Move dracut directory to contrib

The dracut code is analogous to the initramfs code and as such
it should be located in the contrib with initramfs for consistency.

Signed-off-by: Brian Behlendorf <[email protected]>

10 files changed, 522 insertions, 2 deletions

diff --git a/contrib/Makefile.am b/contrib/Makefile.am
index 4a13cfa98..b05e5c45b 100644
--- a/contrib/Makefile.am
+++ b/contrib/Makefile.am
@@ -1,2 +1,2 @@
-SUBDIRS = bash_completion.d initramfs
-DIST_SUBDIRS = bash_completion.d initramfs
+SUBDIRS = bash_completion.d dracut initramfs
+DIST_SUBDIRS = bash_completion.d dracut initramfs
diff --git a/contrib/dracut/90zfs/.gitignore b/contrib/dracut/90zfs/.gitignore
new file mode 100644
index 000000000..9502be985
--- /dev/null
+++ b/contrib/dracut/90zfs/.gitignore
@@ -0,0 +1,5 @@
+export-zfs.sh
+module-setup.sh
+mount-zfs.sh
+parse-zfs.sh
+zfs-lib.sh
diff --git a/contrib/dracut/90zfs/Makefile.am b/contrib/dracut/90zfs/Makefile.am
new file mode 100644
index 000000000..30880bfc5
--- /dev/null
+++ b/contrib/dracut/90zfs/Makefile.am
@@ -0,0 +1,25 @@
+pkgdracutdir = $(dracutdir)/modules.d/90zfs
+pkgdracut_SCRIPTS = \
+	$(top_srcdir)/contrib/dracut/90zfs/export-zfs.sh \
+	$(top_srcdir)/contrib/dracut/90zfs/module-setup.sh \
+	$(top_srcdir)/contrib/dracut/90zfs/mount-zfs.sh \
+	$(top_srcdir)/contrib/dracut/90zfs/parse-zfs.sh \
+	$(top_srcdir)/contrib/dracut/90zfs/zfs-lib.sh
+
+EXTRA_DIST = \
+	$(top_srcdir)/contrib/dracut/90zfs/export-zfs.sh.in \
+	$(top_srcdir)/contrib/dracut/90zfs/module-setup.sh.in \
+	$(top_srcdir)/contrib/dracut/90zfs/mount-zfs.sh.in \
+	$(top_srcdir)/contrib/dracut/90zfs/parse-zfs.sh.in \
+	$(top_srcdir)/contrib/dracut/90zfs/zfs-lib.sh.in
+
+$(pkgdracut_SCRIPTS):
+	-$(SED) -e 's,@bindir\@,$(bindir),g' \
+		-e 's,@sbindir\@,$(sbindir),g' \
+		-e 's,@udevdir\@,$(udevdir),g' \
+		-e 's,@udevruledir\@,$(udevruledir),g' \
+		-e 's,@sysconfdir\@,$(sysconfdir),g' \
+		'[email protected]' >'$@'
+
+distclean-local::
+	-$(RM) $(pkgdracut_SCRIPTS)
diff --git a/contrib/dracut/90zfs/export-zfs.sh.in b/contrib/dracut/90zfs/export-zfs.sh.in
new file mode 100755
index 000000000..393753fbf
--- /dev/null
+++ b/contrib/dracut/90zfs/export-zfs.sh.in
@@ -0,0 +1,29 @@
+#!/bin/sh
+
+. /lib/dracut-zfs-lib.sh
+
+_do_zpool_export() {
+	local ret=0
+	local final="${1}"
+	local opts=""
+
+	if [ "x${final}" != "x" ]; then
+		opts="-f"
+	fi
+
+	info "Exporting ZFS storage pools."
+	export_all ${opts} || ret=$?
