sema-svc: apply releases promptly and decode compute-push releases

The content sweep now:
- decodes a release whose method stream continues with any INC_METHOD,
  not only the CE LAUNCH_DMA group, so the releases at the head of a
  compute/GR channel's first push are applied too;
- remembers releases whose target VA had no translation (deferred list)
  and retries them every service pass, so a VA->PA injection lands them
  immediately instead of after the next full sweep;
- re-arms the fast sliced sweep for a few seconds after an injection;
- treats a channel whose USERD/ring cannot be resolved as stalled, so the
  sweep keeps looking for the releases its unreadable pushes carry.

tools: add per-cdt client-pin helper (sem pages + /dev/nvidia0 windows),
sem-page scanner and memprobe fixes (short-read guard, --brief).
Live-verified: injecting a client sem page applied 12 deferred releases
within a second; the service kept applying (89 -> 202) while cdt ran.

3 files changed, 111 insertions, 3 deletions

diff --git a/tools/guest-diag/memprobe.py b/tools/guest-diag/memprobe.py
index 26ed0af..96dd40b 100644
--- a/tools/guest-diag/memprobe.py
+++ b/tools/guest-diag/memprobe.py
@@ -126,8 +126,10 @@ def dump_tracker(pid, fd, p):
     if sob:
         print("  sem_obj[0:0x40]=%s" % sob.hex())
         mem = r64(sob, 0x10)
-        mvb = rd(fd, mem & ~0xfff, 0x40)
-        print("  sem_mem=0x%x val@+0x%x=0x%x" % (mem, mem & 0xfff, r32(mvb, mem & 0xfff) if mvb else -1))
+        mvb = rd(fd, mem & ~0xfff, 0x1000)
+        off = mem & 0xfff
+        val = r32(mvb, off) if mvb and off + 4 <= len(mvb) else -1
+        print("  sem_mem=0x%x val@+0x%x=0x%x" % (mem, off, val))
     q = r64(rd(fd, p + 0x48, 8) or b"\0" * 8)
     print("  prog_obj=0x%x next=0x%x cblist=0x%x idx95bc=0x%x p34=0x%x"
           % (q, r64(rd(fd, p + 0x9470, 8) or b"\0" * 8),
@@ -154,15 +156,18 @@ def main():
         if mode == "scan":
             lo, hi = 0x204800000, 0x204c0000
             limit = 8
+            brief = False
             for i, a in enumerate(sys.argv[3:]):
                 if a == "--min": lo = int(sys.argv[4 + i], 16)
                 if a == "--max": hi = int(sys.argv[4 + i], 16)
                 if a == "--limit": limit = int(sys.argv[4 + i])
+                if a == "--brief": brief = True
             res = find_trackers(pid, fd, lo, hi, limit)
             for p, sub, last, cur, sem, mem in res:
                 print("P=0x%x sub=0x%x last=0x%x cur=0x%x sem_obj=0x%x sem_mem=0x%x" %
                       (p, sub, last, cur, sem, mem or 0))
-                dump_tracker(pid, fd, p)
+                if not brief:
+                    dump_tracker(pid, fd, p)
         elif mode == "dump":
             dump_tracker(pid, fd, int(sys.argv[3], 16))
         elif mode == "hex":
diff --git a/tools/guest-diag/pin_client_sems.sh b/tools/guest-diag/pin_client_sems.sh
new file mode 100755
index 0000000..82d2789
--- /dev/null
+++ b/tools/guest-diag/pin_client_sems.sh
@@ -0,0 +1,66 @@
+#!/bin/bash
+# pin_client_sems.sh - bridge the CUDA client's device mappings into the
+# emulation for the live cdt process.
+#
+# Two things are pinned, both per-process (a new cdt maps new physical pages
+# at the same VAs, so re-run this for every cdt run):
+#   1. the /dev/nvidia0 window: the driver's channel rings/USERDs (the GR
+#      channels' GPFIFO VAs live here), so the pump can run their pushes;
+#   2. the semaphore pages libcuda's trackers poll (found by scanning the
+#      client's memory for sem references, then translated through the guest
+#      pagemap).
+#
+# Usage: tools/guest-diag/pin_client_sems.sh [iterations] [sleep-secs]
+set -u
+cd "$(dirname "$(readlink -f "$0")")/../.."
+VMEXEC=./scripts/vgpu_vm.py
+ITER=${1:-1}
+SLEEP=${2:-10}
