, vfid))
 		return true;

drivers/gpu/drm/xe/xe_gt_sriov_pf_control.h

···
 
 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);
+bool xe_gt_sriov_pf_control_check_save_data_done(struct xe_gt *gt, unsigned int vfid);
+bool xe_gt_sriov_pf_control_check_save_failed(struct xe_gt *gt, unsigned int vfid);
+int xe_gt_sriov_pf_control_process_save_data(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_restore_data_done(struct xe_gt *gt, unsigned int vfid);
+bool xe_gt_sriov_pf_control_check_restore_failed(struct xe_gt *gt, unsigned int vfid);
+int xe_gt_sriov_pf_control_process_restore_data(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);

drivers/gpu/drm/xe/xe_gt_sriov_pf_control_types.h

···
  * @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_PROCESS_DATA: indicates that VF migration data is being produced.
+ * @XE_GT_SRIOV_STATE_SAVE_WAIT_DATA: indicates that PF awaits for space in migration data ring.
+ * @XE_GT_SRIOV_STATE_SAVE_DATA_DONE: indicates that all migration data was produced by Xe.
  * @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_PROCESS_DATA: indicates that VF migration data is being consumed.
+ * @XE_GT_SRIOV_STATE_RESTORE_WAIT_DATA: indicates that PF awaits for data in migration data ring.
+ * @XE_GT_SRIOV_STATE_RESTORE_DATA_DONE: indicates that all migration data was produced by the user.
  * @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_PAUSED,
 
 	XE_GT_SRIOV_STATE_SAVE_WIP,
+	XE_GT_SRIOV_STATE_SAVE_PROCESS_DATA,
+	XE_GT_SRIOV_STATE_SAVE_WAIT_DATA,
+	XE_GT_SRIOV_STATE_SAVE_DATA_DONE,
 	XE_GT_SRIOV_STATE_SAVE_FAILED,
 	XE_GT_SRIOV_STATE_SAVED,
 
 	XE_GT_SRIOV_STATE_RESTORE_WIP,
+	XE_GT_SRIOV_STATE_RESTORE_PROCESS_DATA,
+	XE_GT_SRIOV_STATE_RESTORE_WAIT_DATA,
+	XE_GT_SRIOV_STATE_RESTORE_DATA_DONE,
 	XE_GT_SRIOV_STATE_RESTORE_FAILED,
 	XE_GT_SRIOV_STATE_RESTORED,
 

drivers/gpu/drm/xe/xe_gt_sriov_pf_migration.c

···
 
 #include "abi/guc_actions_sriov_abi.h"
 #include "xe_bo.h"
+#include "xe_gt_sriov_pf_control.h"
 #include "xe_gt_sriov_pf_helpers.h"
 #include "xe_gt_sriov_pf_migration.h"
 #include "xe_gt_sriov_printk.h"
 #include "xe_guc.h"
 #include "xe_guc_ct.h"
 #include "xe_sriov.h"
+#include "xe_sriov_packet_types.h"
 #include "xe_sriov_pf_migration.h"
+
+#define XE_GT_SRIOV_PF_MIGRATION_RING_SIZE 5
+
+static struct xe_gt_sriov_migration_data *pf_pick_gt_migration(struct xe_gt *gt, unsigned int vfid)
+{
+	xe_gt_assert(gt, IS_SRIOV_PF(gt_to_xe(gt)));
+	xe_gt_assert(gt, vfid != PFID);
+	xe_gt_assert(gt, vfid <= xe_sriov_pf_get_totalvfs(gt_to_xe(gt)));
+
+	return &gt->sriov.pf.vfs[vfid].migration;
+}
 
 /* Return: number of dwords saved/restored/required or a negative error code on failure */
 static int guc_action_vf_save_restore(struct xe_guc *guc, u32 vfid, u32 opcode,
···
 #endif /* CONFIG_DEBUG_FS */
 
