Merge branch 'for-linus' of git://neil.brown.name/md

* 'for-linus' of git://neil.brown.name/md:
  md: raid5 crash during degradation
  md/raid5: never wait for bad-block acks on failed device.
  md: ensure new badblocks are handled promptly.
  md: bad blocks shouldn't cause a Blocked status on a Faulty device.
  md: take a reference to mddev during sysfs access.
  md: refine interpretation of "hold_active == UNTIL_IOCTL".
  md/lock: ensure updates to page_attrs are properly locked.

3 files changed, 32 insertions, 7 deletions

diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
index 7878712721b..b6907118283 100644
--- a/drivers/md/bitmap.c
+++ b/drivers/md/bitmap.c
@@ -1106,10 +1106,12 @@ void bitmap_write_all(struct bitmap *bitmap)
 	 */
 	int i;
 
+	spin_lock_irq(&bitmap->lock);
 	for (i = 0; i < bitmap->file_pages; i++)
 		set_page_attr(bitmap, bitmap->filemap[i],
 			      BITMAP_PAGE_NEEDWRITE);
 	bitmap->allclean = 0;
+	spin_unlock_irq(&bitmap->lock);
 }
 
 static void bitmap_count_page(struct bitmap *bitmap, sector_t offset, int inc)
@@ -1605,7 +1607,9 @@ void bitmap_dirty_bits(struct bitmap *bitmap, unsigned long s, unsigned long e)
 	for (chunk = s; chunk <= e; chunk++) {
 		sector_t sec = (sector_t)chunk << CHUNK_BLOCK_SHIFT(bitmap);
 		bitmap_set_memory_bits(bitmap, sec, 1);
+		spin_lock_irq(&bitmap->lock);
 		bitmap_file_set_bit(bitmap, sec);
+		spin_unlock_irq(&bitmap->lock);
 		if (sec < bitmap->mddev->recovery_cp)
 			/* We are asserting that the array is dirty,
 			 * so move the recovery_cp address back so
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 84acfe7d10e..ee981737edf 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -570,7 +570,7 @@ static void mddev_put(struct mddev *mddev)
 	    mddev->ctime == 0 && !mddev->hold_active) {
 		/* Array is not configured at all, and not held active,
 		 * so destroy it */
-		list_del(&mddev->all_mddevs);
+		list_del_init(&mddev->all_mddevs);
 		bs = mddev->bio_set;
 		mddev->bio_set = NULL;
 		if (mddev->gendisk) {
@@ -2546,7 +2546,8 @@ state_show(struct md_rdev *rdev, char *page)
 		sep = ",";
 	}
 	if (test_bit(Blocked, &rdev->flags) ||
-	    rdev->badblocks.unacked_exist) {
+	    (rdev->badblocks.unacked_exist
+	     && !test_bit(Faulty, &rdev->flags))) {
 		len += sprintf(page+len, "%sblocked", sep);
 		sep = ",";
 	}
@@ -3788,6 +3789,8 @@ array_state_store(struct mddev *mddev, const char *buf, size_t len)
 	if (err)
 		return err;
 	else {
+		if (mddev->hold_active == UNTIL_IOCTL)
+			mddev->hold_active = 0;
 		sysfs_notify_dirent_safe(mddev->sysfs_state);
 		return len;
 	}
@@ -4487,11 +4490,20 @@ md_attr_show(struct kobject *kobj, struct attribute *attr, char *page)
 
 	if (!entry->show)
 		return -EIO;
+	spin_lock(&all_mddevs_lock);
+	if (list_empty(&mddev->all_mddevs)) {
+		spin_unlock(&all_mddevs_lock);
+		return -EBUSY;
+	}
+	mddev_get(mddev);
+	spin_unlock(&all_mddevs_lock);
+
 	rv = mddev_lock(mddev);
 	if (!rv) {
 		rv = entry->show(mddev, page);
 		mddev_unlock(mddev);
 	}
+	mddev_put(mddev);
 	return rv;
 }
 
@@ -4507,13 +4519,19 @@ md_attr_store(struct kobject *kobj, struct attribute *attr,
 		return -EIO;
 	if (!capable(CAP_SYS_ADMIN))
 		return -EACCES;
+	spin_lock(&all_mddevs_lock);
+	if (list_empty(&mddev->all_mddevs)) {
+		spin_unlock(&all_mddevs_lock);
+		return -EBUSY;
+	}
+	mddev_get(mddev);
+	spin_unlock(&all_mddevs_lock);
 	rv = mddev_lock(mddev);
-	if (mddev->hold_active == UNTIL_IOCTL)
-		mddev->hold_active = 0;
 	if (!rv) {
 		rv = entry->store(mddev, page, length);
 		mddev_unlock(mddev);
 	}
+	mddev_put(mddev);
 	return rv;
 }
 
@@ -7840,6 +7858,7 @@ int rdev_set_badblocks(struct md_rdev *rdev, sector_t s, int sectors,
 				  s + rdev->data_offset, sectors, acknowledged);
 	if (rv) {
 		/* Make sure they get written out promptly */
+		sysfs_notify_dirent_safe(rdev->sysfs_state);
 		set_bit(MD_CHANGE_CLEAN, &rdev->mddev->flags);
 		md_wakeup_thread(rdev->mddev->thread);
 	}
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 297e2609217..31670f8d6b6 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -3036,6 +3036,8 @@ static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s)
 		if (dev->written)
 			s->written++;
 		rdev = rcu_dereference(conf->disks[i].rdev);
+		if (rdev && test_bit(Faulty, &rdev->flags))
+			rdev = NULL;
 		if (rdev) {
 			is_bad = is_badblock(rdev, sh->sector, STRIPE_SECTORS,
 					     &first_bad, &bad_sectors);
@@ -3063,12 +3065,12 @@ static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s)
 			}
 		} else if (test_bit(In_sync, &rdev->flags))
 			set_bit(R5_Insync, &dev->flags);
-		else if (!test_bit(Faulty, &rdev->flags)) {
+		else {
 			/* in sync if before recovery_offset */
 			if (sh->sector + STRIPE_SECTORS <= rdev->recovery_offset)
 				set_bit(R5_Insync, &dev->flags);
 		}
-		if (test_bit(R5_WriteError, &dev->flags)) {
+		if (rdev && test_bit(R5_WriteError, &dev->flags)) {
 			clear_bit(R5_Insync, &dev->flags);
 			if (!test_bit(Faulty, &rdev->flags)) {
 				s->handle_bad_blocks = 1;
@@ -3076,7 +3078,7 @@ static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s)
 			} else
 				clear_bit(R5_WriteError, &dev->flags);
 		}
-		if (test_bit(R5_MadeGood, &dev->flags)) {
+		if (rdev && test_bit(R5_MadeGood, &dev->flags)) {
 			if (!test_bit(Faulty, &rdev->flags)) {
 				s->handle_bad_blocks = 1;
 				atomic_inc(&rdev->nr_pending);