diff options
Diffstat (limited to 'drivers/md')
54 files changed, 28483 insertions, 0 deletions
diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig new file mode 100644 index 000000000000..ac43f98062fd --- /dev/null +++ b/drivers/md/Kconfig @@ -0,0 +1,240 @@ +# +# Block device driver configuration +# + +menu "Multi-device support (RAID and LVM)" + +config MD + bool "Multiple devices driver support (RAID and LVM)" + help + Support multiple physical spindles through a single logical device. + Required for RAID and logical volume management. + +config BLK_DEV_MD + tristate "RAID support" + depends on MD + ---help--- + This driver lets you combine several hard disk partitions into one + logical block device. This can be used to simply append one + partition to another one or to combine several redundant hard disks + into a RAID1/4/5 device so as to provide protection against hard + disk failures. This is called "Software RAID" since the combining of + the partitions is done by the kernel. "Hardware RAID" means that the + combining is done by a dedicated controller; if you have such a + controller, you do not need to say Y here. + + More information about Software RAID on Linux is contained in the + Software RAID mini-HOWTO, available from + <http://www.tldp.org/docs.html#howto>. There you will also learn + where to get the supporting user space utilities raidtools. + + If unsure, say N. + +config MD_LINEAR + tristate "Linear (append) mode" + depends on BLK_DEV_MD + ---help--- + If you say Y here, then your multiple devices driver will be able to + use the so-called linear mode, i.e. it will combine the hard disk + partitions by simply appending one to the other. + + To compile this as a module, choose M here: the module + will be called linear. + + If unsure, say Y. + +config MD_RAID0 + tristate "RAID-0 (striping) mode" + depends on BLK_DEV_MD + ---help--- + If you say Y here, then your multiple devices driver will be able to + use the so-called raid0 mode, i.e. it will combine the hard disk + partitions into one logical device in such a fashion as to fill them + up evenly, one chunk here and one chunk there. This will increase + the throughput rate if the partitions reside on distinct disks. + + Information about Software RAID on Linux is contained in the + Software-RAID mini-HOWTO, available from + <http://www.tldp.org/docs.html#howto>. There you will also + learn where to get the supporting user space utilities raidtools. + + To compile this as a module, choose M here: the module + will be called raid0. + + If unsure, say Y. + +config MD_RAID1 + tristate "RAID-1 (mirroring) mode" + depends on BLK_DEV_MD + ---help--- + A RAID-1 set consists of several disk drives which are exact copies + of each other. In the event of a mirror failure, the RAID driver + will continue to use the operational mirrors in the set, providing + an error free MD (multiple device) to the higher levels of the + kernel. In a set with N drives, the available space is the capacity + of a single drive, and the set protects against a failure of (N - 1) + drives. + + Information about Software RAID on Linux is contained in the + Software-RAID mini-HOWTO, available from + <http://www.tldp.org/docs.html#howto>. There you will also + learn where to get the supporting user space utilities raidtools. + + If you want to use such a RAID-1 set, say Y. To compile this code + as a module, choose M here: the module will be called raid1. + + If unsure, say Y. + +config MD_RAID10 + tristate "RAID-10 (mirrored striping) mode (EXPERIMENTAL)" + depends on BLK_DEV_MD && EXPERIMENTAL + ---help--- + RAID-10 provides a combination of striping (RAID-0) and + mirroring (RAID-1) with easier configuration and more flexable + layout. + Unlike RAID-0, but like RAID-1, RAID-10 requires all devices to + be the same size (or at least, only as much as the smallest device + will be used). + RAID-10 provides a variety of layouts that provide different levels + of redundancy and performance. + + RAID-10 requires mdadm-1.7.0 or later, available at: + + ftp://ftp.kernel.org/pub/linux/utils/raid/mdadm/ + + If unsure, say Y. + +config MD_RAID5 + tristate "RAID-4/RAID-5 mode" + depends on BLK_DEV_MD + ---help--- + 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. + + Information about Software RAID on Linux is contained in the + Software-RAID mini-HOWTO, available from + <http://www.tldp.org/docs.html#howto>. There you will also + learn where to get the supporting user space utilities raidtools. + + If you want to use such a RAID-4/RAID-5 set, say Y. To + compile this code as a module, choose M here: the module + will be called raid5. + + If unsure, say Y. + +config MD_RAID6 + tristate "RAID-6 mode" + depends on BLK_DEV_MD + ---help--- + 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. + + RAID-6 requires mdadm-1.5.0 or later, available at: + + ftp://ftp.kernel.org/pub/linux/utils/raid/mdadm/ + + If you want to use such a RAID-6 set, say Y. To compile + this code as a module, choose M here: the module will be + called raid6. + + If unsure, say Y. + +config MD_MULTIPATH + tristate "Multipath I/O support" + depends on BLK_DEV_MD + help + Multipath-IO is the ability of certain devices to address the same + physical disk over multiple 'IO paths'. The code ensures that such + paths can be defined and handled at runtime, and ensures that a + transparent failover to the backup path(s) happens if a IO errors + arrives on the primary path. + + If unsure, say N. + +config MD_FAULTY + tristate "Faulty test module for MD" + depends on BLK_DEV_MD + help + The "faulty" module allows for a block device that occasionally returns + read or write errors. It is useful for testing. + + In unsure, say N. + +config BLK_DEV_DM + tristate "Device mapper support" + depends on MD + ---help--- + Device-mapper is a low level volume manager. It works by allowing + people to specify mappings for ranges of logical sectors. Various + mapping types are available, in addition people may write their own + modules containing custom mappings if they wish. + + Higher level volume managers such as LVM2 use this driver. + + To compile this as a module, choose M here: the module will be + called dm-mod. + + If unsure, say N. + +config DM_CRYPT + tristate "Crypt target support" + depends on BLK_DEV_DM && EXPERIMENTAL + select CRYPTO + ---help--- + This device-mapper target allows you to create a device that + transparently encrypts the data on it. You'll need to activate + the ciphers you're going to use in the cryptoapi configuration. + + Information on how to use dm-crypt can be found on + + <http://www.saout.de/misc/dm-crypt/> + + To compile this code as a module, choose M here: the module will + be called dm-crypt. + + If unsure, say N. + +config DM_SNAPSHOT + tristate "Snapshot target (EXPERIMENTAL)" + depends on