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

* 'for-linus' of git://neil.brown.name/md: (75 commits)
  md/raid10: handle further errors during fix_read_error better.
  md/raid10: Handle read errors during recovery better.
  md/raid10: simplify read error handling during recovery.
  md/raid10: record bad blocks due to write errors during resync/recovery.
  md/raid10:  attempt to fix read errors during resync/check
  md/raid10:  Handle write errors by updating badblock log.
  md/raid10: clear bad-block record when write succeeds.
  md/raid10: avoid writing to known bad blocks on known bad drives.
  md/raid10 record bad blocks as needed during recovery.
  md/raid10: avoid reading known bad blocks during resync/recovery.
  md/raid10 - avoid reading from known bad blocks - part 3
  md/raid10: avoid reading from known bad blocks - part 2
  md/raid10: avoid reading from known bad blocks - part 1
  md/raid10: Split handle_read_error out from raid10d.
  md/raid10: simplify/reindent some loops.
  md/raid5: Clear bad blocks on successful write.
  md/raid5.  Don't write to known bad block on doubtful devices.
  md/raid5: write errors should be recorded as bad blocks if possible.
  md/raid5: use bad-block log to improve handling of uncorrectable read errors.
  md/raid5: avoid reading from known bad blocks.
  ...

Documentation/md.txt

@@ -360,18 +360,20 @@ Each directory contains:
         A file recording the current state of the device in the array
 	which can be a comma separated list of
 	      faulty   - device has been kicked from active use due to
-                         a detected fault
+                         a detected fault or it has unacknowledged bad
+                         blocks
 	      in_sync  - device is a fully in-sync member of the array
 	      writemostly - device will only be subject to read
 		         requests if there are no other options.
 			 This applies only to raid1 arrays.
-	      blocked  - device has failed, metadata is "external",
-	                 and the failure hasn't been acknowledged yet.
+	      blocked  - device has failed, and the failure hasn't been
+			 acknowledged yet by the metadata handler.
 			 Writes that would write to this device if
 			 it were not faulty are blocked.
 	      spare    - device is working, but not a full member.
 			 This includes spares that are in the process
 			 of being recovered to
+	      write_error - device has ever seen a write error.
 	This list may grow in future.
 	This can be written to.
 	Writing "faulty"  simulates a failure on the device.
@@ -379,9 +381,11 @@ Each directory contains:
 	Writing "writemostly" sets the writemostly flag.
 	Writing "-writemostly" clears the writemostly flag.
 	Writing "blocked" sets the "blocked" flag.
-	Writing "-blocked" clears the "blocked" flag and allows writes
-		to complete.
+	Writing "-blocked" clears the "blocked" flags and allows writes
+		to complete and possibly simulates an error.
 	Writing "in_sync" sets the in_sync flag.
+	Writing "write_error" sets writeerrorseen flag.
+	Writing "-write_error" clears writeerrorseen flag.
 
 	This file responds to select/poll. Any change to 'faulty'
 	or 'blocked' causes an event.
@@ -419,7 +423,6 @@ Each directory contains:
         written, it will be rejected.
 
       recovery_start
-
         When the device is not 'in_sync', this records the number of
 	sectors from the start of the device which are known to be
 	correct.  This is normally zero, but during a recovery
@@ -435,6 +438,20 @@ Each directory contains:
 	Setting this to 'none' is equivalent to setting 'in_sync'.
 	Setting to any other value also clears the 'in_sync' flag.
 	
+      bad_blocks
+	This gives the list of all known bad blocks in the form of
+	start address and length (in sectors respectively). If output
+	is too big to fit in a page, it will be truncated. Writing
+	"sector length" to this file adds new acknowledged (i.e.
+	recorded to disk safely) bad blocks.
+
+      unacknowledged_bad_blocks
+	This gives the list of known-but-not-yet-saved-to-disk bad
+	blocks in the same form of 'bad_blocks'. If output is too big
+	to fit in a page, it will be truncated. Writing to this file
+	adds bad blocks without acknowledging them. This is largely
+	for testing.
+
 
 
 An active md device will also contain and entry for each active device

drivers/md/bitmap.c

@@ -29,7 +29,6 @@
 #include "md.h"
 #include "bitmap.h"
 
