vgsp-rm r680 + wall-2 session-76 forensics: 0x2080a097 reply record-area tunables (wall2_a097_count/rec0..rec7, default 0xffffffff = echo) and the evidence set that re-questions the a097 gate

The real host RM 0x2080a097 handler (GSP-RM 570.144 control table entry,
params 0x490) overwrites params+4..+0x23 with up to four {u32,u32}
mode pairs (engine value + a x1000 clock/percent) and the client copies
back the first 16 bytes; the tick at eglcore 0xd5e3e0 consumes the
second word of the first pair as the per-engine progress (session
+0xe104, compared against per-boot config threshold 95 at
lib+0x2019320+0xffc with 10/20 bit-history cutoffs). New module params
let one boot sweep the record matrix; the r680 sweep (flag/v488/v48c +
count/rec matrix incl. progress 100..1000000) changed nothing
observable, and hw watchpoints show E+0x150 stays 0x00200000 with no
writer over 5+ minutes while the a097 poller is a worker thread and
the main thread sits in a 10 s poll() loop on /dev/nvidia0 inside
vkCreateDevice. Tools: t75g.py (in-guest gdb state/watch probes),
diag76.py (thread bt + address resolution), slots_probe.sh, run75g.sh;
README-session76.md records the firmware handler decode and the sweep.

