Merge tag 'md/4.12-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/shli/md

Pull MD fixes from Shaohua Li:

- Several bug fixes for raid5-cache from Song Liu, mainly handle
journal disk error

- Fix bad block handling in choosing raid1 disk from Tomasz Majchrzak

- Simplify external metadata array sysfs handling from Artur
Paszkiewicz

- Optimize raid0 discard handling from me, now raid0 will dispatch
large discard IO directly to underlayer disks.

* tag 'md/4.12-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/shli/md:
raid1: prefer disk without bad blocks
md/r5cache: handle sync with data in write back cache
md/r5cache: gracefully handle journal device errors for writeback mode
md/raid1/10: avoid unnecessary locking
md/raid5-cache: in r5l_do_submit_io(), submit io->split_bio first
md/md0: optimize raid0 discard handling
md: don't return -EAGAIN in md_allow_write for external metadata arrays
md/raid5: make use of spin_lock_irq over local_irq_disable + spin_lock

drivers/md/md.c

···
  * may proceed without blocking.  It is important to call this before
  * attempting a GFP_KERNEL allocation while holding the mddev lock.
  * Must be called with mddev_lock held.
- *
- * In the ->external case MD_SB_CHANGE_PENDING can not be cleared until mddev->lock
- * is dropped, so return -EAGAIN after notifying userspace.
  */
-int md_allow_write(struct mddev *mddev)
+void md_allow_write(struct mddev *mddev)
 {
 	if (!mddev->pers)
-		return 0;
+		return;
 	if (mddev->ro)
-		return 0;
+		return;
 	if (!mddev->pers->sync_request)
-		return 0;
+		return;
 
 	spin_lock(&mddev->lock);
 	if (mddev->in_sync) {
···
 		spin_unlock(&mddev->lock);
 		md_update_sb(mddev, 0);
 		sysfs_notify_dirent_safe(mddev->sysfs_state);
+		/* wait for the dirty state to be recorded in the metadata */
+		wait_event(mddev->sb_wait,
+			   !test_bit(MD_SB_CHANGE_CLEAN, &mddev->sb_flags) &&
+			   !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags));
 	} else
 		spin_unlock(&mddev->lock);
-
-	if (test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags))
-		return -EAGAIN;
-	else
-		return 0;
 }
 EXPORT_SYMBOL_GPL(md_allow_write);
 

drivers/md/md.h

···
 			bool metadata_op);
 extern void md_do_sync(struct md_thread *thread);
 extern void md_new_event(struct mddev *mddev);
-extern int md_allow_write(struct mddev *mddev);
+extern void md_allow_write(struct mddev *mddev);
 extern void md_wait_for_blocked_rdev(struct md_rdev *rdev, struct mddev *mddev);
 extern void md_set_array_sectors(struct mddev *mddev, sector_t array_sectors);
 extern int md_check_no_bitmap(struct mddev *mddev);

drivers/md/raid0.c

···
 		blk_queue_max_hw_sectors(mddev->queue, mddev->chunk_sectors);
 		blk_queue_max_write_same_sectors(mddev->queue, mddev->chunk_sectors);
 		blk_queue_max_write_zeroes_sectors(mddev->queue, mddev->chunk_sectors);
-		blk_queue_max_discard_sectors(mddev->queue, mddev->chunk_sectors);
+		blk_queue_max_discard_sectors(mddev->queue, UINT_MAX);
 
 		blk_queue_io_min(mddev->queue, mddev->chunk_sectors << 9);
 		blk_queue_io_opt(mddev->queue,
···
 	}
 }
 
