Merge tag 'for-6.12/block-20240913' of git://git.kernel.dk/linux

Pull block updates from Jens Axboe:

 - MD changes via Song:
      - md-bitmap refactoring (Yu Kuai)
      - raid5 performance optimization (Artur Paszkiewicz)
      - Other small fixes (Yu Kuai, Chen Ni)
      - Add a sysfs entry 'new_level' (Xiao Ni)
      - Improve information reported in /proc/mdstat (Mateusz Kusiak)

 - NVMe changes via Keith:
      - Asynchronous namespace scanning (Stuart)
      - TCP TLS updates (Hannes)
      - RDMA queue controller validation (Niklas)
      - Align field names to the spec (Anuj)
      - Metadata support validation (Puranjay)
      - A syntax cleanup (Shen)
      - Fix a Kconfig linking error (Arnd)
      - New queue-depth quirk (Keith)

 - Add missing unplug trace event (Keith)

 - blk-iocost fixes (Colin, Konstantin)

 - t10-pi modular removal and fixes (Alexey)

 - Fix for potential BLKSECDISCARD overflow (Alexey)

 - bio splitting cleanups and fixes (Christoph)

 - Deal with folios rather than rather than pages, speeding up how the
   block layer handles bigger IOs (Kundan)

 - Use spinlocks rather than bit spinlocks in zram (Sebastian, Mike)

 - Reduce zoned device overhead in ublk (Ming)

 - Add and use sendpages_ok() for drbd and nvme-tcp (Ofir)

 - Fix regression in partition error pointer checking (Riyan)

 - Add support for write zeroes and rotational status in nbd (Wouter)

 - Add Yu Kuai as new BFQ maintainer. The scheduler has been
   unmaintained for quite a while.

 - Various sets of fixes for BFQ (Yu Kuai)

 - Misc fixes and cleanups (Alvaro, Christophe, Li, Md Haris, Mikhail,
   Yang)

* tag 'for-6.12/block-20240913' of git://git.kernel.dk/linux: (120 commits)
  nvme-pci: qdepth 1 quirk
  block: fix potential invalid pointer dereference in blk_add_partition
  blk_iocost: make read-only static array vrate_adj_pct const
  block: unpin user pages belonging to a folio at once
  mm: release number of pages of a folio
  block: introduce folio awareness and add a bigger size from folio
  block: Added folio-ized version of bio_add_hw_page()
  block, bfq: factor out a helper to split bfqq in bfq_init_rq()
  block, bfq: remove local variable 'bfqq_already_existing' in bfq_init_rq()
  block, bfq: remove local variable 'split' in bfq_init_rq()
  block, bfq: remove bfq_log_bfqg()
  block, bfq: merge bfq_release_process_ref() into bfq_put_cooperator()
  block, bfq: fix procress reference leakage for bfqq in merge chain
  block, bfq: fix uaf for accessing waker_bfqq after splitting
  blk-throttle: support prioritized processing of metadata
  blk-throttle: remove last_low_overflow_time
  drbd: Add NULL check for net_conf to prevent dereference in state validation
  nvme-tcp: fix link failure for TCP auth
  blk-mq: add missing unplug trace event
  mtip32xx: Remove redundant null pointer checks in mtip_hw_debugfs_init()
  ...

1 files changed, 432 insertions, 136 deletions

diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c
index db5330d97348..29da10e6f703 100644
--- a/drivers/md/md-bitmap.c
+++ b/drivers/md/md-bitmap.c
@@ -32,11 +32,210 @@
 #include "md.h"
 #include "md-bitmap.h"
 
