diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2011-01-13 17:30:47 -0800 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2011-01-13 17:30:47 -0800 |
commit | f6bcfd94c0a97c11ce9197ade93a08bc8af6e057 (patch) | |
tree | 83d867565b4f2a7627b3288f9e000eaf2b217be9 | |
parent | 509e4aef44eb10e4aef1f81c3c3ff1214671503b (diff) | |
parent | 9d09e663d5502c46f2d9481c04c1087e1c2da698 (diff) |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/agk/linux-2.6-dm
* git://git.kernel.org/pub/scm/linux/kernel/git/agk/linux-2.6-dm: (32 commits)
dm: raid456 basic support
dm: per target unplug callback support
dm: introduce target callbacks and congestion callback
dm mpath: delay activate_path retry on SCSI_DH_RETRY
dm: remove superfluous irq disablement in dm_request_fn
dm log: use PTR_ERR value instead of ENOMEM
dm snapshot: avoid storing private suspended state
dm snapshot: persistent make metadata_wq multithreaded
dm: use non reentrant workqueues if equivalent
dm: convert workqueues to alloc_ordered
dm stripe: switch from local workqueue to system_wq
dm: dont use flush_scheduled_work
dm snapshot: remove unused dm_snapshot queued_bios_work
dm ioctl: suppress needless warning messages
dm crypt: add loop aes iv generator
dm crypt: add multi key capability
dm crypt: add post iv call to iv generator
dm crypt: use io thread for reads only if mempool exhausted
dm crypt: scale to multiple cpus
dm crypt: simplify compatible table output
...
-rw-r--r-- | Documentation/device-mapper/dm-crypt.txt | 7 | ||||
-rw-r--r-- | Documentation/device-mapper/dm-raid.txt | 70 | ||||
-rw-r--r-- | drivers/md/Kconfig | 24 | ||||
-rw-r--r-- | drivers/md/Makefile | 1 | ||||
-rw-r--r-- | drivers/md/dm-crypt.c | 618 | ||||
-rw-r--r-- | drivers/md/dm-delay.c | 2 | ||||
-rw-r--r-- | drivers/md/dm-ioctl.c | 111 | ||||
-rw-r--r-- | drivers/md/dm-kcopyd.c | 57 | ||||
-rw-r--r-- | drivers/md/dm-log-userspace-base.c | 139 | ||||
-rw-r--r-- | drivers/md/dm-log-userspace-transfer.c | 1 | ||||
-rw-r--r-- | drivers/md/dm-log.c | 2 | ||||
-rw-r--r-- | drivers/md/dm-mpath.c | 67 | ||||
-rw-r--r-- | drivers/md/dm-raid.c | 697 | ||||
-rw-r--r-- | drivers/md/dm-raid1.c | 19 | ||||
-rw-r--r-- | drivers/md/dm-snap-persistent.c | 4 | ||||
-rw-r--r-- | drivers/md/dm-snap.c | 62 | ||||
-rw-r--r-- | drivers/md/dm-stripe.c | 27 | ||||
-rw-r--r-- | drivers/md/dm-table.c | 19 | ||||
-rw-r--r-- | drivers/md/dm.c | 23 | ||||
-rw-r--r-- | include/linux/device-mapper.h | 12 | ||||
-rw-r--r-- | include/linux/dm-ioctl.h | 14 | ||||
-rw-r--r-- | include/linux/dm-log-userspace.h | 13 |
22 files changed, 1691 insertions, 298 deletions
diff --git a/Documentation/device-mapper/dm-crypt.txt b/Documentation/device-mapper/dm-crypt.txt index 524de926290d..59293ac4a5d0 100644 --- a/Documentation/device-mapper/dm-crypt.txt +++ b/Documentation/device-mapper/dm-crypt.txt @@ -8,7 +8,7 @@ Parameters: <cipher> <key> <iv_offset> <device path> <offset> <cipher> Encryption cipher and an optional IV generation mode. - (In format cipher-chainmode-ivopts:ivmode). + (In format cipher[:keycount]-chainmode-ivopts:ivmode). Examples: des aes-cbc-essiv:sha256 @@ -20,6 +20,11 @@ Parameters: <cipher> <key> <iv_offset> <device path> <offset> Key used for encryption. It is encoded as a hexadecimal number. You can only use key sizes that are valid for the selected cipher. +<keycount> + Multi-key compatibility mode. You can define <keycount> keys and + then sectors are encrypted according to their offsets (sector 0 uses key0; + sector 1 uses key1 etc.). <keycount> must be a power of two. + <iv_offset> The IV offset is a sector count that is added to the sector number before creating the IV. diff --git a/Documentation/device-mapper/dm-raid.txt