drm/xe/pf: Switch VF migration GuC save/restore to struct migration data

In upcoming changes, the GuC VF migration data will be handled as part
of separate SAVE/RESTORE states in VF control state machine.
Now that the data is decoupled from both guc_state debugfs and PAUSE
state, we can safely remove the struct xe_gt_sriov_state_snapshot and
modify the GuC save/restore functions to operate on struct
xe_sriov_migration_data.

Reviewed-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Link: https://patch.msgid.link/20251112132220.516975-16-michal.winiarski@intel.com
Signed-off-by: Michał Winiarski <michal.winiarski@intel.com>

Author: mwiniars

drivers/gpu/drm/xe/xe_gt_sriov_pf_migration.c

@@ -29,6 +29,19 @@ static struct xe_gt_sriov_migration_data *pf_pick_gt_migration(struct xe_gt *gt,
 	return &gt->sriov.pf.vfs[vfid].migration;
 }
 
+static void pf_dump_mig_data(struct xe_gt *gt, unsigned int vfid,
+			     struct xe_sriov_packet *data,
+			     const char *what)
+{
+	if (IS_ENABLED(CONFIG_DRM_XE_DEBUG_SRIOV)) {
+		struct drm_printer p = xe_gt_dbg_printer(gt);
+
+		drm_printf(&p, "VF%u %s (%llu bytes)\n", vfid, what, data->hdr.size);
+		drm_print_hex_dump(&p, "mig_hdr:  ", (void *)&data->hdr, sizeof(data->hdr));
+		drm_print_hex_dump(&p, "mig_data: ", data->vaddr, min(SZ_64, data->hdr.size));
+	}
+}
+
 /* 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)
@@ -48,7 +61,7 @@ static int guc_action_vf_save_restore(struct xe_guc *guc, u32 vfid, u32 opcode,
 }
 
 /* Return: size of the state in dwords or a negative error code on failure */
-static int pf_send_guc_query_vf_state_size(struct xe_gt *gt, unsigned int vfid)
+static int pf_send_guc_query_vf_mig_data_size(struct xe_gt *gt, unsigned int vfid)
 {
 	int ret;
 
@@ -57,8 +70,8 @@ static int pf_send_guc_query_vf_state_size(struct xe_gt *gt, unsigned int vfid)
 }
 
 /* Return: number of state dwords saved or a negative error code on failure */
-static int pf_send_guc_save_vf_state(struct xe_gt *gt, unsigned int vfid,
-				     void *dst, size_t size)
+static int pf_send_guc_save_vf_mig_data(struct xe_gt *gt, unsigned int vfid,
+					void *dst, size_t size)
 {
 	const int ndwords = size / sizeof(u32);
 	struct xe_guc *guc = &gt->uc.guc;
@@ -87,8 +100,8 @@ static int pf_send_guc_save_vf_state(struct xe_gt *gt, unsigned int vfid,
 }
 
 /* Return: number of state dwords restored or a negative error code on failure */
-static int pf_send_guc_restore_vf_state(struct xe_gt *gt, unsigned int vfid,
-					const void *src, size_t size)
+static int pf_send_guc_restore_vf_mig_data(struct xe_gt *gt, unsigned int vfid,
+					   const void *src, size_t size)
 {
 	const int ndwords = size / sizeof(u32);
 	struct xe_guc *guc = &gt->uc.guc;
@@ -116,120 +129,66 @@ static bool pf_migration_supported(struct xe_gt *gt)
 	return xe_sriov_pf_migration_supported(gt_to_xe(gt));
 }
 