BLK_DEV_DM && EXPERIMENTAL + ---help--- + Allow volume managers to take writeable snapshots of a device. + +config DM_MIRROR + tristate "Mirror target (EXPERIMENTAL)" + depends on BLK_DEV_DM && EXPERIMENTAL + ---help--- + Allow volume managers to mirror logical volumes, also + needed for live data migration tools such as 'pvmove'. + +config DM_ZERO + tristate "Zero target (EXPERIMENTAL)" + depends on BLK_DEV_DM && EXPERIMENTAL + ---help--- + A target that discards writes, and returns all zeroes for + reads. Useful in some recovery situations. + +config DM_MULTIPATH + tristate "Multipath target (EXPERIMENTAL)" + depends on BLK_DEV_DM && EXPERIMENTAL + ---help--- + Allow volume managers to support multipath hardware. + +config DM_MULTIPATH_EMC + tristate "EMC CX/AX multipath support (EXPERIMENTAL)" + depends on DM_MULTIPATH && BLK_DEV_DM && EXPERIMENTAL + ---help--- + Multipath support for EMC CX/AX series hardware. + +endmenu + diff --git a/drivers/md/Makefile b/drivers/md/Makefile new file mode 100644 index 000000000000..90de9c146a5f --- /dev/null +++ b/drivers/md/Makefile @@ -0,0 +1,107 @@ +# +# Makefile for the kernel software RAID and LVM drivers. +# + +dm-mod-objs := dm.o dm-table.o dm-target.o dm-linear.o dm-stripe.o \ + dm-ioctl.o dm-io.o kcopyd.o +dm-multipath-objs := dm-hw-handler.o dm-path-selector.o dm-mpath.o +dm-snapshot-objs := dm-snap.o dm-exception-store.o +dm-mirror-objs := dm-log.o dm-raid1.o +raid6-objs := raid6main.o raid6algos.o raid6recov.o raid6tables.o \ + raid6int1.o raid6int2.o raid6int4.o \ + raid6int8.o raid6int16.o raid6int32.o \ + raid6altivec1.o raid6altivec2.o raid6altivec4.o \ + raid6altivec8.o \ + raid6mmx.o raid6sse1.o raid6sse2.o +hostprogs-y := mktables + +# Note: link order is important. All raid personalities +# and xor.o must come before md.o, as they each initialise +# themselves, and md.o may use the personalities when it +# auto-initialised. + +obj-$(CONFIG_MD_LINEAR) += linear.o +obj-$(CONFIG_MD_RAID0) += raid0.o +obj-$(CONFIG_MD_RAID1) += raid1.o +obj-$(CONFIG_MD_RAID10) += raid10.o +obj-$(CONFIG_MD_RAID5) += raid5.o xor.o +obj-$(CONFIG_MD_RAID6) += raid6.o xor.o +obj-$(CONFIG_MD_MULTIPATH) += multipath.o +obj-$(CONFIG_MD_FAULTY) += faulty.o +obj-$(CONFIG_BLK_DEV_MD) += md.o +obj-$(CONFIG_BLK_DEV_DM) += dm-mod.o +obj-$(CONFIG_DM_CRYPT) += dm-crypt.o +obj-$(CONFIG_DM_MULTIPATH) += dm-multipath.o dm-round-robin.o +obj-$(CONFIG_DM_MULTIPATH_EMC) += dm-emc.o +obj-$(CONFIG_DM_SNAPSHOT) += dm-snapshot.o +obj-$(CONFIG_DM_MIRROR) += dm-mirror.o +obj-$(CONFIG_DM_ZERO) += dm-zero.o + +quiet_cmd_unroll = UNROLL $@ + cmd_unroll = $(PERL) $(srctree)/$(src)/unroll.pl $(UNROLL) \ + < $< > $@ || ( rm -f $@ && exit 1 ) + +ifeq ($(CONFIG_ALTIVEC),y) +altivec_flags := -maltivec -mabi=altivec +endif + +targets += raid6int1.c +$(obj)/raid6int1.c: UNROLL := 1 +$(obj)/raid6int1.c: $(src)/raid6int.uc $(src)/unroll.pl FORCE + $(call if_changed,unroll) + +targets += raid6int2.c +$(obj)/raid6int2.c: UNROLL := 2 +$(obj)/raid6int2.c: $(src)/raid6int.uc $(src)/unroll.pl FORCE + $(call if_changed,unroll) + +targets += raid6int4.c +$(obj)/raid6int4.c: UNROLL := 4 +$(obj)/raid6int4.c: $(src)/raid6int.uc $(src)/unroll.pl FORCE + $(call if_changed,unroll) + +targets += raid6int8.c +$(obj)/raid6int8.c: UNROLL := 8 +$(obj)/raid6int8.c: $(src)/raid6int.uc $(src)/unroll.pl FORCE + $(call if_changed,unroll) + +targets += raid6int16.c +$(obj)/raid6int16.c: UNROLL := 16 +$(obj)/raid6int16.c: $(src)/raid6int.uc $(src)/unroll.pl FORCE + $(call if_changed,unroll) + +targets += raid6int32.c +$(obj)/raid6int32.c: UNROLL := 32 +$(obj)/raid6int32.c: $(src)/raid6int.uc $(src)/unroll.pl FORCE + $(call if_changed,unroll) + +CFLAGS_raid6altivec1.o += $(altivec_flags) +targets += raid6altivec1.c +$(obj)/raid6altivec1.c: UNROLL := 1 +$(obj)/raid6altivec1.c: $(src)/raid6altivec.uc $(src)/unroll.pl FORCE + $(call if_changed,unroll) + +CFLAGS_raid6altivec2.o += $(altivec_flags) +targets += raid6altivec2.c +$(obj)/raid6altivec2.c: UNROLL := 2 +$(obj)/raid6altivec2.c: $(src)/raid6altivec.uc $(src)/unroll.pl FORCE + $(call if_changed,unroll) + +CFLAGS_raid6altivec4.o += $(altivec_flags) +targets += raid6altivec4.c +$(obj)/raid6altivec4.c: UNROLL := 4 +$(obj)/raid6altivec4.c: $(src)/raid6altivec.uc $(src)/unroll.pl FORCE + $(call if_changed,unroll) + +CFLAGS_raid6altivec8.o += $(altivec_flags) +targets += raid6altivec8.c +$(obj)/raid6altivec8.c: UNROLL := 8 +$(obj)/raid6altivec8.c: $(src)/raid6altivec.uc $(src)/unroll.pl FORCE + $(call if_changed,unroll) + +quiet_cmd_mktable = TABLE $@ + cmd_mktable = $(obj)/mktables > $@ || ( rm -f $@ && exit 1 ) + +targets += raid6tables.c +$(obj)/raid6tables.c: $(obj)/mktables FORCE + $(call if_changed,mktable) diff --git a/drivers/md/dm-bio-list.h b/drivers/md/dm-bio-list.h new file mode 100644 index 000000000000..bc021e1fd4d1 --- /dev/null +++ b/drivers/md/dm-bio-list.h @@ -0,0 +1,68 @@ +/* + * Copyright (C) 2004 Red Hat UK Ltd. + * + * This file is released under the GPL. + */ + +#ifndef DM_BIO_LIST_H +#define DM_BIO_LIST_H + +#include <linux/bio.h> + +struct bio_list { + struct bio *head; + struct bio *tail; +}; + +static inline void bio_list_init(struct bio_list *bl) +{ + bl->head = bl->tail = NULL; +} + +static inline void bio_list_add(struct bio_list *bl, struct bio *bio) +{ + bio->bi_next = NULL; + + if (bl->tail) + bl->tail->bi_next = bio; + else + bl->head = bio; + + bl->tail = bio; +} + +static inline void bio_list_merge(struct bio_list *bl, struct bio_list *bl2) +{ + if (bl->tail) + bl->tail->bi_next = bl2->head; + else + bl->head = bl2->head; + + bl->tail = bl2->tail; +} + +static inline struct bio *bio_list_pop(struct bio_list *bl) +{ + struct bio *bio = bl->head; + + if (bio) { + bl->head = bl->head->bi_next; + if (!bl->head) + bl->tail = NULL; + + bio->bi_next = NULL; + } + + return bio; +} + +static inline struct bio *bio_list_get(struct bio_list *bl) +{ + struct bio *bio = bl->head; + + bl->head = bl->tail = NULL; + + return bio; +} + +#endif diff --git a/drivers/md/dm-bio-record.h b/drivers/md/dm-bio-record.h new file mode 100644 index 000000000000..d3ec217847d6 --- /dev/null +++ b/drivers/md/dm-bio-record.h @@ -0,0 +1,45 @@ +/* + * Copyright (C) 2004-2005 Red Hat, Inc. All rights reserved. + * + * This file is released under the GPL. + */ + +#ifndef DM_BIO_RECORD_H +#define DM_BIO_RECORD_H + +#include <linux/bio.h> + +/* + * There are lots of mutable fields in the bio struct that get + * changed by the lower levels of the block layer. Some targets, + * such as multipath, may wish to resubmit a bio on error. The + * functions in this file help the target record and restore the + * original bio state. + */ +struct dm_bio_details { + sector_t bi_sector; + struct block_device *bi_bdev; + unsigned int bi_size; + unsigned short bi_idx; + unsigned long bi_flags; +}; + +static inline void