include/linux/ncp.h


1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201

/*
 *  ncp.h
 *
 *  Copyright (C) 1995 by Volker Lendecke
 *  Modified for sparc by J.F. Chadima
 *  Modified for __constant_ntoh by Frank A. Vorstenbosch
 *
 */

#ifndef _LINUX_NCP_H
#define _LINUX_NCP_H

#include <linux/types.h>

#define NCP_PTYPE                (0x11)
#define NCP_PORT                 (0x0451)

#define NCP_ALLOC_SLOT_REQUEST   (0x1111)
#define NCP_REQUEST              (0x2222)
#define NCP_DEALLOC_SLOT_REQUEST (0x5555)

struct ncp_request_header {
	__u16 type;
	__u8 sequence;
	__u8 conn_low;
	__u8 task;
	__u8 conn_high;
	__u8 function;
	__u8 data[0];
} __attribute__((packed));

#define NCP_REPLY                (0x3333)
#define NCP_WATCHDOG		 (0x3E3E)
#define NCP_POSITIVE_ACK         (0x9999)

struct ncp_reply_header {
	__u16 type;
	__u8 sequence;
	__u8 conn_low;
	__u8 task;
	__u8 conn_high;
	__u8 completion_code;
	__u8 connection_state;
	__u8 data[0];
} __attribute__((packed));

#define NCP_VOLNAME_LEN (16)
#define NCP_NUMBER_OF_VOLUMES (256)
struct ncp_volume_info {
	__u32 total_blocks;
	__u32 free_blocks;
	__u32 purgeable_blocks;
	__u32 not_yet_purgeable_blocks;
	__u32 total_dir_entries;
	__u32 available_dir_entries;
	__u8 sectors_per_block;
	char volume_name[NCP_VOLNAME_LEN + 1];
};

#define AR_READ      (cpu_to_le16(1))
#define AR_WRITE     (cpu_to_le16(2))
#define AR_EXCLUSIVE (cpu_to_le16(0x20))

#define NCP_FILE_ID_LEN 6

/* Defines for Name Spaces */
#define NW_NS_DOS     0
#define NW_NS_MAC     1
#define NW_NS_NFS     2
#define NW_NS_FTAM    3
#define NW_NS_OS2     4

/*  Defines for ReturnInformationMask */
#define RIM_NAME	      (cpu_to_le32(1))
#define RIM_SPACE_ALLOCATED   (cpu_to_le32(2))
#define RIM_ATTRIBUTES	      (cpu_to_le32(4))
#define RIM_DATA_SIZE	      (cpu_to_le32(8))
#define RIM_TOTAL_SIZE	      (cpu_to_le32(0x10))
#define RIM_EXT_ATTR_INFO     (cpu_to_le32(0x20))
#define RIM_ARCHIVE	      (cpu_to_le32(0x40))
#define RIM_MODIFY	      (cpu_to_le32(0x80))
#define RIM_CREATION	      (cpu_to_le32(0x100))
#define RIM_OWNING_NAMESPACE  (cpu_to_le32(0x200))
#define RIM_DIRECTORY	      (cpu_to_le32(0x400))
#define RIM_RIGHTS	      (cpu_to_le32(0x800))
#define RIM_ALL 	      (cpu_to_le32(0xFFF))
#define RIM_COMPRESSED_INFO   (cpu_to_le32(0x80000000))

/* Defines for NSInfoBitMask */
#define NSIBM_NFS_NAME		0x0001
#define NSIBM_NFS_MODE		0x0002
#define NSIBM_NFS_GID		0x0004
#define NSIBM_NFS_NLINKS	0x0008
#define NSIBM_NFS_RDEV		0x0010
#define NSIBM_NFS_LINK		0x0020
#define NSIBM_NFS_CREATED	0x0040
#define NSIBM_NFS_UID		0x0080
#define NSIBM_NFS_ACSFLAG	0x0100
#define NSIBM_NFS_MYFLAG	0x0200

