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: (48 commits)
  dm mpath: change to be request based
  dm: disable interrupt when taking map_lock
  dm: do not set QUEUE_ORDERED_DRAIN if request based
  dm: enable request based option
  dm: prepare for request based option
  dm raid1: add userspace log
  dm: calculate queue limits during resume not load
  dm log: fix create_log_context to use logical_block_size of log device
  dm target:s introduce iterate devices fn
  dm table: establish queue limits by copying table limits
  dm table: replace struct io_restrictions with struct queue_limits
  dm table: validate device logical_block_size
  dm table: ensure targets are aligned to logical_block_size
  dm ioctl: support cookies for udev
  dm: sysfs add suspended attribute
  dm table: improve warning message when devices not freed before destruction
  dm mpath: add service time load balancer
  dm mpath: add queue length load balancer
  dm mpath: add start_io and nr_bytes to path selectors
  dm snapshot: use barrier when writing exception store
  ...

35 files changed, 3993 insertions, 435 deletions

diff --git a/Documentation/device-mapper/dm-log.txt b/Documentation/device-mapper/dm-log.txt
new file mode 100644
index 00000000000..994dd75475a
--- /dev/null
+++ b/Documentation/device-mapper/dm-log.txt
@@ -0,0 +1,54 @@
+Device-Mapper Logging
+=====================
+The device-mapper logging code is used by some of the device-mapper
+RAID targets to track regions of the disk that are not consistent.
+A region (or portion of the address space) of the disk may be
+inconsistent because a RAID stripe is currently being operated on or
+a machine died while the region was being altered.  In the case of
+mirrors, a region would be considered dirty/inconsistent while you
+are writing to it because the writes need to be replicated for all
+the legs of the mirror and may not reach the legs at the same time.
+Once all writes are complete, the region is considered clean again.
+
+There is a generic logging interface that the device-mapper RAID
+implementations use to perform logging operations (see
+dm_dirty_log_type in include/linux/dm-dirty-log.h).  Various different
+logging implementations are available and provide different
+capabilities.  The list includes:
+
+Type		Files
+====		=====
+disk		drivers/md/dm-log.c
+core		drivers/md/dm-log.c
+userspace	drivers/md/dm-log-userspace* include/linux/dm-log-userspace.h
+
+The "disk" log type
+-------------------
+This log implementation commits the log state to disk.  This way, the
+logging state survives reboots/crashes.
+
+The "core" log type
+-------------------
+This log implementation keeps the log state in memory.  The log state
+will not survive a reboot or crash, but there may be a small boost in
+performance.  This method can also be used if no storage device is
+available for storing log state.
+
+The "userspace" log type
+------------------------
+This log type simply provides a way to export the log API to userspace,
+so log implementations can be done there.  This is done by forwarding most
+logging requests to userspace, where a daemon receives and processes the
+request.
+
+The structure used for communication between kernel and userspace are
+located in include/linux/dm-log-userspace.h.  Due to the frequency,
+diversity, and 2-way communication nature of the exchanges between
+kernel and userspace, 'connector' is used as the interface for
+communication.
+
+There are currently two userspace log implementations that leverage this
+framework - "clustered_disk" and "clustered_core".  These implementations
+provide a cluster-coherent log for shared-storage.  Device-mapper mirroring
+can be used in a shared-storage environment when the cluster log implementations
+are employed.
diff --git a/Documentation/device-mapper/dm-queue-length.txt b/Documentation/device-mapper/dm-queue-length.txt
new file mode 100644
index 00000000000..f4db2562175
--- /dev/null
+++ b/Documentation/device-mapper/dm-queue-length.txt
@@ -0,0 +1,39 @@
+dm-queue-length
+===============
+
+dm-queue-length is a path selector module for device-mapper targets,
+which selects a path with the least number of in-flight I/Os.
+The path selector name is 'queue-length'.
+
+Table parameters for each path: [<repeat_count>]
+	<repeat_count>: The number of I/Os to dispatch using the selected
+			path before switching to the next path.
+			If not given, internal default is used. To check
+			the default value, see the activated table.
+
+Status for each path: <status> <fail-count> <in-flight>
