The DRBD driver

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>

19 files changed, 20366 insertions, 0 deletions

diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig
index 1d886e079c5..77bfce52e9c 100644
--- a/drivers/block/Kconfig
+++ b/drivers/block/Kconfig
@@ -271,6 +271,8 @@ config BLK_DEV_CRYPTOLOOP
 	  instead, which can be configured to be on-disk compatible with the
 	  cryptoloop device.
 
+source "drivers/block/drbd/Kconfig"
+
 config BLK_DEV_NBD
 	tristate "Network block device support"
 	depends on NET
diff --git a/drivers/block/Makefile b/drivers/block/Makefile
index cdaa3f8fddf..aff5ac925c3 100644
--- a/drivers/block/Makefile
+++ b/drivers/block/Makefile
@@ -36,5 +36,6 @@ obj-$(CONFIG_BLK_DEV_UB)	+= ub.o
 obj-$(CONFIG_BLK_DEV_HD)	+= hd.o
 
 obj-$(CONFIG_XEN_BLKDEV_FRONTEND)	+= xen-blkfront.o
+obj-$(CONFIG_BLK_DEV_DRBD)     += drbd/
 
 swim_mod-objs	:= swim.o swim_asm.o
diff --git a/drivers/block/drbd/Kconfig b/drivers/block/drbd/Kconfig
new file mode 100644
index 00000000000..4e6f90f487c
--- /dev/null
+++ b/drivers/block/drbd/Kconfig
@@ -0,0 +1,82 @@
+#
+# DRBD device driver configuration
+#
+
+comment "DRBD disabled because PROC_FS, INET or CONNECTOR not selected"
+	depends on !PROC_FS || !INET || !CONNECTOR
+
+config BLK_DEV_DRBD
+	tristate "DRBD Distributed Replicated Block Device support"
+	depends on PROC_FS && INET && CONNECTOR
+	select LRU_CACHE
+	default n
+	help
+
+	  NOTE: In order to authenticate connections you have to select
+	  CRYPTO_HMAC and a hash function as well.
+
+	  DRBD is a shared-nothing, synchronously replicated block device. It
+	  is designed to serve as a building block for high availability
+	  clusters and in this context, is a "drop-in" replacement for shared
+	  storage. Simplistically, you could see it as a network RAID 1.
+
+	  Each minor device has a role, which can be 'primary' or 'secondary'.
+	  On the node with the primary device the application is supposed to
+	  run and to access the device (/dev/drbdX). Every write is sent to
+	  the local 'lower level block device' and, across the network, to the
+	  node with the device in 'secondary' state.  The secondary device
+	  simply writes the data to its lower level block device.
+
+	  DRBD can also be used in dual-Primary mode (device writable on both
+	  nodes), which means it can exhibit shared disk semantics in a
+	  shared-nothing cluster.  Needless to say, on top of dual-Primary
+	  DRBD utilizing a cluster file system is necessary to maintain for
+	  cache coherency.
+
+	  For automatic failover you need a cluster manager (e.g. heartbeat).
+	  See also: http://www.drbd.org/, http://www.linux-ha.org
+
+	  If unsure, say N.
+
+config DRBD_TRACE
+	tristate "DRBD tracing"
+	depends on BLK_DEV_DRBD
+	select TRACEPOINTS
+	default n
+	help
+
+	  Say Y here if you want to be able to trace various events in DRBD.
+
+	  If unsure, say N.
+
+config DRBD_FAULT_INJECTION
+	bool "DRBD fault injection"
+	depends on BLK_DEV_DRBD
+	help
+
+	  Say Y here if you want to simulate IO errors, in order to test DRBD's
+	  behavior.
+
+	  The actual simulation of IO errors is done by writing 3 values to
+	  /sys/module/drbd/parameters/
+
+	  enable_faults: bitmask of...
+	  1	meta data write
+	  2               read
+	  4	resync data write
+	  8	            read
+	  16	data write
+	  32	data read
+	  64	read ahead
+	  128	kmalloc of bitmap
+	  256	allocation of EE (epoch_entries)
+
+	  fault_devs: bitmask of minor numbers
+	  fault_rate: frequency in percent
+
+	  Example: Simulate data write errors on /dev/drbd0 with a probability of 5%.
