diff options
Diffstat (limited to 'drivers/md')
34 files changed, 1411 insertions, 840 deletions
diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig index acb3a4e404ff..4a6feac8c94a 100644 --- a/drivers/md/Kconfig +++ b/drivers/md/Kconfig @@ -100,8 +100,8 @@ config MD_RAID1 If unsure, say Y. config MD_RAID10 - tristate "RAID-10 (mirrored striping) mode (EXPERIMENTAL)" - depends on BLK_DEV_MD && EXPERIMENTAL + tristate "RAID-10 (mirrored striping) mode" + depends on BLK_DEV_MD ---help--- RAID-10 provides a combination of striping (RAID-0) and mirroring (RAID-1) with easier configuration and more flexible diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c index 26ac8aad0b19..1742435ce3ae 100644 --- a/drivers/md/bitmap.c +++ b/drivers/md/bitmap.c @@ -505,7 +505,7 @@ void bitmap_update_sb(struct bitmap *bitmap) return; } spin_unlock_irqrestore(&bitmap->lock, flags); - sb = (bitmap_super_t *)kmap_atomic(bitmap->sb_page, KM_USER0); + sb = kmap_atomic(bitmap->sb_page, KM_USER0); sb->events = cpu_to_le64(bitmap->mddev->events); if (bitmap->mddev->events < bitmap->events_cleared) { /* rocking back to read-only */ @@ -526,7 +526,7 @@ void bitmap_print_sb(struct bitmap *bitmap) if (!bitmap || !bitmap->sb_page) return; - sb = (bitmap_super_t *)kmap_atomic(bitmap->sb_page, KM_USER0); + sb = kmap_atomic(bitmap->sb_page, KM_USER0); printk(KERN_DEBUG "%s: bitmap file superblock:\n", bmname(bitmap)); printk(KERN_DEBUG " magic: %08x\n", le32_to_cpu(sb->magic)); printk(KERN_DEBUG " version: %d\n", le32_to_cpu(sb->version)); @@ -575,7 +575,7 @@ static int bitmap_read_sb(struct bitmap *bitmap) return err; } - sb = (bitmap_super_t *)kmap_atomic(bitmap->sb_page, KM_USER0); + sb = kmap_atomic(bitmap->sb_page, KM_USER0); chunksize = le32_to_cpu(sb->chunksize); daemon_sleep = le32_to_cpu(sb->daemon_sleep) * HZ; @@ -661,7 +661,7 @@ static int bitmap_mask_state(struct bitmap *bitmap, enum bitmap_state bits, return 0; } spin_unlock_irqrestore(&bitmap->lock, flags); - sb = (bitmap_super_t *)kmap_atomic(bitmap->sb_page, KM_USER0); + sb = kmap_atomic(bitmap->sb_page, KM_USER0); old = le32_to_cpu(sb->state) & bits; switch (op) { case MASK_SET: sb->state |= cpu_to_le32(bits); @@ -1292,9 +1292,14 @@ int bitmap_startwrite(struct bitmap *bitmap, sector_t offset, unsigned long sect if (!bitmap) return 0; if (behind) { + int bw; atomic_inc(&bitmap->behind_writes); + bw = atomic_read(&bitmap->behind_writes); + if (bw > bitmap->behind_writes_used) + bitmap->behind_writes_used = bw; + PRINTK(KERN_DEBUG "inc write-behind count %d/%d\n", - atomic_read(&bitmap->behind_writes), bitmap->max_write_behind); + bw, bitmap->max_write_behind); } while (sectors) { @@ -1351,7 +1356,8 @@ void bitmap_endwrite(struct bitmap *bitmap, sector_t offset, unsigned long secto { if (!bitmap) return; if (behind) { - atomic_dec(&bitmap->behind_writes); + if (atomic_dec_and_test(&bitmap->behind_writes)) + wake_up(&bitmap->behind_wait); PRINTK(KERN_DEBUG "dec write-behind count %d/%d\n", atomic_read(&bitmap->behind_writes), bitmap->max_write_behind); } @@ -1675,12 +1681,13 @@ int bitmap_create(mddev_t *mddev) atomic_set(&bitmap->pending_writes, 0); init_waitqueue_head(&bitmap->write_wait); init_waitqueue_head(&bitmap->overflow_wait); + init_waitqueue_head(&bitmap->behind_wait); bitmap->mddev = mddev; - bm = sysfs_get_dirent(mddev->kobj.sd, "bitmap"); + bm = sysfs_get_dirent(mddev->kobj.sd, NULL, "bitmap"); if (bm) { - bitmap->sysfs_can_clear = sysfs_get_dirent(bm, "can_clear"); + bitmap->sysfs_can_clear = sysfs_get_dirent(bm, NULL, "can_clear"); sysfs_put(bm); } else bitmap->sysfs_can_clear = NULL; @@ -1692,7 +1699,7 @@ int bitmap_create(mddev_t *mddev) * and bypass the page cache, we must sync the file * first. */ - vfs_fsync(file, file->f_dentry, 1); + vfs_fsync(file, 1); } /* read superblock from bitmap file (this sets mddev->bitmap_info.chunksize) */ if (!mddev->bitmap_info.external) @@ -2006,6 +2013,27 @@ static ssize_t can_clear_store(mddev_t *mddev, const char *buf, size_t len) static struct md_sysfs_entry bitmap_can_clear = __ATTR(can_clear, S_IRUGO|S_IWUSR, can_clear_show, can_clear_store); +static ssize_t +behind_writes_used_show(mddev_t *mddev, char *page) +{ + if (mddev->bitmap == NULL) + return sprintf(page, "0\n"); + return sprintf(page, "%lu\n", + mddev->bitmap->behind_writes_used); +} + +static ssize_t +behind_writes_used_reset(mddev_t *mddev, const char *buf, size_t len) +{ + if (mddev->bitmap) + mddev->bitmap->behind_writes_used = 0; + return len; +} + +static struct md_sysfs_entry max_backlog_used = +__ATTR(max_backlog_used, S_IRUGO | S_IWUSR, + behind_writes_used_show, behind_writes_used_reset); + static struct attribute *md_bitmap_attrs[] = { &bitmap_location.attr, &bitmap_timeout.attr, @@ -2013,6 +2041,7 @@ static struct attribute *md_bitmap_attrs[] = { &bitmap_chunksize.attr, &bitmap_metadata.attr, &bitmap_can_clear.attr, + &max_backlog_used.attr, NULL }; struct attribute_group md_bitmap_group = { diff --git a/drivers/md/bitmap.h b/drivers/md/bitmap.h index cb821d76d1b4..3797dea4723a 100644 --- a/drivers/md/bitmap.h +++ b/drivers/md/bitmap.h @@ -227,6 +227,7 @@ struct bitmap { int allclean; atomic_t behind_writes; + unsigned long behind_writes_used; /* highest actual value at runtime */ /* * the bitmap daemon - periodically wakes up and sweeps the bitmap @@ -239,6 +240,7 @@ struct bitmap { atomic_t pending_writes; /* pending writes to the bitmap file */ wait_queue_head_t write_wait; wait_queue_head_t overflow_wait; + wait_queue_head_t behind_wait; struct sysfs_dirent *sysfs_can_clear; }; diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index a93637223c8d..3bdbb6115702 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -1160,8 +1160,7 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv) } cc->start = tmpll; - if (dm_get_device(ti, argv[3], cc->start, ti->len, - dm_table_get_mode(ti->table), &cc->dev)) { + if (dm_get_device(ti, argv[3], dm_table_get_mode(ti->table), &cc->dev)) { ti->error = "Device lookup failed"; goto bad_device; } diff --git a/drivers/md/dm-delay.c b/drivers/md/dm-delay.c index ebe7381f47c8..852052880d7a 100644 --- a/drivers/md/dm-delay.c +++ b/drivers/md/dm-delay.c @@ -156,8 +156,8 @@ static int delay_ctr(struct dm_target *ti, unsigned int argc, char **argv) goto bad; } - if (dm_get_device(ti, argv[0], dc->start_read, ti->len, - dm_table_get_mode(ti->table), &dc->dev_read)) { + if (dm_get_device(ti, argv[0], dm_table_get_mode(ti->table), + &dc->dev_read)) { ti->error = "Device lookup failed"; goto bad; } @@ -177,8 +177,8 @@ static int delay_ctr(struct dm_target *ti, unsigned int argc, char **argv) goto bad_dev_read; } - if (dm_get_device(ti, argv[3], dc->start_write, ti->len, - dm_table_get_mode(ti->table), &dc->dev_write)) { + if (dm_get_device(ti, argv[3], dm_table_get_mode(ti->table), + &dc->dev_write)) { ti->error = "Write device lookup failed"; goto bad_dev_read; } diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c index 1d669322b27c..d7500e1c26f2 100644 --- a/drivers/md/dm-ioctl.c +++ b/drivers/md/dm-ioctl.c @@ -285,7 +285,8 @@ retry: up_write(&_hash_lock); } -static int dm_hash_rename(uint32_t cookie, const char *old, const char *new) +static int dm_hash_rename(uint32_t cookie, uint32_t *flags, const char *old, + const char *new) { char *new_name, *old_name; struct hash_cell *hc; @@ -344,7 +345,8 @@ static int dm_hash_rename(uint32_t cookie, const char *old, const char *new) dm_table_put(table); } - dm_kobject_uevent(hc->md, KOBJ_CHANGE, cookie); + if (!dm_kobject_uevent(hc->md, KOBJ_CHANGE, cookie)) + *flags |= DM_UEVENT_GENERATED_FLAG; dm_put(hc->md); up_write(&_hash_lock); @@ -736,10 +738,10 @@ static int dev_remove(struct dm_ioctl *param, size_t param_size) __hash_remove(hc); up_write(&_hash_lock); - dm_kobject_uevent(md, KOBJ_REMOVE, param->event_nr); + if (!dm_kobject_uevent(md, KOBJ_REMOVE, param->event_nr)) + param->flags |= DM_UEVENT_GENERATED_FLAG; dm_put(md); - param->data_size = 0; return 0; } @@ -773,7 +775,9 @@ static int dev_rename(struct dm_ioctl *param, size_t param_size) return r; param->data_size = 0; - return dm_hash_rename(param->event_nr, param->name, new_name); + + return dm_hash_rename(param->event_nr, ¶m->flags, param->name, + new_name); } static int dev_set_geometry(struct dm_ioctl *param, size_t param_size) @@ -897,16 +901,17 @@ static int do_resume(struct dm_ioctl *param) set_disk_ro(dm_disk(md), 1); } - if (dm_suspended_md(md)) + if (dm_suspended_md(md)) { r = dm_resume(md); + if (!r && !dm_kobject_uevent(md, KOBJ_CHANGE, param->event_nr)) + param->flags |= DM_UEVENT_GENERATED_FLAG; + } if (old_map) dm_table_destroy(old_map); - if (!r) { - dm_kobject_uevent(md, KOBJ_CHANGE, param->event_nr); + if (!r) r = __dev_status(md, param); - } dm_put(md); return r; @@ -1476,6 +1481,7 @@ static int validate_params(uint cmd, struct dm_ioctl *param) { /* Always clear this flag */ param->flags &= ~DM_BUFFER_FULL_FLAG; + param->flags &= ~DM_UEVENT_GENERATED_FLAG; /* Ignores parameters */ if (cmd == DM_REMOVE_ALL_CMD || diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c index 82f7d6e6b1ea..9200dbf2391a 100644 --- a/drivers/md/dm-linear.c +++ b/drivers/md/dm-linear.c @@ -47,8 +47,7 @@ static int linear_ctr(struct dm_target *ti, unsigned int argc, char **argv) } lc->start = tmp; - if (dm_get_device(ti, argv[0], lc->start, ti->len, - dm_table_get_mode(ti->table), &lc->dev)) { + if (dm_get_device(ti, argv[0], dm_table_get_mode(ti->table), &lc->dev)) { ti->error = "dm-linear: Device lookup failed"; goto bad; } diff --git a/drivers/md/dm-log-userspace-base.c b/drivers/md/dm-log-userspace-base.c index 7ac2c1450d10..1ed0094f064b 100644 --- a/drivers/md/dm-log-userspace-base.c +++ b/drivers/md/dm-log-userspace-base.c @@ -5,6 +5,7 @@ */ #include <linux/bio.h> +#include <linux/slab.h> #include <linux/dm-dirty-log.h> #include <linux/device-mapper.h> #include <linux/dm-log-userspace.h> diff --git a/drivers/md/dm-log-userspace-transfer.c b/drivers/md/dm-log-userspace-transfer.c index f1c8cae70b4b..075cbcf8a9f5 100644 --- a/drivers/md/dm-log-userspace-transfer.c +++ b/drivers/md/dm-log-userspace-transfer.c @@ -6,6 +6,7 @@ #include <linux/kernel.h> #include <linux/module.h> +#include <linux/slab.h> #include <net/sock.h> #include <linux/workqueue.h> #include <linux/connector.h> diff --git a/drivers/md/dm-log.c b/drivers/md/dm-log.c index 7035582786fb..5a08be0222db 100644 --- a/drivers/md/dm-log.c +++ b/drivers/md/dm-log.c @@ -543,8 +543,7 @@ static int disk_ctr(struct dm_dirty_log *log, struct dm_target *ti, return -EINVAL; } - r = dm_get_device(ti, argv[0], 0, 0 /* FIXME */, - FMODE_READ | FMODE_WRITE, &dev); + r = dm_get_device(ti, argv[0], FMODE_READ | FMODE_WRITE, &dev); if (r) return r; diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c index e81345a1d08f..826bce7343b3 100644 --- a/drivers/md/dm-mpath.c +++ b/drivers/md/dm-mpath.c @@ -69,6 +69,7 @@ struct multipath { struct list_head priority_groups; unsigned pg_init_required; /* pg_init needs calling? */ unsigned pg_init_in_progress; /* Only one pg_init allowed at once */ + wait_queue_head_t pg_init_wait; /* Wait for pg_init completion */ unsigned nr_valid_paths; /* Total number of usable paths */ struct pgpath *current_pgpath; @@ -95,8 +96,6 @@ struct multipath { mempool_t *mpio_pool; struct mutex work_mutex; - - unsigned suspended; /* Don't create new I/O internally when set. */ }; /* @@ -202,6 +201,7 @@ static struct multipath *alloc_multipath(struct dm_target *ti) m->queue_io = 1; INIT_WORK(&m->process_queued_ios, process_queued_ios); INIT_WORK(&m->trigger_event, trigger_event); + init_waitqueue_head(&m->pg_init_wait); mutex_init(&m->work_mutex); m->mpio_pool = mempool_create_slab_pool(MIN_IOS, _mpio_cache); if (!m->mpio_pool) { @@ -235,6 +235,21 @@ static void free_multipath(struct multipath *m) * Path selection *-----------------------------------------------*/ +static void __pg_init_all_paths(struct multipath *m) +{ + struct pgpath *pgpath; + + m->pg_init_count++; + m->pg_init_required = 0; + list_for_each_entry(pgpath, &m->current_pg->pgpaths, list) { + /* Skip failed paths */ + if (!pgpath->is_active) + continue; + if (queue_work(kmpath_handlerd, &pgpath->activate_path)) + m->pg_init_in_progress++; + } +} + static void __switch_pg(struct multipath *m, struct pgpath *pgpath) { m->current_pg = pgpath->pg; @@ -439,7 +454,7 @@ static void process_queued_ios(struct work_struct *work) { struct multipath *m = container_of(work, struct multipath, process_queued_ios); - struct pgpath *pgpath = NULL, *tmp; + struct pgpath *pgpath = NULL; unsigned must_queue = 1; unsigned long flags; @@ -457,14 +472,9 @@ static void process_queued_ios(struct work_struct *work) (!pgpath && !m->queue_if_no_path)) must_queue = 0; - if (m->pg_init_required && !m->pg_init_in_progress && pgpath) { - m->pg_init_count++; - m->pg_init_required = 0; - list_for_each_entry(tmp, &pgpath->pg->pgpaths, list) { - if (queue_work(kmpath_handlerd, &tmp->activate_path)) - m->pg_init_in_progress++; - } - } + if (m->pg_init_required && !m->pg_init_in_progress && pgpath) + __pg_init_all_paths(m); + out: spin_unlock_irqrestore(&m->lock, flags); if (!must_queue) @@ -597,8 +607,8 @@ static struct pgpath *parse_path(struct arg_set *as, struct path_selector *ps, if (!p) return ERR_PTR(-ENOMEM); - r = dm_get_device(ti, shift(as), ti->begin, ti->len, - dm_table_get_mode(ti->table), &p->path.dev); + r = dm_get_device(ti, shift(as), dm_table_get_mode(ti->table), + &p->path.dev); if (r) { ti->error = "error getting device"; goto bad; @@ -890,9 +900,34 @@ static int multipath_ctr(struct dm_target *ti, unsigned int argc, return r; } -static void flush_multipath_work(void) +static void multipath_wait_for_pg_init_completion(struct multipath *m) +{ + DECLARE_WAITQUEUE(wait, current); + unsigned long flags; + + add_wait_queue(&m->pg_init_wait, &wait); + + while (1) { + set_current_state(TASK_UNINTERRUPTIBLE); + + spin_lock_irqsave(&m->lock, flags); + if (!m->pg_init_in_progress) { + spin_unlock_irqrestore(&m->lock, flags); + break; + } + spin_unlock_irqrestore(&m->lock, flags); + + io_schedule(); + } + set_current_state(TASK_RUNNING); + + remove_wait_queue(&m->pg_init_wait, &wait); +} + +static void flush_multipath_work(struct multipath *m) { flush_workqueue(kmpath_handlerd); + multipath_wait_for_pg_init_completion(m); flush_workqueue(kmultipathd); flush_scheduled_work(); } @@ -901,7 +936,7 @@ static void multipath_dtr(struct dm_target *ti) { struct multipath *m = ti->private; - flush_multipath_work(); + flush_multipath_work(m); free_multipath(m); } @@ -1128,8 +1163,7 @@ static int pg_init_limit_reached(struct multipath *m, struct pgpath *pgpath) static void pg_init_done(void *data, int errors) { - struct dm_path *path = data; - struct pgpath *pgpath = path_to_pgpath(path); + struct pgpath *pgpath = data; struct priority_group *pg = pgpath->pg; struct multipath *m = pg->m; unsigned long flags; @@ -1143,8 +1177,8 @@ static void pg_init_done(void *data, int errors) errors = 0; break; } - DMERR("Cannot failover device because scsi_dh_%s was not " - "loaded.", m->hw_handler_name); + DMERR("Could not failover the device: Handler scsi_dh_%s " + "Error %d.", m->hw_handler_name, errors); /* * Fail path for now, so we do not ping pong */ @@ -1181,14 +1215,24 @@ static void pg_init_done(void *data, int errors) m->current_pgpath = NULL; m->current_pg = NULL; } - } else if (!m->pg_init_required) { - m->queue_io = 0; + } else if (!m->pg_init_required) pg->bypassed = 0; - } - m->pg_init_in_progress--; - if (!m->pg_init_in_progress) - queue_work(kmultipathd, &m->process_queued_ios); + if (--m->pg_init_in_progress) + /* Activations of other paths are still on going */ + goto out; + + if (!m->pg_init_required) + m->queue_io = 0; + + queue_work(kmultipathd, &m->process_queued_ios); + + /* + * Wake up any thread waiting to suspend. + */ + wake_up(&m->pg_init_wait); + +out: spin_unlock_irqrestore(&m->lock, flags); } @@ -1198,7 +1242,7 @@ static void activate_path(struct work_struct *work) container_of(work, struct pgpath, activate_path); scsi_dh_activate(bdev_get_queue(pgpath->path.dev->bdev), - pg_init_done, &pgpath->path); + pg_init_done, pgpath); } /* @@ -1276,8 +1320,7 @@ static void multipath_postsuspend(struct dm_target *ti) struct multipath *m = ti->private; mutex_lock(&m->work_mutex); - m->suspended = 1; - flush_multipath_work(); + flush_multipath_work(m); mutex_unlock(&m->work_mutex); } @@ -1289,10 +1332,6 @@ static void multipath_resume(struct dm_target *ti) struct multipath *m = (struct multipath *) ti->private; unsigned long flags; - mutex_lock(&m->work_mutex); - m->suspended = 0; - mutex_unlock(&m->work_mutex); - spin_lock_irqsave(&m->lock, flags); m->queue_if_no_path = m->saved_queue_if_no_path; spin_unlock_irqrestore(&m->lock, flags); @@ -1428,11 +1467,6 @@ static int multipath_message(struct dm_target *ti, unsigned argc, char **argv) mutex_lock(&m->work_mutex); - if (m->suspended) { - r = -EBUSY; - goto out; - } - if (dm_suspended(ti)) { r = -EBUSY; goto out; @@ -1471,8 +1505,7 @@ static int multipath_message(struct dm_target *ti, unsigned argc, char **argv) goto out; } - r = dm_get_device(ti, argv[1], ti->begin, ti->len, - dm_table_get_mode(ti->table), &dev); + r = dm_get_device(ti, argv[1], dm_table_get_mode(ti->table), &dev); if (r) { DMWARN("message: error getting device %s", argv[1]); diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c index 6c1046df81f6..ddda531723dc 100644 --- a/drivers/md/dm-raid1.c +++ b/drivers/md/dm-raid1.c @@ -465,9 +465,17 @@ static void map_region(struct dm_io_region *io, struct mirror *m, static void hold_bio(struct mirror_set *ms, struct bio *bio) { /* - * If device is suspended, complete the bio. + * Lock is required to avoid race condition during suspend + * process. */ + spin_lock_irq(&ms->lock); + if (atomic_read(&ms->suspend)) { + spin_unlock_irq(&ms->lock); + + /* + * If device is suspended, complete the bio. + */ if (dm_noflush_suspending(ms->ti)) bio_endio(bio, DM_ENDIO_REQUEUE); else @@ -478,7 +486,6 @@ static void hold_bio(struct mirror_set *ms, struct bio *bio) /* * Hold bio until the suspend is complete. */ - spin_lock_irq(&ms->lock); bio_list_add(&ms->holds, bio); spin_unlock_irq(&ms->lock); } @@ -737,9 +744,12 @@ static void do_writes(struct mirror_set *ms, struct bio_list *writes) dm_rh_delay(ms->rh, bio); while ((bio = bio_list_pop(&nosync))) { - if (unlikely(ms->leg_failure) && errors_handled(ms)) - hold_bio(ms, bio); - else { + if (unlikely(ms->leg_failure) && errors_handled(ms)) { + spin_lock_irq(&ms->lock); + bio_list_add(&ms->failures, bio); + spin_unlock_irq(&ms->lock); + wakeup_mirrord(ms); + } else { map_bio(get_default_mirror(ms), bio); generic_make_request(bio); } @@ -917,8 +927,7 @@ static int get_mirror(struct mirror_set *ms, struct dm_target *ti, return -EINVAL; } - if (dm_get_device(ti, argv[0], offset, ti->len, - dm_table_get_mode(ti->table), + if (dm_get_device(ti, argv[0], dm_table_get_mode(ti->table), &ms->mirror[mirror].dev)) { ti->error = "Device lookup failure"; return -ENXIO; @@ -1259,6 +1268,20 @@ static void mirror_presuspend(struct dm_target *ti) atomic_set(&ms->suspend, 1); /* + * Process bios in the hold list to start recovery waiting + * for bios in the hold list. After the process, no bio has + * a