1 files changed, 88 insertions, 76 deletions

diff --git a/drivers/md/md.c b/drivers/md/md.c
index e25f00f01..3fe3d04a9 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -257,13 +257,17 @@ static void md_make_request(struct request_queue *q, struct bio *bio)
 	unsigned int sectors;
 	int cpu;
 
+	blk_queue_split(q, &bio, q->bio_split);
+
 	if (mddev == NULL || mddev->pers == NULL
 	    || !mddev->ready) {
 		bio_io_error(bio);
 		return;
 	}
 	if (mddev->ro == 1 && unlikely(rw == WRITE)) {
-		bio_endio(bio, bio_sectors(bio) == 0 ? 0 : -EROFS);
+		if (bio_sectors(bio) != 0)
+			bio->bi_error = -EROFS;
+		bio_endio(bio);
 		return;
 	}
 	smp_rmb(); /* Ensure implications of  'active' are visible */
@@ -350,34 +354,11 @@ static int md_congested(void *data, int bits)
 	return mddev_congested(mddev, bits);
 }
 
-static int md_mergeable_bvec(struct request_queue *q,
-			     struct bvec_merge_data *bvm,
-			     struct bio_vec *biovec)
-{
-	struct mddev *mddev = q->queuedata;
-	int ret;
-	rcu_read_lock();
-	if (mddev->suspended) {
-		/* Must always allow one vec */
-		if (bvm->bi_size == 0)
-			ret = biovec->bv_len;
-		else
-			ret = 0;
-	} else {
-		struct md_personality *pers = mddev->pers;
-		if (pers && pers->mergeable_bvec)
-			ret = pers->mergeable_bvec(mddev, bvm, biovec);
-		else
-			ret = biovec->bv_len;
-	}
-	rcu_read_unlock();
-	return ret;
-}
 /*
  * Generic flush handling for md
  */
 
-static void md_end_flush(struct bio *bio, int err)
+static void md_end_flush(struct bio *bio)
 {
 	struct md_rdev *rdev = bio->bi_private;
 	struct mddev *mddev = rdev->mddev;
@@ -433,7 +414,7 @@ static void md_submit_flush_data(struct work_struct *ws)
 
 	if (bio->bi_iter.bi_size == 0)
 		/* an empty barrier - all done */
-		bio_endio(bio, 0);
+		bio_endio(bio);
 	else {
 		bio->bi_rw &= ~REQ_FLUSH;
 		mddev->pers->make_request(mddev, bio);
@@ -502,6 +483,8 @@ static void mddev_put(struct mddev *mddev)
 		bioset_free(bs);
 }
 
+static void md_safemode_timeout(unsigned long data);
+
 void mddev_init(struct mddev *mddev)
 {
 	mutex_init(&mddev->open_mutex);
@@ -509,7 +492,8 @@ void mddev_init(struct mddev *mddev)
 	mutex_init(&mddev->bitmap_info.mutex);
 	INIT_LIST_HEAD(&mddev->disks);
 	INIT_LIST_HEAD(&mddev->all_mddevs);
-	init_timer(&mddev->safemode_timer);
+	setup_timer(&mddev->safemode_timer, md_safemode_timeout,
+		    (unsigned long) mddev);
 	atomic_set(&mddev->active, 1);
 	atomic_set(&mddev->openers, 0);
 	atomic_set(&mddev->active_io, 0);
@@ -728,15 +712,13 @@ void md_rdev_clear(struct md_rdev *rdev)
 }
 EXPORT_SYMBOL_GPL(md_rdev_clear);
 
-static void super_written(struct bio *bio, int error)
+static void super_written(struct bio *bio)
 {
 	struct md_rdev *rdev = bio->bi_private;
 	struct mddev *mddev = rdev->mddev;
 
-	if (error || !test_bit(BIO_UPTODATE, &bio->bi_flags)) {
-		printk("md: super_written gets error=%d, uptodate=%d\n",
-		       error, test_bit(BIO_UPTODATE, &bio->bi_flags));
-		WARN_ON(test_bit(BIO_UPTODATE, &bio->bi_flags));
+	if (bio->bi_error) {
+		printk("md: super_written gets error=%d\n", bio->bi_error);
 		md_error(mddev, rdev);
 	}
 
