Merge pull request #4025 from deitch/tag-sources-in-tar

include image reference as source in every tar file header

src/cmd/linuxkit/moby/apk_tarwriter.go

@@ -8,17 +8,21 @@ import (
 // apkTarWriter apk-aware tar writer that consolidates installed database, so that
 // it can be called multiple times and will do the union of all such databases,
 // rather than overwriting the previous one.
+// Useful only for things that write to the base filesystem, i.e. init, since everything
+// else is inside containers.
 const apkInstalledPath = "lib/apk/db/installed"
 
 type apkTarWriter struct {
 	*tar.Writer
 	dbs      [][]byte
 	current  *bytes.Buffer
+	location string
 }
 
-func newAPKTarWriter(w *tar.Writer) *apkTarWriter {
+func newAPKTarWriter(w *tar.Writer, location string) *apkTarWriter {
 	return &apkTarWriter{
 		Writer:   w,
+		location: location,
 	}
 }
 
@@ -67,6 +71,10 @@ func (a *apkTarWriter) WriteAPKDB() error {
 			Gid:      0,
 			Typeflag: tar.TypeReg,
 			Size:     int64(size),
+			PAXRecords: map[string]string{
+				PaxRecordLinuxkitSource:   "LINUXKIT.apkinit",
+				PaxRecordLinuxkitLocation: a.location,
+			},
 		}
 		if err := a.Writer.WriteHeader(hdr); err != nil {
 			return err

src/cmd/linuxkit/moby/build.go

@@ -92,25 +92,25 @@ func outputImage(image *Image, section string, prefix string, m Moby, idMap map[
 	}
 	src, err := imagePull(&ref, opts.Pull, opts.CacheDir, opts.DockerCache, opts.Arch)
 	if err != nil {
-		return fmt.Errorf("Could not pull image %s: %v", image.Image, err)
+		return fmt.Errorf("could not pull image %s: %v", image.Image, err)
 	}
 	configRaw, err := src.Config()
 	if err != nil {
-		return fmt.Errorf("Failed to retrieve config for %s: %v", image.Image, err)
+		return fmt.Errorf("failed to retrieve config for %s: %v", image.Image, err)
 	}
 	oci, runtime, err := ConfigToOCI(image, configRaw, idMap)
 	if err != nil {
-		return fmt.Errorf("Failed to create OCI spec for %s: %v", image.Image, err)
+		return fmt.Errorf("failed to create OCI spec for %s: %v", image.Image, err)
 	}
 	config, err := json.MarshalIndent(oci, "", "    ")
 	if err != nil {
-		return fmt.Errorf("Failed to create config for %s: %v", image.Image, err)
+		return fmt.Errorf("failed to create config for %s: %v", image.Image, err)
 	}
 	path := path.Join("containers", section, prefix+image.Name)
 	readonly := oci.Root.Readonly
-	err = ImageBundle(path, image.ref, config, runtime, iw, readonly, dupMap, opts)
+	err = ImageBundle(path, section, image.ref, config, runtime, iw, readonly, dupMap, opts)
 	if err != nil {
-		return fmt.Errorf("Failed to extract root filesystem for %s: %v", image.Image, err)
+		return fmt.Errorf("failed to extract root filesystem for %s: %v", image.Image, err)
 	}
 	return nil
 }
@@ -153,14 +153,14 @@ func Build(m Moby, w io.Writer, opts BuildOpts) error {
 	if m.Kernel.ref != nil {
 		// get kernel and initrd tarball and ucode cpio archive from container
 		log.Infof("Extract kernel image: %s", m.Kernel.ref)
-		kf := newKernelFilter(iw, m.Kernel.Cmdline, m.Kernel.Binary, m.Kernel.Tar, m.Kernel.UCode, opts.DecompressKernel)
-		err := ImageTar(m.Kernel.ref, "", kf, "", opts)
+		kf := newKernelFilter(m.Kernel.ref, iw, m.Kernel.Cmdline, m.Kernel.Binary, m.Kernel.Tar, m.Kernel.UCode, opts.DecompressKernel)
+		err := ImageTar("kernel", m.Kernel.ref, "", kf, "", opts)
 		if err != nil {
-			return fmt.Errorf("Failed to extract kernel image and tarball: %v", err)
+			return fmt.Errorf("failed to extract kernel image and tarball: %v", err)
 		}
 		err = kf.Close()
 		if err != nil {
-			return fmt.Errorf("Close error: %v", err)
+			return fmt.Errorf("close error: %v", err)
 		}
 	}
 
