wall-2 forensics tools: GR channel-init push localization (session 73)

Tools and findings from the live wall-2 campaign (r674/r675): the vk_frame
client's GR channel-init push (va=0x4480000 len=1432) cannot be translated by
the sema service, so no release is applied and vkCreateDevice fails -4.

Captured: the RM window-record/memdesc layout (ring memdesc PA == the
service's validated ring pa; push memdesc PA injected live and read by the
service without a false-translation line), the CE-only shape of the service
rescue matcher, the notrace status of nvidia/modeset kprobes (QEMU gdb hbreak
works), and the ring-entry encoding from channelFillGpFifo/nvWriteGpEntry
(neither runs for this channel's kick).

New tools: wall2_resolver{2..5}.py, wall2_livecap{1..3}.py, RAM structure
scanners (scan_r673*.py, trace_push674.py), gdb675*.gdb probes, plus a
README with the ranked next steps.

1 files changed, 149 insertions, 0 deletions

diff --git a/tools/guest-diag/wall2/wall2_resolver4.py b/tools/guest-diag/wall2/wall2_resolver4.py
new file mode 100644
index 0000000..140aaa7
--- /dev/null
+++ b/tools/guest-diag/wall2/wall2_resolver4.py
@@ -0,0 +1,149 @@
+#!/usr/bin/env python3
+# wall2_resolver4.py - HOST-SIDE wall#2 resolver v4 (final recipe).
+#
+# Association proven on r675: the RM keeps, in ONE page, the client's channel
+# window records and their memdescs:
+#   push window record {VA=0x4480000, SIZE=0x20000}
+#   ring window record {VA=0x44a0000, SIZE=0x40000}
+#   push memdesc {0x20000, 0x03008000, FIRST_PA, ptr}
+#   ring memdesc {0x40000, 0x03008000, FIRST_PA, ptr}
+# where FIRST_PA is the PA of the window's FIRST VA page. Verified: the ring
+# memdesc's PA == the service's validated ring pa. So the push memdesc's PA ==
+# the PA of VA 0x4480000 (the push page the service cannot translate).
+#
+# Recipe: wait for a NEW ring line -> find the page containing the ring window
+# record {0x44a0000, 0x40000} -> require the sibling push window record
+# {0x4480000, 0x20000} and the memdescs in the same page -> cross-check the
+# ring memdesc PA == ring_pa -> inject 0x4480000 -> push memdesc PA (sudo).
+import subprocess, struct, time, sys, re, os
+
+RAM = "/dev/shm/vgpu-guest-ram"
+PARAM = "/sys/module/vgsp/parameters/sema_map_add"
+LOG = "/tmp/opencode/wall2_resolver4.log"
+PUSH_VA = 0x4480000
+RING_VA = 0x44a0000
+WAIT_RING_S = int(os.environ.get("W2_WAIT_RING", "420"))
+WATCH_S = int(os.environ.get("W2_WATCH", "180"))
+
+logf = open(LOG, "a", buffering=1)
+def log(*a):
+    s = " ".join(str(x) for x in a)
+    print(s, flush=True)
+    logf.write("[%s] %s\n" % (time.strftime("%H:%M:%S"), s))
+
+img = open(RAM, "rb", buffering=0)
+def gpa2off(pa):
+    if pa < 0x80000000: return pa
+    if pa < 0x180000000: return 0x80000000 + (pa - 0x100000000)
+    return None
+def off2gpa(off):
+    return off if off < 0x80000000 else 0x100000000 + (off - 0x80000000)
+def rd(pa, n):
+    off = gpa2off(pa)
+    if off is None: return None
+    img.seek(off); return img.read(n)
+
+def dmesg():
+    return subprocess.run(["sudo", "dmesg"], capture_output=True, text=True).stdout
+
+def inject(va, pa, ln=0x1000, ap=1):
+    cmd = "echo 0x%x,0x%x,0x%x,%d > %s" % (va, pa, ln, ap, PARAM)
+    r = subprocess.run(["sudo", "sh", "-c", cmd], capture_output=True, text=True)
+    if r.returncode == 0:
