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, 69 insertions, 0 deletions

diff --git a/tools/guest-diag/wall2/scan_r673d.py b/tools/guest-diag/wall2/scan_r673d.py
new file mode 100644
index 0000000..1fa89ca
--- /dev/null
+++ b/tools/guest-diag/wall2/scan_r673d.py
@@ -0,0 +1,69 @@
+#!/usr/bin/env python3
+# r673 deep-dive: all ring-PA refs with low bits, ring page dump, RM record
+# pages, and a RAM-wide scan for 0xa3bf20 VA-table records mentioning 0x4500000.
+import numpy as np, struct, os, time
+
+RAM="/dev/shm/vgpu-guest-ram"
+RING=0x12a783000; TAG=0xa3bf20
+img=open(RAM,"rb"); fsz=os.path.getsize(RAM)
+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 or off+n>fsz: return None
+    img.seek(off); return img.read(n)
+
+MASK=~0xfff & ((1<<64)-1)
+print("== all qwords (v & ~0xfff)==ring_pa ==")
+CH=64<<20
+for pos in range(0,fsz,CH):
+    img.seek(pos); d=img.read(min(CH,fsz-pos))
+    n=len(d)//8
+    a=np.frombuffer(d[:n*8],dtype=np.uint64)
+    idx=np.nonzero((a & np.uint64(MASK))==np.uint64(RING))[0]
+    for i in idx:
+        off=pos+int(i)*8
+        gpa=off2gpa(off); page=gpa&~0xfff
+        dd=rd(page,0x1000); ro=gpa-page
+        s=max(0,ro-32); e=min(0x1000,ro+48)
+        print("  gpa=0x%x low=0x%x ctx=%s" % (gpa,int(a[i])&0xfff,dd[s:e].hex() if dd else "?"))
+
+print()
+print("== ring page 0x%x first 0x120 ==" % RING)
+d=rd(RING,0x120)
+for o in range(0,0x120,0x20):
+    print("  +0x%03x: %s" % (o,d[o:o+0x20].hex()))
+
+for pa in (0x1013a6000,0x104acb000,0x114760000,0x1202cd000,0x13e2c1000,0x13e62e000):
+    print()
+    print("== page 0x%x first 0x140 ==" % pa)
+    d=rd(pa,0x140)
+    for o in range(0,0x140,0x20):
+        q=struct.unpack_from("<4Q",d,o)
+        print("  +0x%03x: %016x %016x %016x %016x" % ((o,)+q))
+
+print()
+print("== RAM-wide: 32-byte records {va, cpu, 0xa3bf20, pages} with va==0x4500000 ==")
+t0=time.time()
+found=0
+for pos in range(0,fsz,CH):
+    img.seek(pos); d=img.read(min(CH,fsz-pos))
+    n=len(d)//8
+    a=np.frombuffer(d[:n*8],dtype=np.uint64)
+    idx=np.nonzero(a==np.uint64(TAG))[0]
+    for i in idx:
+        off=pos+int(i)*8
+        gpa=off2gpa(off); page=gpa&~0xfff
+        dd=rd(page,0x1000)
+        ro=gpa-page
+        if ro>=16 and ro+8<=0x1000:
+            va,cpu=struct.unpack_from("<QQ",dd,ro-16)
+            pgs=struct.unpack_from("<Q",dd,ro+8)[0]
+            if va==0x4500000 or (0x4400000<=va<=0x4600000):
+                print("  rec gpa=0x%x va=0x%x cpu=0x%x pages=0x%x" % (gpa,va,cpu,pgs))
+                found+=1
+print("total", found, "(%.1fs)" % (time.time()-t0))