Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel…

…/git/viro/vfs

Pull vfs fixes from Al Viro:
 "Followups to the parallel lookup work:

   - update docs

   - restore killability of the places that used to take ->i_mutex
     killably now that we have down_write_killable() merged

   - Additionally, it turns out that I missed a prerequisite for
     security_d_instantiate() stuff - ->getxattr() wasn't the only thing
     that could be called before dentry is attached to inode; with smack
     we needed the same treatment applied to ->setxattr() as well"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
  switch ->setxattr() to passing dentry and inode separately
  switch xattr_handler->set() to passing dentry and inode separately
  restore killability of old mutex_lock_killable(&inode->i_mutex) users
  add down_write_killable_nested()
  update D/f/directory-locking

Documentation/filesystems/directory-locking

@@ -1,30 +1,37 @@
 	Locking scheme used for directory operations is based on two
-kinds of locks - per-inode (->i_mutex) and per-filesystem
+kinds of locks - per-inode (->i_rwsem) and per-filesystem
 (->s_vfs_rename_mutex).
 
-	When taking the i_mutex on multiple non-directory objects, we
+	When taking the i_rwsem on multiple non-directory objects, we
 always acquire the locks in order by increasing address.  We'll call
 that "inode pointer" order in the following.
 
 	For our purposes all operations fall in 5 classes:
 
 1) read access.  Locking rules: caller locks directory we are accessing.
+The lock is taken shared.
 
-2) object creation.  Locking rules: same as above.
+2) object creation.  Locking rules: same as above, but the lock is taken
+exclusive.
 
 3) object removal.  Locking rules: caller locks parent, finds victim,
-locks victim and calls the method.
+locks victim and calls the method.  Locks are exclusive.
 
 4) rename() that is _not_ cross-directory.  Locking rules: caller locks
-the parent and finds source and target.  If target already exists, lock
-it.  If source is a non-directory, lock it.  If that means we need to
-lock both, lock them in inode pointer order.
+the parent and finds source and target.  In case of exchange (with
+RENAME_EXCHANGE in rename2() flags argument) lock both.  In any case,
+if the target already exists, lock it.  If the source is a non-directory,
+lock it.  If we need to lock both, lock them in inode pointer order.
+Then call the method.  All locks are exclusive.
+NB: we might get away with locking the the source (and target in exchange
+case) shared.
 
 5) link creation.  Locking rules:
 	* lock parent
 	* check that source is not a directory
 	* lock source
 	* call the method.
+All locks are exclusive.
 
 6) cross-directory rename.  The trickiest in the whole bunch.  Locking
 rules:
@@ -35,11 +42,12 @@ rules:
 		fail with -ENOTEMPTY
 	* if new parent is equal to or is a descendent of source
 		fail with -ELOOP
-	* If target exists, lock it.  If source is a non-directory, lock
-	  it.  In case that means we need to lock both source and target,
-	  do so in inode pointer order.
+	* If it's an exchange, lock both the source and the target.
+	* If the target exists, lock it.  If the source is a non-directory,
+	  lock it.  If we need to lock both, do so in inode pointer order.
 	* call the method.
-
+All ->i_rwsem are taken exclusive.  Again, we might get away with locking
+the the source (and target in exchange case) shared.
 
 The rules above obviously guarantee that all directories that are going to be
 read, modified or removed by method will be locked by caller.
@@ -73,7 +81,7 @@ objects - A < B iff A is an ancestor of B.
 attempt to acquire some lock and already holds at least one lock.  Let's
 consider the set of contended locks.  First of all, filesystem lock is
 not contended, since any process blocked on it is not holding any locks.
-Thus all processes are blocked on ->i_mutex.
+Thus all processes are blocked on ->i_rwsem.
 
 	By (3), any process holding a non-directory lock can only be
 waiting on another non-directory lock with a larger address.  Therefore

Documentation/filesystems/porting

@@ -578,3 +578,10 @@ in your dentry operations instead.
 --
 [mandatory]
 	->atomic_open() calls without O_CREAT may happen in parallel.
+--
+[mandatory]
+	->setxattr() and xattr_handler.set() get dentry and inode passed separately.
+	dentry might be yet to be attached to inode, so do _not_ use its ->d_inode
+	in the instances.  Rationale: !@#!@# security_d_instantiate() needs to be
+	called before we attach dentry to inode and !@#!@##!@$!$#!@#$!@$!@$ smack
+	->d_instantiate() uses not just ->getxattr() but ->setxattr() as well.