chance to be added in the hold list because ms->suspend + * is set. + */ + spin_lock_irq(&ms->lock); + holds = ms->holds; + bio_list_init(&ms->holds); + spin_unlock_irq(&ms->lock); + + while ((bio = bio_list_pop(&holds))) + hold_bio(ms, bio); + + /* * We must finish up all the work that we've * generated (i.e. recovery work). */ @@ -1278,22 +1301,6 @@ static void mirror_presuspend(struct dm_target *ti) * we know that all of our I/O has been pushed. */ flush_workqueue(ms->kmirrord_wq); - - /* - * Now set ms->suspend is set and the workqueue flushed, no more - * entries can be added to ms->hold list, so process it. - * - * Bios can still arrive concurrently with or after this - * presuspend function, but they cannot join the hold list - * because ms->suspend is set. - */ - spin_lock_irq(&ms->lock); - holds = ms->holds; - bio_list_init(&ms->holds); - spin_unlock_irq(&ms->lock); - - while ((bio = bio_list_pop(&holds))) - hold_bio(ms, bio); } static void mirror_postsuspend(struct dm_target *ti) diff --git a/drivers/md/dm-region-hash.c b/drivers/md/dm-region-hash.c index 168bd38f5006..bd5c58b28868 100644 --- a/drivers/md/dm-region-hash.c +++ b/drivers/md/dm-region-hash.c @@ -11,6 +11,7 @@ #include <linux/ctype.h> #include <linux/init.h> #include <linux/module.h> +#include <linux/slab.h> #include <linux/vmalloc.h> #include "dm.h" diff --git a/drivers/md/dm-service-time.c b/drivers/md/dm-service-time.c index cfa668f46c40..9c6c2e47ad62 100644 --- a/drivers/md/dm-service-time.c +++ b/drivers/md/dm-service-time.c @@ -11,6 +11,8 @@ #include "dm.h" #include "dm-path-selector.h" +#include <linux/slab.h> + #define DM_MSG_PREFIX "multipath service-time" #define ST_MIN_IO 1 #define ST_MAX_RELATIVE_THROUGHPUT 100 diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c index ee8eb283650d..54853773510c 100644 --- a/drivers/md/dm-snap.c +++ b/drivers/md/dm-snap.c @@ -83,10 +83,10 @@ struct dm_snapshot { /* Whether or not owning mapped_device is suspended */ int suspended; - mempool_t *pending_pool; - atomic_t pending_exceptions_count; + mempool_t *pending_pool; + struct dm_exception_table pending; struct dm_exception_table complete; @@ -96,6 +96,11 @@ struct dm_snapshot { */ spinlock_t pe_lock; + /* Chunks with outstanding reads */ + spinlock_t tracked_chunk_lock; + mempool_t *tracked_chunk_pool; + struct hlist_head tracked_chunk_hash[DM_TRACKED_CHUNK_HASH_SIZE]; + /* The on disk metadata handler */ struct dm_exception_store *store; @@ -105,10 +110,12 @@ struct dm_snapshot { struct bio_list queued_bios; struct work_struct queued_bios_work; - /* Chunks with outstanding reads */ - mempool_t *tracked_chunk_pool; - spinlock_t tracked_chunk_lock; - struct hlist_head tracked_chunk_hash[DM_TRACKED_CHUNK_HASH_SIZE]; + /* Wait for events based on state_bits */ + unsigned long state_bits; + + /* Range of chunks currently being merged. */ + chunk_t first_merging_chunk; + int num_merging_chunks; /* * The merge operation failed if this flag is set. @@ -125,13 +132,6 @@ struct dm_snapshot { */ int merge_failed; - /* Wait for events based on state_bits */ - unsigned long state_bits; - - /* Range of chunks currently being merged. */ - chunk_t first_merging_chunk; - int num_merging_chunks; - /* * Incoming bios that overlap with chunks being merged must wait * for them to be committed. @@ -1081,8 +1081,7 @@ static int snapshot_ctr(struct dm_target *ti, unsigned int argc, char **argv) argv++; argc--; - r = dm_get_device(ti, cow_path, 0, 0, - FMODE_READ | FMODE_WRITE, &s->cow); + r = dm_get_device(ti, cow_path, FMODE_READ | FMODE_WRITE, &s->cow); if (r) { ti->error = "Cannot get COW device"; goto bad_cow; @@ -1098,7 +1097,7 @@ static int snapshot_ctr(struct dm_target *ti, unsigned int argc, char **argv) argv += args_used; argc -= args_used; - r = dm_get_device(ti, origin_path, 0, ti->len, origin_mode, &s->origin); + r = dm_get_device(ti, origin_path, origin_mode, &s->origin); if (r) { ti->error = "Cannot get origin device"; goto bad_origin; @@ -2100,8 +2099,7 @@ static int origin_ctr(struct dm_target *ti, unsigned int argc, char **argv) return -EINVAL; } - r = dm_get_device(ti, argv[0], 0, ti->len, - dm_table_get_mode(ti->table), &dev); + r = dm_get_device(ti, argv[0], dm_table_get_mode(ti->table), &dev); if (r) { ti->error = "Cannot get target device"; return r; diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c index bd58703ee8f6..e610725db766 100644 --- a/drivers/md/dm-stripe.c +++ b/drivers/md/dm-stripe.c @@ -80,8 +80,7 @@ static int get_stripe(struct dm_target *ti, struct stripe_c *sc, if (sscanf(argv[1], "%llu", &start) != 1) return -EINVAL; - if (dm_get_device(ti, argv[0], start, sc->stripe_width, - dm_table_get_mode(ti->table), + if (dm_get_device(ti, argv[0], dm_table_get_mode(ti->table), &sc->stripe[stripe].dev)) return -ENXIO; diff --git a/drivers/md/dm-sysfs.c b/drivers/md/dm-sysfs.c index f91b40942e07..84d2b91e4efb 100644 --- a/drivers/md/dm-sysfs.c +++ b/drivers/md/dm-sysfs.c @@ -75,7 +75,7 @@ static struct attribute *dm_attrs[] = { NULL, }; -static struct sysfs_ops dm_sysfs_ops = { +static const struct sysfs_ops dm_sysfs_ops = { .show = dm_attr_show, }; diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 4b22feb01a0c..9924ea23032d 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -429,8 +429,7 @@ static int upgrade_mode(struct dm_dev_internal *dd, fmode_t new_mode, * it's already present. */ static int __table_get_device(struct dm_table *t, struct dm_target *ti, - const char *path, sector_t start, sector_t len, - fmode_t mode, struct dm_dev **result) + const char *path, fmode_t mode, struct dm_dev **result) { int r; dev_t uninitialized_var(dev); @@ -527,11 +526,10 @@ int dm_set_device_limits(struct dm_target *ti, struct dm_dev *dev, } EXPORT_SYMBOL_GPL(dm_set_device_limits); -int dm_get_device(struct dm_target *ti, const char *path, sector_t start, - sector_t len, fmode_t mode, struct dm_dev **result) +int dm_get_device(struct dm_target *ti, const char *path, fmode_t mode, + struct dm_dev **result) { - return __table_get_device(ti->table, ti, path, - start, len, mode, result); + return __table_get_device(ti->table, ti, path, mode, result); } @@ -1231,8 +1229,6 @@ void dm_table_unplug_all(struct dm_table *t) struct mapped_device *dm_table_get_md(struct dm_table *t) { - dm_get(t->md); - return t->md; } diff --git a/drivers/md/dm-target.c b/drivers/md/dm-target.c index 04feccf2a997..11dea11dc0b6 100644 --- a/drivers/md/dm-target.c +++ b/drivers/md/dm-target.c @@ -10,7 +10,6 @@ #include <linux/init.h> #include <linux/kmod.h> #include <linux/bio.h> -#include <linux/slab.h> #define DM_MSG_PREFIX "target" diff --git a/drivers/md/dm-uevent.c b/drivers/md/dm-uevent.c index c7c555a8c7b2..6b1e3b61b25e 100644 --- a/drivers/md/dm-uevent.c +++ b/drivers/md/dm-uevent.c @@ -187,7 +187,7 @@ void dm_path_uevent(enum dm_uevent_type event_type, struct dm_target *ti, if (event_type >= ARRAY_SIZE(_dm_uevent_type_names)) { DMERR("%s: Invalid event_type %d", __func__, event_type); - goto out; + return; } event = dm_build_path_uevent(md, ti, @@ -195,12 +195,9 @@ void dm_path_uevent(enum dm_uevent_type event_type, struct dm_target *ti, _dm_uevent_type_names[event_type].name, path, nr_valid_paths); if (IS_ERR(event)) - goto out; + return; dm_uevent_add(md, &event->elist); - -out: - dm_put(md); } EXPORT_SYMBOL_GPL(dm_path_uevent); diff --git a/drivers/md/dm.c b/drivers/md/dm.c index aa4e2aa86d49..d21e1284604f 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -635,8 +635,10 @@ static void dec_pending(struct dm_io *io, int error) if (!md->barrier_error && io_error != -EOPNOTSUPP) md->barrier_error = io_error; end_io_acct(io); + free_io(md, io); } else { end_io_acct(io); + free_io(md, io); if (io_error != DM_ENDIO_REQUEUE) { trace_block_bio_complete(md->queue, bio); @@ -644,8 +646,6 @@ static void dec_pending(struct dm_io *io, int error) bio_endio(bio, io_error); } } - - free_io(md, io); } } @@ -2618,18 +2618,19 @@ out: /*----------------------------------------------------------------- * Event notification. *---------------------------------------------------------------*/ -void dm_kobject_uevent(struct mapped_device *md, enum kobject_action action, +int dm_kobject_uevent(struct mapped_device *md, enum kobject_action action, unsigned cookie) { char udev_cookie[DM_COOKIE_LENGTH]; char *envp[] = { udev_cookie, NULL }; if (!cookie) - kobject_uevent(&disk_to_dev(md->disk)->kobj, action); + return kobject_uevent(&disk_to_dev(md->disk)->kobj, action); else { snprintf(udev_cookie, DM_COOKIE_LENGTH, "%s=%u", DM_COOKIE_ENV_VAR_NAME, cookie); - kobject_uevent_env(&disk_to_dev(md->disk)->kobj, action, envp); + return kobject_uevent_env(&disk_to_dev(md->disk)->kobj, + action, envp); } } @@ -2699,23 +2700,13 @@ int dm_suspended_md(struct mapped_device *md) int dm_suspended(struct dm_target *ti) { - struct mapped_device *md = dm_table_get_md(ti->table); - int r = dm_suspended_md(md); - - dm_put(md); - - return r; + return dm_suspended_md(dm_table_get_md(ti->table)); } EXPORT_SYMBOL_GPL(dm_suspended); int dm_noflush_suspending(struct dm_target *ti) { - struct mapped_device *md = dm_table_get_md(ti->table); - int r = __noflush_suspending(md); - - dm_put(md); - - return r; + return __noflush_suspending(dm_table_get_md(ti->table)); } EXPORT_SYMBOL_GPL(dm_noflush_suspending); diff --git a/drivers/md/dm.h b/drivers/md/dm.h index 8dadaa5bc396..bad1724d4869 100644 --- a/drivers/md/dm.h +++ b/drivers/md/dm.h @@ -125,8 +125,8 @@ void dm_stripe_exit(void); int dm_open_count(struct mapped_device *md); int dm_lock_for_deletion(struct mapped_device *md); -void dm_kobject_uevent(struct mapped_device *md, enum kobject_action action, - unsigned cookie); +int dm_kobject_uevent(struct mapped_device *md, enum kobject_action action, + unsigned cookie); int dm_io_init(void); void dm_io_exit(void); diff --git a/drivers/md/faulty.c b/drivers/md/faulty.c index 713acd02ab39..1a8987884614 100644 --- a/drivers/md/faulty.c +++ b/drivers/md/faulty.c @@ -64,6 +64,7 @@ #define MaxFault 50 #include <linux/blkdev.h> #include <linux/raid/md_u.h> +#include <linux/slab.h> #include "md.h" #include <linux/seq_file.h> @@ -168,10 +169,9 @@ static void add_sector(conf_t *conf, sector_t start, int mode) conf->nfaults = n+1; } -static int make_request(struct request_queue *q, struct bio *bio) +static int make_request(mddev_t *mddev, struct bio *bio) { - mddev_t *mddev = q->queuedata; - conf_t *conf = (conf_t*)mddev->private; + conf_t *conf = mddev->private; int failit = 0; if (bio_data_dir(bio) == WRITE) { @@ -224,7 +224,7 @@ static int make_request(struct request_queue *q, struct bio *bio) static void status(struct seq_file *seq, mddev_t *mddev) { - conf_t *conf = (conf_t*)mddev->private; + conf_t *conf = mddev->private; int n; if ((n=atomic_read(&conf->counters[WriteTransient])) != 0) @@ -327,7 +327,7 @@ static int run(mddev_t *mddev) static int stop(mddev_t *mddev) { - conf_t *conf = (conf_t *)mddev->private; + conf_t *conf = mddev->private; kfree(conf); mddev->private = NULL; diff --git a/drivers/md/linear.c b/drivers/md/linear.c index 00435bd20699..7e0e057db9a7 100644 --- a/drivers/md/linear.c +++ b/drivers/md/linear.c @@ -19,6 +19,7 @@ #include <linux/blkdev.h> #include <linux/raid/md_u.h> #include <linux/seq_file.h> +#include <linux/slab.h> #include "md.h" #include "linear.h" @@ -158,7 +159,8 @@ static linear_conf_t *linear_conf(mddev_t *mddev, int raid_disks) sector_t sectors; if (j < 0 || j >= raid_disks || disk->rdev) { - printk("linear: disk numbering problem. Aborting!\n"); + printk(KERN_ERR "md/linear:%s: disk numbering problem. Aborting!\n", + mdname(mddev)); goto out; } @@ -172,19 +174,22 @@ static linear_conf_t *linear_conf(mddev_t *mddev, int raid_disks) disk_stack_limits(mddev->gendisk, rdev->bdev, rdev->data_offset << 9); /* as we don't honour merge_bvec_fn, we must never risk - * violating it, so limit ->max_sector to one PAGE, as - * a one page request is never in violation. + * violating it, so limit max_segments to 1 lying within + * a single page. */ - if (rdev->bdev->bd_disk->queue->merge_bvec_fn && - queue_max_sectors(mddev->queue) > (PAGE_SIZE>>9)) - blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9); + if (rdev->bdev->bd_disk->queue->merge_bvec_fn) { + blk_queue_max_segments(mddev->queue, 1); + blk_queue_segment_boundary(mddev->queue, + PAGE_CACHE_SIZE - 1); + } conf->array_sectors += rdev->sectors; cnt++; } if (cnt != raid_disks) { - printk("linear: not enough drives present. Aborting!\n"); + printk(KERN_ERR "md/linear:%s: not enough drives present. Aborting!\n", + mdname(mddev)); goto out; } @@ -279,29 +284,21 @@ static int linear_stop (mddev_t *mddev) rcu_barrier(); blk_sync_queue(mddev->queue); /* the unplug fn references 'conf'*/ kfree(conf); + mddev->private = NULL; return 0; } -static int linear_make_request (struct request_queue *q, struct bio *bio) +static int linear_make_request (mddev_t *mddev, struct bio *bio) { - const int rw = bio_data_dir(bio); - mddev_t *mddev = q->queuedata; dev_info_t *tmp_dev; sector_t start_sector; - int cpu; if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER))) { md_barrier_request(mddev, bio); return 0; } - cpu = part_stat_lock(); - part_stat_inc(cpu, &mddev->gendisk->part0, ios[rw]); - part_stat_add(cpu, &mddev->gendisk->part0, sectors[rw], - bio_sectors(bio)); - part_stat_unlock(); - rcu_read_lock(); tmp_dev = which_dev(mddev, bio->bi_sector); start_sector = tmp_dev->end_sector - tmp_dev->rdev->sectors; @@ -311,12 +308,14 @@ static int linear_make_request (struct request_queue *q, struct bio *bio) || (bio->bi_sector < start_sector))) { char b[BDEVNAME_SIZE]; - printk("linear_make_request: Sector %llu out of bounds on " - "dev %s: %llu sectors, offset %llu\n", - (unsigned long long)bio->bi_sector, - bdevname(tmp_dev->rdev->bdev, b), - (unsigned long long)tmp_dev->rdev->sectors, - (unsigned long long)start_sector); + printk(KERN_ERR + "md/linear:%s: make_request: Sector %llu out of bounds on " + "dev %s: %llu sectors, offset %llu\n", + mdname(mddev), + (unsigned long long)bio->bi_sector, + bdevname(tmp_dev->rdev->bdev, b), + (unsigned long long)tmp_dev->rdev->sectors, + (unsigned long long)start_sector); rcu_read_unlock(); bio_io_error(bio); return 0; @@ -333,9 +332,9 @@ static int linear_make_request (struct request_queue *q, struct bio *bio) bp = bio_split(bio, end_sector - bio->bi_sector); - if (linear_make_request(q, &bp->bio1)) + if (linear_make_request(mddev, &bp->bio1)) generic_make_request(&bp->bio1); - if (linear_make_request(q, &bp->bio2)) + if (linear_make_request(mddev, &bp->bio2)) generic_make_request(&bp->bio2); bio_pair_release(bp); return 0; diff --git a/drivers/md/md.c b/drivers/md/md.c index a20a71e5efd3..cb20d0b0555a 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -49,6 +49,7 @@ #include <linux/delay.h> #include <linux/raid/md_p.h> #include <linux/raid/md_u.h> +#include <linux/slab.h> #include "md.h" #include "bitmap.h" @@ -214,8 +215,11 @@ static DEFINE_SPINLOCK(all_mddevs_lock); */ static int md_make_request(struct request_queue *q, struct bio *bio) { + const int rw = bio_data_dir(bio); mddev_t *mddev = q->queuedata; int rv; + int cpu; + if (mddev == NULL || mddev->pers == NULL) { bio_io_error(bio); return 0; @@ -236,13 +240,27 @@ static int md_make_request(struct request_queue *q, struct bio *bio) } atomic_inc(&mddev->active_io); rcu_read_unlock(); - rv = mddev->pers->make_request(q, bio); + + rv = mddev->pers->make_request(mddev, bio); + + cpu = part_stat_lock(); + part_stat_inc(cpu, &mddev->gendisk->part0, ios[rw]); + part_stat_add(cpu, &mddev->gendisk->part0, sectors[rw], + bio_sectors(bio)); + part_stat_unlock(); + if (atomic_dec_and_test(&mddev->active_io) && mddev->suspended) wake_up(&mddev->sb_wait); return rv; } +/* mddev_suspend makes sure no new requests are submitted + * to the device, and that any requests that have been submitted + * are completely handled. + * Once ->stop is called and completes, the module will be completely + * unused. + */ static void mddev_suspend(mddev_t *mddev) { BUG_ON(mddev->suspended); @@ -250,13 +268,6 @@ static void mddev_suspend(mddev_t *mddev) synchronize_rcu(); wait_event(mddev->sb_wait, atomic_read(&mddev->active_io) == 0); mddev->pers->quiesce(mddev, 1); - md_unregister_thread(mddev->thread); - mddev->thread = NULL; - /* we now know that no code is executing in the personality module, - * except possibly the tail end of a ->bi_end_io function, but that - * is certain to complete before the module has a chance to get - * unloaded - */ } static void mddev_resume(mddev_t *mddev) @@ -343,7 +354,7 @@ static void md_submit_barrier(struct work_struct *ws) bio_endio(bio, 0); else { bio->bi_rw &= ~(1<<BIO_RW_BARRIER); - if (mddev->pers->make_request(mddev->queue, bio)) + if (mddev->pers->make_request(mddev, bio)) generic_make_request(bio); mddev->barrier = POST_REQUEST_BARRIER; submit_barriers(mddev); @@ -405,6 +416,27 @@ static void mddev_put(mddev_t *mddev) spin_unlock(&all_mddevs_lock); } +static void mddev_init(mddev_t *mddev) +{ + mutex_init(&mddev->open_mutex); + mutex_init(&mddev->reconfig_mutex); + mutex_init(&mddev->bitmap_info.mutex); + INIT_LIST_HEAD(&mddev->disks); + INIT_LIST_HEAD(&mddev->all_mddevs); + init_timer(&mddev->safemode_timer); + atomic_set(&mddev->active, 1); + atomic_set(&mddev->openers, 0); + atomic_set(&mddev->active_io, 0); + spin_lock_init(&mddev->write_lock); + atomic_set(&mddev->flush_pending, 0); + init_waitqueue_head(&mddev->sb_wait); + init_waitqueue_head(&mddev->recovery_wait); + mddev->reshape_position = MaxSector; + mddev->resync_min = 0; + mddev->resync_max = MaxSector; + mddev->level = LEVEL_NONE; +} + static mddev_t * mddev_find(dev_t unit) { mddev_t *mddev, *new = NULL; @@ -471,23 +503,7 @@ static mddev_t * mddev_find(dev_t unit) else new->md_minor = MINOR(unit) >> MdpMinorShift; - mutex_init(&new->open_mutex); - mutex_init(&new->reconfig_mutex); - mutex_init(&new->bitmap_info.mutex); - INIT_LIST_HEAD(&new->disks); - INIT_LIST_HEAD(&new->all_mddevs); - init_timer(&new->safemode_timer); - atomic_set(&new->active, 1); - atomic_set(&new->openers, 0); - atomic_set(&new->active_io, 0); - spin_lock_init(&new->write_lock); - atomic_set(&new->flush_pending, 0); - init_waitqueue_head(&new->sb_wait); - init_waitqueue_head(&new->recovery_wait); - new->reshape_position = MaxSector; - new->resync_min = 0; - new->resync_max = MaxSector; - new->level = LEVEL_NONE; + mddev_init(new); goto retry; } @@ -507,9 +523,36 @@ static inline int mddev_trylock(mddev_t * mddev) return mutex_trylock(&mddev->reconfig_mutex); } -static inline void mddev_unlock(mddev_t * mddev) +static struct attribute_group md_redundancy_group; + +static void mddev_unlock(mddev_t * mddev) { - mutex_unlock(&mddev->reconfig_mutex); + if (mddev->to_remove) { + /* These cannot be removed under reconfig_mutex as + * an access to the files will try to take reconfig_mutex + * while holding the file unremovable, which leads to + * a deadlock. + * So hold open_mutex instead - we are allowed to take + * it while holding reconfig_mutex, and md_run can + * use it to wait for the remove to complete. + */ + struct attribute_group *to_remove = mddev->to_remove; + mddev->to_remove = NULL; + mutex_lock(&mddev->open_mutex); + mutex_unlock(&mddev->reconfig_mutex); + + if (to_remove != &md_redundancy_group) + sysfs_remove_group(&mddev->kobj, to_remove); + if (mddev->pers == NULL || + mddev->pers->sync_request == NULL) { + sysfs_remove_group(&mddev->kobj, &md_redundancy_group); + if (mddev->sysfs_action) + sysfs_put(mddev->sysfs_action); + mddev->sysfs_action = NULL; + } + mutex_unlock(&mddev->open_mutex); + } else + mutex_unlock(&mddev->reconfig_mutex); md_wakeup_thread(mddev->thread); } @@ -1028,10 +1071,13 @@ static int super_90_validate(mddev_t *mddev, mdk_rdev_t *rdev) mddev->bitmap_info.default_offset; } else if (mddev->pers == NULL) { - /* Insist on good event counter while assembling */ + /* Insist on good event counter while assembling, except + * for spares (which don't need an event count) */ ++ev1; - if (ev1 < mddev->events) - return -EINVAL; + if (sb->disks[rdev->desc_nr].state & ( + (1<<MD_DISK_SYNC) | (1 << MD_DISK_ACTIVE))) + if (ev1 < mddev->events) + return -EINVAL; } else if (mddev->bitmap) { /* if adding to array with a bitmap, then we can accept an * older device ... but not too old. @@ -1427,10 +1473,14 @@ static int super_1_validate(mddev_t *mddev, mdk_rdev_t *rdev) } } else if (mddev->pers == NULL) { - /* Insist of good event counter while assembling */ + /* Insist of good event counter while assembling, except for + * spares (which don't need an event count) */ ++ev1; - if (ev1 < mddev->events) - return -EINVAL; + if (rdev->desc_nr >= 0 && + rdev->desc_nr < le32_to_cpu(sb->max_dev) && + le16_to_cpu(sb->dev_roles[rdev->desc_nr]) < 0xfffe) + if (ev1 < mddev->events) + return -EINVAL; } else if (mddev->bitmap) { /* If adding to array with a bitmap, then we can accept an * older device, but not too old. @@ -1765,7 +1815,7 @@ static int bind_rdev_to_array(mdk_rdev_t * rdev, mddev_t * mddev) kobject_del(&rdev->kobj); goto fail; } - rdev->sysfs_state = sysfs_get_dirent(rdev->kobj.sd, "state"); + rdev->sysfs_state = sysfs_get_dirent(rdev->kobj.sd, NULL, "state"); list_add_rcu(&rdev->same_set, &mddev->disks); bd_claim_by_disk(rdev->bdev, rdev->bdev->bd_holder, mddev->gendisk); @@ -2037,6 +2087,7 @@ static void sync_sbs(mddev_t * mddev, int nospares) /* First make sure individual recovery_offsets are correct */ list_for_each_entry(rdev, &mddev->disks, same_set) { if (rdev->raid_disk >= 0 && + mddev->delta_disks >= 0 && !test_bit(In_sync, &rdev->flags) && mddev->curr_resync_completed > rdev->recovery_offset) rdev->recovery_offset = mddev->curr_resync_completed; @@ -2046,7 +2097,6 @@ static void sync_sbs(mddev_t * mddev, int nospares) if (rdev->sb_events == mddev->events || (nospares && rdev->raid_disk < 0 && - (rdev->sb_events&1)==0 && rdev->sb_events+1 == mddev->events)) { /* Don't update this superblock */ rdev->sb_loaded = 2; @@ -2099,22 +2149,14 @@ repeat: * and 'events' is odd, we can roll back to the previous clean state */ if (nospares && (mddev->in_sync && mddev->recovery_cp == MaxSector) - && (mddev->events & 1) - && mddev->events != 1) + && mddev->can_decrease_events + && mddev->events != 1) { mddev->events--; - else { + mddev->can_decrease_events = 0; + } else { /* otherwise we have to go forward and ... */ mddev->events ++; - if (!mddev->in_sync || mddev->recovery_cp != MaxSector) { /* not clean */ - /* .. if the array isn't clean, an 'even' event must also go - * to spares. */ - if ((mddev->events&1)==0) - nospares = 0; - } else { - /* otherwise an 'odd' event must go to spares */ - if ((mddev->events&1)) - nospares = 0; - } + mddev->can_decrease_events = nospares; } if (!mddev->events) { @@ -2358,6 +2400,7 @@ slot_store(mdk_rdev_t *rdev, const char *buf, size_t len) return err; sprintf(nm, "rd%d", rdev->raid_disk); sysfs_remove_link(&rdev->mddev->kobj, nm); + rdev->raid_disk = -1; set_bit(MD_RECOVERY_NEEDED, &rdev->mddev->recovery); md_wakeup_thread(rdev->mddev->thread); } else if (rdev->mddev->pers) { @@ -2642,7 +2685,7 @@ static void rdev_free(struct kobject *ko) mdk_rdev_t *rdev = container_of(ko, mdk_rdev_t, kobj); kfree(rdev); } -static struct sysfs_ops rdev_sysfs_ops = { +static const struct sysfs_ops rdev_sysfs_ops = { .show = rdev_attr_show, .store = rdev_attr_store, }; @@ -2773,8 +2816,9 @@ static void analyze_sbs(mddev_t * mddev) i = 0; rdev_for_each(rdev, tmp, mddev) { - if (rdev->desc_nr >= mddev->max_disks || - i > mddev->max_disks) { + if (mddev->max_disks && + (rdev->desc_nr >= mddev->max_disks || + i > mddev->max_disks)) { printk(KERN_WARNING "md: %s: %s: only %d devices permitted\n", mdname(mddev), bdevname(rdev->bdev, b), @@ -2890,9 +2934,10 @@ level_show(mddev_t *mddev, char *page) static ssize_t level_store(mddev_t *mddev, const char *buf, size_t len) { - char level[16]; + char clevel[16]; ssize_t rv = len; struct mdk_personality *pers; + long level; void *priv; mdk_rdev_t *rdev; @@ -2925,19 +2970,22 @@ level_store(mddev_t *mddev, const char *buf, size_t len) } /* Now find the new personality */ - if (len == 0 || len >= sizeof(level)) + if (len == 0 || len >= sizeof(clevel)) return -EINVAL; - strncpy(level, buf, len); - if (level[len-1] == '\n') + strncpy(clevel, buf, len); + if (clevel[len-1] == '\n') len--; - level[len] = 0; + clevel[len] = 0; + if (strict_strtol(clevel, 10, &level)) + level = LEVEL_NONE; - request_module("md-%s", level); + if (request_module("md-%s", clevel) != 0) + request_module("md-level-%s", clevel); spin_lock(&pers_lock); - pers = find_pers(LEVEL_NONE, level); + pers = find_pers(level, clevel); if (!pers || !try_module_get(pers->owner)) { spin_unlock(&pers_lock); - printk(KERN_WARNING "md: personality %s not loaded\n", level); + printk(KERN_WARNING "md: personality %s not loaded\n", clevel); return -EINVAL; } spin_unlock(&pers_lock); @@ -2950,10 +2998,13 @@ level_store(mddev_t *mddev, const char *buf, size_t len) if (!pers->takeover) { module_put(pers->owner); printk(KERN_WARNING "md: %s: %s does not support personality takeover\n", - mdname(mddev), level); + mdname(mddev), clevel); return -EINVAL; } + list_for_each_entry(rdev, &mddev->disks, same_set) + rdev->new_raid_disk = rdev->raid_disk; + /* ->takeover must set new_* and/or delta_disks * if it succeeds, and may set them when it fails. */ @@ -2966,20 +3017,73 @@ level_store(mddev_t *mddev, const char *buf, size_t len) mddev->delta_disks = 0; module_put(pers->owner); printk(KERN_WARNING "md: %s: %s would not accept array\n", - mdname(mddev), level); + mdname(mddev), clevel); return PTR_ERR(priv); } /* Looks like we have a winner */ mddev_suspend(mddev); mddev->pers->stop(mddev); - module_put(mddev->pers->owner); - /* Invalidate devices that are now superfluous */ - list_for_each_entry(rdev, &mddev->disks, same_set) - if (rdev->raid_disk >= mddev->raid_disks) { - rdev->raid_disk = -1; + + if (mddev->pers->sync_request == NULL && + pers->sync_request != NULL) { + /* need to add the md_redundancy_group */ + if (sysfs_create_group(&mddev->kobj, &md_redundancy_group)) + printk(KERN_WARNING + "md: cannot register extra attributes for %s\n", + mdname(mddev)); + mddev->sysfs_action = sysfs_get_dirent(mddev->kobj.sd, NULL, "sync_action"); + } + if (mddev->pers->sync_request != NULL && + pers->sync_request == NULL) { + /* need to remove the md_redundancy_group */ + if (mddev->to_remove == NULL) + mddev->to_remove = &md_redundancy_group; + } + + if (mddev->pers->sync_request == NULL && + mddev->external) { + /* We are converting from a no-redundancy array + * to a redundancy array and metadata is managed + * externally so we need to be sure that writes + * won't block due to a need to transition + * clean->dirty + * until external management is started. + */ + mddev->in_sync = 0; + mddev->safemode_delay = 0; + mddev->safemode = 0; + } + + list_for_each_entry(rdev, &mddev->disks, same_set) { + char nm[20]; + if (rdev->raid_disk < 0) + continue; + if (rdev->new_raid_disk > mddev->raid_disks) + rdev->new_raid_disk = -1; + if (rdev->new_raid_disk == rdev->raid_disk) + continue; + sprintf(nm, "rd%d", rdev->raid_disk); + sysfs_remove_link(&mddev->kobj, nm); + } + list_for_each_entry(rdev, &mddev->disks, same_set) { + if (rdev->raid_disk < 0) + continue; + if (rdev->new_raid_disk == rdev->raid_disk) + continue; + rdev->raid_disk = rdev->new_raid_disk; + if (rdev->raid_disk < 0) clear_bit(In_sync, &rdev->flags); + else { + char nm[20]; + sprintf(nm, "rd%d", rdev->raid_disk); + if(sysfs_create_link(&mddev->kobj, &rdev->kobj, nm)) + printk("md: cannot register %s for %s after level change\n", + nm, mdname(mddev)); } + } + + module_put(mddev->pers->owner); mddev->pers = pers; mddev->private = priv; strlcpy(mddev->clevel, pers->name, sizeof(mddev->clevel)); @@ -2987,11 +3091,20 @@ level_store(mddev_t *mddev, const char *buf, size_t len) mddev->layout = mddev->new_layout; mddev->chunk_sectors = mddev->new_chunk_sectors; mddev->delta_disks = 0; + if (mddev->pers->sync_request == NULL) { + /* this is now an array without redundancy, so + * it must always be in_sync + */ + mddev->in_sync = 1; + del_timer_sync(&mddev->safemode_timer); + } pers->run(mddev); mddev_resume(mddev); set_bit(MD_CHANGE_DEVS, &mddev->flags); set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); md_wakeup_thread(mddev->thread); + sysfs_notify(&mddev->kobj, NULL, "level"); + md_new_event(mddev); return rv; } @@ -3230,6 +3343,7 @@ array_state_show(mddev_t *mddev, char *page) } static int do_md_stop(mddev_t * mddev, int ro, int is_open); +static int md_set_readonly(mddev_t * mddev, int is_open); static int do_md_run(mddev_t * mddev); static int restart_array(mddev_t *mddev); @@ -3260,7 +3374,7 @@ array_state_store(mddev_t *mddev, const char *buf, size_t len) break; /* not supported yet */ case readonly: if (mddev->pers) - err = do_md_stop(mddev, 1, 0); + err = md_set_readonly(mddev, 0); else { mddev->ro = 1; set_disk_ro(mddev->gendisk, 1); @@ -3270,7 +3384,7 @@ array_state_store(mddev_t *mddev, const char *buf, size_t len) case read_auto: if (mddev->pers) { if (mddev->ro == 0) - err = do_md_stop(mddev, 1, 0); + err = md_set_readonly(mddev, 0); else if (mddev->ro == 1) err = restart_array(mddev); if (err == 0) { @@ -4059,7 +4173,7 @@ static void md_free(struct kobject *ko) kfree(mddev); } -static struct sysfs_ops md_sysfs_ops = { +static const struct sysfs_ops md_sysfs_ops = { .show = md_attr_show, .store = md_attr_store, }; @@ -4075,15 +4189,6 @@ static void mddev_delayed_delete(struct work_struct *ws) { mddev_t *mddev = container_of(ws, mddev_t, del_work); - if (mddev->private) { - sysfs_remove_group(&mddev->kobj, &md_redundancy_group); - if (mddev->private != (void*)1) - sysfs_remove_group(&mddev->kobj, mddev->private); - if (mddev->sysfs_action) - sysfs_put(mddev->sysfs_action); - mddev->sysfs_action = NULL; - mddev->private = NULL; - } sysfs_remove_group(&mddev->kobj, &md_bitmap_group); kobject_del(&mddev->kobj); kobject_put(&mddev->kobj); @@ -4182,7 +4287,7 @@ static int md_alloc(dev_t dev, char *name) mutex_unlock(&disks_mutex); if (!error) { kobject_uevent(&mddev->kobj, KOBJ_ADD); - mddev->sysfs_state = sysfs_get_dirent(mddev->kobj.sd, "array_state"); + mddev->sysfs_state = sysfs_get_dirent(mddev->kobj.sd, NULL, "array_state"); } mddev_put(mddev); return error; @@ -4227,11 +4332,10 @@ static void md_safemode_timeout(unsigned long data) static int start_dirty_degraded; -static int do_md_run(mddev_t * mddev) +static int md_run(mddev_t *mddev) { int err; mdk_rdev_t *rdev; - struct gendisk *disk; struct mdk_personality *pers; if (list_empty(&mddev->disks)) @@ -4241,6 +4345,13 @@ static int do_md_run(mddev_t * mddev) if (mddev->pers) return -EBUSY; + /* These two calls synchronise us with the + * sysfs_remove_group calls in mddev_unlock, + * so they must have completed. + */ + mutex_lock(&mddev->open_mutex); + mutex_unlock(&mddev->open_mutex); + /* * Analyze all RAID superblock(s) */ @@ -4289,8 +4400,6 @@ static int do_md_run(mddev_t * mddev) sysfs_notify_dirent(rdev->sysfs_state); } - disk = mddev->gendisk; - spin_lock(&pers_lock); pers = find_pers(mddev->level, mddev->clevel); if (!pers || !try_module_get(pers->owner)) { @@ -4391,7 +4500,7 @@ static int do_md_run(mddev_t * mddev) printk(KERN_WARNING "md: cannot register extra attributes for %s\n", mdname(mddev)); - mddev->sysfs_action = sysfs_get_dirent(mddev->kobj.sd, "sync_action"); + mddev->sysfs_action = sysfs_get_dirent(mddev->kobj.sd, NULL, "sync_action"); } else if (mddev->ro == 2) /* auto-readonly not meaningful */ mddev->ro = 0; @@ -4418,22 +4527,32 @@ static int do_md_run(mddev_t * mddev) if (mddev->flags) md_update_sb(mddev, 0); - set_capacity(disk, mddev->array_sectors); - md_wakeup_thread(mddev->thread); md_wakeup_thread(mddev->sync_thread); /* possibly kick off a reshape */ - revalidate_disk(mddev->gendisk); - mddev->changed = 1; md_new_event(mddev); sysfs_notify_dirent(mddev->sysfs_state); if (mddev->sysfs_action) sysfs_notify_dirent(mddev->sysfs_action); sysfs_notify(&mddev->kobj, NULL, "degraded"); - kobject_uevent(&disk_to_dev(mddev->gendisk)->kobj, KOBJ_CHANGE); return 0; } +static int do_md_run(mddev_t *mddev) +{ + int err; + + err = md_run(mddev); + if (err) + goto out; + + set_capacity(mddev->gendisk, mddev->array_sectors); + revalidate_disk(mddev->gendisk); + kobject_uevent(&disk_to_dev(mddev->gendisk)->kobj, KOBJ_CHANGE); +out: + return err; +} + static int restart_array(mddev_t *mddev) { struct gendisk *disk = mddev->gendisk; @@ -4484,9 +4603,110 @@ void restore_bitmap_write_access(struct file *file) spin_unlock(&inode->i_lock); } +static void md_clean(mddev_t *mddev) +{ + mddev->array_sectors = 0; + mddev->external_size = 0; + mddev->dev_sectors = 0; + mddev->raid_disks = 0; + mddev->recovery_cp = 0; + mddev->resync_min = 0; + mddev->resync_max = MaxSector; + mddev->reshape_position = MaxSector; + mddev->external = 0; + mddev->persistent = 0; + mddev->level = LEVEL_NONE; + mddev->clevel[0] = 0; + mddev->flags = 0; + mddev->ro = 0; + mddev->metadata_type[0] = 0; + mddev->chunk_sectors = 0; + mddev->ctime = mddev->utime = 0; + mddev->layout = 0; + mddev->max_disks = 0; + mddev->events = 0; + mddev->can_decrease_events = 0; + mddev->delta_disks = 0; + mddev->new_level = LEVEL_NONE; + mddev->new_layout = 0; + mddev->new_chunk_sectors = 0; + mddev->curr_resync = 0; + mddev->resync_mismatches = 0; + mddev->suspend_lo = mddev->suspend_hi = 0; + mddev->sync_speed_min = mddev->sync_speed_max = 0; + mddev->recovery = 0; + mddev->in_sync = 0; + mddev->degraded = 0; + mddev->barriers_work = 0; + mddev->safemode = 0; + mddev->bitmap_info.offset = 0; + mddev->bitmap_info.default_offset = 0; + mddev->bitmap_info.chunksize = 0; + mddev->bitmap_info.daemon_sleep = 0; + mddev->bitmap_info.max_write_behind = 0; +} + +static void md_stop_writes(mddev_t *mddev) +{ + if (mddev->sync_thread) { + set_bit(MD_RECOVERY_FROZEN, &mddev->recovery); + set_bit(MD_RECOVERY_INTR, &mddev->recovery); + md_unregister_thread(mddev->sync_thread); + mddev->sync_thread = NULL; + } + + del_timer_sync(&mddev->safemode_timer); + + bitmap_flush(mddev); + md_super_wait(mddev); + + if (!mddev->in_sync || mddev->flags) { + /* mark array as shutdown cleanly */ + mddev->in_sync = 1; + md_update_sb(mddev, 1); + } +} + +static void md_stop(mddev_t *mddev) +{ + md_stop_writes(mddev); + + mddev->pers->stop(mddev); + if (mddev->pers->sync_request && mddev->to_remove == NULL) + mddev->to_remove = &md_redundancy_group; + module_put(mddev->pers->owner); + mddev->pers = NULL; + clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); +} + +static int md_set_readonly(mddev_t *mddev, int is_open) +{ + int err = 0; + mutex_lock(&mddev->open_mutex); + if (atomic_read(&mddev->openers) > is_open) { + printk("md: %s still in use.\n",mdname(mddev)); + err = -EBUSY; + goto out; + } + if (mddev->pers) { + md_stop_writes(mddev); + + err = -ENXIO; + if (mddev->ro==1) + goto out; + mddev->ro = 1; + set_disk_ro(mddev->gendisk, 1); + clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); + sysfs_notify_dirent(mddev->sysfs_state); + err = 0; + } +out: + mutex_unlock(&mddev->open_mutex); + return err; +} + /* mode: * 0 - completely stop and dis-assemble array - * 1 - switch to readonly * 2 - stop but do not disassemble array */ static int do_md_stop(mddev_t * mddev, int mode, int is_open) @@ -4501,64 +4721,32 @@ static int do_md_stop(mddev_t * mddev, int mode, int is_open) err = -EBUSY; } else if (mddev->pers) { - if (mddev->sync_thread) { - set_bit(MD_RECOVERY_FROZEN, &mddev->recovery); - set_bit(MD_RECOVERY_INTR, &mddev->recovery); - md_unregister_thread(mddev->sync_thread); - mddev->sync_thread = NULL; - } + if (mddev->ro) + set_disk_ro(disk, 0); - del_timer_sync(&mddev->safemode_timer); + md_stop(mddev); + mddev->queue->merge_bvec_fn = NULL; + mddev->queue->unplug_fn = NULL; + mddev->queue->backing_dev_info.congested_fn = NULL; - switch(mode) { - case 1: /* readonly */ - err = -ENXIO; - if (mddev->ro==1) - goto out; - mddev->ro = 1; - break; - case 0: /* disassemble */ - case 2: /* stop */ - bitmap_flush(mddev); - md_super_wait(mddev); - if (mddev->ro) - set_disk_ro(disk, 0); - - mddev->pers->stop(mddev); - mddev->queue->merge_bvec_fn = NULL; - mddev->queue->unplug_fn = NULL; - mddev->queue->backing_dev_info.congested_fn = NULL; - module_put(mddev->pers->owner); - if (mddev->pers->sync_request && mddev->private == NULL) - mddev->private = (void*)1; - mddev->pers = NULL; - /* tell userspace to handle 'inactive' */ - sysfs_notify_dirent(mddev->sysfs_state); + /* tell userspace to handle 'inactive' */ + sysfs_notify_dirent(mddev->sysfs_state); - list_for_each_entry(rdev, &mddev->disks, same_set) - if (rdev->raid_disk >= 0) { - char nm[20]; - sprintf(nm, "rd%d", rdev->raid_disk); - sysfs_remove_link(&mddev->kobj, nm); - } + list_for_each_entry(rdev, &mddev->disks, same_set) + if (rdev->raid_disk >= 0) { + char nm[20]; + sprintf(nm, "rd%d", rdev->raid_disk); + sysfs_remove_link(&mddev->kobj, nm); + } - set_capacity(disk, 0); - mddev->changed = 1; + set_capacity(disk, 0); + revalidate_disk(disk); - if (mddev->ro) - mddev->ro = 0; - } - if (!mddev->in_sync || mddev->flags) { - /* mark array as shutdown cleanly */ - mddev->in_sync = 1; - md_update_sb(mddev, 1); - } - if (mode == 1) - set_disk_ro(disk, 1); - clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); + if (mddev->ro) + mddev->ro = 0; + err = 0; } -out: mutex_unlock(&mddev->open_mutex); if (err) return err; @@ -4579,52 +4767,12 @@ out: export_array(mddev); - mddev->array_sectors = 0; - mddev->external_size = 0; - mddev->dev_sectors = 0; - mddev->raid_disks = 0; - mddev->recovery_cp = 0; - mddev->resync_min = 0; - mddev->resync_max = MaxSector; - mddev->reshape_position = MaxSector; - mddev->external = 0; - mddev->persistent = 0; - mddev->level = LEVEL_NONE; - mddev->clevel[0] = 0; - mddev->flags = 0; - mddev->ro = 0; - mddev->metadata_type[0] = 0; - mddev->chunk_sectors = 0; - mddev->ctime = mddev->utime = 0; - mddev->layout = 0; - mddev->max_disks = 0; - mddev->events = 0; - mddev->delta_disks = 0; - mddev->new_level = LEVEL_NONE; - mddev->new_layout = 0; - mddev->new_chunk_sectors = 0; - mddev->curr_resync = 0; - mddev->resync_mismatches = 0; - mddev->suspend_lo = mddev->suspend_hi = 0; - mddev->sync_speed_min = mddev->sync_speed_max = 0; - mddev->recovery = 0; - mddev->in_sync = 0; - mddev->changed = 0; - mddev->degraded = 0; - mddev->barriers_work = 0; - mddev->safemode = 0; - mddev->bitmap_info.offset = 0; - mddev->bitmap_info.default_offset = 0; - mddev->bitmap_info.chunksize = 0; - mddev->bitmap_info.daemon_sleep = 0; - mddev->bitmap_info.max_write_behind = 0; + md_clean(mddev); kobject_uevent(&disk_to_dev(mddev->gendisk)->kobj, KOBJ_CHANGE); if (mddev->hold_active == UNTIL_STOP) mddev->hold_active = 0; - } else if (mddev->pers) - printk(KERN_INFO "md: %s switched to read-only mode.