diff options
Diffstat (limited to 'include/linux/raid')
| -rw-r--r-- | include/linux/raid/linear.h | 27 | ||||
| -rw-r--r-- | include/linux/raid/md.h | 84 | ||||
| -rw-r--r-- | include/linux/raid/md_k.h | 369 | ||||
| -rw-r--r-- | include/linux/raid/md_p.h | 230 | ||||
| -rw-r--r-- | include/linux/raid/md_u.h | 117 | ||||
| -rw-r--r-- | include/linux/raid/multipath.h | 42 | ||||
| -rw-r--r-- | include/linux/raid/raid0.h | 30 | ||||
| -rw-r--r-- | include/linux/raid/raid1.h | 98 | ||||
| -rw-r--r-- | include/linux/raid/raid10.h | 103 | ||||
| -rw-r--r-- | include/linux/raid/raid5.h | 243 | ||||
| -rw-r--r-- | include/linux/raid/xor.h | 23 |
11 files changed, 1366 insertions, 0 deletions
diff --git a/include/linux/raid/linear.h b/include/linux/raid/linear.h new file mode 100644 index 000000000000..e04c4fe45b53 --- /dev/null +++ b/include/linux/raid/linear.h @@ -0,0 +1,27 @@ +#ifndef _LINEAR_H +#define _LINEAR_H + +#include <linux/raid/md.h> + +struct dev_info { + mdk_rdev_t *rdev; + sector_t size; + sector_t offset; +}; + +typedef struct dev_info dev_info_t; + +struct linear_private_data +{ + dev_info_t **hash_table; + dev_info_t *smallest; + int nr_zones; + dev_info_t disks[0]; +}; + + +typedef struct linear_private_data linear_conf_t; + +#define mddev_to_conf(mddev) ((linear_conf_t *) mddev->private) + +#endif diff --git a/include/linux/raid/md.h b/include/linux/raid/md.h new file mode 100644 index 000000000000..a6a67d102bfa --- /dev/null +++ b/include/linux/raid/md.h @@ -0,0 +1,84 @@ +/* + md.h : Multiple Devices driver for Linux + Copyright (C) 1996-98 Ingo Molnar, Gadi Oxman + Copyright (C) 1994-96 Marc ZYNGIER + <zyngier@ufr-info-p7.ibp.fr> or + <maz@gloups.fdn.fr> + + This program is free software; you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation; either version 2, or (at your option) + any later version. + + You should have received a copy of the GNU General Public License + (for example /usr/src/linux/COPYING); if not, write to the Free + Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. +*/ + +#ifndef _MD_H +#define _MD_H + +#include <linux/blkdev.h> +#include <asm/semaphore.h> +#include <linux/major.h> +#include <linux/ioctl.h> +#include <linux/types.h> +#include <linux/bitops.h> +#include <linux/module.h> +#include <linux/hdreg.h> +#include <linux/proc_fs.h> +#include <linux/seq_file.h> +#include <linux/smp_lock.h> +#include <linux/delay.h> +#include <net/checksum.h> +#include <linux/random.h> +#include <linux/kernel_stat.h> +#include <asm/io.h> +#include <linux/completion.h> +#include <linux/mempool.h> +#include <linux/list.h> +#include <linux/reboot.h> +#include <linux/vmalloc.h> +#include <linux/blkpg.h> +#include <linux/bio.h> + +/* + * 'md_p.h' holds the 'physical' layout of RAID devices + * 'md_u.h' holds the user <=> kernel API + * + * 'md_k.h' holds kernel internal definitions + */ + +#include <linux/raid/md_p.h> +#include <linux/raid/md_u.h> +#include <linux/raid/md_k.h> + +/* + * Different major versions are not compatible. + * Different minor versions are only downward compatible. + * Different patchlevel versions are downward and upward compatible. + */ +#define MD_MAJOR_VERSION 0 +#define MD_MINOR_VERSION 90 +#define MD_PATCHLEVEL_VERSION 1 + +extern int register_md_personality (int p_num, mdk_personality_t *p); +extern int unregister_md_personality (int p_num); +extern mdk_thread_t * md_register_thread (void (*run) (mddev_t *mddev), + mddev_t *mddev, const char *name); +extern void md_unregister_thread (mdk_thread_t *thread); +extern void md_wakeup_thread(mdk_thread_t *thread); +extern void md_check_recovery(mddev_t *mddev); +extern void md_write_start(mddev_t *mddev); +extern void md_write_end(mddev_t *mddev); +extern void md_handle_safemode(mddev_t *mddev); +extern void md_done_sync(mddev_t *mddev, int blocks, int ok); +extern void md_error (mddev_t *mddev, mdk_rdev_t *rdev); +extern void md_unplug_mddev(mddev_t *mddev); + +extern void md_print_devices (void); + +#define MD_BUG(x...) { printk("md: bug in file %s, line %d\n", __FILE__, __LINE__); md_print_devices(); } + +#endif + diff --git a/include/linux/raid/md_k.h b/include/linux/raid/md_k.h new file mode 100644 index 000000000000..c9a0d4013be7 --- /dev/null +++ b/include/linux/raid/md_k.h @@ -0,0 +1,369 @@ +/* + md_k.h : kernel internal structure of the Linux MD driver + Copyright (C) 1996-98 Ingo Molnar, Gadi Oxman + + This program is free software; you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation; either version 2, or (at your option) + any later version. + + You should have received a copy of the GNU General Public License + (for example /usr/src/linux/COPYING); if not, write to the Free + Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. +*/ + +#ifndef _MD_K_H +#define _MD_K_H + +#define MD_RESERVED 0UL +#define LINEAR 1UL +#define RAID0 2UL +#define RAID1 3UL +#define RAID5 4UL +#define TRANSLUCENT 5UL +#define HSM 6UL +#define MULTIPATH 7UL +#define RAID6 8UL +#define RAID10 9UL +#define FAULTY 10UL +#define MAX_PERSONALITY 11UL + +#define LEVEL_MULTIPATH (-4) +#define LEVEL_LINEAR (-1) +#define LEVEL_FAULTY (-5) + +#define MaxSector (~(sector_t)0) +#define MD_THREAD_NAME_MAX 14 + +static inline int pers_to_level (int pers) +{ + switch (pers) { + case FAULTY: return LEVEL_FAULTY; + case MULTIPATH: return LEVEL_MULTIPATH; + case HSM: return -3; + case TRANSLUCENT: return -2; + case LINEAR: return LEVEL_LINEAR; + case