-#include <linux/dm-dirty-log.h>
 /* debug macros */
 
 #define DEBUG 0
@@ -777,8 +776,6 @@ static inline unsigned long file_page_offset(struct bitmap *bitmap, unsigned lon
 static inline struct page *filemap_get_page(struct bitmap *bitmap,
 					    unsigned long chunk)
 {
-	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)
@@ -878,28 +875,19 @@ enum bitmap_page_attr {
 static inline void set_page_attr(struct bitmap *bitmap, struct page *page,
 				enum bitmap_page_attr 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)
 {
-	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)
 {
-	if (page)
 	return test_bit((page->index<<2) + attr, bitmap->filemap_attr);
-	else
-		return test_bit(attr, &bitmap->logattrs);
 }
 
 /*
@@ -912,15 +900,12 @@ static inline unsigned long test_page_attr(struct bitmap *bitmap, struct page *p
 static void bitmap_file_set_bit(struct bitmap *bitmap, sector_t block)
 {
 	unsigned long bit;
-	struct page *page = NULL;
+	struct page *page;
 	void *kaddr;
 	unsigned long chunk = block >> CHUNK_BLOCK_SHIFT(bitmap);
 
-	if (!bitmap->filemap) {
-		struct dm_dirty_log *log = bitmap->mddev->bitmap_info.log;
-		if (log)
-			log->type->mark_region(log, chunk);
-	} else {
+	if (!bitmap->filemap)
+		return;
 
 	page = filemap_get_page(bitmap, chunk);
 	if (!page)
@@ -932,10 +917,9 @@ static void bitmap_file_set_bit(struct bitmap *bitmap, sector_t block)
 	if (bitmap->flags & BITMAP_HOSTENDIAN)
 		set_bit(bit, kaddr);
 	else
-			__test_and_set_bit_le(bit, kaddr);
+		__set_bit_le(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);
 }
@@ -952,16 +936,6 @@ void bitmap_unplug(struct bitmap *bitmap)
 
 	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 */
@@ -990,7 +964,6 @@ void bitmap_unplug(struct bitmap *bitmap)
 		else
 			md_super_wait(bitmap->mddev);
 	}
-out:
 	if (bitmap->flags & BITMAP_WRITE_ERROR)
 		bitmap_file_kick(bitmap);
 }
@@ -1199,7 +1172,6 @@ void bitmap_daemon_work(mddev_t *mddev)
 	struct page *page = NULL, *lastpage = NULL;
 	sector_t blocks;
 	void *paddr;
-	struct dm_dirty_log *log = mddev->bitmap_info.log;
 
 	/* Use a mutex to guard daemon_work against
 	 * bitmap_destroy.
@@ -1224,11 +1196,10 @@ void bitmap_daemon_work(mddev_t *mddev)
 	spin_lock_irqsave(&bitmap->lock, flags);
 	for (j = 0; j < bitmap->chunks; j++) {
 		bitmap_counter_t *bmc;
-		if (!bitmap->filemap) {
-			if (!log)
+		if (!bitmap->filemap)
 			/* error or shutdown */
 			break;
-		} else
+
 		page = filemap_get_page(bitmap, j);
 
 		if (page != lastpage) {
@@ -1298,17 +1269,16 @@ void bitmap_daemon_work(mddev_t *mddev)
 						  -1);
 
 				/* clear the bit */
-				if (page) {
 				paddr = kmap_atomic(page, KM_USER0);
 				if (bitmap->flags & BITMAP_HOSTENDIAN)
 					clear_bit(file_page_offset(bitmap, j),
 						  paddr);
 				else
-						__test_and_clear_bit_le(file_page_offset(bitmap, j),
+					__clear_bit_le(
+							file_page_offset(bitmap,
+									 j),
 							paddr);
 				kunmap_atomic(paddr, KM_USER0);
-				} else
-					log->type->clear_region(log, j);
 			}
 		} else
 			j |= PAGE_COUNTER_MASK;
@@ -1316,16 +1286,12 @@ void bitmap_daemon_work(mddev_t *mddev)
 	spin_unlock_irqrestore(&bitmap->lock, flags);
 