-static struct mutex *pf_migration_mutex(struct xe_gt *gt)
+static int pf_save_vf_guc_mig_data(struct xe_gt *gt, unsigned int vfid)
 {
-	xe_gt_assert(gt, IS_SRIOV_PF(gt_to_xe(gt)));
-	return &gt->sriov.pf.migration.snapshot_lock;
-}
-
-static struct xe_gt_sriov_state_snapshot *pf_pick_vf_snapshot(struct xe_gt *gt,
-							      unsigned int vfid)
-{
-	xe_gt_assert(gt, IS_SRIOV_PF(gt_to_xe(gt)));
-	xe_gt_assert(gt, vfid <= xe_sriov_pf_get_totalvfs(gt_to_xe(gt)));
-	lockdep_assert_held(pf_migration_mutex(gt));
-
-	return &gt->sriov.pf.vfs[vfid].snapshot;
-}
-
-static unsigned int pf_snapshot_index(struct xe_gt *gt, struct xe_gt_sriov_state_snapshot *snapshot)
-{
-	return container_of(snapshot, struct xe_gt_sriov_metadata, snapshot) - gt->sriov.pf.vfs;
-}
-
-static void pf_free_guc_state(struct xe_gt *gt, struct xe_gt_sriov_state_snapshot *snapshot)
-{
-	struct xe_device *xe = gt_to_xe(gt);
-
-	drmm_kfree(&xe->drm, snapshot->guc.buff);
-	snapshot->guc.buff = NULL;
-	snapshot->guc.size = 0;
-}
-
-static int pf_alloc_guc_state(struct xe_gt *gt,
-			      struct xe_gt_sriov_state_snapshot *snapshot,
-			      size_t size)
-{
-	struct xe_device *xe = gt_to_xe(gt);
-	void *p;
-
-	pf_free_guc_state(gt, snapshot);
-
-	if (!size)
-		return -ENODATA;
-
-	if (size % sizeof(u32))
-		return -EINVAL;
-
-	if (size > SZ_2M)
-		return -EFBIG;
-
-	p = drmm_kzalloc(&xe->drm, size, GFP_KERNEL);
-	if (!p)
-		return -ENOMEM;
-
-	snapshot->guc.buff = p;
-	snapshot->guc.size = size;
-	return 0;
-}
-
-static void pf_dump_guc_state(struct xe_gt *gt, struct xe_gt_sriov_state_snapshot *snapshot)
-{
-	if (IS_ENABLED(CONFIG_DRM_XE_DEBUG_SRIOV)) {
-		unsigned int vfid __maybe_unused = pf_snapshot_index(gt, snapshot);
-
-		xe_gt_sriov_dbg_verbose(gt, "VF%u GuC state is %zu dwords:\n",
-					vfid, snapshot->guc.size / sizeof(u32));
-		print_hex_dump_bytes("state: ", DUMP_PREFIX_OFFSET,
-				     snapshot->guc.buff, min(SZ_64, snapshot->guc.size));
-	}
-}
-
-static int pf_save_vf_guc_state(struct xe_gt *gt, unsigned int vfid)
-{
-	struct xe_gt_sriov_state_snapshot *snapshot = pf_pick_vf_snapshot(gt, vfid);
+	struct xe_sriov_packet *data;
 	size_t size;
 	int ret;
 
-	ret = pf_send_guc_query_vf_state_size(gt, vfid);
+	ret = pf_send_guc_query_vf_mig_data_size(gt, vfid);
 	if (ret < 0)
 		goto fail;
+
 	size = ret * sizeof(u32);
-	xe_gt_sriov_dbg_verbose(gt, "VF%u state size is %d dwords (%zu bytes)\n", vfid, ret, size);
 
-	ret = pf_alloc_guc_state(gt, snapshot, size);
-	if (ret < 0)
+	data = xe_sriov_packet_alloc(gt_to_xe(gt));
+	if (!data) {
+		ret = -ENOMEM;
 		goto fail;
+	}
+
+	ret = xe_sriov_packet_init(data, gt->tile->id, gt->info.id,
+				   XE_SRIOV_PACKET_TYPE_GUC, 0, size);
+	if (ret)
+		goto fail_free;
 
-	ret = pf_send_guc_save_vf_state(gt, vfid, snapshot->guc.buff, size);
+	ret = pf_send_guc_save_vf_mig_data(gt, vfid, data->vaddr, size);
 	if (ret < 0)
-		goto fail;
+		goto fail_free;
 	size = ret * sizeof(u32);
 	xe_gt_assert(gt, size);
-	xe_gt_assert(gt, size <= snapshot->guc.size);
-	snapshot->guc.size = size;
+	xe_gt_assert(gt, size <= data->hdr.size);
+	data->hdr.size = size;
+	data->remaining = size;
+
+	pf_dump_mig_data(gt, vfid, data, "GuC data save");
+
+	ret = xe_gt_sriov_pf_migration_save_produce(gt, vfid, data);
+	if (ret)
+		goto fail_free;
 
