From 542f90381422676544382d4071ba44a2de90a0c1 Mon Sep 17 00:00:00 2001
From: Mike Snitzer <snitzer@redhat.com>
Date: Fri, 27 Jul 2012 15:08:00 +0100
Subject: dm: support non power of two target max_io_len

Remove the restriction that limits a target's specified maximum incoming
I/O size to be a power of 2.

Rename this setting from 'split_io' to the less-ambiguous 'max_io_len'.
Change it from sector_t to uint32_t, which is plenty big enough, and
introduce a wrapper function dm_set_target_max_io_len() to set it.
Use sector_div() to process it now that it is not necessarily a power of 2.

Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Signed-off-by: Alasdair G Kergon <agk@redhat.com>
---
 drivers/md/dm-raid.c | 11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

(limited to 'drivers/md/dm-raid.c')

diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index 017c34d78d61..858a8b70811c 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -353,6 +353,7 @@ static int parse_raid_params(struct raid_set *rs, char **argv,
 {
 	unsigned i, rebuild_cnt = 0;
 	unsigned long value, region_size = 0;
+	sector_t max_io_len;
 	char *key;
 
 	/*
@@ -522,14 +523,12 @@ static int parse_raid_params(struct raid_set *rs, char **argv,
 		return -EINVAL;
 
 	if (rs->md.chunk_sectors)
-		rs->ti->split_io = rs->md.chunk_sectors;
+		max_io_len = rs->md.chunk_sectors;
 	else
-		rs->ti->split_io = region_size;
+		max_io_len = region_size;
 
-	if (rs->md.chunk_sectors)
-		rs->ti->split_io = rs->md.chunk_sectors;
-	else
-		rs->ti->split_io = region_size;
+	if (dm_set_target_max_io_len(rs->ti, max_io_len))
+		return -EINVAL;
 
 	/* Assume there are no metadata devices until the drives are parsed */
 	rs->md.persistent = 0;
-- 
cgit v1.2.3


From f999e8fe70bd0b8faa27ccdac14b5942999c6e78 Mon Sep 17 00:00:00 2001
From: Jonathan E Brassow <jbrassow@redhat.com>
Date: Fri, 27 Jul 2012 15:08:04 +0100
Subject: dm raid: restructure parse_raid_params

In preparation for RAID10 addition to dm-raid, we change an 'if' conditional
to a 'switch' conditional to make it easier to see what is being checked for
each RAID type.

Signed-off-by: Jonathan Brassow <jbrassow@redhat.com>
Signed-off-by: Alasdair G Kergon <agk@redhat.com>
---
 drivers/md/dm-raid.c | 25 ++++++++++++++++++++-----
 1 file changed, 20 insertions(+), 5 deletions(-)

(limited to 'drivers/md/dm-raid.c')

diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index 858a8b70811c..1717ed33dd7f 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -430,13 +430,28 @@ static int parse_raid_params(struct raid_set *rs, char **argv,
 
 		if (!strcasecmp(key, "rebuild")) {
 			rebuild_cnt++;
-			if (((rs->raid_type->level != 1) &&
-			     (rebuild_cnt > rs->raid_type->parity_devs)) ||
-			    ((rs->raid_type->level == 1) &&
-			     (rebuild_cnt > (rs->md.raid_disks - 1)))) {
-				rs->ti->error = "Too many rebuild devices specified for given RAID type";
+
+			switch (rs->raid_type->level) {
+			case 1:
+				if (rebuild_cnt >= rs->md.raid_disks) {
+					rs->ti->error = "Too many rebuild devices specified";
+					return -EINVAL;
+				}
+				break;
+			case 4:
+			case 5:
+			case 6:
+				if (rebuild_cnt > rs->raid_type->parity_devs) {
+					rs->ti->error = "Too many rebuild devices specified for given RAID type";
+					return -EINVAL;
+				}
+				break;
+			default:
+				DMERR("The rebuild parameter is not supported for %s", rs->raid_type->name);
+				rs->ti->error = "Rebuild not supported for this RAID type";
 				return -EINVAL;
 			}
+
 			if (value > rs->md.raid_disks) {
 				rs->ti->error = "Invalid rebuild index given";
 				return -EINVAL;
-- 
cgit v1.2.3


