340 lines
14 KiB
Python
Executable File
340 lines
14 KiB
Python
Executable File
#!/usr/bin/env python3
|
|
"""CMP 170HX batch card checker - guided one-card-at-a-time workflow (23 cards).
|
|
|
|
Per card: detect GPU -> auto serial -> VBIOS backup -> PCIe link/AER/config checks
|
|
-> retrain + rescan tests -> dmesg scrape -> cmpunlocker verify.sh (read-only)
|
|
-> optional 5-min Vulkan VRAM stress (last step, ask yes/no) -> cards/<serial>/report.json.
|
|
|
|
Scoring (lenient): FAIL only on no-device/link-down; WARN on correctable AER/Xid/
|
|
width< x16/verify issues.
|
|
"""
|
|
import argparse
|
|
import json
|
|
import sys
|
|
import time
|
|
from pathlib import Path
|
|
|
|
import cxlib as X
|
|
from cxlib import (C, ask, detect_gpus, err, info, now_iso, ok, sanitize, step, warn)
|
|
|
|
TOTAL_DEFAULT = X.DEFAULT_TOTAL
|
|
|
|
|
|
# ---------------------------------------------------------------- scoring
|
|
|
|
def score(rep):
|
|
fails, warns = [], []
|
|
if not rep.get("bdf"):
|
|
fails.append("no CMP 170HX device detected on the bus")
|
|
link = rep.get("link", {})
|
|
if rep.get("bdf"):
|
|
if link.get("lspci_rc") not in (0, None):
|
|
fails.append("lspci could not read the device")
|
|
if link.get("lnksta_width") in ("x0", "x1", None) or not link.get("lnksta_speed"):
|
|
fails.append(f"link down or untrained: {link.get('lnksta_raw') or 'no LnkSta'}")
|
|
width = link.get("lnksta_width")
|
|
if width and width != "x16":
|
|
warns.append(f"link width {width} (capacitor mod expects x16 - mod likely "
|
|
f"missing/incomplete on this card)")
|
|
if link.get("lnksta_gen") == 1:
|
|
warns.append("link negotiated Gen1 only (cmpunlocker Gen2 patch/service not active?)")
|
|
if rep.get("rescan", {}).get("ok") is False:
|
|
fails.append("device lost after bus rescan")
|
|
if rep.get("retrain", {}).get("ok") is False:
|
|
fails.append("link did not survive retrain")
|
|
aer = rep.get("aer_after", {})
|
|
aer_before = rep.get("aer_before", {})
|
|
if (aer.get("ce_active") or aer.get("parent_ce_active")
|
|
or (aer.get("aer_correctable_sum", 0) > aer_before.get("aer_correctable_sum", 0))):
|
|
warns.append("correctable AER errors present/incremented")
|
|
if aer.get("ue_active"):
|
|
fails.append(f"uncorrectable AER errors active: {aer['ue_active']}")
|
|
dm = rep.get("dmesg", {})
|
|
if dm.get("errors"):
|
|
warns.append(f"{len(dm['errors'])} kernel error line(s) related to this card (see dmesg.log)")
|
|
vu = rep.get("vulkan_test", {})
|
|
if vu.get("requested") and vu.get("ran"):
|
|
if vu.get("tool_errors"):
|
|
warns.append("errors reported during Vulkan VRAM stress")
|
|
if dm.get("errors") and vu.get("ran"):
|
|
warns.append("kernel errors around VRAM stress window")
|
|
if not rep.get("bios", {}).get("ok"):
|
|
warns.append("VBIOS backup failed/incomplete")
|
|
ver = rep.get("cmpunlocker_verify", {})
|
|
if ver.get("ran") and ver.get("status") not in ("unlocked-ok",):
|
|
warns.append(f"cmpunlocker verify status: {ver.get('status')}")
|
|
|
|
result = "FAIL" if fails else ("WARN" if warns else "PASS")
|
|
return result, fails, warns
|
|
|
|
|
|
# ---------------------------------------------------------------- one card
|
|
|
|
def find_gpu(timeout=45):
|
|
"""Wait for a CMP 170HX to appear, offering rescan retries."""
