From b47490c9bc73d0b34e4c194db40de183e592e446 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Wed, 6 Feb 2008 01:39:50 -0800 Subject: md: Update md bitmap during resync. Currently an md array with a write-intent bitmap does not updated that bitmap to reflect successful partial resync. Rather the entire bitmap is updated when the resync completes. This is because there is no guarentee that resync requests will complete in order, and tracking each request individually is unnecessarily burdensome. However there is value in regularly updating the bitmap, so add code to periodically pause while all pending sync requests complete, then update the bitmap. Doing this only every few seconds (the same as the bitmap update time) does not notciably affect resync performance. [snitzer@gmail.com: export bitmap_cond_end_sync] Signed-off-by: Neil Brown Cc: "Mike Snitzer" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/raid/bitmap.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux/raid') diff --git a/include/linux/raid/bitmap.h b/include/linux/raid/bitmap.h index 306a1d1a5af0..e51b531cd0b2 100644 --- a/include/linux/raid/bitmap.h +++ b/include/linux/raid/bitmap.h @@ -244,6 +244,8 @@ struct bitmap { */ unsigned long daemon_lastrun; /* jiffies of last run */ unsigned long daemon_sleep; /* how many seconds between updates? */ + unsigned long last_end_sync; /* when we lasted called end_sync to + * update bitmap with resync progress */ atomic_t pending_writes; /* pending writes to the bitmap file */ wait_queue_head_t write_wait; @@ -275,6 +277,7 @@ void bitmap_endwrite(struct bitmap *bitmap, sector_t offset, int bitmap_start_sync(struct bitmap *bitmap, sector_t offset, int *blocks, int degraded); void bitmap_end_sync(struct bitmap *bitmap, sector_t offset, int *blocks, int aborted); void bitmap_close_sync(struct bitmap *bitmap); +void bitmap_cond_end_sync(struct bitmap *bitmap, sector_t sector); void bitmap_unplug(struct bitmap *bitmap); void bitmap_daemon_work(struct bitmap *bitmap); -- cgit From e691063a61f7f72a7d2882eb744b07a520cde23b Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Wed, 6 Feb 2008 01:39:51 -0800 Subject: md: support 'external' metadata for md arrays - Add a state flag 'external' to indicate that the metadata is managed externally (by user-space) so important changes need to be left of user-space to handle. Alternates are non-persistant ('none') where there is no stable metadata - after the array is stopped there is no record of it's status - and internal which can be version 0.90 or version 1.x These are selected by writing to the 'metadata' attribute. - move the updating of superblocks (sync_sbs) to after we have checked if there are any superblocks or not. - New array state 'write_pending'. This means that the metadata records the array as 'clean', but a write has been requested, so the metadata has to be updated to record a 'dirty' array before the write can continue. This change is reported to md by writing 'active' to the array_state attribute. - tidy up marking of sb_dirty: - don't set sb_dirty when resync finishes as md_check_recovery calls md_update_sb when the sync thread finishes anyway. - Don't set sb_dirty in multipath_run as the array might not be dirty. - don't mark superblock dirty when switching to 'clean' if there is no internal superblock (if external, userspace can choose to update the superblock whenever it chooses to). Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/md/md.c | 77 +++++++++++++++++++++++++++++++++++------------ include/linux/raid/md_k.h | 3 ++ 2 files changed, 61 insertions(+), 19 deletions(-) (limited to 'include/linux/raid') diff --git a/drivers/md/md.c b/drivers/md/md.c index c28a120b4161..e2782a04012d 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -778,7 +778,8 @@ static int super_90_validate(mddev_t *mddev, mdk_rdev_t *rdev) mddev->major_version = 0; mddev->minor_version = sb->minor_version; mddev->patch_version = sb->patch_version; - mddev->persistent = ! sb->not_persistent; + mddev->persistent = 1; + mddev->external = 0; mddev->chunk_size = sb->chunk_size; mddev->ctime = sb->ctime; mddev->utime = sb->utime; @@ -904,7 +905,7 @@ static void super_90_sync(mddev_t *mddev, mdk_rdev_t *rdev) sb->size = mddev->size; sb->raid_disks = mddev->raid_disks; sb->md_minor = mddev->md_minor; - sb->not_persistent = !mddev->persistent; + sb->not_persistent = 0; sb->utime = mddev->utime; sb->state = 0; sb->events_hi = (mddev->events>>32); @@ -1158,6 +1159,7 @@ static int super_1_validate(mddev_t *mddev, mdk_rdev_t *rdev) mddev->major_version = 1; mddev->patch_version = 0; mddev->persistent = 1; + mddev->external = 0; mddev->chunk_size = le32_to_cpu(sb->chunksize) << 9; mddev->ctime = le64_to_cpu(sb->ctime) & ((1ULL << 32)-1); mddev->utime = le64_to_cpu(sb->utime) & ((1ULL << 32)-1); @@ -1696,18 +1698,20 @@ repeat: MD_BUG(); mddev->events --; } - sync_sbs(mddev, nospares); /* * do not write anything to disk if using * nonpersistent superblocks */ if (!mddev->persistent) { - clear_bit(MD_CHANGE_PENDING, &mddev->flags); + if (!mddev->external) + clear_bit(MD_CHANGE_PENDING, &mddev->flags); + spin_unlock_irq(&mddev->write_lock); wake_up(&mddev->sb_wait); return; } + sync_sbs(mddev, nospares); spin_unlock_irq(&mddev->write_lock); dprintk(KERN_INFO @@ -2425,6 +2429,8 @@ array_state_show(mddev_t *mddev, char *page) case 0: if (mddev->in_sync) st = clean; + else if (test_bit(MD_CHANGE_CLEAN, &mddev->flags)) + st = write_pending; else if (mddev->safemode) st = active_idle; else @@ -2455,11 +2461,9 @@ array_state_store(mddev_t *mddev, const char *buf, size_t len) break; case clear: /* stopping an active array */ - if (mddev->pers) { - if (atomic_read(&mddev->active) > 1) - return -EBUSY; - err = do_md_stop(mddev, 0); - } + if (atomic_read(&mddev->active) > 1) + return -EBUSY; + err = do_md_stop(mddev, 0); break; case inactive: /* stopping an active array */ @@ -2467,7 +2471,8 @@ array_state_store(mddev_t *mddev, const char *buf, size_t len) if (atomic_read(&mddev->active) > 1) return -EBUSY; err = do_md_stop(mddev, 2); - } + } else + err = 0; /* already inactive */ break; case suspended: break; /* not supported yet */ @@ -2495,9 +2500,15 @@ array_state_store(mddev_t *mddev, const char *buf, size_t len) restart_array(mddev); spin_lock_irq(&mddev->write_lock); if (atomic_read(&mddev->writes_pending) == 0) { - mddev->in_sync = 1; - set_bit(MD_CHANGE_CLEAN, &mddev->flags); - } + if (mddev->in_sync == 0) { + mddev->in_sync = 1; + if (mddev->persistent) + set_bit(MD_CHANGE_CLEAN, + &mddev->flags); + } + err = 0; + } else + err = -EBUSY; spin_unlock_irq(&mddev->write_lock); } else { mddev->ro = 0; @@ -2508,7 +2519,8 @@ array_state_store(mddev_t *mddev, const char *buf, size_t len) case active: if (mddev->pers) { restart_array(mddev); - clear_bit(MD_CHANGE_CLEAN, &mddev->flags); + if (mddev->external) + clear_bit(MD_CHANGE_CLEAN, &mddev->flags); wake_up(&mddev->sb_wait); err = 0; } else { @@ -2659,7 +2671,9 @@ __ATTR(component_size, S_IRUGO|S_IWUSR, size_show, size_store); /* Metdata version. - * This is either 'none' for arrays with externally managed metadata, + * This is one of + * 'none' for arrays with no metadata (good luck...) + * 'external' for arrays with externally managed metadata, * or N.M for internally known formats */ static ssize_t @@ -2668,6 +2682,8 @@ metadata_show(mddev_t *mddev, char *page) if (mddev->persistent) return sprintf(page, "%d.%d\n", mddev->major_version, mddev->minor_version); + else if (mddev->external) + return sprintf(page, "external:%s\n", mddev->metadata_type); else return sprintf(page, "none\n"); } @@ -2682,6 +2698,21 @@ metadata_store(mddev_t *mddev, const char *buf, size_t len) if (cmd_match(buf, "none")) { mddev->persistent = 0; + mddev->external = 0; + mddev->major_version = 0; + mddev->minor_version = 90; + return len; + } + if (strncmp(buf, "external:", 9) == 0) { + int namelen = len-9; + if (namelen >= sizeof(mddev->metadata_type)) + namelen = sizeof(mddev->metadata_type)-1; + strncpy(mddev->metadata_type, buf+9, namelen); + mddev->metadata_type[namelen] = 0; + if (namelen && mddev->metadata_type[namelen-1] == '\n') + mddev->metadata_type[--namelen] = 0; + mddev->persistent = 0; + mddev->external = 1; mddev->major_version = 0; mddev->minor_version = 90; return len; @@ -2698,6 +2729,7 @@ metadata_store(mddev_t *mddev, const char *buf, size_t len) mddev->major_version = major; mddev->minor_version = minor; mddev->persistent = 1; + mddev->external = 0; return len; } @@ -3524,6 +3556,7 @@ static int do_md_stop(mddev_t * mddev, int mode) mddev->raid_disks = 0; mddev->recovery_cp = 0; mddev->reshape_position = MaxSector; + mddev->external = 0; } else if (mddev->pers) printk(KERN_INFO "md: %s switched to read-only mode.\n", @@ -4165,13 +4198,15 @@ static int set_array_info(mddev_t * mddev, mdu_array_info_t *info) else mddev->recovery_cp = 0; mddev->persistent = ! info->not_persistent; + mddev->external = 0; mddev->layout = info->layout; mddev->chunk_size = info->chunk_size; mddev->max_disks = MD_SB_DISKS; - mddev->flags = 0; + if (mddev->persistent) + mddev->flags = 0; set_bit(MD_CHANGE_DEVS, &mddev->flags); mddev->default_bitmap_offset = MD_SB_BYTES >> 9; @@ -4982,7 +5017,10 @@ static int md_seq_show(struct seq_file *seq, void *v) mddev->major_version, mddev->minor_version); } - } else + } else if (mddev->external) + seq_printf(seq, " super external:%s", + mddev->metadata_type); + else seq_printf(seq, " super non-persistent"); if (mddev->pers) { @@ -5589,7 +5627,7 @@ void md_check_recovery(mddev_t *mddev) } if ( ! ( - mddev->flags || + (mddev->flags && !mddev->external) || test_bit(MD_RECOVERY_NEEDED, &mddev->recovery) || test_bit(MD_RECOVERY_DONE, &mddev->recovery) || (mddev->safemode == 1) || @@ -5605,7 +5643,8 @@ void md_check_recovery(mddev_t *mddev) if (mddev->safemode && !atomic_read(&mddev->writes_pending) && !mddev->in_sync && mddev->recovery_cp == MaxSector) { mddev->in_sync = 1; - set_bit(MD_CHANGE_CLEAN, &mddev->flags); + if (mddev->persistent) + set_bit(MD_CHANGE_CLEAN, &mddev->flags); } if (mddev->safemode == 1) mddev->safemode = 0; diff --git a/include/linux/raid/md_k.h b/include/linux/raid/md_k.h index dcb729244f47..b579cc628303 100644 --- a/include/linux/raid/md_k.h +++ b/include/linux/raid/md_k.h @@ -130,6 +130,9 @@ struct mddev_s minor_version, patch_version; int persistent; + int external; /* metadata is + * managed externally */ + char metadata_type[17]; /* externally set*/ int chunk_size; time_t ctime, utime; int level, layout; -- cgit From c620727779f7cc8ea96efb71f0651a26349e59c1 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Wed, 6 Feb 2008 01:39:52 -0800 Subject: md: allow a maximum extent to be set for resyncing This allows userspace to control resync/reshape progress and synchronise it with other activities, such as shared access in a SAN, or backing up critical sections during a tricky reshape. Writing a number of sectors (which must be a multiple of the chunk size if such is meaningful) causes a resync to pause when it gets to that point. Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/md.txt | 10 +++++++ drivers/md/md.c | 75 ++++++++++++++++++++++++++++++++++++++++------- drivers/md/raid1.c | 2 ++ drivers/md/raid10.c | 3 ++ drivers/md/raid5.c | 25 ++++++++++++++++ include/linux/raid/md_k.h | 2 ++ 6 files changed, 107 insertions(+), 10 deletions(-) (limited to 'include/linux/raid') diff --git a/Documentation/md.txt b/Documentation/md.txt index 5818628207b5..396cdd982c26 100644 --- a/Documentation/md.txt +++ b/Documentation/md.txt @@ -416,6 +416,16 @@ also have sectors in total that could need to be processed. The two numbers are separated by a '/' thus effectively showing one value, a fraction of the process that is complete. + A 'select' on this attribute will return when resync completes, + when it reaches the current sync_max (below) and possibly at + other times. + + sync_max + This is a number of sectors at which point a resync/recovery + process will pause. When a resync is active, the value can + only ever be increased, never decreased. The value of 'max' + effectively disables the limit. + sync_speed This shows the current actual speed, in K/sec, of the current diff --git a/drivers/md/md.c b/drivers/md/md.c index 00788c56276f..79eb63fdb4b3 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -275,6 +275,7 @@ static mddev_t * mddev_find(dev_t unit) spin_lock_init(&new->write_lock); init_waitqueue_head(&new->sb_wait); new->reshape_position = MaxSector; + new->resync_max = MaxSector; new->queue = blk_alloc_queue(GFP_KERNEL); if (!new->queue) { @@ -2920,6 +2921,43 @@ sync_completed_show(mddev_t *mddev, char *page) static struct md_sysfs_entry md_sync_completed = __ATTR_RO(sync_completed); +static ssize_t +max_sync_show(mddev_t *mddev, char *page) +{ + if (mddev->resync_max == MaxSector) + return sprintf(page, "max\n"); + else + return sprintf(page, "%llu\n", + (unsigned long long)mddev->resync_max); +} +static ssize_t +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')) + return -EINVAL; + if (max < mddev->resync_max && + test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) + return -EBUSY; + + /* Must be a multiple of chunk_size */ + if (mddev->chunk_size) { + if (max & (sector_t)((mddev->chunk_size>>9)-1)) + return -EINVAL; + } + mddev->resync_max = max; + } + wake_up(&mddev->recovery_wait); + return len; +} + +static struct md_sysfs_entry md_max_sync = +__ATTR(sync_max, S_IRUGO|S_IWUSR, max_sync_show, max_sync_store); + static ssize_t suspend_lo_show(mddev_t *mddev, char *page) { @@ -3030,6 +3068,7 @@ static struct attribute *md_redundancy_attrs[] = { &md_sync_max.attr, &md_sync_speed.attr, &md_sync_completed.attr, + &md_max_sync.attr, &md_suspend_lo.attr, &md_suspend_hi.attr, &md_bitmap.attr, @@ -3579,6 +3618,7 @@ static int do_md_stop(mddev_t * mddev, int mode) mddev->size = 0; mddev->raid_disks = 0; mddev->recovery_cp = 0; + mddev->resync_max = MaxSector; mddev->reshape_position = MaxSector; mddev->external = 0; @@ -5443,8 +5483,16 @@ void md_do_sync(mddev_t *mddev) sector_t sectors; skipped = 0; + if (j >= mddev->resync_max) { + sysfs_notify(&mddev->kobj, NULL, "sync_completed"); + wait_event(mddev->recovery_wait, + mddev->resync_max > j + || kthread_should_stop()); + } + if (kthread_should_stop()) + goto interrupted; sectors = mddev->pers->sync_request(mddev, j, &skipped, - currspeed < speed_min(mddev)); + currspeed < speed_min(mddev)); if (sectors == 0) { set_bit(MD_RECOVERY_ERR, &mddev->recovery); goto out; @@ -5486,15 +5534,9 @@ void md_do_sync(mddev_t *mddev) } - if (kthread_should_stop()) { - /* - * got a signal, exit. - */ - printk(KERN_INFO - "md: md_do_sync() got signal ... exiting\n"); - set_bit(MD_RECOVERY_INTR, &mddev->recovery); - goto out; - } + if (kthread_should_stop()) + goto interrupted; + /* * this loop exits only if either when we are slower than @@ -5558,9 +5600,22 @@ void md_do_sync(mddev_t *mddev) skip: mddev->curr_resync = 0; + mddev->resync_max = MaxSector; + sysfs_notify(&mddev->kobj, NULL, "sync_completed"); wake_up(&resync_wait); set_bit(MD_RECOVERY_DONE, &mddev->recovery); md_wakeup_thread(mddev->thread); + return; + + interrupted: + /* + * got a signal, exit. + */ + printk(KERN_INFO + "md: md_do_sync() got signal ... exiting\n"); + set_bit(MD_RECOVERY_INTR, &mddev->recovery); + goto out; + } EXPORT_SYMBOL_GPL(md_do_sync); diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index e0b8d0dd7a87..ae7c15207df5 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -1767,6 +1767,8 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i return