Merge tag 'md-3.4' of git://neil.brown.name/md

Pull md updates for 3.4 from Neil Brown:
 "Mostly tidying up code in preparation for some bigger changes next
  time.

  A few bug fixes tagged for -stable.

  Main functionality change is that some RAID10 arrays can now grow to
  use extra space that may have been made available on the individual
  devices."

Fixed up trivial conflicts with the k[un]map_atomic() cleanups in
drivers/md/bitmap.c.

* tag 'md-3.4' of git://neil.brown.name/md: (22 commits)
  md: Add judgement bb->unacked_exist in function md_ack_all_badblocks().
  md: fix clearing of the 'changed' flags for the bad blocks list.
  md/bitmap: discard CHUNK_BLOCK_SHIFT macro
  md/bitmap: remove unnecessary indirection when allocating.
  md/bitmap: remove some pointless locking.
  md/bitmap: change a 'goto' to a normal 'if' construct.
  md/bitmap: move printing of bitmap status to bitmap.c
  md/bitmap: remove some unused noise from bitmap.h
  md/raid10 - support resizing some RAID10 arrays.
  md/raid1: handle merge_bvec_fn in member devices.
  md/raid10: handle merge_bvec_fn in member devices.
  md: add proper merge_bvec handling to RAID0 and Linear.
  md: tidy up rdev_for_each usage.
  md/raid1,raid10: avoid deadlock during resync/recovery.
  md/bitmap: ensure to load bitmap when creating via sysfs.
  md: don't set md arrays to readonly on shutdown.
  md: allow re-add to failed arrays.
  md/raid5: use atomic_dec_return() instead of atomic_dec() and atomic_read().
  md: Use existed macros instead of numbers
  md/raid5: removed unused 'added_devices' variable.
  ...

13 files changed, 491 insertions, 373 deletions

diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
index 045e086144ad..3d0dfa7a89a2 100644
--- a/drivers/md/bitmap.c
+++ b/drivers/md/bitmap.c
@@ -26,6 +26,7 @@
 #include <linux/file.h>
 #include <linux/mount.h>
 #include <linux/buffer_head.h>
+#include <linux/seq_file.h>
 #include "md.h"
 #include "bitmap.h"
 
@@ -35,31 +36,6 @@ static inline char *bmname(struct bitmap *bitmap)
 }
 
 /*
- * just a placeholder - calls kmalloc for bitmap pages
- */
-static unsigned char *bitmap_alloc_page(struct bitmap *bitmap)
-{
-	unsigned char *page;
-
-	page = kzalloc(PAGE_SIZE, GFP_NOIO);
-	if (!page)
-		printk("%s: bitmap_alloc_page FAILED\n", bmname(bitmap));
-	else
-		pr_debug("%s: bitmap_alloc_page: allocated page at %p\n",
-			 bmname(bitmap), page);
-	return page;
-}
-
-/*
- * for now just a placeholder -- just calls kfree for bitmap pages
- */
-static void bitmap_free_page(struct bitmap *bitmap, unsigned char *page)
-{
-	pr_debug("%s: bitmap_free_page: free page %p\n", bmname(bitmap), page);
-	kfree(page);
-}
-
-/*
  * check a page and, if necessary, allocate it (or hijack it if the alloc fails)
  *
  * 1) check to see if this page is allocated, if it's not then try to alloc
@@ -96,7 +72,7 @@ __acquires(bitmap->lock)
 	/* this page has not been allocated yet */
 
 	spin_unlock_irq(&bitmap->lock);
-	mappage = bitmap_alloc_page(bitmap);
+	mappage = kzalloc(PAGE_SIZE, GFP_NOIO);
 	spin_lock_irq(&bitmap->lock);
 
 	if (mappage == NULL) {
@@ -109,7 +85,7 @@ __acquires(bitmap->lock)
 	} else if (bitmap->bp[page].map ||
 		   bitmap->bp[page].hijacked) {
 		/* somebody beat us to getting the page */
-		bitmap_free_page(bitmap, mappage);
+		kfree(mappage);
 		return 0;
 	} else {
 
@@ -141,7 +117,7 @@ static void bitmap_checkfree(struct bitmap *bitmap, unsigned long page)
 		ptr = bitmap->bp[page].map;
 		bitmap->bp[page].map = NULL;
 		bitmap->missing_pages++;
-		bitmap_free_page(bitmap, ptr);
+		kfree(ptr);
 	}
 }
 
@@ -171,7 +147,7 @@ static struct page *read_sb_page(struct mddev *mddev, loff_t offset,
 		did_alloc = 1;
 	}
 
-	list_for_each_entry(rdev, &mddev->disks, same_set) {
+	rdev_for_each(rdev, mddev) {
 		if (! test_bit(In_sync, &rdev->flags)
 		    || test_bit(Faulty, &rdev->flags))
 			continue;
@@ -445,18 +421,13 @@ out:
 void bitmap_update_sb(struct bitmap *bitmap)
 {
 	bitmap_super_t *sb;
-	unsigned long flags;
 
 	if (!bitmap || !bitmap->mddev) /* no bitmap for this array */
 		return;
 	if (bitmap->mddev->bitmap_info.external)
 		return;
-	spin_lock_irqsave(&bitmap->lock, flags);
-	if (!bitmap->sb_page) { /* no superblock */
-		spin_unlock_irqrestore(&bitmap->lock, flags);
+	if (!bitmap->sb_page) /* no superblock */
 		return;
-	}
-	spin_unlock_irqrestore(&bitmap->lock, flags);
 	sb = kmap_atomic(bitmap->sb_page);
 	sb->events = cpu_to_le64(bitmap->mddev->events);
 	if (bitmap->mddev->events < bitmap->events_cleared)
@@ -632,26 +603,28 @@ static int bitmap_read_sb(struct bitmap *bitmap)
 	/* keep the array size field of the bitmap superblock up to date */
 	sb->sync_size = cpu_to_le64(bitmap->mddev->resync_max_sectors);
 
