2005-04-16 16:20:36 -06:00
|
|
|
#ifndef __LINUX_DCACHE_H
|
|
|
|
#define __LINUX_DCACHE_H
|
|
|
|
|
|
|
|
#ifdef __KERNEL__
|
|
|
|
|
|
|
|
#include <asm/atomic.h>
|
|
|
|
#include <linux/list.h>
|
|
|
|
#include <linux/spinlock.h>
|
|
|
|
#include <linux/cache.h>
|
|
|
|
#include <linux/rcupdate.h>
|
|
|
|
|
|
|
|
struct nameidata;
|
|
|
|
struct vfsmount;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* linux/include/linux/dcache.h
|
|
|
|
*
|
|
|
|
* Dirent cache data structures
|
|
|
|
*
|
|
|
|
* (C) Copyright 1997 Thomas Schoebel-Theuer,
|
|
|
|
* with heavy changes by Linus Torvalds
|
|
|
|
*/
|
|
|
|
|
|
|
|
#define IS_ROOT(x) ((x) == (x)->d_parent)
|
|
|
|
|
|
|
|
/*
|
|
|
|
* "quick string" -- eases parameter passing, but more importantly
|
|
|
|
* saves "metadata" about the string (ie length and the hash).
|
|
|
|
*
|
|
|
|
* hash comes first so it snuggles against d_parent in the
|
|
|
|
* dentry.
|
|
|
|
*/
|
|
|
|
struct qstr {
|
|
|
|
unsigned int hash;
|
|
|
|
unsigned int len;
|
|
|
|
const unsigned char *name;
|
|
|
|
};
|
|
|
|
|
|
|
|
struct dentry_stat_t {
|
|
|
|
int nr_dentry;
|
|
|
|
int nr_unused;
|
|
|
|
int age_limit; /* age in seconds */
|
|
|
|
int want_pages; /* pages requested by system */
|
|
|
|
int dummy[2];
|
|
|
|
};
|
|
|
|
extern struct dentry_stat_t dentry_stat;
|
|
|
|
|
|
|
|
/* Name hashing routines. Initial hash value */
|
|
|
|
/* Hash courtesy of the R5 hash in reiserfs modulo sign bits */
|
|
|
|
#define init_name_hash() 0
|
|
|
|
|
|
|
|
/* partial hash update function. Assume roughly 4 bits per character */
|
|
|
|
static inline unsigned long
|
|
|
|
partial_name_hash(unsigned long c, unsigned long prevhash)
|
|
|
|
{
|
|
|
|
return (prevhash + (c << 4) + (c >> 4)) * 11;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Finally: cut down the number of bits to a int value (and try to avoid
|
|
|
|
* losing bits)
|
|
|
|
*/
|
|
|
|
static inline unsigned long end_name_hash(unsigned long hash)
|
|
|
|
{
|
|
|
|
return (unsigned int) hash;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Compute the hash for a name string. */
|
|
|
|
static inline unsigned int
|
|
|
|
full_name_hash(const unsigned char *name, unsigned int len)
|
|
|
|
{
|
|
|
|
unsigned long hash = init_name_hash();
|
|
|
|
while (len--)
|
|
|
|
hash = partial_name_hash(*name++, hash);
|
|
|
|
return end_name_hash(hash);
|
|
|
|
}
|
|
|
|
|
|
|
|
struct dcookie_struct;
|
|
|
|
|
|
|
|
#define DNAME_INLINE_LEN_MIN 36
|
|
|
|
|
|
|
|
struct dentry {
|
|
|
|
atomic_t d_count;
|
|
|
|
unsigned int d_flags; /* protected by d_lock */
|
|
|
|
spinlock_t d_lock; /* per dentry lock */
|
|
|
|
struct inode *d_inode; /* Where the name belongs to - NULL is
|
|
|
|
* negative */
|
|
|
|
/*
|
|
|
|
* The next three fields are touched by __d_lookup. Place them here
|
2005-09-06 16:18:16 -06:00
|
|
|
* so they all fit in a cache line.
|
2005-04-16 16:20:36 -06:00
|
|
|
*/
|
2005-09-06 16:18:16 -06:00
|
|
|
struct hlist_node d_hash; /* lookup hash list */
|
2005-04-16 16:20:36 -06:00
|
|
|
struct dentry *d_parent; /* parent directory */
|
|
|
|
struct qstr d_name;
|
|
|
|
|
|
|
|
struct list_head d_lru; /* LRU list */
|
[PATCH] shrink dentry struct
Some long time ago, dentry struct was carefully tuned so that on 32 bits
UP, sizeof(struct dentry) was exactly 128, ie a power of 2, and a multiple
of memory cache lines.