From c039c332f23e794deb6d6f37b9f07ff3b27fb2cf Mon Sep 17 00:00:00 2001
From: Jonathan E Brassow <jbrassow@redhat.com>
Date: Fri, 27 Jul 2012 15:08:04 +0100
Subject: dm raid: move sectors_per_dev calculation

In preparation for RAID10 inclusion in dm-raid, we move the sectors_per_dev
calculation later in the device creation process.  This is because we won't
know up-front how many stripes vs how many mirrors there are which will
change the calculation.

Signed-off-by: Jonathan Brassow <jbrassow@redhat.com>
Signed-off-by: Alasdair G Kergon <agk@redhat.com>
---
 drivers/md/dm-raid.c | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

(limited to 'drivers/md/dm-raid.c')

diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index 1717ed33dd7f..f4275a8e860c 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -101,20 +101,12 @@ static struct raid_set *context_alloc(struct dm_target *ti, struct raid_type *ra
 {
 	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 ((raid_type->level > 1) &&
-	    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";
@@ -128,7 +120,6 @@ static struct raid_set *context_alloc(struct dm_target *ti, struct raid_type *ra
 	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;
@@ -143,6 +134,7 @@ static struct raid_set *context_alloc(struct dm_target *ti, struct raid_type *ra
 	 *  rs->md.external
 	 *  rs->md.chunk_sectors
 	 *  rs->md.new_chunk_sectors
+	 *  rs->md.dev_sectors
 	 */
 
 	return rs;
@@ -353,6 +345,7 @@ static int parse_raid_params(struct raid_set *rs, char **argv,
 {
 	unsigned i, rebuild_cnt = 0;
 	unsigned long value, region_size = 0;
+	sector_t sectors_per_dev = rs->ti->len;
 	sector_t max_io_len;
 	char *key;
 
@@ -545,6 +538,13 @@ static int parse_raid_params(struct raid_set *rs, char **argv,
 	if (dm_set_target_max_io_len(rs->ti, max_io_len))
 		return -EINVAL;
 
+	if ((rs->raid_type->level > 1) &&
+	    sector_div(sectors_per_dev, (rs->md.raid_disks - rs->raid_type->parity_devs))) {
+		rs->ti->error = "Target length not divisible by number of data devices";
+		return -EINVAL;
+	}
+	rs->md.dev_sectors = sectors_per_dev;
+
 	/* Assume there are no metadata devices until the drives are parsed */
 	rs->md.persistent = 0;
 	rs->md.external = 1;
-- 
cgit v1.2.3


From 1f4e0ff07980820977f45d6a5dbc81d3bb9ce4d3 Mon Sep 17 00:00:00 2001
From: Alasdair G Kergon <agk@redhat.com>
Date: Fri, 27 Jul 2012 15:08:16 +0100
Subject: dm thin: commit before gathering status

Commit outstanding metadata before returning the status for a dm thin
pool so that the numbers reported are as up-to-date as possible.

The commit is not performed if the device is suspended or if
the DM_NOFLUSH_FLAG is supplied by userspace and passed to the target
through a new 'status_flags' parameter in the target's dm_status_fn.

The userspace dmsetup tool will support the --noflush flag with the
'dmsetup status' and 'dmsetup wait' commands from version 1.02.76
onwards.

