1 files changed, 69 insertions, 95 deletions

diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index f80f1af61ce7..4517f06c41ba 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -255,9 +255,10 @@ static void call_bio_endio(struct r1bio *r1_bio)
 		done = 1;
 
 	if (!test_bit(R1BIO_Uptodate, &r1_bio->state))
-		clear_bit(BIO_UPTODATE, &bio->bi_flags);
+		bio->bi_error = -EIO;
+
 	if (done) {
-		bio_endio(bio, 0);
+		bio_endio(bio);
 		/*
 		 * Wake up any possible resync thread that waits for the device
 		 * to go idle.
@@ -312,9 +313,9 @@ static int find_bio_disk(struct r1bio *r1_bio, struct bio *bio)
 	return mirror;
 }
 
-static void raid1_end_read_request(struct bio *bio, int error)
+static void raid1_end_read_request(struct bio *bio)
 {
-	int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
+	int uptodate = !bio->bi_error;
 	struct r1bio *r1_bio = bio->bi_private;
 	int mirror;
 	struct r1conf *conf = r1_bio->mddev->private;
@@ -336,7 +337,7 @@ static void raid1_end_read_request(struct bio *bio, int error)
 		spin_lock_irqsave(&conf->device_lock, flags);
 		if (r1_bio->mddev->degraded == conf->raid_disks ||
 		    (r1_bio->mddev->degraded == conf->raid_disks-1 &&
-		     !test_bit(Faulty, &conf->mirrors[mirror].rdev->flags)))
+		     test_bit(In_sync, &conf->mirrors[mirror].rdev->flags)))
 			uptodate = 1;
 		spin_unlock_irqrestore(&conf->device_lock, flags);
 	}
@@ -397,9 +398,8 @@ static void r1_bio_write_done(struct r1bio *r1_bio)
 	}
 }
 
-static void raid1_end_write_request(struct bio *bio, int error)
+static void raid1_end_write_request(struct bio *bio)
 {
-	int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
 	struct r1bio *r1_bio = bio->bi_private;
 	int mirror, behind = test_bit(R1BIO_BehindIO, &r1_bio->state);
 	struct r1conf *conf = r1_bio->mddev->private;
@@ -410,7 +410,7 @@ static void raid1_end_write_request(struct bio *bio, int error)
 	/*
 	 * 'one mirror IO has finished' event handler:
 	 */
-	if (!uptodate) {
+	if (bio->bi_error) {
 		set_bit(WriteErrorSeen,
 			&conf->mirrors[mirror].rdev->flags);
 		if (!test_and_set_bit(WantReplacement,
@@ -541,7 +541,7 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect
 
 	if ((conf->mddev->recovery_cp < this_sector + sectors) ||
 	    (mddev_is_clustered(conf->mddev) &&
-	    md_cluster_ops->area_resyncing(conf->mddev, this_sector,
+	    md_cluster_ops->area_resyncing(conf->mddev, READ, this_sector,
 		    this_sector + sectors)))
 		choose_first = 1;
 	else
@@ -557,7 +557,6 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect
 		rdev = rcu_dereference(conf->mirrors[disk].rdev);
 		if (r1_bio->bios[disk] == IO_BLOCKED
 		    || rdev == NULL
-		    || test_bit(Unmerged, &rdev->flags)
 		    || test_bit(Faulty, &rdev->flags))
 			continue;
 		if (!test_bit(In_sync, &rdev->flags) &&
@@ -708,38 +707,6 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect
 	return best_disk;
 }
 