@@ -168,10 +168,10 @@ func Build(m Moby, w io.Writer, opts BuildOpts) error {
 	if len(m.Init) != 0 {
 		log.Infof("Add init containers:")
 	}
-	apkTar := newAPKTarWriter(iw)
+	apkTar := newAPKTarWriter(iw, "init")
 	for _, ii := range m.initRefs {
 		log.Infof("Process init image: %s", ii)
-		err := ImageTar(ii, "", apkTar, resolvconfSymlink, opts)
+		err := ImageTar("init", ii, "", apkTar, resolvconfSymlink, opts)
 		if err != nil {
 			return fmt.Errorf("failed to build init tarball from %s: %v", ii, err)
 		}
@@ -252,9 +252,10 @@ type kernelFilter struct {
 	foundKernel      bool
 	foundKTar        bool
 	foundUCode       bool
+	ref              *reference.Spec
 }
 
-func newKernelFilter(tw *tar.Writer, cmdline string, kernel string, tar, ucode *string, decompressKernel bool) *kernelFilter {
+func newKernelFilter(ref *reference.Spec, tw *tar.Writer, cmdline string, kernel string, tar, ucode *string, decompressKernel bool) *kernelFilter {
 	tarName, kernelName, ucodeName := "kernel.tar", "kernel", ""
 	if tar != nil {
 		tarName = *tar
@@ -268,7 +269,7 @@ func newKernelFilter(tw *tar.Writer, cmdline string, kernel string, tar, ucode *
 	if ucode != nil {
 		ucodeName = *ucode
 	}
-	return &kernelFilter{tw: tw, cmdline: cmdline, kernel: kernelName, tar: tarName, ucode: ucodeName, decompressKernel: decompressKernel}
+	return &kernelFilter{ref: ref, tw: tw, cmdline: cmdline, kernel: kernelName, tar: tarName, ucode: ucodeName, decompressKernel: decompressKernel}
 }
 
 func (k *kernelFilter) finishTar() error {
@@ -299,7 +300,7 @@ func (k *kernelFilter) finishTar() error {
 	}
 
 	tr := tar.NewReader(k.buffer)
-	err := tarAppend(k.tw, tr)
+	err := tarAppend(k.ref, k.tw, tr)
 	k.buffer = nil
 	return err
 }
@@ -353,6 +354,7 @@ func (k *kernelFilter) WriteHeader(hdr *tar.Header) error {
 				Typeflag:   tar.TypeDir,
 				ModTime:    defaultModTime,
 				Format:     tar.FormatPAX,
+				PAXRecords: hdr.PAXRecords,
 			}
 			if err := tw.WriteHeader(whdr); err != nil {
 				return err
@@ -365,6 +367,7 @@ func (k *kernelFilter) WriteHeader(hdr *tar.Header) error {
 			Size:       int64(len(k.cmdline)),
 			ModTime:    defaultModTime,
 			Format:     tar.FormatPAX,
+			PAXRecords: hdr.PAXRecords,
 		}
 		if err := tw.WriteHeader(whdr); err != nil {
 			return err
@@ -380,6 +383,7 @@ func (k *kernelFilter) WriteHeader(hdr *tar.Header) error {
 			Size:       hdr.Size,
 			ModTime:    defaultModTime,
 			Format:     tar.FormatPAX,
+			PAXRecords: hdr.PAXRecords,
 		}
 		k.buffer = new(bytes.Buffer)
 	case k.tar:
@@ -397,6 +401,7 @@ func (k *kernelFilter) WriteHeader(hdr *tar.Header) error {
 				Typeflag:   tar.TypeDir,
 				ModTime:    defaultModTime,
 				Format:     tar.FormatPAX,
+				PAXRecords: hdr.PAXRecords,
 			}
 			if err := tw.WriteHeader(whdr); err != nil {
 				return err
@@ -408,6 +413,7 @@ func (k *kernelFilter) WriteHeader(hdr *tar.Header) error {
 			Size:       hdr.Size,
 			ModTime:    defaultModTime,
 			Format:     tar.FormatPAX,
+			PAXRecords: hdr.PAXRecords,
 		}
 		if err := tw.WriteHeader(whdr); err != nil {
 			return err
@@ -419,7 +425,7 @@ func (k *kernelFilter) WriteHeader(hdr *tar.Header) error {
 	return nil
 }
 
