diff options
Diffstat (limited to 'drivers/md')
-rw-r--r-- | drivers/md/bitmap.c | 29 | ||||
-rw-r--r-- | drivers/md/linear.c | 2 | ||||
-rw-r--r-- | drivers/md/md.c | 280 | ||||
-rw-r--r-- | drivers/md/multipath.c | 15 | ||||
-rw-r--r-- | drivers/md/raid1.c | 13 | ||||
-rw-r--r-- | drivers/md/raid10.c | 20 | ||||
-rw-r--r-- | drivers/md/raid5.c | 724 |
7 files changed, 537 insertions, 546 deletions
diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c index b26927ce889c..dedba16d42f7 100644 --- a/drivers/md/bitmap.c +++ b/drivers/md/bitmap.c @@ -454,8 +454,11 @@ void bitmap_update_sb(struct bitmap *bitmap) spin_unlock_irqrestore(&bitmap->lock, flags); sb = (bitmap_super_t *)kmap_atomic(bitmap->sb_page, KM_USER0); sb->events = cpu_to_le64(bitmap->mddev->events); - if (!bitmap->mddev->degraded) - sb->events_cleared = cpu_to_le64(bitmap->mddev->events); + if (bitmap->mddev->events < bitmap->events_cleared) { + /* rocking back to read-only */ + bitmap->events_cleared = bitmap->mddev->events; + sb->events_cleared = cpu_to_le64(bitmap->events_cleared); + } kunmap_atomic(sb, KM_USER0); write_page(bitmap, bitmap->sb_page, 1); } @@ -1085,9 +1088,19 @@ void bitmap_daemon_work(struct bitmap *bitmap) } else spin_unlock_irqrestore(&bitmap->lock, flags); lastpage = page; -/* - printk("bitmap clean at page %lu\n", j); -*/ + + /* We are possibly going to clear some bits, so make + * sure that events_cleared is up-to-date. + */ + if (bitmap->need_sync) { + bitmap_super_t *sb; + bitmap->need_sync = 0; + sb = kmap_atomic(bitmap->sb_page, KM_USER0); + sb->events_cleared = + cpu_to_le64(bitmap->events_cleared); + kunmap_atomic(sb, KM_USER0); + write_page(bitmap, bitmap->sb_page, 1); + } spin_lock_irqsave(&bitmap->lock, flags); clear_page_attr(bitmap, page, BITMAP_PAGE_CLEAN); } @@ -1257,6 +1270,12 @@ void bitmap_endwrite(struct bitmap *bitmap, sector_t offset, unsigned long secto return; } + if (success && + bitmap->events_cleared < bitmap->mddev->events) { + bitmap->events_cleared = bitmap->mddev->events; + bitmap->need_sync = 1; + } + if (!success && ! (*bmc & NEEDED_MASK)) *bmc |= NEEDED_MASK; diff --git a/drivers/md/linear.c b/drivers/md/linear.c index 10748240cb2f..ec921f58fbb8 100644 --- a/drivers/md/linear.c +++ b/drivers/md/linear.c @@ -126,7 +126,7 @@ static linear_conf_t *linear_conf(mddev_t *mddev, int raid_disks) int j = rdev->raid_disk; dev_info_t *disk = conf->disks + j; - if (j < 0 || j > raid_disks || disk->rdev) { + if (j < 0 || j >= raid_disks || disk->rdev) { printk("linear: disk numbering problem. Aborting!\n"); goto out; } diff --git a/drivers/md/md.c b/drivers/md/md.c index 2580ac1b9b0f..df1230af02cd 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -169,7 +169,6 @@ void md_new_event(mddev_t *mddev) { atomic_inc(&md_event_count); wake_up(&md_event_waiters); - sysfs_notify(&mddev->kobj, NULL, "sync_action"); } EXPORT_SYMBOL_GPL(md_new_event); @@ -278,6 +277,7 @@ static mddev_t * mddev_find(dev_t unit) 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; @@ -658,11 +658,14 @@ static unsigned int calc_sb_csum(mdp_super_t * sb) */ struct super_type { - char *name; - struct module *owner; - int (*load_super)(mdk_rdev_t *rdev, mdk_rdev_t *refdev, int minor_version); - int (*validate_super)(mddev_t *mddev, mdk_rdev_t *rdev); - void (*sync_super)(mddev_t *mddev, mdk_rdev_t *rdev); + char *name; + struct module *owner; + int (*load_super)(mdk_rdev_t *rdev, mdk_rdev_t *refdev, + int minor_version); + int (*validate_super)(mddev_t *mddev, mdk_rdev_t *rdev); + void (*sync_super)(mddev_t *mddev, mdk_rdev_t *rdev); + unsigned long long (*rdev_size_change)(mdk_rdev_t *rdev, + unsigned long long size); }; /* @@ -1004,6 +1007,27 @@ static void super_90_sync(mddev_t *mddev, mdk_rdev_t *rdev) } /* + * rdev_size_change for 0.90.0 + */ +static unsigned long long +super_90_rdev_size_change(mdk_rdev_t *rdev, unsigned long long size) +{ + if (size && size < rdev->mddev->size) + return 0; /* component must fit device */ + size *= 2; /* convert to sectors */ + if (rdev->mddev->bitmap_offset) + return 0; /* can't move bitmap */ + rdev->sb_offset = calc_dev_sboffset(rdev->bdev); + if (!size || size > rdev->sb_offset*2) + size = rdev->sb_offset*2; + md_super_write(rdev->mddev, rdev, rdev->sb_offset << 1, rdev->sb_size, + rdev->sb_page); + md_super_wait(rdev->mddev); + return size/2; /* kB for sysfs */ +} + + +/* * version 1 superblock */ @@ -1328,21 +1352,59 @@ static void super_1_sync(mddev_t *mddev, mdk_rdev_t *rdev) sb->sb_csum = calc_sb_1_csum(sb); } +static unsigned long long +super_1_rdev_size_change(mdk_rdev_t *rdev, unsigned long long size) +{ + struct mdp_superblock_1 *sb; + unsigned long long max_size; + if (size && size < rdev->mddev->size) + return 0; /* component must fit device */ + size *= 2; /* convert to sectors */ + if (rdev->sb_offset < rdev->data_offset/2) { + /* minor versions 1 and 2; superblock before data */ + max_size = (rdev->bdev->bd_inode->i_size >> 9); + max_size -= rdev->data_offset; + if (!size || size > max_size) + size = max_size; + } else if (rdev->mddev->bitmap_offset) { + /* minor version 0 with bitmap we can't move */ + return 0; + } else { + /* minor version 0; superblock after data */ + sector_t sb_offset; + sb_offset = (rdev->bdev->bd_inode->i_size >> 9) - 8*2; + sb_offset &= ~(sector_t)(4*2 - 1); + max_size = rdev->size*2 + sb_offset - rdev->sb_offset*2; + if (!size || size > max_size) + size = max_size; + rdev->sb_offset = sb_offset/2; + } + sb = (struct mdp_superblock_1 *) page_address(rdev->sb_page); + sb->data_size = cpu_to_le64(size); + sb->super_offset = rdev->sb_offset*2; + sb->sb_csum = calc_sb_1_csum(sb); + md_super_write(rdev->mddev, rdev, rdev->sb_offset << 1, rdev->sb_size, + rdev->sb_page); + md_super_wait(rdev->mddev); + return size/2; /* kB for sysfs */ +} static struct super_type super_types[] = { [0] = { .name = "0.90.0", .owner = THIS_MODULE, - .load_super = super_90_load, - .validate_super = super_90_validate, - .sync_super = super_90_sync, + .load_super = super_90_load, + .validate_super = super_90_validate, + .sync_super = super_90_sync, + .rdev_size_change = super_90_rdev_size_change, }, [1] = { .name = "md-1", .owner = THIS_MODULE, - .load_super = super_1_load, - .validate_super = super_1_validate, - .sync_super = super_1_sync, + .load_super = super_1_load, + .validate_super = super_1_validate, + .sync_super = super_1_sync, + .rdev_size_change = super_1_rdev_size_change, }, }; @@ -1886,6 +1948,8 @@ state_store(mdk_rdev_t *rdev, const char *buf, size_t len) err = 0; } + if (!err) + sysfs_notify(&rdev->kobj, NULL, "state"); return err ? err : len; } static struct rdev_sysfs_entry rdev_state = @@ -1931,7 +1995,7 @@ slot_store(mdk_rdev_t *rdev, const char *buf, size_t len) slot = -1; else if (e==buf || (*e && *e!= '\n')) return -EINVAL; - if (rdev->mddev->pers) { + if (rdev->mddev->pers && slot == -1) { /* Setting 'slot' on an active array requires also * updating the 'rd%d' link, and communicating * with the personality with ->hot_*_disk. @@ -1939,8 +2003,6 @@ slot_store(mdk_rdev_t *rdev, const char *buf, size_t len) * failed/spare devices. This normally happens automatically, * but not when the metadata is externally managed. */ - if (slot != -1) - return -EBUSY; if (rdev->raid_disk == -1) return -EEXIST; /* personality does all needed checks */ @@ -1954,6 +2016,43 @@ slot_store(mdk_rdev_t *rdev, const char *buf, size_t len) sysfs_remove_link(&rdev->mddev->kobj, nm); set_bit(MD_RECOVERY_NEEDED, &rdev->mddev->recovery); md_wakeup_thread(rdev->mddev->thread); + } else if (rdev->mddev->pers) { + mdk_rdev_t *rdev2; + struct list_head *tmp; + /* Activating a spare .. or possibly reactivating + * if we every get bitmaps working here. + */ + + if (rdev->raid_disk != -1) + return -EBUSY; + + if (rdev->mddev->pers->hot_add_disk == NULL) + return -EINVAL; + + rdev_for_each(rdev2, tmp, rdev->mddev) + if (rdev2->raid_disk == slot) + return -EEXIST; + + rdev->raid_disk = slot; + if (test_bit(In_sync, &rdev->flags)) + rdev->saved_raid_disk = slot; + else + rdev->saved_raid_disk = -1; + err = rdev->mddev->pers-> + hot_add_disk(rdev->mddev, rdev); + if (err) { + rdev->raid_disk = -1; + return err; + } else + sysfs_notify(&rdev->kobj, NULL, "state"); + sprintf(nm, "rd%d", rdev->raid_disk); + if (sysfs_create_link(&rdev->mddev->kobj, &rdev->kobj, nm)) + printk(KERN_WARNING + "md: cannot register " + "%s for %s\n", + nm, mdname(rdev->mddev)); + + /* don't wakeup anyone, leave that to userspace. */ } else { if (slot >= rdev->mddev->raid_disks) return -ENOSPC; @@ -1962,6 +2061,7 @@ slot_store(mdk_rdev_t *rdev, const char *buf, size_t