1 files changed, 90 insertions, 49 deletions

diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 6953d78297b0..ee7fc3701700 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -659,6 +659,7 @@ raid5_get_active_stripe(struct r5conf *conf, sector_t sector,
 {
 	struct stripe_head *sh;
 	int hash = stripe_hash_locks_hash(sector);
+	int inc_empty_inactive_list_flag;
 
 	pr_debug("get_stripe, sector %llu\n", (unsigned long long)sector);
 
@@ -703,7 +704,12 @@ raid5_get_active_stripe(struct r5conf *conf, sector_t sector,
 					atomic_inc(&conf->active_stripes);
 				BUG_ON(list_empty(&sh->lru) &&
 				       !test_bit(STRIPE_EXPANDING, &sh->state));
+				inc_empty_inactive_list_flag = 0;
+				if (!list_empty(conf->inactive_list + hash))
+					inc_empty_inactive_list_flag = 1;
 				list_del_init(&sh->lru);
+				if (list_empty(conf->inactive_list + hash) && inc_empty_inactive_list_flag)
+					atomic_inc(&conf->empty_inactive_list_nr);
 				if (sh->group) {
 					sh->group->stripes_cnt--;
 					sh->group = NULL;
@@ -762,6 +768,7 @@ static void stripe_add_to_batch_list(struct r5conf *conf, struct stripe_head *sh
 	sector_t head_sector, tmp_sec;
 	int hash;
 	int dd_idx;
+	int inc_empty_inactive_list_flag;
 
 	/* Don't cross chunks, so stripe pd_idx/qd_idx is the same */
 	tmp_sec = sh->sector;
@@ -779,7 +786,12 @@ static void stripe_add_to_batch_list(struct r5conf *conf, struct stripe_head *sh
 				atomic_inc(&conf->active_stripes);
 			BUG_ON(list_empty(&head->lru) &&
 			       !test_bit(STRIPE_EXPANDING, &head->state));
+			inc_empty_inactive_list_flag = 0;
+			if (!list_empty(conf->inactive_list + hash))
+				inc_empty_inactive_list_flag = 1;
 			list_del_init(&head->lru);
+			if (list_empty(conf->inactive_list + hash) && inc_empty_inactive_list_flag)
+				atomic_inc(&conf->empty_inactive_list_nr);
 			if (head->group) {
 				head->group->stripes_cnt--;
 				head->group = NULL;
@@ -806,7 +818,7 @@ static void stripe_add_to_batch_list(struct r5conf *conf, struct stripe_head *sh
 	dd_idx = 0;
 	while (dd_idx == sh->pd_idx || dd_idx == sh->qd_idx)
 		dd_idx++;
-	if (head->dev[dd_idx].towrite->bi_rw != sh->dev[dd_idx].towrite->bi_rw ||
+	if (head->dev[dd_idx].towrite->bi_opf != sh->dev[dd_idx].towrite->bi_opf ||
 	    bio_op(head->dev[dd_idx].towrite) != bio_op(sh->dev[dd_idx].towrite))
 		goto unlock_out;
 
@@ -993,7 +1005,6 @@ again:
 
 			set_bit(STRIPE_IO_STARTED, &sh->state);
 
-			bio_reset(bi);
 			bi->bi_bdev = rdev->bdev;
 			bio_set_op_attrs(bi, op, op_flags);
 			bi->bi_end_io = op_is_write(op)
@@ -1003,7 +1014,7 @@ again:
 
 			pr_debug("%s: for %llu schedule op %d on disc %d\n",
 				__func__, (unsigned long long)sh->sector,
-				bi->bi_rw, i);
+				bi->bi_opf, i);
 			atomic_inc(&sh->count);
 			if (sh != head_sh)
 				atomic_inc(&head_sh->count);
@@ -1014,7 +1025,7 @@ again:
 				bi->bi_iter.bi_sector = (sh->sector
 						 + rdev->data_offset);
 			if (test_bit(R5_ReadNoMerge, &head_sh->dev[i].flags))
-				bi->bi_rw |= REQ_NOMERGE;
+				bi->bi_opf |= REQ_NOMERGE;
 
 			if (test_bit(R5_SkipCopy, &sh->dev[i].flags))
 				WARN_ON(test_bit(R5_UPTODATE, &sh->dev[i].flags));
@@ -1045,7 +1056,6 @@ again:
 
 			set_bit(STRIPE_IO_STARTED, &sh->state);
 
