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

* 'for-linus' of git://neil.brown.name/md: (45 commits)
  md: don't insist on valid event count for spare devices.
  md: simplify updating of event count to sometimes avoid updating spares.
  md/raid6: Fix raid-6 read-error correction in degraded state
  md: restore ability of spare drives to spin down.
  md: Fix read balancing in RAID1 and RAID10 on drives > 2TB
  md/linear: standardise all printk messages
  md/raid0: tidy up printk messages.
  md/raid10: tidy up printk messages.
  md/raid1: improve printk messages
  md/raid5: improve consistency of error messages.
  md: remove EXPERIMENTAL designation from RAID10
  md: allow integers to be passed to md/level
  md: notify mdstat waiters of level change
  md/raid4: permit raid0 takeover
  md/raid1: delay reads that could overtake behind-writes.
  md/raid1: fix confusing 'redirect sector' message.
  md: don't unregister the thread in mddev_suspend
  md: factor out init code for an mddev
  md: pass mddev to make_request functions rather than request_queue
  md: call md_stop_writes from md_stop
  ...

drivers/md/Kconfig

@@ -100,8 +100,8 @@ config MD_RAID1
 	  If unsure, say Y.
 
 config MD_RAID10
-	tristate "RAID-10 (mirrored striping) mode (EXPERIMENTAL)"
-	depends on BLK_DEV_MD && EXPERIMENTAL
+	tristate "RAID-10 (mirrored striping) mode"
+	depends on BLK_DEV_MD
 	---help---
 	  RAID-10 provides a combination of striping (RAID-0) and
 	  mirroring (RAID-1) with easier configuration and more flexible

drivers/md/bitmap.c

@@ -505,7 +505,7 @@ void bitmap_update_sb(struct bitmap *bitmap)
 		return;
 	}
 	spin_unlock_irqrestore(&bitmap->lock, flags);
-	sb = (bitmap_super_t *)kmap_atomic(bitmap->sb_page, KM_USER0);
+	sb = kmap_atomic(bitmap->sb_page, KM_USER0);
 	sb->events = cpu_to_le64(bitmap->mddev->events);
 	if (bitmap->mddev->events < bitmap->events_cleared) {
 		/* rocking back to read-only */
@@ -526,7 +526,7 @@ void bitmap_print_sb(struct bitmap *bitmap)
 
 	if (!bitmap || !bitmap->sb_page)
 		return;
-	sb = (bitmap_super_t *)kmap_atomic(bitmap->sb_page, KM_USER0);
+	sb = kmap_atomic(bitmap->sb_page, KM_USER0);
 	printk(KERN_DEBUG "%s: bitmap file superblock:\n", bmname(bitmap));
 	printk(KERN_DEBUG "         magic: %08x\n", le32_to_cpu(sb->magic));
 	printk(KERN_DEBUG "       version: %d\n", le32_to_cpu(sb->version));
@@ -575,7 +575,7 @@ static int bitmap_read_sb(struct bitmap *bitmap)
 		return err;
 	}
 
-	sb = (bitmap_super_t *)kmap_atomic(bitmap->sb_page, KM_USER0);
+	sb = kmap_atomic(bitmap->sb_page, KM_USER0);
 
 	chunksize = le32_to_cpu(sb->chunksize);
 	daemon_sleep = le32_to_cpu(sb->daemon_sleep) * HZ;
@@ -661,7 +661,7 @@ static int bitmap_mask_state(struct bitmap *bitmap, enum bitmap_state bits,
 		return 0;
 	}
 	spin_unlock_irqrestore(&bitmap->lock, flags);
-	sb = (bitmap_super_t *)kmap_atomic(bitmap->sb_page, KM_USER0);
+	sb = kmap_atomic(bitmap->sb_page, KM_USER0);
 	old = le32_to_cpu(sb->state) & bits;
 	switch (op) {
 		case MASK_SET: sb->state |= cpu_to_le32(bits);
@@ -1292,9 +1292,14 @@ int bitmap_startwrite(struct bitmap *bitmap, sector_t offset, unsigned long sect
 	if (!bitmap) return 0;
 
 	if (behind) {
+		int bw;
 		atomic_inc(&bitmap->behind_writes);
+		bw = atomic_read(&bitmap->behind_writes);
+		if (bw > bitmap->behind_writes_used)
+			bitmap->behind_writes_used = bw;
+
 		PRINTK(KERN_DEBUG "inc write-behind count %d/%d\n",
-		  atomic_read(&bitmap->behind_writes), bitmap->max_write_behind);
+		       bw, bitmap->max_write_behind);
 	}
 
