Merge tag 'dm-3.4-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/agk/linux-dm

Pull device-mapper changes for 3.4 from Alasdair Kergon: - Update thin provisioning to support read-only external snapshot origins and discards. - A new target, dm verity, for device content validation. - Mark dm uevent and dm raid as no-longer-experimental. - Miscellaneous other fixes and clean-ups. * tag 'dm-3.4-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/agk/linux-dm: (27 commits) dm: add verity target dm bufio: prefetch dm thin: add pool target flags to control discard dm thin: support discards dm thin: prepare to support discard dm thin: use dm_target_offset dm thin: support read only external snapshot origins dm thin: relax hard limit on the maximum size of a metadata device dm persistent data: remove space map ref_count entries if redundant dm thin: commit outstanding data every second dm: reject trailing characters in sccanf input dm raid: handle failed devices during start up dm thin metadata: pass correct space map to dm_sm_root_size dm persistent data: remove redundant value_size arg from value_ptr dm mpath: detect invalid map_context dm: clear bi_end_io on remapping failure dm table: simplify call to free_devices dm thin: correct comments dm raid: no longer experimental dm uevent: no longer experimental ...
2026-05-01 15:00:59 -07:00 · 2012-03-28 12:55:04 -07:00
parent 516e779770 a4ffc15219
commit 89e5d6f0d9
32 changed files with 2105 additions and 393 deletions
@@ -0,0 +1,25 @@
+What:		/sys/block/dm-<num>/dm/name
+Date:		January 2009
+KernelVersion:	2.6.29
+Contact:	dm-devel@redhat.com
+Description:	Device-mapper device name.
+		Read-only string containing mapped device name.
+Users:		util-linux, device-mapper udev rules
+
+What:		/sys/block/dm-<num>/dm/uuid
+Date:		January 2009
+KernelVersion:	2.6.29
+Contact:	dm-devel@redhat.com
+Description:	Device-mapper device UUID.
+		Read-only string containing DM-UUID or empty string
+		if DM-UUID is not set.
+Users:		util-linux, device-mapper udev rules
+
+What:		/sys/block/dm-<num>/dm/suspended
+Date:		June 2009
+KernelVersion:	2.6.31
+Contact:	dm-devel@redhat.com
+Description:	Device-mapper device suspend state.
+		Contains the value 1 while the device is suspended.
+		Otherwise it contains 0. Read-only attribute.
+Users:		util-linux, device-mapper udev rules
@@ -75,10 +75,12 @@ less sharing than average you'll need a larger-than-average metadata device.

 As a guide, we suggest you calculate the number of bytes to use in the
 metadata device as 48 * $data_dev_size / $data_block_size but round it up
-to 2MB if the answer is smaller.  The largest size supported is 16GB.
+to 2MB if the answer is smaller.  If you're creating large numbers of
+snapshots which are recording large amounts of change, you may find you
+need to increase this.

-If you're creating large numbers of snapshots which are recording large
-amounts of change, you may need find you need to increase this.
+The largest size supported is 16GB: If the device is larger,
+a warning will be issued and the excess space will not be used.

 Reloading a pool table
 ----------------------
@@ -167,6 +169,38 @@ ii) Using an internal snapshot.

    dmsetup create snap --table "0 2097152 thin /dev/mapper/pool 1"

+External snapshots
+------------------
+
+You can use an external _read only_ device as an origin for a
+thinly-provisioned volume.  Any read to an unprovisioned area of the
+thin device will be passed through to the origin.  Writes trigger
+the allocation of new blocks as usual.
+
+One use case for this is VM hosts that want to run guests on
+thinly-provisioned volumes but have the base image on another device
+(possibly shared between many VMs).
+
+You must not write to the origin device if you use this technique!
+Of course, you may write to the thin device and take internal snapshots
+of the thin volume.
+
+i) Creating a snapshot of an external device
+
+  This is the same as creating a thin device.
+  You don't mention the origin at this stage.
+
+    dmsetup message /dev/mapper/pool 0 "create_thin 0"
+
+ii) Using a snapshot of an external device.
+
+  Append an extra parameter to the thin target specifying the origin:
+
+    dmsetup create snap --table "0 2097152 thin /dev/mapper/pool 0 /dev/image"
+
+  N.B. All descendants (internal snapshots) of this snapshot require the
+  same extra origin parameter.
+
 Deactivation
 ------------

@@ -189,7 +223,13 @@ i) Constructor
 	      <low water mark (blocks)> [<number of feature args> [<arg>]*]

    Optional feature arguments:
-    - 'skip_block_zeroing': skips the zeroing of newly-provisioned blocks.
+
+      skip_block_zeroing: Skip the zeroing of newly-provisioned blocks.
+
+      ignore_discard: Disable discard support.
+
+      no_discard_passdown: Don't pass discards down to the underlying
+			   data device, but just remove the mapping.

    Data block size must be between 64KB (128 sectors) and 1GB
    (2097152 sectors) inclusive.
@@ -237,16 +277,6 @@ iii) Messages

 	Deletes a thin device.  Irreversible.

-    trim <dev id> <new size in sectors>
-
-	Delete mappings from the end of a thin device.  Irreversible.
-	You might want to use this if you're reducing the size of
-	your thinly-provisioned device.  In many cases, due to the
-	sharing of blocks between devices, it is not possible to
-	determine in advance how much space 'trim' will release.  (In
-	future a userspace tool might be able to perform this
-	calculation.)
-
    set_transaction_id <current id> <new id>

 	Userland volume managers, such as LVM, need a way to
@@ -262,7 +292,7 @@ iii) Messages

 i) Constructor

-    thin <pool dev> <dev id>
+    thin <pool dev> <dev id> [<external origin dev>]

    pool dev:
 	the thin-pool device, e.g. /dev/mapper/my_pool or 253:0
@@ -271,6 +301,11 @@ i) Constructor
 	the internal device identifier of the device to be
 	activated.

