diff options
Diffstat (limited to 'drivers/md/dm-raid.c')
| -rw-r--r-- | drivers/md/dm-raid.c | 147 |
1 files changed, 123 insertions, 24 deletions
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index 017c34d78d6..982e3e390c4 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -11,6 +11,7 @@ #include "md.h" #include "raid1.h" #include "raid5.h" +#include "raid10.h" #include "bitmap.h" #include <linux/device-mapper.h> @@ -52,7 +53,10 @@ struct raid_dev { #define DMPF_MAX_RECOVERY_RATE 0x20 #define DMPF_MAX_WRITE_BEHIND 0x40 #define DMPF_STRIPE_CACHE 0x80 -#define DMPF_REGION_SIZE 0X100 +#define DMPF_REGION_SIZE 0x100 +#define DMPF_RAID10_COPIES 0x200 +#define DMPF_RAID10_FORMAT 0x400 + struct raid_set { struct dm_target *ti; @@ -76,6 +80,7 @@ static struct raid_type { const unsigned algorithm; /* RAID algorithm. */ } raid_types[] = { {"raid1", "RAID1 (mirroring)", 0, 2, 1, 0 /* NONE */}, + {"raid10", "RAID10 (striped mirrors)", 0, 2, 10, UINT_MAX /* Varies */}, {"raid4", "RAID4 (dedicated parity disk)", 1, 2, 5, ALGORITHM_PARITY_0}, {"raid5_la", "RAID5 (left asymmetric)", 1, 2, 5, ALGORITHM_LEFT_ASYMMETRIC}, {"raid5_ra", "RAID5 (right asymmetric)", 1, 2, 5, ALGORITHM_RIGHT_ASYMMETRIC}, @@ -86,6 +91,17 @@ static struct raid_type { {"raid6_nc", "RAID6 (N continue)", 2, 4, 6, ALGORITHM_ROTATING_N_CONTINUE} }; +static unsigned raid10_md_layout_to_copies(int layout) +{ + return layout & 0xFF; +} + +static int raid10_format_to_md_layout(char *format, unsigned copies) +{ + /* 1 "far" copy, and 'copies' "near" copies */ + return (1 << 8) | (copies & 0xFF); +} + static struct raid_type *get_raid_type(char *name) { int i; @@ -101,20 +117,12 @@ static struct raid_set *context_alloc(struct dm_target *ti, struct raid_type *ra { unsigned i; struct raid_set *rs; - sector_t sectors_per_dev; if (raid_devs <= raid_type->parity_devs) { ti->error = "Insufficient number of devices"; return ERR_PTR(-EINVAL); } - sectors_per_dev = ti->len; - if ((raid_type->level > 1) && - sector_div(sectors_per_dev, (raid_devs - raid_type->parity_devs))) { - ti->error = "Target length not divisible by number of data devices"; - return ERR_PTR(-EINVAL); - } - rs = kzalloc(sizeof(*rs) + raid_devs * sizeof(rs->dev[0]), GFP_KERNEL); if (!rs) { ti->error = "Cannot allocate raid context"; @@ -128,7 +136,6 @@ static struct raid_set *context_alloc(struct dm_target *ti, struct raid_type *ra rs->md.raid_disks = raid_devs; rs->md.level = raid_type->level; rs->md.new_level = rs->md.level; - rs->md.dev_sectors = sectors_per_dev; rs->md.layout = raid_type->algorithm; rs->md.new_layout = rs->md.layout; rs->md.delta_disks = 0; @@ -143,6 +150,7 @@ static struct raid_set *context_alloc(struct dm_target *ti, struct raid_type *ra * rs->md.external * rs->md.chunk_sectors * rs->md.new_chunk_sectors + * rs->md.dev_sectors */ return rs; @@ -347,12 +355,20 @@ static int validate_region_size(struct raid_set *rs, unsigned long region_size) * [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 + * + * RAID10-only options: + * [raid10_copies <# copies>] Number of copies. (Default: 2) + * [raid10_format <near>] Layout algorithm. (Default: near) */ static int parse_raid_params(struct