// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2010-2011 Neil Brown * Copyright (C) 2010-2018 Red Hat, Inc. All rights reserved. * * This file is released under the GPL.
*/
/* * Minimum sectors of free reshape space per raid device
*/ #define MIN_FREE_RESHAPE_SPACE to_sector(4*4096)
/* * Minimum journal space 4 MiB in sectors.
*/ #define MIN_RAID456_JOURNAL_SPACE (4*2048)
staticbool devices_handle_discard_safely;
/* * The following flags are used by dm-raid to set up the array state. * They must be cleared before md_run is called.
*/ #define FirstUse 10 /* rdev flag */
struct raid_dev { /* * Two DM devices, one to hold metadata and one to hold the * actual data/parity. The reason for this is to not confuse * ti->len and give more flexibility in altering size and * characteristics. * * While it is possible for this device to be associated * with a different physical device than the data_dev, it * is intended for it to be the same. * |--------- Physical Device ---------| * |- meta_dev -|------ data_dev ------|
*/ struct dm_dev *meta_dev; struct dm_dev *data_dev; struct md_rdev rdev;
};
/* * Bits for establishing rs->ctr_flags * * 1 = no flag value * 2 = flag with value
*/ #define __CTR_FLAG_SYNC 0 /* 1 */ /* Not with raid0! */ #define __CTR_FLAG_NOSYNC 1 /* 1 */ /* Not with raid0! */ #define __CTR_FLAG_REBUILD 2 /* 2 */ /* Not with raid0! */ #define __CTR_FLAG_DAEMON_SLEEP 3 /* 2 */ /* Not with raid0! */ #define __CTR_FLAG_MIN_RECOVERY_RATE 4 /* 2 */ /* Not with raid0! */ #define __CTR_FLAG_MAX_RECOVERY_RATE 5 /* 2 */ /* Not with raid0! */ #define __CTR_FLAG_MAX_WRITE_BEHIND 6 /* 2 */ /* Only with raid1! */ #define __CTR_FLAG_WRITE_MOSTLY 7 /* 2 */ /* Only with raid1! */ #define __CTR_FLAG_STRIPE_CACHE 8 /* 2 */ /* Only with raid4/5/6! */ #define __CTR_FLAG_REGION_SIZE 9 /* 2 */ /* Not with raid0! */ #define __CTR_FLAG_RAID10_COPIES 10 /* 2 */ /* Only with raid10 */ #define __CTR_FLAG_RAID10_FORMAT 11 /* 2 */ /* Only with raid10 */ /* New for v1.9.0 */ #define __CTR_FLAG_DELTA_DISKS 12 /* 2 */ /* Only with reshapable raid1/4/5/6/10! */ #define __CTR_FLAG_DATA_OFFSET 13 /* 2 */ /* Only with reshapable raid4/5/6/10! */ #define __CTR_FLAG_RAID10_USE_NEAR_SETS 14 /* 2 */ /* Only with raid10! */
/* New for v1.10.0 */ #define __CTR_FLAG_JOURNAL_DEV 15 /* 2 */ /* Only with raid4/5/6 (journal device)! */
/* New for v1.11.1 */ #define __CTR_FLAG_JOURNAL_MODE 16 /* 2 */ /* Only with raid4/5/6 (journal mode)! */
/* * Definitions of various constructor flags to * be used in checks of valid / invalid flags * per raid level.
*/ /* Define all any sync flags */ #define CTR_FLAGS_ANY_SYNC (CTR_FLAG_SYNC | CTR_FLAG_NOSYNC)
/* Define flags for options without argument (e.g. 'nosync') */ #define CTR_FLAG_OPTIONS_NO_ARGS (CTR_FLAGS_ANY_SYNC | \
CTR_FLAG_RAID10_USE_NEAR_SETS)
/* * "raid4/5/6" do not accept any raid1 or raid10 specific options * * "raid6" does not accept "nosync", because it is not guaranteed * that both parity and q-syndrome are being written properly with * any writes
*/ #define RAID45_VALID_FLAGS (CTR_FLAGS_ANY_SYNC | \
CTR_FLAG_REBUILD | \
CTR_FLAG_DAEMON_SLEEP | \
CTR_FLAG_MIN_RECOVERY_RATE | \
CTR_FLAG_MAX_RECOVERY_RATE | \
CTR_FLAG_STRIPE_CACHE | \
CTR_FLAG_REGION_SIZE | \
CTR_FLAG_DELTA_DISKS | \
CTR_FLAG_DATA_OFFSET | \
CTR_FLAG_JOURNAL_DEV | \
CTR_FLAG_JOURNAL_MODE)
/* * Flags for rs->runtime_flags field * (RT_FLAG prefix meaning "runtime flag") * * These are all internal and used to define runtime state, * e.g. to prevent another resume from preresume processing * the raid set all over again.