+    external origin dev:
+	an optional block device outside the pool to be treated as a
+	read-only snapshot origin: reads to unprovisioned areas of the
+	thin target will be mapped to this device.
+
 The pool doesn't store any size against the thin devices.  If you
 load a thin target that is smaller than you've been using previously,
 then you'll have no access to blocks mapped beyond the end.  If you
@@ -0,0 +1,194 @@
+dm-verity
+==========
+
+Device-Mapper's "verity" target provides transparent integrity checking of
+block devices using a cryptographic digest provided by the kernel crypto API.
+This target is read-only.
+
+Construction Parameters
+=======================
+    <version> <dev> <hash_dev> <hash_start>
+    <data_block_size> <hash_block_size>
+    <num_data_blocks> <hash_start_block>
+    <algorithm> <digest> <salt>
+
+<version>
+    This is the version number of the on-disk format.
+
+    0 is the original format used in the Chromium OS.
+	The salt is appended when hashing, digests are stored continuously and
+	the rest of the block is padded with zeros.
+
+    1 is the current format that should be used for new devices.
+	The salt is prepended when hashing and each digest is
+	padded with zeros to the power of two.
+
+<dev>
+    This is the device containing the data the integrity of which needs to be
+    checked.  It may be specified as a path, like /dev/sdaX, or a device number,
+    <major>:<minor>.
+
+<hash_dev>
+    This is the device that that supplies the hash tree data.  It may be
+    specified similarly to the device path and may be the same device.  If the
+    same device is used, the hash_start should be outside of the dm-verity
+    configured device size.
+
+<data_block_size>
+    The block size on a data device.  Each block corresponds to one digest on
+    the hash device.
+
+<hash_block_size>
+    The size of a hash block.
+
+<num_data_blocks>
+    The number of data blocks on the data device.  Additional blocks are
+    inaccessible.  You can place hashes to the same partition as data, in this
+    case hashes are placed after <num_data_blocks>.
+
+<hash_start_block>
+    This is the offset, in <hash_block_size>-blocks, from the start of hash_dev
+    to the root block of the hash tree.
+
+<algorithm>
+    The cryptographic hash algorithm used for this device.  This should
+    be the name of the algorithm, like "sha1".
+
+<digest>
+    The hexadecimal encoding of the cryptographic hash of the root hash block
+    and the salt.  This hash should be trusted as there is no other authenticity
+    beyond this point.
+
+<salt>
+    The hexadecimal encoding of the salt value.
+
+Theory of operation
+===================
+
+dm-verity is meant to be setup as part of a verified boot path.  This
+may be anything ranging from a boot using tboot or trustedgrub to just
+booting from a known-good device (like a USB drive or CD).
+
+When a dm-verity device is configured, it is expected that the caller
+has been authenticated in some way (cryptographic signatures, etc).
+After instantiation, all hashes will be verified on-demand during
+disk access.  If they cannot be verified up to the root node of the
+tree, the root hash, then the I/O will fail.  This should identify
+tampering with any data on the device and the hash data.
+
+Cryptographic hashes are used to assert the integrity of the device on a
+per-block basis.  This allows for a lightweight hash computation on first read
+into the page cache.  Block hashes are stored linearly-aligned to the nearest
+block the size of a page.
+
+Hash Tree
+---------
+
+Each node in the tree is a cryptographic hash.  If it is a leaf node, the hash
+is of some block data on disk.  If it is an intermediary node, then the hash is
+of a number of child nodes.
+
+Each entry in the tree is a collection of neighboring nodes that fit in one
+block.  The number is determined based on block_size and the size of the
+selected cryptographic digest algorithm.  The hashes are linearly-ordered in
+this entry and any unaligned trailing space is ignored but included when
+calculating the parent node.
+
+The tree looks something like:
+
+alg = sha256, num_blocks = 32768, block_size = 4096
+
+                                 [   root    ]
+                                /    . . .    \
+                     [entry_0]                 [entry_1]
+                    /  . . .  \                 . . .   \
+         [entry_0_0]   . . .  [entry_0_127]    . . . .  [entry_1_127]
+           / ... \             /   . . .  \             /           \
+     blk_0 ... blk_127  blk_16256   blk_16383      blk_32640 . . . blk_32767
+
+
+On-disk format
+==============
+
+Below is the recommended on-disk format. The verity kernel code does not
+read the on-disk header. It only reads the hash blocks which directly
+follow the header. It is expected that a user-space tool will verify the
+integrity of the verity_header and then call dmsetup with the correct
+parameters. Alternatively, the header can be omitted and the dmsetup
+parameters can be passed via the kernel command-line in a rooted chain
+of trust where the command-line is verified.
+
+The on-disk format is especially useful in cases where the hash blocks
+are on a separate partition. The magic number allows easy identification
+of the partition contents. Alternatively, the hash blocks can be stored
+in the same partition as the data to be verified. In such a configuration
+the filesystem on the partition would be sized a little smaller than
+the full-partition, leaving room for the hash blocks.
+
+struct superblock {
+	uint8_t signature[8]
+		"verity\0\0";
+
+	uint8_t version;
+		1 - current format
+
+	uint8_t data_block_bits;
+		log2(data block size)
+
+	uint8_t hash_block_bits;
+		log2(hash block size)
+
+	uint8_t pad1[1];
+		zero padding
+
+	uint16_t salt_size;
+		big-endian salt size
+
+	uint8_t pad2[2];
+		zero padding
+
+	uint32_t data_blocks_hi;
+		big-endian high 32 bits of the 64-bit number of data blocks
+
+	uint32_t data_blocks_lo;
+		big-endian low 32 bits of the 64-bit number of data blocks
+
+	uint8_t algorithm[16];
+		cryptographic algorithm
+
+	uint8_t salt[384];
+		salt (the salt size is specified above)
+
+	uint8_t pad3[88];
+		zero padding to 512-byte boundary
+}
+
+Directly following the header (and with sector number padded to the next hash
+block boundary) are the hash blocks which are stored a depth at a time
+(starting from the root), sorted in order of increasing index.
+
+Status
+======
+V (for Valid) is returned if every check performed so far was valid.
+If any check failed, C (for Corruption) is returned.
+
+Example
+=======
+
+Setup a device:
+  dmsetup create vroot --table \
+    "0 2097152 "\
+    "verity 1 /dev/sda1 /dev/sda2 4096 4096 2097152 1 "\
+    "4392712ba01368efdf14b05c76f9e4df0d53664630b5d48632ed17a137f39076 "\
+    "1234000000000000000000000000000000000000000000000000000000000000"
+
+A command line tool veritysetup is available to compute or verify
+the hash tree or activate the kernel driver.  This is available from
+the LVM2 upstream repository and may be supplied as a package called
+device-mapper-verity-tools:
+    git://sources.redhat.com/git/lvm2
+    http://sourceware.org/git/?p=lvm2.git
+    http://sourceware.org/cgi-bin/cvsweb.cgi/LVM2/verity?cvsroot=lvm2
+
+veritysetup -a vroot /dev/sda1 /dev/sda2 \
+	4392712ba01368efdf14b05c76f9e4df0d53664630b5d48632ed17a137f39076
@@ -2225,13 +2225,16 @@ W:	http://lanana.org/docs/device-list/index.html
 S:	Maintained

