Merge branch 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jack/linux-fs

Pull misc filesystem updates from Jan Kara:
 "udf, ext2, quota, fsnotify fixes & cleanups:

   - udf fixes for handling of media without uid/gid

   - udf fixes for some corner cases in parsing of volume recognition
     sequence

   - improvements of fsnotify handling of ENOMEM

   - new ioctl to allow setting of watch descriptor id for inotify (for
     checkpoint - restart)

   - small ext2, reiserfs, quota cleanups"

* 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jack/linux-fs:
  quota: Kill an unused extern entry form quota.h
  reiserfs: Remove VLA from fs/reiserfs/reiserfs.h
  udf: fix potential refcnt problem of nls module
  ext2: change return code to -ENOMEM when failing memory allocation
  udf: Do not mark possibly inconsistent filesystems as closed
  fsnotify: Let userspace know about lost events due to ENOMEM
  fanotify: Avoid lost events due to ENOMEM for unlimited queues
  udf: Remove never implemented mount options
  udf: Update mount option documentation
  udf: Provide saner default for invalid uid / gid
  udf: Clean up handling of invalid uid/gid
  udf: Apply uid/gid mount options also to new inodes & chown
  udf: Ignore [ug]id=ignore mount options
  udf: Fix handling of Partition Descriptors
  udf: Unify common handling of descriptors
  udf: Convert descriptor index definitions to enum
  udf: Allow volume descriptor sequence to be terminated by unrecorded block
  udf: Simplify handling of Volume Descriptor Pointers
  udf: Fix off-by-one in volume descriptor sequence length
  inotify: Extend ioctl to allow to request id of new watch descriptor

Documentation/filesystems/udf.txt

@@ -36,18 +36,14 @@ The following mount options are supported:
 	iocharset=	Set the NLS character set
 
 The uid= and gid= options need a bit more explaining.  They will accept a
-decimal numeric value which will be used as the default ID for that mount.
-They will also accept the string "ignore" and "forget".  For files on the disk
-that are owned by nobody ( -1 ), they will instead look as if they are owned
-by the default ID.  The ignore option causes the default ID to override all
-IDs on the disk, not just -1.  The forget option causes all IDs to be written
-to disk as -1, so when the media is later remounted, they will appear to be
-owned by whatever default ID it is mounted with at that time.
+decimal numeric value and all inodes on that mount will then appear as
+belonging to that uid and gid.  Mount options also accept the string "forget".
+The forget option causes all IDs to be written to disk as -1 which is a way
+of UDF standard to indicate that IDs are not supported for these files .
 
-For typical desktop use of removable media, you should set the ID to that
-of the interactively logged on user, and also specify both the forget and
-ignore options.  This way the interactive user will always see the files
-on the disk as belonging to him.
+For typical desktop use of removable media, you should set the ID to that of
+the interactively logged on user, and also specify the forget option.  This way
+the interactive user will always see the files on the disk as belonging to him.
 
 The remaining are for debugging and disaster recovery:
 
@@ -57,16 +53,8 @@ The following expect a offset from 0.
 
 	session=	Set the CDROM session (default= last session)
 	anchor=		Override standard anchor location. (default= 256)
-	volume=		Override the VolumeDesc location. (unused)
-	partition=	Override the PartitionDesc location. (unused)
 	lastblock=	Set the last block of the filesystem/
 
-The following expect a offset from the partition root.
-
-	fileset=	Override the fileset block location. (unused)
-	rootdir=	Override the root directory location. (unused)
-			WARNING: overriding the rootdir to a non-directory may
-				yield highly unpredictable results.
 -------------------------------------------------------------------------------
 
 

fs/ext2/super.c

@@ -827,7 +827,7 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
 	unsigned long logic_sb_block;
 	unsigned long offset = 0;
 	unsigned long def_mount_opts;
-	long ret = -EINVAL;
+	long ret = -ENOMEM;
 	int blocksize = BLOCK_SIZE;
 	int db_count;
 	int i, j;
@@ -835,7 +835,6 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
 	int err;
 	struct ext2_mount_options opts;
 
-	err = -ENOMEM;
 	sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
 	if (!sbi)
 		goto failed;
@@ -851,6 +850,7 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
 	sbi->s_daxdev = dax_dev;
 
 	spin_lock_init(&sbi->s_lock);
+	ret = -EINVAL;
 