/* open/create modes */
#define OC_MODE_OPEN	  0x01
#define OC_MODE_TRUNCATE  0x02
#define OC_MODE_REPLACE   0x02
#define OC_MODE_CREATE	  0x08

/* open/create results */
#define OC_ACTION_NONE	   0x00
#define OC_ACTION_OPEN	   0x01
#define OC_ACTION_CREATE   0x02
#define OC_ACTION_TRUNCATE 0x04
#define OC_ACTION_REPLACE  0x04

/* access rights attributes */
#ifndef AR_READ_ONLY
#define AR_READ_ONLY	   0x0001
#define AR_WRITE_ONLY	   0x0002
#define AR_DENY_READ	   0x0004
#define AR_DENY_WRITE	   0x0008
#define AR_COMPATIBILITY   0x0010
#define AR_WRITE_THROUGH   0x0040
#define AR_OPEN_COMPRESSED 0x0100
#endif

struct nw_nfs_info {
	__u32 mode;
	__u32 rdev;
};

struct nw_info_struct {
	__u32 spaceAlloc;
	__le32 attributes;
	__u16 flags;
	__le32 dataStreamSize;
	__le32 totalStreamSize;
	__u16 numberOfStreams;
	__le16 creationTime;
	__le16 creationDate;
	__u32 creatorID;
	__le16 modifyTime;
	__le16 modifyDate;
	__u32 modifierID;
	__le16 lastAccessDate;
	__u16 archiveTime;
	__u16 archiveDate;
	__u32 archiverID;
	__u16 inheritedRightsMask;
	__le32 dirEntNum;
	__le32 DosDirNum;
	__u32 volNumber;
	__u32 EADataSize;
	__u32 EAKeyCount;
	__u32 EAKeySize;
	__u32 NSCreator;
	__u8 nameLen;
	__u8 entryName[256];
	/* libncp may depend on there being nothing after entryName */
#ifdef __KERNEL__
	struct nw_nfs_info nfs;
#endif
} __attribute__((packed));

/* modify mask - use with MODIFY_DOS_INFO structure */
#define DM_ATTRIBUTES		  (cpu_to_le32(0x02))
#define DM_CREATE_DATE		  (cpu_to_le32(0x04))
#define DM_CREATE_TIME		  (cpu_to_le32(0x08))
#define DM_CREATOR_ID		  (cpu_to_le32(0x10))
#define DM_ARCHIVE_DATE 	  (cpu_to_le32(0x20))
#define DM_ARCHIVE_TIME 	  (cpu_to_le32(0x40))
#define DM_ARCHIVER_ID		  (cpu_to_le32(0x80))
#define DM_MODIFY_DATE		  (cpu_to_le32(0x0100))
#define DM_MODIFY_TIME		  (cpu_to_le32(0x0200))
#define DM_MODIFIER_ID		  (cpu_to_le32(0x0400))
#define DM_LAST_ACCESS_DATE	  (cpu_to_le32(0x0800))
#define DM_INHERITED_RIGHTS_MASK  (cpu_to_le32(0x1000))
#define DM_MAXIMUM_SPACE	  (cpu_to_le32(0x2000))

struct nw_modify_dos_info {
	__le32 attributes;
	__le16 creationDate;
	__le16 creationTime;
	__u32 creatorID;
	__le16 modifyDate;
	__le16 modifyTime;
	__u32 modifierID;
	__u16 archiveDate;
	__u16 archiveTime;
	__u32 archiverID;
	__le16 lastAccessDate;
	__u16 inheritanceGrantMask;
	__u16 inheritanceRevokeMask;
	__u32 maximumSpace;
} __attribute__((packed));

struct nw_search_sequence {
	__u8 volNumber;
	__u32 dirBase;
	__u32 sequence;
} __attribute__((packed));

