vgsp-sema: bounded channel rewind (sema_chan_rewind: hex h_object or 'all' -> clears slot_done_epoch + last_get + the per-entry rescue state so entries skipped before the VAS pdb anchor re-decode) + bounded per-chunk push-read failure witness (sema-pushfail: va/chunk/page/last_rc/trusted_rc/ipin/alt/win per failed chunk); wall2: runbook.py (trigger the anchor then rewind). Session 118: the anchor+rewind path is wired; the automated rewind scheduler missed (dmesg churn) and the pushfail trace still needs one clean capture

1 files changed, 24 insertions, 0 deletions

diff --git a/kernel/main.c b/kernel/main.c
index 5ff5047..7af236d 100644
--- a/kernel/main.c
+++ b/kernel/main.c
@@ -2991,6 +2991,30 @@ module_param_cb(sema_pdb_discover, &nv_vgpu_sema_pdb_discover_ops, NULL, 0200);
 MODULE_PARM_DESC(sema_pdb_discover, "Retrigger the VAS pdb discovery with a verified ring pair (hex va,hex pa)");
 
 /*
+ * Debug: bounded channel rewind. Clears the consumed-slot bitmap and the
+ * per-entry rescue state for one channel (hex h_object) or every channel
+ * ("all"), so the pump re-processes its ring from slot 0 - used after the
+ * VAS pdb anchor lands so entries skipped before it re-decode (the release
+ * they carry would otherwise be lost for that put epoch).
+ */
+static int nv_vgpu_sema_chan_rewind_set(const char *val,
+					const struct kernel_param *kp)
+{
+	u32 h = 0xffffffffu;
+
+	if (strncmp(val, "all", 3) && kstrtouint(val, 0, &h))
+		return -EINVAL;
+	return gsp_sema_service_chan_rewind(h);
+}
+
+static const struct kernel_param_ops nv_vgpu_sema_chan_rewind_ops = {
+	.set = nv_vgpu_sema_chan_rewind_set,
+};
+
+module_param_cb(sema_chan_rewind, &nv_vgpu_sema_chan_rewind_ops, NULL, 0200);
+MODULE_PARM_DESC(sema_chan_rewind, "Rewind a channel's ring (hex h_object or 'all')");
+
+/*
  * Debug: register a channel's GPU completion counter (guest PA of the u32
  * tracking counter the GPU would write when a push completes):
  *   echo <h_object>,<pa> > .../parameters/sema_counter