wall-2 session-77: vkCreateDevice PASSES - r682 0x7E event validated live (registered slot 13, EVPOST rc=0) and the completion word found/driven: the main-thread wait reads a u32 at +0x80 of a 16 KB rw-s /dev/nvidiactl notification mapping (should-wait = word != 1); a host write of 1 via the guest RAM file (PA from pagemap, file offset PA-0x80000000 above 4G) flips the wait and vkCreateDevice returns success (VKDEVICE ok family=0) - reproduced 3x (r683 manual, r684 nudger, r684d probe+single-word). Tools: t79.py (wait-chain resolver), guest_words.sh, nudge.sh; README-session77.md records the recipe, the residual guest event-dispatch gap (records consumed, notification word not written), and the -4/gdb-attach cautions.

1 files changed, 99 insertions, 0 deletions

diff --git a/tools/guest-diag/wall2/t79.py b/tools/guest-diag/wall2/t79.py
new file mode 100644
index 0000000..c2fe381
--- /dev/null
+++ b/tools/guest-diag/wall2/t79.py
@@ -0,0 +1,99 @@
+import gdb, sys
+
+inf = gdb.selected_inferior()
+pid = inf.pid
+base = None
+for line in open("/proc/%d/maps" % pid):
+    if "libnvidia-eglcore.so.570.144" in line:
+        parts = line.split()
+        lo, hi = [int(x, 16) for x in parts[0].split('-')]
+        off = int(parts[2], 16)
+        if off == 0:
+            base = lo
+            break
+if base is None:
+    print("EGLBASE not found"); gdb.execute("detach"); sys.exit(1)
+print("EGLBASE 0x%x PID %d" % (base, pid))
+
+maps = []
+for line in open("/proc/%d/maps" % pid):
+    parts = line.split()
+    try:
+        lo, hi = [int(x, 16) for x in parts[0].split('-')]
+        maps.append((lo, hi, parts[1], parts[-1] if len(parts) > 5 else "anon"))
+    except Exception:
+        pass
+
+def resolve(addr):
+    for lo, hi, perm, name in maps:
+        if lo <= addr < hi:
+            return "0x%x-0x%x %s %s" % (lo, hi, perm, name)
+    return "?"
+
+def rd(a, n):
+    return inf.read_memory(a, n).tobytes()
+def u32(a):
+    return int.from_bytes(rd(a, 4), 'little')
+def u64(a):
+    return int.from_bytes(rd(a, 8), 'little')
+
+state = {"done": False}
+
+class B(gdb.Breakpoint):
+    def __init__(self, spec, fn, limit=100000):
+        super().__init__(spec, internal=False)
+        self.fn = fn; self.limit = limit; self.hits = 0
+        self.silent = True
+    def stop(self):
+        self.hits += 1
+        try:
+            stop = bool(self.fn(self))
+        except Exception as e:
+            print("ERR@0x%x %s" % (int(gdb.parse_and_eval("$pc")), e))
+            stop = False
+        return stop or self.hits >= self.limit
+
+def loophead(bp):
+    if state["done"]:
+        return False
+    state["done"] = True
+    rbx = int(gdb.parse_and_eval("$rbx"))
+    sub = u64(rbx+0x70)
+    print("WAIT rbx=0x%x sub=0x%x" % (rbx, sub))
+    try:
+        obj2 = u64(sub+0x58)
+        off = u32(obj2+0x60)
+        holder = u64(obj2+0x58)
+        base2 = u64(holder+0x58)
+        word_addr = base2 + off
+        val = u32(word_addr)
+        print("WAIT obj2=0x%x off=0x%x holder=0x%x base=0x%x word=0x%x val=0x%x" %
+              (obj2, off, holder, base2, word_addr, val))
+        print("WAIT word map:", resolve(word_addr))
+        print("WAIT holder obj2+0x50=0x%x obj2+0x64=0x%x" % (u64(obj2+0x50), u32(obj2+0x64)))
+        try:
+            hd = rd(holder, 0x30)
+            print("WAIT holder dump:", " ".join("%02x" % b for b in hd))
+        except Exception as e:
+            print("WAIT holder dump err", e)
+    except Exception as e:
+        print("WAIT chain err", e)
+    # dump the client's nvidiactl rw-s mappings
+    print("WAIT nvidiactl maps:")
+    for lo, hi, perm, name in maps:
+        if "nvidiactl" in name and "rw-s" in perm:
+            print("  0x%x-0x%x size=0x%x" % (lo, hi, hi-lo))
+    return True
+
+B("*0x%x" % (base+0xdcebd9), loophead, 1)
+
+try:
+    gdb.execute("continue")
+except gdb.error as e:
+    print("CONT-ERR %s" % e)
+print("TRACE-END")
+try:
+    gdb.execute("detach")
+except gdb.error as e:
+    print("DETACH-ERR %s" % e)
+gdb.execute("quit")