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.
  ...

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"
 
@@ -34,31 +35,6 @@ static inline char *bmname(struct bitmap *bitmap)
 	return bitmap->mddev ? mdname(bitmap->mddev) : "mdX";
 }
 
-/*
- * 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)
  *
@@ -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;

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);

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;
 

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));

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++;

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)
 				if (rdev->raid_disk >= 0 &&
 				    mddev->delta_disks >= 0 &&
 				    !test_bit(Faulty, &rdev->flags) &&
@@ -7388,7 +7369,7 @@ static int remove_and_add_spares(struct mddev *mddev)
 
 	mddev->curr_resync_completed = 0;
 
-	list_for_each_entry(rdev, &mddev->disks, same_set)
+	rdev_for_each(rdev, mddev)
 		if (rdev->raid_disk >= 0 &&
 		    !test_bit(Blocked, &rdev->flags) &&
 		    (test_bit(Faulty, &rdev->flags) ||
@@ -7406,7 +7387,7 @@ static int remove_and_add_spares(struct mddev *mddev)
 			     "degraded");
 
 
-	list_for_each_entry(rdev, &mddev->disks, same_set) {
+	rdev_for_each(rdev, mddev) {
 		if (rdev->raid_disk >= 0 &&
 		    !test_bit(In_sync, &rdev->flags) &&
 		    !test_bit(Faulty, &rdev->flags))
@@ -7451,7 +7432,7 @@ static void reap_sync_thread(struct mddev *mddev)
 	 * do the superblock for an incrementally recovered device
 	 * written out.
 	 */
-	list_for_each_entry(rdev, &mddev->disks, same_set)
+	rdev_for_each(rdev, mddev)
 		if (!mddev->degraded ||
 		    test_bit(In_sync, &rdev->flags))
 			rdev->saved_raid_disk = -1;
@@ -7529,7 +7510,7 @@ void md_check_recovery(struct mddev *mddev)
 			 * failed devices.
 			 */
 			struct md_rdev *rdev;
-			list_for_each_entry(rdev, &mddev->disks, same_set)
+			rdev_for_each(rdev, mddev)
 				if (rdev->raid_disk >= 0 &&
 				    !test_bit(Blocked, &rdev->flags) &&
 				    test_bit(Faulty, &rdev->flags) &&
@@ -8040,7 +8021,7 @@ void md_ack_all_badblocks(struct badblocks *bb)
 		return;
 	write_seqlock_irq(&bb->lock);
 
-	if (bb->changed == 0) {
+	if (bb->changed == 0 && bb->unacked_exist) {
 		u64 *p = bb->page;
 		int i;
 		for (i = 0; i < bb->count ; i++) {
@@ -8157,30 +8138,23 @@ static int md_notify_reboot(struct notifier_block *this,
 	struct mddev *mddev;
 	int need_delay = 0;
 
-	if ((code == SYS_DOWN) || (code == SYS_HALT) || (code == SYS_POWER_OFF)) {
-
-		printk(KERN_INFO "md: stopping all md devices.\n");
-
-		for_each_mddev(mddev, tmp) {
-			if (mddev_trylock(mddev)) {
-				/* Force a switch to readonly even array
-				 * appears to still be in use.  Hence
-				 * the '100'.
-				 */
-				md_set_readonly(mddev, 100);
-				mddev_unlock(mddev);
-			}
-			need_delay = 1;
+	for_each_mddev(mddev, tmp) {
+		if (mddev_trylock(mddev)) {
+			__md_stop_writes(mddev);
+			mddev->safemode = 2;
+			mddev_unlock(mddev);
 		}
-		/*
-		 * certain more exotic SCSI devices are known to be
-		 * volatile wrt too early system reboots. While the
-		 * right place to handle this issue is the given
-		 * driver, we do want to have a safe RAID driver ...
-		 */
-		if (need_delay)
-			mdelay(1000*1);
+		need_delay = 1;
 	}
+	/*
+	 * certain more exotic SCSI devices are known to be
+	 * volatile wrt too early system reboots. While the
+	 * right place to handle this issue is the given
+	 * driver, we do want to have a safe RAID driver ...
+	 */
+	if (need_delay)
+		mdelay(1000*1);
+
 	return NOTIFY_DONE;
 }
 

drivers/md/md.h

@@ -128,6 +128,10 @@ struct md_rdev {
 enum flag_bits {
 	Faulty,			/* device is known to have a fault */
 	In_sync,		/* device is in_sync with rest of array */
+	Unmerged,		/* device is being added to array and should
+				 * be considerred for bvec_merge_fn but not
+				 * yet for actual IO
+				 */
 	WriteMostly,		/* Avoid reading if at all possible */
 	AutoDetected,		/* added by auto-detect */
 	Blocked,		/* An error occurred but has not yet
@@ -345,6 +349,10 @@ struct mddev {
 	int				degraded;	/* whether md should consider
 							 * adding a spare
 							 */
+	int				merge_check_needed; /* at least one
+							     * member device
+							     * has a
+							     * merge_bvec_fn */
 
 	atomic_t			recovery_active; /* blocks scheduled, but not written */
 	wait_queue_head_t		recovery_wait;
@@ -519,7 +527,10 @@ static inline void sysfs_unlink_rdev(struct mddev *mddev, struct md_rdev *rdev)
 /*
  * iterates through the 'same array disks' ringlist
  */
-#define rdev_for_each(rdev, tmp, mddev)				\
+#define rdev_for_each(rdev, mddev)				\
+	list_for_each_entry(rdev, &((mddev)->disks), same_set)
+
+#define rdev_for_each_safe(rdev, tmp, mddev)				\
 	list_for_each_entry_safe(rdev, tmp, &((mddev)->disks), same_set)
 