\n", - mdname(mddev)); + } err = 0; blk_integrity_unregister(disk); md_new_event(mddev); @@ -5342,7 +5490,7 @@ static int update_raid_disks(mddev_t *mddev, int raid_disks) if (mddev->pers->check_reshape == NULL) return -EINVAL; if (raid_disks <= 0 || - raid_disks >= mddev->max_disks) + (mddev->max_disks && raid_disks >= mddev->max_disks)) return -EINVAL; if (mddev->sync_thread || mddev->reshape_position != MaxSector) return -EBUSY; @@ -5479,7 +5627,7 @@ static int md_getgeo(struct block_device *bdev, struct hd_geometry *geo) geo->heads = 2; geo->sectors = 4; - geo->cylinders = get_capacity(mddev->gendisk) / 8; + geo->cylinders = mddev->array_sectors / 8; return 0; } @@ -5489,6 +5637,7 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode, int err = 0; void __user *argp = (void __user *)arg; mddev_t *mddev = NULL; + int ro; if (!capable(CAP_SYS_ADMIN)) return -EACCES; @@ -5621,9 +5770,37 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode, goto done_unlock; case STOP_ARRAY_RO: - err = do_md_stop(mddev, 1, 1); + err = md_set_readonly(mddev, 1); goto done_unlock; + case BLKROSET: + if (get_user(ro, (int __user *)(arg))) { + err = -EFAULT; + goto done_unlock; + } + err = -EINVAL; + + /* if the bdev is going readonly the value of mddev->ro + * does not matter, no writes are coming + */ + if (ro) + goto done_unlock; + + /* are we are already prepared for writes? */ + if (mddev->ro != 1) + goto done_unlock; + + /* transitioning to readauto need only happen for + * arrays that call md_write_start + */ + if (mddev->pers) { + err = restart_array(mddev); + if (err == 0) { + mddev->ro = 2; + set_disk_ro(mddev->gendisk, 0); + } + } + goto done_unlock; } /* @@ -5744,7 +5921,7 @@ static int md_open(struct block_device *bdev, fmode_t mode) atomic_inc(&mddev->openers); mutex_unlock(&mddev->open_mutex); - check_disk_change(bdev); + check_disk_size_change(mddev->gendisk, bdev); out: return err; } @@ -5759,21 +5936,6 @@ static int md_release(struct gendisk *disk, fmode_t mode) return 0; } - -static int md_media_changed(struct gendisk *disk) -{ - mddev_t *mddev = disk->private_data; - - return mddev->changed; -} - -static int md_revalidate(struct gendisk *disk) -{ - mddev_t *mddev = disk->private_data; - - mddev->changed = 0; - return 0; -} static const struct block_device_operations md_fops = { .owner = THIS_MODULE, @@ -5784,8 +5946,6 @@ static const struct block_device_operations md_fops = .compat_ioctl = md_compat_ioctl, #endif .getgeo = md_getgeo, - .media_changed = md_media_changed, - .revalidate_disk= md_revalidate, }; static int md_thread(void * arg) @@ -5899,7 +6059,7 @@ void md_error(mddev_t *mddev, mdk_rdev_t *rdev) mddev->pers->error_handler(mddev,rdev); if (mddev->degraded) set_bit(MD_RECOVERY_RECOVER, &mddev->recovery); - set_bit(StateChanged, &rdev->flags); + sysfs_notify_dirent(rdev->sysfs_state); set_bit(MD_RECOVERY_INTR, &mddev->recovery); set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); md_wakeup_thread(mddev->thread); @@ -6713,6 +6873,7 @@ void md_do_sync(mddev_t *mddev) rcu_read_lock(); list_for_each_entry_rcu(rdev, &mddev->disks, same_set) if (rdev->raid_disk >= 0 && + mddev->delta_disks >= 0 && !test_bit(Faulty, &rdev->flags) && !test_bit(In_sync, &rdev->flags) && rdev->recovery_offset < mddev->curr_resync) @@ -6891,11 +7052,6 @@ void md_check_recovery(mddev_t *mddev) if (mddev->flags) md_update_sb(mddev, 0); - list_for_each_entry(rdev, &mddev->disks, same_set) - if (test_and_clear_bit(StateChanged, &rdev->flags)) - sysfs_notify_dirent(rdev->sysfs_state); - - if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) && !test_bit(MD_RECOVERY_DONE, &mddev->recovery)) { /* resync/recovery still happening */ @@ -7032,7 +7188,7 @@ static int md_notify_reboot(struct notifier_block *this, * appears to still be in use. Hence * the '100'. */ - do_md_stop(mddev, 1, 100); + md_set_readonly(mddev, 100); mddev_unlock(mddev); } /* diff --git a/drivers/md/md.h b/drivers/md/md.h index 8e4c75c00d46..10597bfec000 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -74,13 +74,13 @@ struct mdk_rdev_s #define Blocked 8 /* An error occured on an externally * managed array, don't allow writes * until it is cleared */ -#define StateChanged 9 /* Faulty or Blocked has changed during - * interrupt, so it needs to be - * notified by the thread */ wait_queue_head_t blocked_wait; int desc_nr; /* descriptor index in the superblock */ int raid_disk; /* role of device in array */ + int new_raid_disk; /* role that the device will have in + * the array after a level-change completes. + */ int saved_raid_disk; /* role that device used to have in the * array and could again if we did a partial * resync from the bitmap @@ -153,6 +153,12 @@ struct mddev_s int external_size; /* size managed * externally */ __u64 events; + /* If the last 'event' was simply a clean->dirty transition, and + * we didn't write it to the spares, then it is safe and simple + * to just decrement the event count on a dirty->clean transition. + * So we record that possibility here. + */ + int can_decrease_events; char uuid[16]; @@ -240,7 +246,6 @@ struct mddev_s atomic_t active; /* general refcount */ atomic_t openers; /* number of active opens */ - int changed; /* true if we might need to reread partition info */ int degraded; /* whether md should consider * adding a spare */ @@ -279,9 +284,6 @@ struct mddev_s atomic_t writes_pending; struct request_queue *queue; /* for plugging ... */ - atomic_t write_behind; /* outstanding async IO */ - unsigned int max_write_behind; /* 0 = sync */ - struct bitmap *bitmap; /* the bitmap for the device */ struct { struct file *file; /* the bitmap file */ @@ -305,6 +307,7 @@ struct mddev_s atomic_t max_corr_read_errors; /* max read retries */ struct list_head all_mddevs; + struct attribute_group *to_remove; /* Generic barrier handling. * If there is a pending barrier request, all other * writes are blocked while the devices are flushed. @@ -336,7 +339,7 @@ struct mdk_personality int level; struct list_head list; struct module *owner; - int (*make_request)(struct request_queue *q, struct bio *bio); + int (*make_request)(mddev_t *mddev, struct bio *bio); int (*run)(mddev_t *mddev); int (*stop)(mddev_t *mddev); void (*status)(struct seq_file *seq, mddev_t *mddev); diff --git a/drivers/md/multipath.c b/drivers/md/multipath.c index 32a662fc55c9..410fb60699ac 100644 --- a/drivers/md/multipath.c +++ b/drivers/md/multipath.c @@ -22,6 +22,7 @@ #include <linux/blkdev.h> #include <linux/raid/md_u.h> #include <linux/seq_file.h> +#include <linux/slab.h> #include "md.h" #include "multipath.h" @@ -84,7 +85,7 @@ static void multipath_end_bh_io (struct multipath_bh *mp_bh, int err) static void multipath_end_request(struct bio *bio, int error) { int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags); - struct multipath_bh * mp_bh = (struct multipath_bh *)(bio->bi_private); + struct multipath_bh *mp_bh = bio->bi_private; multipath_conf_t *conf = mp_bh->mddev->private; mdk_rdev_t *rdev = conf->multipaths[mp_bh->path].rdev; @@ -135,14 +136,11 @@ static void multipath_unplug(struct request_queue *q) } -static int multipath_make_request (struct request_queue *q, struct bio * bio) +static int multipath_make_request(mddev_t *mddev, struct bio * bio) { - mddev_t *mddev = q->queuedata; multipath_conf_t *conf = mddev->private; struct multipath_bh * mp_bh; struct multipath_info *multipath; - const int rw = bio_data_dir(bio); - int cpu; if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER))) { md_barrier_request(mddev, bio); @@ -154,12 +152,6 @@ static int multipath_make_request (struct request_queue *q, struct bio * bio) mp_bh->master_bio = bio; mp_bh->mddev = mddev; - cpu = part_stat_lock(); - part_stat_inc(cpu, &mddev->gendisk->part0, ios[rw]); - part_stat_add(cpu, &mddev->gendisk->part0, sectors[rw], - bio_sectors(bio)); - part_stat_unlock(); - mp_bh->path = multipath_map(conf); if (mp_bh->path < 0) { bio_endio(bio, -EIO); @@ -301,14 +293,16 @@ static int multipath_add_disk(mddev_t *mddev, mdk_rdev_t *rdev) rdev->data_offset << 9); /* as we don't honour merge_bvec_fn, we must never risk - * violating it, so limit ->max_sector to one PAGE, as - * a one page request is never in violation. + * violating it, so limit ->max_segments to one, lying + * within a single page. * (Note: it is very unlikely that a device with * merge_bvec_fn will be involved in multipath.) */ - if (q->merge_bvec_fn && - queue_max_sectors(q) > (PAGE_SIZE>>9)) - blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9); + if (q->merge_bvec_fn) { + blk_queue_max_segments(mddev->queue, 1); + blk_queue_segment_boundary(mddev->queue, + PAGE_CACHE_SIZE - 1); + } conf->working_disks++; mddev->degraded--; @@ -476,9 +470,11 @@ static int multipath_run (mddev_t *mddev) /* as we don't honour merge_bvec_fn, we must never risk * violating it, not that we ever expect a device with * a merge_bvec_fn to be involved in multipath */ - if (rdev->bdev->bd_disk->queue->merge_bvec_fn && - queue_max_sectors(mddev->queue) > (PAGE_SIZE>>9)) - blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9); + if (rdev->bdev->bd_disk->queue->merge_bvec_fn) { + blk_queue_max_segments(mddev->queue, 1); + blk_queue_segment_boundary(mddev->queue, + PAGE_CACHE_SIZE - 1); + } if (!test_bit(Faulty, &rdev->flags)) conf->working_disks++; diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index 77605cdceaf1..563abed5a2cb 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -20,17 +20,20 @@ #include <linux/blkdev.h> #include <linux/seq_file.h> +#include <linux/slab.h> #include "md.h" #include "raid0.h" +#include "raid5.h" static void raid0_unplug(struct request_queue *q) { mddev_t *mddev = q->queuedata; raid0_conf_t *conf = mddev->private; mdk_rdev_t **devlist = conf->devlist; + int raid_disks = conf->strip_zone[0].nb_dev; int i; - for (i=0; i<mddev->raid_disks; i++) { + for (i=0; i < raid_disks; i++) { struct request_queue *r_queue = bdev_get_queue(devlist[i]->bdev); blk_unplug(r_queue); @@ -42,12 +45,13 @@ static int raid0_congested(void *data, int bits) mddev_t *mddev = data; raid0_conf_t *conf = mddev->private; mdk_rdev_t **devlist = conf->devlist; + int raid_disks = conf->strip_zone[0].nb_dev; int i, ret = 0; if (mddev_congested(mddev, bits)) return 1; - for (i = 0; i < mddev->raid_disks && !ret ; i++) { + for (i = 0; i < raid_disks && !ret ; i++) { struct request_queue *q = bdev_get_queue(devlist[i]->bdev); ret |= bdi_congested(&q->backing_dev_info, bits); @@ -65,16 +69,17 @@ static void dump_zones(mddev_t *mddev) sector_t zone_start = 0; char b[BDEVNAME_SIZE]; raid0_conf_t *conf = mddev->private; + int raid_disks = conf->strip_zone[0].nb_dev; printk(KERN_INFO "******* %s configuration *********\n", mdname(mddev)); h = 0; for (j = 0; j < conf->nr_strip_zones; j++) { printk(KERN_INFO "zone%d=[", j); for (k = 0; k < conf->strip_zone[j].nb_dev; k++) - printk("%s/", - bdevname(conf->devlist[j*mddev->raid_disks + printk(KERN_CONT "%s/", + bdevname(conf->devlist[j*raid_disks + k]->bdev, b)); - printk("]\n"); + printk(KERN_CONT "]\n"); zone_size = conf->strip_zone[j].zone_end - zone_start; printk(KERN_INFO " zone offset=%llukb " @@ -87,7 +92,7 @@ static void dump_zones(mddev_t *mddev) printk(KERN_INFO "**********************************\n\n"); } -static int create_strip_zones(mddev_t *mddev) +static int create_strip_zones(mddev_t *mddev, raid0_conf_t **private_conf) { int i, c, err; sector_t curr_zone_end, sectors; @@ -100,8 +105,9 @@ static int create_strip_zones(mddev_t *mddev) if (!conf) return -ENOMEM; list_for_each_entry(rdev1, &mddev->disks, same_set) { - printk(KERN_INFO "raid0: looking at %s\n", - bdevname(rdev1->bdev,b)); + printk(KERN_INFO "md/raid0:%s: looking at %s\n", + mdname(mddev), + bdevname(rdev1->bdev, b)); c = 0; /* round size to chunk_size */ @@ -110,14 +116,16 @@ static int create_strip_zones(mddev_t *mddev) rdev1->sectors = sectors * mddev->chunk_sectors; list_for_each_entry(rdev2, &mddev->disks, same_set) { - printk(KERN_INFO "raid0: comparing %s(%llu)", + printk(KERN_INFO "md/raid0:%s: comparing %s(%llu)", + mdname(mddev), bdevname(rdev1->bdev,b), (unsigned long long)rdev1->sectors); - printk(KERN_INFO " with %s(%llu)\n", + printk(KERN_CONT " with %s(%llu)\n", bdevname(rdev2->bdev,b), (unsigned long long)rdev2->sectors); if (rdev2 == rdev1) { - printk(KERN_INFO "raid0: END\n"); + printk(KERN_INFO "md/raid0:%s: END\n", + mdname(mddev)); break; } if (rdev2->sectors == rdev1->sectors) { @@ -125,20 +133,24 @@ static int create_strip_zones(mddev_t *mddev) * Not unique, don't count it as a new * group */ - printk(KERN_INFO "raid0: EQUAL\n"); + printk(KERN_INFO "md/raid0:%s: EQUAL\n", + mdname(mddev)); c = 1; break; } - printk(KERN_INFO "raid0: NOT EQUAL\n"); + printk(KERN_INFO "md/raid0:%s: NOT EQUAL\n", + mdname(mddev)); } if (!c) { - printk(KERN_INFO "raid0: ==> UNIQUE\n"); + printk(KERN_INFO "md/raid0:%s: ==> UNIQUE\n", + mdname(mddev)); conf->nr_strip_zones++; - printk(KERN_INFO "raid0: %d zones\n", - conf->nr_strip_zones); + printk(KERN_INFO "md/raid0:%s: %d zones\n", + mdname(mddev), conf->nr_strip_zones); } } - printk(KERN_INFO "raid0: FINAL %d zones\n", conf->nr_strip_zones); + printk(KERN_INFO "md/raid0:%s: FINAL %d zones\n", + mdname(mddev), conf->nr_strip_zones); err = -ENOMEM; conf->strip_zone = kzalloc(sizeof(struct strip_zone)* conf->nr_strip_zones, GFP_KERNEL); @@ -161,14 +173,20 @@ static int create_strip_zones(mddev_t *mddev) list_for_each_entry(rdev1, &mddev->disks, same_set) { int j = rdev1->raid_disk; + if (mddev->level == 10) { + /* taking over a raid10-n2 array */ + j /= 2; + rdev1->new_raid_disk = j; + } + if (j < 0 || j >= mddev->raid_disks) { - printk(KERN_ERR "raid0: bad disk number %d - " - "aborting!\n", j); + printk(KERN_ERR "md/raid0:%s: bad disk number %d - " + "aborting!\n", mdname(mddev), j); goto abort; } if (dev[j]) { - printk(KERN_ERR "raid0: multiple devices for %d - " - "aborting!\n", j); + printk(KERN_ERR "md/raid0:%s: multiple devices for %d - " + "aborting!\n", mdname(mddev), j); goto abort; } dev[j] = rdev1; @@ -176,21 +194,22 @@ static int create_strip_zones(mddev_t *mddev) disk_stack_limits(mddev->gendisk, rdev1->bdev, rdev1->data_offset << 9); /* as we don't honour merge_bvec_fn, we must never risk - * violating it, so limit ->max_sector to one PAGE, as - * a one page request is never in violation. + * violating it, so limit ->max_segments to 1, lying within + * a single page. */ - if (rdev1->bdev->bd_disk->queue->merge_bvec_fn && - queue_max_sectors(mddev->queue) > (PAGE_SIZE>>9)) - blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9); - + if (rdev1->bdev->bd_disk->queue->merge_bvec_fn) { + blk_queue_max_segments(mddev->queue, 1); + blk_queue_segment_boundary(mddev->queue, + PAGE_CACHE_SIZE - 1); + } if (!smallest || (rdev1->sectors < smallest->sectors)) smallest = rdev1; cnt++; } if (cnt != mddev->raid_disks) { - printk(KERN_ERR "raid0: too few disks (%d of %d) - " - "aborting!\n", cnt, mddev->raid_disks); + printk(KERN_ERR "md/raid0:%s: too few disks (%d of %d) - " + "aborting!\n", mdname(mddev), cnt, mddev->raid_disks); goto abort; } zone->nb_dev = cnt; @@ -206,39 +225,44 @@ static int create_strip_zones(mddev_t *mddev) zone = conf->strip_zone + i; dev = conf->devlist + i * mddev->raid_disks; - printk(KERN_INFO "raid0: zone %d\n", i); + printk(KERN_INFO "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]; - printk(KERN_INFO "raid0: checking %s ...", - bdevname(rdev->bdev, b)); + printk(KERN_INFO "md/raid0:%s: checking %s ...", + mdname(mddev), + bdevname(rdev->bdev, b)); if (rdev->sectors <= zone->dev_start) { - printk(KERN_INFO " nope.\n"); + printk(KERN_CONT " nope.\n"); continue; } - printk(KERN_INFO " contained as device %d\n", c); + printk(KERN_CONT " contained as device %d\n", c); dev[c] = rdev; c++; if (!smallest || rdev->sectors < smallest->sectors) { smallest = rdev; - printk(KERN_INFO " (%llu) is smallest!.\n", - (unsigned long long)rdev->sectors); + printk(KERN_INFO "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; - printk(KERN_INFO "raid0: zone->nb_dev: %d, sectors: %llu\n", - zone->nb_dev, (unsigned long long)sectors); + printk(KERN_INFO "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; - printk(KERN_INFO "raid0: current zone start: %llu\n", - (unsigned long long)smallest->sectors); + printk(KERN_INFO "md/raid0:%s: current zone start: %llu\n", + mdname(mddev), + (unsigned long long)smallest->sectors); } mddev->queue->unplug_fn = raid0_unplug; mddev->queue->backing_dev_info.congested_fn = raid0_congested; @@ -249,7 +273,7 @@ static int create_strip_zones(mddev_t *mddev) * chunk size is a multiple of that sector size */ if ((mddev->chunk_sectors << 9) % queue_logical_block_size(mddev->queue)) { - printk(KERN_ERR "%s chunk_size of %d not valid\n", + printk(KERN_ERR "md/raid0:%s: chunk_size of %d not valid\n", mdname(mddev), mddev->chunk_sectors << 9); goto abort; @@ -259,14 +283,15 @@ static int create_strip_zones(mddev_t *mddev) blk_queue_io_opt(mddev->queue, (mddev->chunk_sectors << 9) * mddev->raid_disks); - printk(KERN_INFO "raid0: done.\n"); - mddev->private = conf; + printk(KERN_INFO "md/raid0:%s: done.\n", mdname(mddev)); + *private_conf = conf; + return 0; abort: kfree(conf->strip_zone); kfree(conf->devlist); kfree(conf); - mddev->private = NULL; + *private_conf = NULL; return err; } @@ -317,26 +342,34 @@ static sector_t raid0_size(mddev_t *mddev, sector_t sectors, int raid_disks) static int raid0_run(mddev_t *mddev) { + raid0_conf_t *conf; int ret; if (mddev->chunk_sectors == 0) { - printk(KERN_ERR "md/raid0: chunk size must be set.\n"); + printk(KERN_ERR "md/raid0:%s: chunk size must be set.\n", + mdname(mddev)); return -EINVAL; } if (md_check_no_bitmap(mddev)) return -EINVAL; - blk_queue_max_sectors(mddev->queue, mddev->chunk_sectors); + blk_queue_max_hw_sectors(mddev->queue, mddev->chunk_sectors); mddev->queue->queue_lock = &mddev->queue->__queue_lock; - ret = create_strip_zones(mddev); - if (ret < 0) - 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)); - printk(KERN_INFO "raid0 : md_size is %llu sectors.\n", - (unsigned long long)mddev->array_sectors); + printk(KERN_INFO "md/raid0:%s: md_size is %llu sectors.