|
|
deadline = time.time() + timeout
|
|
while time.time() < deadline:
|
|
bdfs = detect_gpus()
|
|
if len(bdfs) == 1:
|
|
return bdfs[0]
|
|
if len(bdfs) > 1:
|
|
warn(f"multiple CMP 170HX devices present: {', '.join(bdfs)}")
|
|
return bdfs[0]
|
|
time.sleep(2)
|
|
warn("no CMP 170HX detected yet")
|
|
if ask("trigger PCI bus rescan and retry? (y/N)", "n").lower().startswith("y"):
|
|
if X.rescan_bus():
|
|
ok("bus rescanned")
|
|
else:
|
|
err("rescan not permitted - reseat the card and press Enter")
|
|
input()
|
|
return find_gpu(timeout=30)
|
|
return None
|
|
|
|
|
|
def process_card(index, total, args):
|
|
header = f"Card {index}/{total}"
|
|
step(header)
|
|
bdf = find_gpu()
|
|
if not bdf:
|
|
err("no device - skipping this card")
|
|
return None
|
|
devid = ""
|
|
for line in X.run(["lspci", "-D", "-s", bdf, "-nn"])["out"].splitlines():
|
|
if "[10de:" in line:
|
|
devid = line[line.index("[10de:") + 1:line.index("[10de:") + 10].rstrip("]")
|
|
ok(f"device found at {bdf} ({devid})")
|
|
|
|
nf = X.nvflash_bin(args)
|
|
serial, serial_src = X.get_serial(nf, args)
|
|
folder = X.CARDS_DIR / sanitize(serial)
|
|
folder.mkdir(parents=True, exist_ok=True)
|
|
info(f"folder: {folder}")
|
|
|
|
rep = {
|
|
"card_index": index, "total": total, "serial": serial, "serial_source": serial_src,
|
|
"started_at": now_iso(), "bdf": bdf, "device_id": devid, "host": X.run(["uname", "-n"])["out"].strip(),
|
|
"kernel": X.run(["uname", "-r"])["out"].strip(),
|
|
}
|
|
|
|
step(f"[{index}/{total}] VBIOS backup")
|
|
rep["bios"] = X.save_bios(nf, folder / "bios.rom", args)
|
|
(ok if rep["bios"]["ok"] else warn)(f"bios: {rep['bios']['method'] or 'FAILED'} "
|
|
f"{rep['bios']['size']} bytes - {rep['bios']['note']}")
|
|
|
|
step(f"[{index}/{total}] PCIe link + config")
|
|
link, lspci_txt = X.check_link(bdf)
|
|
rep["link"] = link
|
|
(folder / "lspci.txt").write_text(lspci_txt)
|
|
(folder / "config_space.hex").write_text(X.dump_config(bdf))
|
|
info(f"LnkSta: {link.get('lnksta_raw') or 'n/a'} (setpci gen={link.get('setpci_current_gen')})")
|
|
rep["aer_before"] = X.aer_snapshot(bdf)
|
|
|
|
step(f"[{index}/{total}] retrain + rescan tests")
|
|
rep["retrain"] = X.retrain_test(bdf)
|
|
info(f"retrain: ok={rep['retrain']['ok']} - {rep['retrain']['note']}")
|
|
rep["rescan"] = X.rescan_test(bdf)
|
|
info(f"rescan: ok={rep['rescan']['ok']} - {rep['rescan']['note']}")
|
|
rep["aer_after"] = X.aer_snapshot(bdf)
|
|
link2, lspci2 = X.check_link(bdf)
|
|
rep["link_after"] = link2
|
|
if lspci2:
|
|
(folder / "lspci_after.txt").write_text(lspci2)
|
|
|
|
step(f"[{index}/{total}] kernel log scrape")
|
|
dm = X.dmesg_capture(bdf)
|
|
rep["dmesg"] = dm
|
|
(folder / "dmesg.log").write_text("\n".join(dm.get("related", [])))
|
|
info(f"{dm.get('note')} (source: {dm.get('source')})")
|
|
if dm.get("errors"):
|
|
for e in dm["errors"][-5:]:
|
|
warn(e.strip()[:160])
|
|
|
|
step(f"[{index}/{total}] nvidia-smi + cmpunlocker verify")
|
|
rep["nvidia_smi"] = X.nvidia_smi_info()
|
|
rep["cmpunlocker_verify"] = X.run_verify_unlocker()
|
|
v = rep["cmpunlocker_verify"]
|
|
(folder / "verify_unlocker.log").write_text(
|
|
"\n".join(v.get("tail", [])) or (v.get("note") or "not run"))
|
|
info(f"verify: {'ran rc=' + str(v.get('rc')) + ' -> ' + str(v.get('status')) if v.get('ran') else 'skipped - ' + str(v.get('note'))}")
|
|
|
|
step(f"[{index}/{total}] optional Vulkan VRAM test (last step)")
|
|
if args.vulkan == "never":
|
|
rep["vulkan_test"] = {"requested": False, "ran": False, "note": "disabled via --vulkan never"}
|
|
elif args.vulkan == "always":
|
|
rep["vulkan_test"] = X.run_vulkan_test()
|
|
else:
|
|
if ask("Run 5-min Vulkan VRAM stress test now? (y/N)", "n").lower().startswith("y"):
|
|
rep["vulkan_test"] = X.run_vulkan_test()
|
|
else:
|
|
rep["vulkan_test"] = {"requested": False, "ran": False, "note": "operator declined"}
|
|
info("vulkan test skipped")
|
|
|
|
result, fails, warns = score(rep)
|
|
rep.update(finished_at=now_iso(), result=result, failures=fails, warnings=warns)
|
|
(folder / "report.json").write_text(json.dumps(rep, indent=2))
|
|
|
|
print()
|
|
if result == "PASS":
|
|
ok(f"{serial}: PASS")
|
|
elif result == "WARN":
|
|
warn(f"{serial}: WARN")
|
|
else:
|
|
err(f"{serial}: FAIL")
|
|
for f in fails:
|
|
err(" FAIL: " + f)
|
|
for w in warns:
|
|
warn(" WARN: " + w)
|
|
info(f"report: {folder / 'report.json'}")
|
|
return rep
|
|
|
|
|
|
# ---------------------------------------------------------------- progress
|
|
|
|
def load_progress():
|
|
try:
|
|
return json.loads(X.PROGRESS_FILE.read_text())
|
|
except Exception:
|
|
return {"done": []}
|
|
|
|
|
|
def save_progress(prog):
|
|
X.PROGRESS_FILE.write_text(json.dumps(prog, indent=2))
|
|
|
|
|
|
def scoreboard(results):
|
|
step("Scoreboard")
|
|
counts = {"PASS": 0, "WARN": 0, "FAIL": 0}
|
|
for r in results:
|
|
if not r:
|
|
continue
|
|
counts[r["result"]] = counts.get(r["result"], 0) + 1
|
|
color = {"PASS": C.GREEN, "WARN": C.YELLOW, "FAIL": C.RED}[r["result"]]
|
|
print(f" {color}{r['result']:<4}{C.RESET} #{r['card_index']:>2} "
|
|
f"{r['serial']:<24} {r.get('bdf') or '-':<12} "
|
|
f"{r.get('link', {}).get('lnksta_width') or '?':<4} "
|
|
f"{r.get('link', {}).get('lnksta_speed') or '?'}")
|
|
skipped = [r for r in results if r is None]
|
|
print(f"\n PASS={counts.get('PASS', 0)} WARN={counts.get('WARN', 0)} "
|
|
f"FAIL={counts.get('FAIL', 0)} skipped={len(skipped)} "
|
|
f"total_seen={len(results)}/{TOTAL_DEFAULT}")
|
|
|
|
|
|
# ---------------------------------------------------------------- demo
|
|
|
|
def demo(args):
|
|
"""Validate report pipeline without hardware: writes cards/DEMO-*."""
|
|
step("Demo mode (no hardware)")
|
|
args.vulkan = "never"
|
|
args.serial = "DEMO-SERIAL-001"
|
|
args.skip_bios = True
|
|
real_find = globals()["find_gpu"]
|
|
globals()["find_gpu"] = lambda timeout=0: "0000:0a:00.0"
|
|
|
|
class FakeRun:
|
|
pass
|
|
|
|
orig_detect, orig_check = X.detect_gpus, X.check_link
|
|
orig_aer, orig_dm, orig_cfg = X.aer_snapshot, X.dmesg_capture, X.dump_config
|
|
orig_retrain, orig_rescan = X.retrain_test, X.rescan_test
|
|
orig_smi, orig_verify = X.nvidia_smi_info, X.run_verify_unlocker
|
|
X.detect_gpus = lambda: ["0000:0a:00.0"]
|
|
X.check_link = lambda b: ({"lnksta_speed": "5GT/s", "lnksta_width": "x4", "lnksta_gen": 2,
|
|
"lnkcap_speed": "8GT/s", "lnkcap_width": "x16",
|
|
"lnksta_raw": "LnkSta: Speed 5GT/s, Width x4, TrErr-",
|
|
"setpci_current_gen": 2, "lspci_rc": 0}, "demo lspci output\n")
|
|
X.aer_snapshot = lambda b: {"aer_sysfs_correctable": None, "aer_sysfs_fatal": None,
|
|
"aer_correctable_sum": 0, "ce_active": [], "ue_active": [],
|
|
"parent_bdf": None, "parent_ce_active": []}
|
|
X.dmesg_capture = lambda b: {"source": "demo", "related": ["demo line"], "errors": [],
|
|
"note": "demo"}
|
|
X.dump_config = lambda b: "demo config space dump\n"
|
|
X.retrain_test = lambda b: {"attempted": True, "ok": True, "note": "x4 -> x4",
|
|
