drbd: cleanup ondisk meta data layout calculations and defines

Add a comment about our meta data layout variants,
and rename a few defines (e.g. MD_RESERVED_SECT -> MD_128MB_SECT)
to make it clear that they are short hand for fixed constants,
and not arbitrarily to be redefined as one may see fit.

Properly pad struct meta_data_on_disk to 4kB,
and initialize to zero not only the first 512 Byte,
but all of it in drbd_md_sync().

Signed-off-by: Philipp Reisner <[e-mail]>
Signed-off-by: Lars Ellenberg <[e-mail]>
Signed-off-by: Jens Axboe <[e-mail]>

drivers/block/drbd/drbd_actlog.c

···
 		     current->comm, current->pid, __func__,
 		     (unsigned long long)sector, (rw & WRITE) ? "WRITE" : "READ");
 
-	err = _drbd_md_sync_page_io(mdev, bdev, iop, sector, rw, MD_BLOCK_SIZE);
+	/* we do all our meta data IO in aligned 4k blocks. */
+	err = _drbd_md_sync_page_io(mdev, bdev, iop, sector, rw, 4096);
 	if (err) {
 		dev_err(DEV, "drbd_md_sync_page_io(,%llus,%s) failed with error %d\n",
 		    (unsigned long long)sector, (rw & WRITE) ? "WRITE" : "READ", err);
···
 		 (BM_EXT_SHIFT - BM_BLOCK_SHIFT));
 }
 
+static sector_t al_tr_number_to_on_disk_sector(struct drbd_conf *mdev)
+{
+	const unsigned int stripes = 1;
+	const unsigned int stripe_size_4kB = MD_32kB_SECT/MD_4kB_SECT;
+
+	/* transaction number, modulo on-disk ring buffer wrap around */
+	unsigned int t = mdev->al_tr_number % (stripe_size_4kB * stripes);
+
+	/* ... to aligned 4k on disk block */
+	t = ((t % stripes) * stripe_size_4kB) + t/stripes;
+
+	/* ... to 512 byte sector in activity log */
+	t *= 8;
+
+	/* ... plus offset to the on disk position */
+	return mdev->ldev->md.md_offset + mdev->ldev->md.al_offset + t;
+}
+
 static int
 _al_write_transaction(struct drbd_conf *mdev)
 {
···
 	if (mdev->al_tr_cycle >= mdev->act_log->nr_elements)
 		mdev->al_tr_cycle = 0;
 
-	sector =  mdev->ldev->md.md_offset
-		+ mdev->ldev->md.al_offset
-		+ mdev->al_tr_pos * (MD_BLOCK_SIZE>>9);
+	sector = al_tr_number_to_on_disk_sector(mdev);
 
 	crc = crc32c(0, buffer, 4096);
 	buffer->crc32c = cpu_to_be32(crc);
 
+	/* normal execution path goes through all three branches */
 	if (drbd_bm_write_hinted(mdev))
 		err = -EIO;
 		/* drbd_chk_io_error done already */
···
 		err = -EIO;
 		drbd_chk_io_error(mdev, 1, DRBD_META_IO_ERROR);
 	} else {
-		/* advance ringbuffer position and transaction counter */
-		mdev->al_tr_pos = (mdev->al_tr_pos + 1) % (MD_AL_SECTORS*512/MD_BLOCK_SIZE);
 		mdev->al_tr_number++;
 	}
 

drivers/block/drbd/drbd_bitmap.c

···
 	}
 }
 
+/* For the layout, see comment above drbd_md_set_sector_offsets(). */
+static u64 drbd_md_on_disk_bits(struct drbd_backing_dev *ldev)
+{
+	u64 bitmap_sectors;
+	if (ldev->md.al_offset == 8)
+		bitmap_sectors = ldev->md.md_size_sect - ldev->md.bm_offset;
+	else
+		bitmap_sectors = ldev->md.al_offset - ldev->md.bm_offset;
+	return bitmap_sectors << (9 + 3);
+}
+
 /*
  * make sure the bitmap has enough room for the attached storage,
  * if necessary, resize.
···
 	words = ALIGN(bits, 64) >> LN2_BPL;
 
 	if (get_ldev(mdev)) {
-		u64 bits_on_disk = ((u64)mdev->ldev->md.md_size_sect-MD_BM_OFFSET) << 12;
+		u64 bits_on_disk = drbd_md_on_disk_bits(mdev->ldev);
 		put_ldev(mdev);
 		if (bits > bits_on_disk) {
 			dev_info(DEV, "bits = %lu\n", bits);

drivers/block/drbd/drbd_int.h

···
 	u32 flags;
 	u32 md_size_sect;
 
