Skip /dev submount hack on VFS2.

containerd usually configures both /dev and /dev/shm as tmpfs mounts, e.g.:

```
  "mounts": [
    ...
    {
      "destination": "/dev",
      "type": "tmpfs",
      "source": "/run/containerd/io.containerd.runtime.v2.task/moby/10eedbd6a0e7937ddfcab90f2c25bd9a9968b734c4ae361318142165d445e67e/tmpfs",
      "options": [
        "nosuid",
        "strictatime",
        "mode=755",
        "size=65536k"
      ]
    },
    ...
    {
      "destination": "/dev/shm",
      "type": "tmpfs",
      "source": "/run/containerd/io.containerd.runtime.v2.task/moby/10eedbd6a0e7937ddfcab90f2c25bd9a9968b734c4ae361318142165d445e67e/shm",
      "options": [
        "nosuid",
        "noexec",
        "nodev",
        "mode=1777",
        "size=67108864"
      ]
    },
    ...
```

(This is mostly consistent with how Linux is usually configured, except that
/dev is conventionally devtmpfs, not regular tmpfs. runc/libcontainer
implements OCI-runtime-spec-undocumented behavior to create
/dev/{ptmx,fd,stdin,stdout,stderr} in non-bind /dev mounts. runsc silently
switches /dev to devtmpfs. In VFS1, this is necessary to get device files like
/dev/null at all, since VFS1 doesn't support real device special files, only
what is hardcoded in devfs. VFS2 does support device special files, but using
devtmpfs is the easiest way to get pre-created files in /dev.)

runsc ignores many /dev submounts in the spec, including /dev/shm. In VFS1,
this appears to be to avoid introducing a submount overlay for /dev, and is
mostly fine since the typical mode for the /dev/shm mount is ~consistent with
the mode of the /dev/shm directory provided by devfs (modulo the sticky bit).
In VFS2, this is vestigial (VFS2 does not use submount overlays), and devtmpfs'
/dev/shm mode is correct for the mount point but not the mount. So turn off
this behavior for VFS2.

After this change:

```
$ docker run --rm -it ubuntu:focal ls -lah /dev/shm
total 0
drwxrwxrwt 2 root root  40 Mar 18 00:16 .
drwxr-xr-x 5 root root 360 Mar 18 00:16 ..

$ docker run --runtime=runsc --rm -it ubuntu:focal ls -lah /dev/shm
total 0
drwxrwxrwx 1 root root 0 Mar 18 00:16 .
dr-xr-xr-x 1 root root 0 Mar 18 00:16 ..

$ docker run --runtime=runsc-vfs2 --rm -it ubuntu:focal ls -lah /dev/shm
total 0
drwxrwxrwt 2 root root  40 Mar 18 00:16 .
drwxr-xr-x 5 root root 320 Mar 18 00:16 ..
```

Fixes #5687

PiperOrigin-RevId: 363699385

1 files changed, 4 insertions, 4 deletions

diff --git a/runsc/boot/fs.go b/runsc/boot/fs.go
index 77f632bb9..d1dacee03 100644
--- a/runsc/boot/fs.go
+++ b/runsc/boot/fs.go
@@ -103,14 +103,14 @@ func addOverlay(ctx context.Context, conf *config.Config, lower *fs.Inode, name
 
 // compileMounts returns the supported mounts from the mount spec, adding any
 // mandatory mounts that are required by the OCI specification.
-func compileMounts(spec *specs.Spec) []specs.Mount {
+func compileMounts(spec *specs.Spec, vfs2Enabled bool) []specs.Mount {
 	// Keep track of whether proc and sys were mounted.
 	var procMounted, sysMounted, devMounted, devptsMounted bool
 	var mounts []specs.Mount
 
 	// Mount all submounts from the spec.
 	for _, m := range spec.Mounts {
-		if !specutils.IsSupportedDevMount(m) {
+		if !vfs2Enabled && !specutils.IsVFS1SupportedDevMount(m) {
 			log.Warningf("ignoring dev mount at %q", m.Destination)
 			continue
 		}
@@ -572,10 +572,10 @@ type containerMounter struct {
 	hints *podMountHints
 }
 
-func newContainerMounter(spec *specs.Spec, goferFDs []*fd.FD, k *kernel.Kernel, hints *podMountHints) *containerMounter {
+func newContainerMounter(spec *specs.Spec, goferFDs []*fd.FD, k *kernel.Kernel, hints *podMountHints, vfs2Enabled bool) *containerMounter {
 	return &containerMounter{
 		root:   spec.Root,
-		mounts: compileMounts(spec),
+		mounts: compileMounts(spec, vfs2Enabled),
 		fds:    fdDispenser{fds: goferFDs},
 		k:      k,
 		hints:  hints,