\n", + mdname(mddev), + (unsigned long long)mddev->array_sectors); /* calculate the max read-ahead size. * For read-ahead of large files to be effective, we need to * readahead at least twice a whole stripe. i.e. number of devices @@ -400,6 +433,7 @@ static mdk_rdev_t *map_sector(mddev_t *mddev, struct strip_zone *zone, unsigned int sect_in_chunk; sector_t chunk; raid0_conf_t *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)) { @@ -422,7 +456,7 @@ static mdk_rdev_t *map_sector(mddev_t *mddev, struct strip_zone *zone, * + the position in the chunk */ *sector_offset = (chunk * chunk_sects) + sect_in_chunk; - return conf->devlist[(zone - conf->strip_zone)*mddev->raid_disks + return conf->devlist[(zone - conf->strip_zone)*raid_disks + sector_div(sector, zone->nb_dev)]; } @@ -442,27 +476,18 @@ static inline int is_io_in_chunk_boundary(mddev_t *mddev, } } -static int raid0_make_request(struct request_queue *q, struct bio *bio) +static int raid0_make_request(mddev_t *mddev, struct bio *bio) { - mddev_t *mddev = q->queuedata; unsigned int chunk_sects; sector_t sector_offset; struct strip_zone *zone; mdk_rdev_t *tmp_dev; - const int rw = bio_data_dir(bio); - int cpu; if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER))) { md_barrier_request(mddev, bio); return 0; } - cpu = part_stat_lock(); - part_stat_inc(cpu, &mddev->gendisk->part0, ios[rw]); - part_stat_add(cpu, &mddev->gendisk->part0, sectors[rw], - bio_sectors(bio)); - part_stat_unlock(); - chunk_sects = mddev->chunk_sectors; if (unlikely(!is_io_in_chunk_boundary(mddev, chunk_sects, bio))) { sector_t sector = bio->bi_sector; @@ -480,9 +505,9 @@ static int raid0_make_request(struct request_queue *q, struct bio *bio) else bp = bio_split(bio, chunk_sects - sector_div(sector, chunk_sects)); - if (raid0_make_request(q, &bp->bio1)) + if (raid0_make_request(mddev, &bp->bio1)) generic_make_request(&bp->bio1); - if (raid0_make_request(q, &bp->bio2)) + if (raid0_make_request(mddev, &bp->bio2)) generic_make_request(&bp->bio2); bio_pair_release(bp); @@ -502,9 +527,10 @@ static int raid0_make_request(struct request_queue *q, struct bio *bio) return 1; bad_map: - printk("raid0_make_request bug: can't convert block across chunks" - " or bigger than %dk %llu %d\n", chunk_sects / 2, - (unsigned long long)bio->bi_sector, bio->bi_size >> 10); + printk("md/raid0:%s: make_request bug: can't convert block across chunks" + " or bigger than %dk %llu %d\n", + mdname(mddev), chunk_sects / 2, + (unsigned long long)bio->bi_sector, bio->bi_size >> 10); bio_io_error(bio); return 0; @@ -517,6 +543,7 @@ static void raid0_status(struct seq_file *seq, mddev_t *mddev) int j, k, h; char b[BDEVNAME_SIZE]; raid0_conf_t *conf = mddev->private; + int raid_disks = conf->strip_zone[0].nb_dev; sector_t zone_size; sector_t zone_start = 0; @@ -527,7 +554,7 @@ static void raid0_status(struct seq_file *seq, mddev_t *mddev) seq_printf(seq, "=["); for (k = 0; k < conf->strip_zone[j].nb_dev; k++) seq_printf(seq, "%s/", bdevname( - conf->devlist[j*mddev->raid_disks + k] + conf->devlist[j*raid_disks + k] ->bdev, b)); zone_size = conf->strip_zone[j].zone_end - zone_start; @@ -542,6 +569,109 @@ static void raid0_status(struct seq_file *seq, mddev_t *mddev) return; } +static void *raid0_takeover_raid45(mddev_t *mddev) +{ + mdk_rdev_t *rdev; + raid0_conf_t *priv_conf; + + if (mddev->degraded != 1) { + printk(KERN_ERR "md/raid0:%s: raid5 must be degraded! Degraded disks: %d\n", + mdname(mddev), + mddev->degraded); + return ERR_PTR(-EINVAL); + } + + list_for_each_entry(rdev, &mddev->disks, same_set) { + /* check slot number for a disk */ + if (rdev->raid_disk == mddev->raid_disks-1) { + printk(KERN_ERR "md/raid0:%s: raid5 must have missing parity disk!\n", + mdname(mddev)); + return ERR_PTR(-EINVAL); + } + } + + /* Set new parameters */ + mddev->new_level = 0; + mddev->new_layout = 0; + mddev->new_chunk_sectors = mddev->chunk_sectors; + mddev->raid_disks--; + mddev->delta_disks = -1; + /* make sure it will be not marked as dirty */ + mddev->recovery_cp = MaxSector; + + create_strip_zones(mddev, &priv_conf); + return priv_conf; +} + +static void *raid0_takeover_raid10(mddev_t *mddev) +{ + raid0_conf_t *priv_conf; + + /* Check layout: + * - far_copies must be 1 + * - near_copies must be 2 + * - disks number must be even + * - all mirrors must be already degraded + */ + if (mddev->layout != ((1 << 8) + 2)) { + printk(KERN_ERR "md/raid0:%s:: Raid0 cannot takover layout: 0x%x\n", + mdname(mddev), + mddev->layout); + return ERR_PTR(-EINVAL); + } + if (mddev->raid_disks & 1) { + printk(KERN_ERR "md/raid0:%s: Raid0 cannot takover Raid10 with odd disk number.\n", + mdname(mddev)); + return ERR_PTR(-EINVAL); + } + if (mddev->degraded != (mddev->raid_disks>>1)) { + printk(KERN_ERR "md/raid0:%s: All mirrors must be already degraded!\n", + mdname(mddev)); + return ERR_PTR(-EINVAL); + } + + /* Set new parameters */ + mddev->new_level = 0; + mddev->new_layout = 0; + mddev->new_chunk_sectors = mddev->chunk_sectors; + mddev->delta_disks = - mddev->raid_disks / 2; + mddev->raid_disks += mddev->delta_disks; + mddev->degraded = 0; + /* make sure it will be not marked as dirty */ + mddev->recovery_cp = MaxSector; + + create_strip_zones(mddev, &priv_conf); + return priv_conf; +} + +static void *raid0_takeover(mddev_t *mddev) +{ + /* raid0 can take over: + * raid4 - if all data disks are active. + * raid5 - providing it is Raid4 layout and one disk is faulty + * raid10 - assuming we have all necessary active disks + */ + if (mddev->level == 4) + return raid0_takeover_raid45(mddev); + + if (mddev->level == 5) { + if (mddev->layout == ALGORITHM_PARITY_N) + return raid0_takeover_raid45(mddev); + + printk(KERN_ERR "md/raid0:%s: Raid can only takeover Raid5 with layout: %d\n", + mdname(mddev), ALGORITHM_PARITY_N); + } + + if (mddev->level == 10) + return raid0_takeover_raid10(mddev); + + return ERR_PTR(-EINVAL); +} + +static void raid0_quiesce(mddev_t *mddev, int state) +{ +} + static struct mdk_personality raid0_personality= { .name = "raid0", @@ -552,6 +682,8 @@ static struct mdk_personality raid0_personality= .stop = raid0_stop, .status = raid0_status, .size = raid0_size, + .takeover = raid0_takeover, + .quiesce = raid0_quiesce, }; static int __init raid0_init (void) diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 859bd3ffe435..a948da8012de 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -31,6 +31,7 @@ * Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ +#include <linux/slab.h> #include <linux/delay.h> #include <linux/blkdev.h> #include <linux/seq_file.h> @@ -262,7 +263,7 @@ static inline void update_head_pos(int disk, r1bio_t *r1_bio) static void raid1_end_read_request(struct bio *bio, int error) { int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags); - r1bio_t * r1_bio = (r1bio_t *)(bio->bi_private); + r1bio_t *r1_bio = bio->bi_private; int mirror; conf_t *conf = r1_bio->mddev->private; @@ -296,7 +297,8 @@ static void raid1_end_read_request(struct bio *bio, int error) */ char b[BDEVNAME_SIZE]; if (printk_ratelimit()) - printk(KERN_ERR "raid1: %s: rescheduling sector %llu\n", + printk(KERN_ERR "md/raid1:%s: %s: rescheduling sector %llu\n", + mdname(conf->mddev), bdevname(conf->mirrors[mirror].rdev->bdev,b), (unsigned long long)r1_bio->sector); reschedule_retry(r1_bio); } @@ -307,7 +309,7 @@ static void raid1_end_read_request(struct bio *bio, int error) static void raid1_end_write_request(struct bio *bio, int error) { int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags); - r1bio_t * r1_bio = (r1bio_t *)(bio->bi_private); + r1bio_t *r1_bio = bio->bi_private; int mirror, behind = test_bit(R1BIO_BehindIO, &r1_bio->state); conf_t *conf = r1_bio->mddev->private; struct bio *to_put = NULL; @@ -417,7 +419,7 @@ static void raid1_end_write_request(struct bio *bio, int error) */ static int read_balance(conf_t *conf, r1bio_t *r1_bio) { - const unsigned long this_sector = r1_bio->sector; + const sector_t this_sector = r1_bio->sector; int new_disk = conf->last_used, disk = new_disk; int wonly_disk = -1; const int sectors = r1_bio->sectors; @@ -433,7 +435,7 @@ static int read_balance(conf_t *conf, r1bio_t *r1_bio) retry: if (conf->mddev->recovery_cp < MaxSector && (this_sector + sectors >= conf->next_resync)) { - /* Choose the first operation device, for consistancy */ + /* Choose the first operational device, for consistancy */ new_disk = 0; for (rdev = rcu_dereference(conf->mirrors[new_disk].rdev); @@ -773,9 +775,8 @@ do_sync_io: return NULL; } -static int make_request(struct request_queue *q, struct bio * bio) +static int make_request(mddev_t *mddev, struct bio * bio) { - mddev_t *mddev = q->queuedata; conf_t *conf = mddev->private; mirror_info_t *mirror; r1bio_t *r1_bio; @@ -787,7 +788,6 @@ static int make_request(struct request_queue *q, struct bio * bio) struct page **behind_pages = NULL; const int rw = bio_data_dir(bio); const bool do_sync = bio_rw_flagged(bio, BIO_RW_SYNCIO); - int cpu; bool do_barriers; mdk_rdev_t *blocked_rdev; @@ -833,12 +833,6 @@ static int make_request(struct request_queue *q, struct bio * bio) bitmap = mddev->bitmap; - cpu = part_stat_lock(); - part_stat_inc(cpu, &mddev->gendisk->part0, ios[rw]); - part_stat_add(cpu, &mddev->gendisk->part0, sectors[rw], - bio_sectors(bio)); - part_stat_unlock(); - /* * make_request() can abort the operation when READA is being * used and no empty request is available. @@ -865,6 +859,15 @@ static int make_request(struct request_queue *q, struct bio * bio) } mirror = conf->mirrors + rdisk; + if (test_bit(WriteMostly, &mirror->rdev->flags) && + bitmap) { + /* Reading from a write-mostly device must + * take care not to over-take any writes + * that are 'behind' + */ + wait_event(bitmap->behind_wait, + atomic_read(&bitmap->behind_writes) == 0); + } r1_bio->read_disk = rdisk; read_bio = bio_clone(bio, GFP_NOIO); @@ -911,9 +914,10 @@ static int make_request(struct request_queue *q, struct bio * bio) if (test_bit(Faulty, &rdev->flags)) { rdev_dec_pending(rdev, mddev); r1_bio->bios[i] = NULL; - } else + } else { r1_bio->bios[i] = bio; - targets++; + targets++; + } } else r1_bio->bios[i] = NULL; } @@ -941,10 +945,14 @@ static int make_request(struct request_queue *q, struct bio * bio) set_bit(R1BIO_Degraded, &r1_bio->state); } - /* do behind I/O ? */ + /* do behind I/O ? + * Not if there are too many, or cannot allocate memory, + * or a reader on WriteMostly is waiting for behind writes + * to flush */ if (bitmap && (atomic_read(&bitmap->behind_writes) < mddev->bitmap_info.max_write_behind) && + !waitqueue_active(&bitmap->behind_wait) && (behind_pages = alloc_behind_pages(bio)) != NULL) set_bit(R1BIO_BehindIO, &r1_bio->state); @@ -1069,21 +1077,22 @@ static void error(mddev_t *mddev, mdk_rdev_t *rdev) } else set_bit(Faulty, &rdev->flags); set_bit(MD_CHANGE_DEVS, &mddev->flags); - printk(KERN_ALERT "raid1: Disk failure on %s, disabling device.\n" - "raid1: Operation continuing on %d devices.\n", - bdevname(rdev->bdev,b), conf->raid_disks - mddev->degraded); + printk(KERN_ALERT "md/raid1:%s: Disk failure on %s, disabling device.\n" + KERN_ALERT "md/raid1:%s: Operation continuing on %d devices.\n", + mdname(mddev), bdevname(rdev->bdev, b), + mdname(mddev), conf->raid_disks - mddev->degraded); } static void print_conf(conf_t *conf) { int i; - printk("RAID1 conf printout:\n"); + printk(KERN_DEBUG "RAID1 conf printout:\n"); if (!conf) { - printk("(!conf)\n"); + printk(KERN_DEBUG "(!conf)\n"); return; } - printk(" --- wd:%d rd:%d\n", conf->raid_disks - conf->mddev->degraded, + printk(KERN_DEBUG " --- wd:%d rd:%d\n", conf->raid_disks - conf->mddev->degraded, conf->raid_disks); rcu_read_lock(); @@ -1091,7 +1100,7 @@ static void print_conf(conf_t *conf) char b[BDEVNAME_SIZE]; mdk_rdev_t *rdev = rcu_dereference(conf->mirrors[i].rdev); if (rdev) - printk(" disk %d, wo:%d, o:%d, dev:%s\n", + printk(KERN_DEBUG " disk %d, wo:%d, o:%d, dev:%s\n", i, !test_bit(In_sync, &rdev->flags), !test_bit(Faulty, &rdev->flags), bdevname(rdev->bdev,b)); @@ -1152,13 +1161,17 @@ static int raid1_add_disk(mddev_t *mddev, mdk_rdev_t *rdev) disk_stack_limits(mddev->gendisk, rdev->bdev, rdev->data_offset << 9); - /* as we don't honour merge_bvec_fn, we must never risk - * violating it, so limit ->max_sector to one PAGE, as - * a one page request is never in violation. + /* as we don't honour merge_bvec_fn, we must + * never risk violating it, so limit + * ->max_segments to one lying with a single + * page, as a one page request is never in + * violation. */ - if (rdev->bdev->bd_disk->queue->merge_bvec_fn && - queue_max_sectors(mddev->queue) > (PAGE_SIZE>>9)) - blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9); + if (rdev->bdev->bd_disk->queue->merge_bvec_fn) { + blk_queue_max_segments(mddev->queue, 1); + blk_queue_segment_boundary(mddev->queue, + PAGE_CACHE_SIZE - 1); + } p->head_position = 0; rdev->raid_disk = mirror; @@ -1218,7 +1231,7 @@ abort: static void end_sync_read(struct bio *bio, int error) { - r1bio_t * r1_bio = (r1bio_t *)(bio->bi_private); + r1bio_t *r1_bio = bio->bi_private; int i; for (i=r1_bio->mddev->raid_disks; i--; ) @@ -1241,7 +1254,7 @@ static void end_sync_read(struct bio *bio, int error) static void end_sync_write(struct bio *bio, int error) { int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags); - r1bio_t * r1_bio = (r1bio_t *)(bio->bi_private); + r1bio_t *r1_bio = bio->bi_private; mddev_t *mddev = r1_bio->mddev; conf_t *conf = mddev->private; int i; @@ -1448,9 +1461,10 @@ static void sync_request_write(mddev_t *mddev, r1bio_t *r1_bio) char b[BDEVNAME_SIZE]; /* Cannot read from anywhere, array is toast */ md_error(mddev, conf->mirrors[r1_bio->read_disk].rdev); - printk(KERN_ALERT "raid1: %s: unrecoverable I/O read error" + printk(KERN_ALERT "md/raid1:%s: %s: unrecoverable I/O read error" " for block %llu\n", - bdevname(bio->bi_bdev,b), + mdname(mddev), + bdevname(bio->bi_bdev, b), (unsigned long long)r1_bio->sector); md_done_sync(mddev, r1_bio->sectors, 0); put_buf(r1_bio); @@ -1572,7 +1586,7 @@ static void fix_read_error(conf_t *conf, int read_disk, else { atomic_add(s, &rdev->corrected_errors); printk(KERN_INFO - "raid1:%s: read error corrected " + "md/raid1:%s: read error corrected " "(%d sectors at %llu on %s)\n", mdname(mddev), s, (unsigned long long)(sect + @@ -1677,8 +1691,9 @@ static void raid1d(mddev_t *mddev) bio = r1_bio->bios[r1_bio->read_disk]; if ((disk=read_balance(conf, r1_bio)) == -1) { - printk(KERN_ALERT "raid1: %s: unrecoverable I/O" + printk(KERN_ALERT "md/raid1:%s: %s: unrecoverable I/O" " read error for block %llu\n", + mdname(mddev), bdevname(bio->bi_bdev,b), (unsigned long long)r1_bio->sector); raid_end_bio_io(r1_bio); @@ -1692,10 +1707,11 @@ static void raid1d(mddev_t *mddev) r1_bio->bios[r1_bio->read_disk] = bio; rdev = conf->mirrors[disk].rdev; if (printk_ratelimit()) - printk(KERN_ERR "raid1: %s: redirecting sector %llu to" - " another mirror\n", - bdevname(rdev->bdev,b), - (unsigned long long)r1_bio->sector); + printk(KERN_ERR "md/raid1:%s: redirecting sector %llu to" + " other mirror: %s\n", + mdname(mddev), + (unsigned long long)r1_bio->sector, + bdevname(rdev->bdev,b)); bio->bi_sector = r1_bio->sector + rdev->data_offset; bio->bi_bdev = rdev->bdev; bio->bi_end_io = raid1_end_read_request; @@ -1750,13 +1766,8 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i int still_degraded = 0; if (!conf->r1buf_pool) - { -/* - printk("sync start - bitmap %p\n", mddev->bitmap); -*/ if (init_resync(conf)) return 0; - } max_sector = mddev->dev_sectors; if (sector_nr >= max_sector) { @@ -2037,7 +2048,7 @@ static conf_t *setup_conf(mddev_t *mddev) err = -EIO; if (conf->last_used < 0) { - printk(KERN_ERR "raid1: no operational mirrors for %s\n", + printk(KERN_ERR "md/raid1:%s: no operational mirrors\n", mdname(mddev)); goto abort; } @@ -2045,7 +2056,7 @@ static conf_t *setup_conf(mddev_t *mddev) conf->thread = md_register_thread(raid1d, mddev, NULL); if (!conf->thread) { printk(KERN_ERR - "raid1: couldn't allocate thread for %s\n", + "md/raid1:%s: couldn't allocate thread\n", mdname(mddev)); goto abort; } @@ -2071,12 +2082,12 @@ static int run(mddev_t *mddev) mdk_rdev_t *rdev; if (mddev->level != 1) { - printk("raid1: %s: raid level not set to mirroring (%d)\n", + printk(KERN_ERR "md/raid1:%s: raid level not set to mirroring (%d)\n", mdname(mddev), mddev->level); return -EIO; } if (mddev->reshape_position != MaxSector) { - printk("raid1: %s: reshape_position set but not supported\n", + printk(KERN_ERR "md/raid1:%s: reshape_position set but not supported\n", mdname(mddev)); return -EIO; } @@ -2098,12 +2109,14 @@ static int run(mddev_t *mddev) disk_stack_limits(mddev->gendisk, rdev->bdev, rdev->data_offset << 9); /* as we don't honour merge_bvec_fn, we must never risk - * violating it, so limit ->max_sector to one PAGE, as - * a one page request is never in violation. + * violating it, so limit ->max_segments to 1 lying within + * a single page, as a one page request is never in violation. */ - if (rdev->bdev->bd_disk->queue->merge_bvec_fn && - queue_max_sectors(mddev->queue) > (PAGE_SIZE>>9)) - blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9); + if (rdev->bdev->bd_disk->queue->merge_bvec_fn) { + blk_queue_max_segments(mddev->queue, 1); + blk_queue_segment_boundary(mddev->queue, + PAGE_CACHE_SIZE - 1); + } } mddev->degraded = 0; @@ -2117,11 +2130,11 @@ static int run(mddev_t *mddev) mddev->recovery_cp = MaxSector; if (mddev->recovery_cp != MaxSector) - printk(KERN_NOTICE "raid1: %s is not clean" + printk(KERN_NOTICE "md/raid1:%s: not clean" " -- starting background reconstruction\n", mdname(mddev)); printk(KERN_INFO - "raid1: raid set %s active with %d out of %d mirrors\n", + "md/raid1:%s: active with %d out of %d mirrors\n", mdname(mddev), mddev->raid_disks - mddev->degraded, mddev->raid_disks); @@ -2145,15 +2158,14 @@ static int stop(mddev_t *mddev) { conf_t *conf = mddev->private; struct bitmap *bitmap = mddev->bitmap; - int behind_wait = 0; /* wait for behind writes to complete */ - while (bitmap && atomic_read(&bitmap->behind_writes) > 0) { - behind_wait++; - printk(KERN_INFO "raid1: behind writes in progress on device %s, waiting to stop (%d)\n", mdname(mddev), behind_wait); - set_current_state(TASK_UNINTERRUPTIBLE); - schedule_timeout(HZ); /* wait a second */ + if (bitmap && atomic_read(&bitmap->behind_writes) > 0) { + printk(KERN_INFO "md/raid1:%s: behind writes in progress - waiting to stop.