drm/xe/vf: Start post-migration fixups with provisioning query

During post-migration recovery, only MMIO communication to GuC is
allowed. The VF KMD needs to use that channel to ask for the new
provisioning, which includes a new GGTT range assigned to the VF.

v2: query config only instead of handshake; no need to get pm ref as
 it's now kept through whole recovery (Michal)
v3: switched names of 'err' and 'ret'  (Michal)

Signed-off-by: Tomasz Lis <tomasz.lis@intel.com>
Reviewed-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20241104213449.1455694-5-tomasz.lis@intel.com
Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>

diff --git a/drivers/gpu/drm/xe/xe_sriov_vf.c b/drivers/gpu/drm/xe/xe_sriov_vf.c
index 945893ad967f349e7d04714393c3f3c508ecb1d2..ad29bd835d8e15d72778c41ee1b9ba7218f83163 100644 (file)
--- a/drivers/gpu/drm/xe/xe_sriov_vf.c
+++ b/drivers/gpu/drm/xe/xe_sriov_vf.c
@@ -132,6 +132,31 @@ void xe_sriov_vf_init_early(struct xe_device *xe)
        INIT_WORK(&xe->sriov.vf.migration.worker, migration_worker_func);
 }
 
+/**
+ * vf_post_migration_requery_guc - Re-query GuC for current VF provisioning.
+ * @xe: the &xe_device struct instance
+ *
+ * After migration, we need to re-query all VF configuration to make sure
+ * they match previous provisioning. Note that most of VF provisioning
+ * shall be the same, except GGTT range, since GGTT is not virtualized per-VF.
+ *
+ * Returns: 0 if the operation completed successfully, or a negative error
+ * code otherwise.
+ */
+static int vf_post_migration_requery_guc(struct xe_device *xe)
+{
+       struct xe_gt *gt;
+       unsigned int id;
+       int err, ret = 0;
+
+       for_each_gt(gt, xe, id) {
+               err = xe_gt_sriov_vf_query_config(gt);
+               ret = ret ?: err;
+       }
+
+       return ret;
+}
+
 /*
  * Notify all GuCs about resource fixups apply finished.
  */
@@ -147,12 +172,23 @@ static void vf_post_migration_notify_resfix_done(struct xe_device *xe)
 
 static void vf_post_migration_recovery(struct xe_device *xe)
 {
+       int err;
+
        drm_dbg(&xe->drm, "migration recovery in progress\n");
        xe_pm_runtime_get(xe);
+       err = vf_post_migration_requery_guc(xe);
+       if (unlikely(err))
+               goto fail;
+
        /* FIXME: add the recovery steps */
        vf_post_migration_notify_resfix_done(xe);
        xe_pm_runtime_put(xe);
        drm_notice(&xe->drm, "migration recovery ended\n");
+       return;
+fail:
+       xe_pm_runtime_put(xe);
+       drm_err(&xe->drm, "migration recovery failed (%pe)\n", ERR_PTR(err));
+       xe_device_declare_wedged(xe);
 }
 
 static void migration_worker_func(struct work_struct *w)