summaryrefslogtreecommitdiff
path: root/release/src/linux/linux/include/linux/raid
diff options
context:
space:
mode:
authorAndreas Baumann <mail@andreasbaumann.cc>2015-01-03 12:04:58 +0100
committerAndreas Baumann <mail@andreasbaumann.cc>2015-01-03 12:04:58 +0100
commit008d0be72b2f160382c6e880765e96b64a050c65 (patch)
tree36f48a98a3815a408e2ce1693dd182af90f80305 /release/src/linux/linux/include/linux/raid
parent611becfb8726c60cb060368541ad98191d4532f5 (diff)
downloadtomato-008d0be72b2f160382c6e880765e96b64a050c65.tar.gz
tomato-008d0be72b2f160382c6e880765e96b64a050c65.tar.bz2
imported original firmware WRT54GL_v4.30.11_11_US
Diffstat (limited to 'release/src/linux/linux/include/linux/raid')
-rw-r--r--release/src/linux/linux/include/linux/raid/linear.h32
-rw-r--r--release/src/linux/linux/include/linux/raid/md.h91
-rw-r--r--release/src/linux/linux/include/linux/raid/md_compatible.h157
-rw-r--r--release/src/linux/linux/include/linux/raid/md_k.h399
-rw-r--r--release/src/linux/linux/include/linux/raid/md_p.h172
-rw-r--r--release/src/linux/linux/include/linux/raid/md_u.h117
-rw-r--r--release/src/linux/linux/include/linux/raid/multipath.h71
-rw-r--r--release/src/linux/linux/include/linux/raid/raid0.h33
-rw-r--r--release/src/linux/linux/include/linux/raid/raid1.h94
-rw-r--r--release/src/linux/linux/include/linux/raid/raid5.h240
-rw-r--r--release/src/linux/linux/include/linux/raid/xor.h23
11 files changed, 1429 insertions, 0 deletions
diff --git a/release/src/linux/linux/include/linux/raid/linear.h b/release/src/linux/linux/include/linux/raid/linear.h
new file mode 100644
index 00000000..80bf2476
--- /dev/null
+++ b/release/src/linux/linux/include/linux/raid/linear.h
@@ -0,0 +1,32 @@
+#ifndef _LINEAR_H
+#define _LINEAR_H
+
+#include <linux/raid/md.h>
+
+struct dev_info {
+ kdev_t dev;
+ unsigned long size;
+ unsigned long offset;
+};
+
+typedef struct dev_info dev_info_t;
+
+struct linear_hash
+{
+ dev_info_t *dev0, *dev1;
+};
+
+struct linear_private_data
+{
+ struct linear_hash *hash_table;
+ dev_info_t disks[MD_SB_DISKS];
+ dev_info_t *smallest;
+ int nr_zones;
+};
+
+
+typedef struct linear_private_data linear_conf_t;
+
+#define mddev_to_conf(mddev) ((linear_conf_t *) mddev->private)
+
+#endif
diff --git a/release/src/linux/linux/include/linux/raid/md.h b/release/src/linux/linux/include/linux/raid/md.h
new file mode 100644
index 00000000..a7e18913
--- /dev/null
+++ b/release/src/linux/linux/include/linux/raid/md.h
@@ -0,0 +1,91 @@
+/*
+ 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/mm.h>
+#include <linux/fs.h>
+#include <linux/blkdev.h>
+#include <asm/semaphore.h>
+#include <linux/major.h>
+#include <linux/ioctl.h>
+#include <linux/types.h>
+#include <asm/bitops.h>
+#include <linux/module.h>
+#include <linux/hdreg.h>
+#include <linux/proc_fs.h>
+#include <linux/smp_lock.h>
+#include <linux/delay.h>
+#include <net/checksum.h>
+#include <linux/random.h>
+#include <linux/locks.h>
+#include <linux/kernel_stat.h>
+#include <asm/io.h>
+#include <linux/completion.h>
+
+#include <linux/raid/md_compatible.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 0
+
+extern int md_size[MAX_MD_DEVS];
+extern struct hd_struct md_hd_struct[MAX_MD_DEVS];
+
+extern void add_mddev_mapping (mddev_t *mddev, kdev_t dev, void *data);
