[PATCH v5] do_image: Implement IMAGE_ROOTFS_EXCLUDE_PATH feature.

[Kristian Amlie <kristian.amlie@northern.tech>]

From: Kristian Amlie <kristian.amlie@mender.io>

This is a direct followup from the earlier f6a064d969f414 commit in
wic. It works more or less the same way: The variable specifies a list
of directories relative to the root of the rootfs, and these
directories will be excluded from the resulting rootfs image. If an
entry ends with a slash, only the contents are omitted, not the
directory itself.

Since the intended use of the variable is to exclude certain
directories from the rootfs, and then include said directories in
other partitions, it is not natural for this variable to be respected
for image creators that create multi partition images. Therefore the
default is to ignore the variable, and image creators that create
single root filesystems need to set

  do_image_myfs[respect_exclude_path] = "1"

in order to honor it. Specifically, "wic" and "multiubi" have not
received this variable flag, while others have.

Signed-off-by: Kristian Amlie <kristian.amlie@mender.io>
---
 documentation/ref-manual/ref-variables.xml | 35 +++++++++++++
 meta/classes/image.bbclass                 | 83 +++++++++++++++++++++++++++++-
 meta/classes/image_types.bbclass           | 13 +++++
 3 files changed, 129 insertions(+), 2 deletions(-)

diff --git a/documentation/ref-manual/ref-variables.xml b/documentation/ref-manual/ref-variables.xml
index ff8f4e7..a4f2de5 100644
--- a/documentation/ref-manual/ref-variables.xml
+++ b/documentation/ref-manual/ref-variables.xml
@@ -6043,6 +6043,41 @@
             </glossdef>
         </glossentry>
 
+        <glossentry id='var-IMAGE_ROOTFS_EXCLUDE_PATH'><glossterm>IMAGE_ROOTFS_EXCLUDE_PATH</glossterm>
+            <info>
+                IMAGE_ROOTFS_EXCLUDE_PATH[doc] = "Specifies paths to omit from the rootfs."
+            </info>
+            <glossdef>
+                <para role="glossdeffirst">
+<!--                <para role="glossdeffirst"><imagedata fileref="figures/define-generic.png" /> -->
+                    Specifies paths that should be omitted from the root filesystem, separated by
+                    spaces. The paths must be relative to the root of the filesystem (for example
+                    "usr"). Single root filesystem images will not include the path in the
+                    filesystem, except if the path ends with a slash, then the directory will be
+                    included, but without any content.
+                    <literallayout class='monospaced'>
+     # Omit /usr completely from rootfs.
+     IMAGE_ROOTFS_EXCLUDE_PATH += "<replaceable>usr</replaceable> ..."
+     # Include the directory /usr in rootfs, but not its content.
+     IMAGE_ROOTFS_EXCLUDE_PATH += "<replaceable>usr/</replaceable> ..."
+                    </literallayout>
+                </para>
+                <para>
+                    Image creators that create multi partition images typically do not honor this
+                    variable, and must provide their own method to split the directory
+                    structure. For example, <filename>wic</filename> has
+                    <filename>--exclude-path</filename> and <filename>--rootfs-dir</filename>.
+                </para>
+                <para>
+                    The default for custom image creators is to ignore this variable. Those that
+                    need to honor it must set:
+                    <literallayout class='monospaced'>
+     do_image_<replaceable>custom</replaceable>[respect_exclude_path] = "1"
+                    </literallayout>
+                </para>
+            </glossdef>
+        </glossentry>
+
         <glossentry id='var-IMAGE_ROOTFS_EXTRA_SPACE'><glossterm>IMAGE_ROOTFS_EXTRA_SPACE</glossterm>
             <info>
                 IMAGE_ROOTFS_EXTRA_SPACE[doc] = "Defines additional free disk space created in the image in Kbytes. By default, this variable is set to '0'."
diff --git a/meta/classes/image.bbclass b/meta/classes/image.bbclass
index 3639aa4..e215541 100644
--- a/meta/classes/image.bbclass
+++ b/meta/classes/image.bbclass
@@ -117,7 +117,8 @@ def rootfs_variables(d):
                  'IMAGE_ROOTFS_MAXSIZE','IMAGE_NAME','IMAGE_LINK_NAME','IMAGE_MANIFEST','DEPLOY_DIR_IMAGE','IMAGE_FSTYPES','IMAGE_INSTALL_COMPLEMENTARY','IMAGE_LINGUAS',
                  'MULTILIBRE_ALLOW_REP','MULTILIB_TEMP_ROOTFS','MULTILIB_VARIANTS','MULTILIBS','ALL_MULTILIB_PACKAGE_ARCHS','MULTILIB_GLOBAL_VARIANTS','BAD_RECOMMENDATIONS','NO_RECOMMENDATIONS',
                  'PACKAGE_ARCHS','PACKAGE_CLASSES','TARGET_VENDOR','TARGET_ARCH','TARGET_OS','OVERRIDES','BBEXTENDVARIANT','FEED_DEPLOYDIR_BASE_URI','INTERCEPT_DIR','USE_DEVFS',
-                 'CONVERSIONTYPES', 'IMAGE_GEN_DEBUGFS', 'ROOTFS_RO_UNNEEDED', 'IMGDEPLOYDIR', 'PACKAGE_EXCLUDE_COMPLEMENTARY', 'REPRODUCIBLE_TIMESTAMP_ROOTFS']
+                 'CONVERSIONTYPES', 'IMAGE_GEN_DEBUGFS', 'ROOTFS_RO_UNNEEDED', 'IMGDEPLOYDIR', 'PACKAGE_EXCLUDE_COMPLEMENTARY', 'REPRODUCIBLE_TIMESTAMP_ROOTFS',
+                 'IMAGE_ROOTFS_EXCLUDE_PATH']
     variables.extend(rootfs_command_variables(d))
     variables.extend(variable_depends(d))
     return " ".join(variables)
@@ -496,8 +497,9 @@ python () {
         d.setVarFlag(task, 'func', '1')
         d.setVarFlag(task, 'fakeroot', '1')
 