raid_set *rs, char **argv, unsigned num_raid_params) { + char *raid10_format = "near"; + unsigned raid10_copies = 2; unsigned i, rebuild_cnt = 0; unsigned long value, region_size = 0; + sector_t sectors_per_dev = rs->ti->len; + sector_t max_io_len; char *key; /* @@ -422,20 +438,53 @@ static int parse_raid_params(struct raid_set *rs, char **argv, } key = argv[i++]; + + /* Parameters that take a string value are checked here. */ + if (!strcasecmp(key, "raid10_format")) { + if (rs->raid_type->level != 10) { + rs->ti->error = "'raid10_format' is an invalid parameter for this RAID type"; + return -EINVAL; + } + if (strcmp("near", argv[i])) { + rs->ti->error = "Invalid 'raid10_format' value given"; + return -EINVAL; + } + raid10_format = argv[i]; + rs->print_flags |= DMPF_RAID10_FORMAT; + continue; + } + if (strict_strtoul(argv[i], 10, &value) < 0) { rs->ti->error = "Bad numerical argument given in raid params"; return -EINVAL; } + /* Parameters that take a numeric value are checked here */ if (!strcasecmp(key, "rebuild")) { rebuild_cnt++; - if (((rs->raid_type->level != 1) && - (rebuild_cnt > rs->raid_type->parity_devs)) || - ((rs->raid_type->level == 1) && - (rebuild_cnt > (rs->md.raid_disks - 1)))) { - rs->ti->error = "Too many rebuild devices specified for given RAID type"; + + switch (rs->raid_type->level) { + case 1: + if (rebuild_cnt >= rs->md.raid_disks) { + rs->ti->error = "Too many rebuild devices specified"; + return -EINVAL; + } + break; + case 4: + case 5: + case 6: + if (rebuild_cnt > rs->raid_type->parity_devs) { + rs->ti->error = "Too many rebuild devices specified for given RAID type"; + return -EINVAL; + } + break; + case 10: + default: + DMERR("The rebuild parameter is not supported for %s", rs->raid_type->name); + rs->ti->error = "Rebuild not supported for this RAID type"; return -EINVAL; } + if (value > rs->md.raid_disks) { rs->ti->error = "Invalid rebuild index given"; return -EINVAL; @@ -486,7 +535,8 @@ static int parse_raid_params(struct raid_set *rs, char **argv, */ value /= 2; - if (rs->raid_type->level < 5) { + if ((rs->raid_type->level != 5) && + (rs->raid_type->level != 6)) { rs->ti->error = "Inappropriate argument: stripe_cache"; return -EINVAL; } @@ -511,6 +561,14 @@ static int parse_raid_params(struct raid_set *rs, char **argv, } else if (!strcasecmp(key, "region_size")) { rs->print_flags |= DMPF_REGION_SIZE; region_size = value; + } else if (!strcasecmp(key, "raid10_copies") && + (rs->raid_type->level == 10)) { + if ((value < 2) || (value > 0xFF)) { + rs->ti->error = "Bad value for 'raid10_copies'"; + return -EINVAL; + } + rs->print_flags |= DMPF_RAID10_COPIES; + raid10_copies = value; } else { DMERR("Unable to parse RAID parameter: %s", key); rs->ti->error = "Unable to parse RAID parameters"; @@ -522,14 +580,33 @@ static int parse_raid_params(struct raid_set *rs, char **argv, return -EINVAL; if (rs->md.chunk_sectors) - rs->ti->split_io = rs->md.chunk_sectors; + max_io_len = rs->md.chunk_sectors; else - rs->ti->split_io = region_size; + max_io_len = region_size; - if (rs->md.chunk_sectors) - rs->ti->split_io = rs->md.chunk_sectors; - else - rs->ti->split_io = region_size; + if (dm_set_target_max_io_len(rs->ti, max_io_len)) + return -EINVAL; + + if (rs->raid_type->level == 10) { + if (raid10_copies > rs->md.raid_disks) { + rs->ti->error = "Not enough devices to satisfy specification"; + return -EINVAL; + } + + /* (Len * #mirrors) / #devices */ + sectors_per_dev = rs->ti->len * raid10_copies; + sector_div(sectors_per_dev, rs->md.raid_disks); + + rs->md.layout = raid10_format_to_md_layout(raid10_format, + raid10_copies); + rs->md.new_layout = rs->md.layout; + } else if ((rs->raid_type->level > 1) && + sector_div(sectors_per_dev, + (rs->md.raid_disks - rs->raid_type->parity_devs))) { + rs->ti->error = "Target length not divisible by number of data devices"; + return -EINVAL; + } + rs->md.dev_sectors = sectors_per_dev; /* Assume there are no metadata devices until the drives are parsed */ rs->md.persistent = 0; @@ -552,6 +629,9 @@ static int raid_is_congested(struct dm_target_callbacks *cb, int bits) if (rs->raid_type->level == 1) return md_raid1_congested(&rs->md, bits); + if (rs->raid_type->level == 10) + return md_raid10_congested(&rs->md, bits); + return md_raid5_congested(&rs->md, bits); } @@ -870,6 +950,9 @@ static int analyse_superblocks(struct dm_target *ti, struct raid_set *rs) case 6: redundancy = rs->raid_type->parity_devs; break; + case 10: + redundancy = raid10_md_layout_to_copies(mddev->layout) - 1; + break; default: ti->error = "Unknown RAID type"; return -EINVAL; @@ -1035,12 +1118,19 @@ static int raid_ctr(struct dm_target *ti, unsigned argc, char **argv) goto bad; } + if (ti->len != rs->md.array_sectors) { + ti->error = "Array size does not match requested target length"; + ret = -EINVAL; + goto size_mismatch; + } rs->callbacks.congested_fn = raid_is_congested; dm_table_add_target_callbacks(ti->table, &rs->callbacks); mddev_suspend(&rs->md); return 0; +size_mismatch: + md_stop(&rs->md); bad: context_free(rs); @@ -1067,7 +1157,7 @@ static int raid_map(struct dm_target *ti, struct bio *bio, union map_info *map_c } static int raid_status(struct dm_target *ti, status_type_t type, - char *result, unsigned maxlen) + unsigned status_flags, char *result, unsigned maxlen) { struct raid_set *rs = ti->private; unsigned raid_param_cnt = 1; /* at least 1 for chunksize */ @@ -1189,6 +1279,13 @@ static int raid_status(struct dm_target *ti, status_type_t type, DMEMIT(" region_size %lu", rs->md.bitmap_info.chunksize >> 9); + if (rs->print_flags & DMPF_RAID10_COPIES) + DMEMIT(" raid10_copies %u", + raid10_md_layout_to_copies(rs->md.layout)); + + if (rs->print_flags & DMPF_RAID10_FORMAT) + DMEMIT(" raid10_format near"); + DMEMIT(" %d", rs->md.raid_disks); for (i = 0; i < rs->md.raid_disks; i++) { if (rs->dev[i].meta_dev) @@ -1263,7 +1360,7 @@ static void raid_resume(struct dm_target *ti) static struct target_type raid_target = { .name = "raid", - .version = {1, 2, 0}, + .version = {1, 3, 0}, .module = THIS_MODULE, .ctr = raid_ctr, .dtr = raid_dtr, @@ -1290,6 +1387,8 @@ module_init(dm_raid_init); module_exit(dm_raid_exit); MODULE_DESCRIPTION(DM_NAME " raid4/5/6 target"); +MODULE_ALIAS("dm-raid1"); +MODULE_ALIAS("dm-raid10"); MODULE_ALIAS("dm-raid4"); MODULE_ALIAS("dm-raid5"); MODULE_ALIAS("dm-raid6"); |