wall2 session 115: decompose the first-fence wall - the sema service cannot decode the submit's GR pushes because the client VAS page directory is undiscoverable (walk_probe: discovered pdb=0x0; the COPY_SERVER_PDES candidate is garbage; the r496f vidmem discovery never runs) and the pushbuffer is noncontiguous; the RAM ring scan gives up after 12 slices before the pushes exist; ring pages ARE content-locatable by their GPFIFO entries and injectable via sema_map_add (fence_assist.py) but the ring pair alone does not unlock the push decode; next = extract the pdb from the guest kernel's RM objects (PDB injection) or scan vidmem with the ring pair as verifier

1 files changed, 112 insertions, 0 deletions

diff --git a/tools/guest-diag/wall2/fence_assist.py b/tools/guest-diag/wall2/fence_assist.py
new file mode 100644
index 0000000..4ea0b0c
--- /dev/null
+++ b/tools/guest-diag/wall2/fence_assist.py
@@ -0,0 +1,112 @@
+#!/usr/bin/env python3
+# fence_assist.py - content-locate the client's ring pages in guest RAM from the
+# service's own GPFIFO entry decodes (dmesg) and inject the TRUE VA->PA pairs
+# via sema_map_add, so the pump's push reads (and its pushbuffer pairing) have
+# a correct anchor.
+import mmap, re, struct, subprocess, sys, threading, time
+
+F = "/dev/shm/vgpu-guest-ram"
+PARAM = "/sys/module/vgsp/parameters/sema_map_add"
+
+def gpa_of(fo):
+    return fo if fo < 0x80000000 else fo - 0x80000000 + 0x100000000
+
+def inject(va, pa, ln=0x1000, flag=1):
+    cmd = "echo 0x%x,0x%x,0x%x,%d > %s" % (va & ~0xfff, pa & ~0xfff, ln, flag, PARAM)
+    r = subprocess.run(["sudo", "sh", "-c", cmd], capture_output=True)
+    print("INJECT va=0x%x pa=0x%x : %s" % (va & ~0xfff, pa & ~0xfff,
+          "ok" if r.returncode == 0 else "FAIL"), flush=True)
+
+def search(mm, pats, results):
+    CH = 8 << 20
+    size = len(mm)
+    off = 0
+    while off < size:
+        d = mm[off:off+CH]
+        for (name, pat) in pats.items():
+            if name in results:
+                continue
+            i = d.find(pat)
+            if i >= 0:
+                results[name] = gpa_of(off + i)
+        off += CH - 32
+
+def main():
+    dur = float(sys.argv[1]) if len(sys.argv) > 1 else 120
+    f = open(F, "rb")
+    mm = mmap.mmap(f.fileno(), 0, access=mmap.ACCESS_READ)
+    end = time.time() + dur
+    pats = {}       # name -> pattern bytes
+    ring_va = {}    # name -> ring VA
+    seen = set()    # raw entry lines processed
+    done = set()    # injected names
+    print("# fence_assist start (%.0fs)" % dur, flush=True)
+    while time.time() < end:
+        try:
+            with open("/tmp/opencode/dmsg_w.txt", "r", errors="ignore") as df:
+                tail = df.read().splitlines()[-6000:]
+            out = "\n".join(tail)
+        except OSError:
+            out = ""
+            tail = []
+        tail = [ln for ln in tail if "sema-chan:" in ln or "sema-push" in ln]
+        cur = {}
+        for ln in tail:
+            m = re.search(r"sema-chan: entry\[(\d+)\] h=0x([0-9a-f]+) eng=\d+ raw=([0-9a-f]+) va=0x([0-9a-f]+)", ln)
+            if m:
+                idx, h, raw, va = int(m.group(1)), m.group(2), int(m.group(3), 16), int(m.group(4), 16)
+                cur.setdefault(h, {})[idx] = raw
+                if idx == 0:
+                    ring_va[h] = va  # entry[0] va is the push VA (ring_va - 0x20000)
+        for h, ents in cur.items():
+            key = (h, tuple(sorted(ents.items())))
+            if key in seen or len(ents) < 2:
+                continue
+            seen.add(key)
+            name = h
+            pat = b"".join(struct.pack("<Q", ents[i]) for i in sorted(ents)[:2])
+            pats[name] = pat
+            print("# channel h=0x%s entries=%s pattern ready" % (h, sorted(ents)), flush=True)
+        if pats:
+            results = {}
+            threads = []
+            # split the map among 4 threads
+            LO = 0x100000000; HI = 0x180000000
+            size = len(mm)
+            step = size // 4
+            class Sl(shim := object):
+                def __init__(self, a, b):
+                    self.a, self.b = a, b
+            def worker(a, b):
+                CH = 8 << 20
+                off = a
+                while off < b:
+                    if off < 0x80000000 and b <= 0x80000000: pass
+                    d = mm[off:off+CH]
+                    for (nm, p) in list(pats.items()):
+                        if nm in results: continue
+                        i = d.find(p)
+                        if i >= 0:
+                            results[nm] = gpa_of(off + i)
+                    off += CH - 32
+            for k in range(4):
+                a = 0x80000000 + k * (0x80000000 // 4)
+                b = 0x80000000 + (k + 1) * (0x80000000 // 4)
+                t = threading.Thread(target=worker, args=(a, b))
+                t.start(); threads.append(t)
+            for t in threads: t.join()
+            for nm, gpa in results.items():
+                if nm in done: continue
+                done.add(nm)
+                # ring page content starts with entry[0]; the ring VA is the
+                # channel's gpfifo VA = we reconstruct: entry0 va is the push,
+                # ring = first "gpfifo=0x..." dmesg line for this h
+                m = re.search(r"sema-chan: h=0x%s eng=\d+ cid=\d+ gpfifo=0x([0-9a-f]+)" % nm, out)
+                rva = int(m.group(1), 16) if m else None
+                if rva:
+                    print("RING FOUND h=0x%s gpfifo_va=0x%x -> gpa=0x%x" % (nm, rva, gpa), flush=True)
+                    inject(rva, gpa, 0x1000)
+        time.sleep(0.6)
+    print("# fence_assist done, injected %d" % len(done), flush=True)
+
+main()