-			bio_reset(rbi);
 			rbi->bi_bdev = rrdev->bdev;
 			bio_set_op_attrs(rbi, op, op_flags);
 			BUG_ON(!op_is_write(op));
@@ -1055,7 +1065,7 @@ again:
 			pr_debug("%s: for %llu schedule op %d on "
 				 "replacement disc %d\n",
 				__func__, (unsigned long long)sh->sector,
-				rbi->bi_rw, i);
+				rbi->bi_opf, i);
 			atomic_inc(&sh->count);
 			if (sh != head_sh)
 				atomic_inc(&head_sh->count);
@@ -1088,7 +1098,7 @@ again:
 			if (op_is_write(op))
 				set_bit(STRIPE_DEGRADED, &sh->state);
 			pr_debug("skip op %d on disc %d for sector %llu\n",
-				bi->bi_rw, i, (unsigned long long)sh->sector);
+				bi->bi_opf, i, (unsigned long long)sh->sector);
 			clear_bit(R5_LOCKED, &sh->dev[i].flags);
 			set_bit(STRIPE_HANDLE, &sh->state);
 		}
@@ -1619,9 +1629,9 @@ again:
 
 			while (wbi && wbi->bi_iter.bi_sector <
 				dev->sector + STRIPE_SECTORS) {
-				if (wbi->bi_rw & REQ_FUA)
+				if (wbi->bi_opf & REQ_FUA)
 					set_bit(R5_WantFUA, &dev->flags);
-				if (wbi->bi_rw & REQ_SYNC)
+				if (wbi->bi_opf & REQ_SYNC)
 					set_bit(R5_SyncIO, &dev->flags);
 				if (bio_op(wbi) == REQ_OP_DISCARD)
 					set_bit(R5_Discard, &dev->flags);
@@ -1978,9 +1988,11 @@ static void raid_run_ops(struct stripe_head *sh, unsigned long ops_request)
 	put_cpu();
 }
 
-static struct stripe_head *alloc_stripe(struct kmem_cache *sc, gfp_t gfp)
+static struct stripe_head *alloc_stripe(struct kmem_cache *sc, gfp_t gfp,
+	int disks)
 {
 	struct stripe_head *sh;
+	int i;
 
 	sh = kmem_cache_zalloc(sc, gfp);
 	if (sh) {
@@ -1989,6 +2001,17 @@ static struct stripe_head *alloc_stripe(struct kmem_cache *sc, gfp_t gfp)
 		INIT_LIST_HEAD(&sh->batch_list);
 		INIT_LIST_HEAD(&sh->lru);
 		atomic_set(&sh->count, 1);
+		for (i = 0; i < disks; i++) {
+			struct r5dev *dev = &sh->dev[i];
+
+			bio_init(&dev->req);
+			dev->req.bi_io_vec = &dev->vec;
+			dev->req.bi_max_vecs = 1;
+
+			bio_init(&dev->rreq);
+			dev->rreq.bi_io_vec = &dev->rvec;
+			dev->rreq.bi_max_vecs = 1;
+		}
 	}
 	return sh;
 }
@@ -1996,7 +2019,7 @@ static int grow_one_stripe(struct r5conf *conf, gfp_t gfp)
 {
 	struct stripe_head *sh;
 
-	sh = alloc_stripe(conf->slab_cache, gfp);
+	sh = alloc_stripe(conf->slab_cache, gfp, conf->pool_size);
 	if (!sh)
 		return 0;
 