RAID0: return 0; + case RAID1: return 1; + case RAID5: return 5; + case RAID6: return 6; + case RAID10: return 10; + } + BUG(); + return MD_RESERVED; +} + +static inline int level_to_pers (int level) +{ + switch (level) { + case LEVEL_FAULTY: return FAULTY; + case LEVEL_MULTIPATH: return MULTIPATH; + case -3: return HSM; + case -2: return TRANSLUCENT; + case LEVEL_LINEAR: return LINEAR; + case 0: return RAID0; + case 1: return RAID1; + case 4: + case 5: return RAID5; + case 6: return RAID6; + case 10: return RAID10; + } + return MD_RESERVED; +} + +typedef struct mddev_s mddev_t; +typedef struct mdk_rdev_s mdk_rdev_t; + +#define MAX_MD_DEVS 256 /* Max number of md dev */ + +/* + * options passed in raidrun: + */ + +#define MAX_CHUNK_SIZE (4096*1024) + +/* + * default readahead + */ + +static inline int disk_faulty(mdp_disk_t * d) +{ + return d->state & (1 << MD_DISK_FAULTY); +} + +static inline int disk_active(mdp_disk_t * d) +{ + return d->state & (1 << MD_DISK_ACTIVE); +} + +static inline int disk_sync(mdp_disk_t * d) +{ + return d->state & (1 << MD_DISK_SYNC); +} + +static inline int disk_spare(mdp_disk_t * d) +{ + return !disk_sync(d) && !disk_active(d) && !disk_faulty(d); +} + +static inline int disk_removed(mdp_disk_t * d) +{ + return d->state & (1 << MD_DISK_REMOVED); +} + +static inline void mark_disk_faulty(mdp_disk_t * d) +{ + d->state |= (1 << MD_DISK_FAULTY); +} + +static inline void mark_disk_active(mdp_disk_t * d) +{ + d->state |= (1 << MD_DISK_ACTIVE); +} + +static inline void mark_disk_sync(mdp_disk_t * d) +{ + d->state |= (1 << MD_DISK_SYNC); +} + +static inline void mark_disk_spare(mdp_disk_t * d) +{ + d->state = 0; +} + +static inline void mark_disk_removed(mdp_disk_t * d) +{ + d->state = (1 << MD_DISK_FAULTY) | (1 << MD_DISK_REMOVED); +} + +static inline void mark_disk_inactive(mdp_disk_t * d) +{ + d->state &= ~(1 << MD_DISK_ACTIVE); +} + +static inline void mark_disk_nonsync(mdp_disk_t * d) +{ + d->state &= ~(1 << MD_DISK_SYNC); +} + +/* + * MD's 'extended' device + */ +struct mdk_rdev_s +{ + struct list_head same_set; /* RAID devices within the same set */ + + sector_t size; /* Device size (in blocks) */ + mddev_t *mddev; /* RAID array if running */ + unsigned long last_events; /* IO event timestamp */ + + struct block_device *bdev; /* block device handle */ + + struct page *sb_page; + int sb_loaded; + sector_t data_offset; /* start of data in array */ + sector_t sb_offset; + int preferred_minor; /* autorun support */ + + /* A device can be in one of three states based on two flags: + * Not working: faulty==1 in_sync==0 + * Fully working: faulty==0 in_sync==1 + * Working, but not + * in sync with array + * faulty==0 in_sync==0 + * + * It can never have faulty==1, in_sync==1 + * This reduces the burden of testing multiple flags in many cases + */ + int faulty; /* if faulty do not issue IO requests */ + int in_sync; /* device is a full member of the array */ + + int desc_nr; /* descriptor index in the superblock */ + int raid_disk; /* role of device in array */ + + atomic_t nr_pending; /* number of pending requests. + * only maintained for arrays that + * support hot removal + */ +}; + +typedef struct mdk_personality_s mdk_personality_t; + +struct mddev_s +{ + void *private; + mdk_personality_t *pers; + dev_t unit; + int md_minor; + struct list_head disks; + int sb_dirty; + int ro; + + struct gendisk *gendisk; + + /* Superblock information */ + int major_version, + minor_version, + patch_version; + int persistent; + int chunk_size; + time_t ctime, utime; + int level, layout; + int raid_disks; + int max_disks; + sector_t size; /* used size of component devices */ + sector_t array_size; /* exported array size */ + __u64 events; + + char uuid[16]; + + struct mdk_thread_s *thread; /* management thread */ + struct mdk_thread_s *sync_thread; /* doing resync or reconstruct */ + sector_t curr_resync; /* blocks scheduled */ + unsigned long resync_mark; /* a recent timestamp */ + sector_t resync_mark_cnt;/* blocks written at resync_mark */ + + sector_t resync_max_sectors; /* may be set by personality */ + /* recovery/resync flags + * NEEDED: we might need to start a resync/recover + * RUNNING: a thread is running, or about to be started + * SYNC: actually doing a resync, not a recovery + * ERR: and IO error was detected - abort the resync/recovery + * INTR: someone requested a (clean) early abort. + * DONE: thread is done and is waiting to be reaped + */ +#define MD_RECOVERY_RUNNING 0 +#define MD_RECOVERY_SYNC 1 +#define MD_RECOVERY_ERR 2 +#define MD_RECOVERY_INTR 3 +#define MD_RECOVERY_DONE 4 +#define MD_RECOVERY_NEEDED 5 + unsigned long recovery; + + int in_sync; /* know to not need resync */ + struct semaphore reconfig_sem; + atomic_t active; + + int changed; /* true if we might need to reread partition info */ + int degraded; /* whether md should consider + * adding a spare + */ + + atomic_t recovery_active; /* blocks scheduled, but not written */ + wait_queue_head_t recovery_wait; + sector_t recovery_cp; + unsigned int safemode; /* if set, update "clean" superblock + * when no writes pending. + */ + unsigned int safemode_delay; + struct timer_list safemode_timer; + atomic_t writes_pending; + request_queue_t *queue; /* for plugging ... */ + + struct list_head all_mddevs; +}; + + +static inline void rdev_dec_pending(mdk_rdev_t *rdev, mddev_t *mddev) +{ + int faulty = rdev->faulty; + if (atomic_dec_and_test(&rdev->nr_pending) && faulty) + set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); +} + +static inline void md_sync_acct(struct block_device *bdev, unsigned long nr_sectors) +{ + atomic_add(nr_sectors, &bdev->bd_contains->bd_disk->sync_io); +} + +struct mdk_personality_s +{ + char *name; + struct module *owner; + int (*make_request)(request_queue_t *q, struct bio *bio); + int (*run)(mddev_t *mddev); + int (*stop)(mddev_t *mddev); + void (*status)(struct seq_file *seq, mddev_t *mddev); + /* error_handler must set ->faulty and clear ->in_sync + * if appropriate, and should abort recovery if needed + */ + void (*error_handler)(mddev_t *mddev, mdk_rdev_t *rdev); + int (*hot_add_disk) (mddev_t *mddev, mdk_rdev_t *rdev); + int (*hot_remove_disk) (mddev_t *mddev, int number); + int (*spare_active) (mddev_t *mddev); + int (*sync_request)(mddev_t *mddev, sector_t sector_nr, int go_faster); + int (*resize) (mddev_t *mddev, sector_t sectors); + int (*reshape) (mddev_t *mddev, int raid_disks); + int (*reconfig) (mddev_t *mddev, int layout, int chunk_size); +}; + + +static inline char * mdname (mddev_t * mddev) +{ + return mddev->gendisk ? mddev->gendisk->disk_name : "mdX"; +} + +extern mdk_rdev_t * find_rdev_nr(mddev_t *mddev, int nr); + +/* + * iterates through some rdev ringlist. It's safe to remove the + * current 'rdev'. Dont touch 'tmp' though. + */ +#define ITERATE_RDEV_GENERIC(head,rdev,tmp) \ + \ + for ((tmp) = (head).next; \ + (rdev) = (list_entry((tmp), mdk_rdev_t, same_set)), \ + (tmp) = (tmp)->next, (tmp)->prev != &(head) \ + ; ) +/* + * iterates through the 'same array disks' ringlist + */ +#define ITERATE_RDEV(mddev,rdev,tmp) \ + ITERATE_RDEV_GENERIC((mddev)->disks,rdev,tmp) + +/* + * Iterates through 'pending RAID disks' + */ +#define ITERATE_RDEV_PENDING(rdev,tmp) \ + ITERATE_RDEV_GENERIC(pending_raid_disks,rdev,tmp) + +typedef struct mdk_thread_s { + void (*run) (mddev_t *mddev); + mddev_t *mddev; + wait_queue_head_t wqueue; + unsigned long flags; + struct completion *event; + struct task_struct *tsk; + const char *name; +} mdk_thread_t; + +#define THREAD_WAKEUP 0 + +#define __wait_event_lock_irq(wq, condition, lock, cmd) \ +do { \ + wait_queue_t __wait; \ + init_waitqueue_entry(&__wait, current); \ + \ + add_wait_queue(&wq, &__wait); \ + for (;;) { \ + set_current_state(TASK_UNINTERRUPTIBLE); \ + if (condition) \ + break; \ + spin_unlock_irq(&lock); \ + cmd; \ + schedule(); \ + spin_lock_irq(&lock); \ + } \ + current->state = TASK_RUNNING; \ + remove_wait_queue(&wq, &__wait); \ +} while (0) + +#define wait_event_lock_irq(wq, condition, lock, cmd) \ +do { \ + if (condition) \ + break; \ + __wait_event_lock_irq(wq, condition, lock, cmd); \ +} while (0) + +#endif + diff --git a/include/linux/raid/md_p.h b/include/linux/raid/md_p.h new file mode 100644 index 000000000000..8ba95d67329f --- /dev/null +++ b/include/linux/raid/md_p.h @@ -0,0 +1,230 @@ +/* + md_p.h : physical layout of Linux RAID devices + Copyright (C) 1996-98 Ingo Molnar, Gadi Oxman + + This program is free software; you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation; either version 2, or (at your option) + any later version. + + You should have received a copy of the GNU General Public License + (for example /usr/src/linux/COPYING); if not, write to the Free + Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. +*/ + +#ifndef _MD_P_H +#define _MD_P_H + +/* + * RAID superblock. + * + * The RAID superblock maintains some statistics on each RAID configuration. + * Each real device in the RAID set contains it near the end of the device. + * Some of the ideas are copied from the ext2fs implementation. + * + * We currently use 4096 bytes as follows: + * + * word offset function + * + * 0 - 31 Constant generic RAID device information. + * 32 - 63 Generic state information. + * 64 - 127 Personality specific information. + * 128 - 511 12 32-words descriptors of the disks in the raid set. + * 512 - 911 Reserved. + * 912 - 1023 Disk specific descriptor. + */ + +/* + * If x is the real device size in bytes, we return an apparent size of: + * + * y = (x & ~(MD_RESERVED_BYTES - 1)) - MD_RESERVED_BYTES + * + * and place the 4kB superblock at offset y. + */ +#define MD_RESERVED_BYTES (64 * 1024) +#define MD_RESERVED_SECTORS (MD_RESERVED_BYTES / 512) +#define MD_RESERVED_BLOCKS (MD_RESERVED_BYTES / BLOCK_SIZE) + +#define MD_NEW_SIZE_SECTORS(x) ((x & ~(MD_RESERVED_SECTORS - 1)) - MD_RESERVED_SECTORS) +#define MD_NEW_SIZE_BLOCKS(x) ((x & ~(MD_RESERVED_BLOCKS - 1)) - MD_RESERVED_BLOCKS) + +#define MD_SB_BYTES 4096 +#define MD_SB_WORDS (MD_SB_BYTES / 4) +#define MD_SB_BLOCKS (MD_SB_BYTES / BLOCK_SIZE) +#define MD_SB_SECTORS (MD_SB_BYTES / 512) + +/* + * The following are counted in 32-bit words + */ +#define MD_SB_GENERIC_OFFSET 0 +#define MD_SB_PERSONALITY_OFFSET 64 +#define MD_SB_DISKS_OFFSET 128 +#define MD_SB_DESCRIPTOR_OFFSET 992 + +#define MD_SB_GENERIC_CONSTANT_WORDS 32 +#define MD_SB_GENERIC_STATE_WORDS 32 +#define MD_SB_GENERIC_WORDS (MD_SB_GENERIC_CONSTANT_WORDS + MD_SB_GENERIC_STATE_WORDS) +#define MD_SB_PERSONALITY_WORDS 64 +#define MD_SB_DESCRIPTOR_WORDS 32 +#define MD_SB_DISKS 27 +#define MD_SB_DISKS_WORDS (MD_SB_DISKS*MD_SB_DESCRIPTOR_WORDS) +#define MD_SB_RESERVED_WORDS (1024 - MD_SB_GENERIC_WORDS - MD_SB_PERSONALITY_WORDS - MD_SB_DISKS_WORDS - MD_SB_DESCRIPTOR_WORDS) +#define MD_SB_EQUAL_WORDS (MD_SB_GENERIC_WORDS + MD_SB_PERSONALITY_WORDS + MD_SB_DISKS_WORDS) + +/* + * Device "operational" state bits + */ +#define MD_DISK_FAULTY 0 /* disk is faulty / operational */ +#define MD_DISK_ACTIVE 1 /* disk is running or spare disk */ +#define MD_DISK_SYNC 2 /* disk is in sync with the raid set */ +#define MD_DISK_REMOVED 3 /* disk is in sync with the raid set */ + +typedef struct mdp_device_descriptor_s { + __u32 number; /* 0 Device number in the entire set */ + __u32 major; /* 1 Device major number */ + __u32 minor; /* 2 Device minor number */ + __u32 raid_disk; /* 3 The role of the device in the raid set */ + __u32 state; /* 4 Operational state */ + __u32 reserved[MD_SB_DESCRIPTOR_WORDS - 5]; +} mdp_disk_t; + +#define MD_SB_MAGIC 0xa92b4efc + +/* + * Superblock state bits + */ +#define MD_SB_CLEAN 0 +#define MD_SB_ERRORS 1 + +typedef struct mdp_superblock_s { + /* + * Constant generic information + */ + __u32 md_magic; /* 0 MD identifier */ + __u32 major_version; /* 1 major version to which the set conforms */ + __u32 minor_version; /* 2 minor version ... */ + __u32 patch_version; /* 3 patchlevel version ... */ + __u32 gvalid_words; /* 4 Number of used words in this section */ + __u32 set_uuid0; /* 5 Raid set identifier */ + __u32 ctime; /* 6 Creation time */ + __u32 level; /* 7 Raid personality */ + __u32 size; /* 8 Apparent size of each individual disk */ + __u32 nr_disks; /* 9 total disks in the raid set */ + __u32 raid_disks; /* 10 disks in a fully functional raid set */ + __u32 md_minor; /* 11 preferred MD minor device number */ + __u32 not_persistent; /* 12 does it have a persistent superblock */ + __u32 set_uuid1; /* 13 Raid set identifier #2 */ + __u32 set_uuid2; /* 14 Raid set identifier #3 */ + __u32 set_uuid3; /* 15 Raid set identifier #4 */ + __u32 gstate_creserved[MD_SB_GENERIC_CONSTANT_WORDS - 16]; + + /* + * Generic state information + */ + __u32 utime; /* 0 Superblock update time */ + __u32 state; /* 1 State bits (clean, ...) */ + __u32 active_disks; /* 2 Number of currently active disks */ + __u32 working_disks; /* 3 Number of working disks */ + __u32 failed_disks; /* 4 Number of failed disks */ + __u32 spare_disks; /* 5 Number of spare disks */ + __u32 sb_csum; /* 6 checksum of the whole superblock */ +#ifdef __BIG_ENDIAN + __u32 events_hi; /* 7 high-order of superblock update count */ + __u32 events_lo; /* 8 low-order of superblock update count */ + __u32 cp_events_hi; /* 9 high-order of checkpoint update count */ + __u32 cp_events_lo; /* 10 low-order of checkpoint update count */ +#else + __u32 events_lo; /* 7 low-order of superblock update count */ + __u32 events_hi; /* 8 high-order of superblock update count */ + __u32 cp_events_lo; /* 9 low-order of checkpoint update count */ + __u32 cp_events_hi; /* 10 high-order of checkpoint update count */ +#endif + __u32 recovery_cp; /* 11 recovery checkpoint sector count */ + __u32 gstate_sreserved[MD_SB_GENERIC_STATE_WORDS - 12]; + + /* + * Personality information + */ + __u32 layout; /* 0 the array's physical layout */ + __u32 chunk_size; /* 1 chunk size in bytes */ + __u32 root_pv; /* 2 LV root PV */ + __u32 root_block; /* 3 LV root block */ + __u32 pstate_reserved[MD_SB_PERSONALITY_WORDS - 4]; + + /* + * Disks information + */ + mdp_disk_t disks[MD_SB_DISKS]; + + /* + * Reserved + */ + __u32 reserved[MD_SB_RESERVED_WORDS]; + + /* + * Active descriptor + */ + mdp_disk_t this_disk; + +} mdp_super_t; + +static inline __u64 md_event(mdp_super_t *sb) { + __u64 ev = sb->events_hi; + return (ev<<32)| sb->events_lo; +} + +/* + * The version-1 superblock : + * All numeric fields are little-endian. + * + * total size: 256 bytes plus 2 per device. + * 1K allows 384 devices. + */ +struct mdp_superblock_1 { + /* constant array information - 128 bytes */ + __u32 magic; /* MD_SB_MAGIC: 0xa92b4efc - little endian */ + __u32 major_version; /* 1 */ + __u32 feature_map; /* 0 for now */ + __u32 pad0; /* always set to 0 when writing */ + + __u8 set_uuid[16]; /* user-space generated. */ + char set_name[32]; /* set and interpreted by user-space */ + + __u64 ctime; /* lo 40 bits are seconds, top 24 are microseconds or 0*/ + __u32 level; /* -4 (multipath), -1 (linear), 0,1,4,5 */ + __u32 layout; /* only for raid5 currently */ + __u64 size; /* used size of component devices, in 512byte sectors */ + + __u32 chunksize; /* in 512byte sectors */ + __u32 raid_disks; + __u8 pad1[128-96]; /* set to 0 when written */ + + /* constant this-device information - 64 bytes */ + __u64 data_offset; /* sector start of data, often 0 */ + __u64 data_size; /* sectors in this device that can be used for data */ + __u64 super_offset; /* sector start of this superblock */ + __u64 recovery_offset;/* sectors before this offset (from data_offset) have been recovered */ + __u32 dev_number; /* permanent identifier of this device - not role in raid */ + __u32 cnt_corrected_read; /* number of read errors that were corrected by re-writing */ + __u8 device_uuid[16]; /* user-space setable, ignored by kernel */ + __u8 pad2[64-56]; /* set to 0 when writing */ + + /* array state information - 64 bytes */ + __u64 utime; /* 40 bits second, 24 btes microseconds */ + __u64 events; /* incremented when superblock updated */ + __u64 resync_offset; /* data before this offset (from data_offset) known to be in sync */ + __u32 sb_csum; /* checksum upto devs[max_dev] */ + __u32 max_dev; /* size of devs[] array to consider */ + __u8 pad3[64-32]; /* set to 0 when writing */ + + /* device state