-func tarAppend(iw *tar.Writer, tr *tar.Reader) error {
+func tarAppend(ref *reference.Spec, iw *tar.Writer, tr *tar.Reader) error {
 	for {
 		hdr, err := tr.Next()
 		if err == io.EOF {
@@ -428,6 +434,12 @@ func tarAppend(iw *tar.Writer, tr *tar.Reader) error {
 		if err != nil {
 			return err
 		}
+		hdr.Format = tar.FormatPAX
+		if hdr.PAXRecords == nil {
+			hdr.PAXRecords = make(map[string]string)
+		}
+		hdr.PAXRecords[PaxRecordLinuxkitSource] = ref.String()
+		hdr.PAXRecords[PaxRecordLinuxkitLocation] = "kernel"
 		err = iw.WriteHeader(hdr)
 		if err != nil {
 			return err
@@ -478,7 +490,7 @@ func decompressKernel(src *bytes.Buffer) (*bytes.Buffer, error) {
 		versionMajor := int(s[versionIdx])
 		versionMinor := int(s[versionIdx+1])
 		if versionMajor < 2 && versionMinor < 8 {
-			return nil, fmt.Errorf("Unsupported bzImage version: %d.%d", versionMajor, versionMinor)
+			return nil, fmt.Errorf("unsupported bzImage version: %d.%d", versionMajor, versionMinor)
 		}
 
 		setupSectors := uint32(s[setupSectorsIdx])
@@ -488,7 +500,7 @@ func decompressKernel(src *bytes.Buffer) (*bytes.Buffer, error) {
 		log.Debugf("bzImage: Payload at Offset: %d Length: %d", payloadOff, payloadLen)
 
 		if len(s) < int(payloadOff+payloadLen) {
-			return nil, fmt.Errorf("Compressed bzImage payload exceeds size of image")
+			return nil, fmt.Errorf("compressed bzImage payload exceeds size of image")
 		}
 
 		if bytes.HasPrefix(s[payloadOff:], []byte(gzipMagic)) {
@@ -496,10 +508,10 @@ func decompressKernel(src *bytes.Buffer) (*bytes.Buffer, error) {
 			return gunzip(bytes.NewBuffer(s[payloadOff : payloadOff+payloadLen]))
 		}
 		// TODO(rn): Add more supported formats
-		return nil, fmt.Errorf("Unsupported bzImage payload format at offset %d", payloadOff)
+		return nil, fmt.Errorf("unsupported bzImage payload format at offset %d", payloadOff)
 	}
 
-	return nil, fmt.Errorf("No compressed kernel or no supported format found")
+	return nil, fmt.Errorf("no compressed kernel or no supported format found")
 }
 
 func gunzip(src *bytes.Buffer) (*bytes.Buffer, error) {
@@ -529,7 +541,7 @@ func metadata(m Moby, md string) ([]byte, error) {
 	case "yaml":
 		return yaml.Marshal(m)
 	default:
-		return []byte{}, fmt.Errorf("Unsupported metadata type: %s", md)
+		return []byte{}, fmt.Errorf("unsupported metadata type: %s", md)
 	}
 }
 