 	while (sectors) {
@@ -1351,7 +1356,8 @@ void bitmap_endwrite(struct bitmap *bitmap, sector_t offset, unsigned long secto
 {
 	if (!bitmap) return;
 	if (behind) {
-		atomic_dec(&bitmap->behind_writes);
+		if (atomic_dec_and_test(&bitmap->behind_writes))
+			wake_up(&bitmap->behind_wait);
 		PRINTK(KERN_DEBUG "dec write-behind count %d/%d\n",
 		  atomic_read(&bitmap->behind_writes), bitmap->max_write_behind);
 	}
@@ -1675,6 +1681,7 @@ int bitmap_create(mddev_t *mddev)
 	atomic_set(&bitmap->pending_writes, 0);
 	init_waitqueue_head(&bitmap->write_wait);
 	init_waitqueue_head(&bitmap->overflow_wait);
+	init_waitqueue_head(&bitmap->behind_wait);
 
 	bitmap->mddev = mddev;
 
@@ -2006,6 +2013,27 @@ static ssize_t can_clear_store(mddev_t *mddev, const char *buf, size_t len)
 static struct md_sysfs_entry bitmap_can_clear =
 __ATTR(can_clear, S_IRUGO|S_IWUSR, can_clear_show, can_clear_store);
 
+static ssize_t
+behind_writes_used_show(mddev_t *mddev, char *page)
+{
+	if (mddev->bitmap == NULL)
+		return sprintf(page, "0\n");
+	return sprintf(page, "%lu\n",
+		       mddev->bitmap->behind_writes_used);
+}
+
+static ssize_t
+behind_writes_used_reset(mddev_t *mddev, const char *buf, size_t len)
+{
+	if (mddev->bitmap)
+		mddev->bitmap->behind_writes_used = 0;
+	return len;
+}
+
+static struct md_sysfs_entry max_backlog_used =
+__ATTR(max_backlog_used, S_IRUGO | S_IWUSR,
+       behind_writes_used_show, behind_writes_used_reset);
+
 static struct attribute *md_bitmap_attrs[] = {
 	&bitmap_location.attr,
 	&bitmap_timeout.attr,
@@ -2013,6 +2041,7 @@ static struct attribute *md_bitmap_attrs[] = {
 	&bitmap_chunksize.attr,
 	&bitmap_metadata.attr,
 	&bitmap_can_clear.attr,
+	&max_backlog_used.attr,
 	NULL
 };
 struct attribute_group md_bitmap_group = {

drivers/md/bitmap.h

@@ -227,6 +227,7 @@ struct bitmap {
 	int allclean;
 
 	atomic_t behind_writes;
+	unsigned long behind_writes_used; /* highest actual value at runtime */
 
 	/*
 	 * the bitmap daemon - periodically wakes up and sweeps the bitmap
@@ -239,6 +240,7 @@ struct bitmap {
 	atomic_t pending_writes; /* pending writes to the bitmap file */
 	wait_queue_head_t write_wait;
 	wait_queue_head_t overflow_wait;
+	wait_queue_head_t behind_wait;
 
 	struct sysfs_dirent *sysfs_can_clear;
 };

drivers/md/faulty.c

@@ -169,10 +169,9 @@ static void add_sector(conf_t *conf, sector_t start, int mode)
 		conf->nfaults = n+1;
 }
 
-static int make_request(struct request_queue *q, struct bio *bio)
+static int make_request(mddev_t *mddev, struct bio *bio)
 {
-	mddev_t *mddev = q->queuedata;
-	conf_t *conf = (conf_t*)mddev->private;
+	conf_t *conf = mddev->private;
 	int failit = 0;
 
 	if (bio_data_dir(bio) == WRITE) {
@@ -225,7 +224,7 @@ static int make_request(struct request_queue *q, struct bio *bio)
 
 static void status(struct seq_file *seq, mddev_t *mddev)
 {
-	conf_t *conf = (conf_t*)mddev->private;
+	conf_t *conf = mddev->private;
 	int n;
 
 	if ((n=atomic_read(&conf->counters[WriteTransient])) != 0)
@@ -328,7 +327,7 @@ static int run(mddev_t *mddev)
 
 static int stop(mddev_t *mddev)
 {
-	conf_t *conf = (conf_t *)mddev->private;
+	conf_t *conf = mddev->private;
 
 	kfree(conf);
 	mddev->private = NULL;

drivers/md/linear.c

@@ -159,7 +159,8 @@ static linear_conf_t *linear_conf(mddev_t *mddev, int raid_disks)
 		sector_t sectors;
 
 		if (j < 0 || j >= raid_disks || disk->rdev) {
-			printk("linear: disk numbering problem. Aborting!\n");
+			printk(KERN_ERR "md/linear:%s: disk numbering problem. Aborting!\n",
+			       mdname(mddev));
 			goto out;
 		}
 