\n", + mdname(mddev)); /* need to kick something here to make sure I/O goes? */ + wait_event(bitmap->behind_wait, + atomic_read(&bitmap->behind_writes) == 0); } raise_barrier(conf); @@ -2184,7 +2196,6 @@ static int raid1_resize(mddev_t *mddev, sector_t sectors) if (mddev->array_sectors > raid1_size(mddev, sectors, 0)) return -EINVAL; set_capacity(mddev->gendisk, mddev->array_sectors); - mddev->changed = 1; revalidate_disk(mddev->gendisk); if (sectors > mddev->dev_sectors && mddev->recovery_cp == MaxSector) { @@ -2279,9 +2290,9 @@ static int raid1_reshape(mddev_t *mddev) if (sysfs_create_link(&mddev->kobj, &rdev->kobj, nm)) printk(KERN_WARNING - "md/raid1: cannot register " - "%s for %s\n", - nm, mdname(mddev)); + "md/raid1:%s: cannot register " + "%s\n", + mdname(mddev), nm); } if (rdev) newmirrors[d2++].rdev = rdev; diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index d119b7b75e71..42e64e4e5e25 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -18,11 +18,13 @@ * Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ +#include <linux/slab.h> #include <linux/delay.h> #include <linux/blkdev.h> #include <linux/seq_file.h> #include "md.h" #include "raid10.h" +#include "raid0.h" #include "bitmap.h" /* @@ -254,7 +256,7 @@ static inline void update_head_pos(int slot, r10bio_t *r10_bio) static void raid10_end_read_request(struct bio *bio, int error) { int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags); - r10bio_t * r10_bio = (r10bio_t *)(bio->bi_private); + r10bio_t *r10_bio = bio->bi_private; int slot, dev; conf_t *conf = r10_bio->mddev->private; @@ -284,7 +286,8 @@ static void raid10_end_read_request(struct bio *bio, int error) */ char b[BDEVNAME_SIZE]; if (printk_ratelimit()) - printk(KERN_ERR "raid10: %s: rescheduling sector %llu\n", + printk(KERN_ERR "md/raid10:%s: %s: rescheduling sector %llu\n", + mdname(conf->mddev), bdevname(conf->mirrors[dev].rdev->bdev,b), (unsigned long long)r10_bio->sector); reschedule_retry(r10_bio); } @@ -295,7 +298,7 @@ static void raid10_end_read_request(struct bio *bio, int error) static void raid10_end_write_request(struct bio *bio, int error) { int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags); - r10bio_t * r10_bio = (r10bio_t *)(bio->bi_private); + r10bio_t *r10_bio = bio->bi_private; int slot, dev; conf_t *conf = r10_bio->mddev->private; @@ -493,7 +496,7 @@ static int raid10_mergeable_bvec(struct request_queue *q, */ static int read_balance(conf_t *conf, r10bio_t *r10_bio) { - const unsigned long this_sector = r10_bio->sector; + const sector_t this_sector = r10_bio->sector; int disk, slot, nslot; const int sectors = r10_bio->sectors; sector_t new_distance, current_distance; @@ -600,7 +603,7 @@ static void unplug_slaves(mddev_t *mddev) int i; rcu_read_lock(); - for (i=0; i<mddev->raid_disks; i++) { + for (i=0; i < conf->raid_disks; i++) { mdk_rdev_t *rdev = rcu_dereference(conf->mirrors[i].rdev); if (rdev && !test_bit(Faulty, &rdev->flags) && atomic_read(&rdev->nr_pending)) { struct request_queue *r_queue = bdev_get_queue(rdev->bdev); @@ -634,7 +637,7 @@ static int raid10_congested(void *data, int bits) if (mddev_congested(mddev, bits)) return 1; rcu_read_lock(); - for (i = 0; i < mddev->raid_disks && ret == 0; i++) { + for (i = 0; i < conf->raid_disks && ret == 0; i++) { mdk_rdev_t *rdev = rcu_dereference(conf->mirrors[i].rdev); if (rdev && !test_bit(Faulty, &rdev->flags)) { struct request_queue *q = bdev_get_queue(rdev->bdev); @@ -787,14 +790,12 @@ static void unfreeze_array(conf_t *conf) spin_unlock_irq(&conf->resync_lock); } -static int make_request(struct request_queue *q, struct bio * bio) +static int make_request(mddev_t *mddev, struct bio * bio) { - mddev_t *mddev = q->queuedata; conf_t *conf = mddev->private; mirror_info_t *mirror; r10bio_t *r10_bio; struct bio *read_bio; - int cpu; int i; int chunk_sects = conf->chunk_mask + 1; const int rw = bio_data_dir(bio); @@ -824,16 +825,16 @@ static int make_request(struct request_queue *q, struct bio * bio) */ bp = bio_split(bio, chunk_sects - (bio->bi_sector & (chunk_sects - 1)) ); - if (make_request(q, &bp->bio1)) + if (make_request(mddev, &bp->bio1)) generic_make_request(&bp->bio1); - if (make_request(q, &bp->bio2)) + if (make_request(mddev, &bp->bio2)) generic_make_request(&bp->bio2); bio_pair_release(bp); return 0; bad_map: - printk("raid10_make_request bug: can't convert block across chunks" - " or bigger than %dk %llu %d\n", chunk_sects/2, + printk("md/raid10:%s: make_request bug: can't convert block across chunks" + " or bigger than %dk %llu %d\n", mdname(mddev), chunk_sects/2, (unsigned long long)bio->bi_sector, bio->bi_size >> 10); bio_io_error(bio); @@ -849,12 +850,6 @@ static int make_request(struct request_queue *q, struct bio * bio) */ wait_barrier(conf); - cpu = part_stat_lock(); - part_stat_inc(cpu, &mddev->gendisk->part0, ios[rw]); - part_stat_add(cpu, &mddev->gendisk->part0, sectors[rw], - bio_sectors(bio)); - part_stat_unlock(); - r10_bio = mempool_alloc(conf->r10bio_pool, GFP_NOIO); r10_bio->master_bio = bio; @@ -1038,9 +1033,10 @@ static void error(mddev_t *mddev, mdk_rdev_t *rdev) } set_bit(Faulty, &rdev->flags); set_bit(MD_CHANGE_DEVS, &mddev->flags); - printk(KERN_ALERT "raid10: Disk failure on %s, disabling device.\n" - "raid10: Operation continuing on %d devices.\n", - bdevname(rdev->bdev,b), conf->raid_disks - mddev->degraded); + printk(KERN_ALERT "md/raid10:%s: Disk failure on %s, disabling device.\n" + KERN_ALERT "md/raid10:%s: Operation continuing on %d devices.\n", + mdname(mddev), bdevname(rdev->bdev, b), + mdname(mddev), conf->raid_disks - mddev->degraded); } static void print_conf(conf_t *conf) @@ -1048,19 +1044,19 @@ static void print_conf(conf_t *conf) int i; mirror_info_t *tmp; - printk("RAID10 conf printout:\n"); + printk(KERN_DEBUG "RAID10 conf printout:\n"); if (!conf) { - printk("(!conf)\n"); + printk(KERN_DEBUG "(!conf)\n"); return; } - printk(" --- wd:%d rd:%d\n", conf->raid_disks - conf->mddev->degraded, + printk(KERN_DEBUG " --- wd:%d rd:%d\n", conf->raid_disks - conf->mddev->degraded, conf->raid_disks); for (i = 0; i < conf->raid_disks; i++) { char b[BDEVNAME_SIZE]; tmp = conf->mirrors + i; if (tmp->rdev) - printk(" disk %d, wo:%d, o:%d, dev:%s\n", + printk(KERN_DEBUG " disk %d, wo:%d, o:%d, dev:%s\n", i, !test_bit(In_sync, &tmp->rdev->flags), !test_bit(Faulty, &tmp->rdev->flags), bdevname(tmp->rdev->bdev,b)); @@ -1131,7 +1127,7 @@ static int raid10_add_disk(mddev_t *mddev, mdk_rdev_t *rdev) int mirror; mirror_info_t *p; int first = 0; - int last = mddev->raid_disks - 1; + int last = conf->raid_disks - 1; if (mddev->recovery_cp < MaxSector) /* only hot-add to in-sync arrays, as recovery is @@ -1155,13 +1151,17 @@ static int raid10_add_disk(mddev_t *mddev, mdk_rdev_t *rdev) disk_stack_limits(mddev->gendisk, rdev->bdev, rdev->data_offset << 9); - /* as we don't honour merge_bvec_fn, we must never risk - * violating it, so limit ->max_sector to one PAGE, as - * a one page request is never in violation. + /* as we don't honour merge_bvec_fn, we must + * never risk violating it, so limit + * ->max_segments to one lying with a single + * page, as a one page request is never in + * violation. */ - if (rdev->bdev->bd_disk->queue->merge_bvec_fn && - queue_max_sectors(mddev->queue) > (PAGE_SIZE>>9)) - blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9); + if (rdev->bdev->bd_disk->queue->merge_bvec_fn) { + blk_queue_max_segments(mddev->queue, 1); + blk_queue_segment_boundary(mddev->queue, + PAGE_CACHE_SIZE - 1); + } p->head_position = 0; rdev->raid_disk = mirror; @@ -1219,7 +1219,7 @@ abort: static void end_sync_read(struct bio *bio, int error) { - r10bio_t * r10_bio = (r10bio_t *)(bio->bi_private); + r10bio_t *r10_bio = bio->bi_private; conf_t *conf = r10_bio->mddev->private; int i,d; @@ -1256,7 +1256,7 @@ static void end_sync_read(struct bio *bio, int error) static void end_sync_write(struct bio *bio, int error) { int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags); - r10bio_t * r10_bio = (r10bio_t *)(bio->bi_private); + r10bio_t *r10_bio = bio->bi_private; mddev_t *mddev = r10_bio->mddev; conf_t *conf = mddev->private; int i,d; @@ -1482,14 +1482,14 @@ static void fix_read_error(conf_t *conf, mddev_t *mddev, r10bio_t *r10_bio) int sectors = r10_bio->sectors; mdk_rdev_t*rdev; int max_read_errors = atomic_read(&mddev->max_corr_read_errors); + int d = r10_bio->devs[r10_bio->read_slot].devnum; rcu_read_lock(); - { - int d = r10_bio->devs[r10_bio->read_slot].devnum; + rdev = rcu_dereference(conf->mirrors[d].rdev); + if (rdev) { /* If rdev is not NULL */ char b[BDEVNAME_SIZE]; int cur_read_error_count = 0; - rdev = rcu_dereference(conf->mirrors[d].rdev); bdevname(rdev->bdev, b); if (test_bit(Faulty, &rdev->flags)) { @@ -1505,13 +1505,14 @@ static void fix_read_error(conf_t *conf, mddev_t *mddev, r10bio_t *r10_bio) if (cur_read_error_count > max_read_errors) { rcu_read_unlock(); printk(KERN_NOTICE - "raid10: %s: Raid device exceeded " + "md/raid10:%s: %s: Raid device exceeded " "read_error threshold " "[cur %d:max %d]\n", + mdname(mddev), b, cur_read_error_count, max_read_errors); printk(KERN_NOTICE - "raid10: %s: Failing raid " - "device\n", b); + "md/raid10:%s: %s: Failing raid " + "device\n", mdname(mddev), b); md_error(mddev, conf->mirrors[d].rdev); return; } @@ -1529,7 +1530,7 @@ static void fix_read_error(conf_t *conf, mddev_t *mddev, r10bio_t *r10_bio) rcu_read_lock(); do { - int d = r10_bio->devs[sl].devnum; + d = r10_bio->devs[sl].devnum; rdev = rcu_dereference(conf->mirrors[d].rdev); if (rdev && test_bit(In_sync, &rdev->flags)) { @@ -1563,7 +1564,7 @@ static void fix_read_error(conf_t *conf, mddev_t *mddev, r10bio_t *r10_bio) rcu_read_lock(); while (sl != r10_bio->read_slot) { char b[BDEVNAME_SIZE]; - int d; + if (sl==0) sl = conf->copies; sl--; @@ -1581,15 +1582,16 @@ static void fix_read_error(conf_t *conf, mddev_t *mddev, r10bio_t *r10_bio) == 0) { /* Well, this device is dead */ printk(KERN_NOTICE - "raid10:%s: read correction " + "md/raid10:%s: read correction " "write failed" " (%d sectors at %llu on %s)\n", mdname(mddev), s, (unsigned long long)(sect+ rdev->data_offset), bdevname(rdev->bdev, b)); - printk(KERN_NOTICE "raid10:%s: failing " + printk(KERN_NOTICE "md/raid10:%s: %s: failing " "drive\n", + mdname(mddev), bdevname(rdev->bdev, b)); md_error(mddev, rdev); } @@ -1599,7 +1601,7 @@ static void fix_read_error(conf_t *conf, mddev_t *mddev, r10bio_t *r10_bio) } sl = start; while (sl != r10_bio->read_slot) { - int d; + if (sl==0) sl = conf->copies; sl--; @@ -1617,20 +1619,21 @@ static void fix_read_error(conf_t *conf, mddev_t *mddev, r10bio_t *r10_bio) READ) == 0) { /* Well, this device is dead */ printk(KERN_NOTICE - "raid10:%s: unable to read back " + "md/raid10:%s: unable to read back " "corrected sectors" " (%d sectors at %llu on %s)\n", mdname(mddev), s, (unsigned long long)(sect+ rdev->data_offset), bdevname(rdev->bdev, b)); - printk(KERN_NOTICE "raid10:%s: failing drive\n", + printk(KERN_NOTICE "md/raid10:%s: %s: failing drive\n", + mdname(mddev), bdevname(rdev->bdev, b)); md_error(mddev, rdev); } else { printk(KERN_INFO - "raid10:%s: read error corrected" + "md/raid10:%s: read error corrected" " (%d sectors at %llu on %s)\n", mdname(mddev), s, (unsigned long long)(sect+ @@ -1705,8 +1708,9 @@ static void raid10d(mddev_t *mddev) mddev->ro ? IO_BLOCKED : NULL; mirror = read_balance(conf, r10_bio); if (mirror == -1) { - printk(KERN_ALERT "raid10: %s: unrecoverable I/O" + printk(KERN_ALERT "md/raid10:%s: %s: unrecoverable I/O" " read error for block %llu\n", + mdname(mddev), bdevname(bio->bi_bdev,b), (unsigned long long)r10_bio->sector); raid_end_bio_io(r10_bio); @@ -1716,8 +1720,9 @@ static void raid10d(mddev_t *mddev) bio_put(bio); rdev = conf->mirrors[mirror].rdev; if (printk_ratelimit()) - printk(KERN_ERR "raid10: %s: redirecting sector %llu to" + printk(KERN_ERR "md/raid10:%s: %s: redirecting sector %llu to" " another mirror\n", + mdname(mddev), bdevname(rdev->bdev,b), (unsigned long long)r10_bio->sector); bio = bio_clone(r10_bio->master_bio, GFP_NOIO); @@ -1975,7 +1980,8 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i r10_bio = rb2; if (!test_and_set_bit(MD_RECOVERY_INTR, &mddev->recovery)) - printk(KERN_INFO "raid10: %s: insufficient working devices for recovery.\n", + printk(KERN_INFO "md/raid10:%s: insufficient " + "working devices for recovery.\n", mdname(mddev)); break; } @@ -2135,9 +2141,9 @@ raid10_size(mddev_t *mddev, sector_t sectors, int raid_disks) conf_t *conf = mddev->private; if (!raid_disks) - raid_disks = mddev->raid_disks; + raid_disks = conf->raid_disks; if (!sectors) - sectors = mddev->dev_sectors; + sectors = conf->dev_sectors; size = sectors >> conf->chunk_shift; sector_div(size, conf->far_copies); @@ -2147,62 +2153,61 @@ raid10_size(mddev_t *mddev, sector_t sectors, int raid_disks) return size << conf->chunk_shift; } -static int run(mddev_t *mddev) + +static conf_t *setup_conf(mddev_t *mddev) { - conf_t *conf; - int i, disk_idx, chunk_size; - mirror_info_t *disk; - mdk_rdev_t *rdev; + conf_t *conf = NULL; int nc, fc, fo; sector_t stride, size; + int err = -EINVAL; - if (mddev->chunk_sectors < (PAGE_SIZE >> 9) || - !is_power_of_2(mddev->chunk_sectors)) { - printk(KERN_ERR "md/raid10: chunk size must be " - "at least PAGE_SIZE(%ld) and be a power of 2.\n", PAGE_SIZE); - return -EINVAL; + if (mddev->new_chunk_sectors < (PAGE_SIZE >> 9) || + !is_power_of_2(mddev->new_chunk_sectors)) { + printk(KERN_ERR "md/raid10:%s: chunk size must be " + "at least PAGE_SIZE(%ld) and be a power of 2.\n", + mdname(mddev), PAGE_SIZE); + goto out; } - nc = mddev->layout & 255; - fc = (mddev->layout >> 8) & 255; - fo = mddev->layout & (1<<16); + nc = mddev->new_layout & 255; + fc = (mddev->new_layout >> 8) & 255; + fo = mddev->new_layout & (1<<16); + if ((nc*fc) <2 || (nc*fc) > mddev->raid_disks || - (mddev->layout >> 17)) { - printk(KERN_ERR "raid10: %s: unsupported raid10 layout: 0x%8x\n", - mdname(mddev), mddev->layout); + (mddev->new_layout >> 17)) { + printk(KERN_ERR "md/raid10:%s: unsupported raid10 layout: 0x%8x\n", + mdname(mddev), mddev->new_layout); goto out; } - /* - * copy the already verified devices into our private RAID10 - * bookkeeping area. [whatever we allocate in run(), - * should be freed in stop()] - */ + + err = -ENOMEM; conf = kzalloc(sizeof(conf_t), GFP_KERNEL); - mddev->private = conf; - if (!conf) { - printk(KERN_ERR "raid10: couldn't allocate memory for %s\n", - mdname(mddev)); + if (!conf) goto out; - } + conf->mirrors = kzalloc(sizeof(struct mirror_info)*mddev->raid_disks, - GFP_KERNEL); - if (!conf->mirrors) { - printk(KERN_ERR "raid10: couldn't allocate memory for %s\n", - mdname(mddev)); - goto out_free_conf; - } + GFP_KERNEL); + if (!conf->mirrors) + goto out; conf->tmppage = alloc_page(GFP_KERNEL); if (!conf->tmppage) - goto out_free_conf; + goto out; + conf->raid_disks = mddev->raid_disks; conf->near_copies = nc; conf->far_copies = fc; conf->copies = nc*fc; conf->far_offset = fo; - conf->chunk_mask = mddev->chunk_sectors - 1; - conf->chunk_shift = ffz(~mddev->chunk_sectors); + conf->chunk_mask = mddev->new_chunk_sectors - 1; + conf->chunk_shift = ffz(~mddev->new_chunk_sectors); + + conf->r10bio_pool = mempool_create(NR_RAID10_BIOS, r10bio_pool_alloc, + r10bio_pool_free, conf); + if (!conf->r10bio_pool) + goto out; + size = mddev->dev_sectors >> conf->chunk_shift; sector_div(size, fc); size = size * conf->raid_disks; @@ -2216,7 +2221,8 @@ static int run(mddev_t *mddev) */ stride += conf->raid_disks - 1; sector_div(stride, conf->raid_disks); - mddev->dev_sectors = stride << conf->chunk_shift; + + conf->dev_sectors = stride << conf->chunk_shift; if (fo) stride = 1; @@ -2224,18 +2230,62 @@ static int run(mddev_t *mddev) sector_div(stride, fc); conf->stride = stride << conf->chunk_shift; - conf->r10bio_pool = mempool_create(NR_RAID10_BIOS, r10bio_pool_alloc, - r10bio_pool_free, conf); - if (!conf->r10bio_pool) { - printk(KERN_ERR "raid10: couldn't allocate memory for %s\n", - mdname(mddev)); - goto out_free_conf; - } - conf->mddev = mddev; spin_lock_init(&conf->device_lock); + INIT_LIST_HEAD(&conf->retry_list); + + spin_lock_init(&conf->resync_lock); + init_waitqueue_head(&conf->wait_barrier); + + conf->thread = md_register_thread(raid10d, mddev, NULL); + if (!conf->thread) + goto out; + + conf->mddev = mddev; + return conf; + + out: + printk(KERN_ERR "md/raid10:%s: couldn't allocate memory.\n", + mdname(mddev)); + if (conf) { + if (conf->r10bio_pool) + mempool_destroy(conf->r10bio_pool); + kfree(conf->mirrors); + safe_put_page(conf->tmppage); + kfree(conf); + } + return ERR_PTR(err); +} + +static int run(mddev_t *mddev) +{ + conf_t *conf; + int i, disk_idx, chunk_size; + mirror_info_t *disk; + mdk_rdev_t *rdev; + sector_t size; + + /* + * copy the already verified devices into our private RAID10 + * bookkeeping area. [whatever we allocate in run(), + * should be freed in stop()] + */ + + if (mddev->private == NULL) { + conf = setup_conf(mddev); + if (IS_ERR(conf)) + return PTR_ERR(conf); + mddev->private = conf; + } + conf = mddev->private; + if (!conf) + goto out; + mddev->queue->queue_lock = &conf->device_lock; + mddev->thread = conf->thread; + conf->thread = NULL; + chunk_size = mddev->chunk_sectors << 9; blk_queue_io_min(mddev->queue, chunk_size); if (conf->raid_disks % conf->near_copies) @@ -2246,7 +2296,7 @@ static int run(mddev_t *mddev) list_for_each_entry(rdev, &mddev->disks, same_set) { disk_idx = rdev->raid_disk; - if (disk_idx >= mddev->raid_disks + if (disk_idx >= conf->raid_disks || disk_idx < 0) continue; disk = conf->mirrors + disk_idx; @@ -2255,23 +2305,20 @@ static int run(mddev_t *mddev) disk_stack_limits(mddev->gendisk, rdev->bdev, rdev->data_offset << 9); /* as we don't honour merge_bvec_fn, we must never risk - * violating it, so limit ->max_sector to one PAGE, as - * a one page request is never in violation. + * violating it, so limit max_segments to 1 lying + * within a single page. */ - if (rdev->bdev->bd_disk->queue->merge_bvec_fn && - queue_max_sectors(mddev->queue) > (PAGE_SIZE>>9)) - blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9); + if (rdev->bdev->bd_disk->queue->merge_bvec_fn) { + blk_queue_max_segments(mddev->queue, 1); + blk_queue_segment_boundary(mddev->queue, + PAGE_CACHE_SIZE - 1); + } disk->head_position = 0; } - INIT_LIST_HEAD(&conf->retry_list); - - spin_lock_init(&conf->resync_lock); - init_waitqueue_head(&conf->wait_barrier); - /* need to check that every block has at least one working mirror */ if (!enough(conf)) { - printk(KERN_ERR "raid10: not enough operational mirrors for %s\n", + printk(KERN_ERR "md/raid10:%s: not enough operational mirrors.\n", mdname(mddev)); goto out_free_conf; } @@ -2290,28 +2337,21 @@ static int run(mddev_t *mddev) } } - - mddev->thread = md_register_thread(raid10d, mddev, NULL); - if (!mddev->thread) { - printk(KERN_ERR - "raid10: couldn't allocate thread for %s\n", - mdname(mddev)); - goto out_free_conf; - } - if (mddev->recovery_cp != MaxSector) - printk(KERN_NOTICE "raid10: %s is not clean" + printk(KERN_NOTICE "md/raid10:%s: not clean" " -- starting background reconstruction\n", mdname(mddev)); printk(KERN_INFO - "raid10: raid set %s active with %d out of %d devices\n", - mdname(mddev), mddev->raid_disks - mddev->degraded, - mddev->raid_disks); + "md/raid10:%s: active with %d out of %d devices\n", + mdname(mddev), conf->raid_disks - mddev->degraded, + conf->raid_disks); /* * Ok, everything is just fine now */ - md_set_array_sectors(mddev, raid10_size(mddev, 0, 0)); - mddev->resync_max_sectors = raid10_size(mddev, 0, 0); + mddev->dev_sectors = conf->dev_sectors; + size = raid10_size(mddev, 0, 0); + md_set_array_sectors(mddev, size); + mddev->resync_max_sectors = size; mddev->queue->unplug_fn = raid10_unplug; mddev->queue->backing_dev_info.congested_fn = raid10_congested; @@ -2329,7 +2369,7 @@ static int run(mddev_t *mddev) mddev->queue->backing_dev_info.ra_pages = 2* stripe; } - if (conf->near_copies < mddev->raid_disks) + if (conf->near_copies < conf->raid_disks) blk_queue_merge_bvec(mddev->queue, raid10_mergeable_bvec); md_integrity_register(mddev); return 0; @@ -2341,6 +2381,7 @@ out_free_conf: kfree(conf->mirrors); kfree(conf); mddev->private = NULL; + md_unregister_thread(mddev->thread); out: return -EIO; } @@ -2377,6 +2418,57 @@ static void raid10_quiesce(mddev_t *mddev, int state) } } +static void *raid10_takeover_raid0(mddev_t *mddev) +{ + mdk_rdev_t *rdev; + conf_t *conf; + + if (mddev->degraded > 0) { + printk(KERN_ERR "md/raid10:%s: Error: degraded raid0!