-        d.appendVarFlag(task, 'prefuncs', ' ' + debug + ' set_image_size')
+        d.appendVarFlag(task, 'prefuncs', ' ' + debug + ' set_image_size prepare_excluded_directories')
         d.prependVarFlag(task, 'postfuncs', ' create_symlinks')
+        d.appendVarFlag(task, 'postfuncs', ' cleanup_excluded_directories')
         d.appendVarFlag(task, 'subimages', ' ' + ' '.join(subimages))
         d.appendVarFlag(task, 'vardeps', ' ' + ' '.join(vardeps))
         d.appendVarFlag(task, 'vardepsexclude', 'DATETIME DATE')
@@ -506,6 +508,83 @@ python () {
         bb.build.addtask(task, 'do_image_complete', after, d)
 }
 
+python prepare_excluded_directories() {
+    exclude_var = d.getVar('IMAGE_ROOTFS_EXCLUDE_PATH')
+    if not exclude_var:
+        return
+
+    taskname = d.getVar("BB_CURRENTTASK")
+
+    if d.getVarFlag('do_%s' % taskname, 'respect_exclude_path') != '1':
+        return
+
+    import shutil
+    from oe.path import copyhardlinktree
+
+    exclude_list = exclude_var.split()
+
+    rootfs_orig = d.getVar('IMAGE_ROOTFS')
+    # We need a new rootfs directory we can delete files from. Copy to
+    # workdir.
+    new_rootfs = os.path.realpath(os.path.join(d.getVar("WORKDIR"), "rootfs.%s" % taskname))
+
+    if os.path.lexists(new_rootfs):
+        shutil.rmtree(os.path.join(new_rootfs))
+
+    copyhardlinktree(rootfs_orig, new_rootfs)
+
+    for orig_path in exclude_list:
+        path = orig_path
+        if os.path.isabs(path):
+            bb.fatal("IMAGE_ROOTFS_EXCLUDE_PATH: Must be relative: %s" % orig_path)
+
+        full_path = os.path.realpath(os.path.join(new_rootfs, path))
+
+        # Disallow climbing outside of parent directory using '..',
+        # because doing so could be quite disastrous (we will delete the
+        # directory).
+        if not full_path.startswith(new_rootfs):
+            bb.fatal("'%s' points to a path outside the rootfs" % orig_path)
+
+        if path.endswith(os.sep):
+            # Delete content only.
+            for entry in os.listdir(full_path):
+                full_entry = os.path.join(full_path, entry)
+                if os.path.isdir(full_entry) and not os.path.islink(full_entry):
+                    shutil.rmtree(full_entry)
+                else:
+                    os.remove(full_entry)
