[PATCH 08/17] Make follow_down() handle d_manage()
From: David Howells
Date: Thu Sep 30 2010 - 14:16:18 EST
The previous patch (that adds d_manage()) offers autofs the opportunity to
block processes whilst it is rearranging its dentry tree, but only covers cases
where managed_dentry() is called. Some places call follow_down(), which would
allow processes to bypass autofs's attempts to block them.
Make follow_down() handle managed dentries. Do this by renaming follow_down()
to follow_down_one() and instituting a new follow_down(). follow_down_one() is
then only used where a call to d_manage() is not needed.
follow_down() then incorporates the loop from its remaining callers to follow
down through all mounted filesystems at that point. Before each mountpoint is
transited and if requested by the filesystem, d_manage() is called to hold or
reject that transit. The callers of follow_down() must then handle a possible
error condition.
follow_down() is given a parameter to say whether someone is trying to mount on
that point (and holding namespace_sem). This is now passed on to d_manage().
The filesystem may reject this request by returning an error from d_manage().
Furthermore, d_manage() may end follow_down() processing early by returning
-EISDIR to indicate it wants the dentry to be dealt with as an ordinary
directory, not a mountpoint. This permits autofs to let its daemon see the
underlying dentry.
Signed-off-by: David Howells <dhowells@xxxxxxxxxx>
Acked-by: Ian Kent <raven@xxxxxxxxxx>
---
fs/autofs/dirhash.c | 5 ++--
fs/autofs4/autofs_i.h | 13 -----------
fs/autofs4/dev-ioctl.c | 2 +-
fs/autofs4/expire.c | 2 +-
fs/autofs4/root.c | 11 ++++-----
fs/namei.c | 57 +++++++++++++++++++++++++++++++++++++++++++++---
fs/namespace.c | 14 +++++++-----
fs/nfsd/vfs.c | 5 +++-
include/linux/dcache.h | 7 +++++-
include/linux/namei.h | 3 ++-
10 files changed, 82 insertions(+), 37 deletions(-)
diff --git a/fs/autofs/dirhash.c b/fs/autofs/dirhash.c
index e947915..a24092c 100644
--- a/fs/autofs/dirhash.c
+++ b/fs/autofs/dirhash.c
@@ -85,13 +85,12 @@ struct autofs_dir_ent *autofs_expire(struct super_block *sb,
}
path.mnt = mnt;
path_get(&path);
- if (!follow_down(&path)) {
+ if (!follow_down_one(&path)) {
path_put(&path);
DPRINTK(("autofs: not expirable (not a mounted directory): %s\n", ent->name));
continue;
}
- while (d_mountpoint(path.dentry) && follow_down(&path))
- ;
+ follow_down(&path, false); // TODO: need to check error
umount_ok = may_umount(path.mnt);
path_put(&path);
diff --git a/fs/autofs4/autofs_i.h b/fs/autofs4/autofs_i.h
index 3d283ab..08af160 100644
--- a/fs/autofs4/autofs_i.h
+++ b/fs/autofs4/autofs_i.h
@@ -226,19 +226,6 @@ 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 path *path)
-{
- int res = 0;
-
- while (d_mountpoint(path->dentry)) {
- int followed = follow_down(path);
- 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);
diff --git a/fs/autofs4/dev-ioctl.c b/fs/autofs4/dev-ioctl.c
index ba4a38b..8567abc 100644
--- a/fs/autofs4/dev-ioctl.c
+++ b/fs/autofs4/dev-ioctl.c
@@ -551,7 +551,7 @@ static int autofs_dev_ioctl_ismountpoint(struct file *fp,
err = have_submounts(path.dentry);
- if (follow_down(&path))
+ if (follow_down_one(&path))
magic = path.mnt->mnt_sb->s_magic;
}
diff --git a/fs/autofs4/expire.c b/fs/autofs4/expire.c
index 9f5bde2..47feba9 100644
--- a/fs/autofs4/expire.c
+++ b/fs/autofs4/expire.c
@@ -56,7 +56,7 @@ static int autofs4_mount_busy(struct vfsmount *mnt, struct dentry *dentry)
path_get(&path);
- if (!follow_down(&path))
+ if (!follow_down_one(&path))
goto done;
if (is_autofs4_dentry(path.dentry)) {
diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c
index cb1bd38..7dd218b 100644
--- a/fs/autofs4/root.c
+++ b/fs/autofs4/root.c
@@ -227,7 +227,7 @@ static void *autofs4_follow_link(struct dentry *dentry, struct nameidata *nd)
nd->flags);
/*
* For an expire of a covered direct or offset mount we need
- * to break out of follow_down() at the autofs mount trigger
+ * to break out of follow_down_one() at the autofs mount trigger
* (d_mounted--), so we can see the expiring flag, and manage
* the blocking and following here until the expire is completed.
*/
@@ -236,7 +236,7 @@ static void *autofs4_follow_link(struct dentry *dentry, struct nameidata *nd)
if (ino->flags & AUTOFS_INF_EXPIRING) {
spin_unlock(&sbi->fs_lock);
/* Follow down to our covering mount. */
- if (!follow_down(&nd->path))
+ if (!follow_down_one(&nd->path))
goto done;
goto follow;
}
@@ -281,11 +281,10 @@ follow:
* multi-mount with no root offset so we don't need
* to follow it.