*/ #define RT_FLAG_RS_PRERESUMED 0 #define RT_FLAG_RS_RESUMED 1 #define RT_FLAG_RS_BITMAP_LOADED 2 #define RT_FLAG_UPDATE_SBS 3 #define RT_FLAG_RESHAPE_RS 4 #define RT_FLAG_RS_SUSPENDED 5 #define RT_FLAG_RS_IN_SYNC 6 #define RT_FLAG_RS_RESYNCING 7 #define RT_FLAG_RS_GROW 8 #define RT_FLAG_RS_FROZEN 9
/* Array elements of 64 bit needed for rebuild/failed disk bits */ #define DISKS_ARRAY_ELEMS ((MAX_RAID_DEVICES + (sizeof(uint64_t) * 8 - 1)) / sizeof(uint64_t) / 8)
/* * raid set level, layout and chunk sectors backup/restore
*/ struct rs_layout { int new_level; int new_layout; int new_chunk_sectors;
};
/* Return MD raid4/5/6 journal mode for dm @journal_mode one */ staticint dm_raid_journal_mode_to_md(constchar *mode)
{ int m = ARRAY_SIZE(_raid456_journal_mode);
while (m--) if (!strcasecmp(mode, _raid456_journal_mode[m].param)) return _raid456_journal_mode[m].mode;
return -EINVAL;
}
/* Return dm-raid raid4/5/6 journal mode string for @mode */ staticconstchar *md_journal_mode_to_dm_raid(constint mode)
{ int m = ARRAY_SIZE(_raid456_journal_mode);
while (m--) if (mode == _raid456_journal_mode[m].mode) return _raid456_journal_mode[m].param;
return"unknown";
}
/* * Bool helpers to test for various raid levels of a raid set. * It's level as reported by the superblock rather than * the requested raid_type passed to the constructor.
*/ /* Return true, if raid set in @rs is raid0 */ staticbool rs_is_raid0(struct raid_set *rs)
{ return !rs->md.level;
}
/* Return true, if raid set in @rs is raid1 */ staticbool rs_is_raid1(struct raid_set *rs)
{ return rs->md.level == 1;
}
/* Return true, if raid set in @rs is raid10 */ staticbool rs_is_raid10(struct raid_set *rs)
{ return rs->md.level == 10;
}
/* Return true, if raid set in @rs is level 6 */ staticbool rs_is_raid6(struct raid_set *rs)
{ return rs->md.level == 6;
}
/* Return true, if raid set in @rs is level 4, 5 or 6 */ staticbool rs_is_raid456(struct raid_set *rs)
{ return __within_range(rs->md.level, 4, 6);
}
/* Return true, if raid set in @rs is reshapable */ staticbool __is_raid10_far(int layout); staticbool rs_is_reshapable(struct raid_set *rs)
{ return rs_is_raid456(rs) ||
(rs_is_raid10(rs) && !__is_raid10_far(rs->md.new_layout));
}
/* Return true, if raid set in @rs is recovering */ staticbool rs_is_recovering(struct raid_set *rs)
{ return rs->md.resync_offset < rs->md.dev_sectors;
}
/* Return true, if raid set in @rs is reshaping */ staticbool rs_is_reshaping(struct raid_set *rs)
{ return rs->md.reshape_position != MaxSector;
}
/* * bool helpers to test for various raid levels of a raid type @rt
*/
/* Return true, if raid type in @rt is raid0 */ staticbool rt_is_raid0(struct raid_type *rt)
{ return !rt->level;
}
/* Return true, if raid type in @rt is raid1 */ staticbool rt_is_raid1(struct raid_type *rt)
{ return rt->level == 1;
}
/* Return true, if raid type in @rt is raid10 */ staticbool rt_is_raid10(struct raid_type *rt)
{ return rt->level == 10;
}
/* Return true, if raid type in @rt is raid4/5 */ staticbool rt_is_raid45(struct raid_type *rt)
{ return __within_range(rt->level, 4, 5);
}
/* Return true, if raid type in @rt is raid6 */ staticbool rt_is_raid6(struct raid_type *rt)
{ return rt->level == 6;
}
/* Return true, if raid type in @rt is raid4/5/6 */ staticbool rt_is_raid456(struct raid_type *rt)
{ return __within_range(rt->level, 4, 6);
} /* END: raid level bools */
/* Return valid ctr flags for the raid level of @rs */ staticunsignedlong __valid_flags(struct raid_set *rs)
{ if (rt_is_raid0(rs->raid_type)) return RAID0_VALID_FLAGS; elseif (rt_is_raid1(rs->raid_type)) return RAID1_VALID_FLAGS; elseif (rt_is_raid10(rs->raid_type)) return RAID10_VALID_FLAGS; elseif (rt_is_raid45(rs->raid_type)) return RAID45_VALID_FLAGS; elseif (rt_is_raid6(rs->raid_type)) return RAID6_VALID_FLAGS;
return 0;
}
/* * Check for valid flags set on @rs * * Has to be called after parsing of the ctr flags!