 DEVICE-MAPPER  (LVM)
-P:	Alasdair Kergon
+M:	Alasdair Kergon <agk@redhat.com>
+M:	dm-devel@redhat.com
 L:	dm-devel@redhat.com
 W:	http://sources.redhat.com/dm
 Q:	http://patchwork.kernel.org/project/dm-devel/list/
+T:	quilt http://people.redhat.com/agk/patches/linux/editing/
 S:	Maintained
 F:	Documentation/device-mapper/
 F:	drivers/md/dm*
+F:	drivers/md/persistent-data/
 F:	include/linux/device-mapper.h
 F:	include/linux/dm-*.h

@@ -277,8 +277,8 @@ config DM_MIRROR
         needed for live data migration tools such as 'pvmove'.

 config DM_RAID
-       tristate "RAID 1/4/5/6 target (EXPERIMENTAL)"
-       depends on BLK_DEV_DM && EXPERIMENTAL
+       tristate "RAID 1/4/5/6 target"
+       depends on BLK_DEV_DM
       select MD_RAID1
       select MD_RAID456
       select BLK_DEV_MD
@@ -359,8 +359,8 @@ config DM_DELAY
 	If unsure, say N.

 config DM_UEVENT
-	bool "DM uevents (EXPERIMENTAL)"
-	depends on BLK_DEV_DM && EXPERIMENTAL
+	bool "DM uevents"
+	depends on BLK_DEV_DM
 	---help---
 	Generate udev events for DM events.

@@ -370,4 +370,24 @@ config DM_FLAKEY
       ---help---
         A target that intermittently fails I/O for debugging purposes.

+config DM_VERITY
+	tristate "Verity target support (EXPERIMENTAL)"
+	depends on BLK_DEV_DM && EXPERIMENTAL
+	select CRYPTO
+	select CRYPTO_HASH
+	select DM_BUFIO
+	---help---
+	  This device-mapper target creates a read-only device that
+	  transparently validates the data on one underlying device against
+	  a pre-generated tree of cryptographic checksums stored on a second
+	  device.
+
+	  You'll need to activate the digests you're going to use in the
+	  cryptoapi configuration.
+
+	  To compile this code as a module, choose M here: the module will
+	  be called dm-verity.
+
+	  If unsure, say N.
+
 endif # MD
@@ -42,6 +42,7 @@ obj-$(CONFIG_DM_LOG_USERSPACE)	+= dm-log-userspace.o
 obj-$(CONFIG_DM_ZERO)		+= dm-zero.o
 obj-$(CONFIG_DM_RAID)	+= dm-raid.o
 obj-$(CONFIG_DM_THIN_PROVISIONING)	+= dm-thin-pool.o
+obj-$(CONFIG_DM_VERITY)		+= dm-verity.o

 ifeq ($(CONFIG_DM_UEVENT),y)
 dm-mod-objs			+= dm-uevent.o
@@ -578,7 +578,7 @@ static void write_endio(struct bio *bio, int error)
 	struct dm_buffer *b = container_of(bio, struct dm_buffer, bio);

 	b->write_error = error;
-	if (error) {
+	if (unlikely(error)) {
 		struct dm_bufio_client *c = b->c;
 		(void)cmpxchg(&c->async_write_error, 0, error);
 	}
@@ -697,13 +697,20 @@ static void __wait_for_free_buffer(struct dm_bufio_client *c)
 	dm_bufio_lock(c);
 }

+enum new_flag {
+	NF_FRESH = 0,
+	NF_READ = 1,
+	NF_GET = 2,
+	NF_PREFETCH = 3
+};
+
 /*
 * Allocate a new buffer. If the allocation is not possible, wait until
 * some other thread frees a buffer.
 *
 * May drop the lock and regain it.
 */
-static struct dm_buffer *__alloc_buffer_wait_no_callback(struct dm_bufio_client *c)
+static struct dm_buffer *__alloc_buffer_wait_no_callback(struct dm_bufio_client *c, enum new_flag nf)
 {
 	struct dm_buffer *b;

@@ -726,6 +733,9 @@ static struct dm_buffer *__alloc_buffer_wait_no_callback(struct dm_bufio_client
 				return b;
 		}

+		if (nf == NF_PREFETCH)
+			return NULL;
+
 		if (!list_empty(&c->reserved_buffers)) {
 			b = list_entry(c->reserved_buffers.next,
 				       struct dm_buffer, lru_list);
@@ -743,9 +753,12 @@ static struct dm_buffer *__alloc_buffer_wait_no_callback(struct dm_bufio_client
 	}
 }

