md: move md_k.h from include/linux/raid/ to drivers/md/

It really is nicer to keep related code together..

Signed-off-by: NeilBrown <neilb@suse.de>

10 files changed, 420 insertions, 9 deletions

diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
index 1df012e9d73d..623292a5473e 100644
--- a/drivers/md/bitmap.c
+++ b/drivers/md/bitmap.c
@@ -27,7 +27,7 @@
 #include <linux/file.h>
 #include <linux/mount.h>
 #include <linux/buffer_head.h>
-#include <linux/raid/md_k.h>
+#include "md.h"
 #include "bitmap.h"
 
 /* debug macros */
diff --git a/drivers/md/faulty.c b/drivers/md/faulty.c
index cc5d2cf08dfc..7b66b9fca29d 100644
--- a/drivers/md/faulty.c
+++ b/drivers/md/faulty.c
@@ -64,7 +64,7 @@
 #define MaxFault	50
 #include <linux/blkdev.h>
 #include <linux/raid/md_u.h>
-#include <linux/raid/md_k.h>
+#include "md.h"
 #include <linux/seq_file.h>
 
 
diff --git a/drivers/md/linear.c b/drivers/md/linear.c
index c43c3b60ef09..f2488343ed4a 100644
--- a/drivers/md/linear.c
+++ b/drivers/md/linear.c
@@ -18,8 +18,8 @@
 
 #include <linux/blkdev.h>
 #include <linux/raid/md_u.h>
-#include <linux/raid/md_k.h>
 #include <linux/seq_file.h>
+#include "md.h"
 #include "linear.h"
 
 /*
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 11d6e0e1045a..aad0ac54bf90 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -45,9 +45,9 @@
 #include <linux/reboot.h>
 #include <linux/file.h>
 #include <linux/delay.h>
-#include <linux/raid/md_k.h>
 #include <linux/raid/md_p.h>
 #include <linux/raid/md_u.h>
+#include "md.h"
 #include "bitmap.h"
 
