obj-$(CONFIG_BINFMT_ELF_FDPIC) += binfmt_elf_fdpic.o
obj-$(CONFIG_BINFMT_FLAT) += binfmt_flat.o
-obj-$(CONFIG_FS_MBCACHE) += mbcache2.o
+obj-$(CONFIG_FS_MBCACHE) += mbcache.o
obj-$(CONFIG_FS_POSIX_ACL) += posix_acl.o
obj-$(CONFIG_NFS_COMMON) += nfs_common/
obj-$(CONFIG_COREDUMP) += coredump.o
#define rsv_start rsv_window._rsv_start
#define rsv_end rsv_window._rsv_end
-struct mb2_cache;
+struct mb_cache;
/*
* second extended-fs super-block data in memory
* of the mount options.
*/
spinlock_t s_lock;
- struct mb2_cache *s_mb_cache;
+ struct mb_cache *s_mb_cache;
};
static inline spinlock_t *
#include <linux/buffer_head.h>
#include <linux/init.h>
#include <linux/slab.h>
-#include <linux/mbcache2.h>
+#include <linux/mbcache.h>
#include <linux/quotaops.h>
#include <linux/rwsem.h>
#include <linux/security.h>
static int ext2_xattr_set2(struct inode *, struct buffer_head *,
struct ext2_xattr_header *);
-static int ext2_xattr_cache_insert(struct mb2_cache *, struct buffer_head *);
+static int ext2_xattr_cache_insert(struct mb_cache *, struct buffer_head *);
static struct buffer_head *ext2_xattr_cache_find(struct inode *,
struct ext2_xattr_header *);
static void ext2_xattr_rehash(struct ext2_xattr_header *,
size_t name_len, size;
char *end;
int error;
- struct mb2_cache *ext2_mb_cache = EXT2_SB(inode->i_sb)->s_mb_cache;
+ struct mb_cache *ext2_mb_cache = EXT2_SB(inode->i_sb)->s_mb_cache;
ea_idebug(inode, "name=%d.%s, buffer=%p, buffer_size=%ld",
name_index, name, buffer, (long)buffer_size);
char *end;
size_t rest = buffer_size;
int error;
- struct mb2_cache *ext2_mb_cache = EXT2_SB(inode->i_sb)->s_mb_cache;
+ struct mb_cache *ext2_mb_cache = EXT2_SB(inode->i_sb)->s_mb_cache;
ea_idebug(inode, "buffer=%p, buffer_size=%ld",
buffer, (long)buffer_size);
* This must happen under buffer lock for
* ext2_xattr_set2() to reliably detect modified block
*/
- mb2_cache_entry_delete_block(EXT2_SB(sb)->s_mb_cache,
- hash, bh->b_blocknr);
+ mb_cache_entry_delete_block(EXT2_SB(sb)->s_mb_cache,
+ hash, bh->b_blocknr);
/* keep the buffer locked while modifying it. */
} else {
struct super_block *sb = inode->i_sb;
struct buffer_head *new_bh = NULL;
int error;
- struct mb2_cache *ext2_mb_cache = EXT2_SB(sb)->s_mb_cache;
+ struct mb_cache *ext2_mb_cache = EXT2_SB(sb)->s_mb_cache;
if (header) {
new_bh = ext2_xattr_cache_find(inode, header);
* This must happen under buffer lock for
* ext2_xattr_set2() to reliably detect freed block
*/
- mb2_cache_entry_delete_block(ext2_mb_cache,
- hash, old_bh->b_blocknr);
+ mb_cache_entry_delete_block(ext2_mb_cache,
+ hash, old_bh->b_blocknr);
/* Free the old block. */
ea_bdebug(old_bh, "freeing");
ext2_free_blocks(inode, old_bh->b_blocknr, 1);
* This must happen under buffer lock for ext2_xattr_set2() to
* reliably detect freed block
*/
- mb2_cache_entry_delete_block(EXT2_SB(inode->i_sb)->s_mb_cache,
- hash, bh->b_blocknr);
+ mb_cache_entry_delete_block(EXT2_SB(inode->i_sb)->s_mb_cache,
+ hash, bh->b_blocknr);
ext2_free_blocks(inode, EXT2_I(inode)->i_file_acl, 1);
get_bh(bh);
bforget(bh);
* Returns 0, or a negative error number on failure.
*/
static int
-ext2_xattr_cache_insert(struct mb2_cache *cache, struct buffer_head *bh)
+ext2_xattr_cache_insert(struct mb_cache *cache, struct buffer_head *bh)
{
__u32 hash = le32_to_cpu(HDR(bh)->h_hash);
int error;
- error = mb2_cache_entry_create(cache, GFP_NOFS, hash, bh->b_blocknr);
+ error = mb_cache_entry_create(cache, GFP_NOFS, hash, bh->b_blocknr);
if (error) {
if (error == -EBUSY) {
ea_bdebug(bh, "already in cache (%d cache entries)",
ext2_xattr_cache_find(struct inode *inode, struct ext2_xattr_header *header)
{
__u32 hash = le32_to_cpu(header->h_hash);
- struct mb2_cache_entry *ce;
- struct mb2_cache *ext2_mb_cache = EXT2_SB(inode->i_sb)->s_mb_cache;
+ struct mb_cache_entry *ce;
+ struct mb_cache *ext2_mb_cache = EXT2_SB(inode->i_sb)->s_mb_cache;
if (!header->h_hash)
return NULL; /* never share */
ea_idebug(inode, "looking for cached blocks [%x]", (int)hash);
again:
- ce = mb2_cache_entry_find_first(ext2_mb_cache, hash);
+ ce = mb_cache_entry_find_first(ext2_mb_cache, hash);
while (ce) {
struct buffer_head *bh;
* entry is still hashed is reliable.
