Merge git://git.kernel.org/pub/scm/linux/kernel/git/agk/linux-2.6-dm

* git://git.kernel.org/pub/scm/linux/kernel/git/agk/linux-2.6-dm: (32 commits)
  dm: raid456 basic support
  dm: per target unplug callback support
  dm: introduce target callbacks and congestion callback
  dm mpath: delay activate_path retry on SCSI_DH_RETRY
  dm: remove superfluous irq disablement in dm_request_fn
  dm log: use PTR_ERR value instead of ENOMEM
  dm snapshot: avoid storing private suspended state
  dm snapshot: persistent make metadata_wq multithreaded
  dm: use non reentrant workqueues if equivalent
  dm: convert workqueues to alloc_ordered
  dm stripe: switch from local workqueue to system_wq
  dm: dont use flush_scheduled_work
  dm snapshot: remove unused dm_snapshot queued_bios_work
  dm ioctl: suppress needless warning messages
  dm crypt: add loop aes iv generator
  dm crypt: add multi key capability
  dm crypt: add post iv call to iv generator
  dm crypt: use io thread for reads only if mempool exhausted
  dm crypt: scale to multiple cpus
  dm crypt: simplify compatible table output
  ...

Documentation/device-mapper/dm-crypt.txt

@@ -8,7 +8,7 @@ Parameters: <cipher> <key> <iv_offset> <device path> <offset>
 
 <cipher>
     Encryption cipher and an optional IV generation mode.
-    (In format cipher-chainmode-ivopts:ivmode).
+    (In format cipher[:keycount]-chainmode-ivopts:ivmode).
     Examples:
        des
        aes-cbc-essiv:sha256
@@ -20,6 +20,11 @@ Parameters: <cipher> <key> <iv_offset> <device path> <offset>
     Key used for encryption. It is encoded as a hexadecimal number.
     You can only use key sizes that are valid for the selected cipher.
 
+<keycount>
+    Multi-key compatibility mode. You can define <keycount> keys and
+    then sectors are encrypted according to their offsets (sector 0 uses key0;
+    sector 1 uses key1 etc.).  <keycount> must be a power of two.
+
 <iv_offset>
     The IV offset is a sector count that is added to the sector number
     before creating the IV.

Documentation/device-mapper/dm-raid.txt

+Device-mapper RAID (dm-raid) is a bridge from DM to MD.  It
+provides a way to use device-mapper interfaces to access the MD RAID
+drivers.
+
+As with all device-mapper targets, the nominal public interfaces are the
+constructor (CTR) tables and the status outputs (both STATUSTYPE_INFO
+and STATUSTYPE_TABLE).  The CTR table looks like the following:
+
+1: <s> <l> raid \
+2:      <raid_type> <#raid_params> <raid_params> \
+3:      <#raid_devs> <meta_dev1> <dev1> .. <meta_devN> <devN>
+
+Line 1 contains the standard first three arguments to any device-mapper
+target - the start, length, and target type fields.  The target type in
+this case is "raid".
+
+Line 2 contains the arguments that define the particular raid
+type/personality/level, the required arguments for that raid type, and
+any optional arguments.  Possible raid types include: raid4, raid5_la,
+raid5_ls, raid5_rs, raid6_zr, raid6_nr, and raid6_nc.  (raid1 is
+planned for the future.)  The list of required and optional parameters
+is the same for all the current raid types.  The required parameters are
+positional, while the optional parameters are given as key/value pairs.
+The possible parameters are as follows:
+ <chunk_size>           Chunk size in sectors.
+ [[no]sync]             Force/Prevent RAID initialization
+ [rebuild <idx>]        Rebuild the drive indicated by the index
+ [daemon_sleep <ms>]    Time between bitmap daemon work to clear bits
+ [min_recovery_rate <kB/sec/disk>]      Throttle RAID initialization
+ [max_recovery_rate <kB/sec/disk>]      Throttle RAID initialization
+ [max_write_behind <sectors>]           See '-write-behind=' (man mdadm)
+ [stripe_cache <sectors>]               Stripe cache size for higher RAIDs
+
+Line 3 contains the list of devices that compose the array in
+metadata/data device pairs.  If the metadata is stored separately, a '-'
+is given for the metadata device position.  If a drive has failed or is
+missing at creation time, a '-' can be given for both the metadata and
+data drives for a given position.
+
+NB. Currently all metadata devices must be specified as '-'.
+
+Examples:
+# RAID4 - 4 data drives, 1 parity
+# No metadata devices specified to hold superblock/bitmap info
+# Chunk size of 1MiB
+# (Lines separated for easy reading)
+0 1960893648 raid \
+        raid4 1 2048 \
+        5 - 8:17 - 8:33 - 8:49 - 8:65 - 8:81
+
+# RAID4 - 4 data drives, 1 parity (no metadata devices)
+# Chunk size of 1MiB, force RAID initialization,
+#       min recovery rate at 20 kiB/sec/disk
+0 1960893648 raid \
+        raid4 4 2048 min_recovery_rate 20 sync\
+        5 - 8:17 - 8:33 - 8:49 - 8:65 - 8:81
+
+Performing a 'dmsetup table' should display the CTR table used to
+construct the mapping (with possible reordering of optional
+parameters).
+
+Performing a 'dmsetup status' will yield information on the state and
+health of the array.  The output is as follows:
+1: <s> <l> raid \
+2:      <raid_type> <#devices> <1 health char for each dev> <resync_ratio>
+
+Line 1 is standard DM output.  Line 2 is best shown by example:
+        0 1960893648 raid raid4 5 AAAAA 2/490221568
+Here we can see the RAID type is raid4, there are 5 devices - all of
+which are 'A'live, and the array is 2/490221568 complete with recovery.

drivers/md/Kconfig

@@ -240,6 +240,30 @@ config DM_MIRROR
          Allow volume managers to mirror logical volumes, also
          needed for live data migration tools such as 'pvmove'.
 
+config DM_RAID
+       tristate "RAID 4/5/6 target (EXPERIMENTAL)"
+       depends on BLK_DEV_DM && EXPERIMENTAL
+       select MD_RAID456
+       select BLK_DEV_MD
+       ---help---
+	 A dm target that supports RAID4, RAID5 and RAID6 mappings
+
+	 A RAID-5 set of N drives with a capacity of C MB per drive provides
+	 the capacity of C * (N - 1) MB, and protects against a failure
+	 of a single drive. For a given sector (row) number, (N - 1) drives
+	 contain data sectors, and one drive contains the parity protection.
+	 For a RAID-4 set, the parity blocks are present on a single drive,
+	 while a RAID-5 set distributes the parity across the drives in one
+	 of the available parity distribution methods.
+
+	 A RAID-6 set of N drives with a capacity of C MB per drive
+	 provides the capacity of C * (N - 2) MB, and protects
+	 against a failure of any two drives. For a given sector
+	 (row) number, (N - 2) drives contain data sectors, and two
+	 drives contains two independent redundancy syndromes.  Like
+	 RAID-5, RAID-6 distributes the syndromes across the drives
+	 in one of the available parity distribution methods.
+
 config DM_LOG_USERSPACE
 	tristate "Mirror userspace logging (EXPERIMENTAL)"
 	depends on DM_MIRROR && EXPERIMENTAL && NET

drivers/md/Makefile

@@ -36,6 +36,7 @@ obj-$(CONFIG_DM_SNAPSHOT)	+= dm-snapshot.o
 obj-$(CONFIG_DM_MIRROR)		+= dm-mirror.o dm-log.o dm-region-hash.o
 obj-$(CONFIG_DM_LOG_USERSPACE)	+= dm-log-userspace.o
 obj-$(CONFIG_DM_ZERO)		+= dm-zero.o
+obj-$(CONFIG_DM_RAID)	+= dm-raid.o
 
 ifeq ($(CONFIG_DM_UEVENT),y)
 dm-mod-objs			+= dm-uevent.o

drivers/md/dm-delay.c

@@ -352,7 +352,7 @@ static int __init dm_delay_init(void)
 {
 	int r = -ENOMEM;
 
-	kdelayd_wq = create_workqueue("kdelayd");
+	kdelayd_wq = alloc_workqueue("kdelayd", WQ_MEM_RECLAIM, 0);
 	if (!kdelayd_wq) {
 		DMERR("Couldn't start kdelayd");
 		goto bad_queue;

drivers/md/dm-ioctl.c

@@ -295,19 +295,55 @@ static void dm_hash_remove_all(int keep_open_devices)
 		DMWARN("remove_all left %d open device(s)", dev_skipped);
 }
 
+/*
+ * Set the uuid of a hash_cell that isn't already set.
+ */
+static void __set_cell_uuid(struct hash_cell *hc, char *new_uuid)
+{
+	mutex_lock(&dm_hash_cells_mutex);
+	hc->uuid = new_uuid;
+	mutex_unlock(&dm_hash_cells_mutex);
+
+	list_add(&hc->uuid_list, _uuid_buckets + hash_str(new_uuid));
+}
+
+/*
+ * Changes the name of a hash_cell and returns the old name for
+ * the caller to free.
+ */
+static char *__change_cell_name(struct hash_cell *hc, char *new_name)
+{
+	char *old_name;
+
+	/*
+	 * Rename and move the name cell.
+	 */
+	list_del(&hc->name_list);
+	old_name = hc->name;
+
+	mutex_lock(&dm_hash_cells_mutex);
+	hc->name = new_name;
+	mutex_unlock(&dm_hash_cells_mutex);
+
+	list_add(&hc->name_list, _name_buckets + hash_str(new_name));
+
+	return old_name;
+}
+
 static struct mapped_device *dm_hash_rename(struct dm_ioctl *param,
 					    const char *new)
 {
-	char *new_name, *old_name;
+	char *new_data, *old_name = NULL;
 	struct hash_cell *hc;
 	struct dm_table *table;
 	struct mapped_device *md;
+	unsigned change_uuid = (param->flags & DM_UUID_FLAG) ? 1 : 0;
 
 	/*
 	 * duplicate new.
 	 */
-	new_name = kstrdup(new, GFP_KERNEL);
-	if (!new_name)
+	new_data = kstrdup(new, GFP_KERNEL);
+	if (!new_data)
 		return ERR_PTR(-ENOMEM);
 
 	down_write(&_hash_lock);
@@ -315,13 +351,19 @@ static struct mapped_device *dm_hash_rename(struct dm_ioctl *param,
 	/*
 	 * Is new free ?
 	 */
-	hc = __get_name_cell(new);
+	if (change_uuid)
+		hc = __get_uuid_cell(new);
+	else
+		hc = __get_name_cell(new);
+
 	if (hc) {
-		DMWARN("asked to rename to an already-existing name %s -> %s",
+		DMWARN("Unable to change %s on mapped device %s to one that "
+		       "already exists: %s",
+		       change_uuid ? "uuid" : "name",
 		       param->name, new);
 		dm_put(hc->md);
 		up_write(&_hash_lock);
-		kfree(new_name);
+		kfree(new_data);
 		return ERR_PTR(-EBUSY);
 	}
 
