1 files changed, 125 insertions, 108 deletions

diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 4fcfcb350d2b..0578bcda7c6b 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -325,7 +325,7 @@ static void raid_end_bio_io(struct r10bio *r10_bio)
 	if (!test_bit(R10BIO_Uptodate, &r10_bio->state))
 		bio->bi_status = BLK_STS_IOERR;
 
-	if (blk_queue_io_stat(bio->bi_bdev->bd_disk->queue))
+	if (r10_bio->start_time)
 		bio_end_io_acct(bio, r10_bio->start_time);
 	bio_endio(bio);
 	/*
@@ -779,8 +779,16 @@ static struct md_rdev *read_balance(struct r10conf *conf,
 		disk = r10_bio->devs[slot].devnum;
 		rdev = rcu_dereference(conf->mirrors[disk].replacement);
 		if (rdev == NULL || test_bit(Faulty, &rdev->flags) ||
-		    r10_bio->devs[slot].addr + sectors > rdev->recovery_offset)
+		    r10_bio->devs[slot].addr + sectors >
+		    rdev->recovery_offset) {
+			/*
+			 * Read replacement first to prevent reading both rdev
+			 * and replacement as NULL during replacement replace
+			 * rdev.
+			 */
+			smp_mb();
 			rdev = rcu_dereference(conf->mirrors[disk].rdev);
+		}
 		if (rdev == NULL ||
 		    test_bit(Faulty, &rdev->flags))
 			continue;
@@ -902,25 +910,15 @@ static void flush_pending_writes(struct r10conf *conf)
 		__set_current_state(TASK_RUNNING);
 
 		blk_start_plug(&plug);
-		/* flush any pending bitmap writes to disk
-		 * before proceeding w/ I/O */
-		md_bitmap_unplug(conf->mddev->bitmap);
+		raid1_prepare_flush_writes(conf->mddev->bitmap);
 		wake_up(&conf->wait_barrier);
 
 		while (bio) { /* submit pending writes */
 			struct bio *next = bio->bi_next;
-			struct md_rdev *rdev = (void*)bio->bi_bdev;
-			bio->bi_next = NULL;
-			bio_set_dev(bio, rdev->bdev);
-			if (test_bit(Faulty, &rdev->flags)) {
-				bio_io_error(bio);
-			} else if (unlikely((bio_op(bio) ==  REQ_OP_DISCARD) &&
-					    !bdev_max_discard_sectors(bio->bi_bdev)))
-				/* Just ignore it */
-				bio_endio(bio);
-			else
-				submit_bio_noacct(bio);
+
+			raid1_submit_write(bio);
 			bio = next;
+			cond_resched();
 		}
 		blk_finish_plug(&plug);
 	} else
@@ -982,6 +980,7 @@ static void lower_barrier(struct r10conf *conf)
 static bool stop_waiting_barrier(struct r10conf *conf)
 {
 	struct bio_list *bio_list = current->bio_list;
+	struct md_thread *thread;
 
 	/* barrier is dropped */
 	if (!conf->barrier)
@@ -997,12 +996,14 @@ static bool stop_waiting_barrier(struct r10conf *conf)
 	    (!bio_list_empty(&bio_list[0]) || !bio_list_empty(&bio_list[1])))
 		return true;
 
+	/* daemon thread must exist while handling io */
+	thread = rcu_dereference_protected(conf->mddev->thread, true);
 	/*
 	 * move on if io is issued from raid10d(), nr_pending is not released
 	 * from original io(see handle_read_error()). All raise barrier is
 	 * blocked until this io is done.
 	 */
-	if (conf->mddev->thread->tsk == current) {
+	if (thread->tsk == current) {
 		WARN_ON_ONCE(atomic_read(&conf->nr_pending) == 0);
 		return true;
 	}
@@ -1113,11 +1114,11 @@ static void raid10_unplug(struct blk_plug_cb *cb, bool from_schedule)
 	struct r10conf *conf = mddev->private;
 	struct bio *bio;
 