b/Documentation/device-mapper/dm-raid.txt new file mode 100644 index 000000000000..33b6b7071ac8 --- /dev/null +++ b/Documentation/device-mapper/dm-raid.txt @@ -0,0 +1,70 @@ +Device-mapper RAID (dm-raid) is a bridge from DM to MD. It +provides a way to use device-mapper interfaces to access the MD RAID +drivers. + +As with all device-mapper targets, the nominal public interfaces are the +constructor (CTR) tables and the status outputs (both STATUSTYPE_INFO +and STATUSTYPE_TABLE). The CTR table looks like the following: + +1: <s> <l> raid \ +2: <raid_type> <#raid_params> <raid_params> \ +3: <#raid_devs> <meta_dev1> <dev1> .. <meta_devN> <devN> + +Line 1 contains the standard first three arguments to any device-mapper +target - the start, length, and target type fields. The target type in +this case is "raid". + +Line 2 contains the arguments that define the particular raid +type/personality/level, the required arguments for that raid type, and +any optional arguments. Possible raid types include: raid4, raid5_la, +raid5_ls, raid5_rs, raid6_zr, raid6_nr, and raid6_nc. (raid1 is +planned for the future.) The list of required and optional parameters +is the same for all the current raid types. The required parameters are +positional, while the optional parameters are given as key/value pairs. +The possible parameters are as follows: + <chunk_size> Chunk size in sectors. + [[no]sync] Force/Prevent RAID initialization + [rebuild <idx>] Rebuild the drive indicated by the index + [daemon_sleep <ms>] Time between bitmap daemon work to clear bits + [min_recovery_rate <kB/sec/disk>] Throttle RAID initialization + [max_recovery_rate <kB/sec/disk>] Throttle RAID initialization + [max_write_behind <sectors>] See '-write-behind=' (man mdadm) + [stripe_cache <sectors>] Stripe cache size for higher RAIDs + +Line 3 contains the list of devices that compose the array in +metadata/data device pairs. If the metadata is stored separately, a '-' +is given for the metadata device position. If a drive has failed or is +missing at creation time, a '-' can be given for both the metadata and +data drives for a given position. + +NB. Currently all metadata devices must be specified as '-'. + +Examples: +# RAID4 - 4 data drives, 1 parity +# No metadata devices specified to hold superblock/bitmap info +# Chunk size of 1MiB +# (Lines separated for easy reading) +0 1960893648 raid \ + raid4 1 2048 \ + 5 - 8:17 - 8:33 - 8:49 - 8:65 - 8:81 + +# RAID4 - 4 data drives, 1 parity (no metadata devices) +# Chunk size of 1MiB, force RAID initialization, +# min recovery rate at 20 kiB/sec/disk +0 1960893648 raid \ + raid4 4 2048 min_recovery_rate 20 sync\ + 5 - 8:17 - 8:33 - 8:49 - 8:65 - 8:81 + +Performing a 'dmsetup table' should display the CTR table used to +construct the mapping (with possible reordering of optional +parameters). + +Performing a 'dmsetup status' will yield information on the state and +health of the array. The output is as follows: +1: <s> <l> raid \ +2: <raid_type> <#devices> <1 health char for each dev> <resync_ratio> + +Line 1 is standard DM output. Line 2 is best shown by example: + 0 1960893648 raid raid4 5 AAAAA 2/490221568 +Here we can see the RAID type is raid4, there are 5 devices - all of +which are 'A'live, and the array is 2/490221568 complete with recovery. diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig index bf1a95e31559..98d9ec85e0eb 100644 --- a/drivers/md/Kconfig +++ b/drivers/md/Kconfig @@ -240,6 +240,30 @@ config DM_MIRROR Allow volume managers to mirror logical volumes, also needed for live data migration tools such as 'pvmove'. +config DM_RAID + tristate "RAID 4/5/6 target (EXPERIMENTAL)" + depends