-static struct dm_buffer *__alloc_buffer_wait(struct dm_bufio_client *c)
+static struct dm_buffer *__alloc_buffer_wait(struct dm_bufio_client *c, enum new_flag nf)
 {
-	struct dm_buffer *b = __alloc_buffer_wait_no_callback(c);
+	struct dm_buffer *b = __alloc_buffer_wait_no_callback(c, nf);
+
+	if (!b)
+		return NULL;

 	if (c->alloc_callback)
 		c->alloc_callback(b);
@@ -865,32 +878,23 @@ static struct dm_buffer *__find(struct dm_bufio_client *c, sector_t block)
 * Getting a buffer
 *--------------------------------------------------------------*/

-enum new_flag {
-	NF_FRESH = 0,
-	NF_READ = 1,
-	NF_GET = 2
-};
-
 static struct dm_buffer *__bufio_new(struct dm_bufio_client *c, sector_t block,
-				     enum new_flag nf, struct dm_buffer **bp,
-				     int *need_submit)
+				     enum new_flag nf, int *need_submit)
 {
 	struct dm_buffer *b, *new_b = NULL;

 	*need_submit = 0;

 	b = __find(c, block);
-	if (b) {
-		b->hold_count++;
-		__relink_lru(b, test_bit(B_DIRTY, &b->state) ||
-			     test_bit(B_WRITING, &b->state));
-		return b;
-	}
+	if (b)
+		goto found_buffer;

 	if (nf == NF_GET)
 		return NULL;

-	new_b = __alloc_buffer_wait(c);
+	new_b = __alloc_buffer_wait(c, nf);
+	if (!new_b)
+		return NULL;

 	/*
 	 * We've had a period where the mutex was unlocked, so need to
@@ -899,10 +903,7 @@ static struct dm_buffer *__bufio_new(struct dm_bufio_client *c, sector_t block,
 	b = __find(c, block);
 	if (b) {
 		__free_buffer_wake(new_b);
-		b->hold_count++;
-		__relink_lru(b, test_bit(B_DIRTY, &b->state) ||
-			     test_bit(B_WRITING, &b->state));
-		return b;
+		goto found_buffer;
 	}

 	__check_watermark(c);
@@ -922,6 +923,24 @@ static struct dm_buffer *__bufio_new(struct dm_bufio_client *c, sector_t block,
 	*need_submit = 1;

 	return b;
+
+found_buffer:
+	if (nf == NF_PREFETCH)
+		return NULL;
+	/*
+	 * Note: it is essential that we don't wait for the buffer to be
+	 * read if dm_bufio_get function is used. Both dm_bufio_get and
+	 * dm_bufio_prefetch can be used in the driver request routine.
+	 * If the user called both dm_bufio_prefetch and dm_bufio_get on
+	 * the same buffer, it would deadlock if we waited.
+	 */
+	if (nf == NF_GET && unlikely(test_bit(B_READING, &b->state)))
+		return NULL;
+
+	b->hold_count++;
+	__relink_lru(b, test_bit(B_DIRTY, &b->state) ||
+		     test_bit(B_WRITING, &b->state));
+	return b;
 }

 /*
@@ -956,10 +975,10 @@ static void *new_read(struct dm_bufio_client *c, sector_t block,
 	struct dm_buffer *b;

 	dm_bufio_lock(c);
-	b = __bufio_new(c, block, nf, bp, &need_submit);
+	b = __bufio_new(c, block, nf, &need_submit);
 	dm_bufio_unlock(c);

-	if (!b || IS_ERR(b))
+	if (!b)
 		return b;

 	if (need_submit)
@@ -1005,13 +1024,47 @@ void *dm_bufio_new(struct dm_bufio_client *c, sector_t block,
 }
 EXPORT_SYMBOL_GPL(dm_bufio_new);

+void dm_bufio_prefetch(struct dm_bufio_client *c,
+		       sector_t block, unsigned n_blocks)
+{
+	struct blk_plug plug;
+
+	blk_start_plug(&plug);
+	dm_bufio_lock(c);
+
+	for (; n_blocks--; block++) {
+		int need_submit;
+		struct dm_buffer *b;
+		b = __bufio_new(c, block, NF_PREFETCH, &need_submit);
+		if (unlikely(b != NULL)) {
+			dm_bufio_unlock(c);
+
+			if (need_submit)
+				submit_io(b, READ, b->block, read_endio);
+			dm_bufio_release(b);
+
+			dm_bufio_cond_resched();
+
+			if (!n_blocks)
+				goto flush_plug;
+			dm_bufio_lock(c);
+		}
+
+	}
+
+	dm_bufio_unlock(c);
+
+flush_plug:
+	blk_finish_plug(&plug);
+}
+EXPORT_SYMBOL_GPL(dm_bufio_prefetch);
+
 void dm_bufio_release(struct dm_buffer *b)
 {
 	struct dm_bufio_client *c = b->c;

 	dm_bufio_lock(c);

-	BUG_ON(test_bit(B_READING, &b->state));
 	BUG_ON(!b->hold_count);

 	b->hold_count--;
@@ -1024,6 +1077,7 @@ void dm_bufio_release(struct dm_buffer *b)
 		 * invalid buffer.
 		 */
 		if ((b->read_error || b->write_error) &&
+		    !test_bit(B_READING, &b->state) &&
 		    !test_bit(B_WRITING, &b->state) &&
 		    !test_bit(B_DIRTY, &b->state)) {
 			__unlink_buffer(b);
@@ -1041,6 +1095,8 @@ void dm_bufio_mark_buffer_dirty(struct dm_buffer *b)

 	dm_bufio_lock(c);

+	BUG_ON(test_bit(B_READING, &b->state));
+
 	if (!test_and_set_bit(B_DIRTY, &b->state))
 		__relink_lru(b, LIST_DIRTY);