#endif				/* _LINUX_NCP_H */
/*
 * linux/fs/mbcache.c
 * (C) 2001-2002 Andreas Gruenbacher, <a.gruenbacher@computer.org>
 */

/*
 * Filesystem Meta Information Block Cache (mbcache)
 *
 * The mbcache caches blocks of block devices that need to be located
 * by their device/block number, as well as by other criteria (such
 * as the block's contents).
 *
 * There can only be one cache entry in a cache per device and block number.
 * Additional indexes need not be unique in this sense. The number of
 * additional indexes (=other criteria) can be hardwired at compile time
 * or specified at cache create time.
 *
 * Each cache entry is of fixed size. An entry may be `valid' or `invalid'
 * in the cache. A valid entry is in the main hash tables of the cache,
 * and may also be in the lru list. An invalid entry is not in any hashes
 * or lists.
 *
 * A valid cache entry is only in the lru list if no handles refer to it.
 * Invalid cache entries will be freed when the last handle to the cache
 * entry is released. Entries that cannot be freed immediately are put
 * back on the lru list.
 */

#include <linux/kernel.h>
#include <linux/module.h>

#include <linux/hash.h>
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/sched.h>
#include <linux/init.h>
#include <linux/mbcache.h>


#ifdef MB_CACHE_DEBUG
# define mb_debug(f...) do { \
		printk(KERN_DEBUG f); \
		printk("\n"); \
	} while (0)
#define mb_assert(c) do { if (!(c)) \
		printk(KERN_ERR "assertion " #c " failed\n"); \
	} while(0)
#else
# define mb_debug(f...) do { } while(0)
# define mb_assert(c) do { } while(0)
#endif
#define mb_error(f...) do { \
		printk(KERN_ERR f); \
		printk("\n"); \
	} while(0)

#define MB_CACHE_WRITER ((unsigned short)~0U >> 1)

static DECLARE_WAIT_QUEUE_HEAD(mb_cache_queue);
		
MODULE_AUTHOR("Andreas Gruenbacher <a.gruenbacher@computer.org>");
MODULE_DESCRIPTION("Meta block cache (for extended attributes)");
MODULE_LICENSE("GPL");

EXPORT_SYMBOL(mb_cache_create);
EXPORT_SYMBOL(mb_cache_shrink);
EXPORT_SYMBOL(mb_cache_destroy);
EXPORT_SYMBOL(mb_cache_entry_alloc);
EXPORT_SYMBOL(mb_cache_entry_insert);
EXPORT_SYMBOL(mb_cache_entry_release);
EXPORT_SYMBOL(mb_cache_entry_free);
EXPORT_SYMBOL(mb_cache_entry_get);
#if !defined(MB_CACHE_INDEXES_COUNT) || (MB_CACHE_INDEXES_COUNT > 0)
EXPORT_SYMBOL(mb_cache_entry_find_first);
EXPORT_SYMBOL(mb_cache_entry_find_next);
#endif

struct mb_cache {
	struct list_head		c_cache_list;
	const char			*c_name;
	struct mb_cache_op		c_op;
	atomic_t			c_entry_count;
	int				c_bucket_bits;
#ifndef MB_CACHE_INDEXES_COUNT
	int				c_indexes_count;
#endif
	kmem_cache_t			*c_entry_cache;
	struct list_head		*c_block_hash;
	struct list_head		*c_indexes_hash[0];
};


/*
 * Global data: list of all mbcache's, lru list, and a spinlock for
 * accessing cache data structures on SMP machines. The lru list is
 * global across all mbcaches.
 */

static LIST_HEAD(mb_cache_list);
static LIST_HEAD(mb_cache_lru_list);
static DEFINE_SPINLOCK(mb_cache_spinlock);
static struct shrinker *mb_shrinker;

static inline int
mb_cache_indexes(struct mb_cache *cache)
{
#ifdef MB_CACHE_INDEXES_COUNT
	return MB_CACHE_INDEXES_COUNT;
#else
	return cache->c_indexes_count;
#endif
}