Tested-by: Mike Snitzer <snitzer@redhat.com>
Signed-off-by: Alasdair G Kergon <agk@redhat.com>
---
 drivers/md/dm-crypt.c         | 2 +-
 drivers/md/dm-delay.c         | 2 +-
 drivers/md/dm-flakey.c        | 2 +-
 drivers/md/dm-ioctl.c         | 5 ++++-
 drivers/md/dm-linear.c        | 2 +-
 drivers/md/dm-mpath.c         | 2 +-
 drivers/md/dm-raid.c          | 2 +-
 drivers/md/dm-raid1.c         | 2 +-
 drivers/md/dm-snap.c          | 6 +++---
 drivers/md/dm-stripe.c        | 4 ++--
 drivers/md/dm-thin.c          | 9 +++++++--
 drivers/md/dm-verity.c        | 2 +-
 drivers/md/dm.h               | 5 +++++
 include/linux/device-mapper.h | 2 +-
 include/linux/dm-ioctl.h      | 8 +++++---
 15 files changed, 35 insertions(+), 20 deletions(-)

(limited to 'drivers/md/dm-raid.c')

diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 00a25ab987c9..664743d6a6cd 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -1733,7 +1733,7 @@ static int crypt_map(struct dm_target *ti, struct bio *bio,
 }
 
 static int crypt_status(struct dm_target *ti, status_type_t type,
-			char *result, unsigned int maxlen)
+			unsigned status_flags, char *result, unsigned maxlen)
 {
 	struct crypt_config *cc = ti->private;
 	unsigned int sz = 0;
diff --git a/drivers/md/dm-delay.c b/drivers/md/dm-delay.c
index 2dc22dddb2ae..f53846f9ab50 100644
--- a/drivers/md/dm-delay.c
+++ b/drivers/md/dm-delay.c
@@ -295,7 +295,7 @@ static int delay_map(struct dm_target *ti, struct bio *bio,
 }
 
 static int delay_status(struct dm_target *ti, status_type_t type,
-			char *result, unsigned maxlen)
+			unsigned status_flags, char *result, unsigned maxlen)
 {
 	struct delay_c *dc = ti->private;
 	int sz = 0;
diff --git a/drivers/md/dm-flakey.c b/drivers/md/dm-flakey.c
index ac49c01f1a44..cc15543a6ad7 100644
--- a/drivers/md/dm-flakey.c
+++ b/drivers/md/dm-flakey.c
@@ -333,7 +333,7 @@ static int flakey_end_io(struct dm_target *ti, struct bio *bio,
 }
 
 static int flakey_status(struct dm_target *ti, status_type_t type,
-			 char *result, unsigned int maxlen)
+			 unsigned status_flags, char *result, unsigned maxlen)
 {
 	unsigned sz = 0;
 	struct flakey_c *fc = ti->private;
diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c
index a1a3e6df17b8..afd95986d099 100644
--- a/drivers/md/dm-ioctl.c
+++ b/drivers/md/dm-ioctl.c
@@ -1054,6 +1054,7 @@ static void retrieve_status(struct dm_table *table,
 	char *outbuf, *outptr;
 	status_type_t type;
 	size_t remaining, len, used = 0;
+	unsigned status_flags = 0;
 
 	outptr = outbuf = get_result_buffer(param, param_size, &len);
 
@@ -1090,7 +1091,9 @@ static void retrieve_status(struct dm_table *table,
 
 		/* Get the status/table string from the target driver */
 		if (ti->type->status) {
-			if (ti->type->status(ti, type, outptr, remaining)) {
+			if (param->flags & DM_NOFLUSH_FLAG)
+				status_flags |= DM_STATUS_NOFLUSH_FLAG;
+			if (ti->type->status(ti, type, status_flags, outptr, remaining)) {
 				param->flags |= DM_BUFFER_FULL_FLAG;
 				break;
 			}
diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c
index 3639eeab6042..1bf19a93eef0 100644
--- a/drivers/md/dm-linear.c
+++ b/drivers/md/dm-linear.c
@@ -96,7 +96,7 @@ static int linear_map(struct dm_target *ti, struct bio *bio,
 }
 
 static int linear_status(struct dm_target *ti, status_type_t type,
-			 char *result, unsigned int maxlen)
+			 unsigned status_flags, char *result, unsigned maxlen)
 {
 	struct linear_c *lc = (struct linear_c *) ti->private;
 
diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index 8a3b2d53f81b..d8abb90a6c2f 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -1378,7 +1378,7 @@ static void multipath_resume(struct dm_target *ti)
  *      num_paths num_selector_args [path_dev [selector_args]* ]+ ]+
  */
 static int multipath_status(struct dm_target *ti, status_type_t type,
-			    char *result, unsigned int maxlen)
+			    unsigned status_flags, char *result, unsigned maxlen)
 {
 	int sz = 0;
 	unsigned long flags;
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index f4275a8e860c..f2f29c526544 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -1081,7 +1081,7 @@ static int raid_map(struct dm_target *ti, struct bio *bio, union map_info *map_c
 }
 
 static int raid_status(struct dm_target *ti, status_type_t type,
-		       char *result, unsigned maxlen)
+		       unsigned status_flags, char *result, unsigned maxlen)
 {
 	struct raid_set *rs = ti->private;
 	unsigned raid_param_cnt = 1; /* at least 1 for chunksize */
diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c
index 596a3a1164a7..bc5ddba8045b 100644
--- a/drivers/md/dm-raid1.c
+++ b/drivers/md/dm-raid1.c
@@ -1367,7 +1367,7 @@ static char device_status_char(struct mirror *m)
 
 
 static int mirror_status(struct dm_target *ti, status_type_t type,
-			 char *result, unsigned int maxlen)
+			 unsigned status_flags, char *result, unsigned maxlen)
 {
 	unsigned int m, sz = 0;
 	struct mirror_set *ms = (struct mirror_set *) ti->private;
diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c
index 6c0f3e33923a..a143921feaf6 100644
--- a/drivers/md/dm-snap.c
+++ b/drivers/md/dm-snap.c
@@ -1849,7 +1849,7 @@ static void snapshot_merge_resume(struct dm_target *ti)
 }
 
 static int snapshot_status(struct dm_target *ti, status_type_t type,
-			   char *result, unsigned int maxlen)
+			   unsigned status_flags, char *result, unsigned maxlen)
 {
 	unsigned sz = 0;
 	struct dm_snapshot *snap = ti->private;
@@ -2151,8 +2151,8 @@ static void origin_resume(struct dm_target *ti)
 	ti->max_io_len = get_origin_minimum_chunksize(dev->bdev);
 }
 
-static int origin_status(struct dm_target *ti, status_type_t type, char *result,
-			 unsigned int maxlen)
+static int origin_status(struct dm_target *ti, status_type_t type,
+			 unsigned status_flags, char *result, unsigned maxlen)
 {
 	struct dm_dev *dev = ti->private;
 
diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c
index 9e8f4cc63d6c..a087bf2a8d66 100644
--- a/drivers/md/dm-stripe.c
+++ b/drivers/md/dm-stripe.c
@@ -311,8 +311,8 @@ static int stripe_map(struct dm_target *ti, struct bio *bio,
  *
  */
 
-static int stripe_status(struct dm_target *ti,
-			 status_type_t type, char *result, unsigned int maxlen)
+static int stripe_status(struct dm_target *ti, status_type_t type,
+			 unsigned status_flags, char *result, unsigned maxlen)
 {
 	struct stripe_c *sc = (struct stripe_c *) ti->private;
 	char buffer[sc->stripes + 1];
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index 087e9b34d290..af1fc3b2c2ad 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -5,6 +5,7 @@
  */
 
 #include "dm-thin-metadata.h"
+#include "dm.h"
 
 #include <linux/device-mapper.h>
 #include <linux/dm-io.h>
@@ -2619,7 +2620,7 @@ static void emit_flags(struct pool_features *pf, char *result,
  *    <used data sectors>/<total data sectors> <held metadata root>
  */
 static int pool_status(struct dm_target *ti, status_type_t type,
-		       char *result, unsigned maxlen)
+		       unsigned status_flags, char *result, unsigned maxlen)
 {
 	int r;
 	unsigned sz = 0;
@@ -2641,6 +2642,10 @@ static int pool_status(struct dm_target *ti, status_type_t type,
 			break;
 		}
 