+        else:
+            # Delete whole directory.
+            shutil.rmtree(full_path)
+
+    # Save old value for cleanup later.
+    d.setVar('IMAGE_ROOTFS_ORIG', rootfs_orig)
+    d.setVar('IMAGE_ROOTFS', new_rootfs)
+}
+
+python cleanup_excluded_directories() {
+    exclude_var = d.getVar('IMAGE_ROOTFS_EXCLUDE_PATH')
+    if not exclude_var:
+        return
+
+    taskname = d.getVar("BB_CURRENTTASK")
+
+    if d.getVarFlag('do_%s' % taskname, 'respect_exclude_path') != '1':
+        return
+
+    import shutil
+
+    rootfs_dirs_excluded = d.getVar('IMAGE_ROOTFS')
+    rootfs_orig = d.getVar('IMAGE_ROOTFS_ORIG')
+    # This should never happen, since we should have set it to a different
+    # directory in the prepare function.
+    assert rootfs_dirs_excluded != rootfs_orig
+
+    shutil.rmtree(rootfs_dirs_excluded)
+    d.setVar('IMAGE_ROOTFS', rootfs_orig)
+}
+
 #
 # Compute the rootfs size
 #
diff --git a/meta/classes/image_types.bbclass b/meta/classes/image_types.bbclass
index e0368c7..a063df9 100644
--- a/meta/classes/image_types.bbclass
+++ b/meta/classes/image_types.bbclass
@@ -62,8 +62,10 @@ ZIP_COMPRESSION_LEVEL ?= "-9"
 
 JFFS2_SUM_EXTRA_ARGS ?= ""
 IMAGE_CMD_jffs2 = "mkfs.jffs2 --root=${IMAGE_ROOTFS} --faketime --output=${IMGDEPLOYDIR}/${IMAGE_NAME}${IMAGE_NAME_SUFFIX}.jffs2 ${EXTRA_IMAGECMD}"
+do_image_jffs2[respect_exclude_path] = "1"
 
 IMAGE_CMD_cramfs = "mkfs.cramfs ${IMAGE_ROOTFS} ${IMGDEPLOYDIR}/${IMAGE_NAME}${IMAGE_NAME_SUFFIX}.cramfs ${EXTRA_IMAGECMD}"
+do_image_cramfs[respect_exclude_path] = "1"
 
 oe_mkext234fs () {
 	fstype=$1
@@ -92,6 +94,9 @@ oe_mkext234fs () {
 IMAGE_CMD_ext2 = "oe_mkext234fs ext2 ${EXTRA_IMAGECMD}"
 IMAGE_CMD_ext3 = "oe_mkext234fs ext3 ${EXTRA_IMAGECMD}"
 IMAGE_CMD_ext4 = "oe_mkext234fs ext4 ${EXTRA_IMAGECMD}"
+do_image_ext2[respect_exclude_path] = "1"
+do_image_ext3[respect_exclude_path] = "1"
+do_image_ext4[respect_exclude_path] = "1"
 
 MIN_BTRFS_SIZE ?= "16384"
 IMAGE_CMD_btrfs () {
@@ -103,10 +108,14 @@ IMAGE_CMD_btrfs () {
 	dd if=/dev/zero of=${IMGDEPLOYDIR}/${IMAGE_NAME}${IMAGE_NAME_SUFFIX}.btrfs count=${size} bs=1024
 	mkfs.btrfs ${EXTRA_IMAGECMD} -r ${IMAGE_ROOTFS} ${IMGDEPLOYDIR}/${IMAGE_NAME}${IMAGE_NAME_SUFFIX}.btrfs
 }
+do_image_btrfs[respect_exclude_path] = "1"
 