*/ staticint rs_check_for_valid_flags(struct raid_set *rs)
{ if (rs->ctr_flags & ~__valid_flags(rs)) {
rs->ti->error = "Invalid flags combination"; return -EINVAL;
}
return 0;
}
/* MD raid10 bit definitions and helpers */ #define RAID10_OFFSET (1 << 16) /* stripes with data copies area adjacent on devices */ #define RAID10_BROCKEN_USE_FAR_SETS (1 << 17) /* Broken in raid10.c: use sets instead of whole stripe rotation */ #define RAID10_USE_FAR_SETS (1 << 18) /* Use sets instead of whole stripe rotation */ #define RAID10_FAR_COPIES_SHIFT 8 /* raid10 # far copies shift (2nd byte of layout) */
/* Return md raid10 near copies for @layout */ staticunsignedint __raid10_near_copies(int layout)
{ return layout & 0xFF;
}
/* Return md raid10 far copies for @layout */ staticunsignedint __raid10_far_copies(int layout)
{ return __raid10_near_copies(layout >> RAID10_FAR_COPIES_SHIFT);
}
/* Return true if md raid10 offset for @layout */ staticbool __is_raid10_offset(int layout)
{ return !!(layout & RAID10_OFFSET);
}
/* Return true if md raid10 near for @layout */ staticbool __is_raid10_near(int layout)
{ return !__is_raid10_offset(layout) && __raid10_near_copies(layout) > 1;
}
/* Return true if md raid10 far for @layout */ staticbool __is_raid10_far(int layout)
{ return !__is_raid10_offset(layout) && __raid10_far_copies(layout) > 1;
}
/* Return md raid10 layout string for @layout */ staticconstchar *raid10_md_layout_to_format(int layout)
{ /* * Bit 16 stands for "offset" * (i.e. adjacent stripes hold copies) * * Refer to MD's raid10.c for details
*/ if (__is_raid10_offset(layout)) return"offset";
if (__raid10_near_copies(layout) > 1) return"near";
/* Return md raid10 format id for @format string */ staticint raid10_format_to_md_layout(struct raid_set *rs, unsignedint algorithm, unsignedint copies)
{ unsignedint n = 1, f = 1, r = 0;
/* * MD resilienece flaw: * * enabling use_far_sets for far/offset formats causes copies * to be colocated on the same devs together with their origins! * * -> disable it for now in the definition above
*/ if (algorithm == ALGORITHM_RAID10_DEFAULT ||
algorithm == ALGORITHM_RAID10_NEAR)
n = copies;
elseif (algorithm == ALGORITHM_RAID10_OFFSET) {
f = copies;
r = RAID10_OFFSET; if (!test_bit(__CTR_FLAG_RAID10_USE_NEAR_SETS, &rs->ctr_flags))
r |= RAID10_USE_FAR_SETS;
} elseif (algorithm == ALGORITHM_RAID10_FAR) {
f = copies; if (!test_bit(__CTR_FLAG_RAID10_USE_NEAR_SETS, &rs->ctr_flags))
r |= RAID10_USE_FAR_SETS;
} else return -EINVAL;
return r | (f << RAID10_FAR_COPIES_SHIFT) | n;
} /* END: MD raid10 bit definitions and helpers */
/* Check for any of the raid10 algorithms */ staticbool __got_raid10(struct raid_type *rtp, constint layout)
{ if (rtp->level == 10) { switch (rtp->algorithm) { case ALGORITHM_RAID10_DEFAULT: case ALGORITHM_RAID10_NEAR: return __is_raid10_near(layout); case ALGORITHM_RAID10_OFFSET: return __is_raid10_offset(layout); case ALGORITHM_RAID10_FAR: return __is_raid10_far(layout); default: break;
}
}
/* * raid10 sets rdev->sector to the device size, which * is unintended in case of out-of-place reshaping
*/
rdev_for_each(rdev, mddev) if (!test_bit(Journal, &rdev->flags))
rdev->sectors = mddev->dev_sectors;
}
/* * Change bdev capacity of @rs in case of a disk add/remove reshape
*/ staticvoid rs_set_capacity(struct raid_set *rs)
{ struct gendisk *gendisk = dm_disk(dm_table_get_md(rs->ti->table));
/* * Set the mddev properties in @rs to the current * ones retrieved from the freshest superblock
*/ staticvoid rs_set_cur(struct raid_set *rs)
{ struct mddev *mddev = &rs->md;
/* * Set the mddev properties in @rs to the new * ones requested by the ctr
*/ staticvoid rs_set_new(struct raid_set *rs)
{ struct mddev *mddev = &rs->md;
for (i = 0; i < raid_devs; i++)
md_rdev_init(&rs->dev[i].rdev);
/* * Remaining items to be initialized by further RAID params: * rs->md.persistent * rs->md.external * rs->md.chunk_sectors * rs->md.new_chunk_sectors * rs->md.dev_sectors
*/
return rs;
}
/* Free all @rs allocations */ staticvoid raid_set_free(struct raid_set *rs)
{ int i;
if (rs->journal_dev.dev) {
md_rdev_clear(&rs->journal_dev.rdev);
dm_put_device(rs->ti, rs->journal_dev.dev);
}
for (i = 0; i < rs->raid_disks; i++) { if (rs->dev[i].meta_dev)
dm_put_device(rs->ti, rs->dev[i].meta_dev);
md_rdev_clear(&rs->dev[i].rdev); if (rs->dev[i].data_dev)
dm_put_device(rs->ti, rs->dev[i].data_dev);
}
mddev_destroy(&rs->md);
kfree(rs);
}
/* * For every device we have two words * <meta_dev>: meta device name or '-' if missing * <data_dev>: data device name or '-' if missing * * The following are permitted: * - - * - <data_dev> * <meta_dev> <data_dev> * * The following is not allowed: * <meta_dev> - * * This code parses those words. If there is a failure, * the caller must use raid_set_free() to unwind the operations.
*/ staticint parse_dev_params(struct raid_set *rs, struct dm_arg_set *as)
{ int i; int rebuild = 0; int metadata_available = 0; int r = 0; constchar *arg;
/* Put off the number of raid devices argument to get to dev pairs */
arg = dm_shift_arg(as); if (!arg) return -EINVAL;
for (i = 0; i < rs->raid_disks; i++) {
rs->dev[i].rdev.raid_disk = i;
/* * There are no offsets initially. * Out of place reshape will set them accordingly.