@@ -330,22 +372,30 @@ static struct mapped_device *dm_hash_rename(struct dm_ioctl *param,
 	 */
 	hc = __get_name_cell(param->name);
 	if (!hc) {
-		DMWARN("asked to rename a non-existent device %s -> %s",
-		       param->name, new);
+		DMWARN("Unable to rename non-existent device, %s to %s%s",
+		       param->name, change_uuid ? "uuid " : "", new);
 		up_write(&_hash_lock);
-		kfree(new_name);
+		kfree(new_data);
 		return ERR_PTR(-ENXIO);
 	}
 
 	/*
-	 * rename and move the name cell.
+	 * Does this device already have a uuid?
 	 */
-	list_del(&hc->name_list);
-	old_name = hc->name;
-	mutex_lock(&dm_hash_cells_mutex);
-	hc->name = new_name;
-	mutex_unlock(&dm_hash_cells_mutex);
-	list_add(&hc->name_list, _name_buckets + hash_str(new_name));
+	if (change_uuid && hc->uuid) {
+		DMWARN("Unable to change uuid of mapped device %s to %s "
+		       "because uuid is already set to %s",
+		       param->name, new, hc->uuid);
+		dm_put(hc->md);
+		up_write(&_hash_lock);
+		kfree(new_data);
+		return ERR_PTR(-EINVAL);
+	}
+
+	if (change_uuid)
+		__set_cell_uuid(hc, new_data);
+	else
+		old_name = __change_cell_name(hc, new_data);
 
 	/*
 	 * Wake up any dm event waiters.
@@ -729,7 +779,7 @@ static int dev_remove(struct dm_ioctl *param, size_t param_size)
 	hc = __find_device_hash_cell(param);
 
 	if (!hc) {
-		DMWARN("device doesn't appear to be in the dev hash table.");
+		DMDEBUG_LIMIT("device doesn't appear to be in the dev hash table.");
 		up_write(&_hash_lock);
 		return -ENXIO;
 	}
@@ -741,7 +791,7 @@ static int dev_remove(struct dm_ioctl *param, size_t param_size)
 	 */
 	r = dm_lock_for_deletion(md);
 	if (r) {
-		DMWARN("unable to remove open device %s", hc->name);
+		DMDEBUG_LIMIT("unable to remove open device %s", hc->name);
 		up_write(&_hash_lock);
 		dm_put(md);
 		return r;
@@ -774,21 +824,24 @@ static int invalid_str(char *str, void *end)
 static int dev_rename(struct dm_ioctl *param, size_t param_size)
 {
 	int r;
-	char *new_name = (char *) param + param->data_start;
+	char *new_data = (char *) param + param->data_start;
 	struct mapped_device *md;
+	unsigned change_uuid = (param->flags & DM_UUID_FLAG) ? 1 : 0;
 
-	if (new_name < param->data ||
-	    invalid_str(new_name, (void *) param + param_size) ||
-	    strlen(new_name) > DM_NAME_LEN - 1) {
-		DMWARN("Invalid new logical volume name supplied.");
+	if (new_data < param->data ||
+	    invalid_str(new_data, (void *) param + param_size) ||
+	    strlen(new_data) > (change_uuid ? DM_UUID_LEN - 1 : DM_NAME_LEN - 1)) {
+		DMWARN("Invalid new mapped device name or uuid string supplied.");
 		return -EINVAL;
 	}
 
-	r = check_name(new_name);
-	if (r)
-		return r;
+	if (!change_uuid) {
+		r = check_name(new_data);
+		if (r)
+			return r;
+	}
 
-	md = dm_hash_rename(param, new_name);
+	md = dm_hash_rename(param, new_data);
 	if (IS_ERR(md))
 		return PTR_ERR(md);
 
@@ -885,7 +938,7 @@ static int do_resume(struct dm_ioctl *param)
 
 	hc = __find_device_hash_cell(param);
 	if (!hc) {
-		DMWARN("device doesn't appear to be in the dev hash table.");
+		DMDEBUG_LIMIT("device doesn't appear to be in the dev hash table.");
 		up_write(&_hash_lock);
 		return -ENXIO;
 	}
@@ -1212,7 +1265,7 @@ static int table_clear(struct dm_ioctl *param, size_t param_size)
 
 	hc = __find_device_hash_cell(param);
 	if (!hc) {
-		DMWARN("device doesn't appear to be in the dev hash table.");
+		DMDEBUG_LIMIT("device doesn't appear to be in the dev hash table.");
 		up_write(&_hash_lock);
 		return -ENXIO;
 	}

drivers/md/dm-kcopyd.c

@@ -37,6 +37,13 @@ struct dm_kcopyd_client {
 	unsigned int nr_pages;
 	unsigned int nr_free_pages;
 
+	/*
+	 * Block devices to unplug.
+	 * Non-NULL pointer means that a block device has some pending requests
+	 * and needs to be unplugged.
+	 */
+	struct block_device *unplug[2];
+
 	struct dm_io_client *io_client;
 
 	wait_queue_head_t destroyq;
@@ -308,6 +315,31 @@ static int run_complete_job(struct kcopyd_job *job)
 	return 0;
 }
 
+/*
+ * Unplug the block device at the specified index.
+ */
+static void unplug(struct dm_kcopyd_client *kc, int rw)
+{
+	if (kc->unplug[rw] != NULL) {
+		blk_unplug(bdev_get_queue(kc->unplug[rw]));
+		kc->unplug[rw] = NULL;
+	}
+}
+
+/*
+ * Prepare block device unplug. If there's another device
+ * to be unplugged at the same array index, we unplug that
+ * device first.
+ */
+static void prepare_unplug(struct dm_kcopyd_client *kc, int rw,
+			   struct block_device *bdev)
+{
+	if (likely(kc->unplug[rw] == bdev))
+		return;
+	unplug(kc, rw);
+	kc->unplug[rw] = bdev;
+}
+
 static void complete_io(unsigned long error, void *context)
 {
 	struct kcopyd_job *job = (struct kcopyd_job *) context;
@@ -345,7 +377,7 @@ static int run_io_job(struct kcopyd_job *job)
 {
 	int r;
 	struct dm_io_request io_req = {
-		.bi_rw = job->rw | REQ_SYNC | REQ_UNPLUG,
+		.bi_rw = job->rw,
 		.mem.type = DM_IO_PAGE_LIST,
 		.mem.ptr.pl = job->pages,
 		.mem.offset = job->offset,
@@ -354,10 +386,16 @@ static int run_io_job(struct kcopyd_job *job)
 		.client = job->kc->io_client,
 	};
 
-	if (job->rw == READ)
+	if (job->rw == READ) {
 		r = dm_io(&io_req, 1, &job->source, NULL);
-	else
+		prepare_unplug(job->kc, READ, job->source.bdev);
+	} else {
+		if (job->num_dests > 1)
+			io_req.bi_rw |= REQ_UNPLUG;
 		r = dm_io(&io_req, job->num_dests, job->dests, NULL);
+		if (!(io_req.bi_rw & REQ_UNPLUG))
+			prepare_unplug(job->kc, WRITE, job->dests[0].bdev);
+	}
 
 	return r;
 }
@@ -435,10 +473,18 @@ static void do_work(struct work_struct *work)
 	 * Pages jobs when successful will jump onto the io jobs
 	 * list.  io jobs call wake when they complete and it all
 	 * starts again.
+	 *
+	 * Note that io_jobs add block devices to the unplug array,
+	 * this array is cleared with "unplug" calls. It is thus
+	 * forbidden to run complete_jobs after io_jobs and before
+	 * unplug because the block device could be destroyed in
+	 * job completion callback.
 	 */
 	process_jobs(&kc->complete_jobs, kc, run_complete_job);
 	process_jobs(&kc->pages_jobs, kc, run_pages_job);
 	process_jobs(&kc->io_jobs, kc, run_io_job);
+	unplug(kc, READ);
+	unplug(kc, WRITE);
 }
 
 /*
@@ -619,12 +665,15 @@ int dm_kcopyd_client_create(unsigned int nr_pages,
 	INIT_LIST_HEAD(&kc->io_jobs);
 	INIT_LIST_HEAD(&kc->pages_jobs);
 
+	memset(kc->unplug, 0, sizeof(kc->unplug));
+
 	kc->job_pool = mempool_create_slab_pool(MIN_JOBS, _job_cache);
 	if (!kc->job_pool)
 		goto bad_slab;
 
 	INIT_WORK(&kc->kcopyd_work, do_work);
-	kc->kcopyd_wq = create_singlethread_workqueue("kcopyd");
+	kc->kcopyd_wq = alloc_workqueue("kcopyd",
+					WQ_NON_REENTRANT | WQ_MEM_RECLAIM, 0);
 	if (!kc->kcopyd_wq)
 		goto bad_workqueue;
 

drivers/md/dm-log-userspace-base.c

@@ -12,12 +12,22 @@
 
 #include "dm-log-userspace-transfer.h"
 
+#define DM_LOG_USERSPACE_VSN "1.1.0"
+
 struct flush_entry {
 	int type;
 	region_t region;
 	struct list_head list;
 };
 
+/*
+ * This limit on the number of mark and clear request is, to a degree,
+ * arbitrary.  However, there is some basis for the choice in the limits
+ * imposed on the size of data payload by dm-log-userspace-transfer.c:
+ * dm_consult_userspace().
+ */
+#define MAX_FLUSH_GROUP_COUNT 32
+
 struct log_c {
 	struct dm_target *ti;
 	uint32_t region_size;
@@ -37,8 +47,15 @@ struct log_c {
 	 */
 	uint64_t in_sync_hint;
 
+	/*
+	 * Mark and clear requests are held until a flush is issued
+	 * so that we can group, and thereby limit, the amount of
+	 * network traffic between kernel and userspace.  The 'flush_lock'
+	 * is used to protect these lists.
+	 */
 	spinlock_t flush_lock;
-	struct list_head flush_list;  /* only for clear and mark requests */
+	struct list_head mark_list;
+	struct list_head clear_list;
 };
 
 static mempool_t *flush_entry_pool;
@@ -169,7 +186,8 @@ static int userspace_ctr(struct dm_dirty_log *log, struct dm_target *ti,
 
 	strncpy(lc->uuid, argv[0], DM_UUID_LEN);
 	spin_lock_init(&lc->flush_lock);
-	INIT_LIST_HEAD(&lc->flush_list);
+	INIT_LIST_HEAD(&lc->mark_list);
+	INIT_LIST_HEAD(&lc->clear_list);
 
 	str_size = build_constructor_string(ti, argc - 1, argv + 1, &ctr_str);
 	if (str_size < 0) {
@@ -181,8 +199,11 @@ static int userspace_ctr(struct dm_dirty_log *log, struct dm_target *ti,
 	r = dm_consult_userspace(lc->uuid, lc->luid, DM_ULOG_CTR,
 				 ctr_str, str_size, NULL, NULL);
 
