1 files changed, 77 insertions, 47 deletions

diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 2e38cfac5b1d..62c965be97e1 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -103,8 +103,7 @@ static inline void unlock_device_hash_lock(struct r5conf *conf, int hash)
 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);
@@ -114,9 +113,9 @@ static inline void unlock_all_device_hash_locks_irq(struct r5conf *conf)
 {
 	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 */
@@ -234,11 +233,15 @@ static void do_release_stripe(struct r5conf *conf, struct stripe_head *sh,
 			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);
@@ -714,12 +717,11 @@ static bool is_full_stripe_write(struct stripe_head *sh)
 
 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);
 	}
 }
@@ -727,8 +729,7 @@ static void lock_two_stripes(struct stripe_head *sh1, struct stripe_head *sh2)
 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 */
@@ -2312,14 +2313,12 @@ static int resize_stripes(struct r5conf *conf, int newsize)
 	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],
@@ -2477,7 +2476,7 @@ static void raid5_end_read_request(struct bio * bi)
 
 	pr_debug("end_read_request %llu/%d, count: %d, error %d.\n",
 		(unsigned long long)sh->sector, i, atomic_read(&sh->count),
-		bi->bi_error);
+		bi->bi_status);
 	if (i == disks) {
 		bio_reset(bi);
 		BUG();
@@ -2497,7 +2496,7 @@ static void raid5_end_read_request(struct bio * bi)
 		s = sh->sector + rdev->new_data_offset;
 	else
 		s = sh->sector + rdev->data_offset;
-	if (!bi->bi_error) {
+	if (!bi->bi_status) {
 		set_bit(R5_UPTODATE, &sh->dev[i].flags);
 		if (test_bit(R5_ReadError, &sh->dev[i].flags)) {
 			/* Note that this cannot happen on a
@@ -2614,7 +2613,7 @@ static void raid5_end_write_request(struct bio *bi)
 	}
 	pr_debug("end_write_request %llu/%d, count %d, error: %d.\n",
 		(unsigned long long)sh->sector, i, atomic_read(&sh->count),
-		bi->bi_error);
+		bi->bi_status);
 	if (i == disks) {
 		bio_reset(bi);
 		BUG();
@@ -2622,14 +2621,14 @@ static void raid5_end_write_request(struct bio *bi)
 	}
 
 	if (replacement) {
-		if (bi->bi_error)
+		if (bi->bi_status)
 			md_error(conf->mddev, rdev);
 		else if (is_badblock(rdev, sh->sector,
 				     STRIPE_SECTORS,
 				     &first_bad, &bad_sectors))
 			set_bit(R5_MadeGoodRepl, &sh->dev[i].flags);
 	} else {
-		if (bi->bi_error) {
+		if (bi->bi_status) {
 			set_bit(STRIPE_DEGRADED, &sh->state);
 			set_bit(WriteErrorSeen, &rdev->flags);
 			set_bit(R5_WriteError, &sh->dev[i].flags);
@@ -2650,7 +2649,7 @@ static void raid5_end_write_request(struct bio *bi)
 	}
 	rdev_dec_pending(rdev, conf->mddev);
 
-	if (sh->batch_head && bi->bi_error && !replacement)
+	if (sh->batch_head && bi->bi_status && !replacement)
 		set_bit(STRIPE_BATCH_ERR, &sh->batch_head->state);
 
 	bio_reset(bi);
@@ -2694,7 +2693,7 @@ static void raid5_error(struct mddev *mddev, struct md_rdev *rdev)
 		bdevname(rdev->bdev, b),
 		mdname(mddev),
 		conf->raid_disks - mddev->degraded);
-	r5c_update_on_rdev_error(mddev);
+	r5c_update_on_rdev_error(mddev, rdev);
 }
 
 /*
@@ -3055,6 +3054,11 @@ sector_t raid5_compute_blocknr(struct stripe_head *sh, int i, int previous)
  *      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,
@@ -3068,6 +3072,9 @@ static inline bool delay_towrite(struct r5conf *conf,
 	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;
 }
 
@@ -3374,7 +3381,7 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
 			sh->dev[i].sector + STRIPE_SECTORS) {
 			struct bio *nextbi = r5_next_bio(bi, sh->dev[i].sector);
 
-			bi->bi_error = -EIO;
+			bi->bi_status = BLK_STS_IOERR;
 			md_write_end(conf->mddev);
 			bio_endio(bi);
 			bi = nextbi;
@@ -3396,7 +3403,7 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
 		       sh->dev[i].sector + STRIPE_SECTORS) {
 			struct bio *bi2 = r5_next_bio(bi, sh->dev[i].sector);
 
