From 54ca82d81bacb56197a607d0039ca6a015f5ac44 Mon Sep 17 00:00:00 2001
From: Arthur Hanson Rasmusson <arthur@vgpu.io>
Date: Wed, 23 Sep 2026 07:05:45 -0400
Subject: userspace/cuda: libcuda analysis tree (debug-focused), guest ioctl
 tracer

Analysis tooling for debugging CUDA execution in Open-IOV guests:
- userspace/cuda/570.144/: fetch a library from a running guest (nc),
  objdump helpers, crash ip -> file vaddr + symbol mapping, and Ghidra
  headless import/analysis/decompile scripts (project kept so single
  functions decompile in seconds). The purpose is debugging correctness
  and performance of CUDA in Open-IOV VMs (not a reimplementation);
  extracted binaries and decompiled output are gitignored.
- tools/guest-diag/ioctl_trace.c: ptrace tracker for the NVIDIA driver
  ioctls of a child (libcuda issues raw syscalls, so LD_PRELOAD sees
  nothing). Decodes RM_ALLOC (class) and RM_CONTROL (cmd) arguments;
  this is how the cuCtxCreate crash sequence was captured.
- tools/test/cuda_drv_test.c: unbuffered + per-call markers so a crash
  identifies the CUDA call it happened in.
---
 userspace/cuda/570.144/scripts/fetch_from_guest.sh | 57 ++++++++++++++++++++++
 1 file changed, 57 insertions(+)
 create mode 100755 userspace/cuda/570.144/scripts/fetch_from_guest.sh

(limited to 'userspace/cuda/570.144/scripts/fetch_from_guest.sh')

diff --git a/userspace/cuda/570.144/scripts/fetch_from_guest.sh b/userspace/cuda/570.144/scripts/fetch_from_guest.sh
new file mode 100755
index 0000000..6ed24f1
--- /dev/null
+++ b/userspace/cuda/570.144/scripts/fetch_from_guest.sh
@@ -0,0 +1,57 @@
+#!/bin/bash
+# SPDX-License-Identifier: BSD-3-Clause
+#
+# fetch_from_guest.sh - copy a file out of a running Open-IOV guest.
+#
+# The guest agent is used to start a netcat transfer from the guest to the
+# host (QEMU user networking: the host is 10.0.2.2), which is much faster and
+# more robust than pushing tens of megabytes through the agent in base64
+# chunks.
+#
+# Usage: scripts/fetch_from_guest.sh <guest-path> [guest-bind-ip]
+#        e.g. scripts/fetch_from_guest.sh \
+#               /usr/lib/x86_64-linux-gnu/libcuda.so.570.144
+set -e
+
+HERE="$(cd "$(dirname "$0")" && pwd)"
+RUN="$(cd "$HERE/.." && pwd)/run"
+VMEXEC="$HERE/../../../scripts/vgpu_vm.py"
+PORT="${PORT:-47311}"
+
+GUEST_PATH="${1:?usage: $0 <guest-path> [guest-bind-ip]}"
+HOST_IP="${2:-10.0.2.2}"
+OUT="$RUN/$(basename "$GUEST_PATH")"
+
+mkdir -p "$RUN"
+
+# Guest-side md5 for verification
+GUEST_MD5=$("$VMEXEC" exec "md5sum '$GUEST_PATH'" 2>/dev/null | awk '{print $1}')
+[ -n "$GUEST_MD5" ] || { echo "cannot stat $GUEST_PATH in guest"; exit 1; }
+
+echo "[*] guest md5: $GUEST_MD5"
+echo "[*] listening on :$PORT -> $OUT"
+rm -f "$OUT"
+
+nc -l "$PORT" > "$OUT" &
+NCPID=$!
+sleep 1
+
+"$VMEXEC" exec "setsid sh -c 'nc $HOST_IP $PORT < $GUEST_PATH' >/dev/null 2>&1 &" >/dev/null 2>&1 || true
+
+# Wait for the transfer to settle (size stable for two checks)
+prev=0
+for _ in $(seq 1 60); do
+    sleep 2
+    cur=$(stat -c%s "$OUT" 2>/dev/null || echo 0)
+    [ "$cur" -gt 0 ] && [ "$cur" = "$prev" ] && break
+    prev=$cur
+done
+wait $NCPID 2>/dev/null || true
+
+HOST_MD5=$(md5sum "$OUT" | awk '{print $1}')
+echo "[*] host  md5: $HOST_MD5"
+if [ "$GUEST_MD5" != "$HOST_MD5" ]; then
+    echo "[FAIL] md5 mismatch"
+    exit 1
+fi
+echo "[ok] $OUT ($(stat -c%s "$OUT") bytes)"
-- 
cgit v1.2.3