// SPDX-License-Identifier: GPL-2.0-or-later/* raid0.c : Multiple Devices driver for Linux Copyright (C) 1994-96 Marc ZYNGIER <zyngier@ufr-info-p7.ibp.fr> or <maz@gloups.fdn.fr> Copyright (C) 1999, 2000 Ingo Molnar, Red Hat RAID-0 management functions. */ #include <linux/blkdev.h>#include <linux/seq_file.h>#include <linux/module.h>#include <linux/slab.h>#include <linux/string_choices.h>#include <trace/events/block.h>#include "md.h"#include "raid0.h"#include "raid5.h" static int default_layout = 0;module_param(default_layout, int, 0644); #define UNSUPPORTED_MDDEV_FLAGS \ ((1L << MD_HAS_JOURNAL) | \ (1L << MD_JOURNAL_CLEAN) | \ (1L << MD_FAILFAST_SUPPORTED) |\ (1L << MD_HAS_PPL) | \ (1L << MD_HAS_MULTIPLE_PPLS) | \ (1L << MD_FAILLAST_DEV) | \ (1L << MD_SERIALIZE_POLICY)) /* * inform the user of the raid configuration*/static void dump_zones(struct mddev *mddev){ int j, k; sector_t zone_size = 0; sector_t zone_start = 0; struct r0conf *conf = mddev->private; int raid_disks = conf->strip_zone[0].nb_dev; pr_debug("md: RAID0 configuration for %s - %d zone%s\n", mdname(mddev), conf->nr_strip_zones, str_plural(conf->nr_strip_zones)); for (j = 0; j < conf->nr_strip_zones; j++) { char line[200]; int len = 0; for (k = 0; k < conf->strip_zone[j].nb_dev; k++) len += scnprintf(line+len, 200-len, "%s%pg", k?"/":"", conf->devlist[j * raid_disks + k]->bdev); pr_debug("md: zone%d=[%s]\n", j, line); zone_size = conf->strip_zone[j].zone_end - zone_start; pr_debug(" zone-offset=%10lluKB, device-offset=%10lluKB, size=%10lluKB\n", (unsigned long long)zone_start>>1, (unsigned long long)conf->strip_zone[j].dev_start>>1, (unsigned long long)zone_size>>1); zone_start = conf->strip_zone[j].zone_end; }} static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf){ int i, c, err; sector_t curr_zone_end, sectors; struct md_rdev *smallest, *rdev1, *rdev2, *rdev, **dev; struct strip_zone *zone; int cnt; struct r0conf *conf = kzalloc_obj(*conf); unsigned int blksize = 512; if (!mddev_is_dm(mddev)) blksize = queue_logical_block_size(mddev->gendisk->queue); *private_conf = ERR_PTR(-ENOMEM); if (!conf) return -ENOMEM; rdev_for_each(rdev1, mddev) { pr_debug("md/raid0:%s: looking at %pg\n", mdname(mddev), rdev1->bdev); c = 0; /* round size to chunk_size */ sectors = rdev1->sectors; sector_div(sectors, mddev->chunk_sectors); rdev1->sectors = sectors * mddev->chunk_sectors; if (mddev_is_dm(mddev)) blksize = max(blksize, queue_logical_block_size( rdev1->bdev->bd_disk->queue)); rdev_for_each(rdev2, mddev) { pr_debug("md/raid0:%s: comparing %pg(%llu)" " with %pg(%llu)\n", mdname(mddev), rdev1->bdev, (unsigned long long)rdev1->sectors, rdev2->bdev, (unsigned long long)rdev2->sectors); if (rdev2 == rdev1) { pr_debug("md/raid0:%s: END\n", mdname(mddev)); break; } if (rdev2->sectors == rdev1->sectors) { /* * Not unique, don't count it as a new * group */ pr_debug("md/raid0:%s: EQUAL\n", mdname(mddev)); c = 1; break; } pr_debug("md/raid0:%s: NOT EQUAL\n", mdname(mddev)); } if (!c) { pr_debug("md/raid0:%s: ==> UNIQUE\n", mdname(mddev)); conf->nr_strip_zones++; pr_debug("md/raid0:%s: %d zones\n", mdname(mddev), conf->nr_strip_zones); } } pr_debug("md/raid0:%s: FINAL %d zones\n", mdname(mddev), conf->nr_strip_zones); /* * now since we have the hard sector sizes, we can make sure * chunk size is a multiple of that sector size */ if ((mddev->chunk_sectors << 9) % blksize) { pr_warn("md/raid0:%s: chunk_size of %d not multiple of block size %d\n", mdname(mddev), mddev->chunk_sectors << 9, blksize); err = -EINVAL; goto abort; } err = -ENOMEM; conf->strip_zone = kvzalloc_objs(struct strip_zone, conf->nr_strip_zones); if (!conf->strip_zone) goto abort; conf->devlist = kvzalloc(array3_size(sizeof(struct md_rdev *), conf->nr_strip_zones, mddev->raid_disks), GFP_KERNEL); if (!conf->devlist) goto abort; /* The first zone must contain all devices, so here we check that * there is a proper alignment of slots to devices and find them all */ zone = &conf->strip_zone[0]; cnt = 0; smallest = NULL; dev = conf->devlist; err = -EINVAL; rdev_for_each(rdev1, mddev) { int j = rdev1->raid_disk; if (mddev->level == 10) { /* taking over a raid10-n2 array */ j /= 2; rdev1->new_raid_disk = j; } if (mddev->level == 1) { /* taiking over a raid1 array- * we have only one active disk */ j = 0; rdev1->new_raid_disk = j; } if (j < 0) { pr_warn("md/raid0:%s: remove inactive devices before converting to RAID0\n", mdname(mddev)); goto abort; } if (j >= mddev->raid_disks) { pr_warn("md/raid0:%s: bad disk number %d - aborting!\n", mdname(mddev), j); goto abort; } if (dev[j]) { pr_warn("md/raid0:%s: multiple devices for %d - aborting!\n", mdname(mddev), j); goto abort; } dev[j] = rdev1; if (!smallest || (rdev1->sectors < smallest->sectors)) smallest = rdev1; cnt++; } if (cnt != mddev->raid_disks) { pr_warn("md/raid0:%s: too few disks (%d of %d) - aborting!\n", mdname(mddev), cnt, mddev->raid_disks); goto abort; } zone->nb_dev = cnt; zone->zone_end = smallest->sectors * cnt; curr_zone_end = zone->zone_end; /* now do the other zones */ for (i = 1; i < conf->nr_strip_zones; i++) { int j; zone = conf->strip_zone + i; dev = conf->devlist + i * mddev->raid_disks; pr_debug("md/raid0:%s: zone %d\n", mdname(mddev), i); zone->dev_start = smallest->sectors; smallest = NULL; c = 0; for (j=0; j<cnt; j++) { rdev = conf->devlist[j]; if (rdev->sectors <= zone->dev_start) { pr_debug("md/raid0:%s: checking %pg ... nope\n", mdname(mddev), rdev->bdev); continue; } pr_debug("md/raid0:%s: checking %pg ..." " contained as device %d\n", mdname(mddev), rdev->bdev, c); dev[c] = rdev; c++; if (!smallest || rdev->sectors < smallest->sectors) { smallest = rdev; pr_debug("md/raid0:%s: (%llu) is smallest!.\n", mdname(mddev), (unsigned long long)rdev->sectors); } } zone->nb_dev = c; sectors = (smallest->sectors - zone->dev_start) * c; pr_debug("md/raid0:%s: zone->nb_dev: %d, sectors: %llu\n", mdname(mddev), zone->nb_dev, (unsigned long long)sectors); curr_zone_end += sectors; zone->zone_end = curr_zone_end; pr_debug("md/raid0:%s: current zone start: %llu\n", mdname(mddev), (unsigned long long)smallest->sectors); } if (conf->nr_strip_zones == 1 || conf->strip_zone[1].nb_dev == 1) { conf->layout = RAID0_ORIG_LAYOUT; } else if (mddev->layout == RAID0_ORIG_LAYOUT || mddev->layout == RAID0_ALT_MULTIZONE_LAYOUT) { conf->layout = mddev->layout; } else if (default_layout == RAID0_ORIG_LAYOUT || default_layout == RAID0_ALT_MULTIZONE_LAYOUT) { conf->layout = default_layout; } else { pr_err("md/raid0:%s: cannot assemble multi-zone RAID0 with default_layout setting\n", mdname(mddev)); pr_err("md/raid0: please set raid0.default_layout to 1 or 2\n"); err = -EOPNOTSUPP; goto abort; } if (conf->layout == RAID0_ORIG_LAYOUT) { for (i = 1; i < conf->nr_strip_zones; i++) { sector_t first_sector = conf->strip_zone[i-1].zone_end; sector_div(first_sector, mddev->chunk_sectors); zone = conf->strip_zone + i; /* disk_shift is first disk index used in the zone */ zone->disk_shift = sector_div(first_sector, zone->nb_dev); } } pr_debug("md/raid0:%s: done.\n", mdname(mddev)); *private_conf = conf; return 0;abort: kvfree(conf->strip_zone); kvfree(conf->devlist); kfree(conf); *private_conf = ERR_PTR(err); return err;} /* Find the zone which holds a particular offset * Update *sectorp to be an offset in that zone */static struct strip_zone *find_zone(struct r0conf *conf, sector_t *sectorp){ int i; struct strip_zone *z = conf->strip_zone; sector_t sector = *sectorp; for (i = 0; i < conf->nr_strip_zones; i++) if (sector < z[i].zone_end) { if (i) *sectorp = sector - z[i-1].zone_end; return z + i; } BUG();} /* * remaps the bio to the target device. we separate two flows. * power 2 flow and a general flow for the sake of performance*/static struct md_rdev *map_sector(struct mddev *mddev, struct strip_zone *zone, sector_t sector, sector_t *sector_offset){ unsigned int sect_in_chunk; sector_t chunk; struct r0conf *conf = mddev->private; int raid_disks = conf->strip_zone[0].nb_dev; unsigned int chunk_sects = mddev->chunk_sectors; if (is_power_of_2(chunk_sects)) { int chunksect_bits = ffz(~chunk_sects); /* find the sector offset inside the chunk */ sect_in_chunk = sector & (chunk_sects - 1); sector >>= chunksect_bits; /* chunk in zone */ chunk = *sector_offset; /* quotient is the chunk in real device*/ sector_div(chunk, zone->nb_dev << chunksect_bits); } else{ sect_in_chunk = sector_div(sector, chunk_sects); chunk = *sector_offset; sector_div(chunk, chunk_sects * zone->nb_dev); } /* * position the bio over the real device * real sector = chunk in device + starting of zone * + the position in the chunk */ *sector_offset = (chunk * chunk_sects) + sect_in_chunk; return conf->devlist[(zone - conf->strip_zone)*raid_disks + sector_div(sector, zone->nb_dev)];} static sector_t raid0_size(struct mddev *mddev, sector_t sectors, int raid_disks){ sector_t array_sectors = 0; struct md_rdev *rdev; WARN_ONCE(sectors || raid_disks, "%s does not support generic reshape\n", __func__); rdev_for_each(rdev, mddev) array_sectors += (rdev->sectors & ~(sector_t)(mddev->chunk_sectors-1)); return array_sectors;} static void raid0_free(struct mddev *mddev, void *priv){ struct r0conf *conf = priv; kvfree(conf->strip_zone); kvfree(conf->devlist); kfree(conf);} static int raid0_set_limits(struct mddev *mddev){ struct queue_limits lim; int err; md_init_stacking_limits(&lim); lim.features |= BLK_FEAT_NOWAIT; lim.max_hw_sectors = mddev->chunk_sectors; lim.max_write_zeroes_sectors = mddev->chunk_sectors; lim.max_hw_wzeroes_unmap_sectors = mddev->chunk_sectors; lim.logical_block_size = mddev->logical_block_size; lim.io_min = mddev->chunk_sectors << 9; lim.io_opt = lim.io_min * mddev->raid_disks; lim.chunk_sectors = mddev->chunk_sectors; lim.features |= BLK_FEAT_ATOMIC_WRITES; lim.features |= BLK_FEAT_PCI_P2PDMA; err = mddev_stack_rdev_limits(mddev, &lim, MDDEV_STACK_INTEGRITY); if (err) return err; return queue_limits_set(mddev->gendisk->queue, &lim);} static int raid0_run(struct mddev *mddev){ struct r0conf *conf; int ret; if (mddev->chunk_sectors == 0) { pr_warn("md/raid0:%s: chunk size must be set.\n", mdname(mddev)); return -EINVAL; } if (md_check_no_bitmap(mddev)) return -EINVAL; if (!mddev_is_dm(mddev)) { ret = raid0_set_limits(mddev); if (ret) return ret; } /* if private is not null, we are here after takeover */ if (mddev->private == NULL) { ret = create_strip_zones(mddev, &conf); if (ret < 0) return ret; mddev->private = conf; } conf = mddev->private; /* calculate array device size */ md_set_array_sectors(mddev, raid0_size(mddev, 0, 0)); pr_debug("md/raid0:%s: md_size is %llu sectors.\n", mdname(mddev), (unsigned long long)mddev->array_sectors); dump_zones(mddev); return md_integrity_register(mddev);} /* * Convert disk_index to the disk order in which it is read/written. * For example, if we have 4 disks, they are numbered 0,1,2,3. If we * write the disks starting at disk 3, then the read/write order would * be disk 3, then 0, then 1, and then disk 2 and we want map_disk_shift() * to map the disks as follows 0,1,2,3 => 1,2,3,0. So disk 0 would map * to 1, 1 to 2, 2 to 3, and 3 to 0. That way we can compare disks in * that 'output' space to understand the read/write disk ordering. */static int map_disk_shift(int disk_index, int num_disks, int disk_shift){ return ((disk_index + num_disks - disk_shift) % num_disks);} static void raid0_handle_discard(struct mddev *mddev, struct bio *bio){ struct r0conf *conf = mddev->private; struct strip_zone *zone; sector_t start = bio->bi_iter.bi_sector; sector_t end; unsigned int stripe_size; sector_t first_stripe_index, last_stripe_index; sector_t start_disk_offset; unsigned int start_disk_index; sector_t end_disk_offset; unsigned int end_disk_index; unsigned int disk; sector_t orig_start, orig_end; orig_start = start; zone = find_zone(conf, &start); if (bio_end_sector(bio) > zone->zone_end) { bio = bio_submit_split_bioset(bio, zone->zone_end - bio->bi_iter.bi_sector, &mddev->bio_set); if (!bio) return; end = zone->zone_end; } else { end = bio_end_sector(bio); } orig_end = end; if (zone != conf->strip_zone) end = end - zone[-1].zone_end; /* Now start and end is the offset in zone */ stripe_size = zone->nb_dev * mddev->chunk_sectors; first_stripe_index = start; sector_div(first_stripe_index, stripe_size); last_stripe_index = end; sector_div(last_stripe_index, stripe_size); /* In the first zone the original and alternate layouts are the same */ if ((conf->layout == RAID0_ORIG_LAYOUT) && (zone != conf->strip_zone)) {Lines 1–500 of 844. Load more