@@ -187,7 +188,8 @@ static linear_conf_t *linear_conf(mddev_t *mddev, int raid_disks)
 
 	}
 	if (cnt != raid_disks) {
-		printk("linear: not enough drives present. Aborting!\n");
+		printk(KERN_ERR "md/linear:%s: not enough drives present. Aborting!\n",
+		       mdname(mddev));
 		goto out;
 	}
 
@@ -282,29 +284,21 @@ static int linear_stop (mddev_t *mddev)
 	rcu_barrier();
 	blk_sync_queue(mddev->queue); /* the unplug fn references 'conf'*/
 	kfree(conf);
+	mddev->private = NULL;
 
 	return 0;
 }
 
-static int linear_make_request (struct request_queue *q, struct bio *bio)
+static int linear_make_request (mddev_t *mddev, struct bio *bio)
 {
-	const int rw = bio_data_dir(bio);
-	mddev_t *mddev = q->queuedata;
 	dev_info_t *tmp_dev;
 	sector_t start_sector;
-	int cpu;
 
 	if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER))) {
 		md_barrier_request(mddev, bio);
 		return 0;
 	}
 
-	cpu = part_stat_lock();
-	part_stat_inc(cpu, &mddev->gendisk->part0, ios[rw]);
-	part_stat_add(cpu, &mddev->gendisk->part0, sectors[rw],
-		      bio_sectors(bio));
-	part_stat_unlock();
-
 	rcu_read_lock();
 	tmp_dev = which_dev(mddev, bio->bi_sector);
 	start_sector = tmp_dev->end_sector - tmp_dev->rdev->sectors;
@@ -314,8 +308,10 @@ static int linear_make_request (struct request_queue *q, struct bio *bio)
 		     || (bio->bi_sector < start_sector))) {
 		char b[BDEVNAME_SIZE];
 
-		printk("linear_make_request: Sector %llu out of bounds on "
+		printk(KERN_ERR
+		       "md/linear:%s: make_request: Sector %llu out of bounds on "
 		       "dev %s: %llu sectors, offset %llu\n",
+		       mdname(mddev),
 		       (unsigned long long)bio->bi_sector,
 		       bdevname(tmp_dev->rdev->bdev, b),
 		       (unsigned long long)tmp_dev->rdev->sectors,
@@ -336,9 +332,9 @@ static int linear_make_request (struct request_queue *q, struct bio *bio)
 
 		bp = bio_split(bio, end_sector - bio->bi_sector);
 
-		if (linear_make_request(q, &bp->bio1))
+		if (linear_make_request(mddev, &bp->bio1))
 			generic_make_request(&bp->bio1);
-		if (linear_make_request(q, &bp->bio2))
+		if (linear_make_request(mddev, &bp->bio2))
 			generic_make_request(&bp->bio2);
 		bio_pair_release(bp);
 		return 0;

drivers/md/md.h

@@ -74,9 +74,6 @@ struct mdk_rdev_s
 #define Blocked		8		/* An error occured on an externally
 					 * managed array, don't allow writes
 					 * until it is cleared */
-#define StateChanged	9		/* Faulty or Blocked has changed during
-					 * interrupt, so it needs to be
-					 * notified by the thread */
 	wait_queue_head_t blocked_wait;
 
 	int desc_nr;			/* descriptor index in the superblock */
@@ -153,6 +150,12 @@ struct mddev_s
 	int				external_size; /* size managed
 							* externally */
 	__u64				events;
+	/* If the last 'event' was simply a clean->dirty transition, and
+	 * we didn't write it to the spares, then it is safe and simple
+	 * to just decrement the event count on a dirty->clean transition.
+	 * So we record that possibility here.
+	 */
+	int				can_decrease_events;
 
 	char				uuid[16];
 
@@ -240,7 +243,6 @@ struct mddev_s
 	atomic_t			active;		/* general refcount */
 	atomic_t			openers;	/* number of active opens */
 