information. Indexed by dev_number. + * 2 bytes per device + * Note there are no per-device state flags. State information is rolled + * into the 'roles' value. If a device is spare or faulty, then it doesn't + * have a meaningful role. + */ + __u16 dev_roles[0]; /* role in array, or 0xffff for a spare, or 0xfffe for faulty */ +}; + +#endif + diff --git a/include/linux/raid/md_u.h b/include/linux/raid/md_u.h new file mode 100644 index 000000000000..a2df5c2a42af --- /dev/null +++ b/include/linux/raid/md_u.h @@ -0,0 +1,117 @@ +/* + md_u.h : user <=> kernel API between Linux raidtools and RAID drivers + Copyright (C) 1998 Ingo Molnar + + This program is free software; you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation; either version 2, or (at your option) + any later version. + + You should have received a copy of the GNU General Public License + (for example /usr/src/linux/COPYING); if not, write to the Free + Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. +*/ + +#ifndef _MD_U_H +#define _MD_U_H + +/* ioctls */ + +/* status */ +#define RAID_VERSION _IOR (MD_MAJOR, 0x10, mdu_version_t) +#define GET_ARRAY_INFO _IOR (MD_MAJOR, 0x11, mdu_array_info_t) +#define GET_DISK_INFO _IOR (MD_MAJOR, 0x12, mdu_disk_info_t) +#define PRINT_RAID_DEBUG _IO (MD_MAJOR, 0x13) +#define RAID_AUTORUN _IO (MD_MAJOR, 0x14) + +/* configuration */ +#define CLEAR_ARRAY _IO (MD_MAJOR, 0x20) +#define ADD_NEW_DISK _IOW (MD_MAJOR, 0x21, mdu_disk_info_t) +#define HOT_REMOVE_DISK _IO (MD_MAJOR, 0x22) +#define SET_ARRAY_INFO _IOW (MD_MAJOR, 0x23, mdu_array_info_t) +#define SET_DISK_INFO _IO (MD_MAJOR, 0x24) +#define WRITE_RAID_INFO _IO (MD_MAJOR, 0x25) +#define UNPROTECT_ARRAY _IO (MD_MAJOR, 0x26) +#define PROTECT_ARRAY _IO (MD_MAJOR, 0x27) +#define HOT_ADD_DISK _IO (MD_MAJOR, 0x28) +#define SET_DISK_FAULTY _IO (MD_MAJOR, 0x29) +#define HOT_GENERATE_ERROR _IO (MD_MAJOR, 0x2a) + +/* usage */ +#define RUN_ARRAY _IOW (MD_MAJOR, 0x30, mdu_param_t) +#define START_ARRAY _IO (MD_MAJOR, 0x31) +#define STOP_ARRAY _IO (MD_MAJOR, 0x32) +#define STOP_ARRAY_RO _IO (MD_MAJOR, 0x33) +#define RESTART_ARRAY_RW _IO (MD_MAJOR, 0x34) + +typedef struct mdu_version_s { + int major; + int minor; + int patchlevel; +} mdu_version_t; + +typedef struct mdu_array_info_s { + /* + * Generic constant information + */ + int major_version; + int minor_version; + int patch_version; + int ctime; + int level; + int size; + int nr_disks; + int raid_disks; + int md_minor; + int not_persistent; + + /* + * Generic state information + */ + int utime; /* 0 Superblock update time */ + int state; /* 1 State bits (clean, ...) */ + int active_disks; /* 2 Number of currently active disks */ + int working_disks; /* 3 Number of working disks */ + int failed_disks; /* 4 Number of failed disks */ + int spare_disks; /* 5 Number of spare disks */ + + /* + * Personality information + */ + int layout; /* 0 the array's physical layout */ + int chunk_size; /* 1 chunk size in bytes */ + +} mdu_array_info_t; + +typedef struct mdu_disk_info_s { + /* + * configuration/status of one particular disk + */ + int number; + int major; + int minor; + int raid_disk; + int state; + +} mdu_disk_info_t; + +typedef struct mdu_start_info_s { + /* + * configuration/status of one particular disk + */ + int major; + int minor; + int raid_disk; + int state; + +} mdu_start_info_t; + +typedef struct mdu_param_s +{ + int personality; /* 1,2,3,4 */ + int chunk_size; /* in bytes */ + int max_fault; /* unused for now */ +} mdu_param_t; + +#endif + diff --git a/include/linux/raid/multipath.h b/include/linux/raid/multipath.h new file mode 100644 index 000000000000..6f53fc177a47 --- /dev/null +++ b/include/linux/raid/multipath.h @@ -0,0 +1,42 @@ +#ifndef _MULTIPATH_H +#define _MULTIPATH_H + +#include <linux/raid/md.h> + +struct multipath_info { + mdk_rdev_t *rdev; +}; + +struct multipath_private_data { + mddev_t *mddev; + struct multipath_info *multipaths; + int raid_disks; + int working_disks; + spinlock_t device_lock; + struct list_head retry_list; + + mempool_t *pool; +}; + +typedef struct multipath_private_data multipath_conf_t; + +/* + * this is the only point in the RAID code where we violate + * C type safety. mddev->private is an 'opaque' pointer. + */ +#define mddev_to_conf(mddev) ((multipath_conf_t *) mddev->private) + +/* + * this is our 'private' 'collective' MULTIPATH buffer head. + * it contains information about what kind of IO operations were started + * for this MULTIPATH operation, and about their status: + */ + +struct multipath_bh { + mddev_t *mddev; + struct bio *master_bio; + struct bio bio; + int path; + struct list_head retry_list; +}; +#endif diff --git a/include/linux/raid/raid0.h b/include/linux/raid/raid0.h new file mode 100644 index 000000000000..1b2dda035f8e --- /dev/null +++ b/include/linux/raid/raid0.h @@ -0,0 +1,30 @@ +#ifndef _RAID0_H +#define _RAID0_H + +#include <linux/raid/md.h> + +struct strip_zone +{ + sector_t zone_offset; /* Zone offset in md_dev */ + sector_t dev_offset; /* Zone offset in real dev */ + sector_t size; /* Zone size */ + int nb_dev; /* # of devices attached to the zone */ + mdk_rdev_t **dev; /* Devices attached to the zone */ +}; + +struct raid0_private_data +{ + struct strip_zone **hash_table; /* Table of indexes into strip_zone */ + struct strip_zone *strip_zone; + mdk_rdev_t **devlist; /* lists of rdevs, pointed to by strip_zone->dev */ + int nr_strip_zones; + + sector_t hash_spacing; + int