@@ -791,7 +773,7 @@ int sync_page_io(struct md_rdev *rdev, sector_t sector, int size,
 	bio_add_page(bio, page, size, 0);
 	submit_bio_wait(rw, bio);
 
-	ret = test_bit(BIO_UPTODATE, &bio->bi_flags);
+	ret = !bio->bi_error;
 	bio_put(bio);
 	return ret;
 }
@@ -3276,8 +3258,6 @@ int strict_strtoul_scaled(const char *cp, unsigned long *res, int scale)
 	return 0;
 }
 
-static void md_safemode_timeout(unsigned long data);
-
 static ssize_t
 safe_delay_show(struct mddev *mddev, char *page)
 {
@@ -4210,6 +4190,8 @@ action_show(struct mddev *mddev, char *page)
 				type = "repair";
 		} else if (test_bit(MD_RECOVERY_RECOVER, &recovery))
 			type = "recover";
+		else if (mddev->reshape_position != MaxSector)
+			type = "reshape";
 	}
 	return sprintf(page, "%s\n", type);
 }
@@ -5186,7 +5168,6 @@ int md_run(struct mddev *mddev)
 	if (mddev->queue) {
 		mddev->queue->backing_dev_info.congested_data = mddev;
 		mddev->queue->backing_dev_info.congested_fn = md_congested;
-		blk_queue_merge_bvec(mddev->queue, md_mergeable_bvec);
 	}
 	if (pers->sync_request) {
 		if (mddev->kobj.sd &&
@@ -5202,8 +5183,6 @@ int md_run(struct mddev *mddev)
 	atomic_set(&mddev->max_corr_read_errors,
 		   MD_DEFAULT_MAX_CORRECTED_READ_ERRORS);
 	mddev->safemode = 0;
-	mddev->safemode_timer.function = md_safemode_timeout;
-	mddev->safemode_timer.data = (unsigned long) mddev;
 	mddev->safemode_delay = (200 * HZ)/1000 +1; /* 200 msec delay */
 	mddev->in_sync = 1;
 	smp_wmb();
@@ -5216,6 +5195,11 @@ int md_run(struct mddev *mddev)
 			if (sysfs_link_rdev(mddev, rdev))
 				/* failure here is OK */;
 
+	if (mddev->degraded && !mddev->ro)
+		/* This ensures that recovering status is reported immediately
+		 * via sysfs - until a lack of spares is confirmed.
+		 */
+		set_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
 	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 
 	if (mddev->flags & MD_UPDATE_SB_FLAGS)
@@ -5315,7 +5299,6 @@ static void md_clean(struct mddev *mddev)
 	mddev->degraded = 0;
 	mddev->safemode = 0;
 	mddev->private = NULL;
-	mddev->merge_check_needed = 0;
 	mddev->bitmap_info.offset = 0;
 	mddev->bitmap_info.default_offset = 0;
 	mddev->bitmap_info.default_space = 0;
@@ -5426,9 +5409,13 @@ static int md_set_readonly(struct mddev *mddev, struct block_device *bdev)
 		 * which will now never happen */
 		wake_up_process(mddev->sync_thread->tsk);
 
+	if (mddev->external && test_bit(MD_CHANGE_PENDING, &mddev->flags))
+		return -EBUSY;
 	mddev_unlock(mddev);
 	wait_event(resync_wait, !test_bit(MD_RECOVERY_RUNNING,
 					  &mddev->recovery));
+	wait_event(mddev->sb_wait,
+		   !test_bit(MD_CHANGE_PENDING, &mddev->flags));
 	mddev_lock_nointr(mddev);
 
 	mutex_lock(&mddev->open_mutex);
@@ -5514,7 +5501,6 @@ static int do_md_stop(struct mddev *mddev, int mode,
 
 		__md_stop_writes(mddev);
 		__md_stop(mddev);
-		mddev->queue->merge_bvec_fn = NULL;
 		mddev->queue->backing_dev_info.congested_fn = NULL;
 