@@ -2167,7 +2190,7 @@ static int resize_stripes(struct r5conf *conf, int newsize)
 	mutex_lock(&conf->cache_size_mutex);
 
 	for (i = conf->max_nr_stripes; i; i--) {
-		nsh = alloc_stripe(sc, GFP_KERNEL);
+		nsh = alloc_stripe(sc, GFP_KERNEL, newsize);
 		if (!nsh)
 			break;
 
@@ -2299,6 +2322,7 @@ static void raid5_end_read_request(struct bio * bi)
 		(unsigned long long)sh->sector, i, atomic_read(&sh->count),
 		bi->bi_error);
 	if (i == disks) {
+		bio_reset(bi);
 		BUG();
 		return;
 	}
@@ -2399,6 +2423,7 @@ static void raid5_end_read_request(struct bio * bi)
 		}
 	}
 	rdev_dec_pending(rdev, conf->mddev);
+	bio_reset(bi);
 	clear_bit(R5_LOCKED, &sh->dev[i].flags);
 	set_bit(STRIPE_HANDLE, &sh->state);
 	raid5_release_stripe(sh);
@@ -2436,6 +2461,7 @@ static void raid5_end_write_request(struct bio *bi)
 		(unsigned long long)sh->sector, i, atomic_read(&sh->count),
 		bi->bi_error);
 	if (i == disks) {
+		bio_reset(bi);
 		BUG();
 		return;
 	}
@@ -2472,6 +2498,7 @@ static void raid5_end_write_request(struct bio *bi)
 	if (sh->batch_head && bi->bi_error && !replacement)
 		set_bit(STRIPE_BATCH_ERR, &sh->batch_head->state);
 
+	bio_reset(bi);
 	if (!test_and_clear_bit(R5_DOUBLE_LOCKED, &sh->dev[i].flags))
 		clear_bit(R5_LOCKED, &sh->dev[i].flags);
 	set_bit(STRIPE_HANDLE, &sh->state);
@@ -2485,16 +2512,6 @@ static void raid5_build_block(struct stripe_head *sh, int i, int previous)
 {
 	struct r5dev *dev = &sh->dev[i];
 
-	bio_init(&dev->req);
-	dev->req.bi_io_vec = &dev->vec;
-	dev->req.bi_max_vecs = 1;
-	dev->req.bi_private = sh;
-
-	bio_init(&dev->rreq);
-	dev->rreq.bi_io_vec = &dev->rvec;
-	dev->rreq.bi_max_vecs = 1;
-	dev->rreq.bi_private = sh;
-
 	dev->flags = 0;
 	dev->sector = raid5_compute_blocknr(sh, i, previous);
 }
@@ -3080,7 +3097,8 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
 			struct md_rdev *rdev;
 			rcu_read_lock();
 			rdev = rcu_dereference(conf->disks[i].rdev);
-			if (rdev && test_bit(In_sync, &rdev->flags))
+			if (rdev && test_bit(In_sync, &rdev->flags) &&
+			    !test_bit(Faulty, &rdev->flags))
 				atomic_inc(&rdev->nr_pending);
 			else
 				rdev = NULL;
@@ -3210,15 +3228,16 @@ handle_failed_sync(struct r5conf *conf, struct stripe_head *sh,
 		/* During recovery devices cannot be removed, so
 		 * locking and refcounting of rdevs is not needed
 		 */
+		rcu_read_lock();
 		for (i = 0; i < conf->raid_disks; i++) {
-			struct md_rdev *rdev = conf->disks[i].rdev;
+			struct md_rdev *rdev = rcu_dereference(conf->disks[i].rdev);
 			if (rdev
 			    && !test_bit(Faulty, &rdev->flags)
 			    && !test_bit(In_sync, &rdev->flags)
 			    && !rdev_set_badblocks(rdev, sh->sector,
 						   STRIPE_SECTORS, 0))
 				abort = 1;
-			rdev = conf->disks[i].replacement;
+			rdev = rcu_dereference(conf->disks[i].replacement);
 			if (rdev
 			    && !test_bit(Faulty, &rdev->flags)
 			    && !test_bit(In_sync, &rdev->flags)
@@ -3226,6 +3245,7 @@ handle_failed_sync(struct r5conf *conf, struct stripe_head *sh,
 						   STRIPE_SECTORS, 0))
 				abort = 1;
 		}
+		rcu_read_unlock();
 		if (abort)
 			conf->recovery_disabled =
 				conf->mddev->recovery_disabled;
@@ -3237,15 +3257,16 @@ static int want_replace(struct stripe_head *sh, int disk_idx)
 {
 	struct md_rdev *rdev;
 	int rv = 0;
-	/* Doing recovery so rcu locking not required */
-	rdev = sh->raid_conf->disks[disk_idx].replacement;
+
+	rcu_read_lock();
+	rdev = rcu_dereference(sh->raid_conf->disks[disk_idx].replacement);
 	if (rdev
 	    && !test_bit(Faulty, &rdev->flags)
 	    && !test_bit(In_sync, &rdev->flags)
 	    && (rdev->recovery_offset <= sh->sector
 		|| rdev->mddev->recovery_cp <= sh->sector))
 		rv = 1;
-
+	rcu_read_unlock();
 	return rv;
 }
 