\n", + mdname(mddev)); + return ERR_PTR(-EINVAL); + } + + /* Set new parameters */ + mddev->new_level = 10; + /* new layout: far_copies = 1, near_copies = 2 */ + mddev->new_layout = (1<<8) + 2; + mddev->new_chunk_sectors = mddev->chunk_sectors; + mddev->delta_disks = mddev->raid_disks; + mddev->raid_disks *= 2; + /* make sure it will be not marked as dirty */ + mddev->recovery_cp = MaxSector; + + conf = setup_conf(mddev); + if (!IS_ERR(conf)) + list_for_each_entry(rdev, &mddev->disks, same_set) + if (rdev->raid_disk >= 0) + rdev->new_raid_disk = rdev->raid_disk * 2; + + return conf; +} + +static void *raid10_takeover(mddev_t *mddev) +{ + struct raid0_private_data *raid0_priv; + + /* raid10 can take over: + * raid0 - providing it has only two drives + */ + if (mddev->level == 0) { + /* for raid0 takeover only one zone is supported */ + raid0_priv = mddev->private; + if (raid0_priv->nr_strip_zones > 1) { + printk(KERN_ERR "md/raid10:%s: cannot takeover raid 0" + " with more than one zone.\n", + mdname(mddev)); + return ERR_PTR(-EINVAL); + } + return raid10_takeover_raid0(mddev); + } + return ERR_PTR(-EINVAL); +} + static struct mdk_personality raid10_personality = { .name = "raid10", @@ -2393,6 +2485,7 @@ static struct mdk_personality raid10_personality = .sync_request = sync_request, .quiesce = raid10_quiesce, .size = raid10_size, + .takeover = raid10_takeover, }; static int __init raid_init(void) diff --git a/drivers/md/raid10.h b/drivers/md/raid10.h index 59cd1efb8d30..2316ac2e8e21 100644 --- a/drivers/md/raid10.h +++ b/drivers/md/raid10.h @@ -33,6 +33,8 @@ struct r10_private_data_s { * 1 stripe. */ + sector_t dev_sectors; /* temp copy of mddev->dev_sectors */ + int chunk_shift; /* shift from chunks to sectors */ sector_t chunk_mask; @@ -57,6 +59,11 @@ struct r10_private_data_s { mempool_t *r10bio_pool; mempool_t *r10buf_pool; struct page *tmppage; + + /* When taking over an array from a different personality, we store + * the new thread here until we fully activate the array. + */ + struct mdk_thread_s *thread; }; typedef struct r10_private_data_s conf_t; diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index ceb24afdc147..96c690279fc6 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -50,8 +50,10 @@ #include <linux/async.h> #include <linux/seq_file.h> #include <linux/cpu.h> +#include <linux/slab.h> #include "md.h" #include "raid5.h" +#include "raid0.h" #include "bitmap.h" /* @@ -275,12 +277,13 @@ out: return sh; } -static void shrink_buffers(struct stripe_head *sh, int num) +static void shrink_buffers(struct stripe_head *sh) { struct page *p; int i; + int num = sh->raid_conf->pool_size; - for (i=0; i<num ; i++) { + for (i = 0; i < num ; i++) { p = sh->dev[i].page; if (!p) continue; @@ -289,11 +292,12 @@ static void shrink_buffers(struct stripe_head *sh, int num) } } -static int grow_buffers(struct stripe_head *sh, int num) +static int grow_buffers(struct stripe_head *sh) { int i; + int num = sh->raid_conf->pool_size; - for (i=0; i<num; i++) { + for (i = 0; i < num; i++) { struct page *page; if (!(page = alloc_page(GFP_KERNEL))) { @@ -362,6 +366,73 @@ static struct stripe_head *__find_stripe(raid5_conf_t *conf, sector_t sector, return NULL; } +/* + * Need to check if array has failed when deciding whether to: + * - start an array + * - remove non-faulty devices + * - add a spare + * - allow a reshape + * This determination is simple when no reshape is happening. + * However if there is a reshape, we need to carefully check + * both the before and after sections. + * This is because some failed devices may only affect one + * of the two sections, and some non-in_sync devices may + * be insync in the section most affected by failed devices. + */ +static int has_failed(raid5_conf_t *conf) +{ + int degraded; + int i; + if (conf->mddev->reshape_position == MaxSector) + return conf->mddev->degraded > conf->max_degraded; + + rcu_read_lock(); + degraded = 0; + for (i = 0; i < conf->previous_raid_disks; i++) { + mdk_rdev_t *rdev = rcu_dereference(conf->disks[i].rdev); + if (!rdev || test_bit(Faulty, &rdev->flags)) + degraded++; + else if (test_bit(In_sync, &rdev->flags)) + ; + else + /* not in-sync or faulty. + * If the reshape increases the number of devices, + * this is being recovered by the reshape, so + * this 'previous' section is not in_sync. + * If the number of devices is being reduced however, + * the device can only be part of the array if + * we are reverting a reshape, so this section will + * be in-sync. + */ + if (conf->raid_disks >= conf->previous_raid_disks) + degraded++; + } + rcu_read_unlock(); + if (degraded > conf->max_degraded) + return 1; + rcu_read_lock(); + degraded = 0; + for (i = 0; i < conf->raid_disks; i++) { + mdk_rdev_t *rdev = rcu_dereference(conf->disks[i].rdev); + if (!rdev || test_bit(Faulty, &rdev->flags)) + degraded++; + else if (test_bit(In_sync, &rdev->flags)) + ; + else + /* not in-sync or faulty. + * If reshape increases the number of devices, this + * section has already been recovered, else it + * almost certainly hasn't. + */ + if (conf->raid_disks <= conf->previous_raid_disks) + degraded++; + } + rcu_read_unlock(); + if (degraded > conf->max_degraded) + return 1; + return 0; +} + static void unplug_slaves(mddev_t *mddev); static void raid5_unplug_device(struct request_queue *q); @@ -1238,19 +1309,18 @@ static void raid_run_ops(struct stripe_head *sh, unsigned long ops_request) static int grow_one_stripe(raid5_conf_t *conf) { struct stripe_head *sh; - int disks = max(conf->raid_disks, conf->previous_raid_disks); sh = kmem_cache_alloc(conf->slab_cache, GFP_KERNEL); if (!sh) return 0; - memset(sh, 0, sizeof(*sh) + (disks-1)*sizeof(struct r5dev)); + memset(sh, 0, sizeof(*sh) + (conf->pool_size-1)*sizeof(struct r5dev)); sh->raid_conf = conf; spin_lock_init(&sh->lock); #ifdef CONFIG_MULTICORE_RAID456 init_waitqueue_head(&sh->ops.wait_for_ops); #endif - if (grow_buffers(sh, disks)) { - shrink_buffers(sh, disks); + if (grow_buffers(sh)) { + shrink_buffers(sh); kmem_cache_free(conf->slab_cache, sh); return 0; } @@ -1466,7 +1536,7 @@ static int drop_one_stripe(raid5_conf_t *conf) if (!sh) return 0; BUG_ON(atomic_read(&sh->count)); - shrink_buffers(sh, conf->pool_size); + shrink_buffers(sh); kmem_cache_free(conf->slab_cache, sh); atomic_dec(&conf->active_stripes); return 1; @@ -1508,7 +1578,7 @@ static void raid5_end_read_request(struct bio * bi, int error) set_bit(R5_UPTODATE, &sh->dev[i].flags); if (test_bit(R5_ReadError, &sh->dev[i].flags)) { rdev = conf->disks[i].rdev; - printk_rl(KERN_INFO "raid5:%s: read error corrected" + printk_rl(KERN_INFO "md/raid:%s: read error corrected" " (%lu sectors at %llu on %s)\n", mdname(conf->mddev), STRIPE_SECTORS, (unsigned long long)(sh->sector @@ -1526,9 +1596,9 @@ static void raid5_end_read_request(struct bio * bi, int error) clear_bit(R5_UPTODATE, &sh->dev[i].flags); atomic_inc(&rdev->read_errors); - if (conf->mddev->degraded) + if (conf->mddev->degraded >= conf->max_degraded) printk_rl(KERN_WARNING - "raid5:%s: read error not correctable " + "md/raid:%s: read error not correctable " "(sector %llu on %s).\n", mdname(conf->mddev), (unsigned long long)(sh->sector @@ -1537,7 +1607,7 @@ static void raid5_end_read_request(struct bio * bi, int error) else if (test_bit(R5_ReWrite, &sh->dev[i].flags)) /* Oh, no!!! */ printk_rl(KERN_WARNING - "raid5:%s: read error NOT corrected!! " + "md/raid:%s: read error NOT corrected!! " "(sector %llu on %s).\n", mdname(conf->mddev), (unsigned long long)(sh->sector @@ -1546,7 +1616,7 @@ static void raid5_end_read_request(struct bio * bi, int error) else if (atomic_read(&rdev->read_errors) > conf->max_nr_stripes) printk(KERN_WARNING - "raid5:%s: Too many read errors, failing device %s.\n", + "md/raid:%s: Too many read errors, failing device %s.\n", mdname(conf->mddev), bdn); else retry = 1; @@ -1618,8 +1688,8 @@ static void raid5_build_block(struct stripe_head *sh, int i, int previous) static void error(mddev_t *mddev, mdk_rdev_t *rdev) { char b[BDEVNAME_SIZE]; - raid5_conf_t *conf = (raid5_conf_t *) mddev->private; - pr_debug("raid5: error called\n"); + raid5_conf_t *conf = mddev->private; + pr_debug("raid456: error called\n"); if (!test_bit(Faulty, &rdev->flags)) { set_bit(MD_CHANGE_DEVS, &mddev->flags); @@ -1635,9 +1705,13 @@ static void error(mddev_t *mddev, mdk_rdev_t *rdev) } set_bit(Faulty, &rdev->flags); printk(KERN_ALERT - "raid5: Disk failure on %s, disabling device.\n" - "raid5: Operation continuing on %d devices.\n", - bdevname(rdev->bdev,b), conf->raid_disks - mddev->degraded); + "md/raid:%s: Disk failure on %s, disabling device.\n" + KERN_ALERT + "md/raid:%s: Operation continuing on %d devices.\n", + mdname(mddev), + bdevname(rdev->bdev, b), + mdname(mddev), + conf->raid_disks - mddev->degraded); } } @@ -1649,8 +1723,8 @@ static sector_t raid5_compute_sector(raid5_conf_t *conf, sector_t r_sector, int previous, int *dd_idx, struct stripe_head *sh) { - long stripe; - unsigned long chunk_number; + sector_t stripe, stripe2; + sector_t chunk_number; unsigned int chunk_offset; int pd_idx, qd_idx; int ddf_layout = 0; @@ -1670,18 +1744,13 @@ static sector_t raid5_compute_sector(raid5_conf_t *conf, sector_t r_sector, */ chunk_offset = sector_div(r_sector, sectors_per_chunk); chunk_number = r_sector; - BUG_ON(r_sector != chunk_number); /* * Compute the stripe number */ - stripe = chunk_number / data_disks; - - /* - * Compute the data disk and parity disk indexes inside the stripe - */ - *dd_idx = chunk_number % data_disks; - + stripe = chunk_number; + *dd_idx = sector_div(stripe, data_disks); + stripe2 = stripe; /* * Select the parity disk based on the user selected algorithm. */ @@ -1693,21 +1762,21 @@ static sector_t raid5_compute_sector(raid5_conf_t *conf, sector_t r_sector, case 5: switch (algorithm) { case ALGORITHM_LEFT_ASYMMETRIC: - pd_idx = data_disks - stripe % raid_disks; + pd_idx = data_disks - sector_div(stripe2, raid_disks); if (*dd_idx >= pd_idx) (*dd_idx)++; break; case ALGORITHM_RIGHT_ASYMMETRIC: - pd_idx = stripe % raid_disks; + pd_idx = sector_div(stripe2, raid_disks); if (*dd_idx >= pd_idx) (*dd_idx)++; break; case ALGORITHM_LEFT_SYMMETRIC: - pd_idx = data_disks - stripe % raid_disks; + pd_idx = data_disks - sector_div(stripe2, raid_disks); *dd_idx = (pd_idx + 1 + *dd_idx) % raid_disks; break; case ALGORITHM_RIGHT_SYMMETRIC: - pd_idx = stripe % raid_disks; + pd_idx = sector_div(stripe2, raid_disks); *dd_idx = (pd_idx + 1 + *dd_idx) % raid_disks; break; case ALGORITHM_PARITY_0: @@ -1718,8 +1787,6 @@ static sector_t raid5_compute_sector(raid5_conf_t *conf, sector_t r_sector, pd_idx = data_disks; break; default: - printk(KERN_ERR "raid5: unsupported algorithm %d\n", - algorithm); BUG(); } break; @@ -1727,7 +1794,7 @@ static sector_t raid5_compute_sector(raid5_conf_t *conf, sector_t r_sector, switch (algorithm) { case ALGORITHM_LEFT_ASYMMETRIC: - pd_idx = raid_disks - 1 - (stripe % raid_disks); + pd_idx = raid_disks - 1 - sector_div(stripe2, raid_disks); qd_idx = pd_idx + 1; if (pd_idx == raid_disks-1) { (*dd_idx)++; /* Q D D D P */ @@ -1736,7 +1803,7 @@ static sector_t raid5_compute_sector(raid5_conf_t *conf, sector_t r_sector, (*dd_idx) += 2; /* D D P Q D */ break; case ALGORITHM_RIGHT_ASYMMETRIC: - pd_idx = stripe % raid_disks; + pd_idx = sector_div(stripe2, raid_disks); qd_idx = pd_idx + 1; if (pd_idx == raid_disks-1) { (*dd_idx)++; /* Q D D D P */ @@ -1745,12 +1812,12 @@ static sector_t raid5_compute_sector(raid5_conf_t *conf, sector_t r_sector, (*dd_idx) += 2; /* D D P Q D */ break; case ALGORITHM_LEFT_SYMMETRIC: - pd_idx = raid_disks - 1 - (stripe % raid_disks); + pd_idx = raid_disks - 1 - sector_div(stripe2, raid_disks); qd_idx = (pd_idx + 1) % raid_disks; *dd_idx = (pd_idx + 2 + *dd_idx) % raid_disks; break; case ALGORITHM_RIGHT_SYMMETRIC: - pd_idx = stripe % raid_disks; + pd_idx = sector_div(stripe2, raid_disks); qd_idx = (pd_idx + 1) % raid_disks; *dd_idx = (pd_idx + 2 + *dd_idx) % raid_disks; break; @@ -1769,7 +1836,7 @@ static sector_t raid5_compute_sector(raid5_conf_t *conf, sector_t r_sector, /* Exactly the same as RIGHT_ASYMMETRIC, but or * of blocks for computing Q is different. */ - pd_idx = stripe % raid_disks; + pd_idx = sector_div(stripe2, raid_disks); qd_idx = pd_idx + 1; if (pd_idx == raid_disks-1) { (*dd_idx)++; /* Q D D D P */ @@ -1784,7 +1851,8 @@ static sector_t raid5_compute_sector(raid5_conf_t *conf, sector_t r_sector, * D D D P Q rather than * Q D D D P */ - pd_idx = raid_disks - 1 - ((stripe + 1) % raid_disks); + stripe2 += 1; + pd_idx = raid_disks - 1 - sector_div(stripe2, raid_disks); qd_idx = pd_idx + 1; if (pd_idx == raid_disks-1) { (*dd_idx)++; /* Q D D D P */ @@ -1796,7 +1864,7 @@ static sector_t raid5_compute_sector(raid5_conf_t *conf, sector_t r_sector, case ALGORITHM_ROTATING_N_CONTINUE: /* Same as left_symmetric but Q is before P */ - pd_idx = raid_disks - 1 - (stripe % raid_disks); + pd_idx = raid_disks - 1 - sector_div(stripe2, raid_disks); qd_idx = (pd_idx + raid_disks - 1) % raid_disks; *dd_idx = (pd_idx + 1 + *dd_idx) % raid_disks; ddf_layout = 1; @@ -1804,27 +1872,27 @@ static sector_t raid5_compute_sector(raid5_conf_t *conf, sector_t r_sector, case ALGORITHM_LEFT_ASYMMETRIC_6: /* RAID5 left_asymmetric, with Q on last device */ - pd_idx = data_disks - stripe % (raid_disks-1); + pd_idx = data_disks - sector_div(stripe2, raid_disks-1); if (*dd_idx >= pd_idx) (*dd_idx)++; qd_idx = raid_disks - 1; break; case ALGORITHM_RIGHT_ASYMMETRIC_6: - pd_idx = stripe % (raid_disks-1); + pd_idx = sector_div(stripe2, raid_disks-1); if (*dd_idx >= pd_idx) (*dd_idx)++; qd_idx = raid_disks - 1; break; case ALGORITHM_LEFT_SYMMETRIC_6: - pd_idx = data_disks - stripe % (raid_disks-1); + pd_idx = data_disks - sector_div(stripe2, raid_disks-1); *dd_idx = (pd_idx + 1 + *dd_idx) % (raid_disks-1); qd_idx = raid_disks - 1; break; case ALGORITHM_RIGHT_SYMMETRIC_6: - pd_idx = stripe % (raid_disks-1); + pd_idx = sector_div(stripe2, raid_disks-1); *dd_idx = (pd_idx + 1 + *dd_idx) % (raid_disks-1); qd_idx = raid_disks - 1; break; @@ -1835,10 +1903,7 @@ static sector_t raid5_compute_sector(raid5_conf_t *conf, sector_t r_sector, qd_idx = raid_disks - 1; break; - default: - printk(KERN_CRIT "raid6: unsupported algorithm %d\n", - algorithm); BUG(); } break; @@ -1869,14 +1934,14 @@ static sector_t compute_blocknr(struct stripe_head *sh, int i, int previous) : conf->algorithm; sector_t stripe; int chunk_offset; - int chunk_number, dummy1, dd_idx = i; + sector_t chunk_number; + int dummy1, dd_idx = i; sector_t r_sector; struct stripe_head sh2; chunk_offset = sector_div(new_sector, sectors_per_chunk); stripe = new_sector; - BUG_ON(new_sector != stripe); if (i == sh->pd_idx) return 0; @@ -1901,8 +1966,6 @@ static sector_t compute_blocknr(struct stripe_head *sh, int i, int previous) case ALGORITHM_PARITY_N: break; default: - printk(KERN_ERR "raid5: unsupported algorithm %d\n", - algorithm); BUG(); } break; @@ -1961,21 +2024,20 @@ static sector_t compute_blocknr(struct stripe_head *sh, int i, int previous) i -= 1; break; default: - printk(KERN_CRIT "raid6: unsupported algorithm %d\n", - algorithm); BUG(); } break; } chunk_number = stripe * data_disks + i; - r_sector = (sector_t)chunk_number * sectors_per_chunk + chunk_offset; + r_sector = chunk_number * sectors_per_chunk + chunk_offset; check = raid5_compute_sector(conf, r_sector, previous, &dummy1, &sh2); if (check != sh->sector || dummy1 != dd_idx || sh2.pd_idx != sh->pd_idx || sh2.qd_idx != sh->qd_idx) { - printk(KERN_ERR "compute_blocknr: map not correct\n"); + printk(KERN_ERR "md/raid:%s: compute_blocknr: map not correct\n", + mdname(conf->mddev)); return 0; } return r_sector; @@ -2969,7 +3031,6 @@ static void handle_stripe5(struct stripe_head *sh) mdk_rdev_t *rdev; dev = &sh->dev[i]; - clear_bit(R5_Insync, &dev->flags); pr_debug("check %d: state 0x%lx toread %p read %p write %p " "written %p\n", i, dev->flags, dev->toread, dev->read, @@ -3006,17 +3067,27 @@ static void handle_stripe5(struct stripe_head *sh) blocked_rdev = rdev; atomic_inc(&rdev->nr_pending); } - if (!rdev || !test_bit(In_sync, &rdev->flags)) { + clear_bit(R5_Insync, &dev->flags); + if (!rdev) + /* Not in-sync */; + else if (test_bit(In_sync, &rdev->flags)) + set_bit(R5_Insync, &dev->flags); + else { + /* could be in-sync depending on recovery/reshape status */ + if (sh->sector + STRIPE_SECTORS <= rdev->recovery_offset) + set_bit(R5_Insync, &dev->flags); + } + if (!test_bit(R5_Insync, &dev->flags)) { /* The ReadError flag will just be confusing now */ clear_bit(R5_ReadError, &dev->flags); clear_bit(R5_ReWrite, &dev->flags); } - if (!rdev || !test_bit(In_sync, &rdev->flags) - || test_bit(R5_ReadError, &dev->flags)) { + if (test_bit(R5_ReadError, &dev->flags)) + clear_bit(R5_Insync, &dev->flags); + if (!test_bit(R5_Insync, &dev->flags)) { s.failed++; s.failed_num = i; - } else - set_bit(R5_Insync, &dev->flags); + } } rcu_read_unlock(); @@ -3250,7 +3321,6 @@ static void handle_stripe6(struct stripe_head *sh) for (i=disks; i--; ) { mdk_rdev_t *rdev; dev = &sh->dev[i]; - clear_bit(R5_Insync, &dev->flags); pr_debug("check %d: state 0x%lx read %p write %p written %p\n", i, dev->flags, dev->toread, dev->towrite, dev->written); @@ -3288,18 +3358,28 @@ static void handle_stripe6(struct stripe_head *sh) blocked_rdev = rdev; atomic_inc(&rdev->nr_pending); } - if (!rdev || !test_bit(In_sync, &rdev->flags)) { + clear_bit(R5_Insync, &dev->flags); + if (!rdev) + /* Not in-sync */; + else if (test_bit(In_sync, &rdev->flags)) + set_bit(R5_Insync, &dev->flags); + else { + /* in sync if before recovery_offset */ + if (sh->sector + STRIPE_SECTORS <= rdev->recovery_offset) + set_bit(R5_Insync, &dev->flags); + } + if (!test_bit(R5_Insync, &dev->flags)) { /* The ReadError flag will just be confusing now */ clear_bit(R5_ReadError, &dev->flags); clear_bit(R5_ReWrite, &dev->flags); } - if (!rdev || !test_bit(In_sync, &rdev->flags) - || test_bit(R5_ReadError, &dev->flags)) { + if (test_bit(R5_ReadError, &dev->flags)) + clear_bit(R5_Insync, &dev->flags); + if (!test_bit(R5_Insync, &dev->flags)) { if (s.failed < 2) r6s.failed_num[s.failed] = i; s.failed++; - } else - set_bit(R5_Insync, &dev->flags); + } } rcu_read_unlock(); @@ -3712,10 +3792,10 @@ static void raid5_align_endio(struct bio *bi, int error) bio_put(bi); - mddev = raid_bi->bi_bdev->bd_disk->queue->queuedata; - conf = mddev->private; rdev = (void*)raid_bi->bi_next; raid_bi->bi_next = NULL; + mddev = rdev->mddev; + conf = mddev->private; rdev_dec_pending(rdev, conf->mddev); @@ -3739,7 +3819,7 @@ static int bio_fits_rdev(struct bio *bi) if ((bi->bi_size>>9) > queue_max_sectors(q)) return 0; blk_recount_segments(q, bi); - if (bi->bi_phys_segments > queue_max_phys_segments(q)) + if (bi->bi_phys_segments > queue_max_segments(q)) return 0; if (q->merge_bvec_fn) @@ -3752,9 +3832,8 @@ static int bio_fits_rdev(struct bio *bi) } -static int chunk_aligned_read(struct request_queue *q, struct bio * raid_bio) +static int chunk_aligned_read(mddev_t *mddev, struct bio * raid_bio) { - mddev_t *mddev = q->queuedata; raid5_conf_t *conf = mddev->private; int dd_idx; struct bio* align_bi; @@ -3869,16 +3948,15 @@ static struct stripe_head *__get_priority_stripe(raid5_conf_t *conf) return sh; } -static int make_request(struct request_queue *q, struct bio * bi) +static int make_request(mddev_t *mddev, struct bio * bi) { - mddev_t *mddev = q->queuedata; raid5_conf_t *conf = mddev->private; int dd_idx; sector_t new_sector; sector_t