+		/* Commit to ensure statistics aren't out-of-date */
+		if (!(status_flags & DM_STATUS_NOFLUSH_FLAG) && !dm_suspended(ti))
+			(void) commit_or_fallback(pool);
+
 		r = dm_pool_get_metadata_transaction_id(pool->pmd,
 							&transaction_id);
 		if (r)
@@ -2968,7 +2973,7 @@ static void thin_postsuspend(struct dm_target *ti)
  * <nr mapped sectors> <highest mapped sector>
  */
 static int thin_status(struct dm_target *ti, status_type_t type,
-		       char *result, unsigned maxlen)
+		       unsigned status_flags, char *result, unsigned maxlen)
 {
 	int r;
 	ssize_t sz = 0;
diff --git a/drivers/md/dm-verity.c b/drivers/md/dm-verity.c
index fa365d39b612..254d19268ad2 100644
--- a/drivers/md/dm-verity.c
+++ b/drivers/md/dm-verity.c
@@ -515,7 +515,7 @@ static int verity_map(struct dm_target *ti, struct bio *bio,
  * Status: V (valid) or C (corruption found)
  */
 static int verity_status(struct dm_target *ti, status_type_t type,
-			 char *result, unsigned maxlen)
+			 unsigned status_flags, char *result, unsigned maxlen)
 {
 	struct dm_verity *v = ti->private;
 	unsigned sz = 0;
diff --git a/drivers/md/dm.h b/drivers/md/dm.h
index b7dacd59d8d7..52eef493d266 100644
--- a/drivers/md/dm.h
+++ b/drivers/md/dm.h
@@ -22,6 +22,11 @@
 #define DM_SUSPEND_LOCKFS_FLAG		(1 << 0)
 #define DM_SUSPEND_NOFLUSH_FLAG		(1 << 1)
 
+/*
+ * Status feature flags
+ */
+#define DM_STATUS_NOFLUSH_FLAG		(1 << 0)
+
 /*
  * Type of table and mapped_device's mempool
  */
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index eb753633b576..38d27a10aa5d 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -72,7 +72,7 @@ typedef int (*dm_preresume_fn) (struct dm_target *ti);
 typedef void (*dm_resume_fn) (struct dm_target *ti);
 
 typedef int (*dm_status_fn) (struct dm_target *ti, status_type_t status_type,
-			     char *result, unsigned int maxlen);
+			     unsigned status_flags, char *result, unsigned maxlen);
 
 typedef int (*dm_message_fn) (struct dm_target *ti, unsigned argc, char **argv);
 
diff --git a/include/linux/dm-ioctl.h b/include/linux/dm-ioctl.h
index 3ece4eee84cb..91e3a360f611 100644
--- a/include/linux/dm-ioctl.h
+++ b/include/linux/dm-ioctl.h
@@ -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	22
-#define DM_VERSION_PATCHLEVEL	1
-#define DM_VERSION_EXTRA	"-ioctl (2012-06-01)"
+#define DM_VERSION_MINOR	23
+#define DM_VERSION_PATCHLEVEL	0
+#define DM_VERSION_EXTRA	"-ioctl (2012-07-25)"
 
 /* Status bits */
 #define DM_READONLY_FLAG	(1 << 0) /* In/Out */
@@ -307,6 +307,8 @@ enum {
 
 /*
  * Set this to suspend without flushing queued ios.
+ * Also disables flushing uncommitted changes in the thin target before
+ * generating statistics for DM_TABLE_STATUS and DM_DEV_WAIT.
  */
 #define DM_NOFLUSH_FLAG		(1 << 11) /* In */
 
-- 
cgit v1.2.3


From 63f33b8dda88923487004b20fba825486d009e7b Mon Sep 17 00:00:00 2001
From: Jonathan Brassow <jbrassow@redhat.com>
Date: Tue, 31 Jul 2012 21:44:26 -0500
Subject: DM RAID: Add support for MD RAID10

Support the MD RAID10 personality through dm-raid.c

Signed-off-by: Jonathan Brassow <jbrassow@redhat.com>
Signed-off-by: NeilBrown <neilb@suse.de>
---
 Documentation/device-mapper/dm-raid.txt | 26 +++++++++
 drivers/md/dm-raid.c                    | 95 +++++++++++++++++++++++++++++++--
 2 files changed, 116 insertions(+), 5 deletions(-)

