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 <michal.wajdeczko@intel.com>
Link: https://patch.msgid.link/20251112132220.516975-6-michal.winiarski@intel.com
Signed-off-by: Michał Winiarski <michal.winiarski@intel.com>

Author: mwiniars

drivers/gpu/drm/xe/xe_gt_sriov_pf_control.c

@@ -16,8 +16,14 @@ 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);
+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.h

@@ -32,9 +32,15 @@
  * @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.
@@ -70,10 +76,16 @@ enum xe_gt_sriov_control_bits {
 	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_control_types.h

@@ -7,14 +7,27 @@
 
 #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,
 				      u64 addr, u32 ndwords)
@@ -382,6 +395,178 @@ ssize_t xe_gt_sriov_pf_migration_write_guc_state(struct xe_gt *gt, unsigned int
 }
 #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
@@ -393,6 +578,7 @@ ssize_t xe_gt_sriov_pf_migration_write_guc_state(struct xe_gt *gt, unsigned int
 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));
@@ -404,5 +590,19 @@ int xe_gt_sriov_pf_migration_init(struct xe_gt *gt)
 	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.c

@@ -9,11 +9,25 @@
 #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,
 						char __user *buf, size_t count, loff_t *pos);

drivers/gpu/drm/xe/xe_gt_sriov_pf_migration.h

@@ -7,6 +7,7 @@
 #define _XE_GT_SRIOV_PF_MIGRATION_TYPES_H_
 
 #include <linux/mutex.h>
+#include <linux/ptr_ring.h>
 #include <linux/types.h>
 
 /**
@@ -24,6 +25,16 @@ struct xe_gt_sriov_state_snapshot {
 	} 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;
+};
+
 /**
  * struct xe_gt_sriov_pf_migration - GT-level data.
  *

drivers/gpu/drm/xe/xe_gt_sriov_pf_migration_types.h

@@ -33,6 +33,9 @@ struct xe_gt_sriov_metadata {
 
 	/** @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;
 };
 
 /**