preshift; /* shift this before divide by hash_spacing */ +}; + +typedef struct raid0_private_data raid0_conf_t; + +#define mddev_to_conf(mddev) ((raid0_conf_t *) mddev->private) + +#endif diff --git a/include/linux/raid/raid1.h b/include/linux/raid/raid1.h new file mode 100644 index 000000000000..abbfdd9afe1e --- /dev/null +++ b/include/linux/raid/raid1.h @@ -0,0 +1,98 @@ +#ifndef _RAID1_H +#define _RAID1_H + +#include <linux/raid/md.h> + +typedef struct mirror_info mirror_info_t; + +struct mirror_info { + mdk_rdev_t *rdev; + sector_t head_position; +}; + +/* + * memory pools need a pointer to the mddev, so they can force an unplug + * when memory is tight, and a count of the number of drives that the + * pool was allocated for, so they know how much to allocate and free. + * mddev->raid_disks cannot be used, as it can change while a pool is active + * These two datums are stored in a kmalloced struct. + */ + +struct pool_info { + mddev_t *mddev; + int raid_disks; +}; + + +typedef struct r1bio_s r1bio_t; + +struct r1_private_data_s { + mddev_t *mddev; + mirror_info_t *mirrors; + int raid_disks; + int working_disks; + int last_used; + sector_t next_seq_sect; + spinlock_t device_lock; + + struct list_head retry_list; + /* for use when syncing mirrors: */ + + spinlock_t resync_lock; + int nr_pending; + int barrier; + sector_t next_resync; + + wait_queue_head_t wait_idle; + wait_queue_head_t wait_resume; + + struct pool_info *poolinfo; + + mempool_t *r1bio_pool; + mempool_t *r1buf_pool; +}; + +typedef struct r1_private_data_s conf_t; + +/* + * this is the only point in the RAID code where we violate + * C type safety. mddev->private is an 'opaque' pointer. + */ +#define mddev_to_conf(mddev) ((conf_t *) mddev->private) + +/* + * this is our 'private' RAID1 bio. + * + * it contains information about what kind of IO operations were started + * for this RAID1 operation, and about their status: + */ + +struct r1bio_s { + atomic_t remaining; /* 'have we finished' count, + * used from IRQ handlers + */ + sector_t sector; + int sectors; + unsigned long state; + mddev_t *mddev; + /* + * original bio going to /dev/mdx + */ + struct bio *master_bio; + /* + * if the IO is in READ direction, then this is where we read + */ + int read_disk; + + struct list_head retry_list; + /* + * if the IO is in WRITE direction, then multiple bios are used. + * We choose the number when they are allocated. + */ + struct bio *bios[0]; +}; + +/* bits for r1bio.state */ +#define R1BIO_Uptodate 0 +#define R1BIO_IsSync 1 +#endif diff --git a/include/linux/raid/raid10.h b/include/linux/raid/raid10.h new file mode 100644 index 000000000000..60708789c8f9 --- /dev/null +++ b/include/linux/raid/raid10.h @@ -0,0 +1,103 @@ +#ifndef _RAID10_H +#define _RAID10_H + +#include <linux/raid/md.h> + +typedef struct mirror_info mirror_info_t; + +struct mirror_info { + mdk_rdev_t *rdev; + sector_t head_position; +}; + +typedef struct r10bio_s r10bio_t; + +struct r10_private_data_s { + mddev_t *mddev; + mirror_info_t *mirrors; + int raid_disks; + int working_disks; + spinlock_t device_lock; + + /* geometry */ + int near_copies; /* number of copies layed out raid0 style */ + int far_copies; /* number of copies layed out + * at large strides across drives + */ + int copies; /* near_copies * far_copies. + * must be <= raid_disks + */ + sector_t stride; /* distance between far copies. + * This is size / far_copies + */ + + int chunk_shift; /* shift from chunks to sectors */ + sector_t chunk_mask; + + struct list_head retry_list; + /* for use when syncing mirrors: */ + + spinlock_t resync_lock; + int nr_pending; + int barrier; + sector_t next_resync; + + wait_queue_head_t wait_idle; + wait_queue_head_t wait_resume; + + mempool_t *r10bio_pool; + mempool_t *r10buf_pool; +}; + +typedef struct r10_private_data_s conf_t; + +/* + * this is the only point in the RAID code where we violate + * C type safety. mddev->private is an 'opaque' pointer. + */ +#define mddev_to_conf(mddev) ((conf_t *) mddev->private) + +/* + * this is our 'private' RAID10 bio. + * + * it contains information about what kind of IO operations were started + * for this RAID10 operation, and about their status: + */ + +struct r10bio_s { + atomic_t remaining; /* 'have we finished' count, + * used from IRQ handlers + */ + sector_t sector; /* virtual sector number */ + int sectors; + unsigned long state; + mddev_t *mddev; + /* + * original bio going to /dev/mdx + */ + struct bio *master_bio; + /* + * if the IO is in READ direction, then this is where we read + */ + int read_slot; + + struct list_head retry_list; + /* + * if the IO is in WRITE direction, then multiple bios are used, + * one for each copy. + * When resyncing we also use one for each copy. + * When reconstructing, we use 2 bios, one for read, one for write. + * We choose the number when they are allocated. + */ + struct { + struct bio *bio; + sector_t addr; + int devnum; + } devs[0]; +}; + +/* bits for r10bio.state */ +#define R10BIO_Uptodate 0 +#define R10BIO_IsSync 1 +#define R10BIO_IsRecover 2 +#endif diff --git a/include/linux/raid/raid5.h b/include/linux/raid/raid5.h new file mode 100644 index 000000000000..d63ddcb4afad --- /dev/null +++ b/include/linux/raid/raid5.h @@ -0,0 +1,243 @@ +#ifndef _RAID5_H +#define _RAID5_H + +#include <linux/raid/md.h> +#include <linux/raid/xor.h> + +/* + * + * Each stripe contains one buffer per disc. Each buffer can be in + * one