1 files changed, 122 insertions, 84 deletions

diff --git a/drivers/md/md.c b/drivers/md/md.c
index 21da0c48f6c2..49f897fbb89b 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -734,78 +734,94 @@ void mddev_init(struct mddev *mddev)
 }
 EXPORT_SYMBOL_GPL(mddev_init);
 
+static struct mddev *mddev_find_locked(dev_t unit)
+{
+	struct mddev *mddev;
+
+	list_for_each_entry(mddev, &all_mddevs, all_mddevs)
+		if (mddev->unit == unit)
+			return mddev;
+
+	return NULL;
+}
+
+/* find an unused unit number */
+static dev_t mddev_alloc_unit(void)
+{
+	static int next_minor = 512;
+	int start = next_minor;
+	bool is_free = 0;
+	dev_t dev = 0;
+
+	while (!is_free) {
+		dev = MKDEV(MD_MAJOR, next_minor);
+		next_minor++;
+		if (next_minor > MINORMASK)
+			next_minor = 0;
+		if (next_minor == start)
+			return 0;		/* Oh dear, all in use. */
+		is_free = !mddev_find_locked(dev);
+	}
+
+	return dev;
+}
+
 static struct mddev *mddev_find(dev_t unit)
 {
-	struct mddev *mddev, *new = NULL;
+	struct mddev *mddev;
 
-	if (unit && MAJOR(unit) != MD_MAJOR)
-		unit &= ~((1<<MdpMinorShift)-1);
+	if (MAJOR(unit) != MD_MAJOR)
+		unit &= ~((1 << MdpMinorShift) - 1);
 
- retry:
 	spin_lock(&all_mddevs_lock);
+	mddev = mddev_find_locked(unit);
+	if (mddev)
+		mddev_get(mddev);
+	spin_unlock(&all_mddevs_lock);
 
-	if (unit) {
-		list_for_each_entry(mddev, &all_mddevs, all_mddevs)
-			if (mddev->unit == unit) {
-				mddev_get(mddev);
-				spin_unlock(&all_mddevs_lock);
-				kfree(new);
-				return mddev;
-			}
+	return mddev;
+}
 
-		if (new) {
-			list_add(&new->all_mddevs, &all_mddevs);
-			spin_unlock(&all_mddevs_lock);
-			new->hold_active = UNTIL_IOCTL;
-			return new;
-		}
-	} else if (new) {
-		/* find an unused unit number */
-		static int next_minor = 512;
-		int start = next_minor;
-		int is_free = 0;
-		int dev = 0;
-		while (!is_free) {
-			dev = MKDEV(MD_MAJOR, next_minor);
-			next_minor++;
-			if (next_minor > MINORMASK)
-				next_minor = 0;
-			if (next_minor == start) {
-				/* Oh dear, all in use. */
-				spin_unlock(&all_mddevs_lock);
-				kfree(new);
-				return NULL;
-			}
+static struct mddev *mddev_alloc(dev_t unit)
+{
+	struct mddev *new;
+	int error;
 
-			is_free = 1;
-			list_for_each_entry(mddev, &all_mddevs, all_mddevs)
-				if (mddev->unit == dev) {
-					is_free = 0;
-					break;
-				}
-		}
-		new->unit = dev;
-		new->md_minor = MINOR(dev);
-		new->hold_active = UNTIL_STOP;
-		list_add(&new->all_mddevs, &all_mddevs);
-		spin_unlock(&all_mddevs_lock);
-		return new;
-	}
-	spin_unlock(&all_mddevs_lock);
+	if (unit && MAJOR(unit) != MD_MAJOR)
+		unit &= ~((1 << MdpMinorShift) - 1);
 
 	new = kzalloc(sizeof(*new), GFP_KERNEL);
 	if (!new)
-		return NULL;
-
-	new->unit = unit;
-	if (MAJOR(unit) == MD_MAJOR)
-		new->md_minor = MINOR(unit);
-	else
-		new->md_minor = MINOR(unit) >> MdpMinorShift;
-
+		return ERR_PTR(-ENOMEM);
 	mddev_init(new);
 
-	goto retry;
+	spin_lock(&all_mddevs_lock);
+	if (unit) {
+		error = -EEXIST;
+		if (mddev_find_locked(unit))
+			goto out_free_new;
+		new->unit = unit;
+		if (MAJOR(unit) == MD_MAJOR)
+			new->md_minor = MINOR(unit);
+		else
+			new->md_minor = MINOR(unit) >> MdpMinorShift;
+		new->hold_active = UNTIL_IOCTL;
+	} else {
+		error = -ENODEV;
+		new->unit = mddev_alloc_unit();
+		if (!new->unit)
+			goto out_free_new;
+		new->md_minor = MINOR(new->unit);
+		new->hold_active = UNTIL_STOP;
+	}
+
+	list_add(&new->all_mddevs, &all_mddevs);
+	spin_unlock(&all_mddevs_lock);
+	return new;
+out_free_new:
+	spin_unlock(&all_mddevs_lock);
+	kfree(new);
+	return ERR_PTR(error);
 }
 
 static struct attribute_group md_redundancy_group;
@@ -5644,29 +5660,29 @@ static int md_alloc(dev_t dev, char *name)
 	 * writing to /sys/module/md_mod/parameters/new_array.
 	 */
 	static DEFINE_MUTEX(disks_mutex);
-	struct mddev *mddev = mddev_find(dev);
+	struct mddev *mddev;
 	struct gendisk *disk;
 	int partitioned;
 	int shift;
 	int unit;
-	int error;
+	int error ;
 