len) clear_bit(Faulty, &rdev->flags); clear_bit(WriteMostly, &rdev->flags); set_bit(In_sync, &rdev->flags); + sysfs_notify(&rdev->kobj, NULL, "state"); } return len; } @@ -1983,7 +2083,7 @@ offset_store(mdk_rdev_t *rdev, const char *buf, size_t len) unsigned long long offset = simple_strtoull(buf, &e, 10); if (e==buf || (*e && *e != '\n')) return -EINVAL; - if (rdev->mddev->pers) + if (rdev->mddev->pers && rdev->raid_disk >= 0) return -EBUSY; if (rdev->size && rdev->mddev->external) /* Must set offset before size, so overlap checks @@ -2022,8 +2122,20 @@ rdev_size_store(mdk_rdev_t *rdev, const char *buf, size_t len) if (e==buf || (*e && *e != '\n')) return -EINVAL; - if (my_mddev->pers) - return -EBUSY; + if (my_mddev->pers && rdev->raid_disk >= 0) { + if (rdev->mddev->persistent) { + size = super_types[rdev->mddev->major_version]. + rdev_size_change(rdev, size); + if (!size) + return -EBUSY; + } else if (!size) { + size = (rdev->bdev->bd_inode->i_size >> 10); + size -= rdev->data_offset/2; + } + if (size < rdev->mddev->size) + return -EINVAL; /* component must fit device */ + } + rdev->size = size; if (size > oldsize && rdev->mddev->external) { /* need to check that all other rdevs with the same ->bdev @@ -2681,8 +2793,10 @@ array_state_store(mddev_t *mddev, const char *buf, size_t len) } if (err) return err; - else + else { + sysfs_notify(&mddev->kobj, NULL, "array_state"); return len; + } } static struct md_sysfs_entry md_array_state = __ATTR(array_state, S_IRUGO|S_IWUSR, array_state_show, array_state_store); @@ -2899,7 +3013,7 @@ action_show(mddev_t *mddev, char *page) type = "check"; else type = "repair"; - } else + } else if (test_bit(MD_RECOVERY_RECOVER, &mddev->recovery)) type = "recover"; } return sprintf(page, "%s\n", type); @@ -2921,15 +3035,19 @@ action_store(mddev_t *mddev, const char *page, size_t len) } else if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) || test_bit(MD_RECOVERY_NEEDED, &mddev->recovery)) return -EBUSY; - else if (cmd_match(page, "resync") || cmd_match(page, "recover")) + else if (cmd_match(page, "resync")) set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); - else if (cmd_match(page, "reshape")) { + else if (cmd_match(page, "recover")) { + set_bit(MD_RECOVERY_RECOVER, &mddev->recovery); + set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); + } else if (cmd_match(page, "reshape")) { int err; if (mddev->pers->start_reshape == NULL) return -EINVAL; err = mddev->pers->start_reshape(mddev); if (err) return err; + sysfs_notify(&mddev->kobj, NULL, "degraded"); } else { if (cmd_match(page, "check")) set_bit(MD_RECOVERY_CHECK, &mddev->recovery); @@ -2940,6 +3058,7 @@ action_store(mddev_t *mddev, const char *page, size_t len) } set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); md_wakeup_thread(mddev->thread); + sysfs_notify(&mddev->kobj, NULL, "sync_action"); return len; } @@ -3075,6 +3194,36 @@ sync_completed_show(mddev_t *mddev, char *page) static struct md_sysfs_entry md_sync_completed = __ATTR_RO(sync_completed); static ssize_t +min_sync_show(mddev_t *mddev, char *page) +{ + return sprintf(page, "%llu\n", + (unsigned long long)mddev->resync_min); +} +static ssize_t +min_sync_store(mddev_t *mddev, const char *buf, size_t len) +{ + unsigned long long min; + if (strict_strtoull(buf, 10, &min)) + return -EINVAL; + if (min > mddev->resync_max) + return -EINVAL; + if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) + return -EBUSY; + + /* Must be a multiple of chunk_size */ + if (mddev->chunk_size) { + if (min & (sector_t)((mddev->chunk_size>>9)-1)) + return -EINVAL; + } + mddev->resync_min = min; + + return len; +} + +static struct md_sysfs_entry md_min_sync = +__ATTR(sync_min, S_IRUGO|S_IWUSR, min_sync_show, min_sync_store); + +static ssize_t max_sync_show(mddev_t *mddev, char *page) { if (mddev->resync_max == MaxSector) @@ -3089,9 +3238,10 @@ max_sync_store(mddev_t *mddev, const char *buf, size_t len) if (strncmp(buf, "max", 3) == 0) mddev->resync_max = MaxSector; else { - char *ep; - unsigned long long max = simple_strtoull(buf, &ep, 10); - if (ep == buf || (*ep != 0 && *ep != '\n')) + unsigned long long max; + if (strict_strtoull(buf, 10, &max)) + return -EINVAL; + if (max < mddev->resync_min) return -EINVAL; if (max < mddev->resync_max && test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) @@ -3222,6 +3372,7 @@ static struct attribute *md_redundancy_attrs[] = { &md_sync_speed.attr, &md_sync_force_parallel.attr, &md_sync_completed.attr, + &md_min_sync.attr, &md_max_sync.attr, &md_suspend_lo.attr, &md_suspend_hi.attr, @@ -3326,9 +3477,9 @@ static struct kobject *md_probe(dev_t dev, int *part, void *data) disk->queue = mddev->queue; add_disk(disk); mddev->gendisk = disk; - mutex_unlock(&disks_mutex); error = kobject_init_and_add(&mddev->kobj, &md_ktype, &disk->dev.kobj, "%s", "md"); + mutex_unlock(&disks_mutex); if (error) printk(KERN_WARNING "md: cannot register %s/md - name in use\n", disk->disk_name); @@ -3341,7 +3492,11 @@ static void md_safemode_timeout(unsigned long data) { mddev_t *mddev = (mddev_t *) data; - mddev->safemode = 1; + if (!atomic_read(&mddev->writes_pending)) { + mddev->safemode = 1; + if (mddev->external) + sysfs_notify(&mddev->kobj, NULL, "array_state"); + } md_wakeup_thread(mddev->thread); } @@ -3448,6 +3603,7 @@ static int do_md_run(mddev_t * mddev) return -EINVAL; } } + sysfs_notify(&rdev->kobj, NULL, "state"); } md_probe(mddev->unit, NULL, NULL); @@ -3608,6 +3764,9 @@ static int do_md_run(mddev_t * mddev) mddev->changed = 1; md_new_event(mddev); + sysfs_notify(&mddev->kobj, NULL, "array_state"); + sysfs_notify(&mddev->kobj, NULL, "sync_action"); + sysfs_notify(&mddev->kobj, NULL, "degraded"); kobject_uevent(&mddev->gendisk->dev.kobj, KOBJ_CHANGE); return 0; } @@ -3642,6 +3801,8 @@ static int restart_array(mddev_t *mddev) md_wakeup_thread(mddev->thread); md_wakeup_thread(mddev->sync_thread); err = 0; + sysfs_notify(&mddev->kobj, NULL, "array_state"); + } else err = -EINVAL; @@ -3777,6 +3938,7 @@ static int do_md_stop(mddev_t * mddev, int mode) mddev->size = 0; mddev->raid_disks = 0; mddev->recovery_cp = 0; + mddev->resync_min = 0; mddev->resync_max = MaxSector; mddev->reshape_position = MaxSector; mddev->external = 0; @@ -3811,6 +3973,7 @@ static int do_md_stop(mddev_t * mddev, int mode) mdname(mddev)); err = 0; md_new_event(mddev); + sysfs_notify(&mddev->kobj, NULL, "array_state"); out: return err; } @@ -4172,8 +4335,12 @@ static int add_new_disk(mddev_t * mddev, mdu_disk_info_t *info) } if (err) export_rdev(rdev); + else + sysfs_notify(&rdev->kobj, NULL, "state"); md_update_sb(mddev, 1); + if (mddev->degraded) + set_bit(MD_RECOVERY_RECOVER, &mddev->recovery); set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); md_wakeup_thread(mddev->thread); return err; @@ -4232,9 +4399,6 @@ static int hot_remove_disk(mddev_t * mddev, dev_t dev) char b[BDEVNAME_SIZE]; mdk_rdev_t *rdev; - if (!mddev->pers) - return -ENODEV; - rdev = find_rdev(mddev, dev); if (!rdev) return -ENXIO; @@ -4811,8 +4975,9 @@ static int md_ioctl(struct inode *inode, struct file *file, mddev->ro && mddev->pers) { if (mddev->ro == 2) { mddev->ro = 0; - set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); - md_wakeup_thread(mddev->thread); + sysfs_notify(&mddev->kobj, NULL, "array_state"); + set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); + md_wakeup_thread(mddev->thread); } else { err = -EROFS; @@ -5029,6 +5194,9 @@ void md_error(mddev_t *mddev, mdk_rdev_t *rdev) if (!mddev->pers->error_handler) return; mddev->pers->error_handler(mddev,rdev); + if (mddev->degraded) + set_bit(MD_RECOVERY_RECOVER, &mddev->recovery); + set_bit(StateChanged, &rdev->flags); set_bit(MD_RECOVERY_INTR, &mddev->recovery); set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); md_wakeup_thread(mddev->thread); @@ -5451,6 +5619,7 @@ void md_done_sync(mddev_t *mddev, int blocks, int ok) */ void md_write_start(mddev_t *mddev, struct bio *bi) { + int did_change = 0; if (bio_data_dir(bi) != WRITE) return; @@ -5461,6 +5630,7 @@ void md_write_start(mddev_t *mddev, struct bio *bi) set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); md_wakeup_thread(mddev->thread); md_wakeup_thread(mddev->sync_thread); + did_change = 1; } atomic_inc(&mddev->writes_pending); if (mddev->safemode == 1) @@ -5471,10 +5641,12 @@ void md_write_start(mddev_t *mddev, struct bio *bi) mddev->in_sync = 0; set_bit(MD_CHANGE_CLEAN, &mddev->flags); md_wakeup_thread(mddev->thread); + did_change = 1; } spin_unlock_irq(&mddev->write_lock); - sysfs_notify(&mddev->kobj, NULL, "array_state"); } + if (did_change) + sysfs_notify(&mddev->kobj, NULL, "array_state"); wait_event(mddev->sb_wait, !test_bit(MD_CHANGE_CLEAN, &mddev->flags) && !test_bit(MD_CHANGE_PENDING, &mddev->flags)); @@ -5502,6 +5674,8 @@ void md_allow_write(mddev_t *mddev) return; if (mddev->ro) return; + if (!mddev->pers->sync_request) + return; spin_lock_irq(&mddev->write_lock); if (mddev->in_sync) { @@ -5625,9 +5799,11 @@ void md_do_sync(mddev_t *mddev) max_sectors = mddev->resync_max_sectors; mddev->resync_mismatches = 0; /* we don't use the checkpoint if there's a bitmap */ - if (!mddev->bitmap && - !