+
+	if [ "x${final}" != "x" ]; then
+		info "zpool list"
+		zpool list 2>&1 | vinfo
+	fi
+
+	return ${ret}
+}
+
+if command -v zpool >/dev/null; then
+	_do_zpool_export "${1}"
+else
+	:
+fi
diff --git a/contrib/dracut/90zfs/module-setup.sh.in b/contrib/dracut/90zfs/module-setup.sh.in
new file mode 100755
index 000000000..9eb9f5765
--- /dev/null
+++ b/contrib/dracut/90zfs/module-setup.sh.in
@@ -0,0 +1,61 @@
+#!/bin/sh
+
+check() {
+	# We depend on udev-rules being loaded
+	[ "${1}" = "-d" ] && return 0
+
+	# Verify the zfs tool chain
+	which zpool >/dev/null 2>&1 || return 1
+	which zfs >/dev/null 2>&1 || return 1
+
+	return 0
+}
+
+depends() {
+	echo udev-rules
+	return 0
+}
+
+installkernel() {
+	instmods zfs
+	instmods zcommon
+	instmods znvpair
+	instmods zavl
+	instmods zunicode
+	instmods spl
+	instmods zlib_deflate
+	instmods zlib_inflate
+}
+
+install() {
+	inst_rules @udevruledir@/90-zfs.rules
+	inst_rules @udevruledir@/69-vdev.rules
+	inst_rules @udevruledir@/60-zvol.rules
+	dracut_install @sbindir@/zfs
+	dracut_install @sbindir@/zpool
+	dracut_install @udevdir@/vdev_id
+	dracut_install @udevdir@/zvol_id
+	dracut_install mount.zfs
+	dracut_install hostid
+	dracut_install awk
+	dracut_install head
+	inst_hook cmdline 95 "${moddir}/parse-zfs.sh"
+	inst_hook mount 98 "${moddir}/mount-zfs.sh"
+	inst_hook shutdown 30 "${moddir}/export-zfs.sh"
+
+	inst_simple "${moddir}/zfs-lib.sh" "/lib/dracut-zfs-lib.sh"
+	if [ -e @sysconfdir@/zfs/zpool.cache ]; then
+		inst @sysconfdir@/zfs/zpool.cache
+	fi
+
+	if [ -e @sysconfdir@/zfs/vdev_id.conf ]; then
+		inst @sysconfdir@/zfs/vdev_id.conf
+	fi
+
+	# Synchronize initramfs and system hostid
+	AA=`hostid | cut -b 1,2`
+	BB=`hostid | cut -b 3,4`
+	CC=`hostid | cut -b 5,6`
+	DD=`hostid | cut -b 7,8`
+	printf "\x${DD}\x${CC}\x${BB}\x${AA}" > "${initdir}/etc/hostid"
+}
diff --git a/contrib/dracut/90zfs/mount-zfs.sh.in b/contrib/dracut/90zfs/mount-zfs.sh.in
new file mode 100755
index 000000000..2abc8766b
--- /dev/null
+++ b/contrib/dracut/90zfs/mount-zfs.sh.in
@@ -0,0 +1,44 @@
+#!/bin/sh
+
+. /lib/dracut-zfs-lib.sh
+
+ZFS_DATASET=""
+ZFS_POOL=""
+
+case "${root}" in
+	zfs:*) ;;
+	*) return ;;
+esac
+
+# Delay until all required block devices are present.
+udevadm settle
+
+if [ "${root}" = "zfs:AUTO" ] ; then
+	ZFS_DATASET="$(find_bootfs)"
+	if [ $? -ne 0 ] ; then
+		zpool import -N -a ${ZPOOL_IMPORT_OPTS}
+		ZFS_DATASET="$(find_bootfs)"
+		if [ $? -ne 0 ] ; then
+			warn "ZFS: No bootfs attribute found in importable pools."
+			export_all || export_all "-f"
+
+			rootok=0
+			return 1
+		fi
+	fi
+	info "ZFS: Using ${ZFS_DATASET} as root."
+fi
+
+ZFS_DATASET="${ZFS_DATASET:-${root#zfs:}}"
+ZFS_POOL="${ZFS_DATASET%%/*}"
+
+if import_pool "${ZFS_POOL}" ; then
+	info "ZFS: Mounting dataset ${ZFS_DATASET}..."
