Merge branch 'for-linus' of git://git.kernel.dk/linux-2.6-block

* 'for-linus' of git://git.kernel.dk/linux-2.6-block: (34 commits)
  cfq-iosched: Fix the incorrect timeslice accounting with forced_dispatch
  loop: Update mtime when writing using aops
  block: expose the statistics in blkio.time and blkio.sectors for the root cgroup
  backing-dev: Handle class_create() failure
  Block: Fix block/elevator.c elevator_get() off-by-one error
  drbd: lc_element_by_index() never returns NULL
  cciss: unlock on error path
  cfq-iosched: Do not merge queues of BE and IDLE classes
  cfq-iosched: Add additional blktrace log messages in CFQ for easier debugging
  i2o: Remove the dangerous kobj_to_i2o_device macro
  block: remove 16 bytes of padding from struct request on 64bits
  cfq-iosched: fix a kbuild regression
  block: make CONFIG_BLK_CGROUP visible
  Remove GENHD_FL_DRIVERFS
  block: Export max number of segments and max segment size in sysfs
  block: Finalize conversion of block limits functions
  block: Fix overrun in lcm() and move it to lib
  vfs: improve writeback_inodes_wb()
  paride: fix off-by-one test
  drbd: fix al-to-on-disk-bitmap for 4k logical_block_size
  ...

34 files changed, 475 insertions, 178 deletions

diff --git a/Documentation/DocBook/tracepoint.tmpl b/Documentation/DocBook/tracepoint.tmpl
index 8bca1d5cec0..e8473eae2a2 100644
--- a/Documentation/DocBook/tracepoint.tmpl
+++ b/Documentation/DocBook/tracepoint.tmpl
@@ -16,6 +16,15 @@
      </address>
     </affiliation>
    </author>
+   <author>
+    <firstname>William</firstname>
+    <surname>Cohen</surname>
+    <affiliation>
+     <address>
+      <email>wcohen@redhat.com</email>
+     </address>
+    </affiliation>
+   </author>
   </authorgroup>
 
   <legalnotice>
@@ -91,4 +100,8 @@
 !Iinclude/trace/events/signal.h
   </chapter>
 
+  <chapter id="block">
+   <title>Block IO</title>
+!Iinclude/trace/events/block.h
+  </chapter>
 </book>
diff --git a/Documentation/block/biodoc.txt b/Documentation/block/biodoc.txt
index 6fab97ea7e6..508b5b2b028 100644
--- a/Documentation/block/biodoc.txt
+++ b/Documentation/block/biodoc.txt
@@ -1162,8 +1162,8 @@ where a driver received a request ala this before:
 
 As mentioned, there is no virtual mapping of a bio. For DMA, this is
 not a problem as the driver probably never will need a virtual mapping.
-Instead it needs a bus mapping (pci_map_page for a single segment or
-use blk_rq_map_sg for scatter gather) to be able to ship it to the driver. For
+Instead it needs a bus mapping (dma_map_page for a single segment or
+use dma_map_sg for scatter gather) to be able to ship it to the driver. For
 PIO drivers (or drivers that need to revert to PIO transfer once in a
 while (IDE for example)), where the CPU is doing the actual data
 transfer a virtual mapping is needed. If the driver supports highmem I/O,
diff --git a/block/Kconfig b/block/Kconfig
index 62a5921321c..f9e89f4d94b 100644
--- a/block/Kconfig
+++ b/block/Kconfig
@@ -78,8 +78,9 @@ config BLK_DEV_INTEGRITY
 	Protection.  If in doubt, say N.
 
 config BLK_CGROUP
-	tristate
+	tristate "Block cgroup support"
 	depends on CGROUPS
+	depends on CFQ_GROUP_IOSCHED
 	default n
 	---help---
 	Generic block IO controller cgroup interface. This is the common
diff --git a/block/blk-settings.c b/block/blk-settings.c
index d9a9db5f0a2..f5ed5a1187b 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -8,6 +8,7 @@
 #include <linux/blkdev.h>
 #include <linux/bootmem.h>	/* for max_pfn/max_low_pfn */
 #include <linux/gcd.h>
+#include <linux/lcm.h>
 #include <linux/jiffies.h>
 #include <linux/gfp.h>
 