 /**
+ * xe_gt_sriov_pf_migration_ring_empty() - Check if a migration ring is empty.
+ * @gt: the &xe_gt
+ * @vfid: the VF identifier
+ *
+ * Return: true if the ring is empty, otherwise false.
+ */
+bool xe_gt_sriov_pf_migration_ring_empty(struct xe_gt *gt, unsigned int vfid)
+{
+	return ptr_ring_empty(&pf_pick_gt_migration(gt, vfid)->ring);
+}
+
+/**
+ * xe_gt_sriov_pf_migration_ring_full() - Check if a migration ring is full.
+ * @gt: the &xe_gt
+ * @vfid: the VF identifier
+ *
+ * Return: true if the ring is full, otherwise false.
+ */
+bool xe_gt_sriov_pf_migration_ring_full(struct xe_gt *gt, unsigned int vfid)
+{
+	return ptr_ring_full(&pf_pick_gt_migration(gt, vfid)->ring);
+}
+
+/**
+ * xe_gt_sriov_pf_migration_save_produce() - Add VF save data packet to migration ring.
+ * @gt: the &xe_gt
+ * @vfid: the VF identifier
+ * @data: the &xe_sriov_packet
+ *
+ * Called by the save migration data producer (PF SR-IOV Control worker) when
+ * processing migration data.
+ * Wakes up the save migration data consumer (userspace), that is potentially
+ * waiting for data when the ring was empty.
+ *
+ * Return: 0 on success or a negative error code on failure.
+ */
+int xe_gt_sriov_pf_migration_save_produce(struct xe_gt *gt, unsigned int vfid,
+					  struct xe_sriov_packet *data)
+{
+	int ret;
+
+	ret = ptr_ring_produce(&pf_pick_gt_migration(gt, vfid)->ring, data);
+	if (ret)
+		return ret;
+
+	wake_up_all(xe_sriov_pf_migration_waitqueue(gt_to_xe(gt), vfid));
+
+	return 0;
+}
+
+/**
+ * xe_gt_sriov_pf_migration_restore_consume() - Get VF restore data packet from migration ring.
+ * @gt: the &xe_gt
+ * @vfid: the VF identifier
+ *
+ * Called by the restore migration data consumer (PF SR-IOV Control worker) when
+ * processing migration data.
+ * Wakes up the restore migration data producer (userspace), that is
+ * potentially waiting to add more data when the ring is full.
+ *
+ * Return: Pointer to &xe_sriov_packet on success,
+ *	   NULL if ring is empty.
+ */
+struct xe_sriov_packet *
+xe_gt_sriov_pf_migration_restore_consume(struct xe_gt *gt, unsigned int vfid)
+{
+	struct xe_gt_sriov_migration_data *migration = pf_pick_gt_migration(gt, vfid);
+	struct wait_queue_head *wq = xe_sriov_pf_migration_waitqueue(gt_to_xe(gt), vfid);
+	struct xe_sriov_packet *data;
+
+	data = ptr_ring_consume(&migration->ring);
+	if (data)
+		wake_up_all(wq);
+
+	return data;
+}
+
+static bool pf_restore_data_ready(struct xe_gt *gt, unsigned int vfid)
+{
+	if (xe_gt_sriov_pf_control_check_restore_failed(gt, vfid) ||
+	    !ptr_ring_full(&pf_pick_gt_migration(gt, vfid)->ring))
+		return true;
+
+	return false;
+}
+
+/**
+ * xe_gt_sriov_pf_migration_restore_produce() - Add VF restore data packet to migration ring.