+	if mount_dataset "${ZFS_DATASET}" ; then
+		ROOTFS_MOUNTED=yes
+		return 0
+	fi
+fi
+
+rootok=0
+need_shutdown
diff --git a/contrib/dracut/90zfs/parse-zfs.sh.in b/contrib/dracut/90zfs/parse-zfs.sh.in
new file mode 100755
index 000000000..c305c7821
--- /dev/null
+++ b/contrib/dracut/90zfs/parse-zfs.sh.in
@@ -0,0 +1,59 @@
+#!/bin/sh
+
+. /lib/dracut-lib.sh
+
+# Let the command line override our host id.
+spl_hostid=`getarg spl_hostid=`
+if [ -n "${spl_hostid}" ] ; then
+	info "ZFS: Using hostid from command line: ${spl_hostid}"
+	AA=`echo ${spl_hostid} | cut -b 1,2`
+	BB=`echo ${spl_hostid} | cut -b 3,4`
+	CC=`echo ${spl_hostid} | cut -b 5,6`
+	DD=`echo ${spl_hostid} | cut -b 7,8`
+	printf "\x${DD}\x${CC}\x${BB}\x${AA}" >/etc/hostid
+elif [ -f "/etc/hostid" ] ; then
+	info "ZFS: Using hostid from /etc/hostid: `hostid`"
+else
+	warn "ZFS: No hostid found on kernel command line or /etc/hostid."
+	warn "ZFS: Pools may not import correctly."
+fi
+
+wait_for_zfs=0
+case "${root}" in
+	""|zfs|zfs:)
+		# We'll take root unset, root=zfs, or root=zfs:
+		# No root set, so we want to read the bootfs attribute.  We
+		# can't do that until udev settles so we'll set dummy values
+		# and hope for the best later on.
+		root="zfs:AUTO"
+		rootok=1
+		wait_for_zfs=1
+
+		info "ZFS: Enabling autodetection of bootfs after udev settles."
+		;;
+
+	ZFS\=*|zfs:*|zfs:FILESYSTEM\=*|FILESYSTEM\=*)
+		# root is explicit ZFS root.  Parse it now.  We can handle
+		# a root=... param in any of the following formats:
+		# root=ZFS=rpool/ROOT
+		# root=zfs:rpool/ROOT
+		# root=zfs:FILESYSTEM=rpool/ROOT
+		# root=FILESYSTEM=rpool/ROOT
+
+		# Strip down to just the pool/fs
+		root="${root#zfs:}"
+		root="${root#FILESYSTEM=}"
+		root="zfs:${root#ZFS=}"
+		rootok=1
+		wait_for_zfs=1
+
+		info "ZFS: Set ${root} as bootfs."
+		;;
+esac
+
+# Make sure Dracut is happy that we have a root and will wait for ZFS
+# modules to settle before mounting.
+if [ ${wait_for_zfs} -eq 1 ]; then
+	ln -s /dev/null /dev/root 2>/dev/null
+	echo '[ -e /dev/zfs ]' > "${hookdir}/initqueue/finished/zfs.sh"
+fi
diff --git a/contrib/dracut/90zfs/zfs-lib.sh.in b/contrib/dracut/90zfs/zfs-lib.sh.in
new file mode 100755
index 000000000..1c223befd
--- /dev/null
+++ b/contrib/dracut/90zfs/zfs-lib.sh.in
@@ -0,0 +1,87 @@
+#!/bin/sh
+
+command -v getarg >/dev/null || . /lib/dracut-lib.sh
+
+OLDIFS="${IFS}"
+NEWLINE="
+"
+
+ZPOOL_IMPORT_OPTS=""
+if getargbool 0 zfs_force -y zfs.force -y zfsforce ; then
+	warn "ZFS: Will force-import pools if necessary."
+	ZPOOL_IMPORT_OPTS="${ZPOOL_IMPORT_OPTS} -f"
+fi
+
+# find_bootfs
+#   returns the first dataset with the bootfs attribute.
