From 9200f35a11df0c021c08f55fbc04e08ac7c702a6 Mon Sep 17 00:00:00 2001
From: Arthur Hanson Rasmusson <arthur@vgpu.io>
Date: Wed, 7 Oct 2026 12:37:42 -0400
Subject: vgsp/gr-regs: per-GPC exception + activity + GPCMMU ESR readback

PGRAPH_EXCEPTION bit24 (GPC) with EXCEPTION1 GPC1:0=0b11 fires at every
forwarded QMD activation and the engine then saves/unloads. The per-GPC PRI
window (BAR0 0x500000 + gpc*0x8000) carries NV_PGPC_PRI_GPCCS_GPC_EXCEPTION
(0x2c90: PROP/ZCULL/GCC/SETUP/PES/TPC/GPCMMU0/GPCCS bits),
GPC_ACTIVITY1.GPCMMU0 (0x2c84: FAULTED=6) and the GPCMMU GLOBAL_ESR (0x324):
the post-mortem and the external sampler now record them to name the failing
GPC sub-unit (or the GPC MMU).
---
 kernel/gsp_phys_booter.c     | 14 ++++++++++++++
 tools/gr-regs/reg_sampler.py |  7 +++++++
 2 files changed, 21 insertions(+)

diff --git a/kernel/gsp_phys_booter.c b/kernel/gsp_phys_booter.c
index ee433e1..c70a79f 100644
--- a/kernel/gsp_phys_booter.c
+++ b/kernel/gsp_phys_booter.c
@@ -17021,6 +17021,20 @@ gr_page_unmapped:
 						ioread32(bar0 + 0x00405b00u),
 						ioread32(bar0 + 0x00400100u),
 						ioread32(bar0 + 0x0040013cu));
+				if (bar0) {
+					u32 g;
+
+					for (g = 0; g < 6; g++) {
+						u32 b = 0x00500000u +
+							g * 0x8000u;
+
+						pr_info("vgsp-gr: post-mortem GPC%u exc=0x%08x act1=0x%08x mmuesr=0x%08x\n",
+							g,
+							ioread32(bar0 + b + 0x2c90u),
+							ioread32(bar0 + b + 0x2c84u),
+							ioread32(bar0 + b + 0x324u));
+					}
+				}
 				if (bar0)
 					pr_info("vgsp-gr: SKED watermark[0..15]=0x%08x 0x%08x 0x%08x 0x%08x 0x%08x 0x%08x 0x%08x 0x%08x 0x%08x 0x%08x 0x%08x 0x%08x 0x%08x 0x%08x 0x%08x 0x%08x\n",
 						ioread32(bar0 + 0x004070a0u),
diff --git a/tools/gr-regs/reg_sampler.py b/tools/gr-regs/reg_sampler.py
index 25879ef..e66a299 100644
--- a/tools/gr-regs/reg_sampler.py
+++ b/tools/gr-regs/reg_sampler.py
@@ -36,6 +36,13 @@ REGS = [
     (0x400118, "PGRAPH_EXCEPTION1"),
     (0x40011C, "PGRAPH_EXCEPTION2"),
     (0x40013C, "PGRAPH_INTR_EN"),
+    (0x502C90, "GPC0_EXCEPTION"),
+    (0x502C84, "GPC0_ACTIVITY1"),
+    (0x50AC90, "GPC1_EXCEPTION"),
+    (0x512C90, "GPC2_EXCEPTION"),
+    (0x51AC90, "GPC3_EXCEPTION"),
+    (0x522C90, "GPC4_EXCEPTION"),
+    (0x52AC90, "GPC5_EXCEPTION"),
     (0x400700, "PGRAPH_STATUS"),
     (0x400504, "GRFIFO_STATUS"),
     (0x400704, "TRAPPED_ADDR"),
-- 
cgit v1.2.3