@@ -462,16 +463,6 @@ void blk_queue_stack_limits(struct request_queue *t, struct request_queue *b)
 }
 EXPORT_SYMBOL(blk_queue_stack_limits);
 
-static unsigned int lcm(unsigned int a, unsigned int b)
-{
-	if (a && b)
-		return (a * b) / gcd(a, b);
-	else if (b)
-		return b;
-
-	return a;
-}
-
 /**
  * blk_stack_limits - adjust queue_limits for stacked devices
  * @t:	the stacking driver limits (top device)
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index c2b821fa324..306759bbdf1 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -107,6 +107,19 @@ static ssize_t queue_max_sectors_show(struct request_queue *q, char *page)
 	return queue_var_show(max_sectors_kb, (page));
 }
 
+static ssize_t queue_max_segments_show(struct request_queue *q, char *page)
+{
+	return queue_var_show(queue_max_segments(q), (page));
+}
+
+static ssize_t queue_max_segment_size_show(struct request_queue *q, char *page)
+{
+	if (test_bit(QUEUE_FLAG_CLUSTER, &q->queue_flags))
+		return queue_var_show(queue_max_segment_size(q), (page));
+
+	return queue_var_show(PAGE_CACHE_SIZE, (page));
+}
+
 static ssize_t queue_logical_block_size_show(struct request_queue *q, char *page)
 {
 	return queue_var_show(queue_logical_block_size(q), page);
@@ -281,6 +294,16 @@ static struct queue_sysfs_entry queue_max_hw_sectors_entry = {
 	.show = queue_max_hw_sectors_show,
 };
 
+static struct queue_sysfs_entry queue_max_segments_entry = {
+	.attr = {.name = "max_segments", .mode = S_IRUGO },
+	.show = queue_max_segments_show,
+};
+
+static struct queue_sysfs_entry queue_max_segment_size_entry = {
+	.attr = {.name = "max_segment_size", .mode = S_IRUGO },
+	.show = queue_max_segment_size_show,
+};
+
 static struct queue_sysfs_entry queue_iosched_entry = {
 	.attr = {.name = "scheduler", .mode = S_IRUGO | S_IWUSR },
 	.show = elv_iosched_show,
@@ -356,6 +379,8 @@ static struct attribute *default_attrs[] = {
 	&queue_ra_entry.attr,
 	&queue_max_hw_sectors_entry.attr,
 	&queue_max_sectors_entry.attr,
+	&queue_max_segments_entry.attr,
+	&queue_max_segment_size_entry.attr,
 	&queue_iosched_entry.attr,
 	&queue_hw_sector_size_entry.attr,
 	&queue_logical_block_size_entry.attr,
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index fc98a48554f..838834be115 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -48,6 +48,7 @@ static const int cfq_hist_divisor = 4;
 #define CFQ_SERVICE_SHIFT       12
 
 #define CFQQ_SEEK_THR		(sector_t)(8 * 100)
+#define CFQQ_CLOSE_THR		(sector_t)(8 * 1024)
 #define CFQQ_SECT_THR_NONROT	(sector_t)(2 * 32)
 #define CFQQ_SEEKY(cfqq)	(hweight32(cfqq->seek_history) > 32/8)
 
@@ -948,6 +949,11 @@ cfq_find_alloc_cfqg(struct cfq_data *cfqd, struct cgroup *cgroup, int create)
 	unsigned int major, minor;
 
 	cfqg = cfqg_of_blkg(blkiocg_lookup_group(blkcg, key));
+	if (cfqg && !cfqg->blkg.dev && bdi->dev && dev_name(bdi->dev)) {
+		sscanf(dev_name(bdi->dev), "%u:%u", &major, &minor);
+		cfqg->blkg.dev = MKDEV(major, minor);
+		goto done;
+	}
 	if (cfqg || !create)
 		goto done;
 