-	if (r == -ESRCH) {
-		DMERR("Userspace log server not found");
+	if (r < 0) {
+		if (r == -ESRCH)
+			DMERR("Userspace log server not found");
+		else
+			DMERR("Userspace log server failed to create log");
 		goto out;
 	}
 
@@ -214,10 +235,9 @@ static int userspace_ctr(struct dm_dirty_log *log, struct dm_target *ti,
 
 static void userspace_dtr(struct dm_dirty_log *log)
 {
-	int r;
 	struct log_c *lc = log->context;
 
-	r = dm_consult_userspace(lc->uuid, lc->luid, DM_ULOG_DTR,
+	(void) dm_consult_userspace(lc->uuid, lc->luid, DM_ULOG_DTR,
 				 NULL, 0,
 				 NULL, NULL);
 
@@ -338,6 +358,71 @@ static int userspace_in_sync(struct dm_dirty_log *log, region_t region,
 	return (r) ? 0 : (int)in_sync;
 }
 
+static int flush_one_by_one(struct log_c *lc, struct list_head *flush_list)
+{
+	int r = 0;
+	struct flush_entry *fe;
+
+	list_for_each_entry(fe, flush_list, list) {
+		r = userspace_do_request(lc, lc->uuid, fe->type,
+					 (char *)&fe->region,
+					 sizeof(fe->region),
+					 NULL, NULL);
+		if (r)
+			break;
+	}
+
+	return r;
+}
+
+static int flush_by_group(struct log_c *lc, struct list_head *flush_list)
+{
+	int r = 0;
+	int count;
+	uint32_t type = 0;
+	struct flush_entry *fe, *tmp_fe;
+	LIST_HEAD(tmp_list);
+	uint64_t group[MAX_FLUSH_GROUP_COUNT];
+
+	/*
+	 * Group process the requests
+	 */
+	while (!list_empty(flush_list)) {
+		count = 0;
+
+		list_for_each_entry_safe(fe, tmp_fe, flush_list, list) {
+			group[count] = fe->region;
+			count++;
+
+			list_del(&fe->list);
+			list_add(&fe->list, &tmp_list);
+
+			type = fe->type;
+			if (count >= MAX_FLUSH_GROUP_COUNT)
+				break;
+		}
+
+		r = userspace_do_request(lc, lc->uuid, type,
+					 (char *)(group),
+					 count * sizeof(uint64_t),
+					 NULL, NULL);
+		if (r) {
+			/* Group send failed.  Attempt one-by-one. */
+			list_splice_init(&tmp_list, flush_list);
+			r = flush_one_by_one(lc, flush_list);
+			break;
+		}
+	}
+
+	/*
+	 * Must collect flush_entrys that were successfully processed
+	 * as a group so that they will be free'd by the caller.
+	 */
+	list_splice_init(&tmp_list, flush_list);
+
+	return r;
+}
+
 /*
  * userspace_flush
  *
@@ -360,31 +445,25 @@ static int userspace_flush(struct dm_dirty_log *log)
 	int r = 0;
 	unsigned long flags;
 	struct log_c *lc = log->context;
-	LIST_HEAD(flush_list);
+	LIST_HEAD(mark_list);
+	LIST_HEAD(clear_list);
 	struct flush_entry *fe, *tmp_fe;
 
 	spin_lock_irqsave(&lc->flush_lock, flags);
-	list_splice_init(&lc->flush_list, &flush_list);
+	list_splice_init(&lc->mark_list, &mark_list);
+	list_splice_init(&lc->clear_list, &clear_list);
 	spin_unlock_irqrestore(&lc->flush_lock, flags);
 
-	if (list_empty(&flush_list))
+	if (list_empty(&mark_list) && list_empty(&clear_list))
 		return 0;
 
-	/*
-	 * FIXME: Count up requests, group request types,
-	 * allocate memory to stick all requests in and
-	 * send to server in one go.  Failing the allocation,
-	 * do it one by one.
-	 */
+	r = flush_by_group(lc, &mark_list);
+	if (r)
+		goto fail;
 
-	list_for_each_entry(fe, &flush_list, list) {
-		r = userspace_do_request(lc, lc->uuid, fe->type,
-					 (char *)&fe->region,
-					 sizeof(fe->region),
-					 NULL, NULL);
-		if (r)
-			goto fail;
-	}
+	r = flush_by_group(lc, &clear_list);
+	if (r)
+		goto fail;
 
 	r = userspace_do_request(lc, lc->uuid, DM_ULOG_FLUSH,
 				 NULL, 0, NULL, NULL);
@@ -395,7 +474,11 @@ static int userspace_flush(struct dm_dirty_log *log)
 	 * Calling code will receive an error and will know that
 	 * the log facility has failed.
 	 */
-	list_for_each_entry_safe(fe, tmp_fe, &flush_list, list) {
+	list_for_each_entry_safe(fe, tmp_fe, &mark_list, list) {
+		list_del(&fe->list);
+		mempool_free(fe, flush_entry_pool);
+	}
+	list_for_each_entry_safe(fe, tmp_fe, &clear_list, list) {
 		list_del(&fe->list);
 		mempool_free(fe, flush_entry_pool);
 	}
@@ -425,7 +508,7 @@ static void userspace_mark_region(struct dm_dirty_log *log, region_t region)
 	spin_lock_irqsave(&lc->flush_lock, flags);
 	fe->type = DM_ULOG_MARK_REGION;
 	fe->region = region;
-	list_add(&fe->list, &lc->flush_list);
+	list_add(&fe->list, &lc->mark_list);
 	spin_unlock_irqrestore(&lc->flush_lock, flags);
 
 	return;
@@ -462,7 +545,7 @@ static void userspace_clear_region(struct dm_dirty_log *log, region_t region)
 	spin_lock_irqsave(&lc->flush_lock, flags);
 	fe->type = DM_ULOG_CLEAR_REGION;
 	fe->region = region;
-	list_add(&fe->list, &lc->flush_list);
+	list_add(&fe->list, &lc->clear_list);
 	spin_unlock_irqrestore(&lc->flush_lock, flags);
 
 	return;
@@ -684,7 +767,7 @@ static int __init userspace_dirty_log_init(void)
 		return r;
 	}
 
-	DMINFO("version 1.0.0 loaded");
+	DMINFO("version " DM_LOG_USERSPACE_VSN " loaded");
 	return 0;
 }
 
@@ -694,7 +777,7 @@ static void __exit userspace_dirty_log_exit(void)
 	dm_ulog_tfr_exit();
 	mempool_destroy(flush_entry_pool);
 
-	DMINFO("version 1.0.0 unloaded");
+	DMINFO("version " DM_LOG_USERSPACE_VSN " unloaded");
 	return;
 }
 

drivers/md/dm-log-userspace-transfer.c

@@ -198,6 +198,7 @@ int dm_consult_userspace(const char *uuid, uint64_t luid, int request_type,
 
 	memset(tfr, 0, DM_ULOG_PREALLOCED_SIZE - sizeof(struct cn_msg));
 	memcpy(tfr->uuid, uuid, DM_UUID_LEN);
+	tfr->version = DM_ULOG_REQUEST_VERSION;
 	tfr->luid = luid;
 	tfr->seq = dm_ulog_seq++;
 

drivers/md/dm-log.c

@@ -455,7 +455,7 @@ static int create_log_context(struct dm_dirty_log *log, struct dm_target *ti,
 			r = PTR_ERR(lc->io_req.client);
 			DMWARN("couldn't allocate disk io client");
 			kfree(lc);
-			return -ENOMEM;
+			return r;
 		}
 
 		lc->disk_header = vmalloc(buf_size);

drivers/md/dm-mpath.c

@@ -23,6 +23,8 @@
 
 #define DM_MSG_PREFIX "multipath"
 #define MESG_STR(x) x, sizeof(x)
+#define DM_PG_INIT_DELAY_MSECS 2000
+#define DM_PG_INIT_DELAY_DEFAULT ((unsigned) -1)
 
 /* Path properties */
 struct pgpath {
@@ -33,8 +35,7 @@ struct pgpath {
 	unsigned fail_count;		/* Cumulative failure count */
 
 	struct dm_path path;
-	struct work_struct deactivate_path;
-	struct work_struct activate_path;
+	struct delayed_work activate_path;
 };
 
 #define path_to_pgpath(__pgp) container_of((__pgp), struct pgpath, path)
@@ -65,11 +66,15 @@ struct multipath {
 
 	const char *hw_handler_name;
 	char *hw_handler_params;
+
 	unsigned nr_priority_groups;
 	struct list_head priority_groups;
+
+	wait_queue_head_t pg_init_wait;	/* Wait for pg_init completion */
+
 	unsigned pg_init_required;	/* pg_init needs calling? */
 	unsigned pg_init_in_progress;	/* Only one pg_init allowed at once */
-	wait_queue_head_t pg_init_wait;	/* Wait for pg_init completion */
+	unsigned pg_init_delay_retry;	/* Delay pg_init retry? */
 
 	unsigned nr_valid_paths;	/* Total number of usable paths */
 	struct pgpath *current_pgpath;
@@ -82,6 +87,7 @@ struct multipath {
 	unsigned saved_queue_if_no_path;/* Saved state during suspension */
 	unsigned pg_init_retries;	/* Number of times to retry pg_init */
 	unsigned pg_init_count;		/* Number of times pg_init called */
+	unsigned pg_init_delay_msecs;	/* Number of msecs before pg_init retry */
 
 	struct work_struct process_queued_ios;
 	struct list_head queued_ios;
@@ -116,7 +122,6 @@ static struct workqueue_struct *kmultipathd, *kmpath_handlerd;
 static void process_queued_ios(struct work_struct *work);
 static void trigger_event(struct work_struct *work);
 static void activate_path(struct work_struct *work);
-static void deactivate_path(struct work_struct *work);
 
 
 /*-----------------------------------------------
@@ -129,8 +134,7 @@ static struct pgpath *alloc_pgpath(void)
 
 	if (pgpath) {
 		pgpath->is_active = 1;
-		INIT_WORK(&pgpath->deactivate_path, deactivate_path);
-		INIT_WORK(&pgpath->activate_path, activate_path);
+		INIT_DELAYED_WORK(&pgpath->activate_path, activate_path);
 	}
 
 	return pgpath;
@@ -141,14 +145,6 @@ static void free_pgpath(struct pgpath *pgpath)
 	kfree(pgpath);
 }
 