+extern void del_mddev_mapping (mddev_t *mddev, kdev_t dev);
+extern char * partition_name (kdev_t dev);
+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) (void *data),
+ void *data, const char *name);
+extern void md_unregister_thread (mdk_thread_t *thread);
+extern void md_wakeup_thread(mdk_thread_t *thread);
+extern void md_interrupt_thread (mdk_thread_t *thread);
+extern int md_update_sb (mddev_t *mddev);
+extern int md_do_sync(mddev_t *mddev, mdp_disk_t *spare);
+extern void md_done_sync(mddev_t *mddev, int blocks, int ok);
+extern void md_sync_acct(kdev_t dev, unsigned long nr_sectors);
+extern void md_recover_arrays (void);
+extern int md_check_ordering (mddev_t *mddev);
+extern int md_notify_reboot(struct notifier_block *this,
+ unsigned long code, void *x);
+extern int md_error (mddev_t *mddev, kdev_t rdev);
+extern int md_run_setup(void);
+
+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/release/src/linux/linux/include/linux/raid/md_compatible.h b/release/src/linux/linux/include/linux/raid/md_compatible.h
new file mode 100644
index 00000000..a4f9ae57
--- /dev/null
+++ b/release/src/linux/linux/include/linux/raid/md_compatible.h
@@ -0,0 +1,157 @@
+
+/*
+ md.h : Multiple Devices driver compatibility layer for Linux 2.0/2.2
+ 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.
+*/
+
+#include <linux/version.h>
+
+#ifndef _MD_COMPATIBLE_H
+#define _MD_COMPATIBLE_H
+
+/** 2.3/2.4 stuff: **/
+
+#include <linux/reboot.h>
+#include <linux/vmalloc.h>
+#include <linux/blkpg.h>
+
+/* 000 */
+#define md__get_free_pages(x,y) __get_free_pages(x,y)
+
+#if defined(__i386__) || defined(__x86_64__)
+/* 001 */
+static __inline__ int md_cpu_has_mmx(void)
+{
+ return test_bit(X86_FEATURE_MMX, &boot_cpu_data.x86_capability);
+}
+#else
+#define md_cpu_has_mmx() (0)
+#endif
+
+/* 002 */
+#define md_clear_page(page) clear_page(page)
+
+/* 003 */
+#define MD_EXPORT_SYMBOL(x) EXPORT_SYMBOL(x)
+
+/* 004 */
+#define md_copy_to_user(x,y,z) copy_to_user(x,y,z)
+
+/* 005 */
+#define md_copy_from_user(x,y,z) copy_from_user(x,y,z)
+
+/* 006 */
+#define md_put_user put_user
+
+/* 007 */
+static inline int md_capable_admin(void)
+{
+ return capable(CAP_SYS_ADMIN);
+}
+
+/* 008 */
+#define MD_FILE_TO_INODE(file) ((file)->f_dentry->d_inode)
+
+/* 009 */
+static inline void md_flush_signals (void)
+{
+ spin_lock(&current->sigmask_lock);
+ flush_signals(current);
+ spin_unlock(&current->sigmask_lock);
+}
+
+/* 010 */
+static inline void md_init_signals (void)
+{
+ current->exit_signal = SIGCHLD;
+ siginitsetinv(&current->blocked, sigmask(SIGKILL));
+}
+
+/* 011 */
+#define md_signal_pending signal_pending
+
+/* 012 - md_set_global_readahead - nowhere used */
+
+/* 013 */
+#define md_mdelay(x) mdelay(x)
+
+/* 014 */
+#define MD_SYS_DOWN SYS_DOWN
+#define MD_SYS_HALT SYS_HALT
+#define MD_SYS_POWER_OFF SYS_POWER_OFF
+
+/* 015 */
+#define md_register_reboot_notifier register_reboot_notifier
+
+/* 016 */
+#define md_test_and_set_bit test_and_set_bit
+
+/* 017 */
+#define md_test_and_clear_bit test_and_clear_bit
+
+/* 018 */
+#define md_atomic_set atomic_set
+
+/* 019 */
+#define md_lock_kernel lock_kernel
+#define md_unlock_kernel unlock_kernel
+
+/* 020 */
+
+#include <linux/init.h>
+