+#define BITMAP_MAJOR_LO 3
+/* version 4 insists the bitmap is in little-endian order
+ * with version 3, it is host-endian which is non-portable
+ * Version 5 is currently set only for clustered devices
+ */
+#define BITMAP_MAJOR_HI 4
+#define BITMAP_MAJOR_CLUSTERED 5
+#define	BITMAP_MAJOR_HOSTENDIAN 3
+
+/*
+ * in-memory bitmap:
+ *
+ * Use 16 bit block counters to track pending writes to each "chunk".
+ * The 2 high order bits are special-purpose, the first is a flag indicating
+ * whether a resync is needed.  The second is a flag indicating whether a
+ * resync is active.
+ * This means that the counter is actually 14 bits:
+ *
+ * +--------+--------+------------------------------------------------+
+ * | resync | resync |               counter                          |
+ * | needed | active |                                                |
+ * |  (0-1) |  (0-1) |              (0-16383)                         |
+ * +--------+--------+------------------------------------------------+
+ *
+ * The "resync needed" bit is set when:
+ *    a '1' bit is read from storage at startup.
+ *    a write request fails on some drives
+ *    a resync is aborted on a chunk with 'resync active' set
+ * It is cleared (and resync-active set) when a resync starts across all drives
+ * of the chunk.
+ *
+ *
+ * The "resync active" bit is set when:
+ *    a resync is started on all drives, and resync_needed is set.
+ *       resync_needed will be cleared (as long as resync_active wasn't already set).
+ * It is cleared when a resync completes.
+ *
+ * The counter counts pending write requests, plus the on-disk bit.
+ * When the counter is '1' and the resync bits are clear, the on-disk
+ * bit can be cleared as well, thus setting the counter to 0.
+ * When we set a bit, or in the counter (to start a write), if the fields is
+ * 0, we first set the disk bit and set the counter to 1.
+ *
+ * If the counter is 0, the on-disk bit is clear and the stripe is clean
+ * Anything that dirties the stripe pushes the counter to 2 (at least)
+ * and sets the on-disk bit (lazily).
+ * If a periodic sweep find the counter at 2, it is decremented to 1.
+ * If the sweep find the counter at 1, the on-disk bit is cleared and the
+ * counter goes to zero.
+ *
+ * Also, we'll hijack the "map" pointer itself and use it as two 16 bit block
+ * counters as a fallback when "page" memory cannot be allocated:
+ *
+ * Normal case (page memory allocated):
+ *
+ *     page pointer (32-bit)
+ *
+ *     [ ] ------+
+ *               |
+ *               +-------> [   ][   ]..[   ] (4096 byte page == 2048 counters)
+ *                          c1   c2    c2048
+ *
+ * Hijacked case (page memory allocation failed):
+ *
+ *     hijacked page pointer (32-bit)
+ *
+ *     [		  ][		  ] (no page memory allocated)
+ *      counter #1 (16-bit) counter #2 (16-bit)
+ *
+ */
+
+#define PAGE_BITS (PAGE_SIZE << 3)
+#define PAGE_BIT_SHIFT (PAGE_SHIFT + 3)
+
+#define NEEDED(x) (((bitmap_counter_t) x) & NEEDED_MASK)
+#define RESYNC(x) (((bitmap_counter_t) x) & RESYNC_MASK)
+#define COUNTER(x) (((bitmap_counter_t) x) & COUNTER_MAX)
+
+/* how many counters per page? */
+#define PAGE_COUNTER_RATIO (PAGE_BITS / COUNTER_BITS)
+/* same, except a shift value for more efficient bitops */
+#define PAGE_COUNTER_SHIFT (PAGE_BIT_SHIFT - COUNTER_BIT_SHIFT)
+/* same, except a mask value for more efficient bitops */
+#define PAGE_COUNTER_MASK  (PAGE_COUNTER_RATIO - 1)
+
+#define BITMAP_BLOCK_SHIFT 9
+
+/*
+ * bitmap structures:
+ */
+
+/* the in-memory bitmap is represented by bitmap_pages */
+struct bitmap_page {
+	/*
+	 * map points to the actual memory page
+	 */
+	char *map;
+	/*
+	 * in emergencies (when map cannot be alloced), hijack the map
+	 * pointer and use it as two counters itself
+	 */
+	unsigned int hijacked:1;
+	/*
+	 * If any counter in this page is '1' or '2' - and so could be
+	 * cleared then that page is marked as 'pending'
+	 */
+	unsigned int pending:1;
+	/*
+	 * count of dirty bits on the page
+	 */
+	unsigned int  count:30;
+};
+
+/* the main bitmap structure - one per mddev */
+struct bitmap {
+
+	struct bitmap_counts {
+		spinlock_t lock;
+		struct bitmap_page *bp;
+		/* total number of pages in the bitmap */
+		unsigned long pages;
+		/* number of pages not yet allocated */
+		unsigned long missing_pages;
+		/* chunksize = 2^chunkshift (for bitops) */
+		unsigned long chunkshift;
+		/* total number of data chunks for the array */
+		unsigned long chunks;
+	} counts;
+
+	struct mddev *mddev; /* the md device that the bitmap is for */
+
+	__u64	events_cleared;
+	int need_sync;
+
+	struct bitmap_storage {
+		/* backing disk file */
+		struct file *file;
+		/* cached copy of the bitmap file superblock */
+		struct page *sb_page;
+		unsigned long sb_index;
+		/* list of cache pages for the file */
+		struct page **filemap;
+		/* attributes associated filemap pages */
+		unsigned long *filemap_attr;
+		/* number of pages in the file */
+		unsigned long file_pages;
+		/* total bytes in the bitmap */
+		unsigned long bytes;
+	} storage;
+
+	unsigned long flags;
+
+	int allclean;
+
+	atomic_t behind_writes;
+	/* highest actual value at runtime */
+	unsigned long behind_writes_used;
+
+	/*
+	 * the bitmap daemon - periodically wakes up and sweeps the bitmap
+	 * file, cleaning up bits and flushing out pages to disk as necessary
+	 */
+	unsigned long daemon_lastrun; /* jiffies of last run */
+	/*
+	 * when we lasted called end_sync to update bitmap with resync
+	 * progress.
+	 */
+	unsigned long last_end_sync;
+
+	/* pending writes to the bitmap file */
+	atomic_t pending_writes;
+	wait_queue_head_t write_wait;
+	wait_queue_head_t overflow_wait;
+	wait_queue_head_t behind_wait;
+
+	struct kernfs_node *sysfs_can_clear;
+	/* slot offset for clustered env */
+	int cluster_slot;
+};
+
+static int __bitmap_resize(struct bitmap *bitmap, sector_t blocks,
+			   int chunksize, bool init);
+
 static inline char *bmname(struct bitmap *bitmap)
 {
 	return bitmap->mddev ? mdname(bitmap->mddev) : "mdX";
 }
 
+static bool __bitmap_enabled(struct bitmap *bitmap)
+{
+	return bitmap->storage.filemap &&
+	       !test_bit(BITMAP_STALE, &bitmap->flags);
+}
+
+static bool bitmap_enabled(struct mddev *mddev)
+{
+	struct bitmap *bitmap = mddev->bitmap;
+
+	if (!bitmap)
+		return false;
+
+	return __bitmap_enabled(bitmap);
+}
+
 /*
  * check a page and, if necessary, allocate it (or hijack it if the alloc fails)
  *
@@ -472,9 +671,10 @@ static void md_bitmap_wait_writes(struct bitmap *bitmap)
 
