2005-04-17 00:20:36 +02:00
|
|
|
#ifndef _LINUX_NAMEI_H
|
|
|
|
|
#define _LINUX_NAMEI_H
|
|
|
|
|
|
2006-10-01 08:27:22 +02:00
|
|
|
#include <linux/dcache.h>
|
2005-04-17 00:20:36 +02:00
|
|
|
#include <linux/linkage.h>
|
2008-02-15 04:34:31 +01:00
|
|
|
#include <linux/path.h>
|
2005-04-17 00:20:36 +02:00
|
|
|
|
|
|
|
|
struct vfsmount;
|
|
|
|
|
|
|
|
|
|
struct open_intent {
|
|
|
|
|
int flags;
|
|
|
|
|
int create_mode;
|
2005-10-18 23:20:16 +02:00
|
|
|
struct file *file;
|
2005-04-17 00:20:36 +02:00
|
|
|
};
|
|
|
|
|
|
2006-07-14 09:24:29 +02:00
|
|
|
enum { MAX_NESTED_LINKS = 8 };
|
2005-04-17 00:20:36 +02:00
|
|
|
|
|
|
|
|
struct nameidata {
|
2008-02-15 04:34:32 +01:00
|
|
|
struct path path;
|
2005-04-17 00:20:36 +02:00
|
|
|
struct qstr last;
|
2009-04-07 17:49:53 +02:00
|
|
|
struct path root;
|
fs: rcu-walk for path lookup
Perform common cases of path lookups without any stores or locking in the
ancestor dentry elements. This is called rcu-walk, as opposed to the current
algorithm which is a refcount based walk, or ref-walk.
This results in far fewer atomic operations on every path element,
significantly improving path lookup performance. It also avoids cacheline
bouncing on common dentries, significantly improving scalability.
The overall design is like this:
* LOOKUP_RCU is set in nd->flags, which distinguishes rcu-walk from ref-walk.
* Take the RCU lock for the entire path walk, starting with the acquiring
of the starting path (eg. root/cwd/fd-path). So now dentry refcounts are
not required for dentry persistence.
* synchronize_rcu is called when unregistering a filesystem, so we can
access d_ops and i_ops during rcu-walk.
* Similarly take the vfsmount lock for the entire path walk. So now mnt
refcounts are not required for persistence. Also we are free to perform mount
lookups, and to assume dentry mount points and mount roots are stable up and
down the path.
* Have a per-dentry seqlock to protect the dentry name, parent, and inode,
so we can load this tuple atomically, and also check whether any of its
members have changed.
* Dentry lookups (based on parent, candidate string tuple) recheck the parent
sequence after the child is found in case anything changed in the parent
during the path walk.
* inode is also RCU protected so we can load d_inode and use the inode for
limited things.
* i_mode, i_uid, i_gid can be tested for exec permissions during path walk.
* i_op can be loaded.
When we reach the destination dentry, we lock it, recheck lookup sequence,
and increment its refcount and mountpoint refcount. RCU and vfsmount locks
are dropped. This is termed "dropping rcu-walk". If the dentry refcount does
not match, we can not drop rcu-walk gracefully at the current point in the
lokup, so instead return -ECHILD (for want of a better errno). This signals the
path walking code to re-do the entire lookup with a ref-walk.
Aside from the final dentry, there are other situations that may be encounted
where we cannot continue rcu-walk. In that case, we drop rcu-walk (ie. take
a reference on the last good dentry) and continue with a ref-walk. Again, if
we can drop rcu-walk gracefully, we return -ECHILD and do the whole lookup
using ref-walk. But it is very important that we can continue with ref-walk
for most cases, particularly to avoid the overhead of double lookups, and to
gain the scalability advantages on common path elements (like cwd and root).
The cases where rcu-walk cannot continue are:
* NULL dentry (ie. any uncached path element)
* parent with d_inode->i_op->permission or ACLs
* dentries with d_revalidate
* Following links
In future patches, permission checks and d_revalidate become rcu-walk aware. It
may be possible eventually to make following links rcu-walk aware.