 		/* tell userspace to handle 'inactive' */
@@ -5765,16 +5751,16 @@ static int get_bitmap_file(struct mddev *mddev, void __user * arg)
 
 	err = 0;
 	spin_lock(&mddev->lock);
-	/* bitmap disabled, zero the first byte and copy out */
-	if (!mddev->bitmap_info.file)
-		file->pathname[0] = '\0';
-	else if ((ptr = file_path(mddev->bitmap_info.file,
-			       file->pathname, sizeof(file->pathname))),
-		 IS_ERR(ptr))
-		err = PTR_ERR(ptr);
-	else
-		memmove(file->pathname, ptr,
-			sizeof(file->pathname)-(ptr-file->pathname));
+	/* bitmap enabled */
+	if (mddev->bitmap_info.file) {
+		ptr = file_path(mddev->bitmap_info.file, file->pathname,
+				sizeof(file->pathname));
+		if (IS_ERR(ptr))
+			err = PTR_ERR(ptr);
+		else
+			memmove(file->pathname, ptr,
+				sizeof(file->pathname)-(ptr-file->pathname));
+	}
 	spin_unlock(&mddev->lock);
 
 	if (err == 0 &&
@@ -7093,7 +7079,7 @@ static void status_unused(struct seq_file *seq)
 	seq_printf(seq, "\n");
 }
 
-static void status_resync(struct seq_file *seq, struct mddev *mddev)
+static int status_resync(struct seq_file *seq, struct mddev *mddev)
 {
 	sector_t max_sectors, resync, res;
 	unsigned long dt, db;
@@ -7101,18 +7087,32 @@ static void status_resync(struct seq_file *seq, struct mddev *mddev)
 	int scale;
 	unsigned int per_milli;
 
-	if (mddev->curr_resync <= 3)
-		resync = 0;
-	else
-		resync = mddev->curr_resync
-			- atomic_read(&mddev->recovery_active);
-
 	if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery) ||
 	    test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery))
 		max_sectors = mddev->resync_max_sectors;
 	else
 		max_sectors = mddev->dev_sectors;
 
+	resync = mddev->curr_resync;
+	if (resync <= 3) {
+		if (test_bit(MD_RECOVERY_DONE, &mddev->recovery))
+			/* Still cleaning up */
+			resync = max_sectors;
+	} else
+		resync -= atomic_read(&mddev->recovery_active);
+
+	if (resync == 0) {
+		if (mddev->recovery_cp < MaxSector) {
+			seq_printf(seq, "\tresync=PENDING");
+			return 1;
+		}
+		return 0;
+	}
+	if (resync < 3) {
+		seq_printf(seq, "\tresync=DELAYED");
+		return 1;
+	}
+
 	WARN_ON(max_sectors == 0);
 	/* Pick 'scale' such that (resync>>scale)*1000 will fit
 	 * in a sector_t, and (max_sectors>>scale) will fit in a
@@ -7177,6 +7177,7 @@ static void status_resync(struct seq_file *seq, struct mddev *mddev)
 		   ((unsigned long)rt % 60)/6);
 
 	seq_printf(seq, " speed=%ldK/sec", db/2/dt);
+	return 1;
 }
 
 static void *md_seq_start(struct seq_file *seq, loff_t *pos)
@@ -7322,13 +7323,8 @@ static int md_seq_show(struct seq_file *seq, void *v)
 			mddev->pers->status(seq, mddev);
 			seq_printf(seq, "\n      ");
 			if (mddev->pers->sync_request) {
-				if (mddev->curr_resync > 2) {
-					status_resync(seq, mddev);
+				if (status_resync(seq, mddev))
 					seq_printf(seq, "\n      ");
-				} else if (mddev->curr_resync >= 1)
-					seq_printf(seq, "\tresync=DELAYED\n      ");
-				else if (mddev->recovery_cp < MaxSector)
-					seq_printf(seq, "\tresync=PENDING\n      ");
 			}
 		} else
 			seq_printf(seq, "\n       ");
@@ -7411,15 +7407,19 @@ int unregister_md_personality(struct md_personality *p)
 }
 EXPORT_SYMBOL(unregister_md_personality);
 
-int register_md_cluster_operations(struct md_cluster_operations *ops, struct module *module)
+int register_md_cluster_operations(struct md_cluster_operations *ops,
+				   struct module *module)
 {
-	if (md_cluster_ops != NULL)
-		return -EALREADY;
+	int ret = 0;
 	spin_lock(&pers_lock);
-	md_cluster_ops = ops;
-	md_cluster_mod = module;
+	if (md_cluster_ops != NULL)
+		ret = -EALREADY;
+	else {
+		md_cluster_ops = ops;
+		md_cluster_mod = module;
+	}
 	spin_unlock(&pers_lock);
-	return 0;
+	return ret;
 }
 EXPORT_SYMBOL(register_md_cluster_operations);
 