 
 /* update the event counter and sync the superblock to disk */
-void md_bitmap_update_sb(struct bitmap *bitmap)
+static void bitmap_update_sb(void *data)
 {
 	bitmap_super_t *sb;
+	struct bitmap *bitmap = data;
 
 	if (!bitmap || !bitmap->mddev) /* no bitmap for this array */
 		return;
@@ -510,10 +710,8 @@ void md_bitmap_update_sb(struct bitmap *bitmap)
 		write_sb_page(bitmap, bitmap->storage.sb_index,
 			      bitmap->storage.sb_page, 1);
 }
-EXPORT_SYMBOL(md_bitmap_update_sb);
 
-/* print out the bitmap file superblock */
-void md_bitmap_print_sb(struct bitmap *bitmap)
+static void bitmap_print_sb(struct bitmap *bitmap)
 {
 	bitmap_super_t *sb;
 
@@ -760,7 +958,7 @@ out_no_sb:
 			bitmap->mddev->bitmap_info.space > sectors_reserved)
 			bitmap->mddev->bitmap_info.space = sectors_reserved;
 	} else {
-		md_bitmap_print_sb(bitmap);
+		bitmap_print_sb(bitmap);
 		if (bitmap->cluster_slot < 0)
 			md_cluster_stop(bitmap->mddev);
 	}
@@ -893,7 +1091,7 @@ static void md_bitmap_file_unmap(struct bitmap_storage *store)
 static void md_bitmap_file_kick(struct bitmap *bitmap)
 {
 	if (!test_and_set_bit(BITMAP_STALE, &bitmap->flags)) {
-		md_bitmap_update_sb(bitmap);
+		bitmap_update_sb(bitmap);
 
 		if (bitmap->storage.file) {
 			pr_warn("%s: kicking failed bitmap file %pD4 from array!\n",
@@ -1028,13 +1226,13 @@ static int md_bitmap_file_test_bit(struct bitmap *bitmap, sector_t block)
 /* this gets called when the md device is ready to unplug its underlying
  * (slave) device queues -- before we let any writes go down, we need to
  * sync the dirty pages of the bitmap file to disk */
-void md_bitmap_unplug(struct bitmap *bitmap)
+static void __bitmap_unplug(struct bitmap *bitmap)
 {
 	unsigned long i;
 	int dirty, need_write;
 	int writing = 0;
 
-	if (!md_bitmap_enabled(bitmap))
+	if (!__bitmap_enabled(bitmap))
 		return;
 
 	/* look at each page to see if there are any set bits that need to be
@@ -1060,7 +1258,6 @@ void md_bitmap_unplug(struct bitmap *bitmap)
 	if (test_bit(BITMAP_WRITE_ERROR, &bitmap->flags))
 		md_bitmap_file_kick(bitmap);
 }
-EXPORT_SYMBOL(md_bitmap_unplug);
 
 struct bitmap_unplug_work {
 	struct work_struct work;
@@ -1073,11 +1270,11 @@ static void md_bitmap_unplug_fn(struct work_struct *work)
 	struct bitmap_unplug_work *unplug_work =
 		container_of(work, struct bitmap_unplug_work, work);
 
-	md_bitmap_unplug(unplug_work->bitmap);
+	__bitmap_unplug(unplug_work->bitmap);
 	complete(unplug_work->done);
 }
 
-void md_bitmap_unplug_async(struct bitmap *bitmap)
+static void bitmap_unplug_async(struct bitmap *bitmap)
 {
 	DECLARE_COMPLETION_ONSTACK(done);
 	struct bitmap_unplug_work unplug_work;
@@ -1089,7 +1286,19 @@ void md_bitmap_unplug_async(struct bitmap *bitmap)
 	queue_work(md_bitmap_wq, &unplug_work.work);
 	wait_for_completion(&done);
 }
-EXPORT_SYMBOL(md_bitmap_unplug_async);
+
+static void bitmap_unplug(struct mddev *mddev, bool sync)
+{
+	struct bitmap *bitmap = mddev->bitmap;
+
+	if (!bitmap)
+		return;
+
+	if (sync)
+		__bitmap_unplug(bitmap);
+	else
+		bitmap_unplug_async(bitmap);
+}
 
 static void md_bitmap_set_memory_bits(struct bitmap *bitmap, sector_t offset, int needed);
 
@@ -1226,22 +1435,21 @@ static int md_bitmap_init_from_disk(struct bitmap *bitmap, sector_t start)
 	return ret;
 }
 
-void md_bitmap_write_all(struct bitmap *bitmap)
+/* just flag bitmap pages as needing to be written. */
+static void bitmap_write_all(struct mddev *mddev)
 {
-	/* We don't actually write all bitmap blocks here,
-	 * just flag them as needing to be written
-	 */
 	int i;
+	struct bitmap *bitmap = mddev->bitmap;
 
 	if (!bitmap || !bitmap->storage.filemap)
 		return;
+
+	/* Only one copy, so nothing needed */
 	if (bitmap->storage.file)
-		/* Only one copy, so nothing needed */
 		return;
 
 	for (i = 0; i < bitmap->storage.file_pages; i++)
-		set_page_attr(bitmap, i,
-			      BITMAP_PAGE_NEEDWRITE);
+		set_page_attr(bitmap, i, BITMAP_PAGE_NEEDWRITE);
 	bitmap->allclean = 0;
 }
 
@@ -1290,7 +1498,7 @@ out:
  * bitmap daemon -- periodically wakes up to clean bits and flush pages
  *			out to disk
  */
-void md_bitmap_daemon_work(struct mddev *mddev)
+static void bitmap_daemon_work(struct mddev *mddev)
 {
 	struct bitmap *bitmap;
 	unsigned long j;
@@ -1461,8 +1669,11 @@ __acquires(bitmap->lock)
 			&(bitmap->bp[page].map[pageoff]);
 }
 
