kernel: authoritative host-injected VA->PA pins (ipin table) + wider pin table

The CE push-buffer page 0x120000000 resolved to a zero-filled page even after
sema_map_add injected the correct translation: the shared pin table silently
dropped inserts once a hash cluster exceeded the 32-probe window (the page
hashes to slot 0, a hot cluster), and lookups fell through to the
content-scanned map and answered with a stale page - so every CE push read as
implausible and memset stayed 0. Injected translations now live in a separate
authoritative table checked before every other source and are never written by
self-discovery; the general pin table is 4x larger with a 4x probe window and
counts drops (pin_drop/ipin_drop) in the stats line. guest_kprobes.sh disables
the kprobe group before removal (EBUSY) and matches p:kprobes/<name>; the
guest wait sampler can run counters-only with GDB=0.

2 files changed, 10 insertions, 4 deletions

diff --git a/tools/guest-diag/guest_kprobes.sh b/tools/guest-diag/guest_kprobes.sh
index f676e20..0afe6c6 100644
--- a/tools/guest-diag/guest_kprobes.sh
+++ b/tools/guest-diag/guest_kprobes.sh
@@ -15,29 +15,35 @@
 TR=/sys/kernel/tracing
 [ -d "$TR" ] || TR=/sys/kernel/debug/tracing
 
+# An enabled kprobe event cannot be deleted (EBUSY); disable the group first.
+echo 0 > "$TR/events/kprobes/enable" 2>/dev/null || true
+
 add_probe() {
     name=$1; sym=$2; fmt=$3
+    echo "-:kprobes/$name" >> "$TR/kprobe_events" 2>/dev/null
     echo "-:$name" >> "$TR/kprobe_events" 2>/dev/null
     if ! grep -qw "$sym" /proc/kallsyms 2>/dev/null; then
         echo "FAIL $name: symbol $sym not in kallsyms"
         return 1
     fi
     if echo "p:$name $sym $fmt" >> "$TR/kprobe_events" 2>/dev/null; then
-        if grep -q "p:$name" "$TR/kprobe_events" 2>/dev/null; then
+        if grep -qE "p:[^ ]*[ /]$name( |$)" "$TR/kprobe_events" 2>/dev/null; then
             echo "ok $name $sym"
             return 0
         fi
     fi
+    echo "-:kprobes/$name" >> "$TR/kprobe_events" 2>/dev/null
     echo "-:$name" >> "$TR/kprobe_events" 2>/dev/null
     if echo "p:$name nvidia_uvm:$sym $fmt" >> "$TR/kprobe_events" 2>/dev/null; then
-        if grep -q "p:$name" "$TR/kprobe_events" 2>/dev/null; then
+        if grep -qE "p:[^ ]*[ /]$name( |$)" "$TR/kprobe_events" 2>/dev/null; then
             echo "ok-module $name $sym"
             return 0
         fi
     fi
+    echo "-:kprobes/$name" >> "$TR/kprobe_events" 2>/dev/null
     echo "-:$name" >> "$TR/kprobe_events" 2>/dev/null
     if echo "p:$name $sym" >> "$TR/kprobe_events" 2>/dev/null; then
-        if grep -q "p:$name" "$TR/kprobe_events" 2>/dev/null; then
+        if grep -qE "p:[^ ]*[ /]$name( |$)" "$TR/kprobe_events" 2>/dev/null; then
             echo "ok-bare $name $sym"
             return 0
         fi
diff --git a/tools/guest-diag/track_waits.sh b/tools/guest-diag/track_waits.sh
index 4c9cd1a..45a9a66 100644
--- a/tools/guest-diag/track_waits.sh
+++ b/tools/guest-diag/track_waits.sh
@@ -52,7 +52,7 @@ for i in $(seq 1 "$N"); do
     TS=$(date +%T.%3N)
     kill -0 "$PID" 2>/dev/null || { echo "PROCESS GONE at $TS (sample $i)" >> /tmp/trk.log; break; }
 
-    if [ $((i % 2)) -eq 1 ]; then
+    if [ $((i % 2)) -eq 1 ] && [ "${GDB:-1}" = "1" ]; then
         echo "=== $TS sample $i ===" >> /tmp/trk.log
         timeout 8 gdb -p "$PID" -batch -x /tmp/trkinfo.py 2>&1 \
             | grep -vE "^\[|Reading symbols|^0x[0-9a-f]+ in |warning:" >> /tmp/trk.log