rv; } + if (max_sector > mddev->resync_max) + max_sector = mddev->resync_max; /* Don't do IO beyond here */ nr_sectors = 0; sync_blocks = 0; do { diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index ba125277c6c4..d6f12882424d 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -1657,6 +1657,9 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i return (max_sector - sector_nr) + sectors_skipped; } + if (max_sector > mddev->resync_max) + max_sector = mddev->resync_max; /* Don't do IO beyond here */ + /* make sure whole request will fit in a chunk - if chunks * are meaningful */ diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 388a974d63ef..e946de6f46bc 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -3698,6 +3698,25 @@ static sector_t reshape_request(mddev_t *mddev, sector_t sector_nr, int *skipped release_stripe(sh); first_sector += STRIPE_SECTORS; } + /* If this takes us to the resync_max point where we have to pause, + * then we need to write out the superblock. + */ + sector_nr += conf->chunk_size>>9; + if (sector_nr >= mddev->resync_max) { + /* Cannot proceed until we've updated the superblock... */ + wait_event(conf->wait_for_overlap, + atomic_read(&conf->reshape_stripes) == 0); + mddev->reshape_position = conf->expand_progress; + set_bit(MD_CHANGE_DEVS, &mddev->flags); + md_wakeup_thread(mddev->thread); + wait_event(mddev->sb_wait, + !test_bit(MD_CHANGE_DEVS, &mddev->flags) + || kthread_should_stop()); + spin_lock_irq(&conf->device_lock); + conf->expand_lo = mddev->reshape_position; + spin_unlock_irq(&conf->device_lock); + wake_up(&conf->wait_for_overlap); + } return conf->chunk_size>>9; } @@ -3734,6 +3753,12 @@ static inline sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *ski if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery)) return reshape_request(mddev, sector_nr, skipped); + /* No need to check resync_max as we never do more than one + * stripe, and as resync_max will always be on a chunk boundary, + * if the check in md_do_sync didn't fire, there is no chance + * of overstepping resync_max here + */ + /* if there is too many failed drives and we are trying * to resync, then assert that we are finished, because there is * nothing we can do. diff --git a/include/linux/raid/md_k.h b/include/linux/raid/md_k.h index b579cc628303..c77dca3221ed 100644 --- a/include/linux/raid/md_k.h +++ b/include/linux/raid/md_k.h @@ -219,6 +219,8 @@ struct mddev_s atomic_t recovery_active; /* blocks scheduled, but not written */ wait_queue_head_t recovery_wait; sector_t recovery_cp; + sector_t resync_max; /* resync should pause + * when it gets here */ spinlock_t write_lock; wait_queue_head_t sb_wait; /* for waiting on superblock updates */ -- cgit From c5d79adba7ced41d7ac097c2ab74759d10522dd5 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Wed, 6 Feb 2008 01:39:54 -0800 Subject: md: allow devices to be shared between md arrays Currently, a given device is "claimed" by a particular array so that it cannot be used by other arrays. This is not ideal for DDF and other metadata schemes which have their own partitioning concept. So for externally managed metadata, just claim the device for md in general, require that "offset" and "size" are set properly for each device, and make sure that if a device is included in different arrays then the active sections do not overlap. This involves adding another flag to the rdev which makes it awkward to set "->flags = 0" to clear certain flags. So now clear flags explicitly by name when we want to clear things. Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/md/md.c | 88 +++++++++++++++++++++++++++++++++++++++++------ include/linux/raid/md_k.h | 2 ++ 2 files changed, 80 insertions(+), 10 deletions(-) (limited to 'include/linux/raid') diff --git a/drivers/md/md.c b/drivers/md/md.c index 78fe3e97ff99..7c9a87b02e77 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -774,7 +774,11 @@ static int super_90_validate(mddev_t *mddev, mdk_rdev_t *rdev) __u64 ev1 = md_event(sb); rdev->raid_disk = -1; - rdev->flags = 0; + clear_bit(Faulty, &rdev->flags); + clear_bit(In_sync, &rdev->flags); + clear_bit(WriteMostly, &rdev->flags); + clear_bit(BarriersNotsupp, &rdev->flags); + if (mddev->raid_disks == 0) { mddev->major_version = 0; mddev->minor_version = sb->minor_version; @@ -1154,7 +1158,11 @@ static int super_1_validate(mddev_t *mddev, mdk_rdev_t *rdev) __u64 ev1 = le64_to_cpu(sb->events); rdev->raid_disk = -1; - rdev->flags = 0; + clear_bit(Faulty, &rdev->flags); + clear_bit(In_sync, &rdev->flags); + clear_bit(WriteMostly, &rdev->flags); + clear_bit(BarriersNotsupp, &rdev->flags); + if (mddev->raid_disks == 0) { mddev->major_version = 1; mddev->patch_version = 0; @@ -1402,7 +1410,7 @@ static int bind_rdev_to_array(mdk_rdev_t * rdev, mddev_t * mddev) goto fail; } list_add(&rdev->same_set, &mddev->disks); - bd_claim_by_disk(rdev->bdev, rdev, mddev->gendisk); + bd_claim_by_disk(rdev->bdev, rdev->bdev->bd_holder, mddev->gendisk); return 0; fail: @@ -1442,7 +1450,7 @@ static void unbind_rdev_from_array(mdk_rdev_t * rdev) * otherwise reused by a RAID array (or any other kernel * subsystem), by bd_claiming the device. */ -static int lock_rdev(mdk_rdev_t *rdev, dev_t dev) +static int lock_rdev(mdk_rdev_t *rdev, dev_t dev, int shared) { int err = 0; struct block_device *bdev; @@ -1454,13 +1462,15 @@ static int lock_rdev(mdk_rdev_t *rdev, dev_t dev) __bdevname(dev, b)); return PTR_ERR(bdev); } - err = bd_claim(bdev, rdev); + err = bd_claim(bdev, shared ? (mdk_rdev_t *)lock_rdev : rdev); if (err) { printk(KERN_ERR "md: could not bd_claim %s.