-int md_bitmap_startwrite(struct bitmap *bitmap, sector_t offset, unsigned long sectors, int behind)
+static int bitmap_startwrite(struct mddev *mddev, sector_t offset,
+			     unsigned long sectors, bool behind)
 {
+	struct bitmap *bitmap = mddev->bitmap;
+
 	if (!bitmap)
 		return 0;
 
@@ -1523,13 +1734,15 @@ int md_bitmap_startwrite(struct bitmap *bitmap, sector_t offset, unsigned long s
 	}
 	return 0;
 }
-EXPORT_SYMBOL(md_bitmap_startwrite);
 
-void md_bitmap_endwrite(struct bitmap *bitmap, sector_t offset,
-			unsigned long sectors, int success, int behind)
+static void bitmap_endwrite(struct mddev *mddev, sector_t offset,
+			    unsigned long sectors, bool success, bool behind)
 {
+	struct bitmap *bitmap = mddev->bitmap;
+
 	if (!bitmap)
 		return;
+
 	if (behind) {
 		if (atomic_dec_and_test(&bitmap->behind_writes))
 			wake_up(&bitmap->behind_wait);
@@ -1576,26 +1789,27 @@ void md_bitmap_endwrite(struct bitmap *bitmap, sector_t offset,
 			sectors = 0;
 	}
 }
-EXPORT_SYMBOL(md_bitmap_endwrite);
 
-static int __bitmap_start_sync(struct bitmap *bitmap, sector_t offset, sector_t *blocks,
-			       int degraded)
+static bool __bitmap_start_sync(struct bitmap *bitmap, sector_t offset,
+				sector_t *blocks, bool degraded)
 {
 	bitmap_counter_t *bmc;
-	int rv;
+	bool rv;
+
 	if (bitmap == NULL) {/* FIXME or bitmap set as 'failed' */
 		*blocks = 1024;
-		return 1; /* always resync if no bitmap */
+		return true; /* always resync if no bitmap */
 	}
 	spin_lock_irq(&bitmap->counts.lock);
+
+	rv = false;
 	bmc = md_bitmap_get_counter(&bitmap->counts, offset, blocks, 0);
-	rv = 0;
 	if (bmc) {
 		/* locked */
-		if (RESYNC(*bmc))
-			rv = 1;
-		else if (NEEDED(*bmc)) {
-			rv = 1;
+		if (RESYNC(*bmc)) {
+			rv = true;
+		} else if (NEEDED(*bmc)) {
+			rv = true;
 			if (!degraded) { /* don't set/clear bits if degraded */
 				*bmc |= RESYNC_MASK;
 				*bmc &= ~NEEDED_MASK;
@@ -1603,11 +1817,12 @@ static int __bitmap_start_sync(struct bitmap *bitmap, sector_t offset, sector_t
 		}
 	}
 	spin_unlock_irq(&bitmap->counts.lock);
+
 	return rv;
 }
 
-int md_bitmap_start_sync(struct bitmap *bitmap, sector_t offset, sector_t *blocks,
-			 int degraded)
+static bool bitmap_start_sync(struct mddev *mddev, sector_t offset,
+			      sector_t *blocks, bool degraded)
 {
 	/* bitmap_start_sync must always report on multiples of whole
 	 * pages, otherwise resync (which is very PAGE_SIZE based) will
@@ -1616,21 +1831,22 @@ int md_bitmap_start_sync(struct bitmap *bitmap, sector_t offset, sector_t *block
 	 * At least PAGE_SIZE>>9 blocks are covered.
 	 * Return the 'or' of the result.
 	 */
-	int rv = 0;
+	bool rv = false;
 	sector_t blocks1;
 
 	*blocks = 0;
 	while (*blocks < (PAGE_SIZE>>9)) {
-		rv |= __bitmap_start_sync(bitmap, offset,
+		rv |= __bitmap_start_sync(mddev->bitmap, offset,
 					  &blocks1, degraded);
 		offset += blocks1;
 		*blocks += blocks1;
 	}
+
 	return rv;
 }
-EXPORT_SYMBOL(md_bitmap_start_sync);
 
-void md_bitmap_end_sync(struct bitmap *bitmap, sector_t offset, sector_t *blocks, int aborted)
+static void __bitmap_end_sync(struct bitmap *bitmap, sector_t offset,
+			      sector_t *blocks, bool aborted)
 {
 	bitmap_counter_t *bmc;
 	unsigned long flags;
@@ -1659,9 +1875,14 @@ void md_bitmap_end_sync(struct bitmap *bitmap, sector_t offset, sector_t *blocks
  unlock:
 	spin_unlock_irqrestore(&bitmap->counts.lock, flags);
 }
-EXPORT_SYMBOL(md_bitmap_end_sync);
 
-void md_bitmap_close_sync(struct bitmap *bitmap)
+static void bitmap_end_sync(struct mddev *mddev, sector_t offset,
+			    sector_t *blocks)
+{
+	__bitmap_end_sync(mddev->bitmap, offset, blocks, true);
+}
+
+static void bitmap_close_sync(struct mddev *mddev)
 {
 	/* Sync has finished, and any bitmap chunks that weren't synced
 	 * properly have been aborted.  It remains to us to clear the
@@ -1669,19 +1890,23 @@ void md_bitmap_close_sync(struct bitmap *bitmap)
 	 */
 	sector_t sector = 0;
 	sector_t blocks;
+	struct bitmap *bitmap = mddev->bitmap;
+
 	if (!bitmap)
 		return;
+
 	while (sector < bitmap->mddev->resync_max_sectors) {
-		md_bitmap_end_sync(bitmap, sector, &blocks, 0);
+		__bitmap_end_sync(bitmap, sector, &blocks, false);
 		sector += blocks;
 	}
 }
-EXPORT_SYMBOL(md_bitmap_close_sync);
 