*/
rs->dev[i].rdev.data_offset = 0;
rs->dev[i].rdev.new_data_offset = 0;
rs->dev[i].rdev.mddev = &rs->md;
arg = dm_shift_arg(as); if (!arg) return -EINVAL;
if (strcmp(arg, "-")) {
r = dm_get_device(rs->ti, arg, dm_table_get_mode(rs->ti->table),
&rs->dev[i].meta_dev); if (r) {
rs->ti->error = "RAID metadata device lookup failure"; return r;
}
rs->dev[i].rdev.sb_page = alloc_page(GFP_KERNEL); if (!rs->dev[i].rdev.sb_page) {
rs->ti->error = "Failed to allocate superblock page"; return -ENOMEM;
}
}
arg = dm_shift_arg(as); if (!arg) return -EINVAL;
if (!strcmp(arg, "-")) { if (!test_bit(In_sync, &rs->dev[i].rdev.flags) &&
(!rs->dev[i].rdev.recovery_offset)) {
rs->ti->error = "Drive designated for rebuild not specified"; return -EINVAL;
}
if (rs->dev[i].meta_dev) {
rs->ti->error = "No data device supplied with metadata device"; return -EINVAL;
}
continue;
}
r = dm_get_device(rs->ti, arg, dm_table_get_mode(rs->ti->table),
&rs->dev[i].data_dev); if (r) {
rs->ti->error = "RAID device lookup failure"; return r;
}
if (rs->dev[i].meta_dev) {
metadata_available = 1;
rs->dev[i].rdev.meta_bdev = rs->dev[i].meta_dev->bdev;
}
rs->dev[i].rdev.bdev = rs->dev[i].data_dev->bdev;
list_add_tail(&rs->dev[i].rdev.same_set, &rs->md.disks); if (!test_bit(In_sync, &rs->dev[i].rdev.flags))
rebuild++;
}
if (rs->journal_dev.dev)
list_add_tail(&rs->journal_dev.rdev.same_set, &rs->md.disks);
if (metadata_available) {
rs->md.external = 0;
rs->md.persistent = 1;
rs->md.major_version = 2;
} elseif (rebuild && !rs->md.resync_offset) { /* * Without metadata, we will not be able to tell if the array * is in-sync or not - we must assume it is not. Therefore, * it is impossible to rebuild a drive. * * Even if there is metadata, the on-disk information may * indicate that the array is not in-sync and it will then * fail at that time. * * User could specify 'nosync' option if desperate.
*/
rs->ti->error = "Unable to rebuild drive while array is not in-sync"; return -EINVAL;
}
return 0;
}
/* * validate_region_size * @rs * @region_size: region size in sectors. If 0, pick a size (4MiB default). * * Set rs->md.bitmap_info.chunksize (which really refers to 'region size'). * Ensure that (ti->len/region_size < 2^21) - required by MD bitmap. * * Returns: 0 on success, -EINVAL on failure.
*/ staticint validate_region_size(struct raid_set *rs, unsignedlong region_size)
{ unsignedlong min_region_size = rs->ti->len / (1 << 21);
if (rs_is_raid0(rs)) return 0;
if (!region_size) { /* * Choose a reasonable default. All figures in sectors.
*/ if (min_region_size > (1 << 13)) { /* If not a power of 2, make it the next power of 2 */
region_size = roundup_pow_of_two(min_region_size);
DMINFO("Choosing default region size of %lu sectors",
region_size);
} else {
DMINFO("Choosing default region size of 4MiB");
region_size = 1 << 13; /* sectors */
}
} else { /* * Validate user-supplied value.
*/ if (region_size > rs->ti->len) {
rs->ti->error = "Supplied region size is too large"; return -EINVAL;
}
if (region_size < min_region_size) {
DMERR("Supplied region_size (%lu sectors) below minimum (%lu)",
region_size, min_region_size);
rs->ti->error = "Supplied region size is too small"; return -EINVAL;
}
if (!is_power_of_2(region_size)) {
rs->ti->error = "Region size is not a power of 2"; return -EINVAL;
}
if (region_size < rs->md.chunk_sectors) {
rs->ti->error = "Region size is smaller than the chunk size"; return -EINVAL;
}
}
/* * Convert sectors to bytes.
*/
rs->md.bitmap_info.chunksize = to_bytes(region_size);
return 0;
}
/* * validate_raid_redundancy * @rs * * Determine if there are enough devices in the array that haven't * failed (or are being rebuilt) to form a usable array. * * Returns: 0 on success, -EINVAL on failure.
*/ staticint validate_raid_redundancy(struct raid_set *rs)
{ unsignedint i, rebuild_cnt = 0; unsignedint rebuilds_per_group = 0, copies, raid_disks; unsignedint group_size, last_group_start;
for (i = 0; i < rs->raid_disks; i++) if (!test_bit(FirstUse, &rs->dev[i].rdev.flags) &&
((!test_bit(In_sync, &rs->dev[i].rdev.flags) ||
!rs->dev[i].rdev.sb_page)))
rebuild_cnt++;
switch (rs->md.level) { case 0: break; case 1: if (rebuild_cnt >= rs->md.raid_disks) goto too_many; break; case 4: case 5: case 6: if (rebuild_cnt > rs->raid_type->parity_devs) goto too_many; break; case 10:
copies = raid10_md_layout_to_copies(rs->md.new_layout); if (copies < 2) {
DMERR("Bogus raid10 data copies < 2!"); return -EINVAL;
}
if (rebuild_cnt < copies) break;
/* * It is possible to have a higher rebuild count for RAID10, * as long as the failed devices occur in different mirror * groups (i.e. different stripes). * * When checking "near" format, make sure no adjacent devices * have failed beyond what can be handled. In addition to the * simple case where the number of devices is a multiple of the * number of copies, we must also handle cases where the number * of devices is not a multiple of the number of copies. * E.g. dev1 dev2 dev3 dev4 dev5 * A A B B C * C D D E E
*/
raid_disks = min(rs->raid_disks, rs->md.raid_disks); if (__is_raid10_near(rs->md.new_layout)) { for (i = 0; i < raid_disks; i++) { if (!(i % copies))
rebuilds_per_group = 0; if ((!rs->dev[i].rdev.sb_page ||
!test_bit(In_sync, &rs->dev[i].rdev.flags)) &&
(++rebuilds_per_group >= copies)) goto too_many;
} break;
}
/* * When checking "far" and "offset" formats, we need to ensure * that the device that holds its copy is not also dead or * being rebuilt. (Note that "far" and "offset" formats only * support two copies right now. These formats also only ever * use the 'use_far_sets' variant.) * * This check is somewhat complicated by the need to account * for arrays that are not a multiple of (far) copies. This * results in the need to treat the last (potentially larger) * set differently.