 IMAGE_CMD_squashfs = "mksquashfs ${IMAGE_ROOTFS} ${IMGDEPLOYDIR}/${IMAGE_NAME}${IMAGE_NAME_SUFFIX}.squashfs ${EXTRA_IMAGECMD} -noappend"
 IMAGE_CMD_squashfs-xz = "mksquashfs ${IMAGE_ROOTFS} ${IMGDEPLOYDIR}/${IMAGE_NAME}${IMAGE_NAME_SUFFIX}.squashfs-xz ${EXTRA_IMAGECMD} -noappend -comp xz"
 IMAGE_CMD_squashfs-lzo = "mksquashfs ${IMAGE_ROOTFS} ${IMGDEPLOYDIR}/${IMAGE_NAME}${IMAGE_NAME_SUFFIX}.squashfs-lzo ${EXTRA_IMAGECMD} -noappend -comp lzo"
+do_image_squashfs[respect_exclude_path] = "1"
+do_image_squashfs-xz[respect_exclude_path] = "1"
+do_image_squashfs-lzo[respect_exclude_path] = "1"
 
 # By default, tar from the host is used, which can be quite old. If
 # you need special parameters (like --xattrs) which are only supported
@@ -121,6 +130,7 @@ IMAGE_CMD_squashfs-lzo = "mksquashfs ${IMAGE_ROOTFS} ${IMGDEPLOYDIR}/${IMAGE_NAM
 IMAGE_CMD_TAR ?= "tar"
 # ignore return code 1 "file changed as we read it" as other tasks(e.g. do_image_wic) may be hardlinking rootfs
 IMAGE_CMD_tar = "${IMAGE_CMD_TAR} -cf ${IMGDEPLOYDIR}/${IMAGE_NAME}${IMAGE_NAME_SUFFIX}.tar -C ${IMAGE_ROOTFS} . || [ $? -eq 1 ]"
+do_image_tar[respect_exclude_path] = "1"
 
 do_image_cpio[cleandirs] += "${WORKDIR}/cpio_append"
 IMAGE_CMD_cpio () {
@@ -141,6 +151,7 @@ IMAGE_CMD_cpio () {
 		fi
 	fi
 }
+do_image_cpio[respect_exclude_path] = "1"
 
 ELF_KERNEL ?= "${DEPLOY_DIR_IMAGE}/${KERNEL_IMAGETYPE}"
 ELF_APPEND ?= "ramdisk_size=32768 root=/dev/ram0 rw console="
@@ -149,6 +160,7 @@ IMAGE_CMD_elf () {
 	test -f ${IMGDEPLOYDIR}/${IMAGE_NAME}${IMAGE_NAME_SUFFIX}.elf && rm -f ${IMGDEPLOYDIR}/${IMAGE_NAME}${IMAGE_NAME_SUFFIX}.elf
 	mkelfImage --kernel=${ELF_KERNEL} --initrd=${IMGDEPLOYDIR}/${IMAGE_LINK_NAME}.cpio.gz --output=${IMGDEPLOYDIR}/${IMAGE_NAME}${IMAGE_NAME_SUFFIX}.elf --append='${ELF_APPEND}' ${EXTRA_IMAGECMD}
 }
+do_image_elf[respect_exclude_path] = "1"
 
 IMAGE_TYPEDEP_elf = "cpio.gz"
 
@@ -212,6 +224,7 @@ IMAGE_CMD_ubi () {
 }
 
 IMAGE_CMD_ubifs = "mkfs.ubifs -r ${IMAGE_ROOTFS} -o ${IMGDEPLOYDIR}/${IMAGE_NAME}${IMAGE_NAME_SUFFIX}.ubifs ${MKUBIFS_ARGS}"
+do_image_ubifs[respect_exclude_path] = "1"
 
 EXTRA_IMAGECMD = ""
 
-- 
2.7.4