/*
 * What the mbcache registers as to get shrunk dynamically.
 */

static int mb_cache_shrink_fn(int nr_to_scan, gfp_t gfp_mask);


static inline int
__mb_cache_entry_is_hashed(struct mb_cache_entry *ce)
{
	return !list_empty(&ce->e_block_list);
}


static void
__mb_cache_entry_unhash(struct mb_cache_entry *ce)
{
	int n;

	if (__mb_cache_entry_is_hashed(ce)) {
		list_del_init(&ce->e_block_list);
		for (n=0; n<mb_cache_indexes(ce->e_cache); n++)
			list_del(&ce->e_indexes[n].o_list);
	}
}


static void
__mb_cache_entry_forget(struct mb_cache_entry *ce, gfp_t gfp_mask)
{
	struct mb_cache *cache = ce->e_cache;

	mb_assert(!(ce->e_used || ce->e_queued));
	if (cache->c_op.free && cache->c_op.free(ce, gfp_mask)) {
		/* free failed -- put back on the lru list
		   for freeing later. */
		spin_lock(&mb_cache_spinlock);
		list_add(&ce->e_lru_list, &mb_cache_lru_list);
		spin_unlock(&mb_cache_spinlock);
	} else {
		kmem_cache_free(cache->c_entry_cache, ce);
		atomic_dec(&cache->c_entry_count);
	}
}


static void
__mb_cache_entry_release_unlock(struct mb_cache_entry *ce)
{
	/* Wake up all processes queuing for this cache entry. */
	if (ce->e_queued)
		wake_up_all(&mb_cache_queue);
	if (ce->e_used >= MB_CACHE_WRITER)
		ce->e_used -= MB_CACHE_WRITER;
	ce->e_used--;
	if (!(ce->e_used || ce->e_queued)) {
		if (!__mb_cache_entry_is_hashed(ce))
			goto forget;
		mb_assert(list_empty(&ce->e_lru_list));
		list_add_tail(&ce->e_lru_list, &mb_cache_lru_list);
	}
	spin_unlock(&mb_cache_spinlock);
	return;
forget:
	spin_unlock(&mb_cache_spinlock);
	__mb_cache_entry_forget(ce, GFP_KERNEL);
}


/*
 * mb_cache_shrink_fn()  memory pressure callback
 *
 * This function is called by the kernel memory management when memory
 * gets low.
 *
 * @nr_to_scan: Number of objects to scan
 * @gfp_mask: (ignored)
 *
 * Returns the number of objects which are present in the cache.
 */
static int
mb_cache_shrink_fn(int nr_to_scan, gfp_t gfp_mask)
{
	LIST_HEAD(free_list);
	struct list_head *l, *ltmp;
	int count = 0;

	spin_lock(&mb_cache_spinlock);
	list_for_each(l, &mb_cache_list) {
		struct mb_cache *cache =
			list_entry(l, struct mb_cache, c_cache_list);
		mb_debug("cache %s (%d)", cache->c_name,
			  atomic_read(&cache->c_entry_count));
		count += atomic_read(&cache->c_entry_count);
	}
	mb_debug("trying to free %d entries", nr_to_scan);
	if (nr_to_scan == 0) {
		spin_unlock(&mb_cache_spinlock);
		goto out;
	}
	while (nr_to_scan-- && !list_empty(&mb_cache_lru_list)) {
		struct mb_cache_entry *ce =
			list_entry(mb_cache_lru_list.next,
				   struct mb_cache_entry, e_lru_list);
		list_move_tail(&ce->e_lru_list, &free_list);
		__mb_cache_entry_unhash(ce);
	}
	spin_unlock(&mb_cache_spinlock);
	list_for_each_safe(l, ltmp, &free_list) {
		__mb_cache_entry_forget(list_entry(l, struct mb_cache_entry,
						   e_lru_list), gfp_mask);
	}
out:
	return (count / 100) * sysctl_vfs_cache_pressure;
}