Uncached path elements will always require dropping to ref-walk mode, at the
very least because i_mutex needs to be grabbed, and objects allocated.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
2011-01-07 07:49:52 +01:00
|
|
|
struct file *file;
|
|
|
|
|
struct inode *inode; /* path.dentry.d_inode */
|
2005-04-17 00:20:36 +02:00
|
|
|
unsigned int flags;
|
fs: rcu-walk for path lookup
Perform common cases of path lookups without any stores or locking in the
ancestor dentry elements. This is called rcu-walk, as opposed to the current
algorithm which is a refcount based walk, or ref-walk.
This results in far fewer atomic operations on every path element,
significantly improving path lookup performance. It also avoids cacheline
bouncing on common dentries, significantly improving scalability.
The overall design is like this:
* LOOKUP_RCU is set in nd->flags, which distinguishes rcu-walk from ref-walk.
* Take the RCU lock for the entire path walk, starting with the acquiring
of the starting path (eg. root/cwd/fd-path). So now dentry refcounts are
not required for dentry persistence.
* synchronize_rcu is called when unregistering a filesystem, so we can
access d_ops and i_ops during rcu-walk.
* Similarly take the vfsmount lock for the entire path walk. So now mnt
refcounts are not required for persistence. Also we are free to perform mount
lookups, and to assume dentry mount points and mount roots are stable up and
down the path.
* Have a per-dentry seqlock to protect the dentry name, parent, and inode,
so we can load this tuple atomically, and also check whether any of its
members have changed.
* Dentry lookups (based on parent, candidate string tuple) recheck the parent
sequence after the child is found in case anything changed in the parent
during the path walk.
* inode is also RCU protected so we can load d_inode and use the inode for
limited things.
* i_mode, i_uid, i_gid can be tested for exec permissions during path walk.
* i_op can be loaded.
When we reach the destination dentry, we lock it, recheck lookup sequence,
and increment its refcount and mountpoint refcount. RCU and vfsmount locks
are dropped. This is termed "dropping rcu-walk". If the dentry refcount does
not match, we can not drop rcu-walk gracefully at the current point in the
lokup, so instead return -ECHILD (for want of a better errno). This signals the
path walking code to re-do the entire lookup with a ref-walk.
Aside from the final dentry, there are other situations that may be encounted
where we cannot continue rcu-walk. In that case, we drop rcu-walk (ie. take
a reference on the last good dentry) and continue with a ref-walk. Again, if
we can drop rcu-walk gracefully, we return -ECHILD and do the whole lookup
using ref-walk. But it is very important that we can continue with ref-walk
for most cases, particularly to avoid the overhead of double lookups, and to
gain the scalability advantages on common path elements (like cwd and root).
The cases where rcu-walk cannot continue are:
* NULL dentry (ie. any uncached path element)
* parent with d_inode->i_op->permission or ACLs
* dentries with d_revalidate
* Following links
In future patches, permission checks and d_revalidate become rcu-walk aware. It
may be possible eventually to make following links rcu-walk aware.
Uncached path elements will always require dropping to ref-walk mode, at the
very least because i_mutex needs to be grabbed, and objects allocated.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
2011-01-07 07:49:52 +01:00
|
|
|
unsigned seq;
|
2005-04-17 00:20:36 +02:00
|
|
|
int last_type;
|
|
|
|
|
unsigned depth;
|
|
|
|
|
char *saved_names[MAX_NESTED_LINKS + 1];
|
|
|
|
|
|
|
|
|
|
/* Intent data */
|
|
|
|
|
union {
|
|
|
|
|
struct open_intent open;
|
|
|
|
|
} intent;
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Type of the last component on LOOKUP_PARENT
|
|
|
|
|
*/
|
|
|
|
|
enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT, LAST_BIND};
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* The bitmask for a lookup event:
|
|
|
|
|
* - follow links at the end
|
|
|
|
|
* - require a directory
|
|
|
|
|
* - ending slashes ok even for nonexistent files
|
2009-06-16 11:17:53 +02:00
|
|
|
* - internal "there are more path components" flag
|
2005-04-17 00:20:36 +02:00
|
|
|
* - dentry cache is untrusted; force a real lookup
|
|
|
|
|
*/
|
fs: rcu-walk for path lookup
Perform common cases of path lookups without any stores or locking in the
ancestor dentry elements. This is called rcu-walk, as opposed to the current
algorithm which is a refcount based walk, or ref-walk.