-	pf_dump_guc_state(gt, snapshot);
 	return 0;
 
+fail_free:
+	xe_sriov_packet_free(data);
 fail:
-	xe_gt_sriov_dbg(gt, "Unable to save VF%u state (%pe)\n", vfid, ERR_PTR(ret));
-	pf_free_guc_state(gt, snapshot);
+	xe_gt_sriov_err(gt, "Failed to save VF%u GuC data (%pe)\n",
+			vfid, ERR_PTR(ret));
 	return ret;
 }
 
 /**
- * xe_gt_sriov_pf_migration_save_guc_state() - Take a GuC VF state snapshot.
+ * xe_gt_sriov_pf_migration_guc_size() - Get the size of VF GuC migration data.
  * @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.
+ * Return: size in bytes or a negative error code on failure.
  */
-int xe_gt_sriov_pf_migration_save_guc_state(struct xe_gt *gt, unsigned int vfid)
+ssize_t xe_gt_sriov_pf_migration_guc_size(struct xe_gt *gt, unsigned int vfid)
 {
-	int err;
+	ssize_t size;
 
 	xe_gt_assert(gt, IS_SRIOV_PF(gt_to_xe(gt)));
 	xe_gt_assert(gt, vfid != PFID);
@@ -238,146 +197,77 @@ int xe_gt_sriov_pf_migration_save_guc_state(struct xe_gt *gt, unsigned int vfid)
 	if (!pf_migration_supported(gt))
 		return -ENOPKG;
 
-	mutex_lock(pf_migration_mutex(gt));
-	err = pf_save_vf_guc_state(gt, vfid);
-	mutex_unlock(pf_migration_mutex(gt));
+	size = pf_send_guc_query_vf_mig_data_size(gt, vfid);
+	if (size >= 0)
+		size *= sizeof(u32);
 
-	return err;
-}
-
-static int pf_restore_vf_guc_state(struct xe_gt *gt, unsigned int vfid)
-{
-	struct xe_gt_sriov_state_snapshot *snapshot = pf_pick_vf_snapshot(gt, vfid);
-	int ret;
-
-	if (!snapshot->guc.size)
-		return -ENODATA;
-
-	xe_gt_sriov_dbg_verbose(gt, "restoring %zu dwords of VF%u GuC state\n",
-				snapshot->guc.size / sizeof(u32), vfid);
-	ret = pf_send_guc_restore_vf_state(gt, vfid, snapshot->guc.buff, snapshot->guc.size);
-	if (ret < 0)
-		goto fail;
-
-	xe_gt_sriov_dbg_verbose(gt, "restored %d dwords of VF%u GuC state\n", ret, vfid);
-	return 0;
-
-fail:
-	xe_gt_sriov_dbg(gt, "Failed to restore VF%u GuC state (%pe)\n", vfid, ERR_PTR(ret));
-	return ret;
+	return size;
 }
 
 /**
- * xe_gt_sriov_pf_migration_restore_guc_state() - Restore a GuC VF state.
+ * xe_gt_sriov_pf_migration_guc_save() - Save VF GuC migration data.
  * @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_migration_restore_guc_state(struct xe_gt *gt, unsigned int vfid)
+int xe_gt_sriov_pf_migration_guc_save(struct xe_gt *gt, unsigned int vfid)
 {
-	int ret;
-
 	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)));
 
 	if (!pf_migration_supported(gt))
 		return -ENOPKG;
 
-	mutex_lock(pf_migration_mutex(gt));
-	ret = pf_restore_vf_guc_state(gt, vfid);
-	mutex_unlock(pf_migration_mutex(gt));
-
-	return ret;
+	return pf_save_vf_guc_mig_data(gt, vfid);
 }
 