*/
group_size = (raid_disks / copies);
last_group_start = (raid_disks / group_size) - 1;
last_group_start *= group_size; for (i = 0; i < raid_disks; i++) { if (!(i % copies) && !(i > last_group_start))
rebuilds_per_group = 0; if ((!rs->dev[i].rdev.sb_page ||
!test_bit(In_sync, &rs->dev[i].rdev.flags)) &&
(++rebuilds_per_group >= copies)) goto too_many;
} break; default: if (rebuild_cnt) return -EINVAL;
}
return 0;
too_many: return -EINVAL;
}
/* * Possible arguments are... * <chunk_size> [optional_args] * * Argument definitions * <chunk_size> The number of sectors per disk that * will form the "stripe" * [[no]sync] Force or prevent recovery of the * entire array * [rebuild <idx>] Rebuild the drive indicated by the index * [daemon_sleep <ms>] Time between bitmap daemon work to * clear bits * [min_recovery_rate <kB/sec/disk>] Throttle RAID initialization * [max_recovery_rate <kB/sec/disk>] Throttle RAID initialization * [write_mostly <idx>] Indicate a write mostly drive via index * [max_write_behind <sectors>] See '-write-behind=' (man mdadm) * [stripe_cache <sectors>] Stripe cache size for higher RAIDs * [region_size <sectors>] Defines granularity of bitmap * [journal_dev <dev>] raid4/5/6 journaling deviice * (i.e. write hole closing log) * * RAID10-only options: * [raid10_copies <# copies>] Number of copies. (Default: 2) * [raid10_format <near|far|offset>] Layout algorithm. (Default: near)
*/ staticint parse_raid_params(struct raid_set *rs, struct dm_arg_set *as, unsignedint num_raid_params)
{ int value, raid10_format = ALGORITHM_RAID10_DEFAULT; unsignedint raid10_copies = 2; unsignedint i, write_mostly = 0; unsignedint region_size = 0;
sector_t max_io_len; constchar *arg, *key; struct raid_dev *rd; struct raid_type *rt = rs->raid_type;
arg = dm_shift_arg(as);
num_raid_params--; /* Account for chunk_size argument */
if (kstrtoint(arg, 10, &value) < 0) {
rs->ti->error = "Bad numerical argument given for chunk_size"; return -EINVAL;
}
/* * First, parse the in-order required arguments * "chunk_size" is the only argument of this type.
*/ if (rt_is_raid1(rt)) { if (value)
DMERR("Ignoring chunk size parameter for RAID 1");
value = 0;
} elseif (!is_power_of_2(value)) {
rs->ti->error = "Chunk size must be a power of 2"; return -EINVAL;
} elseif (value < 8) {
rs->ti->error = "Chunk size value is too small"; return -EINVAL;
}
/* * We set each individual device as In_sync with a completed * 'recovery_offset'. If there has been a device failure or * replacement then one of the following cases applies: * * 1) User specifies 'rebuild'. * - Device is reset when param is read. * 2) A new device is supplied. * - No matching superblock found, resets device. * 3) Device failure was transient and returns on reload. * - Failure noticed, resets device for bitmap replay. * 4) Device hadn't completed recovery after previous failure. * - Superblock is read and overrides recovery_offset. * * What is found in the superblocks of the devices is always * authoritative, unless 'rebuild' or '[no]sync' was specified.
*/ for (i = 0; i < rs->raid_disks; i++) {
set_bit(In_sync, &rs->dev[i].rdev.flags);
rs->dev[i].rdev.recovery_offset = MaxSector;
}
/* * Second, parse the unordered optional arguments
*/ for (i = 0; i < num_raid_params; i++) {
key = dm_shift_arg(as); if (!key) {
rs->ti->error = "Not enough raid parameters given"; return -EINVAL;
}
if (!strcasecmp(key, dm_raid_arg_name_by_flag(CTR_FLAG_NOSYNC))) { if (test_and_set_bit(__CTR_FLAG_NOSYNC, &rs->ctr_flags)) {
rs->ti->error = "Only one 'nosync' argument allowed"; return -EINVAL;
} continue;
} if (!strcasecmp(key, dm_raid_arg_name_by_flag(CTR_FLAG_SYNC))) { if (test_and_set_bit(__CTR_FLAG_SYNC, &rs->ctr_flags)) {
rs->ti->error = "Only one 'sync' argument allowed"; return -EINVAL;
} continue;
} if (!strcasecmp(key, dm_raid_arg_name_by_flag(CTR_FLAG_RAID10_USE_NEAR_SETS))) { if (test_and_set_bit(__CTR_FLAG_RAID10_USE_NEAR_SETS, &rs->ctr_flags)) {
rs->ti->error = "Only one 'raid10_use_new_sets' argument allowed"; return -EINVAL;
} continue;
}
arg = dm_shift_arg(as);
i++; /* Account for the argument pairs */ if (!arg) {
rs->ti->error = "Wrong number of raid parameters given"; return -EINVAL;
}
/* * Parameters that take a string value are checked here.