/*
 * mb_cache_create()  create a new cache
 *
 * All entries in one cache are equal size. Cache entries may be from
 * multiple devices. If this is the first mbcache created, registers
 * the cache with kernel memory management. Returns NULL if no more
 * memory was available.
 *
 * @name: name of the cache (informal)
 * @cache_op: contains the callback called when freeing a cache entry
 * @entry_size: The size of a cache entry, including
 *              struct mb_cache_entry
 * @indexes_count: number of additional indexes in the cache. Must equal
 *                 MB_CACHE_INDEXES_COUNT if the number of indexes is
 *                 hardwired.
 * @bucket_bits: log2(number of hash buckets)
 */
struct mb_cache *
mb_cache_create(const char *name, struct mb_cache_op *cache_op,
		size_t entry_size, int indexes_count, int bucket_bits)
{
	int m=0, n, bucket_count = 1 << bucket_bits;
	struct mb_cache *cache = NULL;

	if(entry_size < sizeof(struct mb_cache_entry) +
	   indexes_count * sizeof(((struct mb_cache_entry *) 0)->e_indexes[0]))
		return NULL;

	cache = kmalloc(sizeof(struct mb_cache) +
	                indexes_count * sizeof(struct list_head), GFP_KERNEL);
	if (!cache)
		goto fail;
	cache->c_name = name;
	cache->c_op.free = NULL;
	if (cache_op)
		cache->c_op.free = cache_op->free;
	atomic_set(&cache->c_entry_count, 0);
	cache->c_bucket_bits = bucket_bits;
#ifdef MB_CACHE_INDEXES_COUNT
	mb_assert(indexes_count == MB_CACHE_INDEXES_COUNT);
#else
	cache->c_indexes_count = indexes_count;
#endif
	cache->c_block_hash = kmalloc(bucket_count * sizeof(struct list_head),
	                              GFP_KERNEL);
	if (!cache->c_block_hash)
		goto fail;
	for (n=0; n<bucket_count; n++)
		INIT_LIST_HEAD(&cache->c_block_hash[n]);
	for (m=0; m<indexes_count; m++) {
		cache->c_indexes_hash[m] = kmalloc(bucket_count *
		                                 sizeof(struct list_head),
		                                 GFP_KERNEL);
		if (!cache->c_indexes_hash[m])
			goto fail;
		for (n=0; n<bucket_count; n++)
			INIT_LIST_HEAD(&cache->c_indexes_hash[m][n]);
	}
	cache->c_entry_cache = kmem_cache_create(name, entry_size, 0,
		SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD, NULL, NULL);
	if (!cache->c_entry_cache)
		goto fail;

	spin_lock(&mb_cache_spinlock);
	list_add(&cache->c_cache_list, &mb_cache_list);
	spin_unlock(&mb_cache_spinlock);
	return cache;

fail:
	if (cache) {
		while (--m >= 0)
			kfree(cache->c_indexes_hash[m]);
		kfree(cache->c_block_hash);
		kfree(cache);
	}
	return NULL;
}


/*
 * mb_cache_shrink()
 *
 * Removes all cache entries of a device from the cache. All cache entries
 * currently in use cannot be freed, and thus remain in the cache. All others
 * are freed.
 *
 * @bdev: which device's cache entries to shrink
 */
void
mb_cache_shrink(struct block_device *bdev)
{
	LIST_HEAD(free_list);
	struct list_head *l, *ltmp;

	spin_lock(&mb_cache_spinlock);
	list_for_each_safe(l, ltmp, &mb_cache_lru_list) {
		struct mb_cache_entry *ce =
			list_entry(l, struct mb_cache_entry, e_lru_list);
		if (ce->e_bdev == bdev) {
			list_move_tail(&ce->e_lru_list, &free_list);
			__mb_cache_entry_unhash(ce);
		}
	}
	spin_unlock(&mb_cache_spinlock);
	list_for_each_safe(l, ltmp, &free_list) {
		__mb_cache_entry_forget(list_entry(l, struct mb_cache_entry,
						   e_lru_list), GFP_KERNEL);
	}
}