-void md_bitmap_cond_end_sync(struct bitmap *bitmap, sector_t sector, bool force)
+static void bitmap_cond_end_sync(struct mddev *mddev, sector_t sector,
+				 bool force)
 {
 	sector_t s = 0;
 	sector_t blocks;
+	struct bitmap *bitmap = mddev->bitmap;
 
 	if (!bitmap)
 		return;
@@ -1700,34 +1925,32 @@ void md_bitmap_cond_end_sync(struct bitmap *bitmap, sector_t sector, bool force)
 	sector &= ~((1ULL << bitmap->counts.chunkshift) - 1);
 	s = 0;
 	while (s < sector && s < bitmap->mddev->resync_max_sectors) {
-		md_bitmap_end_sync(bitmap, s, &blocks, 0);
+		__bitmap_end_sync(bitmap, s, &blocks, false);
 		s += blocks;
 	}
 	bitmap->last_end_sync = jiffies;
 	sysfs_notify_dirent_safe(bitmap->mddev->sysfs_completed);
 }
-EXPORT_SYMBOL(md_bitmap_cond_end_sync);
 
-void md_bitmap_sync_with_cluster(struct mddev *mddev,
-			      sector_t old_lo, sector_t old_hi,
-			      sector_t new_lo, sector_t new_hi)
+static void bitmap_sync_with_cluster(struct mddev *mddev,
+				     sector_t old_lo, sector_t old_hi,
+				     sector_t new_lo, sector_t new_hi)
 {
 	struct bitmap *bitmap = mddev->bitmap;
 	sector_t sector, blocks = 0;
 
 	for (sector = old_lo; sector < new_lo; ) {
-		md_bitmap_end_sync(bitmap, sector, &blocks, 0);
+		__bitmap_end_sync(bitmap, sector, &blocks, false);
 		sector += blocks;
 	}
 	WARN((blocks > new_lo) && old_lo, "alignment is not correct for lo\n");
 
 	for (sector = old_hi; sector < new_hi; ) {
-		md_bitmap_start_sync(bitmap, sector, &blocks, 0);
+		bitmap_start_sync(mddev, sector, &blocks, false);
 		sector += blocks;
 	}
 	WARN((blocks > new_hi) && old_hi, "alignment is not correct for hi\n");
 }
-EXPORT_SYMBOL(md_bitmap_sync_with_cluster);
 
 static void md_bitmap_set_memory_bits(struct bitmap *bitmap, sector_t offset, int needed)
 {
@@ -1756,12 +1979,18 @@ static void md_bitmap_set_memory_bits(struct bitmap *bitmap, sector_t offset, in
 }
 
 /* dirty the memory and file bits for bitmap chunks "s" to "e" */
-void md_bitmap_dirty_bits(struct bitmap *bitmap, unsigned long s, unsigned long e)
+static void bitmap_dirty_bits(struct mddev *mddev, unsigned long s,
+			      unsigned long e)
 {
 	unsigned long chunk;
+	struct bitmap *bitmap = mddev->bitmap;
+
+	if (!bitmap)
+		return;
 
 	for (chunk = s; chunk <= e; chunk++) {
 		sector_t sec = (sector_t)chunk << bitmap->counts.chunkshift;
+
 		md_bitmap_set_memory_bits(bitmap, sec, 1);
 		md_bitmap_file_set_bit(bitmap, sec);
 		if (sec < bitmap->mddev->recovery_cp)
@@ -1773,10 +2002,7 @@ void md_bitmap_dirty_bits(struct bitmap *bitmap, unsigned long s, unsigned long
 	}
 }
 
-/*
- * flush out any pending updates
- */
-void md_bitmap_flush(struct mddev *mddev)
+static void bitmap_flush(struct mddev *mddev)
 {
 	struct bitmap *bitmap = mddev->bitmap;
 	long sleep;
@@ -1789,23 +2015,21 @@ void md_bitmap_flush(struct mddev *mddev)
 	 */
 	sleep = mddev->bitmap_info.daemon_sleep * 2;
 	bitmap->daemon_lastrun -= sleep;
-	md_bitmap_daemon_work(mddev);
+	bitmap_daemon_work(mddev);
 	bitmap->daemon_lastrun -= sleep;
-	md_bitmap_daemon_work(mddev);
+	bitmap_daemon_work(mddev);
 	bitmap->daemon_lastrun -= sleep;
-	md_bitmap_daemon_work(mddev);
+	bitmap_daemon_work(mddev);
 	if (mddev->bitmap_info.external)
 		md_super_wait(mddev);
-	md_bitmap_update_sb(bitmap);
+	bitmap_update_sb(bitmap);
 }
 
-/*
- * free memory that was allocated
- */
-void md_bitmap_free(struct bitmap *bitmap)
+static void md_bitmap_free(void *data)
 {
 	unsigned long k, pages;
 	struct bitmap_page *bp;
+	struct bitmap *bitmap = data;
 
 	if (!bitmap) /* there was no bitmap */
 		return;
@@ -1836,9 +2060,8 @@ void md_bitmap_free(struct bitmap *bitmap)
 	kfree(bp);
 	kfree(bitmap);
 }
-EXPORT_SYMBOL(md_bitmap_free);
 