 	/* now sync the final page */
-	if (lastpage != NULL || log != NULL) {
+	if (lastpage != 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);
-			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);
@@ -1767,12 +1733,10 @@ int bitmap_create(mddev_t *mddev)
 	BUILD_BUG_ON(sizeof(bitmap_super_t) != 256);
 
 	if (!file
-	    && !mddev->bitmap_info.offset
-	    && !mddev->bitmap_info.log) /* bitmap disabled, nothing to do */
+	    && !mddev->bitmap_info.offset) /* 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)
@@ -1863,6 +1827,7 @@ int bitmap_create(mddev_t *mddev)
 int bitmap_load(mddev_t *mddev)
 {
 	int err = 0;
+	sector_t start = 0;
 	sector_t sector = 0;
 	struct bitmap *bitmap = mddev->bitmap;
 
@@ -1881,16 +1846,6 @@ int bitmap_load(mddev_t *mddev)
 	}
 	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
@@ -1898,7 +1853,7 @@ int bitmap_load(mddev_t *mddev)
 		start = mddev->recovery_cp;
 
 	err = bitmap_init_from_disk(bitmap, start);
-	}
+
 	if (err)
 		goto out;
 

drivers/md/bitmap.h

@@ -212,10 +212,6 @@ struct bitmap {
 	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;
@@ -237,7 +233,6 @@ struct bitmap {
 	wait_queue_head_t behind_wait;
 
 	struct sysfs_dirent *sysfs_can_clear;
-
 };
 
 /* the bitmap API */

drivers/md/md.h

@@ -29,6 +29,13 @@
 typedef struct mddev_s mddev_t;
 typedef struct mdk_rdev_s mdk_rdev_t;
 
+/* Bad block numbers are stored sorted in a single page.
+ * 64bits is used for each block or extent.
+ * 54 bits are sector number, 9 bits are extent size,
+ * 1 bit is an 'acknowledged' flag.
+ */
+#define MD_MAX_BADBLOCKS	(PAGE_SIZE/8)
+
 /*
  * MD's 'extended' device
  */
@@ -48,7 +55,7 @@ struct mdk_rdev_s
 	struct block_device *meta_bdev;
 	struct block_device *bdev;	/* block device handle */
 
-	struct page	*sb_page;
+	struct page	*sb_page, *bb_page;
 	int		sb_loaded;
 	__u64		sb_events;
 	sector_t	data_offset;	/* start of data in array */
@@ -74,9 +81,29 @@ struct mdk_rdev_s
 #define	In_sync		2		/* device is in_sync with rest of array */
 #define	WriteMostly	4		/* Avoid reading if at all possible */
 #define	AutoDetected	7		/* added by auto-detect */
-#define Blocked		8		/* An error occurred on an externally
-					 * managed array, don't allow writes
+#define Blocked		8		/* An error occurred but has not yet
+					 * been acknowledged by the metadata
+					 * handler, so don't allow writes
 					 * until it is cleared */
+#define WriteErrorSeen	9		/* A write error has been seen on this
+					 * device
+					 */
+#define FaultRecorded	10		/* Intermediate state for clearing
+					 * Blocked.  The Fault is/will-be
+					 * recorded in the metadata, but that
+					 * metadata hasn't been stored safely
+					 * on disk yet.
+					 */
+#define BlockedBadBlocks 11		/* A writer is blocked because they
+					 * found an unacknowledged bad-block.
+					 * This can safely be cleared at any
+					 * time, and the writer will re-check.
+					 * It may be set at any time, and at
+					 * worst the writer will timeout and
+					 * re-check.  So setting it as
+					 * accurately as possible is good, but
+					 * not absolutely critical.
+					 */
 	wait_queue_head_t blocked_wait;
 
 	int desc_nr;			/* descriptor index in the superblock */
@@ -111,8 +138,54 @@ struct mdk_rdev_s
 
 	struct sysfs_dirent *sysfs_state; /* handle for 'state'
 					   * sysfs entry */
+
+	struct badblocks {
+		int	count;		/* count of bad blocks */
+		int	unacked_exist;	/* there probably are unacknowledged
+					 * bad blocks.  This is only cleared
+					 * when a read discovers none
+					 */
+		int	shift;		/* shift from sectors to block size
+					 * a -ve shift means badblocks are
+					 * disabled.*/
+		u64	*page;		/* badblock list */
+		int	changed;
+		seqlock_t lock;
+
+		sector_t sector;
+		sector_t size;		/* in sectors */
+	} badblocks;
 };
 