/*
 * mb_cache_destroy()
 *
 * Shrinks the cache to its minimum possible size (hopefully 0 entries),
 * and then destroys it. If this was the last mbcache, un-registers the
 * mbcache from kernel memory management.
 */
void
mb_cache_destroy(struct mb_cache *cache)
{
	LIST_HEAD(free_list);
	struct list_head *l, *ltmp;
	int n;

	spin_lock(&mb_cache_spinlock);
	list_for_each_safe(l, ltmp, &mb_cache_lru_list) {
		struct mb_cache_entry *ce =
			list_entry(l, struct mb_cache_entry, e_lru_list);
		if (ce->e_cache == cache) {
			list_move_tail(&ce->e_lru_list, &free_list);
			__mb_cache_entry_unhash(ce);
		}
	}
	list_del(&cache->c_cache_list);
	spin_unlock(&mb_cache_spinlock);

	list_for_each_safe(l, ltmp, &free_list) {
		__mb_cache_entry_forget(list_entry(l, struct mb_cache_entry,
						   e_lru_list), GFP_KERNEL);
	}

	if (atomic_read(&cache->c_entry_count) > 0) {
		mb_error("cache %s: %d orphaned entries",
			  cache->c_name,
			  atomic_read(&cache->c_entry_count));
	}

	kmem_cache_destroy(cache->c_entry_cache);

	for (n=0; n < mb_cache_indexes(cache); n++)
		kfree(cache->c_indexes_hash[n]);
	kfree(cache->c_block_hash);
	kfree(cache);
}


/*
 * mb_cache_entry_alloc()
 *
 * Allocates a new cache entry. The new entry will not be valid initially,
 * and thus cannot be looked up yet. It should be filled with data, and
 * then inserted into the cache using mb_cache_entry_insert(). Returns NULL
 * if no more memory was available.
 */
struct mb_cache_entry *
mb_cache_entry_alloc(struct mb_cache *cache)
{
	struct mb_cache_entry *ce;

	atomic_inc(&cache->c_entry_count);
	ce = kmem_cache_alloc(cache->c_entry_cache, GFP_KERNEL);
	if (ce) {
		INIT_LIST_HEAD(&ce->e_lru_list);
		INIT_LIST_HEAD(&ce->e_block_list);
		ce->e_cache = cache;
		ce->e_used = 1 + MB_CACHE_WRITER;
		ce->e_queued = 0;
	}
	return ce;
}


/*
 * mb_cache_entry_insert()
 *
 * Inserts an entry that was allocated using mb_cache_entry_alloc() into
 * the cache. After this, the cache entry can be looked up, but is not yet
 * in the lru list as the caller still holds a handle to it. Returns 0 on
 * success, or -EBUSY if a cache entry for that device + inode exists
 * already (this may happen after a failed lookup, but when another process
 * has inserted the same cache entry in the meantime).
 *
 * @bdev: device the cache entry belongs to
 * @block: block number
 * @keys: array of additional keys. There must be indexes_count entries
 *        in the array (as specified when creating the cache).
 */
int
mb_cache_entry_insert(struct mb_cache_entry *ce, struct block_device *bdev,
		      sector_t block, unsigned int keys[])
{
	struct mb_cache *cache = ce->e_cache;
	unsigned int bucket;
	struct list_head *l;
	int error = -EBUSY, n;