@@ -1518,7 +1524,8 @@ static void __cfq_set_active_queue(struct cfq_data *cfqd,
 				   struct cfq_queue *cfqq)
 {
 	if (cfqq) {
-		cfq_log_cfqq(cfqd, cfqq, "set_active");
+		cfq_log_cfqq(cfqd, cfqq, "set_active wl_prio:%d wl_type:%d",
+				cfqd->serving_prio, cfqd->serving_type);
 		cfqq->slice_start = 0;
 		cfqq->dispatch_start = jiffies;
 		cfqq->allocated_slice = 0;
@@ -1661,9 +1668,9 @@ static inline sector_t cfq_dist_from_last(struct cfq_data *cfqd,
 }
 
 static inline int cfq_rq_close(struct cfq_data *cfqd, struct cfq_queue *cfqq,
-			       struct request *rq, bool for_preempt)
+			       struct request *rq)
 {
-	return cfq_dist_from_last(cfqd, rq) <= CFQQ_SEEK_THR;
+	return cfq_dist_from_last(cfqd, rq) <= CFQQ_CLOSE_THR;
 }
 
 static struct cfq_queue *cfqq_close(struct cfq_data *cfqd,
@@ -1690,7 +1697,7 @@ static struct cfq_queue *cfqq_close(struct cfq_data *cfqd,
 	 * will contain the closest sector.
 	 */
 	__cfqq = rb_entry(parent, struct cfq_queue, p_node);
-	if (cfq_rq_close(cfqd, cur_cfqq, __cfqq->next_rq, false))
+	if (cfq_rq_close(cfqd, cur_cfqq, __cfqq->next_rq))
 		return __cfqq;
 
 	if (blk_rq_pos(__cfqq->next_rq) < sector)
@@ -1701,7 +1708,7 @@ static struct cfq_queue *cfqq_close(struct cfq_data *cfqd,
 		return NULL;
 
 	__cfqq = rb_entry(node, struct cfq_queue, p_node);
-	if (cfq_rq_close(cfqd, cur_cfqq, __cfqq->next_rq, false))
+	if (cfq_rq_close(cfqd, cur_cfqq, __cfqq->next_rq))
 		return __cfqq;
 
 	return NULL;
@@ -1722,6 +1729,8 @@ static struct cfq_queue *cfq_close_cooperator(struct cfq_data *cfqd,
 {
 	struct cfq_queue *cfqq;
 
+	if (cfq_class_idle(cur_cfqq))
+		return NULL;
 	if (!cfq_cfqq_sync(cur_cfqq))
 		return NULL;
 	if (CFQQ_SEEKY(cur_cfqq))
@@ -1788,7 +1797,11 @@ static bool cfq_should_idle(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 	 * Otherwise, we do only if they are the last ones
 	 * in their service tree.
 	 */
-	return service_tree->count == 1 && cfq_cfqq_sync(cfqq);
+	if (service_tree->count == 1 && cfq_cfqq_sync(cfqq))
+		return 1;
+	cfq_log_cfqq(cfqd, cfqq, "Not idling. st->count:%d",
+			service_tree->count);
+	return 0;
 }
 
 static void cfq_arm_slice_timer(struct cfq_data *cfqd)
@@ -1833,8 +1846,11 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd)
 	 * time slice.
 	 */
 	if (sample_valid(cic->ttime_samples) &&
-	    (cfqq->slice_end - jiffies < cic->ttime_mean))
+	    (cfqq->slice_end - jiffies < cic->ttime_mean)) {
+		cfq_log_cfqq(cfqd, cfqq, "Not idling. think_time:%d",
+				cic->ttime_mean);
 		return;
+	}
 
 	cfq_mark_cfqq_wait_request(cfqq);
 
@@ -2042,6 +2058,7 @@ static void choose_service_tree(struct cfq_data *cfqd, struct cfq_group *cfqg)
 		slice = max(slice, 2 * cfqd->cfq_slice_idle);
 
 	slice = max_t(unsigned, slice, CFQ_MIN_TT);
+	cfq_log(cfqd, "workload slice:%d", slice);
 	cfqd->workload_expires = jiffies + slice;
 	cfqd->noidle_tree_requires_idle = false;
 }
@@ -2189,10 +2206,13 @@ static int cfq_forced_dispatch(struct cfq_data *cfqd)
 	struct cfq_queue *cfqq;
 	int dispatched = 0;
 
-	while ((cfqq = cfq_get_next_queue_forced(cfqd)) != NULL)
+	/* Expire the timeslice of the current active queue first */
+	cfq_slice_expired(cfqd, 0);
+	while ((cfqq = cfq_get_next_queue_forced(cfqd)) != NULL) {
+		__cfq_set_active_queue(cfqd, cfqq);
 		dispatched += __cfq_forced_dispatch_cfqq(cfqq);
+	}
 