+find_bootfs() {
+	IFS="${NEWLINE}"
+	for dataset in $(zpool list -H -o bootfs); do
+		case "${dataset}" in
+			"" | "-")
+				continue
+				;;
+			"no pools available")
+				IFS="${OLDIFS}"
+				return 1
+				;;
+			*)
+				IFS="${OLDIFS}"
+				echo "${dataset}"
+				return 0
+				;;
+		esac
+	done
+
+	IFS="${OLDIFS}"
+	return 1
+}
+
+# import_pool POOL
+#   imports the given zfs pool if it isn't imported already.
+import_pool() {
+	local pool="${1}"
+
+	if ! zpool list -H "${pool}" 2>&1 > /dev/null ; then
+		info "ZFS: Importing pool ${pool}..."
+		if ! zpool import -N ${ZPOOL_IMPORT_OPTS} "${pool}" ; then
+			warn "ZFS: Unable to import pool ${pool}"
+			return 1
+		fi
+	fi
+
+	return 0
+}
+
+# mount_dataset DATASET
+#   mounts the given zfs dataset.
+mount_dataset() {
+	local dataset="${1}"
+	local mountpoint="$(zfs get -H -o value mountpoint "${dataset}")"
+
+	# We need zfsutil for non-legacy mounts and not for legacy mounts.
+	if [ "${mountpoint}" = "legacy" ] ; then
+		mount -t zfs "${dataset}" "${NEWROOT}"
+	else
+		mount -o zfsutil -t zfs "${dataset}" "${NEWROOT}"
+	fi
+
+	return $?
+}
+
+# export_all OPTS
+#   exports all imported zfs pools.
+export_all() {
+	local opts="${1}"
+	local ret=0
+
+	IFS="${NEWLINE}"
+	for pool in `zpool list -H -o name` ; do
+		if zpool list -H "${pool}" 2>&1 > /dev/null ; then
+			zpool export "${pool}" ${opts} || ret=$?
+		fi
+	done
+	IFS="${OLDIFS}"
+
+	return ${ret}
+}
diff --git a/contrib/dracut/Makefile.am b/contrib/dracut/Makefile.am
new file mode 100644
index 000000000..35b88c36f
--- /dev/null
+++ b/contrib/dracut/Makefile.am
@@ -0,0 +1,3 @@
+SUBDIRS = 90zfs
+
+EXTRA_DIST = README.dracut.markdown
diff --git a/contrib/dracut/README.dracut.markdown b/contrib/dracut/README.dracut.markdown
new file mode 100644
index 000000000..46d032f70
--- /dev/null
+++ b/contrib/dracut/README.dracut.markdown
@@ -0,0 +1,207 @@
+How to setup a zfs root filesystem using dracut
+-----------------------------------------------
+
+1) Install the zfs-dracut package.  This package adds a zfs dracut module
+to the /usr/share/dracut/modules.d/ directory which allows dracut to
+create an initramfs which is zfs aware.
+
+2) Set the bootfs property for the bootable dataset in the pool.  Then set
+the dataset mountpoint property to '/'.
+
+    $ zpool set bootfs=pool/dataset pool
+    $ zfs set mountpoint=/ pool/dataset
+
+It is also possible to set the bootfs property for an entire pool, just in
+case you are not using a dedicated dataset for '/'.
+
+    $ zpool set bootfs=pool pool
+    $ zfs set mountpoint=/ pool
+
+Alternately, legacy mountpoints can be used by setting the 'root=' option
+on the kernel line of your grub.conf/menu.lst configuration file.  Then
+set the dataset mountpoint property to 'legacy'.
+
+    $ grub.conf/menu.lst: kernel ... root=ZFS=pool/dataset
+    $ zfs set mountpoint=legacy pool/dataset
+
+3) To set zfs module options put them in /etc/modprobe.d/zfs.conf file.
+The complete list of zfs module options is available by running the
+_modinfo zfs_ command.  Commonly set options include: zfs_arc_min,
+zfs_arc_max, zfs_prefetch_disable, and zfs_vdev_max_pending.
+
+4) Finally, create your new initramfs by running dracut.