*/
if (hlist_bl_unhashed(&ce->e_hash_list)) {
- mb2_cache_entry_put(ext2_mb_cache, ce);
+ mb_cache_entry_put(ext2_mb_cache, ce);
unlock_buffer(bh);
brelse(bh);
goto again;
} else if (!ext2_xattr_cmp(header, HDR(bh))) {
ea_bdebug(bh, "b_count=%d",
atomic_read(&(bh->b_count)));
- mb2_cache_entry_touch(ext2_mb_cache, ce);
- mb2_cache_entry_put(ext2_mb_cache, ce);
+ mb_cache_entry_touch(ext2_mb_cache, ce);
+ mb_cache_entry_put(ext2_mb_cache, ce);
return bh;
}
unlock_buffer(bh);
brelse(bh);
}
- ce = mb2_cache_entry_find_next(ext2_mb_cache, ce);
+ ce = mb_cache_entry_find_next(ext2_mb_cache, ce);
}
return NULL;
}
#define HASH_BUCKET_BITS 10
-struct mb2_cache *ext2_xattr_create_cache(void)
+struct mb_cache *ext2_xattr_create_cache(void)
{
- return mb2_cache_create(HASH_BUCKET_BITS);
+ return mb_cache_create(HASH_BUCKET_BITS);
}
-void ext2_xattr_destroy_cache(struct mb2_cache *cache)
+void ext2_xattr_destroy_cache(struct mb_cache *cache)
{
if (cache)
- mb2_cache_destroy(cache);
+ mb_cache_destroy(cache);
}
#define EXT2_XATTR_SIZE(size) \
(((size) + EXT2_XATTR_ROUND) & ~EXT2_XATTR_ROUND)
-struct mb2_cache;
+struct mb_cache;
# ifdef CONFIG_EXT2_FS_XATTR
extern void ext2_xattr_delete_inode(struct inode *);
-extern struct mb2_cache *ext2_xattr_create_cache(void);
-extern void ext2_xattr_destroy_cache(struct mb2_cache *cache);
+extern struct mb_cache *ext2_xattr_create_cache(void);
+extern void ext2_xattr_destroy_cache(struct mb_cache *cache);
extern const struct xattr_handler *ext2_xattr_handlers[];
{
}
-static inline void ext2_xattr_destroy_cache(struct mb2_cache *cache)
+static inline void ext2_xattr_destroy_cache(struct mb_cache *cache)
{
}
struct list_head s_es_list; /* List of inodes with reclaimable extents */
long s_es_nr_inode;
struct ext4_es_stats s_es_stats;
- struct mb2_cache *s_mb_cache;
+ struct mb_cache *s_mb_cache;
spinlock_t s_es_lock ____cacheline_aligned_in_smp;
/* Ratelimit ext4 messages. */
#include <linux/init.h>
#include <linux/fs.h>
#include <linux/slab.h>
-#include <linux/mbcache2.h>
+#include <linux/mbcache.h>
#include <linux/quotaops.h>
#include "ext4_jbd2.h"
#include "ext4.h"
# define ea_bdebug(bh, fmt, ...) no_printk(fmt, ##__VA_ARGS__)
#endif
-static void ext4_xattr_cache_insert(struct mb2_cache *, struct buffer_head *);
+static void ext4_xattr_cache_insert(struct mb_cache *, struct buffer_head *);
static struct buffer_head *ext4_xattr_cache_find(struct inode *,
struct ext4_xattr_header *,
- struct mb2_cache_entry **);
+ struct mb_cache_entry **);
static void ext4_xattr_rehash(struct ext4_xattr_header *,
struct ext4_xattr_entry *);
static int ext4_xattr_list(struct dentry *dentry, char *buffer,
struct ext4_xattr_entry *entry;
size_t size;
int error;
- struct mb2_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode);
+ struct mb_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode);
ea_idebug(inode, "name=%d.%s, buffer=%p, buffer_size=%ld",
name_index, name, buffer, (long)buffer_size);
struct inode *inode = d_inode(dentry);
struct buffer_head *bh = NULL;
int error;
- struct mb2_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode);
+ struct mb_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode);
ea_idebug(inode, "buffer=%p, buffer_size=%ld",
buffer, (long)buffer_size);
* This must happen under buffer lock for
* ext4_xattr_block_set() to reliably detect freed block
*/
- mb2_cache_entry_delete_block(EXT4_GET_MB_CACHE(inode), hash,
- bh->b_blocknr);
+ mb_cache_entry_delete_block(EXT4_GET_MB_CACHE(inode), hash,
+ bh->b_blocknr);
get_bh(bh);
unlock_buffer(bh);
ext4_free_blocks(handle, inode, bh, 0, 1,
struct super_block *sb = inode->i_sb;
struct buffer_head *new_bh = NULL;
struct ext4_xattr_search *s = &bs->s;
- struct mb2_cache_entry *ce = NULL;
+ struct mb_cache_entry *ce = NULL;
int error = 0;
- struct mb2_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode);
+ struct mb_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode);
#define header(x) ((struct ext4_xattr_header *)(x))
* ext4_xattr_block_set() to reliably detect modified
* block
*/
- mb2_cache_entry_delete_block(ext4_mb_cache, hash,
- bs->bh->b_blocknr);
+ mb_cache_entry_delete_block(ext4_mb_cache, hash,
+ bs->bh->b_blocknr);
ea_bdebug(bs->bh, "modifying in-place");
error = ext4_xattr_set_entry(i, s);
if (!error) {
EXT4_C2B(EXT4_SB(sb),
1));
brelse(new_bh);
- mb2_cache_entry_put(ext4_mb_cache, ce);
+ mb_cache_entry_put(ext4_mb_cache, ce);
ce = NULL;
new_bh = NULL;
goto inserted;
if (error)
goto cleanup_dquot;
}
- mb2_cache_entry_touch(ext4_mb_cache, ce);
- mb2_cache_entry_put(ext4_mb_cache, ce);
+ mb_cache_entry_touch(ext4_mb_cache, ce);
+ mb_cache_entry_put(ext4_mb_cache, ce);
ce = NULL;
} else if (bs->bh && s->base == bs->bh->b_data) {
/* We were modifying this block in-place. */
cleanup:
if (ce)
- mb2_cache_entry_put(ext4_mb_cache, ce);
+ mb_cache_entry_put(ext4_mb_cache, ce);
brelse(new_bh);
if (!(bs->bh && s->base == bs->bh->b_data))
kfree(s->base);
* Returns 0, or a negative error number on failure.