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery)) + if (test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery)) + j = mddev->resync_min; + else if (!mddev->bitmap) j = mddev->recovery_cp; + } else if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery)) max_sectors = mddev->size << 1; else { @@ -5796,6 +5972,7 @@ void md_do_sync(mddev_t *mddev) skip: mddev->curr_resync = 0; + mddev->resync_min = 0; mddev->resync_max = MaxSector; sysfs_notify(&mddev->kobj, NULL, "sync_completed"); wake_up(&resync_wait); @@ -5845,7 +6022,8 @@ static int remove_and_add_spares(mddev_t *mddev) if (rdev->raid_disk < 0 && !test_bit(Faulty, &rdev->flags)) { rdev->recovery_offset = 0; - if (mddev->pers->hot_add_disk(mddev,rdev)) { + if (mddev->pers-> + hot_add_disk(mddev, rdev) == 0) { char nm[20]; sprintf(nm, "rd%d", rdev->raid_disk); if (sysfs_create_link(&mddev->kobj, @@ -5920,23 +6098,31 @@ void md_check_recovery(mddev_t *mddev) int spares = 0; if (!mddev->external) { + int did_change = 0; spin_lock_irq(&mddev->write_lock); if (mddev->safemode && !atomic_read(&mddev->writes_pending) && !mddev->in_sync && mddev->recovery_cp == MaxSector) { mddev->in_sync = 1; + did_change = 1; if (mddev->persistent) set_bit(MD_CHANGE_CLEAN, &mddev->flags); } if (mddev->safemode == 1) mddev->safemode = 0; spin_unlock_irq(&mddev->write_lock); + if (did_change) + sysfs_notify(&mddev->kobj, NULL, "array_state"); } if (mddev->flags) md_update_sb(mddev, 0); + rdev_for_each(rdev, rtmp, mddev) + if (test_and_clear_bit(StateChanged, &rdev->flags)) + sysfs_notify(&rdev->kobj, NULL, "state"); + if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) && !test_bit(MD_RECOVERY_DONE, &mddev->recovery)) { @@ -5951,7 +6137,9 @@ void md_check_recovery(mddev_t *mddev) if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery)) { /* success...*/ /* activate any spares */ - mddev->pers->spare_active(mddev); + if (mddev->pers->spare_active(mddev)) + sysfs_notify(&mddev->kobj, NULL, + "degraded"); } md_update_sb(mddev, 1); @@ -5965,13 +6153,18 @@ void md_check_recovery(mddev_t *mddev) mddev->recovery = 0; /* flag recovery needed just to double check */ set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); + sysfs_notify(&mddev->kobj, NULL, "sync_action"); md_new_event(mddev); goto unlock; } + /* Set RUNNING before clearing NEEDED to avoid + * any transients in the value of "sync_action". + */ + set_bit(MD_RECOVERY_RUNNING, &mddev->recovery); + clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery); /* Clear some bits that don't mean anything, but * might be left set */ - clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery); clear_bit(MD_RECOVERY_INTR, &mddev->recovery); clear_bit(MD_RECOVERY_DONE, &mddev->recovery); @@ -5989,17 +6182,19 @@ void md_check_recovery(mddev_t *mddev) /* Cannot proceed */ goto unlock; set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery); + clear_bit(MD_RECOVERY_RECOVER, &mddev->recovery); } else if ((spares = remove_and_add_spares(mddev))) { clear_bit(MD_RECOVERY_SYNC, &mddev->recovery); clear_bit(MD_RECOVERY_CHECK, &mddev->recovery); + set_bit(MD_RECOVERY_RECOVER, &mddev->recovery); } else if (mddev->recovery_cp < MaxSector) { set_bit(MD_RECOVERY_SYNC, &mddev->recovery); + clear_bit(MD_RECOVERY_RECOVER, &mddev->recovery); } else if (!test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) /* nothing to be done ... */ goto unlock; if (mddev->pers->sync_request) { - set_bit(MD_RECOVERY_RUNNING, &mddev->recovery); if (spares && mddev->bitmap && ! mddev->bitmap->file) { /* We are adding a device or devices to an array * which has the bitmap stored on all devices. @@ -6018,9 +6213,16 @@ void md_check_recovery(mddev_t *mddev) mddev->recovery = 0; } else md_wakeup_thread(mddev->sync_thread); + sysfs_notify(&mddev->kobj, NULL, "sync_action"); md_new_event(mddev); } unlock: + if (!mddev->sync_thread) { + clear_bit(MD_RECOVERY_RUNNING, &mddev->recovery); + if (test_and_clear_bit(MD_RECOVERY_RECOVER, + &mddev->recovery)) + sysfs_notify(&mddev->kobj, NULL, "sync_action"); + } mddev_unlock(mddev); } } diff --git a/drivers/md/multipath.c b/drivers/md/multipath.c index e968116e0de9..541cbe3414bd 100644 --- a/drivers/md/multipath.c +++ b/drivers/md/multipath.c @@ -281,13 +281,18 @@ static int multipath_add_disk(mddev_t *mddev, mdk_rdev_t *rdev) { multipath_conf_t *conf = mddev->private; struct request_queue *q; - int found = 0; + int err = -EEXIST; int path; struct multipath_info *p; + int first = 0; + int last = mddev->raid_disks - 1; + + if (rdev->raid_disk >= 0) + first = last = rdev->raid_disk; print_multipath_conf(conf); - for (path=0; path<mddev->raid_disks; path++) + for (path = first; path <= last; path++) if ((p=conf->multipaths+path)->rdev == NULL) { q = rdev->bdev->bd_disk->queue; blk_queue_stack_limits(mddev->queue, q); @@ -307,11 +312,13 @@ static int multipath_add_disk(mddev_t *mddev, mdk_rdev_t *rdev) rdev->raid_disk = path; set_bit(In_sync, &rdev->flags); rcu_assign_pointer(p->rdev, rdev); - found = 1; + err = 0; + break; } print_multipath_conf(conf); - return found; + + return err; } static int multipath_remove_disk(mddev_t *mddev, int number) diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index c610b947218a..f05d5983efb6 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -1100,11 +1100,16 @@ static int raid1_spare_active(mddev_t *mddev) static int raid1_add_disk(mddev_t *mddev, mdk_rdev_t *rdev) { conf_t *conf = mddev->private; - int found = 0; + int err = -EEXIST; int mirror = 0; mirror_info_t *p; + int first = 0; + int last = mddev->raid_disks - 1; - for (mirror=0; mirror < mddev->raid_disks; mirror++) + if (rdev->raid_disk >= 0) + first = last = rdev->raid_disk; + + for (mirror = first; mirror <= last; mirror++) if ( !(p=conf->mirrors+mirror)->rdev) { blk_queue_stack_limits(mddev->queue, @@ -1119,7 +1124,7 @@ static int raid1_add_disk(mddev_t *mddev, mdk_rdev_t *rdev) p->head_position = 0; rdev->raid_disk = mirror; - found = 1; + err = 0; /* As all devices are equivalent, we don't need a full recovery * if this was recently any drive of the array */ @@ -1130,7 +1135,7 @@ static int raid1_add_disk(mddev_t *mddev, mdk_rdev_t *rdev) } print_conf(conf); - return found; + return err; } static int raid1_remove_disk(mddev_t *mddev, int number) diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index a71277b640ab..df08a9fa3a1f 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -1113,24 +1113,30 @@ static int raid10_spare_active(mddev_t *mddev) static int raid10_add_disk(mddev_t *mddev, mdk_rdev_t *rdev) { conf_t *conf = mddev->private; - int found = 0; + int err = -EEXIST; int mirror; mirror_info_t *p; + int first = 0; + int last = mddev->raid_disks - 1; if (mddev->recovery_cp < MaxSector) /* only hot-add to in-sync arrays, as recovery is * very different from resync */ - return 0; + return -EBUSY; if (!enough(conf)) - return 0; + return -EINVAL; + + if (rdev->raid_disk) + first = last = rdev->raid_disk; if (rdev->saved_raid_disk >= 0 && + rdev->saved_raid_disk >= first && conf->mirrors[rdev->saved_raid_disk].rdev == NULL) mirror = rdev->saved_raid_disk; else - mirror = 0; - for ( ; mirror < mddev->raid_disks; mirror++) + mirror = first; + for ( ; mirror <= last ; mirror++) if ( !(p=conf->mirrors+mirror)->rdev) { blk_queue_stack_limits(mddev->queue, @@ -1145,7 +1151,7 @@ static int raid10_add_disk(mddev_t *mddev, mdk_rdev_t *rdev) p->head_position = 0; rdev->raid_disk = mirror; - found = 1; + err = 0; if (rdev->saved_raid_disk != mirror) conf->fullsync = 1; rcu_assign_pointer(p->rdev, rdev); @@ -1153,7 +1159,7 @@ static int raid10_add_disk(mddev_t *mddev, mdk_rdev_t *rdev) } print_conf(conf); - return found; + return err; } static int raid10_remove_disk(mddev_t *mddev, int number) diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 54c8ee28fcc4..442622067cae 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -115,15 +115,20 @@ static void return_io(struct bio *return_bi) return_bi = bi->bi_next; bi->bi_next = NULL; bi->bi_size = 0; - bi->bi_end_io(bi, - test_bit(BIO_UPTODATE, &bi->bi_flags) - ? 