-static void deactivate_path(struct work_struct *work)
-{
-	struct pgpath *pgpath =
-		container_of(work, struct pgpath, deactivate_path);
-
-	blk_abort_queue(pgpath->path.dev->bdev->bd_disk->queue);
-}
-
 static struct priority_group *alloc_priority_group(void)
 {
 	struct priority_group *pg;
@@ -199,6 +195,7 @@ static struct multipath *alloc_multipath(struct dm_target *ti)
 		INIT_LIST_HEAD(&m->queued_ios);
 		spin_lock_init(&m->lock);
 		m->queue_io = 1;
+		m->pg_init_delay_msecs = DM_PG_INIT_DELAY_DEFAULT;
 		INIT_WORK(&m->process_queued_ios, process_queued_ios);
 		INIT_WORK(&m->trigger_event, trigger_event);
 		init_waitqueue_head(&m->pg_init_wait);
@@ -238,14 +235,19 @@ static void free_multipath(struct multipath *m)
 static void __pg_init_all_paths(struct multipath *m)
 {
 	struct pgpath *pgpath;
+	unsigned long pg_init_delay = 0;
 
 	m->pg_init_count++;
 	m->pg_init_required = 0;
+	if (m->pg_init_delay_retry)
+		pg_init_delay = msecs_to_jiffies(m->pg_init_delay_msecs != DM_PG_INIT_DELAY_DEFAULT ?
+						 m->pg_init_delay_msecs : DM_PG_INIT_DELAY_MSECS);
 	list_for_each_entry(pgpath, &m->current_pg->pgpaths, list) {
 		/* Skip failed paths */
 		if (!pgpath->is_active)
 			continue;
-		if (queue_work(kmpath_handlerd, &pgpath->activate_path))
+		if (queue_delayed_work(kmpath_handlerd, &pgpath->activate_path,
+				       pg_init_delay))
 			m->pg_init_in_progress++;
 	}
 }
@@ -793,8 +795,9 @@ static int parse_features(struct arg_set *as, struct multipath *m)
 	const char *param_name;
 
 	static struct param _params[] = {
-		{0, 3, "invalid number of feature args"},
+		{0, 5, "invalid number of feature args"},
 		{1, 50, "pg_init_retries must be between 1 and 50"},
+		{0, 60000, "pg_init_delay_msecs must be between 0 and 60000"},
 	};
 
 	r = read_param(_params, shift(as), &argc, &ti->error);
@@ -821,6 +824,14 @@ static int parse_features(struct arg_set *as, struct multipath *m)
 			continue;
 		}
 
+		if (!strnicmp(param_name, MESG_STR("pg_init_delay_msecs")) &&
+		    (argc >= 1)) {
+			r = read_param(_params + 2, shift(as),
+				       &m->pg_init_delay_msecs, &ti->error);
+			argc--;
+			continue;
+		}
+
 		ti->error = "Unrecognised multipath feature request";
 		r = -EINVAL;
 	} while (argc && !r);
@@ -931,7 +942,7 @@ static void flush_multipath_work(struct multipath *m)
 	flush_workqueue(kmpath_handlerd);
 	multipath_wait_for_pg_init_completion(m);
 	flush_workqueue(kmultipathd);
-	flush_scheduled_work();
+	flush_work_sync(&m->trigger_event);
 }
 
 static void multipath_dtr(struct dm_target *ti)
@@ -995,7 +1006,6 @@ static int fail_path(struct pgpath *pgpath)
 		      pgpath->path.dev->name, m->nr_valid_paths);
 
 	schedule_work(&m->trigger_event);
-	queue_work(kmultipathd, &pgpath->deactivate_path);
 
 out:
 	spin_unlock_irqrestore(&m->lock, flags);
@@ -1034,7 +1044,7 @@ static int reinstate_path(struct pgpath *pgpath)
 		m->current_pgpath = NULL;
 		queue_work(kmultipathd, &m->process_queued_ios);
 	} else if (m->hw_handler_name && (m->current_pg == pgpath->pg)) {
-		if (queue_work(kmpath_handlerd, &pgpath->activate_path))
+		if (queue_work(kmpath_handlerd, &pgpath->activate_path.work))
 			m->pg_init_in_progress++;
 	}
 
@@ -1169,6 +1179,7 @@ static void pg_init_done(void *data, int errors)
 	struct priority_group *pg = pgpath->pg;
 	struct multipath *m = pg->m;
 	unsigned long flags;
+	unsigned delay_retry = 0;
 
 	/* device or driver problems */
 	switch (errors) {
@@ -1193,8 +1204,9 @@ static void pg_init_done(void *data, int errors)
 		 */
 		bypass_pg(m, pg, 1);
 		break;
-	/* TODO: For SCSI_DH_RETRY we should wait a couple seconds */
 	case SCSI_DH_RETRY:
+		/* Wait before retrying. */
+		delay_retry = 1;
 	case SCSI_DH_IMM_RETRY:
 	case SCSI_DH_RES_TEMP_UNAVAIL:
 		if (pg_init_limit_reached(m, pgpath))
@@ -1227,6 +1239,7 @@ static void pg_init_done(void *data, int errors)
 	if (!m->pg_init_required)
 		m->queue_io = 0;
 
+	m->pg_init_delay_retry = delay_retry;
 	queue_work(kmultipathd, &m->process_queued_ios);
 
 	/*
@@ -1241,7 +1254,7 @@ static void pg_init_done(void *data, int errors)
 static void activate_path(struct work_struct *work)
 {
 	struct pgpath *pgpath =
-		container_of(work, struct pgpath, activate_path);
+		container_of(work, struct pgpath, activate_path.work);
 
 	scsi_dh_activate(bdev_get_queue(pgpath->path.dev->bdev),
 				pg_init_done, pgpath);
@@ -1382,11 +1395,14 @@ static int multipath_status(struct dm_target *ti, status_type_t type,
 		DMEMIT("2 %u %u ", m->queue_size, m->pg_init_count);
 	else {
 		DMEMIT("%u ", m->queue_if_no_path +
-			      (m->pg_init_retries > 0) * 2);
+			      (m->pg_init_retries > 0) * 2 +
+			      (m->pg_init_delay_msecs != DM_PG_INIT_DELAY_DEFAULT) * 2);
 		if (m->queue_if_no_path)
 			DMEMIT("queue_if_no_path ");
 		if (m->pg_init_retries)
 			DMEMIT("pg_init_retries %u ", m->pg_init_retries);
+		if (m->pg_init_delay_msecs != DM_PG_INIT_DELAY_DEFAULT)
+			DMEMIT("pg_init_delay_msecs %u ", m->pg_init_delay_msecs);
 	}
 
 	if (!m->hw_handler_name || type == STATUSTYPE_INFO)
@@ -1655,7 +1671,7 @@ static int multipath_busy(struct dm_target *ti)
  *---------------------------------------------------------------*/
 static struct target_type multipath_target = {
 	.name = "multipath",
-	.version = {1, 1, 1},
+	.version = {1, 2, 0},
 	.module = THIS_MODULE,
 	.ctr = multipath_ctr,
 	.dtr = multipath_dtr,
@@ -1687,7 +1703,7 @@ static int __init dm_multipath_init(void)
 		return -EINVAL;
 	}
 
-	kmultipathd = create_workqueue("kmpathd");
+	kmultipathd = alloc_workqueue("kmpathd", WQ_MEM_RECLAIM, 0);
 	if (!kmultipathd) {
 		DMERR("failed to create workqueue kmpathd");
 		dm_unregister_target(&multipath_target);
@@ -1701,7 +1717,8 @@ static int __init dm_multipath_init(void)
 	 * old workqueue would also create a bottleneck in the
 	 * path of the storage hardware device activation.
 	 */
-	kmpath_handlerd = create_singlethread_workqueue("kmpath_handlerd");
+	kmpath_handlerd = alloc_ordered_workqueue("kmpath_handlerd",
+						  WQ_MEM_RECLAIM);
 	if (!kmpath_handlerd) {
 		DMERR("failed to create workqueue kmpath_handlerd");
 		destroy_workqueue(kmultipathd);