+
+PID=$(timeout 20 $VMEXEC exec --timeout 15 'pgrep -x cdt | head -1' 2>/dev/null | tail -1)
+[ -n "$PID" ] || { echo "no cdt pid"; exit 1; }
+echo "cdt pid=$PID"
+
+B64=$(gzip -9 < tools/guest-diag/sempages.py | base64 -w0)
+timeout 30 $VMEXEC exec --timeout 25 "echo '$B64' | base64 -d | gunzip > /tmp/sempages.py" >/dev/null 2>&1
+B64=$(gzip -9 < tools/guest-diag/memprobe.py | base64 -w0)
+timeout 30 $VMEXEC exec --timeout 25 "echo '$B64' | base64 -d | gunzip > /tmp/memprobe.py" >/dev/null 2>&1
+B64=$(base64 -w0 tools/guest-diag/guest_pmap_all.py)
+timeout 30 $VMEXEC exec --timeout 25 "echo '$B64' | base64 -d > /tmp/pmapall.py" >/dev/null 2>&1
+
+pin_range() {   # pin_range <lo-dec> <hi-dec> <label>
+    local cur=$1 hi=$2 label=$3 total=0
+    while [ "$cur" -lt "$hi" ]; do
+        mapfile -t lines < <(timeout 60 $VMEXEC exec --timeout 50 "sudo python3 /tmp/pmapall.py $PID $(printf '0x%x' "$cur") 32" 2>/dev/null | grep -aE '^0x[0-9a-f]+,0x[0-9a-f]+$')
+        [ "${#lines[@]}" -gt 0 ] || break
+        for l in "${lines[@]}"; do
+            echo "$l,0x1000,1" | sudo tee /sys/module/open_iov_vfio/parameters/sema_map_add >/dev/null
+        done
+        total=$((total + ${#lines[@]}))
+        local last=${lines[-1]%%,*}
+        cur=$(( 16#${last#0x} + 0x1000 ))
+    done
+    echo "  $label: pinned $total page(s)"
+}
+
+for it in $(seq 1 "$ITER"); do
+    # 1. /dev/nvidia0 windows (channel rings/USERDs).
+    mapfile -t n0 < <(timeout 30 $VMEXEC exec --timeout 25 "awk '/\\/dev\\/nvidia0/ {print \$1}' /proc/$PID/maps" 2>/dev/null | grep -E '^[0-9a-f]+-[0-9a-f]+$')
+    for r in "${n0[@]}"; do
+        lo=$(( 16#${r%-*} ))
+        hi=$(( 16#${r#*-} ))
+        pin_range "$lo" "$hi" "nvidia0 $r"
+    done
+
+    # 2. client semaphore pages.
+    lines=$(timeout 150 $VMEXEC exec --timeout 140 "sudo timeout 120 python3 /tmp/sempages.py $PID" 2>/dev/null | grep -E '^0x[0-9a-f]+$')
+    n=0
+    for va in $lines; do
+        line=$(timeout 30 $VMEXEC exec --timeout 25 "sudo python3 /tmp/pmapall.py $PID $va 1" 2>/dev/null | grep -E '^0x[0-9a-f]+,0x[0-9a-f]+$' | head -1)
+        [ -n "$line" ] || continue
+        echo "$line,0x1000,1" | sudo tee /sys/module/open_iov_vfio/parameters/sema_map_add >/dev/null || continue
+        n=$((n + 1))
+    done
+    echo "iter $it: pinned $n sem page(s) (pid $PID)"
+    [ "$it" -lt "$ITER" ] && sleep "$SLEEP"
+done
diff --git a/tools/guest-diag/sempages.py b/tools/guest-diag/sempages.py
new file mode 100755
index 0000000..ad4dae6
--- /dev/null
+++ b/tools/guest-diag/sempages.py
@@ -0,0 +1,37 @@
+#!/usr/bin/env python3
+# Print the distinct pages of the semaphore VAs a process references
+# (reuses memprobe.py's scanner; run in the guest as root). The VA window is
+# derived from the process's /dev/nvidia* mappings unless lo/hi are given.
+# usage: sudo python3 sempages.py <pid> [lo] [hi]
+import os
+import sys
+
+sys.path.insert(0, '/tmp')
+import memprobe as m
+
+pid = int(sys.argv[1])
+if len(sys.argv) > 3:
+    lo = int(sys.argv[2], 16)
+    hi = int(sys.argv[3], 16)
+else:
+    lo = 1 << 64
+    hi = 0
+    with open('/proc/%d/maps' % pid) as f:
+        for line in f:
+            parts = line.split()
+            if len(parts) < 6 or not parts[5].startswith('/dev/nvidia'):
+                continue
+            a, b = parts[0].split('-')
+            lo = min(lo, int(a, 16))
+            hi = max(hi, int(b, 16))
+    if hi == 0:
+        print('no /dev/nvidia mappings')
+        raise SystemExit(1)
+
+fd = os.open('/proc/%d/mem' % pid, os.O_RDONLY)
+sems = m.sem_objs(pid, fd, lo, hi)
+os.close(fd)
+pages = sorted({va & ~0xfff for va in sems})
+print('sem VAs: %d pages: %d (window 0x%x..0x%x)' % (len(sems), len(pages), lo, hi))
+for pg in pages:
+    print('0x%x' % pg)