// SPDX-License-Identifier: GPL-2.0-or-later /* raid0.c : Multiple Devices driver for Linux Copyright (C) 1994-96 Marc ZYNGIER <zyngier@ufr-info-p7.ibp.fr> or <maz@gloups.fdn.fr> Copyright (C) 1999, 2000 Ingo Molnar, Red Hat RAID-0 management functions. */ #include <linux/blkdev.h> #include <linux/seq_file.h> #include <linux/module.h> #include <linux/slab.h> #include <linux/string_choices.h> #include <trace/events/block.h> #include "md.h" #include "raid0.h" #include "raid5.h" static int default_layout = 0; module_param(default_layout, int, 0644); #define UNSUPPORTED_MDDEV_FLAGS \ ((1L << MD_HAS_JOURNAL) | \ (1L << MD_JOURNAL_CLEAN) | \ (1L << MD_FAILFAST_SUPPORTED) |\ (1L << MD_HAS_PPL) | \ (1L << MD_HAS_MULTIPLE_PPLS) | \ (1L << MD_FAILLAST_DEV) | \ (1L << MD_SERIALIZE_POLICY)) /* * inform the user of the raid configuration */ static void dump_zones(struct mddev *mddev) { int j, k; sector_t zone_size = 0; sector_t zone_start = 0; struct r0conf *conf = mddev->private; int raid_disks = conf->strip_zone[0].nb_dev; pr_debug("md: RAID0 configuration for %s - %d zone%s\n", mdname(mddev), conf->nr_strip_zones, str_plural(conf->nr_strip_zones)); for (j = 0; j < conf->nr_strip_zones; j++) { char line[200]; int len = 0; for (k = 0; k < conf->strip_zone[j].nb_dev; k++) len += scnprintf(line+len, 200-len, "%s%pg", k?"/":"", conf->devlist[j * raid_disks + k]->bdev); pr_debug("md: zone%d=[%s]\n", j, line); zone_size = conf->strip_zone[j].zone_end - zone_start; pr_debug(" zone-offset=%10lluKB, device-offset=%10lluKB, size=%10lluKB\n", (unsigned long long)zone_start>>1, (unsigned long long)conf->strip_zone[j].dev_start>>1, (unsigned long long)zone_size>>1); zone_start = conf->strip_zone[j].zone_end; } } static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf) { int i, c, err; sector_t curr_zone_end, sectors; struct md_rdev *smallest, *rdev1, *rdev2, *rdev, **dev; struct strip_zone *zone; int cnt; struct r0conf *conf = kzalloc_obj(*conf); unsigned int blksize = 512; if (!mddev_is_dm(mddev)) blksize = queue_logical_block_size(mddev->gendisk->queue); *private_conf = ERR_PTR(-ENOMEM); if (!conf) return -ENOMEM; rdev_for_each(rdev1, mddev) { pr_debug("md/raid0:%s: looking at %pg\n", mdname(mddev), rdev1->bdev); c = 0; /* round size to chunk_size */ sectors = rdev1->sectors; sector_div(sectors, mddev->chunk_sectors); rdev1->sectors = sectors * mddev->chunk_sectors; if (mddev_is_dm(mddev)) blksize = max(blksize, queue_logical_block_size( rdev1->bdev->bd_disk->queue)); rdev_for_each(rdev2, mddev) { pr_debug("md/raid0:%s: comparing %pg(%llu)" " with %pg(%llu)\n", mdname(mddev), rdev1->bdev, (unsigned long long)rdev1->sectors, rdev2->bdev, (unsigned long long)rdev2->sectors); if (rdev2 == rdev1) { pr_debug("md/raid0:%s: END\n", mdname(mddev)); break; } if (rdev2->sectors == rdev1->sectors) { /* * Not unique, don't count it as a new * group */ pr_debug("md/raid0:%s: EQUAL\n", mdname(mddev)); c = 1; break; } pr_debug("md/raid0:%s: NOT EQUAL\n", mdname(mddev)); } if (!c) { pr_debug("md/raid0:%s: ==> UNIQUE\n", mdname(mddev)); conf->nr_strip_zones++; pr_debug("md/raid0:%s: %d