drivers/md/dm-raid.c

+/*
+ * Copyright (C) 2010-2011 Neil Brown
+ * Copyright (C) 2010-2011 Red Hat, Inc. All rights reserved.
+ *
+ * This file is released under the GPL.
+ */
+
+#include <linux/slab.h>
+
+#include "md.h"
+#include "raid5.h"
+#include "dm.h"
+#include "bitmap.h"
+
+#define DM_MSG_PREFIX "raid"
+
+/*
+ * If the MD doesn't support MD_SYNC_STATE_FORCED yet, then
+ * make it so the flag doesn't set anything.
+ */
+#ifndef MD_SYNC_STATE_FORCED
+#define MD_SYNC_STATE_FORCED 0
+#endif
+
+struct raid_dev {
+	/*
+	 * Two DM devices, one to hold metadata and one to hold the
+	 * actual data/parity.  The reason for this is to not confuse
+	 * ti->len and give more flexibility in altering size and
+	 * characteristics.
+	 *
+	 * While it is possible for this device to be associated
+	 * with a different physical device than the data_dev, it
+	 * is intended for it to be the same.
+	 *    |--------- Physical Device ---------|
+	 *    |- meta_dev -|------ data_dev ------|
+	 */
+	struct dm_dev *meta_dev;
+	struct dm_dev *data_dev;
+	struct mdk_rdev_s rdev;
+};
+
+/*
+ * Flags for rs->print_flags field.
+ */
+#define DMPF_DAEMON_SLEEP      0x1
+#define DMPF_MAX_WRITE_BEHIND  0x2
+#define DMPF_SYNC              0x4
+#define DMPF_NOSYNC            0x8
+#define DMPF_STRIPE_CACHE      0x10
+#define DMPF_MIN_RECOVERY_RATE 0x20
+#define DMPF_MAX_RECOVERY_RATE 0x40
+
+struct raid_set {
+	struct dm_target *ti;
+
+	uint64_t print_flags;
+
+	struct mddev_s md;
+	struct raid_type *raid_type;
+	struct dm_target_callbacks callbacks;
+
+	struct raid_dev dev[0];
+};
+
+/* Supported raid types and properties. */
+static struct raid_type {
+	const char *name;		/* RAID algorithm. */
+	const char *descr;		/* Descriptor text for logging. */
+	const unsigned parity_devs;	/* # of parity devices. */
+	const unsigned minimal_devs;	/* minimal # of devices in set. */
+	const unsigned level;		/* RAID level. */
+	const unsigned algorithm;	/* RAID algorithm. */
+} raid_types[] = {
+	{"raid4",    "RAID4 (dedicated parity disk)",	1, 2, 5, ALGORITHM_PARITY_0},
+	{"raid5_la", "RAID5 (left asymmetric)",		1, 2, 5, ALGORITHM_LEFT_ASYMMETRIC},
+	{"raid5_ra", "RAID5 (right asymmetric)",	1, 2, 5, ALGORITHM_RIGHT_ASYMMETRIC},
+	{"raid5_ls", "RAID5 (left symmetric)",		1, 2, 5, ALGORITHM_LEFT_SYMMETRIC},
+	{"raid5_rs", "RAID5 (right symmetric)",		1, 2, 5, ALGORITHM_RIGHT_SYMMETRIC},
+	{"raid6_zr", "RAID6 (zero restart)",		2, 4, 6, ALGORITHM_ROTATING_ZERO_RESTART},
+	{"raid6_nr", "RAID6 (N restart)",		2, 4, 6, ALGORITHM_ROTATING_N_RESTART},
+	{"raid6_nc", "RAID6 (N continue)",		2, 4, 6, ALGORITHM_ROTATING_N_CONTINUE}
+};
+
+static struct raid_type *get_raid_type(char *name)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(raid_types); i++)
+		if (!strcmp(raid_types[i].name, name))
+			return &raid_types[i];
+
+	return NULL;
+}
+
+static struct raid_set *context_alloc(struct dm_target *ti, struct raid_type *raid_type, unsigned raid_devs)
+{
+	unsigned i;
+	struct raid_set *rs;
+	sector_t sectors_per_dev;
+
+	if (raid_devs <= raid_type->parity_devs) {
+		ti->error = "Insufficient number of devices";
+		return ERR_PTR(-EINVAL);
+	}
+
+	sectors_per_dev = ti->len;
+	if (sector_div(sectors_per_dev, (raid_devs - raid_type->parity_devs))) {
+		ti->error = "Target length not divisible by number of data devices";
+		return ERR_PTR(-EINVAL);
+	}
+
+	rs = kzalloc(sizeof(*rs) + raid_devs * sizeof(rs->dev[0]), GFP_KERNEL);
+	if (!rs) {
+		ti->error = "Cannot allocate raid context";
+		return ERR_PTR(-ENOMEM);
+	}
+
+	mddev_init(&rs->md);
+
+	rs->ti = ti;
+	rs->raid_type = raid_type;
+	rs->md.raid_disks = raid_devs;
+	rs->md.level = raid_type->level;
+	rs->md.new_level = rs->md.level;
+	rs->md.dev_sectors = sectors_per_dev;
+	rs->md.layout = raid_type->algorithm;
+	rs->md.new_layout = rs->md.layout;
+	rs->md.delta_disks = 0;
+	rs->md.recovery_cp = 0;
+
+	for (i = 0; i < raid_devs; i++)
+		md_rdev_init(&rs->dev[i].rdev);
+
+	/*
+	 * Remaining items to be initialized by further RAID params:
+	 *  rs->md.persistent
+	 *  rs->md.external
+	 *  rs->md.chunk_sectors
+	 *  rs->md.new_chunk_sectors
+	 */
+
+	return rs;
+}
+
+static void context_free(struct raid_set *rs)
+{
+	int i;
+
+	for (i = 0; i < rs->md.raid_disks; i++)
+		if (rs->dev[i].data_dev)
+			dm_put_device(rs->ti, rs->dev[i].data_dev);
+
+	kfree(rs);
+}
+
+/*
+ * For every device we have two words
+ *  <meta_dev>: meta device name or '-' if missing
+ *  <data_dev>: data device name or '-' if missing
+ *
+ * This code parses those words.
+ */
+static int dev_parms(struct raid_set *rs, char **argv)
+{
+	int i;
+	int rebuild = 0;
+	int metadata_available = 0;
+	int ret = 0;
+
+	for (i = 0; i < rs->md.raid_disks; i++, argv += 2) {
+		rs->dev[i].rdev.raid_disk = i;
+
+		rs->dev[i].meta_dev = NULL;
+		rs->dev[i].data_dev = NULL;
+
+		/*
+		 * There are no offsets, since there is a separate device
+		 * for data and metadata.
+		 */
+		rs->dev[i].rdev.data_offset = 0;
+		rs->dev[i].rdev.mddev = &rs->md;
+
+		if (strcmp(argv[0], "-")) {
+			rs->ti->error = "Metadata devices not supported";
+			return -EINVAL;
+		}
+
+		if (!strcmp(argv[1], "-")) {
+			if (!test_bit(In_sync, &rs->dev[i].rdev.flags) &&
+			    (!rs->dev[i].rdev.recovery_offset)) {
+				rs->ti->error = "Drive designated for rebuild not specified";
+				return -EINVAL;
+			}
+
+			continue;
+		}
+
+		ret = dm_get_device(rs->ti, argv[1],
+				    dm_table_get_mode(rs->ti->table),
+				    &rs->dev[i].data_dev);
+		if (ret) {
+			rs->ti->error = "RAID device lookup failure";
+			return ret;
+		}
+
+		rs->dev[i].rdev.bdev = rs->dev[i].data_dev->bdev;
+		list_add(&rs->dev[i].rdev.same_set, &rs->md.disks);
+		if (!test_bit(In_sync, &rs->dev[i].rdev.flags))
+			rebuild++;
+	}
+
+	if (metadata_available) {
+		rs->md.external = 0;
+		rs->md.persistent = 1;
+		rs->md.major_version = 2;
+	} else if (rebuild && !rs->md.recovery_cp) {
+		/*
+		 * Without metadata, we will not be able to tell if the array
+		 * is in-sync or not - we must assume it is not.  Therefore,
+		 * it is impossible to rebuild a drive.
+		 *
+		 * Even if there is metadata, the on-disk information may
+		 * indicate that the array is not in-sync and it will then
+		 * fail at that time.
+		 *
+		 * User could specify 'nosync' option if desperate.
+		 */
+		DMERR("Unable to rebuild drive while array is not in-sync");
+		rs->ti->error = "RAID device lookup failure";
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+/*
+ * Possible arguments are...
+ * RAID456:
+ *	<chunk_size> [optional_args]
+ *
+ * Optional args:
+ *    [[no]sync]			Force or prevent recovery of the entire array
+ *    [rebuild <idx>]			Rebuild the drive indicated by the index
+ *    [daemon_sleep <ms>]		Time between bitmap daemon work to clear bits
+ *    [min_recovery_rate <kB/sec/disk>]	Throttle RAID initialization
+ *    [max_recovery_rate <kB/sec/disk>]	Throttle RAID initialization
+ *    [max_write_behind <sectors>]	See '-write-behind=' (man mdadm)
+ *    [stripe_cache <sectors>]		Stripe cache size for higher RAIDs
+ */
+static int parse_raid_params(struct raid_set *rs, char **argv,
+			     unsigned num_raid_params)
+{
+	unsigned i, rebuild_cnt = 0;
+	unsigned long value;
+	char *key;
+
+	/*
+	 * First, parse the in-order required arguments
+	 */
+	if ((strict_strtoul(argv[0], 10, &value) < 0) ||
+	    !is_power_of_2(value) || (value < 8)) {
+		rs->ti->error = "Bad chunk size";
+		return -EINVAL;
+	}
+
+	rs->md.new_chunk_sectors = rs->md.chunk_sectors = value;
+	argv++;
+	num_raid_params--;
+
+	/*
+	 * Second, parse the unordered optional arguments
+	 */
+	for (i = 0; i < rs->md.raid_disks; i++)
+		set_bit(In_sync, &rs->dev[i].rdev.flags);
+
+	for (i = 0; i < num_raid_params; i++) {
+		if (!strcmp(argv[i], "nosync")) {
+			rs->md.recovery_cp = MaxSector;
+			rs->print_flags |= DMPF_NOSYNC;
+			rs->md.flags |= MD_SYNC_STATE_FORCED;
+			continue;
+		}
+		if (!strcmp(argv[i], "sync")) {
+			rs->md.recovery_cp = 0;
+			rs->print_flags |= DMPF_SYNC;
+			rs->md.flags |= MD_SYNC_STATE_FORCED;
+			continue;
+		}
+
+		/* The rest of the optional arguments come in key/value pairs */
+		if ((i + 1) >= num_raid_params) {
+			rs->ti->error = "Wrong number of raid parameters given";
+			return -EINVAL;
+		}
+
+		key = argv[i++];
+		if (strict_strtoul(argv[i], 10, &value) < 0) {
+			rs->ti->error = "Bad numerical argument given in raid params";
+			return -EINVAL;
+		}
+
+		if (!strcmp(key, "rebuild")) {
+			if (++rebuild_cnt > rs->raid_type->parity_devs) {
+				rs->ti->error = "Too many rebuild drives given";
+				return -EINVAL;
+			}
+			if (value > rs->md.raid_disks) {
+				rs->ti->error = "Invalid rebuild index given";
+				return -EINVAL;
+			}
+			clear_bit(In_sync, &rs->dev[value].rdev.flags);
+			rs->dev[value].rdev.recovery_offset = 0;
+		} else if (!strcmp(key, "max_write_behind")) {
+			rs->print_flags |= DMPF_MAX_WRITE_BEHIND;
+
+			/*
+			 * In device-mapper, we specify things in sectors, but
+			 * MD records this value in kB
+			 */
+			value /= 2;
+			if (value > COUNTER_MAX) {
+				rs->ti->error = "Max write-behind limit out of range";
+				return -EINVAL;
+			}
+			rs->md.bitmap_info.max_write_behind = value;
+		} else if (!strcmp(key, "daemon_sleep")) {
+			rs->print_flags |= DMPF_DAEMON_SLEEP;
+			if (!value || (value > MAX_SCHEDULE_TIMEOUT)) {
