mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-10-28 07:13:34 +00:00
cc53ce53c8
Add a dentry op (d_manage) to permit a filesystem to hold a process and make it sleep when it tries to transit away from one of that filesystem's directories during a pathwalk. The operation is keyed off a new dentry flag (DCACHE_MANAGE_TRANSIT). The filesystem is allowed to be selective about which processes it holds and which it permits to continue on or prohibits from transiting from each flagged directory. This will allow autofs to hold up client processes whilst letting its userspace daemon through to maintain the directory or the stuff behind it or mounted upon it. The ->d_manage() dentry operation: int (*d_manage)(struct path *path, bool mounting_here); takes a pointer to the directory about to be transited away from and a flag indicating whether the transit is undertaken by do_add_mount() or do_move_mount() skipping through a pile of filesystems mounted on a mountpoint. It should return 0 if successful and to let the process continue on its way; -EISDIR to prohibit the caller from skipping to overmounted filesystems or automounting, and to use this directory; or some other error code to return to the user. ->d_manage() is called with namespace_sem writelocked if mounting_here is true and no other locks held, so it may sleep. However, if mounting_here is true, it may not initiate or wait for a mount or unmount upon the parameter directory, even if the act is actually performed by userspace. Within fs/namei.c, follow_managed() is extended to check with d_manage() first on each managed directory, before transiting away from it or attempting to automount upon it. follow_down() is renamed follow_down_one() and should only be used where the filesystem deliberately intends to avoid management steps (e.g. autofs). A new follow_down() is added that incorporates the loop done by all other callers of follow_down() (do_add/move_mount(), autofs and NFSD; whilst AFS, NFS and CIFS do use it, their use is removed by converting them to use d_automount()). The new follow_down() calls d_manage() as appropriate. It also takes an extra parameter to indicate if it is being called from mount code (with namespace_sem writelocked) which it passes to d_manage(). follow_down() ignores automount points so that it can be used to mount on them. __follow_mount_rcu() is made to abort rcu-walk mode if it hits a directory with DCACHE_MANAGE_TRANSIT set on the basis that we're probably going to have to sleep. It would be possible to enter d_manage() in rcu-walk mode too, and have that determine whether to abort or not itself. That would allow the autofs daemon to continue on in rcu-walk mode. Note that DCACHE_MANAGE_TRANSIT on a directory should be cleared when it isn't required as every tranist from that directory will cause d_manage() to be invoked. It can always be set again when necessary. ========================== WHAT THIS MEANS FOR AUTOFS ========================== Autofs currently uses the lookup() inode op and the d_revalidate() dentry op to trigger the automounting of indirect mounts, and both of these can be called with i_mutex held. autofs knows that the i_mutex will be held by the caller in lookup(), and so can drop it before invoking the daemon - but this isn't so for d_revalidate(), since the lock is only held on _some_ of the code paths that call it. This means that autofs can't risk dropping i_mutex from its d_revalidate() function before it calls the daemon. The bug could manifest itself as, for example, a process that's trying to validate an automount dentry that gets made to wait because that dentry is expired and needs cleaning up: mkdir S ffffffff8014e05a 0 32580 24956 Call Trace: [<ffffffff885371fd>] :autofs4:autofs4_wait+0x674/0x897 [<ffffffff80127f7d>] avc_has_perm+0x46/0x58 [<ffffffff8009fdcf>] autoremove_wake_function+0x0/0x2e [<ffffffff88537be6>] :autofs4:autofs4_expire_wait+0x41/0x6b [<ffffffff88535cfc>] :autofs4:autofs4_revalidate+0x91/0x149 [<ffffffff80036d96>] __lookup_hash+0xa0/0x12f [<ffffffff80057a2f>] lookup_create+0x46/0x80 [<ffffffff800e6e31>] sys_mkdirat+0x56/0xe4 versus the automount daemon which wants to remove that dentry, but can't because the normal process is holding the i_mutex lock: automount D ffffffff8014e05a 0 32581 1 32561 Call Trace: [<ffffffff80063c3f>] __mutex_lock_slowpath+0x60/0x9b [<ffffffff8000ccf1>] do_path_lookup+0x2ca/0x2f1 [<ffffffff80063c89>] .text.lock.mutex+0xf/0x14 [<ffffffff800e6d55>] do_rmdir+0x77/0xde [<ffffffff8005d229>] tracesys+0x71/0xe0 [<ffffffff8005d28d>] tracesys+0xd5/0xe0 which means that the system is deadlocked. This patch allows autofs to hold up normal processes whilst the daemon goes ahead and does things to the dentry tree behind the automouter point without risking a deadlock as almost no locks are held in d_manage() and none in d_automount(). Signed-off-by: David Howells <dhowells@redhat.com> Was-Acked-by: Ian Kent <raven@themaw.net> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
104 lines
2.6 KiB
C
104 lines
2.6 KiB
C
#ifndef _LINUX_NAMEI_H
|
|
#define _LINUX_NAMEI_H
|
|
|
|
#include <linux/dcache.h>
|
|
#include <linux/linkage.h>
|
|
#include <linux/path.h>
|
|
|
|
struct vfsmount;
|
|
|
|
struct open_intent {
|
|
int flags;
|
|
int create_mode;
|
|
struct file *file;
|
|
};
|
|
|
|
enum { MAX_NESTED_LINKS = 8 };
|
|
|
|
struct nameidata {
|
|
struct path path;
|
|
struct qstr last;
|
|
struct path root;
|
|
struct file *file;
|
|
struct inode *inode; /* path.dentry.d_inode */
|
|
unsigned int flags;
|
|
unsigned seq;
|
|
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
|
|
* - internal "there are more path components" flag
|
|
* - dentry cache is untrusted; force a real lookup
|
|
*/
|
|
#define LOOKUP_FOLLOW 0x0001
|
|
#define LOOKUP_DIRECTORY 0x0002
|
|
#define LOOKUP_CONTINUE 0x0004
|
|
|
|
#define LOOKUP_PARENT 0x0010
|
|
#define LOOKUP_REVAL 0x0020
|
|
#define LOOKUP_RCU 0x0040
|
|
/*
|
|
* Intent data
|
|
*/
|
|
#define LOOKUP_OPEN 0x0100
|
|
#define LOOKUP_CREATE 0x0200
|
|
#define LOOKUP_EXCL 0x0400
|
|
#define LOOKUP_RENAME_TARGET 0x0800
|
|
|
|
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)
|
|
|
|
extern int kern_path(const char *, unsigned, struct path *);
|
|
|
|
extern int path_lookup(const char *, unsigned, struct nameidata *);
|
|
extern int vfs_path_lookup(struct dentry *, struct vfsmount *,
|
|
const char *, unsigned int, struct nameidata *);
|
|
|
|
extern struct file *lookup_instantiate_filp(struct nameidata *nd, struct dentry *dentry,
|
|
int (*open)(struct inode *, struct file *));
|
|
|
|
extern struct dentry *lookup_one_len(const char *, struct dentry *, int);
|
|
|
|
extern int follow_down_one(struct path *);
|
|
extern int follow_down(struct path *, bool);
|
|
extern int follow_up(struct path *);
|
|
|
|
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];
|
|
}
|
|
|
|
static inline void nd_terminate_link(void *name, size_t len, size_t maxlen)
|
|
{
|
|
((char *) name)[min(len, maxlen)] = '\0';
|
|
}
|
|
|
|
#endif /* _LINUX_NAMEI_H */
|