-	if (!bitmap->mddev->persistent)
-		goto success;
-
-	/*
-	 * if we have a persistent array superblock, compare the
-	 * bitmap's UUID and event counter to the mddev's
-	 */
-	if (memcmp(sb->uuid, bitmap->mddev->uuid, 16)) {
-		printk(KERN_INFO "%s: bitmap superblock UUID mismatch\n",
-			bmname(bitmap));
-		goto out;
-	}
-	events = le64_to_cpu(sb->events);
-	if (events < bitmap->mddev->events) {
-		printk(KERN_INFO "%s: bitmap file is out of date (%llu < %llu) "
-			"-- forcing full recovery\n", bmname(bitmap), events,
-			(unsigned long long) bitmap->mddev->events);
-		sb->state |= cpu_to_le32(BITMAP_STALE);
+	if (bitmap->mddev->persistent) {
+		/*
+		 * We have a persistent array superblock, so compare the
+		 * bitmap's UUID and event counter to the mddev's
+		 */
+		if (memcmp(sb->uuid, bitmap->mddev->uuid, 16)) {
+			printk(KERN_INFO
+			       "%s: bitmap superblock UUID mismatch\n",
+			       bmname(bitmap));
+			goto out;
+		}
+		events = le64_to_cpu(sb->events);
+		if (events < bitmap->mddev->events) {
+			printk(KERN_INFO
+			       "%s: bitmap file is out of date (%llu < %llu) "
+			       "-- forcing full recovery\n",
+			       bmname(bitmap), events,
+			       (unsigned long long) bitmap->mddev->events);
+			sb->state |= cpu_to_le32(BITMAP_STALE);
+		}
 	}
-success:
+
 	/* assign fields using values from superblock */
 	bitmap->mddev->bitmap_info.chunksize = chunksize;
 	bitmap->mddev->bitmap_info.daemon_sleep = daemon_sleep;
@@ -680,15 +653,10 @@ static int bitmap_mask_state(struct bitmap *bitmap, enum bitmap_state bits,
 			     enum bitmap_mask_op op)
 {
 	bitmap_super_t *sb;
-	unsigned long flags;
 	int old;
 
-	spin_lock_irqsave(&bitmap->lock, flags);
-	if (!bitmap->sb_page) { /* can't set the state */
-		spin_unlock_irqrestore(&bitmap->lock, flags);
+	if (!bitmap->sb_page) /* can't set the state */
 		return 0;
-	}
-	spin_unlock_irqrestore(&bitmap->lock, flags);
 	sb = kmap_atomic(bitmap->sb_page);
 	old = le32_to_cpu(sb->state) & bits;
 	switch (op) {
@@ -870,7 +838,7 @@ static void bitmap_file_set_bit(struct bitmap *bitmap, sector_t block)
 	unsigned long bit;
 	struct page *page;
 	void *kaddr;
-	unsigned long chunk = block >> CHUNK_BLOCK_SHIFT(bitmap);
+	unsigned long chunk = block >> bitmap->chunkshift;
 
 	if (!bitmap->filemap)
 		return;
@@ -1069,10 +1037,10 @@ static int bitmap_init_from_disk(struct bitmap *bitmap, sector_t start)
 		kunmap_atomic(paddr);
 		if (b) {
 			/* if the disk bit is set, set the memory bit */
-			int needed = ((sector_t)(i+1) << (CHUNK_BLOCK_SHIFT(bitmap))
+			int needed = ((sector_t)(i+1) << bitmap->chunkshift
 				      >= start);
 			bitmap_set_memory_bits(bitmap,
-					       (sector_t)i << CHUNK_BLOCK_SHIFT(bitmap),
+					       (sector_t)i << bitmap->chunkshift,
 					       needed);
 			bit_cnt++;
 		}
@@ -1116,7 +1084,7 @@ void bitmap_write_all(struct bitmap *bitmap)
 
 static void bitmap_count_page(struct bitmap *bitmap, sector_t offset, int inc)
 {
-	sector_t chunk = offset >> CHUNK_BLOCK_SHIFT(bitmap);
+	sector_t chunk = offset >> bitmap->chunkshift;
 	unsigned long page = chunk >> PAGE_COUNTER_SHIFT;
 	bitmap->bp[page].count += inc;
 	bitmap_checkfree(bitmap, page);
@@ -1222,7 +1190,7 @@ void bitmap_daemon_work(struct mddev *mddev)
 				bitmap->allclean = 0;
 		}
 		bmc = bitmap_get_counter(bitmap,
-					 (sector_t)j << CHUNK_BLOCK_SHIFT(bitmap),
+					 (sector_t)j << bitmap->chunkshift,
 					 &blocks, 0);
 		if (!bmc)
 			j |= PAGE_COUNTER_MASK;
@@ -1231,7 +1199,7 @@ void bitmap_daemon_work(struct mddev *mddev)
 				/* we can clear the bit */
 				*bmc = 0;
 				bitmap_count_page(bitmap,
-						  (sector_t)j << CHUNK_BLOCK_SHIFT(bitmap),
+						  (sector_t)j << bitmap->chunkshift,
 						  -1);
 