+static void raid0_handle_discard(struct mddev *mddev, struct bio *bio)
+{
+	struct r0conf *conf = mddev->private;
+	struct strip_zone *zone;
+	sector_t start = bio->bi_iter.bi_sector;
+	sector_t end;
+	unsigned int stripe_size;
+	sector_t first_stripe_index, last_stripe_index;
+	sector_t start_disk_offset;
+	unsigned int start_disk_index;
+	sector_t end_disk_offset;
+	unsigned int end_disk_index;
+	unsigned int disk;
+
+	zone = find_zone(conf, &start);
+
+	if (bio_end_sector(bio) > zone->zone_end) {
+		struct bio *split = bio_split(bio,
+			zone->zone_end - bio->bi_iter.bi_sector, GFP_NOIO,
+			mddev->bio_set);
+		bio_chain(split, bio);
+		generic_make_request(bio);
+		bio = split;
+		end = zone->zone_end;
+	} else
+		end = bio_end_sector(bio);
+
+	if (zone != conf->strip_zone)
+		end = end - zone[-1].zone_end;
+
+	/* Now start and end is the offset in zone */
+	stripe_size = zone->nb_dev * mddev->chunk_sectors;
+
+	first_stripe_index = start;
+	sector_div(first_stripe_index, stripe_size);
+	last_stripe_index = end;
+	sector_div(last_stripe_index, stripe_size);
+
+	start_disk_index = (int)(start - first_stripe_index * stripe_size) /
+		mddev->chunk_sectors;
+	start_disk_offset = ((int)(start - first_stripe_index * stripe_size) %
+		mddev->chunk_sectors) +
+		first_stripe_index * mddev->chunk_sectors;
+	end_disk_index = (int)(end - last_stripe_index * stripe_size) /
+		mddev->chunk_sectors;
+	end_disk_offset = ((int)(end - last_stripe_index * stripe_size) %
+		mddev->chunk_sectors) +
+		last_stripe_index * mddev->chunk_sectors;
+
+	for (disk = 0; disk < zone->nb_dev; disk++) {
+		sector_t dev_start, dev_end;
+		struct bio *discard_bio = NULL;
+		struct md_rdev *rdev;
+
+		if (disk < start_disk_index)
+			dev_start = (first_stripe_index + 1) *
+				mddev->chunk_sectors;
+		else if (disk > start_disk_index)
+			dev_start = first_stripe_index * mddev->chunk_sectors;
+		else
+			dev_start = start_disk_offset;
+
+		if (disk < end_disk_index)
+			dev_end = (last_stripe_index + 1) * mddev->chunk_sectors;
+		else if (disk > end_disk_index)
+			dev_end = last_stripe_index * mddev->chunk_sectors;
+		else
+			dev_end = end_disk_offset;
+
+		if (dev_end <= dev_start)
+			continue;
+
+		rdev = conf->devlist[(zone - conf->strip_zone) *
+			conf->strip_zone[0].nb_dev + disk];
+		if (__blkdev_issue_discard(rdev->bdev,
+			dev_start + zone->dev_start + rdev->data_offset,
+			dev_end - dev_start, GFP_NOIO, 0, &discard_bio) ||
+		    !discard_bio)
+			continue;
+		bio_chain(discard_bio, bio);
+		if (mddev->gendisk)
+			trace_block_bio_remap(bdev_get_queue(rdev->bdev),
+				discard_bio, disk_devt(mddev->gendisk),
+				bio->bi_iter.bi_sector);
+		generic_make_request(discard_bio);
+	}
+	bio_endio(bio);
+}
+
 static void raid0_make_request(struct mddev *mddev, struct bio *bio)
 {
 	struct strip_zone *zone;
···
 
 	if (unlikely(bio->bi_opf & REQ_PREFLUSH)) {
 		md_flush_request(mddev, bio);
+		return;
+	}
+
+	if (unlikely((bio_op(bio) == REQ_OP_DISCARD))) {
+		raid0_handle_discard(mddev, bio);
 		return;
 	}
 
···
 	bio->bi_iter.bi_sector = sector + zone->dev_start +
 		tmp_dev->data_offset;
 