+#define BB_LEN_MASK	(0x00000000000001FFULL)
+#define BB_OFFSET_MASK	(0x7FFFFFFFFFFFFE00ULL)
+#define BB_ACK_MASK	(0x8000000000000000ULL)
+#define BB_MAX_LEN	512
+#define BB_OFFSET(x)	(((x) & BB_OFFSET_MASK) >> 9)
+#define BB_LEN(x)	(((x) & BB_LEN_MASK) + 1)
+#define BB_ACK(x)	(!!((x) & BB_ACK_MASK))
+#define BB_MAKE(a, l, ack) (((a)<<9) | ((l)-1) | ((u64)(!!(ack)) << 63))
+
+extern int md_is_badblock(struct badblocks *bb, sector_t s, int sectors,
+			  sector_t *first_bad, int *bad_sectors);
+static inline int is_badblock(mdk_rdev_t *rdev, sector_t s, int sectors,
+			      sector_t *first_bad, int *bad_sectors)
+{
+	if (unlikely(rdev->badblocks.count)) {
+		int rv = md_is_badblock(&rdev->badblocks, rdev->data_offset + s,
+					sectors,
+					first_bad, bad_sectors);
+		if (rv)
+			*first_bad -= rdev->data_offset;
+		return rv;
+	}
+	return 0;
+}
+extern int rdev_set_badblocks(mdk_rdev_t *rdev, sector_t s, int sectors,
+			      int acknowledged);
+extern int rdev_clear_badblocks(mdk_rdev_t *rdev, sector_t s, int sectors);
+extern void md_ack_all_badblocks(struct badblocks *bb);
+
 struct mddev_s
 {
 	void				*private;
@@ -239,9 +312,12 @@ struct mddev_s
 #define	MD_RECOVERY_FROZEN	9
 
 	unsigned long			recovery;
-	int				recovery_disabled; /* if we detect that recovery
-							    * will always fail, set this
-							    * so we don't loop trying */
+	/* If a RAID personality determines that recovery (of a particular
+	 * device) will fail due to a read error on the source device, it
+	 * takes a copy of this number and does not attempt recovery again
+	 * until this number changes.
+	 */
+	int				recovery_disabled;
 
 	int				in_sync;	/* know to not need resync */
 	/* 'open_mutex' avoids races between 'md_open' and 'do_md_stop', so
@@ -304,11 +380,6 @@ struct mddev_s
 							 * 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 jiffies between updates? */
@@ -413,6 +484,20 @@ static inline char * mdname (mddev_t * mddev)
 	return mddev->gendisk ? mddev->gendisk->disk_name : "mdX";
 }
 
+static inline int sysfs_link_rdev(mddev_t *mddev, mdk_rdev_t *rdev)
+{
+	char nm[20];
+	sprintf(nm, "rd%d", rdev->raid_disk);
+	return sysfs_create_link(&mddev->kobj, &rdev->kobj, nm);
+}
+
+static inline void sysfs_unlink_rdev(mddev_t *mddev, mdk_rdev_t *rdev)
+{
+	char nm[20];
+	sprintf(nm, "rd%d", rdev->raid_disk);
+	sysfs_remove_link(&mddev->kobj, nm);
+}
+
 /*
  * iterates through some rdev ringlist. It's safe to remove the
  * current 'rdev'. Dont touch 'tmp' though.
@@ -505,7 +590,7 @@ 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 int md_rdev_init(mdk_rdev_t *rdev);
 
 extern void mddev_suspend(mddev_t *mddev);
 extern void mddev_resume(mddev_t *mddev);
@@ -514,4 +599,5 @@ extern struct bio *bio_clone_mddev(struct bio *bio, gfp_t gfp_mask,
 extern struct bio *bio_alloc_mddev(gfp_t gfp_mask, int nr_iovecs,
 				   mddev_t *mddev);
 extern int mddev_check_plugged(mddev_t *mddev);
+extern void md_trim_bio(struct bio *bio, int offset, int size);
 #endif /* _MD_MD_H */

drivers/md/raid1.h

@@ -48,6 +48,12 @@ struct r1_private_data_s {
 					    * (fresh device added).
 					    * Cleared when a sync completes.
 					    */
+	int			recovery_disabled; /* when the same as
+						    * mddev->recovery_disabled
+						    * we don't allow recovery
+						    * to be attempted as we
+						    * expect a read error
+						    */
 
 	wait_queue_head_t	wait_barrier;
 