-static int raid1_mergeable_bvec(struct mddev *mddev,
-				struct bvec_merge_data *bvm,
-				struct bio_vec *biovec)
-{
-	struct r1conf *conf = mddev->private;
-	sector_t sector = bvm->bi_sector + get_start_sect(bvm->bi_bdev);
-	int max = biovec->bv_len;
-
-	if (mddev->merge_check_needed) {
-		int disk;
-		rcu_read_lock();
-		for (disk = 0; disk < conf->raid_disks * 2; disk++) {
-			struct md_rdev *rdev = rcu_dereference(
-				conf->mirrors[disk].rdev);
-			if (rdev && !test_bit(Faulty, &rdev->flags)) {
-				struct request_queue *q =
-					bdev_get_queue(rdev->bdev);
-				if (q->merge_bvec_fn) {
-					bvm->bi_sector = sector +
-						rdev->data_offset;
-					bvm->bi_bdev = rdev->bdev;
-					max = min(max, q->merge_bvec_fn(
-							  q, bvm, biovec));
-				}
-			}
-		}
-		rcu_read_unlock();
-	}
-	return max;
-
-}
-
 static int raid1_congested(struct mddev *mddev, int bits)
 {
 	struct r1conf *conf = mddev->private;
@@ -793,7 +760,7 @@ static void flush_pending_writes(struct r1conf *conf)
 			if (unlikely((bio->bi_rw & REQ_DISCARD) &&
 			    !blk_queue_discard(bdev_get_queue(bio->bi_bdev))))
 				/* Just ignore it */
-				bio_endio(bio, 0);
+				bio_endio(bio);
 			else
 				generic_make_request(bio);
 			bio = next;
@@ -1068,7 +1035,7 @@ static void raid1_unplug(struct blk_plug_cb *cb, bool from_schedule)
 		if (unlikely((bio->bi_rw & REQ_DISCARD) &&
 		    !blk_queue_discard(bdev_get_queue(bio->bi_bdev))))
 			/* Just ignore it */
-			bio_endio(bio, 0);
+			bio_endio(bio);
 		else
 			generic_make_request(bio);
 		bio = next;
@@ -1111,7 +1078,8 @@ static void make_request(struct mddev *mddev, struct bio * bio)
 	    ((bio_end_sector(bio) > mddev->suspend_lo &&
 	    bio->bi_iter.bi_sector < mddev->suspend_hi) ||
 	    (mddev_is_clustered(mddev) &&
-	     md_cluster_ops->area_resyncing(mddev, bio->bi_iter.bi_sector, bio_end_sector(bio))))) {
+	     md_cluster_ops->area_resyncing(mddev, WRITE,
+		     bio->bi_iter.bi_sector, bio_end_sector(bio))))) {
 		/* As the suspend_* range is controlled by
 		 * userspace, we want an interruptible
 		 * wait.
@@ -1124,7 +1092,7 @@ static void make_request(struct mddev *mddev, struct bio * bio)
 			if (bio_end_sector(bio) <= mddev->suspend_lo ||
 			    bio->bi_iter.bi_sector >= mddev->suspend_hi ||
 			    (mddev_is_clustered(mddev) &&
-			     !md_cluster_ops->area_resyncing(mddev,
+			     !md_cluster_ops->area_resyncing(mddev, WRITE,
 				     bio->bi_iter.bi_sector, bio_end_sector(bio))))
 				break;
 			schedule();
@@ -1157,7 +1125,7 @@ static void make_request(struct mddev *mddev, struct bio * bio)
 	 * non-zero, then it is the number of not-completed requests.
 	 */
 	bio->bi_phys_segments = 0;
-	clear_bit(BIO_SEG_VALID, &bio->bi_flags);
+	bio_clear_flag(bio, BIO_SEG_VALID);
 
 	if (rw == READ) {
 		/*
@@ -1268,8 +1236,7 @@ read_again:
 			break;
 		}
 		r1_bio->bios[i] = NULL;
-		if (!rdev || test_bit(Faulty, &rdev->flags)
-		    || test_bit(Unmerged, &rdev->flags)) {
+		if (!rdev || test_bit(Faulty, &rdev->flags)) {
 			if (i < conf->raid_disks)
 				set_bit(R1BIO_Degraded, &r1_bio->state);
 			continue;
@@ -1475,6 +1442,7 @@ static void error(struct mddev *mddev, struct md_rdev *rdev)
 {
 	char b[BDEVNAME_SIZE];
 	struct r1conf *conf = mddev->private;
+	unsigned long flags;
 