-	if (from_schedule || current->bio_list) {
+	if (from_schedule) {
 		spin_lock_irq(&conf->device_lock);
 		bio_list_merge(&conf->pending_bio_list, &plug->pending);
 		spin_unlock_irq(&conf->device_lock);
-		wake_up(&conf->wait_barrier);
+		wake_up_barrier(conf);
 		md_wakeup_thread(mddev->thread);
 		kfree(plug);
 		return;
@@ -1125,23 +1126,15 @@ static void raid10_unplug(struct blk_plug_cb *cb, bool from_schedule)
 
 	/* we aren't scheduling, so we can do the write-out directly. */
 	bio = bio_list_get(&plug->pending);
-	md_bitmap_unplug(mddev->bitmap);
-	wake_up(&conf->wait_barrier);
+	raid1_prepare_flush_writes(mddev->bitmap);
+	wake_up_barrier(conf);
 
 	while (bio) { /* submit pending writes */
 		struct bio *next = bio->bi_next;
-		struct md_rdev *rdev = (void*)bio->bi_bdev;
-		bio->bi_next = NULL;
-		bio_set_dev(bio, rdev->bdev);
-		if (test_bit(Faulty, &rdev->flags)) {
-			bio_io_error(bio);
-		} else if (unlikely((bio_op(bio) ==  REQ_OP_DISCARD) &&
-				    !bdev_max_discard_sectors(bio->bi_bdev)))
-			/* Just ignore it */
-			bio_endio(bio);
-		else
-			submit_bio_noacct(bio);
+
+		raid1_submit_write(bio);
 		bio = next;
+		cond_resched();
 	}
 	kfree(plug);
 }
@@ -1282,8 +1275,6 @@ static void raid10_write_one_disk(struct mddev *mddev, struct r10bio *r10_bio,
 	const blk_opf_t do_sync = bio->bi_opf & REQ_SYNC;
 	const blk_opf_t do_fua = bio->bi_opf & REQ_FUA;
 	unsigned long flags;
-	struct blk_plug_cb *cb;
-	struct raid1_plug_cb *plug = NULL;
 	struct r10conf *conf = mddev->private;
 	struct md_rdev *rdev;
 	int devnum = r10_bio->devs[n_copy].devnum;
@@ -1323,14 +1314,7 @@ static void raid10_write_one_disk(struct mddev *mddev, struct r10bio *r10_bio,
 
 	atomic_inc(&r10_bio->remaining);
 
-	cb = blk_check_plugged(raid10_unplug, mddev, sizeof(*plug));
-	if (cb)
-		plug = container_of(cb, struct raid1_plug_cb, cb);
-	else
-		plug = NULL;
-	if (plug) {
-		bio_list_add(&plug->pending, mbio);
-	} else {
+	if (!raid1_add_bio_to_plug(mddev, mbio, raid10_unplug, conf->copies)) {
 		spin_lock_irqsave(&conf->device_lock, flags);
 		bio_list_add(&conf->pending_bio_list, mbio);
 		spin_unlock_irqrestore(&conf->device_lock, flags);
@@ -1338,6 +1322,25 @@ static void raid10_write_one_disk(struct mddev *mddev, struct r10bio *r10_bio,
 	}
 }
 
+static struct md_rdev *dereference_rdev_and_rrdev(struct raid10_info *mirror,
+						  struct md_rdev **prrdev)
+{
+	struct md_rdev *rdev, *rrdev;
+
+	rrdev = rcu_dereference(mirror->replacement);
+	/*
+	 * Read replacement first to prevent reading both rdev and
+	 * replacement as NULL during replacement replace rdev.
+	 */
+	smp_mb();
+	rdev = rcu_dereference(mirror->rdev);
+	if (rdev == rrdev)
+		rrdev = NULL;
+
+	*prrdev = rrdev;
+	return rdev;
+}
+
 static void wait_blocked_dev(struct mddev *mddev, struct r10bio *r10_bio)
 {
 	int i;
@@ -1348,11 +1351,9 @@ retry_wait:
 	blocked_rdev = NULL;
 	rcu_read_lock();
 	for (i = 0; i < conf->copies; i++) {
-		struct md_rdev *rdev = rcu_dereference(conf->mirrors[i].rdev);
-		struct md_rdev *rrdev = rcu_dereference(
-			conf->mirrors[i].replacement);
-		if (rdev == rrdev)
-			rrdev = NULL;
+		struct md_rdev *rdev, *rrdev;
+
+		rdev = dereference_rdev_and_rrdev(&conf->mirrors[i], &rrdev);
 		if (rdev && unlikely(test_bit(Blocked, &rdev->flags))) {
 			atomic_inc(&rdev->nr_pending);
 			blocked_rdev = rdev;
@@ -1479,11 +1480,9 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio,
 
