1 files changed, 27 insertions, 0 deletions
diff --git a/kernel/gsp_phys_gpu.c b/kernel/gsp_phys_gpu.c
index b93c254..4c0fd37 100644
--- a/kernel/gsp_phys_gpu.c
+++ b/kernel/gsp_phys_gpu.c
@@ -1057,6 +1057,33 @@ int gsp_phys_gr_icache_inv_value(void)
 EXPORT_SYMBOL_GPL(gsp_phys_gr_icache_inv_value);
 
 /*
+ * r433 RELEASE_MEMBAR_TYPE A/B (gsp_phys_gr_rel_membar; default 0). The
+ * captured guest QMDs carry RELEASE_MEMBAR_TYPE=FE_NONE (QMDV00_06 word 11
+ * bit 14 clear, w11=0x44010000), so when the front-end completes a grid it
+ * writes the QMD release semaphore without first flushing its pending
+ * system-memory stores. The post-dispatch store-loss signature (the engine
+ * processes the QMD, writes the release, the grid completes and ZERO data
+ * pages are host-visible) is exactly what an unflushed write-back L2 looks
+ * like from the host: the release is host-visible while the data sits in the
+ * GPU's L2. Forcing RELEASE_MEMBAR_TYPE=FE_SYSMEMBAR makes the release
+ * ordering guarantee the stores are in memory before the semaphore write, so
+ * the host's retire scan (and the copy-out) can never observe a completion
+ * whose data has not landed. 0 keeps the guest's captured value (the
+ * historical behaviour) for a one-flip A/B; read per launch.
+ */
+static int gsp_phys_gr_rel_membar_param;
+module_param_named(gsp_phys_gr_rel_membar, gsp_phys_gr_rel_membar_param,
+		   int, 0644);
+MODULE_PARM_DESC(gsp_phys_gr_rel_membar,
+		 "r433: force QMD RELEASE_MEMBAR_TYPE=FE_SYSMEMBAR (word11 bit14) on forwarded GR launches (default 0 = guest's captured FE_NONE)");
+
+int gsp_phys_gr_rel_membar_value(void)
+{
+	return gsp_phys_gr_rel_membar_param;
+}
+EXPORT_SYMBOL_GPL(gsp_phys_gr_rel_membar_value);
+
+/*
  * m179 no-write retry budget (gsp_phys_gr_nowrite_retries; default 3, clamped
  * to [0, 4]). The m153 outcome retry loop re-executes a data-bearing launch
  * whose retirement wait saw zero engine writes; it shared the timeout ladder's