*/ /* "raid10_format {near|offset|far} */ if (!strcasecmp(key, dm_raid_arg_name_by_flag(CTR_FLAG_RAID10_FORMAT))) { if (test_and_set_bit(__CTR_FLAG_RAID10_FORMAT, &rs->ctr_flags)) {
rs->ti->error = "Only one 'raid10_format' argument pair allowed"; return -EINVAL;
} if (!rt_is_raid10(rt)) {
rs->ti->error = "'raid10_format' is an invalid parameter for this RAID type"; return -EINVAL;
}
raid10_format = raid10_name_to_format(arg); if (raid10_format < 0) {
rs->ti->error = "Invalid 'raid10_format' value given"; return raid10_format;
} continue;
}
/* "journal_dev <dev>" */ if (!strcasecmp(key, dm_raid_arg_name_by_flag(CTR_FLAG_JOURNAL_DEV))) { int r; struct md_rdev *jdev;
if (test_and_set_bit(__CTR_FLAG_JOURNAL_DEV, &rs->ctr_flags)) {
rs->ti->error = "Only one raid4/5/6 set journaling device allowed"; return -EINVAL;
} if (!rt_is_raid456(rt)) {
rs->ti->error = "'journal_dev' is an invalid parameter for this RAID type"; return -EINVAL;
}
r = dm_get_device(rs->ti, arg, dm_table_get_mode(rs->ti->table),
&rs->journal_dev.dev); if (r) {
rs->ti->error = "raid4/5/6 journal device lookup failure"; return r;
}
jdev = &rs->journal_dev.rdev;
md_rdev_init(jdev);
jdev->mddev = &rs->md;
jdev->bdev = rs->journal_dev.dev->bdev;
jdev->sectors = bdev_nr_sectors(jdev->bdev); if (jdev->sectors < MIN_RAID456_JOURNAL_SPACE) {
rs->ti->error = "No space for raid4/5/6 journal"; return -ENOSPC;
}
rs->journal_dev.mode = R5C_JOURNAL_MODE_WRITE_THROUGH;
set_bit(Journal, &jdev->flags); continue;
}
/* "journal_mode <mode>" ("journal_dev" mandatory!) */ if (!strcasecmp(key, dm_raid_arg_name_by_flag(CTR_FLAG_JOURNAL_MODE))) { int r;
if (!test_bit(__CTR_FLAG_JOURNAL_DEV, &rs->ctr_flags)) {
rs->ti->error = "raid4/5/6 'journal_mode' is invalid without 'journal_dev'"; return -EINVAL;
} if (test_and_set_bit(__CTR_FLAG_JOURNAL_MODE, &rs->ctr_flags)) {
rs->ti->error = "Only one raid4/5/6 'journal_mode' argument allowed"; return -EINVAL;
}
r = dm_raid_journal_mode_to_md(arg); if (r < 0) {
rs->ti->error = "Invalid 'journal_mode' argument"; return r;
}
rs->journal_dev.mode = r; continue;
}
/* * Parameters with number values from here on.
*/ if (kstrtoint(arg, 10, &value) < 0) {
rs->ti->error = "Bad numerical argument given in raid params"; return -EINVAL;
}
if (!strcasecmp(key, dm_raid_arg_name_by_flag(CTR_FLAG_REBUILD))) { /* * "rebuild" is being passed in by userspace to provide * indexes of replaced devices and to set up additional * devices on raid level takeover.
*/ if (!__within_range(value, 0, rs->raid_disks - 1)) {
rs->ti->error = "Invalid rebuild index given"; return -EINVAL;
}
if (test_and_set_bit(value, (void *) rs->rebuild_disks)) {
rs->ti->error = "rebuild for this index already given"; return -EINVAL;
}
rd = rs->dev + value;
clear_bit(In_sync, &rd->rdev.flags);
clear_bit(Faulty, &rd->rdev.flags);
rd->rdev.recovery_offset = 0;
set_bit(__CTR_FLAG_REBUILD, &rs->ctr_flags);
} elseif (!strcasecmp(key, dm_raid_arg_name_by_flag(CTR_FLAG_WRITE_MOSTLY))) { if (!rt_is_raid1(rt)) {
rs->ti->error = "write_mostly option is only valid for RAID1"; return -EINVAL;
}
if (!__within_range(value, 0, rs->md.raid_disks - 1)) {
rs->ti->error = "Invalid write_mostly index given"; return -EINVAL;
}
write_mostly++;
set_bit(WriteMostly, &rs->dev[value].rdev.flags);
set_bit(__CTR_FLAG_WRITE_MOSTLY, &rs->ctr_flags);
} elseif (!strcasecmp(key, dm_raid_arg_name_by_flag(CTR_FLAG_MAX_WRITE_BEHIND))) { if (!rt_is_raid1(rt)) {
rs->ti->error = "max_write_behind option is only valid for RAID1"; return -EINVAL;
}
if (test_and_set_bit(__CTR_FLAG_MAX_WRITE_BEHIND, &rs->ctr_flags)) {
rs->ti->error = "Only one max_write_behind argument pair allowed"; return -EINVAL;
}
if (value < 0) {
rs->ti->error = "Max write-behind limit out of range"; return -EINVAL;
}
rs->md.bitmap_info.max_write_behind = value / 2;
} elseif (!strcasecmp(key, dm_raid_arg_name_by_flag(CTR_FLAG_DAEMON_SLEEP))) { if (test_and_set_bit(__CTR_FLAG_DAEMON_SLEEP, &rs->ctr_flags)) {
rs->ti->error = "Only one daemon_sleep argument pair allowed"; return -EINVAL;
} if (value < 0) {
rs->ti->error = "daemon sleep period out of range"; return -EINVAL;
}
rs->md.bitmap_info.daemon_sleep = value;