(limited to 'drivers/md/dm-raid.c')

diff --git a/Documentation/device-mapper/dm-raid.txt b/Documentation/device-mapper/dm-raid.txt
index 946c73342cde..1c1844957166 100644
--- a/Documentation/device-mapper/dm-raid.txt
+++ b/Documentation/device-mapper/dm-raid.txt
@@ -27,6 +27,10 @@ The target is named "raid" and it accepts the following parameters:
 		- rotating parity N (right-to-left) with data restart
   raid6_nc	RAID6 N continue
 		- rotating parity N (right-to-left) with data continuation
+  raid10        Various RAID10 inspired algorithms chosen by additional params
+		- RAID10: Striped Mirrors (aka 'Striping on top of mirrors')
+		- RAID1E: Integrated Adjacent Stripe Mirroring
+		-  and other similar RAID10 variants
 
   Reference: Chapter 4 of
   http://www.snia.org/sites/default/files/SNIA_DDF_Technical_Position_v2.0.pdf
@@ -59,6 +63,28 @@ The target is named "raid" and it accepts the following parameters:
 		logical size of the array.  The bitmap records the device
 		synchronisation state for each region.
 
+        [raid10_copies   <# copies>]
+        [raid10_format   near]
+		These two options are used to alter the default layout of
+		a RAID10 configuration.  The number of copies is can be
+		specified, but the default is 2.  There are other variations
+		to how the copies are laid down - the default and only current
+		option is "near".  Near copies are what most people think of
+		with respect to mirroring.  If these options are left
+		unspecified, or 'raid10_copies 2' and/or 'raid10_format near'
+		are given, then the layouts for 2, 3 and 4 devices are:
+		2 drives         3 drives          4 drives
+		--------         ----------        --------------
+		A1  A1           A1  A1  A2        A1  A1  A2  A2
+		A2  A2           A2  A3  A3        A3  A3  A4  A4
+		A3  A3           A4  A4  A5        A5  A5  A6  A6
+		A4  A4           A5  A6  A6        A7  A7  A8  A8
+		..  ..           ..  ..  ..        ..  ..  ..  ..
+		The 2-device layout is equivalent 2-way RAID1.  The 4-device
+		layout is what a traditional RAID10 would look like.  The
+		3-device layout is what might be called a 'RAID1E - Integrated
+		Adjacent Stripe Mirroring'.
+
 <#raid_devs>: The number of devices composing the array.
 	Each device consists of two entries.  The first is the device
 	containing the metadata (if any); the second is the one containing the
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index f4275a8e860c..691b3c59088e 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -11,6 +11,7 @@
 #include "md.h"
 #include "raid1.h"
 #include "raid5.h"
+#include "raid10.h"
 #include "bitmap.h"
 
 #include <linux/device-mapper.h>
@@ -52,7 +53,10 @@ struct raid_dev {
 #define DMPF_MAX_RECOVERY_RATE 0x20
 #define DMPF_MAX_WRITE_BEHIND  0x40
 #define DMPF_STRIPE_CACHE      0x80
-#define DMPF_REGION_SIZE       0X100
+#define DMPF_REGION_SIZE       0x100
+#define DMPF_RAID10_COPIES     0x200
+#define DMPF_RAID10_FORMAT     0x400
+
 struct raid_set {
 	struct dm_target *ti;
 
@@ -76,6 +80,7 @@ static struct raid_type {
 	const unsigned algorithm;	/* RAID algorithm. */
 } raid_types[] = {
 	{"raid1",    "RAID1 (mirroring)",               0, 2, 1, 0 /* NONE */},
+	{"raid10",   "RAID10 (striped mirrors)",        0, 2, 10, UINT_MAX /* Varies */},
 	{"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},
@@ -86,6 +91,17 @@ static struct raid_type {
 	{"raid6_nc", "RAID6 (N continue)",		2, 4, 6, ALGORITHM_ROTATING_N_CONTINUE}
 };
 