@@ -540,10 +552,10 @@ func filesystem(m Moby, tw *tar.Writer, idMap map[string]uint32) error {
 	if len(m.Files) != 0 {
 		log.Infof("Add files:")
 	}
-	for _, f := range m.Files {
+	for filecount, f := range m.Files {
 		log.Infof("  %s", f.Path)
 		if f.Path == "" {
-			return errors.New("Did not specify path for file")
+			return errors.New("did not specify path for file")
 		}
 		// tar archives should not have absolute paths
 		if f.Path[0] == '/' {
@@ -557,7 +569,7 @@ func filesystem(m Moby, tw *tar.Writer, idMap map[string]uint32) error {
 			var err error
 			mode, err = strconv.ParseInt(f.Mode, 8, 32)
 			if err != nil {
-				return fmt.Errorf("Cannot parse file mode as octal value: %v", err)
+				return fmt.Errorf("cannot parse file mode as octal value: %v", err)
 			}
 		}
 		dirMode := mode
@@ -586,10 +598,10 @@ func filesystem(m Moby, tw *tar.Writer, idMap map[string]uint32) error {
 		}
 		if !f.Directory && f.Symlink == "" && f.Contents == nil {
 			if f.Source == "" && f.Metadata == "" {
-				return fmt.Errorf("Contents of file (%s) not specified", f.Path)
+				return fmt.Errorf("contents of file (%s) not specified", f.Path)
 			}
 			if f.Source != "" && f.Metadata != "" {
-				return fmt.Errorf("Specified Source and Metadata for file: %s", f.Path)
+				return fmt.Errorf("specified Source and Metadata for file: %s", f.Path)
 			}
 			if f.Source != "" {
 				source := f.Source
@@ -600,7 +612,7 @@ func filesystem(m Moby, tw *tar.Writer, idMap map[string]uint32) error {
 					_, err := os.Stat(source)
 					if err != nil {
 						// skip if not found or readable
-						log.Debugf("Skipping file [%s] as not readable and marked optional", source)
+						log.Debugf("skipping file [%s] as not readable and marked optional", source)
 						continue
 					}
 				}
@@ -617,10 +629,10 @@ func filesystem(m Moby, tw *tar.Writer, idMap map[string]uint32) error {
 			}
 		} else {
 			if f.Metadata != "" {
-				return fmt.Errorf("Specified Contents and Metadata for file: %s", f.Path)
+				return fmt.Errorf("specified Contents and Metadata for file: %s", f.Path)
 			}
 			if f.Source != "" {
-				return fmt.Errorf("Specified Contents and Source for file: %s", f.Path)
+				return fmt.Errorf("specified Contents and Source for file: %s", f.Path)
 			}
 		}
 		// we need all the leading directories
@@ -644,6 +656,10 @@ func filesystem(m Moby, tw *tar.Writer, idMap map[string]uint32) error {
 					Uid:      int(uid),
 					Gid:      int(gid),
 					Format:   tar.FormatPAX,
+					PAXRecords: map[string]string{
+						PaxRecordLinuxkitSource:   "linuxkit.files",
+						PaxRecordLinuxkitLocation: fmt.Sprintf("files[%d]", filecount),
+					},
 				}
 				err := tw.WriteHeader(hdr)
 				if err != nil {
@@ -660,10 +676,14 @@ func filesystem(m Moby, tw *tar.Writer, idMap map[string]uint32) error {
 			Uid:     int(uid),
 			Gid:     int(gid),
 			Format:  tar.FormatPAX,
+			PAXRecords: map[string]string{
+				PaxRecordLinuxkitSource:   "linuxkit.files",
+				PaxRecordLinuxkitLocation: fmt.Sprintf("files[%d]", filecount),
+			},
 		}
 		if f.Directory {
 			if f.Contents != nil {
-				return errors.New("Directory with contents not allowed")
+				return errors.New("directory with contents not allowed")
 			}
 			hdr.Typeflag = tar.TypeDir
 			err := tw.WriteHeader(hdr)

src/cmd/linuxkit/moby/image.go

@@ -14,6 +14,14 @@ import (
 	log "github.com/sirupsen/logrus"
 )
 
+const (
+	// PaxRecordLinuxkitSource report the package source for a specific file
+	PaxRecordLinuxkitSource = "LINUXKIT.source"
+	// PaxRecordLinuxkitLocation report the location of the file in the linuxkit.yaml
+	// that led to this file being in this location
+	PaxRecordLinuxkitLocation = "LINUXKIT.location"
+)
+
 type tarWriter interface {
 	Close() error
 	Flush() error
@@ -140,7 +148,8 @@ var touch = map[string]tar.Header{
 }
 