 				/* clear the bit */
@@ -1285,7 +1253,7 @@ __acquires(bitmap->lock)
 	 * The lock must have been taken with interrupts enabled.
 	 * If !create, we don't release the lock.
 	 */
-	sector_t chunk = offset >> CHUNK_BLOCK_SHIFT(bitmap);
+	sector_t chunk = offset >> bitmap->chunkshift;
 	unsigned long page = chunk >> PAGE_COUNTER_SHIFT;
 	unsigned long pageoff = (chunk & PAGE_COUNTER_MASK) << COUNTER_BYTE_SHIFT;
 	sector_t csize;
@@ -1295,10 +1263,10 @@ __acquires(bitmap->lock)
 
 	if (bitmap->bp[page].hijacked ||
 	    bitmap->bp[page].map == NULL)
-		csize = ((sector_t)1) << (CHUNK_BLOCK_SHIFT(bitmap) +
+		csize = ((sector_t)1) << (bitmap->chunkshift +
 					  PAGE_COUNTER_SHIFT - 1);
 	else
-		csize = ((sector_t)1) << (CHUNK_BLOCK_SHIFT(bitmap));
+		csize = ((sector_t)1) << bitmap->chunkshift;
 	*blocks = csize - (offset & (csize - 1));
 
 	if (err < 0)
@@ -1424,7 +1392,7 @@ void bitmap_endwrite(struct bitmap *bitmap, sector_t offset, unsigned long secto
 			set_page_attr(bitmap,
 				      filemap_get_page(
 					      bitmap,
-					      offset >> CHUNK_BLOCK_SHIFT(bitmap)),
+					      offset >> bitmap->chunkshift),
 				      BITMAP_PAGE_PENDING);
 			bitmap->allclean = 0;
 		}
@@ -1512,7 +1480,7 @@ void bitmap_end_sync(struct bitmap *bitmap, sector_t offset, sector_t *blocks, i
 		else {
 			if (*bmc <= 2) {
 				set_page_attr(bitmap,
-					      filemap_get_page(bitmap, offset >> CHUNK_BLOCK_SHIFT(bitmap)),
+					      filemap_get_page(bitmap, offset >> bitmap->chunkshift),
 					      BITMAP_PAGE_PENDING);
 				bitmap->allclean = 0;
 			}
@@ -1559,7 +1527,7 @@ void bitmap_cond_end_sync(struct bitmap *bitmap, sector_t sector)
 
 	bitmap->mddev->curr_resync_completed = sector;
 	set_bit(MD_CHANGE_CLEAN, &bitmap->mddev->flags);
-	sector &= ~((1ULL << CHUNK_BLOCK_SHIFT(bitmap)) - 1);
+	sector &= ~((1ULL << bitmap->chunkshift) - 1);
 	s = 0;
 	while (s < sector && s < bitmap->mddev->resync_max_sectors) {
 		bitmap_end_sync(bitmap, s, &blocks, 0);
@@ -1589,7 +1557,7 @@ static void bitmap_set_memory_bits(struct bitmap *bitmap, sector_t offset, int n
 		struct page *page;
 		*bmc = 2 | (needed ? NEEDED_MASK : 0);
 		bitmap_count_page(bitmap, offset, 1);
-		page = filemap_get_page(bitmap, offset >> CHUNK_BLOCK_SHIFT(bitmap));
+		page = filemap_get_page(bitmap, offset >> bitmap->chunkshift);
 		set_page_attr(bitmap, page, BITMAP_PAGE_PENDING);
 		bitmap->allclean = 0;
 	}
@@ -1602,7 +1570,7 @@ void bitmap_dirty_bits(struct bitmap *bitmap, unsigned long s, unsigned long e)
 	unsigned long chunk;
 
 	for (chunk = s; chunk <= e; chunk++) {
-		sector_t sec = (sector_t)chunk << CHUNK_BLOCK_SHIFT(bitmap);
+		sector_t sec = (sector_t)chunk << bitmap->chunkshift;
 		bitmap_set_memory_bits(bitmap, sec, 1);
 		spin_lock_irq(&bitmap->lock);
 		bitmap_file_set_bit(bitmap, sec);
@@ -1759,11 +1727,12 @@ int bitmap_create(struct mddev *mddev)
 		goto error;
 
 	bitmap->daemon_lastrun = jiffies;
-	bitmap->chunkshift = ffz(~mddev->bitmap_info.chunksize);
+	bitmap->chunkshift = (ffz(~mddev->bitmap_info.chunksize)
+			      - BITMAP_BLOCK_SHIFT);
 
 	/* now that chunksize and chunkshift are set, we can use these macros */
-	chunks = (blocks + CHUNK_BLOCK_RATIO(bitmap) - 1) >>
-			CHUNK_BLOCK_SHIFT(bitmap);
+	chunks = (blocks + bitmap->chunkshift - 1) >>
+			bitmap->chunkshift;
 	pages = (chunks + PAGE_COUNTER_RATIO - 1) / PAGE_COUNTER_RATIO;
 
 	BUG_ON(!pages);
@@ -1836,6 +1805,33 @@ out:
 }
 EXPORT_SYMBOL_GPL(bitmap_load);
 