Then RCU was added and dentry struct enlarged by two pointers, with nice
results for SMP, but not so good on UP, because breaking the above tuning
(128 + 8 = 136 bytes)
This patch reverts this unwanted side effect, by using an union (d_u),
where d_rcu and d_child are placed so that these two fields can share their
memory needs.
At the time d_free() is called (and d_rcu is really used), d_child is known
to be empty and not touched by the dentry freeing.
Lockless lookups only access d_name, d_parent, d_lock, d_op, d_flags (so
the previous content of d_child is not needed if said dentry was unhashed
but still accessed by a CPU because of RCU constraints)
As dentry cache easily contains millions of entries, a size reduction is
worth the extra complexity of the ugly C union.
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Cc: Dipankar Sarma <dipankar@in.ibm.com>
Cc: Maneesh Soni <maneesh@in.ibm.com>
Cc: Miklos Szeredi <miklos@szeredi.hu>
Cc: "Paul E. McKenney" <paulmck@us.ibm.com>
Cc: Ian Kent <raven@themaw.net>
Cc: Paul Jackson <pj@sgi.com>
Cc: Al Viro <viro@ftp.linux.org.uk>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Trond Myklebust <trond.myklebust@fys.uio.no>
Cc: Neil Brown <neilb@cse.unsw.edu.au>
Cc: James Morris <jmorris@namei.org>
Cc: Stephen Smalley <sds@epoch.ncsc.mil>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-08 02:03:32 -07:00
|
|
|
/*
|
|
|
|
* d_child and d_rcu can share memory
|
|
|
|
*/
|
|
|
|
union {
|
|
|
|
struct list_head d_child; /* child of parent list */
|
|
|
|
struct rcu_head d_rcu;
|
|
|
|
} d_u;
|
2005-04-16 16:20:36 -06:00
|
|
|
struct list_head d_subdirs; /* our children */
|
|
|
|
struct list_head d_alias; /* inode alias list */
|
|
|
|
unsigned long d_time; /* used by d_revalidate */
|
|
|
|
struct dentry_operations *d_op;
|
|
|
|
struct super_block *d_sb; /* The root of the dentry tree */
|
|
|
|
void *d_fsdata; /* fs-specific data */
|
2006-02-03 04:04:06 -07:00
|
|
|
#ifdef CONFIG_PROFILING
|
2005-04-16 16:20:36 -06:00
|
|
|
struct dcookie_struct *d_cookie; /* cookie, if any */
|
2006-02-03 04:04:06 -07:00
|
|
|
#endif
|
2005-04-16 16:20:36 -06:00
|
|
|
int d_mounted;
|
|
|
|
unsigned char d_iname[DNAME_INLINE_LEN_MIN]; /* small names */
|
|
|
|
};
|
|
|
|
|
|
|
|
struct dentry_operations {
|
|
|
|
int (*d_revalidate)(struct dentry *, struct nameidata *);
|
|
|
|
int (*d_hash) (struct dentry *, struct qstr *);
|
|
|
|
int (*d_compare) (struct dentry *, struct qstr *, struct qstr *);
|
|
|
|
int (*d_delete)(struct dentry *);
|
|
|
|
void (*d_release)(struct dentry *);
|
|
|
|
void (*d_iput)(struct dentry *, struct inode *);
|
|
|
|
};
|
|
|
|
|
|
|
|
/* the dentry parameter passed to d_hash and d_compare is the parent
|
|
|
|
* directory of the entries to be compared. It is used in case these
|
|
|
|
* functions need any directory specific information for determining
|
|
|
|
* equivalency classes. Using the dentry itself might not work, as it
|
|
|
|
* might be a negative dentry which has no information associated with
|
|
|
|
* it */
|
|
|
|
|
|
|
|
/*
|
|
|
|
locking rules:
|
|
|
|
big lock dcache_lock d_lock may block
|
|
|
|
d_revalidate: no no no yes
|
|
|
|
d_hash no no no yes
|
|
|
|
d_compare: no yes yes no
|
|
|
|
d_delete: no yes no no
|
|
|
|
d_release: no no no yes
|
|
|
|
d_iput: no no no yes
|
|
|
|
*/
|
|
|
|
|
|
|
|
/* d_flags entries */
|
|
|
|
#define DCACHE_AUTOFS_PENDING 0x0001 /* autofs: "under construction" */