*/
static void
-ext4_xattr_cache_insert(struct mb2_cache *ext4_mb_cache, struct buffer_head *bh)
+ext4_xattr_cache_insert(struct mb_cache *ext4_mb_cache, struct buffer_head *bh)
{
__u32 hash = le32_to_cpu(BHDR(bh)->h_hash);
int error;
- error = mb2_cache_entry_create(ext4_mb_cache, GFP_NOFS, hash,
- bh->b_blocknr);
+ error = mb_cache_entry_create(ext4_mb_cache, GFP_NOFS, hash,
+ bh->b_blocknr);
if (error) {
if (error == -EBUSY)
ea_bdebug(bh, "already in cache");
*/
static struct buffer_head *
ext4_xattr_cache_find(struct inode *inode, struct ext4_xattr_header *header,
- struct mb2_cache_entry **pce)
+ struct mb_cache_entry **pce)
{
__u32 hash = le32_to_cpu(header->h_hash);
- struct mb2_cache_entry *ce;
- struct mb2_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode);
+ struct mb_cache_entry *ce;
+ struct mb_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode);
if (!header->h_hash)
return NULL; /* never share */
ea_idebug(inode, "looking for cached blocks [%x]", (int)hash);
- ce = mb2_cache_entry_find_first(ext4_mb_cache, hash);
+ ce = mb_cache_entry_find_first(ext4_mb_cache, hash);
while (ce) {
struct buffer_head *bh;
return bh;
}
brelse(bh);
- ce = mb2_cache_entry_find_next(ext4_mb_cache, ce);
+ ce = mb_cache_entry_find_next(ext4_mb_cache, ce);
}
return NULL;
}
#define HASH_BUCKET_BITS 10
-struct mb2_cache *
+struct mb_cache *
ext4_xattr_create_cache(void)
{
- return mb2_cache_create(HASH_BUCKET_BITS);
+ return mb_cache_create(HASH_BUCKET_BITS);
}
-void ext4_xattr_destroy_cache(struct mb2_cache *cache)
+void ext4_xattr_destroy_cache(struct mb_cache *cache)
{
if (cache)
- mb2_cache_destroy(cache);
+ mb_cache_destroy(cache);
}
struct ext4_xattr_info *i,
struct ext4_xattr_ibody_find *is);
-extern struct mb2_cache *ext4_xattr_create_cache(void);
-extern void ext4_xattr_destroy_cache(struct mb2_cache *);
+extern struct mb_cache *ext4_xattr_create_cache(void);
+extern void ext4_xattr_destroy_cache(struct mb_cache *);
#ifdef CONFIG_EXT4_FS_SECURITY
extern int ext4_init_security(handle_t *handle, struct inode *inode,
--- /dev/null
+#include <linux/spinlock.h>
+#include <linux/slab.h>
+#include <linux/list.h>
+#include <linux/list_bl.h>
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/workqueue.h>
+#include <linux/mbcache.h>
+
+/*
+ * Mbcache is a simple key-value store. Keys need not be unique, however
+ * key-value pairs are expected to be unique (we use this fact in
+ * mb_cache_entry_delete_block()).
+ *
+ * Ext2 and ext4 use this cache for deduplication of extended attribute blocks.
+ * They use hash of a block contents as a key and block number as a value.
+ * That's why keys need not be unique (different xattr blocks may end up having
+ * the same hash). However block number always uniquely identifies a cache
+ * entry.
+ *
+ * We provide functions for creation and removal of entries, search by key,
+ * and a special "delete entry with given key-value pair" operation. Fixed
+ * size hash table is used for fast key lookups.
+ */
+
+struct mb_cache {
+ /* Hash table of entries */
+ struct hlist_bl_head *c_hash;
+ /* log2 of hash table size */
+ int c_bucket_bits;
+ /* Maximum entries in cache to avoid degrading hash too much */
+ int c_max_entries;
+ /* Protects c_list, c_entry_count */
+ spinlock_t c_list_lock;
+ struct list_head c_list;
+ /* Number of entries in cache */
+ unsigned long c_entry_count;
+ struct shrinker c_shrink;
+ /* Work for shrinking when the cache has too many entries */
+ struct work_struct c_shrink_work;
+};
+
+static struct kmem_cache *mb_entry_cache;
+
+static unsigned long mb_cache_shrink(struct mb_cache *cache,
+ unsigned int nr_to_scan);
+
+static inline bool mb_cache_entry_referenced(struct mb_cache_entry *entry)
+{
+ return entry->_e_hash_list_head & 1;
+}
+
+static inline void mb_cache_entry_set_referenced(struct mb_cache_entry *entry)
+{
+ entry->_e_hash_list_head |= 1;
+}
+
+static inline void mb_cache_entry_clear_referenced(
+ struct mb_cache_entry *entry)
+{
+ entry->_e_hash_list_head &= ~1;
+}
+
+static inline struct hlist_bl_head *mb_cache_entry_head(
+ struct mb_cache_entry *entry)
+{
+ return (struct hlist_bl_head *)
+ (entry->_e_hash_list_head & ~1);
+}
+
+/*
+ * Number of entries to reclaim synchronously when there are too many entries
+ * in cache
+ */
+#define SYNC_SHRINK_BATCH 64
+
+/*
+ * mb_cache_entry_create - create entry in cache
+ * @cache - cache where the entry should be created
+ * @mask - gfp mask with which the entry should be allocated
+ * @key - key of the entry
+ * @block - block that contains data
+ *
+ * Creates entry in @cache with key @key and records that data is stored in
+ * block @block. The function returns -EBUSY if entry with the same key
+ * and for the same block already exists in cache. Otherwise 0 is returned.
