diff options
Diffstat (limited to 'kernel/drivers/md/raid1.c')
| -rw-r--r-- | kernel/drivers/md/raid1.c | 221 |
1 files changed, 115 insertions, 106 deletions
diff --git a/kernel/drivers/md/raid1.c b/kernel/drivers/md/raid1.c index 5ce3cd5c4..c4b913409 100644 --- a/kernel/drivers/md/raid1.c +++ b/kernel/drivers/md/raid1.c @@ -90,6 +90,8 @@ static void r1bio_pool_free(void *r1_bio, void *data) #define RESYNC_PAGES ((RESYNC_BLOCK_SIZE + PAGE_SIZE-1) / PAGE_SIZE) #define RESYNC_WINDOW (RESYNC_BLOCK_SIZE * RESYNC_DEPTH) #define RESYNC_WINDOW_SECTORS (RESYNC_WINDOW >> 9) +#define CLUSTER_RESYNC_WINDOW (16 * RESYNC_WINDOW) +#define CLUSTER_RESYNC_WINDOW_SECTORS (CLUSTER_RESYNC_WINDOW >> 9) #define NEXT_NORMALIO_DISTANCE (3 * RESYNC_WINDOW_SECTORS) static void * r1buf_pool_alloc(gfp_t gfp_flags, void *data) @@ -255,9 +257,10 @@ static void call_bio_endio(struct r1bio *r1_bio) done = 1; if (!test_bit(R1BIO_Uptodate, &r1_bio->state)) - clear_bit(BIO_UPTODATE, &bio->bi_flags); + bio->bi_error = -EIO; + if (done) { - bio_endio(bio, 0); + bio_endio(bio); /* * Wake up any possible resync thread that waits for the device * to go idle. @@ -312,9 +315,9 @@ static int find_bio_disk(struct r1bio *r1_bio, struct bio *bio) return mirror; } -static void raid1_end_read_request(struct bio *bio, int error) +static void raid1_end_read_request(struct bio *bio) { - int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags); + int uptodate = !bio->bi_error; struct r1bio *r1_bio = bio->bi_private; int mirror; struct r1conf *conf = r1_bio->mddev->private; @@ -397,9 +400,8 @@ static void r1_bio_write_done(struct r1bio *r1_bio) } } -static void raid1_end_write_request(struct bio *bio, int error) +static void raid1_end_write_request(struct bio *bio) { - int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags); struct r1bio *r1_bio = bio->bi_private; int mirror, behind = test_bit(R1BIO_BehindIO, &r1_bio->state); struct r1conf *conf = r1_bio->mddev->private; @@ -410,7 +412,7 @@ static void raid1_end_write_request(struct bio *bio, int error) /* * 'one mirror IO has finished' event handler: */ - if (!uptodate) { + if (bio->bi_error) { set_bit(WriteErrorSeen, &conf->mirrors[mirror].rdev->flags); if (!test_and_set_bit(WantReplacement, @@ -541,7 +543,7 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect if ((conf->mddev->recovery_cp < this_sector + sectors) || (mddev_is_clustered(conf->mddev) && - md_cluster_ops->area_resyncing(conf->mddev, this_sector, + md_cluster_ops->area_resyncing(conf->mddev, READ, this_sector, this_sector + sectors))) choose_first = 1; else @@ -557,7 +559,6 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect rdev = rcu_dereference(conf->mirrors[disk].rdev); if (r1_bio->bios[disk] == IO_BLOCKED || rdev == NULL - || test_bit(Unmerged, &rdev->flags) || test_bit(Faulty, &rdev->flags)) continue; if (!test_bit(In_sync, &rdev->flags) && @@ -708,44 +709,12 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect return best_disk; } -static int raid1_mergeable_bvec(struct mddev *mddev, - struct bvec_merge_data *bvm, - struct bio_vec *biovec) -{ - struct r1conf *conf = mddev->private; - sector_t sector = bvm->bi_sector + get_start_sect(bvm->bi_bdev); - int max = biovec->bv_len; - - if (mddev->merge_check_needed) { - int disk; - rcu_read_lock(); - for (disk = 0; disk < conf->raid_disks * 2; disk++) { - struct md_rdev *rdev = rcu_dereference( - conf->mirrors[disk].rdev); - if (rdev && !test_bit(Faulty, &rdev->flags)) { - struct request_queue *q = - bdev_get_queue(rdev->bdev); - if (q->merge_bvec_fn) { - bvm->bi_sector = sector + - rdev->data_offset; - bvm->bi_bdev = rdev->bdev; - max = min(max, q->merge_bvec_fn( - q, bvm, biovec)); - } - } - } - rcu_read_unlock(); - } - return max; - -} - static int raid1_congested(struct mddev *mddev, int bits) { struct r1conf *conf = mddev->private; int i, ret = 0; - if ((bits & (1 << BDI_async_congested)) && + if ((bits & (1 << WB_async_congested)) && conf->pending_count >= max_queued_requests) return 1; @@ -760,7 +729,7 @@ static int raid1_congested(struct mddev *mddev, int bits) /* Note the '|| 1' - when read_balance prefers * non-congested targets, it can be removed */ - if ((bits & (1<<BDI_async_congested)) || 1) + if ((bits & (1 << WB_async_congested)) || 1) ret |= bdi_congested(&q->backing_dev_info, bits); else ret &= bdi_congested(&q->backing_dev_info, bits); @@ -793,7 +762,7 @@ static void flush_pending_writes(struct r1conf *conf) if (unlikely((bio->bi_rw & REQ_DISCARD) && !blk_queue_discard(bdev_get_queue(bio->bi_bdev)))) /* Just ignore it */ - bio_endio(bio, 0); + bio_endio(bio); else generic_make_request(bio); bio = next; @@ -914,8 +883,7 @@ static sector_t wait_barrier(struct r1conf *conf, struct bio *bio) } if (bio && bio_data_dir(bio) == WRITE) { - if (bio->bi_iter.bi_sector >= - conf->mddev->curr_resync_completed) { + if (bio->bi_iter.bi_sector >= conf->next_resync) { if (conf->start_next_window == MaxSector) conf->start_next_window = conf->next_resync + @@ -1068,7 +1036,7 @@ static void raid1_unplug(struct blk_plug_cb *cb, bool from_schedule) if (unlikely((bio->bi_rw & REQ_DISCARD) && !blk_queue_discard(bdev_get_queue(bio->bi_bdev)))) /* Just ignore it */ - bio_endio(bio, 0); + bio_endio(bio); else generic_make_request(bio); bio = next; @@ -1111,7 +1079,8 @@ static void make_request(struct mddev *mddev, struct bio * bio) ((bio_end_sector(bio) > mddev->suspend_lo && bio->bi_iter.bi_sector < mddev->suspend_hi) || (mddev_is_clustered(mddev) && - md_cluster_ops->area_resyncing(mddev, bio->bi_iter.bi_sector, bio_end_sector(bio))))) { + md_cluster_ops->area_resyncing(mddev, WRITE, + bio->bi_iter.bi_sector, bio_end_sector(bio))))) { /* As the suspend_* range is controlled by * userspace, we want an interruptible * wait. @@ -1124,7 +1093,7 @@ static void make_request(struct mddev *mddev, struct bio * bio) if (bio_end_sector(bio) <= mddev->suspend_lo || bio->bi_iter.bi_sector >= mddev->suspend_hi || (mddev_is_clustered(mddev) && - !md_cluster_ops->area_resyncing(mddev, + !md_cluster_ops->area_resyncing(mddev, WRITE, bio->bi_iter.bi_sector, bio_end_sector(bio)))) break; schedule(); @@ -1157,7 +1126,7 @@ static void make_request(struct mddev *mddev, struct bio * bio) * non-zero, then it is the number of not-completed requests. */ bio->bi_phys_segments = 0; - clear_bit(BIO_SEG_VALID, &bio->bi_flags); + bio_clear_flag(bio, BIO_SEG_VALID); if (rw == READ) { /* @@ -1268,8 +1237,7 @@ read_again: break; } r1_bio->bios[i] = NULL; - if (!rdev || test_bit(Faulty, &rdev->flags) - || test_bit(Unmerged, &rdev->flags)) { + if (!rdev || test_bit(Faulty, &rdev->flags)) { if (i < conf->raid_disks) set_bit(R1BIO_Degraded, &r1_bio->state); continue; @@ -1507,6 +1475,7 @@ static void error(struct mddev *mddev, struct md_rdev *rdev) */ set_bit(MD_RECOVERY_INTR, &mddev->recovery); set_bit(MD_CHANGE_DEVS, &mddev->flags); + set_bit(MD_CHANGE_PENDING, &mddev->flags); printk(KERN_ALERT "md/raid1:%s: Disk failure on %s, disabling device.\n" "md/raid1:%s: Operation continuing on %d devices.