This results in far fewer atomic operations on every path element,
significantly improving path lookup performance. It also avoids cacheline
bouncing on common dentries, significantly improving scalability.
The overall design is like this:
* LOOKUP_RCU is set in nd->flags, which distinguishes rcu-walk from ref-walk.
* Take the RCU lock for the entire path walk, starting with the acquiring
of the starting path (eg. root/cwd/fd-path). So now dentry refcounts are
not required for dentry persistence.
* synchronize_rcu is called when unregistering a filesystem, so we can
access d_ops and i_ops during rcu-walk.
* Similarly take the vfsmount lock for the entire path walk. So now mnt
refcounts are not required for persistence. Also we are free to perform mount
lookups, and to assume dentry mount points and mount roots are stable up and
down the path.
* Have a per-dentry seqlock to protect the dentry name, parent, and inode,
so we can load this tuple atomically, and also check whether any of its
members have changed.
* Dentry lookups (based on parent, candidate string tuple) recheck the parent
sequence after the child is found in case anything changed in the parent
during the path walk.
* inode is also RCU protected so we can load d_inode and use the inode for
limited things.
* i_mode, i_uid, i_gid can be tested for exec permissions during path walk.
* i_op can be loaded.
When we reach the destination dentry, we lock it, recheck lookup sequence,
and increment its refcount and mountpoint refcount. RCU and vfsmount locks
are dropped. This is termed "dropping rcu-walk". If the dentry refcount does
not match, we can not drop rcu-walk gracefully at the current point in the
lokup, so instead return -ECHILD (for want of a better errno). This signals the
path walking code to re-do the entire lookup with a ref-walk.
Aside from the final dentry, there are other situations that may be encounted
where we cannot continue rcu-walk. In that case, we drop rcu-walk (ie. take
a reference on the last good dentry) and continue with a ref-walk. Again, if
we can drop rcu-walk gracefully, we return -ECHILD and do the whole lookup
using ref-walk. But it is very important that we can continue with ref-walk
for most cases, particularly to avoid the overhead of double lookups, and to
gain the scalability advantages on common path elements (like cwd and root).
The cases where rcu-walk cannot continue are:
* NULL dentry (ie. any uncached path element)
* parent with d_inode->i_op->permission or ACLs
* dentries with d_revalidate
* Following links
In future patches, permission checks and d_revalidate become rcu-walk aware. It
may be possible eventually to make following links rcu-walk aware.
Uncached path elements will always require dropping to ref-walk mode, at the
very least because i_mutex needs to be grabbed, and objects allocated.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
2011-01-07 07:49:52 +01:00
|
|
|
#define LOOKUP_FOLLOW 0x0001
|
|
|
|
|
#define LOOKUP_DIRECTORY 0x0002
|
|
|
|
|
#define LOOKUP_CONTINUE 0x0004
|
|
|
|
|
|
|
|
|
|
#define LOOKUP_PARENT 0x0010
|
|
|
|
|
#define LOOKUP_REVAL 0x0020
|
|
|
|
|
#define LOOKUP_RCU 0x0040
|
2005-04-17 00:20:36 +02:00
|
|
|
/*
|
|
|
|
|
* Intent data
|
|
|
|
|
*/
|
2008-08-05 09:00:49 +02:00
|
|
|
#define LOOKUP_OPEN 0x0100
|
|
|
|
|
#define LOOKUP_CREATE 0x0200
|
|
|
|
|
#define LOOKUP_EXCL 0x0400
|
2008-10-16 00:50:29 +02:00
|
|
|
#define LOOKUP_RENAME_TARGET 0x0800
|
2005-04-17 00:20:36 +02:00
|
|
|
|
2008-07-22 15:59:21 +02:00
|
|
|
extern int user_path_at(int, const char __user *, unsigned, struct path *);
|
|
|
|
|
|
|
|
|
|
#define user_path(name, path) user_path_at(AT_FDCWD, name, LOOKUP_FOLLOW, path)
|
|
|
|
|
#define user_lpath(name, path) user_path_at(AT_FDCWD, name, 0, path)
|
|
|
|
|
#define user_path_dir(name, path) \
|
|
|
|
|
user_path_at(AT_FDCWD, name, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, path)
|
|
|
|
|
|
2008-08-02 06:49:18 +02:00
|
|
|
extern int kern_path(const char *, unsigned, struct path *);
|
|
|
|
|
|
2008-02-14 00:03:15 +01:00
|
|
|
extern int path_lookup(const char *, unsigned, struct nameidata *);
|
fs: introduce vfs_path_lookup
Stackable file systems, among others, frequently need to lookup paths or
path components starting from an arbitrary point in the namespace
(identified by a dentry and a vfsmount). Currently, such file systems use
lookup_one_len, which is frowned upon [1] as it does not pass the lookup
intent along; not passing a lookup intent, for example, can trigger BUG_ON's
when stacking on top of NFSv4.
