From 009304f03b38d57b2c26c24e53b4f9c86121c738 Mon Sep 17 00:00:00 2001
From: Donald Buczek <buczek@molgen.mpg.de>
Date: Sat, 30 Dec 2023 13:27:46 +0100
Subject: [PATCH] gpu-setup: Don't unlock to early during release

Currently, the gpu lock file `pid` is released (removed) to early, so
that there is a small race condition with a new GPU allocation:

```
   MXQ           job1                        job2
* fork job1
                 * other initialization
                 * reserve gpu:
                 * * find slot without pid
                 * * change access to UID
                 * run user program
                 * exit
* fork job2
                                             *  other initialization
* cleanup job 1:
* * rm .../pid
                                             * reserve gpu:
                                             * * find slot without pid
                                             * * change access to UID
* * change access to root
```

On release, keep the `pid` file until after the access mode has been
changed back to root.
---
 helper/gpu-setup | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/helper/gpu-setup b/helper/gpu-setup
index e06d5b11..a0413fb3 100755
--- a/helper/gpu-setup
+++ b/helper/gpu-setup
@@ -274,7 +274,6 @@ job_release() {
             test_pid="$(cat $d/pid 2>/dev/null)"
             if [ "$pid" = "$test_pid" ]; then
                 echo "XXX $$ job_release $pid: found my pid in $d, releasing" >&2
-                rm $d/pid
                 for f in $(cat $d/access-files); do
                     case $f in
                         /dev/nvidia-caps/nvidia-cap*)
@@ -287,6 +286,7 @@ job_release() {
                             ;;
                     esac
                 done
+                rm $d/pid
                 exit 0
             fi
         fi