 	for (i = 0;  i < conf->copies; i++) {
 		int d = r10_bio->devs[i].devnum;
-		struct md_rdev *rdev = rcu_dereference(conf->mirrors[d].rdev);
-		struct md_rdev *rrdev = rcu_dereference(
-			conf->mirrors[d].replacement);
-		if (rdev == rrdev)
-			rrdev = NULL;
+		struct md_rdev *rdev, *rrdev;
+
+		rdev = dereference_rdev_and_rrdev(&conf->mirrors[d], &rrdev);
 		if (rdev && (test_bit(Faulty, &rdev->flags)))
 			rdev = NULL;
 		if (rrdev && (test_bit(Faulty, &rrdev->flags)))
@@ -1790,10 +1789,9 @@ retry_discard:
 	 */
 	rcu_read_lock();
 	for (disk = 0; disk < geo->raid_disks; disk++) {
-		struct md_rdev *rdev = rcu_dereference(conf->mirrors[disk].rdev);
-		struct md_rdev *rrdev = rcu_dereference(
-			conf->mirrors[disk].replacement);
+		struct md_rdev *rdev, *rrdev;
 
+		rdev = dereference_rdev_and_rrdev(&conf->mirrors[disk], &rrdev);
 		r10_bio->devs[disk].bio = NULL;
 		r10_bio->devs[disk].repl_bio = NULL;
 
@@ -2148,9 +2146,10 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 {
 	struct r10conf *conf = mddev->private;
 	int err = -EEXIST;
-	int mirror;
+	int mirror, repl_slot = -1;
 	int first = 0;
 	int last = conf->geo.raid_disks - 1;
+	struct raid10_info *p;
 
 	if (mddev->recovery_cp < MaxSector)
 		/* only hot-add to in-sync arrays, as recovery is
@@ -2173,23 +2172,14 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 	else
 		mirror = first;
 	for ( ; mirror <= last ; mirror++) {
-		struct raid10_info *p = &conf->mirrors[mirror];
+		p = &conf->mirrors[mirror];
 		if (p->recovery_disabled == mddev->recovery_disabled)
 			continue;
 		if (p->rdev) {
-			if (!test_bit(WantReplacement, &p->rdev->flags) ||
-			    p->replacement != NULL)
-				continue;
-			clear_bit(In_sync, &rdev->flags);
-			set_bit(Replacement, &rdev->flags);
-			rdev->raid_disk = mirror;
-			err = 0;
-			if (mddev->gendisk)
-				disk_stack_limits(mddev->gendisk, rdev->bdev,
-						  rdev->data_offset << 9);
-			conf->fullsync = 1;
-			rcu_assign_pointer(p->replacement, rdev);
-			break;
+			if (test_bit(WantReplacement, &p->rdev->flags) &&
+			    p->replacement == NULL && repl_slot < 0)
+				repl_slot = mirror;
+			continue;
 		}
 
 		if (mddev->gendisk)
@@ -2206,6 +2196,19 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 		break;
 	}
 