+
+    $ dracut --force /path/to/initramfs kernel_version
+
+Kernel Command Line
+-------------------
+
+The initramfs' behavior is influenced by the following kernel command line
+parameters passed in from the boot loader:
+
+* `root=...`: If not set, importable pools are searched for a bootfs
+attribute.  If an explicitly set root is desired, you may use
+`root=ZFS:pool/dataset`
+
+* `zfs_force=0`: If set to 1, the initramfs will run `zpool import -f` when
+attempting to import pools if the required pool isn't automatically imported
+by the zfs module.  This can save you a trip to a bootcd if hostid has
+changed, but is dangerous and can lead to zpool corruption, particularly in
+cases where storage is on a shared fabric such as iSCSI where multiple hosts
+can access storage devices concurrently.  _Please understand the implications
+of force-importing a pool before enabling this option!_
+
+* `spl_hostid`: By default, the hostid used by the SPL module is read from
+/etc/hostid inside the initramfs.  This file is placed there from the host
+system when the initramfs is built which effectively ties the ramdisk to the
+host which builds it.  If a different hostid is desired, one may be set in
+this attribute and will override any file present in the ramdisk.  The
+format should be hex exactly as found in the `/etc/hostid` file, IE
+`spl_hostid=0x00bab10c`.
+
+Note that changing the hostid between boots will most likely lead to an
+un-importable pool since the last importing hostid won't match.  In order
+to recover from this, you may use the `zfs_force` option or boot from a
+different filesystem and `zpool import -f` then `zpool export` the pool
+before rebooting with the new hostid.
+
+How it Works
+============
+
+The Dracut module consists of the following files (less Makefile's):
+
+* `module-setup.sh`: Script run by the initramfs builder to create the
+ramdisk.  Contains instructions on which files are required by the modules
+and z* programs.  Also triggers inclusion of `/etc/hostid` and the zpool
+cache.  This file is not included in the initramfs.
+
+* `90-zfs.rules`: udev rules which trigger loading of the ZFS modules at boot.
+
+* `zfs-lib.sh`: Utility functions used by the other files.
+
+* `parse-zfs.sh`: Run early in the initramfs boot process to parse kernel
+command line and determine if ZFS is the active root filesystem.
+
+* `mount-zfs.sh`: Run later in initramfs boot process after udev has settled
+to mount the root dataset.
+
+* `export-zfs.sh`: Run on shutdown after dracut has restored the initramfs
+and pivoted to it, allowing for a clean unmount and export of the ZFS root.
+
+`zfs-lib.sh`
+------------
+
+This file provides a few handy functions for working with ZFS. Those
+functions are used by the `mount-zfs.sh` and `export-zfs.sh` files.
+However, they could be used by any other file as well, as long as the file
+sources `/lib/dracut-zfs-lib.sh`.
+
+`module-setup.sh`
+-----------------
+
+This file is run by the Dracut script within the live system, not at boot
+time.  It's not included in the final initramfs.  Functions in this script
+describe which files are needed by ZFS at boot time.
+
+Currently all the various z* and spl modules are included, a dependency is
+asserted on udev-rules, and the various zfs, zpool, etc. helpers are included.
+Dracut provides library functions which automatically gather the shared libs
+necessary to run each of these binaries, so statically built binaries are
+not required.
+
+The zpool and zvol udev rules files are copied from where they are
+installed by the ZFS build.  __PACKAGERS TAKE NOTE__: If you move
+`/etc/udev/rules/60-z*.rules`, you'll need to update this file to match.
+
+Currently this file also includes `/etc/hostid` and `/etc/zfs/zpool.cache`
+which means the generated ramdisk is specific to the host system which built
+it.  If a generic initramfs is required, it may be preferable to omit these
+files and specify the `spl_hostid` from the boot loader instead.
+
+`parse-zfs.sh`
+--------------
+
+Run during the cmdline phase of the initramfs boot process, this script
+performs some basic sanity checks on kernel command line parameters to
+determine if booting from ZFS is likely to be what is desired.  Dracut
+requires this script to adjust the `root` variable if required and to set
+`rootok=1` if a mountable root filesystem is available.  Unfortunately this
+script must run before udev is settled and kernel modules are known to be
+loaded, so accessing the zpool and zfs commands is unsafe.
