Add a dentry op (d_automount) to handle automounting directories rather than
abusing the follow_link() inode operation. The operation is keyed off a new
inode flag (S_AUTOMOUNT).
This makes it easier to add an AT_ flag to suppress terminal segment automount
during pathwalk. It should also remove the need for the kludge code in the
pathwalk algorithm to handle directories with follow_link() semantics.
A new pathwalk subroutine, follow_automount() is added to handle mountpoints.
It will return -EREMOTE if the S_AUTOMOUNT was set, but no d_automount() op was
supplied, -ELOOP if we've encountered too many symlinks or mountpoints, -EISDIR
if the walk point should be used without mounting and 0 if successful. path
will be updated if an automount took place to point to the mounted filesystem.
I've only changed __follow_mount() to handle call follow_automount(), but it
might be necessary to change follow_mount() too. The latter is only called
from follow_dotdot(), but any automounts on ".." should be pinned whilst we're
using a child of it.
I've also extracted the mount/don't-mount logic from autofs4 and included it
here. It makes the mount go ahead anyway if someone calls open() or creat(),
tries to traverse the directory, tries to chdir/chroot/etc. into the directory,
or sticks a '/' on the end of the pathname. If they do a stat(), however,
they'll only trigger the automount if they didn't also say O_NOFOLLOW.
Signed-off-by: David Howells <dhowells@xxxxxxxxxx>
Acked-by: Ian Kent <raven@xxxxxxxxxx>
---
Documentation/filesystems/Locking | 2 +
Documentation/filesystems/vfs.txt | 13 ++++
fs/namei.c | 120 ++++++++++++++++++++++++++++---------
include/linux/dcache.h | 4 +
include/linux/fs.h | 2 +
5 files changed, 111 insertions(+), 30 deletions(-)
diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index 977d891..7ebe42d 100644
--- a/Documentation/filesystems/Locking
+++ b/Documentation/filesystems/Locking
@@ -19,6 +19,7 @@ prototypes:
void (*d_release)(struct dentry *);
void (*d_iput)(struct dentry *, struct inode *);
char *(*d_dname)((struct dentry *dentry, char *buffer, int buflen);
+ struct vfsmount *(*d_automount)(struct path *path);
locking rules:
rename_lock ->d_lock may block rcu-walk
@@ -29,6 +30,7 @@ d_delete: no yes no no
d_release: no no yes no
d_iput: no no yes no
d_dname: no no no no
+d_automount: no no no yes
--------------------------- inode_operations ---------------------------
prototypes:
diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt
index fbb324e..bb8d277 100644
--- a/Documentation/filesystems/vfs.txt
+++ b/Documentation/filesystems/vfs.txt
@@ -864,6 +864,7 @@ struct dentry_operations {
void (*d_release)(struct dentry *);
void (*d_iput)(struct dentry *, struct inode *);
char *(*d_dname)(struct dentry *, char *, int);
+ struct vfsmount *(*d_automount)(struct path *);
};
d_revalidate: called when the VFS needs to revalidate a dentry. This
@@ -930,6 +931,18 @@ struct dentry_operations {
at the end of the buffer, and returns a pointer to the first char.
dynamic_dname() helper function is provided to take care of this.
+ d_automount: called when an automount dentry is to be traversed (optional).
+ This should create a new VFS mount record, mount it on the directory
+ and return the record to the caller. The caller is supplied with a
+ path parameter giving the automount directory to describe the automount
+ target and the parent VFS mount record to provide inheritable mount
+ parameters. NULL should be returned if someone else managed to make
+ the automount first. If the automount failed, then an error code
+ should be returned.
+
+ This function is only used if S_AUTOMOUNT is set on the inode to which
+ the dentry refers.
+
Example :
static char *pipefs_dname(struct dentry *dent, char *buffer, int buflen)
diff --git a/fs/namei.c b/fs/namei.c
index 24ece10..159da29 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -877,38 +877,84 @@ int follow_up(struct path *path)
}
/*
- * serialization is taken care of in namespace.c
+ * Perform an automount
+ * - return -EISDIR to tell __follow_mount() to stop and return the path we
+ * were called with.
*/
-static void __follow_mount_rcu(struct nameidata *nd, struct path *path,
- struct inode **inode)
+static int follow_automount(struct path *path, unsigned flags,
+ bool *need_mntput)
{
- while (d_mountpoint(path->dentry)) {
- struct vfsmount *mounted;
- mounted = __lookup_mnt(path->mnt, path->dentry, 1);
- if (!mounted)
- return;
- path->mnt = mounted;
- path->dentry = mounted->mnt_root;
- nd->seq = read_seqcount_begin(&path->dentry->d_seq);
- *inode = path->dentry->d_inode;
+ struct vfsmount *mnt;
+
+ if (!path->dentry->d_op || !path->dentry->d_op->d_automount)
+ return -EREMOTE;
+
+ /* We want to mount if someone is trying to open/create a file of any
+ * type under the mountpoint, wants to traverse through the mountpoint
+ * or wants to open the mounted directory.
+ *
+ * We don't want to mount if someone's just doing a stat and they've
+ * set AT_SYMLINK_NOFOLLOW - unless they're stat'ing a directory and
+ * appended a '/' to the name.