-	if (unlikely((bio_op(bio) == REQ_OP_DISCARD) &&
-		     !blk_queue_discard(bdev_get_queue(bio->bi_bdev)))) {
-		/* Just ignore it */
-		bio_endio(bio);
-	} else {
-		if (mddev->gendisk)
-			trace_block_bio_remap(bdev_get_queue(bio->bi_bdev),
-					      bio, disk_devt(mddev->gendisk),
-					      bio_sector);
-		mddev_check_writesame(mddev, bio);
-		mddev_check_write_zeroes(mddev, bio);
-		generic_make_request(bio);
-	}
+	if (mddev->gendisk)
+		trace_block_bio_remap(bdev_get_queue(bio->bi_bdev),
+				      bio, disk_devt(mddev->gendisk),
+				      bio_sector);
+	mddev_check_writesame(mddev, bio);
+	mddev_check_write_zeroes(mddev, bio);
+	generic_make_request(bio);
 }
 
 static void raid0_status(struct seq_file *seq, struct mddev *mddev)

drivers/md/raid1.c

···
 					break;
 			}
 			continue;
-		} else
+		} else {
+			if ((sectors > best_good_sectors) && (best_disk >= 0))
+				best_disk = -1;
 			best_good_sectors = sectors;
+		}
 
 		if (best_disk >= 0)
 			/* At least two disks to choose from so failfast is OK */
···
 			plug = container_of(cb, struct raid1_plug_cb, cb);
 		else
 			plug = NULL;
-		spin_lock_irqsave(&conf->device_lock, flags);
 		if (plug) {
 			bio_list_add(&plug->pending, mbio);
 			plug->pending_cnt++;
 		} else {
+			spin_lock_irqsave(&conf->device_lock, flags);
 			bio_list_add(&conf->pending_bio_list, mbio);
 			conf->pending_count++;
-		}
-		spin_unlock_irqrestore(&conf->device_lock, flags);
-		if (!plug)
+			spin_unlock_irqrestore(&conf->device_lock, flags);
 			md_wakeup_thread(mddev->thread);
+		}
 	}
 
 	r1_bio_write_done(r1_bio);
···
 	struct r1conf *conf = mddev->private;
 	int cnt, raid_disks;
 	unsigned long flags;
-	int d, d2, err;
+	int d, d2;
 
 	/* Cannot change chunk_size, layout, or level */
 	if (mddev->chunk_sectors != mddev->new_chunk_sectors ||
···
 		return -EINVAL;
 	}
 
-	if (!mddev_is_clustered(mddev)) {
-		err = md_allow_write(mddev);
-		if (err)
-			return err;
-	}
+	if (!mddev_is_clustered(mddev))
+		md_allow_write(mddev);
 
 	raid_disks = mddev->raid_disks + mddev->delta_disks;
 

drivers/md/raid10.c

···
 		plug = container_of(cb, struct raid10_plug_cb, cb);
 	else
 		plug = NULL;
-	spin_lock_irqsave(&conf->device_lock, flags);
 	if (plug) {
 		bio_list_add(&plug->pending, mbio);
 		plug->pending_cnt++;
 	} else {
+		spin_lock_irqsave(&conf->device_lock, flags);
 		bio_list_add(&conf->pending_bio_list, mbio);
 		conf->pending_count++;
-	}
-	spin_unlock_irqrestore(&conf->device_lock, flags);
-	if (!plug)
+		spin_unlock_irqrestore(&conf->device_lock, flags);
 		md_wakeup_thread(mddev->thread);
+	}
 }
 
 static void raid10_write_request(struct mddev *mddev, struct bio *bio,

drivers/md/raid5-cache.c

···
 #include "md.h"
 #include "raid5.h"
 #include "bitmap.h"
+#include "raid5-log.h"
 
 /*
  * metadata/data stored in disk with 4k size unit (a block) regardless
···
 	__r5l_set_io_unit_state(io, IO_UNIT_IO_START);
 	spin_unlock_irqrestore(&log->io_list_lock, flags);
 