+ */
+int mb_cache_entry_create(struct mb_cache *cache, gfp_t mask, u32 key,
+ sector_t block)
+{
+ struct mb_cache_entry *entry, *dup;
+ struct hlist_bl_node *dup_node;
+ struct hlist_bl_head *head;
+
+ /* Schedule background reclaim if there are too many entries */
+ if (cache->c_entry_count >= cache->c_max_entries)
+ schedule_work(&cache->c_shrink_work);
+ /* Do some sync reclaim if background reclaim cannot keep up */
+ if (cache->c_entry_count >= 2*cache->c_max_entries)
+ mb_cache_shrink(cache, SYNC_SHRINK_BATCH);
+
+ entry = kmem_cache_alloc(mb_entry_cache, mask);
+ if (!entry)
+ return -ENOMEM;
+
+ INIT_LIST_HEAD(&entry->e_list);
+ /* One ref for hash, one ref returned */
+ atomic_set(&entry->e_refcnt, 1);
+ entry->e_key = key;
+ entry->e_block = block;
+ head = &cache->c_hash[hash_32(key, cache->c_bucket_bits)];
+ entry->_e_hash_list_head = (unsigned long)head;
+ hlist_bl_lock(head);
+ hlist_bl_for_each_entry(dup, dup_node, head, e_hash_list) {
+ if (dup->e_key == key && dup->e_block == block) {
+ hlist_bl_unlock(head);
+ kmem_cache_free(mb_entry_cache, entry);
+ return -EBUSY;
+ }
+ }
+ hlist_bl_add_head(&entry->e_hash_list, head);
+ hlist_bl_unlock(head);
+
+ spin_lock(&cache->c_list_lock);
+ list_add_tail(&entry->e_list, &cache->c_list);
+ /* Grab ref for LRU list */
+ atomic_inc(&entry->e_refcnt);
+ cache->c_entry_count++;
+ spin_unlock(&cache->c_list_lock);
+
+ return 0;
+}
+EXPORT_SYMBOL(mb_cache_entry_create);
+
+void __mb_cache_entry_free(struct mb_cache_entry *entry)
+{
+ kmem_cache_free(mb_entry_cache, entry);
+}
+EXPORT_SYMBOL(__mb_cache_entry_free);
+
+static struct mb_cache_entry *__entry_find(struct mb_cache *cache,
+ struct mb_cache_entry *entry,
+ u32 key)
+{
+ struct mb_cache_entry *old_entry = entry;
+ struct hlist_bl_node *node;
+ struct hlist_bl_head *head;
+
+ if (entry)
+ head = mb_cache_entry_head(entry);
+ else
+ head = &cache->c_hash[hash_32(key, cache->c_bucket_bits)];
+ hlist_bl_lock(head);
+ if (entry && !hlist_bl_unhashed(&entry->e_hash_list))
+ node = entry->e_hash_list.next;
+ else
+ node = hlist_bl_first(head);
+ while (node) {
+ entry = hlist_bl_entry(node, struct mb_cache_entry,
+ e_hash_list);
+ if (entry->e_key == key) {
+ atomic_inc(&entry->e_refcnt);
+ goto out;
+ }
+ node = node->next;
+ }
+ entry = NULL;
+out:
+ hlist_bl_unlock(head);
+ if (old_entry)
+ mb_cache_entry_put(cache, old_entry);
+
+ return entry;
+}
+
+/*
+ * mb_cache_entry_find_first - find the first entry in cache with given key
+ * @cache: cache where we should search
+ * @key: key to look for
+ *
+ * Search in @cache for entry with key @key. Grabs reference to the first
+ * entry found and returns the entry.
+ */
+struct mb_cache_entry *mb_cache_entry_find_first(struct mb_cache *cache,
+ u32 key)
+{
+ return __entry_find(cache, NULL, key);
+}
+EXPORT_SYMBOL(mb_cache_entry_find_first);
+
+/*
+ * mb_cache_entry_find_next - find next entry in cache with the same
+ * @cache: cache where we should search
+ * @entry: entry to start search from
+ *
+ * Finds next entry in the hash chain which has the same key as @entry.
+ * If @entry is unhashed (which can happen when deletion of entry races
+ * with the search), finds the first entry in the hash chain. The function
+ * drops reference to @entry and returns with a reference to the found entry.
+ */
+struct mb_cache_entry *mb_cache_entry_find_next(struct mb_cache *cache,
+ struct mb_cache_entry *entry)
+{
+ return __entry_find(cache, entry, entry->e_key);
+}
+EXPORT_SYMBOL(mb_cache_entry_find_next);
+
+/* mb_cache_entry_delete_block - remove information about block from cache
+ * @cache - cache we work with
+ * @key - key of the entry to remove
+ * @block - block containing data for @key
+ *
+ * Remove entry from cache @cache with key @key with data stored in @block.
+ */
+void mb_cache_entry_delete_block(struct mb_cache *cache, u32 key,
+ sector_t block)
+{
+ struct hlist_bl_node *node;
+ struct hlist_bl_head *head;
+ struct mb_cache_entry *entry;
+
+ head = &cache->c_hash[hash_32(key, cache->c_bucket_bits)];
+ hlist_bl_lock(head);
+ hlist_bl_for_each_entry(entry, node, head, e_hash_list) {
+ if (entry->e_key == key && entry->e_block == block) {
+ /* We keep hash list reference to keep entry alive */
+ hlist_bl_del_init(&entry->e_hash_list);
+ hlist_bl_unlock(head);
+ spin_lock(&cache->c_list_lock);
+ if (!list_empty(&entry->e_list)) {
+ list_del_init(&entry->e_list);
+ cache->c_entry_count--;
+ atomic_dec(&entry->e_refcnt);
+ }
+ spin_unlock(&cache->c_list_lock);
+ mb_cache_entry_put(cache, entry);
+ return;
+ }
+ }
+ hlist_bl_unlock(head);
+}
+EXPORT_SYMBOL(mb_cache_entry_delete_block);
+
+/* mb_cache_entry_touch - cache entry got used
+ * @cache - cache the entry belongs to
+ * @entry - entry that got used
+ *
+ * Marks entry as used to give hit higher chances of surviving in cache.
+ */
+void mb_cache_entry_touch(struct mb_cache *cache,
+ struct mb_cache_entry *entry)
+{
+ mb_cache_entry_set_referenced(entry);
+}
+EXPORT_SYMBOL(mb_cache_entry_touch);
+
+static unsigned long mb_cache_count(struct shrinker *shrink,
+ struct shrink_control *sc)
+{
+ struct mb_cache *cache = container_of(shrink, struct mb_cache,
+ c_shrink);
+
+ return cache->c_entry_count;
+}
+
+/* Shrink number of entries in cache */
+static unsigned long mb_cache_shrink(struct mb_cache *cache,
+ unsigned int nr_to_scan)
+{
+ struct mb_cache_entry *entry;
+ struct hlist_bl_head *head;
+ unsigned int shrunk = 0;
+
+ spin_lock(&cache->c_list_lock);
+ while (nr_to_scan-- && !list_empty(&cache->c_list)) {
+ entry = list_first_entry(&cache->c_list,
+ struct mb_cache_entry, e_list);
+ if (mb_cache_entry_referenced(entry)) {
+ mb_cache_entry_clear_referenced(entry);
+ list_move_tail(&cache->c_list, &entry->e_list);
+ continue;
+ }
+ list_del_init(&entry->e_list);
+ cache->c_entry_count--;
+ /*
+ * We keep LRU list reference so that entry doesn't go away
+ * from under us.