dm_bio_record(struct dm_bio_details *bd, struct bio *bio) +{ + bd->bi_sector = bio->bi_sector; + bd->bi_bdev = bio->bi_bdev; + bd->bi_size = bio->bi_size; + bd->bi_idx = bio->bi_idx; + bd->bi_flags = bio->bi_flags; +} + +static inline void dm_bio_restore(struct dm_bio_details *bd, struct bio *bio) +{ + bio->bi_sector = bd->bi_sector; + bio->bi_bdev = bd->bi_bdev; + bio->bi_size = bd->bi_size; + bio->bi_idx = bd->bi_idx; + bio->bi_flags = bd->bi_flags; +} + +#endif diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c new file mode 100644 index 000000000000..77619a56e2bf --- /dev/null +++ b/drivers/md/dm-crypt.c @@ -0,0 +1,977 @@ +/* + * Copyright (C) 2003 Christophe Saout <christophe@saout.de> + * Copyright (C) 2004 Clemens Fruhwirth <clemens@endorphin.org> + * + * This file is released under the GPL. + */ + +#include <linux/module.h> +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/bio.h> +#include <linux/blkdev.h> +#include <linux/mempool.h> +#include <linux/slab.h> +#include <linux/crypto.h> +#include <linux/workqueue.h> +#include <asm/atomic.h> +#include <asm/scatterlist.h> +#include <asm/page.h> + +#include "dm.h" + +#define PFX "crypt: " + +/* + * per bio private data + */ +struct crypt_io { + struct dm_target *target; + struct bio *bio; + struct bio *first_clone; + struct work_struct work; + atomic_t pending; + int error; +}; + +/* + * context holding the current state of a multi-part conversion + */ +struct convert_context { + struct bio *bio_in; + struct bio *bio_out; + unsigned int offset_in; + unsigned int offset_out; + unsigned int idx_in; + unsigned int idx_out; + sector_t sector; + int write; +}; + +struct crypt_config; + +struct crypt_iv_operations { + int (*ctr)(struct crypt_config *cc, struct dm_target *ti, + const char *opts); + void (*dtr)(struct crypt_config *cc); + const char *(*status)(struct crypt_config *cc); + int (*generator)(struct crypt_config *cc, u8 *iv, sector_t sector); +}; + +/* + * Crypt: maps a linear range of a block device + * and encrypts / decrypts at the same time. + */ +struct crypt_config { + struct dm_dev *dev; + sector_t start; + + /* + * pool for per bio private data and + * for encryption buffer pages + */ + mempool_t *io_pool; + mempool_t *page_pool; + + /* + * crypto related data + */ + struct crypt_iv_operations *iv_gen_ops; + char *iv_mode; + void *iv_gen_private; + sector_t iv_offset; + unsigned int iv_size; + + struct crypto_tfm *tfm; + unsigned int key_size; + u8 key[0]; +}; + +#define MIN_IOS 256 +#define MIN_POOL_PAGES 32 +#define MIN_BIO_PAGES 8 + +static kmem_cache_t *_crypt_io_pool; + +/* + * Mempool alloc and free functions for the page + */ +static void *mempool_alloc_page(unsigned int __nocast gfp_mask, void *data) +{ + return alloc_page(gfp_mask); +} + +static void mempool_free_page(void *page, void *data) +{ + __free_page(page); +} + + +/* + * Different IV generation algorithms: + * + * plain: the initial vector is the 32-bit low-endian version of the sector + * number, padded with zeros if neccessary. + * + * ess_iv: "encrypted sector|salt initial vector", the sector number is + * encrypted with the bulk cipher using a salt as key. The salt + * should be derived from the bulk cipher's key via hashing. + * + * 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) +{ + memset(iv, 0, cc->iv_size); + *(u32 *)iv = cpu_to_le32(sector & 0xffffffff); + + return 0; +} + +static int crypt_iv_essiv_ctr(struct