@@ -3600,7 +3621,7 @@ static void handle_stripe_dirtying(struct r5conf *conf,
 	pr_debug("for sector %llu, rmw=%d rcw=%d\n",
 		(unsigned long long)sh->sector, rmw, rcw);
 	set_bit(STRIPE_HANDLE, &sh->state);
-	if ((rmw < rcw || (rmw == rcw && conf->rmw_level == PARITY_ENABLE_RMW)) && rmw > 0) {
+	if ((rmw < rcw || (rmw == rcw && conf->rmw_level == PARITY_PREFER_RMW)) && rmw > 0) {
 		/* prefer read-modify-write, but need to get some data */
 		if (conf->mddev->queue)
 			blk_add_trace_msg(conf->mddev->queue,
@@ -3627,7 +3648,7 @@ static void handle_stripe_dirtying(struct r5conf *conf,
 			}
 		}
 	}
-	if ((rcw < rmw || (rcw == rmw && conf->rmw_level != PARITY_ENABLE_RMW)) && rcw > 0) {
+	if ((rcw < rmw || (rcw == rmw && conf->rmw_level != PARITY_PREFER_RMW)) && rcw > 0) {
 		/* want reconstruct write, but need to get some data */
 		int qread =0;
 		rcw = 0;
@@ -4624,7 +4645,9 @@ finish:
 	}
 
 	if (!bio_list_empty(&s.return_bi)) {
-		if (test_bit(MD_CHANGE_PENDING, &conf->mddev->flags)) {
+		if (test_bit(MD_CHANGE_PENDING, &conf->mddev->flags) &&
+				(s.failed <= conf->max_degraded ||
+					conf->mddev->external == 0)) {
 			spin_lock_irq(&conf->device_lock);
 			bio_list_merge(&conf->return_bi, &s.return_bi);
 			spin_unlock_irq(&conf->device_lock);
@@ -5150,7 +5173,7 @@ static void raid5_make_request(struct mddev *mddev, struct bio * bi)
 	DEFINE_WAIT(w);
 	bool do_prepare;
 
-	if (unlikely(bi->bi_rw & REQ_PREFLUSH)) {
+	if (unlikely(bi->bi_opf & REQ_PREFLUSH)) {
 		int ret = r5l_handle_flush_request(conf->log, bi);
 
 		if (ret == 0)
@@ -5233,7 +5256,7 @@ static void raid5_make_request(struct mddev *mddev, struct bio * bi)
 			(unsigned long long)logical_sector);
 