+	<status>: 'A' if the path is active, 'F' if the path is failed.
+	<fail-count>: The number of path failures.
+	<in-flight>: The number of in-flight I/Os on the path.
+
+
+Algorithm
+=========
+
+dm-queue-length increments/decrements 'in-flight' when an I/O is
+dispatched/completed respectively.
+dm-queue-length selects a path with the minimum 'in-flight'.
+
+
+Examples
+========
+In case that 2 paths (sda and sdb) are used with repeat_count == 128.
+
+# echo "0 10 multipath 0 0 1 1 queue-length 0 2 1 8:0 128 8:16 128" \
+  dmsetup create test
+#
+# dmsetup table
+test: 0 10 multipath 0 0 1 1 queue-length 0 2 1 8:0 128 8:16 128
+#
+# dmsetup status
+test: 0 10 multipath 2 0 0 0 1 1 E 0 2 1 8:0 A 0 0 8:16 A 0 0
diff --git a/Documentation/device-mapper/dm-service-time.txt b/Documentation/device-mapper/dm-service-time.txt
new file mode 100644
index 00000000000..7d00668e97b
--- /dev/null
+++ b/Documentation/device-mapper/dm-service-time.txt
@@ -0,0 +1,91 @@
+dm-service-time
+===============
+
+dm-service-time is a path selector module for device-mapper targets,
+which selects a path with the shortest estimated service time for
+the incoming I/O.
+
+The service time for each path is estimated by dividing the total size
+of in-flight I/Os on a path with the performance value of the path.
+The performance value is a relative throughput value among all paths
+in a path-group, and it can be specified as a table argument.
+
+The path selector name is 'service-time'.
+
+Table parameters for each path: [<repeat_count> [<relative_throughput>]]
+	<repeat_count>: The number of I/Os to dispatch using the selected
+			path before switching to the next path.
+			If not given, internal default is used.  To check
+			the default value, see the activated table.
+	<relative_throughput>: The relative throughput value of the path
+			among all paths in the path-group.
+			The valid range is 0-100.
+			If not given, minimum value '1' is used.
+			If '0' is given, the path isn't selected while
+			other paths having a positive value are available.
+
+Status for each path: <status> <fail-count> <in-flight-size> \
+		      <relative_throughput>
+	<status>: 'A' if the path is active, 'F' if the path is failed.
+	<fail-count>: The number of path failures.
+	<in-flight-size>: The size of in-flight I/Os on the path.
+	<relative_throughput>: The relative throughput value of the path
+			among all paths in the path-group.
+
+
+Algorithm
+=========
+
+dm-service-time adds the I/O size to 'in-flight-size' when the I/O is
+dispatched and substracts when completed.
+Basically, dm-service-time selects a path having minimum service time
+which is calculated by:
+
+	('in-flight-size' + 'size-of-incoming-io') / 'relative_throughput'
+
+However, some optimizations below are used to reduce the calculation
+as much as possible.
+
+	1. If the paths have the same 'relative_throughput', skip
+	   the division and just compare the 'in-flight-size'.
+
+	2. If the paths have the same 'in-flight-size', skip the division
+	   and just compare the 'relative_throughput'.
+
+	3. If some paths have non-zero 'relative_throughput' and others
+	   have zero 'relative_throughput', ignore those paths with zero
+	   'relative_throughput'.
+
+If such optimizations can't be applied, calculate service time, and
+compare service time.
+If calculated service time is equal, the path having maximum
+'relative_throughput' may be better.  So compare 'relative_throughput'
+then.
+
+
+Examples
+========
+In case that 2 paths (sda and sdb) are used with repeat_count == 128
+and sda has an average throughput 1GB/s and sdb has 4GB/s,
+'relative_throughput' value may be '1' for sda and '4' for sdb.
+
+# echo "0 10 multipath 0 0 1 1 service-time 0 2 2 8:0 128 1 8:16 128 4" \
+  dmsetup create test
+#
+# dmsetup table
+test: 0 10 multipath 0 0 1 1 service-time 0 2 2 8:0 128 1 8:16 128 4
+#
+# dmsetup status
+test: 0 10 multipath 2 0 0 0 1 1 E 0 2 2 8:0 A 0 0 1 8:16 A 0 0 4
+
+
+Or '2' for sda and '8' for sdb would be also true.
+
+# echo "0 10 multipath 0 0 1 1 service-time 0 2 2 8:0 128 2 8:16 128 8" \
+  dmsetup create test
+#
+# dmsetup table
+test: 0 10 multipath 0 0 1 1 service-time 0 2 2 8:0 128 2 8:16 128 8
+#
+# dmsetup status
+test: 0 10 multipath 2 0 0 0 1 1 E 0 2 2 8:0 A 0 0 2 8:16 A 0 0 8
diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig
index 36e0675be9f..020f9573fd8 100644
--- a/drivers/md/Kconfig
+++ b/drivers/md/Kconfig
@@ -231,6 +231,17 @@ config DM_MIRROR
          Allow volume managers to mirror logical volumes, also
          needed for live data migration tools such as 'pvmove'.
 