 #define rdev_for_each_rcu(rdev, mddev)				\

drivers/md/multipath.c

@@ -428,7 +428,7 @@ static int multipath_run (struct mddev *mddev)
 	}
 
 	working_disks = 0;
-	list_for_each_entry(rdev, &mddev->disks, same_set) {
+	rdev_for_each(rdev, mddev) {
 		disk_idx = rdev->raid_disk;
 		if (disk_idx < 0 ||
 		    disk_idx >= mddev->raid_disks)

drivers/md/raid0.c

@@ -91,7 +91,7 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf)
 
 	if (!conf)
 		return -ENOMEM;
-	list_for_each_entry(rdev1, &mddev->disks, same_set) {
+	rdev_for_each(rdev1, mddev) {
 		pr_debug("md/raid0:%s: looking at %s\n",
 			 mdname(mddev),
 			 bdevname(rdev1->bdev, b));
@@ -102,7 +102,7 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf)
 		sector_div(sectors, mddev->chunk_sectors);
 		rdev1->sectors = sectors * mddev->chunk_sectors;
 
-		list_for_each_entry(rdev2, &mddev->disks, same_set) {
+		rdev_for_each(rdev2, mddev) {
 			pr_debug("md/raid0:%s:   comparing %s(%llu)"
 				 " with %s(%llu)\n",
 				 mdname(mddev),
@@ -157,7 +157,7 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf)
 	smallest = NULL;
 	dev = conf->devlist;
 	err = -EINVAL;
-	list_for_each_entry(rdev1, &mddev->disks, same_set) {
+	rdev_for_each(rdev1, mddev) {
 		int j = rdev1->raid_disk;
 
 		if (mddev->level == 10) {
@@ -188,16 +188,10 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf)
 
 		disk_stack_limits(mddev->gendisk, rdev1->bdev,
 				  rdev1->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 (rdev1->bdev->bd_disk->queue->merge_bvec_fn) {
-			blk_queue_max_segments(mddev->queue, 1);
-			blk_queue_segment_boundary(mddev->queue,
-						   PAGE_CACHE_SIZE - 1);
-		}
+		if (rdev1->bdev->bd_disk->queue->merge_bvec_fn)
+			conf->has_merge_bvec = 1;
+
 		if (!smallest || (rdev1->sectors < smallest->sectors))
 			smallest = rdev1;
 		cnt++;
@@ -290,8 +284,64 @@ abort:
 	return err;
 }
 
+/* Find the zone which holds a particular offset
+ * Update *sectorp to be an offset in that zone
+ */
+static struct strip_zone *find_zone(struct r0conf *conf,
+				    sector_t *sectorp)
+{
+	int i;
+	struct strip_zone *z = conf->strip_zone;
+	sector_t sector = *sectorp;
+
+	for (i = 0; i < conf->nr_strip_zones; i++)
+		if (sector < z[i].zone_end) {
+			if (i)
+				*sectorp = sector - z[i-1].zone_end;
+			return z + i;
+		}
+	BUG();
+}
+
+/*
+ * remaps the bio to the target device. we separate two flows.
+ * power 2 flow and a general flow for the sake of perfromance
+*/
+static struct md_rdev *map_sector(struct mddev *mddev, struct strip_zone *zone,
+				sector_t sector, sector_t *sector_offset)
+{
+	unsigned int sect_in_chunk;
+	sector_t chunk;
+	struct r0conf *conf = mddev->private;
+	int raid_disks = conf->strip_zone[0].nb_dev;
+	unsigned int chunk_sects = mddev->chunk_sectors;
+
+	if (is_power_of_2(chunk_sects)) {
+		int chunksect_bits = ffz(~chunk_sects);
+		/* find the sector offset inside the chunk */
+		sect_in_chunk  = sector & (chunk_sects - 1);
+		sector >>= chunksect_bits;
+		/* chunk in zone */
+		chunk = *sector_offset;
+		/* quotient is the chunk in real device*/
+		sector_div(chunk, zone->nb_dev << chunksect_bits);
+	} else{
+		sect_in_chunk = sector_div(sector, chunk_sects);
+		chunk = *sector_offset;
+		sector_div(chunk, chunk_sects * zone->nb_dev);
+	}
+	/*
+	*  position the bio over the real device
+	*  real sector = chunk in device + starting of zone
+	*	+ the position in the chunk
+	*/
+	*sector_offset = (chunk * chunk_sects) + sect_in_chunk;
+	return conf->devlist[(zone - conf->strip_zone)*raid_disks
+			     + sector_div(sector, zone->nb_dev)];
+}
+
 /**
- *	raid0_mergeable_bvec -- tell bio layer if a two requests can be merged
+ *	raid0_mergeable_bvec -- tell bio layer if two requests can be merged
  *	@q: request queue
  *	@bvm: properties of new bio
  *	@biovec: the request that could be merged to it.
@@ -303,10 +353,15 @@ static int raid0_mergeable_bvec(struct request_queue *q,
 				struct bio_vec *biovec)
 {
 	struct mddev *mddev = q->queuedata;
+	struct r0conf *conf = mddev->private;
 	sector_t sector = bvm->bi_sector + get_start_sect(bvm->bi_bdev);
+	sector_t sector_offset = sector;
 	int max;
 	unsigned int chunk_sectors = mddev->chunk_sectors;
 	unsigned int bio_sectors = bvm->bi_size >> 9;
+	struct strip_zone *zone;
+	struct md_rdev *rdev;
+	struct request_queue *subq;
 
 	if (is_power_of_2(chunk_sectors))
 		max =  (chunk_sectors - ((sector & (chunk_sectors-1))
@@ -314,10 +369,27 @@ static int raid0_mergeable_bvec(struct request_queue *q,
 	else
 		max =  (chunk_sectors - (sector_div(sector, chunk_sectors)
 						+ bio_sectors)) << 9;
-	if (max < 0) max = 0; /* bio_add cannot handle a negative return */
+	if (max < 0)
+		max = 0; /* bio_add cannot handle a negative return */
 	if (max <= biovec->bv_len && bio_sectors == 0)
 		return biovec->bv_len;
-	else 
+	if (max < biovec->bv_len)
+		/* too small already, no need to check further */
+		return max;
+	if (!conf->has_merge_bvec)
+		return max;
+
+	/* May need to check subordinate device */
+	sector = sector_offset;
+	zone = find_zone(mddev->private, &sector_offset);
+	rdev = map_sector(mddev, zone, sector, &sector_offset);
+	subq = bdev_get_queue(rdev->bdev);
+	if (subq->merge_bvec_fn) {
+		bvm->bi_bdev = rdev->bdev;
+		bvm->bi_sector = sector_offset + zone->dev_start +
+			rdev->data_offset;
+		return min(max, subq->merge_bvec_fn(subq, bvm, biovec));
+	} else
 		return max;
 }
 
@@ -329,7 +401,7 @@ static sector_t raid0_size(struct mddev *mddev, sector_t sectors, int raid_disks
 	WARN_ONCE(sectors || raid_disks,
 		  "%s does not support generic reshape\n", __func__);
 
-	list_for_each_entry(rdev, &mddev->disks, same_set)
+	rdev_for_each(rdev, mddev)
 		array_sectors += rdev->sectors;
 
 	return array_sectors;
@@ -397,62 +469,6 @@ static int raid0_stop(struct mddev *mddev)
 	return 0;
 }
 
-/* Find the zone which holds a particular offset
- * Update *sectorp to be an offset in that zone
- */
-static struct strip_zone *find_zone(struct r0conf *conf,
-				    sector_t *sectorp)
-{
-	int i;
-	struct strip_zone *z = conf->strip_zone;
-	sector_t sector = *sectorp;
-
-	for (i = 0; i < conf->nr_strip_zones; i++)
-		if (sector < z[i].zone_end) {
-			if (i)
-				*sectorp = sector - z[i-1].zone_end;
-			return z + i;
-		}
-	BUG();
-}
-
-/*
- * remaps the bio to the target device. we separate two flows.
- * power 2 flow and a general flow for the sake of perfromance
-*/
-static struct md_rdev *map_sector(struct mddev *mddev, struct strip_zone *zone,
-				sector_t sector, sector_t *sector_offset)
-{
-	unsigned int sect_in_chunk;
-	sector_t chunk;
-	struct r0conf *conf = mddev->private;
-	int raid_disks = conf->strip_zone[0].nb_dev;
-	unsigned int chunk_sects = mddev->chunk_sectors;
-
-	if (is_power_of_2(chunk_sects)) {
-		int chunksect_bits = ffz(~chunk_sects);
-		/* find the sector offset inside the chunk */
-		sect_in_chunk  = sector & (chunk_sects - 1);
-		sector >>= chunksect_bits;
-		/* chunk in zone */
-		chunk = *sector_offset;
-		/* quotient is the chunk in real device*/
-		sector_div(chunk, zone->nb_dev << chunksect_bits);
-	} else{
-		sect_in_chunk = sector_div(sector, chunk_sects);
-		chunk = *sector_offset;
-		sector_div(chunk, chunk_sects * zone->nb_dev);
-	}
-	/*
-	*  position the bio over the real device
-	*  real sector = chunk in device + starting of zone
-	*	+ the position in the chunk
-	*/
-	*sector_offset = (chunk * chunk_sects) + sect_in_chunk;
-	return conf->devlist[(zone - conf->strip_zone)*raid_disks
-			     + sector_div(sector, zone->nb_dev)];
-}
-
 /*
  * Is io distribute over 1 or more chunks ?
 */
@@ -505,7 +521,7 @@ static void raid0_make_request(struct mddev *mddev, struct bio *bio)
 	}
 
 	sector_offset = bio->bi_sector;
-	zone =  find_zone(mddev->private, &sector_offset);
+	zone = find_zone(mddev->private, &sector_offset);
 	tmp_dev = map_sector(mddev, zone, bio->bi_sector,
 			     &sector_offset);
 	bio->bi_bdev = tmp_dev->bdev;
@@ -543,7 +559,7 @@ static void *raid0_takeover_raid45(struct mddev *mddev)
 		return ERR_PTR(-EINVAL);
 	}
 
-	list_for_each_entry(rdev, &mddev->disks, same_set) {
+	rdev_for_each(rdev, mddev) {
 		/* check slot number for a disk */
 		if (rdev->raid_disk == mddev->raid_disks-1) {
 			printk(KERN_ERR "md/raid0:%s: raid5 must have missing parity disk!\n",

drivers/md/raid0.h

@@ -4,13 +4,16 @@
 struct strip_zone {
 	sector_t zone_end;	/* Start of the next zone (in sectors) */
 	sector_t dev_start;	/* Zone offset in real dev (in sectors) */
-	int nb_dev;		/* # of devices attached to the zone */
+	int	 nb_dev;	/* # of devices attached to the zone */
 };
 
 struct r0conf {
-	struct strip_zone *strip_zone;
-	struct md_rdev **devlist; /* lists of rdevs, pointed to by strip_zone->dev */
-	int nr_strip_zones;
+	struct strip_zone	*strip_zone;
+	struct md_rdev		**devlist; /* lists of rdevs, pointed to
+					    * by strip_zone->dev */
+	int			nr_strip_zones;
+	int			has_merge_bvec;	/* at least one member has
+						 * a merge_bvec_fn */
 };
 
 #endif

drivers/md/raid1.c

@@ -523,6 +523,7 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect
 		rdev = rcu_dereference(conf->mirrors[disk].rdev);
 		if (r1_bio->bios[disk] == IO_BLOCKED
 		    || rdev == NULL
+		    || test_bit(Unmerged, &rdev->flags)
 		    || test_bit(Faulty, &rdev->flags))
 			continue;
 		if (!test_bit(In_sync, &rdev->flags) &&
@@ -614,6 +615,39 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect
 	return best_disk;
 }
 
+static int raid1_mergeable_bvec(struct request_queue *q,
+				struct bvec_merge_data *bvm,
+				struct bio_vec *biovec)
+{
+	struct mddev *mddev = q->queuedata;
+	struct r1conf *conf = mddev->private;
+	sector_t sector = bvm->bi_sector + get_start_sect(bvm->bi_bdev);
+	int max = biovec->bv_len;
+
+	if (mddev->merge_check_needed) {
+		int disk;
+		rcu_read_lock();
+		for (disk = 0; disk < conf->raid_disks * 2; disk++) {
+			struct md_rdev *rdev = rcu_dereference(
+				conf->mirrors[disk].rdev);
+			if (rdev && !test_bit(Faulty, &rdev->flags)) {
+				struct request_queue *q =
+					bdev_get_queue(rdev->bdev);
+				if (q->merge_bvec_fn) {
+					bvm->bi_sector = sector +
+						rdev->data_offset;
+					bvm->bi_bdev = rdev->bdev;
+					max = min(max, q->merge_bvec_fn(
+							  q, bvm, biovec));
+				}
+			}
+		}
+		rcu_read_unlock();
+	}
+	return max;
+
+}
+
 int md_raid1_congested(struct mddev *mddev, int bits)
 {
 	struct r1conf *conf = mddev->private;
@@ -737,9 +771,22 @@ static void wait_barrier(struct r1conf *conf)
 	spin_lock_irq(&conf->resync_lock);
 	if (conf->barrier) {
 		conf->nr_waiting++;
-		wait_event_lock_irq(conf->wait_barrier, !conf->barrier,
+		/* Wait for the barrier to drop.
+		 * However if there are already pending
+		 * requests (preventing the barrier from
+		 * rising completely), and the
+		 * pre-process bio queue isn't empty,
+		 * then don't wait, as we need to empty
+		 * that queue to get the nr_pending
+		 * count down.
+		 */
+		wait_event_lock_irq(conf->wait_barrier,
+				    !conf->barrier ||
+				    (conf->nr_pending &&
+				     current->bio_list &&
+				     !bio_list_empty(current->bio_list)),
 				    conf->resync_lock,
-				    );
+			);
 		conf->nr_waiting--;
 	}
 	conf->nr_pending++;
@@ -1002,7 +1049,8 @@ read_again:
 			break;
 		}
 		r1_bio->bios[i] = NULL;
-		if (!rdev || test_bit(Faulty, &rdev->flags)) {
+		if (!rdev || test_bit(Faulty, &rdev->flags)
+		    || test_bit(Unmerged, &rdev->flags)) {
 			if (i < conf->raid_disks)
 				set_bit(R1BIO_Degraded, &r1_bio->state);
 			continue;
@@ -1322,6 +1370,7 @@ static int raid1_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 	struct mirror_info *p;
 	int first = 0;
 	int last = conf->raid_disks - 1;
+	struct request_queue *q = bdev_get_queue(rdev->bdev);
 
 	if (mddev->recovery_disabled == conf->recovery_disabled)
 		return -EBUSY;
@@ -1329,23 +1378,17 @@ static int raid1_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 	if (rdev->raid_disk >= 0)
 		first = last = rdev->raid_disk;
 
+	if (q->merge_bvec_fn) {
+		set_bit(Unmerged, &rdev->flags);
+		mddev->merge_check_needed = 1;
+	}
+
 	for (mirror = first; mirror <= last; mirror++) {
 		p = conf->mirrors+mirror;
 		if (!p->rdev) {
 
 			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 one lying with a single
-			 * page, as a one page request is never in
-			 * violation.
-			 */
-			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);
-			}
 
 			p->head_position = 0;
 			rdev->raid_disk = mirror;
@@ -1370,6 +1413,19 @@ static int raid1_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 			break;
 		}
 	}
+	if (err == 0 && test_bit(Unmerged, &rdev->flags)) {
+		/* Some requests might not have seen this new
+		 * merge_bvec_fn.  We must wait for them to complete
+		 * before merging the device fully.
+		 * First we make sure any code which has tested
+		 * our function has submitted the request, then
+		 * we wait for all outstanding requests to complete.
+		 */
+		synchronize_sched();
+		raise_barrier(conf);
+		lower_barrier(conf);
+		clear_bit(Unmerged, &rdev->flags);
+	}
 	md_integrity_add_rdev(rdev, mddev);
 	print_conf(conf);
 	return err;
@@ -2491,7 +2547,7 @@ static struct r1conf *setup_conf(struct mddev *mddev)
 
 	err = -EINVAL;
 	spin_lock_init(&conf->device_lock);
-	list_for_each_entry(rdev, &mddev->disks, same_set) {
+	rdev_for_each(rdev, mddev) {
 		int disk_idx = rdev->raid_disk;
 		if (disk_idx >= mddev->raid_disks
 		    || disk_idx < 0)
@@ -2609,20 +2665,11 @@ static int run(struct mddev *mddev)
 	if (IS_ERR(conf))
 		return PTR_ERR(conf);
 
-	list_for_each_entry(rdev, &mddev->disks, same_set) {
+	rdev_for_each(rdev, mddev) {
 		if (!mddev->gendisk)
 			continue;
 		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, as a one page request is never in violation.
-		 */
-		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);
-		}
 	}
 
 	mddev->degraded = 0;
@@ -2656,6 +2703,7 @@ static int run(struct mddev *mddev)
 	if (mddev->queue) {
 		mddev->queue->backing_dev_info.congested_fn = raid1_congested;
 		mddev->queue->backing_dev_info.congested_data = mddev;
+		blk_queue_merge_bvec(mddev->queue, raid1_mergeable_bvec);
 	}
 	return md_integrity_register(mddev);
 }

drivers/md/raid10.c

@@ -586,25 +586,68 @@ static sector_t raid10_find_virt(struct r10conf *conf, sector_t sector, int dev)
  *	@biovec: the request that could be merged to it.
  *
  *	Return amount of bytes we can accept at this offset
- *      If near_copies == raid_disk, there are no striping issues,
- *      but in that case, the function isn't called at all.
+ *	This requires checking for end-of-chunk if near_copies != raid_disks,
+ *	and for subordinate merge_bvec_fns if merge_check_needed.
  */
 static int raid10_mergeable_bvec(struct request_queue *q,
 				 struct bvec_merge_data *bvm,
 				 struct bio_vec *biovec)
 {
 	struct mddev *mddev = q->queuedata;
+	struct r10conf *conf = mddev->private;
 	sector_t sector = bvm->bi_sector + get_start_sect(bvm->bi_bdev);
 	int max;
 	unsigned int chunk_sectors = mddev->chunk_sectors;
 	unsigned int bio_sectors = bvm->bi_size >> 9;
 
-	max =  (chunk_sectors - ((sector & (chunk_sectors - 1)) + bio_sectors)) << 9;
-	if (max < 0) max = 0; /* bio_add cannot handle a negative return */
-	if (max <= biovec->bv_len && bio_sectors == 0)
-		return biovec->bv_len;
-	else
-		return max;
+	if (conf->near_copies < conf->raid_disks) {
+		max = (chunk_sectors - ((sector & (chunk_sectors - 1))
+					+ bio_sectors)) << 9;
+		if (max < 0)
+			/* bio_add cannot handle a negative return */
+			max = 0;
+		if (max <= biovec->bv_len && bio_sectors == 0)
+			return biovec->bv_len;
+	} else
+		max = biovec->bv_len;
+
+	if (mddev->merge_check_needed) {
+		struct r10bio r10_bio;
+		int s;
+		r10_bio.sector = sector;
+		raid10_find_phys(conf, &r10_bio);
+		rcu_read_lock();
+		for (s = 0; s < conf->copies; s++) {
+			int disk = r10_bio.devs[s].devnum;
+			struct md_rdev *rdev = rcu_dereference(
+				conf->mirrors[disk].rdev);
+			if (rdev && !test_bit(Faulty, &rdev->flags)) {
+				struct request_queue *q =
+					bdev_get_queue(rdev->bdev);
+				if (q->merge_bvec_fn) {
+					bvm->bi_sector = r10_bio.devs[s].addr
+						+ rdev->data_offset;
+					bvm->bi_bdev = rdev->bdev;
+					max = min(max, q->merge_bvec_fn(
+							  q, bvm, biovec));
+				}
+			}
+			rdev = rcu_dereference(conf->mirrors[disk].replacement);
+			if (rdev && !test_bit(Faulty, &rdev->flags)) {
+				struct request_queue *q =
+					bdev_get_queue(rdev->bdev);
+				if (q->merge_bvec_fn) {
+					bvm->bi_sector = r10_bio.devs[s].addr
+						+ rdev->data_offset;
+					bvm->bi_bdev = rdev->bdev;
+					max = min(max, q->merge_bvec_fn(
+							  q, bvm, biovec));
+				}
+			}
+		}
+		rcu_read_unlock();
+	}
+	return max;
 }
 
 /*
@@ -668,11 +711,12 @@ retry:
 		disk = r10_bio->devs[slot].devnum;
 		rdev = rcu_dereference(conf->mirrors[disk].replacement);
 		if (rdev == NULL || test_bit(Faulty, &rdev->flags) ||
+		    test_bit(Unmerged, &rdev->flags) ||
 		    r10_bio->devs[slot].addr + sectors > rdev->recovery_offset)
 			rdev = rcu_dereference(conf->mirrors[disk].rdev);
-		if (rdev == NULL)
-			continue;
-		if (test_bit(Faulty, &rdev->flags))
+		if (rdev == NULL ||
+		    test_bit(Faulty, &rdev->flags) ||
+		    test_bit(Unmerged, &rdev->flags))
 			continue;
 		if (!test_bit(In_sync, &rdev->flags) &&
 		    r10_bio->devs[slot].addr + sectors > rdev->recovery_offset)
@@ -863,9 +907,22 @@ static void wait_barrier(struct r10conf *conf)
 	spin_lock_irq(&conf->resync_lock);
 	if (conf->barrier) {
 		conf->nr_waiting++;
-		wait_event_lock_irq(conf->wait_barrier, !conf->barrier,
+		/* Wait for the barrier to drop.
+		 * However if there are already pending
+		 * requests (preventing the barrier from
+		 * rising completely), and the
+		 * pre-process bio queue isn't empty,
+		 * then don't wait, as we need to empty
+		 * that queue to get the nr_pending
+		 * count down.
+		 */
+		wait_event_lock_irq(conf->wait_barrier,
+				    !conf->barrier ||
+				    (conf->nr_pending &&
+				     current->bio_list &&
+				     !bio_list_empty(current->bio_list)),
 				    conf->resync_lock,
-				    );
+			);
 		conf->nr_waiting--;
 	}
 	conf->nr_pending++;
@@ -1121,12 +1178,14 @@ retry_write:
 			blocked_rdev = rrdev;
 			break;
 		}
-		if (rrdev && test_bit(Faulty, &rrdev->flags))
+		if (rrdev && (test_bit(Faulty, &rrdev->flags)
+			      || test_bit(Unmerged, &rrdev->flags)))
 			rrdev = NULL;
 
 		r10_bio->devs[i].bio = NULL;
 		r10_bio->devs[i].repl_bio = NULL;
-		if (!rdev || test_bit(Faulty, &rdev->flags)) {
+		if (!rdev || test_bit(Faulty, &rdev->flags) ||
+		    test_bit(Unmerged, &rdev->flags)) {
 			set_bit(R10BIO_Degraded, &r10_bio->state);
 			continue;
 		}
@@ -1477,18 +1536,24 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 	int mirror;
 	int first = 0;
 	int last = conf->raid_disks - 1;
+	struct request_queue *q = bdev_get_queue(rdev->bdev);
 
 	if (mddev->recovery_cp < MaxSector)
 		/* only hot-add to in-sync arrays, as recovery is
 		 * very different from resync
 		 */
 		return -EBUSY;
-	if (!enough(conf, -1))
+	if (rdev->saved_raid_disk < 0 && !enough(conf, -1))
 		return -EINVAL;
 
 	if (rdev->raid_disk >= 0)
 		first = last = rdev->raid_disk;
 
+	if (q->merge_bvec_fn) {
+		set_bit(Unmerged, &rdev->flags);
+		mddev->merge_check_needed = 1;
+	}
+
 	if (rdev->saved_raid_disk >= first &&
 	    conf->mirrors[rdev->saved_raid_disk].rdev == NULL)
 		mirror = rdev->saved_raid_disk;
@@ -1508,11 +1573,6 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 			err = 0;
 			disk_stack_limits(mddev->gendisk, rdev->bdev,
 					  rdev->data_offset << 9);
-			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->fullsync = 1;
 			rcu_assign_pointer(p->replacement, rdev);
 			break;
@@ -1520,17 +1580,6 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 
 		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 one lying with a single
-		 * page, as a one page request is never in
-		 * violation.
-		 */
-		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);
-		}
 
 		p->head_position = 0;
 		p->recovery_disabled = mddev->recovery_disabled - 1;
@@ -1541,7 +1590,19 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 		rcu_assign_pointer(p->rdev, rdev);
 		break;
 	}
-
+	if (err == 0 && test_bit(Unmerged, &rdev->flags)) {
+		/* Some requests might not have seen this new
+		 * merge_bvec_fn.  We must wait for them to complete
+		 * before merging the device fully.
+		 * First we make sure any code which has tested
+		 * our function has submitted the request, then
+		 * we wait for all outstanding requests to complete.
+		 */
+		synchronize_sched();
+		raise_barrier(conf, 0);
+		lower_barrier(conf);
+		clear_bit(Unmerged, &rdev->flags);
+	}
 	md_integrity_add_rdev(rdev, mddev);
 	print_conf(conf);
 	return err;
@@ -1682,10 +1743,8 @@ static void end_sync_write(struct bio *bio, int error)
 	d = find_bio_disk(conf, r10_bio, bio, &slot, &repl);
 	if (repl)
 		rdev = conf->mirrors[d].replacement;
-	if (!rdev) {
-		smp_mb();
+	else
 		rdev = conf->mirrors[d].rdev;
-	}
 
 	if (!uptodate) {
 		if (repl)
@@ -2087,6 +2146,7 @@ static void fix_read_error(struct r10conf *conf, struct mddev *mddev, struct r10
 			d = r10_bio->devs[sl].devnum;
 			rdev = rcu_dereference(conf->mirrors[d].rdev);
 			if (rdev &&
+			    !test_bit(Unmerged, &rdev->flags) &&
 			    test_bit(In_sync, &rdev->flags) &&
 			    is_badblock(rdev, r10_bio->devs[sl].addr + sect, s,
 					&first_bad, &bad_sectors) == 0) {
@@ -2140,6 +2200,7 @@ static void fix_read_error(struct r10conf *conf, struct mddev *mddev, struct r10
 			d = r10_bio->devs[sl].devnum;
 			rdev = rcu_dereference(conf->mirrors[d].rdev);
 			if (!rdev ||
+			    test_bit(Unmerged, &rdev->flags) ||
 			    !test_bit(In_sync, &rdev->flags))
 				continue;
 
@@ -3242,7 +3303,7 @@ static int run(struct mddev *mddev)
 		blk_queue_io_opt(mddev->queue, chunk_size *
 				 (conf->raid_disks / conf->near_copies));
 
-	list_for_each_entry(rdev, &mddev->disks, same_set) {
+	rdev_for_each(rdev, mddev) {
 
 		disk_idx = rdev->raid_disk;
 		if (disk_idx >= conf->raid_disks
@@ -3262,15 +3323,6 @@ static int run(struct mddev *mddev)
 
 		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);
-		}
 
 		disk->head_position = 0;
 	}
@@ -3334,8 +3386,7 @@ static int run(struct mddev *mddev)
 			mddev->queue->backing_dev_info.ra_pages = 2* stripe;
 	}
 
-	if (conf->near_copies < conf->raid_disks)
-		blk_queue_merge_bvec(mddev->queue, raid10_mergeable_bvec);
+	blk_queue_merge_bvec(mddev->queue, raid10_mergeable_bvec);
 
 	if (md_integrity_register(mddev))
 		goto out_free_conf;
@@ -3385,6 +3436,43 @@ static void raid10_quiesce(struct mddev *mddev, int state)
 	}
 }
 
+static int raid10_resize(struct mddev *mddev, sector_t sectors)
+{
+	/* Resize of 'far' arrays is not supported.
+	 * For 'near' and 'offset' arrays we can set the
+	 * number of sectors used to be an appropriate multiple
+	 * of the chunk size.
+	 * For 'offset', this is far_copies*chunksize.
+	 * For 'near' the multiplier is the LCM of
+	 * near_copies and raid_disks.
+	 * So if far_copies > 1 && !far_offset, fail.
+	 * Else find LCM(raid_disks, near_copy)*far_copies and
+	 * multiply by chunk_size.  Then round to this number.
+	 * This is mostly done by raid10_size()
+	 */
+	struct r10conf *conf = mddev->private;
+	sector_t oldsize, size;
+
+	if (conf->far_copies > 1 && !conf->far_offset)
+		return -EINVAL;
+
+	oldsize = raid10_size(mddev, 0, 0);
+	size = raid10_size(mddev, sectors, 0);
+	md_set_array_sectors(mddev, size);
+	if (mddev->array_sectors > size)
+		return -EINVAL;
+	set_capacity(mddev->gendisk, mddev->array_sectors);
+	revalidate_disk(mddev->gendisk);
+	if (sectors > mddev->dev_sectors &&
+	    mddev->recovery_cp > oldsize) {
+		mddev->recovery_cp = oldsize;
+		set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+	}
+	mddev->dev_sectors = sectors;
+	mddev->resync_max_sectors = size;
+	return 0;
+}
+
 static void *raid10_takeover_raid0(struct mddev *mddev)
 {
 	struct md_rdev *rdev;
@@ -3408,7 +3496,7 @@ static void *raid10_takeover_raid0(struct mddev *mddev)
 
 	conf = setup_conf(mddev);
 	if (!IS_ERR(conf)) {
-		list_for_each_entry(rdev, &mddev->disks, same_set)
+		rdev_for_each(rdev, mddev)
 			if (rdev->raid_disk >= 0)
 				rdev->new_raid_disk = rdev->raid_disk * 2;
 		conf->barrier = 1;
@@ -3454,6 +3542,7 @@ static struct md_personality raid10_personality =
 	.sync_request	= sync_request,
 	.quiesce	= raid10_quiesce,
 	.size		= raid10_size,
+	.resize		= raid10_resize,
 	.takeover	= raid10_takeover,
 };
 

drivers/md/raid5.c

@@ -208,11 +208,10 @@ static void __release_stripe(struct r5conf *conf, struct stripe_head *sh)
 			md_wakeup_thread(conf->mddev->thread);
 		} else {
 			BUG_ON(stripe_operations_active(sh));
-			if (test_and_clear_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) {
-				atomic_dec(&conf->preread_active_stripes);
-				if (atomic_read(&conf->preread_active_stripes) < IO_THRESHOLD)
+			if (test_and_clear_bit(STRIPE_PREREAD_ACTIVE, &sh->state))
+				if (atomic_dec_return(&conf->preread_active_stripes)
+				    < IO_THRESHOLD)
 					md_wakeup_thread(conf->mddev->thread);
-			}
 			atomic_dec(&conf->active_stripes);
 			if (!test_bit(STRIPE_EXPANDING, &sh->state)) {
 				list_add_tail(&sh->lru, &conf->inactive_list);
@@ -4843,7 +4842,7 @@ static struct r5conf *setup_conf(struct mddev *mddev)
 
 	pr_debug("raid456: run(%s) called.\n", mdname(mddev));
 
-	list_for_each_entry(rdev, &mddev->disks, same_set) {
+	rdev_for_each(rdev, mddev) {
 		raid_disk = rdev->raid_disk;
 		if (raid_disk >= max_disks
 		    || raid_disk < 0)
@@ -5178,7 +5177,7 @@ static int run(struct mddev *mddev)
 		blk_queue_io_opt(mddev->queue, chunk_size *
 				 (conf->raid_disks - conf->max_degraded));
 
-		list_for_each_entry(rdev, &mddev->disks, same_set)
+		rdev_for_each(rdev, mddev)
 			disk_stack_limits(mddev->gendisk, rdev->bdev,
 					  rdev->data_offset << 9);
 	}
@@ -5362,7 +5361,7 @@ static int raid5_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 	if (mddev->recovery_disabled == conf->recovery_disabled)
 		return -EBUSY;
 
-	if (has_failed(conf))
+	if (rdev->saved_raid_disk < 0 && has_failed(conf))
 		/* no point adding a device */
 		return -EINVAL;
 
@@ -5501,7 +5500,7 @@ static int raid5_start_reshape(struct mddev *mddev)
 	if (!check_stripe_cache(mddev))
 		return -ENOSPC;
 
-	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))
 			spares++;
@@ -5547,16 +5546,14 @@ static int raid5_start_reshape(struct mddev *mddev)
 	 * such devices during the reshape and confusion could result.
 	 */
 	if (mddev->delta_disks >= 0) {
-		int added_devices = 0;
-		list_for_each_entry(rdev, &mddev->disks, same_set)
+		rdev_for_each(rdev, mddev)
 			if (rdev->raid_disk < 0 &&
 			    !test_bit(Faulty, &rdev->flags)) {
 				if (raid5_add_disk(mddev, rdev) == 0) {
 					if (rdev->raid_disk
-					    >= conf->previous_raid_disks) {
+					    >= conf->previous_raid_disks)
 						set_bit(In_sync, &rdev->flags);
-						added_devices++;
-					} else
+					else
 						rdev->recovery_offset = 0;
 
 					if (sysfs_link_rdev(mddev, rdev))
@@ -5566,7 +5563,6 @@ static int raid5_start_reshape(struct mddev *mddev)
 				   && !test_bit(Faulty, &rdev->flags)) {
 				/* This is a spare that was manually added */
 				set_bit(In_sync, &rdev->flags);
-				added_devices++;
 			}
 
 		/* When a reshape changes the number of devices,
@@ -5592,6 +5588,7 @@ static int raid5_start_reshape(struct mddev *mddev)
 		spin_lock_irq(&conf->device_lock);
 		mddev->raid_disks = conf->raid_disks = conf->previous_raid_disks;
 		conf->reshape_progress = MaxSector;
+		mddev->reshape_position = MaxSector;
 		spin_unlock_irq(&conf->device_lock);
 		return -EAGAIN;
 	}

include/linux/raid/md_p.h

@@ -281,6 +281,10 @@ struct mdp_superblock_1 {
 					    * active device with same 'role'.
 					    * 'recovery_offset' is also set.
 					    */
-#define	MD_FEATURE_ALL			(1|2|4|8|16)
+#define	MD_FEATURE_ALL			(MD_FEATURE_BITMAP_OFFSET	\
+					|MD_FEATURE_RECOVERY_OFFSET	\
+					|MD_FEATURE_RESHAPE_ACTIVE	\
+					|MD_FEATURE_BAD_BLOCKS		\
+					|MD_FEATURE_REPLACEMENT)
 
 #endif