+				rs->ti->error = "daemon sleep period out of range";
+				return -EINVAL;
+			}
+			rs->md.bitmap_info.daemon_sleep = value;
+		} else if (!strcmp(key, "stripe_cache")) {
+			rs->print_flags |= DMPF_STRIPE_CACHE;
+
+			/*
+			 * In device-mapper, we specify things in sectors, but
+			 * MD records this value in kB
+			 */
+			value /= 2;
+
+			if (rs->raid_type->level < 5) {
+				rs->ti->error = "Inappropriate argument: stripe_cache";
+				return -EINVAL;
+			}
+			if (raid5_set_cache_size(&rs->md, (int)value)) {
+				rs->ti->error = "Bad stripe_cache size";
+				return -EINVAL;
+			}
+		} else if (!strcmp(key, "min_recovery_rate")) {
+			rs->print_flags |= DMPF_MIN_RECOVERY_RATE;
+			if (value > INT_MAX) {
+				rs->ti->error = "min_recovery_rate out of range";
+				return -EINVAL;
+			}
+			rs->md.sync_speed_min = (int)value;
+		} else if (!strcmp(key, "max_recovery_rate")) {
+			rs->print_flags |= DMPF_MAX_RECOVERY_RATE;
+			if (value > INT_MAX) {
+				rs->ti->error = "max_recovery_rate out of range";
+				return -EINVAL;
+			}
+			rs->md.sync_speed_max = (int)value;
+		} else {
+			DMERR("Unable to parse RAID parameter: %s", key);
+			rs->ti->error = "Unable to parse RAID parameters";
+			return -EINVAL;
+		}
+	}
+
+	/* Assume there are no metadata devices until the drives are parsed */
+	rs->md.persistent = 0;
+	rs->md.external = 1;
+
+	return 0;
+}
+
+static void do_table_event(struct work_struct *ws)
+{
+	struct raid_set *rs = container_of(ws, struct raid_set, md.event_work);
+
+	dm_table_event(rs->ti->table);
+}
+
+static int raid_is_congested(struct dm_target_callbacks *cb, int bits)
+{
+	struct raid_set *rs = container_of(cb, struct raid_set, callbacks);
+
+	return md_raid5_congested(&rs->md, bits);
+}
+
+static void raid_unplug(struct dm_target_callbacks *cb)
+{
+	struct raid_set *rs = container_of(cb, struct raid_set, callbacks);
+
+	md_raid5_unplug_device(rs->md.private);
+}
+
+/*
+ * Construct a RAID4/5/6 mapping:
+ * Args:
+ *	<raid_type> <#raid_params> <raid_params>		\
+ *	<#raid_devs> { <meta_dev1> <dev1> .. <meta_devN> <devN> }
+ *
+ * ** metadata devices are not supported yet, use '-' instead **
+ *
+ * <raid_params> varies by <raid_type>.  See 'parse_raid_params' for
+ * details on possible <raid_params>.
+ */
+static int raid_ctr(struct dm_target *ti, unsigned argc, char **argv)
+{
+	int ret;
+	struct raid_type *rt;
+	unsigned long num_raid_params, num_raid_devs;
+	struct raid_set *rs = NULL;
+
+	/* Must have at least <raid_type> <#raid_params> */
+	if (argc < 2) {
+		ti->error = "Too few arguments";
+		return -EINVAL;
+	}
+
+	/* raid type */
+	rt = get_raid_type(argv[0]);
+	if (!rt) {
+		ti->error = "Unrecognised raid_type";
+		return -EINVAL;
+	}
+	argc--;
+	argv++;
+
+	/* number of RAID parameters */
+	if (strict_strtoul(argv[0], 10, &num_raid_params) < 0) {
+		ti->error = "Cannot understand number of RAID parameters";
+		return -EINVAL;
+	}
+	argc--;
+	argv++;
+
+	/* Skip over RAID params for now and find out # of devices */
+	if (num_raid_params + 1 > argc) {
+		ti->error = "Arguments do not agree with counts given";
+		return -EINVAL;
+	}
+
+	if ((strict_strtoul(argv[num_raid_params], 10, &num_raid_devs) < 0) ||
+	    (num_raid_devs >= INT_MAX)) {
+		ti->error = "Cannot understand number of raid devices";
+		return -EINVAL;
+	}
+
+	rs = context_alloc(ti, rt, (unsigned)num_raid_devs);
+	if (IS_ERR(rs))
+		return PTR_ERR(rs);
+
+	ret = parse_raid_params(rs, argv, (unsigned)num_raid_params);
+	if (ret)
+		goto bad;
+
+	ret = -EINVAL;
+
+	argc -= num_raid_params + 1; /* +1: we already have num_raid_devs */
+	argv += num_raid_params + 1;
+
+	if (argc != (num_raid_devs * 2)) {
+		ti->error = "Supplied RAID devices does not match the count given";
+		goto bad;
+	}
+
+	ret = dev_parms(rs, argv);
+	if (ret)
+		goto bad;
+
+	INIT_WORK(&rs->md.event_work, do_table_event);
+	ti->split_io = rs->md.chunk_sectors;
+	ti->private = rs;
+
+	mutex_lock(&rs->md.reconfig_mutex);
+	ret = md_run(&rs->md);
+	rs->md.in_sync = 0; /* Assume already marked dirty */
+	mutex_unlock(&rs->md.reconfig_mutex);
+
+	if (ret) {
+		ti->error = "Fail to run raid array";
+		goto bad;
+	}
+
+	rs->callbacks.congested_fn = raid_is_congested;
+	rs->callbacks.unplug_fn = raid_unplug;
+	dm_table_add_target_callbacks(ti->table, &rs->callbacks);
+
+	return 0;
+
+bad:
+	context_free(rs);
+
+	return ret;
+}
+
+static void raid_dtr(struct dm_target *ti)
+{
+	struct raid_set *rs = ti->private;
+
+	list_del_init(&rs->callbacks.list);
+	md_stop(&rs->md);
+	context_free(rs);
+}
+
+static int raid_map(struct dm_target *ti, struct bio *bio, union map_info *map_context)
+{
+	struct raid_set *rs = ti->private;
+	mddev_t *mddev = &rs->md;
+
+	mddev->pers->make_request(mddev, bio);
+
+	return DM_MAPIO_SUBMITTED;
+}
+
+static int raid_status(struct dm_target *ti, status_type_t type,
+		       char *result, unsigned maxlen)
+{
+	struct raid_set *rs = ti->private;
+	unsigned raid_param_cnt = 1; /* at least 1 for chunksize */
+	unsigned sz = 0;
+	int i;
+	sector_t sync;
+
+	switch (type) {
+	case STATUSTYPE_INFO:
+		DMEMIT("%s %d ", rs->raid_type->name, rs->md.raid_disks);
+
+		for (i = 0; i < rs->md.raid_disks; i++) {
+			if (test_bit(Faulty, &rs->dev[i].rdev.flags))
+				DMEMIT("D");
+			else if (test_bit(In_sync, &rs->dev[i].rdev.flags))
+				DMEMIT("A");
+			else
+				DMEMIT("a");
+		}
+
+		if (test_bit(MD_RECOVERY_RUNNING, &rs->md.recovery))
+			sync = rs->md.curr_resync_completed;
+		else
+			sync = rs->md.recovery_cp;
+
+		if (sync > rs->md.resync_max_sectors)
+			sync = rs->md.resync_max_sectors;
+
+		DMEMIT(" %llu/%llu",
+		       (unsigned long long) sync,
+		       (unsigned long long) rs->md.resync_max_sectors);
+
+		break;
+	case STATUSTYPE_TABLE:
+		/* The string you would use to construct this array */
+		for (i = 0; i < rs->md.raid_disks; i++)
+			if (rs->dev[i].data_dev &&
+			    !test_bit(In_sync, &rs->dev[i].rdev.flags))
+				raid_param_cnt++; /* for rebuilds */
+
+		raid_param_cnt += (hweight64(rs->print_flags) * 2);
+		if (rs->print_flags & (DMPF_SYNC | DMPF_NOSYNC))
+			raid_param_cnt--;
+
+		DMEMIT("%s %u %u", rs->raid_type->name,
+		       raid_param_cnt, rs->md.chunk_sectors);
+
+		if ((rs->print_flags & DMPF_SYNC) &&
+		    (rs->md.recovery_cp == MaxSector))
+			DMEMIT(" sync");
+		if (rs->print_flags & DMPF_NOSYNC)
+			DMEMIT(" nosync");
+
+		for (i = 0; i < rs->md.raid_disks; i++)
+			if (rs->dev[i].data_dev &&
+			    !test_bit(In_sync, &rs->dev[i].rdev.flags))
+				DMEMIT(" rebuild %u", i);
+
+		if (rs->print_flags & DMPF_DAEMON_SLEEP)
+			DMEMIT(" daemon_sleep %lu",
+			       rs->md.bitmap_info.daemon_sleep);
+
+		if (rs->print_flags & DMPF_MIN_RECOVERY_RATE)
+			DMEMIT(" min_recovery_rate %d", rs->md.sync_speed_min);
+
+		if (rs->print_flags & DMPF_MAX_RECOVERY_RATE)
+			DMEMIT(" max_recovery_rate %d", rs->md.sync_speed_max);
+
+		if (rs->print_flags & DMPF_MAX_WRITE_BEHIND)
+			DMEMIT(" max_write_behind %lu",
+			       rs->md.bitmap_info.max_write_behind);
+
+		if (rs->print_flags & DMPF_STRIPE_CACHE) {
+			raid5_conf_t *conf = rs->md.private;
+
+			/* convert from kiB to sectors */
+			DMEMIT(" stripe_cache %d",
+			       conf ? conf->max_nr_stripes * 2 : 0);
+		}
+
+		DMEMIT(" %d", rs->md.raid_disks);
+		for (i = 0; i < rs->md.raid_disks; i++) {
+			DMEMIT(" -"); /* metadata device */
+
+			if (rs->dev[i].data_dev)
+				DMEMIT(" %s", rs->dev[i].data_dev->name);
+			else
+				DMEMIT(" -");
+		}
+	}
+
+	return 0;
+}
+
+static int raid_iterate_devices(struct dm_target *ti, iterate_devices_callout_fn fn, void *data)
+{
+	struct raid_set *rs = ti->private;
+	unsigned i;
+	int ret = 0;
+
+	for (i = 0; !ret && i < rs->md.raid_disks; i++)
+		if (rs->dev[i].data_dev)
+			ret = fn(ti,
+				 rs->dev[i].data_dev,
+				 0, /* No offset on data devs */
+				 rs->md.dev_sectors,
+				 data);
+
+	return ret;
+}
+
+static void raid_io_hints(struct dm_target *ti, struct queue_limits *limits)
+{
+	struct raid_set *rs = ti->private;
+	unsigned chunk_size = rs->md.chunk_sectors << 9;
+	raid5_conf_t *conf = rs->md.private;
+
+	blk_limits_io_min(limits, chunk_size);
+	blk_limits_io_opt(limits, chunk_size * (conf->raid_disks - conf->max_degraded));
+}
+
+static void raid_presuspend(struct dm_target *ti)
+{
+	struct raid_set *rs = ti->private;
+
+	md_stop_writes(&rs->md);
+}
+
+static void raid_postsuspend(struct dm_target *ti)
+{
+	struct raid_set *rs = ti->private;
+
+	mddev_suspend(&rs->md);
+}
+
+static void raid_resume(struct dm_target *ti)
+{
+	struct raid_set *rs = ti->private;
+
+	mddev_resume(&rs->md);
+}
+
+static struct target_type raid_target = {
+	.name = "raid",
+	.version = {1, 0, 0},
+	.module = THIS_MODULE,
+	.ctr = raid_ctr,
+	.dtr = raid_dtr,
+	.map = raid_map,
+	.status = raid_status,
+	.iterate_devices = raid_iterate_devices,
+	.io_hints = raid_io_hints,
+	.presuspend = raid_presuspend,
+	.postsuspend = raid_postsuspend,
+	.resume = raid_resume,
+};
+
+static int __init dm_raid_init(void)
+{
+	return dm_register_target(&raid_target);
+}
+
+static void __exit dm_raid_exit(void)
+{
+	dm_unregister_target(&raid_target);
+}
+
+module_init(dm_raid_init);
+module_exit(dm_raid_exit);
+
+MODULE_DESCRIPTION(DM_NAME " raid4/5/6 target");
+MODULE_ALIAS("dm-raid4");
+MODULE_ALIAS("dm-raid5");
+MODULE_ALIAS("dm-raid6");
+MODULE_AUTHOR("Neil Brown <dm-devel@redhat.com>");
+MODULE_LICENSE("GPL");