|
|
|
|
#define DCACHE_NFSFS_RENAMED 0x0002 /* this dentry has been "silly
|
|
|
|
* renamed" and has to be
|
|
|
|
* deleted on the last dput()
|
|
|
|
*/
|
|
|
|
#define DCACHE_DISCONNECTED 0x0004
|
|
|
|
/* This dentry is possibly not currently connected to the dcache tree,
|
|
|
|
* in which case its parent will either be itself, or will have this
|
|
|
|
* flag as well. nfsd will not use a dentry with this bit set, but will
|
|
|
|
* first endeavour to clear the bit either by discovering that it is
|
|
|
|
* connected, or by performing lookup operations. Any filesystem which
|
|
|
|
* supports nfsd_operations MUST have a lookup function which, if it finds
|
|
|
|
* a directory inode with a DCACHE_DISCONNECTED dentry, will d_move
|
|
|
|
* that dentry into place and return that dentry rather than the passed one,
|
|
|
|
* typically using d_splice_alias.
|
|
|
|
*/
|
|
|
|
|
|
|
|
#define DCACHE_REFERENCED 0x0008 /* Recently used, don't discard. */
|
|
|
|
#define DCACHE_UNHASHED 0x0010
|
|
|
|
|
2006-03-25 04:07:09 -07:00
|
|
|
#define DCACHE_INOTIFY_PARENT_WATCHED 0x0020 /* Parent inode is watched */
|
|
|
|
|
2005-04-16 16:20:36 -06:00
|
|
|
extern spinlock_t dcache_lock;
|
|
|
|
|
|
|
|
/**
|
|
|
|
* d_drop - drop a dentry
|
|
|
|
* @dentry: dentry to drop
|
|
|
|
*
|
|
|
|
* d_drop() unhashes the entry from the parent dentry hashes, so that it won't
|
|
|
|
* be found through a VFS lookup any more. Note that this is different from
|
|
|
|
* deleting the dentry - d_delete will try to mark the dentry negative if
|
|
|
|
* possible, giving a successful _negative_ lookup, while d_drop will
|
|
|
|
* just make the cache lookup fail.
|
|
|
|
*
|
|
|
|
* d_drop() is used mainly for stuff that wants to invalidate a dentry for some
|
|
|
|
* reason (NFS timeouts or autofs deletes).
|
|
|
|
*
|
|
|
|
* __d_drop requires dentry->d_lock.
|
|
|
|
*/
|
|
|
|
|
|
|
|
static inline void __d_drop(struct dentry *dentry)
|
|
|
|
{
|
|
|
|
if (!(dentry->d_flags & DCACHE_UNHASHED)) {
|
|
|
|
dentry->d_flags |= DCACHE_UNHASHED;
|
|
|
|
hlist_del_rcu(&dentry->d_hash);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void d_drop(struct dentry *dentry)
|
|
|
|
{
|
|
|
|
spin_lock(&dcache_lock);
|
|
|
|
spin_lock(&dentry->d_lock);
|
|
|
|
__d_drop(dentry);
|
|
|
|
spin_unlock(&dentry->d_lock);
|
|
|
|
spin_unlock(&dcache_lock);
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline int dname_external(struct dentry *dentry)
|
|
|
|
{
|
|
|
|
return dentry->d_name.name != dentry->d_iname;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* These are the low-level FS interfaces to the dcache..
|
|
|
|
*/
|
|
|
|
extern void d_instantiate(struct dentry *, struct inode *);
|
|
|
|
extern struct dentry * d_instantiate_unique(struct dentry *, struct inode *);
|
|
|
|
extern void d_delete(struct dentry *);
|
|
|
|
|
|
|
|
/* allocate/de-allocate */
|
|
|
|
extern struct dentry * d_alloc(struct dentry *, const struct qstr *);
|
|
|
|
extern struct dentry * d_alloc_anon(struct inode *);
|
|
|
|
extern struct dentry * d_splice_alias(struct inode *, struct dentry *);
|
|
|
|
extern void shrink_dcache_sb(struct super_block *);
|
|
|
|
extern void shrink_dcache_parent(struct dentry *);
|
[PATCH] Fix dcache race during umount
The race is that the shrink_dcache_memory shrinker could get called while a
filesystem is being unmounted, and could try to prune a dentry belonging to
that filesystem.
