r433 RELEASE_MEMBAR_TYPE A/B: gsp_phys_gr_rel_membar forces QMD word11 bit14 (FE_SYSMEMBAR) on forwarded GR launches so the engine flushes pending sysmem stores before writing the release semaphore - the post-dispatch store-loss signature (release host-visible, data stuck in L2) is what an unflushed write-back L2 looks like from the host; 0 keeps the guest's captured FE_NONE for a one-flip A/B

1 files changed, 21 insertions, 0 deletions

diff --git a/kernel/gsp_phys_booter.c b/kernel/gsp_phys_booter.c
index bbb6d52..f4e558f 100644
--- a/kernel/gsp_phys_booter.c
+++ b/kernel/gsp_phys_booter.c
@@ -18454,6 +18454,7 @@ static u32 gsp_phys_m91_fault_start;
 static u32 gsp_phys_m91_cap_used;
 static bool gsp_phys_m91_cap_suppressed;
 static bool gsp_phys_m91_icache_log;
+static bool gsp_phys_gr_rel_membar_log;
 static noinline void
 gsp_phys_gr_m91_fault_cap(const struct gsp_phys_gr_submit *req,
 			  const u32 *qmd, u64 qmd_dst, const u8 *qmd_dst_mem,
@@ -18963,6 +18964,26 @@ int gsp_phys_backend_guest_gr_submit(const struct gsp_phys_gr_submit *req,
 		}
 	}
 	/*
+	 * r433 RELEASE_MEMBAR_TYPE A/B (gsp_phys_gr_rel_membar): force the
+	 * forwarded QMD's RELEASE_MEMBAR_TYPE to FE_SYSMEMBAR (QMDV00_06
+	 * word 11 bit 14) so the front-end flushes its pending system-memory
+	 * stores before writing the release semaphore. The captured guest
+	 * QMDs carry FE_NONE, so a grid that completes with its data still
+	 * in the GPU's L2 releases the client while no store is host-visible
+	 * - the post-dispatch store-loss signature. The release ordering then
+	 * guarantees the host's retire scan and copy-out can never observe a
+	 * completion whose data has not landed. 0 (default) keeps the
+	 * guest's captured value.
+	 */
+	if (gsp_phys_gr_rel_membar_value() && !(qmd[11] & (1u << 14))) {
+		qmd[11] |= 1u << 14;
+		if (!gsp_phys_gr_rel_membar_log) {
+			gsp_phys_gr_rel_membar_log = true;
+			pr_info("vgsp-gr: r433 RELEASE_MEMBAR_TYPE forced to FE_SYSMEMBAR in the forwarded QMD (w11=0x%08x)\n",
+				qmd[11]);
+		}
+	}
+	/*
 	 * Two-step PCAS (gsp_phys_rmcall_gr_pcas_two_step): set the QMD's
 	 * REQUIRE_SCHEDULING_PCAS (w4 bit12) so the copy PCAS does not
 	 * schedule and the trailing schedule-only PCAS does.