+void bitmap_status(struct seq_file *seq, struct bitmap *bitmap)
+{
+	unsigned long chunk_kb;
+	unsigned long flags;
+
+	if (!bitmap)
+		return;
+
+	spin_lock_irqsave(&bitmap->lock, flags);
+	chunk_kb = bitmap->mddev->bitmap_info.chunksize >> 10;
+	seq_printf(seq, "bitmap: %lu/%lu pages [%luKB], "
+		   "%lu%s chunk",
+		   bitmap->pages - bitmap->missing_pages,
+		   bitmap->pages,
+		   (bitmap->pages - bitmap->missing_pages)
+		   << (PAGE_SHIFT - 10),
+		   chunk_kb ? chunk_kb : bitmap->mddev->bitmap_info.chunksize,
+		   chunk_kb ? "KB" : "B");
+	if (bitmap->file) {
+		seq_printf(seq, ", file: ");
+		seq_path(seq, &bitmap->file->f_path, " \t\n");
+	}
+
+	seq_printf(seq, "\n");
+	spin_unlock_irqrestore(&bitmap->lock, flags);
+}
+
 static ssize_t
 location_show(struct mddev *mddev, char *page)
 {
@@ -1904,6 +1900,8 @@ location_store(struct mddev *mddev, const char *buf, size_t len)
 			if (mddev->pers) {
 				mddev->pers->quiesce(mddev, 1);
 				rv = bitmap_create(mddev);
+				if (!rv)
+					rv = bitmap_load(mddev);
 				if (rv) {
 					bitmap_destroy(mddev);
 					mddev->bitmap_info.offset = 0;
diff --git a/drivers/md/bitmap.h b/drivers/md/bitmap.h
index a15436dd9b3e..55ca5aec84e4 100644
--- a/drivers/md/bitmap.h
+++ b/drivers/md/bitmap.h
@@ -13,8 +13,6 @@
 #define BITMAP_MAJOR_HI 4
 #define	BITMAP_MAJOR_HOSTENDIAN 3
 
-#define BITMAP_MINOR 39
-
 /*
  * in-memory bitmap:
  *
@@ -101,21 +99,10 @@ typedef __u16 bitmap_counter_t;
 /* same, except a mask value for more efficient bitops */
 #define PAGE_COUNTER_MASK  (PAGE_COUNTER_RATIO - 1)
 
-#define BITMAP_BLOCK_SIZE 512
 #define BITMAP_BLOCK_SHIFT 9
 
 /* how many blocks per chunk? (this is variable) */
 #define CHUNK_BLOCK_RATIO(bitmap) ((bitmap)->mddev->bitmap_info.chunksize >> BITMAP_BLOCK_SHIFT)
-#define CHUNK_BLOCK_SHIFT(bitmap) ((bitmap)->chunkshift - BITMAP_BLOCK_SHIFT)
-#define CHUNK_BLOCK_MASK(bitmap) (CHUNK_BLOCK_RATIO(bitmap) - 1)
-
-/* when hijacked, the counters and bits represent even larger "chunks" */
-/* there will be 1024 chunks represented by each counter in the page pointers */
-#define PAGEPTR_BLOCK_RATIO(bitmap) \
-			(CHUNK_BLOCK_RATIO(bitmap) << PAGE_COUNTER_SHIFT >> 1)
-#define PAGEPTR_BLOCK_SHIFT(bitmap) \
-			(CHUNK_BLOCK_SHIFT(bitmap) + PAGE_COUNTER_SHIFT - 1)
-#define PAGEPTR_BLOCK_MASK(bitmap) (PAGEPTR_BLOCK_RATIO(bitmap) - 1)
 
 #endif
 
@@ -181,12 +168,6 @@ struct bitmap_page {
 	unsigned int  count:31;
 };
 
-/* keep track of bitmap file pages that have pending writes on them */
-struct page_list {
-	struct list_head list;
-	struct page *page;
-};
-
 /* the main bitmap structure - one per mddev */
 struct bitmap {
 	struct bitmap_page *bp;
@@ -196,7 +177,7 @@ struct bitmap {
 	struct mddev *mddev; /* the md device that the bitmap is for */
 
 	/* bitmap chunksize -- how much data does each bit represent? */
-	unsigned long chunkshift; /* chunksize = 2^chunkshift (for bitops) */
+	unsigned long chunkshift; /* chunksize = 2^(chunkshift+9) (for bitops) */
 	unsigned long chunks; /* total number of data chunks for the array */
 
 	__u64	events_cleared;
@@ -245,6 +226,7 @@ void bitmap_destroy(struct mddev *mddev);
 
 void bitmap_print_sb(struct bitmap *bitmap);
 void bitmap_update_sb(struct bitmap *bitmap);
+void bitmap_status(struct seq_file *seq, struct bitmap *bitmap);
 
 int  bitmap_setallbits(struct bitmap *bitmap);
 void bitmap_write_all(struct bitmap *bitmap);
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index 787022c18187..c5a875d7b882 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -615,14 +615,14 @@ static int read_disk_sb(struct md_rdev *rdev, int size)
 
 static void super_sync(struct mddev *mddev, struct md_rdev *rdev)
 {
-	struct md_rdev *r, *t;
+	struct md_rdev *r;
 	uint64_t failed_devices;
 	struct dm_raid_superblock *sb;
 
 	sb = page_address(rdev->sb_page);
 	failed_devices = le64_to_cpu(sb->failed_devices);
 
-	rdev_for_each(r, t, mddev)
+	rdev_for_each(r, mddev)
 		if ((r->raid_disk >= 0) && test_bit(Faulty, &r->flags))
 			failed_devices |= (1ULL << r->raid_disk);
 
