mirror_zfs/module/os/freebsd/zfs/vdev_label_os.c

134 lines
3.6 KiB
C
Raw Normal View History

/*
* CDDL HEADER START
*
* The contents of this file are subject to the terms of the
* Common Development and Distribution License (the "License").
* You may not use this file except in compliance with the License.
*
* You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE
* or https://opensource.org/licenses/CDDL-1.0.
* See the License for the specific language governing permissions
* and limitations under the License.
*
* When distributing Covered Code, include this CDDL HEADER in each
* file and include the License file at usr/src/OPENSOLARIS.LICENSE.
* If applicable, add the following below this CDDL HEADER, with the
* fields enclosed by brackets "[]" replaced with your own identifying
* information: Portions Copyright [yyyy] [name of copyright owner]
*
* CDDL HEADER END
*/
#include <sys/zfs_context.h>
#include <sys/spa.h>
#include <sys/spa_impl.h>
#include <sys/dmu.h>
#include <sys/zap.h>
#include <sys/vdev.h>
#include <sys/vdev_os.h>
#include <sys/vdev_impl.h>
#include <sys/uberblock_impl.h>
#include <sys/metaslab.h>
#include <sys/metaslab_impl.h>
#include <sys/zio.h>
#include <sys/dsl_scan.h>
#include <sys/abd.h>
#include <sys/fs/zfs.h>
int
vdev_label_write_pad2(vdev_t *vd, const char *buf, size_t size)
{
spa_t *spa = vd->vdev_spa;
zio_t *zio;
abd_t *pad2;
int flags = ZIO_FLAG_CONFIG_WRITER | ZIO_FLAG_CANFAIL;
int error;
if (size > VDEV_PAD_SIZE)
return (EINVAL);
if (!vd->vdev_ops->vdev_op_leaf)
return (ENODEV);
if (vdev_is_dead(vd))
return (ENXIO);
ASSERT3U(spa_config_held(spa, SCL_ALL, RW_WRITER), ==, SCL_ALL);
pad2 = abd_alloc_for_io(VDEV_PAD_SIZE, B_TRUE);
abd_copy_from_buf(pad2, buf, size);
abd_zero_off(pad2, size, VDEV_PAD_SIZE - size);
retry:
zio = zio_root(spa, NULL, NULL, flags);
vdev_label_write(zio, vd, 0, pad2,
Add support for boot environment data to be stored in the label Modern bootloaders leverage data stored in the root filesystem to enable some of their powerful features. GRUB specifically has a grubenv file which can store large amounts of configuration data that can be read and written at boot time and during normal operation. This allows sysadmins to configure useful features like automated failover after failed boot attempts. Unfortunately, due to the Copy-on-Write nature of ZFS, the standard behavior of these tools cannot handle writing to ZFS files safely at boot time. We need an alternative way to store data that allows the bootloader to make changes to the data. This work is very similar to work that was done on Illumos to enable similar functionality in the FreeBSD bootloader. This patch is different in that the data being stored is a raw grubenv file; this file can store arbitrary variables and values, and the scripting provided by grub is powerful enough that special structures are not required to implement advanced behavior. We repurpose the second padding area in each label to store the grubenv file, protected by an embedded checksum. We add two ioctls to get and set this data, and libzfs_core and libzfs functions to access them more easily. There are no direct command line interfaces to these functions; these will be added directly to the bootloader utilities. Reviewed-by: Pavel Zakharov <pavel.zakharov@delphix.com> Reviewed-by: Matthew Ahrens <mahrens@delphix.com> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Signed-off-by: Paul Dagnelie <pcd@delphix.com> Closes #10009
2020-05-07 19:36:33 +03:00
offsetof(vdev_label_t, vl_be),
VDEV_PAD_SIZE, NULL, NULL, flags);
error = zio_wait(zio);
if (error != 0 && !(flags & ZIO_FLAG_TRYHARD)) {
flags |= ZIO_FLAG_TRYHARD;
goto retry;
}
abd_free(pad2);
return (error);
}