+ * @gt: the &xe_gt
+ * @vfid: the VF identifier
+ * @data: the &xe_sriov_packet
+ *
+ * Called by the restore migration data producer (userspace) when processing
+ * migration data.
+ * If the ring is full, waits until there is space.
+ * Queues the restore migration data consumer (PF SR-IOV Control worker), that
+ * is potentially waiting for data when the ring was empty.
+ *
+ * Return: 0 on success or a negative error code on failure.
+ */
+int xe_gt_sriov_pf_migration_restore_produce(struct xe_gt *gt, unsigned int vfid,
+					     struct xe_sriov_packet *data)
+{
+	int ret;
+
+	xe_gt_assert(gt, data->hdr.tile_id == gt->tile->id);
+	xe_gt_assert(gt, data->hdr.gt_id == gt->info.id);
+
+	for (;;) {
+		if (xe_gt_sriov_pf_control_check_restore_failed(gt, vfid))
+			return -EIO;
+
+		ret = ptr_ring_produce(&pf_pick_gt_migration(gt, vfid)->ring, data);
+		if (!ret)
+			break;
+
+		ret = wait_event_interruptible(*xe_sriov_pf_migration_waitqueue(gt_to_xe(gt), vfid),
+					       pf_restore_data_ready(gt, vfid));
+		if (ret)
+			return ret;
+	}
+
+	return xe_gt_sriov_pf_control_process_restore_data(gt, vfid);
+}
+
+/**
+ * xe_gt_sriov_pf_migration_save_consume() - Get VF save data packet from migration ring.
+ * @gt: the &xe_gt
+ * @vfid: the VF identifier
+ *
+ * Called by the save migration data consumer (userspace) when
+ * processing migration data.
+ * Queues the save migration data producer (PF SR-IOV Control worker), that is
+ * potentially waiting to add more data when the ring is full.
+ *
+ * Return: Pointer to &xe_sriov_packet on success,
+ *	   NULL if ring is empty and there's no more data available,
+ *	   ERR_PTR(-EAGAIN) if the ring is empty, but data is still produced.
+ */
+struct xe_sriov_packet *
+xe_gt_sriov_pf_migration_save_consume(struct xe_gt *gt, unsigned int vfid)
+{
+	struct xe_gt_sriov_migration_data *migration = pf_pick_gt_migration(gt, vfid);
+	struct xe_sriov_packet *data;
+	int ret;
+
+	data = ptr_ring_consume(&migration->ring);
+	if (data) {
+		ret = xe_gt_sriov_pf_control_process_save_data(gt, vfid);
+		if (ret)
+			return ERR_PTR(ret);
+
+		return data;
+	}
+
+	if (xe_gt_sriov_pf_control_check_save_data_done(gt, vfid))
+		return NULL;
+
+	if (xe_gt_sriov_pf_control_check_save_failed(gt, vfid))
+		return ERR_PTR(-EIO);
+
+	return ERR_PTR(-EAGAIN);
+}
+
+static void action_ring_cleanup(void *arg)
+{
+	struct ptr_ring *r = arg;
+
+	ptr_ring_cleanup(r, NULL);
+}
+
+/**
  * xe_gt_sriov_pf_migration_init() - Initialize support for VF migration.
  * @gt: the &xe_gt
  *
···
 int xe_gt_sriov_pf_migration_init(struct xe_gt *gt)
 {
 	struct xe_device *xe = gt_to_xe(gt);
+	unsigned int n, totalvfs;
 	int err;
 
