Pass parent directory inode and expected name to ->d_revalidate()

->d_revalidate() often needs to access dentry parent and name; that has
to be done carefully, since the locking environment varies from caller
to caller.  We are not guaranteed that dentry in question will not be
moved right under us - not unless the filesystem is such that nothing
on it ever gets renamed.

It can be dealt with, but that results in boilerplate code that isn't
even needed - the callers normally have just found the dentry via dcache
lookup and want to verify that it's in the right place; they already
have the values of ->d_parent and ->d_name stable.  There is a couple
of exceptions (overlayfs and, to less extent, ecryptfs), but for the
majority of calls that song and dance is not needed at all.

It's easier to make ecryptfs and overlayfs find and pass those values if
there's a ->d_revalidate() instance to be called, rather than doing that
in the instances.

This commit only changes the calling conventions; making use of supplied
values is left to followups.

NOTE: some instances need more than just the parent - things like CIFS
may need to build an entire path from filesystem root, so they need
more precautions than the usual boilerplate.  This series doesn't
do anything to that need - these filesystems have to keep their locking
mechanisms (rename_lock loops, use of dentry_path_raw(), private rwsem
a-la v9fs).

One thing to keep in mind when using name is that name->name will normally
point into the pathname being resolved; the filename in question occupies
name->len bytes starting at name->name, and there is NUL somewhere after it,
but it the next byte might very well be '/' rather than '\0'.  Do not
ignore name->len.

Reviewed-by: Jeff Layton <[email protected]>
Reviewed-by: Gabriel Krisman Bertazi <[email protected]>
Signed-off-by: Al Viro <[email protected]>

Author: Al Viro

Documentation/filesystems/locking.rst

@@ -17,7 +17,8 @@ dentry_operations
 
 prototypes::
 
-	int (*d_revalidate)(struct dentry *, unsigned int);
+	int (*d_revalidate)(struct inode *, const struct qstr *,
+			    struct dentry *, unsigned int);
 	int (*d_weak_revalidate)(struct dentry *, unsigned int);
 	int (*d_hash)(const struct dentry *, struct qstr *);
 	int (*d_compare)(const struct dentry *,

Documentation/filesystems/porting.rst

@@ -1141,3 +1141,19 @@ pointer are gone.
 
 set_blocksize() takes opened struct file instead of struct block_device now
 and it *must* be opened exclusive.
+
+---
+
+** mandatory**
+
+->d_revalidate() gets two extra arguments - inode of parent directory and
+name our dentry is expected to have.  Both are stable (dir is pinned in
+non-RCU case and will stay around during the call in RCU case, and name
+is guaranteed to stay unchanging).  Your instance doesn't have to use
+either, but it often helps to avoid a lot of painful boilerplate.
+Note that while name->name is stable and NUL-terminated, it may (and
+often will) have name->name[name->len] equal to '/' rather than '\0' -
+in normal case it points into the pathname being looked up.
+NOTE: if you need something like full path from the root of filesystem,
+you are still on your own - this assists with simple cases, but it's not
+magic.

Documentation/filesystems/vfs.rst

@@ -1251,7 +1251,8 @@ defined:
 .. code-block:: c
 
 	struct dentry_operations {
-		int (*d_revalidate)(struct dentry *, unsigned int);
+		int (*d_revalidate)(struct inode *, const struct qstr *,
+				    struct dentry *, unsigned int);
 		int (*d_weak_revalidate)(struct dentry *, unsigned int);
 		int (*d_hash)(const struct dentry *, struct qstr *);
 		int (*d_compare)(const struct dentry *,

fs/9p/vfs_dentry.c

@@ -61,7 +61,7 @@ static void v9fs_dentry_release(struct dentry *dentry)
 		p9_fid_put(hlist_entry(p, struct p9_fid, dlist));
 }
 
-static int v9fs_lookup_revalidate(struct dentry *dentry, unsigned int flags)
+static int __v9fs_lookup_revalidate(struct dentry *dentry, unsigned int flags)
 {
 	struct p9_fid *fid;
 	struct inode *inode;
@@ -99,9 +99,15 @@ static int v9fs_lookup_revalidate(struct dentry *dentry, unsigned int flags)
 	return 1;
 }
 
+static int v9fs_lookup_revalidate(struct inode *dir, const struct qstr *name,
+				  struct dentry *dentry, unsigned int flags)
+{
+	return __v9fs_lookup_revalidate(dentry, flags);
+}
+
 const struct dentry_operations v9fs_cached_dentry_operations = {
 	.d_revalidate = v9fs_lookup_revalidate,
-	.d_weak_revalidate = v9fs_lookup_revalidate,
+	.d_weak_revalidate = __v9fs_lookup_revalidate,
 	.d_delete = v9fs_cached_dentry_delete,
 	.d_release = v9fs_dentry_release,
 };