-	cfq_slice_expired(cfqd, 0);
 	BUG_ON(cfqd->busy_queues);
 
 	cfq_log(cfqd, "forced_dispatch=%d", dispatched);
@@ -3104,7 +3124,7 @@ cfq_should_preempt(struct cfq_data *cfqd, struct cfq_queue *new_cfqq,
 	 * if this request is as-good as one we would expect from the
 	 * current cfqq, let it preempt
 	 */
-	if (cfq_rq_close(cfqd, cfqq, rq, true))
+	if (cfq_rq_close(cfqd, cfqq, rq))
 		return true;
 
 	return false;
@@ -3308,6 +3328,7 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq)
 		if (cfq_should_wait_busy(cfqd, cfqq)) {
 			cfqq->slice_end = jiffies + cfqd->cfq_slice_idle;
 			cfq_mark_cfqq_wait_busy(cfqq);
+			cfq_log_cfqq(cfqd, cfqq, "will busy wait");
 		}
 
 		/*
diff --git a/block/elevator.c b/block/elevator.c
index df75676f667..76e3702d538 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -154,7 +154,7 @@ static struct elevator_type *elevator_get(const char *name)
 
 		spin_unlock(&elv_list_lock);
 
-		sprintf(elv, "%s-iosched", name);
+		snprintf(elv, sizeof(elv), "%s-iosched", name);
 
 		request_module("%s", elv);
 		spin_lock(&elv_list_lock);
diff --git a/drivers/block/DAC960.c b/drivers/block/DAC960.c
index 459f1bc25a7..c5f22bb0a48 100644
--- a/drivers/block/DAC960.c
+++ b/drivers/block/DAC960.c
@@ -2533,7 +2533,6 @@ static bool DAC960_RegisterBlockDevice(DAC960_Controller_T *Controller)
   	Controller->RequestQueue[n] = RequestQueue;
   	blk_queue_bounce_limit(RequestQueue, Controller->BounceBufferLimit);
   	RequestQueue->queuedata = Controller;
-  	blk_queue_max_hw_segments(RequestQueue, Controller->DriverScatterGatherLimit);
 	blk_queue_max_segments(RequestQueue, Controller->DriverScatterGatherLimit);
 	blk_queue_max_hw_sectors(RequestQueue, Controller->MaxBlocksPerCommand);
 	disk->queue = RequestQueue;
diff --git a/drivers/block/drbd/drbd_actlog.c b/drivers/block/drbd/drbd_actlog.c
index 17956ff6a08..df018990c42 100644
--- a/drivers/block/drbd/drbd_actlog.c
+++ b/drivers/block/drbd/drbd_actlog.c
@@ -536,7 +536,9 @@ static void atodb_endio(struct bio *bio, int error)
 	put_ldev(mdev);
 }
 
+/* sector to word */
 #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,
@@ -546,13 +548,20 @@ static int atodb_prepare_unless_covered(struct drbd_conf *mdev,
 {
 	struct bio *bio;
 	struct page *page;
-	sector_t on_disk_sector = enr + mdev->ldev->md.md_offset
-				      + mdev->ldev->md.bm_offset;
+	sector_t on_disk_sector;
 	unsigned int page_offset = PAGE_SIZE;
 	int offset;
 	int i = 0;
 	int err = -ENOMEM;
 
+	/* We always write aligned, full 4k blocks,
+	 * so we can ignore the logical_block_size (for now) */
+	enr &= ~7U;
+	on_disk_sector = enr + mdev->ldev->md.md_offset
+			     + mdev->ldev->md.bm_offset;
+
+	D_ASSERT(!(on_disk_sector & 7U));
+
 	/* Check if that enr is already covered by an already created bio.
 	 * Caution, bios[] is not NULL terminated,
 	 * but only initialized to all NULL.
@@ -588,7 +597,7 @@ static int atodb_prepare_unless_covered(struct drbd_conf *mdev,
 
 	offset = S2W(enr);
 	drbd_bm_get_lel(mdev, offset,
-			min_t(size_t, S2W(1), drbd_bm_words(mdev) - offset),
+			min_t(size_t, S2W(8), drbd_bm_words(mdev) - offset),
 			kmap(page) + page_offset);
 	kunmap(page);
 