If it does, then it will call in to iput on the inode while the dentry is
no longer able to be found by the umounting process. If iput takes a
while, generic_shutdown_super could get all the way though
shrink_dcache_parent and shrink_dcache_anon and invalidate_inodes without
ever waiting on this particular inode.
Eventually the superblock gets freed anyway and if the iput tried to touch
it (which some filesystems certainly do), it will lose. The promised
"Self-destruct in 5 seconds" doesn't lead to a nice day.
The race is closed by holding s_umount while calling prune_one_dentry on
someone else's dentry. As a down_read_trylock is used,
shrink_dcache_memory will no longer try to prune the dentry of a filesystem
that is being unmounted, and unmount will not be able to start until any
such active prune_one_dentry completes.
This requires that prune_dcache *knows* which filesystem (if any) it is
doing the prune on behalf of so that it can be careful of other
filesystems. shrink_dcache_memory isn't called it on behalf of any
filesystem, and so is careful of everything.
shrink_dcache_anon is now passed a super_block rather than the s_anon list
out of the superblock, so it can get the s_anon list itself, and can pass
the superblock down to prune_dcache.
If prune_dcache finds a dentry that it cannot free, it leaves it where it
is (at the tail of the list) and exits, on the assumption that some other
thread will be removing that dentry soon. To try to make sure that some
work gets done, a limited number of dnetries which are untouchable are
skipped over while choosing the dentry to work on.
I believe this race was first found by Kirill Korotaev.
Cc: Jan Blunck <jblunck@suse.de>
Acked-by: Kirill Korotaev <dev@openvz.org>
Cc: Olaf Hering <olh@suse.de>
Acked-by: Balbir Singh <balbir@in.ibm.com>
Signed-off-by: Neil Brown <neilb@suse.de>
Signed-off-by: Balbir Singh <balbir@in.ibm.com>
Acked-by: David Howells <dhowells@redhat.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-22 15:47:28 -06:00
|
|
|
extern void shrink_dcache_anon(struct super_block *);
|
2005-04-16 16:20:36 -06:00
|
|
|
extern int d_invalidate(struct dentry *);
|
|
|
|
|
|
|
|
/* only used at mount-time */
|
|
|
|
extern struct dentry * d_alloc_root(struct inode *);
|
|
|
|
|
|
|
|
/* <clickety>-<click> the ramfs-type tree */
|
|
|
|
extern void d_genocide(struct dentry *);
|
|
|
|
|
|
|
|
extern struct dentry *d_find_alias(struct inode *);
|
|
|
|
extern void d_prune_aliases(struct inode *);
|
|
|
|
|
|
|
|
/* test whether we have any submounts in a subdir tree */
|
|
|
|
extern int have_submounts(struct dentry *);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* This adds the entry to the hash queues.
|
|
|
|
*/
|
|
|
|
extern void d_rehash(struct dentry *);
|
|
|
|
|
|
|
|
/**
|
|
|
|
* d_add - add dentry to hash queues
|
|
|
|
* @entry: dentry to add
|
|
|
|
* @inode: The inode to attach to this dentry
|
|
|
|
*
|
|
|
|
* This adds the entry to the hash queues and initializes @inode.
|
|
|
|
* The entry was actually filled in earlier during d_alloc().
|
|
|
|
*/
|
|
|
|
|
|
|
|
static inline void d_add(struct dentry *entry, struct inode *inode)
|
|
|
|
{
|
|
|
|
d_instantiate(entry, inode);
|
|
|
|
d_rehash(entry);
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* d_add_unique - add dentry to hash queues without aliasing
|
|
|
|
* @entry: dentry to add
|
|
|
|
* @inode: The inode to attach to this dentry
|
|
|
|
*
|
|
|
|
* This adds the entry to the hash queues and initializes @inode.
