diff options
Diffstat (limited to 'drivers/md/md.c')
| -rw-r--r-- | drivers/md/md.c | 197 |
1 files changed, 117 insertions, 80 deletions
diff --git a/drivers/md/md.c b/drivers/md/md.c index b76cfc89e1b..6e853c61d87 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -287,6 +287,7 @@ static int md_make_request(struct request_queue *q, struct bio *bio) mddev_t *mddev = q->queuedata; int rv; int cpu; + unsigned int sectors; if (mddev == NULL || mddev->pers == NULL || !mddev->ready) { @@ -311,12 +312,16 @@ static int md_make_request(struct request_queue *q, struct bio *bio) atomic_inc(&mddev->active_io); rcu_read_unlock(); + /* + * save the sectors now since our bio can + * go away inside make_request + */ + sectors = bio_sectors(bio); rv = mddev->pers->make_request(mddev, bio); cpu = part_stat_lock(); part_stat_inc(cpu, &mddev->gendisk->part0, ios[rw]); - part_stat_add(cpu, &mddev->gendisk->part0, sectors[rw], - bio_sectors(bio)); + part_stat_add(cpu, &mddev->gendisk->part0, sectors[rw], sectors); part_stat_unlock(); if (atomic_dec_and_test(&mddev->active_io) && mddev->suspended) @@ -442,48 +447,59 @@ EXPORT_SYMBOL(md_flush_request); /* Support for plugging. * This mirrors the plugging support in request_queue, but does not - * require having a whole queue + * require having a whole queue or request structures. + * We allocate an md_plug_cb for each md device and each thread it gets + * plugged on. This links tot the private plug_handle structure in the + * personality data where we keep a count of the number of outstanding + * plugs so other code can see if a plug is active. */ -static void plugger_work(struct work_struct *work) -{ - struct plug_handle *plug = - container_of(work, struct plug_handle, unplug_work); - plug->unplug_fn(plug); -} -static void plugger_timeout(unsigned long data) -{ - struct plug_handle *plug = (void *)data; - kblockd_schedule_work(NULL, &plug->unplug_work); -} -void plugger_init(struct plug_handle *plug, - void (*unplug_fn)(struct plug_handle *)) -{ - plug->unplug_flag = 0; - plug->unplug_fn = unplug_fn; - init_timer(&plug->unplug_timer); - plug->unplug_timer.function = plugger_timeout; - plug->unplug_timer.data = (unsigned long)plug; - INIT_WORK(&plug->unplug_work, plugger_work); -} -EXPORT_SYMBOL_GPL(plugger_init); +struct md_plug_cb { + struct blk_plug_cb cb; + mddev_t *mddev; +}; -void plugger_set_plug(struct plug_handle *plug) +static void plugger_unplug(struct blk_plug_cb *cb) { - if (!test_and_set_bit(PLUGGED_FLAG, &plug->unplug_flag)) - mod_timer(&plug->unplug_timer, jiffies + msecs_to_jiffies(3)+1); + struct md_plug_cb *mdcb = container_of(cb, struct md_plug_cb, cb); + if (atomic_dec_and_test(&mdcb->mddev->plug_cnt)) + md_wakeup_thread(mdcb->mddev->thread); + kfree(mdcb); } -EXPORT_SYMBOL_GPL(plugger_set_plug); -int plugger_remove_plug(struct plug_handle *plug) +/* Check that an unplug wakeup will come shortly. + * If not, wakeup the md thread immediately + */ +int mddev_check_plugged(mddev_t *mddev) { - if (test_and_clear_bit(PLUGGED_FLAG, &plug->unplug_flag)) { - del_timer(&plug->unplug_timer); - return 1; - } else + struct blk_plug *plug = current->plug; + struct md_plug_cb *mdcb; + + if (!plug) return 0; -} -EXPORT_SYMBOL_GPL(plugger_remove_plug); + list_for_each_entry(mdcb, &plug->cb_list, cb.list) { + if (mdcb->cb.callback == plugger_unplug && + mdcb->mddev == mddev) { + /* Already on the list, move to top */ + if (mdcb != list_first_entry(&plug->cb_list, + struct md_plug_cb, + cb.list)) + list_move(&mdcb->cb.list, &plug->cb_list); + return 1; + } + } + /* Not currently on the callback list */ + mdcb = kmalloc(sizeof(*mdcb), GFP_ATOMIC); + if (!mdcb) + return 0; + + mdcb->mddev = mddev; + mdcb->cb.callback = plugger_unplug; + atomic_inc(&mddev->plug_cnt); + list_add(&mdcb->cb.list, &plug->cb_list); + return 1; +} +EXPORT_SYMBOL_GPL(mddev_check_plugged); static inline mddev_t *mddev_get(mddev_t *mddev) { @@ -533,6 +549,7 @@ void mddev_init(mddev_t *mddev) atomic_set(&mddev->active, 1); atomic_set(&mddev->openers, 0); atomic_set(&mddev->active_io, 0); + atomic_set(&mddev->plug_cnt, 0); spin_lock_init(&mddev->write_lock); atomic_set(&mddev->flush_pending, 0); init_waitqueue_head(&mddev->sb_wait); @@ -548,6 +565,9 @@ static mddev_t * mddev_find(dev_t unit) { mddev_t *mddev, *new = NULL; + if (unit && MAJOR(unit) != MD_MAJOR) + unit &= ~((1<<MdpMinorShift)-1); + retry: spin_lock(&all_mddevs_lock); @@ -772,8 +792,7 @@ void md_super_write(mddev_t *mddev, mdk_rdev_t *rdev, bio->bi_end_io = super_written; atomic_inc(&mddev->pending_writes); - submit_bio(REQ_WRITE | REQ_SYNC | REQ_UNPLUG | REQ_FLUSH | REQ_FUA, - bio); + submit_bio(REQ_WRITE | REQ_SYNC | REQ_FLUSH | REQ_FUA, bio); } void md_super_wait(mddev_t *mddev) @@ -801,7 +820,7 @@ int sync_page_io(mdk_rdev_t *rdev, sector_t sector, int size, struct completion event; int ret; - rw |= REQ_SYNC | REQ_UNPLUG; + rw |= REQ_SYNC; bio->bi_bdev = (metadata_op && rdev->meta_bdev) ? rdev->meta_bdev : rdev->bdev; @@ -1770,12 +1789,6 @@ int md_integrity_register(mddev_t *mddev) continue; if (rdev->raid_disk < 0) continue; - /* - * If at least one rdev is not integrity capable, we can not - * enable data integrity for the md device. - */ - if (!bdev_get_integrity(rdev->bdev)) - return -EINVAL; if (!reference) { /* Use the first rdev as the reference */ reference = rdev; @@ -1786,6 +1799,8 @@ int md_integrity_register(mddev_t *mddev) rdev->bdev->bd_disk) < 0) return -EINVAL; } + if (!reference || !bdev_get_integrity(reference->bdev)) + return 0; /* * All component devices are integrity capable and have matching * profiles, register the common profile for the md device. @@ -1796,8 +1811,12 @@ int md_integrity_register(mddev_t *mddev) mdname(mddev)); return -EINVAL; } - printk(KERN_NOTICE "md: data integrity on %s enabled\n", - mdname(mddev)); + printk(KERN_NOTICE "md: data integrity enabled on %s\n", mdname(mddev)); + if (bioset_integrity_create(mddev->bio_set, BIO_POOL_SIZE)) { + printk(KERN_ERR "md: failed to create integrity pool for %s\n", + mdname(mddev)); + return -EINVAL; + } return 0; } EXPORT_SYMBOL(md_integrity_register); @@ -1947,8 +1966,6 @@ static int lock_rdev(mdk_rdev_t *rdev, dev_t dev, int shared) __bdevname(dev, b)); return PTR_ERR(bdev); } - if (!shared) - set_bit(AllReserved, &rdev->flags); rdev->bdev = bdev; return err; } @@ -2465,6 +2482,9 @@ slot_store(mdk_rdev_t *rdev, const char *buf, size_t len) if (rdev->raid_disk != -1) return -EBUSY; + if (test_bit(MD_RECOVERY_RUNNING, &rdev->mddev->recovery)) + return -EBUSY; + if (rdev->mddev->pers->hot_add_disk == NULL) return -EINVAL; @@ -2610,12 +2630,11 @@ rdev_size_store(mdk_rdev_t *rdev, const char *buf, size_t len) mddev_lock(mddev); list_for_each_entry(rdev2, &mddev->disks, same_set) - if (test_bit(AllReserved, &rdev2->flags) || - (rdev->bdev == rdev2->bdev && - rdev != rdev2 && - overlaps(rdev->data_offset, rdev->sectors, - rdev2->data_offset, - rdev2->sectors))) { + if (rdev->bdev == rdev2->bdev && + rdev != rdev2 && + overlaps(rdev->data_offset, rdev->sectors, + rdev2->data_offset, + rdev2->sectors)) { overlap = 1; break; } @@ -4133,10 +4152,10 @@ array_size_store(mddev_t *mddev, const char *buf, size_t len) } mddev->array_sectors = sectors; - set_capacity(mddev->gendisk, mddev->array_sectors); - if (mddev->pers) + if (mddev->pers) { + set_capacity(mddev->gendisk, mddev->array_sectors); revalidate_disk(mddev->gendisk); - + } return len; } @@ -4619,6 +4638,7 @@ static int do_md_run(mddev_t *mddev) } set_capacity(mddev->gendisk, mddev->array_sectors); revalidate_disk(mddev->gendisk); + mddev->changed = 1; kobject_uevent(&disk_to_dev(mddev->gendisk)->kobj, KOBJ_CHANGE); out: return err; @@ -4707,6 +4727,7 @@ static void md_clean(mddev_t *mddev) mddev->sync_speed_min = mddev->sync_speed_max = 0; mddev->recovery = 0; mddev->in_sync = 0; + mddev->changed = 0; mddev->degraded = 0; mddev->safemode = 0; mddev->bitmap_info.offset = 0; @@ -4714,7 +4735,6 @@ static void md_clean(mddev_t *mddev) mddev->bitmap_info.chunksize = 0; mddev->bitmap_info.daemon_sleep = 0; mddev->bitmap_info.max_write_behind = 0; - mddev->plug = NULL; } static void __md_stop_writes(mddev_t *mddev) @@ -4807,7 +4827,6 @@ static int do_md_stop(mddev_t * mddev, int mode, int is_open) __md_stop_writes(mddev); md_stop(mddev); mddev->queue->merge_bvec_fn = NULL; - mddev->queue->unplug_fn = NULL; mddev->queue->backing_dev_info.congested_fn = NULL; /* tell userspace to handle 'inactive' */ @@ -4822,6 +4841,7 @@ static int do_md_stop(mddev_t * mddev, int mode, int is_open) set_capacity(disk, 0); mutex_unlock(&mddev->open_mutex); + mddev->changed = 1; revalidate_disk(disk); if (mddev->ro) @@ -5578,6 +5598,8 @@ static int update_raid_disks(mddev_t *mddev, int raid_disks) mddev->delta_disks = raid_disks - mddev->raid_disks; rv = mddev->pers->check_reshape(mddev); + if (rv < 0) + mddev->delta_disks = 0; return rv; } @@ -6004,7 +6026,7 @@ static int md_open(struct block_device *bdev, fmode_t mode) atomic_inc(&mddev->openers); mutex_unlock(&mddev->open_mutex); - check_disk_size_change(mddev->gendisk, bdev); + check_disk_change(bdev); out: return err; } @@ -6019,6 +6041,21 @@ static int md_release(struct gendisk *disk, fmode_t mode) return 0; } + +static int md_media_changed(struct gendisk *disk) +{ + mddev_t *mddev = disk->private_data; + + return mddev->changed; +} + +static int md_revalidate(struct gendisk *disk) +{ + mddev_t *mddev = disk->private_data; + + mddev->changed = 0; + return 0; +} static const struct block_device_operations md_fops = { .owner = THIS_MODULE, @@ -6029,6 +6066,8 @@ static const struct block_device_operations md_fops = .compat_ioctl = md_compat_ioctl, #endif .getgeo = md_getgeo, + .media_changed = md_media_changed, + .revalidate_disk= md_revalidate, }; static int