drivers/md/dm-raid1.c

@@ -261,7 +261,7 @@ static int mirror_flush(struct dm_target *ti)
 	struct dm_io_request io_req = {
 		.bi_rw = WRITE_FLUSH,
 		.mem.type = DM_IO_KMEM,
-		.mem.ptr.bvec = NULL,
+		.mem.ptr.addr = NULL,
 		.client = ms->io_client,
 	};
 
@@ -637,6 +637,12 @@ static void do_write(struct mirror_set *ms, struct bio *bio)
 		.client = ms->io_client,
 	};
 
+	if (bio->bi_rw & REQ_DISCARD) {
+		io_req.bi_rw |= REQ_DISCARD;
+		io_req.mem.type = DM_IO_KMEM;
+		io_req.mem.ptr.addr = NULL;
+	}
+
 	for (i = 0, m = ms->mirror; i < ms->nr_mirrors; i++, m++)
 		map_region(dest++, m, bio);
 
@@ -670,7 +676,8 @@ static void do_writes(struct mirror_set *ms, struct bio_list *writes)
 	bio_list_init(&requeue);
 
 	while ((bio = bio_list_pop(writes))) {
-		if (bio->bi_rw & REQ_FLUSH) {
+		if ((bio->bi_rw & REQ_FLUSH) ||
+		    (bio->bi_rw & REQ_DISCARD)) {
 			bio_list_add(&sync, bio);
 			continue;
 		}
@@ -1076,8 +1083,10 @@ static int mirror_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	ti->private = ms;
 	ti->split_io = dm_rh_get_region_size(ms->rh);
 	ti->num_flush_requests = 1;
+	ti->num_discard_requests = 1;
 
-	ms->kmirrord_wq = create_singlethread_workqueue("kmirrord");
+	ms->kmirrord_wq = alloc_workqueue("kmirrord",
+					  WQ_NON_REENTRANT | WQ_MEM_RECLAIM, 0);
 	if (!ms->kmirrord_wq) {
 		DMERR("couldn't start kmirrord");
 		r = -ENOMEM;
@@ -1130,7 +1139,7 @@ static void mirror_dtr(struct dm_target *ti)
 
 	del_timer_sync(&ms->timer);
 	flush_workqueue(ms->kmirrord_wq);
-	flush_scheduled_work();
+	flush_work_sync(&ms->trigger_event);
 	dm_kcopyd_client_destroy(ms->kcopyd_client);
 	destroy_workqueue(ms->kmirrord_wq);
 	free_context(ms, ti, ms->nr_mirrors);
@@ -1406,7 +1415,7 @@ static int mirror_iterate_devices(struct dm_target *ti,
 
 static struct target_type mirror_target = {
 	.name	 = "mirror",
-	.version = {1, 12, 0},
+	.version = {1, 12, 1},
 	.module	 = THIS_MODULE,
 	.ctr	 = mirror_ctr,
 	.dtr	 = mirror_dtr,

drivers/md/dm-snap-persistent.c

@@ -256,7 +256,7 @@ static int chunk_io(struct pstore *ps, void *area, chunk_t chunk, int rw,
 	 */
 	INIT_WORK_ONSTACK(&req.work, do_metadata);
 	queue_work(ps->metadata_wq, &req.work);
-	flush_workqueue(ps->metadata_wq);
+	flush_work(&req.work);
 
 	return req.result;
 }
@@ -818,7 +818,7 @@ static int persistent_ctr(struct dm_exception_store *store,
 	atomic_set(&ps->pending_count, 0);
 	ps->callbacks = NULL;
 
-	ps->metadata_wq = create_singlethread_workqueue("ksnaphd");
+	ps->metadata_wq = alloc_workqueue("ksnaphd", WQ_MEM_RECLAIM, 0);
 	if (!ps->metadata_wq) {
 		kfree(ps);
 		DMERR("couldn't start header metadata update thread");

drivers/md/dm-snap.c

@@ -19,7 +19,6 @@
 #include <linux/vmalloc.h>
 #include <linux/log2.h>
 #include <linux/dm-kcopyd.h>
-#include <linux/workqueue.h>
 
 #include "dm-exception-store.h"
 
@@ -80,9 +79,6 @@ struct dm_snapshot {
 	/* Origin writes don't trigger exceptions until this is set */
 	int active;
 
-	/* Whether or not owning mapped_device is suspended */
-	int suspended;
-
 	atomic_t pending_exceptions_count;
 
 	mempool_t *pending_pool;
@@ -106,10 +102,6 @@ struct dm_snapshot {
 
 	struct dm_kcopyd_client *kcopyd_client;
 
-	/* Queue of snapshot writes for ksnapd to flush */
-	struct bio_list queued_bios;
-	struct work_struct queued_bios_work;
-
 	/* Wait for events based on state_bits */
 	unsigned long state_bits;
 
@@ -160,9 +152,6 @@ struct dm_dev *dm_snap_cow(struct dm_snapshot *s)
 }
 EXPORT_SYMBOL(dm_snap_cow);
 
-static struct workqueue_struct *ksnapd;
-static void flush_queued_bios(struct work_struct *work);
-
 static sector_t chunk_to_sector(struct dm_exception_store *store,
 				chunk_t chunk)
 {
@@ -1110,7 +1099,6 @@ static int snapshot_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	s->ti = ti;
 	s->valid = 1;
 	s->active = 0;
-	s->suspended = 0;
 	atomic_set(&s->pending_exceptions_count, 0);
 	init_rwsem(&s->lock);
 	INIT_LIST_HEAD(&s->list);
@@ -1153,9 +1141,6 @@ static int snapshot_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 
 	spin_lock_init(&s->tracked_chunk_lock);
 
-	bio_list_init(&s->queued_bios);
-	INIT_WORK(&s->queued_bios_work, flush_queued_bios);
-
 	ti->private = s;
 	ti->num_flush_requests = num_flush_requests;
 
@@ -1279,8 +1264,6 @@ static void snapshot_dtr(struct dm_target *ti)
 	struct dm_snapshot *s = ti->private;
 	struct dm_snapshot *snap_src = NULL, *snap_dest = NULL;
 
-	flush_workqueue(ksnapd);
-
 	down_read(&_origins_lock);
 	/* Check whether exception handover must be cancelled */
 	(void) __find_snapshots_sharing_cow(s, &snap_src, &snap_dest, NULL);
@@ -1342,20 +1325,6 @@ static void flush_bios(struct bio *bio)
 	}
 }
 
-static void flush_queued_bios(struct work_struct *work)
-{
-	struct dm_snapshot *s =
-		container_of(work, struct dm_snapshot, queued_bios_work);
-	struct bio *queued_bios;
-	unsigned long flags;
-
-	spin_lock_irqsave(&s->pe_lock, flags);
-	queued_bios = bio_list_get(&s->queued_bios);
-	spin_unlock_irqrestore(&s->pe_lock, flags);
-
-	flush_bios(queued_bios);
-}
-
 static int do_origin(struct dm_dev *origin, struct bio *bio);
 
 /*
@@ -1760,15 +1729,6 @@ static void snapshot_merge_presuspend(struct dm_target *ti)
 	stop_merge(s);
 }
 
-static void snapshot_postsuspend(struct dm_target *ti)
-{
-	struct dm_snapshot *s = ti->private;
-
-	down_write(&s->lock);
-	s->suspended = 1;
-	up_write(&s->lock);
-}
-
 static int snapshot_preresume(struct dm_target *ti)
 {
 	int r = 0;
@@ -1783,7 +1743,7 @@ static int snapshot_preresume(struct dm_target *ti)
 			DMERR("Unable to resume snapshot source until "
 			      "handover completes.");
 			r = -EINVAL;
-		} else if (!snap_src->suspended) {
+		} else if (!dm_suspended(snap_src->ti)) {
 			DMERR("Unable to perform snapshot handover until "
 			      "source is suspended.");
 			r = -EINVAL;
@@ -1816,7 +1776,6 @@ static void snapshot_resume(struct dm_target *ti)
 
 	down_write(&s->lock);
 	s->active = 1;
-	s->suspended = 0;
 	up_write(&s->lock);
 }
 
@@ -2194,7 +2153,7 @@ static int origin_iterate_devices(struct dm_target *ti,
 
 static struct target_type origin_target = {
 	.name    = "snapshot-origin",
-	.version = {1, 7, 0},
+	.version = {1, 7, 1},
 	.module  = THIS_MODULE,
 	.ctr     = origin_ctr,
 	.dtr     = origin_dtr,
@@ -2207,13 +2166,12 @@ static struct target_type origin_target = {
 
 static struct target_type snapshot_target = {
 	.name    = "snapshot",
-	.version = {1, 9, 0},
+	.version = {1, 10, 0},
 	.module  = THIS_MODULE,
 	.ctr     = snapshot_ctr,
 	.dtr     = snapshot_dtr,
 	.map     = snapshot_map,
 	.end_io  = snapshot_end_io,
-	.postsuspend = snapshot_postsuspend,
 	.preresume  = snapshot_preresume,
 	.resume  = snapshot_resume,
 	.status  = snapshot_status,
@@ -2222,14 +2180,13 @@ static struct target_type snapshot_target = {
 
 static struct target_type merge_target = {
 	.name    = dm_snapshot_merge_target_name,
-	.version = {1, 0, 0},
+	.version = {1, 1, 0},
 	.module  = THIS_MODULE,
 	.ctr     = snapshot_ctr,
 	.dtr     = snapshot_dtr,
 	.map     = snapshot_merge_map,
 	.end_io  = snapshot_end_io,
 	.presuspend = snapshot_merge_presuspend,
-	.postsuspend = snapshot_postsuspend,
 	.preresume  = snapshot_preresume,
 	.resume  = snapshot_merge_resume,
 	.status  = snapshot_status,
@@ -2291,17 +2248,8 @@ static int __init dm_snapshot_init(void)
 		goto bad_tracked_chunk_cache;
 	}
 
-	ksnapd = create_singlethread_workqueue("ksnapd");
-	if (!ksnapd) {
-		DMERR("Failed to create ksnapd workqueue.");
-		r = -ENOMEM;
-		goto bad_pending_pool;
-	}
-
 	return 0;
 
-bad_pending_pool:
-	kmem_cache_destroy(tracked_chunk_cache);
 bad_tracked_chunk_cache:
 	kmem_cache_destroy(pending_cache);
 bad_pending_cache:
@@ -2322,8 +2270,6 @@ static int __init dm_snapshot_init(void)
 
 static void __exit dm_snapshot_exit(void)
 {
-	destroy_workqueue(ksnapd);
-
 	dm_unregister_target(&snapshot_target);
 	dm_unregister_target(&origin_target);
 	dm_unregister_target(&merge_target);

drivers/md/dm-stripe.c

@@ -39,23 +39,20 @@ struct stripe_c {
 	struct dm_target *ti;
 
 	/* Work struct used for triggering events*/
-	struct work_struct kstriped_ws;
+	struct work_struct trigger_event;
 
 	struct stripe stripe[0];
 };
 
-static struct workqueue_struct *kstriped;
-
 /*
  * An event is triggered whenever a drive
  * drops out of a stripe volume.
  */
 static void trigger_event(struct work_struct *work)
 {
-	struct stripe_c *sc = container_of(work, struct stripe_c, kstriped_ws);
-
+	struct stripe_c *sc = container_of(work, struct stripe_c,
+					   trigger_event);
 	dm_table_event(sc->ti->table);
-
 }
 
 static inline struct stripe_c *alloc_context(unsigned int stripes)
@@ -160,7 +157,7 @@ static int stripe_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 		return -ENOMEM;
 	}
 