+config DM_LOG_USERSPACE
+	tristate "Mirror userspace logging (EXPERIMENTAL)"
+	depends on DM_MIRROR && EXPERIMENTAL && NET
+	select CONNECTOR
+	---help---
+	  The userspace logging module provides a mechanism for
+	  relaying the dm-dirty-log API to userspace.  Log designs
+	  which are more suited to userspace implementation (e.g.
+	  shared storage logs) or experimental logs can be implemented
+	  by leveraging this framework.
+
 config DM_ZERO
 	tristate "Zero target"
 	depends on BLK_DEV_DM
@@ -249,6 +260,25 @@ config DM_MULTIPATH
 	---help---
 	  Allow volume managers to support multipath hardware.
 
+config DM_MULTIPATH_QL
+	tristate "I/O Path Selector based on the number of in-flight I/Os"
+	depends on DM_MULTIPATH
+	---help---
+	  This path selector is a dynamic load balancer which selects
+	  the path with the least number of in-flight I/Os.
+
+	  If unsure, say N.
+
+config DM_MULTIPATH_ST
+	tristate "I/O Path Selector based on the service time"
+	depends on DM_MULTIPATH
+	---help---
+	  This path selector is a dynamic load balancer which selects
+	  the path expected to complete the incoming I/O in the shortest
+	  time.
+
+	  If unsure, say N.
+
 config DM_DELAY
 	tristate "I/O delaying target (EXPERIMENTAL)"
 	depends on BLK_DEV_DM && EXPERIMENTAL
diff --git a/drivers/md/Makefile b/drivers/md/Makefile
index 45cc5951d92..1dc4185bd78 100644
--- a/drivers/md/Makefile
+++ b/drivers/md/Makefile
@@ -8,6 +8,8 @@ dm-multipath-y	+= dm-path-selector.o dm-mpath.o
 dm-snapshot-y	+= dm-snap.o dm-exception-store.o dm-snap-transient.o \
 		    dm-snap-persistent.o
 dm-mirror-y	+= dm-raid1.o
+dm-log-userspace-y \
+		+= dm-log-userspace-base.o dm-log-userspace-transfer.o
 md-mod-y	+= md.o bitmap.o
 raid456-y	+= raid5.o
 raid6_pq-y	+= raid6algos.o raid6recov.o raid6tables.o \
@@ -36,8 +38,11 @@ obj-$(CONFIG_BLK_DEV_DM)	+= dm-mod.o
 obj-$(CONFIG_DM_CRYPT)		+= dm-crypt.o
 obj-$(CONFIG_DM_DELAY)		+= dm-delay.o
 obj-$(CONFIG_DM_MULTIPATH)	+= dm-multipath.o dm-round-robin.o
+obj-$(CONFIG_DM_MULTIPATH_QL)	+= dm-queue-length.o
+obj-$(CONFIG_DM_MULTIPATH_ST)	+= dm-service-time.o
 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
 
 quiet_cmd_unroll = UNROLL  $@
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 53394e863c7..9933eb861c7 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -1132,6 +1132,7 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 		goto bad_crypt_queue;
 	}
 
+	ti->num_flush_requests = 1;
 	ti->private = cc;
 	return 0;
 
@@ -1189,6 +1190,13 @@ static int crypt_map(struct dm_target *ti, struct bio *bio,
 		     union map_info *map_context)
 {
 	struct dm_crypt_io *io;
+	struct crypt_config *cc;
+
+	if (unlikely(bio_empty_barrier(bio))) {
+		cc = ti->private;
+		bio->bi_bdev = cc->dev->bdev;
+		return DM_MAPIO_REMAPPED;
+	}
 
 	io = crypt_io_alloc(ti, bio, bio->bi_sector - ti->begin);
 