 	/*
 	 * If it is not operational, then we have already marked it as dead
@@ -1494,19 +1462,19 @@ static void error(struct mddev *mddev, struct md_rdev *rdev)
 		return;
 	}
 	set_bit(Blocked, &rdev->flags);
+	spin_lock_irqsave(&conf->device_lock, flags);
 	if (test_and_clear_bit(In_sync, &rdev->flags)) {
-		unsigned long flags;
-		spin_lock_irqsave(&conf->device_lock, flags);
 		mddev->degraded++;
 		set_bit(Faulty, &rdev->flags);
-		spin_unlock_irqrestore(&conf->device_lock, flags);
 	} else
 		set_bit(Faulty, &rdev->flags);
+	spin_unlock_irqrestore(&conf->device_lock, flags);
 	/*
 	 * if recovery is running, make sure it aborts.
 	 */
 	set_bit(MD_RECOVERY_INTR, &mddev->recovery);
 	set_bit(MD_CHANGE_DEVS, &mddev->flags);
+	set_bit(MD_CHANGE_PENDING, &mddev->flags);
 	printk(KERN_ALERT
 	       "md/raid1:%s: Disk failure on %s, disabling device.\n"
 	       "md/raid1:%s: Operation continuing on %d devices.\n",
@@ -1567,7 +1535,10 @@ static int raid1_spare_active(struct mddev *mddev)
 	 * Find all failed disks within the RAID1 configuration
 	 * and mark them readable.
 	 * Called under mddev lock, so rcu protection not needed.
+	 * device_lock used to avoid races with raid1_end_read_request
+	 * which expects 'In_sync' flags and ->degraded to be consistent.
 	 */
+	spin_lock_irqsave(&conf->device_lock, flags);
 	for (i = 0; i < conf->raid_disks; i++) {
 		struct md_rdev *rdev = conf->mirrors[i].rdev;
 		struct md_rdev *repl = conf->mirrors[conf->raid_disks + i].rdev;
@@ -1598,7 +1569,6 @@ static int raid1_spare_active(struct mddev *mddev)
 			sysfs_notify_dirent_safe(rdev->sysfs_state);
 		}
 	}
-	spin_lock_irqsave(&conf->device_lock, flags);
 	mddev->degraded -= count;
 	spin_unlock_irqrestore(&conf->device_lock, flags);
 
@@ -1614,7 +1584,6 @@ static int raid1_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 	struct raid1_info *p;
 	int first = 0;
 	int last = conf->raid_disks - 1;
-	struct request_queue *q = bdev_get_queue(rdev->bdev);
 
 	if (mddev->recovery_disabled == conf->recovery_disabled)
 		return -EBUSY;
@@ -1622,11 +1591,6 @@ static int raid1_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 	if (rdev->raid_disk >= 0)
 		first = last = rdev->raid_disk;
 
-	if (q->merge_bvec_fn) {
-		set_bit(Unmerged, &rdev->flags);
-		mddev->merge_check_needed = 1;
-	}
-
 	for (mirror = first; mirror <= last; mirror++) {
 		p = conf->mirrors+mirror;
 		if (!p->rdev) {
@@ -1658,19 +1622,6 @@ static int raid1_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 			break;
 		}
 	}
-	if (err == 0 && test_bit(Unmerged, &rdev->flags)) {
-		/* Some requests might not have seen this new
-		 * merge_bvec_fn.  We must wait for them to complete
-		 * before merging the device fully.
-		 * First we make sure any code which has tested
-		 * our function has submitted the request, then
-		 * we wait for all outstanding requests to complete.
-		 */
-		synchronize_sched();
-		freeze_array(conf, 0);
-		unfreeze_array(conf);
-		clear_bit(Unmerged, &rdev->flags);
-	}
 	md_integrity_add_rdev(rdev, mddev);
 	if (mddev->queue && blk_queue_discard(bdev_get_queue(rdev->bdev)))
 		queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, mddev->queue);
@@ -1734,7 +1685,7 @@ abort:
 	return err;
 }
 
-static void end_sync_read(struct bio *bio, int error)
+static void end_sync_read(struct bio *bio)
 {
 	struct r1bio *r1_bio = bio->bi_private;
 
@@ -1745,16 +1696,16 @@ static void end_sync_read(struct bio *bio, int error)
 	 * or re-read if the read failed.
 	 * We don't do much here, just schedule handling by raid1d
 	 */
-	if (test_bit(BIO_UPTODATE, &bio->bi_flags))
+	if (!bio->bi_error)
 		set_bit(R1BIO_Uptodate, &r1_bio->state);
 
 	if (atomic_dec_and_test(&r1_bio->remaining))
 		reschedule_retry(r1_bio);
 }
 
-static void end_sync_write(struct bio *bio, int error)
+static void end_sync_write(struct bio *bio)
 {
-	int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
+	int uptodate = !bio->bi_error;
 	struct r1bio *r1_bio = bio->bi_private;
 	struct mddev *mddev = r1_bio->mddev;
 	struct r1conf *conf = mddev->private;
@@ -1941,7 +1892,7 @@ static int fix_sync_read_error(struct r1bio *r1_bio)
 		idx ++;
 	}
 	set_bit(R1BIO_Uptodate, &r1_bio->state);
-	set_bit(BIO_UPTODATE, &bio->bi_flags);
+	bio->bi_error = 0;
 	return 1;
 }
 