-void md_bitmap_wait_behind_writes(struct mddev *mddev)
+static void bitmap_wait_behind_writes(struct mddev *mddev)
 {
 	struct bitmap *bitmap = mddev->bitmap;
 
@@ -1852,14 +2075,14 @@ void md_bitmap_wait_behind_writes(struct mddev *mddev)
 	}
 }
 
-void md_bitmap_destroy(struct mddev *mddev)
+static void bitmap_destroy(struct mddev *mddev)
 {
 	struct bitmap *bitmap = mddev->bitmap;
 
 	if (!bitmap) /* there was no bitmap */
 		return;
 
-	md_bitmap_wait_behind_writes(mddev);
+	bitmap_wait_behind_writes(mddev);
 	if (!mddev->serialize_policy)
 		mddev_destroy_serial_pool(mddev, NULL);
 
@@ -1878,7 +2101,7 @@ void md_bitmap_destroy(struct mddev *mddev)
  * if this returns an error, bitmap_destroy must be called to do clean up
  * once mddev->bitmap is set
  */
-struct bitmap *md_bitmap_create(struct mddev *mddev, int slot)
+static struct bitmap *__bitmap_create(struct mddev *mddev, int slot)
 {
 	struct bitmap *bitmap;
 	sector_t blocks = mddev->resync_max_sectors;
@@ -1948,7 +2171,8 @@ struct bitmap *md_bitmap_create(struct mddev *mddev, int slot)
 		goto error;
 
 	bitmap->daemon_lastrun = jiffies;
-	err = md_bitmap_resize(bitmap, blocks, mddev->bitmap_info.chunksize, 1);
+	err = __bitmap_resize(bitmap, blocks, mddev->bitmap_info.chunksize,
+			      true);
 	if (err)
 		goto error;
 
@@ -1965,7 +2189,18 @@ struct bitmap *md_bitmap_create(struct mddev *mddev, int slot)
 	return ERR_PTR(err);
 }
 
-int md_bitmap_load(struct mddev *mddev)
+static int bitmap_create(struct mddev *mddev, int slot)
+{
+	struct bitmap *bitmap = __bitmap_create(mddev, slot);
+
+	if (IS_ERR(bitmap))
+		return PTR_ERR(bitmap);
+
+	mddev->bitmap = bitmap;
+	return 0;
+}
+
+static int bitmap_load(struct mddev *mddev)
 {
 	int err = 0;
 	sector_t start = 0;
@@ -1989,10 +2224,10 @@ int md_bitmap_load(struct mddev *mddev)
 	 */
 	while (sector < mddev->resync_max_sectors) {
 		sector_t blocks;
-		md_bitmap_start_sync(bitmap, sector, &blocks, 0);
+		bitmap_start_sync(mddev, sector, &blocks, false);
 		sector += blocks;
 	}
-	md_bitmap_close_sync(bitmap);
+	bitmap_close_sync(mddev);
 
 	if (mddev->degraded == 0
 	    || bitmap->events_cleared == mddev->events)
@@ -2014,22 +2249,21 @@ int md_bitmap_load(struct mddev *mddev)
 	mddev_set_timeout(mddev, mddev->bitmap_info.daemon_sleep, true);
 	md_wakeup_thread(mddev->thread);
 
-	md_bitmap_update_sb(bitmap);
+	bitmap_update_sb(bitmap);
 
 	if (test_bit(BITMAP_WRITE_ERROR, &bitmap->flags))
 		err = -EIO;
 out:
 	return err;
 }
-EXPORT_SYMBOL_GPL(md_bitmap_load);
 
 /* caller need to free returned bitmap with md_bitmap_free() */
-struct bitmap *get_bitmap_from_slot(struct mddev *mddev, int slot)
+static void *bitmap_get_from_slot(struct mddev *mddev, int slot)
 {
 	int rv = 0;
 	struct bitmap *bitmap;
 
-	bitmap = md_bitmap_create(mddev, slot);
+	bitmap = __bitmap_create(mddev, slot);
 	if (IS_ERR(bitmap)) {
 		rv = PTR_ERR(bitmap);
 		return ERR_PTR(rv);
@@ -2043,20 +2277,19 @@ struct bitmap *get_bitmap_from_slot(struct mddev *mddev, int slot)
 
 	return bitmap;
 }
-EXPORT_SYMBOL(get_bitmap_from_slot);
 
 /* Loads the bitmap associated with slot and copies the resync information
  * to our bitmap
  */
-int md_bitmap_copy_from_slot(struct mddev *mddev, int slot,
-		sector_t *low, sector_t *high, bool clear_bits)
+static int bitmap_copy_from_slot(struct mddev *mddev, int slot, sector_t *low,
+				 sector_t *high, bool clear_bits)
 {
 	int rv = 0, i, j;
 	sector_t block, lo = 0, hi = 0;
 	struct bitmap_counts *counts;
 	struct bitmap *bitmap;
 
-	bitmap = get_bitmap_from_slot(mddev, slot);
+	bitmap = bitmap_get_from_slot(mddev, slot);
 	if (IS_ERR(bitmap)) {
 		pr_err("%s can't get bitmap from slot %d\n", __func__, slot);
 		return -1;
@@ -2076,53 +2309,59 @@ int md_bitmap_copy_from_slot(struct mddev *mddev, int slot,
 	}
 
 	if (clear_bits) {
-		md_bitmap_update_sb(bitmap);
+		bitmap_update_sb(bitmap);
 		/* BITMAP_PAGE_PENDING is set, but bitmap_unplug needs
 		 * BITMAP_PAGE_DIRTY or _NEEDWRITE to write ... */
 		for (i = 0; i < bitmap->storage.file_pages; i++)
 			if (test_page_attr(bitmap, i, BITMAP_PAGE_PENDING))
 				set_page_attr(bitmap, i, BITMAP_PAGE_NEEDWRITE);
-		md_bitmap_unplug(bitmap);
+		__bitmap_unplug(bitmap);
 	}
-	md_bitmap_unplug(mddev->bitmap);
+	__bitmap_unplug(mddev->bitmap);
 	*low = lo;
 	*high = hi;
 	md_bitmap_free(bitmap);
 
 	return rv;
 }
-EXPORT_SYMBOL_GPL(md_bitmap_copy_from_slot);
 