RAID-Z expansion feature This feature allows disks to be added one at a time to a RAID-Z group, expanding its capacity incrementally. This feature is especially useful for small pools (typically with only one RAID-Z group), where there isn't sufficient hardware to add capacity by adding a whole new RAID-Z group (typically doubling the number of disks). == Initiating expansion == A new device (disk) can be attached to an existing RAIDZ vdev, by running `zpool attach POOL raidzP-N NEW_DEVICE`, e.g. `zpool attach tank raidz2-0 sda`. The new device will become part of the RAIDZ group. A "raidz expansion" will be initiated, and the new device will contribute additional space to the RAIDZ group once the expansion completes. The `feature@raidz_expansion` on-disk feature flag must be `enabled` to initiate an expansion, and it remains `active` for the life of the pool. In other words, pools with expanded RAIDZ vdevs can not be imported by older releases of the ZFS software. == During expansion == The expansion entails reading all allocated space from existing disks in the RAIDZ group, and rewriting it to the new disks in the RAIDZ group (including the newly added device). The expansion progress can be monitored with `zpool status`. Data redundancy is maintained during (and after) the expansion. If a disk fails while the expansion is in progress, the expansion pauses until the health of the RAIDZ vdev is restored (e.g. by replacing the failed disk and waiting for reconstruction to complete). The pool remains accessible during expansion. Following a reboot or export/import, the expansion resumes where it left off. == After expansion == When the expansion completes, the additional space is available for use, and is reflected in the `available` zfs property (as seen in `zfs list`, `df`, etc). Expansion does not change the number of failures that can be tolerated without data loss (e.g. a RAIDZ2 is still a RAIDZ2 even after expansion). A RAIDZ vdev can be expanded multiple times. After the expansion completes, old blocks remain with their old data-to-parity ratio (e.g. 5-wide RAIDZ2, has 3 data to 2 parity), but distributed among the larger set of disks. New blocks will be written with the new data-to-parity ratio (e.g. a 5-wide RAIDZ2 which has been expanded once to 6-wide, has 4 data to 2 parity). However, the RAIDZ vdev's "assumed parity ratio" does not change, so slightly less space than is expected may be reported for newly-written blocks, according to `zfs list`, `df`, `ls -s`, and similar tools. Sponsored-by: The FreeBSD Foundation Sponsored-by: iXsystems, Inc. Sponsored-by: vStack Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Reviewed-by: Mark Maybee <mark.maybee@delphix.com> Authored-by: Matthew Ahrens <mahrens@delphix.com> Contributions-by: Fedor Uporov <fuporov.vstack@gmail.com> Contributions-by: Stuart Maybee <stuart.maybee@comcast.net> Contributions-by: Thorsten Behrens <tbehrens@outlook.com> Contributions-by: Fmstrat <nospam@nowsci.com> Contributions-by: Don Brady <dev.fs.zfs@gmail.com> Signed-off-by: Don Brady <dev.fs.zfs@gmail.com> Closes #15022
2023-11-08 21:19:41 +03:00
static void
vdev_child_done(zio_t *zio)
{
zio_t *pio = zio->io_private;
mutex_enter(&pio->io_lock);
pio->io_error = zio_worst_error(pio->io_error, zio->io_error);
mutex_exit(&pio->io_lock);
}
/*
* Check if the reserved boot area is in-use.
*
* When booting FreeBSD with an MBR partition with ZFS, the zfsboot file
* (which understands the ZFS file system) is written to the ZFS BOOT
* reserve area (at offset 512K). We check for that here before attaching
* a disk to raidz which would then corrupt this boot data.
*/
int
vdev_check_boot_reserve(spa_t *spa, vdev_t *childvd)
{
ASSERT(childvd->vdev_ops->vdev_op_leaf);
size_t size = SPA_MINBLOCKSIZE;
abd_t *abd = abd_alloc_linear(size, B_FALSE);
zio_t *pio = zio_root(spa, NULL, NULL, 0);
/*
* Note: zio_vdev_child_io() adds VDEV_LABEL_START_SIZE to the offset
* to calculate the physical offset to write to. Passing in a negative
* offset lets us access the boot area.
*/
zio_nowait(zio_vdev_child_io(pio, NULL, childvd,
VDEV_BOOT_OFFSET - VDEV_LABEL_START_SIZE, abd, size, ZIO_TYPE_READ,
ZIO_PRIORITY_ASYNC_READ, 0, vdev_child_done, pio));
zio_wait(pio);
unsigned char *buf = abd_to_buf(abd);
/*
* The BTX server has a special header at the begining.
*
* btx_hdr: .byte 0xeb # Machine ID
* .byte 0xe # Header size
* .ascii "BTX" # Magic
* .byte 0x1 # Major version
* .byte 0x2 # Minor version
* .byte BTX_FLAGS # Flags
*/
if (buf[0] == 0xeb && buf[1] == 0x0e &&
buf[2] == 'B' && buf[3] == 'T' && buf[4] == 'X') {
abd_free(abd);
return (EBUSY);
}
abd_free(abd);
return (0);
}