} elseif (!strcasecmp(key, dm_raid_arg_name_by_flag(CTR_FLAG_DATA_OFFSET))) { /* Userspace passes new data_offset after having extended the data image LV */ if (test_and_set_bit(__CTR_FLAG_DATA_OFFSET, &rs->ctr_flags)) {
rs->ti->error = "Only one data_offset argument pair allowed"; return -EINVAL;
} /* Ensure sensible data offset */ if (value < 0 ||
(value && (value < MIN_FREE_RESHAPE_SPACE || value % to_sector(PAGE_SIZE)))) {
rs->ti->error = "Bogus data_offset value"; return -EINVAL;
}
rs->data_offset = value;
} elseif (!strcasecmp(key, dm_raid_arg_name_by_flag(CTR_FLAG_DELTA_DISKS))) { /* Define the +/-# of disks to add to/remove from the given raid set */ if (test_and_set_bit(__CTR_FLAG_DELTA_DISKS, &rs->ctr_flags)) {
rs->ti->error = "Only one delta_disks argument pair allowed"; return -EINVAL;
} /* Ensure MAX_RAID_DEVICES and raid type minimal_devs! */ if (!__within_range(abs(value), 1, MAX_RAID_DEVICES - rt->minimal_devs)) {
rs->ti->error = "Too many delta_disk requested"; return -EINVAL;
}
if (nr_stripes < min_stripes) {
DMINFO("Adjusting requested %u stripe cache entries to %u to suit stripe size",
nr_stripes, min_stripes);
nr_stripes = min_stripes;
}
conf = mddev->private; if (!conf) {
rs->ti->error = "Cannot change stripe_cache size on inactive RAID set"; return -EINVAL;
}
/* Try setting number of stripes in raid456 stripe cache */ if (conf->min_nr_stripes != nr_stripes) {
r = raid5_set_cache_size(mddev, nr_stripes); if (r) {
rs->ti->error = "Failed to set raid4/5/6 stripe cache size"; return r;
}
DMINFO("%u stripe cache entries", nr_stripes);
}
return 0;
}
/* Return # of data stripes as kept in mddev as of @rs (i.e. as of superblock) */ staticunsignedint mddev_data_stripes(struct raid_set *rs)
{ return rs->md.raid_disks - rs->raid_type->parity_devs;
}
/* Return # of data stripes of @rs (i.e. as of ctr) */ staticunsignedint rs_data_stripes(struct raid_set *rs)
{ return rs->raid_disks - rs->raid_type->parity_devs;
}
/* * Retrieve rdev->sectors from any valid raid device of @rs * to allow userpace to pass in arbitray "- -" device tupples.
*/ static sector_t __rdev_sectors(struct raid_set *rs)
{ int i;
for (i = 0; i < rs->raid_disks; i++) { struct md_rdev *rdev = &rs->dev[i].rdev;
if (!test_bit(Journal, &rdev->flags) &&
rdev->bdev && rdev->sectors) return rdev->sectors;
}
return _check_data_dev_sectors(rs);
bad:
rs->ti->error = "Target length not divisible by number of data devices"; return -EINVAL;
}
/* Setup recovery on @rs */ staticvoid rs_setup_recovery(struct raid_set *rs, sector_t dev_sectors)
{ /* raid0 does not recover */ if (rs_is_raid0(rs))
rs->md.resync_offset = MaxSector; /* * A raid6 set has to be recovered either * completely or for the grown part to * ensure proper parity and Q-Syndrome
*/ elseif (rs_is_raid6(rs))
rs->md.resync_offset = dev_sectors; /* * Other raid set types may skip recovery * depending on the 'nosync' flag.
*/ else
rs->md.resync_offset = test_bit(__CTR_FLAG_NOSYNC, &rs->ctr_flags)
? MaxSector : dev_sectors;
}
/* * Make sure a valid takover (level switch) is being requested on @rs * * Conversions of raid sets from one MD personality to another * have to conform to restrictions which are enforced here.
*/ staticint rs_check_takeover(struct raid_set *rs)
{ struct mddev *mddev = &rs->md; unsignedint near_copies;
/* State flags for sb->flags */ #define SB_FLAG_RESHAPE_ACTIVE 0x1 #define SB_FLAG_RESHAPE_BACKWARDS 0x2
/* * This structure is never routinely used by userspace, unlike md superblocks. * Devices with this superblock should only ever be accessed via device-mapper.
*/ #define DM_RAID_MAGIC 0x64526D44 struct dm_raid_superblock {
__le32 magic; /* "DmRd" */
__le32 compat_features; /* Used to indicate compatible features (like 1.9.0 ondisk metadata extension) */
__le32 num_devices; /* Number of devices in this raid set. (Max 64) */
__le32 array_position; /* The position of this drive in the raid set */
__le64 events; /* Incremented by md when superblock updated */
__le64 failed_devices; /* Pre 1.9.0 part of bit field of devices to */ /* indicate failures (see extension below) */
/* * This offset tracks the progress of the repair or replacement of * an individual drive.