 	xe_gt_assert(gt, IS_SRIOV_PF(xe));
···
 	err = drmm_mutex_init(&xe->drm, &gt->sriov.pf.migration.snapshot_lock);
 	if (err)
 		return err;
+
+	totalvfs = xe_sriov_pf_get_totalvfs(xe);
+	for (n = 1; n <= totalvfs; n++) {
+		struct xe_gt_sriov_migration_data *migration = pf_pick_gt_migration(gt, n);
+
+		err = ptr_ring_init(&migration->ring,
+				    XE_GT_SRIOV_PF_MIGRATION_RING_SIZE, GFP_KERNEL);
+		if (err)
+			return err;
+
+		err = devm_add_action_or_reset(xe->drm.dev, action_ring_cleanup, &migration->ring);
+		if (err)
+			return err;
+	}
 
 	return 0;
 }

drivers/gpu/drm/xe/xe_gt_sriov_pf_migration.h

···
 #include <linux/types.h>
 
 struct xe_gt;
+struct xe_sriov_packet;
 
 int xe_gt_sriov_pf_migration_init(struct xe_gt *gt);
 int xe_gt_sriov_pf_migration_save_guc_state(struct xe_gt *gt, unsigned int vfid);
 int xe_gt_sriov_pf_migration_restore_guc_state(struct xe_gt *gt, unsigned int vfid);
+
+bool xe_gt_sriov_pf_migration_ring_empty(struct xe_gt *gt, unsigned int vfid);
+bool xe_gt_sriov_pf_migration_ring_full(struct xe_gt *gt, unsigned int vfid);
+
+int xe_gt_sriov_pf_migration_save_produce(struct xe_gt *gt, unsigned int vfid,
+					  struct xe_sriov_packet *data);
+struct xe_sriov_packet *
+xe_gt_sriov_pf_migration_restore_consume(struct xe_gt *gt, unsigned int vfid);
+
+int xe_gt_sriov_pf_migration_restore_produce(struct xe_gt *gt, unsigned int vfid,
+					     struct xe_sriov_packet *data);
+struct xe_sriov_packet *
+xe_gt_sriov_pf_migration_save_consume(struct xe_gt *gt, unsigned int vfid);
 
 #ifdef CONFIG_DEBUG_FS
 ssize_t xe_gt_sriov_pf_migration_read_guc_state(struct xe_gt *gt, unsigned int vfid,

drivers/gpu/drm/xe/xe_gt_sriov_pf_migration_types.h

···
 #define _XE_GT_SRIOV_PF_MIGRATION_TYPES_H_
 
 #include <linux/mutex.h>
+#include <linux/ptr_ring.h>
 #include <linux/types.h>
 
 /**
···
 		/** @guc.size: size of the buffer (must be dwords aligned) */
 		u32 size;
 	} guc;
+};
+
+/**
+ * struct xe_gt_sriov_migration_data - GT-level per-VF migration data.
+ *
+ * Used by the PF driver to maintain per-VF migration data.
+ */
+struct xe_gt_sriov_migration_data {
+	/** @ring: queue containing VF save / restore migration data */
+	struct ptr_ring ring;
 };
 
 /**

drivers/gpu/drm/xe/xe_gt_sriov_pf_types.h

···
 
 	/** @snapshot: snapshot of the VF state data */
 	struct xe_gt_sriov_state_snapshot snapshot;
+
+	/** @migration: per-VF migration data. */
+	struct xe_gt_sriov_migration_data migration;
 };
 
 /**

drivers/gpu/drm/xe/xe_sriov_packet_types.h

···
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2025 Intel Corporation
+ */
+
+#ifndef _XE_SRIOV_PACKET_TYPES_H_
+#define _XE_SRIOV_PACKET_TYPES_H_
+
+#include <linux/types.h>
+
+/**
+ * struct xe_sriov_packet_hdr - Xe SR-IOV VF migration data packet header
+ */
+struct xe_sriov_packet_hdr {
+	/** @version: migration data protocol version */
+	u8 version;
+	/** @type: migration data type */
+	u8 type;
+	/** @tile_id: migration data tile id */
+	u8 tile_id;
+	/** @gt_id: migration data gt id */
+	u8 gt_id;
+	/** @flags: migration data flags */
+	u32 flags;
+	/**
+	 * @offset: offset into the resource;
+	 * used when multiple packets of given type are used for migration
+	 */
+	u64 offset;
+	/** @size: migration data size  */
+	u64 size;
+} __packed;
+
+/**
+ * struct xe_sriov_packet - Xe SR-IOV VF migration data packet
+ */
+struct xe_sriov_packet {
+	/** @xe: the PF &xe_device this data packet belongs to */
+	struct xe_device *xe;
+	/** @vaddr: CPU pointer to payload data */
+	void *vaddr;
+	/** @remaining: payload data remaining */
+	size_t remaining;
+	/** @hdr_remaining: header data remaining */
+	size_t hdr_remaining;
+	union {
+		/** @bo: Buffer object with migration data */
+		struct xe_bo *bo;
+		/** @buff: Buffer with migration data */
+		void *buff;
+	};
+	/** @hdr: data packet header */
+	struct xe_sriov_packet_hdr hdr;
+};
+
+#endif