@@ -62,6 +62,14 @@ void *dm_bufio_get(struct dm_bufio_client *c, sector_t block,
 void *dm_bufio_new(struct dm_bufio_client *c, sector_t block,
 		   struct dm_buffer **bp);

+/*
+ * Prefetch the specified blocks to the cache.
+ * The function starts to read the blocks and returns without waiting for
+ * I/O to finish.
+ */
+void dm_bufio_prefetch(struct dm_bufio_client *c,
+		       sector_t block, unsigned n_blocks);
+
 /*
 * Release a reference obtained with dm_bufio_{read,get,new}. The data
 * pointer and dm_buffer pointer is no longer valid after this call.
@@ -176,7 +176,6 @@ struct crypt_config {

 #define MIN_IOS        16
 #define MIN_POOL_PAGES 32
-#define MIN_BIO_PAGES  8

 static struct kmem_cache *_crypt_io_pool;

@@ -848,12 +847,11 @@ static struct bio *crypt_alloc_buffer(struct dm_crypt_io *io, unsigned size,
 		}

 		/*
-		 * if additional pages cannot be allocated without waiting,
-		 * return a partially allocated bio, the caller will then try
-		 * to allocate additional bios while submitting this partial bio
+		 * If additional pages cannot be allocated without waiting,
+		 * return a partially-allocated bio.  The caller will then try
+		 * to allocate more bios while submitting this partial bio.
 		 */
-		if (i == (MIN_BIO_PAGES - 1))
-			gfp_mask = (gfp_mask | __GFP_NOWARN) & ~__GFP_WAIT;
+		gfp_mask = (gfp_mask | __GFP_NOWARN) & ~__GFP_WAIT;

 		len = (size > PAGE_SIZE) ? PAGE_SIZE : size;

@@ -1046,16 +1044,14 @@ static void kcryptd_queue_io(struct dm_crypt_io *io)
 	queue_work(cc->io_queue, &io->work);
 }

-static void kcryptd_crypt_write_io_submit(struct dm_crypt_io *io,
-					  int error, int async)
+static void kcryptd_crypt_write_io_submit(struct dm_crypt_io *io, int async)
 {
 	struct bio *clone = io->ctx.bio_out;
 	struct crypt_config *cc = io->target->private;

-	if (unlikely(error < 0)) {
+	if (unlikely(io->error < 0)) {
 		crypt_free_buffer_pages(cc, clone);
 		bio_put(clone);
-		io->error = -EIO;
 		crypt_dec_pending(io);
 		return;
 	}
@@ -1106,12 +1102,16 @@ static void kcryptd_crypt_write_convert(struct dm_crypt_io *io)
 		sector += bio_sectors(clone);

 		crypt_inc_pending(io);
+
 		r = crypt_convert(cc, &io->ctx);
+		if (r < 0)
+			io->error = -EIO;
+
 		crypt_finished = atomic_dec_and_test(&io->ctx.pending);

 		/* Encryption was already finished, submit io now */
 		if (crypt_finished) {
-			kcryptd_crypt_write_io_submit(io, r, 0);
+			kcryptd_crypt_write_io_submit(io, 0);

 			/*
 			 * If there was an error, do not try next fragments.
@@ -1162,11 +1162,8 @@ static void kcryptd_crypt_write_convert(struct dm_crypt_io *io)
 	crypt_dec_pending(io);
 }

-static void kcryptd_crypt_read_done(struct dm_crypt_io *io, int error)
+static void kcryptd_crypt_read_done(struct dm_crypt_io *io)
 {
-	if (unlikely(error < 0))
-		io->error = -EIO;
-
 	crypt_dec_pending(io);
 }

@@ -1181,9 +1178,11 @@ static void kcryptd_crypt_read_convert(struct dm_crypt_io *io)
 			   io->sector);

 	r = crypt_convert(cc, &io->ctx);
+	if (r < 0)
+		io->error = -EIO;

 	if (atomic_dec_and_test(&io->ctx.pending))
-		kcryptd_crypt_read_done(io, r);
+		kcryptd_crypt_read_done(io);

 	crypt_dec_pending(io);
 }
@@ -1204,15 +1203,18 @@ static void kcryptd_async_done(struct crypto_async_request *async_req,
 	if (!error && cc->iv_gen_ops && cc->iv_gen_ops->post)
 		error = cc->iv_gen_ops->post(cc, iv_of_dmreq(cc, dmreq), dmreq);

+	if (error < 0)
+		io->error = -EIO;
+
 	mempool_free(req_of_dmreq(cc, dmreq), cc->req_pool);

 	if (!atomic_dec_and_test(&ctx->pending))
 		return;

 	if (bio_data_dir(io->base_bio) == READ)
-		kcryptd_crypt_read_done(io, error);
+		kcryptd_crypt_read_done(io);
 	else
-		kcryptd_crypt_write_io_submit(io, error, 1);
+		kcryptd_crypt_write_io_submit(io, 1);
 }

 static void kcryptd_crypt(struct work_struct *work)
@@ -1413,6 +1415,7 @@ static int crypt_ctr_cipher(struct dm_target *ti,
 	char *tmp, *cipher, *chainmode, *ivmode, *ivopts, *keycount;
 	char *cipher_api = NULL;
 	int cpu, ret = -EINVAL;
+	char dummy;

 	/* Convert to crypto api definition? */
 	if (strchr(cipher_in, '(')) {
@@ -1434,7 +1437,7 @@ static int crypt_ctr_cipher(struct dm_target *ti,

 	if (!keycount)
 		cc->tfms_count = 1;
-	else if (sscanf(keycount, "%u", &cc->tfms_count) != 1 ||
+	else if (sscanf(keycount, "%u%c", &cc->tfms_count, &dummy) != 1 ||
 		 !is_power_of_2(cc->tfms_count)) {
 		ti->error = "Bad cipher key count specification";
 		return -EINVAL;
@@ -1579,6 +1582,7 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	int ret;
 	struct dm_arg_set as;
 	const char *opt_string;
+	char dummy;

 	static struct dm_arg _args[] = {
 		{0, 1, "Invalid number of feature args"},
@@ -1636,7 +1640,7 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	}

 	ret = -EINVAL;
-	if (sscanf(argv[2], "%llu", &tmpll) != 1) {
+	if (sscanf(argv[2], "%llu%c", &tmpll, &dummy) != 1) {
 		ti->error = "Invalid iv_offset sector";
 		goto bad;
 	}
@@ -1647,7 +1651,7 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 		goto bad;
 	}