	bucket = hash_long((unsigned long)bdev + (block & 0xffffffff), 
			   cache->c_bucket_bits);
	spin_lock(&mb_cache_spinlock);
	list_for_each_prev(l, &cache->c_block_hash[bucket]) {
		struct mb_cache_entry *ce =
			list_entry(l, struct mb_cache_entry, e_block_list);
		if (ce->e_bdev == bdev && ce->e_block == block)
			goto out;
	}
	__mb_cache_entry_unhash(ce);
	ce->e_bdev = bdev;
	ce->e_block = block;
	list_add(&ce->e_block_list, &cache->c_block_hash[bucket]);
	for (n=0; n<mb_cache_indexes(cache); n++) {
		ce->e_indexes[n].o_key = keys[n];
		bucket = hash_long(keys[n], cache->c_bucket_bits);
		list_add(&ce->e_indexes[n].o_list,
			 &cache->c_indexes_hash[n][bucket]);
	}
	error = 0;
out:
	spin_unlock(&mb_cache_spinlock);
	return error;
}


/*
 * mb_cache_entry_release()
 *
 * Release a handle to a cache entry. When the last handle to a cache entry
 * is released it is either freed (if it is invalid) or otherwise inserted
 * in to the lru list.
 */
void
mb_cache_entry_release(struct mb_cache_entry *ce)
{
	spin_lock(&mb_cache_spinlock);
	__mb_cache_entry_release_unlock(ce);
}


/*
 * mb_cache_entry_free()
 *
 * This is equivalent to the sequence mb_cache_entry_takeout() --
 * mb_cache_entry_release().
 */
void
mb_cache_entry_free(struct mb_cache_entry *ce)
{
	spin_lock(&mb_cache_spinlock);
	mb_assert(list_empty(&ce->e_lru_list));
	__mb_cache_entry_unhash(ce);
	__mb_cache_entry_release_unlock(ce);
}


/*
 * mb_cache_entry_get()
 *
 * Get a cache entry  by device / block number. (There can only be one entry
 * in the cache per device and block.) Returns NULL if no such cache entry
 * exists. The returned cache entry is locked for exclusive access ("single
 * writer").
 */
struct mb_cache_entry *
mb_cache_entry_get(struct mb_cache *cache, struct block_device *bdev,
		   sector_t block)
{
	unsigned int bucket;
	struct list_head *l;
	struct mb_cache_entry *ce;

	bucket = hash_long((unsigned long)bdev + (block & 0xffffffff),
			   cache->c_bucket_bits);
	spin_lock(&mb_cache_spinlock);
	list_for_each(l, &cache->c_block_hash[bucket]) {
		ce = list_entry(l, struct mb_cache_entry, e_block_list);
		if (ce->e_bdev == bdev && ce->e_block == block) {
			DEFINE_WAIT(wait);

			if (!list_empty(&ce->e_lru_list))
				list_del_init(&ce->e_lru_list);

			while (ce->e_used > 0) {
				ce->e_queued++;
				prepare_to_wait(&mb_cache_queue, &wait,
						TASK_UNINTERRUPTIBLE);
				spin_unlock(&mb_cache_spinlock);
				schedule();
				spin_lock(&mb_cache_spinlock);
				ce->e_queued--;
			}
			finish_wait(&mb_cache_queue, &wait);
			ce->e_used += 1 + MB_CACHE_WRITER;

			if (!__mb_cache_entry_is_hashed(ce)) {
				__mb_cache_entry_release_unlock(ce);
				return NULL;
			}
			goto cleanup;
		}
	}
	ce = NULL;

cleanup:
	spin_unlock(&mb_cache_spinlock);
	return ce;
}

#if !defined(MB_CACHE_INDEXES_COUNT) || (MB_CACHE_INDEXES_COUNT > 0)

static struct mb_cache_entry *
__mb_cache_entry_find(struct list_head *l, struct list_head *head,
		      int index, struct block_device *bdev, unsigned int key)
{
	while (l != head) {
		struct mb_cache_entry *ce =
			list_entry(l, struct mb_cache_entry,
			           e_indexes[index].o_list);
		if (ce->e_bdev == bdev && ce->e_indexes[index].o_key == key) {
			DEFINE_WAIT(wait);

			if (!list_empty(&ce->e_lru_list))
				list_del_init(&ce->e_lru_list);