@@ -1305,9 +1313,17 @@ static int crypt_merge(struct dm_target *ti, struct bvec_merge_data *bvm,
 	return min(max_size, q->merge_bvec_fn(q, bvm, biovec));
 }
 
+static int crypt_iterate_devices(struct dm_target *ti,
+				 iterate_devices_callout_fn fn, void *data)
+{
+	struct crypt_config *cc = ti->private;
+
+	return fn(ti, cc->dev, cc->start, data);
+}
+
 static struct target_type crypt_target = {
 	.name   = "crypt",
-	.version= {1, 6, 0},
+	.version = {1, 7, 0},
 	.module = THIS_MODULE,
 	.ctr    = crypt_ctr,
 	.dtr    = crypt_dtr,
@@ -1318,6 +1334,7 @@ static struct target_type crypt_target = {
 	.resume = crypt_resume,
 	.message = crypt_message,
 	.merge  = crypt_merge,
+	.iterate_devices = crypt_iterate_devices,
 };
 
 static int __init dm_crypt_init(void)
diff --git a/drivers/md/dm-delay.c b/drivers/md/dm-delay.c
index 559dbb52bc8..4e5b843cd4d 100644
--- a/drivers/md/dm-delay.c
+++ b/drivers/md/dm-delay.c
@@ -197,6 +197,7 @@ out:
 	mutex_init(&dc->timer_lock);
 	atomic_set(&dc->may_delay, 1);
 
+	ti->num_flush_requests = 1;
 	ti->private = dc;
 	return 0;
 
@@ -278,8 +279,9 @@ static int delay_map(struct dm_target *ti, struct bio *bio,
 
 	if ((bio_data_dir(bio) == WRITE) && (dc->dev_write)) {
 		bio->bi_bdev = dc->dev_write->bdev;
-		bio->bi_sector = dc->start_write +
-				 (bio->bi_sector - ti->begin);
+		if (bio_sectors(bio))
+			bio->bi_sector = dc->start_write +
+					 (bio->bi_sector - ti->begin);
 
 		return delay_bio(dc, dc->write_delay, bio);
 	}
@@ -316,9 +318,26 @@ static int delay_status(struct dm_target *ti, status_type_t type,
 	return 0;
 }
 
+static int delay_iterate_devices(struct dm_target *ti,
+				 iterate_devices_callout_fn fn, void *data)
+{
+	struct delay_c *dc = ti->private;
+	int ret = 0;
+
+	ret = fn(ti, dc->dev_read, dc->start_read, data);
+	if (ret)
+		goto out;
+
+	if (dc->dev_write)
+		ret = fn(ti, dc->dev_write, dc->start_write, data);
+
+out:
+	return ret;
+}
+
 static struct target_type delay_target = {
 	.name	     = "delay",
-	.version     = {1, 0, 2},
+	.version     = {1, 1, 0},
 	.module      = THIS_MODULE,
 	.ctr	     = delay_ctr,
 	.dtr	     = delay_dtr,
@@ -326,6 +345,7 @@ static struct target_type delay_target = {
 	.presuspend  = delay_presuspend,
 	.resume	     = delay_resume,
 	.status	     = delay_status,
+	.iterate_devices = delay_iterate_devices,
 };
 
 static int __init dm_delay_init(void)
diff --git a/drivers/md/dm-exception-store.c b/drivers/md/dm-exception-store.c
index 75d8081a904..c3ae51584b1 100644
--- a/drivers/md/dm-exception-store.c
+++ b/drivers/md/dm-exception-store.c
@@ -216,7 +216,7 @@ int dm_exception_store_create(struct dm_target *ti, int argc, char **argv,
 		return -EINVAL;
 	}
 
-	type = get_type(argv[1]);
+	type = get_type(&persistent);
 	if (!type) {
 		ti->error = "Exception store type not recognised";
 		r = -EINVAL;
diff --git a/drivers/md/dm-exception-store.h b/drivers/md/dm-exception-store.h
index c92701dc500..2442c8c0789 100644
--- a/drivers/md/dm-exception-store.h
+++ b/drivers/md/dm-exception-store.h
@@ -156,7 +156,7 @@ static inline void dm_consecutive_chunk_count_inc(struct dm_snap_exception *e)
  */
 static inline sector_t get_dev_size(struct block_device *bdev)
 {
-	return bdev->bd_inode->i_size >> SECTOR_SHIFT;
+	return i_size_read(bdev->bd_inode) >> SECTOR_SHIFT;
 }
 