fs/afs/dir.c

@@ -22,7 +22,8 @@ static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry,
 				 unsigned int flags);
 static int afs_dir_open(struct inode *inode, struct file *file);
 static int afs_readdir(struct file *file, struct dir_context *ctx);
-static int afs_d_revalidate(struct dentry *dentry, unsigned int flags);
+static int afs_d_revalidate(struct inode *dir, const struct qstr *name,
+			    struct dentry *dentry, unsigned int flags);
 static int afs_d_delete(const struct dentry *dentry);
 static void afs_d_iput(struct dentry *dentry, struct inode *inode);
 static bool afs_lookup_one_filldir(struct dir_context *ctx, const char *name, int nlen,
@@ -1093,7 +1094,8 @@ static int afs_d_revalidate_rcu(struct dentry *dentry)
  * - NOTE! the hit can be a negative hit too, so we can't assume we have an
  *   inode
  */
-static int afs_d_revalidate(struct dentry *dentry, unsigned int flags)
+static int afs_d_revalidate(struct inode *parent_dir, const struct qstr *name,
+			    struct dentry *dentry, unsigned int flags)
 {
 	struct afs_vnode *vnode, *dir;
 	struct afs_fid fid;

fs/ceph/dir.c

@@ -1940,15 +1940,16 @@ static int dir_lease_is_valid(struct inode *dir, struct dentry *dentry,
 /*
  * Check if cached dentry can be trusted.
  */
-static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags)
+static int ceph_d_revalidate(struct inode *parent_dir, const struct qstr *name,
+			     struct dentry *dentry, unsigned int flags)
 {
 	struct ceph_mds_client *mdsc = ceph_sb_to_fs_client(dentry->d_sb)->mdsc;
 	struct ceph_client *cl = mdsc->fsc->client;
 	int valid = 0;
 	struct dentry *parent;
 	struct inode *dir, *inode;
 
-	valid = fscrypt_d_revalidate(dentry, flags);
+	valid = fscrypt_d_revalidate(parent_dir, name, dentry, flags);
 	if (valid <= 0)
 		return valid;
 

fs/coda/dir.c

@@ -445,7 +445,8 @@ static int coda_readdir(struct file *coda_file, struct dir_context *ctx)
 }
 
 /* called when a cache lookup succeeds */
-static int coda_dentry_revalidate(struct dentry *de, unsigned int flags)
+static int coda_dentry_revalidate(struct inode *dir, const struct qstr *name,
+				  struct dentry *de, unsigned int flags)
 {
 	struct inode *inode;
 	struct coda_inode_info *cii;

fs/crypto/fname.c

@@ -574,7 +574,8 @@ EXPORT_SYMBOL_GPL(fscrypt_fname_siphash);
  * Validate dentries in encrypted directories to make sure we aren't potentially
  * caching stale dentries after a key has been added.
  */
-int fscrypt_d_revalidate(struct dentry *dentry, unsigned int flags)
+int fscrypt_d_revalidate(struct inode *parent_dir, const struct qstr *name,
+			 struct dentry *dentry, unsigned int flags)
 {
 	struct dentry *dir;
 	int err;

fs/ecryptfs/dentry.c

@@ -17,7 +17,9 @@
 
 /**
  * ecryptfs_d_revalidate - revalidate an ecryptfs dentry
- * @dentry: The ecryptfs dentry
+ * @dir: inode of expected parent
+ * @name: expected name
+ * @dentry: dentry to revalidate
  * @flags: lookup flags
  *
  * Called when the VFS needs to revalidate a dentry. This
@@ -28,16 +30,24 @@
  * Returns 1 if valid, 0 otherwise.
  *
  */
-static int ecryptfs_d_revalidate(struct dentry *dentry, unsigned int flags)
+static int ecryptfs_d_revalidate(struct inode *dir, const struct qstr *name,
+				 struct dentry *dentry, unsigned int flags)
 {
 	struct dentry *lower_dentry = ecryptfs_dentry_to_lower(dentry);
 	int rc = 1;
 
 	if (flags & LOOKUP_RCU)
 		return -ECHILD;
 
-	if (lower_dentry->d_flags & DCACHE_OP_REVALIDATE)
-		rc = lower_dentry->d_op->d_revalidate(lower_dentry, flags);
+	if (lower_dentry->d_flags & DCACHE_OP_REVALIDATE) {
+		struct inode *lower_dir = ecryptfs_inode_to_lower(dir);
+		struct name_snapshot n;
+
+		take_dentry_name_snapshot(&n, lower_dentry);
+		rc = lower_dentry->d_op->d_revalidate(lower_dir, &n.name,
+						      lower_dentry, flags);
+		release_dentry_name_snapshot(&n);
+	}
 
 	if (d_really_is_positive(dentry)) {
 		struct inode *inode = d_inode(dentry);

fs/exfat/namei.c

@@ -31,7 +31,8 @@ static inline void exfat_d_version_set(struct dentry *dentry,
  * If it happened, the negative dentry isn't actually negative anymore.  So,
  * drop it.
  */
-static int exfat_d_revalidate(struct dentry *dentry, unsigned int flags)
+static int exfat_d_revalidate(struct inode *dir, const struct qstr *name,
+			      struct dentry *dentry, unsigned int flags)
 {
 	int ret;