diff options
Diffstat (limited to 'drivers/md/raid10.c')
-rw-r--r-- | drivers/md/raid10.c | 250 |
1 files changed, 152 insertions, 98 deletions
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 26ae74fd0d01..ed29fc899f06 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -707,7 +707,6 @@ static struct md_rdev *read_balance(struct r10conf *conf, raid10_find_phys(conf, r10_bio); rcu_read_lock(); -retry: sectors = r10_bio->sectors; best_slot = -1; best_rdev = NULL; @@ -804,13 +803,6 @@ retry: if (slot >= 0) { atomic_inc(&rdev->nr_pending); - if (test_bit(Faulty, &rdev->flags)) { - /* Cannot risk returning a device that failed - * before we inc'ed nr_pending - */ - rdev_dec_pending(rdev, conf->mddev); - goto retry; - } r10_bio->read_slot = slot; } else rdev = NULL; @@ -913,7 +905,7 @@ static void raise_barrier(struct r10conf *conf, int force) /* Now wait for all pending IO to complete */ wait_event_lock_irq(conf->wait_barrier, - !conf->nr_pending && conf->barrier < RESYNC_DEPTH, + !atomic_read(&conf->nr_pending) && conf->barrier < RESYNC_DEPTH, conf->resync_lock); spin_unlock_irq(&conf->resync_lock); @@ -944,23 +936,23 @@ static void wait_barrier(struct r10conf *conf) */ wait_event_lock_irq(conf->wait_barrier, !conf->barrier || - (conf->nr_pending && + (atomic_read(&conf->nr_pending) && current->bio_list && !bio_list_empty(current->bio_list)), conf->resync_lock); conf->nr_waiting--; + if (!conf->nr_waiting) + wake_up(&conf->wait_barrier); } - conf->nr_pending++; + atomic_inc(&conf->nr_pending); spin_unlock_irq(&conf->resync_lock); } static void allow_barrier(struct r10conf *conf) { - unsigned long flags; - spin_lock_irqsave(&conf->resync_lock, flags); - conf->nr_pending--; - spin_unlock_irqrestore(&conf->resync_lock, flags); - wake_up(&conf->wait_barrier); + if ((atomic_dec_and_test(&conf->nr_pending)) || + (conf->array_freeze_pending)) + wake_up(&conf->wait_barrier); } static void freeze_array(struct r10conf *conf, int extra) @@ -978,13 +970,15 @@ static void freeze_array(struct r10conf *conf, int extra) * we continue. */ spin_lock_irq(&conf->resync_lock); + conf->array_freeze_pending++; conf->barrier++; conf->nr_waiting++; wait_event_lock_irq_cmd(conf->wait_barrier, - conf->nr_pending == conf->nr_queued+extra, + atomic_read(&conf->nr_pending) == conf->nr_queued+extra, conf->resync_lock, flush_pending_writes(conf)); + conf->array_freeze_pending--; spin_unlock_irq(&conf->resync_lock); } @@ -1499,10 +1493,12 @@ static void raid10_status(struct seq_file *seq, struct mddev *mddev) } seq_printf(seq, " [%d/%d] [", conf->geo.raid_disks, conf->geo.raid_disks - mddev->degraded); - for (i = 0; i < conf->geo.raid_disks; i++) - seq_printf(seq, "%s", - conf->mirrors[i].rdev && - test_bit(In_sync, &conf->mirrors[i].rdev->flags) ? "U" : "_"); + rcu_read_lock(); + for (i = 0; i < conf->geo.raid_disks; i++) { + struct md_rdev *rdev = rcu_dereference(conf->mirrors[i].rdev); + seq_printf(seq, "%s", rdev && test_bit(In_sync, &rdev->flags) ? "U" : "_"); + } + rcu_read_unlock(); seq_printf(seq, "]"); } @@ -1600,7 +1596,7 @@ static void raid10_error(struct mddev *mddev, struct md_rdev *rdev) static void print_conf(struct r10conf *conf) { int