\n", bdevname(bdev, b)); blkdev_put(bdev); return err; } + if (!shared) + set_bit(AllReserved, &rdev->flags); rdev->bdev = bdev; return err; } @@ -1925,7 +1935,8 @@ slot_store(mdk_rdev_t *rdev, const char *buf, size_t len) return -ENOSPC; rdev->raid_disk = slot; /* assume it is working */ - rdev->flags = 0; + clear_bit(Faulty, &rdev->flags); + clear_bit(WriteMostly, &rdev->flags); set_bit(In_sync, &rdev->flags); } return len; @@ -1950,6 +1961,10 @@ offset_store(mdk_rdev_t *rdev, const char *buf, size_t len) return -EINVAL; if (rdev->mddev->pers) return -EBUSY; + if (rdev->size && rdev->mddev->external) + /* Must set offset before size, so overlap checks + * can be sane */ + return -EBUSY; rdev->data_offset = offset; return len; } @@ -1963,16 +1978,69 @@ rdev_size_show(mdk_rdev_t *rdev, char *page) return sprintf(page, "%llu\n", (unsigned long long)rdev->size); } +static int overlaps(sector_t s1, sector_t l1, sector_t s2, sector_t l2) +{ + /* check if two start/length pairs overlap */ + if (s1+l1 <= s2) + return 0; + if (s2+l2 <= s1) + return 0; + return 1; +} + static ssize_t rdev_size_store(mdk_rdev_t *rdev, const char *buf, size_t len) { char *e; unsigned long long size = simple_strtoull(buf, &e, 10); + unsigned long long oldsize = rdev->size; if (e==buf || (*e && *e != '\n')) return -EINVAL; if (rdev->mddev->pers) return -EBUSY; rdev->size = size; + if (size > oldsize && rdev->mddev->external) { + /* need to check that all other rdevs with the same ->bdev + * do not overlap. We need to unlock the mddev to avoid + * a deadlock. We have already changed rdev->size, and if + * we have to change it back, we will have the lock again. + */ + mddev_t *mddev; + int overlap = 0; + struct list_head *tmp, *tmp2; + + mddev_unlock(rdev->mddev); + ITERATE_MDDEV(mddev, tmp) { + mdk_rdev_t *rdev2; + + mddev_lock(mddev); + ITERATE_RDEV(mddev, rdev2, tmp2) + if (test_bit(AllReserved, &rdev2->flags) || + (rdev->bdev == rdev2->bdev && + rdev != rdev2 && + overlaps(rdev->data_offset, rdev->size, + rdev2->data_offset, rdev2->size))) { + overlap = 1; + break; + } + mddev_unlock(mddev); + if (overlap) { + mddev_put(mddev); + break; + } + } + mddev_lock(rdev->mddev); + if (overlap) { + /* Someone else could have slipped in a size + * change here, but doing so is just silly. + * We put oldsize back because we *know* it is + * safe, and trust userspace not to race with + * itself + */ + rdev->size = oldsize; + return -EBUSY; + } + } if (size < rdev->mddev->size || rdev->mddev->size == 0) rdev->mddev->size = size; return len; @@ -2056,7 +2124,7 @@ static mdk_rdev_t *md_import_device(dev_t newdev, int super_format, int super_mi if ((err = alloc_disk_sb(rdev))) goto abort_free; - err = lock_rdev(rdev, newdev); + err = lock_rdev(rdev, newdev, super_format == -2); if (err) goto abort_free; @@ -2609,7 +2677,9 @@ new_dev_store(mddev_t *mddev, const char *buf, size_t len) if (err < 0) goto out; } - } else + } else if (mddev->external) + rdev = md_import_device(dev, -2, -1); + else rdev = md_import_device(dev, -1, -1); if (IS_ERR(rdev)) @@ -4019,8 +4089,6 @@ static int add_new_disk(mddev_t * mddev, mdu_disk_info_t *info) else rdev->raid_disk = -1; - rdev->flags = 0; - if (rdev->raid_disk < mddev->raid_disks) if (info->state & (1<flags); diff --git a/include/linux/raid/md_k.h b/include/linux/raid/md_k.h index c77dca3221ed..5b2102e40286 100644 --- a/include/linux/raid/md_k.h +++ b/include/linux/raid/md_k.h @@ -81,6 +81,8 @@ struct mdk_rdev_s #define In_sync 2 /* device is in_sync with rest of array */ #define WriteMostly 4 /* Avoid reading if at all possible */ #define BarriersNotsupp 5 /* BIO_RW_BARRIER is not supported */ +#define AllReserved 6 /* If whole device is reserved for + * one array */ int desc_nr; /* descriptor index in the superblock */ int raid_disk; /* role of device in array */ -- cgit From d089c6af10c2be5988f03667d6d22fe6085fbe5e Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Wed, 6 Feb 2008 01:39:59 -0800 Subject: md: change ITERATE_RDEV to rdev_for_each As this is more in line with common practice in the kernel. Also swap the args around to be more like list_for_each. Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/md/bitmap.c | 4 +-- drivers/md/faulty.c | 2 +- drivers/md/linear.c | 2 +- drivers/md/md.c | 64 +++++++++++++++++++++++------------------------ drivers/md/multipath.c | 2 +- drivers/md/raid0.c | 8 +++--- drivers/md/raid1.c | 2 +- drivers/md/raid10.c | 2 +- drivers/md/raid5.c | 6 ++--- include/linux/raid/md_k.h | 2 +- 10 files changed, 47 insertions(+), 47 deletions(-) (limited to 'include/linux/raid') diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c index 9231cd700fe8..a0585fb6da94 100644 --- a/drivers/md/bitmap.c +++ b/drivers/md/bitmap.c @@ -237,7 +237,7 @@ static struct page *read_sb_page(mddev_t *mddev, long offset, unsigned long inde if (!page) return ERR_PTR(-ENOMEM); - ITERATE_RDEV(mddev, rdev, tmp) { + rdev_for_each(rdev, tmp, mddev) { if (! test_bit(In_sync, &rdev->flags) || test_bit(Faulty, &rdev->flags)) continue; @@ -261,7 +261,7 @@ static int write_sb_page(struct bitmap *bitmap, struct page *page, int wait) struct list_head *tmp; mddev_t *mddev = bitmap->mddev; - ITERATE_RDEV(mddev, rdev, tmp) + rdev_for_each(rdev, tmp, mddev) if (test_bit(In_sync, &rdev->flags) && !test_bit(Faulty, &rdev->flags)) { int size = PAGE_SIZE; diff --git a/drivers/md/faulty.c b/drivers/md/faulty.c index cf2ddce34118..d107ddceefcd 100644 --- a/drivers/md/faulty.c +++ b/drivers/md/faulty.c @@ -294,7 +294,7 @@ static int run(mddev_t *mddev) } conf->nfaults = 0; - ITERATE_RDEV(mddev, rdev, tmp) + rdev_for_each(rdev, tmp, mddev) conf->rdev = rdev; mddev->array_size = mddev->size; diff --git a/drivers/md/linear.c b/drivers/md/linear.c index 3dac1cfb8189..0b8511776b3e 100644 --- a/drivers/md/linear.c +++ b/drivers/md/linear.c @@ -122,7 +122,7 @@ static linear_conf_t *linear_conf(mddev_t *mddev, int raid_disks) cnt = 0; conf->array_size = 0; - ITERATE_RDEV(mddev,rdev,tmp) { + rdev_for_each(rdev, tmp, mddev) { int j = rdev->raid_disk; dev_info_t *disk = conf->disks + j; diff --git a/drivers/md/md.c b/drivers/md/md.c index c912ce2752a4..e02022864f08 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -311,7 +311,7 @@ static mdk_rdev_t * find_rdev_nr(mddev_t *mddev, int nr) mdk_rdev_t * rdev; struct list_head *tmp; - ITERATE_RDEV(mddev,rdev,tmp) { + rdev_for_each(rdev, tmp, mddev) { if (rdev->desc_nr == nr) return rdev; } @@ -323,7 +323,7 @@ static mdk_rdev_t * find_rdev(mddev_t * mddev, dev_t dev) struct list_head *tmp; mdk_rdev_t *rdev; - ITERATE_RDEV(mddev,rdev,tmp) { + rdev_for_each(rdev, tmp, mddev) { if (rdev->bdev->bd_dev == dev) return rdev; } @@ -943,7 +943,7 @@ static void super_90_sync(mddev_t *mddev, mdk_rdev_t *rdev) sb->state |= (1<disks[0].state = (1<raid_disk >= 0 && test_bit(In_sync, &rdev2->flags) @@ -1295,7 +1295,7 @@ static void super_1_sync(mddev_t *mddev, mdk_rdev_t *rdev) } max_dev = 0; - ITERATE_RDEV(mddev,rdev2,tmp) + rdev_for_each(rdev2, tmp, mddev) if (rdev2->desc_nr+1 > max_dev) max_dev = rdev2->desc_nr+1; @@ -1304,7 +1304,7 @@ static void super_1_sync(mddev_t *mddev, mdk_rdev_t *rdev) for (i=0; idev_roles[i] = cpu_to_le16(0xfffe); - ITERATE_RDEV(mddev,rdev2,tmp) { + rdev_for_each(rdev2, tmp, mddev) { i = rdev2->desc_nr; if (test_bit(Faulty, &rdev2->flags)) sb->dev_roles[i] = cpu_to_le16(0xfffe); @@ -1342,8 +1342,8 @@ static int match_mddev_units(mddev_t *mddev1, mddev_t *mddev2) struct list_head *tmp, *tmp2; mdk_rdev_t *rdev, *rdev2; - ITERATE_RDEV(mddev1,rdev,tmp) - ITERATE_RDEV(mddev2, rdev2, tmp2) + rdev_for_each(rdev, tmp, mddev1) + rdev_for_each(rdev2, tmp2, mddev2) if (rdev->bdev->bd_contains == rdev2->bdev->bd_contains) return 1; @@ -1516,7 +1516,7 @@ static void export_array(mddev_t *mddev) struct list_head *tmp; mdk_rdev_t *rdev; - ITERATE_RDEV(mddev,rdev,tmp) { + rdev_for_each(rdev, tmp, mddev) { if (!rdev->mddev) { MD_BUG(); continue; @@ -1600,11 +1600,11 @@ static void md_print_devices(void) bitmap_print_sb(mddev->bitmap); else printk("%s: ", mdname(mddev)); - ITERATE_RDEV(mddev,rdev,tmp2) + rdev_for_each(rdev, tmp2, mddev) printk("<%s>", bdevname(rdev->bdev,b)); printk("\n"); - ITERATE_RDEV(mddev,rdev,tmp2) + rdev_for_each(rdev, tmp2, mddev) print_rdev(rdev); } printk("md: **********************************\n"); @@ -1623,7 +1623,7 @@ static void sync_sbs(mddev_t * mddev, int nospares) mdk_rdev_t *rdev; struct list_head *tmp; - ITERATE_RDEV(mddev,rdev,tmp) { + rdev_for_each(rdev, tmp, mddev) { if (rdev->sb_events == mddev->events || (nospares && rdev->raid_disk < 0 && @@ -1730,7 +1730,7 @@ repeat: mdname(mddev),mddev->in_sync); bitmap_update_sb(mddev->bitmap); - ITERATE_RDEV(mddev,rdev,tmp) { + rdev_for_each(rdev, tmp, mddev) { char b[BDEVNAME_SIZE]; dprintk(KERN_INFO "md: "); if (rdev->sb_loaded != 1) @@ -2016,7 +2016,7 @@ rdev_size_store(mdk_rdev_t *rdev, const char *buf, size_t len) mdk_rdev_t *rdev2; mddev_lock(mddev); - ITERATE_RDEV(mddev, rdev2, tmp2) + rdev_for_each(rdev2, tmp2, mddev) if (test_bit(AllReserved, &rdev2->flags) || (rdev->bdev == rdev2->bdev && rdev != rdev2 && @@ -2202,7 +2202,7 @@ static void analyze_sbs(mddev_t * mddev) char b[BDEVNAME_SIZE]; freshest = NULL; - ITERATE_RDEV(mddev,rdev,tmp) + rdev_for_each(rdev, tmp, mddev) switch (super_types[mddev->major_version]. load_super(rdev, freshest, mddev->minor_version)) { case 1: @@ -2223,7 +2223,7 @@ static void analyze_sbs(mddev_t * mddev) validate_super(mddev, freshest); i = 0; - ITERATE_RDEV(mddev,rdev,tmp) { + rdev_for_each(rdev, tmp, mddev) { if (rdev != freshest) if (super_types[mddev->major_version]. validate_super(mddev, rdev)) { @@ -3317,7 +3317,7 @@ static int do_md_run(mddev_t * mddev) } /* devices must have minimum size of one chunk */ - ITERATE_RDEV(mddev,rdev,tmp) { + rdev_for_each(rdev, tmp, mddev) { if (test_bit(Faulty, &rdev->flags)) continue; if (rdev->size < chunk_size / 1024) { @@ -3344,7 +3344,7 @@ static int do_md_run(mddev_t * mddev) * the only valid external interface is through the md * device. */ - ITERATE_RDEV(mddev,rdev,tmp) { + rdev_for_each(rdev, tmp, mddev) { if (test_bit(Faulty, &rdev->flags)) continue; sync_blockdev(rdev->bdev); @@ -3410,8 +3410,8 @@ static int do_md_run(mddev_t * mddev) mdk_rdev_t *rdev2; struct list_head *tmp2; int warned = 0; - ITERATE_RDEV(mddev, rdev, tmp) { - ITERATE_RDEV(mddev, rdev2, tmp2) { + rdev_for_each(rdev, tmp, mddev) { + rdev_for_each(rdev2, tmp2, mddev) { if (rdev < rdev2 && rdev->bdev->bd_contains == rdev2->bdev->bd_contains) { @@ -3471,7 +3471,7 @@ static int do_md_run(mddev_t * mddev) mddev->safemode_delay = (200 * HZ)/1000 +1; /* 200 msec delay */ mddev->in_sync = 1; - ITERATE_RDEV(mddev,rdev,tmp) + rdev_for_each(rdev, tmp, mddev) if (rdev->raid_disk >= 0) { char nm[20]; sprintf(nm, "rd%d", rdev->raid_disk); @@ -3504,7 +3504,7 @@ static int do_md_run(mddev_t * mddev) if (mddev->degraded && !mddev->sync_thread) { struct list_head *rtmp; int spares = 0; - ITERATE_RDEV(mddev,rdev,rtmp) + rdev_for_each(rdev, rtmp, mddev) if (rdev->raid_disk >= 0 && !test_bit(In_sync, &rdev->flags) && !test_bit(Faulty, &rdev->flags)) @@ -3681,7 +3681,7 @@ static int do_md_stop(mddev_t * mddev, int mode) } mddev->bitmap_offset = 0; - ITERATE_RDEV(mddev,rdev,tmp) + rdev_for_each(rdev, tmp, mddev) if (rdev->raid_disk >= 0) { char nm[20]; sprintf(nm, "rd%d", rdev->raid_disk); @@ -3723,7 +3723,7 @@ static void autorun_array(mddev_t *mddev) printk(KERN_INFO "md: running: "); - ITERATE_RDEV(mddev,rdev,tmp) { + rdev_for_each(rdev, tmp, mddev) { char b[BDEVNAME_SIZE]; printk("<%s>", bdevname(rdev->bdev,b)); } @@ -3851,7 +3851,7 @@ static int get_array_info(mddev_t * mddev, void __user * arg) struct list_head *tmp; nr=working=active=failed=spare=0; - ITERATE_RDEV(mddev,rdev,tmp) { + rdev_for_each(rdev, tmp, mddev) { nr++; if (test_bit(Faulty, &rdev->flags)) failed++; @@ -4391,7 +4391,7 @@ static int update_size(mddev_t *mddev, unsigned long size) */ if (mddev->sync_thread) return -EBUSY; - ITERATE_RDEV(mddev,rdev,tmp) { + rdev_for_each(rdev, tmp, mddev) { sector_t avail; avail = rdev->size * 2; @@ -5132,7 +5132,7 @@ static int md_seq_show(struct seq_file *seq, void *v) } size = 0; - ITERATE_RDEV(mddev,rdev,tmp2) { + rdev_for_each(rdev, tmp2, mddev) { char b[BDEVNAME_SIZE]; seq_printf(seq, " %s[%d]", bdevname(rdev->bdev,b), rdev->desc_nr); @@ -5288,7 +5288,7 @@ static int is_mddev_idle(mddev_t *mddev) long curr_events; idle = 1; - ITERATE_RDEV(mddev,rdev,tmp) { + rdev_for_each(rdev, tmp, mddev) { struct gendisk *disk = rdev->bdev->bd_contains->bd_disk; curr_events = disk_stat_read(disk, sectors[0]) + disk_stat_read(disk, sectors[1]) - @@ -5515,7 +5515,7 @@ void md_do_sync(mddev_t *mddev) /* recovery follows the physical size of devices */ max_sectors = mddev->size << 1; j = MaxSector; - ITERATE_RDEV(mddev,rdev,rtmp) + rdev_for_each(rdev, rtmp, mddev) if (rdev->raid_disk >= 0 && !test_bit(Faulty, &rdev->flags) && !test_bit(In_sync, &rdev->flags) && @@ -5668,7 +5668,7 @@ void md_do_sync(mddev_t *mddev) } else { if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery)) mddev->curr_resync = MaxSector; - ITERATE_RDEV(mddev,rdev,rtmp) + rdev_for_each(rdev, rtmp, mddev) if (rdev->raid_disk >= 0 && !test_bit(Faulty, &rdev->flags) && !test_bit(In_sync, &rdev->flags) && @@ -5706,7 +5706,7 @@ static int remove_and_add_spares(mddev_t *mddev) struct list_head *rtmp; int spares = 0; - ITERATE_RDEV(mddev,rdev,rtmp) + rdev_for_each(rdev, rtmp, mddev) if (rdev->raid_disk >= 0 && !mddev->external && (test_bit(Faulty, &rdev->flags) || @@ -5722,7 +5722,7 @@ static int remove_and_add_spares(mddev_t *mddev) } if (mddev->degraded) { - ITERATE_RDEV(mddev,rdev,rtmp) + rdev_for_each(rdev, rtmp, mddev) if (rdev->raid_disk < 0 && !test_bit(Faulty, &rdev->flags)) { rdev->recovery_offset = 0; @@ -5836,7 +5836,7 @@ void md_check_recovery(mddev_t *mddev) * information must be scrapped */ if (!mddev->degraded) - ITERATE_RDEV(mddev,rdev,rtmp) + rdev_for_each(rdev, rtmp, mddev) rdev->saved_raid_disk = -1; mddev->recovery = 0; diff --git a/drivers/md/multipath.c b/drivers/md/multipath.c index eb631ebed686..3f299d835a2b 100644 --- a/drivers/md/multipath.c +++ b/drivers/md/multipath.c @@ -436,7 +436,7 @@ static int multipath_run (mddev_t *mddev) } conf->working_disks = 0; - ITERATE_RDEV(mddev,rdev,tmp) { + rdev_for_each(rdev, tmp, mddev) { disk_idx = rdev->raid_disk; if (disk_idx < 0 || disk_idx >= mddev->raid_disks) diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index f8e591708d1f..818b48284096 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -72,11 +72,11 @@ static int create_strip_zones (mddev_t *mddev) */ conf->nr_strip_zones = 0; - ITERATE_RDEV(mddev,rdev1,tmp1) { + rdev_for_each(rdev1, tmp1, mddev) { printk("raid0: looking at %s\n", bdevname(rdev1->bdev,b)); c = 0; - ITERATE_RDEV(mddev,rdev2,tmp2) { + rdev_for_each(rdev2, tmp2, mddev) { printk("raid0: comparing %s(%llu)", bdevname(rdev1->bdev,b), (unsigned long long)rdev1->size); @@ -124,7 +124,7 @@ static int create_strip_zones (mddev_t *mddev) cnt = 0; smallest = NULL; zone->dev = conf->devlist; - ITERATE_RDEV(mddev, rdev1, tmp1) { + rdev_for_each(rdev1, tmp1, mddev) { int j = rdev1->raid_disk; if (j < 0 || j >= mddev->raid_disks) { @@ -293,7 +293,7 @@ static int raid0_run (mddev_t *mddev) /* calculate array device size */ mddev->array_size = 0; - ITERATE_RDEV(mddev,rdev,tmp) + rdev_for_each(rdev, tmp, mddev) mddev->array_size += rdev->size; printk("raid0 : md_size is %llu blocks.