linux/fs/autofs4/autofs_i.h

267 lines
7.1 KiB
C
Raw Normal View History

/* -*- c -*- ------------------------------------------------------------- *
*
* linux/fs/autofs/autofs_i.h
*
* Copyright 1997-1998 Transmeta Corporation - All Rights Reserved
* Copyright 2005-2006 Ian Kent <raven@themaw.net>
*
* This file is part of the Linux kernel and is made available under
* the terms of the GNU General Public License, version 2, or at your
* option, any later version, incorporated herein by reference.
*
* ----------------------------------------------------------------------- */
/* Internal header file for autofs */
#include <linux/auto_fs4.h>
#include <linux/auto_dev-ioctl.h>
#include <linux/mutex.h>
#include <linux/list.h>
/* This is the range of ioctl() numbers we claim as ours */
#define AUTOFS_IOC_FIRST AUTOFS_IOC_READY
#define AUTOFS_IOC_COUNT 32
#define AUTOFS_DEV_IOCTL_IOC_FIRST (AUTOFS_DEV_IOCTL_VERSION)
#define AUTOFS_DEV_IOCTL_IOC_COUNT (AUTOFS_IOC_COUNT - 11)
#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/time.h>
#include <linux/string.h>
#include <linux/wait.h>
#include <linux/sched.h>
#include <linux/mount.h>
#include <linux/namei.h>
#include <asm/current.h>
#include <asm/uaccess.h>
/* #define DEBUG */
#ifdef DEBUG
#define DPRINTK(fmt, args...) \
do { \
printk(KERN_DEBUG "pid %d: %s: " fmt "\n", \
current->pid, __func__, ##args); \
} while (0)
#else
#define DPRINTK(fmt, args...) do {} while (0)
#endif
#define AUTOFS_WARN(fmt, args...) \
do { \
printk(KERN_WARNING "pid %d: %s: " fmt "\n", \
current->pid, __func__, ##args); \
} while (0)
#define AUTOFS_ERROR(fmt, args...) \
do { \
printk(KERN_ERR "pid %d: %s: " fmt "\n", \
current->pid, __func__, ##args); \
} while (0)
/* Unified info structure. This is pointed to by both the dentry and
inode structures. Each file in the filesystem has an instance of this
structure. It holds a reference to the dentry, so dentries are never
flushed while the file exists. All name lookups are dealt with at the
dentry level, although the filesystem can interfere in the validation
process. Readdir is implemented by traversing the dentry lists. */
struct autofs_info {
struct dentry *dentry;
struct inode *inode;
int flags;
struct completion expire_complete;
autofs4: use look aside list for lookups A while ago a patch to resolve a deadlock during directory creation was merged. This delayed the hashing of lookup dentrys until the ->mkdir() (or ->symlink()) operation completed to ensure we always went through ->lookup() instead of also having processes go through ->revalidate() so our VFS locking remained consistent. Now we are seeing a couple of side affects of that change in situations with heavy mount activity. Two cases have been identified: 1) When a mount request is triggered, due to the delayed hashing, the directory created by user space for the mount point doesn't have the DCACHE_AUTOFS_PENDING flag set. In the case of an autofs multi-mount where a tree of mount point directories are created this can lead to the path walk continuing rather than the dentry being sent to the wait queue to wait for request completion. This is because, if the pending flag isn't set, the criteria for deciding this is a mount in progress fails to hold, namely that the dentry is not a mount point and has no subdirectories. 