of a number of states stored in "flags". Changes between + * these states happen *almost* exclusively under a per-stripe + * spinlock. Some very specific changes can happen in bi_end_io, and + * these are not protected by the spin lock. + * + * The flag bits that are used to represent these states are: + * R5_UPTODATE and R5_LOCKED + * + * State Empty == !UPTODATE, !LOCK + * We have no data, and there is no active request + * State Want == !UPTODATE, LOCK + * A read request is being submitted for this block + * State Dirty == UPTODATE, LOCK + * Some new data is in this buffer, and it is being written out + * State Clean == UPTODATE, !LOCK + * We have valid data which is the same as on disc + * + * The possible state transitions are: + * + * Empty -> Want - on read or write to get old data for parity calc + * Empty -> Dirty - on compute_parity to satisfy write/sync request.(RECONSTRUCT_WRITE) + * Empty -> Clean - on compute_block when computing a block for failed drive + * Want -> Empty - on failed read + * Want -> Clean - on successful completion of read request + * Dirty -> Clean - on successful completion of write request + * Dirty -> Clean - on failed write + * Clean -> Dirty - on compute_parity to satisfy write/sync (RECONSTRUCT or RMW) + * + * The Want->Empty, Want->Clean, Dirty->Clean, transitions + * all happen in b_end_io at interrupt time. + * Each sets the Uptodate bit before releasing the Lock bit. + * This leaves one multi-stage transition: + * Want->Dirty->Clean + * This is safe because thinking that a Clean buffer is actually dirty + * will at worst delay some action, and the stripe will be scheduled + * for attention after the transition is complete. + * + * There is one possibility that is not covered by these states. That + * is if one drive has failed and there is a spare being rebuilt. We + * can't distinguish between a clean block that has been generated + * from parity calculations, and a clean block that has been + * successfully written to the spare ( or to parity when resyncing). + * To distingush these states we have a stripe bit STRIPE_INSYNC that + * is set whenever a write is scheduled to the spare, or to the parity + * disc if there is no spare. A sync request clears this bit, and + * when we find it set with no buffers locked, we know the sync is + * complete. + * + * Buffers for the md device that arrive via make_request are attached + * to the appropriate stripe in one of two lists linked on b_reqnext. + * One list (bh_read) for read requests, one (bh_write) for write. + * There should never be more than one buffer on the two lists + * together, but we are not guaranteed of that so we allow for more. + * + * If a buffer is on the read list when the associated cache buffer is + * Uptodate, the data is copied into the read buffer and it's b_end_io + * routine is called. This may happen in the end_request routine only + * if the buffer has just successfully been read. end_request should + * remove the buffers from the list and then set the Uptodate bit on + * the buffer. Other threads may do this only if they first check + * that the Uptodate bit is set. Once they have checked that they may + * take buffers off the read queue. + * + * When a buffer on the write list is committed for write it is copied + * into the cache buffer, which is then marked dirty, and moved onto a + * third list, the written list (bh_written). Once both the parity + * block and the cached buffer are successfully written, any buffer on + * a written list can be returned with b_end_io. + * + * The write list and read list both act as fifos. The read list is + * protected by the device_lock. The write and written lists are + * protected by the stripe lock. The device_lock, which can be + * claimed while the stipe lock is held, is only for list + * manipulations and will only be held for a very short time. It can + * be claimed from interrupts. + * + * + * Stripes in the stripe cache can be on one of two lists (or on + * neither). The "inactive_list" contains stripes which are not + * currently being used for any request. They can freely be reused + * for another stripe. The "handle_list" contains stripes that need + * to be handled in some way. Both of these are fifo queues. Each + * stripe is also (potentially) linked to a hash bucket in the hash + * table so that it can be found by sector number. Stripes that are + * not hashed must be on the inactive_list, and will normally be at + * the front. All stripes start life this way. + * + * The inactive_list, handle_list and hash bucket lists are all protected by the + * device_lock. + * - stripes on the inactive_list never have their stripe_lock held. + * - stripes have a reference counter. If count==0, they are on a list. + * - If a stripe might need handling, STRIPE_HANDLE is set. + * - When refcount reaches zero, then if STRIPE_HANDLE it is put on + * handle_list else inactive_list + * + * This, combined with the fact that STRIPE_HANDLE is only ever + * cleared while a stripe has a non-zero count means that if the + * refcount is 0 and STRIPE_HANDLE is set, then it is on the + * handle_list and if recount is 0 and STRIPE_HANDLE is not set, then + * the stripe is on inactive_list. + * + * The possible transitions are: + * activate an unhashed/inactive stripe (get_active_stripe()) + * lockdev check-hash unlink-stripe cnt++ clean-stripe hash-stripe unlockdev + * activate a hashed, possibly active stripe (get_active_stripe()) + * lockdev check-hash if(!cnt++)unlink-stripe unlockdev + * attach a request to an active stripe (add_stripe_bh()) + * lockdev attach-buffer unlockdev + * handle a stripe (handle_stripe()) + * lockstripe clrSTRIPE_HANDLE ... (lockdev check-buffers unlockdev) .. change-state .. record io needed unlockstripe schedule io + * release an active stripe (release_stripe()) + * lockdev if (!