crypt_config *cc, struct dm_target *ti, + const char *opts) +{ + struct crypto_tfm *essiv_tfm; + struct crypto_tfm *hash_tfm; + struct scatterlist sg; + unsigned int saltsize; + u8 *salt; + + if (opts == NULL) { + ti->error = PFX "Digest algorithm missing for ESSIV mode"; + return -EINVAL; + } + + /* Hash the cipher key with the given hash algorithm */ + hash_tfm = crypto_alloc_tfm(opts, 0); + if (hash_tfm == NULL) { + ti->error = PFX "Error initializing ESSIV hash"; + return -EINVAL; + } + + if (crypto_tfm_alg_type(hash_tfm) != CRYPTO_ALG_TYPE_DIGEST) { + ti->error = PFX "Expected digest algorithm for ESSIV hash"; + crypto_free_tfm(hash_tfm); + return -EINVAL; + } + + saltsize = crypto_tfm_alg_digestsize(hash_tfm); + salt = kmalloc(saltsize, GFP_KERNEL); + if (salt == NULL) { + ti->error = PFX "Error kmallocing salt storage in ESSIV"; + crypto_free_tfm(hash_tfm); + return -ENOMEM; + } + + sg.page = virt_to_page(cc->key); + sg.offset = offset_in_page(cc->key); + sg.length = cc->key_size; + crypto_digest_digest(hash_tfm, &sg, 1, salt); + crypto_free_tfm(hash_tfm); + + /* Setup the essiv_tfm with the given salt */ + essiv_tfm = crypto_alloc_tfm(crypto_tfm_alg_name(cc->tfm), + CRYPTO_TFM_MODE_ECB); + if (essiv_tfm == NULL) { + ti->error = PFX "Error allocating crypto tfm for ESSIV"; + kfree(salt); + return -EINVAL; + } + if (crypto_tfm_alg_blocksize(essiv_tfm) + != crypto_tfm_alg_ivsize(cc->tfm)) { + ti->error = PFX "Block size of ESSIV cipher does " + "not match IV size of block cipher"; + crypto_free_tfm(essiv_tfm); + kfree(salt); + return -EINVAL; + } + if (crypto_cipher_setkey(essiv_tfm, salt, saltsize) < 0) { + ti->error = PFX "Failed to set key for ESSIV cipher"; + crypto_free_tfm(essiv_tfm); + kfree(salt); + return -EINVAL; + } + kfree(salt); + + cc->iv_gen_private = (void *)essiv_tfm; + return 0; +} + +static void crypt_iv_essiv_dtr(struct crypt_config *cc) +{ + crypto_free_tfm((struct crypto_tfm *)cc->iv_gen_private); + cc->iv_gen_private = NULL; +} + +static int crypt_iv_essiv_gen(struct crypt_config *cc, u8 *iv, sector_t sector) +{ + struct scatterlist sg = { NULL, }; + + memset(iv, 0, cc->iv_size); + *(u64 *)iv = cpu_to_le64(sector); + + sg.page = virt_to_page(iv); + sg.offset = offset_in_page(iv); + sg.length = cc->iv_size; + crypto_cipher_encrypt((struct crypto_tfm *)cc->iv_gen_private, + &sg, &sg, cc->iv_size); + + return 0; +} + +static struct crypt_iv_operations crypt_iv_plain_ops = { + .generator = crypt_iv_plain_gen +}; + +static struct crypt_iv_operations crypt_iv_essiv_ops = { + .ctr = crypt_iv_essiv_ctr, + .dtr = crypt_iv_essiv_dtr, + .generator = crypt_iv_essiv_gen +}; + + +static inline int +crypt_convert_scatterlist(struct crypt_config *cc, struct scatterlist *out, + struct scatterlist *in, unsigned int length, + int write, sector_t sector) +{ + u8 iv[cc->iv_size]; + int r; + + if (cc->iv_gen_ops) { + r = cc->iv_gen_ops->generator(cc, iv, sector); + if (r < 0) + return r; + + if (write) + r = crypto_cipher_encrypt_iv(cc->tfm, out, in, length, iv); + else + r = crypto_cipher_decrypt_iv(cc->tfm, out, in, length, iv); + } else { + if (write) + r = crypto_cipher_encrypt(cc->tfm, out, in, length); + else + r = crypto_cipher_decrypt(cc->tfm, out, in, length); + } + + return r; +} + +static void +crypt_convert_init(struct crypt_config *cc, struct convert_context *ctx, + struct bio *bio_out, struct bio *bio_in, + sector_t sector, int write)< |