@@ -707,7 +707,7 @@ static int super_init_validation(struct mddev *mddev, struct md_rdev *rdev)
 	struct dm_raid_superblock *sb;
 	uint32_t new_devs = 0;
 	uint32_t rebuilds = 0;
-	struct md_rdev *r, *t;
+	struct md_rdev *r;
 	struct dm_raid_superblock *sb2;
 
 	sb = page_address(rdev->sb_page);
@@ -750,7 +750,7 @@ static int super_init_validation(struct mddev *mddev, struct md_rdev *rdev)
 	 *    case the In_sync bit will /not/ be set and
 	 *    recovery_cp must be MaxSector.
 	 */
-	rdev_for_each(r, t, mddev) {
+	rdev_for_each(r, mddev) {
 		if (!test_bit(In_sync, &r->flags)) {
 			DMINFO("Device %d specified for rebuild: "
 			       "Clearing superblock", r->raid_disk);
@@ -782,7 +782,7 @@ static int super_init_validation(struct mddev *mddev, struct md_rdev *rdev)
 	 * Now we set the Faulty bit for those devices that are
 	 * recorded in the superblock as failed.
 	 */
-	rdev_for_each(r, t, mddev) {
+	rdev_for_each(r, mddev) {
 		if (!r->sb_page)
 			continue;
 		sb2 = page_address(r->sb_page);
@@ -855,11 +855,11 @@ static int super_validate(struct mddev *mddev, struct md_rdev *rdev)
 static int analyse_superblocks(struct dm_target *ti, struct raid_set *rs)
 {
 	int ret;
-	struct md_rdev *rdev, *freshest, *tmp;
+	struct md_rdev *rdev, *freshest;
 	struct mddev *mddev = &rs->md;
 
 	freshest = NULL;
-	rdev_for_each(rdev, tmp, mddev) {
+	rdev_for_each(rdev, mddev) {
 		if (!rdev->meta_bdev)
 			continue;
 
@@ -888,7 +888,7 @@ static int analyse_superblocks(struct dm_target *ti, struct raid_set *rs)
 	if (super_validate(mddev, freshest))
 		return -EINVAL;
 
-	rdev_for_each(rdev, tmp, mddev)
+	rdev_for_each(rdev, mddev)
 		if ((rdev != freshest) && super_validate(mddev, rdev))
 			return -EINVAL;
 
diff --git a/drivers/md/faulty.c b/drivers/md/faulty.c
index feb2c3c7bb44..45135f69509c 100644
--- a/drivers/md/faulty.c
+++ b/drivers/md/faulty.c
@@ -315,7 +315,7 @@ static int run(struct mddev *mddev)
 	}
 	conf->nfaults = 0;
 
-	list_for_each_entry(rdev, &mddev->disks, same_set)
+	rdev_for_each(rdev, mddev)
 		conf->rdev = rdev;
 
 	md_set_array_sectors(mddev, faulty_size(mddev, 0, 0));
diff --git a/drivers/md/linear.c b/drivers/md/linear.c
index 627456542fb3..b0fcc7d02adb 100644
--- a/drivers/md/linear.c
+++ b/drivers/md/linear.c
@@ -68,10 +68,19 @@ static int linear_mergeable_bvec(struct request_queue *q,
 	struct dev_info *dev0;
 	unsigned long maxsectors, bio_sectors = bvm->bi_size >> 9;
 	sector_t sector = bvm->bi_sector + get_start_sect(bvm->bi_bdev);
+	int maxbytes = biovec->bv_len;
+	struct request_queue *subq;
 
 	rcu_read_lock();
 	dev0 = which_dev(mddev, sector);
 	maxsectors = dev0->end_sector - sector;
+	subq = bdev_get_queue(dev0->rdev->bdev);
+	if (subq->merge_bvec_fn) {
+		bvm->bi_bdev = dev0->rdev->bdev;
+		bvm->bi_sector -= dev0->end_sector - dev0->rdev->sectors;
+		maxbytes = min(maxbytes, subq->merge_bvec_fn(subq, bvm,
+							     biovec));
+	}
 	rcu_read_unlock();
 
 	if (maxsectors < bio_sectors)
@@ -80,12 +89,12 @@ static int linear_mergeable_bvec(struct request_queue *q,
 		maxsectors -= bio_sectors;
 
 	if (maxsectors <= (PAGE_SIZE >> 9 ) && bio_sectors == 0)
-		return biovec->bv_len;
-	/* The bytes available at this offset could be really big,
-	 * so we cap at 2^31 to avoid overflow */
-	if (maxsectors > (1 << (31-9)))
-		return 1<<31;
-	return maxsectors << 9;
+		return maxbytes;
+
+	if (maxsectors > (maxbytes >> 9))
+		return maxbytes;
+	else
+		return maxsectors << 9;
 }
 
 static int linear_congested(void *data, int bits)
@@ -138,7 +147,7 @@ static struct linear_conf *linear_conf(struct mddev *mddev, int raid_disks)
 	cnt = 0;
 	conf->array_sectors = 0;
 
