vgsp: host CUDA bridge + sema release recovery; greeneye simulator wave

- kernel: gsp_cuda_bridge (QMD launch capture, debugfs job/out/done, param+output resolution cached from inline writes), sema drain fixes (never hold/starve a channel), GR ring autopin + counter autoreg, per-page push reads, counter-derive gate; module builds clean
- tools/cuda-bridge: CUDA driver-API daemon executing mail/vadd kernels on the physical GPU, CUBB2/CBD2 v2 protocol, layout check + self-tests
- tools/guest-diag + tools/cuda-ab: scanner/pin fixes, victory push-only mode
- debug/risc-v-gsp-rm-vm: Phase S simulator wave (GSP device model, boot ladder, triage/re-demo harnesses, docs 30-41), GPGPU-sim scaffolding
- STATE-CURRENT/docs updates

1 files changed, 22 insertions, 14 deletions

diff --git a/tools/guest-diag/pin_gr_stream.py b/tools/guest-diag/pin_gr_stream.py
index d8b6b61..7f8e4b8 100644
--- a/tools/guest-diag/pin_gr_stream.py
+++ b/tools/guest-diag/pin_gr_stream.py
@@ -58,6 +58,8 @@ def _start_cmd():
     with open(GUEST_SCRIPT) as f:
         b64 = subprocess.run(["base64", "-w0"], stdin=f,
                              capture_output=True, text=True).stdout
+    prefixes = os.environ.get("CLIENT_PREFIXES", "cdt,va,victory")
+    vma_every = os.environ.get("STREAM_VMA_EVERY", "1")
     return ("echo '%s' | base64 -d > /tmp/guest_pin_stream.py; "
             "if [ -f /tmp/guest_pin_stream.pid ]; then "
             "p=$(cat /tmp/guest_pin_stream.pid 2>/dev/null); "
@@ -65,10 +67,12 @@ def _start_cmd():
             "/proc/$p/cmdline 2>/dev/null && sudo kill $p 2>/dev/null; "
             "fi; "
             "sudo rm -f /tmp/guest_pin_stream.pid; "
-            "sudo setsid nohup python3 /tmp/guest_pin_stream.py %d %d %s %s %s "
+            "sudo setsid nohup env CLIENT_PREFIXES='%s' "
+            "STREAM_VMA_EVERY='%s' "
+            "python3 /tmp/guest_pin_stream.py %d %d %s %s %s "
             ">/tmp/guest_pin_stream.log 2>&1 & sleep 2; "
             "sudo cat /tmp/guest_pin_stream.pid 2>/dev/null"
-            % (b64, 2, PORT, LO, HI, PAMAX))
+            % (b64, prefixes, vma_every, 2, PORT, LO, HI, PAMAX))
 
 
 def install_and_start():
@@ -189,18 +193,22 @@ def _flush(runs, seen):
             "echo 'FAIL 0x%x 0x%x 0x%x'"
             % (va, pa, n * 0x1000, PARAM, va, pa, n * 0x1000))
     failed = set()
-    try:
-        r = subprocess.run(["sudo", "-n", "sh", "-c", "\n".join(script)],
-                           capture_output=True, text=True, timeout=60)
-        for line in r.stdout.splitlines():
-            m = re.match(r"FAIL (0x[0-9a-f]+) (0x[0-9a-f]+) (0x[0-9a-f]+)",
-                         line.strip())
-            if m:
-                failed.add((int(m.group(1), 16), int(m.group(2), 16),
-                            int(m.group(3), 16) // 0x1000))
-    except Exception as e:
-        log("batch inject failed: %s" % e)
-        failed = set(todo)
+    CHUNK = 200
+    for start in range(0, len(script), CHUNK):
+        batch = script[start:start + CHUNK]
+        try:
+            r = subprocess.run(["sudo", "-n", "sh", "-c", "\n".join(batch)],
+                               capture_output=True, text=True, timeout=60)
+            for line in r.stdout.splitlines():
+                m = re.match(r"FAIL (0x[0-9a-f]+) (0x[0-9a-f]+) (0x[0-9a-f]+)",
+                             line.strip())
+                if m:
+                    failed.add((int(m.group(1), 16), int(m.group(2), 16),
+                                int(m.group(3), 16) // 0x1000))
+        except Exception as e:
+            log("batch inject failed: %s" % e)
+            for va, pa, n in todo[start:start + CHUNK]:
+                failed.add((va, pa, n))
 
     pages = 0
     for va, pa, n in todo: