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

* 'for-linus' of git://neil.brown.name/md: (24 commits)
md: clean up do_md_stop
md: fix another deadlock with removing sysfs attributes.
md: move revalidate_disk() back outside open_mutex
md/raid10: fix deadlock with unaligned read during resync
md/bitmap: separate out loading a bitmap from initialising the structures.
md/bitmap: prepare for storing write-intent-bitmap via dm-dirty-log.
md/bitmap: optimise scanning of empty bitmaps.
md/bitmap: clean up plugging calls.
md/bitmap: reduce dependence on sysfs.
md/bitmap: white space clean up and similar.
md/raid5: export raid5 unplugging interface.
md/plug: optionally use plugger to unplug an array during resync/recovery.
md/raid5: add simple plugging infrastructure.
md/raid5: export is_congested test
raid5: Don't set read-ahead when there is no queue
md: add support for raising dm events.
md: export various start/stop interfaces
md: split out md_rdev_init
md: be more careful setting MD_CHANGE_CLEAN
md/raid5: ensure we create a unique name for kmem_cache when mddev has no gendisk
...

crypto/async_tx/Kconfig

···
 	tristate
 	select ASYNC_CORE
 	select ASYNC_PQ
+	select ASYNC_XOR
+
+config ASYNC_RAID6_TEST
+	tristate "Self test for hardware accelerated raid6 recovery"
+	depends on ASYNC_RAID6_RECOV
+	select ASYNC_MEMCPY
+	---help---
+	  This is a one-shot self test that permutes through the
+	  recovery of all the possible two disk failure scenarios for a
+	  N-disk array.  Recovery is performed with the asynchronous
+	  raid6 recovery routines, and will optionally use an offload
+	  engine if one is available.
+
+	  If unsure, say N.
 
 config ASYNC_TX_DISABLE_PQ_VAL_DMA
 	bool

drivers/md/Kconfig

···
 config MD_RAID456
 	tristate "RAID-4/RAID-5/RAID-6 mode"
 	depends on BLK_DEV_MD
-	select MD_RAID6_PQ
+	select RAID6_PQ
 	select ASYNC_MEMCPY
 	select ASYNC_XOR
 	select ASYNC_PQ
···
 	---help---
 	  Enable the raid456 module to dispatch per-stripe raid operations to a
 	  thread pool.
-
-	  If unsure, say N.
-
-config MD_RAID6_PQ
-	tristate
-
-config ASYNC_RAID6_TEST
-	tristate "Self test for hardware accelerated raid6 recovery"
-	depends on MD_RAID6_PQ
-	select ASYNC_RAID6_RECOV
-	---help---
-	  This is a one-shot self test that permutes through the
-	  recovery of all the possible two disk failure scenarios for a
-	  N-disk array.  Recovery is performed with the asynchronous
-	  raid6 recovery routines, and will optionally use an offload
-	  engine if one is available.
 
 	  If unsure, say N.
 

drivers/md/Makefile

···
 		+= dm-log-userspace-base.o dm-log-userspace-transfer.o
 md-mod-y	+= md.o bitmap.o
 raid456-y	+= raid5.o
-raid6_pq-y	+= raid6algos.o raid6recov.o raid6tables.o \
-		   raid6int1.o raid6int2.o raid6int4.o \
-		   raid6int8.o raid6int16.o raid6int32.o \
-		   raid6altivec1.o raid6altivec2.o raid6altivec4.o \
-		   raid6altivec8.o \
-		   raid6mmx.o raid6sse1.o raid6sse2.o
-hostprogs-y	+= mktables
 
 # Note: link order is important.  All raid personalities
 # and must come before md.o, as they each initialise 
···
 obj-$(CONFIG_MD_RAID0)		+= raid0.o
 obj-$(CONFIG_MD_RAID1)		+= raid1.o
 obj-$(CONFIG_MD_RAID10)		+= raid10.o
-obj-$(CONFIG_MD_RAID6_PQ)	+= raid6_pq.o
 obj-$(CONFIG_MD_RAID456)	+= raid456.o
 obj-$(CONFIG_MD_MULTIPATH)	+= multipath.o
 obj-$(CONFIG_MD_FAULTY)		+= faulty.o
···
 obj-$(CONFIG_DM_LOG_USERSPACE)	+= dm-log-userspace.o
 obj-$(CONFIG_DM_ZERO)		+= dm-zero.o
 
-quiet_cmd_unroll = UNROLL  $@
-      cmd_unroll = $(AWK) -f$(srctree)/$(src)/unroll.awk -vN=$(UNROLL) \
-                   < $< > $@ || ( rm -f $@ && exit 1 )
-
-ifeq ($(CONFIG_ALTIVEC),y)
-altivec_flags := -maltivec -mabi=altivec
-endif
-
 ifeq ($(CONFIG_DM_UEVENT),y)
 dm-mod-objs			+= dm-uevent.o
 endif
-
-targets += raid6int1.c
-$(obj)/raid6int1.c:   UNROLL := 1
-$(obj)/raid6int1.c:   $(src)/raid6int.uc $(src)/unroll.awk FORCE
-	$(call if_changed,unroll)
-
-targets += raid6int2.c
-$(obj)/raid6int2.c:   UNROLL := 2
-$(obj)/raid6int2.c:   $(src)/raid6int.uc $(src)/unroll.awk FORCE
-	$(call if_changed,unroll)
-
-targets += raid6int4.c
-$(obj)/raid6int4.c:   UNROLL := 4
-$(obj)/raid6int4.c:   $(src)/raid6int.uc $(src)/unroll.awk FORCE
-	$(call if_changed,unroll)
-
-targets += raid6int8.c
-$(obj)/raid6int8.c:   UNROLL := 8
-$(obj)/raid6int8.c:   $(src)/raid6int.uc $(src)/unroll.awk FORCE
-	$(call if_changed,unroll)
-
-targets += raid6int16.c
-$(obj)/raid6int16.c:  UNROLL := 16
-$(obj)/raid6int16.c:  $(src)/raid6int.uc $(src)/unroll.awk FORCE
-	$(call if_changed,unroll)
-
-targets += raid6int32.c
-$(obj)/raid6int32.c:  UNROLL := 32
-$(obj)/raid6int32.c:  $(src)/raid6int.uc $(src)/unroll.awk FORCE
-	$(call if_changed,unroll)
-
-CFLAGS_raid6altivec1.o += $(altivec_flags)
-targets += raid6altivec1.c
-$(obj)/raid6altivec1.c:   UNROLL := 1
-$(obj)/raid6altivec1.c:   $(src)/raid6altivec.uc $(src)/unroll.awk FORCE
-	$(call if_changed,unroll)
-
-CFLAGS_raid6altivec2.o += $(altivec_flags)
-targets += raid6altivec2.c
-$(obj)/raid6altivec2.c:   UNROLL := 2
-$(obj)/raid6altivec2.c:   $(src)/raid6altivec.uc $(src)/unroll.awk FORCE
-	$(call if_changed,unroll)
-
-CFLAGS_raid6altivec4.o += $(altivec_flags)
-targets += raid6altivec4.c
-$(obj)/raid6altivec4.c:   UNROLL := 4
-$(obj)/raid6altivec4.c:   $(src)/raid6altivec.uc $(src)/unroll.awk FORCE
-	$(call if_changed,unroll)
-
-CFLAGS_raid6altivec8.o += $(altivec_flags)
-targets += raid6altivec8.c
-$(obj)/raid6altivec8.c:   UNROLL := 8
-$(obj)/raid6altivec8.c:   $(src)/raid6altivec.uc $(src)/unroll.awk FORCE
-	$(call if_changed,unroll)
-
-quiet_cmd_mktable = TABLE   $@
-      cmd_mktable = $(obj)/mktables > $@ || ( rm -f $@ && exit 1 )
-
-targets += raid6tables.c
-$(obj)/raid6tables.c: $(obj)/mktables FORCE
-	$(call if_changed,mktable)

drivers/md/bitmap.c

···
  * Still to do:
  *
  * flush after percent set rather than just time based. (maybe both).
- * wait if count gets too high, wake when it drops to half.
  */
 
 #include <linux/blkdev.h>
···
 #include "md.h"
 #include "bitmap.h"
 
+#include <linux/dm-dirty-log.h>
 /* debug macros */
 
 #define DEBUG 0
···
 #define INJECT_FATAL_FAULT_3 0 /* undef */
 #endif
 
-//#define DPRINTK PRINTK /* set this NULL to avoid verbose debug output */
-#define DPRINTK(x...) do { } while(0)
-
 #ifndef PRINTK
 #  if DEBUG > 0
 #    define PRINTK(x...) printk(KERN_DEBUG x)
···
 #  endif
 #endif
 
-static inline char * bmname(struct bitmap *bitmap)
+static inline char *bmname(struct bitmap *bitmap)
 {
 	return bitmap->mddev ? mdname(bitmap->mddev) : "mdX";
 }
-
 
 /*
  * just a placeholder - calls kmalloc for bitmap pages
···
 #ifdef INJECT_FAULTS_1
 	page = NULL;
 #else
-	page = kmalloc(PAGE_SIZE, GFP_NOIO);
+	page = kzalloc(PAGE_SIZE, GFP_NOIO);
 #endif
 	if (!page)
 		printk("%s: bitmap_alloc_page FAILED\n", bmname(bitmap));
···
  * if we find our page, we increment the page's refcount so that it stays
  * allocated while we're using it
  */
-static int bitmap_checkpage(struct bitmap *bitmap, unsigned long page, int create)
+static int bitmap_checkpage(struct bitmap *bitmap,
+			    unsigned long page, int create)
 __releases(bitmap->lock)
 __acquires(bitmap->lock)
 {
···
 		return -EINVAL;
 	}
 
-
 	if (bitmap->bp[page].hijacked) /* it's hijacked, don't try to alloc */
 		return 0;
 
···
 	if (!create)
 		return -ENOENT;
 
-	spin_unlock_irq(&bitmap->lock);
-
 	/* this page has not been allocated yet */
 
-	if ((mappage = bitmap_alloc_page(bitmap)) == NULL) {
+	spin_unlock_irq(&bitmap->lock);
+	mappage = bitmap_alloc_page(bitmap);
+	spin_lock_irq(&bitmap->lock);
+
+	if (mappage == NULL) {
 		PRINTK("%s: bitmap map page allocation failed, hijacking\n",
 			bmname(bitmap));
 		/* failed - set the hijacked flag so that we can use the
 		 * pointer as a counter */
-		spin_lock_irq(&bitmap->lock);
 		if (!bitmap->bp[page].map)
 			bitmap->bp[page].hijacked = 1;
-		goto out;
-	}
-
-	/* got a page */
-
-	spin_lock_irq(&bitmap->lock);
-
-	/* recheck the page */
-
-	if (bitmap->bp[page].map || bitmap->bp[page].hijacked) {
+	} else if (bitmap->bp[page].map ||
+		   bitmap->bp[page].hijacked) {
 		/* somebody beat us to getting the page */
 		bitmap_free_page(bitmap, mappage);
 		return 0;
+	} else {
+
+		/* no page was in place and we have one, so install it */
+
+		bitmap->bp[page].map = mappage;
+		bitmap->missing_pages--;
 	}
-
-	/* no page was in place and we have one, so install it */
-
-	memset(mappage, 0, PAGE_SIZE);
-	bitmap->bp[page].map = mappage;
-	bitmap->missing_pages--;
-out:
 	return 0;
 }
-
 
 /* if page is completely empty, put it back on the free list, or dealloc it */
 /* if page was hijacked, unmark the flag so it might get alloced next time */
···
 	if (bitmap->bp[page].hijacked) { /* page was hijacked, undo this now */
 		bitmap->bp[page].hijacked = 0;
 		bitmap->bp[page].map = NULL;
-		return;
+	} else {
+		/* normal case, free the page */
+		ptr = bitmap->bp[page].map;
+		bitmap->bp[page].map = NULL;
+		bitmap->missing_pages++;
+		bitmap_free_page(bitmap, ptr);
 	}
-
-	/* normal case, free the page */
-
-#if 0
-/* actually ... let's not.  We will probably need the page again exactly when
- * memory is tight and we are flusing to disk
- */
-	return;
-#else
-	ptr = bitmap->bp[page].map;
-	bitmap->bp[page].map = NULL;
-	bitmap->missing_pages++;
-	bitmap_free_page(bitmap, ptr);
-	return;
-#endif
 }
-
 
 /*
  * bitmap file handling - read and write the bitmap file and its superblock
···
 
 	mdk_rdev_t *rdev;
 	sector_t target;
+	int did_alloc = 0;
 
-	if (!page)
+	if (!page) {
 		page = alloc_page(GFP_KERNEL);
-	if (!page)
-		return ERR_PTR(-ENOMEM);
+		if (!page)
+			return ERR_PTR(-ENOMEM);
+		did_alloc = 1;
+	}
 
 	list_for_each_entry(rdev, &mddev->disks, same_set) {
 		if (! test_bit(In_sync, &rdev->flags)
···
 			return page;
 		}
 	}
+	if (did_alloc)
+		put_page(page);
 	return ERR_PTR(-EIO);
 
 }
···
 	mddev_t *mddev = bitmap->mddev;
 
 	while ((rdev = next_active_rdev(rdev, mddev)) != NULL) {
-			int size = PAGE_SIZE;
-			loff_t offset = mddev->bitmap_info.offset;
-			if (page->index == bitmap->file_pages-1)
-				size = roundup(bitmap->last_page_size,
-					       bdev_logical_block_size(rdev->bdev));
-			/* Just make sure we aren't corrupting data or
-			 * metadata
-			 */
-			if (mddev->external) {
-				/* Bitmap could be anywhere. */
-				if (rdev->sb_start + offset + (page->index *(PAGE_SIZE/512)) >
-				    rdev->data_offset &&
-				    rdev->sb_start + offset < 
-				    rdev->data_offset + mddev->dev_sectors +
-				    (PAGE_SIZE/512))
-					goto bad_alignment;
-			} else if (offset < 0) {
-				/* DATA  BITMAP METADATA  */
-				if (offset
-				    + (long)(page->index * (PAGE_SIZE/512))
-				    + size/512 > 0)
-					/* bitmap runs in to metadata */
-					goto bad_alignment;
-				if (rdev->data_offset + mddev->dev_sectors
-				    > rdev->sb_start + offset)
-					/* data runs in to bitmap */
-					goto bad_alignment;
-			} else if (rdev->sb_start < rdev->data_offset) {
-				/* METADATA BITMAP DATA */
-				if (rdev->sb_start
-				    + offset
-				    + page->index*(PAGE_SIZE/512) + size/512
-				    > rdev->data_offset)
-					/* bitmap runs in to data */
-					goto bad_alignment;
-			} else {
-				/* DATA METADATA BITMAP - no problems */
-			}
-			md_super_write(mddev, rdev,
-				       rdev->sb_start + offset
-				       + page->index * (PAGE_SIZE/512),
-				       size,
-				       page);
+		int size = PAGE_SIZE;
+		loff_t offset = mddev->bitmap_info.offset;
+		if (page->index == bitmap->file_pages-1)
+			size = roundup(bitmap->last_page_size,
+				       bdev_logical_block_size(rdev->bdev));
+		/* Just make sure we aren't corrupting data or
+		 * metadata
+		 */
+		if (mddev->external) {
+			/* Bitmap could be anywhere. */
+			if (rdev->sb_start + offset + (page->index
+						       * (PAGE_SIZE/512))
+			    > rdev->data_offset
+			    &&
+			    rdev->sb_start + offset
+			    < (rdev->data_offset + mddev->dev_sectors
+			     + (PAGE_SIZE/512)))
+				goto bad_alignment;
+		} else if (offset < 0) {
+			/* DATA  BITMAP METADATA  */
+			if (offset
+			    + (long)(page->index * (PAGE_SIZE/512))
+			    + size/512 > 0)
+				/* bitmap runs in to metadata */
+				goto bad_alignment;
+			if (rdev->data_offset + mddev->dev_sectors
+			    > rdev->sb_start + offset)
+				/* data runs in to bitmap */
+				goto bad_alignment;
+		} else if (rdev->sb_start < rdev->data_offset) {
+			/* METADATA BITMAP DATA */
+			if (rdev->sb_start
+			    + offset
+			    + page->index*(PAGE_SIZE/512) + size/512
+			    > rdev->data_offset)
+				/* bitmap runs in to data */
+				goto bad_alignment;
+		} else {
+			/* DATA METADATA BITMAP - no problems */
+		}
+		md_super_write(mddev, rdev,
+			       rdev->sb_start + offset
+			       + page->index * (PAGE_SIZE/512),
+			       size,
+			       page);
 	}
 
 	if (wait)
···
 			bh = bh->b_this_page;
 		}
 
-		if (wait) {
+		if (wait)
 			wait_event(bitmap->write_wait,
 				   atomic_read(&bitmap->pending_writes)==0);
-		}
 	}
 	if (bitmap->flags & BITMAP_WRITE_ERROR)
 		bitmap_file_kick(bitmap);
···
 	struct buffer_head *bh;
 	sector_t block;
 
-	PRINTK("read bitmap file (%dB @ %Lu)\n", (int)PAGE_SIZE,
+	PRINTK("read bitmap file (%dB @ %llu)\n", (int)PAGE_SIZE,
 			(unsigned long long)index << PAGE_SHIFT);
 
 	page = alloc_page(GFP_KERNEL);
···
 	}
 out:
 	if (IS_ERR(page))
-		printk(KERN_ALERT "md: bitmap read error: (%dB @ %Lu): %ld\n",
+		printk(KERN_ALERT "md: bitmap read error: (%dB @ %llu): %ld\n",
 			(int)PAGE_SIZE,
 			(unsigned long long)index << PAGE_SHIFT,
 			PTR_ERR(page));
···
 	sb = kmap_atomic(bitmap->sb_page, KM_USER0);
 	old = le32_to_cpu(sb->state) & bits;
 	switch (op) {
-		case MASK_SET: sb->state |= cpu_to_le32(bits);
-				break;
-		case MASK_UNSET: sb->state &= cpu_to_le32(~bits);
-				break;
-		default: BUG();
+	case MASK_SET:
+		sb->state |= cpu_to_le32(bits);
+		break;
+	case MASK_UNSET:
+		sb->state &= cpu_to_le32(~bits);
+		break;
+	default:
+		BUG();
 	}
 	kunmap_atomic(sb, KM_USER0);
 	return old;
···
 static inline struct page *filemap_get_page(struct bitmap *bitmap,
 					unsigned long chunk)
 {
-	if (file_page_index(bitmap, chunk) >= bitmap->file_pages) return NULL;
+	if (bitmap->filemap == NULL)
+		return NULL;
+	if (file_page_index(bitmap, chunk) >= bitmap->file_pages)
+		return NULL;
 	return bitmap->filemap[file_page_index(bitmap, chunk)
 			       - file_page_index(bitmap, 0)];
 }
-
 
 static void bitmap_file_unmap(struct bitmap *bitmap)
 {
···
 	}
 }
 
-
 /*
  * bitmap_file_kick - if an error occurs while manipulating the bitmap file
  * then it is no longer reliable, so we stop using it and we mark the file
···
 				ptr = d_path(&bitmap->file->f_path, path,
 					     PAGE_SIZE);
 
-
 			printk(KERN_ALERT
 			      "%s: kicking failed bitmap file %s from array!\n",
 			      bmname(bitmap), IS_ERR(ptr) ? "" : ptr);
···
 }
 
 enum bitmap_page_attr {
-	BITMAP_PAGE_DIRTY = 0, // there are set bits that need to be synced
-	BITMAP_PAGE_CLEAN = 1, // there are bits that might need to be cleared
-	BITMAP_PAGE_NEEDWRITE=2, // there are cleared bits that need to be synced
+	BITMAP_PAGE_DIRTY = 0,     /* there are set bits that need to be synced */
+	BITMAP_PAGE_CLEAN = 1,     /* there are bits that might need to be cleared */
+	BITMAP_PAGE_NEEDWRITE = 2, /* there are cleared bits that need to be synced */
 };
 
 static inline void set_page_attr(struct bitmap *bitmap, struct page *page,
 				enum bitmap_page_attr attr)
 {
-	__set_bit((page->index<<2) + attr, bitmap->filemap_attr);
+	if (page)
+		__set_bit((page->index<<2) + attr, bitmap->filemap_attr);
+	else
+		__set_bit(attr, &bitmap->logattrs);
 }
 
 static inline void clear_page_attr(struct bitmap *bitmap, struct page *page,
 				enum bitmap_page_attr attr)
 {
-	__clear_bit((page->index<<2) + attr, bitmap->filemap_attr);
+	if (page)
+		__clear_bit((page->index<<2) + attr, bitmap->filemap_attr);
+	else
+		__clear_bit(attr, &bitmap->logattrs);
 }
 
 static inline unsigned long test_page_attr(struct bitmap *bitmap, struct page *page,
 					   enum bitmap_page_attr attr)
 {
-	return test_bit((page->index<<2) + attr, bitmap->filemap_attr);
+	if (page)
+		return test_bit((page->index<<2) + attr, bitmap->filemap_attr);
+	else
+		return test_bit(attr, &bitmap->logattrs);
 }
 
 /*
···
 static void bitmap_file_set_bit(struct bitmap *bitmap, sector_t block)
 {
 	unsigned long bit;
-	struct page *page;
+	struct page *page = NULL;
 	void *kaddr;
 	unsigned long chunk = block >> CHUNK_BLOCK_SHIFT(bitmap);
 
 	if (!bitmap->filemap) {
-		return;
+		struct dm_dirty_log *log = bitmap->mddev->bitmap_info.log;
+		if (log)
+			log->type->mark_region(log, chunk);
+	} else {
+
+		page = filemap_get_page(bitmap, chunk);
+		if (!page)
+			return;
+		bit = file_page_offset(bitmap, chunk);
+
+		/* set the bit */
+		kaddr = kmap_atomic(page, KM_USER0);
+		if (bitmap->flags & BITMAP_HOSTENDIAN)
+			set_bit(bit, kaddr);
+		else
+			ext2_set_bit(bit, kaddr);
+		kunmap_atomic(kaddr, KM_USER0);
+		PRINTK("set file bit %lu page %lu\n", bit, page->index);
 	}
-
-	page = filemap_get_page(bitmap, chunk);
-	if (!page) return;
-	bit = file_page_offset(bitmap, chunk);
-
- 	/* set the bit */
-	kaddr = kmap_atomic(page, KM_USER0);
-	if (bitmap->flags & BITMAP_HOSTENDIAN)
-		set_bit(bit, kaddr);
-	else
-		ext2_set_bit(bit, kaddr);
-	kunmap_atomic(kaddr, KM_USER0);
-	PRINTK("set file bit %lu page %lu\n", bit, page->index);
-
 	/* record page number so it gets flushed to disk when unplug occurs */
 	set_page_attr(bitmap, page, BITMAP_PAGE_DIRTY);
-
 }
 
 /* this gets called when the md device is ready to unplug its underlying
···
 
 	if (!bitmap)
 		return;
+	if (!bitmap->filemap) {
+		/* Must be using a dirty_log */
+		struct dm_dirty_log *log = bitmap->mddev->bitmap_info.log;
+		dirty = test_and_clear_bit(BITMAP_PAGE_DIRTY, &bitmap->logattrs);
+		need_write = test_and_clear_bit(BITMAP_PAGE_NEEDWRITE, &bitmap->logattrs);
+		if (dirty || need_write)
+			if (log->type->flush(log))
+				bitmap->flags |= BITMAP_WRITE_ERROR;
+		goto out;
+	}
 
 	/* look at each page to see if there are any set bits that need to be
 	 * flushed out to disk */
···
 			wait = 1;
 		spin_unlock_irqrestore(&bitmap->lock, flags);
 
-		if (dirty | need_write)
+		if (dirty || need_write)
 			write_page(bitmap, page, 0);
 	}
 	if (wait) { /* if any writes were performed, we need to wait on them */
···
 		else
 			md_super_wait(bitmap->mddev);
 	}
+out:
 	if (bitmap->flags & BITMAP_WRITE_ERROR)
 		bitmap_file_kick(bitmap);
 }
+EXPORT_SYMBOL(bitmap_unplug);
 
 static void bitmap_set_memory_bits(struct bitmap *bitmap, sector_t offset, int needed);
 /* * bitmap_init_from_disk -- called at bitmap_create time to initialize
···
 		printk(KERN_INFO "%s: bitmap file is out of date, doing full "
 			"recovery\n", bmname(bitmap));
 
-	bytes = (chunks + 7) / 8;
+	bytes = DIV_ROUND_UP(bitmap->chunks, 8);
 	if (!bitmap->mddev->bitmap_info.external)
 		bytes += sizeof(bitmap_super_t);
 
-	
-	num_pages = (bytes + PAGE_SIZE - 1) / PAGE_SIZE;
+	num_pages = DIV_ROUND_UP(bytes, PAGE_SIZE);
 
 	if (file && i_size_read(file->f_mapping->host) < bytes) {
 		printk(KERN_INFO "%s: bitmap file too short %lu < %lu\n",
···
 
 	/* We need 4 bits per page, rounded up to a multiple of sizeof(unsigned long) */
 	bitmap->filemap_attr = kzalloc(
-		roundup( DIV_ROUND_UP(num_pages*4, 8), sizeof(unsigned long)),
+		roundup(DIV_ROUND_UP(num_pages*4, 8), sizeof(unsigned long)),
 		GFP_KERNEL);
 	if (!bitmap->filemap_attr)
 		goto err;
···
 			if (outofdate) {
 				/*
 				 * if bitmap is out of date, dirty the
-			 	 * whole page and write it out
+				 * whole page and write it out
 				 */
 				paddr = kmap_atomic(page, KM_USER0);
 				memset(paddr + offset, 0xff,
···
 		}
 	}
 
- 	/* everything went OK */
+	/* everything went OK */
 	ret = 0;
 	bitmap_mask_state(bitmap, BITMAP_STALE, MASK_UNSET);
 
···
 	 */
 	int i;
 
-	for (i=0; i < bitmap->file_pages; i++)
+	for (i = 0; i < bitmap->file_pages; i++)
 		set_page_attr(bitmap, bitmap->filemap[i],
 			      BITMAP_PAGE_NEEDWRITE);
 }
-
 
 static void bitmap_count_page(struct bitmap *bitmap, sector_t offset, int inc)
 {
 	sector_t chunk = offset >> CHUNK_BLOCK_SHIFT(bitmap);
 	unsigned long page = chunk >> PAGE_COUNTER_SHIFT;
 	bitmap->bp[page].count += inc;
-/*
-	if (page == 0) printk("count page 0, offset %llu: %d gives %d\n",
-			      (unsigned long long)offset, inc, bitmap->bp[page].count);
-*/
 	bitmap_checkfree(bitmap, page);
 }
 static bitmap_counter_t *bitmap_get_counter(struct bitmap *bitmap,
···
 	struct page *page = NULL, *lastpage = NULL;
 	int blocks;
 	void *paddr;
+	struct dm_dirty_log *log = mddev->bitmap_info.log;
 
 	/* Use a mutex to guard daemon_work against
 	 * bitmap_destroy.
···
 	spin_lock_irqsave(&bitmap->lock, flags);
 	for (j = 0; j < bitmap->chunks; j++) {
 		bitmap_counter_t *bmc;
-		if (!bitmap->filemap)
-			/* error or shutdown */
-			break;
-
-		page = filemap_get_page(bitmap, j);
+		if (!bitmap->filemap) {
+			if (!log)
+				/* error or shutdown */
+				break;
+		} else
+			page = filemap_get_page(bitmap, j);
 
 		if (page != lastpage) {
 			/* skip this page unless it's marked as needing cleaning */
···
 					 (sector_t)j << CHUNK_BLOCK_SHIFT(bitmap),
 					 &blocks, 0);
 		if (bmc) {
-/*
-  if (j < 100) printk("bitmap: j=%lu, *bmc = 0x%x\n", j, *bmc);
-*/
 			if (*bmc)
 				bitmap->allclean = 0;
 
 			if (*bmc == 2) {
-				*bmc=1; /* maybe clear the bit next time */
+				*bmc = 1; /* maybe clear the bit next time */
 				set_page_attr(bitmap, page, BITMAP_PAGE_CLEAN);
 			} else if (*bmc == 1 && !bitmap->need_sync) {
 				/* we can clear the bit */
···
 						  -1);
 
 				/* clear the bit */
-				paddr = kmap_atomic(page, KM_USER0);
-				if (bitmap->flags & BITMAP_HOSTENDIAN)
-					clear_bit(file_page_offset(bitmap, j),
-						  paddr);
-				else
-					ext2_clear_bit(file_page_offset(bitmap, j),
-						       paddr);
-				kunmap_atomic(paddr, KM_USER0);
+				if (page) {
+					paddr = kmap_atomic(page, KM_USER0);
+					if (bitmap->flags & BITMAP_HOSTENDIAN)
+						clear_bit(file_page_offset(bitmap, j),
+							  paddr);
+					else
+						ext2_clear_bit(file_page_offset(bitmap, j),
+							       paddr);
+					kunmap_atomic(paddr, KM_USER0);
+				} else
+					log->type->clear_region(log, j);
 			}
 		} else
 			j |= PAGE_COUNTER_MASK;
···
 	spin_unlock_irqrestore(&bitmap->lock, flags);
 
 	/* now sync the final page */
-	if (lastpage != NULL) {
+	if (lastpage != NULL || log != NULL) {
 		spin_lock_irqsave(&bitmap->lock, flags);
 		if (test_page_attr(bitmap, lastpage, BITMAP_PAGE_NEEDWRITE)) {
 			clear_page_attr(bitmap, lastpage, BITMAP_PAGE_NEEDWRITE);
 			spin_unlock_irqrestore(&bitmap->lock, flags);
-			write_page(bitmap, lastpage, 0);
+			if (lastpage)
+				write_page(bitmap, lastpage, 0);
+			else
+				if (log->type->flush(log))
+					bitmap->flags |= BITMAP_WRITE_ERROR;
 		} else {
 			set_page_attr(bitmap, lastpage, BITMAP_PAGE_NEEDWRITE);
 			spin_unlock_irqrestore(&bitmap->lock, flags);
···
 
  done:
 	if (bitmap->allclean == 0)
-		bitmap->mddev->thread->timeout = 
+		bitmap->mddev->thread->timeout =
 			bitmap->mddev->bitmap_info.daemon_sleep;
 	mutex_unlock(&mddev->bitmap_info.mutex);
 }
···
 	unsigned long page = chunk >> PAGE_COUNTER_SHIFT;
 	unsigned long pageoff = (chunk & PAGE_COUNTER_MASK) << COUNTER_BYTE_SHIFT;
 	sector_t csize;
+	int err;
 
-	if (bitmap_checkpage(bitmap, page, create) < 0) {
+	err = bitmap_checkpage(bitmap, page, create);
+
+	if (bitmap->bp[page].hijacked ||
+	    bitmap->bp[page].map == NULL)
+		csize = ((sector_t)1) << (CHUNK_BLOCK_SHIFT(bitmap) +
+					  PAGE_COUNTER_SHIFT - 1);
+	else
 		csize = ((sector_t)1) << (CHUNK_BLOCK_SHIFT(bitmap));
-		*blocks = csize - (offset & (csize- 1));
+	*blocks = csize - (offset & (csize - 1));
+
+	if (err < 0)
 		return NULL;
-	}
+
 	/* now locked ... */
 
 	if (bitmap->bp[page].hijacked) { /* hijacked pointer */
 		/* should we use the first or second counter field
 		 * of the hijacked pointer? */
 		int hi = (pageoff > PAGE_COUNTER_MASK);
-		csize = ((sector_t)1) << (CHUNK_BLOCK_SHIFT(bitmap) +
-					  PAGE_COUNTER_SHIFT - 1);
-		*blocks = csize - (offset & (csize- 1));
 		return  &((bitmap_counter_t *)
 			  &bitmap->bp[page].map)[hi];
-	} else { /* page is allocated */
-		csize = ((sector_t)1) << (CHUNK_BLOCK_SHIFT(bitmap));
-		*blocks = csize - (offset & (csize- 1));
+	} else /* page is allocated */
 		return (bitmap_counter_t *)
 			&(bitmap->bp[page].map[pageoff]);
-	}
 }
 
 int bitmap_startwrite(struct bitmap *bitmap, sector_t offset, unsigned long sectors, int behind)
 {
-	if (!bitmap) return 0;
+	if (!bitmap)
+		return 0;
 
 	if (behind) {
 		int bw;
···
 			prepare_to_wait(&bitmap->overflow_wait, &__wait,
 					TASK_UNINTERRUPTIBLE);
 			spin_unlock_irq(&bitmap->lock);
-			blk_unplug(bitmap->mddev->queue);
+			md_unplug(bitmap->mddev);
 			schedule();
 			finish_wait(&bitmap->overflow_wait, &__wait);
 			continue;
 		}
 
-		switch(*bmc) {
+		switch (*bmc) {
 		case 0:
 			bitmap_file_set_bit(bitmap, offset);
-			bitmap_count_page(bitmap,offset, 1);
-			blk_plug_device_unlocked(bitmap->mddev->queue);
+			bitmap_count_page(bitmap, offset, 1);
 			/* fall through */
 		case 1:
 			*bmc = 2;
···
 		offset += blocks;
 		if (sectors > blocks)
 			sectors -= blocks;
-		else sectors = 0;
+		else
+			sectors = 0;
 	}
 	bitmap->allclean = 0;
 	return 0;
 }
+EXPORT_SYMBOL(bitmap_startwrite);
 
 void bitmap_endwrite(struct bitmap *bitmap, sector_t offset, unsigned long sectors,
 		     int success, int behind)
 {
-	if (!bitmap) return;
+	if (!bitmap)
+		return;
 	if (behind) {
 		if (atomic_dec_and_test(&bitmap->behind_writes))
 			wake_up(&bitmap->behind_wait);
···
 		    bitmap->events_cleared < bitmap->mddev->events) {
 			bitmap->events_cleared = bitmap->mddev->events;
 			bitmap->need_sync = 1;
-			sysfs_notify_dirent(bitmap->sysfs_can_clear);
+			sysfs_notify_dirent_safe(bitmap->sysfs_can_clear);
 		}
 
 		if (!success && ! (*bmc & NEEDED_MASK))
···
 			wake_up(&bitmap->overflow_wait);
 
 		(*bmc)--;
-		if (*bmc <= 2) {
+		if (*bmc <= 2)
 			set_page_attr(bitmap,
-				      filemap_get_page(bitmap, offset >> CHUNK_BLOCK_SHIFT(bitmap)),
+				      filemap_get_page(
+					      bitmap,
+					      offset >> CHUNK_BLOCK_SHIFT(bitmap)),
 				      BITMAP_PAGE_CLEAN);
-		}
+
 		spin_unlock_irqrestore(&bitmap->lock, flags);
 		offset += blocks;
 		if (sectors > blocks)
 			sectors -= blocks;
-		else sectors = 0;
+		else
+			sectors = 0;
 	}
 }
+EXPORT_SYMBOL(bitmap_endwrite);
 
 static int __bitmap_start_sync(struct bitmap *bitmap, sector_t offset, int *blocks,
 			       int degraded)
···
 	}
 	return rv;
 }
+EXPORT_SYMBOL(bitmap_start_sync);
 
 void bitmap_end_sync(struct bitmap *bitmap, sector_t offset, int *blocks, int aborted)
 {
 	bitmap_counter_t *bmc;
 	unsigned long flags;
-/*
-	if (offset == 0) printk("bitmap_end_sync 0 (%d)\n", aborted);
-*/	if (bitmap == NULL) {
+
+	if (bitmap == NULL) {
 		*blocks = 1024;
 		return;
 	}
···
 	if (bmc == NULL)
 		goto unlock;
 	/* locked */
-/*
-	if (offset == 0) printk("bitmap_end sync found 0x%x, blocks %d\n", *bmc, *blocks);
-*/
 	if (RESYNC(*bmc)) {
 		*bmc &= ~RESYNC_MASK;
 
 		if (!NEEDED(*bmc) && aborted)
 			*bmc |= NEEDED_MASK;
 		else {
-			if (*bmc <= 2) {
+			if (*bmc <= 2)
 				set_page_attr(bitmap,
 					      filemap_get_page(bitmap, offset >> CHUNK_BLOCK_SHIFT(bitmap)),
 					      BITMAP_PAGE_CLEAN);
-			}
 		}
 	}
  unlock:
 	spin_unlock_irqrestore(&bitmap->lock, flags);
 	bitmap->allclean = 0;
 }
+EXPORT_SYMBOL(bitmap_end_sync);
 
 void bitmap_close_sync(struct bitmap *bitmap)
 {
···
 		sector += blocks;
 	}
 }
+EXPORT_SYMBOL(bitmap_close_sync);
 
 void bitmap_cond_end_sync(struct bitmap *bitmap, sector_t sector)
 {
···
 		   atomic_read(&bitmap->mddev->recovery_active) == 0);
 
 	bitmap->mddev->curr_resync_completed = bitmap->mddev->curr_resync;
-	set_bit(MD_CHANGE_CLEAN, &bitmap->mddev->flags);
+	if (bitmap->mddev->persistent)
+		set_bit(MD_CHANGE_CLEAN, &bitmap->mddev->flags);
 	sector &= ~((1ULL << CHUNK_BLOCK_SHIFT(bitmap)) - 1);
 	s = 0;
 	while (s < sector && s < bitmap->mddev->resync_max_sectors) {
···
 	bitmap->last_end_sync = jiffies;
 	sysfs_notify(&bitmap->mddev->kobj, NULL, "sync_completed");
 }
+EXPORT_SYMBOL(bitmap_cond_end_sync);
 
 static void bitmap_set_memory_bits(struct bitmap *bitmap, sector_t offset, int needed)
 {
···
 		spin_unlock_irq(&bitmap->lock);
 		return;
 	}
-	if (! *bmc) {
+	if (!*bmc) {
 		struct page *page;
-		*bmc = 1 | (needed?NEEDED_MASK:0);
+		*bmc = 1 | (needed ? NEEDED_MASK : 0);
 		bitmap_count_page(bitmap, offset, 1);
 		page = filemap_get_page(bitmap, offset >> CHUNK_BLOCK_SHIFT(bitmap));
 		set_page_attr(bitmap, page, BITMAP_PAGE_CLEAN);
···
 	unsigned long pages;
 	struct file *file = mddev->bitmap_info.file;
 	int err;
-	sector_t start;
-	struct sysfs_dirent *bm;
+	struct sysfs_dirent *bm = NULL;
 
 	BUILD_BUG_ON(sizeof(bitmap_super_t) != 256);
 
-	if (!file && !mddev->bitmap_info.offset) /* bitmap disabled, nothing to do */
+	if (!file
+	    && !mddev->bitmap_info.offset
+	    && !mddev->bitmap_info.log) /* bitmap disabled, nothing to do */
 		return 0;
 
 	BUG_ON(file && mddev->bitmap_info.offset);
+	BUG_ON(mddev->bitmap_info.offset && mddev->bitmap_info.log);
 
 	bitmap = kzalloc(sizeof(*bitmap), GFP_KERNEL);
 	if (!bitmap)
···
 
 	bitmap->mddev = mddev;
 
-	bm = sysfs_get_dirent(mddev->kobj.sd, NULL, "bitmap");
+	if (mddev->kobj.sd)
+		bm = sysfs_get_dirent(mddev->kobj.sd, NULL, "bitmap");
 	if (bm) {
 		bitmap->sysfs_can_clear = sysfs_get_dirent(bm, NULL, "can_clear");
 		sysfs_put(bm);
···
 	bitmap->chunkshift = ffz(~mddev->bitmap_info.chunksize);
 
 	/* now that chunksize and chunkshift are set, we can use these macros */
- 	chunks = (blocks + CHUNK_BLOCK_RATIO(bitmap) - 1) >>
+	chunks = (blocks + CHUNK_BLOCK_RATIO(bitmap) - 1) >>
 			CHUNK_BLOCK_SHIFT(bitmap);
- 	pages = (chunks + PAGE_COUNTER_RATIO - 1) / PAGE_COUNTER_RATIO;
+	pages = (chunks + PAGE_COUNTER_RATIO - 1) / PAGE_COUNTER_RATIO;
 
 	BUG_ON(!pages);
 
···
 	if (!bitmap->bp)
 		goto error;
 
-	/* now that we have some pages available, initialize the in-memory
-	 * bitmap from the on-disk bitmap */
-	start = 0;
-	if (mddev->degraded == 0
-	    || bitmap->events_cleared == mddev->events)
-		/* no need to keep dirty bits to optimise a re-add of a missing device */
-		start = mddev->recovery_cp;
-	err = bitmap_init_from_disk(bitmap, start);
-
-	if (err)
-		goto error;
-
 	printk(KERN_INFO "created bitmap (%lu pages) for device %s\n",
 		pages, bmname(bitmap));
 
 	mddev->bitmap = bitmap;
 
-	mddev->thread->timeout = mddev->bitmap_info.daemon_sleep;
-	md_wakeup_thread(mddev->thread);
-
-	bitmap_update_sb(bitmap);
 
 	return (bitmap->flags & BITMAP_WRITE_ERROR) ? -EIO : 0;
 
···
 	return err;
 }
 
+int bitmap_load(mddev_t *mddev)
+{
+	int err = 0;
+	sector_t sector = 0;
+	struct bitmap *bitmap = mddev->bitmap;
+
+	if (!bitmap)
+		goto out;
+
+	/* Clear out old bitmap info first:  Either there is none, or we
+	 * are resuming after someone else has possibly changed things,
+	 * so we should forget old cached info.
+	 * All chunks should be clean, but some might need_sync.
+	 */
+	while (sector < mddev->resync_max_sectors) {
+		int blocks;
+		bitmap_start_sync(bitmap, sector, &blocks, 0);
+		sector += blocks;
+	}
+	bitmap_close_sync(bitmap);
+
+	if (mddev->bitmap_info.log) {
+		unsigned long i;
+		struct dm_dirty_log *log = mddev->bitmap_info.log;
+		for (i = 0; i < bitmap->chunks; i++)
+			if (!log->type->in_sync(log, i, 1))
+				bitmap_set_memory_bits(bitmap,
+						       (sector_t)i << CHUNK_BLOCK_SHIFT(bitmap),
+						       1);
+	} else {
+		sector_t start = 0;
+		if (mddev->degraded == 0
+		    || bitmap->events_cleared == mddev->events)
+			/* no need to keep dirty bits to optimise a
+			 * re-add of a missing device */
+			start = mddev->recovery_cp;
+
+		err = bitmap_init_from_disk(bitmap, start);
+	}
+	if (err)
+		goto out;
+
+	mddev->thread->timeout = mddev->bitmap_info.daemon_sleep;
+	md_wakeup_thread(mddev->thread);
+
+	bitmap_update_sb(bitmap);
+
+	if (bitmap->flags & BITMAP_WRITE_ERROR)
+		err = -EIO;
+out:
+	return err;
+}
+EXPORT_SYMBOL_GPL(bitmap_load);
+
 static ssize_t
 location_show(mddev_t *mddev, char *page)
 {
 	ssize_t len;
-	if (mddev->bitmap_info.file) {
+	if (mddev->bitmap_info.file)
 		len = sprintf(page, "file");
-	} else if (mddev->bitmap_info.offset) {
+	else if (mddev->bitmap_info.offset)
 		len = sprintf(page, "%+lld", (long long)mddev->bitmap_info.offset);
-	} else
+	else
 		len = sprintf(page, "none");
 	len += sprintf(page+len, "\n");
 	return len;
···
 	ssize_t len;
 	unsigned long secs = mddev->bitmap_info.daemon_sleep / HZ;
 	unsigned long jifs = mddev->bitmap_info.daemon_sleep % HZ;
-	
+
 	len = sprintf(page, "%lu", secs);
 	if (jifs)
 		len += sprintf(page+len, ".%03u", jiffies_to_msecs(jifs));
···
 	.attrs = md_bitmap_attrs,
 };
 
-
-/* the bitmap API -- for raid personalities */
-EXPORT_SYMBOL(bitmap_startwrite);
-EXPORT_SYMBOL(bitmap_endwrite);
-EXPORT_SYMBOL(bitmap_start_sync);
-EXPORT_SYMBOL(bitmap_end_sync);
-EXPORT_SYMBOL(bitmap_unplug);
-EXPORT_SYMBOL(bitmap_close_sync);
-EXPORT_SYMBOL(bitmap_cond_end_sync);

drivers/md/bitmap.h

···
 	unsigned long file_pages; /* number of pages in the file */
 	int last_page_size; /* bytes in the last page */
 
+	unsigned long logattrs; /* used when filemap_attr doesn't exist
+				 * because we are working with a dirty_log
+				 */
+
 	unsigned long flags;
 
 	int allclean;
···
 	wait_queue_head_t behind_wait;
 
 	struct sysfs_dirent *sysfs_can_clear;
+
 };
 
 /* the bitmap API */
 
 /* these are used only by md/bitmap */
 int  bitmap_create(mddev_t *mddev);
+int bitmap_load(mddev_t *mddev);
 void bitmap_flush(mddev_t *mddev);
 void bitmap_destroy(mddev_t *mddev);
 

drivers/md/md.c

···
  * Once ->stop is called and completes, the module will be completely
  * unused.
  */
-static void mddev_suspend(mddev_t *mddev)
+void mddev_suspend(mddev_t *mddev)
 {
 	BUG_ON(mddev->suspended);
 	mddev->suspended = 1;
···
 	wait_event(mddev->sb_wait, atomic_read(&mddev->active_io) == 0);
 	mddev->pers->quiesce(mddev, 1);
 }
+EXPORT_SYMBOL_GPL(mddev_suspend);
 
-static void mddev_resume(mddev_t *mddev)
+void mddev_resume(mddev_t *mddev)
 {
 	mddev->suspended = 0;
 	wake_up(&mddev->sb_wait);
 	mddev->pers->quiesce(mddev, 0);
 }
+EXPORT_SYMBOL_GPL(mddev_resume);
 
 int mddev_congested(mddev_t *mddev, int bits)
 {
···
 }
 EXPORT_SYMBOL(md_barrier_request);
 
+/* Support for plugging.
+ * This mirrors the plugging support in request_queue, but does not
+ * require having a whole queue
+ */
+static void plugger_work(struct work_struct *work)
+{
+	struct plug_handle *plug =
+		container_of(work, struct plug_handle, unplug_work);
+	plug->unplug_fn(plug);
+}
+static void plugger_timeout(unsigned long data)
+{
+	struct plug_handle *plug = (void *)data;
+	kblockd_schedule_work(NULL, &plug->unplug_work);
+}
+void plugger_init(struct plug_handle *plug,
+		  void (*unplug_fn)(struct plug_handle *))
+{
+	plug->unplug_flag = 0;
+	plug->unplug_fn = unplug_fn;
+	init_timer(&plug->unplug_timer);
+	plug->unplug_timer.function = plugger_timeout;
+	plug->unplug_timer.data = (unsigned long)plug;
+	INIT_WORK(&plug->unplug_work, plugger_work);
+}
+EXPORT_SYMBOL_GPL(plugger_init);
+
+void plugger_set_plug(struct plug_handle *plug)
+{
+	if (!test_and_set_bit(PLUGGED_FLAG, &plug->unplug_flag))
+		mod_timer(&plug->unplug_timer, jiffies + msecs_to_jiffies(3)+1);
+}
+EXPORT_SYMBOL_GPL(plugger_set_plug);
+
+int plugger_remove_plug(struct plug_handle *plug)
+{
+	if (test_and_clear_bit(PLUGGED_FLAG, &plug->unplug_flag)) {
+		del_timer(&plug->unplug_timer);
+		return 1;
+	} else
+		return 0;
+}
+EXPORT_SYMBOL_GPL(plugger_remove_plug);
+
+
 static inline mddev_t *mddev_get(mddev_t *mddev)
 {
 	atomic_inc(&mddev->active);
···
 	spin_unlock(&all_mddevs_lock);
 }
 
-static void mddev_init(mddev_t *mddev)
+void mddev_init(mddev_t *mddev)
 {
 	mutex_init(&mddev->open_mutex);
 	mutex_init(&mddev->reconfig_mutex);
···
 	mddev->resync_max = MaxSector;
 	mddev->level = LEVEL_NONE;
 }
+EXPORT_SYMBOL_GPL(mddev_init);
 
 static mddev_t * mddev_find(dev_t unit)
 {
···
 		 * an access to the files will try to take reconfig_mutex
 		 * while holding the file unremovable, which leads to
 		 * a deadlock.
-		 * So hold open_mutex instead - we are allowed to take
-		 * it while holding reconfig_mutex, and md_run can
-		 * use it to wait for the remove to complete.
+		 * So hold set sysfs_active while the remove in happeing,
+		 * and anything else which might set ->to_remove or my
+		 * otherwise change the sysfs namespace will fail with
+		 * -EBUSY if sysfs_active is still set.
+		 * We set sysfs_active under reconfig_mutex and elsewhere
+		 * test it under the same mutex to ensure its correct value
+		 * is seen.
 		 */
 		struct attribute_group *to_remove = mddev->to_remove;
 		mddev->to_remove = NULL;
-		mutex_lock(&mddev->open_mutex);
+		mddev->sysfs_active = 1;
 		mutex_unlock(&mddev->reconfig_mutex);
 
-		if (to_remove != &md_redundancy_group)
-			sysfs_remove_group(&mddev->kobj, to_remove);
-		if (mddev->pers == NULL ||
-		    mddev->pers->sync_request == NULL) {
-			sysfs_remove_group(&mddev->kobj, &md_redundancy_group);
-			if (mddev->sysfs_action)
-				sysfs_put(mddev->sysfs_action);
-			mddev->sysfs_action = NULL;
+		if (mddev->kobj.sd) {
+			if (to_remove != &md_redundancy_group)
+				sysfs_remove_group(&mddev->kobj, to_remove);
+			if (mddev->pers == NULL ||
+			    mddev->pers->sync_request == NULL) {
+				sysfs_remove_group(&mddev->kobj, &md_redundancy_group);
+				if (mddev->sysfs_action)
+					sysfs_put(mddev->sysfs_action);
+				mddev->sysfs_action = NULL;
+			}
 		}
-		mutex_unlock(&mddev->open_mutex);
+		mddev->sysfs_active = 0;
 	} else
 		mutex_unlock(&mddev->reconfig_mutex);
 
···
 		goto fail;
 
 	ko = &part_to_dev(rdev->bdev->bd_part)->kobj;
-	if ((err = sysfs_create_link(&rdev->kobj, ko, "block"))) {
-		kobject_del(&rdev->kobj);
-		goto fail;
-	}
-	rdev->sysfs_state = sysfs_get_dirent(rdev->kobj.sd, NULL, "state");
+	if (sysfs_create_link(&rdev->kobj, ko, "block"))
+		/* failure here is OK */;
+	rdev->sysfs_state = sysfs_get_dirent_safe(rdev->kobj.sd, "state");
 
 	list_add_rcu(&rdev->same_set, &mddev->disks);
 	bd_claim_by_disk(rdev->bdev, rdev->bdev->bd_holder, mddev->gendisk);
···
 		set_bit(In_sync, &rdev->flags);
 		err = 0;
 	}
-	if (!err && rdev->sysfs_state)
-		sysfs_notify_dirent(rdev->sysfs_state);
+	if (!err)
+		sysfs_notify_dirent_safe(rdev->sysfs_state);
 	return err ? err : len;
 }
 static struct rdev_sysfs_entry rdev_state =
···
 			rdev->raid_disk = -1;
 			return err;
 		} else
-			sysfs_notify_dirent(rdev->sysfs_state);
+			sysfs_notify_dirent_safe(rdev->sysfs_state);
 		sprintf(nm, "rd%d", rdev->raid_disk);
 		if (sysfs_create_link(&rdev->mddev->kobj, &rdev->kobj, nm))
-			printk(KERN_WARNING
-			       "md: cannot register "
-			       "%s for %s\n",
-			       nm, mdname(rdev->mddev));
-
+			/* failure here is OK */;
 		/* don't wakeup anyone, leave that to userspace. */
 	} else {
 		if (slot >= rdev->mddev->raid_disks)
···
 		clear_bit(Faulty, &rdev->flags);
 		clear_bit(WriteMostly, &rdev->flags);
 		set_bit(In_sync, &rdev->flags);
-		sysfs_notify_dirent(rdev->sysfs_state);
+		sysfs_notify_dirent_safe(rdev->sysfs_state);
 	}
 	return len;
 }
···
 	.default_attrs	= rdev_default_attrs,
 };
 
+void md_rdev_init(mdk_rdev_t *rdev)
+{
+	rdev->desc_nr = -1;
+	rdev->saved_raid_disk = -1;
+	rdev->raid_disk = -1;
+	rdev->flags = 0;
+	rdev->data_offset = 0;
+	rdev->sb_events = 0;
+	rdev->last_read_error.tv_sec  = 0;
+	rdev->last_read_error.tv_nsec = 0;
+	atomic_set(&rdev->nr_pending, 0);
+	atomic_set(&rdev->read_errors, 0);
+	atomic_set(&rdev->corrected_errors, 0);
+
+	INIT_LIST_HEAD(&rdev->same_set);
+	init_waitqueue_head(&rdev->blocked_wait);
+}
+EXPORT_SYMBOL_GPL(md_rdev_init);
 /*
  * Import a device. If 'super_format' >= 0, then sanity check the superblock
  *
···
 		return ERR_PTR(-ENOMEM);
 	}
 
+	md_rdev_init(rdev);
 	if ((err = alloc_disk_sb(rdev)))
 		goto abort_free;
 
···
 		goto abort_free;
 
 	kobject_init(&rdev->kobj, &rdev_ktype);
-
-	rdev->desc_nr = -1;
-	rdev->saved_raid_disk = -1;
-	rdev->raid_disk = -1;
-	rdev->flags = 0;
-	rdev->data_offset = 0;
-	rdev->sb_events = 0;
-	rdev->last_read_error.tv_sec  = 0;
-	rdev->last_read_error.tv_nsec = 0;
-	atomic_set(&rdev->nr_pending, 0);
-	atomic_set(&rdev->read_errors, 0);
-	atomic_set(&rdev->corrected_errors, 0);
 
 	size = rdev->bdev->bd_inode->i_size >> BLOCK_SIZE_BITS;
 	if (!size) {
···
 			goto abort_free;
 		}
 	}
-
-	INIT_LIST_HEAD(&rdev->same_set);
-	init_waitqueue_head(&rdev->blocked_wait);
 
 	return rdev;
 
···
 	 *  - new personality will access other array.
 	 */
 
-	if (mddev->sync_thread || mddev->reshape_position != MaxSector)
+	if (mddev->sync_thread ||
+	    mddev->reshape_position != MaxSector ||
+	    mddev->sysfs_active)
 		return -EBUSY;
 
 	if (!mddev->pers->quiesce) {
···
 	if (err)
 		return err;
 	else {
-		sysfs_notify_dirent(mddev->sysfs_state);
+		sysfs_notify_dirent_safe(mddev->sysfs_state);
 		return len;
 	}
 }
···
 	}
 	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 	md_wakeup_thread(mddev->thread);
-	sysfs_notify_dirent(mddev->sysfs_action);
+	sysfs_notify_dirent_safe(mddev->sysfs_action);
 	return len;
 }
 
···
 		       disk->disk_name);
 		error = 0;
 	}
-	if (sysfs_create_group(&mddev->kobj, &md_bitmap_group))
+	if (mddev->kobj.sd &&
+	    sysfs_create_group(&mddev->kobj, &md_bitmap_group))
 		printk(KERN_DEBUG "pointless warning\n");
  abort:
 	mutex_unlock(&disks_mutex);
-	if (!error) {
+	if (!error && mddev->kobj.sd) {
 		kobject_uevent(&mddev->kobj, KOBJ_ADD);
-		mddev->sysfs_state = sysfs_get_dirent(mddev->kobj.sd, NULL, "array_state");
+		mddev->sysfs_state = sysfs_get_dirent_safe(mddev->kobj.sd, "array_state");
 	}
 	mddev_put(mddev);
 	return error;
···
 	if (!atomic_read(&mddev->writes_pending)) {
 		mddev->safemode = 1;
 		if (mddev->external)
-			sysfs_notify_dirent(mddev->sysfs_state);
+			sysfs_notify_dirent_safe(mddev->sysfs_state);
 	}
 	md_wakeup_thread(mddev->thread);
 }
 
 static int start_dirty_degraded;
 
-static int md_run(mddev_t *mddev)
+int md_run(mddev_t *mddev)
 {
 	int err;
 	mdk_rdev_t *rdev;
···
 
 	if (mddev->pers)
 		return -EBUSY;
-
-	/* These two calls synchronise us with the
-	 * sysfs_remove_group calls in mddev_unlock,
-	 * so they must have completed.
-	 */
-	mutex_lock(&mddev->open_mutex);
-	mutex_unlock(&mddev->open_mutex);
+	/* Cannot run until previous stop completes properly */
+	if (mddev->sysfs_active)
+		return -EBUSY;
 
 	/*
 	 * Analyze all RAID superblock(s)
···
 				return -EINVAL;
 			}
 		}
-		sysfs_notify_dirent(rdev->sysfs_state);
+		sysfs_notify_dirent_safe(rdev->sysfs_state);
 	}
 
 	spin_lock(&pers_lock);
···
 		return err;
 	}
 	if (mddev->pers->sync_request) {
-		if (sysfs_create_group(&mddev->kobj, &md_redundancy_group))
+		if (mddev->kobj.sd &&
+		    sysfs_create_group(&mddev->kobj, &md_redundancy_group))
 			printk(KERN_WARNING
 			       "md: cannot register extra attributes for %s\n",
 			       mdname(mddev));
-		mddev->sysfs_action = sysfs_get_dirent(mddev->kobj.sd, NULL, "sync_action");
+		mddev->sysfs_action = sysfs_get_dirent_safe(mddev->kobj.sd, "sync_action");
 	} else if (mddev->ro == 2) /* auto-readonly not meaningful */
 		mddev->ro = 0;
 
···
 			char nm[20];
 			sprintf(nm, "rd%d", rdev->raid_disk);
 			if (sysfs_create_link(&mddev->kobj, &rdev->kobj, nm))
-				printk("md: cannot register %s for %s\n",
-				       nm, mdname(mddev));
+				/* failure here is OK */;
 		}
 	
 	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
···
 	md_wakeup_thread(mddev->sync_thread); /* possibly kick off a reshape */
 
 	md_new_event(mddev);
-	sysfs_notify_dirent(mddev->sysfs_state);
-	if (mddev->sysfs_action)
-		sysfs_notify_dirent(mddev->sysfs_action);
+	sysfs_notify_dirent_safe(mddev->sysfs_state);
+	sysfs_notify_dirent_safe(mddev->sysfs_action);
 	sysfs_notify(&mddev->kobj, NULL, "degraded");
 	return 0;
 }
+EXPORT_SYMBOL_GPL(md_run);
 
 static int do_md_run(mddev_t *mddev)
 {
···
 	err = md_run(mddev);
 	if (err)
 		goto out;
-
+	err = bitmap_load(mddev);
+	if (err) {
+		bitmap_destroy(mddev);
+		goto out;
+	}
 	set_capacity(mddev->gendisk, mddev->array_sectors);
 	revalidate_disk(mddev->gendisk);
 	kobject_uevent(&disk_to_dev(mddev->gendisk)->kobj, KOBJ_CHANGE);
···
 	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 	md_wakeup_thread(mddev->thread);
 	md_wakeup_thread(mddev->sync_thread);
-	sysfs_notify_dirent(mddev->sysfs_state);
+	sysfs_notify_dirent_safe(mddev->sysfs_state);
 	return 0;
 }
 
···
 	mddev->bitmap_info.chunksize = 0;
 	mddev->bitmap_info.daemon_sleep = 0;
 	mddev->bitmap_info.max_write_behind = 0;
+	mddev->plug = NULL;
 }
 
-static void md_stop_writes(mddev_t *mddev)
+void md_stop_writes(mddev_t *mddev)
 {
 	if (mddev->sync_thread) {
 		set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
···
 		md_update_sb(mddev, 1);
 	}
 }
+EXPORT_SYMBOL_GPL(md_stop_writes);
 
-static void md_stop(mddev_t *mddev)
+void md_stop(mddev_t *mddev)
 {
-	md_stop_writes(mddev);
-
 	mddev->pers->stop(mddev);
 	if (mddev->pers->sync_request && mddev->to_remove == NULL)
 		mddev->to_remove = &md_redundancy_group;
···
 	mddev->pers = NULL;
 	clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
 }
+EXPORT_SYMBOL_GPL(md_stop);
 
 static int md_set_readonly(mddev_t *mddev, int is_open)
 {
···
 		mddev->ro = 1;
 		set_disk_ro(mddev->gendisk, 1);
 		clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
-		sysfs_notify_dirent(mddev->sysfs_state);
+		sysfs_notify_dirent_safe(mddev->sysfs_state);
 		err = 0;	
 	}
 out:
···
  */
 static int do_md_stop(mddev_t * mddev, int mode, int is_open)
 {
-	int err = 0;
 	struct gendisk *disk = mddev->gendisk;
 	mdk_rdev_t *rdev;
 
 	mutex_lock(&mddev->open_mutex);
-	if (atomic_read(&mddev->openers) > is_open) {
+	if (atomic_read(&mddev->openers) > is_open ||
+	    mddev->sysfs_active) {
 		printk("md: %s still in use.\n",mdname(mddev));
-		err = -EBUSY;
-	} else if (mddev->pers) {
+		mutex_unlock(&mddev->open_mutex);
+		return -EBUSY;
+	}
 
+	if (mddev->pers) {
 		if (mddev->ro)
 			set_disk_ro(disk, 0);
 
+		md_stop_writes(mddev);
 		md_stop(mddev);
 		mddev->queue->merge_bvec_fn = NULL;
 		mddev->queue->unplug_fn = NULL;
 		mddev->queue->backing_dev_info.congested_fn = NULL;
 
 		/* tell userspace to handle 'inactive' */
-		sysfs_notify_dirent(mddev->sysfs_state);
+		sysfs_notify_dirent_safe(mddev->sysfs_state);
 
 		list_for_each_entry(rdev, &mddev->disks, same_set)
 			if (rdev->raid_disk >= 0) {
···
 			}
 
 		set_capacity(disk, 0);
+		mutex_unlock(&mddev->open_mutex);
 		revalidate_disk(disk);
 
 		if (mddev->ro)
 			mddev->ro = 0;
-		
-		err = 0;
-	}
-	mutex_unlock(&mddev->open_mutex);
-	if (err)
-		return err;
+	} else
+		mutex_unlock(&mddev->open_mutex);
 	/*
 	 * Free resources if final stop
 	 */
 	if (mode == 0) {
-
 		printk(KERN_INFO "md: %s stopped.\n", mdname(mddev));
 
 		bitmap_destroy(mddev);
···
 		kobject_uevent(&disk_to_dev(mddev->gendisk)->kobj, KOBJ_CHANGE);
 		if (mddev->hold_active == UNTIL_STOP)
 			mddev->hold_active = 0;
-
 	}
-	err = 0;
 	blk_integrity_unregister(disk);
 	md_new_event(mddev);
-	sysfs_notify_dirent(mddev->sysfs_state);
-	return err;
+	sysfs_notify_dirent_safe(mddev->sysfs_state);
+	return 0;
 }
 
 #ifndef MODULE
···
 		if (err)
 			export_rdev(rdev);
 		else
-			sysfs_notify_dirent(rdev->sysfs_state);
+			sysfs_notify_dirent_safe(rdev->sysfs_state);
 
 		md_update_sb(mddev, 1);
 		if (mddev->degraded)
···
 	err = 0;
 	if (mddev->pers) {
 		mddev->pers->quiesce(mddev, 1);
-		if (fd >= 0)
+		if (fd >= 0) {
 			err = bitmap_create(mddev);
+			if (!err)
+				err = bitmap_load(mddev);
+		}
 		if (fd < 0 || err) {
 			bitmap_destroy(mddev);
 			fd = -1; /* make sure to put the file */
···
 				mddev->bitmap_info.default_offset;
 			mddev->pers->quiesce(mddev, 1);
 			rv = bitmap_create(mddev);
+			if (!rv)
+				rv = bitmap_load(mddev);
 			if (rv)
 				bitmap_destroy(mddev);
 			mddev->pers->quiesce(mddev, 0);
···
 	if (_IOC_TYPE(cmd) == MD_MAJOR && mddev->ro && mddev->pers) {
 		if (mddev->ro == 2) {
 			mddev->ro = 0;
-			sysfs_notify_dirent(mddev->sysfs_state);
+			sysfs_notify_dirent_safe(mddev->sysfs_state);
 			set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 			md_wakeup_thread(mddev->thread);
 		} else {
···
 	mddev->pers->error_handler(mddev,rdev);
 	if (mddev->degraded)
 		set_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
-	sysfs_notify_dirent(rdev->sysfs_state);
+	sysfs_notify_dirent_safe(rdev->sysfs_state);
 	set_bit(MD_RECOVERY_INTR, &mddev->recovery);
 	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 	md_wakeup_thread(mddev->thread);
+	if (mddev->event_work.func)
+		schedule_work(&mddev->event_work);
 	md_new_event_inintr(mddev);
 }
 
···
 		spin_unlock_irq(&mddev->write_lock);
 	}
 	if (did_change)
-		sysfs_notify_dirent(mddev->sysfs_state);
+		sysfs_notify_dirent_safe(mddev->sysfs_state);
 	wait_event(mddev->sb_wait,
 		   !test_bit(MD_CHANGE_CLEAN, &mddev->flags) &&
 		   !test_bit(MD_CHANGE_PENDING, &mddev->flags));
···
 			mddev->safemode = 1;
 		spin_unlock_irq(&mddev->write_lock);
 		md_update_sb(mddev, 0);
-		sysfs_notify_dirent(mddev->sysfs_state);
+		sysfs_notify_dirent_safe(mddev->sysfs_state);
 	} else
 		spin_unlock_irq(&mddev->write_lock);
 
···
 		return 0;
 }
 EXPORT_SYMBOL_GPL(md_allow_write);
+
+void md_unplug(mddev_t *mddev)
+{
+	if (mddev->queue)
+		blk_unplug(mddev->queue);
+	if (mddev->plug)
+		mddev->plug->unplug_fn(mddev->plug);
+}
 
 #define SYNC_MARKS	10
 #define	SYNC_MARK_STEP	(3*HZ)
···
 		     >= mddev->resync_max - mddev->curr_resync_completed
 			    )) {
 			/* time to update curr_resync_completed */
-			blk_unplug(mddev->queue);
+			md_unplug(mddev);
 			wait_event(mddev->recovery_wait,
 				   atomic_read(&mddev->recovery_active) == 0);
 			mddev->curr_resync_completed =
 				mddev->curr_resync;
-			set_bit(MD_CHANGE_CLEAN, &mddev->flags);
+			if (mddev->persistent)
+				set_bit(MD_CHANGE_CLEAN, &mddev->flags);
 			sysfs_notify(&mddev->kobj, NULL, "sync_completed");
 		}
 
···
 		 * about not overloading the IO subsystem. (things like an
 		 * e2fsck being done on the RAID array should execute fast)
 		 */
-		blk_unplug(mddev->queue);
+		md_unplug(mddev);
 		cond_resched();
 
 		currspeed = ((unsigned long)(io_sectors-mddev->resync_mark_cnt))/2
···
 	 * this also signals 'finished resyncing' to md_stop
 	 */
  out:
-	blk_unplug(mddev->queue);
+	md_unplug(mddev);
 
 	wait_event(mddev->recovery_wait, !atomic_read(&mddev->recovery_active));
 
···
 					sprintf(nm, "rd%d", rdev->raid_disk);
 					if (sysfs_create_link(&mddev->kobj,
 							      &rdev->kobj, nm))
-						printk(KERN_WARNING
-						       "md: cannot register "
-						       "%s for %s\n",
-						       nm, mdname(mddev));
+						/* failure here is OK */;
 					spares++;
 					md_new_event(mddev);
 					set_bit(MD_CHANGE_DEVS, &mddev->flags);
···
 				mddev->safemode = 0;
 			spin_unlock_irq(&mddev->write_lock);
 			if (did_change)
-				sysfs_notify_dirent(mddev->sysfs_state);
+				sysfs_notify_dirent_safe(mddev->sysfs_state);
 		}
 
 		if (mddev->flags)
···
 			mddev->recovery = 0;
 			/* flag recovery needed just to double check */
 			set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
-			sysfs_notify_dirent(mddev->sysfs_action);
+			sysfs_notify_dirent_safe(mddev->sysfs_action);
 			md_new_event(mddev);
 			goto unlock;
 		}
···
 				mddev->recovery = 0;
 			} else
 				md_wakeup_thread(mddev->sync_thread);
-			sysfs_notify_dirent(mddev->sysfs_action);
+			sysfs_notify_dirent_safe(mddev->sysfs_action);
 			md_new_event(mddev);
 		}
 	unlock:
···
 			if (test_and_clear_bit(MD_RECOVERY_RECOVER,
 					       &mddev->recovery))
 				if (mddev->sysfs_action)
-					sysfs_notify_dirent(mddev->sysfs_action);
+					sysfs_notify_dirent_safe(mddev->sysfs_action);
 		}
 		mddev_unlock(mddev);
 	}
···
 
 void md_wait_for_blocked_rdev(mdk_rdev_t *rdev, mddev_t *mddev)
 {
-	sysfs_notify_dirent(rdev->sysfs_state);
+	sysfs_notify_dirent_safe(rdev->sysfs_state);
 	wait_event_timeout(rdev->blocked_wait,
 			   !test_bit(Blocked, &rdev->flags),
 			   msecs_to_jiffies(5000));

drivers/md/md.h

···
 typedef struct mddev_s mddev_t;
 typedef struct mdk_rdev_s mdk_rdev_t;
 
+/* generic plugging support - like that provided with request_queue,
+ * but does not require a request_queue
+ */
+struct plug_handle {
+	void			(*unplug_fn)(struct plug_handle *);
+	struct timer_list	unplug_timer;
+	struct work_struct	unplug_work;
+	unsigned long		unplug_flag;
+};
+#define	PLUGGED_FLAG 1
+void plugger_init(struct plug_handle *plug,
+		  void (*unplug_fn)(struct plug_handle *));
+void plugger_set_plug(struct plug_handle *plug);
+int plugger_remove_plug(struct plug_handle *plug);
+static inline void plugger_flush(struct plug_handle *plug)
+{
+	del_timer_sync(&plug->unplug_timer);
+	cancel_work_sync(&plug->unplug_work);
+}
+
 /*
  * MD's 'extended' device
  */
···
 	int				suspended;
 	atomic_t			active_io;
 	int				ro;
+	int				sysfs_active; /* set when sysfs deletes
+						       * are happening, so run/
+						       * takeover/stop are not safe
+						       */
 
 	struct gendisk			*gendisk;
 
···
 							 * hot-adding a bitmap.  It should
 							 * eventually be settable by sysfs.
 							 */
+		/* When md is serving under dm, it might use a
+		 * dirty_log to store the bits.
+		 */
+		struct dm_dirty_log *log;
+
 		struct mutex		mutex;
 		unsigned long		chunksize;
-		unsigned long		daemon_sleep; /* how many seconds between updates? */
+		unsigned long		daemon_sleep; /* how many jiffies between updates? */
 		unsigned long		max_write_behind; /* write-behind mode */
 		int			external;
 	} bitmap_info;
···
 	struct list_head		all_mddevs;
 
 	struct attribute_group		*to_remove;
+	struct plug_handle		*plug; /* if used by personality */
+
 	/* Generic barrier handling.
 	 * If there is a pending barrier request, all other
 	 * writes are blocked while the devices are flushed.
···
 	struct bio *barrier;
 	atomic_t flush_pending;
 	struct work_struct barrier_work;
+	struct work_struct event_work;	/* used by dm to report failure event */
 };
 
 
···
 	ssize_t (*store)(mddev_t *, const char *, size_t);
 };
 extern struct attribute_group md_bitmap_group;
+
+static inline struct sysfs_dirent *sysfs_get_dirent_safe(struct sysfs_dirent *sd, char *name)
+{
+	if (sd)
+		return sysfs_get_dirent(sd, NULL, name);
+	return sd;
+}
+static inline void sysfs_notify_dirent_safe(struct sysfs_dirent *sd)
+{
+	if (sd)
+		sysfs_notify_dirent(sd);
+}
 
 static inline char * mdname (mddev_t * mddev)
 {
···
 extern void md_integrity_add_rdev(mdk_rdev_t *rdev, mddev_t *mddev);
 extern int strict_strtoul_scaled(const char *cp, unsigned long *res, int scale);
 extern void restore_bitmap_write_access(struct file *file);
+extern void md_unplug(mddev_t *mddev);
 
+extern void mddev_init(mddev_t *mddev);
+extern int md_run(mddev_t *mddev);
+extern void md_stop(mddev_t *mddev);
+extern void md_stop_writes(mddev_t *mddev);
+extern void md_rdev_init(mdk_rdev_t *rdev);
+
+extern void mddev_suspend(mddev_t *mddev);
+extern void mddev_resume(mddev_t *mddev);
 #endif /* _MD_MD_H */

drivers/md/raid10.c

···
 		 */
 		bp = bio_split(bio,
 			       chunk_sects - (bio->bi_sector & (chunk_sects - 1)) );
+
+		/* Each of these 'make_request' calls will call 'wait_barrier'.
+		 * If the first succeeds but the second blocks due to the resync
+		 * thread raising the barrier, we will deadlock because the
+		 * IO to the underlying device will be queued in generic_make_request
+		 * and will never complete, so will never reduce nr_pending.
+		 * So increment nr_waiting here so no new raise_barriers will
+		 * succeed, and so the second wait_barrier cannot block.
+		 */
+		spin_lock_irq(&conf->resync_lock);
+		conf->nr_waiting++;
+		spin_unlock_irq(&conf->resync_lock);
+
 		if (make_request(mddev, &bp->bio1))
 			generic_make_request(&bp->bio1);
 		if (make_request(mddev, &bp->bio2))
 			generic_make_request(&bp->bio2);
+
+		spin_lock_irq(&conf->resync_lock);
+		conf->nr_waiting--;
+		wake_up(&conf->wait_barrier);
+		spin_unlock_irq(&conf->resync_lock);
 
 		bio_pair_release(bp);
 		return 0;

drivers/md/raid5.c

···
 		if (test_bit(STRIPE_HANDLE, &sh->state)) {
 			if (test_bit(STRIPE_DELAYED, &sh->state)) {
 				list_add_tail(&sh->lru, &conf->delayed_list);
-				blk_plug_device(conf->mddev->queue);
+				plugger_set_plug(&conf->plug);
 			} else if (test_bit(STRIPE_BIT_DELAY, &sh->state) &&
 				   sh->bm_seq - conf->seq_write > 0) {
 				list_add_tail(&sh->lru, &conf->bitmap_list);
-				blk_plug_device(conf->mddev->queue);
+				plugger_set_plug(&conf->plug);
 			} else {
 				clear_bit(STRIPE_BIT_DELAY, &sh->state);
 				list_add_tail(&sh->lru, &conf->handle_list);
···
 }
 
 static void unplug_slaves(mddev_t *mddev);
-static void raid5_unplug_device(struct request_queue *q);
 
 static struct stripe_head *
 get_active_stripe(raid5_conf_t *conf, sector_t sector,
···
 						     < (conf->max_nr_stripes *3/4)
 						     || !conf->inactive_blocked),
 						    conf->device_lock,
-						    raid5_unplug_device(conf->mddev->queue)
+						    md_raid5_unplug_device(conf)
 					);
 				conf->inactive_blocked = 0;
 			} else
···
 	struct kmem_cache *sc;
 	int devs = max(conf->raid_disks, conf->previous_raid_disks);
 
-	sprintf(conf->cache_name[0],
-		"raid%d-%s", conf->level, mdname(conf->mddev));
-	sprintf(conf->cache_name[1],
-		"raid%d-%s-alt", conf->level, mdname(conf->mddev));
+	if (conf->mddev->gendisk)
+		sprintf(conf->cache_name[0],
+			"raid%d-%s", conf->level, mdname(conf->mddev));
+	else
+		sprintf(conf->cache_name[0],
+			"raid%d-%p", conf->level, conf->mddev);
+	sprintf(conf->cache_name[1], "%s-alt", conf->cache_name[0]);
+
 	conf->active_name = 0;
 	sc = kmem_cache_create(conf->cache_name[conf->active_name],
 			       sizeof(struct stripe_head)+(devs-1)*sizeof(struct r5dev),
···
 			list_add_tail(&sh->lru, &conf->hold_list);
 		}
 	} else
-		blk_plug_device(conf->mddev->queue);
+		plugger_set_plug(&conf->plug);
 }
 
 static void activate_bit_delay(raid5_conf_t *conf)
···
 	rcu_read_unlock();
 }
 
-static void raid5_unplug_device(struct request_queue *q)
+void md_raid5_unplug_device(raid5_conf_t *conf)
 {
-	mddev_t *mddev = q->queuedata;
-	raid5_conf_t *conf = mddev->private;
 	unsigned long flags;
 
 	spin_lock_irqsave(&conf->device_lock, flags);
 
-	if (blk_remove_plug(q)) {
+	if (plugger_remove_plug(&conf->plug)) {
 		conf->seq_flush++;
 		raid5_activate_delayed(conf);
 	}
-	md_wakeup_thread(mddev->thread);
+	md_wakeup_thread(conf->mddev->thread);
 
 	spin_unlock_irqrestore(&conf->device_lock, flags);
 
-	unplug_slaves(mddev);
+	unplug_slaves(conf->mddev);
+}
+EXPORT_SYMBOL_GPL(md_raid5_unplug_device);
+
+static void raid5_unplug(struct plug_handle *plug)
+{
+	raid5_conf_t *conf = container_of(plug, raid5_conf_t, plug);
+	md_raid5_unplug_device(conf);
 }
 
-static int raid5_congested(void *data, int bits)
+static void raid5_unplug_queue(struct request_queue *q)
 {
-	mddev_t *mddev = data;
+	mddev_t *mddev = q->queuedata;
+	md_raid5_unplug_device(mddev->private);
+}
+
+int md_raid5_congested(mddev_t *mddev, int bits)
+{
 	raid5_conf_t *conf = mddev->private;
 
 	/* No difference between reads and writes.  Just check
 	 * how busy the stripe_cache is
 	 */
 
-	if (mddev_congested(mddev, bits))
-		return 1;
 	if (conf->inactive_blocked)
 		return 1;
 	if (conf->quiesce)
···
 		return 1;
 
 	return 0;
+}
+EXPORT_SYMBOL_GPL(md_raid5_congested);
+
+static int raid5_congested(void *data, int bits)
+{
+	mddev_t *mddev = data;
+
+	return mddev_congested(mddev, bits) ||
+		md_raid5_congested(mddev, bits);
 }
 
 /* We want read requests to align with chunks where possible,
···
 				 * add failed due to overlap.  Flush everything
 				 * and wait a while
 				 */
-				raid5_unplug_device(mddev->queue);
+				md_raid5_unplug_device(conf);
 				release_stripe(sh);
 				schedule();
 				goto retry;
···
 		return 0;
 }
 
