File 0630-fix-shutdown-add-timeout-to-umount-calls.patch of Package dracut.18204

From da2c1abbb5da0717388a7560ce03394b30878c58 Mon Sep 17 00:00:00 2001
From: Petr Pavlu <petr.pavlu@suse.com>
Date: Tue, 9 Feb 2021 13:13:25 +0100
Subject: [PATCH 2/2] fix(shutdown): add timeout to umount calls

When terminating a system, the shutdown module attempts to unmount all
file systems from under /oldroot. This reaps remaining file systems that
systemd cannot unmount and detaches /oldroot itself.

In case that running umount for some file system repeatedly fails, the
module reports this error and continues the processing in order to
shutdown the system. This handles a condition when the umount command
actually terminates but it can happen in some cases that it waits
indefinitely.

An example with NFS mounts:
# mount -t nfs 192.168.0.1:/srv/nfs/dir /mnt/nfs
# mkdir /mnt/nfs/dir2
# mount -t nfs 192.168.0.1:/srv/nfs/dir2 /mnt/nfs/dir2
# touch /mnt/nfs/dir2/file
# systemd-run -pKillMode=none -pSendSIGKILL=no tail -f /mnt/nfs/dir2/file
Running as unit: run-r367825c967ca4d88a793ae4793c02f8b.service
# systemctl poweroff

The invoked tail command escapes normal termination by systemd and
prevents stopping mnt-nfs.mount and mnt-nfs-dir2.mount as it makes the
mounts busy. Systemd then again attempts to unmount these file systems
in systemd-shutdown but this fails as well. The utility tries to unmount
/mnt/nfs/dir2 but the kernel waits indefinitely doing a path lookup for
/mnt/nfs because network is no longer available at that point. The
systemd-shutdown gives up after 90 seconds. Finally, the control is
transferred to dracut which tries to unmount the file systems in the
same way and ends up indefinitely waiting on umount to finish.

This situation causes that the system hangs during shutdown. The patch
improves the shutdown module to add a timeout of 90 seconds for the
umount operation and continue with the shutdown if it gets reached,
similarly to what systemd-shutdown does.

(cherry picked from commit 38ef31939056dea30017d782988ba1a46df4784a)
---
 modules.d/99shutdown/module-setup.sh |  2 +-
 modules.d/99shutdown/shutdown.sh     | 44 +++++++++++++++++++++++-----
 2 files changed, 37 insertions(+), 9 deletions(-)

diff --git a/modules.d/99shutdown/module-setup.sh b/modules.d/99shutdown/module-setup.sh
index dfd6caa20..ff9b7734b 100755
--- a/modules.d/99shutdown/module-setup.sh
+++ b/modules.d/99shutdown/module-setup.sh
@@ -14,7 +14,7 @@ depends() {
 # called by dracut
 install() {
     local _d
-    inst_multiple umount poweroff reboot halt losetup stat sleep
+    inst_multiple umount poweroff reboot halt losetup stat sleep timeout
     inst_multiple -o kexec
     inst "$moddir/shutdown.sh" "$prefix/shutdown"
     [ -e "${initdir}/lib" ] || mkdir -m 0755 -p ${initdir}/lib
diff --git a/modules.d/99shutdown/shutdown.sh b/modules.d/99shutdown/shutdown.sh
index f21cc811b..d158bef44 100755
--- a/modules.d/99shutdown/shutdown.sh
+++ b/modules.d/99shutdown/shutdown.sh
@@ -40,28 +40,56 @@ warn "Killing all remaining processes"
 
 killall_proc_mountpoint /oldroot || sleep 0.2
 
+# Timeout for umount calls. The value can be set to 0 to wait forever.
+_umount_timeout=$(getarg rd.shutdown.timeout.umount)
+_umount_timeout=${_umount_timeout:-90s}
+_timed_out_umounts=""
+
 umount_a() {
+    local _verbose="n"
+    if [ "$1" = "-v" ]; then
+        _verbose="y"; shift
+        exec 7>&2
+    else
+        exec 7>/dev/null
+    fi
+
     local _did_umount="n"
     while read a mp a || [ -n "$mp" ]; do
-        if strstr "$mp" oldroot; then
-            if umount "$mp"; then
-                _did_umount="y"
-                warn "Unmounted $mp."
-            fi
+        strstr "$mp" oldroot || continue
+        strstr "$_timed_out_umounts" " $mp " && continue
+
+        # Unmount the file system. The operation uses a timeout to avoid waiting
+        # indefinitely if this is e.g. a stuck NFS mount. The command is
+        # invoked in a subshell to silence also the "Killed" message that might
+        # be produced by the shell.
+        (set +m; timeout --signal=KILL "$_umount_timeout" umount "$mp") 2>&7
+        local ret=$?
+        if [ $ret -eq 0 ]; then
+            _did_umount="y"
+            warn "Unmounted $mp."
+        elif [ $ret -eq 137 ]; then
+            _timed_out_umounts="$_timed_out_umounts $mp "
+            warn "Unmounting $mp timed out."
+        elif [ "$_verbose" = "y" ]; then
+            warn "Unmounting $mp failed with status $ret."
         fi
     done </proc/mounts
-    losetup -D
+
+    losetup -D 2>&7
+
+    exec 7>&-
     [ "$_did_umount" = "y" ] && return 0
     return 1
 }
 
 _cnt=0
 while [ $_cnt -le 40 ]; do
-    umount_a 2>/dev/null || break
+    umount_a || break
     _cnt=$(($_cnt+1))
 done
 
-[ $_cnt -ge 40 ] && umount_a
+[ $_cnt -ge 40 ] && umount_a -v
 
 if strstr "$(cat /proc/mounts)" "/oldroot"; then
     warn "Cannot umount /oldroot"
-- 
2.31.1