+static void bitmap_set_pages(void *data, unsigned long pages)
+{
+	struct bitmap *bitmap = data;
+
+	bitmap->counts.pages = pages;
+}
 
-void md_bitmap_status(struct seq_file *seq, struct bitmap *bitmap)
+static int bitmap_get_stats(void *data, struct md_bitmap_stats *stats)
 {
-	unsigned long chunk_kb;
+	struct bitmap_storage *storage;
 	struct bitmap_counts *counts;
+	struct bitmap *bitmap = data;
+	bitmap_super_t *sb;
 
 	if (!bitmap)
-		return;
+		return -ENOENT;
+
+	sb = kmap_local_page(bitmap->storage.sb_page);
+	stats->sync_size = le64_to_cpu(sb->sync_size);
+	kunmap_local(sb);
 
 	counts = &bitmap->counts;
+	stats->missing_pages = counts->missing_pages;
+	stats->pages = counts->pages;
 
-	chunk_kb = bitmap->mddev->bitmap_info.chunksize >> 10;
-	seq_printf(seq, "bitmap: %lu/%lu pages [%luKB], "
-		   "%lu%s chunk",
-		   counts->pages - counts->missing_pages,
-		   counts->pages,
-		   (counts->pages - counts->missing_pages)
-		   << (PAGE_SHIFT - 10),
-		   chunk_kb ? chunk_kb : bitmap->mddev->bitmap_info.chunksize,
-		   chunk_kb ? "KB" : "B");
-	if (bitmap->storage.file) {
-		seq_printf(seq, ", file: ");
-		seq_file_path(seq, bitmap->storage.file, " \t\n");
-	}
+	storage = &bitmap->storage;
+	stats->file_pages = storage->file_pages;
+	stats->file = storage->file;
 
-	seq_printf(seq, "\n");
+	stats->behind_writes = atomic_read(&bitmap->behind_writes);
+	stats->behind_wait = wq_has_sleeper(&bitmap->behind_wait);
+	stats->events_cleared = bitmap->events_cleared;
+	return 0;
 }
 
-int md_bitmap_resize(struct bitmap *bitmap, sector_t blocks,
-		  int chunksize, int init)
+static int __bitmap_resize(struct bitmap *bitmap, sector_t blocks,
+			   int chunksize, bool init)
 {
 	/* If chunk_size is 0, choose an appropriate chunk size.
 	 * Then possibly allocate new storage space.
@@ -2320,14 +2559,24 @@ int md_bitmap_resize(struct bitmap *bitmap, sector_t blocks,
 	spin_unlock_irq(&bitmap->counts.lock);
 
 	if (!init) {
-		md_bitmap_unplug(bitmap);
+		__bitmap_unplug(bitmap);
 		bitmap->mddev->pers->quiesce(bitmap->mddev, 0);
 	}
 	ret = 0;
 err:
 	return ret;
 }
-EXPORT_SYMBOL_GPL(md_bitmap_resize);
+
+static int bitmap_resize(struct mddev *mddev, sector_t blocks, int chunksize,
+			 bool init)
+{
+	struct bitmap *bitmap = mddev->bitmap;
+
+	if (!bitmap)
+		return 0;
+
+	return __bitmap_resize(bitmap, blocks, chunksize, init);
+}
 
 static ssize_t
 location_show(struct mddev *mddev, char *page)
@@ -2367,7 +2616,7 @@ location_store(struct mddev *mddev, const char *buf, size_t len)
 			goto out;
 		}
 
-		md_bitmap_destroy(mddev);
+		bitmap_destroy(mddev);
 		mddev->bitmap_info.offset = 0;
 		if (mddev->bitmap_info.file) {
 			struct file *f = mddev->bitmap_info.file;
@@ -2377,7 +2626,6 @@ location_store(struct mddev *mddev, const char *buf, size_t len)
 	} else {
 		/* No bitmap, OK to set a location */
 		long long offset;
-		struct bitmap *bitmap;
 
 		if (strncmp(buf, "none", 4) == 0)
 			/* nothing to be done */;
@@ -2404,17 +2652,14 @@ location_store(struct mddev *mddev, const char *buf, size_t len)
 			}
 
 			mddev->bitmap_info.offset = offset;
-			bitmap = md_bitmap_create(mddev, -1);
-			if (IS_ERR(bitmap)) {
-				rv = PTR_ERR(bitmap);
+			rv = bitmap_create(mddev, -1);
+			if (rv)
 				goto out;
-			}
 
-			mddev->bitmap = bitmap;
-			rv = md_bitmap_load(mddev);
+			rv = bitmap_load(mddev);
 			if (rv) {
 				mddev->bitmap_info.offset = 0;
-				md_bitmap_destroy(mddev);
+				bitmap_destroy(mddev);
 				goto out;
 			}
 		}
@@ -2450,6 +2695,7 @@ space_show(struct mddev *mddev, char *page)
 static ssize_t
 space_store(struct mddev *mddev, const char *buf, size_t len)
 {
+	struct bitmap *bitmap;
 	unsigned long sectors;
 	int rv;
 
