guest-diag: scanner EOF guard + exclude non-client nvidia fd holders

Two failure modes found when the scanner detects clients by device fd:
a transient boot nvidia-smi was picked and its exited pagemap read back
EOF, and scan_window advanced by got=0 forever (busy spin, no stream);
and non-client nvidia fd holders must never be committed to. Break on
got<=0 in scan_window (scan_range already did), skip nvidia-smi/
persistenced/Xorg, and prefer /dev/nvidia-uvm holders.

1 files changed, 11 insertions, 0 deletions

diff --git a/tools/guest-diag/guest_pin_stream.py b/tools/guest-diag/guest_pin_stream.py
index 29ef114..04aba73 100644
--- a/tools/guest-diag/guest_pin_stream.py
+++ b/tools/guest-diag/guest_pin_stream.py
@@ -659,6 +659,10 @@ def nvidia_fds(pid):
 def cdt_pid():
     prefixes = tuple(p for p in os.environ.get("CLIENT_PREFIXES",
                                                "cdt,va,victory").split(",") if p)
+    # Processes that hold a /dev/nvidia* fd but are not CUDA clients; the
+    # scanner must never commit to them (a transient nvidia-smi at boot was
+    # picked once and its exited pagemap read back EOF forever).
+    non_clients = ("nvidia-smi", "nvidia-persistenced", "Xorg", "X")
     best = None
     uvm = None
     gpu = None
@@ -679,6 +683,8 @@ def cdt_pid():
             if any(name.startswith(p) for p in prefixes):
                 best = int(d)
                 continue
+            if any(name.startswith(p) for p in non_clients):
+                continue
             # Arbitrary CUDA binaries (any comm) are clients too: match by
             # the CUDA device they hold open so streaming never depends on
             # the binary's name. Prefer a UVM holder (compute client) over a
@@ -710,6 +716,11 @@ def scan_window(fd, lo, hi, span, out):
             os.lseek(fd, (va // 4096) * 8, 0)
             data = os.read(fd, n * 8)
             got = len(data) // 8
+            # EOF: the process's address space (or the pagemap of an exited
+            # pid) does not reach this VA. Without this the loop reads the
+            # same offset forever (got == 0 -> va never advances).
+            if got <= 0:
+                break
             for i in range(got):
                 e = int.from_bytes(data[i * 8:i * 8 + 8], 'little')
                 if not ((e >> 63) & 1):