-	list_for_each_entry(rdev, &mddev->disks, same_set) {
+	rdev_for_each(rdev, mddev) {
 		int j = rdev->raid_disk;
 		struct dev_info *disk = conf->disks + j;
 		sector_t sectors;
@@ -158,15 +167,6 @@ static struct linear_conf *linear_conf(struct mddev *mddev, int raid_disks)
 
 		disk_stack_limits(mddev->gendisk, rdev->bdev,
 				  rdev->data_offset << 9);
-		/* as we don't honour merge_bvec_fn, we must never risk
-		 * violating it, so limit max_segments to 1 lying within
-		 * a single page.
-		 */
-		if (rdev->bdev->bd_disk->queue->merge_bvec_fn) {
-			blk_queue_max_segments(mddev->queue, 1);
-			blk_queue_segment_boundary(mddev->queue,
-						   PAGE_CACHE_SIZE - 1);
-		}
 
 		conf->array_sectors += rdev->sectors;
 		cnt++;
diff --git a/drivers/md/md.c b/drivers/md/md.c
index ce88755baf4a..b572e1e386ce 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -439,7 +439,7 @@ static void submit_flushes(struct work_struct *ws)
 	INIT_WORK(&mddev->flush_work, md_submit_flush_data);
 	atomic_set(&mddev->flush_pending, 1);
 	rcu_read_lock();
-	list_for_each_entry_rcu(rdev, &mddev->disks, same_set)
+	rdev_for_each_rcu(rdev, mddev)
 		if (rdev->raid_disk >= 0 &&
 		    !test_bit(Faulty, &rdev->flags)) {
 			/* Take two references, one is dropped
@@ -749,7 +749,7 @@ static struct md_rdev * find_rdev_nr(struct mddev *mddev, int nr)
 {
 	struct md_rdev *rdev;
 
-	list_for_each_entry(rdev, &mddev->disks, same_set)
+	rdev_for_each(rdev, mddev)
 		if (rdev->desc_nr == nr)
 			return rdev;
 
@@ -760,7 +760,7 @@ static struct md_rdev * find_rdev(struct mddev * mddev, dev_t dev)
 {
 	struct md_rdev *rdev;
 
-	list_for_each_entry(rdev, &mddev->disks, same_set)
+	rdev_for_each(rdev, mddev)
 		if (rdev->bdev->bd_dev == dev)
 			return rdev;
 
@@ -1342,7 +1342,7 @@ static void super_90_sync(struct mddev *mddev, struct md_rdev *rdev)
 		sb->state |= (1<<MD_SB_BITMAP_PRESENT);
 
 	sb->disks[0].state = (1<<MD_DISK_REMOVED);
-	list_for_each_entry(rdev2, &mddev->disks, same_set) {
+	rdev_for_each(rdev2, mddev) {
 		mdp_disk_t *d;
 		int desc_nr;
 		int is_active = test_bit(In_sync, &rdev2->flags);
@@ -1805,18 +1805,18 @@ retry:
 						| BB_LEN(internal_bb));
 				*bbp++ = cpu_to_le64(store_bb);
 			}
+			bb->changed = 0;
 			if (read_seqretry(&bb->lock, seq))
 				goto retry;
 
 			bb->sector = (rdev->sb_start +
 				      (int)le32_to_cpu(sb->bblog_offset));
 			bb->size = le16_to_cpu(sb->bblog_size);
-			bb->changed = 0;
 		}
 	}
 
 	max_dev = 0;
-	list_for_each_entry(rdev2, &mddev->disks, same_set)
+	rdev_for_each(rdev2, mddev)
 		if (rdev2->desc_nr+1 > max_dev)
 			max_dev = rdev2->desc_nr+1;
 
@@ -1833,7 +1833,7 @@ retry:
 	for (i=0; i<max_dev;i++)
 		sb->dev_roles[i] = cpu_to_le16(0xfffe);
 	
-	list_for_each_entry(rdev2, &mddev->disks, same_set) {
+	rdev_for_each(rdev2, mddev) {
 		i = rdev2->desc_nr;
 		if (test_bit(Faulty, &rdev2->flags))
 			sb->dev_roles[i] = cpu_to_le16(0xfffe);
@@ -1948,7 +1948,7 @@ int md_integrity_register(struct mddev *mddev)
 		return 0; /* nothing to do */
 	if (!mddev->gendisk || blk_get_integrity(mddev->gendisk))
 		return 0; /* shouldn't register, or already is */
-	list_for_each_entry(rdev, &mddev->disks, same_set) {
+	rdev_for_each(rdev, mddev) {
 		/* skip spares and non-functional disks */
 		if (test_bit(Faulty, &rdev->flags))
 			continue;
@@ -2175,7 +2175,7 @@ static void export_array(struct mddev *mddev)
 {
 	struct md_rdev *rdev, *tmp;
 
-	rdev_for_each(rdev, tmp, mddev) {
+	rdev_for_each_safe(rdev, tmp, mddev) {
 		if (!rdev->mddev) {
 			MD_BUG();
 			continue;
@@ -2307,11 +2307,11 @@ static void md_print_devices(void)
 			bitmap_print_sb(mddev->bitmap);
 		else
 			printk("%s: ", mdname(mddev));
-		list_for_each_entry(rdev, &mddev->disks, same_set)
+		rdev_for_each(rdev, mddev)
 			printk("<%s>", bdevname(rdev->bdev,b));
 		printk("\n");
 