+static unsigned raid10_md_layout_to_copies(int layout)
+{
+	return layout & 0xFF;
+}
+
+static int raid10_format_to_md_layout(char *format, unsigned copies)
+{
+	/* 1 "far" copy, and 'copies' "near" copies */
+	return (1 << 8) | (copies & 0xFF);
+}
+
 static struct raid_type *get_raid_type(char *name)
 {
 	int i;
@@ -339,10 +355,16 @@ static int validate_region_size(struct raid_set *rs, unsigned long region_size)
  *    [max_write_behind <sectors>]	See '-write-behind=' (man mdadm)
  *    [stripe_cache <sectors>]		Stripe cache size for higher RAIDs
  *    [region_size <sectors>]           Defines granularity of bitmap
+ *
+ * RAID10-only options:
+ *    [raid10_copies <# copies>]        Number of copies.  (Default: 2)
+ *    [raid10_format <near>]            Layout algorithm.  (Default: near)
  */
 static int parse_raid_params(struct raid_set *rs, char **argv,
 			     unsigned num_raid_params)
 {
+	char *raid10_format = "near";
+	unsigned raid10_copies = 2;
 	unsigned i, rebuild_cnt = 0;
 	unsigned long value, region_size = 0;
 	sector_t sectors_per_dev = rs->ti->len;
@@ -416,11 +438,28 @@ static int parse_raid_params(struct raid_set *rs, char **argv,
 		}
 
 		key = argv[i++];
+
+		/* Parameters that take a string value are checked here. */
+		if (!strcasecmp(key, "raid10_format")) {
+			if (rs->raid_type->level != 10) {
+				rs->ti->error = "'raid10_format' is an invalid parameter for this RAID type";
+				return -EINVAL;
+			}
+			if (strcmp("near", argv[i])) {
+				rs->ti->error = "Invalid 'raid10_format' value given";
+				return -EINVAL;
+			}
+			raid10_format = argv[i];
+			rs->print_flags |= DMPF_RAID10_FORMAT;
+			continue;
+		}
+
 		if (strict_strtoul(argv[i], 10, &value) < 0) {
 			rs->ti->error = "Bad numerical argument given in raid params";
 			return -EINVAL;
 		}
 
+		/* Parameters that take a numeric value are checked here */
 		if (!strcasecmp(key, "rebuild")) {
 			rebuild_cnt++;
 
@@ -439,6 +478,7 @@ static int parse_raid_params(struct raid_set *rs, char **argv,
 					return -EINVAL;
 				}
 				break;
+			case 10:
 			default:
 				DMERR("The rebuild parameter is not supported for %s", rs->raid_type->name);
 				rs->ti->error = "Rebuild not supported for this RAID type";
@@ -495,7 +535,8 @@ static int parse_raid_params(struct raid_set *rs, char **argv,
 			 */
 			value /= 2;
 
-			if (rs->raid_type->level < 5) {
+			if ((rs->raid_type->level != 5) &&
+			    (rs->raid_type->level != 6)) {
 				rs->ti->error = "Inappropriate argument: stripe_cache";
 				return -EINVAL;
 			}
@@ -520,6 +561,14 @@ static int parse_raid_params(struct raid_set *rs, char **argv,
 		} else if (!strcasecmp(key, "region_size")) {
 			rs->print_flags |= DMPF_REGION_SIZE;
 			region_size = value;
+		} else if (!strcasecmp(key, "raid10_copies") &&
+			   (rs->raid_type->level == 10)) {
+			if ((value < 2) || (value > 0xFF)) {
+				rs->ti->error = "Bad value for 'raid10_copies'";
+				return -EINVAL;
+			}
+			rs->print_flags |= DMPF_RAID10_COPIES;
+			raid10_copies = value;
 		} else {
 			DMERR("Unable to parse RAID parameter: %s", key);
 			rs->ti->error = "Unable to parse RAID parameters";
@@ -538,8 +587,22 @@ static int parse_raid_params(struct raid_set *rs, char **argv,
 	if (dm_set_target_max_io_len(rs->ti, max_io_len))
 		return -EINVAL;
 