@@ -597,7 +606,7 @@ static int atodb_prepare_unless_covered(struct drbd_conf *mdev,
 	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)
+	if (bio_add_page(bio, page, 4096, page_offset) != 4096)
 		goto out_put_page;
 
 	atomic_inc(&wc->count);
@@ -1327,7 +1336,7 @@ int drbd_rs_del_all(struct drbd_conf *mdev)
 		/* ok, ->resync is there. */
 		for (i = 0; i < mdev->resync->nr_elements; i++) {
 			e = lc_element_by_index(mdev->resync, i);
-			bm_ext = e ? lc_entry(e, struct bm_extent, lce) : NULL;
+			bm_ext = lc_entry(e, struct bm_extent, lce);
 			if (bm_ext->lce.lc_number == LC_FREE)
 				continue;
 			if (bm_ext->lce.lc_number == mdev->resync_wenr) {
diff --git a/drivers/block/drbd/drbd_bitmap.c b/drivers/block/drbd/drbd_bitmap.c
index 3d6f3d98894..3390716898d 100644
--- a/drivers/block/drbd/drbd_bitmap.c
+++ b/drivers/block/drbd/drbd_bitmap.c
@@ -67,7 +67,7 @@ struct drbd_bitmap {
 	size_t   bm_words;
 	size_t   bm_number_of_pages;
 	sector_t bm_dev_capacity;
-	struct semaphore bm_change; /* serializes resize operations */
+	struct mutex bm_change; /* serializes resize operations */
 
 	atomic_t bm_async_io;
 	wait_queue_head_t bm_io_wait;
@@ -115,7 +115,7 @@ void drbd_bm_lock(struct drbd_conf *mdev, char *why)
 		return;
 	}
 
-	trylock_failed = down_trylock(&b->bm_change);
+	trylock_failed = !mutex_trylock(&b->bm_change);
 
 	if (trylock_failed) {
 		dev_warn(DEV, "%s going to '%s' but bitmap already locked for '%s' by %s\n",
@@ -126,7 +126,7 @@ void drbd_bm_lock(struct drbd_conf *mdev, char *why)
 		    b->bm_task == mdev->receiver.task ? "receiver" :
 		    b->bm_task == mdev->asender.task  ? "asender"  :
 		    b->bm_task == mdev->worker.task   ? "worker"   : "?");
-		down(&b->bm_change);
+		mutex_lock(&b->bm_change);
 	}
 	if (__test_and_set_bit(BM_LOCKED, &b->bm_flags))
 		dev_err(DEV, "FIXME bitmap already locked in bm_lock\n");
@@ -148,7 +148,7 @@ void drbd_bm_unlock(struct drbd_conf *mdev)
 
 	b->bm_why  = NULL;
 	b->bm_task = NULL;
-	up(&b->bm_change);
+	mutex_unlock(&b->bm_change);
 }
 
 /* word offset to long pointer */
@@ -296,7 +296,7 @@ int drbd_bm_init(struct drbd_conf *mdev)
 	if (!b)
 		return -ENOMEM;
 	spin_lock_init(&b->bm_lock);
-	init_MUTEX(&b->bm_change);
+	mutex_init(&b->bm_change);
 	init_waitqueue_head(&b->bm_io_wait);
 
 	mdev->bitmap = b;
diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index d9301e861d9..e5e86a78182 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -261,6 +261,9 @@ static inline const char *cmdname(enum drbd_packets cmd)
 		[P_OV_REQUEST]          = "OVRequest",
 		[P_OV_REPLY]            = "OVReply",
 		[P_OV_RESULT]           = "OVResult",
+		[P_CSUM_RS_REQUEST]     = "CsumRSRequest",
+		[P_RS_IS_IN_SYNC]	= "CsumRSIsInSync",
+		[P_COMPRESSED_BITMAP]   = "CBitmap",
 		[P_MAX_CMD]	        = NULL,
 	};
 
@@ -443,13 +446,18 @@ struct p_rs_param_89 {
 	char csums_alg[SHARED_SECRET_MAX];
 } __packed;
 
+enum drbd_conn_flags {
+	CF_WANT_LOSE = 1,
+	CF_DRY_RUN = 2,
+};
+
 struct p_protocol {
 	struct p_header head;
 	u32 protocol;
 	u32 after_sb_0p;
 	u32 after_sb_1p;
 	u32 after_sb_2p;
-	u32 want_lose;
+	u32 conn_flags;
 	u32 two_primaries;
 