-	s32 al_offset;	/* signed relative sector offset to al area */
+	s32 al_offset;	/* signed relative sector offset to activity log */
 	s32 bm_offset;	/* signed relative sector offset to bitmap */
-
-	/* u32 al_nr_extents;	   important for restoring the AL
-	 * is stored into  ldev->dc.al_extents, which in turn
-	 * gets applied to act_log->nr_elements
-	 */
 };
 
 struct drbd_backing_dev {
···
 	struct lru_cache *act_log;	/* activity log */
 	unsigned int al_tr_number;
 	int al_tr_cycle;
-	int al_tr_pos;   /* position of the next transaction in the journal */
 	wait_queue_head_t seq_wait;
 	atomic_t packet_seq;
 	unsigned int peer_seq;
···
 extern void drbd_ldev_destroy(struct drbd_conf *mdev);
 
 /* Meta data layout
-   We reserve a 128MB Block (4k aligned)
-   * either at the end of the backing device
-   * or on a separate meta data device. */
+ *
+ * We currently have two possible layouts.
+ * Offsets in (512 byte) sectors.
+ * external:
+ *   |----------- md_size_sect ------------------|
+ *   [ 4k superblock ][ activity log ][  Bitmap  ]
+ *   | al_offset == 8 |
+ *   | bm_offset = al_offset + X      |
+ *  ==> bitmap sectors = md_size_sect - bm_offset
+ *
+ *  Variants:
+ *     old, indexed fixed size meta data:
+ *
+ * internal:
+ *            |----------- md_size_sect ------------------|
+ * [data.....][  Bitmap  ][ activity log ][ 4k superblock ][padding*]
+ *                        | al_offset < 0 |
+ *            | bm_offset = al_offset - Y |
+ *  ==> bitmap sectors = Y = al_offset - bm_offset
+ *
+ *  [padding*] are zero or up to 7 unused 512 Byte sectors to the
+ *  end of the device, so that the [4k superblock] will be 4k aligned.
+ *
+ *  The activity log consists of 4k transaction blocks,
+ *  which are written in a ring-buffer, or striped ring-buffer like fashion,
+ *  which are writtensize used to be fixed 32kB,
+ *  but is about to become configurable.
+ */
 
-/* The following numbers are sectors */
-/* Allows up to about 3.8TB, so if you want more,
+/* Our old fixed size meta data layout
+ * allows up to about 3.8TB, so if you want more,
  * you need to use the "flexible" meta data format. */
-#define MD_RESERVED_SECT (128LU << 11)  /* 128 MB, unit sectors */
-#define MD_AL_OFFSET	8    /* 8 Sectors after start of meta area */
-#define MD_AL_SECTORS	64   /* = 32 kB on disk activity log ring buffer */
-#define MD_BM_OFFSET (MD_AL_OFFSET + MD_AL_SECTORS)
-
-/* we do all meta data IO in 4k blocks */
-#define MD_BLOCK_SHIFT	12
-#define MD_BLOCK_SIZE	(1<<MD_BLOCK_SHIFT)
+#define MD_128MB_SECT (128LLU << 11)  /* 128 MB, unit sectors */
+#define MD_4kB_SECT	 8
+#define MD_32kB_SECT	64
 
 /* One activity log extent represents 4M of storage */
 #define AL_EXTENT_SHIFT 22
···
 
 /* in one sector of the bitmap, we have this many activity_log extents. */
 #define AL_EXT_PER_BM_SECT  (1 << (BM_EXT_SHIFT - AL_EXTENT_SHIFT))
-#define BM_WORDS_PER_AL_EXT (1 << (AL_EXTENT_SHIFT-BM_BLOCK_SHIFT-LN2_BPL))
 
 #define BM_BLOCKS_PER_BM_EXT_B (BM_EXT_SHIFT - BM_BLOCK_SHIFT)
 #define BM_BLOCKS_PER_BM_EXT_MASK  ((1<<BM_BLOCKS_PER_BM_EXT_B) - 1)
···
  */
 