+		echo 16 > /sys/module/drbd/parameters/enable_faults
+		echo 1 > /sys/module/drbd/parameters/fault_devs
+		echo 5 > /sys/module/drbd/parameters/fault_rate
+
+	  If unsure, say N.
diff --git a/drivers/block/drbd/Makefile b/drivers/block/drbd/Makefile
new file mode 100644
index 00000000000..7d86ef8a8b4
--- /dev/null
+++ b/drivers/block/drbd/Makefile
@@ -0,0 +1,8 @@
+drbd-y := drbd_bitmap.o drbd_proc.o
+drbd-y += drbd_worker.o drbd_receiver.o drbd_req.o drbd_actlog.o
+drbd-y += drbd_main.o drbd_strings.o drbd_nl.o
+
+drbd_trace-y := drbd_tracing.o
+
+obj-$(CONFIG_BLK_DEV_DRBD)     += drbd.o
+obj-$(CONFIG_DRBD_TRACE)       += drbd_trace.o
diff --git a/drivers/block/drbd/drbd_actlog.c b/drivers/block/drbd/drbd_actlog.c
new file mode 100644
index 00000000000..74b4835d310
--- /dev/null
+++ b/drivers/block/drbd/drbd_actlog.c
@@ -0,0 +1,1484 @@
+/*
+   drbd_actlog.c
+
+   This file is part of DRBD by Philipp Reisner and Lars Ellenberg.
+
+   Copyright (C) 2003-2008, LINBIT Information Technologies GmbH.
+   Copyright (C) 2003-2008, Philipp Reisner <philipp.reisner@linbit.com>.
+   Copyright (C) 2003-2008, Lars Ellenberg <lars.ellenberg@linbit.com>.
+
+   drbd is free software; you can redistribute it and/or modify
+   it under the terms of the GNU General Public License as published by
+   the Free Software Foundation; either version 2, or (at your option)
+   any later version.
+
+   drbd is distributed in the hope that it will be useful,
+   but WITHOUT ANY WARRANTY; without even the implied warranty of
+   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+   GNU General Public License for more details.
+
+   You should have received a copy of the GNU General Public License
+   along with drbd; see the file COPYING.  If not, write to
+   the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA.
+
+ */
+
+#include <linux/slab.h>
+#include <linux/drbd.h>
+#include "drbd_int.h"
+#include "drbd_tracing.h"
+#include "drbd_wrappers.h"
+
+/* We maintain a trivial check sum in our on disk activity log.
+ * With that we can ensure correct operation even when the storage
+ * device might do a partial (last) sector write while loosing power.
+ */
+struct __packed al_transaction {
+	u32       magic;
+	u32       tr_number;
+	struct __packed {
+		u32 pos;
+		u32 extent; } updates[1 + AL_EXTENTS_PT];
+	u32       xor_sum;
+};
+
+struct update_odbm_work {
+	struct drbd_work w;
+	unsigned int enr;
+};
+
+struct update_al_work {
+	struct drbd_work w;
+	struct lc_element *al_ext;
+	struct completion event;
+	unsigned int enr;
+	/* if old_enr != LC_FREE, write corresponding bitmap sector, too */
+	unsigned int old_enr;
+};
+
+struct drbd_atodb_wait {
+	atomic_t           count;
+	struct completion  io_done;
+	struct drbd_conf   *mdev;
+	int                error;
+};
+
+
+int w_al_write_transaction(struct drbd_conf *, struct drbd_work *, int);
+
+/* The actual tracepoint needs to have constant number of known arguments...
+ */
+void trace_drbd_resync(struct drbd_conf *mdev, int level, const char *fmt, ...)
+{
+	va_list ap;
+
+	va_start(ap, fmt);
+	trace__drbd_resync(mdev, level, fmt, ap);
+	va_end(ap);
+}
+
+static int _drbd_md_sync_page_io(struct drbd_conf *mdev,
+				 struct drbd_backing_dev *bdev,
+				 struct page *page, sector_t sector,
+				 int rw, int size)
+{
+	struct bio *bio;
+	struct drbd_md_io md_io;
+	int ok;
+
+	md_io.mdev = mdev;
+	init_completion(&md_io.event);
+	md_io.error = 0;
+
+	if ((rw & WRITE) && !test_bit(MD_NO_BARRIER, &mdev->flags))
+		rw |= (1 << BIO_RW_BARRIER);
+	rw |= ((1<<BIO_RW_UNPLUG) | (1<<BIO_RW_SYNCIO));
+
+ retry:
+	bio = bio_alloc(GFP_NOIO, 1);
+	bio->bi_bdev = bdev->md_bdev;
+	bio->bi_sector = sector;
+	ok = (bio_add_page(bio, page, size, 0) == size);
+	if (!ok)
+		goto out;
+	bio->bi_private = &md_io;
+	bio->bi_end_io = drbd_md_io_complete;
+	bio->bi_rw = rw;
+
+	trace_drbd_bio(mdev, "Md", bio, 0, NULL);
+
+	if (FAULT_ACTIVE(mdev, (rw & WRITE) ? DRBD_FAULT_MD_WR : DRBD_FAULT_MD_RD))
+		bio_endio(bio, -EIO);
+	else
+		submit_bio(rw, bio);
+	wait_for_completion(&md_io.event);
+	ok = bio_flagged(bio, BIO_UPTODATE) && md_io.error == 0;
+
+	/* check for unsupported barrier op.