drivers/staging/lustre/lustre/llite/llite_internal.h

@@ -976,8 +976,8 @@ static inline __u64 ll_file_maxbytes(struct inode *inode)
 }
 
 /* llite/xattr.c */
-int ll_setxattr(struct dentry *dentry, const char *name,
-		const void *value, size_t size, int flags);
+int ll_setxattr(struct dentry *dentry, struct inode *inode,
+		const char *name, const void *value, size_t size, int flags);
 ssize_t ll_getxattr(struct dentry *dentry, struct inode *inode,
 		    const char *name, void *buffer, size_t size);
 ssize_t ll_listxattr(struct dentry *dentry, char *buffer, size_t size);

drivers/staging/lustre/lustre/llite/xattr.c

@@ -211,11 +211,9 @@ int ll_setxattr_common(struct inode *inode, const char *name,
 	return 0;
 }
 
-int ll_setxattr(struct dentry *dentry, const char *name,
-		const void *value, size_t size, int flags)
+int ll_setxattr(struct dentry *dentry, struct inode *inode,
+		const char *name, const void *value, size_t size, int flags)
 {
-	struct inode *inode = d_inode(dentry);
-
 	LASSERT(inode);
 	LASSERT(name);
 

fs/9p/acl.c

@@ -239,13 +239,13 @@ static int v9fs_xattr_get_acl(const struct xattr_handler *handler,
 }
 
 static int v9fs_xattr_set_acl(const struct xattr_handler *handler,
-			      struct dentry *dentry, const char *name,
-			      const void *value, size_t size, int flags)
+			      struct dentry *dentry, struct inode *inode,
+			      const char *name, const void *value,
+			      size_t size, int flags)
 {
 	int retval;
 	struct posix_acl *acl;
 	struct v9fs_session_info *v9ses;
-	struct inode *inode = d_inode(dentry);
 
 	v9ses = v9fs_dentry2v9ses(dentry);
 	/*

fs/9p/xattr.c

@@ -147,8 +147,9 @@ static int v9fs_xattr_handler_get(const struct xattr_handler *handler,
 }
 
 static int v9fs_xattr_handler_set(const struct xattr_handler *handler,
-				  struct dentry *dentry, const char *name,
-				  const void *value, size_t size, int flags)
+				  struct dentry *dentry, struct inode *inode,
+				  const char *name, const void *value,
+				  size_t size, int flags)
 {
 	const char *full_name = xattr_full_name(handler, name);
 

fs/bad_inode.c

@@ -100,8 +100,8 @@ static int bad_inode_setattr(struct dentry *direntry, struct iattr *attrs)
 	return -EIO;
 }
 
-static int bad_inode_setxattr(struct dentry *dentry, const char *name,
-		const void *value, size_t size, int flags)
+static int bad_inode_setxattr(struct dentry *dentry, struct inode *inode,
+		const char *name, const void *value, size_t size, int flags)
 {
 	return -EIO;
 }

fs/btrfs/ioctl.c

@@ -846,11 +846,9 @@ static noinline int btrfs_mksubvol(struct path *parent,
 	struct dentry *dentry;
 	int error;
 
-	inode_lock_nested(dir, I_MUTEX_PARENT);
-	// XXX: should've been
-	// mutex_lock_killable_nested(&dir->i_mutex, I_MUTEX_PARENT);
-	// if (error == -EINTR)
-	//	return error;
+	error = down_write_killable_nested(&dir->i_rwsem, I_MUTEX_PARENT);
+	if (error == -EINTR)
+		return error;
 
 	dentry = lookup_one_len(name, parent->dentry, namelen);
 	error = PTR_ERR(dentry);
@@ -2377,11 +2375,9 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
 		goto out;
 
 
-	inode_lock_nested(dir, I_MUTEX_PARENT);
-	// XXX: should've been
-	// err = mutex_lock_killable_nested(&dir->i_mutex, I_MUTEX_PARENT);
-	// if (err == -EINTR)
-	//	goto out_drop_write;
+	err = down_write_killable_nested(&dir->i_rwsem, I_MUTEX_PARENT);
+	if (err == -EINTR)
+		goto out_drop_write;
 	dentry = lookup_one_len(vol_args->name, parent, namelen);
 	if (IS_ERR(dentry)) {
 		err = PTR_ERR(dentry);
@@ -2571,7 +2567,7 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
 	dput(dentry);
 out_unlock_dir:
 	inode_unlock(dir);
-//out_drop_write:
+out_drop_write:
 	mnt_drop_write_file(file);
 out:
 	kfree(vol_args);

fs/btrfs/xattr.c

@@ -380,23 +380,21 @@ static int btrfs_xattr_handler_get(const struct xattr_handler *handler,
 }
 
 static int btrfs_xattr_handler_set(const struct xattr_handler *handler,
-				   struct dentry *dentry, const char *name,
-				   const void *buffer, size_t size,
-				   int flags)
+				   struct dentry *unused, struct inode *inode,
+				   const char *name, const void *buffer,
+				   size_t size, int flags)
 {
-	struct inode *inode = d_inode(dentry);
-
 	name = xattr_full_name(handler, name);
 	return __btrfs_setxattr(NULL, inode, name, buffer, size, flags);
 }
 