 #define DRBD_MAX_SECTORS_32 (0xffffffffLU)
-#define DRBD_MAX_SECTORS_BM \
-	  ((MD_RESERVED_SECT - MD_BM_OFFSET) * (1LL<<(BM_EXT_SHIFT-9)))
-#if DRBD_MAX_SECTORS_BM < DRBD_MAX_SECTORS_32
-#define DRBD_MAX_SECTORS      DRBD_MAX_SECTORS_BM
-#define DRBD_MAX_SECTORS_FLEX DRBD_MAX_SECTORS_BM
-#elif !defined(CONFIG_LBDAF) && BITS_PER_LONG == 32
+/* we have a certain meta data variant that has a fixed on-disk size of 128
+ * MiB, of which 4k are our "superblock", and 32k are the fixed size activity
+ * log, leaving this many sectors for the bitmap.
+ */
+
+#define DRBD_MAX_SECTORS_FIXED_BM \
+	  ((MD_128MB_SECT - MD_32kB_SECT - MD_4kB_SECT) * (1LL<<(BM_EXT_SHIFT-9)))
+#if !defined(CONFIG_LBDAF) && BITS_PER_LONG == 32
 #define DRBD_MAX_SECTORS      DRBD_MAX_SECTORS_32
 #define DRBD_MAX_SECTORS_FLEX DRBD_MAX_SECTORS_32
 #else
-#define DRBD_MAX_SECTORS      DRBD_MAX_SECTORS_BM
+#define DRBD_MAX_SECTORS      DRBD_MAX_SECTORS_FIXED_BM
 /* 16 TB in units of sectors */
 #if BITS_PER_LONG == 32
 /* adjust by one page worth of bitmap,
···
 	switch (meta_dev_idx) {
 	case DRBD_MD_INDEX_INTERNAL:
 	case DRBD_MD_INDEX_FLEX_INT:
-		return bdev->md.md_offset + MD_AL_OFFSET - 1;
+		return bdev->md.md_offset + MD_4kB_SECT -1;
 	case DRBD_MD_INDEX_FLEX_EXT:
 	default:
-		return bdev->md.md_offset + bdev->md.md_size_sect;
+		return bdev->md.md_offset + bdev->md.md_size_sect -1;
 	}
 }
 
···
 	rcu_read_unlock();
 
 	switch (meta_dev_idx) {
-	default: /* external, some index */
-		return MD_RESERVED_SECT * meta_dev_idx;
+	default: /* external, some index; this is the old fixed size layout */
+		return MD_128MB_SECT * meta_dev_idx;
 	case DRBD_MD_INDEX_INTERNAL:
 		/* with drbd08, internal meta data is always "flexible" */
 	case DRBD_MD_INDEX_FLEX_INT:
-		/* sizeof(struct md_on_disk_07) == 4k
-		 * position: last 4k aligned block of 4k size */
 		if (!bdev->backing_bdev) {
 			if (__ratelimit(&drbd_ratelimit_state)) {
 				dev_err(DEV, "bdev->backing_bdev==NULL\n");
···
 			}
 			return 0;
 		}
-		return (drbd_get_capacity(bdev->backing_bdev) & ~7ULL)
-			- MD_AL_OFFSET;
+		/* sizeof(struct md_on_disk_07) == 4k
+		 * position: last 4k aligned block of 4k size */
+		return (drbd_get_capacity(bdev->backing_bdev) & ~7ULL) - 8;
 	case DRBD_MD_INDEX_FLEX_EXT:
 		return 0;
 	}

drivers/block/drbd/drbd_main.c

···
 	rcu_read_unlock();
 }
 
+/* aligned 4kByte */
 struct meta_data_on_disk {
 	u64 la_size;           /* last agreed size. */
 	u64 uuid[UI_SIZE];   /* UUIDs. */
···
 	u32 magic;
 	u32 md_size_sect;
 	u32 al_offset;         /* offset to this block */
-	u32 al_nr_extents;     /* important for restoring the AL */
+	u32 al_nr_extents;     /* important for restoring the AL (userspace) */
 	      /* `-- act_log->nr_elements <-- ldev->dc.al_extents */
 	u32 bm_offset;         /* offset to the bitmap, from here */
 	u32 bm_bytes_per_bit;  /* BM_BLOCK_SIZE */
 	u32 la_peer_max_bio_size;   /* last peer max_bio_size */
-	u32 reserved_u32[3];
 
+	u8 reserved_u8[4096 - (7*8 + 8*4)];
 } __packed;
 
 /**
···
 	struct meta_data_on_disk *buffer;
 	sector_t sector;
 	int i;
+
+	/* Don't accidentally change the DRBD meta data layout. */
+	BUILD_BUG_ON(UI_SIZE != 4);
+	BUILD_BUG_ON(sizeof(struct meta_data_on_disk) != 4096);
 
 	del_timer(&mdev->md_sync_timer);
 	/* timer may be rearmed by drbd_md_mark_dirty() now. */
···
 	if (!buffer)
 		goto out;
 