-	INIT_WORK(&sc->kstriped_ws, trigger_event);
+	INIT_WORK(&sc->trigger_event, trigger_event);
 
 	/* Set pointer to dm target; used in trigger_event */
 	sc->ti = ti;
@@ -211,7 +208,7 @@ static void stripe_dtr(struct dm_target *ti)
 	for (i = 0; i < sc->stripes; i++)
 		dm_put_device(ti, sc->stripe[i].dev);
 
-	flush_workqueue(kstriped);
+	flush_work_sync(&sc->trigger_event);
 	kfree(sc);
 }
 
@@ -367,7 +364,7 @@ static int stripe_end_io(struct dm_target *ti, struct bio *bio,
 			atomic_inc(&(sc->stripe[i].error_count));
 			if (atomic_read(&(sc->stripe[i].error_count)) <
 			    DM_IO_ERROR_THRESHOLD)
-				queue_work(kstriped, &sc->kstriped_ws);
+				schedule_work(&sc->trigger_event);
 		}
 
 	return error;
@@ -401,7 +398,7 @@ static void stripe_io_hints(struct dm_target *ti,
 
 static struct target_type stripe_target = {
 	.name   = "striped",
-	.version = {1, 3, 0},
+	.version = {1, 3, 1},
 	.module = THIS_MODULE,
 	.ctr    = stripe_ctr,
 	.dtr    = stripe_dtr,
@@ -422,20 +419,10 @@ int __init dm_stripe_init(void)
 		return r;
 	}
 
-	kstriped = create_singlethread_workqueue("kstriped");
-	if (!kstriped) {
-		DMERR("failed to create workqueue kstriped");
-		dm_unregister_target(&stripe_target);
-		return -ENOMEM;
-	}
-
 	return r;
 }
 
 void dm_stripe_exit(void)
 {
 	dm_unregister_target(&stripe_target);
-	destroy_workqueue(kstriped);
-
-	return;
 }

drivers/md/dm-table.c

@@ -71,6 +71,8 @@ struct dm_table {
 	void *event_context;
 
 	struct dm_md_mempools *mempools;
+
+	struct list_head target_callbacks;
 };
 
 /*
@@ -204,6 +206,7 @@ int dm_table_create(struct dm_table **result, fmode_t mode,
 		return -ENOMEM;
 
 	INIT_LIST_HEAD(&t->devices);
+	INIT_LIST_HEAD(&t->target_callbacks);
 	atomic_set(&t->holders, 0);
 	t->discards_supported = 1;
 
@@ -1225,10 +1228,17 @@ int dm_table_resume_targets(struct dm_table *t)
 	return 0;
 }
 
+void dm_table_add_target_callbacks(struct dm_table *t, struct dm_target_callbacks *cb)
+{
+	list_add(&cb->list, &t->target_callbacks);
+}
+EXPORT_SYMBOL_GPL(dm_table_add_target_callbacks);
+
 int dm_table_any_congested(struct dm_table *t, int bdi_bits)
 {
 	struct dm_dev_internal *dd;
 	struct list_head *devices = dm_table_get_devices(t);
+	struct dm_target_callbacks *cb;
 	int r = 0;
 
 	list_for_each_entry(dd, devices, list) {
@@ -1243,6 +1253,10 @@ int dm_table_any_congested(struct dm_table *t, int bdi_bits)
 				     bdevname(dd->dm_dev.bdev, b));
 	}
 
+	list_for_each_entry(cb, &t->target_callbacks, list)
+		if (cb->congested_fn)
+			r |= cb->congested_fn(cb, bdi_bits);
+
 	return r;
 }
 
@@ -1264,6 +1278,7 @@ void dm_table_unplug_all(struct dm_table *t)
 {
 	struct dm_dev_internal *dd;
 	struct list_head *devices = dm_table_get_devices(t);
+	struct dm_target_callbacks *cb;
 
 	list_for_each_entry(dd, devices, list) {
 		struct request_queue *q = bdev_get_queue(dd->dm_dev.bdev);
@@ -1276,6 +1291,10 @@ void dm_table_unplug_all(struct dm_table *t)
 				     dm_device_name(t->md),
 				     bdevname(dd->dm_dev.bdev, b));
 	}
+
+	list_for_each_entry(cb, &t->target_callbacks, list)
+		if (cb->unplug_fn)
+			cb->unplug_fn(cb);
 }
 
 struct mapped_device *dm_table_get_md(struct dm_table *t)

drivers/md/dm.c

@@ -32,7 +32,6 @@
 #define DM_COOKIE_ENV_VAR_NAME "DM_COOKIE"
 #define DM_COOKIE_LENGTH 24
 
-static DEFINE_MUTEX(dm_mutex);
 static const char *_name = DM_NAME;
 
 static unsigned int major = 0;
@@ -328,7 +327,6 @@ static int dm_blk_open(struct block_device *bdev, fmode_t mode)
 {
 	struct mapped_device *md;
 
-	mutex_lock(&dm_mutex);
 	spin_lock(&_minor_lock);
 
 	md = bdev->bd_disk->private_data;
@@ -346,7 +344,6 @@ static int dm_blk_open(struct block_device *bdev, fmode_t mode)
 
 out:
 	spin_unlock(&_minor_lock);
-	mutex_unlock(&dm_mutex);
 
 	return md ? 0 : -ENXIO;
 }
@@ -355,10 +352,12 @@ static int dm_blk_close(struct gendisk *disk, fmode_t mode)
 {
 	struct mapped_device *md = disk->private_data;
 
-	mutex_lock(&dm_mutex);
+	spin_lock(&_minor_lock);
+
 	atomic_dec(&md->open_count);
 	dm_put(md);
-	mutex_unlock(&dm_mutex);
+
+	spin_unlock(&_minor_lock);
 
 	return 0;
 }
@@ -1638,13 +1637,15 @@ static void dm_request_fn(struct request_queue *q)
 		if (map_request(ti, clone, md))
 			goto requeued;
 
-		spin_lock_irq(q->queue_lock);
+		BUG_ON(!irqs_disabled());
+		spin_lock(q->queue_lock);
 	}
 
 	goto out;
 
 requeued:
-	spin_lock_irq(q->queue_lock);
+	BUG_ON(!irqs_disabled());
+	spin_lock(q->queue_lock);
 
 plug_and_out:
 	if (!elv_queue_empty(q))
@@ -1884,7 +1885,8 @@ static struct mapped_device *alloc_dev(int minor)
 	add_disk(md->disk);
 	format_dev_t(md->name, MKDEV(_major, minor));
 
-	md->wq = create_singlethread_workqueue("kdmflush");
+	md->wq = alloc_workqueue("kdmflush",
+				 WQ_NON_REENTRANT | WQ_MEM_RECLAIM, 0);
 	if (!md->wq)
 		goto bad_thread;
 
@@ -1992,13 +1994,14 @@ static void event_callback(void *context)
 	wake_up(&md->eventq);
 }
 
+/*
+ * Protected by md->suspend_lock obtained by dm_swap_table().
+ */
 static void __set_size(struct mapped_device *md, sector_t size)
 {
 	set_capacity(md->disk, size);
 
-	mutex_lock(&md->bdev->bd_inode->i_mutex);
 	i_size_write(md->bdev->bd_inode, (loff_t)size << SECTOR_SHIFT);
-	mutex_unlock(&md->bdev->bd_inode->i_mutex);
 }
 
 /*

include/linux/device-mapper.h

@@ -193,6 +193,13 @@ struct dm_target {
 	char *error;
 };
 
+/* Each target can link one of these into the table */
+struct dm_target_callbacks {
+	struct list_head list;
+	int (*congested_fn) (struct dm_target_callbacks *, int);
+	void (*unplug_fn)(struct dm_target_callbacks *);
+};
+
 int dm_register_target(struct target_type *t);
 void dm_unregister_target(struct target_type *t);
 
@@ -268,6 +275,11 @@ int dm_table_create(struct dm_table **result, fmode_t mode,
 int dm_table_add_target(struct dm_table *t, const char *type,
 			sector_t start, sector_t len, char *params);
 
+/*
+ * Target_ctr should call this if it needs to add any callbacks.
+ */
+void dm_table_add_target_callbacks(struct dm_table *t, struct dm_target_callbacks *cb);
+
 /*
  * Finally call this to make the table ready for use.
  */

include/linux/dm-ioctl.h

@@ -44,7 +44,7 @@
  * Remove a device, destroy any tables.
  *
  * DM_DEV_RENAME:
- * Rename a device.
+ * Rename a device or set its uuid if none was previously supplied.
  *
  * DM_SUSPEND:
  * This performs both suspend and resume, depending which flag is
@@ -267,9 +267,9 @@ enum {
 #define DM_DEV_SET_GEOMETRY	_IOWR(DM_IOCTL, DM_DEV_SET_GEOMETRY_CMD, struct dm_ioctl)
 
 #define DM_VERSION_MAJOR	4
-#define DM_VERSION_MINOR	18
-#define DM_VERSION_PATCHLEVEL	0
-#define DM_VERSION_EXTRA	"-ioctl (2010-06-29)"
+#define DM_VERSION_MINOR	19
+#define DM_VERSION_PATCHLEVEL	1
+#define DM_VERSION_EXTRA	"-ioctl (2011-01-07)"
 
 /* Status bits */
 #define DM_READONLY_FLAG	(1 << 0) /* In/Out */
@@ -322,4 +322,10 @@ enum {
  */
 #define DM_UEVENT_GENERATED_FLAG	(1 << 13) /* Out */
 
+/*
+ * If set, rename changes the uuid not the name.  Only permitted
+ * if no uuid was previously supplied: an existing uuid cannot be changed.
+ */
+#define DM_UUID_FLAG			(1 << 14) /* In */
+
 #endif				/* _LINUX_DM_IOCTL_H */

include/linux/dm-log-userspace.h

@@ -370,6 +370,16 @@
 #define DM_ULOG_REQUEST_TYPE(request_type) \
 	(DM_ULOG_REQUEST_MASK & (request_type))
 
+/*
+ * DM_ULOG_REQUEST_VERSION is incremented when there is a
+ * change to the way information is passed between kernel
+ * and userspace.  This could be a structure change of
+ * dm_ulog_request or a change in the way requests are
+ * issued/handled.  Changes are outlined here:
+ *	version 1:  Initial implementation
+ */
+#define DM_ULOG_REQUEST_VERSION 1
+
 struct dm_ulog_request {
 	/*
 	 * The local unique identifier (luid) and the universally unique
@@ -383,8 +393,9 @@ struct dm_ulog_request {
 	 */
 	uint64_t luid;
 	char uuid[DM_UUID_LEN];
-	char padding[7];        /* Padding because DM_UUID_LEN = 129 */
+	char padding[3];        /* Padding because DM_UUID_LEN = 129 */
 
+	uint32_t version;       /* See DM_ULOG_REQUEST_VERSION */
 	int32_t error;          /* Used to report back processing errors */
 
 	uint32_t seq;           /* Sequence number for request */