-	if ((rs->raid_type->level > 1) &&
-	    sector_div(sectors_per_dev, (rs->md.raid_disks - rs->raid_type->parity_devs))) {
+	if (rs->raid_type->level == 10) {
+		if (raid10_copies > rs->md.raid_disks) {
+			rs->ti->error = "Not enough devices to satisfy specification";
+			return -EINVAL;
+		}
+
+		/* (Len * #mirrors) / #devices */
+		sectors_per_dev = rs->ti->len * raid10_copies;
+		sector_div(sectors_per_dev, rs->md.raid_disks);
+
+		rs->md.layout = raid10_format_to_md_layout(raid10_format,
+							   raid10_copies);
+		rs->md.new_layout = rs->md.layout;
+	} else if ((rs->raid_type->level > 1) &&
+		   sector_div(sectors_per_dev,
+			      (rs->md.raid_disks - rs->raid_type->parity_devs))) {
 		rs->ti->error = "Target length not divisible by number of data devices";
 		return -EINVAL;
 	}
@@ -566,6 +629,9 @@ static int raid_is_congested(struct dm_target_callbacks *cb, int bits)
 	if (rs->raid_type->level == 1)
 		return md_raid1_congested(&rs->md, bits);
 
+	if (rs->raid_type->level == 10)
+		return md_raid10_congested(&rs->md, bits);
+
 	return md_raid5_congested(&rs->md, bits);
 }
 
@@ -884,6 +950,9 @@ static int analyse_superblocks(struct dm_target *ti, struct raid_set *rs)
 	case 6:
 		redundancy = rs->raid_type->parity_devs;
 		break;
+	case 10:
+		redundancy = raid10_md_layout_to_copies(mddev->layout) - 1;
+		break;
 	default:
 		ti->error = "Unknown RAID type";
 		return -EINVAL;
@@ -1049,12 +1118,19 @@ static int raid_ctr(struct dm_target *ti, unsigned argc, char **argv)
 		goto bad;
 	}
 
+	if (ti->len != rs->md.array_sectors) {
+		ti->error = "Array size does not match requested target length";
+		ret = -EINVAL;
+		goto size_mismatch;
+	}
 	rs->callbacks.congested_fn = raid_is_congested;
 	dm_table_add_target_callbacks(ti->table, &rs->callbacks);
 
 	mddev_suspend(&rs->md);
 	return 0;
 
+size_mismatch:
+	md_stop(&rs->md);
 bad:
 	context_free(rs);
 
@@ -1203,6 +1279,13 @@ static int raid_status(struct dm_target *ti, status_type_t type,
 			DMEMIT(" region_size %lu",
 			       rs->md.bitmap_info.chunksize >> 9);
 
+		if (rs->print_flags & DMPF_RAID10_COPIES)
+			DMEMIT(" raid10_copies %u",
+			       raid10_md_layout_to_copies(rs->md.layout));
+
+		if (rs->print_flags & DMPF_RAID10_FORMAT)
+			DMEMIT(" raid10_format near");
+
 		DMEMIT(" %d", rs->md.raid_disks);
 		for (i = 0; i < rs->md.raid_disks; i++) {
 			if (rs->dev[i].meta_dev)
@@ -1277,7 +1360,7 @@ static void raid_resume(struct dm_target *ti)
 
 static struct target_type raid_target = {
 	.name = "raid",
-	.version = {1, 2, 0},
+	.version = {1, 3, 0},
 	.module = THIS_MODULE,
 	.ctr = raid_ctr,
 	.dtr = raid_dtr,
@@ -1304,6 +1387,8 @@ module_init(dm_raid_init);
 module_exit(dm_raid_exit);
 
 MODULE_DESCRIPTION(DM_NAME " raid4/5/6 target");
+MODULE_ALIAS("dm-raid1");
+MODULE_ALIAS("dm-raid10");
 MODULE_ALIAS("dm-raid4");
 MODULE_ALIAS("dm-raid5");
 MODULE_ALIAS("dm-raid6");
-- 
cgit v1.2.3