 #define DEBUG 0
diff --git a/drivers/md/md.h b/drivers/md/md.h
new file mode 100644
index 000000000000..e78b3c1d55fd
--- /dev/null
+++ b/drivers/md/md.h
@@ -0,0 +1,411 @@
+/*
+   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
+
+#ifdef CONFIG_BLOCK
+
+#define MaxSector (~(sector_t)0)
+
+typedef struct mddev_s mddev_t;
+typedef struct mdk_rdev_s mdk_rdev_t;
+
+/*
+ * options passed in raidrun:
+ */
+
+/* Currently this must fit in an 'int' */
+#define MAX_CHUNK_SIZE (1<<30)
+
+/*
+ * 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 */
+	int last_events;		/* IO event timestamp */
+
+	struct block_device *bdev;	/* block device handle */
+
+	struct page	*sb_page;
+	int		sb_loaded;
+	__u64		sb_events;
+	sector_t	data_offset;	/* start of data in array */
+	sector_t 	sb_start;	/* offset of the super block (in 512byte sectors) */
+	int		sb_size;	/* bytes in the superblock */
+	int		preferred_minor;	/* autorun support */
+
+	struct kobject	kobj;
+
+	/* 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
+	 */
+
+	unsigned long	flags;
+#define	Faulty		1		/* device is known to have a fault */
+#define	In_sync		2		/* device is in_sync with rest of array */
+#define	WriteMostly	4		/* Avoid reading if at all possible */
+#define	BarriersNotsupp	5		/* BIO_RW_BARRIER is not supported */
+#define	AllReserved	6		/* If whole device is reserved for
+					 * one array */
+#define	AutoDetected	7		/* added by auto-detect */
+#define Blocked		8		/* An error occured on an externally
+					 * managed array, don't allow writes
+					 * until it is cleared */
+#define StateChanged	9		/* Faulty or Blocked has changed during
+					 * interrupt, so it needs to be
+					 * notified by the thread */
+	wait_queue_head_t blocked_wait;
+
+	int desc_nr;			/* descriptor index in the superblock */
+	int raid_disk;			/* role of device in array */
+	int saved_raid_disk;		/* role that device used to have in the
+					 * array and could again if we did a partial
+					 * resync from the bitmap
+					 */
+	sector_t	recovery_offset;/* If this device has been partially
+					 * recovered, this is where we were
+					 * up to.
+					 */
+
+	atomic_t	nr_pending;	/* number of pending requests.
+					 * only maintained for arrays that
+					 * support hot removal
+					 */
+	atomic_t	read_errors;	/* number of consecutive read errors that
+					 * we have tried to ignore.
+					 */
+	atomic_t	corrected_errors; /* number of corrected read errors,
+					   * for reporting to userspace and storing
+					   * in superblock.
+					   */
+	struct work_struct del_work;	/* used for delayed sysfs removal */
+
+	struct sysfs_dirent *sysfs_state; /* handle for 'state'
+					   * sysfs entry */
+};
+
+struct mddev_s
+{
+	void				*private;
+	struct mdk_personality		*pers;
+	dev_t				unit;
+	int				md_minor;
+	struct list_head 		disks;
+	unsigned long			flags;
+#define MD_CHANGE_DEVS	0	/* Some device status has changed */
+#define MD_CHANGE_CLEAN 1	/* transition to or from 'clean' */
+#define MD_CHANGE_PENDING 2	/* superblock update in progress */
+
+	int				ro;
+
+	struct gendisk			*gendisk;
+
+	struct kobject			kobj;
+	int				hold_active;
+#define	UNTIL_IOCTL	1
+#define	UNTIL_STOP	2
+
+	/* Superblock information */
+	int				major_version,
+					minor_version,
+					patch_version;
+	int				persistent;
+	int 				external;	/* metadata is
+							 * managed externally */
+	char				metadata_type[17]; /* externally set*/
+	int				chunk_size;
+	time_t				ctime, utime;
+	int				level, layout;
+	char				clevel[16];
+	int				raid_disks;
+	int				max_disks;
+	sector_t			size; /* used size of component devices */
+	sector_t			array_sectors; /* exported array size */
+	__u64				events;
+
+	char				uuid[16];
+
+	/* If the array is being reshaped, we need to record the
+	 * new shape and an indication of where we are up to.
+	 * This is written to the superblock.
+	 * If reshape_position is MaxSector, then no reshape is happening (yet).
+	 */
+	sector_t			reshape_position;
+	int				delta_disks, new_level, new_layout, new_chunk;
+
+	struct mdk_thread_s		*thread;	/* management thread */
+	struct mdk_thread_s		*sync_thread;	/* doing resync or reconstruct */
+	sector_t			curr_resync;	/* last block scheduled */
+	unsigned long			resync_mark;	/* a recent timestamp */
+	sector_t			resync_mark_cnt;/* blocks written at resync_mark */
+	sector_t			curr_mark_cnt; /* blocks scheduled now */
+
+	sector_t			resync_max_sectors; /* may be set by personality */
+
+	sector_t			resync_mismatches; /* count of sectors where
+							    * parity/replica mismatch found
+							    */
+
+	/* allow user-space to request suspension of IO to regions of the array */
+	sector_t			suspend_lo;
+	sector_t			suspend_hi;
+	/* if zero, use the system-wide default */
+	int				sync_speed_min;
+	int				sync_speed_max;
+
+	/* resync even though the same disks are shared among md-devices */
+	int				parallel_resync;
+
+	int				ok_start_degraded;
+	/* 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
+	 * RECOVER:  doing recovery, or need to try it.
+	 * INTR:     resync needs to be aborted for some reason
+	 * DONE:     thread is done and is waiting to be reaped
+	 * REQUEST:  user-space has requested a sync (used with SYNC)
+	 * CHECK:    user-space request for for check-only, no repair
+	 * RESHAPE:  A reshape is happening
+	 *
+	 * If neither SYNC or RESHAPE are set, then it is a recovery.
+	 */