logical_sector, last_sector; struct stripe_head *sh; const int rw = bio_data_dir(bi); - int cpu, remaining; + int remaining; if (unlikely(bio_rw_flagged(bi, BIO_RW_BARRIER))) { /* Drain all pending writes. We only really need @@ -3893,15 +3971,9 @@ static int make_request(struct request_queue *q, struct bio * bi) md_write_start(mddev, bi); - cpu = part_stat_lock(); - part_stat_inc(cpu, &mddev->gendisk->part0, ios[rw]); - part_stat_add(cpu, &mddev->gendisk->part0, sectors[rw], - bio_sectors(bi)); - part_stat_unlock(); - if (rw == READ && mddev->reshape_position == MaxSector && - chunk_aligned_read(q,bi)) + chunk_aligned_read(mddev,bi)) return 0; logical_sector = bi->bi_sector & ~((sector_t)STRIPE_SECTORS-1); @@ -3949,7 +4021,7 @@ static int make_request(struct request_queue *q, struct bio * bi) new_sector = raid5_compute_sector(conf, logical_sector, previous, &dd_idx, NULL); - pr_debug("raid5: make_request, sector %llu logical %llu\n", + pr_debug("raid456: make_request, sector %llu logical %llu\n", (unsigned long long)new_sector, (unsigned long long)logical_sector); @@ -4057,7 +4129,7 @@ static sector_t reshape_request(mddev_t *mddev, sector_t sector_nr, int *skipped * As the reads complete, handle_stripe will copy the data * into the destination stripe and release that stripe. */ - raid5_conf_t *conf = (raid5_conf_t *) mddev->private; + raid5_conf_t *conf = mddev->private; struct stripe_head *sh; sector_t first_sector, last_sector; int raid_disks = conf->previous_raid_disks; @@ -4266,7 +4338,7 @@ static sector_t reshape_request(mddev_t *mddev, sector_t sector_nr, int *skipped /* FIXME go_faster isn't used */ static inline sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, int go_faster) { - raid5_conf_t *conf = (raid5_conf_t *) mddev->private; + raid5_conf_t *conf = mddev->private; struct stripe_head *sh; sector_t max_sector = mddev->dev_sectors; int sync_blocks; @@ -4659,7 +4731,7 @@ static int raid456_cpu_notify(struct notifier_block *nfb, unsigned long action, kfree(percpu->scribble); pr_err("%s: failed memory allocation for cpu%ld\n", __func__, cpu); - return NOTIFY_BAD; + return notifier_from_errno(-ENOMEM); } break; case CPU_DEAD: @@ -4680,7 +4752,7 @@ static int raid5_alloc_percpu(raid5_conf_t *conf) { unsigned long cpu; struct page *spare_page; - struct raid5_percpu *allcpus; + struct raid5_percpu __percpu *allcpus; void *scribble; int err; @@ -4728,7 +4800,7 @@ static raid5_conf_t *setup_conf(mddev_t *mddev) if (mddev->new_level != 5 && mddev->new_level != 4 && mddev->new_level != 6) { - printk(KERN_ERR "raid5: %s: raid level not set to 4/5/6 (%d)\n", + printk(KERN_ERR "md/raid:%s: raid level not set to 4/5/6 (%d)\n", mdname(mddev), mddev->new_level); return ERR_PTR(-EIO); } @@ -4736,12 +4808,12 @@ static raid5_conf_t *setup_conf(mddev_t *mddev) && !algorithm_valid_raid5(mddev->new_layout)) || (mddev->new_level == 6 && !algorithm_valid_raid6(mddev->new_layout))) { - printk(KERN_ERR "raid5: %s: layout %d not supported\n", + printk(KERN_ERR "md/raid:%s: layout %d not supported\n", mdname(mddev), mddev->new_layout); return ERR_PTR(-EIO); } if (mddev->new_level == 6 && mddev->raid_disks < 4) { - printk(KERN_ERR "raid6: not enough configured devices for %s (%d, minimum 4)\n", + printk(KERN_ERR "md/raid:%s: not enough configured devices (%d, minimum 4)\n", mdname(mddev), mddev->raid_disks); return ERR_PTR(-EINVAL); } @@ -4749,8 +4821,8 @@ static raid5_conf_t *setup_conf(mddev_t *mddev) if (!mddev->new_chunk_sectors || (mddev->new_chunk_sectors << 9) % PAGE_SIZE || !is_power_of_2(mddev->new_chunk_sectors)) { - printk(KERN_ERR "raid5: invalid chunk size %d for %s\n", - mddev->new_chunk_sectors << 9, mdname(mddev)); + printk(KERN_ERR "md/raid:%s: invalid chunk size %d\n", + mdname(mddev), mddev->new_chunk_sectors << 9); return ERR_PTR(-EINVAL); } @@ -4792,7 +4864,7 @@ static raid5_conf_t *setup_conf(mddev_t *mddev) if (raid5_alloc_percpu(conf) != 0) goto abort; - pr_debug("raid5: run(%s) called.\n", mdname(mddev)); + pr_debug("raid456: run(%s) called.\n", mdname(mddev)); list_for_each_entry(rdev, &mddev->disks, same_set) { raid_disk = rdev->raid_disk; @@ -4805,9 +4877,9 @@ static raid5_conf_t *setup_conf(mddev_t *mddev) if (test_bit(In_sync, &rdev->flags)) { char b[BDEVNAME_SIZE]; - printk(KERN_INFO "raid5: device %s operational as raid" - " disk %d\n", bdevname(rdev->bdev,b), - raid_disk); + printk(KERN_INFO "md/raid:%s: device %s operational as raid" + " disk %d\n", + mdname(mddev), bdevname(rdev->bdev, b), raid_disk); } else /* Cannot rely on bitmap to complete recovery */ conf->fullsync = 1; @@ -4831,16 +4903,17 @@ static raid5_conf_t *setup_conf(mddev_t *mddev) max_disks * ((sizeof(struct bio) + PAGE_SIZE))) / 1024; if (grow_stripes(conf, conf->max_nr_stripes)) { printk(KERN_ERR - "raid5: couldn't allocate %dkB for buffers\n", memory); + "md/raid:%s: couldn't allocate %dkB for buffers\n", + mdname(mddev), memory); goto abort; } else - printk(KERN_INFO "raid5: allocated %dkB for %s\n", - memory, mdname(mddev)); + printk(KERN_INFO "md/raid:%s: allocated %dkB\n", + mdname(mddev), memory); conf->thread = md_register_thread(raid5d, mddev, NULL); if (!conf->thread) { printk(KERN_ERR - "raid5: couldn't allocate thread for %s\n", + "md/raid:%s: couldn't allocate thread.\n", mdname(mddev)); goto abort; } @@ -4891,7 +4964,7 @@ static int run(mddev_t *mddev) sector_t reshape_offset = 0; if (mddev->recovery_cp != MaxSector) - printk(KERN_NOTICE "raid5: %s is not clean" + printk(KERN_NOTICE "md/raid:%s: not clean" " -- starting background reconstruction\n", mdname(mddev)); if (mddev->reshape_position != MaxSector) { @@ -4905,7 +4978,7 @@ static int run(mddev_t *mddev) int max_degraded = (mddev->level == 6 ? 2 : 1); if (mddev->new_level != mddev->level) { - printk(KERN_ERR "raid5: %s: unsupported reshape " + printk(KERN_ERR "md/raid:%s: unsupported reshape " "required - aborting.\n", mdname(mddev)); return -EINVAL; @@ -4918,8 +4991,8 @@ static int run(mddev_t *mddev) here_new = mddev->reshape_position; if (sector_div(here_new, mddev->new_chunk_sectors * (mddev->raid_disks - max_degraded))) { - printk(KERN_ERR "raid5: reshape_position not " - "on a stripe boundary\n"); + printk(KERN_ERR "md/raid:%s: reshape_position not " + "on a stripe boundary\n", mdname(mddev)); return -EINVAL; } reshape_offset = here_new * mddev->new_chunk_sectors; @@ -4940,8 +5013,9 @@ static int run(mddev_t *mddev) if ((here_new * mddev->new_chunk_sectors != here_old * mddev->chunk_sectors) || mddev->ro == 0) { - printk(KERN_ERR "raid5: in-place reshape must be started" - " in read-only mode - aborting\n"); + printk(KERN_ERR "md/raid:%s: in-place reshape must be started" + " in read-only mode - aborting\n", + mdname(mddev)); return -EINVAL; } } else if (mddev->delta_disks < 0 @@ -4950,11 +5024,13 @@ static int run(mddev_t *mddev) : (here_new * mddev->new_chunk_sectors >= here_old * mddev->chunk_sectors)) { /* Reading from the same stripe as writing to - bad */ - printk(KERN_ERR "raid5: reshape_position too early for " - "auto-recovery - aborting.\n"); + printk(KERN_ERR "md/raid:%s: reshape_position too early for " + "auto-recovery - aborting.\n", + mdname(mddev)); return -EINVAL; } - printk(KERN_INFO "raid5: reshape will continue\n"); + printk(KERN_INFO "md/raid:%s: reshape will continue\n", + mdname(mddev)); /* OK, we should be able to continue; */ } else { BUG_ON(mddev->level != mddev->new_level); @@ -4981,8 +5057,10 @@ static int run(mddev_t *mddev) list_for_each_entry(rdev, &mddev->disks, same_set) { if (rdev->raid_disk < 0) continue; - if (test_bit(In_sync, &rdev->flags)) + if (test_bit(In_sync, &rdev->flags)) { working_disks++; + continue; + } /* This disc is not fully in-sync. However if it * just stored parity (beyond the recovery_offset), * when we don't need to be concerned about the @@ -4996,18 +5074,6 @@ static int run(mddev_t *mddev) mddev->minor_version > 90) rdev->recovery_offset = reshape_offset; - printk("%d: w=%d pa=%d pr=%d m=%d a=%d r=%d op1=%d op2=%d\n", - rdev->raid_disk, working_disks, conf->prev_algo, - conf->previous_raid_disks, conf->max_degraded, - conf->algorithm, conf->raid_disks, - only_parity(rdev->raid_disk, - conf->prev_algo, - conf->previous_raid_disks, - conf->max_degraded), - only_parity(rdev->raid_disk, - conf->algorithm, - conf->raid_disks, - conf->max_degraded)); if (rdev->recovery_offset < reshape_offset) { /* We need to check old and new layout */ if (!only_parity(rdev->raid_disk, @@ -5027,8 +5093,8 @@ static int run(mddev_t *mddev) mddev->degraded = (max(conf->raid_disks, conf->previous_raid_disks) - working_disks); - if (mddev->degraded > conf->max_degraded) { - printk(KERN_ERR "raid5: not enough operational devices for %s" + if (has_failed(conf)) { + printk(KERN_ERR "md/raid:%s: not enough operational devices" " (%d/%d failed)\n", mdname(mddev), mddev->degraded, conf->raid_disks); goto abort; @@ -5042,32 +5108,32 @@ static int run(mddev_t *mddev) mddev->recovery_cp != MaxSector) { if (mddev->ok_start_degraded) printk(KERN_WARNING - "raid5: starting dirty degraded array: %s" - "- data corruption possible.\n", + "md/raid:%s: starting dirty degraded array" + " - data corruption possible.\n", mdname(mddev)); else { printk(KERN_ERR - "raid5: cannot start dirty degraded array for %s\n", + "md/raid:%s: cannot start dirty degraded array.\n", mdname(mddev)); goto abort; } } if (mddev->degraded == 0) - printk("raid5: raid level %d set %s active with %d out of %d" - " devices, algorithm %d\n", conf->level, mdname(mddev), + printk(KERN_INFO "md/raid:%s: raid level %d active with %d out of %d" + " devices, algorithm %d\n", mdname(mddev), conf->level, mddev->raid_disks-mddev->degraded, mddev->raid_disks, mddev->new_layout); else - printk(KERN_ALERT "raid5: raid level %d set %s active with %d" - " out of %d devices, algorithm %d\n", conf->level, - mdname(mddev), mddev->raid_disks - mddev->degraded, - mddev->raid_disks, mddev->new_layout); + printk(KERN_ALERT "md/raid:%s: raid level %d active with %d" + " out of %d devices, algorithm %d\n", + mdname(mddev), conf->level, + mddev->raid_disks - mddev->degraded, + mddev->raid_disks, mddev->new_layout); print_raid5_conf(conf); if (conf->reshape_progress != MaxSector) { - printk("...ok start reshape thread\n"); conf->reshape_safe = conf->reshape_progress; atomic_set(&conf->reshape_stripes, 0); clear_bit(MD_RECOVERY_SYNC, &mddev->recovery); @@ -5090,9 +5156,11 @@ static int run(mddev_t *mddev) } /* Ok, everything is just fine now */ - if (sysfs_create_group(&mddev->kobj, &raid5_attrs_group)) + if (mddev->to_remove == &raid5_attrs_group) + mddev->to_remove = NULL; + else if (sysfs_create_group(&mddev->kobj, &raid5_attrs_group)) printk(KERN_WARNING - "raid5: failed to create sysfs attributes for %s\n", + "md/raid:%s: failed to create sysfs attributes.\n", mdname(mddev)); mddev->queue->queue_lock = &conf->device_lock; @@ -5122,22 +5190,21 @@ abort: free_conf(conf); } mddev->private = NULL; - printk(KERN_ALERT "raid5: failed to run raid set %s\n", mdname(mddev)); + printk(KERN_ALERT "md/raid:%s: failed to run raid set.\n", mdname(mddev)); return -EIO; } - - static int stop(mddev_t *mddev) { - raid5_conf_t *conf = (raid5_conf_t *) mddev->private; + raid5_conf_t *conf = mddev->private; md_unregister_thread(mddev->thread); mddev->thread = NULL; mddev->queue->backing_dev_info.congested_fn = NULL; blk_sync_queue(mddev->queue); /* the unplug fn references 'conf'*/ free_conf(conf); - mddev->private = &raid5_attrs_group; + mddev->private = NULL; + mddev->to_remove = &raid5_attrs_group; return 0; } @@ -5178,7 +5245,7 @@ static void printall(struct seq_file *seq, raid5_conf_t *conf) static void status(struct seq_file *seq, mddev_t *mddev) { - raid5_conf_t *conf = (raid5_conf_t *) mddev->private; + raid5_conf_t *conf = mddev->private; int i; seq_printf(seq, " level %d, %dk chunk, algorithm %d", mddev->level, @@ -5200,21 +5267,22 @@ static void print_raid5_conf (raid5_conf_t *conf) int i; struct disk_info *tmp; - printk("RAID5 conf printout:\n"); + printk(KERN_DEBUG "RAID conf printout:\n"); if (!conf) { printk("(conf==NULL)\n"); return; } - printk(" --- rd:%d wd:%d\n", conf->raid_disks, - conf->raid_disks - conf->mddev->degraded); + printk(KERN_DEBUG " --- level:%d rd:%d wd:%d\n", conf->level, + conf->raid_disks, + conf->raid_disks - conf->mddev->degraded); for (i = 0; i < conf->raid_disks; i++) { char b[BDEVNAME_SIZE]; tmp = conf->disks + i; if (tmp->rdev) - printk(" disk %d, o:%d, dev:%s\n", - i, !test_bit(Faulty, &tmp->rdev->flags), - bdevname(tmp->rdev->bdev,b)); + printk(KERN_DEBUG " disk %d, o:%d, dev:%s\n", + i, !test_bit(Faulty, &tmp->rdev->flags), + bdevname(tmp->rdev->bdev, b)); } } @@ -5227,6 +5295,7 @@ static int raid5_spare_active(mddev_t *mddev) for (i = 0; i < conf->raid_disks; i++) { tmp = conf->disks + i; if (tmp->rdev + && tmp->rdev->recovery_offset == MaxSector && !test_bit(Faulty, &tmp->rdev->flags) && !test_and_set_bit(In_sync, &tmp->rdev->flags)) { unsigned long flags; @@ -5262,7 +5331,7 @@ static int raid5_remove_disk(mddev_t *mddev, int number) * isn't possible. */ if (!test_bit(Faulty, &rdev->flags) && - mddev->degraded <= conf->max_degraded && + !has_failed(conf) && number < conf->raid_disks) { err = -EBUSY; goto abort; @@ -5290,7 +5359,7 @@ static int raid5_add_disk(mddev_t *mddev, mdk_rdev_t *rdev) int first = 0; int last = conf->raid_disks - 1; - if (mddev->degraded > conf->max_degraded) + if (has_failed(conf)) /* no point adding a device */ return -EINVAL; @@ -5337,7 +5406,6 @@ static int raid5_resize(mddev_t *mddev, sector_t sectors) raid5_size(mddev, sectors, mddev->raid_disks)) return -EINVAL; set_capacity(mddev->gendisk, mddev->array_sectors); - mddev->changed = 1; revalidate_disk(mddev->gendisk); if (sectors > mddev->dev_sectors && mddev->recovery_cp == MaxSector) { mddev->recovery_cp = mddev->dev_sectors; @@ -5363,7 +5431,8 @@ static int check_stripe_cache(mddev_t *mddev) > conf->max_nr_stripes || ((mddev->new_chunk_sectors << 9) / STRIPE_SIZE) * 4 > conf->max_nr_stripes) { - printk(KERN_WARNING "raid5: reshape: not enough stripes. Needed %lu\n", + printk(KERN_WARNING "md/raid:%s: reshape: not enough stripes. Needed %lu\n", + mdname(mddev), ((max(mddev->chunk_sectors, mddev->new_chunk_sectors) << 9) / STRIPE_SIZE)*4); return 0; @@ -5382,7 +5451,7 @@ static int check_reshape(mddev_t *mddev) if (mddev->bitmap) /* Cannot grow a bitmap yet */ return -EBUSY; - if (mddev->degraded > conf->max_degraded) + if (has_failed(conf)) return -EINVAL; if (mddev->delta_disks < 0) { /* We might be able to shrink, but the devices must @@ -5434,7 +5503,7 @@ static int raid5_start_reshape(mddev_t *mddev) */ if (raid5_size(mddev, 0, conf->raid_disks + mddev->delta_disks) < mddev->array_sectors) { - printk(KERN_ERR "md: %s: array size must be reduced " + printk(KERN_ERR "md/raid:%s: array size must be reduced " "before number of disks\n", mdname(mddev)); return -EINVAL; } @@ -5457,8 +5526,13 @@ static int raid5_start_reshape(mddev_t *mddev) /* Add some new drives, as many as will fit. * We know there are enough to make the newly sized array work. + * Don't add devices if we are reducing the number of + * devices in the array. This is because it is not possible + * to correctly record the "partially reconstructed" state of + * such devices during the reshape and confusion could result. */ - list_for_each_entry(rdev, &mddev->disks, same_set) + if (mddev->delta_disks >= 0) + list_for_each_entry(rdev, &mddev->disks, same_set) if (rdev->raid_disk < 0 && !test_bit(Faulty, &rdev->flags)) { if (raid5_add_disk(mddev, rdev) == 0) { @@ -5472,15 +5546,15 @@ static int raid5_start_reshape(mddev_t *mddev) if (sysfs_create_link(&mddev->kobj, &rdev->kobj, nm)) printk(KERN_WARNING - "raid5: failed to create " - " link %s for %s\n", - nm, mdname(mddev)); + "md/raid:%s: failed to create " + " link %s\n", + mdname(mddev), nm); } else break; } /* When a reshape changes the number of devices, ->degraded - * is measured against the large of the pre and post number of + * is measured against the larger of the pre and post number of * devices.*/ if (mddev->delta_disks > 0) { spin_lock_irqsave(&conf->device_lock, flags); @@ -5551,7 +5625,6 @@ static void raid5_finish_reshape(mddev_t *mddev) if (mddev->delta_disks > 0) { md_set_array_sectors(mddev, raid5_size(mddev, 0, 0)); set_capacity(mddev->gendisk, mddev->array_sectors); - mddev->changed = 1; revalidate_disk(mddev->gendisk); } else { int d; @@ -5616,6 +5689,29 @@ static void raid5_quiesce(mddev_t *mddev, int state) } +static void *raid45_takeover_raid0(mddev_t *mddev, int level) +{ + struct raid0_private_data *raid0_priv = mddev->private; + + /* for raid0 takeover only one zone is supported */ + if (raid0_priv->nr_strip_zones > 1) { + printk(KERN_ERR "md/raid:%s: cannot takeover raid0 with more than one zone.\n", + mdname(mddev)); + return ERR_PTR(-EINVAL); + } + + mddev->new_level = level; + mddev->new_layout = ALGORITHM_PARITY_N; + mddev->new_chunk_sectors = mddev->chunk_sectors; + mddev->raid_disks += 1; + mddev->delta_disks = 1; + /* make sure it will be not marked as dirty */ + mddev->recovery_cp = MaxSector; + + return setup_conf(mddev); +} + + static void *raid5_takeover_raid1(mddev_t *mddev) { int chunksect; @@ -5740,12 +5836,13 @@ static int raid6_check_reshape(mddev_t *mddev) static void *raid5_takeover(mddev_t *mddev) { /* raid5 can take over: - * raid0 - if all devices are the same - make it a raid4 layout + * raid0 - if there is only one strip zone - make it a raid4 layout * raid1 - if there are two drives. We need to know the chunk size * raid4 - trivial - just use a raid4 layout. * raid6 - Providing it is a *_6 layout */ - + if (mddev->level == 0) + return raid45_takeover_raid0(mddev, 5); if (mddev->level == 1) return raid5_takeover_raid1(mddev); if (mddev->level == 4) { @@ -5759,6 +5856,22 @@ static void *raid5_takeover(mddev_t *mddev) return ERR_PTR(-EINVAL); } +static void *raid4_takeover(mddev_t *mddev) +{ + /* raid4 can take over: + * raid0 - if there is only one strip zone + * raid5 - if layout is right + */ + if (mddev->level == 0) + return raid45_takeover_raid0(mddev, 4); + if (mddev->level == 5 && + mddev->layout == ALGORITHM_PARITY_N) { + mddev->new_layout = 0; + mddev->new_level = 4; + return setup_conf(mddev); + } + return ERR_PTR(-EINVAL); +} static struct mdk_personality raid5_personality; @@ -5874,6 +5987,7 @@ static struct mdk_personality raid4_personality = .start_reshape = raid5_start_reshape, .finish_reshape = raid5_finish_reshape, .quiesce = raid5_quiesce, + .takeover = raid4_takeover, }; static int __init raid5_init(void) diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h index dd708359b451..0f86f5e36724 100644 --- a/drivers/md/raid5.h +++ b/drivers/md/raid5.h @@ -405,7 +405,7 @@ struct raid5_private_data { * lists and performing address * conversions */ - } *percpu; + } __percpu *percpu; size_t scribble_len; /* size of scribble region must be * associated with conf to handle * cpu hotplug while reshaping diff --git a/drivers/md/raid6algos.c b/drivers/md/raid6algos.c index bffc61bff5ab..1f8784bfd44d 100644 --- a/drivers/md/raid6algos.c +++ b/drivers/md/raid6algos.c @@ -17,6 +17,7 @@ */ #include <linux/raid/pq.h> +#include <linux/gfp.h> #ifndef __KERNEL__ #include <sys/mman.h> #include <stdio.h> |