@@ -1965,15 +1916,14 @@ static void process_checks(struct r1bio *r1_bio)
 	for (i = 0; i < conf->raid_disks * 2; i++) {
 		int j;
 		int size;
-		int uptodate;
+		int error;
 		struct bio *b = r1_bio->bios[i];
 		if (b->bi_end_io != end_sync_read)
 			continue;
-		/* fixup the bio for reuse, but preserve BIO_UPTODATE */
-		uptodate = test_bit(BIO_UPTODATE, &b->bi_flags);
+		/* fixup the bio for reuse, but preserve errno */
+		error = b->bi_error;
 		bio_reset(b);
-		if (!uptodate)
-			clear_bit(BIO_UPTODATE, &b->bi_flags);
+		b->bi_error = error;
 		b->bi_vcnt = vcnt;
 		b->bi_iter.bi_size = r1_bio->sectors << 9;
 		b->bi_iter.bi_sector = r1_bio->sector +
@@ -1996,7 +1946,7 @@ static void process_checks(struct r1bio *r1_bio)
 	}
 	for (primary = 0; primary < conf->raid_disks * 2; primary++)
 		if (r1_bio->bios[primary]->bi_end_io == end_sync_read &&
-		    test_bit(BIO_UPTODATE, &r1_bio->bios[primary]->bi_flags)) {
+		    !r1_bio->bios[primary]->bi_error) {
 			r1_bio->bios[primary]->bi_end_io = NULL;
 			rdev_dec_pending(conf->mirrors[primary].rdev, mddev);
 			break;
@@ -2006,14 +1956,14 @@ static void process_checks(struct r1bio *r1_bio)
 		int j;
 		struct bio *pbio = r1_bio->bios[primary];
 		struct bio *sbio = r1_bio->bios[i];
-		int uptodate = test_bit(BIO_UPTODATE, &sbio->bi_flags);
+		int error = sbio->bi_error;
 
 		if (sbio->bi_end_io != end_sync_read)
 			continue;
-		/* Now we can 'fixup' the BIO_UPTODATE flag */
-		set_bit(BIO_UPTODATE, &sbio->bi_flags);
+		/* Now we can 'fixup' the error value */
+		sbio->bi_error = 0;
 
-		if (uptodate) {
+		if (!error) {
 			for (j = vcnt; j-- ; ) {
 				struct page *p, *s;
 				p = pbio->bi_io_vec[j].bv_page;
@@ -2028,7 +1978,7 @@ static void process_checks(struct r1bio *r1_bio)
 		if (j >= 0)
 			atomic64_add(r1_bio->sectors, &mddev->resync_mismatches);
 		if (j < 0 || (test_bit(MD_RECOVERY_CHECK, &mddev->recovery)
-			      && uptodate)) {
+			      && !error)) {
 			/* No need to write to this device. */
 			sbio->bi_end_io = NULL;
 			rdev_dec_pending(conf->mirrors[i].rdev, mddev);
@@ -2269,11 +2219,11 @@ static void handle_sync_write_finished(struct r1conf *conf, struct r1bio *r1_bio
 		struct bio *bio = r1_bio->bios[m];
 		if (bio->bi_end_io == NULL)
 			continue;
-		if (test_bit(BIO_UPTODATE, &bio->bi_flags) &&
+		if (!bio->bi_error &&
 		    test_bit(R1BIO_MadeGood, &r1_bio->state)) {
 			rdev_clear_badblocks(rdev, r1_bio->sector, s, 0);
 		}
-		if (!test_bit(BIO_UPTODATE, &bio->bi_flags) &&
+		if (bio->bi_error &&
 		    test_bit(R1BIO_WriteError, &r1_bio->state)) {
 			if (!rdev_set_badblocks(rdev, r1_bio->sector, s, 0))
 				md_error(conf->mddev, rdev);
@@ -2286,6 +2236,7 @@ static void handle_sync_write_finished(struct r1conf *conf, struct r1bio *r1_bio
 static void handle_write_finished(struct r1conf *conf, struct r1bio *r1_bio)
 {
 	int m;
+	bool fail = false;
 	for (m = 0; m < conf->raid_disks * 2 ; m++)
 		if (r1_bio->bios[m] == IO_MADE_GOOD) {
 			struct md_rdev *rdev = conf->mirrors[m].rdev;
@@ -2298,6 +2249,7 @@ static void handle_write_finished(struct r1conf *conf, struct r1bio *r1_bio)
 			 * narrow down and record precise write
 			 * errors.
 			 */
+			fail = true;
 			if (!narrow_write_error(r1_bio, m)) {
 				md_error(conf->mddev,
 					 conf->mirrors[m].rdev);
@@ -2309,7 +2261,13 @@ static void handle_write_finished(struct r1conf *conf, struct r1bio *r1_bio)
 		}
 	if (test_bit(R1BIO_WriteError, &r1_bio->state))
 		close_write(r1_bio);
-	raid_end_bio_io(r1_bio);
+	if (fail) {
+		spin_lock_irq(&conf->device_lock);
+		list_add(&r1_bio->retry_list, &conf->bio_end_io_list);
+		spin_unlock_irq(&conf->device_lock);
+		md_wakeup_thread(conf->mddev->thread);
+	} else
+		raid_end_bio_io(r1_bio);
 }
 