-			bi->bi_error = -EIO;
+			bi->bi_status = BLK_STS_IOERR;
 			md_write_end(conf->mddev);
 			bio_endio(bi);
 			bi = bi2;
@@ -3422,7 +3429,7 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
 				struct bio *nextbi =
 					r5_next_bio(bi, sh->dev[i].sector);
 
-				bi->bi_error = -EIO;
+				bi->bi_status = BLK_STS_IOERR;
 				bio_endio(bi);
 				bi = nextbi;
 			}
@@ -4078,10 +4085,15 @@ static void handle_parity_checks5(struct r5conf *conf, struct stripe_head *sh,
 			set_bit(STRIPE_INSYNC, &sh->state);
 		else {
 			atomic64_add(STRIPE_SECTORS, &conf->mddev->resync_mismatches);
-			if (test_bit(MD_RECOVERY_CHECK, &conf->mddev->recovery))
+			if (test_bit(MD_RECOVERY_CHECK, &conf->mddev->recovery)) {
 				/* don't try to repair!! */
 				set_bit(STRIPE_INSYNC, &sh->state);
-			else {
+				pr_warn_ratelimited("%s: mismatch sector in range "
+						    "%llu-%llu\n", mdname(conf->mddev),
+						    (unsigned long long) sh->sector,
+						    (unsigned long long) sh->sector +
+						    STRIPE_SECTORS);
+			} else {
 				sh->check_state = check_state_compute_run;
 				set_bit(STRIPE_COMPUTE_RUN, &sh->state);
 				set_bit(STRIPE_OP_COMPUTE_BLK, &s->ops_request);
@@ -4230,10 +4242,15 @@ static void handle_parity_checks6(struct r5conf *conf, struct stripe_head *sh,
 			}
 		} else {
 			atomic64_add(STRIPE_SECTORS, &conf->mddev->resync_mismatches);
-			if (test_bit(MD_RECOVERY_CHECK, &conf->mddev->recovery))
+			if (test_bit(MD_RECOVERY_CHECK, &conf->mddev->recovery)) {
 				/* don't try to repair!! */
 				set_bit(STRIPE_INSYNC, &sh->state);
-			else {
+				pr_warn_ratelimited("%s: mismatch sector in range "
+						    "%llu-%llu\n", mdname(conf->mddev),
+						    (unsigned long long) sh->sector,
+						    (unsigned long long) sh->sector +
+						    STRIPE_SECTORS);
+			} else {
 				int *target = &sh->ops.target;
 
 				sh->ops.target = -1;
@@ -4653,8 +4670,13 @@ static void handle_stripe(struct stripe_head *sh)
 
 	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);
@@ -4701,10 +4723,15 @@ static void handle_stripe(struct stripe_head *sh)
 	       " 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);
@@ -5127,7 +5154,7 @@ static void raid5_align_endio(struct bio *bi)
 	struct mddev *mddev;
 	struct r5conf *conf;
 	struct md_rdev *rdev;
-	int error = bi->bi_error;
+	blk_status_t error = bi->bi_status;
 
 	bio_put(bi);
 
@@ -5277,8 +5304,10 @@ static struct stripe_head *__get_priority_stripe(struct r5conf *conf, int group)
 	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;
@@ -5702,7 +5731,7 @@ static void raid5_make_request(struct mddev *mddev, struct bio * bi)
 			release_stripe_plug(mddev, sh);
 		} else {
 			/* cannot get stripe for read-ahead, just give-up */
-			bi->bi_error = -EIO;
+			bi->bi_status = BLK_STS_IOERR;
 			break;
 		}
 	}
@@ -6313,7 +6342,6 @@ int
 raid5_set_cache_size(struct mddev *mddev, int size)
 {
 	struct r5conf *conf = mddev->private;
-	int err;
 
 	if (size <= 16 || size > 32768)
 		return -EINVAL;
@@ -6325,10 +6353,7 @@ raid5_set_cache_size(struct mddev *mddev, int size)
 		;
 	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)
@@ -6918,7 +6943,7 @@ static struct r5conf *setup_conf(struct mddev *mddev)
 			goto abort;
 	}
 
-	conf->bio_split = bioset_create(BIO_POOL_SIZE, 0);
+	conf->bio_split = bioset_create(BIO_POOL_SIZE, 0, 0);
 	if (!conf->bio_split)
 		goto abort;
 	conf->mddev = mddev;
@@ -7093,6 +7118,9 @@ static int raid5_run(struct mddev *mddev)
 	long long min_offset_diff = 0;
 	int first = 1;
 
+	if (mddev_init_writes_pending(mddev) < 0)
+		return -ENOMEM;
+
 	if (mddev->recovery_cp != MaxSector)
 		pr_notice("md/raid:%s: not clean -- starting background reconstruction\n",
 			  mdname(mddev));
@@ -7530,7 +7558,9 @@ static int raid5_remove_disk(struct mddev *mddev, struct md_rdev *rdev)
 		 * 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);