+	/*
+	 * In case of journal device failures, submit_bio will get error
+	 * and calls endio, then active stripes will continue write
+	 * process. Therefore, it is not necessary to check Faulty bit
+	 * of journal device here.
+	 *
+	 * We can't check split_bio after current_bio is submitted. If
+	 * io->split_bio is null, after current_bio is submitted, current_bio
+	 * might already be completed and the io_unit is freed. We submit
+	 * split_bio first to avoid the issue.
+	 */
+	if (io->split_bio) {
+		if (io->has_flush)
+			io->split_bio->bi_opf |= REQ_PREFLUSH;
+		if (io->has_fua)
+			io->split_bio->bi_opf |= REQ_FUA;
+		submit_bio(io->split_bio);
+	}
+
 	if (io->has_flush)
 		io->current_bio->bi_opf |= REQ_PREFLUSH;
 	if (io->has_fua)
 		io->current_bio->bi_opf |= REQ_FUA;
 	submit_bio(io->current_bio);
-
-	if (!io->split_bio)
-		return;
-
-	if (io->has_flush)
-		io->split_bio->bi_opf |= REQ_PREFLUSH;
-	if (io->has_fua)
-		io->split_bio->bi_opf |= REQ_FUA;
-	submit_bio(io->split_bio);
 }
 
 /* deferred io_unit will be dispatched here */
···
 		return;
 	pr_info("md/raid:%s: Disabling writeback cache for degraded array.\n",
 		mdname(mddev));
+
+	/* wait superblock change before suspend */
+	wait_event(mddev->sb_wait,
+		   !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags));
+
 	mddev_suspend(mddev);
 	log->r5c_journal_mode = R5C_JOURNAL_MODE_WRITE_THROUGH;
 	mddev_resume(mddev);
···
 	 * When run in degraded mode, array is set to write-through mode.
 	 * This check helps drain pending write safely in the transition to
 	 * write-through mode.
+	 *
+	 * When a stripe is syncing, the write is also handled in write
+	 * through mode.
 	 */
-	if (s->failed) {
+	if (s->failed || test_bit(STRIPE_SYNCING, &sh->state)) {
 		r5c_make_stripe_write_out(sh);
 		return -EAGAIN;
 	}
···
 	}
 
 	r5l_append_flush_payload(log, sh->sector);
+	/* stripe is flused to raid disks, we can do resync now */
+	if (test_bit(STRIPE_SYNC_REQUESTED, &sh->state))
+		set_bit(STRIPE_HANDLE, &sh->state);
 }
 
 int r5c_cache_data(struct r5l_log *log, struct stripe_head *sh)
···
 	return ret;
 }
 
-void r5c_update_on_rdev_error(struct mddev *mddev)
+void r5c_update_on_rdev_error(struct mddev *mddev, struct md_rdev *rdev)
 {
 	struct r5conf *conf = mddev->private;
 	struct r5l_log *log = conf->log;
···
 	if (!log)
 		return;
 
-	if (raid5_calc_degraded(conf) > 0 &&
+	if ((raid5_calc_degraded(conf) > 0 ||
+	     test_bit(Journal, &rdev->flags)) &&
 	    conf->log->r5c_journal_mode == R5C_JOURNAL_MODE_WRITE_BACK)
 		schedule_work(&log->disable_writeback_work);
 }

drivers/md/raid5-log.h

···
 extern void r5c_check_stripe_cache_usage(struct r5conf *conf);
 extern void r5c_check_cached_full_stripe(struct r5conf *conf);
 extern struct md_sysfs_entry r5c_journal_mode;
-extern void r5c_update_on_rdev_error(struct mddev *mddev);
+extern void r5c_update_on_rdev_error(struct mddev *mddev,
+				     struct md_rdev *rdev);
 extern bool r5c_big_stripe_cached(struct r5conf *conf, sector_t sect);
 