 static int btrfs_xattr_handler_set_prop(const struct xattr_handler *handler,
-					struct dentry *dentry,
+					struct dentry *unused, struct inode *inode,
 					const char *name, const void *value,
 					size_t size, int flags)
 {
 	name = xattr_full_name(handler, name);
-	return btrfs_set_prop(d_inode(dentry), name, value, size, flags);
+	return btrfs_set_prop(inode, name, value, size, flags);
 }
 
 static const struct xattr_handler btrfs_security_xattr_handler = {

fs/ceph/xattr.c

@@ -1056,12 +1056,13 @@ static int ceph_get_xattr_handler(const struct xattr_handler *handler,
 }
 
 static int ceph_set_xattr_handler(const struct xattr_handler *handler,
-				  struct dentry *dentry, const char *name,
-				  const void *value, size_t size, int flags)
+				  struct dentry *unused, struct inode *inode,
+				  const char *name, const void *value,
+				  size_t size, int flags)
 {
 	if (!ceph_is_valid_xattr(name))
 		return -EOPNOTSUPP;
-	return __ceph_setxattr(d_inode(dentry), name, value, size, flags);
+	return __ceph_setxattr(inode, name, value, size, flags);
 }
 
 const struct xattr_handler ceph_other_xattr_handler = {

fs/cifs/xattr.c

@@ -39,8 +39,9 @@
 enum { XATTR_USER, XATTR_CIFS_ACL, XATTR_ACL_ACCESS, XATTR_ACL_DEFAULT };
 
 static int cifs_xattr_set(const struct xattr_handler *handler,
-			  struct dentry *dentry, const char *name,
-			  const void *value, size_t size, int flags)
+			  struct dentry *dentry, struct inode *inode,
+			  const char *name, const void *value,
+			  size_t size, int flags)
 {
 	int rc = -EOPNOTSUPP;
 	unsigned int xid;
@@ -99,12 +100,12 @@ static int cifs_xattr_set(const struct xattr_handler *handler,
 			if (value &&
 			    pTcon->ses->server->ops->set_acl)
 				rc = pTcon->ses->server->ops->set_acl(pacl,
-						size, d_inode(dentry),
+						size, inode,
 						full_path, CIFS_ACL_DACL);
 			else
 				rc = -EOPNOTSUPP;
 			if (rc == 0) /* force revalidate of the inode */
-				CIFS_I(d_inode(dentry))->time = 0;
+				CIFS_I(inode)->time = 0;
 			kfree(pacl);
 		}
 #endif /* CONFIG_CIFS_ACL */

fs/ecryptfs/crypto.c

@@ -1141,12 +1141,13 @@ ecryptfs_write_metadata_to_contents(struct inode *ecryptfs_inode,
 
 static int
 ecryptfs_write_metadata_to_xattr(struct dentry *ecryptfs_dentry,
+				 struct inode *ecryptfs_inode,
 				 char *page_virt, size_t size)
 {
 	int rc;
 
-	rc = ecryptfs_setxattr(ecryptfs_dentry, ECRYPTFS_XATTR_NAME, page_virt,
-			       size, 0);
+	rc = ecryptfs_setxattr(ecryptfs_dentry, ecryptfs_inode,
+			       ECRYPTFS_XATTR_NAME, page_virt, size, 0);
 	return rc;
 }
 
@@ -1215,8 +1216,8 @@ int ecryptfs_write_metadata(struct dentry *ecryptfs_dentry,
 		goto out_free;
 	}
 	if (crypt_stat->flags & ECRYPTFS_METADATA_IN_XATTR)
-		rc = ecryptfs_write_metadata_to_xattr(ecryptfs_dentry, virt,
-						      size);
+		rc = ecryptfs_write_metadata_to_xattr(ecryptfs_dentry, ecryptfs_inode,
+						      virt, size);
 	else
 		rc = ecryptfs_write_metadata_to_contents(ecryptfs_inode, virt,
 							 virt_len);

fs/ecryptfs/ecryptfs_kernel.h

@@ -609,8 +609,8 @@ ssize_t
 ecryptfs_getxattr_lower(struct dentry *lower_dentry, struct inode *lower_inode,
 			const char *name, void *value, size_t size);
 int
-ecryptfs_setxattr(struct dentry *dentry, const char *name, const void *value,
-		  size_t size, int flags);
+ecryptfs_setxattr(struct dentry *dentry, struct inode *inode, const char *name,
+		  const void *value, size_t size, int flags);
 int ecryptfs_read_xattr_region(char *page_virt, struct inode *ecryptfs_inode);
 #ifdef CONFIG_ECRYPT_FS_MESSAGING
 int ecryptfs_process_response(struct ecryptfs_daemon *daemon,