			/* Incrementing before holding the lock gives readers
			   priority over writers. */
			ce->e_used++;
			while (ce->e_used >= MB_CACHE_WRITER) {
				ce->e_queued++;
				prepare_to_wait(&mb_cache_queue, &wait,
						TASK_UNINTERRUPTIBLE);
				spin_unlock(&mb_cache_spinlock);
				schedule();
				spin_lock(&mb_cache_spinlock);
				ce->e_queued--;
			}
			finish_wait(&mb_cache_queue, &wait);

			if (!__mb_cache_entry_is_hashed(ce)) {
				__mb_cache_entry_release_unlock(ce);
				spin_lock(&mb_cache_spinlock);
				return ERR_PTR(-EAGAIN);
			}
			return ce;
		}
		l = l->next;
	}
	return NULL;
}


/*
 * mb_cache_entry_find_first()
 *
 * Find the first cache entry on a given device with a certain key in
 * an additional index. Additonal matches can be found with
 * mb_cache_entry_find_next(). Returns NULL if no match was found. The
 * returned cache entry is locked for shared access ("multiple readers").
 *
 * @cache: the cache to search
 * @index: the number of the additonal index to search (0<=index<indexes_count)
 * @bdev: the device the cache entry should belong to
 * @key: the key in the index
 */
struct mb_cache_entry *
mb_cache_entry_find_first(struct mb_cache *cache, int index,
			  struct block_device *bdev, unsigned int key)
{
	unsigned int bucket = hash_long(key, cache->c_bucket_bits);
	struct list_head *l;
	struct mb_cache_entry *ce;

	mb_assert(index < mb_cache_indexes(cache));
	spin_lock(&mb_cache_spinlock);
	l = cache->c_indexes_hash[index][bucket].next;
	ce = __mb_cache_entry_find(l, &cache->c_indexes_hash[index][bucket],
	                           index, bdev, key);
	spin_unlock(&mb_cache_spinlock);
	return ce;
}


/*
 * mb_cache_entry_find_next()
 *
 * Find the next cache entry on a given device with a certain key in an
 * additional index. Returns NULL if no match could be found. The previous
 * entry is atomatically released, so that mb_cache_entry_find_next() can
 * be called like this:
 *
 * entry = mb_cache_entry_find_first();
 * while (entry) {
 * 	...
 *	entry = mb_cache_entry_find_next(entry, ...);
 * }
 *
 * @prev: The previous match
 * @index: the number of the additonal index to search (0<=index<indexes_count)
 * @bdev: the device the cache entry should belong to
 * @key: the key in the index
 */
struct mb_cache_entry *
mb_cache_entry_find_next(struct mb_cache_entry *prev, int index,
			 struct block_device *bdev, unsigned int key)
{
	struct mb_cache *cache = prev->e_cache;
	unsigned int bucket = hash_long(key, cache->c_bucket_bits);
	struct list_head *l;
	struct mb_cache_entry *ce;

	mb_assert(index < mb_cache_indexes(cache));
	spin_lock(&mb_cache_spinlock);
	l = prev->e_indexes[index].o_list.next;
	ce = __mb_cache_entry_find(l, &cache->c_indexes_hash[index][bucket],
	                           index, bdev, key);
	__mb_cache_entry_release_unlock(prev);
	return ce;
}

#endif  /* !defined(MB_CACHE_INDEXES_COUNT) || (MB_CACHE_INDEXES_COUNT > 0) */

static int __init init_mbcache(void)
{
	mb_shrinker = set_shrinker(DEFAULT_SEEKS, mb_cache_shrink_fn);
	return 0;
}

static void __exit exit_mbcache(void)
{
	remove_shrinker(mb_shrinker);
}

module_init(init_mbcache)
module_exit(exit_mbcache)