-	if (sscanf(argv[4], "%llu", &tmpll) != 1) {
+	if (sscanf(argv[4], "%llu%c", &tmpll, &dummy) != 1) {
 		ti->error = "Invalid device sector";
 		goto bad;
 	}
@@ -131,6 +131,7 @@ static int delay_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 {
 	struct delay_c *dc;
 	unsigned long long tmpll;
+	char dummy;

 	if (argc != 3 && argc != 6) {
 		ti->error = "requires exactly 3 or 6 arguments";
@@ -145,13 +146,13 @@ static int delay_ctr(struct dm_target *ti, unsigned int argc, char **argv)

 	dc->reads = dc->writes = 0;

-	if (sscanf(argv[1], "%llu", &tmpll) != 1) {
+	if (sscanf(argv[1], "%llu%c", &tmpll, &dummy) != 1) {
 		ti->error = "Invalid device sector";
 		goto bad;
 	}
 	dc->start_read = tmpll;

-	if (sscanf(argv[2], "%u", &dc->read_delay) != 1) {
+	if (sscanf(argv[2], "%u%c", &dc->read_delay, &dummy) != 1) {
 		ti->error = "Invalid delay";
 		goto bad;
 	}
@@ -166,13 +167,13 @@ static int delay_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	if (argc == 3)
 		goto out;

-	if (sscanf(argv[4], "%llu", &tmpll) != 1) {
+	if (sscanf(argv[4], "%llu%c", &tmpll, &dummy) != 1) {
 		ti->error = "Invalid write device sector";
 		goto bad_dev_read;
 	}
 	dc->start_write = tmpll;

-	if (sscanf(argv[5], "%u", &dc->write_delay) != 1) {
+	if (sscanf(argv[5], "%u%c", &dc->write_delay, &dummy) != 1) {
 		ti->error = "Invalid write delay";
 		goto bad_dev_read;
 	}
@@ -283,7 +283,7 @@ int dm_exception_store_init(void)
 	return 0;

 persistent_fail:
-	dm_persistent_snapshot_exit();
+	dm_transient_snapshot_exit();
 transient_fail:
 	return r;
 }
@@ -160,6 +160,7 @@ static int flakey_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	unsigned long long tmpll;
 	struct dm_arg_set as;
 	const char *devname;
+	char dummy;

 	as.argc = argc;
 	as.argv = argv;
@@ -178,7 +179,7 @@ static int flakey_ctr(struct dm_target *ti, unsigned int argc, char **argv)

 	devname = dm_shift_arg(&as);

-	if (sscanf(dm_shift_arg(&as), "%llu", &tmpll) != 1) {
+	if (sscanf(dm_shift_arg(&as), "%llu%c", &tmpll, &dummy) != 1) {
 		ti->error = "Invalid device sector";
 		goto bad;
 	}
@@ -880,6 +880,7 @@ static int dev_set_geometry(struct dm_ioctl *param, size_t param_size)
 	struct hd_geometry geometry;
 	unsigned long indata[4];
 	char *geostr = (char *) param + param->data_start;
+	char dummy;

 	md = find_device(param);
 	if (!md)
@@ -891,8 +892,8 @@ static int dev_set_geometry(struct dm_ioctl *param, size_t param_size)
 		goto out;
 	}

-	x = sscanf(geostr, "%lu %lu %lu %lu", indata,
-		   indata + 1, indata + 2, indata + 3);
+	x = sscanf(geostr, "%lu %lu %lu %lu%c", indata,
+		   indata + 1, indata + 2, indata + 3, &dummy);

 	if (x != 4) {
 		DMWARN("Unable to interpret geometry settings.");
@@ -29,6 +29,7 @@ static int linear_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 {
 	struct linear_c *lc;
 	unsigned long long tmp;
+	char dummy;

 	if (argc != 2) {
 		ti->error = "Invalid argument count";
@@ -41,7 +42,7 @@ static int linear_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 		return -ENOMEM;
 	}

-	if (sscanf(argv[1], "%llu", &tmp) != 1) {
+	if (sscanf(argv[1], "%llu%c", &tmp, &dummy) != 1) {
 		ti->error = "dm-linear: Invalid device sector";
 		goto bad;
 	}
@@ -369,6 +369,7 @@ static int create_log_context(struct dm_dirty_log *log, struct dm_target *ti,
 	unsigned int region_count;
 	size_t bitset_size, buf_size;
 	int r;
+	char dummy;

 	if (argc < 1 || argc > 2) {
 		DMWARN("wrong number of arguments to dirty region log");
@@ -387,7 +388,7 @@ static int create_log_context(struct dm_dirty_log *log, struct dm_target *ti,
 		}
 	}

-	if (sscanf(argv[0], "%u", &region_size) != 1 ||
+	if (sscanf(argv[0], "%u%c", &region_size, &dummy) != 1 ||
 	    !_check_region_size(ti, region_size)) {
 		DMWARN("invalid region size %s", argv[0]);
 		return -EINVAL;
@@ -226,6 +226,27 @@ static void free_multipath(struct multipath *m)
 	kfree(m);
 }

