From c3a295efd1b1132bbaa5d422cd05b3fa8e89a8bf Mon Sep 17 00:00:00 2001
From: Arthur Hanson Rasmusson <arthur@vgpu.io>
Date: Mon, 21 Sep 2026 13:06:51 -0400
Subject: kernel: Fix GSP emulation shadow binding, eventfd wiring, RPC
 livelocks + docs suite + repo reorg

CRITICAL FIXES (guest driver bring-up):
- gsp_emulation.c: emulation engine bound to the WRONG BAR0 - it polled the
  host physical BAR0 (bars[0].vaddr ioremap) for the doorbell and read RPCs
  from a local dma_alloc_wc buffer, while the guest writes land in the
  vzalloc'd bar0_shadow. The RPC path could never work; PBA writes even
  corrupted the host GPU's physical BAR0+0x3000. gsp_emu_init now binds
  exclusively to bar0_shadow (doorbell/mailbox/PBA aliases;
  shared_mem_dma==0 marks the alias so cleanup never dma_free's it).
- main.c SET_IRQS: DATA_EVENTFD eventfds were DISCARDED ('TODO' + kfree) -
  the guest never received MSI-X completions. Full wiring now:
  eventfd_ctx_fdget per vector, fd -1 clears, dev_close releases refs.
  gsp_emu_inject_completion_interrupt looks up vgpu->irqs[0].trigger LIVE
  (init-time copy was permanently NULL since QEMU wires after gsp_emu_init).
- gsp_rpc_client.c: BAR_TRAP/MIGRATE in emulation mode called
  gsp_rpc_submit_raw which rings the SAME doorbell the thread polls -
  self-triggered RPC livelock + multi-second stalls. Now fail fast with
  -ENOTSUPP + pr_warn_ratelimited (guest BAR access is direct MMIO).

MORE FIXES:
- main.c: nv_vgpu_config_write returned SIZE_MAX (while(count--) wrap) and
  was dead code while the VFIO write handler did unfiltered byte copies
  (guest could rewrite vendor ID/BARs). Return fixed; VFIO write handler
  now routes through the per-register filter.
- kernel/Makefile: M=$(PWD) used the env var which is stale when invoked
  via the top-level make (pointed at repo root -> kbuild silently built
  NOTHING; explains every 'stale .ko' incident). Now M=$(CURDIR).
- Warnings sweep: header prototypes for mdev/type functions, format casts
  in gsp_comm.c DRY-RUN logs, unused variable.

ROBUSTNESS (harness/tooling):
- vgpu_vm.py: run had no timeout (start could block forever);
  guest_shell recv could block forever on a wedged guest. Both now bounded;
  guest_shell pre-flights guest-ping and reports wedge diagnostics.
- stack_manager.sh: qemu/qemu-debug now launch via the vgpu_vm.py harness
  (workflow rule: never raw QEMU).

REPO REORGANIZATION:
- driver/ (legacy guest-side gsp-vgpu.ko) moved to legacy-driver-guest/
  (reference only, not built; README explains). 3 legacy un-buildable test
  files moved to legacy-driver-guest/kernel-tests/. Top-level Makefile
  cleaned of the dead DRIVER_DIR reference.

DOCUMENTATION SUITE (new):
- docs/GSP_EMULATION_ARCHITECTURE.md - emulator deep-dive: shadow BAR0
  model, doorbell protocol, dispatch table, MSI-X path, lifecycle, memory-
  model caveats
- docs/DEBUGGING.md - QEMU GDB stub workflow, serial console, QMP NMI,
  failure taxonomy, full bring-up validation checklist, EPT-livelock case
  study, version-matrix discipline
- docs/ONBOARDING.md - repo tour, coding standards (incl. virt_to_phys /
  dma_addr_t / get-put rules), first build & test
- docs/VERSION_UPGRADE.md - end-to-end new-driver-version procedure
  (firmware fetch, Ghidra analysis, configs, signatures, validation)
- docs/PERFORMANCE.md - bare-metal A/B methodology + targets
- README.md doc index; STATE.md refreshed; DEVELOPMENT_WORKFLOW.md corrected
  (load order: open-iov-vfio BEFORE nvidia; stock-driver blacklist note)
---
 legacy-driver-guest/Makefile | 44 ++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 44 insertions(+)
 create mode 100644 legacy-driver-guest/Makefile

(limited to 'legacy-driver-guest/Makefile')

diff --git a/legacy-driver-guest/Makefile b/legacy-driver-guest/Makefile
new file mode 100644
index 0000000..4675cbf
--- /dev/null
+++ b/legacy-driver-guest/Makefile
@@ -0,0 +1,44 @@
+# GSP vGPU-IO Driver Makefile
+
+obj-m += gsp-vgpu.o
+
+gsp-vgpu-y := \
+    core/gsp_core.o \
+    rpc/gsp_rpc.o \
+    vf/gsp_vf.o \
+    bar/gsp_bar.o \
+    wpr/gsp_wpr.o \
+    migration/gsp_migration.o \
+    debugfs/gsp_debugfs.o
+
+ccflags-y += -I$(src)/include
+ccflags-y += -I$(src)/../kernel/include
+
+# Build against the kernel source
+KDIR ?= /lib/modules/$(shell uname -r)/build
+
+all:
+	$(MAKE) -C $(KDIR) M=$(PWD) modules
+
+clean:
+	$(MAKE) -C $(KDIR) M=$(PWD) clean
+
+install:
+	$(MAKE) -C $(KDIR) M=$(PWD) modules_install
+
+load: all
+	sudo insmod gsp-vgpu.ko firmware_name=gsp-570.144.fwimage.bin
+
+unload:
+	sudo rmmod gsp-vgpu
+
+test: all load
+	@echo "Driver loaded, checking status..."
+	sleep 2
+	dmesg -T | tail -20
+	@echo "Checking debugfs..."
+	ls -la /sys/kernel/debug/gsp-vgpu/ 2>/dev/null || echo "Debugfs not available"
+	@echo "Checking device nodes..."
+	ls -la /dev/gsp-vgpu* 2>/dev/null || echo "No device nodes"
+
+.PHONY: all clean install load unload test
\ No newline at end of file
-- 
cgit v1.2.3