 static void handle_read_error(struct r1conf *conf, struct r1bio *r1_bio)
@@ -2415,6 +2373,23 @@ static void raid1d(struct md_thread *thread)
 
 	md_check_recovery(mddev);
 
+	if (!list_empty_careful(&conf->bio_end_io_list) &&
+	    !test_bit(MD_CHANGE_PENDING, &mddev->flags)) {
+		LIST_HEAD(tmp);
+		spin_lock_irqsave(&conf->device_lock, flags);
+		if (!test_bit(MD_CHANGE_PENDING, &mddev->flags)) {
+			list_add(&tmp, &conf->bio_end_io_list);
+			list_del_init(&conf->bio_end_io_list);
+		}
+		spin_unlock_irqrestore(&conf->device_lock, flags);
+		while (!list_empty(&tmp)) {
+			r1_bio = list_first_entry(&conf->bio_end_io_list,
+						  struct r1bio, retry_list);
+			list_del(&r1_bio->retry_list);
+			raid_end_bio_io(r1_bio);
+		}
+	}
+
 	blk_start_plug(&plug);
 	for (;;) {
 
@@ -2712,7 +2687,7 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr, int *skipp
 						/* remove last page from this bio */
 						bio->bi_vcnt--;
 						bio->bi_iter.bi_size -= len;
-						__clear_bit(BIO_SEG_VALID, &bio->bi_flags);
+						bio_clear_flag(bio, BIO_SEG_VALID);
 					}
 					goto bio_full;
 				}
@@ -2807,8 +2782,6 @@ static struct r1conf *setup_conf(struct mddev *mddev)
 			goto abort;
 		disk->rdev = rdev;
 		q = bdev_get_queue(rdev->bdev);
-		if (q->merge_bvec_fn)
-			mddev->merge_check_needed = 1;
 
 		disk->head_position = 0;
 		disk->seq_start = MaxSector;
@@ -2816,6 +2789,7 @@ static struct r1conf *setup_conf(struct mddev *mddev)
 	conf->raid_disks = mddev->raid_disks;
 	conf->mddev = mddev;
 	INIT_LIST_HEAD(&conf->retry_list);
+	INIT_LIST_HEAD(&conf->bio_end_io_list);
 
 	spin_lock_init(&conf->resync_lock);
 	init_waitqueue_head(&conf->wait_barrier);
@@ -3110,6 +3084,7 @@ static int raid1_reshape(struct mddev *mddev)
 
 	unfreeze_array(conf);
 
+	set_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
 	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 	md_wakeup_thread(mddev->thread);
 
@@ -3173,7 +3148,6 @@ static struct md_personality raid1_personality =
 	.quiesce	= raid1_quiesce,
 	.takeover	= raid1_takeover,
 	.congested	= raid1_congested,
-	.mergeable_bvec	= raid1_mergeable_bvec,
 };
 
 static int __init raid_init(void)