 extern struct dma_async_tx_descriptor *

drivers/md/raid5.c

···
 static inline void lock_all_device_hash_locks_irq(struct r5conf *conf)
 {
 	int i;
-	local_irq_disable();
-	spin_lock(conf->hash_locks);
+	spin_lock_irq(conf->hash_locks);
 	for (i = 1; i < NR_STRIPE_HASH_LOCKS; i++)
 		spin_lock_nest_lock(conf->hash_locks + i, conf->hash_locks);
 	spin_lock(&conf->device_lock);
···
 {
 	int i;
 	spin_unlock(&conf->device_lock);
-	for (i = NR_STRIPE_HASH_LOCKS; i; i--)
-		spin_unlock(conf->hash_locks + i - 1);
-	local_irq_enable();
+	for (i = NR_STRIPE_HASH_LOCKS - 1; i; i--)
+		spin_unlock(conf->hash_locks + i);
+	spin_unlock_irq(conf->hash_locks);
 }
 
 /* Find first data disk in a raid6 stripe */
···
 			if (test_bit(R5_InJournal, &sh->dev[i].flags))
 				injournal++;
 	/*
-	 * When quiesce in r5c write back, set STRIPE_HANDLE for stripes with
-	 * data in journal, so they are not released to cached lists
+	 * In the following cases, the stripe cannot be released to cached
+	 * lists. Therefore, we make the stripe write out and set
+	 * STRIPE_HANDLE:
+	 *   1. when quiesce in r5c write back;
+	 *   2. when resync is requested fot the stripe.
 	 */
-	if (conf->quiesce && r5c_is_writeback(conf->log) &&
-	    !test_bit(STRIPE_HANDLE, &sh->state) && injournal != 0) {
+	if (test_bit(STRIPE_SYNC_REQUESTED, &sh->state) ||
+	    (conf->quiesce && r5c_is_writeback(conf->log) &&
+	     !test_bit(STRIPE_HANDLE, &sh->state) && injournal != 0)) {
 		if (test_bit(STRIPE_R5C_CACHING, &sh->state))
 			r5c_make_stripe_write_out(sh);
 		set_bit(STRIPE_HANDLE, &sh->state);
···
 
 static void lock_two_stripes(struct stripe_head *sh1, struct stripe_head *sh2)
 {
-	local_irq_disable();
 	if (sh1 > sh2) {
-		spin_lock(&sh2->stripe_lock);
+		spin_lock_irq(&sh2->stripe_lock);
 		spin_lock_nested(&sh1->stripe_lock, 1);
 	} else {
-		spin_lock(&sh1->stripe_lock);
+		spin_lock_irq(&sh1->stripe_lock);
 		spin_lock_nested(&sh2->stripe_lock, 1);
 	}
 }
···
 static void unlock_two_stripes(struct stripe_head *sh1, struct stripe_head *sh2)
 {
 	spin_unlock(&sh1->stripe_lock);
-	spin_unlock(&sh2->stripe_lock);
-	local_irq_enable();
+	spin_unlock_irq(&sh2->stripe_lock);
 }
 
 /* Only freshly new full stripe normal write stripe can be added to a batch list */
···
 	struct stripe_head *osh, *nsh;
 	LIST_HEAD(newstripes);
 	struct disk_info *ndisks;
-	int err;
+	int err = 0;
 	struct kmem_cache *sc;
 	int i;
 	int hash, cnt;
 
-	err = md_allow_write(conf->mddev);
-	if (err)
-		return err;
+	md_allow_write(conf->mddev);
 
 	/* Step 1 */
 	sc = kmem_cache_create(conf->cache_name[1-conf->active_name],
···
 		bdevname(rdev->bdev, b),
 		mdname(mddev),
 		conf->raid_disks - mddev->degraded);
-	r5c_update_on_rdev_error(mddev);
+	r5c_update_on_rdev_error(mddev, rdev);
 }
 