0 : -EIO); + bio_endio(bi, 0); bi = return_bi; } } static void print_raid5_conf (raid5_conf_t *conf); +static int stripe_operations_active(struct stripe_head *sh) +{ + return sh->check_state || sh->reconstruct_state || + test_bit(STRIPE_BIOFILL_RUN, &sh->state) || + test_bit(STRIPE_COMPUTE_RUN, &sh->state); +} + static void __release_stripe(raid5_conf_t *conf, struct stripe_head *sh) { if (atomic_dec_and_test(&sh->count)) { @@ -143,7 +148,7 @@ static void __release_stripe(raid5_conf_t *conf, struct stripe_head *sh) } md_wakeup_thread(conf->mddev->thread); } else { - BUG_ON(sh->ops.pending); + BUG_ON(stripe_operations_active(sh)); if (test_and_clear_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) { atomic_dec(&conf->preread_active_stripes); if (atomic_read(&conf->preread_active_stripes) < IO_THRESHOLD) @@ -245,7 +250,7 @@ static void init_stripe(struct stripe_head *sh, sector_t sector, int pd_idx, int BUG_ON(atomic_read(&sh->count) != 0); BUG_ON(test_bit(STRIPE_HANDLE, &sh->state)); - BUG_ON(sh->ops.pending || sh->ops.ack || sh->ops.complete); + BUG_ON(stripe_operations_active(sh)); CHECK_DEVLOCK(); pr_debug("init_stripe called, stripe %llu\n", @@ -346,62 +351,18 @@ static struct stripe_head *get_active_stripe(raid5_conf_t *conf, sector_t sector return sh; } -/* test_and_ack_op() ensures that we only dequeue an operation once */ -#define test_and_ack_op(op, pend) \ -do { \ - if (test_bit(op, &sh->ops.pending) && \ - !test_bit(op, &sh->ops.complete)) { \ - if (test_and_set_bit(op, &sh->ops.ack)) \ - clear_bit(op, &pend); \ - else \ - ack++; \ - } else \ - clear_bit(op, &pend); \ -} while (0) - -/* find new work to run, do not resubmit work that is already - * in flight - */ -static unsigned long get_stripe_work(struct stripe_head *sh) -{ - unsigned long pending; - int ack = 0; - - pending = sh->ops.pending; - - test_and_ack_op(STRIPE_OP_BIOFILL, pending); - test_and_ack_op(STRIPE_OP_COMPUTE_BLK, pending); - test_and_ack_op(STRIPE_OP_PREXOR, pending); - test_and_ack_op(STRIPE_OP_BIODRAIN, pending); - test_and_ack_op(STRIPE_OP_POSTXOR, pending); - test_and_ack_op(STRIPE_OP_CHECK, pending); - if (test_and_clear_bit(STRIPE_OP_IO, &sh->ops.pending)) - ack++; - - sh->ops.count -= ack; - if (unlikely(sh->ops.count < 0)) { - printk(KERN_ERR "pending: %#lx ops.pending: %#lx ops.ack: %#lx " - "ops.complete: %#lx\n", pending, sh->ops.pending, - sh->ops.ack, sh->ops.complete); - BUG(); - } - - return pending; -} - static void raid5_end_read_request(struct bio *bi, int error); static void raid5_end_write_request(struct bio *bi, int error); -static void ops_run_io(struct stripe_head *sh) +static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s) { raid5_conf_t *conf = sh->raid_conf; int i, disks = sh->disks; might_sleep(); - set_bit(STRIPE_IO_STARTED, &sh->state); for (i = disks; i--; ) { int rw; struct bio *bi; @@ -430,11 +391,11 @@ static void ops_run_io(struct stripe_head *sh) rcu_read_unlock(); if (rdev) { - if (test_bit(STRIPE_SYNCING, &sh->state) || - test_bit(STRIPE_EXPAND_SOURCE, &sh->state) || - test_bit(STRIPE_EXPAND_READY, &sh->state)) + if (s->syncing || s->expanding || s->expanded) md_sync_acct(rdev->bdev, STRIPE_SECTORS); + set_bit(STRIPE_IO_STARTED, &sh->state); + bi->bi_bdev = rdev->bdev; pr_debug("%s: for %llu schedule op %ld on disc %d\n", __func__, (unsigned long long)sh->sector, @@ -528,38 +489,34 @@ static void ops_complete_biofill(void *stripe_head_ref) (unsigned long long)sh->sector); /* clear completed biofills */ + spin_lock_irq(&conf->device_lock); for (i = sh->disks; i--; ) { struct r5dev *dev = &sh->dev[i]; /* acknowledge completion of a biofill operation */ /* and check if we need to reply to a read request, * new R5_Wantfill requests are held off until - * !test_bit(STRIPE_OP_BIOFILL, &sh->ops.pending) + * !STRIPE_BIOFILL_RUN */ if (test_and_clear_bit(R5_Wantfill, &dev->flags)) { struct bio *rbi, *rbi2; - /* The access to dev->read is outside of the - * spin_lock_irq(&conf->device_lock), but is protected - * by the STRIPE_OP_BIOFILL pending bit - */ BUG_ON(!dev->read); rbi = dev->read; dev->read = NULL; while (rbi && rbi->bi_sector < dev->sector + STRIPE_SECTORS) { rbi2 = r5_next_bio(rbi, dev->sector); - spin_lock_irq(&conf->device_lock); if (--rbi->bi_phys_segments == 0) { rbi->bi_next = return_bi; return_bi = rbi; } - spin_unlock_irq(&conf->device_lock); rbi = rbi2; } } } - set_bit(STRIPE_OP_BIOFILL, &sh->ops.complete); + spin_unlock_irq(&conf->device_lock); + clear_bit(STRIPE_BIOFILL_RUN, &sh->state); return_io(return_bi); @@ -610,13 +567,14 @@ static void ops_complete_compute5(void *stripe_head_ref) set_bit(R5_UPTODATE, &tgt->flags); BUG_ON(!test_bit(R5_Wantcompute, &tgt->flags)); clear_bit(R5_Wantcompute, &tgt->flags); - set_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.complete); + clear_bit(STRIPE_COMPUTE_RUN, &sh->state); + if (sh->check_state == check_state_compute_run) + sh->check_state = check_state_compute_result; set_bit(STRIPE_HANDLE, &sh->state); release_stripe(sh); } -static struct dma_async_tx_descriptor * -ops_run_compute5(struct stripe_head *sh, unsigned long pending) +static struct dma_async_tx_descriptor *ops_run_compute5(struct stripe_head *sh) { /* kernel stack size limits the total number of disks */ int disks = sh->disks; @@ -646,10 +604,6 @@ ops_run_compute5(struct stripe_head *sh, unsigned long pending) ASYNC_TX_XOR_ZERO_DST, NULL, ops_complete_compute5, sh); - /* ack now if postxor is not set to be run */ - if (tx && !test_bit(STRIPE_OP_POSTXOR, &pending)) - async_tx_ack(tx); - return tx; } @@ -659,8 +613,6 @@ static void ops_complete_prexor(void *stripe_head_ref) pr_debug("%s: stripe %llu\n", __func__, (unsigned long long)sh->sector); - - set_bit(STRIPE_OP_PREXOR, &sh->ops.complete); } static struct dma_async_tx_descriptor * @@ -680,7 +632,7 @@ ops_run_prexor(struct stripe_head *sh, struct dma_async_tx_descriptor *tx) for (i = disks; i--; ) { struct r5dev *dev = &sh->dev[i]; /* Only process blocks that are known to be uptodate */ - if (dev->towrite && test_bit(R5_Wantprexor, &dev->flags)) + if (test_bit(R5_Wantdrain, &dev->flags)) xor_srcs[count++] = dev->page; } @@ -692,16 +644,10 @@ ops_run_prexor(struct stripe_head *sh, struct dma_async_tx_descriptor *tx) } static struct dma_async_tx_descriptor * -ops_run_biodrain(struct stripe_head *sh, struct dma_async_tx_descriptor *tx, - unsigned long pending) +ops_run_biodrain(struct stripe_head *sh, struct dma_async_tx_descriptor *tx) { int disks = sh->disks; - int pd_idx = sh->pd_idx, i; - - /* check if prexor is active which means only process blocks - * that are part of a read-modify-write (Wantprexor) - */ - int prexor = test_bit(STRIPE_OP_PREXOR, &pending); + int i; pr_debug("%s: stripe %llu\n", __func__, (unsigned long long)sh->sector); @@ -709,20 +655,8 @@ ops_run_biodrain(struct stripe_head *sh, struct dma_async_tx_descriptor *tx, for (i = disks; i--; ) { struct r5dev *dev = &sh->dev[i]; struct bio *chosen; - int towrite; - towrite = 0; - if (prexor) { /* rmw */ - if (dev->towrite && - test_bit(R5_Wantprexor, &dev->flags)) - towrite = 1; - } else { /* rcw */ - if (i != pd_idx && dev->towrite && - test_bit(R5_LOCKED, &dev->flags)) - towrite = 1; - } - - if (towrite) { + if (test_and_clear_bit(R5_Wantdrain, &dev->flags)) { struct bio *wbi; spin_lock(&sh->lock); @@ -747,18 +681,6 @@ ops_run_biodrain(struct stripe_head *sh, struct dma_async_tx_descriptor *tx, static void ops_complete_postxor(void *stripe_head_ref) { struct stripe_head *sh = stripe_head_ref; - - pr_debug("%s: stripe %llu\n", __func__, - (unsigned long long)sh->sector); - - set_bit(STRIPE_OP_POSTXOR, &sh->ops.complete); - set_bit(STRIPE_HANDLE, &sh->state); - release_stripe(sh); -} - -static void ops_complete_write(void *stripe_head_ref) -{ - struct stripe_head *sh = stripe_head_ref; int disks = sh->disks, i, pd_idx = sh->pd_idx; pr_debug("%s: stripe %llu\n", __func__, @@ -770,16 +692,21 @@ static void ops_complete_write(void *stripe_head_ref) set_bit(R5_UPTODATE, &dev->flags); } - set_bit(STRIPE_OP_BIODRAIN, &sh->ops.complete); - set_bit(STRIPE_OP_POSTXOR, &sh->ops.complete); + if (sh->reconstruct_state == reconstruct_state_drain_run) + sh->reconstruct_state = reconstruct_state_drain_result; + else if (sh->reconstruct_state == reconstruct_state_prexor_drain_run) + sh->reconstruct_state = reconstruct_state_prexor_drain_result; + else { + BUG_ON(sh->reconstruct_state != reconstruct_state_run); + sh->reconstruct_state = reconstruct_state_result; + } set_bit(STRIPE_HANDLE, &sh->state); release_stripe(sh); } static void -ops_run_postxor(struct stripe_head *sh, struct dma_async_tx_descriptor *tx, - unsigned long pending) +ops_run_postxor(struct stripe_head *sh, struct dma_async_tx_descriptor *tx) { /* kernel stack size