2) A mount request dentry is initially created negative and unhashed. It remains this way until the ->mkdir() callback completes. Since it is unhashed a fresh dentry is used when the user space mount request creates the mount point directory. This leaves the original dentry negative and unhashed. But revalidate has no way to tell the VFS that the dentry has changed, other than to force another ->lookup() by returning false, which is at best wastefull and at worst not possible. This results in an -ENOENT return from the original path walk when in fact the mount succeeded. To resolve this we need to ensure that the same dentry is used in all calls to ->lookup() during the course of a mount request. This patch achieves that by adding the initial dentry to a look aside list and removes it at ->mkdir() or ->symlink() completion (or when the dentry is released), since these are the only create operations autofs4 supports. Signed-off-by: Ian Kent <raven@themaw.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-24 12:30:12 +08:00
struct list_head active;
struct list_head expiring;
struct autofs_sb_info *sbi;
unsigned long last_used;
atomic_t count;
uid_t uid;
gid_t gid;
mode_t mode;
size_t size;
void (*free)(struct autofs_info *);
union {
const char *symlink;
} u;
};
#define AUTOFS_INF_EXPIRING (1<<0) /* dentry is in the process of expiring */
#define AUTOFS_INF_MOUNTPOINT (1<<1) /* mountpoint status for direct expire */
struct autofs_wait_queue {
wait_queue_head_t queue;
struct autofs_wait_queue *next;
autofs_wqt_t wait_queue_token;
/* We use the following to see what we are waiting for */
struct qstr name;
u32 dev;
u64 ino;
uid_t uid;
gid_t gid;
pid_t pid;
pid_t tgid;
/* This is for status reporting upon return */
int status;
unsigned int wait_ctr;
};
#define AUTOFS_SBI_MAGIC 0x6d4a556d
struct autofs_sb_info {
u32 magic;
int pipefd;
struct file *pipe;
pid_t oz_pgrp;
int catatonic;
int version;
int sub_version;
int min_proto;
int max_proto;
unsigned long exp_timeout;
unsigned int type;
int reghost_enabled;
int needs_reghost;
struct super_block *sb;
struct mutex wq_mutex;
spinlock_t fs_lock;
struct autofs_wait_queue *queues; /* Wait queue pointer */
spinlock_t lookup_lock;
autofs4: use look aside list for lookups A while ago a patch to resolve a deadlock during directory creation was merged. This delayed the hashing of lookup dentrys until the ->mkdir() (or ->symlink()) operation completed to ensure we always went through ->lookup() instead of also having processes go through ->revalidate() so our VFS locking remained consistent. Now we are seeing a couple of side affects of that change in situations with heavy mount activity. Two cases have been identified: 1) When a mount request is triggered, due to the delayed hashing, the directory created by user space for the mount point doesn't have the DCACHE_AUTOFS_PENDING flag set. In the case of an autofs multi-mount where a tree of mount point directories are created this can lead to the path walk continuing rather than the dentry being sent to the wait queue to wait for request completion. This is because, if the pending flag isn't set, the criteria for deciding this is a mount in progress fails to hold, namely that the dentry is not a mount point and has no subdirectories. 2) A mount request dentry is initially created negative and unhashed. It remains this way until the ->mkdir() callback completes. Since it is unhashed a fresh dentry is used when the user space mount request creates the mount point directory. This leaves the original dentry negative and unhashed. But revalidate has no way to tell the VFS that the dentry has changed, other than to force another ->lookup() by returning false, which is at best wastefull and at worst not possible. This results in an -ENOENT return from the original path walk when in fact the mount succeeded. To resolve this we need to ensure that the same dentry is used in all calls to ->lookup() during the course of a mount request. This patch achieves that by adding the initial dentry to a look aside list and removes it at ->mkdir() or ->symlink() completion (or when the dentry is released), since these are the only create operations autofs4 supports. Signed-off-by: Ian Kent <raven@themaw.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-24 12:30:12 +08:00