+	 * would rather check on EOPNOTSUPP, but that is not reliable.
+	 * don't try again for ANY return value != 0 */
+	if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER) && !ok)) {
+		/* Try again with no barrier */
+		dev_warn(DEV, "Barriers not supported on meta data device - disabling\n");
+		set_bit(MD_NO_BARRIER, &mdev->flags);
+		rw &= ~(1 << BIO_RW_BARRIER);
+		bio_put(bio);
+		goto retry;
+	}
+ out:
+	bio_put(bio);
+	return ok;
+}
+
+int drbd_md_sync_page_io(struct drbd_conf *mdev, struct drbd_backing_dev *bdev,
+			 sector_t sector, int rw)
+{
+	int logical_block_size, mask, ok;
+	int offset = 0;
+	struct page *iop = mdev->md_io_page;
+
+	D_ASSERT(mutex_is_locked(&mdev->md_io_mutex));
+
+	BUG_ON(!bdev->md_bdev);
+
+	logical_block_size = bdev_logical_block_size(bdev->md_bdev);
+	if (logical_block_size == 0)
+		logical_block_size = MD_SECTOR_SIZE;
+
+	/* in case logical_block_size != 512 [ s390 only? ] */
+	if (logical_block_size != MD_SECTOR_SIZE) {
+		mask = (logical_block_size / MD_SECTOR_SIZE) - 1;
+		D_ASSERT(mask == 1 || mask == 3 || mask == 7);
+		D_ASSERT(logical_block_size == (mask+1) * MD_SECTOR_SIZE);
+		offset = sector & mask;
+		sector = sector & ~mask;
+		iop = mdev->md_io_tmpp;
+
+		if (rw & WRITE) {
+			/* these are GFP_KERNEL pages, pre-allocated
+			 * on device initialization */
+			void *p = page_address(mdev->md_io_page);
+			void *hp = page_address(mdev->md_io_tmpp);
+
+			ok = _drbd_md_sync_page_io(mdev, bdev, iop, sector,
+					READ, logical_block_size);
+
+			if (unlikely(!ok)) {
+				dev_err(DEV, "drbd_md_sync_page_io(,%llus,"
+				    "READ [logical_block_size!=512]) failed!\n",
+				    (unsigned long long)sector);
+				return 0;
+			}
+
+			memcpy(hp + offset*MD_SECTOR_SIZE, p, MD_SECTOR_SIZE);
+		}
+	}
+
+	if (sector < drbd_md_first_sector(bdev) ||
+	    sector > drbd_md_last_sector(bdev))
+		dev_alert(DEV, "%s [%d]:%s(,%llus,%s) out of range md access!\n",
+		     current->comm, current->pid, __func__,
+		     (unsigned long long)sector, (rw & WRITE) ? "WRITE" : "READ");
+
+	ok = _drbd_md_sync_page_io(mdev, bdev, iop, sector, rw, logical_block_size);
+	if (unlikely(!ok)) {
+		dev_err(DEV, "drbd_md_sync_page_io(,%llus,%s) failed!\n",
+		    (unsigned long long)sector, (rw & WRITE) ? "WRITE" : "READ");
+		return 0;
+	}
+
+	if (logical_block_size != MD_SECTOR_SIZE && !(rw & WRITE)) {
+		void *p = page_address(mdev->md_io_page);
+		void *hp = page_address(mdev->md_io_tmpp);
+
+		memcpy(p, hp + offset*MD_SECTOR_SIZE, MD_SECTOR_SIZE);
+	}
+
+	return ok;
+}
+
+static struct lc_element *_al_get(struct drbd_conf *mdev, unsigned int enr)
+{
+	struct lc_element *al_ext;
+	struct lc_element *tmp;
+	unsigned long     al_flags = 0;
+
+	spin_lock_irq(&mdev->al_lock);
+	tmp = lc_find(mdev->resync, enr/AL_EXT_PER_BM_SECT);
+	if (unlikely(tmp != NULL)) {
+		struct bm_extent  *bm_ext = lc_entry(tmp, struct bm_extent, lce);
+		if (test_bit(BME_NO_WRITES, &bm_ext->flags)) {
+			spin_unlock_irq(&mdev->al_lock);
+			return NULL;
+		}
+	}
+	al_ext   = lc_get(mdev->act_log, enr);
+	al_flags = mdev->act_log->flags;
+	spin_unlock_irq(&mdev->al_lock);
+
+	/*
+	if (!al_ext) {
+		if (al_flags & LC_STARVING)
+			dev_warn(DEV, "Have to wait for LRU element (AL too small?)\n");
+		if (al_flags & LC_DIRTY)
+			dev_warn(DEV, "Ongoing AL update (AL device too slow?)\n");
+	}
+	*/
+
+	return al_ext;
+}
+
+void drbd_al_begin_io(struct drbd_conf *mdev, sector_t sector)
+{
+	unsigned int enr = (sector >> (AL_EXTENT_SHIFT-9));
+	struct lc_element *al_ext;
+	struct update_al_work al_work;
+
+	D_ASSERT(atomic_read(&mdev->local_cnt) > 0);
+
+	trace_drbd_actlog(mdev, sector, "al_begin_io");
+
+	wait_event(mdev->al_wait, (al_ext = _al_get(mdev, enr)));
+
+	if (al_ext->lc_number != enr) {
+		/* drbd_al_write_transaction(mdev,al_ext,enr);
+		 * recurses into generic_make_request(), which
+		 * disallows recursion, bios being serialized on the
+		 * current->bio_tail list now.