The first patch introduces a new lookup function to allow lookup starting
from an arbitrary point in the namespace. This approach has been suggested
by Christoph Hellwig [2].
The second patch changes sunrpc to use vfs_path_lookup.
The third patch changes nfsctl.c to use vfs_path_lookup.
The fourth patch marks link_path_walk static.
The fifth, and last patch, unexports path_walk because it is no longer
unnecessary to call it directly, and using the new vfs_path_lookup is
cleaner.
For example, the following snippet of code, looks up "some/path/component"
in a directory pointed to by parent_{dentry,vfsmnt}:
err = vfs_path_lookup(parent_dentry, parent_vfsmnt,
"some/path/component", 0, &nd);
if (!err) {
/* exits */
...
/* once done, release the references */
path_release(&nd);
} else if (err == -ENOENT) {
/* doesn't exist */
} else {
/* other error */
}
VFS functions such as lookup_create can be used on the nameidata structure
to pass the create intent to the file system.
Signed-off-by: Josef 'Jeff' Sipek <jsipek@cs.sunysb.edu>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Acked-by: Christoph Hellwig <hch@lst.de>
Cc: Trond Myklebust <trond.myklebust@fys.uio.no>
Cc: Neil Brown <neilb@suse.de>
Cc: Michael Halcrow <mhalcrow@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-19 10:48:18 +02:00
|
|
|
extern int vfs_path_lookup(struct dentry *, struct vfsmount *,
|
|
|
|
|
const char *, unsigned int, struct nameidata *);
|
2005-04-17 00:20:36 +02:00
|
|
|
|
2005-10-18 23:20:16 +02:00
|
|
|
extern struct file *lookup_instantiate_filp(struct nameidata *nd, struct dentry *dentry,
|
|
|
|
|
int (*open)(struct inode *, struct file *));
|
|
|
|
|
|
2007-10-17 08:25:38 +02:00
|
|
|
extern struct dentry *lookup_one_len(const char *, struct dentry *, int);
|
2005-04-17 00:20:36 +02:00
|
|
|
|
2009-04-18 19:58:15 +02:00
|
|
|
extern int follow_down(struct path *);
|
2009-04-18 09:26:48 +02:00
|
|
|
extern int follow_up(struct path *);
|
2005-04-17 00:20:36 +02:00
|
|
|
|
|
|
|
|
extern struct dentry *lock_rename(struct dentry *, struct dentry *);
|
|
|
|
|
extern void unlock_rename(struct dentry *, struct dentry *);
|
|
|
|
|
|
|
|
|
|
static inline void nd_set_link(struct nameidata *nd, char *path)
|
|
|
|
|
{
|
|
|
|
|
nd->saved_names[nd->depth] = path;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline char *nd_get_link(struct nameidata *nd)
|
|
|
|
|
{
|
|
|
|
|
return nd->saved_names[nd->depth];
|
|
|
|
|
}
|
|
|
|
|
|
2008-12-19 21:47:11 +01:00
|
|
|
static inline void nd_terminate_link(void *name, size_t len, size_t maxlen)
|
|
|
|
|
{
|
|
|
|
|
((char *) name)[min(len, maxlen)] = '\0';
|
|
|
|
|
}
|
|
|
|
|
|
2005-04-17 00:20:36 +02:00
|
|
|
#endif /* _LINUX_NAMEI_H */
|