 // tarPrefix creates the leading directories for a path
-func tarPrefix(path string, tw tarWriter) error {
+// path is the path to prefix, location is where this appears in the linuxkit.yaml file
+func tarPrefix(path, location string, ref *reference.Spec, tw tarWriter) error {
 	if path == "" {
 		return nil
 	}
@@ -160,6 +169,10 @@ func tarPrefix(path string, tw tarWriter) error {
 			ModTime:  defaultModTime,
 			Typeflag: tar.TypeDir,
 			Format:   tar.FormatPAX,
+			PAXRecords: map[string]string{
+				PaxRecordLinuxkitSource:   ref.String(),
+				PaxRecordLinuxkitLocation: location,
+			},
 		}
 		if err := tw.WriteHeader(hdr); err != nil {
 			return err
@@ -170,13 +183,14 @@ func tarPrefix(path string, tw tarWriter) error {
 }
 
 // ImageTar takes a Docker image and outputs it to a tar stream
-func ImageTar(ref *reference.Spec, prefix string, tw tarWriter, resolv string, opts BuildOpts) (e error) {
+// location is where it is in the linuxkit.yaml file
+func ImageTar(location string, ref *reference.Spec, prefix string, tw tarWriter, resolv string, opts BuildOpts) (e error) {
 	log.Debugf("image tar: %s %s", ref, prefix)
 	if prefix != "" && prefix[len(prefix)-1] != '/' {
 		return fmt.Errorf("prefix does not end with /: %s", prefix)
 	}
 
-	err := tarPrefix(prefix, tw)
+	err := tarPrefix(prefix, location, ref, tw)
 	if err != nil {
 		return err
 	}
@@ -185,12 +199,12 @@ func ImageTar(ref *reference.Spec, prefix string, tw tarWriter, resolv string, o
 	// If pull==true, then it always tries to pull from registry.
 	src, err := imagePull(ref, opts.Pull, opts.CacheDir, opts.DockerCache, opts.Arch)
 	if err != nil {
-		return fmt.Errorf("Could not pull image %s: %v", ref, err)
+		return fmt.Errorf("could not pull image %s: %v", ref, err)
 	}
 
 	contents, err := src.TarReader()
 	if err != nil {
-		return fmt.Errorf("Could not unpack image %s: %v", ref, err)
+		return fmt.Errorf("could not unpack image %s: %v", ref, err)
 	}
 
 	defer contents.Close()
@@ -214,6 +228,12 @@ func ImageTar(ref *reference.Spec, prefix string, tw tarWriter, resolv string, o
 		// force PAX format, since it allows for unlimited Name/Linkname
 		// and we move all files below prefix.
 		hdr.Format = tar.FormatPAX
+		// ensure we record the source of the file in the PAX header
+		if hdr.PAXRecords == nil {
+			hdr.PAXRecords = make(map[string]string)
+		}
+		hdr.PAXRecords[PaxRecordLinuxkitSource] = ref.String()
+		hdr.PAXRecords[PaxRecordLinuxkitLocation] = location
 		if exclude[hdr.Name] {
 			log.Debugf("image tar: %s %s exclude %s", ref, prefix, hdr.Name)
 			_, err = io.Copy(io.Discard, tr)
@@ -286,6 +306,12 @@ func ImageTar(ref *reference.Spec, prefix string, tw tarWriter, resolv string, o
 			continue
 		}
 		hdr := touch[name]
+		// ensure that we record the source of the file
+		if hdr.PAXRecords == nil {
+			hdr.PAXRecords = make(map[string]string)
+		}
+		hdr.PAXRecords[PaxRecordLinuxkitSource] = ref.String()
+		hdr.PAXRecords[PaxRecordLinuxkitLocation] = location
 		origName := hdr.Name
 		hdr.Name = prefix + origName
 		hdr.Format = tar.FormatPAX
@@ -329,7 +355,7 @@ func ImageTar(ref *reference.Spec, prefix string, tw tarWriter, resolv string, o
 }
 