drivers/gpu/drm/xe/xe_sriov_pf_migration.c

···
  * Copyright © 2025 Intel Corporation
  */
 
+#include <drm/drm_managed.h>
+
+#include "xe_device.h"
+#include "xe_gt_sriov_pf_control.h"
+#include "xe_gt_sriov_pf_migration.h"
+#include "xe_pm.h"
 #include "xe_sriov.h"
+#include "xe_sriov_packet_types.h"
+#include "xe_sriov_pf_helpers.h"
 #include "xe_sriov_pf_migration.h"
+#include "xe_sriov_printk.h"
+
+static struct xe_sriov_migration_state *pf_pick_migration(struct xe_device *xe, unsigned int vfid)
+{
+	xe_assert(xe, IS_SRIOV_PF(xe));
+	xe_assert(xe, vfid <= xe_sriov_pf_get_totalvfs(xe));
+
+	return &xe->sriov.pf.vfs[vfid].migration;
+}
+
+/**
+ * xe_sriov_pf_migration_waitqueue() - Get waitqueue for migration.
+ * @xe: the &xe_device
+ * @vfid: the VF identifier
+ *
+ * Return: pointer to the migration waitqueue.
+ */
+wait_queue_head_t *xe_sriov_pf_migration_waitqueue(struct xe_device *xe, unsigned int vfid)
+{
+	return &pf_pick_migration(xe, vfid)->wq;
+}
 
 /**
  * xe_sriov_pf_migration_supported() - Check if SR-IOV VF migration is supported by the device
···
  */
 int xe_sriov_pf_migration_init(struct xe_device *xe)
 {
+	unsigned int n, totalvfs;
+
 	xe_assert(xe, IS_SRIOV_PF(xe));
 
 	xe->sriov.pf.migration.supported = pf_check_migration_support(xe);
+	if (!xe_sriov_pf_migration_supported(xe))
+		return 0;
+
+	totalvfs = xe_sriov_pf_get_totalvfs(xe);
+	for (n = 1; n <= totalvfs; n++) {
+		struct xe_sriov_migration_state *migration = pf_pick_migration(xe, n);
+
+		init_waitqueue_head(&migration->wq);
+	}
 