 static inline chunk_t sector_to_chunk(struct dm_exception_store *store,
diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c
index e73aabd61cd..3a2e6a2f8bd 100644
--- a/drivers/md/dm-io.c
+++ b/drivers/md/dm-io.c
@@ -22,6 +22,7 @@ struct dm_io_client {
 /* FIXME: can we shrink this ? */
 struct io {
 	unsigned long error_bits;
+	unsigned long eopnotsupp_bits;
 	atomic_t count;
 	struct task_struct *sleeper;
 	struct dm_io_client *client;
@@ -107,8 +108,11 @@ static inline unsigned bio_get_region(struct bio *bio)
  *---------------------------------------------------------------*/
 static void dec_count(struct io *io, unsigned int region, int error)
 {
-	if (error)
+	if (error) {
 		set_bit(region, &io->error_bits);
+		if (error == -EOPNOTSUPP)
+			set_bit(region, &io->eopnotsupp_bits);
+	}
 
 	if (atomic_dec_and_test(&io->count)) {
 		if (io->sleeper)
@@ -360,7 +364,9 @@ static int sync_io(struct dm_io_client *client, unsigned int num_regions,
 		return -EIO;
 	}
 
+retry:
 	io.error_bits = 0;
+	io.eopnotsupp_bits = 0;
 	atomic_set(&io.count, 1); /* see dispatch_io() */
 	io.sleeper = current;
 	io.client = client;
@@ -377,6 +383,11 @@ static int sync_io(struct dm_io_client *client, unsigned int num_regions,
 	}
 	set_current_state(TASK_RUNNING);
 
+	if (io.eopnotsupp_bits && (rw & (1 << BIO_RW_BARRIER))) {
+		rw &= ~(1 << BIO_RW_BARRIER);
+		goto retry;
+	}
+
 	if (error_bits)
 		*error_bits = io.error_bits;
 
@@ -397,6 +408,7 @@ static int async_io(struct dm_io_client *client, unsigned int num_regions,
 
 	io = mempool_alloc(client->pool, GFP_NOIO);
 	io->error_bits = 0;
+	io->eopnotsupp_bits = 0;
 	atomic_set(&io->count, 1); /* see dispatch_io() */
 	io->sleeper = NULL;
 	io->client = client;
diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c
index 1128d3fba79..7f77f18fcaf 100644
--- a/drivers/md/dm-ioctl.c
+++ b/drivers/md/dm-ioctl.c
@@ -276,7 +276,7 @@ retry:
 	up_write(&_hash_lock);
 }
 
-static int dm_hash_rename(const char *old, const char *new)
+static int dm_hash_rename(uint32_t cookie, const char *old, const char *new)
 {
 	char *new_name, *old_name;
 	struct hash_cell *hc;
@@ -333,7 +333,7 @@ static int dm_hash_rename(const char *old, const char *new)
 		dm_table_put(table);
 	}
 
-	dm_kobject_uevent(hc->md);
+	dm_kobject_uevent(hc->md, KOBJ_CHANGE, cookie);
 
 	dm_put(hc->md);
 	up_write(&_hash_lock);
@@ -680,6 +680,9 @@ static int dev_remove(struct dm_ioctl *param, size_t param_size)
 
 	__hash_remove(hc);
 	up_write(&_hash_lock);
+
+	dm_kobject_uevent(md, KOBJ_REMOVE, param->event_nr);
+
 	dm_put(md);
 	param->data_size = 0;
 	return 0;
@@ -715,7 +718,7 @@ static int dev_rename(struct dm_ioctl *param, size_t param_size)
 		return r;
 
 	param->data_size = 0;
-	return dm_hash_rename(param->name, new_name);
+	return dm_hash_rename(param->event_nr, param->name, new_name);
 }
 
 static int dev_set_geometry(struct dm_ioctl *param, size_t param_size)
@@ -842,8 +845,11 @@ static int do_resume(struct dm_ioctl *param)
 	if (dm_suspended(md))
 		r = dm_resume(md);
 
-	if (!r)
+
+	if (!r) {
+		dm_kobject_uevent(md, KOBJ_CHANGE, param->event_nr);
 		r = __dev_status(md, param);
+	}
 
 	dm_put(md);
 	return r;
@@ -1044,6 +1050,12 @@ static int populate_table(struct dm_table *table,
 		next = spec->next;
 	}
 