-#ifdef CONFIG_DEBUG_FS
-/**
- * xe_gt_sriov_pf_migration_read_guc_state() - Read a GuC VF state.
- * @gt: the &xe_gt
- * @vfid: the VF identifier
- * @buf: the user space buffer to read to
- * @count: the maximum number of bytes to read
- * @pos: the current position in the buffer
- *
- * This function is for PF only.
- *
- * This function reads up to @count bytes from the saved VF GuC state buffer
- * at offset @pos into the user space address starting at @buf.
- *
- * Return: the number of bytes read or a negative error code on failure.
- */
-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)
+static int pf_restore_vf_guc_state(struct xe_gt *gt, unsigned int vfid,
+				   struct xe_sriov_packet *data)
 {
-	struct xe_gt_sriov_state_snapshot *snapshot;
-	ssize_t ret;
+	int ret;
 
-	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)));
+	xe_gt_assert(gt, data->hdr.size);
 
-	if (!pf_migration_supported(gt))
-		return -ENOPKG;
+	pf_dump_mig_data(gt, vfid, data, "GuC data restore");
 
-	mutex_lock(pf_migration_mutex(gt));
-	snapshot = pf_pick_vf_snapshot(gt, vfid);
-	if (snapshot->guc.size)
-		ret = simple_read_from_buffer(buf, count, pos, snapshot->guc.buff,
-					      snapshot->guc.size);
-	else
-		ret = -ENODATA;
-	mutex_unlock(pf_migration_mutex(gt));
+	ret = pf_send_guc_restore_vf_mig_data(gt, vfid, data->vaddr, data->hdr.size);
+	if (ret < 0)
+		goto fail;
+
+	return 0;
 
+fail:
+	xe_gt_sriov_err(gt, "Failed to restore VF%u GuC data (%pe)\n",
+			vfid, ERR_PTR(ret));
 	return ret;
 }
 
 /**
- * xe_gt_sriov_pf_migration_write_guc_state() - Write a GuC VF state.
+ * xe_gt_sriov_pf_migration_guc_restore() - Restore VF GuC migration data.
  * @gt: the &xe_gt
  * @vfid: the VF identifier
- * @buf: the user space buffer with GuC VF state
- * @size: the size of GuC VF state (in bytes)
+ * @data: the &xe_sriov_packet containing migration data
  *
  * This function is for PF only.
  *
- * This function reads @size bytes of the VF GuC state stored at user space
- * address @buf and writes it into a internal VF state buffer.
- *
- * Return: the number of bytes used or a negative error code on failure.
+ * Return: 0 on success or a negative error code on failure.
  */
-ssize_t xe_gt_sriov_pf_migration_write_guc_state(struct xe_gt *gt, unsigned int vfid,
-						 const char __user *buf, size_t size)
+int xe_gt_sriov_pf_migration_guc_restore(struct xe_gt *gt, unsigned int vfid,
+					 struct xe_sriov_packet *data)
 {
-	struct xe_gt_sriov_state_snapshot *snapshot;
-	loff_t pos = 0;
-	ssize_t ret;
-
 	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)));
 
 	if (!pf_migration_supported(gt))
 		return -ENOPKG;
 
-	mutex_lock(pf_migration_mutex(gt));
-	snapshot = pf_pick_vf_snapshot(gt, vfid);
-	ret = pf_alloc_guc_state(gt, snapshot, size);
-	if (!ret) {
-		ret = simple_write_to_buffer(snapshot->guc.buff, size, &pos, buf, size);
-		if (ret < 0)
-			pf_free_guc_state(gt, snapshot);
-		else
-			pf_dump_guc_state(gt, snapshot);
-	}
-	mutex_unlock(pf_migration_mutex(gt));
-
-	return ret;
+	return pf_restore_vf_guc_state(gt, vfid, data);
 }
-#endif /* CONFIG_DEBUG_FS */
 
 /**
  * xe_gt_sriov_pf_migration_size() - Total size of migration data from all components within a GT.
@@ -619,10 +509,6 @@ int xe_gt_sriov_pf_migration_init(struct xe_gt *gt)
 	if (!pf_migration_supported(gt))
 		return 0;
 
-	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);