md_thread(void * arg) @@ -6238,7 +6277,7 @@ static void status_resync(struct seq_file *seq, mddev_t * mddev) * rt is a sector_t, so could be 32bit or 64bit. * So we divide before multiply in case it is 32bit and close * to the limit. - * We scale the divisor (db) by 32 to avoid loosing precision + * We scale the divisor (db) by 32 to avoid losing precision * near the end of resync when the number of remaining sectors * is close to 'db'. * We then divide rt by 32 after multiplying by db to compensate. @@ -6660,14 +6699,6 @@ int md_allow_write(mddev_t *mddev) } EXPORT_SYMBOL_GPL(md_allow_write); -void md_unplug(mddev_t *mddev) -{ - if (mddev->queue) - blk_unplug(mddev->queue); - if (mddev->plug) - mddev->plug->unplug_fn(mddev->plug); -} - #define SYNC_MARKS 10 #define SYNC_MARK_STEP (3*HZ) void md_do_sync(mddev_t *mddev) @@ -6846,7 +6877,6 @@ void md_do_sync(mddev_t *mddev) >= mddev->resync_max - mddev->curr_resync_completed )) { /* time to update curr_resync_completed */ - md_unplug(mddev); wait_event(mddev->recovery_wait, atomic_read(&mddev->recovery_active) == 0); mddev->curr_resync_completed = j; @@ -6922,7 +6952,6 @@ void md_do_sync(mddev_t *mddev) * about not overloading the IO subsystem. (things like an * e2fsck being done on the RAID array should execute fast) */ - md_unplug(mddev); cond_resched(); currspeed = ((unsigned long)(io_sectors-mddev->resync_mark_cnt))/2 @@ -6941,8 +6970,6 @@ void md_do_sync(mddev_t *mddev) * this also signals 'finished resyncing' to md_stop */ out: - md_unplug(mddev); - wait_event(mddev->recovery_wait, !atomic_read(&mddev->recovery_active)); /* tell personality that we are finished */ @@ -6985,9 +7012,6 @@ void md_do_sync(mddev_t *mddev) } else if (test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery)) mddev->resync_min = mddev->curr_resync_completed; mddev->curr_resync = 0; - if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery)) - mddev->curr_resync_completed = 0; - sysfs_notify(&mddev->kobj, NULL, "sync_completed"); wake_up(&resync_wait); set_bit(MD_RECOVERY_DONE, &mddev->recovery); md_wakeup_thread(mddev->thread); @@ -7028,7 +7052,7 @@ static int remove_and_add_spares(mddev_t *mddev) } } - if (mddev->degraded && ! mddev->ro && !mddev->recovery_disabled) { + if (mddev->degraded && !mddev->recovery_disabled) { list_for_each_entry(rdev, &mddev->disks, same_set) { if (rdev->raid_disk >= 0 && !test_bit(In_sync, &rdev->flags) && @@ -7151,7 +7175,20 @@ void md_check_recovery(mddev_t *mddev) /* Only thing we do on a ro array is remove * failed devices. */ - remove_and_add_spares(mddev); + mdk_rdev_t *rdev; + list_for_each_entry(rdev, &mddev->disks, same_set) + if (rdev->raid_disk >= 0 && + !test_bit(Blocked, &rdev->flags) && + test_bit(Faulty, &rdev->flags) && + atomic_read(&rdev->nr_pending)==0) { + if (mddev->pers->hot_remove_disk( + mddev, rdev->raid_disk)==0) { + char nm[20]; + sprintf(nm,"rd%d", rdev->raid_disk); + sysfs_remove_link(&mddev->kobj, nm); + rdev->raid_disk = -1; + } + } clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery); goto unlock; } @@ -7321,7 +7358,7 @@ static int __init md_init(void) { int ret = -ENOMEM; - md_wq = alloc_workqueue("md", WQ_RESCUER, 0); + md_wq = alloc_workqueue("md", WQ_MEM_RECLAIM, 0); if (!md_wq) goto err_wq; |