@@ -95,7 +101,7 @@ struct r1bio_s {
 
 	struct list_head	retry_list;
 	/* Next two are only valid when R1BIO_BehindIO is set */
-	struct page		**behind_pages;
+	struct bio_vec		*behind_bvecs;
 	int			behind_page_count;
 	/*
 	 * if the IO is in WRITE direction, then multiple bios are used.
@@ -110,13 +116,24 @@ struct r1bio_s {
  * correct the read error.  To keep track of bad blocks on a per-bio
  * level, we store IO_BLOCKED in the appropriate 'bios' pointer
  */
-#define IO_BLOCKED ((struct bio*)1)
+#define IO_BLOCKED ((struct bio *)1)
+/* When we successfully write to a known bad-block, we need to remove the
+ * bad-block marking which must be done from process context.  So we record
+ * the success by setting bios[n] to IO_MADE_GOOD
+ */
+#define IO_MADE_GOOD ((struct bio *)2)
+
+#define BIO_SPECIAL(bio) ((unsigned long)bio <= 2)
 
 /* bits for r1bio.state */
 #define	R1BIO_Uptodate	0
 #define	R1BIO_IsSync	1
 #define	R1BIO_Degraded	2
 #define	R1BIO_BehindIO	3
+/* Set ReadError on bios that experience a readerror so that
+ * raid1d knows what to do with them.
+ */
+#define R1BIO_ReadError 4
 /* For write-behind requests, we call bi_end_io when
  * the last non-write-behind device completes, providing
  * any write was successful.  Otherwise we call when
@@ -125,6 +142,11 @@ struct r1bio_s {
  * Record that bi_end_io was called with this flag...
  */
 #define	R1BIO_Returned 6
+/* If a write for this request means we can clear some
+ * known-bad-block records, we set this flag
+ */
+#define	R1BIO_MadeGood 7
+#define	R1BIO_WriteError 8
 
 extern int md_raid1_congested(mddev_t *mddev, int bits);
 

drivers/md/raid10.h

@@ -6,6 +6,11 @@ typedef struct mirror_info mirror_info_t;
 struct mirror_info {
 	mdk_rdev_t	*rdev;
 	sector_t	head_position;
+	int		recovery_disabled;	/* matches
+						 * mddev->recovery_disabled
+						 * when we shouldn't try
+						 * recovering this device.
+						 */
 };
 
 typedef struct r10bio_s r10bio_t;
@@ -113,10 +118,26 @@ struct r10bio_s {
  * level, we store IO_BLOCKED in the appropriate 'bios' pointer
  */
 #define IO_BLOCKED ((struct bio*)1)
+/* When we successfully write to a known bad-block, we need to remove the
+ * bad-block marking which must be done from process context.  So we record
+ * the success by setting devs[n].bio to IO_MADE_GOOD
+ */
+#define IO_MADE_GOOD ((struct bio *)2)
+
+#define BIO_SPECIAL(bio) ((unsigned long)bio <= 2)
 
 /* bits for r10bio.state */
 #define	R10BIO_Uptodate	0
 #define	R10BIO_IsSync	1
 #define	R10BIO_IsRecover 2
 #define	R10BIO_Degraded 3
+/* Set ReadError on bios that experience a read error
+ * so that raid10d knows what to do with them.
+ */
+#define	R10BIO_ReadError 4
+/* If a write for this request means we can clear some
+ * known-bad-block records, we set this flag.
+ */
+#define	R10BIO_MadeGood 5
+#define	R10BIO_WriteError 6
 #endif