on BLK_DEV_DM && EXPERIMENTAL + select MD_RAID456 + select BLK_DEV_MD + ---help--- + A dm target that supports RAID4, RAID5 and RAID6 mappings + + A RAID-5 set of N drives with a capacity of C MB per drive provides + the capacity of C * (N - 1) MB, and protects against a failure + of a single drive. For a given sector (row) number, (N - 1) drives + contain data sectors, and one drive contains the parity protection. + For a RAID-4 set, the parity blocks are present on a single drive, + while a RAID-5 set distributes the parity across the drives in one + of the available parity distribution methods. + + A RAID-6 set of N drives with a capacity of C MB per drive + provides the capacity of C * (N - 2) MB, and protects + against a failure of any two drives. For a given sector + (row) number, (N - 2) drives contain data sectors, and two + drives contains two independent redundancy syndromes. Like + RAID-5, RAID-6 distributes the syndromes across the drives + in one of the available parity distribution methods. + config DM_LOG_USERSPACE tristate "Mirror userspace logging (EXPERIMENTAL)" depends on DM_MIRROR && EXPERIMENTAL && NET diff --git a/drivers/md/Makefile b/drivers/md/Makefile index 5e3aac41919d..d0138606c2e8 100644 --- a/drivers/md/Makefile +++ b/drivers/md/Makefile @@ -36,6 +36,7 @@ obj-$(CONFIG_DM_SNAPSHOT) += dm-snapshot.o obj-$(CONFIG_DM_MIRROR) += dm-mirror.o dm-log.o dm-region-hash.o obj-$(CONFIG_DM_LOG_USERSPACE) += dm-log-userspace.o obj-$(CONFIG_DM_ZERO) += dm-zero.o +obj-$(CONFIG_DM_RAID) += dm-raid.o ifeq ($(CONFIG_DM_UEVENT),y) dm-mod-objs += dm-uevent.o diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index d5b0e4c0e702..4e054bd91664 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -18,10 +18,14 @@ #include <linux/crypto.h> #include <linux/workqueue.h> #include <linux/backing-dev.h> +#include <linux/percpu.h> #include <asm/atomic.h> #include <linux/scatterlist.h> #include <asm/page.h> #include <asm/unaligned.h> +#include <crypto/hash.h> +#include <crypto/md5.h> +#include <crypto/algapi.h> #include <linux/device-mapper.h> @@ -63,6 +67,7 @@ struct dm_crypt_request { struct convert_context *ctx; struct scatterlist sg_in; struct scatterlist sg_out; + sector_t iv_sector; }; struct crypt_config; @@ -73,11 +78,13 @@ struct crypt_iv_operations { void (*dtr)(struct crypt_config *cc); int (*init)(struct crypt_config *cc); int (*wipe)(struct crypt_config *cc); - int (*generator)(struct crypt_config *cc, u8 *iv, sector_t sector); + int (*generator)(struct crypt_config *cc, u8 *iv, + struct dm_crypt_request *dmreq); + int (*post)(struct crypt_config *cc, u8 *iv, + struct dm_crypt_request *dmreq); }; struct iv_essiv_private { - struct crypto_cipher *tfm; struct crypto_hash *hash_tfm; u8 *salt; }; @@ -86,11 +93,32 @@ struct iv_benbi_private { int shift; }; +#define LMK_SEED_SIZE 64 /* hash + 0 */ +struct iv_lmk_private { + struct crypto_shash *hash_tfm; + u8 *seed; +}; + /* * Crypt: maps a linear range of a block device * and encrypts / decrypts at the same time. */ enum flags { DM_CRYPT_SUSPENDED, DM_CRYPT_KEY_VALID }; + +/* + * Duplicated per-CPU state for cipher. + */ +struct crypt_cpu { + struct ablkcipher_request *req; + /* ESSIV: struct crypto_cipher *essiv_tfm */ + void *iv_private; + struct crypto_ablkcipher *tfms[0]; +}; + +/* + * The fields in here must be read only after initialization, + * changing state should be in crypt_cpu. + */ struct crypt_config { struct dm_dev *dev; sector_t start; @@ -108,17 +136,25 @@ struct crypt_config { struct workqueue_struct *crypt_queue; char *cipher; - char *cipher_mode; + char *cipher_string; struct crypt_iv_operations *iv_gen_ops; union { struct iv_essiv_private