1 files changed, 170 insertions, 0 deletions

diff --git a/tools/guest-diag/wall2/t75g.py b/tools/guest-diag/wall2/t75g.py
new file mode 100644
index 0000000..2a0881a
--- /dev/null
+++ b/tools/guest-diag/wall2/t75g.py
@@ -0,0 +1,170 @@
+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))
+
+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 = {"out": 0, "E": 0, "S": 0, "armed150": False, "armedS": False,
+         "bt_done": False, "post_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("$pc")), e))
+            stop = False
+        return stop or self.hits >= self.limit
+
+def a97(bp):
+    rbp = int(gdb.parse_and_eval("$rbp"))
+    r14 = int(gdb.parse_and_eval("$r14"))
+    out = u64(rbp+0x10)
+    state["out"] = out
+    q = rd(out, 0x28)
+    rec_ptr = int.from_bytes(q[8:16], 'little')
+    print("A97 out=0x%x count=%d f10=%08x f20=%08x f24=%08x recp=0x%x" %
+          (out, int.from_bytes(q[0:4], 'little'), int.from_bytes(q[0x10:0x14], 'little'),
+           int.from_bytes(q[0x20:0x24], 'little'), int.from_bytes(q[0x24:0x28], 'little'), rec_ptr))
+    if rec_ptr and rec_ptr > 0x1000:
+        try:
+            rec = rd(rec_ptr, 16)
+            print("A97 rec=%08x %08x %08x %08x" %
+                  tuple(int.from_bytes(rec[i*4:i*4+4], 'little') for i in range(4)))
+        except Exception as e:
+            print("A97 rec-unreadable", e)
+    return False
+
+def post(bp):
+    if state["post_done"]:
+        return False
+    state["post_done"] = True
+    rsp = int(gdb.parse_and_eval("$rsp"))
+    q = rd(rsp, 0x40)
+    print("POST rsp=0x%x out=0x%x" % (rsp, state["out"]))
+    for i in range(0, 0x40, 8):
+        v = int.from_bytes(q[i:i+8], 'little')
+        print("POST rsp+%02x = 0x%016x" % (i, v))
+    if state["out"]:
+        oq = rd(state["out"], 0x40)
+        for i in range(0, 0x40, 8):
+            v = int.from_bytes(oq[i:i+8], 'little')
+            print("POST out+%02x = 0x%016x" % (i, v))
+    return False
+
+def t150(bp):
+    rbp = int(gdb.parse_and_eval("$rbp"))
+    if not state.get("vt_done"):
+        state["vt_done"] = True
+        rdi = u64(rbp+0x148)
+        vt = u64(rdi) if rdi else 0
+        m118 = u64(vt+0x118) if vt else 0
+        m170 = u64(vt+0x170) if vt else 0
+        print("VT E148=0x%x vt=0x%x m118=0x%x m170=0x%x" % (rdi, vt, m118, m170))
+    if not state.get("eng_done"):
+        state["eng_done"] = True
+        n = u32(rbp+8)
+        ids = [u32(rbp+0x54+i*4) for i in range(min(n,8))]
+        print("ENG n=%d ids=%s" % (n, ",".join("0x%x" % x for x in ids)))
+        
+        # cfg area pointer is rip-relative 0x2019320 at runtime = base + (0x2019320 - 0)
+        # eglcore base == min load addr; file offset == vaddr for the .text; data seg present?
+        try:
+            vals = rd(base + 0x2019320 + 0xf80, 0xe0)
+            for i in range(0, 0xe0, 0x10):
+                v4 = [int.from_bytes(vals[i+j:i+j+4],'little') for j in (0,4,8,12)]
+                print("CFG +0x%03x = %s" % (0xf80+i, ["0x%x"%x for x in v4]))
+        except Exception as e:
+            print("CFG dump err", e)
+    v = u32(rbp+0x150)
+    b38 = rd(rbp+0x1b038, 1)[0]; b39 = rd(rbp+0x1b039, 1)[0]
+    p = u64(rbp+0x1b030); s8 = u64(p+8) if p else 0
+    print("T150 E=0x%x v=0x%08x b038=%d b039=%d p=0x%x p8=0x%x" %
+          (rbp, v, b38, b39, p, s8))
+    if not state["bt_done"]:
+        state["bt_done"] = True
+        print(gdb.execute("bt 8", to_string=True))
+    if not state["armed150"]:
+        state["armed150"] = True
+        state["E"] = rbp
+        try:
+            gdb.execute("frame 1")
+            S = int(gdb.parse_and_eval("$rbp"))
+            gdb.execute("frame 0")
+            print("S=0x%x S120=%08x S128=%08x" % (S, u32(S+0x120), u32(S+0x128)))
+            state["S"] = S
+        except Exception as e:
+            print("S capture err", e)
+            S = 0
+        W("*(unsigned int *)0x%x" % (rbp+0x150), rbp, 0x150, 4, "W150")
+        W("*(unsigned char *)0x%x" % (rbp+0x1b038), rbp, 0x1b038, 1, "W038")
+        W("*(unsigned char *)0x%x" % (rbp+0x1b039), rbp, 0x1b039, 1, "W039")
+        if S:
+            W("*(unsigned int *)0x%x" % (S+0x120), S, 0x120, 4, "W120")
+        print("WATCHES armed E=0x%x S=0x%x" % (rbp, S))
+    return False
+
+def sl(bp):
+    rbp = int(gdb.parse_and_eval("$rbp"))
+    print("SLOOP S=0x%x S120=%08x" % (rbp, u32(rbp+0x120)))
+    if not state["armedS"]:
+        state["armedS"] = True
+        W("*(unsigned int *)0x%x" % (rbp+0x120), rbp, 0x120, 4, "W120")
+        print("W120 armed on S+0x120")
+    return False
+
+class W(gdb.Breakpoint):
+    def __init__(self, spec, E, off, size, tag):
+        super().__init__(spec, type=gdb.BP_WATCHPOINT)
+        self.silent = True; self.E = E; self.off = off; self.size = size
+        self.tag = tag; self.hits = 0
+    def stop(self):
+        self.hits += 1
+        cur = int.from_bytes(rd(self.E+self.off, self.size), 'little')
+        pc = int(gdb.parse_and_eval("$pc"))
+        print("%s v=0x%x pc=0x%x (rel 0x%x)" % (self.tag, cur, pc, pc-base))
+        if self.hits <= 8:
+            print(gdb.execute("bt 10", to_string=True))
+        return self.hits >= 400
+
+B("*0x%x" % (base+0xecd43d), a97, 220)
+B("*0x%x" % (base+0xd5e4d3), post, 100000)
+B("*0x%x" % (base+0xd5e449), t150, 220)
+B("*0x%x" % (base+0xd6ef76), sl, 240)
+
+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")