i; - struct raid10_info *tmp; + struct md_rdev *rdev; printk(KERN_DEBUG "RAID10 conf printout:\n"); if (!conf) { @@ -1610,14 +1606,16 @@ static void print_conf(struct r10conf *conf) printk(KERN_DEBUG " --- wd:%d rd:%d\n", conf->geo.raid_disks - conf->mddev->degraded, conf->geo.raid_disks); + /* This is only called with ->reconfix_mutex held, so + * rcu protection of rdev is not needed */ for (i = 0; i < conf->geo.raid_disks; i++) { char b[BDEVNAME_SIZE]; - tmp = conf->mirrors + i; - if (tmp->rdev) + rdev = conf->mirrors[i].rdev; + if (rdev) printk(KERN_DEBUG " disk %d, wo:%d, o:%d, dev:%s\n", - i, !test_bit(In_sync, &tmp->rdev->flags), - !test_bit(Faulty, &tmp->rdev->flags), - bdevname(tmp->rdev->bdev,b)); + i, !test_bit(In_sync, &rdev->flags), + !test_bit(Faulty, &rdev->flags), + bdevname(rdev->bdev,b)); } } @@ -1766,7 +1764,7 @@ static int raid10_remove_disk(struct mddev *mddev, struct md_rdev *rdev) err = -EBUSY; goto abort; } - /* Only remove faulty devices if recovery + /* Only remove non-faulty devices if recovery * is not possible. */ if (!test_bit(Faulty, &rdev->flags) && @@ -1778,13 +1776,16 @@ static int raid10_remove_disk(struct mddev *mddev, struct md_rdev *rdev) goto abort; } *rdevp = NULL; - synchronize_rcu(); - if (atomic_read(&rdev->nr_pending)) { - /* lost the race, try later */ - err = -EBUSY; - *rdevp = rdev; - goto abort; - } else if (p->replacement) { + if (!test_bit(RemoveSynchronized, &rdev->flags)) { + synchronize_rcu(); + if (atomic_read(&rdev->nr_pending)) { + /* lost the race, try later */ + err = -EBUSY; + *rdevp = rdev; + goto abort; + } + } + if (p->replacement) { /* We must have just cleared 'rdev' */ p->rdev = p->replacement; clear_bit(Replacement, &p->replacement->flags); @@ -2171,21 +2172,20 @@ static void recovery_request_write(struct mddev *mddev, struct r10bio *r10_bio) */ static void check_decay_read_errors(struct mddev *mddev, struct md_rdev *rdev) { - struct timespec cur_time_mon; + long cur_time_mon; unsigned long hours_since_last; unsigned int read_errors = atomic_read(&rdev->read_errors); - ktime_get_ts(&cur_time_mon); + cur_time_mon = ktime_get_seconds(); - if (rdev->last_read_error.tv_sec == 0 && - rdev->last_read_error.tv_nsec == 0) { + if (rdev->last_read_error == 0) { /* first time we've seen a read error */ rdev->last_read_error = cur_time_mon; return; } - hours_since_last = (cur_time_mon.tv_sec - - rdev->last_read_error.tv_sec) / 3600; + hours_since_last = (long)(cur_time_mon - + rdev->last_read_error) / 3600; rdev->last_read_error = cur_time_mon; @@ -2264,7 +2264,7 @@ static void fix_read_error(struct r10conf *conf, struct mddev *mddev, struct r10 printk(KERN_NOTICE "md/raid10:%s: %s: Failing raid device\n", mdname(mddev), b); - md_error(mddev, conf->mirrors[d].rdev); + md_error(mddev, rdev); r10_bio->devs[r10_bio->read_slot].bio = IO_BLOCKED; return; } @@ -2287,6 +2287,7 @@ static void fix_read_error(struct r10conf *conf, struct mddev *mddev, struct r10 rdev = rcu_dereference(conf->mirrors[d].rdev); if (rdev && test_bit(In_sync, &rdev->flags) && + !test_bit(Faulty, &rdev->flags) && is_badblock(rdev, r10_bio->devs[sl].addr + sect, s, &first_bad, &bad_sectors) == 