+ */
+ spin_unlock(&cache->c_list_lock);
+ head = mb_cache_entry_head(entry);
+ hlist_bl_lock(head);
+ if (!hlist_bl_unhashed(&entry->e_hash_list)) {
+ hlist_bl_del_init(&entry->e_hash_list);
+ atomic_dec(&entry->e_refcnt);
+ }
+ hlist_bl_unlock(head);
+ if (mb_cache_entry_put(cache, entry))
+ shrunk++;
+ cond_resched();
+ spin_lock(&cache->c_list_lock);
+ }
+ spin_unlock(&cache->c_list_lock);
+
+ return shrunk;
+}
+
+static unsigned long mb_cache_scan(struct shrinker *shrink,
+ struct shrink_control *sc)
+{
+ int nr_to_scan = sc->nr_to_scan;
+ struct mb_cache *cache = container_of(shrink, struct mb_cache,
+ c_shrink);
+ return mb_cache_shrink(cache, nr_to_scan);
+}
+
+/* We shrink 1/X of the cache when we have too many entries in it */
+#define SHRINK_DIVISOR 16
+
+static void mb_cache_shrink_worker(struct work_struct *work)
+{
+ struct mb_cache *cache = container_of(work, struct mb_cache,
+ c_shrink_work);
+ mb_cache_shrink(cache, cache->c_max_entries / SHRINK_DIVISOR);
+}
+
+/*
+ * mb_cache_create - create cache
+ * @bucket_bits: log2 of the hash table size
+ *
+ * Create cache for keys with 2^bucket_bits hash entries.
+ */
+struct mb_cache *mb_cache_create(int bucket_bits)
+{
+ struct mb_cache *cache;
+ int bucket_count = 1 << bucket_bits;
+ int i;
+
+ if (!try_module_get(THIS_MODULE))
+ return NULL;
+
+ cache = kzalloc(sizeof(struct mb_cache), GFP_KERNEL);
+ if (!cache)
+ goto err_out;
+ cache->c_bucket_bits = bucket_bits;
+ cache->c_max_entries = bucket_count << 4;
+ INIT_LIST_HEAD(&cache->c_list);
+ spin_lock_init(&cache->c_list_lock);
+ cache->c_hash = kmalloc(bucket_count * sizeof(struct hlist_bl_head),
+ GFP_KERNEL);
+ if (!cache->c_hash) {
+ kfree(cache);
+ goto err_out;
+ }
+ for (i = 0; i < bucket_count; i++)
+ INIT_HLIST_BL_HEAD(&cache->c_hash[i]);
+
+ cache->c_shrink.count_objects = mb_cache_count;
+ cache->c_shrink.scan_objects = mb_cache_scan;
+ cache->c_shrink.seeks = DEFAULT_SEEKS;
+ register_shrinker(&cache->c_shrink);
+
+ INIT_WORK(&cache->c_shrink_work, mb_cache_shrink_worker);
+
+ return cache;
+
+err_out:
+ module_put(THIS_MODULE);
+ return NULL;
+}
+EXPORT_SYMBOL(mb_cache_create);
+
+/*
+ * mb_cache_destroy - destroy cache
+ * @cache: the cache to destroy
+ *
+ * Free all entries in cache and cache itself. Caller must make sure nobody
+ * (except shrinker) can reach @cache when calling this.
+ */
+void mb_cache_destroy(struct mb_cache *cache)
+{
+ struct mb_cache_entry *entry, *next;
+
+ unregister_shrinker(&cache->c_shrink);
+
+ /*
+ * We don't bother with any locking. Cache must not be used at this
+ * point.
+ */
+ list_for_each_entry_safe(entry, next, &cache->c_list, e_list) {
+ if (!hlist_bl_unhashed(&entry->e_hash_list)) {
+ hlist_bl_del_init(&entry->e_hash_list);
+ atomic_dec(&entry->e_refcnt);
+ } else
+ WARN_ON(1);
+ list_del(&entry->e_list);
+ WARN_ON(atomic_read(&entry->e_refcnt) != 1);
+ mb_cache_entry_put(cache, entry);
+ }
+ kfree(cache->c_hash);
+ kfree(cache);
+ module_put(THIS_MODULE);
+}
+EXPORT_SYMBOL(mb_cache_destroy);
+
+static int __init mbcache_init(void)
+{
+ mb_entry_cache = kmem_cache_create("mbcache",
+ sizeof(struct mb_cache_entry), 0,
+ SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD, NULL);
+ BUG_ON(!mb_entry_cache);
+ return 0;
+}
+
+static void __exit mbcache_exit(void)
+{
+ kmem_cache_destroy(mb_entry_cache);
+}
+
+module_init(mbcache_init)
+module_exit(mbcache_exit)
+
+MODULE_AUTHOR("Jan Kara <jack@suse.cz>");
+MODULE_DESCRIPTION("Meta block cache (for extended attributes)");
+MODULE_LICENSE("GPL");
+++ /dev/null
-#include <linux/spinlock.h>
-#include <linux/slab.h>
-#include <linux/list.h>
-#include <linux/list_bl.h>
-#include <linux/module.h>
-#include <linux/sched.h>
-#include <linux/workqueue.h>
-#include <linux/mbcache2.h>
-
-/*
- * Mbcache is a simple key-value store. Keys need not be unique, however
- * key-value pairs are expected to be unique (we use this fact in
- * mb2_cache_entry_delete_block()).
- *
- * Ext2 and ext4 use this cache for deduplication of extended attribute blocks.
- * They use hash of a block contents as a key and block number as a value.