+	r = dm_table_set_type(table);
+	if (r) {
+		DMWARN("unable to set table type");
+		return r;
+	}
+
 	return dm_table_complete(table);
 }
 
@@ -1089,6 +1101,13 @@ static int table_load(struct dm_ioctl *param, size_t param_size)
 		goto out;
 	}
 
+	r = dm_table_alloc_md_mempools(t);
+	if (r) {
+		DMWARN("unable to allocate mempools for this table");
+		dm_table_destroy(t);
+		goto out;
+	}
+
 	down_write(&_hash_lock);
 	hc = dm_get_mdptr(md);
 	if (!hc || hc->md != md) {
diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c
index 79fb53e51c7..9184b6deb86 100644
--- a/drivers/md/dm-linear.c
+++ b/drivers/md/dm-linear.c
@@ -53,6 +53,7 @@ static int linear_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 		goto bad;
 	}
 
+	ti->num_flush_requests = 1;
 	ti->private = lc;
 	return 0;
 
@@ -81,7 +82,8 @@ static void linear_map_bio(struct dm_target *ti, struct bio *bio)
 	struct linear_c *lc = ti->private;
 
 	bio->bi_bdev = lc->dev->bdev;
-	bio->bi_sector = linear_map_sector(ti, bio->bi_sector);
+	if (bio_sectors(bio))
+		bio->bi_sector = linear_map_sector(ti, bio->bi_sector);
 }
 
 static int linear_map(struct dm_target *ti, struct bio *bio,
@@ -132,9 +134,17 @@ static int linear_merge(struct dm_target *ti, struct bvec_merge_data *bvm,
 	return min(max_size, q->merge_bvec_fn(q, bvm, biovec));
 }
 
+static int linear_iterate_devices(struct dm_target *ti,
+				  iterate_devices_callout_fn fn, void *data)
+{
+	struct linear_c *lc = ti->private;
+
+	return fn(ti, lc->dev, lc->start, data);
+}
+
 static struct target_type linear_target = {
 	.name   = "linear",
-	.version= {1, 0, 3},
+	.version = {1, 1, 0},
 	.module = THIS_MODULE,
 	.ctr    = linear_ctr,
 	.dtr    = linear_dtr,
@@ -142,6 +152,7 @@ static struct target_type linear_target = {
 	.status = linear_status,
 	.ioctl  = linear_ioctl,
 	.merge  = linear_merge,
+	.iterate_devices = linear_iterate_devices,
 };
 