-		list_for_each_entry(rdev, &mddev->disks, same_set)
+		rdev_for_each(rdev, mddev)
 			print_rdev(rdev, mddev->major_version);
 	}
 	printk("md:	**********************************\n");
@@ -2328,7 +2328,7 @@ static void sync_sbs(struct mddev * mddev, int nospares)
 	 * with the rest of the array)
 	 */
 	struct md_rdev *rdev;
-	list_for_each_entry(rdev, &mddev->disks, same_set) {
+	rdev_for_each(rdev, mddev) {
 		if (rdev->sb_events == mddev->events ||
 		    (nospares &&
 		     rdev->raid_disk < 0 &&
@@ -2351,7 +2351,7 @@ static void md_update_sb(struct mddev * mddev, int force_change)
 
 repeat:
 	/* First make sure individual recovery_offsets are correct */
-	list_for_each_entry(rdev, &mddev->disks, same_set) {
+	rdev_for_each(rdev, mddev) {
 		if (rdev->raid_disk >= 0 &&
 		    mddev->delta_disks >= 0 &&
 		    !test_bit(In_sync, &rdev->flags) &&
@@ -2364,8 +2364,9 @@ repeat:
 		clear_bit(MD_CHANGE_DEVS, &mddev->flags);
 		if (!mddev->external) {
 			clear_bit(MD_CHANGE_PENDING, &mddev->flags);
-			list_for_each_entry(rdev, &mddev->disks, same_set) {
+			rdev_for_each(rdev, mddev) {
 				if (rdev->badblocks.changed) {
+					rdev->badblocks.changed = 0;
 					md_ack_all_badblocks(&rdev->badblocks);
 					md_error(mddev, rdev);
 				}
@@ -2430,7 +2431,7 @@ repeat:
 		mddev->events --;
 	}
 
-	list_for_each_entry(rdev, &mddev->disks, same_set) {
+	rdev_for_each(rdev, mddev) {
 		if (rdev->badblocks.changed)
 			any_badblocks_changed++;
 		if (test_bit(Faulty, &rdev->flags))
@@ -2444,7 +2445,7 @@ repeat:
 		 mdname(mddev), mddev->in_sync);
 
 	bitmap_update_sb(mddev->bitmap);
-	list_for_each_entry(rdev, &mddev->disks, same_set) {
+	rdev_for_each(rdev, mddev) {
 		char b[BDEVNAME_SIZE];
 
 		if (rdev->sb_loaded != 1)
@@ -2493,7 +2494,7 @@ repeat:
 	if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
 		sysfs_notify(&mddev->kobj, NULL, "sync_completed");
 
-	list_for_each_entry(rdev, &mddev->disks, same_set) {
+	rdev_for_each(rdev, mddev) {
 		if (test_and_clear_bit(FaultRecorded, &rdev->flags))
 			clear_bit(Blocked, &rdev->flags);
 
@@ -2896,7 +2897,7 @@ rdev_size_store(struct md_rdev *rdev, const char *buf, size_t len)
 			struct md_rdev *rdev2;
 
 			mddev_lock(mddev);
-			list_for_each_entry(rdev2, &mddev->disks, same_set)
+			rdev_for_each(rdev2, mddev)
 				if (rdev->bdev == rdev2->bdev &&
 				    rdev != rdev2 &&
 				    overlaps(rdev->data_offset, rdev->sectors,
@@ -3193,7 +3194,7 @@ static void analyze_sbs(struct mddev * mddev)
 	char b[BDEVNAME_SIZE];
 
 	freshest = NULL;
-	rdev_for_each(rdev, tmp, mddev)
+	rdev_for_each_safe(rdev, tmp, mddev)
 		switch (super_types[mddev->major_version].
 			load_super(rdev, freshest, mddev->minor_version)) {
 		case 1:
@@ -3214,7 +3215,7 @@ static void analyze_sbs(struct mddev * mddev)
 		validate_super(mddev, freshest);
 
 	i = 0;
-	rdev_for_each(rdev, tmp, mddev) {
+	rdev_for_each_safe(rdev, tmp, mddev) {
 		if (mddev->max_disks &&
 		    (rdev->desc_nr >= mddev->max_disks ||
 		     i > mddev->max_disks)) {
@@ -3403,7 +3404,7 @@ level_store(struct mddev *mddev, const char *buf, size_t len)
 		return -EINVAL;
 	}
 
-	list_for_each_entry(rdev, &mddev->disks, same_set)
+	rdev_for_each(rdev, mddev)
 		rdev->new_raid_disk = rdev->raid_disk;
 
 	/* ->takeover must set new_* and/or delta_disks
@@ -3456,7 +3457,7 @@ level_store(struct mddev *mddev, const char *buf, size_t len)
 		mddev->safemode = 0;
 	}
 
-	list_for_each_entry(rdev, &mddev->disks, same_set) {
+	rdev_for_each(rdev, mddev) {
 		if (rdev->raid_disk < 0)
 			continue;
 		if (rdev->new_raid_disk >= mddev->raid_disks)
@@ -3465,7 +3466,7 @@ level_store(struct mddev *mddev, const char *buf, size_t len)
 			continue;
 		sysfs_unlink_rdev(mddev, rdev);
 	}
-	list_for_each_entry(rdev, &mddev->disks, same_set) {
+	rdev_for_each(rdev, mddev) {
 		if (rdev->raid_disk < 0)
 			continue;
 		if (rdev->new_raid_disk == rdev->raid_disk)
@@ -4796,7 +4797,7 @@ int md_run(struct mddev *mddev)
 	 * the only valid external interface is through the md
 	 * device.
 	 */
-	list_for_each_entry(rdev, &mddev->disks, same_set) {
+	rdev_for_each(rdev, mddev) {
 		if (test_bit(Faulty, &rdev->flags))
 			continue;
 		sync_blockdev(rdev->bdev);
@@ -4867,8 +4868,8 @@ int md_run(struct mddev *mddev)
 		struct md_rdev *rdev2;
 		int warned = 0;
 