+	if (err && repl_slot >= 0) {
+		p = &conf->mirrors[repl_slot];
+		clear_bit(In_sync, &rdev->flags);
+		set_bit(Replacement, &rdev->flags);
+		rdev->raid_disk = repl_slot;
+		err = 0;
+		if (mddev->gendisk)
+			disk_stack_limits(mddev->gendisk, rdev->bdev,
+					  rdev->data_offset << 9);
+		conf->fullsync = 1;
+		rcu_assign_pointer(p->replacement, rdev);
+	}
+
 	print_conf(conf);
 	return err;
 }
@@ -3303,6 +3306,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 	int chunks_skipped = 0;
 	sector_t chunk_mask = conf->geo.chunk_mask;
 	int page_idx = 0;
+	int error_disk = -1;
 
 	/*
 	 * Allow skipping a full rebuild for incremental assembly
@@ -3386,8 +3390,21 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 		return reshape_request(mddev, sector_nr, skipped);
 
 	if (chunks_skipped >= conf->geo.raid_disks) {
-		/* if there has been nothing to do on any drive,
-		 * then there is nothing to do at all..
+		pr_err("md/raid10:%s: %s fails\n", mdname(mddev),
+			test_bit(MD_RECOVERY_SYNC, &mddev->recovery) ?  "resync" : "recovery");
+		if (error_disk >= 0 &&
+		    !test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) {
+			/*
+			 * recovery fails, set mirrors.recovery_disabled,
+			 * device shouldn't be added to there.
+			 */
+			conf->mirrors[error_disk].recovery_disabled =
+						mddev->recovery_disabled;
+			return 0;
+		}
+		/*
+		 * if there has been nothing to do on any drive,
+		 * then there is nothing to do at all.
 		 */
 		*skipped = 1;
 		return (max_sector - sector_nr) + sectors_skipped;
@@ -3437,8 +3454,6 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 			sector_t sect;
 			int must_sync;
 			int any_working;
-			int need_recover = 0;
-			int need_replace = 0;
 			struct raid10_info *mirror = &conf->mirrors[i];
 			struct md_rdev *mrdev, *mreplace;
 
@@ -3446,15 +3461,13 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 			mrdev = rcu_dereference(mirror->rdev);
 			mreplace = rcu_dereference(mirror->replacement);
 
-			if (mrdev != NULL &&
-			    !test_bit(Faulty, &mrdev->flags) &&
-			    !test_bit(In_sync, &mrdev->flags))
-				need_recover = 1;
-			if (mreplace != NULL &&
-			    !test_bit(Faulty, &mreplace->flags))
-				need_replace = 1;
+			if (mrdev && (test_bit(Faulty, &mrdev->flags) ||
+			    test_bit(In_sync, &mrdev->flags)))
+				mrdev = NULL;
+			if (mreplace && test_bit(Faulty, &mreplace->flags))
+				mreplace = NULL;
 
-			if (!need_recover && !need_replace) {
+			if (!mrdev && !mreplace) {
 				rcu_read_unlock();
 				continue;
 			}
@@ -3470,8 +3483,6 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 				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
@@ -3490,7 +3501,8 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 				rcu_read_unlock();
 				continue;
 			}
-			atomic_inc(&mrdev->nr_pending);
+			if (mrdev)
+				atomic_inc(&mrdev->nr_pending);
 			if (mreplace)
 				atomic_inc(&mreplace->nr_pending);
 			rcu_read_unlock();
@@ -3577,7 +3589,7 @@ 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;
 