 int __init dm_linear_init(void)
diff --git a/drivers/md/dm-log-userspace-base.c b/drivers/md/dm-log-userspace-base.c
new file mode 100644
index 00000000000..e69b9656099
--- /dev/null
+++ b/drivers/md/dm-log-userspace-base.c
@@ -0,0 +1,696 @@
+/*
+ * Copyright (C) 2006-2009 Red Hat, Inc.
+ *
+ * This file is released under the LGPL.
+ */
+
+#include <linux/bio.h>
+#include <linux/dm-dirty-log.h>
+#include <linux/device-mapper.h>
+#include <linux/dm-log-userspace.h>
+
+#include "dm-log-userspace-transfer.h"
+
+struct flush_entry {
+	int type;
+	region_t region;
+	struct list_head list;
+};
+
+struct log_c {
+	struct dm_target *ti;
+	uint32_t region_size;
+	region_t region_count;
+	char uuid[DM_UUID_LEN];
+
+	char *usr_argv_str;
+	uint32_t usr_argc;
+
+	/*
+	 * in_sync_hint gets set when doing is_remote_recovering.  It
+	 * represents the first region that needs recovery.  IOW, the
+	 * first zero bit of sync_bits.  This can be useful for to limit
+	 * traffic for calls like is_remote_recovering and get_resync_work,
+	 * but be take care in its use for anything else.
+	 */
+	uint64_t in_sync_hint;
+
+	spinlock_t flush_lock;
+	struct list_head flush_list;  /* only for clear and mark requests */
+};
+
+static mempool_t *flush_entry_pool;
+
+static void *flush_entry_alloc(gfp_t gfp_mask, void *pool_data)
+{
+	return kmalloc(sizeof(struct flush_entry), gfp_mask);
+}
+
+static void flush_entry_free(void *element, void *pool_data)
+{
+	kfree(element);
+}
+
+static int userspace_do_request(struct log_c *lc, const char *uuid,
+				int request_type, char *data, size_t data_size,
+				char *rdata, size_t *rdata_size)
+{
+	int r;
+
+	/*
+	 * If the server isn't there, -ESRCH is returned,
+	 * and we must keep trying until the server is
+	 * restored.
+	 */
+retry:
+	r = dm_consult_userspace(uuid, request_type, data,
+				 data_size, rdata, rdata_size);
+
+	if (r != -ESRCH)
+		return r;
+
+	DMERR(" Userspace log server not found.");
+	while (1) {
+		set_current_state(TASK_INTERRUPTIBLE);
+		schedule_timeout(2*HZ);
+		DMWARN("Attempting to contact userspace log server...");
+		r = dm_consult_userspace(uuid, DM_ULOG_CTR, lc->usr_argv_str,
+					 strlen(lc->usr_argv_str) + 1,
+					 NULL, NULL);
+		if (!r)
+			break;
+	}
+	DMINFO("Reconnected to userspace log server... DM_ULOG_CTR complete");
+	r = dm_consult_userspace(uuid, DM_ULOG_RESUME, NULL,
+				 0, NULL, NULL);
+	if (!r)
+		goto retry;
+
+	DMERR("Error trying to resume userspace log: %d", r);
+
+	return -ESRCH;
+}
+
+static int build_constructor_string(struct dm_target *ti,
+				    unsigned argc, char **argv,
+				    char **ctr_str)
+{
+	int i, str_size;
+	char *str = NULL;
+
+	*ctr_str = NULL;
+
+	for (i = 0, str_size = 0; i < argc; i++)
+		str_size += strlen(argv[i]) + 1; /* +1 for space between args */
+
+	str_size += 20; /* Max number of chars in a printed u64 number */
+
+	str = kzalloc(str_size, GFP_KERNEL);
+	if (!str) {
+		DMWARN("Unable to allocate memory for constructor string");
+		return -ENOMEM;
+	}
+
+	for (i = 0, str_size = 0; i < argc; i++)
+		str_size += sprintf(str + str_size, "%s ", argv[i]);
+	str_size += sprintf(str + str_size, "%llu",
+			    (unsigned long long)ti->len);
+
+	*ctr_str = str;
+	return str_size;
+}
+
+/*
+ * userspace_ctr
+ *
+ * argv contains:
+ *	<UUID> <other args>
+ * Where 'other args' is the userspace implementation specific log
+ * arguments.  An example might be:
+ *	<UUID> clustered_disk <arg count> <log dev> <region_size> [[no]sync]
+ *
+ * So, this module will strip off the <UUID> for identification purposes
+ * when communicating with userspace about a log; but will pass on everything
+ * else.
+ */
+static int userspace_ctr(struct dm_dirty_log *log, struct dm_target *ti,
+			 unsigned argc, char **argv)
+{
+	int r = 0;
+	int str_size;
+	char *ctr_str = NULL;
+	struct log_c *lc = NULL;
+	uint64_t rdata;
+	size_t rdata_size = sizeof(rdata);
+
+	if (argc < 3) {
+		DMWARN("Too few arguments to userspace dirty log");
+		return -EINVAL;
+	}
+
+	lc = kmalloc(sizeof(*lc), GFP_KERNEL);
+	if (!lc) {
+		DMWARN("Unable to allocate userspace log context.");
+		return -ENOMEM;
+	}
+
+	lc->ti = ti;
+
+	if (strlen(argv[0]) > (DM_UUID_LEN - 1)) {
+		DMWARN("UUID argument too long.");
+		kfree(lc);
+		return -EINVAL;
+	}
+
+	strncpy(lc->uuid, argv[0], DM_UUID_LEN);
+	spin_lock_init(&lc->flush_lock);
+	INIT_LIST_HEAD(&lc->flush_list);
+
+	str_size = build_constructor_string(ti, argc - 1, argv + 1, &ctr_str);
+	if (str_size < 0) {
+		kfree(lc);
+		return str_size;
+	}
+
+	/* Send table string */
+	r = dm_consult_userspace(lc->uuid, DM_ULOG_CTR,
+				 ctr_str, str_size, NULL, NULL);
+
+	if (r == -ESRCH) {
+		DMERR("Userspa