*/
__le64 disk_recovery_offset;
/* * This offset tracks the progress of the initial raid set * synchronisation/parity calculation.
*/
__le64 array_resync_offset;
/******************************************************************** * BELOW FOLLOW V1.9.0 EXTENSIONS TO THE PRISTINE SUPERBLOCK FORMAT!!! * * FEATURE_FLAG_SUPPORTS_V190 in the compat_features member indicates that those exist
*/
__le32 flags; /* Flags defining array states for reshaping */
/* * This offset tracks the progress of a raid * set reshape in order to be able to restart it
*/
__le64 reshape_position;
/* * These define the properties of the array in case of an interrupted reshape
*/
__le32 new_level;
__le32 new_layout;
__le32 new_stripe_sectors;
__le32 delta_disks;
__le64 array_sectors; /* Array size in sectors */
/* * Sector offsets to data on devices (reshaping). * Needed to support out of place reshaping, thus * not writing over any stripes whilst converting * them from old to new layout
*/
__le64 data_offset;
__le64 new_data_offset;
__le64 sectors; /* Used device size in sectors */
/* * Additional Bit field of devices indicating failures to support * up to 256 devices with the 1.9.0 on-disk metadata format
*/
__le64 extended_failed_devices[DISKS_ARRAY_ELEMS - 1];
__le32 incompat_features; /* Used to indicate any incompatible features */
/* Always set rest up to logical block size to 0 when writing (see get_metadata_device() below). */
} __packed;
/* * Check for reshape constraints on raid set @rs: * * - reshape function non-existent * - degraded set * - ongoing recovery * - ongoing reshape * * Returns 0 if none or -EPERM if given constraint * and error message reference in @errmsg
*/ staticint rs_check_reshape(struct raid_set *rs)
{ struct mddev *mddev = &rs->md;
if (!mddev->pers || !mddev->pers->check_reshape)
rs->ti->error = "Reshape not supported"; elseif (mddev->degraded)
rs->ti->error = "Can't reshape degraded raid set"; elseif (rs_is_recovering(rs))
rs->ti->error = "Convert request on recovering raid set prohibited"; elseif (rs_is_reshaping(rs))
rs->ti->error = "raid set already reshaping!"; elseif (!(rs_is_raid1(rs) || rs_is_raid10(rs) || rs_is_raid456(rs)))
rs->ti->error = "Reshaping only supported for raid1/4/5/6/10"; else return 0;
return -EPERM;
}
staticint read_disk_sb(struct md_rdev *rdev, int size, bool force_reload)
{
BUG_ON(!rdev->sb_page);
if (rdev->sb_loaded && !force_reload) return 0;
rdev->sb_loaded = 0;
if (!sync_page_io(rdev, 0, size, rdev->sb_page, REQ_OP_READ, true)) {
DMERR("Failed to read superblock of device at position %d",
rdev->raid_disk);
md_error(rdev->mddev, rdev);
set_bit(Faulty, &rdev->flags); return -EIO;
}
/******************************************************************** * BELOW FOLLOW V1.9.0 EXTENSIONS TO THE PRISTINE SUPERBLOCK FORMAT!!! * * FEATURE_FLAG_SUPPORTS_V190 in the compat_features member indicates that those exist
*/
sb->new_level = cpu_to_le32(mddev->new_level);
sb->new_layout = cpu_to_le32(mddev->new_layout);
sb->new_stripe_sectors = cpu_to_le32(mddev->new_chunk_sectors);
smp_rmb(); /* Make sure we access most recent reshape position */
sb->reshape_position = cpu_to_le64(mddev->reshape_position); if (le64_to_cpu(sb->reshape_position) != MaxSector) { /* Flag ongoing reshape */
sb->flags |= cpu_to_le32(SB_FLAG_RESHAPE_ACTIVE);
/* Zero out the rest of the payload after the size of the superblock */
memset(sb + 1, 0, rdev->sb_size - sizeof(*sb));
}
/* * super_load * * This function creates a superblock if one is not found on the device * and will decide which superblock to use if there's a choice. * * Return: 1 if use rdev, 0 if use refdev, -Exxx otherwise
*/ staticint super_load(struct md_rdev *rdev, struct md_rdev *refdev)
{ int r; struct dm_raid_superblock *sb; struct dm_raid_superblock *refsb;
uint64_t events_sb, events_refsb;
r = read_disk_sb(rdev, rdev->sb_size, false); if (r) return r;
sb = page_address(rdev->sb_page);
/* * Two cases that we want to write new superblocks and rebuild: * 1) New device (no matching magic number) * 2) Device specified for rebuild (!In_sync w/ offset == 0)
*/ if ((sb->magic != cpu_to_le32(DM_RAID_MAGIC)) ||
(!test_bit(In_sync, &rdev->flags) && !rdev->recovery_offset)) {
super_sync(rdev->mddev, rdev);
/* * Reshaping is supported, e.g. reshape_position is valid * in superblock and superblock content is authoritative.
*/ if (le32_to_cpu(sb->compat_features) & FEATURE_FLAG_SUPPORTS_V190) {
--> --------------------
Die Informationen auf dieser Webseite wurden
nach bestem Wissen sorgfältig zusammengestellt. Es wird jedoch weder Vollständigkeit, noch Richtigkeit,
noch Qualität der bereit gestellten Informationen zugesichert.
Bemerkung:
Die farbliche Syntaxdarstellung und die Messung sind noch experimentell.