 	return 0;
+}
+
+static bool pf_migration_data_ready(struct xe_device *xe, unsigned int vfid)
+{
+	struct xe_gt *gt;
+	u8 gt_id;
+
+	for_each_gt(gt, xe, gt_id) {
+		if (xe_gt_sriov_pf_control_check_save_failed(gt, vfid) ||
+		    xe_gt_sriov_pf_control_check_save_data_done(gt, vfid) ||
+		    !xe_gt_sriov_pf_migration_ring_empty(gt, vfid))
+			return true;
+	}
+
+	return false;
+}
+
+static struct xe_sriov_packet *
+pf_migration_consume(struct xe_device *xe, unsigned int vfid)
+{
+	struct xe_sriov_packet *data;
+	bool more_data = false;
+	struct xe_gt *gt;
+	u8 gt_id;
+
+	for_each_gt(gt, xe, gt_id) {
+		data = xe_gt_sriov_pf_migration_save_consume(gt, vfid);
+		if (data && PTR_ERR(data) != EAGAIN)
+			return data;
+		if (PTR_ERR(data) == -EAGAIN)
+			more_data = true;
+	}
+
+	if (!more_data)
+		return NULL;
+
+	return ERR_PTR(-EAGAIN);
+}
+
+/**
+ * xe_sriov_pf_migration_save_consume() - Consume a VF migration data packet from the device.
+ * @xe: the &xe_device
+ * @vfid: the VF identifier
+ *
+ * Called by the save migration data consumer (userspace) when
+ * processing migration data.
+ * If there is no migration data to process, wait until more data is available.
+ *
+ * Return: Pointer to &xe_sriov_packet on success,
+ *	   NULL if ring is empty and no more migration data is expected,
+ *	   ERR_PTR value in case of error.
+ *
+ * Return: 0 on success or a negative error code on failure.
+ */
+struct xe_sriov_packet *
+xe_sriov_pf_migration_save_consume(struct xe_device *xe, unsigned int vfid)
+{
+	struct xe_sriov_migration_state *migration = pf_pick_migration(xe, vfid);
+	struct xe_sriov_packet *data;
+	int ret;
+
+	xe_assert(xe, IS_SRIOV_PF(xe));
+
+	for (;;) {
+		data = pf_migration_consume(xe, vfid);
+		if (PTR_ERR(data) != -EAGAIN)
+			break;
+
+		ret = wait_event_interruptible(migration->wq,
+					       pf_migration_data_ready(xe, vfid));
+		if (ret)
+			return ERR_PTR(ret);
+	}
+
+	return data;
+}
+
+/**
+ * xe_sriov_pf_migration_restore_produce() - Produce a VF migration data packet to the device.
+ * @xe: the &xe_device
+ * @vfid: the VF identifier
+ * @data: Pointer to &xe_sriov_packet
+ *
+ * Called by the restore migration data producer (userspace) when processing
+ * migration data.
+ * If the underlying data structure is full, wait until there is space.
+ *
+ * Return: 0 on success or a negative error code on failure.
+ */
+int xe_sriov_pf_migration_restore_produce(struct xe_device *xe, unsigned int vfid,
+					  struct xe_sriov_packet *data)
+{
+	struct xe_gt *gt;
+
+	xe_assert(xe, IS_SRIOV_PF(xe));
+
+	gt = xe_device_get_gt(xe, data->hdr.gt_id);
+	if (!gt || data->hdr.tile_id != gt->tile->id || data->hdr.type == 0) {
+		xe_sriov_err_ratelimited(xe, "Received invalid restore packet for VF%u (type:%u, tile:%u, GT:%u)\n",
+					 vfid, data->hdr.type, data->hdr.tile_id, data->hdr.gt_id);
+		return -EINVAL;
+	}
+
+	return xe_gt_sriov_pf_migration_restore_produce(gt, vfid, data);
 }

drivers/gpu/drm/xe/xe_sriov_pf_migration.h

···
 #define _XE_SRIOV_PF_MIGRATION_H_
 
 #include <linux/types.h>
+#include <linux/wait.h>
 
 struct xe_device;
+struct xe_sriov_packet;
 
 int xe_sriov_pf_migration_init(struct xe_device *xe);
 bool xe_sriov_pf_migration_supported(struct xe_device *xe);
+int xe_sriov_pf_migration_restore_produce(struct xe_device *xe, unsigned int vfid,
+					  struct xe_sriov_packet *data);
+struct xe_sriov_packet *
+xe_sriov_pf_migration_save_consume(struct xe_device *xe, unsigned int vfid);
+wait_queue_head_t *xe_sriov_pf_migration_waitqueue(struct xe_device *xe, unsigned int vfid);
 
 #endif

drivers/gpu/drm/xe/xe_sriov_pf_migration_types.h

···
 #define _XE_SRIOV_PF_MIGRATION_TYPES_H_
 
 #include <linux/types.h>
+#include <linux/wait.h>
 
 /**
  * struct xe_sriov_pf_migration - Xe device level VF migration data
···
 struct xe_sriov_pf_migration {
 	/** @supported: indicates whether VF migration feature is supported */
 	bool supported;
+};
+
+/**
+ * struct xe_sriov_migration_state - Per VF device-level migration related data
+ */
+struct xe_sriov_migration_state {
+	/** @wq: waitqueue used to avoid busy-waiting for snapshot production/consumption */
+	wait_queue_head_t wq;
 };
 
 #endif

drivers/gpu/drm/xe/xe_sriov_pf_types.h

···
 
 	/** @version: negotiated VF/PF ABI version */
 	struct xe_sriov_pf_service_version version;
+	/** @migration: migration state */
+	struct xe_sriov_migration_state migration;
 };
 
 /**