-	int				changed;	/* true if we might need to reread partition info */
 	int				degraded;	/* whether md should consider
 							 * adding a spare
 							 */
@@ -279,9 +281,6 @@ struct mddev_s
 	atomic_t			writes_pending; 
 	struct request_queue		*queue;	/* for plugging ... */
 
-	atomic_t                        write_behind; /* outstanding async IO */
-	unsigned int                    max_write_behind; /* 0 = sync */
-
 	struct bitmap                   *bitmap; /* the bitmap for the device */
 	struct {
 		struct file		*file; /* the bitmap file */
@@ -305,6 +304,7 @@ struct mddev_s
 	atomic_t 			max_corr_read_errors; /* max read retries */
 	struct list_head		all_mddevs;
 
+	struct attribute_group		*to_remove;
 	/* Generic barrier handling.
 	 * If there is a pending barrier request, all other
 	 * writes are blocked while the devices are flushed.
@@ -336,7 +336,7 @@ struct mdk_personality
 	int level;
 	struct list_head list;
 	struct module *owner;
-	int (*make_request)(struct request_queue *q, struct bio *bio);
+	int (*make_request)(mddev_t *mddev, struct bio *bio);
 	int (*run)(mddev_t *mddev);
 	int (*stop)(mddev_t *mddev);
 	void (*status)(struct seq_file *seq, mddev_t *mddev);

drivers/md/multipath.c

@@ -85,7 +85,7 @@ static void multipath_end_bh_io (struct multipath_bh *mp_bh, int err)
 static void multipath_end_request(struct bio *bio, int error)
 {
 	int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
-	struct multipath_bh * mp_bh = (struct multipath_bh *)(bio->bi_private);
+	struct multipath_bh *mp_bh = bio->bi_private;
 	multipath_conf_t *conf = mp_bh->mddev->private;
 	mdk_rdev_t *rdev = conf->multipaths[mp_bh->path].rdev;
 
@@ -136,14 +136,11 @@ static void multipath_unplug(struct request_queue *q)
 }
 
 
-static int multipath_make_request (struct request_queue *q, struct bio * bio)
+static int multipath_make_request(mddev_t *mddev, struct bio * bio)
 {
-	mddev_t *mddev = q->queuedata;
 	multipath_conf_t *conf = mddev->private;
 	struct multipath_bh * mp_bh;
 	struct multipath_info *multipath;
-	const int rw = bio_data_dir(bio);
-	int cpu;
 
 	if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER))) {
 		md_barrier_request(mddev, bio);
@@ -155,12 +152,6 @@ static int multipath_make_request (struct request_queue *q, struct bio * bio)
 	mp_bh->master_bio = bio;
 	mp_bh->mddev = mddev;
 
-	cpu = part_stat_lock();
-	part_stat_inc(cpu, &mddev->gendisk->part0, ios[rw]);
-	part_stat_add(cpu, &mddev->gendisk->part0, sectors[rw],
-		      bio_sectors(bio));
-	part_stat_unlock();
-
 	mp_bh->path = multipath_map(conf);
 	if (mp_bh->path < 0) {
 		bio_endio(bio, -EIO);

drivers/md/raid0.h

@@ -13,6 +13,9 @@ struct raid0_private_data
 	struct strip_zone *strip_zone;
 	mdk_rdev_t **devlist; /* lists of rdevs, pointed to by strip_zone->dev */
 	int nr_strip_zones;
+	int scale_raid_disks; /* divide rdev->raid_disks by this in run()
+			       * to handle conversion from raid10
+			       */
 };
 
 typedef struct raid0_private_data raid0_conf_t;

drivers/md/raid10.h

@@ -33,9 +33,16 @@ struct r10_private_data_s {
 					       * 1 stripe.
 					       */
 
+	sector_t		dev_sectors;  /* temp copy of mddev->dev_sectors */
+
 	int chunk_shift; /* shift from chunks to sectors */
 	sector_t chunk_mask;
 
+	int			scale_disks;  /* When starting array, multiply
+					       * each ->raid_disk by this.
+					       * Need for raid0->raid10 migration
+					       */
+
 	struct list_head	retry_list;
 	/* queue pending writes and submit them on unplug */
 	struct bio_list		pending_bio_list;
@@ -57,6 +64,11 @@ struct r10_private_data_s {
 	mempool_t *r10bio_pool;
 	mempool_t *r10buf_pool;
 	struct page		*tmppage;
+
+	/* When taking over an array from a different personality, we store
+	 * the new thread here until we fully activate the array.
+	 */
+	struct mdk_thread_s	*thread;
 };
 
 typedef struct r10_private_data_s conf_t;