--cnt) { if STRIPE_HANDLE, add to handle_list else add to inactive-list } unlockdev + * + * The refcount counts each thread that have activated the stripe, + * plus raid5d if it is handling it, plus one for each active request + * on a cached buffer. + */ + +struct stripe_head { + struct stripe_head *hash_next, **hash_pprev; /* hash pointers */ + struct list_head lru; /* inactive_list or handle_list */ + struct raid5_private_data *raid_conf; + sector_t sector; /* sector of this row */ + int pd_idx; /* parity disk index */ + unsigned long state; /* state flags */ + atomic_t count; /* nr of active thread/requests */ + spinlock_t lock; + struct r5dev { + struct bio req; + struct bio_vec vec; + struct page *page; + struct bio *toread, *towrite, *written; + sector_t sector; /* sector of this page */ + unsigned long flags; + } dev[1]; /* allocated with extra space depending of RAID geometry */ +}; +/* Flags */ +#define R5_UPTODATE 0 /* page contains current data */ +#define R5_LOCKED 1 /* IO has been submitted on "req" */ +#define R5_OVERWRITE 2 /* towrite covers whole page */ +/* and some that are internal to handle_stripe */ +#define R5_Insync 3 /* rdev && rdev->in_sync at start */ +#define R5_Wantread 4 /* want to schedule a read */ +#define R5_Wantwrite 5 +#define R5_Syncio 6 /* this io need to be accounted as resync io */ +#define R5_Overlap 7 /* There is a pending overlapping request on this block */ + +/* + * Write method + */ +#define RECONSTRUCT_WRITE 1 +#define READ_MODIFY_WRITE 2 +/* not a write method, but a compute_parity mode */ +#define CHECK_PARITY 3 + +/* + * Stripe state + */ +#define STRIPE_ERROR 1 +#define STRIPE_HANDLE 2 +#define STRIPE_SYNCING 3 +#define STRIPE_INSYNC 4 +#define STRIPE_PREREAD_ACTIVE 5 +#define STRIPE_DELAYED 6 + +/* + * Plugging: + * + * To improve write throughput, we need to delay the handling of some + * stripes until there has been a chance that several write requests + * for the one stripe have all been collected. + * In particular, any write request that would require pre-reading + * is put on a "delayed" queue until there are no stripes currently + * in a pre-read phase. Further, if the "delayed" queue is empty when + * a stripe is put on it then we "plug" the queue and do not process it + * until an unplug call is made. (the unplug_io_fn() is called). + * + * When preread is initiated on a stripe, we set PREREAD_ACTIVE and add + * it to the count of prereading stripes. + * When write is initiated, or the stripe refcnt == 0 (just in case) we + * clear the PREREAD_ACTIVE flag and decrement the count + * Whenever the delayed queue is empty and the device is not plugged, we + * move any strips from delayed to handle and clear the DELAYED flag and set PREREAD_ACTIVE. + * In stripe_handle, if we find pre-reading is necessary, we do it if + * PREREAD_ACTIVE is set, else we set DELAYED which will send it to the delayed queue. + * HANDLE gets cleared if stripe_handle leave nothing locked. + */ + + +struct disk_info { + mdk_rdev_t *rdev; +}; + +struct raid5_private_data { + struct stripe_head **stripe_hashtbl; + mddev_t *mddev; + struct disk_info *spare; + int chunk_size, level, algorithm; + int raid_disks, working_disks, failed_disks; + int max_nr_stripes; + + struct list_head handle_list; /* stripes needing handling */ + struct list_head delayed_list; /* stripes that have plugged requests */ + atomic_t preread_active_stripes; /* stripes with scheduled io */ + + char cache_name[20]; + kmem_cache_t *slab_cache; /* for allocating stripes */ + /* + * Free stripes pool + */ + atomic_t active_stripes; + struct list_head inactive_list; + wait_queue_head_t wait_for_stripe; + wait_queue_head_t wait_for_overlap; + int inactive_blocked; /* release of inactive stripes blocked, + * waiting for 25% to be free + */ + spinlock_t device_lock; + struct disk_info disks[0]; +}; + +typedef struct raid5_private_data raid5_conf_t; + +#define mddev_to_conf(mddev) ((raid5_conf_t *) mddev->private) + +/* + * Our supported algorithms + */ +#define ALGORITHM_LEFT_ASYMMETRIC 0 +#define ALGORITHM_RIGHT_ASYMMETRIC 1 +#define ALGORITHM_LEFT_SYMMETRIC 2 +#define ALGORITHM_RIGHT_SYMMETRIC 3 + +#endif diff --git a/include/linux/raid/xor.h b/include/linux/raid/xor.h new file mode 100644 index 000000000000..f0d67cbdea40 --- /dev/null +++ b/include/linux/raid/xor.h @@ -0,0 +1,23 @@ +#ifndef _XOR_H +#define _XOR_H + +#include <linux/raid/md.h> + +#define MAX_XOR_BLOCKS 5 + +extern void xor_block(unsigned int count, unsigned int bytes, void **ptr); + +struct xor_block_template { + struct xor_block_template *next; + const char *name; + int speed; + void (*do_2)(unsigned long, unsigned long *, unsigned long *); + void (*do_3)(unsigned long, unsigned long *, unsigned long *, + unsigned long *); + void (*do_4)(unsigned long, unsigned long *, unsigned long *, + unsigned long *, unsigned long *); + void (*do_5)(unsigned long, unsigned long *, unsigned long *, + unsigned long *, unsigned long *, unsigned long *); +}; + +#endif |