essiv; struct iv_benbi_private benbi; + struct iv_lmk_private lmk; } iv_gen_private; sector_t iv_offset; unsigned int iv_size; /* + * Duplicated per cpu state. Access through + * per_cpu_ptr() only. + */ + struct crypt_cpu __percpu *cpu; + unsigned tfms_count; + + /* * Layout of each crypto request: * * struct ablkcipher_request @@ -132,11 +168,10 @@ struct crypt_config { * correctly aligned. */ unsigned int dmreq_start; - struct ablkcipher_request *req; - struct crypto_ablkcipher *tfm; unsigned long flags; unsigned int key_size; + unsigned int key_parts; u8 key[0]; }; @@ -148,6 +183,20 @@ static struct kmem_cache *_crypt_io_pool; static void clone_init(struct dm_crypt_io *, struct bio *); static void kcryptd_queue_crypt(struct dm_crypt_io *io); +static u8 *iv_of_dmreq(struct crypt_config *cc, struct dm_crypt_request *dmreq); + +static struct crypt_cpu *this_crypt_config(struct crypt_config *cc) +{ + return this_cpu_ptr(cc->cpu); +} + +/* + * Use this to access cipher attributes that are the same for each CPU. + */ +static struct crypto_ablkcipher *any_tfm(struct crypt_config *cc) +{ + return __this_cpu_ptr(cc->cpu)->tfms[0]; +} /* * Different IV generation algorithms: @@ -168,23 +217,38 @@ static void kcryptd_queue_crypt(struct dm_crypt_io *io); * null: the initial vector is always zero. Provides compatibility with * obsolete loop_fish2 devices. Do not use for new devices. * + * lmk: Compatible implementation of the block chaining mode used + * by the Loop-AES block device encryption system + * designed by Jari Ruusu. See http://loop-aes.sourceforge.net/ + * It operates on full 512 byte sectors and uses CBC + * with an IV derived from the sector number, the data and + * optionally extra IV seed. + * This means that after decryption the first block + * of sector must be tweaked according to decrypted data. + * Loop-AES can use three encryption schemes: + * version 1: is plain aes-cbc mode + * version 2: uses 64 multikey scheme with lmk IV generator + * version 3: the same as version 2 with additional IV seed + * (it uses 65 keys, last key is used as IV seed) + * * plumb: unimplemented, see: * http://article.gmane.org/gmane.linux.kernel.device-mapper.dm-crypt/454 */ -static int crypt_iv_plain_gen(struct crypt_config *cc, u8 *iv, sector_t sector) +static int crypt_iv_plain_gen(struct crypt_config *cc, u8 *iv, + struct dm_crypt_request *dmreq) { memset(iv, 0, cc->iv_size); - *(u32 *)iv = cpu_to_le32(sector & 0xffffffff); + *(u32 *)iv = cpu_to_le32(dmreq->iv_sector & 0xffffffff); return 0; } static int crypt_iv_plain64_gen(struct crypt_config *cc, u8 *iv, - sector_t sector) + struct dm_crypt_request *dmreq) { memset(iv, 0, cc->iv_size); - *(u64 *)iv = cpu_to_le64(sector); + *(u64 *)iv = cpu_to_le64(dmreq->iv_sector); return 0; } @@ -195,7 +259,8 @@ static int crypt_iv_essiv_init(struct crypt_config *cc) struct iv_essiv_private *essiv = &cc->iv_gen_private.essiv; struct hash_desc desc; struct scatterlist sg; - int err; + struct crypto_cipher *essiv_tfm; + int err, cpu; sg_init_one(&sg, cc->key, cc->key_size); desc.tfm = essiv->hash_tfm; @@ -205,8 +270,16 @@ static int crypt_iv_essiv_init(struct crypt_config *cc) if (err) return err; - return crypto_cipher_setkey(essiv->tfm, essiv->salt, + for_each_possible_cpu(cpu) { + essiv_tfm = per_cpu_ptr(cc->cpu, cpu)->iv_private, + + err = crypto_cipher_setkey(essiv_tfm, essiv->salt, crypto_hash_digestsize(essiv->hash_tfm)); + if (err) + return err; + } + + return 0; } /* Wipe salt and reset key derived from volume key */ @@ -214,24 +287,76 @@ static int crypt_iv_essiv_wipe(struct crypt_config *cc) { struct iv_essiv_private *essiv = &cc->iv_gen_private.essiv; unsigned salt_size = crypto_hash_digestsize(essiv->hash_tfm); + struct crypto_cipher *essiv_tfm; + int cpu, r, err = 0; memset(essiv->salt, 0, salt_size); - return crypto_cipher_setkey(essiv->tfm, essiv->salt, salt_size); + for_each_possible_cpu(cpu) { + essiv_tfm = per_cpu_ptr(cc->cpu, cpu)->iv_private; + r = crypto_cipher_setkey(essiv_tfm, essiv->salt, salt_size); + if (r) + err = r; + } + + return err; +} + +/* Set up per cpu cipher state */ +static struct crypto_cipher *setup_essiv_cpu(struct crypt_config *cc, + struct dm_target *ti, + u8 *salt, unsigned saltsize) +{ + struct crypto_cipher *essiv_tfm; + int err; + + /* Setup the essiv_tfm with the given salt */ + essiv_tfm = crypto_alloc_cipher(cc->cipher, 0, CRYPTO_ALG_ASYNC); + if (IS_ERR(essiv_tfm)) { + ti->error = "Error allocating crypto tfm for ESSIV"; + return essiv_tfm; + } + + if (crypto_cipher_blocksize(essiv_tfm) != + crypto_ablkcipher_ivsize(any_tfm(cc))) { + ti->error = "Block size of ESSIV cipher does " + "not match IV size of block cipher"; + crypto_free_cipher(essiv_tfm); + return ERR_PTR(-EINVAL); + } + + err = crypto_cipher_setkey(essiv_tfm, salt, saltsize); + if (err) { + ti->error = "Failed to set key for ESSIV cipher"; + crypto_free_cipher(essiv_tfm); + return ERR_PTR(err); + } + + return essiv_tfm; } static void crypt_iv_essiv_dtr(struct crypt_config *cc) { + int cpu; + struct crypt_cpu *cpu_cc; + struct crypto_cipher *essiv_tfm; struct iv_essiv_private *essiv = &cc->iv_gen_private.essiv; - crypto_free_cipher(essiv->tfm); - essiv->tfm = NULL; - crypto_free_hash(essiv->hash_tfm); essiv->hash_tfm = NULL; kzfree(essiv->salt); essiv->salt = NULL; + + for_each_possible_cpu(cpu) { + cpu_cc = per_cpu_ptr(cc->cpu, cpu); + essiv_tfm = cpu_cc->iv_private; + + if (essiv_tfm) + crypto_free_cipher(essiv_tfm); + + cpu_cc->iv_private = NULL; + } } static int crypt_iv_essiv_ctr(struct crypt_config *cc, struct dm_target *ti, @@ -240,7 +365,7 @@ static int crypt_iv_essiv_ctr(struct crypt_config *cc, struct dm_target *ti, struct crypto_cipher *essiv_tfm = NULL; struct crypto_hash *hash_tfm = NULL; u8 *salt = NULL; - int err; + int err, cpu; if (!opts) { ti->error = "Digest algorithm missing for ESSIV mode"; @@ -262,48 +387,44 @@ static int crypt_iv_essiv_ctr(struct crypt_config *cc, struct dm_target *ti, goto bad; } - /* Allocate essiv_tfm */ - essiv_tfm = crypto_alloc_cipher(cc->cipher, 0, CRYPTO_ALG_ASYNC); - if (IS_ERR(essiv_tfm)) { - ti->error = "Error allocating crypto tfm for ESSIV"; - err = PTR_ERR(essiv_tfm); - goto bad; - } - if (crypto_cipher_blocksize(essiv_tfm) != - crypto_ablkcipher_ivsize(cc->tfm)) { - ti->error = "Block size of ESSIV cipher does " - "not match IV size of block cipher"; - err = -EINVAL; - goto bad; - } - cc->iv_gen_private.essiv.salt = salt; - cc->iv_gen_private.essiv.tfm = essiv_tfm; cc->iv_gen_private.essiv.hash_tfm = hash_tfm; + for_each_possible_cpu(cpu) { + essiv_tfm = setup_essiv_cpu(cc, ti, salt, + crypto_hash_digestsize(hash_tfm)); + if (IS_ERR(essiv_tfm)) { + crypt_iv_essiv_dtr(cc); + return PTR_ERR(essiv_tfm); + } + per_cpu_ptr(cc->cpu, cpu)->iv_private = essiv_tfm; + } + return 0; bad: - if (essiv_tfm && !IS_ERR(essiv_tfm)) - crypto_free_cipher(essiv_tfm); if (hash_tfm && !IS_ERR(hash_tfm)) crypto_free_hash(hash_tfm); kfree(salt); return err; } -static int crypt_iv_essiv_gen(struct crypt_config *cc, u8 *iv, sector_t sector) +static int crypt_iv_essiv_gen(struct crypt_config *cc, u8 *iv, + struct dm_crypt_request *dmreq) { + struct crypto_cipher *essiv_tfm = this_crypt_config(cc)->iv_private; + memset(iv, 0, cc->iv_size); - *(u64 *)iv = cpu_to_le64(sector); - crypto_cipher_encrypt_one(cc->iv_gen_private.essiv.tfm, iv, iv); + *(u64 *)iv = cpu_to_le64(dmreq->iv_sector); + crypto_cipher_encrypt_one(essiv_tfm, iv, iv); + return 0; } static int crypt_iv_benbi_ctr(struct crypt_config *cc, struct dm_target *ti, const char *opts) { - unsigned bs = crypto_ablkcipher_blocksize(cc->tfm); + unsigned bs = crypto_ablkcipher_blocksize(any_tfm(cc)); int log = ilog2(bs); /* we need to calculate how far we must shift the sector count @@ -328,25 +449,177 @@ static void crypt_iv_benbi_dtr(struct crypt_config *cc) { } -static int crypt_iv_benbi_gen(struct crypt_config *cc, u8 *iv, sector_t sector) +static int crypt_iv_benbi_gen(struct crypt_config *cc, u8 *iv, + struct dm_crypt_request *dmreq) { __be64 val; memset(iv, 0, cc->iv_size - sizeof(u64)); /* rest is cleared below */ - val = cpu_to_be64(((u64)sector << cc->iv_gen_private.benbi.shift) + 1); + val = cpu_to_be64(((u64)dmreq->iv_sector << cc->iv_gen_private.benbi.shift) + 1); put_unaligned(val, (__be64 *)(iv + cc->iv_size - sizeof(u64))); return 0; } -static int crypt_iv_null_gen(struct crypt_config *cc, u8 *iv, sector_t sector) +static int crypt_iv_null_gen(struct crypt_config *cc, u8 *iv, + struct dm_crypt_request *dmreq) { memset(iv, 0, cc->iv_size); return 0; } +static void crypt_iv_lmk_dtr(struct crypt_config *cc) +{ + struct iv_lmk_private *lmk = &cc->iv_gen_private.lmk; + + if (lmk->hash_tfm && !IS_ERR(lmk->hash_tfm)) + crypto_free_shash(lmk->hash_tfm); + lmk->hash_tfm = NULL; + + kzfree(lmk->seed); + lmk->seed = NULL; +} + +static int crypt_iv_lmk_ctr(struct crypt_config *cc, struct dm_target *ti, + const char *opts) +{ + struct iv_lmk_private *lmk = &cc->iv_gen_private.lmk; + + lmk->hash_tfm = crypto_alloc_shash("md5", 0, 0); + if (IS_ERR(lmk->hash_tfm)) { + ti->error = "Error initializing LMK hash"; + return PTR_ERR(lmk->hash_tfm); + } + + /* No seed in LMK version 2 */ + if (cc->key_parts == cc->tfms_count) { + lmk->seed = NULL; + return 0; + } + + lmk->seed = kzalloc(LMK_SEED_SIZE, GFP_KERNEL); + if (!lmk->seed) { + crypt_iv_lmk_dtr(cc); + ti->error = "Error kmallocing seed storage in LMK"; + return -ENOMEM; + } + + return 0; +} + +static int crypt_iv_lmk_init(struct crypt_config *cc) +{ + struct iv_lmk_private *lmk = &cc->iv_gen_private.lmk; + int subkey_size = cc->key_size / cc->key_parts; + + /* LMK seed is on the position of LMK_KEYS + 1 key */ + if (lmk->seed) + memcpy(lmk->seed, cc->key + (cc->tfms_count * subkey_size), + crypto_shash_digestsize(lmk->hash_tfm)); + + return 0; +} + +static int crypt_iv_lmk_wipe(struct crypt_config *cc) +{ + struct iv_lmk_private *lmk = &cc->iv_gen_private.lmk; + + if (lmk->seed) + memset(lmk->seed, 0, LMK_SEED_SIZE); + + return 0; +} + +static int crypt_iv_lmk_one(struct crypt_config *cc, u8 *iv, + struct dm_crypt_request *dmreq, + u8 *data) +{ + struct iv_lmk_private *lmk = &cc->iv_gen_private.lmk; + struct { + struct shash_desc desc; + char ctx[crypto_shash_descsize(lmk->hash_tfm)]; + } sdesc; + struct md5_state md5state; + u32 buf[4]; + int i, r; + + sdesc.desc.tfm = lmk->hash_tfm; + sdesc.desc.flags = CRYPTO_TFM_REQ_MAY_SLEEP; + + r = crypto_shash_init(&sdesc.desc); + if (r) + return r; + + if (lmk->seed) { + r = crypto_shash_update(&sdesc.desc, lmk->seed, LMK_SEED_SIZE); + if (r) + return r; + } + + /* Sector is always 512B, block size 16, add data of blocks 1-31 */ + r = crypto_shash_update(&sdesc.desc, data + 16, 16 * 31); + if (r) + return r; + + /* Sector is cropped to 56 bits here */ + buf[0] = cpu_to_le32(dmreq->iv_sector & 0xFFFFFFFF); + buf[1] = cpu_to_le32((((u64)dmreq->iv_sector >> 32) & 0x00FFFFFF) | 0x80000000); + buf[2] = cpu_to_le32(4024); + buf[3] = 0; + r = crypto_shash_update(&sdesc.desc, (u8 *)buf, sizeof(buf)); + if (r) + return r; + + /* No MD5 padding here */ + r = crypto_shash_export(&sdesc.desc, &md5state); + if (r) + return r; + + for (i = 0; i < MD5_HASH_WORDS; i++) + __cpu_to_le32s(&md5state.hash[i]); + memcpy(iv, &md5state.hash, cc->iv_size); + + return 0; +} + +static int crypt_iv_lmk_gen(struct crypt_config *cc, u8 *iv, + struct dm_crypt_request *dmreq) +{ + u8 *src; + int r = 0; + + if (bio_data_dir(dmreq->ctx->bio_in) == WRITE) { + src = kmap_atomic(sg_page(&dmreq->sg_in), KM_USER0); + r = crypt_iv_lmk_one(cc, iv, dmreq, src + dmreq->sg_in.offset); + kunmap_atomic(src, KM_USER0); + } else + memset(iv, 0, cc->iv_size); + + return r; +} + +static int crypt_iv_lmk_post(struct crypt_config *cc, u8 *iv, + struct dm_crypt_request *dmreq) +{ + u8 *dst; + int r; + + if (bio_data_dir(dmreq->ctx->bio_in) == WRITE) + return 0; + + dst = kmap_atomic(sg_page(&dmreq->sg_out), KM_USER0); + r = crypt_iv_lmk_one(cc, iv, dmreq, dst + dmreq->sg_out.offset); + + /* Tweak the first block of plaintext sector */ + if (!r) + crypto_xor(dst + dmreq->sg_out.offset, iv, cc->iv_size); + + kunmap_atomic(dst, KM_USER0); + return r; +} + static struct crypt_iv_operations crypt_iv_plain_ops = { .generator = crypt_iv_plain_gen }; @@ -373,6 +646,15 @@ static struct crypt_iv_operations crypt_iv_null_ops = { .generator = crypt_iv_null_gen }; +static struct crypt_iv_operations crypt_iv_lmk_ops = { + .ctr = crypt_iv_lmk_ctr, + .dtr = crypt_iv_lmk_dtr, + .init = crypt_iv_lmk_init, + .wipe = crypt_iv_lmk_wipe, + .generator = crypt_iv_lmk_gen, + .post = crypt_iv_lmk_post +}; + static void crypt_convert_init(struct crypt_config *cc, struct convert_context *ctx, struct bio *bio_out, struct bio *bio_in, @@ -400,6 +682,13 @@ static struct ablkcipher_request *req_of_dmreq(struct crypt_config *cc, return (struct ablkcipher_request *)((char *)dmreq - cc->dmreq_start); } +static u8 *iv_of_dmreq(struct crypt_config *cc, + struct dm_crypt_request *dmreq) +{ + return (u8 *)ALIGN((unsigned long)(dmreq + 1), + crypto_ablkcipher_alignmask(any_tfm(cc)) + 1); +} + static int crypt_convert_block(struct crypt_config *cc, struct convert_context *ctx, struct ablkcipher_request *req) @@ -411,9 +700,9 @@ static int crypt_convert_block(struct crypt_config *cc, int r = 0; dmreq = dmreq_of_req(cc, req); - iv = (u8 *)ALIGN((unsigned long)(dmreq + 1), - crypto_ablkcipher_alignmask(cc->tfm) + 1); + iv = iv_of_dmreq(cc, dmreq); + dmreq->iv_sector = ctx->sector; dmreq->ctx = ctx; sg_init_table(&dmreq->sg_in, 1); sg_set_page(&dmreq->sg_in, bv_in->bv_page, 1 << SECTOR_SHIFT, @@ -436,7 +725,7 @@ static int crypt_convert_block(struct crypt_config *cc, } if (cc->iv_gen_ops) { - r = cc->iv_gen_ops->generator(cc, iv, ctx->sector); + r = cc->iv_gen_ops->generator(cc, iv, dmreq); if (r < 0) return r; } @@ -449,21 +738,28 @@ static int crypt_convert_block(struct crypt_config *cc, else r = crypto_ablkcipher_decrypt(req); + if (!r && cc->iv_gen_ops && cc->iv_gen_ops->post) + r = cc->iv_gen_ops->post(cc, iv, dmreq); + return r; } static void kcryptd_async_done(struct crypto_async_request *async_req, int error); + static void crypt_alloc_req(struct crypt_config *cc, struct convert_context *ctx) { - if (!cc->req) - cc->req = mempool_alloc(cc->req_pool, GFP_NOIO); - ablkcipher_request_set_tfm(cc->req, cc->tfm); - ablkcipher_request_set_callback(cc->req, CRYPTO_TFM_REQ_MAY_BACKLOG | - CRYPTO_TFM_REQ_MAY_SLEEP, - kcryptd_async_done, - dmreq_of_req(cc, cc->req)); + struct crypt_cpu *this_cc = this_crypt_config(cc); + unsigned key_index = ctx->sector & (cc->tfms_count - 1); + + if (!this_cc->req) + this_cc->req = mempool_alloc(cc->req_pool, GFP_NOIO); + + ablkcipher_request_set_tfm(this_cc->req, this_cc->tfms[key_index]); + ablkcipher_request_set_callback(this_cc->req, + CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP, + kcryptd_async_done, dmreq_of_req(cc, this_cc->req)); } /* @@ -472,6 +768,7 @@ static void crypt_alloc_req(struct crypt_config *cc, static int crypt_convert(struct crypt_config *cc, struct convert_context *ctx) { + struct crypt_cpu *this_cc = this_crypt_config(cc); int r; atomic_set(&ctx->pending, 1); @@ -483,7 +780,7 @@ static int crypt_convert(struct crypt_config *cc, atomic_inc(&ctx->pending); - r = crypt_convert_block(cc, ctx, cc->req); + r = crypt_convert_block(cc, ctx, this_cc->req); switch (r) { /* async */ @@ -492,7 +789,7 @@ static int crypt_convert(struct crypt_config *cc, INIT_COMPLETION(ctx->restart); /* fall through*/ case -EINPROGRESS: - cc->req = NULL; + this_cc->req = NULL; ctx->sector++; continue; @@ -651,6 +948,9 @@ static void crypt_dec_pending(struct dm_crypt_io *io) * They must be separated as otherwise the final stages could be * starved by new requests which can block in the first stages due * to memory allocation. + * + * The work is done per CPU global for all dm-crypt instances. + * They should not depend on each other and do not block. */ static void crypt_endio(struct bio *clone, int error) { @@ -691,26 +991,30 @@ static void clone_init(struct dm_crypt_io *io, struct bio *clone) clone->bi_destructor = dm_crypt_bio_destructor; } -static void kcryptd_io_read(struct dm_crypt_io *io) +static void kcryptd_unplug(struct crypt_config *cc) +{ + blk_unplug(bdev_get_queue(cc->dev->bdev)); +} + +static int kcryptd_io_read(struct dm_crypt_io *io, gfp_t gfp) { struct crypt_config *cc = io->target->private; struct bio *base_bio = io->base_bio; struct bio *clone; - crypt_inc_pending(io); - /* * The block layer might modify the bvec array, so always * copy the required bvecs because we need the original * one in order to decrypt the whole bio data *afterwards*. */ - clone = bio_alloc_bioset(GFP_NOIO, bio_segments(base_bio), cc->bs); - if (unlikely(!clone)) { - io->error = -ENOMEM; - crypt_dec_pending(io); - return; + clone = bio_alloc_bioset(gfp, bio_segments(base_bio), cc->bs); + if (!clone) { + kcryptd_unplug(cc); + return 1; } + crypt_inc_pending(io); + clone_init(io, clone); clone->bi_idx = 0; clone->bi_vcnt = bio_segments(base_bio); @@ -720,6 +1024,7 @@ static void kcryptd_io_read(struct dm_crypt_io *io) sizeof(struct bio_vec) * clone->bi_vcnt); generic_make_request(clone); + return 0; } static void kcryptd_io_write(struct dm_crypt_io *io) @@ -732,9 +1037,12 @@ static void kcryptd_io(struct work_struct *work) { struct dm_crypt_io *io = container_of(work, struct dm_crypt_io, work); - if (bio_data_dir(io->base_bio) == READ) - kcryptd_io_read(io); - else + if (bio_data_dir(io->base_bio) == READ) { + crypt_inc_pending(io); + if (kcryptd_io_read(io, GFP_NOIO)) + io->error = -ENOMEM; + crypt_dec_pending(io); + } else kcryptd_io_write(io); } @@ -901,6 +1209,9 @@ static void kcryptd_async_done(struct crypto_async_request *async_req, return; } + if (!error && cc->iv_gen_ops && cc->iv_gen_ops->post) + error = cc->iv_gen_ops->post(cc, iv_of_dmreq(cc, dmreq), dmreq); + mempool_free(req_of_dmreq(cc, dmreq), cc->req_pool); if (!atomic_dec_and_test(&ctx->pending)) @@ -971,34 +1282,84 @@ static void crypt_encode_key(char *hex, u8 *key, unsigned int size) } } -static int crypt_set_key(struct crypt_config *cc, char *key) +static void crypt_free_tfms(struct crypt_config *cc, int cpu) { - unsigned key_size = strlen(key) >> 1; + struct crypt_cpu *cpu_cc = per_cpu_ptr(cc->cpu, cpu); + unsigned i; - if (cc->key_size && cc->key_size != key_size) + for (i = 0; i < cc->tfms_count; i++) + if (cpu_cc->tfms[i] && !IS_ERR(cpu_cc->tfms[i])) { + crypto_free_ablkcipher(cpu_cc->tfms[i]); + |