 // ImageBundle produces an OCI bundle at the given path in a tarball, given an image and a config.json
-func ImageBundle(prefix string, ref *reference.Spec, config []byte, runtime Runtime, tw tarWriter, readonly bool, dupMap map[string]string, opts BuildOpts) error { // nolint: lll
+func ImageBundle(prefix, location string, ref *reference.Spec, config []byte, runtime Runtime, tw tarWriter, readonly bool, dupMap map[string]string, opts BuildOpts) error { // nolint: lll
 	// if read only, just unpack in rootfs/ but otherwise set up for overlay
 	rootExtract := "rootfs"
 	if !readonly {
@@ -340,12 +366,12 @@ func ImageBundle(prefix string, ref *reference.Spec, config []byte, runtime Runt
 	root := path.Join(prefix, rootExtract)
 	var foundElsewhere = dupMap[ref.String()] != ""
 	if !foundElsewhere {
-		if err := ImageTar(ref, root+"/", tw, "", opts); err != nil {
+		if err := ImageTar(location, ref, root+"/", tw, "", opts); err != nil {
 			return err
 		}
 		dupMap[ref.String()] = root
 	} else {
-		if err := tarPrefix(prefix+"/", tw); err != nil {
+		if err := tarPrefix(prefix+"/", location, ref, tw); err != nil {
 			return err
 		}
 		root = dupMap[ref.String()]
@@ -357,6 +383,10 @@ func ImageBundle(prefix string, ref *reference.Spec, config []byte, runtime Runt
 		Size:    int64(len(config)),
 		ModTime: defaultModTime,
 		Format:  tar.FormatPAX,
+		PAXRecords: map[string]string{
+			PaxRecordLinuxkitSource:   ref.String(),
+			PaxRecordLinuxkitLocation: location,
+		},
 	}
 	if err := tw.WriteHeader(hdr); err != nil {
 		return err
@@ -375,6 +405,10 @@ func ImageBundle(prefix string, ref *reference.Spec, config []byte, runtime Runt
 			Typeflag: tar.TypeDir,
 			ModTime:  defaultModTime,
 			Format:   tar.FormatPAX,
+			PAXRecords: map[string]string{
+				PaxRecordLinuxkitSource:   ref.String(),
+				PaxRecordLinuxkitLocation: location,
+			},
 		}
 		if err := tw.WriteHeader(hdr); err != nil {
 			return err
@@ -386,6 +420,10 @@ func ImageBundle(prefix string, ref *reference.Spec, config []byte, runtime Runt
 			Typeflag: tar.TypeDir,
 			ModTime:  defaultModTime,
 			Format:   tar.FormatPAX,
+			PAXRecords: map[string]string{
+				PaxRecordLinuxkitSource:   ref.String(),
+				PaxRecordLinuxkitLocation: location,
+			},
 		}
 		if err := tw.WriteHeader(hdr); err != nil {
 			return err
@@ -406,6 +444,10 @@ func ImageBundle(prefix string, ref *reference.Spec, config []byte, runtime Runt
 				Typeflag: tar.TypeDir,
 				ModTime:  defaultModTime,
 				Format:   tar.FormatPAX,
+				PAXRecords: map[string]string{
+					PaxRecordLinuxkitSource:   ref.String(),
+					PaxRecordLinuxkitLocation: location,
+				},
 			}
 			if err := tw.WriteHeader(hdr); err != nil {
 				return err
@@ -424,7 +466,7 @@ func ImageBundle(prefix string, ref *reference.Spec, config []byte, runtime Runt
 	// write the runtime config
 	runtimeConfig, err := json.MarshalIndent(runtime, "", "    ")
 	if err != nil {
-		return fmt.Errorf("Failed to create runtime config for %s: %v", ref, err)
+		return fmt.Errorf("failed to create runtime config for %s: %v", ref, err)
 	}
 
 	hdr = &tar.Header{
@@ -433,6 +475,10 @@ func ImageBundle(prefix string, ref *reference.Spec, config []byte, runtime Runt
 		Size:    int64(len(runtimeConfig)),
 		ModTime: defaultModTime,
 		Format:  tar.FormatPAX,
+		PAXRecords: map[string]string{
+			PaxRecordLinuxkitSource:   ref.String(),
+			PaxRecordLinuxkitLocation: location,
+		},
 	}
 	if err := tw.WriteHeader(hdr); err != nil {
 		return err