limits the total number of disks */ int disks = sh->disks; @@ -787,9 +714,8 @@ ops_run_postxor(struct stripe_head *sh, struct dma_async_tx_descriptor *tx, int count = 0, pd_idx = sh->pd_idx, i; struct page *xor_dest; - int prexor = test_bit(STRIPE_OP_PREXOR, &pending); + int prexor = 0; unsigned long flags; - dma_async_tx_callback callback; pr_debug("%s: stripe %llu\n", __func__, (unsigned long long)sh->sector); @@ -797,7 +723,8 @@ ops_run_postxor(struct stripe_head *sh, struct dma_async_tx_descriptor *tx, /* check if prexor is active which means only process blocks * that are part of a read-modify-write (written) */ - if (prexor) { + if (sh->reconstruct_state == reconstruct_state_prexor_drain_run) { + prexor = 1; xor_dest = xor_srcs[count++] = sh->dev[pd_idx].page; for (i = disks; i--; ) { struct r5dev *dev = &sh->dev[i]; @@ -813,10 +740,6 @@ ops_run_postxor(struct stripe_head *sh, struct dma_async_tx_descriptor *tx, } } - /* check whether this postxor is part of a write */ - callback = test_bit(STRIPE_OP_BIODRAIN, &pending) ? - ops_complete_write : ops_complete_postxor; - /* 1/ if we prexor'd then the dest is reused as a source * 2/ if we did not prexor then we are redoing the parity * set ASYNC_TX_XOR_DROP_DST and ASYNC_TX_XOR_ZERO_DST @@ -830,25 +753,20 @@ ops_run_postxor(struct stripe_head *sh, struct dma_async_tx_descriptor *tx, if (unlikely(count == 1)) { flags &= ~(ASYNC_TX_XOR_DROP_DST | ASYNC_TX_XOR_ZERO_DST); tx = async_memcpy(xor_dest, xor_srcs[0], 0, 0, STRIPE_SIZE, - flags, tx, callback, sh); + flags, tx, ops_complete_postxor, sh); } else tx = async_xor(xor_dest, xor_srcs, 0, count, STRIPE_SIZE, - flags, tx, callback, sh); + flags, tx, ops_complete_postxor, sh); } static void ops_complete_check(void *stripe_head_ref) { struct stripe_head *sh = stripe_head_ref; - int pd_idx = sh->pd_idx; pr_debug("%s: stripe %llu\n", __func__, (unsigned long long)sh->sector); - if (test_and_clear_bit(STRIPE_OP_MOD_DMA_CHECK, &sh->ops.pending) && - sh->ops.zero_sum_result == 0) - set_bit(R5_UPTODATE, &sh->dev[pd_idx].flags); - - set_bit(STRIPE_OP_CHECK, &sh->ops.complete); + sh->check_state = check_state_check_result; set_bit(STRIPE_HANDLE, &sh->state); release_stripe(sh); } @@ -875,46 +793,42 @@ static void ops_run_check(struct stripe_head *sh) tx = async_xor_zero_sum(xor_dest, xor_srcs, 0, count, STRIPE_SIZE, &sh->ops.zero_sum_result, 0, NULL, NULL, NULL); - if (tx) - set_bit(STRIPE_OP_MOD_DMA_CHECK, &sh->ops.pending); - else - clear_bit(STRIPE_OP_MOD_DMA_CHECK, &sh->ops.pending); - atomic_inc(&sh->count); tx = async_trigger_callback(ASYNC_TX_DEP_ACK | ASYNC_TX_ACK, tx, ops_complete_check, sh); } -static void raid5_run_ops(struct stripe_head *sh, unsigned long pending) +static void raid5_run_ops(struct stripe_head *sh, unsigned long ops_request) { int overlap_clear = 0, i, disks = sh->disks; struct dma_async_tx_descriptor *tx = NULL; - if (test_bit(STRIPE_OP_BIOFILL, &pending)) { + if (test_bit(STRIPE_OP_BIOFILL, &ops_request)) { ops_run_biofill(sh); overlap_clear++; } - if (test_bit(STRIPE_OP_COMPUTE_BLK, &pending)) - tx = ops_run_compute5(sh, pending); + if (test_bit(STRIPE_OP_COMPUTE_BLK, &ops_request)) { + tx = ops_run_compute5(sh); + /* terminate the chain if postxor is not set to be run */ + if (tx && !test_bit(STRIPE_OP_POSTXOR, &ops_request)) + async_tx_ack(tx); + } - if (test_bit(STRIPE_OP_PREXOR, &pending)) + if (test_bit(STRIPE_OP_PREXOR, &ops_request)) tx = ops_run_prexor(sh, tx); - if (test_bit(STRIPE_OP_BIODRAIN, &pending)) { - tx = ops_run_biodrain(sh, tx, pending); + if (test_bit(STRIPE_OP_BIODRAIN, &ops_request)) { + tx = ops_run_biodrain(sh, tx); overlap_clear++; } - if (test_bit(STRIPE_OP_POSTXOR, &pending)) - ops_run_postxor(sh, tx, pending); + if (test_bit(STRIPE_OP_POSTXOR, &ops_request)) + ops_run_postxor(sh, tx); - if (test_bit(STRIPE_OP_CHECK, &pending)) + if (test_bit(STRIPE_OP_CHECK, &ops_request)) ops_run_check(sh); - if (test_bit(STRIPE_OP_IO, &pending)) - ops_run_io(sh); - if (overlap_clear) for (i = disks; i--; ) { struct r5dev *dev = &sh->dev[i]; @@ -1703,11 +1617,11 @@ static void compute_block_2(struct stripe_head *sh, int dd_idx1, int dd_idx2) } } -static int -handle_write_operations5(struct stripe_head *sh, int rcw, int expand) +static void +schedule_reconstruction5(struct stripe_head *sh, struct stripe_head_state *s, + int rcw, int expand) { int i, pd_idx = sh->pd_idx, disks = sh->disks; - int locked = 0; if (rcw) { /* if we are not expanding this is a proper write request, and @@ -1715,53 +1629,48 @@ handle_write_operations5(struct stripe_head *sh, int rcw, int expand) * stripe cache */ if (!expand) { - set_bit(STRIPE_OP_BIODRAIN, &sh->ops.pending); - sh->ops.count++; - } + sh->reconstruct_state = reconstruct_state_drain_run; + set_bit(STRIPE_OP_BIODRAIN, &s->ops_request); + } else + sh->reconstruct_state = reconstruct_state_run; - set_bit(STRIPE_OP_POSTXOR, &sh->ops.pending); - sh->ops.count++; + set_bit(STRIPE_OP_POSTXOR, &s->ops_request); for (i = disks; i--; ) { struct r5dev *dev = &sh->dev[i]; if (dev->towrite) { set_bit(R5_LOCKED, &dev->flags); + set_bit(R5_Wantdrain, &dev->flags); if (!expand) clear_bit(R5_UPTODATE, &dev->flags); - locked++; + s->locked++; } } - if (locked + 1 == disks) + if (s->locked + 1 == disks) if (!test_and_set_bit(STRIPE_FULL_WRITE, &sh->state)) atomic_inc(&sh->raid_conf->pending_full_writes); } else { BUG_ON(!(test_bit(R5_UPTODATE, &sh->dev[pd_idx].flags) || test_bit(R5_Wantcompute, &sh->dev[pd_idx].flags))); - set_bit(STRIPE_OP_PREXOR, &sh->ops.pending); - set_bit(STRIPE_OP_BIODRAIN, &sh->ops.pending); - set_bit(STRIPE_OP_POSTXOR, &sh->ops.pending); - - sh->ops.count += 3; + sh->reconstruct_state = reconstruct_state_prexor_drain_run; + set_bit(STRIPE_OP_PREXOR, &s->ops_request); + set_bit(STRIPE_OP_BIODRAIN, &s->ops_request); + set_bit(STRIPE_OP_POSTXOR, &s->ops_request); for (i = disks; i--; ) { struct r5dev *dev = &sh->dev[i]; if (i == pd_idx) continue; - /* For a read-modify write there may be blocks that are - * locked for reading while others are ready to be - * written so we distinguish these blocks by the - * R5_Wantprexor bit - */ if (dev->towrite && (test_bit(R5_UPTODATE, &dev->flags) || - test_bit(R5_Wantcompute, &dev->flags))) { - set_bit(R5_Wantprexor, &dev->flags); + test_bit(R5_Wantcompute, &dev->flags))) { + set_bit(R5_Wantdrain, &dev->flags); set_bit(R5_LOCKED, &dev->flags); clear_bit(R5_UPTODATE, &dev->flags); - locked++; + s->locked++; } } } @@ -1771,13 +1680,11 @@ handle_write_operations5(struct stripe_head *sh, int rcw, int expand) */ set_bit(R5_LOCKED, &sh->dev[pd_idx].flags); clear_bit(R5_UPTODATE, &sh->dev[pd_idx].flags); - locked++; + s->locked++; - pr_debug("%s: stripe %llu locked: %d pending: %lx\n", + pr_debug("%s: stripe %llu locked: %d ops_request: %lx\n", __func__, (unsigned long long)sh->sector, - locked, sh->ops.pending); - - return locked; + s->locked, s->ops_request); } /* @@ -1876,7 +1783,7 @@ static int stripe_to_pdidx(sector_t stripe, raid5_conf_t *conf, int disks) } static void -handle_requests_to_failed_array(raid5_conf_t *conf, struct stripe_head *sh, +handle_failed_stripe(raid5_conf_t *conf, struct stripe_head *sh, struct stripe_head_state *s, int disks, struct bio **return_bi) { @@ -1967,48 +1874,38 @@ handle_requests_to_failed_array(raid5_conf_t *conf, struct stripe_head *sh, md_wakeup_thread(conf->mddev->thread); } -/* __handle_issuing_new_read_requests5 - returns 0 if there are no more disks - * to process +/* fetch_block5 - checks the given member device to see if its data needs + * to be read or computed to satisfy a request. + * + * Returns 1 when no more member devices need to be checked, otherwise returns + * 0 to tell the loop in handle_stripe_fill5 to continue */ -static int __handle_issuing_new_read_requests5(struct stripe_head *sh, - struct stripe_head_state *s, int disk_idx, int disks) +static int fetch_block5(struct stripe_head *sh, struct stripe_head_state *s, + int disk_idx, int disks) { struct r5dev *dev = &sh->dev[disk_idx]; struct r5dev *failed_dev = &sh->dev[s->failed_num]; - /* don't schedule compute operations or reads on the parity block while - * a check is in flight - */ - if ((disk_idx == sh->pd_idx) && - test_bit(STRIPE_OP_CHECK, &sh->ops.pending)) - return ~0; - /* is the data in this block needed, and can we get it? */ if (!test_bit(R5_LOCKED, &dev->flags) && - !test_bit(R5_UPTODATE, &dev->flags) && (dev->toread || - (dev->towrite && !test_bit(R5_OVERWRITE, &dev->flags)) || - s->syncing || s->expanding || (s->failed && - (failed_dev->toread || (failed_dev->towrite && - !test_bit(R5_OVERWRITE, &failed_dev->flags) - ))))) { - /* 1/ We would like to get