+static int set_mapinfo(struct multipath *m, union map_info *info)
+{
+	struct dm_mpath_io *mpio;
+
+	mpio = mempool_alloc(m->mpio_pool, GFP_ATOMIC);
+	if (!mpio)
+		return -ENOMEM;
+
+	memset(mpio, 0, sizeof(*mpio));
+	info->ptr = mpio;
+
+	return 0;
+}
+
+static void clear_mapinfo(struct multipath *m, union map_info *info)
+{
+	struct dm_mpath_io *mpio = info->ptr;
+
+	info->ptr = NULL;
+	mempool_free(mpio, m->mpio_pool);
+}

 /*-----------------------------------------------
 * Path selection
@@ -341,13 +362,14 @@ static int __must_push_back(struct multipath *m)
 }

 static int map_io(struct multipath *m, struct request *clone,
-		  struct dm_mpath_io *mpio, unsigned was_queued)
+		  union map_info *map_context, unsigned was_queued)
 {
 	int r = DM_MAPIO_REMAPPED;
 	size_t nr_bytes = blk_rq_bytes(clone);
 	unsigned long flags;
 	struct pgpath *pgpath;
 	struct block_device *bdev;
+	struct dm_mpath_io *mpio = map_context->ptr;

 	spin_lock_irqsave(&m->lock, flags);

@@ -423,7 +445,6 @@ static void dispatch_queued_ios(struct multipath *m)
 {
 	int r;
 	unsigned long flags;
-	struct dm_mpath_io *mpio;
 	union map_info *info;
 	struct request *clone, *n;
 	LIST_HEAD(cl);
@@ -436,16 +457,15 @@ static void dispatch_queued_ios(struct multipath *m)
 		list_del_init(&clone->queuelist);

 		info = dm_get_rq_mapinfo(clone);
-		mpio = info->ptr;

-		r = map_io(m, clone, mpio, 1);
+		r = map_io(m, clone, info, 1);
 		if (r < 0) {
-			mempool_free(mpio, m->mpio_pool);
+			clear_mapinfo(m, info);
 			dm_kill_unmapped_request(clone, r);
 		} else if (r == DM_MAPIO_REMAPPED)
 			dm_dispatch_request(clone);
 		else if (r == DM_MAPIO_REQUEUE) {
-			mempool_free(mpio, m->mpio_pool);
+			clear_mapinfo(m, info);
 			dm_requeue_unmapped_request(clone);
 		}
 	}
@@ -908,20 +928,16 @@ static int multipath_map(struct dm_target *ti, struct request *clone,
 			 union map_info *map_context)
 {
 	int r;
-	struct dm_mpath_io *mpio;
 	struct multipath *m = (struct multipath *) ti->private;

-	mpio = mempool_alloc(m->mpio_pool, GFP_ATOMIC);
-	if (!mpio)
+	if (set_mapinfo(m, map_context) < 0)
 		/* ENOMEM, requeue */
 		return DM_MAPIO_REQUEUE;
-	memset(mpio, 0, sizeof(*mpio));

-	map_context->ptr = mpio;
 	clone->cmd_flags |= REQ_FAILFAST_TRANSPORT;
-	r = map_io(m, clone, mpio, 0);
+	r = map_io(m, clone, map_context, 0);
 	if (r < 0 || r == DM_MAPIO_REQUEUE)
-		mempool_free(mpio, m->mpio_pool);
+		clear_mapinfo(m, map_context);

 	return r;
 }
@@ -1054,8 +1070,9 @@ static int switch_pg_num(struct multipath *m, const char *pgstr)
 	struct priority_group *pg;
 	unsigned pgnum;
 	unsigned long flags;
+	char dummy;

-	if (!pgstr || (sscanf(pgstr, "%u", &pgnum) != 1) || !pgnum ||
+	if (!pgstr || (sscanf(pgstr, "%u%c", &pgnum, &dummy) != 1) || !pgnum ||
 	    (pgnum > m->nr_priority_groups)) {
 		DMWARN("invalid PG number supplied to switch_pg_num");
 		return -EINVAL;
@@ -1085,8 +1102,9 @@ static int bypass_pg_num(struct multipath *m, const char *pgstr, int bypassed)
 {
 	struct priority_group *pg;
 	unsigned pgnum;
+	char dummy;

-	if (!pgstr || (sscanf(pgstr, "%u", &pgnum) != 1) || !pgnum ||
+	if (!pgstr || (sscanf(pgstr, "%u%c", &pgnum, &dummy) != 1) || !pgnum ||
 	    (pgnum > m->nr_priority_groups)) {
 		DMWARN("invalid PG number supplied to bypass_pg");
 		return -EINVAL;
@@ -1261,13 +1279,15 @@ static int multipath_end_io(struct dm_target *ti, struct request *clone,
 	struct path_selector *ps;
 	int r;

+	BUG_ON(!mpio);
+
 	r  = do_end_io(m, clone, error, mpio);
 	if (pgpath) {
 		ps = &pgpath->pg->ps;
 		if (ps->type->end_io)
 			ps->type->end_io(ps, &pgpath->path, mpio->nr_bytes);
 	}
-	mempool_free(mpio, m->mpio_pool);
+	clear_mapinfo(m, map_context);

 	return r;
 }
@@ -112,6 +112,7 @@ static int ql_add_path(struct path_selector *ps, struct dm_path *path,
 	struct selector *s = ps->context;
 	struct path_info *pi;
 	unsigned repeat_count = QL_MIN_IO;
+	char dummy;

 	/*
 	 * Arguments: [<repeat_count>]
@@ -123,7 +124,7 @@ static int ql_add_path(struct path_selector *ps, struct dm_path *path,
 		return -EINVAL;
 	}

-	if ((argc == 1) && (sscanf(argv[0], "%u", &repeat_count) != 1)) {
+	if ((argc == 1) && (sscanf(argv[0], "%u%c", &repeat_count, &dummy) != 1)) {
 		*error = "queue-length ps: invalid repeat count";
 		return -EINVAL;
 	}
@@ -604,7 +604,9 @@ static int read_disk_sb(struct md_rdev *rdev, int size)
 		return 0;

 	if (!sync_page_io(rdev, 0, size, rdev->sb_page, READ, 1)) {
-		DMERR("Failed to read device superblock");
+		DMERR("Failed to read superblock of device at position %d",
+		      rdev->raid_disk);
+		set_bit(Faulty, &rdev->flags);
 		return -EINVAL;
 	}