@@ -2460,8 +2706,8 @@ space_store(struct mddev *mddev, const char *buf, size_t len)
 	if (sectors == 0)
 		return -EINVAL;
 
-	if (mddev->bitmap &&
-	    sectors < (mddev->bitmap->storage.bytes + 511) >> 9)
+	bitmap = mddev->bitmap;
+	if (bitmap && sectors < (bitmap->storage.bytes + 511) >> 9)
 		return -EFBIG; /* Bitmap is too big for this small space */
 
 	/* could make sure it isn't too big, but that isn't really
@@ -2569,7 +2815,7 @@ backlog_store(struct mddev *mddev, const char *buf, size_t len)
 			mddev_create_serial_pool(mddev, rdev);
 	}
 	if (old_mwb != backlog)
-		md_bitmap_update_sb(mddev->bitmap);
+		bitmap_update_sb(mddev->bitmap);
 
 	mddev_unlock_and_resume(mddev);
 	return len;
@@ -2638,10 +2884,13 @@ __ATTR(metadata, S_IRUGO|S_IWUSR, metadata_show, metadata_store);
 static ssize_t can_clear_show(struct mddev *mddev, char *page)
 {
 	int len;
+	struct bitmap *bitmap;
+
 	spin_lock(&mddev->lock);
-	if (mddev->bitmap)
-		len = sprintf(page, "%s\n", (mddev->bitmap->need_sync ?
-					     "false" : "true"));
+	bitmap = mddev->bitmap;
+	if (bitmap)
+		len = sprintf(page, "%s\n", (bitmap->need_sync ? "false" :
+								 "true"));
 	else
 		len = sprintf(page, "\n");
 	spin_unlock(&mddev->lock);
@@ -2650,17 +2899,24 @@ static ssize_t can_clear_show(struct mddev *mddev, char *page)
 
 static ssize_t can_clear_store(struct mddev *mddev, const char *buf, size_t len)
 {
-	if (mddev->bitmap == NULL)
+	struct bitmap *bitmap = mddev->bitmap;
+
+	if (!bitmap)
 		return -ENOENT;
-	if (strncmp(buf, "false", 5) == 0)
-		mddev->bitmap->need_sync = 1;
-	else if (strncmp(buf, "true", 4) == 0) {
+
+	if (strncmp(buf, "false", 5) == 0) {
+		bitmap->need_sync = 1;
+		return len;
+	}
+
+	if (strncmp(buf, "true", 4) == 0) {
 		if (mddev->degraded)
 			return -EBUSY;
-		mddev->bitmap->need_sync = 0;
-	} else
-		return -EINVAL;
-	return len;
+		bitmap->need_sync = 0;
+		return len;
+	}
+
+	return -EINVAL;
 }
 
 static struct md_sysfs_entry bitmap_can_clear =
@@ -2670,21 +2926,26 @@ static ssize_t
 behind_writes_used_show(struct mddev *mddev, char *page)
 {
 	ssize_t ret;
+	struct bitmap *bitmap;
+
 	spin_lock(&mddev->lock);
-	if (mddev->bitmap == NULL)
+	bitmap = mddev->bitmap;
+	if (!bitmap)
 		ret = sprintf(page, "0\n");
 	else
-		ret = sprintf(page, "%lu\n",
-			      mddev->bitmap->behind_writes_used);
+		ret = sprintf(page, "%lu\n", bitmap->behind_writes_used);
 	spin_unlock(&mddev->lock);
+
 	return ret;
 }
 
 static ssize_t
 behind_writes_used_reset(struct mddev *mddev, const char *buf, size_t len)
 {
-	if (mddev->bitmap)
-		mddev->bitmap->behind_writes_used = 0;
+	struct bitmap *bitmap = mddev->bitmap;
+
+	if (bitmap)
+		bitmap->behind_writes_used = 0;
 	return len;
 }
 
@@ -2707,3 +2968,38 @@ const struct attribute_group md_bitmap_group = {
 	.name = "bitmap",
 	.attrs = md_bitmap_attrs,
 };
+
+static struct bitmap_operations bitmap_ops = {
+	.enabled		= bitmap_enabled,
+	.create			= bitmap_create,
+	.resize			= bitmap_resize,
+	.load			= bitmap_load,
+	.destroy		= bitmap_destroy,
+	.flush			= bitmap_flush,
+	.write_all		= bitmap_write_all,
+	.dirty_bits		= bitmap_dirty_bits,
+	.unplug			= bitmap_unplug,
+	.daemon_work		= bitmap_daemon_work,
+	.wait_behind_writes	= bitmap_wait_behind_writes,
+
+	.startwrite		= bitmap_startwrite,
+	.endwrite		= bitmap_endwrite,
+	.start_sync		= bitmap_start_sync,
+	.end_sync		= bitmap_end_sync,
+	.cond_end_sync		= bitmap_cond_end_sync,
+	.close_sync		= bitmap_close_sync,
+
+	.update_sb		= bitmap_update_sb,
+	.get_stats		= bitmap_get_stats,
+
+	.sync_with_cluster	= bitmap_sync_with_cluster,
+	.get_from_slot		= bitmap_get_from_slot,
+	.copy_from_slot		= bitmap_copy_from_slot,
+	.set_pages		= bitmap_set_pages,
+	.free			= md_bitmap_free,
+};
+
+void mddev_set_bitmap_ops(struct mddev *mddev)
+{
+	mddev->bitmap_ops = &bitmap_ops;
+}