this block, possibly by computing it, - * but we might not be able to. - * - * 2/ Since parity check operations potentially make the parity - * block !uptodate it will need to be refreshed before any - * compute operations on data disks are scheduled. - * - * 3/ We hold off parity block re-reads until check operations - * have quiesced. + !test_bit(R5_UPTODATE, &dev->flags) && + (dev->toread || + (dev->towrite && !test_bit(R5_OVERWRITE, &dev->flags)) || + s->syncing || s->expanding || + (s->failed && + (failed_dev->toread || + (failed_dev->towrite && + !test_bit(R5_OVERWRITE, &failed_dev->flags)))))) { + /* We would like to get this block, possibly by computing it, + * otherwise read it if the backing disk is insync */ if ((s->uptodate == disks - 1) && - (s->failed && disk_idx == s->failed_num) && - !test_bit(STRIPE_OP_CHECK, &sh->ops.pending)) { - set_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.pending); + (s->failed && disk_idx == s->failed_num)) { + set_bit(STRIPE_COMPUTE_RUN, &sh->state); + set_bit(STRIPE_OP_COMPUTE_BLK, &s->ops_request); set_bit(R5_Wantcompute, &dev->flags); sh->ops.target = disk_idx; s->req_compute = 1; - sh->ops.count++; /* Careful: from this point on 'uptodate' is in the eye * of raid5_run_ops which services 'compute' operations * before writes. R5_Wantcompute flags a block that will @@ -2016,58 +1913,40 @@ static int __handle_issuing_new_read_requests5(struct stripe_head *sh, * subsequent operation. */ s->uptodate++; - return 0; /* uptodate + compute == disks */ - } else if ((s->uptodate < disks - 1) && - test_bit(R5_Insync, &dev->flags)) { - /* Note: we hold off compute operations while checks are - * in flight, but we still prefer 'compute' over 'read' - * hence we only read if (uptodate < * disks-1) - */ + return 1; /* uptodate + compute == disks */ + } else if (test_bit(R5_Insync, &dev->flags)) { set_bit(R5_LOCKED, &dev->flags); set_bit(R5_Wantread, &dev->flags); - if (!test_and_set_bit(STRIPE_OP_IO, &sh->ops.pending)) - sh->ops.count++; s->locked++; pr_debug("Reading block %d (sync=%d)\n", disk_idx, s->syncing); } } - return ~0; + return 0; } -static void handle_issuing_new_read_requests5(struct stripe_head *sh, +/** + * handle_stripe_fill5 - read or compute data to satisfy pending requests. + */ +static void handle_stripe_fill5(struct stripe_head *sh, struct stripe_head_state *s, int disks) { int i; - /* Clear completed compute operations. Parity recovery - * (STRIPE_OP_MOD_REPAIR_PD) implies a write-back which is handled - * later on in this routine - */ - if (test_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.complete) && - !test_bit(STRIPE_OP_MOD_REPAIR_PD, &sh->ops.pending)) { - clear_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.complete); - clear_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.ack); - clear_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.pending); - } - /* look for blocks to read/compute, skip this if a compute * is already in flight, or if the stripe contents are in the * midst of changing due to a write */ - if (!test_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.pending) && - !test_bit(STRIPE_OP_PREXOR, &sh->ops.pending) && - !test_bit(STRIPE_OP_POSTXOR, &sh->ops.pending)) { + if (!test_bit(STRIPE_COMPUTE_RUN, &sh->state) && !sh->check_state && + !sh->reconstruct_state) for (i = disks; i--; ) - if (__handle_issuing_new_read_requests5( - sh, s, i, disks) == 0) + if (fetch_block5(sh, s, i, disks)) break; - } set_bit(STRIPE_HANDLE, &sh->state); } -static void handle_issuing_new_read_requests6(struct stripe_head *sh, +static void handle_stripe_fill6(struct stripe_head *sh, struct stripe_head_state *s, struct r6_state *r6s, int disks) { @@ -2126,12 +2005,12 @@ static void handle_issuing_new_read_requests6(struct stripe_head *sh, } -/* handle_completed_write_requests +/* handle_stripe_clean_event * any written block on an uptodate or failed drive can be returned. * Note that if we 'wrote' to a failed drive, it will be UPTODATE, but * never LOCKED, so we don't need to test 'failed' directly. */ -static void handle_completed_write_requests(raid5_conf_t *conf, +static void handle_stripe_clean_event(raid5_conf_t *conf, struct stripe_head *sh, int disks, struct bio **return_bi) { int i; @@ -2176,7 +2055,7 @@ static void handle_completed_write_requests(raid5_conf_t *conf, md_wakeup_thread(conf->mddev->thread); } -static void handle_issuing_new_write_requests5(raid5_conf_t *conf, +static void handle_stripe_dirtying5(raid5_conf_t *conf, struct stripe_head *sh, struct stripe_head_state *s, int disks) { int rmw = 0, rcw = 0, i; @@ -2220,9 +2099,6 @@ static void handle_issuing_new_write_requests5(raid5_conf_t *conf, "%d for r-m-w\n", i); set_bit(R5_LOCKED, &dev->flags); set_bit(R5_Wantread, &dev->flags); - if (!test_and_set_bit( - STRIPE_OP_IO, &sh->ops.pending)) - sh->ops.count++; s->locked++; } else { set_bit(STRIPE_DELAYED, &sh->state); @@ -2246,9 +2122,6 @@ static void handle_issuing_new_write_requests5(raid5_conf_t *conf, "%d for Reconstruct\n", i); set_bit(R5_LOCKED, &dev->flags); set_bit(R5_Wantread, &dev->flags); - if (!test_and_set_bit( - STRIPE_OP_IO, &sh->ops.pending)) - sh->ops.count++; s->locked++; } else { set_bit(STRIPE_DELAYED, &sh->state); @@ -2266,14 +2139,13 @@ static void handle_issuing_new_write_requests5(raid5_conf_t *conf, * simultaneously. If this is not the case then new writes need to be * held off until the compute completes. */ - if ((s->req_compute || - !test_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.pending)) && - (s->locked == 0 && (rcw == 0 || rmw == 0) && - !test_bit(STRIPE_BIT_DELAY, &sh->state))) - s->locked += handle_write_operations5(sh, rcw == 0, 0); + if ((s->req_compute || !test_bit(STRIPE_COMPUTE_RUN, &sh->state)) && + (s->locked == 0 && (rcw == 0 || rmw == 0) && + !test_bit(STRIPE_BIT_DELAY, &sh->state))) + schedule_reconstruction5(sh, s, rcw == 0, 0); } -static void handle_issuing_new_write_requests6(raid5_conf_t *conf, +static void handle_stripe_dirtying6(raid5_conf_t *conf, struct stripe_head *sh, struct stripe_head_state *s, struct r6_state *r6s, int disks) { @@ -2376,92 +2248,86 @@ static void handle_issuing_new_write_requests6(raid5_conf_t *conf, static void handle_parity_checks5(raid5_conf_t *conf, struct stripe_head *sh, struct stripe_head_state *s, int disks) { - int canceled_check = 0; + struct r5dev *dev = NULL; set_bit(STRIPE_HANDLE, &sh->state); - /* complete a check operation */ - if (test_and_clear_bit(STRIPE_OP_CHECK, &sh->ops.complete)) { - clear_bit(STRIPE_OP_CHECK, &sh->ops.ack); - clear_bit(STRIPE_OP_CHECK, &sh->ops.pending); + switch (sh->check_state) { + case check_state_idle: + /* start a new check operation if there are no failures */ if (s->failed == 0) { - if (sh->ops.zero_sum_result == 0) - /* parity is correct (on disc, - * not in buffer any more) - */ - set_bit(STRIPE_INSYNC, &sh->state); - else { - conf->mddev->resync_mismatches += - STRIPE_SECTORS; - if (test_bit( - MD_RECOVERY_CHECK, &conf->mddev->recovery)) - /* don't try to repair!! */ - set_bit(STRIPE_INSYNC, &sh->state); - else { - set_bit(STRIPE_OP_COMPUTE_BLK, - &sh->ops.pending); - set_bit(STRIPE_OP_MOD_REPAIR_PD, - &sh->ops.pending); - set_bit(R5_Wantcompute, - &sh->dev[sh->pd_idx].flags); - sh->ops.target = sh->pd_idx; - sh->ops.count++; - s->uptodate++; - } - } - } else - canceled_check = 1; /* STRIPE_INSYNC is not set */ - } - - /* start a new check operation if there are no failures, the stripe is - * not insync, and a repair is not in flight - */ - if (s->failed == 0 && - !test_bit(STRIPE_INSYNC, &sh->state) && - !test_bit(STRIPE_OP_MOD_REPAIR_PD, &sh->ops.pending)) { - if (!test_and_set_bit(STRIPE_OP_CHECK, &sh->ops.pending)) { BUG_ON(s->uptodate != disks); + sh->check_state = check_state_run; + set_bit(STRIPE_OP_CHECK, &s->ops_request); clear_bit(R5_UPTODATE, &sh->dev[sh->pd_idx].flags); - sh->ops.count++; s->uptodate--; + break; } - } - - /* check if we can clear a parity disk reconstruct */ - if (test_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.complete) && - test_bit(STRIPE_OP_MOD_REPAIR_PD, &sh->ops.pending)) { - - clear_bit(STRIPE_OP_MOD_REPAIR_PD, &sh->ops.pending); - clear_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.complete); - clear_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.ack); - clear_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.pending); - } - + dev = &sh->dev[s->failed_num]; + /* fall through */ + case check_state_compute_result: + sh->check_state = check_state_idle; + if (!dev) + dev = &sh->dev[sh->pd_idx]; + + /* check that a write has not made the stripe insync */ + if (test_bit(STRIPE_INSYNC, &sh->state)) + break; - /* Wait