+#define	MD_RECOVERY_RUNNING	0
+#define	MD_RECOVERY_SYNC	1
+#define	MD_RECOVERY_RECOVER	2
+#define	MD_RECOVERY_INTR	3
+#define	MD_RECOVERY_DONE	4
+#define	MD_RECOVERY_NEEDED	5
+#define	MD_RECOVERY_REQUESTED	6
+#define	MD_RECOVERY_CHECK	7
+#define MD_RECOVERY_RESHAPE	8
+#define	MD_RECOVERY_FROZEN	9
+
+	unsigned long			recovery;
+	int				recovery_disabled; /* if we detect that recovery
+							    * will always fail, set this
+							    * so we don't loop trying */
+
+	int				in_sync;	/* know to not need resync */
+	struct mutex			reconfig_mutex;
+	atomic_t			active;		/* general refcount */
+	atomic_t			openers;	/* number of active opens */
+
+	int				changed;	/* true if we might need to reread partition info */
+	int				degraded;	/* whether md should consider
+							 * adding a spare
+							 */
+	int				barriers_work;	/* initialised to true, cleared as soon
+							 * as a barrier request to slave
+							 * fails.  Only supported
+							 */
+	struct bio			*biolist; 	/* bios that need to be retried
+							 * because BIO_RW_BARRIER is not supported
+							 */
+
+	atomic_t			recovery_active; /* blocks scheduled, but not written */
+	wait_queue_head_t		recovery_wait;
+	sector_t			recovery_cp;
+	sector_t			resync_min;	/* user requested sync
+							 * starts here */
+	sector_t			resync_max;	/* resync should pause
+							 * when it gets here */
+
+	struct sysfs_dirent		*sysfs_state;	/* handle for 'array_state'
+							 * file in sysfs.
+							 */
+	struct sysfs_dirent		*sysfs_action;  /* handle for 'sync_action' */
+
+	struct work_struct del_work;	/* used for delayed sysfs removal */
+
+	spinlock_t			write_lock;
+	wait_queue_head_t		sb_wait;	/* for waiting on superblock updates */
+	atomic_t			pending_writes;	/* number of active superblock writes */
+
+	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; 
+	struct request_queue		*queue;	/* for plugging ... */
+
+	atomic_t                        write_behind; /* outstanding async IO */
+	unsigned int                    max_write_behind; /* 0 = sync */
+
+	struct bitmap                   *bitmap; /* the bitmap for the device */
+	struct file			*bitmap_file; /* the bitmap file */
+	long				bitmap_offset; /* offset from superblock of
+							* start of bitmap. May be
+							* negative, but not '0'
+							*/
+	long				default_bitmap_offset; /* this is the offset to use when
+								* hot-adding a bitmap.  It should
+								* eventually be settable by sysfs.
+								*/
+
+	struct list_head		all_mddevs;
+};
+
+
+static inline void rdev_dec_pending(mdk_rdev_t *rdev, mddev_t *mddev)
+{
+	int faulty = test_bit(Faulty, &rdev->flags);
+	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
+{
+	char *name;
+	int level;
+	struct list_head list;
+	struct module *owner;
+	int (*make_request)(struct request_queue *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);
+	sector_t (*sync_request)(mddev_t *mddev, sector_t sector_nr, int *skipped, int go_faster);
+	int (*resize) (mddev_t *mddev, sector_t sectors);
+	int (*check_reshape) (mddev_t *mddev);
+	int (*start_reshape) (mddev_t *mddev);
+	int (*reconfig) (mddev_t *mddev, int layout, int chunk_size);
+	/* quiesce moves between quiescence states
+	 * 0 - fully active
+	 * 1 - no new requests allowed
+	 * others - reserved
+	 */
+	void (*quiesce) (mddev_t *mddev, int state);
+};
+
+
+struct md_sysfs_entry {
+	struct attribute attr;
+	ssize_t (*show)(mddev_t *, char *);
+	ssize_t (*store)(mddev_t *, const char *, size_t);
+};
+
+
+static inline char * mdname (mddev_t * mddev)
+{
+	return mddev->gendisk ? mddev->gendisk->disk_name : "mdX";
+}
+
+/*
+ * iterates through some rdev ringlist. It's safe to remove the
+ * current 'rdev'. Dont touch 'tmp' though.
+ */
+#define rdev_for_each_list(rdev, tmp, head)				\
+	list_for_each_entry_safe(rdev, tmp, head, same_set)
+
+/*
+ * iterates through the 'same array disks' ringlist
+ */
+#define rdev_for_each(rdev, tmp, mddev)				\
+	list_for_each_entry_safe(rdev, tmp, &((mddev)->disks), same_set)
+
+#define rdev_for_each_rcu(rdev, mddev)				\
+	list_for_each_entry_rcu(rdev, &((mddev)->disks), same_set)
+
+typedef struct mdk_thread_s {
+	void			(*run) (mddev_t *mddev);
+	mddev_t			*mddev;
+	wait_queue_head_t	wqueue;
+	unsigned long           flags;
+	struct task_struct	*tsk;
+	unsigned long		timeout;
+} 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)
+
+static inline void safe_put_page(struct page *p)
+{
+	if (p) put_page(p);
+}
+
+#endif /* CONFIG_BLOCK */
+#endif
+
+
+extern int register_md_personality(struct mdk_personality *p);
+extern int unregister_md_personality(struct mdk_personality *p);
+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, struct bio *bi);
+extern void md_write_end(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_super_write(mddev_t *mddev, mdk_rdev_t *rdev,
+			   sector_t sector, int size, struct page *page);
+extern void md_super_wait(mddev_t *mddev);
+extern int sync_page_io(struct block_device *bdev, sector_t sector, int size,
+			struct page *page, int rw);
+extern void md_do_sync(mddev_t *mddev);
+extern void md_new_event(mddev_t *mddev);
+extern int md_allow_write(mddev_t *mddev);
+extern void md_wait_for_blocked_rdev(mdk_rdev_t *rdev, mddev_t *mddev);
diff --git a/drivers/md/multipath.c b/drivers/md/multipath.c
index 148b3cd058bf..0ed1005afb58 100644
--- a/drivers/md/multipath.c
+++ b/drivers/md/multipath.c
@@ -21,8 +21,8 @@
 