               /* Since protocol version 87 and higher. */
@@ -791,6 +799,8 @@ enum {
 				 * while this is set. */
 	RESIZE_PENDING,		/* Size change detected locally, waiting for the response from
 				 * the peer, if it changed there as well. */
+	CONN_DRY_RUN,		/* Expect disconnect after resync handshake. */
+	GOT_PING_ACK,		/* set when we receive a ping_ack packet, misc wait gets woken */
 };
 
 struct drbd_bitmap; /* opaque for drbd_conf */
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index ab871e00ffc..67e0fc54224 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -1668,7 +1668,7 @@ int drbd_send_sync_param(struct drbd_conf *mdev, struct syncer_conf *sc)
 int drbd_send_protocol(struct drbd_conf *mdev)
 {
 	struct p_protocol *p;
-	int size, rv;
+	int size, cf, rv;
 
 	size = sizeof(struct p_protocol);
 
@@ -1685,9 +1685,21 @@ int drbd_send_protocol(struct drbd_conf *mdev)
 	p->after_sb_0p   = cpu_to_be32(mdev->net_conf->after_sb_0p);
 	p->after_sb_1p   = cpu_to_be32(mdev->net_conf->after_sb_1p);
 	p->after_sb_2p   = cpu_to_be32(mdev->net_conf->after_sb_2p);
-	p->want_lose     = cpu_to_be32(mdev->net_conf->want_lose);
 	p->two_primaries = cpu_to_be32(mdev->net_conf->two_primaries);
 
+	cf = 0;
+	if (mdev->net_conf->want_lose)
+		cf |= CF_WANT_LOSE;
+	if (mdev->net_conf->dry_run) {
+		if (mdev->agreed_pro_version >= 92)
+			cf |= CF_DRY_RUN;
+		else {
+			dev_err(DEV, "--dry-run is not supported by peer");
+			return 0;
+		}
+	}
+	p->conn_flags    = cpu_to_be32(cf);
+
 	if (mdev->agreed_pro_version >= 87)
 		strcpy(p->integrity_alg, mdev->net_conf->integrity_alg);
 
@@ -3161,14 +3173,18 @@ void drbd_free_bc(struct drbd_backing_dev *ldev)
 void drbd_free_sock(struct drbd_conf *mdev)
 {
 	if (mdev->data.socket) {
+		mutex_lock(&mdev->data.mutex);
 		kernel_sock_shutdown(mdev->data.socket, SHUT_RDWR);
 		sock_release(mdev->data.socket);
 		mdev->data.socket = NULL;
+		mutex_unlock(&mdev->data.mutex);
 	}
 	if (mdev->meta.socket) {
+		mutex_lock(&mdev->meta.mutex);
 		kernel_sock_shutdown(mdev->meta.socket, SHUT_RDWR);
 		sock_release(mdev->meta.socket);
 		mdev->meta.socket = NULL;
+		mutex_unlock(&mdev->meta.mutex);
 	}
 }
 
diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index 4df3b40b105..6429d2b19e0 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -285,8 +285,8 @@ int drbd_set_role(struct drbd_conf *mdev, enum drbd_role new_role, int force)
 		}
 
 		if (r == SS_NO_UP_TO_DATE_DISK && force &&
-		    (mdev->state.disk == D_INCONSISTENT ||
-		     mdev->state.disk == D_OUTDATED)) {
+		    (mdev->state.disk < D_UP_TO_DATE &&
+		     mdev->state.disk >= D_INCONSISTENT)) {
 			mask.disk = D_MASK;
 			val.disk  = D_UP_TO_DATE;
 			forced = 1;
@@ -407,7 +407,7 @@ static int drbd_nl_primary(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp,
 	}
 
 	reply->ret_code =
-		drbd_set_role(mdev, R_PRIMARY, primary_args.overwrite_peer);
+		drbd_set_role(mdev, R_PRIMARY, primary_args.primary_force);
 
 	return 0;
 }
@@ -941,6 +941,25 @@ static int drbd_nl_disk_conf(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp
 
 	drbd_md_set_sector_offsets(mdev, nbc);
 