struct list_head active_list;
struct list_head expiring_list;
};
static inline struct autofs_sb_info *autofs4_sbi(struct super_block *sb)
{
return (struct autofs_sb_info *)(sb->s_fs_info);
}
static inline struct autofs_info *autofs4_dentry_ino(struct dentry *dentry)
{
return (struct autofs_info *)(dentry->d_fsdata);
}
/* autofs4_oz_mode(): do we see the man behind the curtain? (The
processes which do manipulations for us in user space sees the raw
filesystem without "magic".) */
static inline int autofs4_oz_mode(struct autofs_sb_info *sbi) {
return sbi->catatonic || task_pgrp_nr(current) == sbi->oz_pgrp;
}
/* Does a dentry have some pending activity? */
static inline int autofs4_ispending(struct dentry *dentry)
{
struct autofs_info *inf = autofs4_dentry_ino(dentry);
if (dentry->d_flags & DCACHE_AUTOFS_PENDING)
return 1;
if (inf->flags & AUTOFS_INF_EXPIRING)
return 1;
return 0;
}
static inline void autofs4_copy_atime(struct file *src, struct file *dst)
{
dst->f_path.dentry->d_inode->i_atime =
src->f_path.dentry->d_inode->i_atime;
return;
}
struct inode *autofs4_get_inode(struct super_block *, struct autofs_info *);
void autofs4_free_ino(struct autofs_info *);
/* Expiration */
int is_autofs4_dentry(struct dentry *);
int autofs4_expire_wait(struct dentry *dentry);
int autofs4_expire_run(struct super_block *, struct vfsmount *,
struct autofs_sb_info *,
struct autofs_packet_expire __user *);
int autofs4_expire_multi(struct super_block *, struct vfsmount *,
struct autofs_sb_info *, int __user *);
struct dentry *autofs4_expire_direct(struct super_block *sb,
struct vfsmount *mnt,
struct autofs_sb_info *sbi, int how);
struct dentry *autofs4_expire_indirect(struct super_block *sb,
struct vfsmount *mnt,
struct autofs_sb_info *sbi, int how);
/* Device node initialization */
int autofs_dev_ioctl_init(void);
void autofs_dev_ioctl_exit(void);
/* Operations structures */
extern const struct inode_operations autofs4_symlink_inode_operations;
extern const struct inode_operations autofs4_dir_inode_operations;
extern const struct inode_operations autofs4_root_inode_operations;
extern const struct inode_operations autofs4_indirect_root_inode_operations;
extern const struct inode_operations autofs4_direct_root_inode_operations;
extern const struct file_operations autofs4_dir_operations;
extern const struct file_operations autofs4_root_operations;
/* Initializing function */
int autofs4_fill_super(struct super_block *, void *, int);
struct autofs_info *autofs4_init_ino(struct autofs_info *, struct autofs_sb_info *sbi, mode_t mode);
/* Queue management functions */
int autofs4_wait(struct autofs_sb_info *,struct dentry *, enum autofs_notify);
int autofs4_wait_release(struct autofs_sb_info *,autofs_wqt_t,int);
void autofs4_catatonic_mode(struct autofs_sb_info *);
static inline int autofs4_follow_mount(struct vfsmount **mnt, struct dentry **dentry)
{
int res = 0;
while (d_mountpoint(*dentry)) {
int followed = follow_down(mnt, dentry);
if (!followed)
break;
res = 1;
}
return res;
}
static inline u32 autofs4_get_dev(struct autofs_sb_info *sbi)
{
return new_encode_dev(sbi->sb->s_dev);
}
static inline u64 autofs4_get_ino(struct autofs_sb_info *sbi)
{
return sbi->sb->s_root->d_inode->i_ino;
}
static inline int simple_positive(struct dentry *dentry)
{
return dentry->d_inode && !d_unhashed(dentry);
}
static inline int __simple_empty(struct dentry *dentry)
{
struct dentry *child;
int ret = 0;
[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 17:03:32 +08:00
list_for_each_entry(child, &dentry->d_subdirs, d_u.d_child)
if (simple_positive(child))
goto out;
ret = 1;
out:
return ret;
}
void autofs4_dentry_release(struct dentry *);
extern void autofs4_kill_sb(struct super_block *);