-	memset(buffer, 0, 512);
+	memset(buffer, 0, sizeof(*buffer));
 
 	buffer->la_size = cpu_to_be64(drbd_get_capacity(mdev->this_bdev));
 	for (i = UI_CURRENT; i < UI_SIZE; i++)

drivers/block/drbd/drbd_nl.c

···
 	return 0;
 }
 
-/* initializes the md.*_offset members, so we are able to find
- * the on disk meta data */
+/* Initializes the md.*_offset members, so we are able to find
+ * the on disk meta data.
+ *
+ * We currently have two possible layouts:
+ * external:
+ *   |----------- md_size_sect ------------------|
+ *   [ 4k superblock ][ activity log ][  Bitmap  ]
+ *   | al_offset == 8 |
+ *   | bm_offset = al_offset + X      |
+ *  ==> bitmap sectors = md_size_sect - bm_offset
+ *
+ * internal:
+ *            |----------- md_size_sect ------------------|
+ * [data.....][  Bitmap  ][ activity log ][ 4k superblock ]
+ *                        | al_offset < 0 |
+ *            | bm_offset = al_offset - Y |
+ *  ==> bitmap sectors = Y = al_offset - bm_offset
+ *
+ *  Activity log size used to be fixed 32kB,
+ *  but is about to become configurable.
+ */
 static void drbd_md_set_sector_offsets(struct drbd_conf *mdev,
 				       struct drbd_backing_dev *bdev)
 {
 	sector_t md_size_sect = 0;
+	unsigned int al_size_sect = MD_32kB_SECT;
 	int meta_dev_idx;
 
 	rcu_read_lock();
···
 	switch (meta_dev_idx) {
 	default:
 		/* v07 style fixed size indexed meta data */
-		bdev->md.md_size_sect = MD_RESERVED_SECT;
+		bdev->md.md_size_sect = MD_128MB_SECT;
 		bdev->md.md_offset = drbd_md_ss__(mdev, bdev);
-		bdev->md.al_offset = MD_AL_OFFSET;
-		bdev->md.bm_offset = MD_BM_OFFSET;
+		bdev->md.al_offset = MD_4kB_SECT;
+		bdev->md.bm_offset = MD_4kB_SECT + al_size_sect;
 		break;
 	case DRBD_MD_INDEX_FLEX_EXT:
 		/* just occupy the full device; unit: sectors */
 		bdev->md.md_size_sect = drbd_get_capacity(bdev->md_bdev);
 		bdev->md.md_offset = 0;
-		bdev->md.al_offset = MD_AL_OFFSET;
-		bdev->md.bm_offset = MD_BM_OFFSET;
+		bdev->md.al_offset = MD_4kB_SECT;
+		bdev->md.bm_offset = MD_4kB_SECT + al_size_sect;
 		break;
 	case DRBD_MD_INDEX_INTERNAL:
 	case DRBD_MD_INDEX_FLEX_INT:
 		bdev->md.md_offset = drbd_md_ss__(mdev, bdev);
 		/* al size is still fixed */
-		bdev->md.al_offset = -MD_AL_SECTORS;
+		bdev->md.al_offset = -al_size_sect;
 		/* we need (slightly less than) ~ this much bitmap sectors: */
 		md_size_sect = drbd_get_capacity(bdev->backing_bdev);
 		md_size_sect = ALIGN(md_size_sect, BM_SECT_PER_EXT);
···
 
 		/* plus the "drbd meta data super block",
 		 * and the activity log; */
-		md_size_sect += MD_BM_OFFSET;
+		md_size_sect += MD_4kB_SECT + al_size_sect;
 
 		bdev->md.md_size_sect = md_size_sect;
 		/* bitmap offset is adjusted by 'super' block size */
-		bdev->md.bm_offset   = -md_size_sect + MD_AL_OFFSET;
+		bdev->md.bm_offset   = -md_size_sect + MD_4kB_SECT;
 		break;
 	}
 	rcu_read_unlock();
···
 		min_md_device_sectors = (2<<10);
 	} else {
 		max_possible_sectors = DRBD_MAX_SECTORS;
-		min_md_device_sectors = MD_RESERVED_SECT * (new_disk_conf->meta_dev_idx + 1);
+		min_md_device_sectors = MD_128MB_SECT * (new_disk_conf->meta_dev_idx + 1);
 	}
 
 	if (drbd_get_capacity(nbc->md_bdev) < min_md_device_sectors) {