Allow d_manage() to be used in RCU-walk mode

Allow d_manage() to be called from pathwalk when it is in RCU-walk mode as well
as when it is in Ref-walk mode.  This permits __follow_mount_rcu() to call
d_manage() directly.  d_manage() needs a parameter to indicate that it is in
RCU-walk mode as it isn't allowed to sleep if in that mode (but should return
-ECHILD instead).

autofs4_d_manage() can then be set to retain RCU-walk mode if the daemon
accesses it and otherwise request dropping back to ref-walk mode.

Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

5 files changed, 22 insertions, 12 deletions

diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index cbf98b989b11..39707748ed2d 100644
--- a/Documentation/filesystems/Locking
+++ b/Documentation/filesystems/Locking
@@ -32,7 +32,7 @@ d_release:	no		no		yes		no
 d_iput:         no              no              yes             no
 d_dname:        no              no              no              no
 d_automount:    no              no              yes             no
-d_manage:       no              no              yes             no
+d_manage:       no              no              yes (ref-walk)  maybe
 
 --------------------------- inode_operations --------------------------- 
 prototypes:
diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt
index 4682586b147a..3c4b2f1b64d0 100644
--- a/Documentation/filesystems/vfs.txt
+++ b/Documentation/filesystems/vfs.txt
@@ -865,7 +865,7 @@ 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 dentry *, bool);
+        int (*d_manage)(struct dentry *, bool, bool);
 };
 
   d_revalidate: called when the VFS needs to revalidate a dentry. This
@@ -960,6 +960,11 @@ struct dentry_operations {
         held by the caller and the function should not initiate any mounts or
         unmounts that it will then wait for.
 
+        If the 'rcu_walk' parameter is true, then the caller is doing a
+        pathwalk in RCU-walk mode.  Sleeping is not permitted in this mode,
+        and the caller can be asked to leave it and call again by returing
+        -ECHILD.
+
         This function is only used if DCACHE_MANAGE_TRANSIT is set on the
         dentry being transited from.
 
diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c
index 9194e274f849..dbd95512808c 100644
--- a/fs/autofs4/root.c
+++ b/fs/autofs4/root.c
@@ -36,7 +36,7 @@ static long autofs4_root_compat_ioctl(struct file *,unsigned int,unsigned long);
 static int autofs4_dir_open(struct inode *inode, struct file *file);
 static struct dentry *autofs4_lookup(struct inode *,struct dentry *, struct nameidata *);
 static struct vfsmount *autofs4_d_automount(struct path *);
-static int autofs4_d_manage(struct dentry *, bool);
+static int autofs4_d_manage(struct dentry *, bool, bool);
 
 const struct file_operations autofs4_root_operations = {
         .open           = dcache_dir_open,
@@ -450,7 +450,7 @@ done:
         return NULL;
 }
 
-int autofs4_d_manage(struct dentry *dentry, bool mounting_here)
+int autofs4_d_manage(struct dentry *dentry, bool mounting_here, bool rcu_walk)
 {
         struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
 
@@ -464,6 +464,10 @@ int autofs4_d_manage(struct dentry *dentry, bool mounting_here)
                 return 0;
         }
 
+        /* We need to sleep, so we need pathwalk to be in ref-mode */
+        if (rcu_walk)
+                return -ECHILD;
+
         /* Wait for pending expires */
         do_expire_wait(dentry);
 
diff --git a/fs/namei.c b/fs/namei.c
index 373852012713..5c89695ae1e4 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -987,7 +987,8 @@ static int follow_managed(struct path *path, unsigned flags)
                 if (managed & DCACHE_MANAGE_TRANSIT) {
                         BUG_ON(!path->dentry->d_op);
                         BUG_ON(!path->dentry->d_op->d_manage);
-                        ret = path->dentry->d_op->d_manage(path->dentry, false);
+                        ret = path->dentry->d_op->d_manage(path->dentry,
+                                                           false, false);
                         if (ret < 0)
                                 return ret == -EISDIR ? 0 : ret;
                 }
@@ -1048,13 +1049,12 @@ int follow_down_one(struct path *path)
 static bool __follow_mount_rcu(struct nameidata *nd, struct path *path,
                                struct inode **inode, bool reverse_transit)
 {
-        unsigned abort_mask =
-                reverse_transit ? 0 : DCACHE_MANAGE_TRANSIT;
-
         while (d_mountpoint(path->dentry)) {
                 struct vfsmount *mounted;
-                if (path->dentry->d_flags & abort_mask)
-                        return true;
+                if (unlikely(path->dentry->d_flags & DCACHE_MANAGE_TRANSIT) &&
+                    !reverse_transit &&
+                    path->dentry->d_op->d_manage(path->dentry, false, true) < 0)
+                        return false;
                 mounted = __lookup_mnt(path->mnt, path->dentry, 1);
                 if (!mounted)
                         break;
@@ -1132,7 +1132,8 @@ int follow_down(struct path *path, bool mounting_here)
                 if (managed & DCACHE_MANAGE_TRANSIT) {
                         BUG_ON(!path->dentry->d_op);
                         BUG_ON(!path->dentry->d_op->d_manage);
-                        ret = path->dentry->d_op->d_manage(path->dentry, mounting_here);
+                        ret = path->dentry->d_op->d_manage(
+                                path->dentry, mounting_here, false);
                         if (ret < 0)
                                 return ret == -EISDIR ? 0 : ret;
                 }
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 1a87760d6532..f958c19e3ca5 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -168,7 +168,7 @@ 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 dentry *, bool);
+        int (*d_manage)(struct dentry *, bool, bool);
 } ____cacheline_aligned;
 
 /*