+#define md__init __init
+#define md__initdata __initdata
+#define md__initfunc(__arginit) __initfunc(__arginit)
+
+/* 021 */
+
+
+/* 022 */
+
+#define md_list_head list_head
+#define MD_LIST_HEAD(name) LIST_HEAD(name)
+#define MD_INIT_LIST_HEAD(ptr) INIT_LIST_HEAD(ptr)
+#define md_list_add list_add
+#define md_list_del list_del
+#define md_list_empty list_empty
+
+#define md_list_entry(ptr, type, member) list_entry(ptr, type, member)
+
+/* 023 */
+
+#define md_schedule_timeout schedule_timeout
+
+/* 024 */
+#define md_need_resched(tsk) ((tsk)->need_resched)
+
+/* 025 */
+#define md_spinlock_t spinlock_t
+#define MD_SPIN_LOCK_UNLOCKED SPIN_LOCK_UNLOCKED
+
+#define md_spin_lock spin_lock
+#define md_spin_unlock spin_unlock
+#define md_spin_lock_irq spin_lock_irq
+#define md_spin_unlock_irq spin_unlock_irq
+#define md_spin_unlock_irqrestore spin_unlock_irqrestore
+#define md_spin_lock_irqsave spin_lock_irqsave
+
+/* 026 */
+typedef wait_queue_head_t md_wait_queue_head_t;
+#define MD_DECLARE_WAITQUEUE(w,t) DECLARE_WAITQUEUE((w),(t))
+#define MD_DECLARE_WAIT_QUEUE_HEAD(x) DECLARE_WAIT_QUEUE_HEAD(x)
+#define md_init_waitqueue_head init_waitqueue_head
+
+/* END */
+
+#endif
+
diff --git a/release/src/linux/linux/include/linux/raid/md_k.h b/release/src/linux/linux/include/linux/raid/md_k.h
new file mode 100644
index 00000000..dcdc744b
--- /dev/null
+++ b/release/src/linux/linux/include/linux/raid/md_k.h
@@ -0,0 +1,399 @@
+/*
+ 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 MAX_PERSONALITY 8UL
+
+static inline int pers_to_level (int pers)
+{
+ switch (pers) {
+ case MULTIPATH: return -4;
+ case HSM: return -3;
+ case TRANSLUCENT: return -2;
+ case LINEAR: return -1;
+ case RAID0: return 0;
+ case RAID1: return 1;
+ case RAID5: return 5;
+ }
+ BUG();
+ return MD_RESERVED;
+}
+
+static inline int level_to_pers (int level)
+{
+ switch (level) {
+ case -4: return MULTIPATH;
+ case -3: return HSM;
+ case -2: return TRANSLUCENT;
+ case -1: return LINEAR;
+ case 0: return RAID0;
+ case 1: return RAID1;
+ case 4:
+ case 5: return RAID5;
+ }
+ return MD_RESERVED;
+}
+
+typedef struct mddev_s mddev_t;
+typedef struct mdk_rdev_s mdk_rdev_t;
+
+#if MINORBITS != 8
+#error MD does not handle bigger kdev yet
+#endif
+
+#define MAX_MD_DEVS (1<<MINORBITS) /* Max number of md dev */
+
+/*
+ * Maps a kdev to an mddev/subdev. How 'data' is handled is up to
+ * the personality. (eg. HSM uses this to identify individual LVs)
+ */
+typedef struct dev_mapping_s {
+ mddev_t *mddev;
+ void *data;
+} dev_mapping_t;
+
+extern dev_mapping_t mddev_map [MAX_MD_DEVS];
+
+static inline mddev_t * kdev_to_mddev (kdev_t dev)
+{
+ if (MAJOR(dev) != MD_MAJOR)
+ BUG();
+ return mddev_map[MINOR(dev)].mddev;
+}
+
+/*
+ * options passed in raidrun:
+ */
+
+#define MAX_CHUNK_SIZE (4096*1024)
+
+/*
+ * default readahead
+ */
+#define MD_READAHEAD vm_max_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 md_list_head same_set; /* RAID devices within the same set */
+ struct md_list_head all; /* all RAID devices */
+ struct md_list_head pending; /* undetected RAID devices */
+
+ kdev_t dev; /* Device number */
+ kdev_t old_dev; /* "" when it was last imported */
+ unsigned long 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 */
+
+ mdp_super_t *sb;
+ unsigned long sb_offset;
+
+ int alias_device; /* device alias to the same disk */
+ int faulty; /* if faulty do not issue IO requests */
+ int desc_nr; /* descriptor index in the superblock */
+};
+
+
+/*
+ * disk operations in a working array:
+ */
+#define DISKOP_SPARE_INACTIVE 0
+#define DISKOP_SPARE_WRITE 1
+#define DISKOP_SPARE_ACTIVE 2
+#define DISKOP_HOT_REMOVE_DISK 3
+#define DISKOP_HOT_ADD_DISK 4
+
+typedef struct mdk_personality_s mdk_personality_t;
+
+struct mddev_s
+{
+ void *private;
+ mdk_personality_t *pers;
+ int __minor;
+ mdp_super_t *sb;
+ int nb_dev;
+ struct md_list_head disks;
+ int sb_dirty;
+ mdu_param_t param;
+ int ro;
+ unsigned long curr_resync; /* blocks scheduled */
+ unsigned long resync_mark; /* a recent timestamp */
+ unsigned long resync_mark_cnt;/* blocks written at resync_mark */
+ char *name;
+ int recovery_running;
+ struct semaphore reconfig_sem;
+ struct semaphore recovery_sem;
+ struct semaphore resync_sem;
+ atomic_t active;
+
+ atomic_t recovery_active; /* blocks scheduled, but not written */
+ md_wait_queue_head_t recovery_wait;
+
+ struct md_list_head all_mddevs;
+};
+
+struct mdk_personality_s
+{
+ char *name;
+ int (*make_request)(mddev_t *mddev, int rw, struct buffer_head * bh);
+ int (*run)(mddev_t *mddev);
+ int (*stop)(mddev_t *mddev);
+ int (*status)(char *page, mddev_t *mddev);
+ int (*error_handler)(mddev_t *mddev, kdev_t dev);
+
+/*
+ * Some personalities (RAID-1, RAID-5) can have disks hot-added and
+ * hot-removed. Hot removal is different from failure. (failure marks
+ * a disk inactive, but the disk is still part of the array) The interface
+ * to such operations is the 'pers->diskop()' function, can be NULL.
+ *
+ * the diskop function can change the pointer pointing to the incoming
+ * descriptor, but must do so very carefully. (currently only
+ * SPARE_ACTIVE expects such a change)
+ */
+ int (*diskop) (mddev_t *mddev, mdp_disk_t **descriptor, int state);
+
+ int (*stop_resync)(mddev_t *mddev);
+ int (*restart_resync)(mddev_t *mddev);
+ int (*sync_request)(mddev_t *mddev, unsigned long block_nr);
+};
+
+
+/*
+ * Currently we index md_array directly, based on the minor
+ * number. This will have to change to dynamic allocation
+ * once we start supporting partitioning of md devices.
+ */
+static inline int mdidx (mddev_t * mddev)
+{
+ return mddev->__minor;
+}
+
+static inline kdev_t mddev_to_kdev(mddev_t * mddev)
+{
+ return MKDEV(MD_MAJOR, mdidx(mddev));
+}
+
+extern mdk_rdev_t * find_rdev(mddev_t * mddev, kdev_t dev);
+extern mdk_rdev_t * find_rdev_nr(mddev_t *mddev, int nr);
+extern mdp_disk_t *get_spare(mddev_t *mddev);
+
+/*
+ * iterates through some rdev ringlist. It's safe to remove the
+ * current 'rdev'. Dont touch 'tmp' though.
+ */
+#define ITERATE_RDEV_GENERIC(head,field,rdev,tmp) \
+ \
+ for (tmp = head.next; \
+ rdev = md_list_entry(tmp, mdk_rdev_t, field), \
+ tmp = tmp->next, tmp->prev != &head \
+ ; )
+/*
+ * iterates through the 'same array disks' ringlist
+ */
+#define ITERATE_RDEV(mddev,rdev,tmp) \
+ ITERATE_RDEV_GENERIC((mddev)->disks,same_set,rdev,tmp)
+
+/*
+ * Same as above, but assumes that the device has rdev->desc_nr numbered
+ * from 0 to mddev->nb_dev, and iterates through rdevs in ascending order.