 		sh = raid5_get_active_stripe(conf, new_sector, previous,
-				       (bi->bi_rw & REQ_RAHEAD), 0);
+				       (bi->bi_opf & REQ_RAHEAD), 0);
 		if (sh) {
 			if (unlikely(previous)) {
 				/* expansion might have moved on while waiting for a
@@ -5301,7 +5324,7 @@ static void raid5_make_request(struct mddev *mddev, struct bio * bi)
 			set_bit(STRIPE_HANDLE, &sh->state);
 			clear_bit(STRIPE_DELAYED, &sh->state);
 			if ((!sh->batch_head || sh == sh->batch_head) &&
-			    (bi->bi_rw & REQ_SYNC) &&
+			    (bi->bi_opf & REQ_SYNC) &&
 			    !test_and_set_bit(STRIPE_PREREAD_ACTIVE, &sh->state))
 				atomic_inc(&conf->preread_active_stripes);
 			release_stripe_plug(mddev, sh);
@@ -6616,6 +6639,16 @@ static struct r5conf *setup_conf(struct mddev *mddev)
 	}
 
 	conf->min_nr_stripes = NR_STRIPES;
+	if (mddev->reshape_position != MaxSector) {
+		int stripes = max_t(int,
+			((mddev->chunk_sectors << 9) / STRIPE_SIZE) * 4,
+			((mddev->new_chunk_sectors << 9) / STRIPE_SIZE) * 4);
+		conf->min_nr_stripes = max(NR_STRIPES, stripes);
+		if (conf->min_nr_stripes != NR_STRIPES)
+			printk(KERN_INFO
+				"md/raid:%s: force stripe size %d for reshape\n",
+				mdname(mddev), conf->min_nr_stripes);
+	}
 	memory = conf->min_nr_stripes * (sizeof(struct stripe_head) +
 		 max_disks * ((sizeof(struct bio) + PAGE_SIZE))) / 1024;
 	atomic_set(&conf->empty_inactive_list_nr, NR_STRIPE_HASH_LOCKS);
@@ -6822,11 +6855,14 @@ static int raid5_run(struct mddev *mddev)
 	if (IS_ERR(conf))
 		return PTR_ERR(conf);
 
-	if (test_bit(MD_HAS_JOURNAL, &mddev->flags) && !journal_dev) {
-		printk(KERN_ERR "md/raid:%s: journal disk is missing, force array readonly\n",
-		       mdname(mddev));
-		mddev->ro = 1;
-		set_disk_ro(mddev->gendisk, 1);
+	if (test_bit(MD_HAS_JOURNAL, &mddev->flags)) {
+		if (!journal_dev) {
+			pr_err("md/raid:%s: journal disk is missing, force array readonly\n",
+			       mdname(mddev));
+			mddev->ro = 1;
+			set_disk_ro(mddev->gendisk, 1);
+		} else if (mddev->recovery_cp == MaxSector)
+			set_bit(MD_JOURNAL_CLEAN, &mddev->flags);
 	}
 
 	conf->min_offset_diff = min_offset_diff;
@@ -7066,10 +7102,12 @@ static void raid5_status(struct seq_file *seq, struct mddev *mddev)
 	seq_printf(seq, " level %d, %dk chunk, algorithm %d", mddev->level,
 		conf->chunk_sectors / 2, mddev->layout);
 	seq_printf (seq, " [%d/%d] [", conf->raid_disks, conf->raid_disks - mddev->degraded);
-	for (i = 0; i < conf->raid_disks; i++)
-		seq_printf (seq, "%s",
-			       conf->disks[i].rdev &&
-			       test_bit(In_sync, &conf->disks[i].rdev->flags) ? "U" : "_");
+	rcu_read_lock();
+	for (i = 0; i < conf->raid_disks; i++) {
+		struct md_rdev *rdev = rcu_dereference(conf->disks[i].rdev);
+		seq_printf (seq, "%s", rdev && test_bit(In_sync, &rdev->flags) ? "U" : "_");
+	}
+	rcu_read_unlock();
 	seq_printf (seq, "]");
 }
 
@@ -7191,12 +7229,15 @@ static int raid5_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;
-	} 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;
+		}
+	}
+	if (p->replacement) {
 		/* We must have just cleared 'rdev' */
 		p->rdev = p->replacement;
 		clear_bit(Replacement, &p->replacement->flags);