zones\n", mdname(mddev), conf->nr_strip_zones); } } pr_debug("md/raid0:%s: FINAL %d zones\n", mdname(mddev), conf->nr_strip_zones); /* * now since we have the hard sector sizes, we can make sure * chunk size is a multiple of that sector size */ if ((mddev->chunk_sectors << 9) % blksize) { pr_warn("md/raid0:%s: chunk_size of %d not multiple of block size %d\n", mdname(mddev), mddev->chunk_sectors << 9, blksize); err = -EINVAL; goto abort; } err = -ENOMEM; conf->strip_zone = kvzalloc_objs(struct strip_zone, conf->nr_strip_zones); if (!conf->strip_zone) goto abort; conf->devlist = kvzalloc(array3_size(sizeof(struct md_rdev *), conf->nr_strip_zones, mddev->raid_disks), GFP_KERNEL); if (!conf->devlist) goto abort; /* The first zone must contain all devices, so here we check that * there is a proper alignment of slots to devices and find them all */ zone = &conf->strip_zone[0]; cnt = 0; smallest = NULL; dev = conf->devlist; err = -EINVAL; rdev_for_each(rdev1, mddev) { int j = rdev1->raid_disk; if (mddev->level == 10) { /* taking over a raid10-n2 array */ j /= 2; rdev1->new_raid_disk = j; } if (mddev->level == 1) { /* taiking over a raid1 array- * we have only one active disk */ j = 0; rdev1->new_raid_disk = j; } if (j < 0) { pr_warn("md/raid0:%s: remove inactive devices before converting to RAID0\n", mdname(mddev)); goto abort; } if (j >= mddev->raid_disks) { pr_warn("md/raid0:%s: bad disk number %d - aborting!\n", mdname(mddev), j); goto abort; } if (dev[j]) { pr_warn("md/raid0:%s: multiple devices for %d - aborting!\n", mdname(mddev), j); goto abort; } dev[j] = rdev1; if (!smallest || (rdev1->sectors < smallest->sectors)) smallest = rdev1; cnt++; } if (cnt != mddev->raid_disks) { pr_warn("md/raid0:%s: too few disks (%d of %d) - aborting!\n", mdname(mddev), cnt, mddev->raid_disks); goto abort; } zone->nb_dev = cnt; zone->zone_end = smallest->sectors * cnt; curr_zone_end = zone->zone_end; /* now do the other zones */ for (i = 1; i < conf->nr_strip_zones; i++) { int j; zone = conf->strip_zone + i; dev = conf->devlist + i * mddev->raid_disks; pr_debug("md/raid0:%s: zone %d\n", mdname(mddev), i); zone->dev_start = smallest->sectors; smallest = NULL; c = 0; for (j=0; j<cnt; j++) { rdev = conf->devlist[j]; if (rdev->sectors <= zone->dev_start) { pr_debug("md/raid0:%s: checking %pg ... nope\n", mdname(mddev), rdev->bdev); continue; } pr_debug("md/raid0:%s: checking %pg ..." " contained as device %d\n", mdname(mddev), rdev->bdev, c); dev[c] = rdev; c++; if (!smallest || rdev->sectors < smallest->sectors) { smallest = rdev; pr_debug("md/raid0:%s: (%llu) is smallest!.\n", mdname(mddev), (unsigned long long)rdev->sectors); } } zone->nb_dev = c; sectors = (smallest->sectors - zone->dev_start) * c; pr_debug("md/raid0:%s: zone->nb_dev: %d, sectors: %llu\n", mdname(mddev), zone->nb_dev, (unsigned long long)sectors); curr_zone_end += sectors; zone->zone_end = curr_zone_end; pr_debug("md/raid0:%s: current zone start: %llu\n", mdname(mddev), (unsigned long long)smallest->sectors); } if (conf->nr_strip_zones == 1 || conf->strip_zone[1].nb_dev == 1) { conf->layout = RAID0_ORIG_LAYOUT; } else if (mddev->layout == RAID0_ORIG_LAYOUT || mddev->layout == RAID0_ALT_MULTIZONE_LAYOUT) { conf->layout = mddev->layout; } else if (default_layout == RAID0_ORIG_LAYOUT || default_layout == RAID0_ALT_MULTIZONE_LAYOUT) { conf->layout = default_layout; } else { pr_err("md/raid0:%s: cannot assemble multi-zone RAID0 with default_layout setting\n", mdname(mddev)); pr_err("md/raid0: please set raid0.default_layout to 1 or 2\n"); err = -EOPNOTSUPP; goto abort; } if (conf->layout == RAID0_ORIG_LAYOUT) { for (i = 1; i < conf->nr_strip_zones; i++) { sector_t first_sector = conf->strip_zone[i-1].zone_end; sector_div(first_sector, mddev->chunk_sectors); zone = conf->strip_zone + i; /* disk_shift is first disk index used in the zone */ zone->disk_shift = sector_div(first_sector, zone->nb_dev); } } pr_debug("md/raid0:%s: done.\n", mdname(mddev)); *private_conf = conf; return 0; abort: kvfree(conf->strip_zone); kvfree(conf->devlist); kfree(conf); *private_conf = ERR_PTR(err); return err; } /* Find the zone which holds a particular offset * Update *sectorp to be an offset in that zone */ static struct strip_zone *find_zone(struct r0conf *conf, sector_t *sectorp) { int i; struct strip_zone *z = conf->strip_zone; sector_t sector = *sectorp; for (i = 0; i < conf->nr_strip_zones; i++) if (sector < z[i].zone_end) { if (i) *sectorp = sector - z[i-1].zone_end; return z + i; } BUG(); } /* * remaps the bio to the target device. we separate two flows. * power 2 flow and a general flow for the sake of performance */ static struct md_rdev *map_sector(struct mddev *mddev, struct strip_zone *zone, sector_t sector, sector_t *sector_offset) { unsigned int sect_in_chunk; sector_t chunk; struct r0conf *conf = mddev->private; int raid_disks = conf->strip_zone[0].nb_dev; unsigned int chunk_sects = mddev->chunk_sectors; if (is_power_of_2(chunk_sects)) { int chunksect_bits = ffz(~chunk_sects); /* find the sector offset inside the chunk */ sect_in_chunk = sector & (chunk_sects - 1); sector >>= chunksect_bits; /* chunk in zone */ chunk = *sector_offset; /* quotient is the chunk in real device*/ sector_div(chunk, zone->nb_dev << chunksect_bits); } else{ sect_in_chunk = sector_div(sector, chunk_sects); chunk = *sector_offset; sector_div(chunk, chunk_sects * zone->nb_dev); } /* * position the bio over the real device * real sector = chunk in device + starting of zone * + the position in the chunk */ *sector_offset = (chunk * chunk_sects) + sect_in_chunk; return conf->devlist[(zone - conf->strip_zone)*raid_disks + sector_div(sector, zone->nb_dev)]; } static sector_t raid0_size(struct mddev *mddev, sector_t sectors, int raid_disks) { sector_t array_sectors = 0; struct md_rdev *rdev; WARN_ONCE(sectors || raid_disks, "%s does not support generic reshape\n", __func__); rdev_for_each(rdev, mddev) array_sectors += (rdev->sectors & ~(sector_t)(mddev->chunk_sectors-1)); return array_sectors; } static void raid0_free(struct mddev *mddev, void *priv) { struct r0conf *conf = priv; kvfree(conf->strip_zone); kvfree(conf->devlist); kfree(conf); } static int raid0_set_limits(struct mddev *mddev) { struct queue_limits lim; int err; md_init_stacking_limits(&lim); lim.features |= BLK_FEAT_NOWAIT; lim.max_hw_sectors = mddev->chunk_sectors; lim.max_write_zeroes_sectors = mddev->chunk_sectors; lim.max_hw_wzeroes_unmap_sectors = mddev->chunk_sectors; lim.logical_block_size = mddev->logical_block_size; lim.io_min = mddev->chunk_sectors << 9; lim.io_opt = lim.io_min * mddev->raid_disks; lim.chunk_sectors = mddev->chunk_sectors; lim.features |= BLK_FEAT_ATOMIC_WRITES; lim.features |= BLK_FEAT_PCI_P2PDMA; err = mddev_stack_rdev_limits(mddev, &lim, MDDEV_STACK_INTEGRITY); if (err) return err; return queue_limits_set(mddev->gendisk->queue, &lim); } static int raid0_run(struct mddev *mddev) { struct r0conf *conf; int ret; if (mddev->chunk_sectors == 0) { pr_warn("md/raid0:%s: chunk size must be set.\n", mdname(mddev)); return -EINVAL; } if (md_check_no_bitmap(mddev)) return -EINVAL; if (!mddev_is_dm(mddev)) { ret = raid0_set_limits(mddev); if (ret) return ret; } /* if private is not null, we are here after takeover */ if (mddev->private == NULL) { ret = create_strip_zones(mddev, &conf); if (ret < 0) return ret; mddev->private = conf; } conf = mddev->private; /* calculate array device size */ md_set_array_sectors(mddev, raid0_size(mddev, 0, 0)); pr_debug("md/raid0:%s: md_size is %llu sectors.\n", mdname(mddev), (unsigned long long)mddev->array_sectors); dump_zones(mddev); return md_integrity_register(mddev); } /* * Convert disk_index to the disk order in which it is read/written. * For example, if we have 4 disks, they are numbered 0,1,2,3. If we * write the disks starting at disk 3, then the read/write order would * be disk 3, then 0, then 1, and then disk 2 and we want map_disk_shift() * to map the disks as follows 0,1,2,3 => 1,2,3,0. So disk 0 would map * to 1, 1 to 2, 2 to 3, and 3 to 0. That way we can compare disks in * that 'output' space to understand the read/write disk ordering. */ static int map_disk_shift(int disk_index, int num_disks, int disk_shift) { return ((disk_index + num_disks - disk_shift) % num_disks); } static void raid0_handle_discard(struct mddev *mddev, struct bio *bio) { struct r0conf *conf = mddev->private; struct strip_zone *zone; sector_t start = bio->bi_iter.bi_sector; sector_t end; unsigned int stripe_size; sector_t first_stripe_index, last_stripe_index; sector_t start_disk_offset; unsigned int start_disk_index; sector_t end_disk_offset; unsigned int end_disk_index; unsigned int disk; sector_t orig_start, orig_end; orig_start = start; zone = find_zone(conf, &start); if (bio_end_sector(bio) > zone->zone_end) { bio = bio_submit_split_bioset(bio, zone->zone_end - bio->bi_iter.bi_sector, &mddev->bio_set); if (!bio) return; end = zone->zone_end; } else { end = bio_end_sector(bio); } orig_end = end; if (zone != conf->strip_zone) end = end - zone[-1].zone_end; /* Now start and end is the offset in zone */ stripe_size = zone->nb_dev * mddev->chunk_sectors; first_stripe_index = start; sector_div(first_stripe_index, stripe_size); last_stripe_index = end; sector_div(last_stripe_index, stripe_size); /* In the first zone the original and alternate layouts are the same */ if ((conf->layout == RAID0_ORIG_LAYOUT) && (zone != conf->strip_zone)) {