*/
- if (d_mountpoint(dentry)) {
- if (!autofs4_follow_mount(&nd->path)) {
- status = -ENOENT;
+ if (d_managed(dentry)) {
+ status = follow_down(&nd->path, false);
+ if (status < 0)
goto out_error;
- }
}
done:
diff --git a/fs/namei.c b/fs/namei.c
index 1bbd2d4..c7f5f71 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -700,9 +700,9 @@ static int managed_dentry(struct path *path, unsigned flags)
if (d_managed & DMANAGED_TRANSIT) {
BUG_ON(!path->dentry->d_op);
BUG_ON(!path->dentry->d_op->d_manage);
- ret = path->dentry->d_op->d_manage(path);
+ ret = path->dentry->d_op->d_manage(path, false);
if (ret < 0)
- return ret;
+ return ret == -EISDIR ? 0 : ret;
}
/* Transit to a mounted filesystem. */
@@ -741,7 +741,7 @@ static int managed_dentry(struct path *path, unsigned flags)
/* no need for dcache_lock, as serialization is taken care in
* namespace.c
*/
-int follow_down(struct path *path)
+int follow_down_one(struct path *path)
{
struct vfsmount *mounted;
@@ -757,6 +757,56 @@ int follow_down(struct path *path)
}
/*
+ * Follow down to the topmost point on a stack of mountpoints. At each point,
+ * the filesystem owning that dentry may be queried as to whether the caller is
+ * permitted to proceed or not.
+ *
+ * Care must be taken as namespace_sem may be held.
+ */
+int follow_down(struct path *path, bool mounting_here)
+{
+ unsigned d_managed;
+ int ret;
+
+ while (d_managed = path->dentry->d_managed,
+ unlikely(d_managed != 0)) {
+ /* Allow the filesystem to manage the transit without i_mutex
+ * being held.
+ *
+ * We indicate to the filesystem if someone is trying to mount
+ * something here. This gives autofs the chance to deny anyone
+ * other than its daemon the right to mount on its
+ * superstructure.
+ *
+ * The filesystem may sleep at this point.
+ */
+ if (d_managed & DMANAGED_TRANSIT) {
+ BUG_ON(!path->dentry->d_op);
+ BUG_ON(!path->dentry->d_op->d_manage);
+ ret = path->dentry->d_op->d_manage(path, mounting_here);
+ if (ret < 0)
+ return ret == -EISDIR ? 0 : ret;
+ }
+
+ /* Transit to a mounted filesystem. */
+ if (d_managed & DMANAGED_MOUNTPOINT) {
+ struct vfsmount *mounted = lookup_mnt(path);
+ if (!mounted)
+ break;
+ dput(path->dentry);
+ mntput(path->mnt);
+ path->mnt = mounted;
+ path->dentry = dget(mounted->mnt_root);
+ continue;
+ }
+
+ /* Don't handle automount points here */
+ break;
+ }
+ return 0;
+}
+
+/*
* Skip to top of mountpoint pile for follow_dotdot().
*/
static void follow_mount(struct path *path)
@@ -2985,6 +3035,7 @@ const struct inode_operations page_symlink_inode_operations = {
};
EXPORT_SYMBOL(user_path_at);
+EXPORT_SYMBOL(follow_down_one);
EXPORT_SYMBOL(follow_down);
EXPORT_SYMBOL(follow_up);
EXPORT_SYMBOL(get_write_access); /* binfmt_aout */
diff --git a/fs/namespace.c b/fs/namespace.c
index e72b7b9..70cf805 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -1668,9 +1668,10 @@ static int do_move_mount(struct path *path, char *old_name)
return err;
down_write(&namespace_sem);
- while (d_mountpoint(path->dentry) &&
- follow_down(path))
- ;
+ err = follow_down(path, true);
+ if (err < 0)
+ goto out;
+
err = -EINVAL;
if (!check_mnt(path->mnt) || !check_mnt(old_path.mnt))
goto out;
@@ -1766,9 +1767,10 @@ int do_add_mount(struct vfsmount *newmnt, struct path *path,
down_write(&namespace_sem);
/* Something was mounted here while we slept */
- while (d_mountpoint(path->dentry) &&
- follow_down(path))
- ;
+ err = follow_down(path, true);
+ if (err < 0)
+ goto unlock;
+
err = -EINVAL;
if (!(mnt_flags & MNT_SHRINKABLE) && !check_mnt(path->mnt))
goto unlock;
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 661a6cf..e20cf68 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -88,8 +88,9 @@ nfsd_cross_mnt(struct svc_rqst *rqstp, struct dentry **dpp,
.dentry = dget(dentry)};
int err = 0;
- while (d_mountpoint(path.dentry) && follow_down(&path))
- ;
+ err = follow_down(&path, false);
+ if (err < 0)
+ goto out;
exp2 = rqst_exp_get_by_name(rqstp, &path);
if (IS_ERR(exp2)) {
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 2da5aa4..970f0ba 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -144,7 +144,7 @@ struct dentry_operations {
void (*d_iput)(struct dentry *, struct inode *);
char *(*d_dname)(struct dentry *, char *, int);
struct vfsmount *(*d_automount)(struct path *);
- int (*d_manage)(struct path *);
+ int (*d_manage)(struct path *, bool);
};
/* the dentry parameter passed to d_hash and d_compare is the parent
@@ -394,6 +394,11 @@ static inline struct dentry *dget_parent(struct dentry *dentry)
extern void dput(struct dentry *);
+static inline bool d_managed(struct dentry *dentry)
+{
+ return dentry->d_managed != 0;
+}
+
static inline bool d_mountpoint(struct dentry *dentry)
{
return (dentry->d_managed & DMANAGED_MOUNTPOINT) != 0;
diff --git a/include/linux/namei.h b/include/linux/namei.h
index 1e1febf..57fa817 100644
--- a/include/linux/namei.h
+++ b/include/linux/namei.h
@@ -77,7 +77,8 @@ extern struct file *lookup_instantiate_filp(struct nameidata *nd, struct dentry
extern struct dentry *lookup_one_len(const char *, struct dentry *, int);
-extern int follow_down(struct path *);
+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 *);
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/