+		 * we have to delegate updates to the activity log
+		 * to the worker thread. */
+		init_completion(&al_work.event);
+		al_work.al_ext = al_ext;
+		al_work.enr = enr;
+		al_work.old_enr = al_ext->lc_number;
+		al_work.w.cb = w_al_write_transaction;
+		drbd_queue_work_front(&mdev->data.work, &al_work.w);
+		wait_for_completion(&al_work.event);
+
+		mdev->al_writ_cnt++;
+
+		spin_lock_irq(&mdev->al_lock);
+		lc_changed(mdev->act_log, al_ext);
+		spin_unlock_irq(&mdev->al_lock);
+		wake_up(&mdev->al_wait);
+	}
+}
+
+void drbd_al_complete_io(struct drbd_conf *mdev, sector_t sector)
+{
+	unsigned int enr = (sector >> (AL_EXTENT_SHIFT-9));
+	struct lc_element *extent;
+	unsigned long flags;
+
+	trace_drbd_actlog(mdev, sector, "al_complete_io");
+
+	spin_lock_irqsave(&mdev->al_lock, flags);
+
+	extent = lc_find(mdev->act_log, enr);
+
+	if (!extent) {
+		spin_unlock_irqrestore(&mdev->al_lock, flags);
+		dev_err(DEV, "al_complete_io() called on inactive extent %u\n", enr);
+		return;
+	}
+
+	if (lc_put(mdev->act_log, extent) == 0)
+		wake_up(&mdev->al_wait);
+
+	spin_unlock_irqrestore(&mdev->al_lock, flags);
+}
+
+int
+w_al_write_transaction(struct drbd_conf *mdev, struct drbd_work *w, int unused)
+{
+	struct update_al_work *aw = container_of(w, struct update_al_work, w);
+	struct lc_element *updated = aw->al_ext;
+	const unsigned int new_enr = aw->enr;
+	const unsigned int evicted = aw->old_enr;
+	struct al_transaction *buffer;
+	sector_t sector;
+	int i, n, mx;
+	unsigned int extent_nr;
+	u32 xor_sum = 0;
+
+	if (!get_ldev(mdev)) {
+		dev_err(DEV, "get_ldev() failed in w_al_write_transaction\n");
+		complete(&((struct update_al_work *)w)->event);
+		return 1;
+	}
+	/* do we have to do a bitmap write, first?
+	 * TODO reduce maximum latency:
+	 * submit both bios, then wait for both,
+	 * instead of doing two synchronous sector writes. */
+	if (mdev->state.conn < C_CONNECTED && evicted != LC_FREE)
+		drbd_bm_write_sect(mdev, evicted/AL_EXT_PER_BM_SECT);
+
+	mutex_lock(&mdev->md_io_mutex); /* protects md_io_page, al_tr_cycle, ... */
+	buffer = (struct al_transaction *)page_address(mdev->md_io_page);
+
+	buffer->magic = __constant_cpu_to_be32(DRBD_MAGIC);
+	buffer->tr_number = cpu_to_be32(mdev->al_tr_number);
+
+	n = lc_index_of(mdev->act_log, updated);
+
+	buffer->updates[0].pos = cpu_to_be32(n);
+	buffer->updates[0].extent = cpu_to_be32(new_enr);
+
+	xor_sum ^= new_enr;
+
+	mx = min_t(int, AL_EXTENTS_PT,
+		   mdev->act_log->nr_elements - mdev->al_tr_cycle);
+	for (i = 0; i < mx; i++) {
+		unsigned idx = mdev->al_tr_cycle + i;
+		extent_nr = lc_element_by_index(mdev->act_log, idx)->lc_number;
+		buffer->updates[i+1].pos = cpu_to_be32(idx);
+		buffer->updates[i+1].extent = cpu_to_be32(extent_nr);
+		xor_sum ^= extent_nr;
+	}
+	for (; i < AL_EXTENTS_PT; i++) {
+		buffer->updates[i+1].pos = __constant_cpu_to_be32(-1);
+		buffer->updates[i+1].extent = __constant_cpu_to_be32(LC_FREE);
+		xor_sum ^= LC_FREE;
+	}
+	mdev->al_tr_cycle += AL_EXTENTS_PT;
+	if (mdev->al_tr_cycle >= mdev->act_log->nr_elements)