\n", diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index ae7c15207df5..5c7fef091cec 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -1887,7 +1887,7 @@ static int run(mddev_t *mddev) if (!conf->r1bio_pool) goto out_no_mem; - ITERATE_RDEV(mddev, rdev, tmp) { + rdev_for_each(rdev, tmp, mddev) { disk_idx = rdev->raid_disk; if (disk_idx >= mddev->raid_disks || disk_idx < 0) diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index d6f12882424d..017f58113c33 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -2026,7 +2026,7 @@ static int run(mddev_t *mddev) goto out_free_conf; } - ITERATE_RDEV(mddev, rdev, tmp) { + rdev_for_each(rdev, tmp, mddev) { disk_idx = rdev->raid_disk; if (disk_idx >= mddev->raid_disks || disk_idx < 0) diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index e946de6f46bc..63bfb0757829 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -4136,7 +4136,7 @@ static int run(mddev_t *mddev) pr_debug("raid5: run(%s) called.\n", mdname(mddev)); - ITERATE_RDEV(mddev,rdev,tmp) { + rdev_for_each(rdev, tmp, mddev) { raid_disk = rdev->raid_disk; if (raid_disk >= conf->raid_disks || raid_disk < 0) @@ -4549,7 +4549,7 @@ static int raid5_start_reshape(mddev_t *mddev) if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) return -EBUSY; - ITERATE_RDEV(mddev, rdev, rtmp) + rdev_for_each(rdev, rtmp, mddev) if (rdev->raid_disk < 0 && !test_bit(Faulty, &rdev->flags)) spares++; @@ -4571,7 +4571,7 @@ 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. */ - ITERATE_RDEV(mddev, rdev, rtmp) + rdev_for_each(rdev, rtmp, mddev) if (rdev->raid_disk < 0 && !test_bit(Faulty, &rdev->flags)) { if (raid5_add_disk(mddev, rdev)) { diff --git a/include/linux/raid/md_k.h b/include/linux/raid/md_k.h index 5b2102e40286..9c19555f314b 100644 --- a/include/linux/raid/md_k.h +++ b/include/linux/raid/md_k.h @@ -322,7 +322,7 @@ static inline char * mdname (mddev_t * mddev) /* * iterates through the 'same array disks' ringlist */ -#define ITERATE_RDEV(mddev,rdev,tmp) \ +#define rdev_for_each(rdev, tmp, mddev) \ ITERATE_RDEV_GENERIC((mddev)->disks,rdev,tmp) /* -- cgit From 73c34431c7119d0bc7d3436abfad75fe47b2c51f Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Wed, 6 Feb 2008 01:39:59 -0800 Subject: md: change ITERATE_RDEV_GENERIC to rdev_for_each_list, and remove ITERATE_RDEV_PENDING. Finish ITERATE_ to for_each conversion. Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/md/md.c | 8 ++++---- include/linux/raid/md_k.h | 14 ++++---------- 2 files changed, 8 insertions(+), 14 deletions(-) (limited to 'include/linux/raid') diff --git a/drivers/md/md.c b/drivers/md/md.c index e02022864f08..5fc326d3970e 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -3766,7 +3766,7 @@ static void autorun_devices(int part) printk(KERN_INFO "md: considering %s ...\n", bdevname(rdev0->bdev,b)); INIT_LIST_HEAD(&candidates); - ITERATE_RDEV_PENDING(rdev,tmp) + rdev_for_each_list(rdev, tmp, pending_raid_disks) if (super_90_load(rdev, rdev0, 0) >= 0) { printk(KERN_INFO "md: adding %s ...\n", bdevname(rdev->bdev,b)); @@ -3810,7 +3810,7 @@ static void autorun_devices(int part) } else { printk(KERN_INFO "md: created %s\n", mdname(mddev)); mddev->persistent = 1; - ITERATE_RDEV_GENERIC(candidates,rdev,tmp) { + rdev_for_each_list(rdev, tmp, candidates) { list_del_init(&rdev->same_set); if (bind_rdev_to_array(rdev, mddev)) export_rdev(rdev); @@ -3821,7 +3821,7 @@ static void autorun_devices(int part) /* on success, candidates will be empty, on error * it won't... */ - ITERATE_RDEV_GENERIC(candidates,rdev,tmp) + rdev_for_each_list(rdev, tmp, candidates) export_rdev(rdev); mddev_put(mddev); } @@ -4936,7 +4936,7 @@ static void status_unused(struct seq_file *seq) seq_printf(seq, "unused devices: "); - ITERATE_RDEV_PENDING(rdev,tmp) { + rdev_for_each_list(rdev, tmp, pending_raid_disks) { char b[BDEVNAME_SIZE]; i++; seq_printf(seq, "%s ", diff --git a/include/linux/raid/md_k.h b/include/linux/raid/md_k.h index 9c19555f314b..85a068bab625 100644 --- a/include/linux/raid/md_k.h +++ b/include/linux/raid/md_k.h @@ -313,23 +313,17 @@ static inline char * mdname (mddev_t * mddev) * iterates through some rdev ringlist. It's safe to remove the * current 'rdev'. Dont touch 'tmp' though. */ -#define ITERATE_RDEV_GENERIC(head,rdev,tmp) \ +#define rdev_for_each_list(rdev, tmp, list) \ \ - for ((tmp) = (head).next; \ + for ((tmp) = (list).next; \ (rdev) = (list_entry((tmp), mdk_rdev_t, same_set)), \ - (tmp) = (tmp)->next, (tmp)->prev != &(head) \ + (tmp) = (tmp)->next, (tmp)->prev != &(list) \ ; ) /* * iterates through the 'same array disks' ringlist */ #define rdev_for_each(rdev, tmp, mddev) \ - ITERATE_RDEV_GENERIC((mddev)->disks,rdev,tmp) - -/* - * Iterates through 'pending RAID disks' - */ -#define ITERATE_RDEV_PENDING(rdev,tmp) \ - ITERATE_RDEV_GENERIC(pending_raid_disks,rdev,tmp) + rdev_for_each_list(rdev, tmp, (mddev)->disks) typedef struct mdk_thread_s { void (*run) (mddev_t *mddev); -- cgit