|
|
|
|
* The entry was actually filled in earlier during d_alloc().
|
|
|
|
*/
|
|
|
|
static inline struct dentry *d_add_unique(struct dentry *entry, struct inode *inode)
|
|
|
|
{
|
|
|
|
struct dentry *res;
|
|
|
|
|
|
|
|
res = d_instantiate_unique(entry, inode);
|
|
|
|
d_rehash(res != NULL ? res : entry);
|
|
|
|
return res;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* used for rename() and baskets */
|
|
|
|
extern void d_move(struct dentry *, struct dentry *);
|
|
|
|
|
|
|
|
/* appendix may either be NULL or be used for transname suffixes */
|
|
|
|
extern struct dentry * d_lookup(struct dentry *, struct qstr *);
|
|
|
|
extern struct dentry * __d_lookup(struct dentry *, struct qstr *);
|
2006-03-31 03:31:43 -07:00
|
|
|
extern struct dentry * d_hash_and_lookup(struct dentry *, struct qstr *);
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
/* validate "insecure" dentry pointer */
|
|
|
|
extern int d_validate(struct dentry *, struct dentry *);
|
|
|
|
|
|
|
|
extern char * d_path(struct dentry *, struct vfsmount *, char *, int);
|
|
|
|
|
|
|
|
/* Allocation counts.. */
|
|
|
|
|
|
|
|
/**
|
|
|
|
* dget, dget_locked - get a reference to a dentry
|
|
|
|
* @dentry: dentry to get a reference to
|
|
|
|
*
|
|
|
|
* Given a dentry or %NULL pointer increment the reference count
|
|
|
|
* if appropriate and return the dentry. A dentry will not be
|
|
|
|
* destroyed when it has references. dget() should never be
|
|
|
|
* called for dentries with zero reference counter. For these cases
|
|
|
|
* (preferably none, functions in dcache.c are sufficient for normal
|
|
|
|
* needs and they take necessary precautions) you should hold dcache_lock
|
|
|
|
* and call dget_locked() instead of dget().
|
|
|
|
*/
|
|
|
|
|
|
|
|
static inline struct dentry *dget(struct dentry *dentry)
|
|
|
|
{
|
|
|
|
if (dentry) {
|
|
|
|
BUG_ON(!atomic_read(&dentry->d_count));
|
|
|
|
atomic_inc(&dentry->d_count);
|
|
|
|
}
|
|
|
|
return dentry;
|
|
|
|
}
|
|
|
|
|
|
|
|
extern struct dentry * dget_locked(struct dentry *);
|
|
|
|
|
|
|
|
/**
|
|
|
|
* d_unhashed - is dentry hashed
|
|
|
|
* @dentry: entry to check
|
|
|
|
*
|
|
|
|
* Returns true if the dentry passed is not currently hashed.
|
|
|
|
*/
|
|
|
|
|
|
|
|
static inline int d_unhashed(struct dentry *dentry)
|
|
|
|
{
|
|
|
|
return (dentry->d_flags & DCACHE_UNHASHED);
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline struct dentry *dget_parent(struct dentry *dentry)
|
|
|
|
{
|
|
|
|
struct dentry *ret;
|
|
|
|
|
|
|
|
spin_lock(&dentry->d_lock);
|
|
|
|
ret = dget(dentry->d_parent);
|
|
|
|
spin_unlock(&dentry->d_lock);
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
extern void dput(struct dentry *);
|
|
|
|
|
|
|
|
static inline int d_mountpoint(struct dentry *dentry)
|
|
|
|
{
|
|
|
|
return dentry->d_mounted;
|
|
|
|
}
|
|
|
|
|
|
|
|
extern struct vfsmount *lookup_mnt(struct vfsmount *, struct dentry *);
|
2005-11-07 15:20:17 -07:00
|
|
|
extern struct vfsmount *__lookup_mnt(struct vfsmount *, struct dentry *, int);
|
2005-04-16 16:20:36 -06:00
|
|
|
extern struct dentry *lookup_create(struct nameidata *nd, int is_dir);
|
|
|
|
|
|
|
|
extern int sysctl_vfs_cache_pressure;
|
|
|
|
|
|
|
|
#endif /* __KERNEL__ */
|
|
|
|
|
|
|
|
#endif /* __LINUX_DCACHE_H */
|