-		list_for_each_entry(rdev, &mddev->disks, same_set)
-			list_for_each_entry(rdev2, &mddev->disks, same_set) {
+		rdev_for_each(rdev, mddev)
+			rdev_for_each(rdev2, mddev) {
 				if (rdev < rdev2 &&
 				    rdev->bdev->bd_contains ==
 				    rdev2->bdev->bd_contains) {
@@ -4945,7 +4946,7 @@ int md_run(struct mddev *mddev)
 	mddev->in_sync = 1;
 	smp_wmb();
 	mddev->ready = 1;
-	list_for_each_entry(rdev, &mddev->disks, same_set)
+	rdev_for_each(rdev, mddev)
 		if (rdev->raid_disk >= 0)
 			if (sysfs_link_rdev(mddev, rdev))
 				/* failure here is OK */;
@@ -5073,6 +5074,7 @@ static void md_clean(struct mddev *mddev)
 	mddev->changed = 0;
 	mddev->degraded = 0;
 	mddev->safemode = 0;
+	mddev->merge_check_needed = 0;
 	mddev->bitmap_info.offset = 0;
 	mddev->bitmap_info.default_offset = 0;
 	mddev->bitmap_info.chunksize = 0;
@@ -5175,7 +5177,7 @@ static int do_md_stop(struct mddev * mddev, int mode, int is_open)
 		/* tell userspace to handle 'inactive' */
 		sysfs_notify_dirent_safe(mddev->sysfs_state);
 
-		list_for_each_entry(rdev, &mddev->disks, same_set)
+		rdev_for_each(rdev, mddev)
 			if (rdev->raid_disk >= 0)
 				sysfs_unlink_rdev(mddev, rdev);
 
@@ -5226,7 +5228,7 @@ static void autorun_array(struct mddev *mddev)
 
 	printk(KERN_INFO "md: running: ");
 
-	list_for_each_entry(rdev, &mddev->disks, same_set) {
+	rdev_for_each(rdev, mddev) {
 		char b[BDEVNAME_SIZE];
 		printk("<%s>", bdevname(rdev->bdev,b));
 	}
@@ -5356,7 +5358,7 @@ static int get_array_info(struct mddev * mddev, void __user * arg)
 	struct md_rdev *rdev;
 
 	nr=working=insync=failed=spare=0;
-	list_for_each_entry(rdev, &mddev->disks, same_set) {
+	rdev_for_each(rdev, mddev) {
 		nr++;
 		if (test_bit(Faulty, &rdev->flags))
 			failed++;
@@ -5923,7 +5925,7 @@ static int update_size(struct mddev *mddev, sector_t num_sectors)
 		 * grow, and re-add.
 		 */
 		return -EBUSY;
-	list_for_each_entry(rdev, &mddev->disks, same_set) {
+	rdev_for_each(rdev, mddev) {
 		sector_t avail = rdev->sectors;
 
 		if (fit && (num_sectors == 0 || num_sectors > avail))
@@ -6724,7 +6726,6 @@ static int md_seq_show(struct seq_file *seq, void *v)
 	struct mddev *mddev = v;
 	sector_t sectors;
 	struct md_rdev *rdev;
-	struct bitmap *bitmap;
 
 	if (v == (void*)1) {
 		struct md_personality *pers;
@@ -6758,7 +6759,7 @@ static int md_seq_show(struct seq_file *seq, void *v)
 		}
 
 		sectors = 0;
-		list_for_each_entry(rdev, &mddev->disks, same_set) {
+		rdev_for_each(rdev, mddev) {
 			char b[BDEVNAME_SIZE];
 			seq_printf(seq, " %s[%d]",
 				bdevname(rdev->bdev,b), rdev->desc_nr);
@@ -6812,27 +6813,7 @@ static int md_seq_show(struct seq_file *seq, void *v)
 		} else
 			seq_printf(seq, "\n       ");
 
-		if ((bitmap = mddev->bitmap)) {
-			unsigned long chunk_kb;
-			unsigned long flags;
-			spin_lock_irqsave(&bitmap->lock, flags);
-			chunk_kb = mddev->bitmap_info.chunksize >> 10;
-			seq_printf(seq, "bitmap: %lu/%lu pages [%luKB], "
-				"%lu%s chunk",
-				bitmap->pages - bitmap->missing_pages,
-				bitmap->pages,
-				(bitmap->pages - bitmap->missing_pages)
-					<< (PAGE_SHIFT - 10),
-				chunk_kb ? chunk_kb : mddev->bitmap_info.chunksize,
-				chunk_kb ? "KB" : "B");
-			if (bitmap->file) {
-				seq_printf(seq, ", file: ");
-				seq_path(seq, &bitmap->file->f_path, " \t\n");
-			}
-
-			seq_printf(seq, "\n");
-			spin_unlock_irqrestore(&bitmap->lock, flags);
-		}
+		bitmap_status(seq, mddev->bitmap);
 
 		seq_printf(seq, "\n");
 	}
@@ -7170,7 +7151,7 @@ void md_do_sync(struct mddev *mddev)
 		max_sectors = mddev->dev_sectors;
 		j = MaxSector;
 		rcu_read_lock();
-		list_for_each_entry_rcu(rdev, &mddev->disks, same_set)
+		rdev_for_each_rcu(rdev, mddev)
 			if (rdev->raid_disk >= 0 &&
 			    !test_bit(Faulty, &rdev->flags) &&
 			    !test_bit(In_sync, &rdev->flags) &&
@@ -7342,7 +7323,7 @@ void md_do_sync(struct mddev *mddev)
 			if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery))
 				mddev->curr_resync = MaxSector;
 			rcu_read_lock();
-			list_for_each_entry_rcu(rdev, &mddev->disks, same_set)
+			rdev_for_each_rcu(rdev, mddev)