+		mdev->al_tr_cycle = 0;
+
+	buffer->xor_sum = cpu_to_be32(xor_sum);
+
+	sector =  mdev->ldev->md.md_offset
+		+ mdev->ldev->md.al_offset + mdev->al_tr_pos;
+
+	if (!drbd_md_sync_page_io(mdev, mdev->ldev, sector, WRITE))
+		drbd_chk_io_error(mdev, 1, TRUE);
+
+	if (++mdev->al_tr_pos >
+	    div_ceil(mdev->act_log->nr_elements, AL_EXTENTS_PT))
+		mdev->al_tr_pos = 0;
+
+	D_ASSERT(mdev->al_tr_pos < MD_AL_MAX_SIZE);
+	mdev->al_tr_number++;
+
+	mutex_unlock(&mdev->md_io_mutex);
+
+	complete(&((struct update_al_work *)w)->event);
+	put_ldev(mdev);
+
+	return 1;
+}
+
+/**
+ * drbd_al_read_tr() - Read a single transaction from the on disk activity log
+ * @mdev:	DRBD device.
+ * @bdev:	Block device to read form.
+ * @b:		pointer to an al_transaction.
+ * @index:	On disk slot of the transaction to read.
+ *
+ * Returns -1 on IO error, 0 on checksum error and 1 upon success.
+ */
+static int drbd_al_read_tr(struct drbd_conf *mdev,
+			   struct drbd_backing_dev *bdev,
+			   struct al_transaction *b,
+			   int index)
+{
+	sector_t sector;
+	int rv, i;
+	u32 xor_sum = 0;
+
+	sector = bdev->md.md_offset + bdev->md.al_offset + index;
+
+	/* Dont process error normally,
+	 * as this is done before disk is attached! */
+	if (!drbd_md_sync_page_io(mdev, bdev, sector, READ))
+		return -1;
+
+	rv = (be32_to_cpu(b->magic) == DRBD_MAGIC);
+
+	for (i = 0; i < AL_EXTENTS_PT + 1; i++)
+		xor_sum ^= be32_to_cpu(b->updates[i].extent);
+	rv &= (xor_sum == be32_to_cpu(b->xor_sum));
+
+	return rv;
+}
+
+/**
+ * drbd_al_read_log() - Restores the activity log from its on disk representation.
+ * @mdev:	DRBD device.
+ * @bdev:	Block device to read form.
+ *
+ * Returns 1 on success, returns 0 when reading the log failed due to IO errors.
+ */
+int drbd_al_read_log(struct drbd_conf *mdev, struct drbd_backing_dev *bdev)
+{
+	struct al_transaction *buffer;
+	int i;
+	int rv;
+	int mx;
+	int active_extents = 0;
+	int transactions = 0;
+	int found_valid = 0;
+	int from = 0;
+	int to = 0;
+	u32 from_tnr = 0;
+	u32 to_tnr = 0;
+	u32 cnr;
+
+	mx = div_ceil(mdev->act_log->nr_elements, AL_EXTENTS_PT);
+
+	/* lock out all other meta data io for now,
+	 * and make sure the page is mapped.
+	 */
+	mutex_lock(&mdev->md_io_mutex);
+	buffer = page_address(mdev->md_io_page);
+
+	/* Find the valid transaction in the log */
+	for (i = 0; i <= mx; i++) {
+		rv = drbd_al_read_tr(mdev, bdev, buffer, i);
+		if (rv == 0)
+			continue;
+		if (rv == -1) {
+			mutex_unlock(&mdev->md_io_mutex);
+			return 0;
+		}
+		cnr = be32_to_cpu(buffer->tr_number);
+
+		if (++found_valid == 1) {
+			from = i;
+			to = i;
+			from_tnr = cnr;
+			to_tnr = cnr;
+			continue;
+		}
+		if ((int)cnr - (int)from_tnr < 0) {
+			D_ASSERT(from_tnr - cnr + i - from == mx+1);
+			from = i;
+			from_tnr = cnr;
+		}
+		if ((int)cnr - (int)to_tnr > 0) {
+			D_ASSERT(cnr - to_tnr == i - to);
+			to = i;
+			to_tnr = cnr;
+		}
+	}
+
+	if (!found_valid) {
+		dev_warn(DEV, "No usable activity log found.\n");
+		mutex_unlock(&mdev->md_io_mutex);
+		return 1;
+	}
+
+	/* Read the valid transactions.