-				if (need_recover) {
+				if (mrdev) {
 					bio = r10_bio->devs[1].bio;
 					bio->bi_next = biolist;
 					biolist = bio;
@@ -3594,11 +3606,11 @@ 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;
-				/* Note: if need_replace, then bio
+				/* Note: if replace is not NULL, then bio
 				 * cannot be NULL as r10buf_pool_alloc will
 				 * have allocated it.
 				 */
-				if (!need_replace)
+				if (!mreplace)
 					break;
 				bio->bi_next = biolist;
 				biolist = bio;
@@ -3622,7 +3634,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 					for (k = 0; k < conf->copies; k++)
 						if (r10_bio->devs[k].devnum == i)
 							break;
-					if (!test_bit(In_sync,
+					if (mrdev && !test_bit(In_sync,
 						      &mrdev->flags)
 					    && !rdev_set_badblocks(
 						    mrdev,
@@ -3643,17 +3655,21 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 						       mdname(mddev));
 					mirror->recovery_disabled
 						= mddev->recovery_disabled;
+				} else {
+					error_disk = i;
 				}
 				put_buf(r10_bio);
 				if (rb2)
 					atomic_dec(&rb2->remaining);
 				r10_bio = rb2;
-				rdev_dec_pending(mrdev, mddev);
+				if (mrdev)
+					rdev_dec_pending(mrdev, mddev);
 				if (mreplace)
 					rdev_dec_pending(mreplace, mddev);
 				break;
 			}
-			rdev_dec_pending(mrdev, mddev);
+			if (mrdev)
+				rdev_dec_pending(mrdev, mddev);
 			if (mreplace)
 				rdev_dec_pending(mreplace, mddev);
 			if (r10_bio->devs[0].bio->bi_opf & MD_FAILFAST) {
@@ -3819,11 +3835,11 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 		for (bio= biolist ; bio ; bio=bio->bi_next) {
 			struct resync_pages *rp = get_resync_pages(bio);
 			page = resync_fetch_page(rp, page_idx);
-			/*
-			 * won't fail because the vec table is big enough
-			 * to hold all these pages
-			 */
-			bio_add_page(bio, page, len, 0);
+			if (WARN_ON(!bio_add_page(bio, page, len, 0))) {
+				bio->bi_status = BLK_STS_RESOURCE;
+				bio_endio(bio);
+				goto giveup;
+			}
 		}
 		nr_sectors += len>>9;
 		sector_nr += len>>9;
@@ -4107,7 +4123,8 @@ static struct r10conf *setup_conf(struct mddev *mddev)
 	atomic_set(&conf->nr_pending, 0);
 
 	err = -ENOMEM;
-	conf->thread = md_register_thread(raid10d, mddev, "raid10");
+	rcu_assign_pointer(conf->thread,
+			   md_register_thread(raid10d, mddev, "raid10"));
 	if (!conf->thread)
 		goto out;
 
@@ -4152,8 +4169,8 @@ static int raid10_run(struct mddev *mddev)
 	if (!conf)
 		goto out;
 
-	mddev->thread = conf->thread;
-	conf->thread = NULL;
+	rcu_assign_pointer(mddev->thread, conf->thread);
+	rcu_assign_pointer(conf->thread, NULL);
 
 	if (mddev_is_clustered(conf->mddev)) {
 		int fc, fo;
@@ -4296,8 +4313,8 @@ static int raid10_run(struct mddev *mddev)
 		clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
 		set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
 		set_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
-		mddev->sync_thread = md_register_thread(md_do_sync, mddev,
-							"reshape");
+		rcu_assign_pointer(mddev->sync_thread,
+			md_register_thread(md_do_sync, mddev, "reshape"));
 		if (!mddev->sync_thread)
 			goto out_free_conf;
 	}
@@ -4698,8 +4715,8 @@ out:
 	set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
 	set_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
 
-	mddev->sync_thread = md_register_thread(md_do_sync, mddev,
-						"reshape");
+	rcu_assign_pointer(mddev->sync_thread,
+			   md_register_thread(md_do_sync, mddev, "reshape"));
 	if (!mddev->sync_thread) {
 		ret = -EAGAIN;
 		goto abort;
@@ -4997,11 +5014,11 @@ read_more:
 		if (len > PAGE_SIZE)
 			len = PAGE_SIZE;
 		for (bio = blist; bio ; bio = bio->bi_next) {
-			/*
-			 * won't fail because the vec table is big enough
-			 * to hold all these pages
-			 */
-			bio_add_page(bio, page, len, 0);
+			if (WARN_ON(!bio_add_page(bio, page, len, 0))) {
+				bio->bi_status = BLK_STS_RESOURCE;
+				bio_endio(bio);
+				return sectors_done;
+			}
 		}
 		sector_nr += len >> 9;
 		nr_sectors += len >> 9;