for check parity and compute block operations to complete - * before write-back. If a failure occurred while the check operation - * was in flight we need to cycle this stripe through handle_stripe - * since the parity block may not be uptodate - */ - if (!canceled_check && !test_bit(STRIPE_INSYNC, &sh->state) && - !test_bit(STRIPE_OP_CHECK, &sh->ops.pending) && - !test_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.pending)) { - struct r5dev *dev; /* either failed parity check, or recovery is happening */ - if (s->failed == 0) - s->failed_num = sh->pd_idx; - dev = &sh->dev[s->failed_num]; BUG_ON(!test_bit(R5_UPTODATE, &dev->flags)); BUG_ON(s->uptodate != disks); set_bit(R5_LOCKED, &dev->flags); + s->locked++; set_bit(R5_Wantwrite, &dev->flags); - if (!test_and_set_bit(STRIPE_OP_IO, &sh->ops.pending)) - sh->ops.count++; clear_bit(STRIPE_DEGRADED, &sh->state); - s->locked++; set_bit(STRIPE_INSYNC, &sh->state); + break; + case check_state_run: + break; /* we will be called again upon completion */ + case check_state_check_result: + sh->check_state = check_state_idle; + + /* if a failure occurred during the check operation, leave + * STRIPE_INSYNC not set and let the stripe be handled again + */ + if (s->failed) + break; + + /* handle a successful check operation, if parity is correct + * we are done. Otherwise update the mismatch count and repair + * parity if !MD_RECOVERY_CHECK + */ + if (sh->ops.zero_sum_result == 0) + /* parity is correct (on disc, + * not in buffer any more) + */ + set_bit(STRIPE_INSYNC, &sh->state); + else { + conf->mddev->resync_mismatches += STRIPE_SECTORS; + if (test_bit(MD_RECOVERY_CHECK, &conf->mddev->recovery)) + /* don't try to repair!! */ + set_bit(STRIPE_INSYNC, &sh->state); + else { + sh->check_state = check_state_compute_run; + set_bit(STRIPE_COMPUTE_RUN, &sh->state); + set_bit(STRIPE_OP_COMPUTE_BLK, &s->ops_request); + set_bit(R5_Wantcompute, + &sh->dev[sh->pd_idx].flags); + sh->ops.target = sh->pd_idx; + s->uptodate++; + } + } + break; + case check_state_compute_run: + break; + default: + printk(KERN_ERR "%s: unknown check_state: %d sector: %llu\n", + __func__, sh->check_state, + (unsigned long long) sh->sector); + BUG(); } } @@ -2646,15 +2512,14 @@ static void handle_stripe5(struct stripe_head *sh) struct bio *return_bi = NULL; struct stripe_head_state s; struct r5dev *dev; - unsigned long pending = 0; mdk_rdev_t *blocked_rdev = NULL; int prexor; memset(&s, 0, sizeof(s)); - pr_debug("handling stripe %llu, state=%#lx cnt=%d, pd_idx=%d " - "ops=%lx:%lx:%lx\n", (unsigned long long)sh->sector, sh->state, - atomic_read(&sh->count), sh->pd_idx, - sh->ops.pending, sh->ops.ack, sh->ops.complete); + pr_debug("handling stripe %llu, state=%#lx cnt=%d, pd_idx=%d check:%d " + "reconstruct:%d\n", (unsigned long long)sh->sector, sh->state, + atomic_read(&sh->count), sh->pd_idx, sh->check_state, + sh->reconstruct_state); spin_lock(&sh->lock); clear_bit(STRIPE_HANDLE, &sh->state); @@ -2663,15 +2528,8 @@ static void handle_stripe5(struct stripe_head *sh) s.syncing = test_bit(STRIPE_SYNCING, &sh->state); s.expanding = test_bit(STRIPE_EXPAND_SOURCE, &sh->state); s.expanded = test_bit(STRIPE_EXPAND_READY, &sh->state); - /* Now to look around and see what can be done */ - - /* clean-up completed biofill operations */ - if (test_bit(STRIPE_OP_BIOFILL, &sh->ops.complete)) { - clear_bit(STRIPE_OP_BIOFILL, &sh->ops.pending); - clear_bit(STRIPE_OP_BIOFILL, &sh->ops.ack); - clear_bit(STRIPE_OP_BIOFILL, &sh->ops.complete); - } + /* Now to look around and see what can be done */ rcu_read_lock(); for (i=disks; i--; ) { mdk_rdev_t *rdev; @@ -2685,10 +2543,10 @@ static void handle_stripe5(struct stripe_head *sh) /* maybe we can request a biofill operation * * new wantfill requests are only permitted while - * STRIPE_OP_BIOFILL is clear + * ops_complete_biofill is guaranteed to be inactive */ if (test_bit(R5_UPTODATE, &dev->flags) && dev->toread && - !test_bit(STRIPE_OP_BIOFILL, &sh->ops.pending)) + !test_bit(STRIPE_BIOFILL_RUN, &sh->state)) set_bit(R5_Wantfill, &dev->flags); /* now count some things */ @@ -2732,8 +2590,10 @@ static void handle_stripe5(struct stripe_head *sh) goto unlock; } - if (s.to_fill && !test_and_set_bit(STRIPE_OP_BIOFILL, &sh->ops.pending)) - sh->ops.count++; + if (s.to_fill && !test_bit(STRIPE_BIOFILL_RUN, &sh->state)) { + set_bit(STRIPE_OP_BIOFILL, &s.ops_request); + set_bit(STRIPE_BIOFILL_RUN, &sh->state); + } pr_debug("locked=%d uptodate=%d to_read=%d" " to_write=%d failed=%d failed_num=%d\n", @@ -2743,8 +2603,7 @@ static void handle_stripe5(struct stripe_head *sh) * need to be failed */ if (s.failed > 1 && s.to_read+s.to_write+s.written) - handle_requests_to_failed_array(conf, sh, &s, disks, - &return_bi); + handle_failed_stripe(conf, sh, &s, disks, &return_bi); if (s.failed > 1 && s.syncing) { md_done_sync(conf->mddev, STRIPE_SECTORS,0); clear_bit(STRIPE_SYNCING, &sh->state); @@ -2760,48 +2619,25 @@ static void handle_stripe5(struct stripe_head *sh) !test_bit(R5_LOCKED, &dev->flags) && test_bit(R5_UPTODATE, &dev->flags)) || (s.failed == 1 && s.failed_num == sh->pd_idx))) - handle_completed_write_requests(conf, sh, disks, &return_bi); + handle_stripe_clean_event(conf, sh, disks, &return_bi); /* Now we might consider reading some blocks, either to check/generate * parity, or to satisfy requests * or to load a block that is being partially written. */ if (s.to_read || s.non_overwrite || - (s.syncing && (s.uptodate + s.compute < disks)) || s.expanding || - test_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.pending)) - handle_issuing_new_read_requests5(sh, &s, disks); + (s.syncing && (s.uptodate + s.compute < disks)) || s.expanding) + handle_stripe_fill5(sh, &s, disks); /* Now we check to see if any write operations have recently * completed */ - - /* leave prexor set until postxor is done, allows us to distinguish - * a rmw from a rcw during biodrain - */ prexor = 0; - if (test_bit(STRIPE_OP_PREXOR, &sh->ops.complete) && - test_bit(STRIPE_OP_POSTXOR, &sh->ops.complete)) { - + if (sh->reconstruct_state == reconstruct_state_prexor_drain_result) prexor = 1; - clear_bit(STRIPE_OP_PREXOR, &sh->ops.complete); - clear_bit(STRIPE_OP_PREXOR, &sh->ops.ack); - clear_bit(STRIPE_OP_PREXOR, &sh->ops.pending); - - for (i = disks; i--; ) - clear_bit(R5_Wantprexor, &sh->dev[i].flags); - } - - /* if only POSTXOR is set then this is an 'expand' postxor */ - if (test_bit(STRIPE_OP_BIODRAIN, &sh->ops.complete) && - test_bit(STRIPE_OP_POSTXOR, &sh->ops.complete)) { - - clear_bit(STRIPE_OP_BIODRAIN, &sh->ops.complete); - clear_bit(STRIPE_OP_BIODRAIN, &sh->ops.ack); - clear_bit(STRIPE_OP_BIODRAIN, &sh->ops.pending); - - clear_bit(STRIPE_OP_POSTXOR, &sh->ops.complete); - clear_bit(STRIPE_OP_POSTXOR, &sh->ops.ack); - clear_bit(STRIPE_OP_POSTXOR, &sh->ops.pending); + if (sh->reconstruct_state == reconstruct_state_drain_result || + sh->reconstruct_state == reconstruct_state_prexor_drain_result) { + sh->reconstruct_state = reconstruct_state_idle; /* All the 'written' buffers and the parity block are ready to * be written back to disk @@ -2813,9 +2649,6 @@ static void handle_stripe5(struct stripe_head *sh) (i == sh->pd_idx || dev->written)) { pr_debug("Writing block %d\n", i); set_bit(R5_Wantwrite, &dev->flags); - if (!test_and_set_bit( - STRIPE_OP_IO, &sh->ops.pending)) - sh->ops.count++; if (prexor) continue; if (!test_bit(R5_Insync, &dev->flags) || @@ -2837,20 +2670,18 @@ static void handle_stripe5(struct stripe_head *sh) * 2/ A 'check' operation is in flight, as it may clobber the parity * block. */ - if (s.to_write && !test_bit(STRIPE_OP_POSTXOR, &sh->ops.pending) && - !test_bit(STRIPE_OP_CHECK, &sh->ops.pending)) - handle_issuing_new_write_requests5(conf, sh, &s, disks); + if (s.to_write && !sh->reconstruct_state && !sh->check_state) + handle_stripe_dirtying5(conf, sh, &s, disks); /* maybe we need to check and possibly fix the parity for this stripe * Any reads will already have been scheduled, so we just see if enough * data is available. The parity check is held off while parity * dependent operations are in flight. */ - if ((s.syncing && s.locked == 0 && - !test_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.pending) && - !test_bit(STRIPE_INSYNC, &sh->state)) || - test_bit(STRIPE_OP_CHECK, &sh->ops.pending) || - test_bit(STRIPE_OP_MOD_REPAIR_PD, &sh->ops.pending)) + if (sh->check_state || + (s.syncing && s.locked == 0 && + !test_bit(STRIPE_COMPUTE_RUN, &sh->state) && + !test_bit(STRIPE_INSYNC, &sh->state))) handle_parity_checks5(conf, sh, &s, disks); if (s.syncing && s.locked == 0 && test_bit(STRIPE_INSYNC, &sh->state)) { @@ -2869,52 +2700,35 @@ static void handle_stripe5(struct stripe_head *sh) dev = &sh->dev[s.failed_num]; if (!test_bit(R5_ReWrite, &dev->flags)) { set_bit(R5_Wantwrite, &dev->flags); - if (!test_and_set_bit(STRIPE_OP_IO, &sh->ops.pending)) - sh->ops.count++; set_bit(R5_ReWrite, &dev->flags); set_bit(R5_LOCKED, &dev->flags); s.locked++; } else { /* let's read it back */ set_bit(R5_Wantread, &dev->flags); - if (!test_and_set_bit(STRIPE_OP_IO, &sh->ops.pending)) - sh->ops.count++; set_bit(R5_LOCKED, &dev->flags); s.locked++; } } - /* Finish postxor operations initiated by the expansion - * process - */ - if (test_bit(STRIPE_OP_POSTXOR, &sh->ops.complete) && - !test_bit(STRIPE_OP_BIODRAIN, &sh->ops.pending)) { - + /* Finish reconstruct operations initiated by the expansion process */ + if (sh->reconstruct_state == reconstruct_state_result) { + sh->reconstruct_state = reconstruct_state_idle; clear_bit(STRIPE_EXPANDING, &sh->state); - - clear_bit(STRIPE_OP_POSTXOR, &sh->ops.pending); - clear_bit(STRIPE_OP_POSTXOR, &sh->ops.ack); - clear_bit(STRIPE_OP_POSTXOR, &sh->ops.complete); - - for (i = conf->raid_disks; i--; ) { + for (i = conf->raid_disks; i--; ) set_bit(R5_Wantwrite, &sh->dev[i].flags); set_bit(R5_LOCKED, &dev->flags); s.locked++; - if (!test_and_set_bit(STRIPE_OP_IO, &sh->ops.pending)) - sh->ops.count++; - } } if (s.expanded && test_bit(STRIPE_EXPANDING, &sh->state) && - !test_bit(STRIPE_OP_POSTXOR, &sh->ops.pending)) { + !sh->reconstruct_state) { /* Need to write out all blocks after computing parity */ sh->disks = conf->raid_disks; sh->pd_idx = stripe_to_pdidx(sh->sector, conf, conf->raid_disks); - s.locked += handle_write_operations5(sh, 1, 1); - } else if (s.expanded && - s.locked == 0 && - !test_bit(STRIPE_OP_POSTXOR, &sh->ops.pending)) { + schedule_reconstruction5(sh, &s, 1, 1); + } else if (s.expanded && !sh->reconstruct_state && s.locked == 0) { clear_bit(STRIPE_EXPAND_READY, &sh->state); atomic_dec(&conf->reshape_stripes); wake_up(&conf->wait_for_overlap); @@ -2922,12 +2736,9 @@ static void handle_stripe5(struct stripe_head *sh) } if (s.expanding && s.locked == 0 && - !test_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.pending)) + !test_bit(STRIPE_COMPUTE_RUN, &sh->state)) handle_stripe_expansion(conf, sh, NULL); - if (sh->ops.count) - pending = get_stripe_work(sh); - unlock: spin_unlock(&sh->lock); @@ -2935,11 +2746,12 @@ static void handle_stripe5(struct stripe_head *sh) if (unlikely(blocked_rdev)) md_wait_for_blocked_rdev(blocked_rdev, conf->mddev); - if (pending) - raid5_run_ops(sh, pending); + if (s.ops_request) + raid5_run_ops(sh, s.ops_request); - return_io(return_bi); + ops_run_io(sh, &s); + return_io(return_bi); } static void handle_stripe6(struct stripe_head *sh, struct page *tmp_page) @@ -3047,8 +2859,7 @@ static void handle_stripe6(struct stripe_head *sh, struct page *tmp_page) * might need to be failed */ if (s.failed > 2 && s.to_read+s.to_write+s.written) - handle_requests_to_failed_array(conf, sh, &s, disks, - &return_bi); + handle_failed_stripe(conf, sh, &s, disks, &return_bi); if (s.failed > 2 && s.syncing) { md_done_sync(conf->mddev, STRIPE_SECTORS,0); clear_bit(STRIPE_SYNCING, &sh->state); @@ -3073,7 +2884,7 @@ static void handle_stripe6(struct stripe_head *sh, struct page *tmp_page) ( r6s.q_failed || ((test_bit(R5_Insync, &qdev->flags) && !test_bit(R5_LOCKED, &qdev->flags) && test_bit(R5_UPTODATE, &qdev->flags))))) - handle_completed_write_requests(conf, sh, disks, &return_bi); + handle_stripe_clean_event(conf, sh, disks, &return_bi); /* Now we might consider reading some blocks, either to check/generate * parity, or to satisfy requests @@ -3081,11 +2892,11 @@ static void handle_stripe6(struct stripe_head *sh, struct page *tmp_page) */ if (s.to_read || s.non_overwrite || (s.to_write && s.failed) || (s.syncing && (s.uptodate < disks)) || s.expanding) - handle_issuing_new_read_requests6(sh, &s, &r6s, disks); + handle_stripe_fill6(sh, &s, &r6s, disks); /* now to consider writing and what else, if anything should be read */ if (s.to_write) - handle_issuing_new_write_requests6(conf, sh, &s, &r6s, disks); + handle_stripe_dirtying6(conf, sh, &s, &r6s, disks); /* maybe we need to check and possibly fix the parity for this stripe * Any reads will already have been scheduled, so we just see if enough @@ -3141,7 +2952,7 @@ static void handle_stripe6(struct stripe_head *sh, struct page *tmp_page) } if (s.expanding && s.locked == 0 && - !test_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.pending)) + !test_bit(STRIPE_COMPUTE_RUN, &sh->state)) handle_stripe_expansion(conf, sh, &r6s); unlock: @@ -3151,68 +2962,9 @@ static void handle_stripe6(struct stripe_head *sh, struct page *tmp_page) if (unlikely(blocked_rdev)) md_wait_for_blocked_rdev(blocked_rdev, conf->mddev); - return_io(return_bi); - - for (i=disks; i-- ;) { - int rw; - struct bio *bi; - mdk_rdev_t *rdev; - if (test_and_clear_bit(R5_Wantwrite, &sh->dev[i].flags)) - rw = WRITE; - else if (test_and_clear_bit(R5_Wantread, &sh->dev[i].flags)) - rw = READ; - else - continue; - - set_bit(STRIPE_IO_STARTED, &sh->state); - - bi = &sh->dev[i].req; - - bi->bi_rw = rw; - if (rw == WRITE) - bi->bi_end_io = raid5_end_write_request; - else - bi->bi_end_io = raid5_end_read_request; - - rcu_read_lock(); - rdev = rcu_dereference(conf->disks[i].rdev); - if (rdev && test_bit(Faulty, &rdev->flags)) - rdev = NULL; - if (rdev) - atomic_inc(&rdev->nr_pending); - rcu_read_unlock(); - - if (rdev) { - if (s.syncing || s.expanding || s.expanded) - md_sync_acct(rdev->bdev, STRIPE_SECTORS); + ops_run_io(sh, &s); - bi->bi_bdev = rdev->bdev; - pr_debug("for %llu schedule op %ld on disc %d\n", - (unsigned long long)sh->sector, bi->bi_rw, i); - atomic_inc(&sh->count); - bi->bi_sector = sh->sector + rdev->data_offset; - bi->bi_flags = 1 << BIO_UPTODATE; - bi->bi_vcnt = 1; - bi->bi_max_vecs = 1; - bi->bi_idx = 0; - bi->bi_io_vec = &sh->dev[i].vec; - bi->bi_io_vec[0].bv_len = STRIPE_SIZE; - bi->bi_io_vec[0].bv_offset = 0; - bi->bi_size = STRIPE_SIZE; - bi->bi_next = NULL; - if (rw == WRITE && - test_bit(R5_ReWrite, &sh->dev[i].flags)) - atomic_add(STRIPE_SECTORS, &rdev->corrected_errors); - generic_make_request(bi); - } else { - if (rw == WRITE) - set_bit(STRIPE_DEGRADED, &sh->state); - pr_debug("skip op %ld on disc %d for sector %llu\n", - bi->bi_rw, i, (unsigned long long)sh->sector); - clear_bit(R5_LOCKED, &sh->dev[i].flags); - set_bit(STRIPE_HANDLE, &sh->state); - } - } + return_io(return_bi); } static void handle_stripe(struct stripe_head *sh, struct page *tmp_page) @@ -3700,9 +3452,7 @@ static int make_request(struct request_queue *q, struct bio * bi) if ( rw == WRITE ) md_write_end(mddev); - bi->bi_end_io(bi, - test_bit(BIO_UPTODATE, &bi->bi_flags) - ? 0 : -EIO); + bio_endio(bi, 0); } return 0; } @@ -4005,12 +3755,8 @@ static int retry_aligned_read(raid5_conf_t *conf, struct bio *raid_bio) spin_lock_irq(&conf->device_lock); remaining = --raid_bio->bi_phys_segments; spin_unlock_irq(&conf->device_lock); - if (remaining == 0) { - - raid_bio->bi_end_io(raid_bio, - test_bit(BIO_UPTODATE, &raid_bio->bi_flags) - ? 0 : -EIO); - } + if (remaining == 0) + bio_endio(raid_bio, 0); if (atomic_dec_and_test(&conf->active_aligned_reads)) wake_up(&conf->wait_for_stripe); return handled; @@ -4612,35 +4358,41 @@ abort: static int raid5_add_disk(mddev_t *mddev, mdk_rdev_t *rdev) { raid5_conf_t *conf = mddev->private; - int found = 0; + int err = -EEXIST; int disk; struct disk_info *p; + int first = 0; + int last = conf->raid_disks - 1; if (mddev->degraded > conf->max_degraded) /* no point adding a device */ - return 0; + return -EINVAL; + + if (rdev->raid_disk >= 0) + first = last = rdev->raid_disk; /* * find the disk ... but prefer rdev->saved_raid_disk * if possible. */ if (rdev->saved_raid_disk >= 0 && + rdev->saved_raid_disk >= first && conf->disks[rdev->saved_raid_disk].rdev == NULL) disk = rdev->saved_raid_disk; else - disk = 0; - for ( ; disk < conf->raid_disks; disk++) + disk = first; + for ( ; disk <= last ; disk++) if ((p=conf->disks + disk)->rdev == NULL) { clear_bit(In_sync, &rdev->flags); rdev->raid_disk = disk; - found = 1; + err = 0; if (rdev->saved_raid_disk != disk) conf->fullsync = 1; rcu_assign_pointer(p->rdev, rdev); break; } print_raid5_conf(conf); - return found; + return err; } static int raid5_resize(mddev_t *mddev, sector_t sectors) @@ -4741,7 +4493,7 @@ static int raid5_start_reshape(mddev_t *mddev) rdev_for_each(rdev, rtmp, mddev) if (rdev->raid_disk < 0 && !test_bit(Faulty, &rdev->flags)) { - if (raid5_add_disk(mddev, rdev)) { + if (raid5_add_disk(mddev, rdev) == 0) { char nm[20]; set_bit(In_sync, &rdev->flags); added_devices++; |