+	 * dev_info(DEV, "Reading from %d to %d.\n",from,to); */
+	i = from;
+	while (1) {
+		int j, pos;
+		unsigned int extent_nr;
+		unsigned int trn;
+
+		rv = drbd_al_read_tr(mdev, bdev, buffer, i);
+		ERR_IF(rv == 0) goto cancel;
+		if (rv == -1) {
+			mutex_unlock(&mdev->md_io_mutex);
+			return 0;
+		}
+
+		trn = be32_to_cpu(buffer->tr_number);
+
+		spin_lock_irq(&mdev->al_lock);
+
+		/* This loop runs backwards because in the cyclic
+		   elements there might be an old version of the
+		   updated element (in slot 0). So the element in slot 0
+		   can overwrite old versions. */
+		for (j = AL_EXTENTS_PT; j >= 0; j--) {
+			pos = be32_to_cpu(buffer->updates[j].pos);
+			extent_nr = be32_to_cpu(buffer->updates[j].extent);
+
+			if (extent_nr == LC_FREE)
+				continue;
+
+			lc_set(mdev->act_log, extent_nr, pos);
+			active_extents++;
+		}
+		spin_unlock_irq(&mdev->al_lock);
+
+		transactions++;
+
+cancel:
+		if (i == to)
+			break;
+		i++;
+		if (i > mx)
+			i = 0;
+	}
+
+	mdev->al_tr_number = to_tnr+1;
+	mdev->al_tr_pos = to;
+	if (++mdev->al_tr_pos >
+	    div_ceil(mdev->act_log->nr_elements, AL_EXTENTS_PT))
+		mdev->al_tr_pos = 0;
+
+	/* ok, we are done with it */
+	mutex_unlock(&mdev->md_io_mutex);
+
+	dev_info(DEV, "Found %d transactions (%d active extents) in activity log.\n",
+	     transactions, active_extents);
+
+	return 1;
+}
+
+static void atodb_endio(struct bio *bio, int error)
+{
+	struct drbd_atodb_wait *wc = bio->bi_private;
+	struct drbd_conf *mdev = wc->mdev;
+	struct page *page;
+	int uptodate = bio_flagged(bio, BIO_UPTODATE);
+
+	/* strange behavior of some lower level drivers...
+	 * fail the request by clearing the uptodate flag,
+	 * but do not return any error?! */
+	if (!error && !uptodate)
+		error = -EIO;
+
+	drbd_chk_io_error(mdev, error, TRUE);
+	if (error && wc->error == 0)
+		wc->error = error;
+
+	if (atomic_dec_and_test(&wc->count))
+		complete(&wc->io_done);
+
+	page = bio->bi_io_vec[0].bv_page;
+	put_page(page);
+	bio_put(bio);
+	mdev->bm_writ_cnt++;
+	put_ldev(mdev);
+}
+
+#define S2W(s)	((s)<<(BM_EXT_SHIFT-BM_BLOCK_SHIFT-LN2_BPL))
+/* activity log to on disk bitmap -- prepare bio unless that sector
+ * is already covered by previously prepared bios */
+static int atodb_prepare_unless_covered(struct drbd_conf *mdev,
+					struct bio **bios,
+					unsigned int enr,
+					struct drbd_atodb_wait *wc) __must_hold(local)
+{
+	struct bio *bio;
+	struct page *page;
+	sector_t on_disk_sector = enr + mdev->ldev->md.md_offset
+				      + mdev->ldev->md.bm_offset;
+	unsigned int page_offset = PAGE_SIZE;
+	int offset;
+	int i = 0;
+	int err = -ENOMEM;
+
+	/* Check if that enr is already covered by an already created bio.
+	 * Caution, bios[] is not NULL terminated,
+	 * but only initialized to all NULL.
+	 * For completely scattered activity log,
+	 * the last invocation iterates over all bios,
+	 * and finds the last NULL entry.