@@ -855,9 +857,25 @@ static int super_validate(struct mddev *mddev, struct md_rdev *rdev)
 static int analyse_superblocks(struct dm_target *ti, struct raid_set *rs)
 {
 	int ret;
+	unsigned redundancy = 0;
+	struct raid_dev *dev;
 	struct md_rdev *rdev, *freshest;
 	struct mddev *mddev = &rs->md;

+	switch (rs->raid_type->level) {
+	case 1:
+		redundancy = rs->md.raid_disks - 1;
+		break;
+	case 4:
+	case 5:
+	case 6:
+		redundancy = rs->raid_type->parity_devs;
+		break;
+	default:
+		ti->error = "Unknown RAID type";
+		return -EINVAL;
+	}
+
 	freshest = NULL;
 	rdev_for_each(rdev, mddev) {
 		if (!rdev->meta_bdev)
@@ -872,6 +890,37 @@ static int analyse_superblocks(struct dm_target *ti, struct raid_set *rs)
 		case 0:
 			break;
 		default:
+			dev = container_of(rdev, struct raid_dev, rdev);
+			if (redundancy--) {
+				if (dev->meta_dev)
+					dm_put_device(ti, dev->meta_dev);
+
+				dev->meta_dev = NULL;
+				rdev->meta_bdev = NULL;
+
+				if (rdev->sb_page)
+					put_page(rdev->sb_page);
+
+				rdev->sb_page = NULL;
+
+				rdev->sb_loaded = 0;
+
+				/*
+				 * We might be able to salvage the data device
+				 * even though the meta device has failed.  For
+				 * now, we behave as though '- -' had been
+				 * set for this device in the table.
+				 */
+				if (dev->data_dev)
+					dm_put_device(ti, dev->data_dev);
+
+				dev->data_dev = NULL;
+				rdev->bdev = NULL;
+
+				list_del(&rdev->same_set);
+
+				continue;
+			}
 			ti->error = "Failed to load superblock";
 			return ret;
 		}
@@ -1214,7 +1263,7 @@ static void raid_resume(struct dm_target *ti)

 static struct target_type raid_target = {
 	.name = "raid",
-	.version = {1, 1, 0},
+	.version = {1, 2, 0},
 	.module = THIS_MODULE,
 	.ctr = raid_ctr,
 	.dtr = raid_dtr,
@@ -924,8 +924,9 @@ static int get_mirror(struct mirror_set *ms, struct dm_target *ti,
 		      unsigned int mirror, char **argv)
 {
 	unsigned long long offset;
+	char dummy;

-	if (sscanf(argv[1], "%llu", &offset) != 1) {
+	if (sscanf(argv[1], "%llu%c", &offset, &dummy) != 1) {
 		ti->error = "Invalid offset";
 		return -EINVAL;
 	}
@@ -953,13 +954,14 @@ static struct dm_dirty_log *create_dirty_log(struct dm_target *ti,
 {
 	unsigned param_count;
 	struct dm_dirty_log *dl;
+	char dummy;

 	if (argc < 2) {
 		ti->error = "Insufficient mirror log arguments";
 		return NULL;
 	}

-	if (sscanf(argv[1], "%u", &param_count) != 1) {
+	if (sscanf(argv[1], "%u%c", &param_count, &dummy) != 1) {
 		ti->error = "Invalid mirror log argument count";
 		return NULL;
 	}
@@ -986,13 +988,14 @@ static int parse_features(struct mirror_set *ms, unsigned argc, char **argv,
 {
 	unsigned num_features;
 	struct dm_target *ti = ms->ti;
+	char dummy;

 	*args_used = 0;

 	if (!argc)
 		return 0;

-	if (sscanf(argv[0], "%u", &num_features) != 1) {
+	if (sscanf(argv[0], "%u%c", &num_features, &dummy) != 1) {
 		ti->error = "Invalid number of features";
 		return -EINVAL;
 	}
@@ -1036,6 +1039,7 @@ static int mirror_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	unsigned int nr_mirrors, m, args_used;
 	struct mirror_set *ms;
 	struct dm_dirty_log *dl;
+	char dummy;

 	dl = create_dirty_log(ti, argc, argv, &args_used);
 	if (!dl)
@@ -1044,7 +1048,7 @@ static int mirror_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	argv += args_used;
 	argc -= args_used;

-	if (!argc || sscanf(argv[0], "%u", &nr_mirrors) != 1 ||
+	if (!argc || sscanf(argv[0], "%u%c", &nr_mirrors, &dummy) != 1 ||
 	    nr_mirrors < 2 || nr_mirrors > DM_KCOPYD_MAX_REGIONS + 1) {
 		ti->error = "Invalid number of mirrors";
 		dm_dirty_log_destroy(dl);
@@ -114,6 +114,7 @@ static int rr_add_path(struct path_selector *ps, struct dm_path *path,
 	struct selector *s = (struct selector *) ps->context;
 	struct path_info *pi;
 	unsigned repeat_count = RR_MIN_IO;
+	char dummy;

 	if (argc > 1) {
 		*error = "round-robin ps: incorrect number of arguments";
@@ -121,7 +122,7 @@ static int rr_add_path(struct path_selector *ps, struct dm_path *path,
 	}

 	/* First path argument is number of I/Os before switching path */
-	if ((argc == 1) && (sscanf(argv[0], "%u", &repeat_count) != 1)) {
+	if ((argc == 1) && (sscanf(argv[0], "%u%c", &repeat_count, &dummy) != 1)) {
 		*error = "round-robin ps: invalid repeat count";
 		return -EINVAL;
 	}
--- a/Show More
+++ b/Show More