 #include <linux/blkdev.h>
 #include <linux/raid/md_u.h>
-#include <linux/raid/md_k.h>
 #include <linux/seq_file.h>
+#include "md.h"
 #include "multipath.h"
 
 #define MAX_WORK_PER_DISK 128
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index 64e4c77a1568..3d06df86da87 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -19,8 +19,8 @@
 */
 
 #include <linux/blkdev.h>
-#include <linux/raid/md_k.h>
 #include <linux/seq_file.h>
+#include "md.h"
 #include "raid0.h"
 
 static void raid0_unplug(struct request_queue *q)
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 253b09c86eca..051ecfa61514 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -33,8 +33,8 @@
 
 #include <linux/delay.h>
 #include <linux/blkdev.h>
-#include <linux/raid/md_k.h>
 #include <linux/seq_file.h>
+#include "md.h"
 #include "dm-bio-list.h"
 #include "raid1.h"
 #include "bitmap.h"
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 186e1b199d46..fea61e3dcd95 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -20,8 +20,8 @@
 
 #include <linux/delay.h>
 #include <linux/blkdev.h>
-#include <linux/raid/md_k.h>
 #include <linux/seq_file.h>
+#include "md.h"
 #include "dm-bio-list.h"
 #include "raid10.h"
 #include "bitmap.h"
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 816157e7d8e0..849478e9afdc 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -44,10 +44,10 @@
  */
 
 #include <linux/blkdev.h>
-#include <linux/raid/md_k.h>
 #include <linux/kthread.h>
 #include <linux/async_tx.h>
 #include <linux/seq_file.h>
+#include "md.h"
 #include "raid5.h"
 #include "raid6.h"
 #include "bitmap.h"