fs/ecryptfs/inode.c

@@ -1001,7 +1001,8 @@ static int ecryptfs_getattr(struct vfsmount *mnt, struct dentry *dentry,
 }
 
 int
-ecryptfs_setxattr(struct dentry *dentry, const char *name, const void *value,
+ecryptfs_setxattr(struct dentry *dentry, struct inode *inode,
+		  const char *name, const void *value,
 		  size_t size, int flags)
 {
 	int rc = 0;
@@ -1014,8 +1015,8 @@ ecryptfs_setxattr(struct dentry *dentry, const char *name, const void *value,
 	}
 
 	rc = vfs_setxattr(lower_dentry, name, value, size, flags);
-	if (!rc && d_really_is_positive(dentry))
-		fsstack_copy_attr_all(d_inode(dentry), d_inode(lower_dentry));
+	if (!rc && inode)
+		fsstack_copy_attr_all(inode, d_inode(lower_dentry));
 out:
 	return rc;
 }

fs/ecryptfs/mmap.c

@@ -442,7 +442,8 @@ static int ecryptfs_write_inode_size_to_xattr(struct inode *ecryptfs_inode)
 	if (size < 0)
 		size = 8;
 	put_unaligned_be64(i_size_read(ecryptfs_inode), xattr_virt);
-	rc = lower_inode->i_op->setxattr(lower_dentry, ECRYPTFS_XATTR_NAME,
+	rc = lower_inode->i_op->setxattr(lower_dentry, lower_inode,
+					 ECRYPTFS_XATTR_NAME,
 					 xattr_virt, size, 0);
 	inode_unlock(lower_inode);
 	if (rc)

fs/ext2/xattr_security.c

@@ -18,10 +18,11 @@ ext2_xattr_security_get(const struct xattr_handler *handler,
 
 static int
 ext2_xattr_security_set(const struct xattr_handler *handler,
-			struct dentry *dentry, const char *name,
-			const void *value, size_t size, int flags)
+			struct dentry *unused, struct inode *inode,
+			const char *name, const void *value,
+			size_t size, int flags)
 {
-	return ext2_xattr_set(d_inode(dentry), EXT2_XATTR_INDEX_SECURITY, name,
+	return ext2_xattr_set(inode, EXT2_XATTR_INDEX_SECURITY, name,
 			      value, size, flags);
 }
 

fs/ext2/xattr_trusted.c

@@ -25,10 +25,11 @@ ext2_xattr_trusted_get(const struct xattr_handler *handler,
 
 static int
 ext2_xattr_trusted_set(const struct xattr_handler *handler,
-		       struct dentry *dentry, const char *name,
-		       const void *value, size_t size, int flags)
+		       struct dentry *unused, struct inode *inode,
+		       const char *name, const void *value,
+		       size_t size, int flags)
 {
-	return ext2_xattr_set(d_inode(dentry), EXT2_XATTR_INDEX_TRUSTED, name,
+	return ext2_xattr_set(inode, EXT2_XATTR_INDEX_TRUSTED, name,
 			      value, size, flags);
 }
 

fs/ext2/xattr_user.c

@@ -29,13 +29,14 @@ ext2_xattr_user_get(const struct xattr_handler *handler,
 
 static int
 ext2_xattr_user_set(const struct xattr_handler *handler,
-		    struct dentry *dentry, const char *name,
-		    const void *value, size_t size, int flags)
+		    struct dentry *unused, struct inode *inode,
+		    const char *name, const void *value,
+		    size_t size, int flags)
 {
-	if (!test_opt(dentry->d_sb, XATTR_USER))
+	if (!test_opt(inode->i_sb, XATTR_USER))
 		return -EOPNOTSUPP;
 
-	return ext2_xattr_set(d_inode(dentry), EXT2_XATTR_INDEX_USER,
+	return ext2_xattr_set(inode, EXT2_XATTR_INDEX_USER,
 			      name, value, size, flags);
 }
 

fs/ext4/xattr_security.c

@@ -22,10 +22,11 @@ ext4_xattr_security_get(const struct xattr_handler *handler,
 
 static int
 ext4_xattr_security_set(const struct xattr_handler *handler,
-			struct dentry *dentry, const char *name,
-			const void *value, size_t size, int flags)
+			struct dentry *unused, struct inode *inode,
+			const char *name, const void *value,
+			size_t size, int flags)
 {
-	return ext4_xattr_set(d_inode(dentry), EXT4_XATTR_INDEX_SECURITY,
+	return ext4_xattr_set(inode, EXT4_XATTR_INDEX_SECURITY,
 			      name, value, size, flags);
 }