@@ -7817,7 +7817,8 @@ void md_do_sync(struct md_thread *thread)
 		      > (max_sectors >> 4)) ||
 		     time_after_eq(jiffies, update_time + UPDATE_FREQUENCY) ||
 		     (j - mddev->curr_resync_completed)*2
-		     >= mddev->resync_max - mddev->curr_resync_completed
+		     >= mddev->resync_max - mddev->curr_resync_completed ||
+		     mddev->curr_resync_completed > mddev->resync_max
 			    )) {
 			/* time to update curr_resync_completed */
 			wait_event(mddev->recovery_wait,
@@ -7862,6 +7863,9 @@ void md_do_sync(struct md_thread *thread)
 			break;
 
 		j += sectors;
+		if (j > max_sectors)
+			/* when skipping, extra large numbers can be returned. */
+			j = max_sectors;
 		if (j > 2)
 			mddev->curr_resync = j;
 		if (mddev_is_clustered(mddev))
@@ -7930,12 +7934,15 @@ void md_do_sync(struct md_thread *thread)
 	blk_finish_plug(&plug);
 	wait_event(mddev->recovery_wait, !atomic_read(&mddev->recovery_active));
 
+	if (!test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) &&
+	    !test_bit(MD_RECOVERY_INTR, &mddev->recovery) &&
+	    mddev->curr_resync > 2) {
+		mddev->curr_resync_completed = mddev->curr_resync;
+		sysfs_notify(&mddev->kobj, NULL, "sync_completed");
+	}
 	/* tell personality that we are finished */
 	mddev->pers->sync_request(mddev, max_sectors, &skipped);
 
-	if (mddev_is_clustered(mddev))
-		md_cluster_ops->resync_finish(mddev);
-
 	if (!test_bit(MD_RECOVERY_CHECK, &mddev->recovery) &&
 	    mddev->curr_resync > 2) {
 		if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) {
@@ -7969,6 +7976,9 @@ void md_do_sync(struct md_thread *thread)
 		}
 	}
  skip:
+	if (mddev_is_clustered(mddev))
+		md_cluster_ops->resync_finish(mddev);
+
 	set_bit(MD_CHANGE_DEVS, &mddev->flags);
 
 	spin_lock(&mddev->lock);
@@ -7979,11 +7989,11 @@ void md_do_sync(struct md_thread *thread)
 		mddev->resync_max = MaxSector;
 	} else if (test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery))
 		mddev->resync_min = mddev->curr_resync_completed;
+	set_bit(MD_RECOVERY_DONE, &mddev->recovery);
 	mddev->curr_resync = 0;
 	spin_unlock(&mddev->lock);
 
 	wake_up(&resync_wait);
-	set_bit(MD_RECOVERY_DONE, &mddev->recovery);
 	md_wakeup_thread(mddev->thread);
 	return;
 }
@@ -8030,8 +8040,7 @@ static int remove_and_add_spares(struct mddev *mddev,
 		       !test_bit(Bitmap_sync, &rdev->flags)))
 			continue;
 
-		if (rdev->saved_raid_disk < 0)
-			rdev->recovery_offset = 0;
+		rdev->recovery_offset = 0;
 		if (mddev->pers->
 		    hot_add_disk(mddev, rdev) == 0) {
 			if (sysfs_link_rdev(mddev, rdev))
@@ -8152,7 +8161,9 @@ void md_check_recovery(struct mddev *mddev)
 			 */
 			set_bit(MD_RECOVERY_INTR, &mddev->recovery);
 			md_reap_sync_thread(mddev);
+			clear_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
 			clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+			clear_bit(MD_CHANGE_PENDING, &mddev->flags);
 			goto unlock;
 		}
 
@@ -8598,6 +8609,7 @@ int rdev_set_badblocks(struct md_rdev *rdev, sector_t s, int sectors,
 		/* Make sure they get written out promptly */
 		sysfs_notify_dirent_safe(rdev->sysfs_state);
 		set_bit(MD_CHANGE_CLEAN, &rdev->mddev->flags);
+		set_bit(MD_CHANGE_PENDING, &rdev->mddev->flags);
 		md_wakeup_thread(rdev->mddev->thread);
 	}
 	return rv;