"width_before": "x4", "width_after": "x4"}
|
|
X.rescan_test = lambda b: {"attempted": True, "ok": True, "note": "re-enumerated"}
|
|
X.nvidia_smi_info = lambda: {"available": False}
|
|
X.run_verify_unlocker = lambda: {"ran": False, "note": "demo"}
|
|
try:
|
|
rep = process_card(1, TOTAL_DEFAULT, args)
|
|
finally:
|
|
globals()["find_gpu"] = real_find
|
|
X.detect_gpus, X.check_link = orig_detect, orig_check
|
|
X.aer_snapshot, X.dmesg_capture, X.dump_config = orig_aer, orig_dm, orig_cfg
|
|
X.retrain_test, X.rescan_test = orig_retrain, orig_rescan
|
|
X.nvidia_smi_info, X.run_verify_unlocker = orig_smi, orig_verify
|
|
return rep
|
|
|
|
|
|
# ---------------------------------------------------------------- main
|
|
|
|
def main():
|
|
global TOTAL_DEFAULT
|
|
ap = argparse.ArgumentParser(description="CMP 170HX guided 23-card checker")
|
|
ap.add_argument("--preflight", action="store_true", help="only run tool check/install/clone")
|
|
ap.add_argument("--demo", action="store_true", help="run pipeline with fake hardware (self-test)")
|
|
ap.add_argument("--cards", type=int, default=TOTAL_DEFAULT, help="total cards (default 23)")
|
|
ap.add_argument("--start", type=int, default=1, help="first card index")
|
|
ap.add_argument("--nvflash", help="path to nvflash binary")
|
|
ap.add_argument("--serial", help="override serial for the next card (single-card run)")
|
|
ap.add_argument("--skip-bios", action="store_true", help="skip VBIOS backup")
|
|
ap.add_argument("--vulkan", choices=("ask", "always", "never"), default="ask",
|
|
help="5-min Vulkan VRAM test policy (default ask, runs as last step)")
|
|
ap.add_argument("--no-install", action="store_true", help="do not auto-install missing packages")
|
|
ap.add_argument("--no-clone", action="store_true", help="do not clone harness repos")
|
|
ap.add_argument("--restart", action="store_true", help="ignore previous progress.json")
|
|
ap.add_argument("--no-pause", action="store_true", help="do not wait for card insertion")
|
|
args = ap.parse_args()
|
|
|
|
TOTAL_DEFAULT = args.cards
|
|
|
|
pf = X.preflight(auto_install=not args.no_install, do_clone=not args.no_clone)
|
|
if args.preflight:
|
|
return 0
|
|
if args.demo:
|
|
demo(args)
|
|
return 0
|
|
|
|
X.CARDS_DIR.mkdir(exist_ok=True)
|
|
prog = {"done": []} if args.restart else load_progress()
|
|
|
|
results = []
|
|
for i in range(args.start, args.cards + 1):
|
|
if str(i) in prog.get("done", []):
|
|
info(f"card {i} already done (progress.json) - skipping")
|
|
results.append(None)
|
|
continue
|
|
if not args.no_pause:
|
|
ans = ask(f"Insert card {i}/{args.cards}, then press Enter "
|
|
f"(s=skip this card, q=quit)", "")
|
|
if ans.lower() == "q":
|
|
break
|
|
if ans.lower() == "s":
|
|
results.append(None)
|
|
prog.setdefault("done", []).append(str(i))
|
|
prog.setdefault("skipped", []).append(str(i))
|
|
save_progress(prog)
|
|
continue
|
|
rep = process_card(i, args.cards, args)
|
|
results.append(rep)
|
|
if rep:
|
|
prog.setdefault("done", []).append(str(i))
|
|
save_progress(prog)
|
|
else:
|
|
if not ask("retry this card? (y/N)", "n").lower().startswith("y"):
|
|
break
|
|
|
|
if results:
|
|
scoreboard(results)
|
|
done = len([r for r in results if r])
|
|
info(f"{done} card(s) processed. Output in {X.CARDS_DIR}")
|
|
return 0
|
|
|
|
|
|
if __name__ == "__main__":
|
|
try:
|
|
sys.exit(main())
|
|
except KeyboardInterrupt:
|
|
print()
|
|
warn("interrupted - progress saved in progress.json")
|
|
sys.exit(130)
|