+ */
+ if (!(flags & LOOKUP_FOLLOW) &&
+ !(flags & (LOOKUP_CONTINUE | LOOKUP_DIRECTORY |
+ LOOKUP_OPEN | LOOKUP_CREATE)))
+ return -EISDIR;
+
+ current->total_link_count++;
+ if (current->total_link_count >= 40)
+ return -ELOOP;
+
+ mnt = path->dentry->d_op->d_automount(path);
+ if (IS_ERR(mnt))
+ return PTR_ERR(mnt);
+ if (!mnt) /* mount collision */
+ return 0;
+
+ if (mnt->mnt_sb == path->mnt->mnt_sb &&
+ mnt->mnt_root == path->dentry) {
+ mntput(mnt);
+ return -ELOOP;
}
+
+ dput(path->dentry);
+ if (*need_mntput)
+ mntput(path->mnt);
+ path->mnt = mnt;
+ path->dentry = dget(mnt->mnt_root);
+ *need_mntput = true;
+ return 0;
}
-static int __follow_mount(struct path *path)
+/*
+ * serialization is taken care of in namespace.c
+ */
+static int __follow_mount(struct path *path, unsigned flags)
{
- int res = 0;
- while (d_mountpoint(path->dentry)) {
- struct vfsmount *mounted = lookup_mnt(path);
- if (!mounted)
+ struct vfsmount *mounted;
+ bool need_mntput = false;
+ int ret;
+
+ for (;;) {
+ while (d_mountpoint(path->dentry)) {
+ mounted = lookup_mnt(path);
+ if (!mounted)
+ break;
+ dput(path->dentry);
+ if (need_mntput)
+ mntput(path->mnt);
+ path->mnt = mounted;
+ path->dentry = dget(mounted->mnt_root);
+ need_mntput = true;
+ }
+ if (!d_automount_point(path->dentry))
break;
- dput(path->dentry);
- if (res)
- mntput(path->mnt);
- path->mnt = mounted;
- path->dentry = dget(mounted->mnt_root);
- res = 1;
+ ret = follow_automount(path, flags, &need_mntput);
+ if (ret < 0)
+ return ret == -EISDIR ? 0 : ret;
}
- return res;
+ return 0;
}
static void follow_mount(struct path *path)
@@ -939,6 +985,21 @@ int follow_down(struct path *path)
return 0;
}
+static void __follow_mount_rcu(struct nameidata *nd, struct path *path,
+ struct inode **inode)
+{
+ while (d_mountpoint(path->dentry)) {
+ struct vfsmount *mounted;
+ mounted = __lookup_mnt(path->mnt, path->dentry, 1);
+ if (!mounted)
+ return;
+ path->mnt = mounted;
+ path->dentry = mounted->mnt_root;
+ nd->seq = read_seqcount_begin(&path->dentry->d_seq);
+ *inode = path->dentry->d_inode;
+ }
+}
+
static int follow_dotdot_rcu(struct nameidata *nd)
{
struct inode *inode = nd->inode;
@@ -1038,6 +1099,7 @@ static int do_lookup(struct nameidata *nd, struct qstr *name,
struct vfsmount *mnt = nd->path.mnt;
struct dentry *dentry, *parent = nd->path.dentry;
struct inode *dir;
+
/*
* See if the low-level filesystem might want
* to use its own hash..
@@ -1083,7 +1145,7 @@ found:
done:
path->mnt = mnt;
path->dentry = dentry;
- __follow_mount(path);
+ __follow_mount(path, nd->flags);
*inode = path->dentry->d_inode;
}
return 0;
@@ -2178,11 +2240,9 @@ static struct file *do_last(struct nameidata *nd, struct path *path,
if (open_flag & O_EXCL)
goto exit_dput;
- if (__follow_mount(path)) {
- error = -ELOOP;
- if (open_flag & O_NOFOLLOW)
- goto exit_dput;
- }
+ error = __follow_mount(path, nd->flags);
+ if (error < 0)
+ goto exit_dput;
error = -ENOENT;
if (!path->dentry->d_inode)
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 59fcd24..444614b 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -167,6 +167,7 @@ struct dentry_operations {
void (*d_release)(struct dentry *);
void (*d_iput)(struct dentry *, struct inode *);
char *(*d_dname)(struct dentry *, char *, int);
+ struct vfsmount *(*d_automount)(struct path *);
} ____cacheline_aligned;
/*
@@ -404,6 +405,9 @@ static inline int d_mountpoint(struct dentry *dentry)
return dentry->d_flags & DCACHE_MOUNTED;
}
+#define d_automount_point(dentry) \
+ (dentry->d_inode && IS_AUTOMOUNT(dentry->d_inode))
+
extern struct vfsmount *lookup_mnt(struct path *);
extern struct dentry *lookup_create(struct nameidata *nd, int is_dir);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index f84d992..5416e1a 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -242,6 +242,7 @@ struct inodes_stat_t {
#define S_SWAPFILE 256 /* Do not truncate: swapon got its bmaps */
#define S_PRIVATE 512 /* Inode is fs-internal */
#define S_IMA 1024 /* Inode has an associated IMA struct */
+#define S_AUTOMOUNT 2048 /* Automount/referral quasi-directory */
/*
* Note that nosuid etc flags are inode-specific: setting some file-system
@@ -277,6 +278,7 @@ struct inodes_stat_t {
#define IS_SWAPFILE(inode) ((inode)->i_flags & S_SWAPFILE)
#define IS_PRIVATE(inode) ((inode)->i_flags & S_PRIVATE)
#define IS_IMA(inode) ((inode)->i_flags & S_IMA)
+#define IS_AUTOMOUNT(inode) ((inode)->i_flags & S_AUTOMOUNT)
/* the read-only stuff doesn't really belong here, but any other place is
probably as bad and I don't want to create yet another include file. */
--
To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