+
+If the root=ZFS... parameter is set on the command line, then it's at least
+certain that ZFS is what is desired, though this script is unable to
+determine if ZFS is in fact available.  This script will alter the `root`
+parameter to replace several historical forms of specifying the pool and
+dataset name with the canonical form of `zfs:pool/dataset`.
+
+If no root= parameter is set, the best this script can do is guess that
+ZFS is desired.  At present, no other known filesystems will work with no
+root= parameter, though this might possibly interfere with using the
+compiled-in default root in the kernel image.  It's considered unlikely
+that would ever be the case when an initramfs is in use, so this script
+sets `root=zfs:AUTO` and hopes for the best.
+
+Once the root=... (or lack thereof) parameter is parsed, a dummy symlink
+is created from `/dev/root` -> `/dev/null` to satisfy parts of the Dracut
+process which check for presence of a single root device node.
+
+Finally, an initqueue/finished hook is registered which causes the initqueue
+phase of Dracut to wait for `/dev/zfs` to become available before attempting
+to mount anything.
+
+`mount-zfs.sh`
+--------------
+
+This script is run after udev has settled and all tasks in the initqueue
+have succeeded.  This ensures that `/dev/zfs` is available and that the
+various ZFS modules are successfully loaded.  As it is now safe to call
+zpool and friends, we can proceed to find the bootfs attribute if necessary.
+
+If the root parameter was explicitly set on the command line, no parsing is
+necessary.  The list of imported pools is checked to see if the desired pool
+is already imported.  If it's not, and attempt is made to import the pool
+explicitly, though no force is attempted.  Finally the specified dataset
+is mounted on `$NEWROOT`, first using the `-o zfsutil` option to handle
+non-legacy mounts, then if that fails, without zfsutil to handle legacy
+mount points.
+
+If no root parameter was specified, this script attempts to find a pool with
+its bootfs attribute set.  First, already-imported pools are scanned and if
+an appropriate pool is found, no additional pools are imported.  If no pool
+with bootfs is found, any additional pools in the system are imported with
+`zpool import -N -a`, and the scan for bootfs is tried again.  If no bootfs
+is found with all pools imported, all pools are re-exported, and boot fails.
+Assuming a bootfs is found, an attempt is made to mount it to `$NEWROOT`,
+first with, then without the zfsutil option as above.
+
+Ordinarily pools are imported _without_ the force option which may cause
+boot to fail if the hostid has changed or a pool has been physically moved
+between servers.  The `zfs_force` kernel parameter is provided which when
+set to `1` causes `zpool import` to be run with the `-f` flag.  Forcing pool
+import can lead to serious data corruption and loss of pools, so this option
+should be used with extreme caution.  Note that even with this flag set, if
+the required zpool was auto-imported by the kernel module, no additional
+`zpool import` commands are run, so nothing is forced.
+
+`export-zfs.sh`
+---------------
+
+Normally the zpool containing the root dataset cannot be exported on
+shutdown as it is still in use by the init process. To work around this,
+Dracut is able to restore the initramfs on shutdown and pivot to it.
+All remaining process are then running from a ramdisk, allowing for a
+clean unmount and export of the ZFS root. The theory of operation is
+described in detail in the [Dracut manual](https://www.kernel.org/pub/linux/utils/boot/dracut/dracut.html#_dracut_on_shutdown).
+
+This script will try to export all remaining zpools after Dracut has
+pivoted to the initramfs. If an initial regular export is not successful,
+Dracut will call this script once more with the `final` option,
+in which case a forceful export is attempted.
+
+Other Dracut modules include similar shutdown scripts and Dracut
+invokes these scripts round-robin until they succeed. In particular,
+the `90dm` module installs a script which tries to close and remove
+all device mapper targets. Thus, if there are ZVOLs containing
+dm-crypt volumes or if the zpool itself is backed by a dm-crypt
+volume, the shutdown scripts will try to untangle this.