+        log("INJECT va=0x%x -> pa=0x%x len=0x%x OK" % (va, pa, ln))
+        return True
+    log("inject FAIL rc=%d %s" % (r.returncode, r.stderr.strip()))
+    return False
+
+def find_qpair(a, b):
+    """Find qword pairs {a,b}; returns [(page, off)]."""
+    img.seek(0, 2); fsz = img.tell()
+    pat = struct.pack("<QQ", a, b)
+    out = []
+    CH = 64 << 20
+    pos = 0
+    while pos < fsz:
+        img.seek(pos); d = img.read(min(CH, fsz - pos))
+        st = 0
+        while True:
+            i = d.find(pat, st)
+            if i < 0: break
+            st = i + 1
+            gpa = off2gpa(pos + i)
+            out.append((gpa & ~0xfff, gpa - (gpa & ~0xfff)))
+        pos += CH
+    return out
+
+def scan_page_descs(page):
+    d = rd(page, 0x1000)
+    if not d: return []
+    out = []
+    for o in range(0, 0x1000 - 24, 8):
+        sz, fl = struct.unpack_from("<QQ", d, o)
+        if fl != 0x03008000: continue
+        if sz not in (0x20000, 0x40000): continue
+        pa = struct.unpack_from("<Q", d, o + 16)[0]
+        if 0x100000000 <= pa < 0x180000000:
+            out.append((sz, o, pa))
+    return out
+
+def main():
+    log("=== resolver4 start ===")
+    def ring_lines():
+        return re.findall(r"ring rc=0 pa=0x([0-9a-f]+) ap=", dmesg())
+    base = ring_lines()
+    log("pre-existing ring lines: %d" % len(base))
+    ring_pa = None
+    deadline = time.time() + WAIT_RING_S
+    while time.time() < deadline:
+        cur = ring_lines()
+        if len(cur) > len(base):
+            ring_pa = int(cur[-1], 16)
+            break
+        time.sleep(1)
+    if not ring_pa:
+        log("no NEW ring line; exit"); return 1
+    log("NEW RING PA = 0x%x" % ring_pa)
+
+    injected = set()
+    LEARNED = [0x101e39000, 0x102a62000]  # RM window-record pages (stable across runs)
+    def try_page(page):
+        descs = scan_page_descs(page)
+        rdesc = [x for x in descs if x[0] == 0x40000]
+        pdesc = [x for x in descs if x[0] == 0x20000]
+        if not rdesc or not pdesc:
+            return False
+        if rdesc[0][2] != ring_pa:
+            return False
+        ok = False
+        for (_sz, o, pa) in pdesc:
+            key = (page, o)
+            if key in injected: continue
+            pd = rd(pa, 0x40)
+            log("page=0x%x ring_desc@0x%x(pa=0x%x OK) push_desc@0x%x pa=0x%x head=%s"
+                % (page, rdesc[0][1], rdesc[0][2], o, pa,
+                   pd.hex() if pd else "?"))
+            if inject(PUSH_VA, pa, 0x1000):
+                injected.add(key); ok = True
+        return ok
+    log("learned pages: %s" % [hex(p) for p in LEARNED])
+    watch = time.time() + WATCH_S
+    last_full = 0
+    while time.time() < watch:
+        hit = False
+        for page in LEARNED:
+            if try_page(page):
+                hit = True
+        if not hit and time.time() - last_full > 5:
+            last_full = time.time()
+            for (page, _off) in find_qpair(RING_VA, 0x40000):
+                if try_page(page):
+                    if page not in LEARNED:
+                        LEARNED.append(page)
+                    hit = True
+        time.sleep(0.25)
+    log("=== resolver4 done: %d injection(s) ===" % len(injected))
+    return 0
+
+if __name__ == "__main__":
+    sys.exit(main())