drivers/md/raid5.h

@@ -6,11 +6,11 @@
 
 /*
  *
- * Each stripe contains one buffer per disc.  Each buffer can be in
+ * Each stripe contains one buffer per device.  Each buffer can be in
  * one of a number of states stored in "flags".  Changes between
- * these states happen *almost* exclusively under a per-stripe
- * spinlock.  Some very specific changes can happen in bi_end_io, and
- * these are not protected by the spin lock.
+ * these states happen *almost* exclusively under the protection of the
+ * STRIPE_ACTIVE flag.  Some very specific changes can happen in bi_end_io, and
+ * these are not protected by STRIPE_ACTIVE.
  *
  * The flag bits that are used to represent these states are:
  *   R5_UPTODATE and R5_LOCKED
@@ -76,12 +76,10 @@
  * block and the cached buffer are successfully written, any buffer on
  * a written list can be returned with b_end_io.
  *
- * The write list and read list both act as fifos.  The read list is
- * protected by the device_lock.  The write and written lists are
- * protected by the stripe lock.  The device_lock, which can be
- * claimed while the stipe lock is held, is only for list
- * manipulations and will only be held for a very short time.  It can
- * be claimed from interrupts.
+ * The write list and read list both act as fifos.  The read list,
+ * write list and written list are protected by the device_lock.
+ * The device_lock is only for list manipulations and will only be
+ * held for a very short time.  It can be claimed from interrupts.
  *
  *
  * Stripes in the stripe cache can be on one of two lists (or on
@@ -96,7 +94,6 @@
  *
  * The inactive_list, handle_list and hash bucket lists are all protected by the
  * device_lock.
- *  - stripes on the inactive_list never have their stripe_lock held.
  *  - stripes have a reference counter. If count==0, they are on a list.
  *  - If a stripe might need handling, STRIPE_HANDLE is set.
  *  - When refcount reaches zero, then if STRIPE_HANDLE it is put on
@@ -116,10 +113,10 @@
  *  attach a request to an active stripe (add_stripe_bh())
  *     lockdev attach-buffer unlockdev
  *  handle a stripe (handle_stripe())
- *     lockstripe clrSTRIPE_HANDLE ...
+ *     setSTRIPE_ACTIVE,  clrSTRIPE_HANDLE ...
  *		(lockdev check-buffers unlockdev) ..
  *		change-state ..
- *		record io/ops needed unlockstripe schedule io/ops
+ *		record io/ops needed clearSTRIPE_ACTIVE schedule io/ops
  *  release an active stripe (release_stripe())
  *     lockdev if (!--cnt) { if  STRIPE_HANDLE, add to handle_list else add to inactive-list } unlockdev
  *
@@ -128,8 +125,7 @@
  * on a cached buffer, and plus one if the stripe is undergoing stripe
  * operations.
  *
- * Stripe operations are performed outside the stripe lock,
- * the stripe operations are:
+ * The stripe operations are:
  * -copying data between the stripe cache and user application buffers
  * -computing blocks to save a disk access, or to recover a missing block
  * -updating the parity on a write operation (reconstruct write and
@@ -159,7 +155,8 @@
  */
 
 /*
- * Operations state - intermediate states that are visible outside of sh->lock
+ * Operations state - intermediate states that are visible outside of 
+ *   STRIPE_ACTIVE.
  * In general _idle indicates nothing is running, _run indicates a data
  * processing operation is active, and _result means the data processing result
  * is stable and can be acted upon.  For simple operations like biofill and
@@ -209,7 +206,6 @@ struct stripe_head {
 	short			ddf_layout;/* use DDF ordering to calculate Q */
 	unsigned long		state;		/* state flags */
 	atomic_t		count;	      /* nr of active thread/requests */
-	spinlock_t		lock;
 	int			bm_seq;	/* sequence number for bitmap flushes */
 	int			disks;		/* disks in stripe */
 	enum check_states	check_state;
@@ -240,19 +236,20 @@ struct stripe_head {
 };
 
 /* stripe_head_state - collects and tracks the dynamic state of a stripe_head
- *     for handle_stripe.  It is only valid under spin_lock(sh->lock);
+ *     for handle_stripe.
  */
 struct stripe_head_state {
 	int syncing, expanding, expanded;
 	int locked, uptodate, to_read, to_write, failed, written;
 	int to_fill, compute, req_compute, non_overwrite;
-	int failed_num;
+	int failed_num[2];
+	int p_failed, q_failed;
+	int dec_preread_active;
 	unsigned long ops_request;
-};
 
-/* r6_state - extra state data only relevant to r6 */
-struct r6_state {
-	int p_failed, q_failed, failed_num[2];
+	struct bio *return_bi;
+	mdk_rdev_t *blocked_rdev;
+	int handle_bad_blocks;
 };
 