+	/* allocate a second IO page if logical_block_size != 512 */
+	logical_block_size = bdev_logical_block_size(nbc->md_bdev);
+	if (logical_block_size == 0)
+		logical_block_size = MD_SECTOR_SIZE;
+
+	if (logical_block_size != MD_SECTOR_SIZE) {
+		if (!mdev->md_io_tmpp) {
+			struct page *page = alloc_page(GFP_NOIO);
+			if (!page)
+				goto force_diskless_dec;
+
+			dev_warn(DEV, "Meta data's bdev logical_block_size = %d != %d\n",
+			     logical_block_size, MD_SECTOR_SIZE);
+			dev_warn(DEV, "Workaround engaged (has performance impact).\n");
+
+			mdev->md_io_tmpp = page;
+		}
+	}
+
 	if (!mdev->bitmap) {
 		if (drbd_bm_init(mdev)) {
 			retcode = ERR_NOMEM;
@@ -980,25 +999,6 @@ static int drbd_nl_disk_conf(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp
 		goto force_diskless_dec;
 	}
 
-	/* allocate a second IO page if logical_block_size != 512 */
-	logical_block_size = bdev_logical_block_size(nbc->md_bdev);
-	if (logical_block_size == 0)
-		logical_block_size = MD_SECTOR_SIZE;
-
-	if (logical_block_size != MD_SECTOR_SIZE) {
-		if (!mdev->md_io_tmpp) {
-			struct page *page = alloc_page(GFP_NOIO);
-			if (!page)
-				goto force_diskless_dec;
-
-			dev_warn(DEV, "Meta data's bdev logical_block_size = %d != %d\n",
-			     logical_block_size, MD_SECTOR_SIZE);
-			dev_warn(DEV, "Workaround engaged (has performance impact).\n");
-
-			mdev->md_io_tmpp = page;
-		}
-	}
-
 	/* Reset the "barriers don't work" bits here, then force meta data to
 	 * be written, to ensure we determine if barriers are supported. */
 	if (nbc->dc.no_md_flush)
diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index d065c646b35..ed9f1de24a7 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -2513,6 +2513,10 @@ static enum drbd_conns drbd_sync_handshake(struct drbd_conf *mdev, enum drbd_rol
 	}
 
 	if (hg == -100) {
+		/* FIXME this log message is not correct if we end up here
+		 * after an attempted attach on a diskless node.
+		 * We just refuse to attach -- well, we drop the "connection"
+		 * to that disk, in a way... */
 		dev_alert(DEV, "Split-Brain detected, dropping connection!\n");
 		drbd_khelper(mdev, "split-brain");
 		return C_MASK;
@@ -2538,6 +2542,16 @@ static enum drbd_conns drbd_sync_handshake(struct drbd_conf *mdev, enum drbd_rol
 		}
 	}
 
+	if (mdev->net_conf->dry_run || test_bit(CONN_DRY_RUN, &mdev->flags)) {
+		if (hg == 0)
+			dev_info(DEV, "dry-run connect: No resync, would become Connected immediately.\n");
+		else
+			dev_info(DEV, "dry-run connect: Would become %s, doing a %s resync.",
+				 drbd_conn_str(hg > 0 ? C_SYNC_SOURCE : C_SYNC_TARGET),
+				 abs(hg) >= 2 ? "full" : "bit-map based");
+		return C_MASK;
+	}
+
 	if (abs(hg) >= 2) {
 		dev_info(DEV, "Writing the whole bitmap, full sync required after drbd_sync_handshake.\n");
 		if (drbd_bitmap_io(mdev, &drbd_bmio_set_n_write, "set_n_write from sync_handshake"))
@@ -2585,7 +2599,7 @@ static int receive_protocol(struct drbd_conf *mdev, struct p_header *h)
 	struct p_protocol *p = (struct p_protocol *)h;
 	int header_size, data_size;
 	int p_proto, p_after_sb_0p, p_after_sb_1p, p_after_sb_2p;
-	int p_want_lose, p_two_primaries;
+	int p_want_lose, p_two_primaries, cf;
 	char p_integrity_alg[SHARED_SECRET_MAX] = "";
 