- * That's why keys need not be unique (different xattr blocks may end up having
- * the same hash). However block number always uniquely identifies a cache
- * entry.
- *
- * We provide functions for creation and removal of entries, search by key,
- * and a special "delete entry with given key-value pair" operation. Fixed
- * size hash table is used for fast key lookups.
- */
-
-struct mb2_cache {
- /* Hash table of entries */
- struct hlist_bl_head *c_hash;
- /* log2 of hash table size */
- int c_bucket_bits;
- /* Maximum entries in cache to avoid degrading hash too much */
- int c_max_entries;
- /* Protects c_list, c_entry_count */
- spinlock_t c_list_lock;
- struct list_head c_list;
- /* Number of entries in cache */
- unsigned long c_entry_count;
- struct shrinker c_shrink;
- /* Work for shrinking when the cache has too many entries */
- struct work_struct c_shrink_work;
-};
-
-static struct kmem_cache *mb2_entry_cache;
-
-static unsigned long mb2_cache_shrink(struct mb2_cache *cache,
- unsigned int nr_to_scan);
-
-static inline bool mb2_cache_entry_referenced(struct mb2_cache_entry *entry)
-{
- return entry->_e_hash_list_head & 1;
-}
-
-static inline void mb2_cache_entry_set_referenced(struct mb2_cache_entry *entry)
-{
- entry->_e_hash_list_head |= 1;
-}
-
-static inline void mb2_cache_entry_clear_referenced(
- struct mb2_cache_entry *entry)
-{
- entry->_e_hash_list_head &= ~1;
-}
-
-static inline struct hlist_bl_head *mb2_cache_entry_head(
- struct mb2_cache_entry *entry)
-{
- return (struct hlist_bl_head *)
- (entry->_e_hash_list_head & ~1);
-}
-
-/*
- * Number of entries to reclaim synchronously when there are too many entries
- * in cache
- */
-#define SYNC_SHRINK_BATCH 64
-
-/*
- * mb2_cache_entry_create - create entry in cache
- * @cache - cache where the entry should be created
- * @mask - gfp mask with which the entry should be allocated
- * @key - key of the entry
- * @block - block that contains data
- *
- * Creates entry in @cache with key @key and records that data is stored in
- * block @block. The function returns -EBUSY if entry with the same key
- * and for the same block already exists in cache. Otherwise 0 is returned.
- */
-int mb2_cache_entry_create(struct mb2_cache *cache, gfp_t mask, u32 key,
- sector_t block)
-{
- struct mb2_cache_entry *entry, *dup;
- struct hlist_bl_node *dup_node;
- struct hlist_bl_head *head;
-
- /* Schedule background reclaim if there are too many entries */
- if (cache->c_entry_count >= cache->c_max_entries)
- schedule_work(&cache->c_shrink_work);
- /* Do some sync reclaim if background reclaim cannot keep up */
- if (cache->c_entry_count >= 2*cache->c_max_entries)
- mb2_cache_shrink(cache, SYNC_SHRINK_BATCH);
-
- entry = kmem_cache_alloc(mb2_entry_cache, mask);
- if (!entry)
- return -ENOMEM;
-
- INIT_LIST_HEAD(&entry->e_list);
- /* One ref for hash, one ref returned */
- atomic_set(&entry->e_refcnt, 1);
- entry->e_key = key;
- entry->e_block = block;
- head = &cache->c_hash[hash_32(key, cache->c_bucket_bits)];
- entry->_e_hash_list_head = (unsigned long)head;
- hlist_bl_lock(head);
- hlist_bl_for_each_entry(dup, dup_node, head, e_hash_list) {
- if (dup->e_key == key && dup->e_block == block) {
- hlist_bl_unlock(head);
- kmem_cache_free(mb2_entry_cache, entry);
- return -EBUSY;
- }
- }
- hlist_bl_add_head(&entry->e_hash_list, head);
- hlist_bl_unlock(head);
-
- spin_lock(&cache->c_list_lock);
- list_add_tail(&entry->e_list, &cache->c_list);
- /* Grab ref for LRU list */
- atomic_inc(&entry->e_refcnt);
- cache->c_entry_count++;
- spin_unlock(&cache->c_list_lock);
-
- return 0;
-}
-EXPORT_SYMBOL(mb2_cache_entry_create);
-
-void __mb2_cache_entry_free(struct mb2_cache_entry *entry)
-{
- kmem_cache_free(mb2_entry_cache, entry);
-}
-EXPORT_SYMBOL(__mb2_cache_entry_free);
-
-static struct mb2_cache_entry *__entry_find(struct mb2_cache *cache,
- struct mb2_cache_entry *entry,
- u32 key)
-{
- struct mb2_cache_entry *old_entry = entry;
- struct hlist_bl_node *node;
- struct hlist_bl_head *head;
-
- if (entry)
- head = mb2_cache_entry_head(entry);
- else
- head = &cache->c_hash[hash_32(key, cache->c_bucket_bits)];
- hlist_bl_lock(head);
- if (entry && !hlist_bl_unhashed(&entry->e_hash_list))
- node = entry->e_hash_list.next;
- else
- node = hlist_bl_first(head);
- while (node) {
- entry = hlist_bl_entry(node, struct mb2_cache_entry,
- e_hash_list);
- if (entry->e_key == key) {
- atomic_inc(&entry->e_refcnt);
- goto out;
- }
- node = node->next;
- }
- entry = NULL;
-out:
- hlist_bl_unlock(head);
- if (old_entry)
- mb2_cache_entry_put(cache, old_entry);
-
- return entry;
-}
-
-/*
- * mb2_cache_entry_find_first - find the first entry in cache with given key
- * @cache: cache where we should search
- * @key: key to look for
- *
- * Search in @cache for entry with key @key. Grabs reference to the first
- * entry found and returns the entry.
- */
-struct mb2_cache_entry *mb2_cache_entry_find_first(struct mb2_cache *cache,
- u32 key)
-{
- return __entry_find(cache, NULL, key);
-}
-EXPORT_SYMBOL(mb2_cache_entry_find_first);
-
-/*
- * mb2_cache_entry_find_next - find next entry in cache with the same
- * @cache: cache where we should search
- * @entry: entry to start search from
- *
- * Finds next entry in the hash chain which has the same key as @entry.