+ */
+#define ITERATE_RDEV_ORDERED(mddev,rdev,i) \
+ for (i = 0; rdev = find_rdev_nr(mddev, i), i < mddev->nb_dev; i++)
+
+
+/*
+ * Iterates through all 'RAID managed disks'
+ */
+#define ITERATE_RDEV_ALL(rdev,tmp) \
+ ITERATE_RDEV_GENERIC(all_raid_disks,all,rdev,tmp)
+
+/*
+ * Iterates through 'pending RAID disks'
+ */
+#define ITERATE_RDEV_PENDING(rdev,tmp) \
+ ITERATE_RDEV_GENERIC(pending_raid_disks,pending,rdev,tmp)
+
+/*
+ * iterates through all used mddevs in the system.
+ */
+#define ITERATE_MDDEV(mddev,tmp) \
+ \
+ for (tmp = all_mddevs.next; \
+ mddev = md_list_entry(tmp, mddev_t, all_mddevs), \
+ tmp = tmp->next, tmp->prev != &all_mddevs \
+ ; )
+
+static inline int lock_mddev (mddev_t * mddev)
+{
+ return down_interruptible(&mddev->reconfig_sem);
+}
+
+static inline void unlock_mddev (mddev_t * mddev)
+{
+ up(&mddev->reconfig_sem);
+}
+
+#define xchg_values(x,y) do { __typeof__(x) __tmp = x; \
+ x = y; y = __tmp; } while (0)
+
+typedef struct mdk_thread_s {
+ void (*run) (void *data);
+ void *data;
+ md_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 MAX_DISKNAME_LEN 64
+
+typedef struct dev_name_s {
+ struct md_list_head list;
+ kdev_t dev;
+ char namebuf [MAX_DISKNAME_LEN];
+ char *name;
+} dev_name_t;
+
+
+#define __wait_event_lock_irq(wq, condition, lock) \
+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); \
+ run_task_queue(&tq_disk); \
+ schedule(); \
+ spin_lock_irq(&lock); \
+ } \
+ current->state = TASK_RUNNING; \
+ remove_wait_queue(&wq, &__wait); \
+} while (0)
+
+#define wait_event_lock_irq(wq, condition, lock) \
+do { \
+ if (condition) \
+ break; \
+ __wait_event_lock_irq(wq, condition, lock); \
+} while (0)
+
+
+#define __wait_disk_event(wq, condition) \
+do { \
+ wait_queue_t __wait; \
+ init_waitqueue_entry(&__wait, current); \
+ \
+ add_wait_queue(&wq, &__wait); \
+ for (;;) { \
+ set_current_state(TASK_UNINTERRUPTIBLE); \
+ if (condition) \
+ break; \
+ run_task_queue(&tq_disk); \
+ schedule(); \
+ } \
+ current->state = TASK_RUNNING; \
+ remove_wait_queue(&wq, &__wait); \
+} while (0)
+
+#define wait_disk_event(wq, condition) \
+do { \
+ if (condition) \
+ break; \
+ __wait_disk_event(wq, condition); \
+} while (0)
+
+#endif
+
diff --git a/release/src/linux/linux/include/linux/raid/md_p.h b/release/src/linux/linux/include/linux/raid/md_p.h
new file mode 100644
index 00000000..d6bb37a8
--- /dev/null
+++ b/release/src/linux/linux/include/linux/raid/md_p.h
@@ -0,0 +1,172 @@
+/*
+ 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 */
+#else
+ __u32 events_lo; /* 7 low-order of superblock update count */
+ __u32 events_hi; /* 8 high-order of superblock update count */
+#endif
+ __u32 gstate_sreserved[MD_SB_GENERIC_STATE_WORDS - 9];
+
+ /*
+ * 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;
+}
+
+#endif
+
diff --git a/release/src/linux/linux/include/linux/raid/md_u.h b/release/src/linux/linux/include/linux/raid/md_u.h
new file mode 100644
index 00000000..a2df5c2a
--- /dev/null
+++ b/release/src/linux/linux/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/release/src/linux/linux/include/linux/raid/multipath.h b/release/src/linux/linux/include/linux/raid/multipath.h
new file mode 100644
index 00000000..261c1c83
--- /dev/null
+++ b/release/src/linux/linux/include/linux/raid/multipath.h
@@ -0,0 +1,71 @@
+#ifndef _MULTIPATH_H
+#define _MULTIPATH_H
+
+#include <linux/raid/md.h>
+
+struct multipath_info {
+ int number;
+ int raid_disk;
+ kdev_t dev;
+
+ /*
+ * State bits:
+ */
+ int operational;
+ int spare;
+
+ int used_slot;
+};
+
+struct multipath_private_data {
+ mddev_t *mddev;
+ struct multipath_info multipaths[MD_SB_DISKS];
+ int nr_disks;
+ int raid_disks;
+ int working_disks;
+ mdk_thread_t *thread;
+ struct multipath_info *spare;
+ md_spinlock_t device_lock;
+
+ /* buffer pool */
+ /* buffer_heads that we have pre-allocated have b_pprev -> &freebh
+ * and are linked into a stack using b_next
+ * multipath_bh that are pre-allocated have MPBH_PreAlloc set.