0) { atomic_inc(&rdev->nr_pending); @@ -2340,6 +2341,7 @@ static void fix_read_error(struct r10conf *conf, struct mddev *mddev, struct r10 d = r10_bio->devs[sl].devnum; rdev = rcu_dereference(conf->mirrors[d].rdev); if (!rdev || + test_bit(Faulty, &rdev->flags) || !test_bit(In_sync, &rdev->flags)) continue; @@ -2379,6 +2381,7 @@ static void fix_read_error(struct r10conf *conf, struct mddev *mddev, struct r10 d = r10_bio->devs[sl].devnum; rdev = rcu_dereference(conf->mirrors[d].rdev); if (!rdev || + test_bit(Faulty, &rdev->flags) || !test_bit(In_sync, &rdev->flags)) continue; @@ -2876,11 +2879,14 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, /* Completed a full sync so the replacements * are now fully recovered. */ - for (i = 0; i < conf->geo.raid_disks; i++) - if (conf->mirrors[i].replacement) - conf->mirrors[i].replacement - ->recovery_offset - = MaxSector; + rcu_read_lock(); + for (i = 0; i < conf->geo.raid_disks; i++) { + struct md_rdev *rdev = + rcu_dereference(conf->mirrors[i].replacement); + if (rdev) + rdev->recovery_offset = MaxSector; + } + rcu_read_unlock(); } conf->fullsync = 0; } @@ -2911,6 +2917,13 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, max_sector > (sector_nr | chunk_mask)) max_sector = (sector_nr | chunk_mask) + 1; + /* + * If there is non-resync activity waiting for a turn, then let it + * though before starting on this new sync request. + */ + if (conf->nr_waiting) + schedule_timeout_uninterruptible(1); + /* Again, very different code for resync and recovery. * Both must result in an r10bio with a list of bios that * have bi_end_io, bi_sector, bi_bdev set, @@ -2939,14 +2952,20 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, int must_sync; int any_working; struct raid10_info *mirror = &conf->mirrors[i]; + struct md_rdev *mrdev, *mreplace; - if ((mirror->rdev == NULL || - test_bit(In_sync, &mirror->rdev->flags)) - && - (mirror->replacement == NULL || - test_bit(Faulty, - &mirror->replacement->flags))) + rcu_read_lock(); + mrdev = rcu_dereference(mirror->rdev); + mreplace = rcu_dereference(mirror->replacement); + + if ((mrdev == NULL || + test_bit(Faulty, &mrdev->flags) || + test_bit(In_sync, &mrdev->flags)) && + (mreplace == NULL || + test_bit(Faulty, &mreplace->flags))) { + rcu_read_unlock(); continue; + } still_degraded = 0; /* want to reconstruct this device */ @@ -2956,8 +2975,11 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, /* last stripe is not complete - don't * try to recover this sector. */ + rcu_read_unlock(); continue; } + if (mreplace && test_bit(Faulty, &mreplace->flags)) + mreplace = NULL; /* Unless we are doing a full sync, or a replacement * we only need to recover the block if it is set in * the bitmap @@ -2967,14 +2989,19 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, if (sync_blocks < max_sync) max_sync = sync_blocks; if (!must_sync && - mirror->replacement == NULL && + mreplace == NULL && !conf->fullsync) { /* yep, skip the sync_blocks here, but don't assume * that there will never be anything to do here */ chunks_skipped = -1; + rcu_read_unlock(); continue; } + atomic_inc(&mrdev->nr_pending); + if (mreplace) + atomic_inc(&mreplace->nr_pending); + rcu_read_unlock(); r10_bio = mempool_alloc(conf->r10buf_pool, GFP_NOIO); r10_bio->state = 0; @@ -2993,12 +3020,15 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, /* Need to check if the array will still be * degraded */ - for (j = 0; j < conf->geo.raid_disks; j++) - if (conf->mirrors[j].rdev == NULL || - test_bit(Faulty, &conf->mirrors[j].rdev->flags)) { + rcu_read_lock(); + for (j = 0; j < conf->geo.raid_disks; j++) { + struct md_rdev *rdev = rcu_dereference( + conf->mirrors[j].rdev); + if (rdev == NULL || test_bit(Faulty, &rdev->flags)) { still_degraded = 1; break; } + } must_sync = bitmap_start_sync(mddev->bitmap, sect, &sync_blocks, still_degraded); @@ -3008,15 +3038,15 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, int k; int d = r10_bio->devs[j].devnum; sector_t from_addr, to_addr; - struct md_rdev *rdev; + struct md_rdev *rdev = + rcu_dereference(conf->mirrors[d].rdev); sector_t sector, first_bad; int bad_sectors; - if (!conf->mirrors[d].rdev || - !test_bit(In_sync, &conf->mirrors[d].rdev->flags)) + if (!rdev || + !test_bit(In_sync, &rdev->flags)) continue; /* This is where we read from */ any_working = 1; - rdev = conf->mirrors[d].rdev; sector = r10_bio->devs[j].addr; if (is_badblock(rdev, sector, max_sync, @@ -3055,8 +3085,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, r10_bio->devs[1].devnum = i; r10_bio->devs[1].addr = to_addr; - rdev = mirror->rdev; - if (!test_bit(In_sync, &rdev->flags)) { + if (!test_bit(In_sync, &mrdev->flags)) { bio = r10_bio->devs[1].bio; bio_reset(bio); bio->bi_next = biolist; @@ -3065,8 +3094,8 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, bio->bi_end_io = end_sync_write; bio_set_op_attrs(bio, REQ_OP_WRITE, 0); bio->bi_iter.bi_sector = to_addr - + rdev->data_offset; - bio->bi_bdev = rdev->bdev; + + mrdev->data_offset; + bio->bi_bdev = mrdev->bdev; atomic_inc(&r10_bio->remaining); } else r10_bio->devs[1].bio->bi_end_io = NULL; @@ -3075,8 +3104,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, bio = r10_bio->devs[1].repl_bio; if (bio) bio->bi_end_io = NULL; - rdev = mirror->replacement; - /* Note: if rdev != NULL, then bio + /* Note: if mreplace != NULL, then bio * cannot be NULL as r10buf_pool_alloc will * have allocated it. * So the second test here is pointless. @@ -3084,8 +3112,8 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, * this comment keeps human reviewers * happy. */ - if (rdev == NULL || bio == NULL || - test_bit(Faulty, &rdev->flags)) + if (mreplace == NULL || bio == NULL || + test_bit(Faulty, &mreplace->flags)) break; bio_reset(bio); bio->bi_next = biolist; @@ -3094,11 +3122,12 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, bio->bi_end_io = end_sync_write; bio_set_op_attrs(bio, REQ_OP_WRITE, 0); bio->bi_iter.bi_sector = to_addr + - rdev->data_offset; - bio->bi_bdev = rdev->bdev; + mreplace->data_offset; + bio->bi_bdev = mreplace->bdev; atomic_inc(&r10_bio->remaining); break; } + rcu_read_unlock(); if (j == conf->copies) { /* Cannot recover, so abort the recovery or * record a bad block */ @@ -3111,15 +3140,15 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, if (r10_bio->devs[k].devnum == i) break; if (!test_bit(In_sync, - &mirror->rdev->flags) + &mrdev->flags) && !rdev_set_badblocks( - mirror->rdev, + mrdev, r10_bio->devs[k].addr, max_sync, 0)) any_working = 0; - if (mirror->replacement && + if (mreplace && !rdev_set_badblocks( - mirror->replacement, + mreplace, r10_bio->devs[k].addr, max_sync, 0)) any_working = 0; @@ -3137,8 +3166,14 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, if (rb2) atomic_dec(&rb2->remaining); r10_bio = rb2; + rdev_dec_pending(mrdev, mddev); + if (mreplace) + rdev_dec_pending(mreplace, mddev); break; } + rdev_dec_pending(mrdev, mddev); + if (mreplace) + rdev_dec_pending(mreplace, mddev); } if (biolist == NULL) { while (r10_bio) { @@ -3183,6 +3218,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, int d = r10_bio->devs[i].devnum; sector_t first_bad, sector; int bad_sectors; + struct md_rdev *rdev; if (r10_bio->devs[i].repl_bio) r10_bio->devs[i].repl_bio->bi_end_io = NULL; @@ -3190,12 +3226,14 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, bio = r10_bio->devs[i].bio; bio_reset(bio); bio->bi_error = -EIO; - if (conf->mirrors[d].rdev == NULL || - test_bit(Faulty, &conf->mirrors[d].rdev->flags)) + rcu_read_lock(); + rdev = rcu_dereference(conf->mirrors[d].rdev); + if (rdev == NULL || test_bit(Faulty, &rdev->flags)) { + rcu_read_unlock(); continue; + } sector = r10_bio->devs[i].addr; - if (is_badblock(conf->mirrors[d].rdev, - sector, max_sync, + if (is_badblock(rdev, sector, max_sync, &first_bad, &bad_sectors)) { if (first_bad > sector) max_sync = first_bad - sector; @@ -3203,25 +3241,28 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, bad_sectors -= (sector - first_bad); if (max_sync > bad_sectors) max_sync = bad_sectors; + rcu_read_unlock(); continue; } } - atomic_inc(&conf->mirrors[d].rdev->nr_pending); + atomic_inc(&rdev->nr_pending); atomic_inc(&r10_bio->remaining); bio->bi_next = biolist; biolist = bio; bio->bi_private = r10_bio; bio->bi_end_io = end_sync_read; bio_set_op_attrs(bio, REQ_OP_READ, 0); - bio->bi_iter.bi_sector = sector + - conf->mirrors[d].rdev->data_offset; - bio->bi_bdev = conf->mirrors[d].rdev->bdev; + bio->bi_iter.bi_sector = sector + rdev->data_offset; + bio->bi_bdev = rdev->bdev; count++; - if (conf->mirrors[d].replacement == NULL || - test_bit(Faulty, - &conf->mirrors[d].replacement->flags)) + rdev = rcu_dereference(conf->mirrors[d].replacement); + if (rdev == NULL || test_bit(Faulty, &rdev->flags)) { + rcu_read_unlock(); continue; + } + atomic_inc(&rdev->nr_pending); + rcu_read_unlock(); /* Need to set up for writing to the replacement */ bio = r10_bio->devs[i].repl_bio; @@ -3229,15 +3270,13 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, bio->bi_error = -EIO; sector = r10_bio->devs[i].addr; - atomic_inc(&conf->mirrors[d].rdev->nr_pending); bio->bi_next = biolist; biolist = bio; bio->bi_private = r10_bio; bio->bi_end_io = end_sync_write; bio_set_op_attrs(bio, REQ_OP_WRITE, 0); - bio->bi_iter.bi_sector = sector + - conf->mirrors[d].replacement->data_offset; - bio->bi_bdev = conf->mirrors[d].replacement->bdev; + bio->bi_iter.bi_sector = sector + rdev->data_offset; + bio->bi_bdev = rdev->bdev; count++; } @@ -3504,6 +3543,7 @@ static struct r10conf *setup_conf(struct