- * If @entry is unhashed (which can happen when deletion of entry races
- * with the search), finds the first entry in the hash chain. The function
- * drops reference to @entry and returns with a reference to the found entry.
- */
-struct mb2_cache_entry *mb2_cache_entry_find_next(struct mb2_cache *cache,
- struct mb2_cache_entry *entry)
-{
- return __entry_find(cache, entry, entry->e_key);
-}
-EXPORT_SYMBOL(mb2_cache_entry_find_next);
-
-/* mb2_cache_entry_delete_block - remove information about block from cache
- * @cache - cache we work with
- * @key - key of the entry to remove
- * @block - block containing data for @key
- *
- * Remove entry from cache @cache with key @key with data stored in @block.
- */
-void mb2_cache_entry_delete_block(struct mb2_cache *cache, u32 key,
- sector_t block)
-{
- struct hlist_bl_node *node;
- struct hlist_bl_head *head;
- struct mb2_cache_entry *entry;
-
- head = &cache->c_hash[hash_32(key, cache->c_bucket_bits)];
- hlist_bl_lock(head);
- hlist_bl_for_each_entry(entry, node, head, e_hash_list) {
- if (entry->e_key == key && entry->e_block == block) {
- /* We keep hash list reference to keep entry alive */
- hlist_bl_del_init(&entry->e_hash_list);
- hlist_bl_unlock(head);
- spin_lock(&cache->c_list_lock);
- if (!list_empty(&entry->e_list)) {
- list_del_init(&entry->e_list);
- cache->c_entry_count--;
- atomic_dec(&entry->e_refcnt);
- }
- spin_unlock(&cache->c_list_lock);
- mb2_cache_entry_put(cache, entry);
- return;
- }
- }
- hlist_bl_unlock(head);
-}
-EXPORT_SYMBOL(mb2_cache_entry_delete_block);
-
-/* mb2_cache_entry_touch - cache entry got used
- * @cache - cache the entry belongs to
- * @entry - entry that got used
- *
- * Marks entry as used to give hit higher chances of surviving in cache.
- */
-void mb2_cache_entry_touch(struct mb2_cache *cache,
- struct mb2_cache_entry *entry)
-{
- mb2_cache_entry_set_referenced(entry);
-}
-EXPORT_SYMBOL(mb2_cache_entry_touch);
-
-static unsigned long mb2_cache_count(struct shrinker *shrink,
- struct shrink_control *sc)
-{
- struct mb2_cache *cache = container_of(shrink, struct mb2_cache,
- c_shrink);
-
- return cache->c_entry_count;
-}
-
-/* Shrink number of entries in cache */
-static unsigned long mb2_cache_shrink(struct mb2_cache *cache,
- unsigned int nr_to_scan)
-{
- struct mb2_cache_entry *entry;
- struct hlist_bl_head *head;
- unsigned int shrunk = 0;
-
- spin_lock(&cache->c_list_lock);
- while (nr_to_scan-- && !list_empty(&cache->c_list)) {
- entry = list_first_entry(&cache->c_list,
- struct mb2_cache_entry, e_list);
- if (mb2_cache_entry_referenced(entry)) {
- mb2_cache_entry_clear_referenced(entry);
- list_move_tail(&cache->c_list, &entry->e_list);
- continue;
- }
- list_del_init(&entry->e_list);
- cache->c_entry_count--;
- /*
- * We keep LRU list reference so that entry doesn't go away
- * from under us.
- */
- spin_unlock(&cache->c_list_lock);
- head = mb2_cache_entry_head(entry);
- hlist_bl_lock(head);
- if (!hlist_bl_unhashed(&entry->e_hash_list)) {
- hlist_bl_del_init(&entry->e_hash_list);
- atomic_dec(&entry->e_refcnt);
- }
- hlist_bl_unlock(head);
- if (mb2_cache_entry_put(cache, entry))
- shrunk++;
- cond_resched();
- spin_lock(&cache->c_list_lock);
- }
- spin_unlock(&cache->c_list_lock);
-
- return shrunk;
-}
-
-static unsigned long mb2_cache_scan(struct shrinker *shrink,
- struct shrink_control *sc)
-{
- int nr_to_scan = sc->nr_to_scan;
- struct mb2_cache *cache = container_of(shrink, struct mb2_cache,
- c_shrink);
- return mb2_cache_shrink(cache, nr_to_scan);
-}
-
-/* We shrink 1/X of the cache when we have too many entries in it */
-#define SHRINK_DIVISOR 16
-
-static void mb2_cache_shrink_worker(struct work_struct *work)
-{
- struct mb2_cache *cache = container_of(work, struct mb2_cache,
- c_shrink_work);
- mb2_cache_shrink(cache, cache->c_max_entries / SHRINK_DIVISOR);
-}
-
-/*
- * mb2_cache_create - create cache
- * @bucket_bits: log2 of the hash table size
- *
- * Create cache for keys with 2^bucket_bits hash entries.
- */
-struct mb2_cache *mb2_cache_create(int bucket_bits)
-{
- struct mb2_cache *cache;
- int bucket_count = 1 << bucket_bits;
- int i;
-
- if (!try_module_get(THIS_MODULE))
- return NULL;
-
- cache = kzalloc(sizeof(struct mb2_cache), GFP_KERNEL);
- if (!cache)
- goto err_out;
- cache->c_bucket_bits = bucket_bits;
- cache->c_max_entries = bucket_count << 4;
- INIT_LIST_HEAD(&cache->c_list);
- spin_lock_init(&cache->c_list_lock);
- cache->c_hash = kmalloc(bucket_count * sizeof(struct hlist_bl_head),
- GFP_KERNEL);
- if (!cache->c_hash) {
- kfree(cache);
- goto err_out;
- }
- for (i = 0; i < bucket_count; i++)
- INIT_HLIST_BL_HEAD(&cache->c_hash[i]);
-
- cache->c_shrink.count_objects = mb2_cache_count;
- cache->c_shrink.scan_objects = mb2_cache_scan;
- cache->c_shrink.seeks = DEFAULT_SEEKS;
- register_shrinker(&cache->c_shrink);
-
- INIT_WORK(&cache->c_shrink_work, mb2_cache_shrink_worker);
-
- return cache;
-
-err_out:
- module_put(THIS_MODULE);
- return NULL;
-}
-EXPORT_SYMBOL(mb2_cache_create);
-
-/*
- * mb2_cache_destroy - destroy cache
- * @cache: the cache to destroy
- *
- * Free all entries in cache and cache itself. Caller must make sure nobody
- * (except shrinker) can reach @cache when calling this.