test/cases/000_build/001_tarheaders/tarheaders.py

@@ -0,0 +1,31 @@
+import tarfile
+import sys
+
+def list_pax_headers(archive_path):
+    # Open the tar archive
+    try:
+        with tarfile.open(archive_path, 'r') as tar:
+            # Iterate over each member in the tar archive
+            for member in tar.getmembers():
+                # ignore the root directory, which just exists
+                if member.name == '.':
+                    continue
+                # Check if there are any PAX headers
+                if member.pax_headers:
+                    # Check for the specific PAX header
+                    if 'LINUXKIT.source' not in member.pax_headers:
+                        print(f"File: {member.name} is missing LINUXKIT.source PAX Header.")
+                    if 'LINUXKIT.location' not in member.pax_headers:
+                        print(f"File: {member.name} is missing LINUXKIT.source PAX Header.")
+                else:
+                    print(f"File: {member.name} has No PAX Headers.")
+    except Exception as e:
+        print("Failed to read tar archive:", e)
+        sys.exit(1)
+
+if __name__ == "__main__":
+    if len(sys.argv) != 2:
+        print("Usage: python list_pax_headers.py <archive.tar>")
+        sys.exit(1)
+    archive_filename = sys.argv[1]
+    list_pax_headers(archive_filename)

test/cases/000_build/001_tarheaders/test.sh

@@ -0,0 +1,38 @@
+#!/bin/sh
+# SUMMARY: Check that tar output format build contains proper headers for each file
+# LABELS:
+
+set -e
+
+# Source libraries. Uncomment if needed/defined
+#. "${RT_LIB}"
+. "${RT_PROJECT_ROOT}/_lib/lib.sh"
+
+NAME=tarheaders
+
+clean_up() {
+	rm -f ${NAME}*
+}
+
+trap clean_up EXIT
+
+# do not include the sbom, because the SBoM unique IDs per file/package are *not* deterministic,
+# (currently based upon syft), and thus will make the file non-reproducible
+linuxkit build --no-sbom --format tar --name "${NAME}" ./test.yml
+
+# Check that the tarball contains the expected headers
+# see that python is installed
+PYTHON=
+if which python ; then PYTHON=python ; elif which python3; then PYTHON=python3 ; else
+echo "Failed to find any executable python or python3"
+exit 1
+fi
+FAILED=$(python ./tarheaders.py "${NAME}.tar")
+
+if [ -n "${FAILED}" ]; then
+	echo "Failed to find linuxkit.packagesource headers for the following files:"
+	echo "${FAILED}"
+	exit 1
+fi
+
+exit 0

test/cases/000_build/001_tarheaders/test.yml

@@ -0,0 +1,46 @@
+# NOTE: Images build from this file likely do not run
+kernel:
+  image: linuxkit/kernel:6.6.13
+  cmdline: "console=ttyS0"
+init:
+  - linuxkit/init:45a1ad5919f0b6acf0f0cf730e9434abfae11fe6
+  - linuxkit/runc:6062483d748609d505f2bcde4e52ee64a3329f5f
+  - linuxkit/containerd:e7a92d9f3282039eac5fb1b07cac2b8664cbf0ad
+
+onboot:
+  - name: dhcpcd
+    image: linuxkit/dhcpcd:e9e3580f2de00e73e7b316a007186d22fea056ee
+    command: ["/sbin/dhcpcd", "--nobackground", "-f", "/dhcpcd.conf", "-1"]
+    # Add some random unsorted caps
+    capabilities:
+      - CAP_SETGID
+      - CAP_DAC_OVERRIDE
+
+services:
+  - name: testservice
+    image: linuxkit/ip:bb250017b05de5e16ac436b1eb19a39c87b5a252
+    # Some environments
+    env:
+      - BENV=true
+      - ARANDOMENV=foobar
+    # Some mounts
+    mounts:
+      - type: cgroup
+        options: ["rw","nosuid","noexec","nodev","relatime"]
+      - type: overlay
+        source: overlay
+        destination: writeable-host-etc
+        options: ["rw", "lowerdir=/etc", "upperdir=/run/hostetc/upper", "workdir=/run/hostetc/work"]
+    # Some binds
+    binds:
+      - /var/run:/var/run
+      - /foobar:/foobar
+      - /etc/foobar:/etc/foobar
+      - /etc/aaa:/etc/aaa
+    # And some runtime settings
+    runtime:
+      mkdir: ["/var/lib/docker","/var/lib/aaa"]
+
+files:
+  - path: etc/linuxkit-config
+    metadata: yaml