 /* Flags */
@@ -276,6 +273,8 @@ struct r6_state {
 				 */
 #define	R5_Wantdrain	13	/* dev->towrite needs to be drained */
 #define	R5_WantFUA	14	/* Write should be FUA */
+#define	R5_WriteError	15	/* got a write error - need to record it */
+#define	R5_MadeGood	16	/* A bad block has been fixed by writing to it*/
 /*
  * Write method
  */
@@ -289,21 +288,25 @@ struct r6_state {
 /*
  * Stripe state
  */
-#define STRIPE_HANDLE		2
-#define	STRIPE_SYNCING		3
-#define	STRIPE_INSYNC		4
-#define	STRIPE_PREREAD_ACTIVE	5
-#define	STRIPE_DELAYED		6
-#define	STRIPE_DEGRADED		7
-#define	STRIPE_BIT_DELAY	8
-#define	STRIPE_EXPANDING	9
-#define	STRIPE_EXPAND_SOURCE	10
-#define	STRIPE_EXPAND_READY	11
-#define	STRIPE_IO_STARTED	12 /* do not count towards 'bypass_count' */
-#define	STRIPE_FULL_WRITE	13 /* all blocks are set to be overwritten */
-#define	STRIPE_BIOFILL_RUN	14
-#define	STRIPE_COMPUTE_RUN	15
-#define	STRIPE_OPS_REQ_PENDING	16
+enum {
+	STRIPE_ACTIVE,
+	STRIPE_HANDLE,
+	STRIPE_SYNC_REQUESTED,
+	STRIPE_SYNCING,
+	STRIPE_INSYNC,
+	STRIPE_PREREAD_ACTIVE,
+	STRIPE_DELAYED,
+	STRIPE_DEGRADED,
+	STRIPE_BIT_DELAY,
+	STRIPE_EXPANDING,
+	STRIPE_EXPAND_SOURCE,
+	STRIPE_EXPAND_READY,
+	STRIPE_IO_STARTED,	/* do not count towards 'bypass_count' */
+	STRIPE_FULL_WRITE,	/* all blocks are set to be overwritten */
+	STRIPE_BIOFILL_RUN,
+	STRIPE_COMPUTE_RUN,
+	STRIPE_OPS_REQ_PENDING,
+};
 
 /*
  * Operation request flags
@@ -336,7 +339,7 @@ struct r6_state {
  * PREREAD_ACTIVE.
  * In stripe_handle, if we find pre-reading is necessary, we do it if
  * PREREAD_ACTIVE is set, else we set DELAYED which will send it to the delayed queue.
- * HANDLE gets cleared if stripe_handle leave nothing locked.
+ * HANDLE gets cleared if stripe_handle leaves nothing locked.
  */
 
 
@@ -399,7 +402,7 @@ struct raid5_private_data {
 					    * (fresh device added).
 					    * Cleared when a sync completes.
 					    */
-
+	int			recovery_disabled;
 	/* per cpu variables */
 	struct raid5_percpu {
 		struct page	*spare_page; /* Used when checking P/Q in raid6 */

include/linux/raid/md_p.h

@@ -245,10 +245,16 @@ struct mdp_superblock_1 {
 	__u8	device_uuid[16]; /* user-space setable, ignored by kernel */
 	__u8	devflags;	/* per-device flags.  Only one defined...*/
 #define	WriteMostly1	1	/* mask for writemostly flag in above */
-	__u8	pad2[64-57];	/* set to 0 when writing */
+	/* Bad block log.  If there are any bad blocks the feature flag is set.
+	 * If offset and size are non-zero, that space is reserved and available
+	 */
+	__u8	bblog_shift;	/* shift from sectors to block size */
+	__le16	bblog_size;	/* number of sectors reserved for list */
+	__le32	bblog_offset;	/* sector offset from superblock to bblog,
+				 * signed - not unsigned */
 
 	/* array state information - 64 bytes */
-	__le64	utime;		/* 40 bits second, 24 btes microseconds */
+	__le64	utime;		/* 40 bits second, 24 bits microseconds */
 	__le64	events;		/* incremented when superblock updated */
 	__le64	resync_offset;	/* data before this offset (from data_offset) known to be in sync */
 	__le32	sb_csum;	/* checksum up to devs[max_dev] */
@@ -270,8 +276,8 @@ struct mdp_superblock_1 {
 					   * must be honoured
 					   */
 #define	MD_FEATURE_RESHAPE_ACTIVE	4
+#define	MD_FEATURE_BAD_BLOCKS		8 /* badblock list is not empty */
 
-#define	MD_FEATURE_ALL			(1|2|4)
+#define	MD_FEATURE_ALL			(1|2|4|8)
 
 #endif 
-