+int
+raid5_set_cache_size(mddev_t *mddev, int size)
+{
+	raid5_conf_t *conf = mddev->private;
+	int err;
+
+	if (size <= 16 || size > 32768)
+		return -EINVAL;
+	while (size < conf->max_nr_stripes) {
+		if (drop_one_stripe(conf))
+			conf->max_nr_stripes--;
+		else
+			break;
+	}
+	err = md_allow_write(mddev);
+	if (err)
+		return err;
+	while (size > conf->max_nr_stripes) {
+		if (grow_one_stripe(conf))
+			conf->max_nr_stripes++;
+		else break;
+	}
+	return 0;
+}
+EXPORT_SYMBOL(raid5_set_cache_size);
+
 static ssize_t
 raid5_store_stripe_cache_size(mddev_t *mddev, const char *page, size_t len)
 {
···
 
 	if (strict_strtoul(page, 10, &new))
 		return -EINVAL;
-	if (new <= 16 || new > 32768)
-		return -EINVAL;
-	while (new < conf->max_nr_stripes) {
-		if (drop_one_stripe(conf))
-			conf->max_nr_stripes--;
-		else
-			break;
-	}
-	err = md_allow_write(mddev);
+	err = raid5_set_cache_size(mddev, new);
 	if (err)
 		return err;
-	while (new > conf->max_nr_stripes) {
-		if (grow_one_stripe(conf))
-			conf->max_nr_stripes++;
-		else break;
-	}
 	return len;
 }
 
···
 static int run(mddev_t *mddev)
 {
 	raid5_conf_t *conf;
-	int working_disks = 0, chunk_size;
+	int working_disks = 0;
 	int dirty_parity_disks = 0;
 	mdk_rdev_t *rdev;
 	sector_t reshape_offset = 0;
···
 							"reshape");
 	}
 
-	/* read-ahead size must cover two whole stripes, which is
-	 * 2 * (datadisks) * chunksize where 'n' is the number of raid devices
-	 */
-	{
+
+	/* Ok, everything is just fine now */
+	if (mddev->to_remove == &raid5_attrs_group)
+		mddev->to_remove = NULL;
+	else if (mddev->kobj.sd &&
+	    sysfs_create_group(&mddev->kobj, &raid5_attrs_group))
+		printk(KERN_WARNING
+		       "raid5: failed to create sysfs attributes for %s\n",
+		       mdname(mddev));
+	md_set_array_sectors(mddev, raid5_size(mddev, 0, 0));
+
+	plugger_init(&conf->plug, raid5_unplug);
+	mddev->plug = &conf->plug;
+	if (mddev->queue) {
+		int chunk_size;
+		/* read-ahead size must cover two whole stripes, which
+		 * is 2 * (datadisks) * chunksize where 'n' is the
+		 * number of raid devices
+		 */
 		int data_disks = conf->previous_raid_disks - conf->max_degraded;
 		int stripe = data_disks *
 			((mddev->chunk_sectors << 9) / PAGE_SIZE);
 		if (mddev->queue->backing_dev_info.ra_pages < 2 * stripe)
 			mddev->queue->backing_dev_info.ra_pages = 2 * stripe;
+
+		blk_queue_merge_bvec(mddev->queue, raid5_mergeable_bvec);
+
+		mddev->queue->backing_dev_info.congested_data = mddev;
+		mddev->queue->backing_dev_info.congested_fn = raid5_congested;
+		mddev->queue->queue_lock = &conf->device_lock;
+		mddev->queue->unplug_fn = raid5_unplug_queue;
+
+		chunk_size = mddev->chunk_sectors << 9;
+		blk_queue_io_min(mddev->queue, chunk_size);
+		blk_queue_io_opt(mddev->queue, chunk_size *
+				 (conf->raid_disks - conf->max_degraded));
+
+		list_for_each_entry(rdev, &mddev->disks, same_set)
+			disk_stack_limits(mddev->gendisk, rdev->bdev,
+					  rdev->data_offset << 9);
 	}
-
-	/* Ok, everything is just fine now */
-	if (mddev->to_remove == &raid5_attrs_group)
-		mddev->to_remove = NULL;
-	else if (sysfs_create_group(&mddev->kobj, &raid5_attrs_group))
-		printk(KERN_WARNING
-		       "md/raid:%s: failed to create sysfs attributes.\n",
-		       mdname(mddev));
-
-	mddev->queue->queue_lock = &conf->device_lock;
-
-	mddev->queue->unplug_fn = raid5_unplug_device;
-	mddev->queue->backing_dev_info.congested_data = mddev;
-	mddev->queue->backing_dev_info.congested_fn = raid5_congested;
-
-	md_set_array_sectors(mddev, raid5_size(mddev, 0, 0));
-
-	blk_queue_merge_bvec(mddev->queue, raid5_mergeable_bvec);
-	chunk_size = mddev->chunk_sectors << 9;
-	blk_queue_io_min(mddev->queue, chunk_size);
-	blk_queue_io_opt(mddev->queue, chunk_size *
-			 (conf->raid_disks - conf->max_degraded));
-
-	list_for_each_entry(rdev, &mddev->disks, same_set)
-		disk_stack_limits(mddev->gendisk, rdev->bdev,
-				  rdev->data_offset << 9);
 
 	return 0;
 abort:
···
 
 	md_unregister_thread(mddev->thread);
 	mddev->thread = NULL;
-	mddev->queue->backing_dev_info.congested_fn = NULL;
-	blk_sync_queue(mddev->queue); /* the unplug fn references 'conf'*/
+	if (mddev->queue)
+		mddev->queue->backing_dev_info.congested_fn = NULL;
+	plugger_flush(&conf->plug); /* the unplug fn references 'conf'*/
 	free_conf(conf);
 	mddev->private = NULL;
 	mddev->to_remove = &raid5_attrs_group;
···
 				sprintf(nm, "rd%d", rdev->raid_disk);
 				if (sysfs_create_link(&mddev->kobj,
 						      &rdev->kobj, nm))
-					printk(KERN_WARNING
-					       "md/raid:%s: failed to create "
-					       " link %s\n",
-					       mdname(mddev), nm);
+					/* Failure here is OK */;
 			} else
 				break;
 		}
···
 		/* read-ahead size must cover two whole stripes, which is
 		 * 2 * (datadisks) * chunksize where 'n' is the number of raid devices
 		 */
-		{
+		if (conf->mddev->queue) {
 			int data_disks = conf->raid_disks - conf->max_degraded;
 			int stripe = data_disks * ((conf->chunk_sectors << 9)
 						   / PAGE_SIZE);

drivers/md/raid5.h

···
 	 * two caches.
 	 */
 	int			active_name;
-	char			cache_name[2][20];
+	char			cache_name[2][32];
 	struct kmem_cache		*slab_cache; /* for allocating stripes */
 
 	int			seq_flush, seq_write;
···
 					    * (fresh device added).
 					    * Cleared when a sync completes.
 					    */
+
+	struct plug_handle	plug;
+
 	/* per cpu variables */
 	struct raid5_percpu {
 		struct page	*spare_page; /* Used when checking P/Q in raid6 */
···
 {
 	return layout >= 8 && layout <= 10;
 }
+
+extern int md_raid5_congested(mddev_t *mddev, int bits);
+extern void md_raid5_unplug_device(raid5_conf_t *conf);
+extern int raid5_set_cache_size(mddev_t *mddev, int size);
 #endif

lib/Kconfig

···
 
 menu "Library routines"
 
+config RAID6_PQ
+	tristate
+
 config BITREVERSE
 	tristate
 

lib/Makefile

···
 obj-$(CONFIG_REED_SOLOMON) += reed_solomon/
 obj-$(CONFIG_LZO_COMPRESS) += lzo/
 obj-$(CONFIG_LZO_DECOMPRESS) += lzo/
+obj-$(CONFIG_RAID6_PQ) += raid6/
 
 lib-$(CONFIG_DECOMPRESS_GZIP) += decompress_inflate.o
 lib-$(CONFIG_DECOMPRESS_BZIP2) += decompress_bunzip2.o

lib/raid6/Makefile

···
+obj-$(CONFIG_RAID6_PQ)	+= raid6_pq.o
+
+raid6_pq-y	+= raid6algos.o raid6recov.o raid6tables.o \
+		   raid6int1.o raid6int2.o raid6int4.o \
+		   raid6int8.o raid6int16.o raid6int32.o \
+		   raid6altivec1.o raid6altivec2.o raid6altivec4.o \
+		   raid6altivec8.o \
+		   raid6mmx.o raid6sse1.o raid6sse2.o
+hostprogs-y	+= mktables
+
+quiet_cmd_unroll = UNROLL  $@
+      cmd_unroll = $(AWK) -f$(srctree)/$(src)/unroll.awk -vN=$(UNROLL) \
+                   < $< > $@ || ( rm -f $@ && exit 1 )
+
+ifeq ($(CONFIG_ALTIVEC),y)
+altivec_flags := -maltivec -mabi=altivec
+endif
+
+targets += raid6int1.c
+$(obj)/raid6int1.c:   UNROLL := 1
+$(obj)/raid6int1.c:   $(src)/raid6int.uc $(src)/unroll.awk FORCE
+	$(call if_changed,unroll)
+
+targets += raid6int2.c
+$(obj)/raid6int2.c:   UNROLL := 2
+$(obj)/raid6int2.c:   $(src)/raid6int.uc $(src)/unroll.awk FORCE
+	$(call if_changed,unroll)
+
+targets += raid6int4.c
+$(obj)/raid6int4.c:   UNROLL := 4
+$(obj)/raid6int4.c:   $(src)/raid6int.uc $(src)/unroll.awk FORCE
+	$(call if_changed,unroll)
+
+targets += raid6int8.c
+$(obj)/raid6int8.c:   UNROLL := 8
+$(obj)/raid6int8.c:   $(src)/raid6int.uc $(src)/unroll.awk FORCE
+	$(call if_changed,unroll)
+
+targets += raid6int16.c
+$(obj)/raid6int16.c:  UNROLL := 16
+$(obj)/raid6int16.c:  $(src)/raid6int.uc $(src)/unroll.awk FORCE
+	$(call if_changed,unroll)
+
+targets += raid6int32.c
+$(obj)/raid6int32.c:  UNROLL := 32
+$(obj)/raid6int32.c:  $(src)/raid6int.uc $(src)/unroll.awk FORCE
+	$(call if_changed,unroll)
+
+CFLAGS_raid6altivec1.o += $(altivec_flags)
+targets += raid6altivec1.c
+$(obj)/raid6altivec1.c:   UNROLL := 1
+$(obj)/raid6altivec1.c:   $(src)/raid6altivec.uc $(src)/unroll.awk FORCE
+	$(call if_changed,unroll)
+
+CFLAGS_raid6altivec2.o += $(altivec_flags)
+targets += raid6altivec2.c
+$(obj)/raid6altivec2.c:   UNROLL := 2
+$(obj)/raid6altivec2.c:   $(src)/raid6altivec.uc $(src)/unroll.awk FORCE
+	$(call if_changed,unroll)
+
+CFLAGS_raid6altivec4.o += $(altivec_flags)
+targets += raid6altivec4.c
+$(obj)/raid6altivec4.c:   UNROLL := 4
+$(obj)/raid6altivec4.c:   $(src)/raid6altivec.uc $(src)/unroll.awk FORCE
+	$(call if_changed,unroll)
+
+CFLAGS_raid6altivec8.o += $(altivec_flags)
+targets += raid6altivec8.c
+$(obj)/raid6altivec8.c:   UNROLL := 8
+$(obj)/raid6altivec8.c:   $(src)/raid6altivec.uc $(src)/unroll.awk FORCE
+	$(call if_changed,unroll)
+
+quiet_cmd_mktable = TABLE   $@
+      cmd_mktable = $(obj)/mktables > $@ || ( rm -f $@ && exit 1 )
+
+targets += raid6tables.c
+$(obj)/raid6tables.c: $(obj)/mktables FORCE
+	$(call if_changed,mktable)