+	 */
+	while ((bio = bios[i])) {
+		if (bio->bi_sector == on_disk_sector)
+			return 0;
+		i++;
+	}
+	/* bios[i] == NULL, the next not yet used slot */
+
+	/* GFP_KERNEL, we are not in the write-out path */
+	bio = bio_alloc(GFP_KERNEL, 1);
+	if (bio == NULL)
+		return -ENOMEM;
+
+	if (i > 0) {
+		const struct bio_vec *prev_bv = bios[i-1]->bi_io_vec;
+		page_offset = prev_bv->bv_offset + prev_bv->bv_len;
+		page = prev_bv->bv_page;
+	}
+	if (page_offset == PAGE_SIZE) {
+		page = alloc_page(__GFP_HIGHMEM);
+		if (page == NULL)
+			goto out_bio_put;
+		page_offset = 0;
+	} else {
+		get_page(page);
+	}
+
+	offset = S2W(enr);
+	drbd_bm_get_lel(mdev, offset,
+			min_t(size_t, S2W(1), drbd_bm_words(mdev) - offset),
+			kmap(page) + page_offset);
+	kunmap(page);
+
+	bio->bi_private = wc;
+	bio->bi_end_io = atodb_endio;
+	bio->bi_bdev = mdev->ldev->md_bdev;
+	bio->bi_sector = on_disk_sector;
+
+	if (bio_add_page(bio, page, MD_SECTOR_SIZE, page_offset) != MD_SECTOR_SIZE)
+		goto out_put_page;
+
+	atomic_inc(&wc->count);
+	/* we already know that we may do this...
+	 * get_ldev_if_state(mdev,D_ATTACHING);
+	 * just get the extra reference, so that the local_cnt reflects
+	 * the number of pending IO requests DRBD at its backing device.
+	 */
+	atomic_inc(&mdev->local_cnt);
+
+	bios[i] = bio;
+
+	return 0;
+
+out_put_page:
+	err = -EINVAL;
+	put_page(page);
+out_bio_put:
+	bio_put(bio);
+	return err;
+}
+
+/**
+ * drbd_al_to_on_disk_bm() -  * Writes bitmap parts covered by active AL extents
+ * @mdev:	DRBD device.
+ *
+ * Called when we detach (unconfigure) local storage,
+ * or when we go from R_PRIMARY to R_SECONDARY role.
+ */
+void drbd_al_to_on_disk_bm(struct drbd_conf *mdev)
+{
+	int i, nr_elements;
+	unsigned int enr;
+	struct bio **bios;
+	struct drbd_atodb_wait wc;
+
+	ERR_IF (!get_ldev_if_state(mdev, D_ATTACHING))
+		return; /* sorry, I don't have any act_log etc... */
+
+	wait_event(mdev->al_wait, lc_try_lock(mdev->act_log));
+
+	nr_elements = mdev->act_log->nr_elements;
+
+	/* GFP_KERNEL, we are not in anyone's write-out path */
+	bios = kzalloc(sizeof(struct bio *) * nr_elements, GFP_KERNEL);
+	if (!bios)
+		goto submit_one_by_one;
+
+	atomic_set(&wc.count, 0);
+	init_completion(&wc.io_done);
+	wc.mdev = mdev;
+	wc.error = 0;
+
+	for (i = 0; i < nr_elements; i++) {
+		enr = lc_element_by_index(mdev->act_log, i)->lc_number;
+		if (enr == LC_FREE)
+			continue;
+		/* next statement also does atomic_inc wc.count and local_cnt */
+		if (atodb_prepare_unless_covered(mdev, bios,
+						enr/AL_EXT_PER_BM_SECT,
+						&wc))
+			goto free_bios_submit_one_by_one;
+	}
+
+	/* unnecessary optimization? */
+	lc_unlock(mdev->act_log);
+	wake_up(&mdev->al_wait);
+
+	/* all prepared, submit them */
+	for (i = 0; i < nr_elements; i++) {
+		if (bios[i] == NULL)
+			break;
+		if (FAULT_ACTIVE(mdev, DRBD_FAULT_MD_WR)) {
+			bios[i]->bi_rw = WRITE;
+			bio_endio(bios[i], -EIO);
+		} else {
+			submit_bio(WRITE, bios[i]);
+		}
+	}
+
+	drbd_blk_run_queue(bdev_get_queue(mdev->ldev->md_bdev));
+
+	/* always (try to) flush bitmap to stable storage */
+	drbd_md_flush(mdev);
+
+	/* In case we did not submit a single IO do not wait for
+	 * them to complete. ( Because we would wait forever here. )
+	 *
+	 * In case we had IOs and they are already complete, there
+	 * is not point in waiting anyways.
+	 * Therefore this if () ... */
+	if (atomic_read(&wc.count))
+		wait_for_completion(&wc.io_done);
+
+	put_ldev(mdev);
+
+	kfree(bios);
+	return;
+
+ free_bios_submit_one_by_one:
+	/* free everything by calling the endio callback directly. */
+	for (i = 0; i < nr_elements && bios[i]; i++)
+		bio_endio(bios[i], 0);
+
+	kfree(bios);
+
+ submit_one_by_one:
+	dev_warn(DEV, "Using the slow drbd_al_to_on_disk_bm()\n");
+
+	for (i = 0; i < mdev->act_log->nr_elements; i++) {
+		enr = lc_element_by_index(mdev->act_log, i)->lc_number;
+		if (enr == LC_FREE)
+			continue;
+		/* Really slow: if we have al-extents 16..19 active,
+		 * sector 4 will be written four times! Synchronous! */
+		drbd_bm_write_sect(mdev, enr/AL_EXT_PER_BM_SECT);
+	}
+
+	lc_unlock(mdev->act_log);
+	wake_up(&mdev->al_wait);
+	put_ldev(mdev);
+}
+
+/**
+ * drbd_al_apply_to_bm() - Sets the bitmap to diry(1) where covered ba active AL extents
+ * @mdev:	DRBD device.