 /*
···
  *      When LOG_CRITICAL, stripes with injournal == 0 will be sent to
  *      no_space_stripes list.
  *
+ *   3. during journal failure
+ *      In journal failure, we try to flush all cached data to raid disks
+ *      based on data in stripe cache. The array is read-only to upper
+ *      layers, so we would skip all pending writes.
+ *
  */
 static inline bool delay_towrite(struct r5conf *conf,
 				 struct r5dev *dev,
···
 	/* case 2 above */
 	if (test_bit(R5C_LOG_CRITICAL, &conf->cache_state) &&
 	    s->injournal > 0)
+		return true;
+	/* case 3 above */
+	if (s->log_failed && s->injournal)
 		return true;
 	return false;
 }
···
 
 	if (test_bit(STRIPE_SYNC_REQUESTED, &sh->state) && !sh->batch_head) {
 		spin_lock(&sh->stripe_lock);
-		/* Cannot process 'sync' concurrently with 'discard' */
-		if (!test_bit(STRIPE_DISCARD, &sh->state) &&
+		/*
+		 * Cannot process 'sync' concurrently with 'discard'.
+		 * Flush data in r5cache before 'sync'.
+		 */
+		if (!test_bit(STRIPE_R5C_PARTIAL_STRIPE, &sh->state) &&
+		    !test_bit(STRIPE_R5C_FULL_STRIPE, &sh->state) &&
+		    !test_bit(STRIPE_DISCARD, &sh->state) &&
 		    test_and_clear_bit(STRIPE_SYNC_REQUESTED, &sh->state)) {
 			set_bit(STRIPE_SYNCING, &sh->state);
 			clear_bit(STRIPE_INSYNC, &sh->state);
···
 	       " to_write=%d failed=%d failed_num=%d,%d\n",
 	       s.locked, s.uptodate, s.to_read, s.to_write, s.failed,
 	       s.failed_num[0], s.failed_num[1]);
-	/* check if the array has lost more than max_degraded devices and,
+	/*
+	 * check if the array has lost more than max_degraded devices and,
 	 * if so, some requests might need to be failed.
+	 *
+	 * When journal device failed (log_failed), we will only process
+	 * the stripe if there is data need write to raid disks
 	 */
-	if (s.failed > conf->max_degraded || s.log_failed) {
+	if (s.failed > conf->max_degraded ||
+	    (s.log_failed && s.injournal == 0)) {
 		sh->check_state = 0;
 		sh->reconstruct_state = 0;
 		break_stripe_batch_list(sh, 0);
···
 	struct stripe_head *sh, *tmp;
 	struct list_head *handle_list = NULL;
 	struct r5worker_group *wg;
-	bool second_try = !r5c_is_writeback(conf->log);
-	bool try_loprio = test_bit(R5C_LOG_TIGHT, &conf->cache_state);
+	bool second_try = !r5c_is_writeback(conf->log) &&
+		!r5l_log_disk_error(conf);
+	bool try_loprio = test_bit(R5C_LOG_TIGHT, &conf->cache_state) ||
+		r5l_log_disk_error(conf);
 
 again:
 	wg = NULL;
···
 raid5_set_cache_size(struct mddev *mddev, int size)
 {
 	struct r5conf *conf = mddev->private;
-	int err;
 
 	if (size <= 16 || size > 32768)
 		return -EINVAL;
···
 		;
 	mutex_unlock(&conf->cache_size_mutex);
 
-
-	err = md_allow_write(mddev);
-	if (err)
-		return err;
+	md_allow_write(mddev);
 
 	mutex_lock(&conf->cache_size_mutex);
 	while (size > conf->max_nr_stripes)
···
 		 * neilb: there is no locking about new writes here,
 		 * so this cannot be safe.
 		 */
-		if (atomic_read(&conf->active_stripes)) {
+		if (atomic_read(&conf->active_stripes) ||
+		    atomic_read(&conf->r5c_cached_full_stripes) ||
+		    atomic_read(&conf->r5c_cached_partial_stripes)) {
 			return -EBUSY;
 		}
 		log_exit(conf);