 	header_size = sizeof(*p) - sizeof(*h);
@@ -2598,8 +2612,14 @@ static int receive_protocol(struct drbd_conf *mdev, struct p_header *h)
 	p_after_sb_0p	= be32_to_cpu(p->after_sb_0p);
 	p_after_sb_1p	= be32_to_cpu(p->after_sb_1p);
 	p_after_sb_2p	= be32_to_cpu(p->after_sb_2p);
-	p_want_lose	= be32_to_cpu(p->want_lose);
 	p_two_primaries = be32_to_cpu(p->two_primaries);
+	cf		= be32_to_cpu(p->conn_flags);
+	p_want_lose = cf & CF_WANT_LOSE;
+
+	clear_bit(CONN_DRY_RUN, &mdev->flags);
+
+	if (cf & CF_DRY_RUN)
+		set_bit(CONN_DRY_RUN, &mdev->flags);
 
 	if (p_proto != mdev->net_conf->wire_protocol) {
 		dev_err(DEV, "incompatible communication protocols\n");
@@ -3118,13 +3138,16 @@ static int receive_state(struct drbd_conf *mdev, struct p_header *h)
 
 		put_ldev(mdev);
 		if (nconn == C_MASK) {
+			nconn = C_CONNECTED;
 			if (mdev->state.disk == D_NEGOTIATING) {
 				drbd_force_state(mdev, NS(disk, D_DISKLESS));
-				nconn = C_CONNECTED;
 			} else if (peer_state.disk == D_NEGOTIATING) {
 				dev_err(DEV, "Disk attach process on the peer node was aborted.\n");
 				peer_state.disk = D_DISKLESS;
+				real_peer_disk = D_DISKLESS;
 			} else {
+				if (test_and_clear_bit(CONN_DRY_RUN, &mdev->flags))
+					return FALSE;
 				D_ASSERT(oconn == C_WF_REPORT_PARAMS);
 				drbd_force_state(mdev, NS(conn, C_DISCONNECTING));
 				return FALSE;
@@ -3594,10 +3617,7 @@ static void drbd_disconnect(struct drbd_conf *mdev)
 
 	/* asender does not clean up anything. it must not interfere, either */
 	drbd_thread_stop(&mdev->asender);
-
-	mutex_lock(&mdev->data.mutex);
 	drbd_free_sock(mdev);
-	mutex_unlock(&mdev->data.mutex);
 
 	spin_lock_irq(&mdev->req_lock);
 	_drbd_wait_ee_list_empty(mdev, &mdev->active_ee);
@@ -4054,6 +4074,8 @@ static int got_PingAck(struct drbd_conf *mdev, struct p_header *h)
 {
 	/* restore idle timeout */
 	mdev->meta.socket->sk->sk_rcvtimeo = mdev->net_conf->ping_int*HZ;
+	if (!test_and_set_bit(GOT_PING_ACK, &mdev->flags))
+		wake_up(&mdev->misc_wait);
 
 	return TRUE;
 }
diff --git a/drivers/block/drbd/drbd_worker.c b/drivers/block/drbd/drbd_worker.c
index b453c2bca3b..44bf6d11197 100644
--- a/drivers/block/drbd/drbd_worker.c
+++ b/drivers/block/drbd/drbd_worker.c
@@ -938,7 +938,8 @@ int w_e_end_csum_rs_req(struct drbd_conf *mdev, struct drbd_work *w, int cancel)
 
 		if (eq) {
 			drbd_set_in_sync(mdev, e->sector, e->size);
-			mdev->rs_same_csum++;
+			/* rs_same_csums unit is BM_BLOCK_SIZE */
+			mdev->rs_same_csum += e->size >> BM_BLOCK_SHIFT;
 			ok = drbd_send_ack(mdev, P_RS_IS_IN_SYNC, e);
 		} else {
 			inc_rs_pending(mdev);
@@ -1288,6 +1289,14 @@ int drbd_alter_sa(struct drbd_conf *mdev, int na)
 	return retcode;
 }
 
+static void ping_peer(struct drbd_conf *mdev)
+{
+	clear_bit(GOT_PING_ACK, &mdev->flags);
+	request_ping(mdev);
+	wait_event(mdev->misc_wait,
+		   test_bit(GOT_PING_ACK, &mdev->flags) || mdev->state.conn < C_CONNECTED);
+}
+
 /**
  * drbd_start_resync() - Start the resync process
  * @mdev:	DRBD device.
@@ -1371,7 +1380,6 @@ void drbd_start_resync(struct drbd_conf *mdev, enum drbd_conns side)
 		_drbd_pause_after(mdev);