+ * All these variable are protected by device_lock
+ */
+ struct multipath_bh *freer1;
+ int freer1_blocked;
+ int freer1_cnt;
+ md_wait_queue_head_t wait_buffer;
+};
+
+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 {
+ atomic_t remaining; /* 'have we finished' count,
+ * used from IRQ handlers
+ */
+ int cmd;
+ unsigned long state;
+ mddev_t *mddev;
+ struct buffer_head *master_bh;
+ struct buffer_head bh_req;
+ struct multipath_bh *next_mp; /* next for retry or in free list */
+};
+/* bits for multipath_bh.state */
+#define MPBH_Uptodate 1
+#define MPBH_SyncPhase 2
+#define MPBH_PreAlloc 3 /* this was pre-allocated, add to free list */
+#endif
diff --git a/release/src/linux/linux/include/linux/raid/raid0.h b/release/src/linux/linux/include/linux/raid/raid0.h
new file mode 100644
index 00000000..0b937295
--- /dev/null
+++ b/release/src/linux/linux/include/linux/raid/raid0.h
@@ -0,0 +1,33 @@
+#ifndef _RAID0_H
+#define _RAID0_H
+
+#include <linux/raid/md.h>
+
+struct strip_zone
+{
+ unsigned long zone_offset; /* Zone offset in md_dev */
+ unsigned long dev_offset; /* Zone offset in real dev */
+ unsigned long size; /* Zone size */
+ int nb_dev; /* # of devices attached to the zone */
+ mdk_rdev_t *dev[MD_SB_DISKS]; /* Devices attached to the zone */
+};
+
+struct raid0_hash
+{
+ struct strip_zone *zone0, *zone1;
+};
+
+struct raid0_private_data
+{
+ struct raid0_hash *hash_table; /* Dynamically allocated */
+ struct strip_zone *strip_zone; /* This one too */
+ int nr_strip_zones;
+ struct strip_zone *smallest;
+ int nr_zones;
+};
+
+typedef struct raid0_private_data raid0_conf_t;
+
+#define mddev_to_conf(mddev) ((raid0_conf_t *) mddev->private)
+
+#endif
diff --git a/release/src/linux/linux/include/linux/raid/raid1.h b/release/src/linux/linux/include/linux/raid/raid1.h
new file mode 100644
index 00000000..40675b40
--- /dev/null
+++ b/release/src/linux/linux/include/linux/raid/raid1.h
@@ -0,0 +1,94 @@
+#ifndef _RAID1_H
+#define _RAID1_H
+
+#include <linux/raid/md.h>
+
+struct mirror_info {
+ int number;
+ int raid_disk;
+ kdev_t dev;
+ int sect_limit;
+ int head_position;
+
+ /*
+ * State bits:
+ */
+ int operational;
+ int write_only;
+ int spare;
+
+ int used_slot;
+};
+
+struct raid1_private_data {
+ mddev_t *mddev;
+ struct mirror_info mirrors[MD_SB_DISKS];
+ int nr_disks;
+ int raid_disks;
+ int working_disks;
+ int last_used;
+ unsigned long next_sect;
+ int sect_count;
+ mdk_thread_t *thread, *resync_thread;
+ int resync_mirrors;
+ struct mirror_info *spare;
+ md_spinlock_t device_lock;
+
+ /* buffer pool */
+ /* buffer_heads that we have pre-allocated have b_pprev -> &freebh
+ * and are linked into a stack using b_next
+ * raid1_bh that are pre-allocated have R1BH_PreAlloc set.
+ * All these variable are protected by device_lock
+ */
+ struct buffer_head *freebh;
+ int freebh_cnt; /* how many are on the list */
+ int freebh_blocked;
+ struct raid1_bh *freer1;
+ int freer1_blocked;
+ int freer1_cnt;
+ struct raid1_bh *freebuf; /* each bh_req has a page allocated */
+ md_wait_queue_head_t wait_buffer;
+
+ /* for use when syncing mirrors: */
+ unsigned long start_active, start_ready,
+ start_pending, start_future;
+ int cnt_done, cnt_active, cnt_ready,
+ cnt_pending, cnt_future;
+ int phase;
+ int window;
+ md_wait_queue_head_t wait_done;
+ md_wait_queue_head_t wait_ready;
+ md_spinlock_t segment_lock;
+};
+
+typedef struct raid1_private_data raid1_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) ((raid1_conf_t *) mddev->private)
+
+/*
+ * this is our 'private' 'collective' RAID1 buffer head.
+ * it contains information about what kind of IO operations were started
+ * for this RAID1 operation, and about their status:
+ */
+
+struct raid1_bh {
+ atomic_t remaining; /* 'have we finished' count,
+ * used from IRQ handlers
+ */
+ int cmd;
+ unsigned long state;
+ mddev_t *mddev;
+ struct buffer_head *master_bh;
+ struct buffer_head *mirror_bh_list;
+ struct buffer_head bh_req;
+ struct raid1_bh *next_r1; /* next for retry or in free list */
+};
+/* bits for raid1_bh.state */
+#define R1BH_Uptodate 1
+#define R1BH_SyncPhase 2
+#define R1BH_PreAlloc 3 /* this was pre-allocated, add to free list */
+#endif
diff --git a/release/src/linux/linux/include/linux/raid/raid5.h b/release/src/linux/linux/include/linux/raid/raid5.h
new file mode 100644
index 00000000..5b4a005e
--- /dev/null
+++ b/release/src/linux/linux/include/linux/raid/raid5.h
@@ -0,0 +1,240 @@
+#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 determined by bh_state. Changes between
+ * these states happen *almost* exclusively under a per-stripe
+ * spinlock. Some very specific changes can happen in b_end_io, and
+ * these are not protected by the spin lock.
+ *
+ * The bh_state bits that are used to represent these states are:
+ * BH_Uptodate, BH_Lock
+ *
+ * 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 is it 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;
+ struct buffer_head *bh_cache[MD_SB_DISKS]; /* buffered copy */
+ struct buffer_head *bh_read[MD_SB_DISKS]; /* read request buffers of the MD device */
+ struct buffer_head *bh_write[MD_SB_DISKS]; /* write request buffers of the MD device */
+ struct buffer_head *bh_written[MD_SB_DISKS]; /* write request buffers of the MD device that have been scheduled for write */
+ struct page *bh_page[MD_SB_DISKS]; /* saved bh_cache[n]->b_page when reading around the cache */
+ unsigned long sector; /* sector of this row */
+ int size; /* buffers size */
+ int pd_idx; /* parity disk index */
+ unsigned long state; /* state flags */
+ atomic_t count; /* nr of active thread/requests */
+ spinlock_t lock;
+ int sync_redone;
+};
+
+
+/*
+ * 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 unplg call is made. (the tq_disk list is run).
+ *
+ * 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 {
+ kdev_t dev;
+ int operational;
+ int number;
+ int raid_disk;
+ int write_only;
+ int spare;
+ int used_slot;
+};
+
+struct raid5_private_data {
+ struct stripe_head **stripe_hashtbl;
+ mddev_t *mddev;
+ mdk_thread_t *thread, *resync_thread;
+ struct disk_info disks[MD_SB_DISKS];
+ struct disk_info *spare;
+ int buffer_size;
+ int chunk_size, level, algorithm;
+ int raid_disks, working_disks, failed_disks;
+ int resync_parity;
+ 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 */
+ /*
+ * Free stripes pool
+ */
+ atomic_t active_stripes;
+ struct list_head inactive_list;
+ md_wait_queue_head_t wait_for_stripe;
+ int inactive_blocked; /* release of inactive stripes blocked,
+ * waiting for 25% to be free
+ */
+ md_spinlock_t device_lock;
+
+ int plugged;
+ struct tq_struct plug_tq;
+};
+
+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/release/src/linux/linux/include/linux/raid/xor.h b/release/src/linux/linux/include/linux/raid/xor.h
new file mode 100644
index 00000000..0e6950a7
--- /dev/null
+++ b/release/src/linux/linux/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, struct buffer_head **bh_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