-	if (!mddev)
-		return -ENODEV;
-
-	partitioned = (MAJOR(mddev->unit) != MD_MAJOR);
-	shift = partitioned ? MdpMinorShift : 0;
-	unit = MINOR(mddev->unit) >> shift;
-
-	/* wait for any previous instance of this device to be
-	 * completely removed (mddev_delayed_delete).
+	/*
+	 * Wait for any previous instance of this device to be completely
+	 * removed (mddev_delayed_delete).
 	 */
 	flush_workqueue(md_misc_wq);
 
 	mutex_lock(&disks_mutex);
-	error = -EEXIST;
-	if (mddev->gendisk)
-		goto abort;
+	mddev = mddev_alloc(dev);
+	if (IS_ERR(mddev)) {
+		mutex_unlock(&disks_mutex);
+		return PTR_ERR(mddev);
+	}
+
+	partitioned = (MAJOR(mddev->unit) != MD_MAJOR);
+	shift = partitioned ? MdpMinorShift : 0;
+	unit = MINOR(mddev->unit) >> shift;
 
 	if (name && !dev) {
 		/* Need to ensure that 'name' is not a duplicate.
@@ -5678,6 +5694,7 @@ static int md_alloc(dev_t dev, char *name)
 			if (mddev2->gendisk &&
 			    strcmp(mddev2->gendisk->disk_name, name) == 0) {
 				spin_unlock(&all_mddevs_lock);
+				error = -EEXIST;
 				goto abort;
 			}
 		spin_unlock(&all_mddevs_lock);
@@ -6524,11 +6541,9 @@ static void autorun_devices(int part)
 
 		md_probe(dev);
 		mddev = mddev_find(dev);
-		if (!mddev || !mddev->gendisk) {
-			if (mddev)
-				mddev_put(mddev);
+		if (!mddev)
 			break;
-		}
+
 		if (mddev_lock(mddev))
 			pr_warn("md: %s locked, cannot run\n", mdname(mddev));
 		else if (mddev->raid_disks || mddev->major_version
@@ -7821,8 +7836,7 @@ static int md_open(struct block_device *bdev, fmode_t mode)
 		/* Wait until bdev->bd_disk is definitely gone */
 		if (work_pending(&mddev->del_work))
 			flush_workqueue(md_misc_wq);
-		/* Then retry the open from the top */
-		return -ERESTARTSYS;
+		return -EBUSY;
 	}
 	BUG_ON(mddev != bdev->bd_disk->private_data);
 
@@ -8153,7 +8167,11 @@ static void *md_seq_start(struct seq_file *seq, loff_t *pos)
 	loff_t l = *pos;
 	struct mddev *mddev;
 
-	if (l >= 0x10000)
+	if (l == 0x10000) {
+		++*pos;
+		return (void *)2;
+	}
+	if (l > 0x10000)
 		return NULL;
 	if (!l--)
 		/* header */
@@ -8575,6 +8593,26 @@ void md_write_end(struct mddev *mddev)
 
 EXPORT_SYMBOL(md_write_end);
 
+/* This is used by raid0 and raid10 */
+void md_submit_discard_bio(struct mddev *mddev, struct md_rdev *rdev,
+			struct bio *bio, sector_t start, sector_t size)
+{
+	struct bio *discard_bio = NULL;
+
+	if (__blkdev_issue_discard(rdev->bdev, start, size, GFP_NOIO, 0,
+			&discard_bio) || !discard_bio)
+		return;
+
+	bio_chain(discard_bio, bio);
+	bio_clone_blkg_association(discard_bio, bio);
+	if (mddev->gendisk)
+		trace_block_bio_remap(discard_bio,
+				disk_devt(mddev->gendisk),
+				bio->bi_iter.bi_sector);
+	submit_bio_noacct(discard_bio);
+}
+EXPORT_SYMBOL_GPL(md_submit_discard_bio);
+
 /* md_allow_write(mddev)
  * Calling this ensures that the array is marked 'active' so that writes
  * may proceed without blocking.  It is important to call this before
@@ -9251,11 +9289,11 @@ void md_check_recovery(struct mddev *mddev)
 		}
 
 		if (mddev_is_clustered(mddev)) {
-			struct md_rdev *rdev;
+			struct md_rdev *rdev, *tmp;
 			/* kick the device if another node issued a
 			 * remove disk.
 			 */
-			rdev_for_each(rdev, mddev) {
+			rdev_for_each_safe(rdev, tmp, mddev) {
 				if (test_and_clear_bit(ClusterRemove, &rdev->flags) &&
 						rdev->raid_disk < 0)
 					md_kick_rdev_from_array(rdev);
@@ -9569,7 +9607,7 @@ err_wq:
 static void check_sb_changes(struct mddev *mddev, struct md_rdev *rdev)
 {
 	struct mdp_superblock_1 *sb = page_address(rdev->sb_page);
-	struct md_rdev *rdev2;
+	struct md_rdev *rdev2, *tmp;
 	int role, ret;
 	char b[BDEVNAME_SIZE];
 
@@ -9586,7 +9624,7 @@ static void check_sb_changes(struct mddev *mddev, struct md_rdev *rdev)
 	}
 
 	/* Check for change of roles in the active devices */
-	rdev_for_each(rdev2, mddev) {
+	rdev_for_each_safe(rdev2, tmp, mddev) {
 		if (test_bit(Faulty, &rdev2->flags))
 			continue;