mddev *mddev) spin_lock_init(&conf->resync_lock); init_waitqueue_head(&conf->wait_barrier); + atomic_set(&conf->nr_pending, 0); conf->thread = md_register_thread(raid10d, mddev, "raid10"); if (!conf->thread) @@ -4333,15 +4373,16 @@ read_more: blist = read_bio; read_bio->bi_next = NULL; + rcu_read_lock(); for (s = 0; s < conf->copies*2; s++) { struct bio *b; int d = r10_bio->devs[s/2].devnum; struct md_rdev *rdev2; if (s&1) { - rdev2 = conf->mirrors[d].replacement; + rdev2 = rcu_dereference(conf->mirrors[d].replacement); b = r10_bio->devs[s/2].repl_bio; } else { - rdev2 = conf->mirrors[d].rdev; + rdev2 = rcu_dereference(conf->mirrors[d].rdev); b = r10_bio->devs[s/2].bio; } if (!rdev2 || test_bit(Faulty, &rdev2->flags)) @@ -4386,6 +4427,7 @@ read_more: nr_sectors += len >> 9; } bio_full: + rcu_read_unlock(); r10_bio->sectors = nr_sectors; /* Now submit the read */ @@ -4437,16 +4479,20 @@ static void reshape_request_write(struct mddev *mddev, struct r10bio *r10_bio) struct bio *b; int d = r10_bio->devs[s/2].devnum; struct md_rdev *rdev; + rcu_read_lock(); if (s&1) { - rdev = conf->mirrors[d].replacement; + rdev = rcu_dereference(conf->mirrors[d].replacement); b = r10_bio->devs[s/2].repl_bio; } else { - rdev = conf->mirrors[d].rdev; + rdev = rcu_dereference(conf->mirrors[d].rdev); b = r10_bio->devs[s/2].bio; } - if (!rdev || test_bit(Faulty, &rdev->flags)) + if (!rdev || test_bit(Faulty, &rdev->flags)) { + rcu_read_unlock(); continue; + } atomic_inc(&rdev->nr_pending); + rcu_read_unlock(); md_sync_acct(b->bi_bdev, r10_bio->sectors); atomic_inc(&r10_bio->remaining); b->bi_next = NULL; @@ -4507,9 +4553,10 @@ static int handle_reshape_read_error(struct mddev *mddev, if (s > (PAGE_SIZE >> 9)) s = PAGE_SIZE >> 9; + rcu_read_lock(); while (!success) { int d = r10b->devs[slot].devnum; - struct md_rdev *rdev = conf->mirrors[d].rdev; + struct md_rdev *rdev = rcu_dereference(conf->mirrors[d].rdev); sector_t addr; if (rdev == NULL || test_bit(Faulty, &rdev->flags) || @@ -4517,11 +4564,15 @@ static int handle_reshape_read_error(struct mddev *mddev, goto failed; addr = r10b->devs[slot].addr + idx * PAGE_SIZE; + atomic_inc(&rdev->nr_pending); + rcu_read_unlock(); success = sync_page_io(rdev, addr, s << 9, bvec[idx].bv_page, REQ_OP_READ, 0, false); + rdev_dec_pending(rdev, mddev); + rcu_read_lock(); if (success) break; failed: @@ -4531,6 +4582,7 @@ static int handle_reshape_read_error(struct mddev *mddev, if (slot == first_slot) break; } + rcu_read_unlock(); if (!success) { /* couldn't read this block, must give up */ set_bit(MD_RECOVERY_INTR, @@ -4600,16 +4652,18 @@ static void raid10_finish_reshape(struct mddev *mddev) } } else { int d; + rcu_read_lock(); for (d = conf->geo.raid_disks ; d < conf->geo.raid_disks - mddev->delta_disks; d++) { - struct md_rdev *rdev = conf->mirrors[d].rdev; + struct md_rdev *rdev = rcu_dereference(conf->mirrors[d].rdev); if (rdev) clear_bit(In_sync, &rdev->flags); - rdev = conf->mirrors[d].replacement; + rdev = rcu_dereference(conf->mirrors[d].replacement); if (rdev) clear_bit(In_sync, &rdev->flags); } + rcu_read_unlock(); } mddev->layout = mddev->new_layout; mddev->chunk_sectors = 1 << conf->geo.chunk_shift; |