Initial commit — leak-hunt project complete

Five bugs identified and patched in retail Asheron's Call client:
- v3b: palette refcount over-increment (3-byte NOP at two sites)
- v5: RenderSurface PurgeResource no-op stub (vtable slot 2 thunk)
- v11: two dangling-pointer crash guards (NULL-check + reorder)
- v14: CEnvCell::Destroy ClipPlaneList leak (18-byte JMP to cleanup thunk)
- v22: unpacker stale-pointer SEH guard (whole-function __try/__except)

All five ship in leakfix.dll (117 KB, SHA d282f23c…) which is loaded
by acclient.exe at process start via PE import table patching by
tools/install_leakfix.py.

Controlled 15-client fleet soak: unpatched control died at 26h with
palette exhaustion; all 14 patched clients survived past that point
and reached ≥5-day uptime.

Residual ~15 MB/h growth traced to d3d9.dll's internal slab allocator
(260KB surface backing buffers retained after Release). See REPORT.md
§10 for the full investigation; conclusion is that it's unfixable from
outside d3d9.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
acbot 2026-05-23 21:05:17 +02:00
commit 57b5e43d0e
199 changed files with 1648333 additions and 0 deletions

108
tools/position_host_v2.py Normal file
View file

@ -0,0 +1,108 @@
"""position_host_v2.py <pid> -- Position is 72 bytes (not 96).
For each Position vt hit:
- Detect array adjacency at stride 72.
- Look at offsets -56..-4 for host vtables.
- Bucket: (array-element, ppv-wrapper, host-embedded, solo).
"""
import ctypes, ctypes.wintypes as wt, struct, sys
from collections import Counter
POSITION_VT = 0x00797910
SIZEOF_POSITION = 72 # vt + objcell_id + Frame(64)
ACMIN, ACMAX = 0x00400000, 0x00900000
PROCESS_VM_READ = 0x10
PROCESS_QUERY_INFORMATION = 0x400
class MBI(ctypes.Structure):
_fields_ = [('BaseAddress', ctypes.c_void_p),
('AllocationBase', ctypes.c_void_p),
('AllocationProtect', wt.DWORD),
('PartitionId', wt.WORD),
('RegionSize', ctypes.c_size_t),
('State', wt.DWORD),
('Protect', wt.DWORD),
('Type', wt.DWORD)]
k = ctypes.windll.kernel32
k.OpenProcess.argtypes = [wt.DWORD, wt.BOOL, wt.DWORD]; k.OpenProcess.restype = wt.HANDLE
k.CloseHandle.argtypes = [wt.HANDLE]; k.CloseHandle.restype = wt.BOOL
k.ReadProcessMemory.argtypes = [wt.HANDLE, wt.LPCVOID, wt.LPVOID, ctypes.c_size_t,
ctypes.POINTER(ctypes.c_size_t)]
k.ReadProcessMemory.restype = wt.BOOL
k.VirtualQueryEx.argtypes = [wt.HANDLE, ctypes.c_void_p, ctypes.POINTER(MBI), ctypes.c_size_t]
k.VirtualQueryEx.restype = ctypes.c_size_t
def classify(data, off, pos_set):
# array adjacency at stride 72
if off >= SIZEOF_POSITION and (off - SIZEOF_POSITION) in pos_set:
return ('array_inner', None)
if (off + SIZEOF_POSITION) in pos_set:
return ('array_head', None)
# Look for any acclient code-range vtable in -56..-4
candidate_offs = list(range(-56, 0, 4))
found = None
for d in candidate_offs:
if off + d < 0: continue
v = struct.unpack_from("<I", data, off + d)[0]
if ACMIN <= v <= ACMAX:
# check vtable plausibility — slot 0 should point to a code-page
# we can't read .text from this script easily — keep just the vtable
found = (d, v)
break
if found:
return ('embedded', found)
return ('solo', None)
def scan(pid):
h = k.OpenProcess(PROCESS_VM_READ | PROCESS_QUERY_INFORMATION, False, pid)
if not h:
print(f"OpenProcess err={ctypes.get_last_error()}"); return 1
buckets = Counter()
host_at_off = Counter() # (off, vtable) -> count
total = 0
mbi = MBI(); addr = 0
while k.VirtualQueryEx(h, addr, ctypes.byref(mbi), ctypes.sizeof(mbi)):
pr = mbi.Protect & 0xff
if (mbi.State == 0x1000 and mbi.Type == 0x20000
and pr in (0x04, 0x40)):
buf = (ctypes.c_ubyte * mbi.RegionSize)()
sz = ctypes.c_size_t(0)
if k.ReadProcessMemory(h, mbi.BaseAddress, buf, mbi.RegionSize, ctypes.byref(sz)):
data = bytes(buf[:sz.value])
end = (len(data) // 4) * 4
pos_offs = []
for off in range(0, end, 4):
if struct.unpack_from("<I", data, off)[0] == POSITION_VT:
pos_offs.append(off)
pos_set = set(pos_offs)
for off in pos_offs:
total += 1
bucket, ev = classify(data, off, pos_set)
buckets[bucket] += 1
if bucket == 'embedded':
host_at_off[ev] += 1
addr = (mbi.BaseAddress or 0) + mbi.RegionSize
if addr >= 0x80000000:
break
print(f"PID {pid}: {total} Position instances")
for b, n in buckets.most_common():
pct = 100.0 * n / total
print(f" {b:>15}: {n:>7} ({pct:5.1f}%)")
print()
print("Top (offset, host-vtable) combos for 'embedded' bucket:")
for (off, vt), n in host_at_off.most_common(20):
pct = 100.0 * n / total
print(f" off={off:+4d} vt=0x{vt:08x} count={n:>6} ({pct:.2f}%)")
k.CloseHandle(h)
return 0
if __name__ == "__main__":
sys.exit(scan(int(sys.argv[1])))