From ba00a21e54db283c9fd745c5c7e3dcb68bb8256f Mon Sep 17 00:00:00 2001
From: Dusty Mabe <dusty@dustymabe.com>
Date: Thu, 16 Apr 2020 17:02:55 -0400
Subject: [PATCH] overlay: 15coreos-copy-firstboot-network: handle race
 condition

Add short while loop to handle a race condition where
After=dev-disk-by\x2dlabel-boot.device doesn't seem to be sufficient
always.
---
 .../coreos-copy-firstboot-network.sh          | 38 +++++++++++++++++--
 1 file changed, 35 insertions(+), 3 deletions(-)

diff --git a/overlay.d/05core/usr/lib/dracut/modules.d/15coreos-copy-firstboot-network/coreos-copy-firstboot-network.sh b/overlay.d/05core/usr/lib/dracut/modules.d/15coreos-copy-firstboot-network/coreos-copy-firstboot-network.sh
index 32af9d7487..38f35454bc 100755
--- a/overlay.d/05core/usr/lib/dracut/modules.d/15coreos-copy-firstboot-network/coreos-copy-firstboot-network.sh
+++ b/overlay.d/05core/usr/lib/dracut/modules.d/15coreos-copy-firstboot-network/coreos-copy-firstboot-network.sh
@@ -4,6 +4,8 @@ set -euo pipefail
 # For a description of how this is used see coreos-copy-firstboot-network.service
 
 bootmnt=/mnt/boot_partition
+mkdir -p ${bootmnt}
+bootdev=/dev/disk/by-label/boot
 firstboot_network_dir_basename="coreos-firstboot-network"
 initramfs_firstboot_network_dir="${bootmnt}/${firstboot_network_dir_basename}"
 initramfs_network_dir="/run/NetworkManager/system-connections/"
@@ -11,10 +13,40 @@ realroot_firstboot_network_dir="/boot/${firstboot_network_dir_basename}"
 
 # Mount /boot. Note that we mount /boot but we don't unmount boot because we
 # are run in a systemd unit with MountFlags=slave so it is unmounted for us.
-mkdir -p ${bootmnt}
-# mount as read-only since we don't strictly need write access and we may be
+# Mount as read-only since we don't strictly need write access and we may be
 # running alongside other code that also has it mounted ro
-mount -o ro /dev/disk/by-label/boot ${bootmnt}
+mountboot() {
+    # Wait for up to 5 seconds for the boot device to be available
+    # The After=...*boot.device in the systemd unit should be enough
+    # but there appears to be some race in the kernel where the link under
+    # /dev/disk/by-label exists but mount is not able to use the device yet.
+    # We saw errors like this in CI:
+    #
+    #   [    4.045181] systemd[1]: Found device /dev/disk/by-label/boot.
+    #   [  OK  ] Found device /dev/disk/by-label/boot
+    #   [    4.051500] systemd[1]: Starting Copy CoreOS Firstboot Networking Config...
+    #         Starting  Copy CoreOS Firstboot Networking Config
+    #   [    4.060573]  vda: vda1 vda2 vda3 vda4
+    #   [    4.063296] coreos-copy-firstboot-network[479]: mount: /mnt/boot_partition: special device /dev/disk/by-label/boot does not exist.
+    #
+    mounted=0
+    for x in {1..5}; do
+        if mount -o ro ${bootdev} ${bootmnt}; then
+            echo "info: ${bootdev} successfully mounted."
+            mounted=1
+            break
+        else
+            echo "info: retrying ${bootdev} mount in 1 second..."
+            sleep 1
+        fi
+    done
+    if [ "${mounted}" == "0" ]; then
+        echo "error: ${bootdev} mount did not succeed" 1>&2
+        return 1
+    fi
+}
+
+mountboot || exit 1
 
 if [ -n "$(ls -A ${initramfs_firstboot_network_dir} 2>/dev/null)" ]; then
     # Clear out any files that may have already been generated from