- */
-void mb2_cache_destroy(struct mb2_cache *cache)
-{
- struct mb2_cache_entry *entry, *next;
-
- unregister_shrinker(&cache->c_shrink);
-
- /*
- * We don't bother with any locking. Cache must not be used at this
- * point.
- */
- list_for_each_entry_safe(entry, next, &cache->c_list, e_list) {
- if (!hlist_bl_unhashed(&entry->e_hash_list)) {
- hlist_bl_del_init(&entry->e_hash_list);
- atomic_dec(&entry->e_refcnt);
- } else
- WARN_ON(1);
- list_del(&entry->e_list);
- WARN_ON(atomic_read(&entry->e_refcnt) != 1);
- mb2_cache_entry_put(cache, entry);
- }
- kfree(cache->c_hash);
- kfree(cache);
- module_put(THIS_MODULE);
-}
-EXPORT_SYMBOL(mb2_cache_destroy);
-
-static int __init mb2cache_init(void)
-{
- mb2_entry_cache = kmem_cache_create("mbcache",
- sizeof(struct mb2_cache_entry), 0,
- SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD, NULL);
- BUG_ON(!mb2_entry_cache);
- return 0;
-}
-
-static void __exit mb2cache_exit(void)
-{
- kmem_cache_destroy(mb2_entry_cache);
-}
-
-module_init(mb2cache_init)
-module_exit(mb2cache_exit)
-
-MODULE_AUTHOR("Jan Kara <jack@suse.cz>");
-MODULE_DESCRIPTION("Meta block cache (for extended attributes)");
-MODULE_LICENSE("GPL");
--- /dev/null
+#ifndef _LINUX_MBCACHE_H
+#define _LINUX_MBCACHE_H
+
+#include <linux/hash.h>
+#include <linux/list_bl.h>
+#include <linux/list.h>
+#include <linux/atomic.h>
+#include <linux/fs.h>
+
+struct mb_cache;
+
+struct mb_cache_entry {
+ /* List of entries in cache - protected by cache->c_list_lock */
+ struct list_head e_list;
+ /* Hash table list - protected by bitlock in e_hash_list_head */
+ struct hlist_bl_node e_hash_list;
+ atomic_t e_refcnt;
+ /* Key in hash - stable during lifetime of the entry */
+ u32 e_key;
+ /* Block number of hashed block - stable during lifetime of the entry */
+ sector_t e_block;
+ /*
+ * Head of hash list (for list bit lock) - stable. Combined with
+ * referenced bit of entry
+ */
+ unsigned long _e_hash_list_head;
+};
+
+struct mb_cache *mb_cache_create(int bucket_bits);
+void mb_cache_destroy(struct mb_cache *cache);
+
+int mb_cache_entry_create(struct mb_cache *cache, gfp_t mask, u32 key,
+ sector_t block);
+void __mb_cache_entry_free(struct mb_cache_entry *entry);
+static inline int mb_cache_entry_put(struct mb_cache *cache,
+ struct mb_cache_entry *entry)
+{
+ if (!atomic_dec_and_test(&entry->e_refcnt))
+ return 0;
+ __mb_cache_entry_free(entry);
+ return 1;
+}
+
+void mb_cache_entry_delete_block(struct mb_cache *cache, u32 key,
+ sector_t block);
+struct mb_cache_entry *mb_cache_entry_find_first(struct mb_cache *cache,
+ u32 key);
+struct mb_cache_entry *mb_cache_entry_find_next(struct mb_cache *cache,
+ struct mb_cache_entry *entry);
+void mb_cache_entry_touch(struct mb_cache *cache,
+ struct mb_cache_entry *entry);
+
+#endif /* _LINUX_MBCACHE_H */
+++ /dev/null
-#ifndef _LINUX_MB2CACHE_H
-#define _LINUX_MB2CACHE_H
-
-#include <linux/hash.h>
-#include <linux/list_bl.h>
-#include <linux/list.h>
-#include <linux/atomic.h>
-#include <linux/fs.h>
-
-struct mb2_cache;
-
-struct mb2_cache_entry {
- /* List of entries in cache - protected by cache->c_list_lock */
- struct list_head e_list;
- /* Hash table list - protected by bitlock in e_hash_list_head */
- struct hlist_bl_node e_hash_list;
- atomic_t e_refcnt;
- /* Key in hash - stable during lifetime of the entry */
- u32 e_key;
- /* Block number of hashed block - stable during lifetime of the entry */
- sector_t e_block;
- /*
- * Head of hash list (for list bit lock) - stable. Combined with
- * referenced bit of entry
- */
- unsigned long _e_hash_list_head;
-};
-
-struct mb2_cache *mb2_cache_create(int bucket_bits);
-void mb2_cache_destroy(struct mb2_cache *cache);
-
-int mb2_cache_entry_create(struct mb2_cache *cache, gfp_t mask, u32 key,
- sector_t block);
-void __mb2_cache_entry_free(struct mb2_cache_entry *entry);
-static inline int mb2_cache_entry_put(struct mb2_cache *cache,
- struct mb2_cache_entry *entry)
-{
- if (!atomic_dec_and_test(&entry->e_refcnt))
- return 0;
- __mb2_cache_entry_free(entry);
- return 1;
-}
-
-void mb2_cache_entry_delete_block(struct mb2_cache *cache, u32 key,
- sector_t block);
-struct mb2_cache_entry *mb2_cache_entry_find_first(struct mb2_cache *cache,
- u32 key);
-struct mb2_cache_entry *mb2_cache_entry_find_next(struct mb2_cache *cache,
- struct mb2_cache_entry *entry);
-void mb2_cache_entry_touch(struct mb2_cache *cache,
- struct mb2_cache_entry *entry);
-
-#endif /* _LINUX_MB2CACHE_H */
projects / linux-2.6-block.git / commitdiff