\n", @@ -1548,7 +1517,7 @@ static void close_sync(struct r1conf *conf) conf->r1buf_pool = NULL; spin_lock_irq(&conf->resync_lock); - conf->next_resync = 0; + conf->next_resync = MaxSector - 2 * NEXT_NORMALIO_DISTANCE; conf->start_next_window = MaxSector; conf->current_window_requests += conf->next_window_requests; @@ -1616,18 +1585,24 @@ static int raid1_add_disk(struct mddev *mddev, struct md_rdev *rdev) struct raid1_info *p; int first = 0; int last = conf->raid_disks - 1; - struct request_queue *q = bdev_get_queue(rdev->bdev); if (mddev->recovery_disabled == conf->recovery_disabled) return -EBUSY; + if (md_integrity_add_rdev(rdev, mddev)) + return -ENXIO; + if (rdev->raid_disk >= 0) first = last = rdev->raid_disk; - if (q->merge_bvec_fn) { - set_bit(Unmerged, &rdev->flags); - mddev->merge_check_needed = 1; - } + /* + * find the disk ... but prefer rdev->saved_raid_disk + * if possible. + */ + if (rdev->saved_raid_disk >= 0 && + rdev->saved_raid_disk >= first && + conf->mirrors[rdev->saved_raid_disk].rdev == NULL) + first = last = rdev->saved_raid_disk; for (mirror = first; mirror <= last; mirror++) { p = conf->mirrors+mirror; @@ -1660,20 +1635,6 @@ static int raid1_add_disk(struct mddev *mddev, struct md_rdev *rdev) break; } } - if (err == 0 && test_bit(Unmerged, &rdev->flags)) { - /* Some requests might not have seen this new - * merge_bvec_fn. We must wait for them to complete - * before merging the device fully. - * First we make sure any code which has tested - * our function has submitted the request, then - * we wait for all outstanding requests to complete. - */ - synchronize_sched(); - freeze_array(conf, 0); - unfreeze_array(conf); - clear_bit(Unmerged, &rdev->flags); - } - md_integrity_add_rdev(rdev, mddev); if (mddev->queue && blk_queue_discard(bdev_get_queue(rdev->bdev))) queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, mddev->queue); print_conf(conf); @@ -1736,7 +1697,7 @@ abort: return err; } -static void end_sync_read(struct bio *bio, int error) +static void end_sync_read(struct bio *bio) { struct r1bio *r1_bio = bio->bi_private; @@ -1747,16 +1708,16 @@ static void end_sync_read(struct bio *bio, int error) * or re-read if the read failed. * We don't do much here, just schedule handling by raid1d */ - if (test_bit(BIO_UPTODATE, &bio->bi_flags)) + if (!bio->bi_error) set_bit(R1BIO_Uptodate, &r1_bio->state); if (atomic_dec_and_test(&r1_bio->remaining)) reschedule_retry(r1_bio); } -static void end_sync_write(struct bio *bio, int error) +static void end_sync_write(struct bio *bio) { - int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags); + int uptodate = !bio->bi_error; struct r1bio *r1_bio = bio->bi_private; struct mddev *mddev = r1_bio->mddev; struct r1conf *conf = mddev->private; @@ -1943,7 +1904,7 @@ static int fix_sync_read_error(struct r1bio *r1_bio) idx ++; } set_bit(R1BIO_Uptodate, &r1_bio->state); - set_bit(BIO_UPTODATE, &bio->bi_flags); + bio->bi_error = 0; return 1; } @@ -1967,15 +1928,14 @@ static void process_checks(struct r1bio *r1_bio) for (i = 0; i < conf->raid_disks * 2; i++) { int j; int size; - int uptodate; + int error; struct bio *b = r1_bio->bios[i]; if (b->bi_end_io != end_sync_read) continue; - /* fixup the bio for reuse, but preserve BIO_UPTODATE */ - uptodate = test_bit(BIO_UPTODATE, &b->bi_flags); + /* fixup the bio for reuse, but preserve errno */ + error = b->bi_error; bio_reset(b); - if (!uptodate) - clear_bit(BIO_UPTODATE, &b->bi_flags); + b->bi_error = error; b->bi_vcnt = vcnt; b->bi_iter.bi_size = r1_bio->sectors << 9; b->bi_iter.bi_sector = r1_bio->sector + @@ -1998,7 +1958,7 @@ static void process_checks(struct r1bio *r1_bio) } for (primary = 0; primary < conf->raid_disks * 2; primary++) if (r1_bio->bios[primary]->bi_end_io == end_sync_read && - test_bit(BIO_UPTODATE, &r1_bio->bios[primary]->bi_flags)) { + !r1_bio->bios[primary]->bi_error) { r1_bio->bios[primary]->bi_end_io = NULL; rdev_dec_pending(conf->mirrors[primary].rdev, mddev); break; @@ -2008,14 +1968,14 @@ static void process_checks(struct r1bio *r1_bio) int j; struct bio *pbio = r1_bio->bios[primary]; struct bio *sbio = r1_bio->bios[i]; - int uptodate = test_bit(BIO_UPTODATE, &sbio->bi_flags); + int error = sbio->bi_error; if (sbio->bi_end_io != end_sync_read) continue; - /* Now we can 'fixup' the BIO_UPTODATE flag */ - set_bit(BIO_UPTODATE, &sbio->bi_flags); + /* Now we can 'fixup' the error value */ + sbio->bi_error = 0; - if (uptodate) { + if (!error) { for (j = vcnt; j-- ; ) { struct page *p, *s; p = pbio->bi_io_vec[j].bv_page; @@ -2030,7 +1990,7 @@ static void process_checks(struct r1bio *r1_bio) if (j >= 0) atomic64_add(r1_bio->sectors, &mddev->resync_mismatches); if (j < 0 || (test_bit(MD_RECOVERY_CHECK, &mddev->recovery) - && uptodate)) { + && !error)) { /* No need to write to this device. */ sbio->bi_end_io = NULL; rdev_dec_pending(conf->mirrors[i].rdev, mddev); @@ -2248,7 +2208,7 @@ static int narrow_write_error(struct r1bio *r1_bio, int i) bio_trim(wbio, sector - r1_bio->sector, sectors); wbio->bi_iter.bi_sector += rdev->data_offset; wbio->bi_bdev = rdev->bdev; - if (submit_bio_wait(WRITE, wbio) == 0) + if (submit_bio_wait(WRITE, wbio) < 0) /* failure! */ ok = rdev_set_badblocks(rdev, sector, sectors, 0) @@ -2271,11 +2231,11 @@ static void handle_sync_write_finished(struct r1conf *conf, struct r1bio *r1_bio struct bio *bio = r1_bio->bios[m]; if (bio->bi_end_io == NULL) continue; - if (test_bit(BIO_UPTODATE, &bio->bi_flags) && + if (!bio->bi_error && test_bit(R1BIO_MadeGood, &r1_bio->state)) { rdev_clear_badblocks(rdev, r1_bio->sector, s, 0); } - if (!test_bit(BIO_UPTODATE, &bio->bi_flags) && + if (bio->bi_error && test_bit(R1BIO_WriteError, &r1_bio->state)) { if (!rdev_set_badblocks(rdev, r1_bio->sector, s, 0)) md_error(conf->mddev, rdev); @@ -2288,6 +2248,7 @@ static void handle_sync_write_finished(struct r1conf *conf, struct r1bio *r1_bio static void handle_write_finished(struct r1conf *conf, struct r1bio *r1_bio) { int m; + bool fail = false; for (m = 0; m < conf->raid_disks * 2 ; m++) if (r1_bio->bios[m] == IO_MADE_GOOD) { struct md_rdev *rdev = conf->mirrors[m].rdev; @@ -2300,6 +2261,7 @@ static void handle_write_finished(struct r1conf *conf, struct r1bio *r1_bio) * narrow down and record precise write * errors. */ + fail = true; if (!narrow_write_error(r1_bio, m)) { md_error(conf->mddev, conf->mirrors[m].rdev); @@ -2309,9 +2271,16 @@ static void handle_write_finished(struct r1conf *conf, struct r1bio *r1_bio) rdev_dec_pending(conf->mirrors[m].rdev, conf->mddev); } - if (test_bit(R1BIO_WriteError, &r1_bio->state)) - close_write(r1_bio); - raid_end_bio_io(r1_bio); + if (fail) { + spin_lock_irq(&conf->device_lock); + list_add(&r1_bio->retry_list, &conf->bio_end_io_list); + spin_unlock_irq(&conf->device_lock); + md_wakeup_thread(conf->mddev->thread); + } else { + if (test_bit(R1BIO_WriteError, &r1_bio->state)) + close_write(r1_bio); + raid_end_bio_io(r1_bio); + } } static void handle_read_error(struct r1conf *conf, struct r1bio *r1_bio) @@ -2417,6 +2386,27 @@ static void raid1d(struct md_thread *thread) md_check_recovery(mddev); + if (!list_empty_careful(&conf->bio_end_io_list) && + !test_bit(MD_CHANGE_PENDING, &mddev->flags)) { + LIST_HEAD(tmp); + spin_lock_irqsave(&conf->device_lock, flags); + if (!test_bit(MD_CHANGE_PENDING, &mddev->flags)) { + list_add(&tmp, &conf->bio_end_io_list); + list_del_init(&conf->bio_end_io_list); + } + spin_unlock_irqrestore(&conf->device_lock, flags); + while (!list_empty(&tmp)) { + r1_bio = list_first_entry(&tmp, struct r1bio, + retry_list); + list_del(&r1_bio->retry_list); + if (mddev->degraded) + set_bit(R1BIO_Degraded, &r1_bio->state); + if (test_bit(R1BIO_WriteError, &r1_bio->state)) + close_write(r1_bio); + raid_end_bio_io(r1_bio); + } + } + blk_start_plug(&plug); for (;;) { @@ -2516,6 +2506,11 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr, int *skipp bitmap_close_sync(mddev->bitmap); close_sync(conf); + + if (mddev_is_clustered(mddev)) { + conf->cluster_sync_low = 0; + conf->cluster_sync_high = 0; + } return 0; } @@ -2536,7 +2531,12 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr, int *skipp return sync_blocks; } - bitmap_cond_end_sync(mddev->bitmap, sector_nr); + /* we are incrementing sector_nr below. To be safe, we check against + * sector_nr + two times RESYNC_SECTORS + */ + + bitmap_cond_end_sync(mddev->bitmap, sector_nr, + mddev_is_clustered(mddev) && (sector_nr + 2 * RESYNC_SECTORS > conf->cluster_sync_high)); r1_bio = mempool_alloc(conf->r1buf_pool, GFP_NOIO); raise_barrier(conf, sector_nr); @@ -2714,7 +2714,7 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr, int *skipp /* remove last page from this bio */ bio->bi_vcnt--; bio->bi_iter.bi_size -= len; - __clear_bit(BIO_SEG_VALID, &bio->bi_flags); + bio_clear_flag(bio, BIO_SEG_VALID); } goto bio_full; } @@ -2727,6 +2727,16 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr, int *skipp bio_full: r1_bio->sectors = nr_sectors; + if (mddev_is_clustered(mddev) && + conf->cluster_sync_high < sector_nr + nr_sectors) { + conf->cluster_sync_low = mddev->curr_resync_completed; + conf->cluster_sync_high = conf->cluster_sync_low + CLUSTER_RESYNC_WINDOW_SECTORS; + /* Send resync message */ + md_cluster_ops->resync_info_update(mddev, + conf->cluster_sync_low, + conf->cluster_sync_high); + } + /* For a user-requested sync, we read all readable devices and do a * compare */ @@ -2809,8 +2819,6 @@ static struct r1conf *setup_conf(struct mddev *mddev) goto abort; disk->rdev = rdev; q = bdev_get_queue(rdev->bdev); - if (q->merge_bvec_fn) - mddev->merge_check_needed = 1; disk->head_position = 0; disk->seq_start = MaxSector; @@ -2818,6 +2826,7 @@ static struct r1conf *setup_conf(struct mddev *mddev) conf->raid_disks = mddev->raid_disks; conf->mddev = mddev; INIT_LIST_HEAD(&conf->retry_list); + INIT_LIST_HEAD(&conf->bio_end_io_list); spin_lock_init(&conf->resync_lock); init_waitqueue_head(&conf->wait_barrier); @@ -2871,8 +2880,7 @@ static struct r1conf *setup_conf(struct mddev *mddev) abort: if (conf) { - if (conf->r1bio_pool) - mempool_destroy(conf->r1bio_pool); + mempool_destroy(conf->r1bio_pool); kfree(conf->mirrors); safe_put_page(conf->tmppage); kfree(conf->poolinfo); @@ -2974,8 +2982,7 @@ static void raid1_free(struct mddev *mddev, void *priv) { struct r1conf *conf = priv; - if (conf->r1bio_pool) - mempool_destroy(conf->r1bio_pool); + mempool_destroy(conf->r1bio_pool); kfree(conf->mirrors); safe_put_page(conf->tmppage); kfree(conf->poolinfo); @@ -3044,9 +3051,11 @@ static int raid1_reshape(struct mddev *mddev) return -EINVAL; } - err = md_allow_write(mddev); - if (err) - return err; + if (!mddev_is_clustered(mddev)) { + err = md_allow_write(mddev); + if (err) + return err; + } raid_disks = mddev->raid_disks + mddev->delta_disks; @@ -3112,6 +3121,7 @@ static int raid1_reshape(struct mddev *mddev) unfreeze_array(conf); + set_bit(MD_RECOVERY_RECOVER, &mddev->recovery); set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); md_wakeup_thread(mddev->thread); @@ -3175,7 +3185,6 @@ static struct md_personality raid1_personality = .quiesce = raid1_quiesce, .takeover = raid1_takeover, .congested = raid1_congested, - .mergeable_bvec = raid1_mergeable_bvec, }; static int __init raid_init(void) |