+ */
+void drbd_al_apply_to_bm(struct drbd_conf *mdev)
+{
+	unsigned int enr;
+	unsigned long add = 0;
+	char ppb[10];
+	int i;
+
+	wait_event(mdev->al_wait, lc_try_lock(mdev->act_log));
+
+	for (i = 0; i < mdev->act_log->nr_elements; i++) {
+		enr = lc_element_by_index(mdev->act_log, i)->lc_number;
+		if (enr == LC_FREE)
+			continue;
+		add += drbd_bm_ALe_set_all(mdev, enr);
+	}
+
+	lc_unlock(mdev->act_log);
+	wake_up(&mdev->al_wait);
+
+	dev_info(DEV, "Marked additional %s as out-of-sync based on AL.\n",
+	     ppsize(ppb, Bit2KB(add)));
+}
+
+static int _try_lc_del(struct drbd_conf *mdev, struct lc_element *al_ext)
+{
+	int rv;
+
+	spin_lock_irq(&mdev->al_lock);
+	rv = (al_ext->refcnt == 0);
+	if (likely(rv))
+		lc_del(mdev->act_log, al_ext);
+	spin_unlock_irq(&mdev->al_lock);
+
+	return rv;
+}
+
+/**
+ * drbd_al_shrink() - Removes all active extents form the activity log
+ * @mdev:	DRBD device.
+ *
+ * Removes all active extents form the activity log, waiting until
+ * the reference count of each entry dropped to 0 first, of course.
+ *
+ * You need to lock mdev->act_log with lc_try_lock() / lc_unlock()
+ */
+void drbd_al_shrink(struct drbd_conf *mdev)
+{
+	struct lc_element *al_ext;
+	int i;
+
+	D_ASSERT(test_bit(__LC_DIRTY, &mdev->act_log->flags));
+
+	for (i = 0; i < mdev->act_log->nr_elements; i++) {
+		al_ext = lc_element_by_index(mdev->act_log, i);
+		if (al_ext->lc_number == LC_FREE)
+			continue;
+		wait_event(mdev->al_wait, _try_lc_del(mdev, al_ext));
+	}
+
+	wake_up(&mdev->al_wait);
+}
+
+static int w_update_odbm(struct drbd_conf *mdev, struct drbd_work *w, int unused)
+{
+	struct update_odbm_work *udw = container_of(w, struct update_odbm_work, w);
+
+	if (!get_ldev(mdev)) {
+		if (__ratelimit(&drbd_ratelimit_state))
+			dev_warn(DEV, "Can not update on disk bitmap, local IO disabled.\n");
+		kfree(udw);
+		return 1;
+	}
+
+	drbd_bm_write_sect(mdev, udw->enr);
+	put_ldev(mdev);
+
+	kfree(udw);
+
+	if (drbd_bm_total_weight(mdev) <= mdev->rs_failed) {
+		switch (mdev->state.conn) {
+		case C_SYNC_SOURCE:  case C_SYNC_TARGET:
+		case C_PAUSED_SYNC_S: case C_PAUSED_SYNC_T:
+			drbd_resync_finished(mdev);
+		default:
+			/* nothing to do */
+			break;
+		}
+	}
+	drbd_bcast_sync_progress(mdev);
+
+	return 1;
+}
+
+
+/* ATTENTION. The AL's extents are 4MB each, while the extents in the
+ * resync LRU-cache are 16MB each.
+ * The caller of this function has to hold an get_ldev() reference.
+ *
+ * TODO will be obsoleted once we have a caching lru of the on disk bitmap
+ */
+static void drbd_try_clear_on_disk_bm(struct drbd_conf *mdev, sector_t sector,
+				      int count, int success)
+{
+	struct lc_element *e;
+	struct update_odbm_work *udw;
+
+	unsigned int enr;
+
+	D_ASSERT(atomic_read(&mdev->local_cnt));
+
+	/* I simply assume that a sector/size pair never crosses
+	 * a 16 MB extent border. (Currently this is true...) */
+	enr = BM_SECT_TO_EXT(sector);
+
+	e = lc_get(mdev->resync, enr);
+	if (e) {
+		struct bm_extent *ext = lc_entry(e, struct bm_extent,