 	/*
 	 * See what the current blocksize for the device is, and

fs/notify/fanotify/fanotify.c

@@ -139,23 +139,32 @@ static bool fanotify_should_send_event(struct fsnotify_mark *inode_mark,
 	return false;
 }
 
-struct fanotify_event_info *fanotify_alloc_event(struct inode *inode, u32 mask,
+struct fanotify_event_info *fanotify_alloc_event(struct fsnotify_group *group,
+						 struct inode *inode, u32 mask,
 						 const struct path *path)
 {
 	struct fanotify_event_info *event;
+	gfp_t gfp = GFP_KERNEL;
+
+	/*
+	 * For queues with unlimited length lost events are not expected and
+	 * can possibly have security implications. Avoid losing events when
+	 * memory is short.
+	 */
+	if (group->max_events == UINT_MAX)
+		gfp |= __GFP_NOFAIL;
 
 	if (fanotify_is_perm_event(mask)) {
 		struct fanotify_perm_event_info *pevent;
 
-		pevent = kmem_cache_alloc(fanotify_perm_event_cachep,
-					  GFP_KERNEL);
+		pevent = kmem_cache_alloc(fanotify_perm_event_cachep, gfp);
 		if (!pevent)
 			return NULL;
 		event = &pevent->fae;
 		pevent->response = 0;
 		goto init;
 	}
-	event = kmem_cache_alloc(fanotify_event_cachep, GFP_KERNEL);
+	event = kmem_cache_alloc(fanotify_event_cachep, gfp);
 	if (!event)
 		return NULL;
 init: __maybe_unused
@@ -210,10 +219,17 @@ static int fanotify_handle_event(struct fsnotify_group *group,
 			return 0;
 	}
 
-	event = fanotify_alloc_event(inode, mask, data);
+	event = fanotify_alloc_event(group, inode, mask, data);
 	ret = -ENOMEM;
-	if (unlikely(!event))
+	if (unlikely(!event)) {
+		/*
+		 * We don't queue overflow events for permission events as
+		 * there the access is denied and so no event is in fact lost.
+		 */
+		if (!fanotify_is_perm_event(mask))
+			fsnotify_queue_overflow(group);
 		goto finish;
+	}
 
 	fsn_event = &event->fse;
 	ret = fsnotify_add_event(group, fsn_event, fanotify_merge);

fs/notify/fanotify/fanotify.h

@@ -52,5 +52,6 @@ static inline struct fanotify_event_info *FANOTIFY_E(struct fsnotify_event *fse)
 	return container_of(fse, struct fanotify_event_info, fse);
 }
 
-struct fanotify_event_info *fanotify_alloc_event(struct inode *inode, u32 mask,
+struct fanotify_event_info *fanotify_alloc_event(struct fsnotify_group *group,
+						 struct inode *inode, u32 mask,
 						 const struct path *path);

fs/notify/fanotify/fanotify_user.c

@@ -757,7 +757,7 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
 	group->fanotify_data.user = user;
 	atomic_inc(&user->fanotify_listeners);
 
-	oevent = fanotify_alloc_event(NULL, FS_Q_OVERFLOW, NULL);
+	oevent = fanotify_alloc_event(group, NULL, FS_Q_OVERFLOW, NULL);
 	if (unlikely(!oevent)) {
 		fd = -ENOMEM;
 		goto out_destroy_group;

fs/notify/inotify/inotify_fsnotify.c

@@ -99,8 +99,14 @@ int inotify_handle_event(struct fsnotify_group *group,
 			      fsn_mark);
 
 	event = kmalloc(alloc_len, GFP_KERNEL);
-	if (unlikely(!event))
+	if (unlikely(!event)) {
+		/*
+		 * Treat lost event due to ENOMEM the same way as queue
+		 * overflow to let userspace know event was lost.
+		 */
+		fsnotify_queue_overflow(group);
 		return -ENOMEM;
+	}
 
 	fsn_event = &event->fse;
 	fsnotify_init_event(fsn_event, inode, mask);

fs/notify/inotify/inotify_user.c

@@ -307,6 +307,20 @@ static long inotify_ioctl(struct file *file, unsigned int cmd,
 		spin_unlock(&group->notification_lock);
 		ret = put_user(send_len, (int __user *) p);
 		break;
+#ifdef CONFIG_CHECKPOINT_RESTORE
+	case INOTIFY_IOC_SETNEXTWD:
+		ret = -EINVAL;
+		if (arg >= 1 && arg <= INT_MAX) {
+			struct inotify_group_private_data *data;
+
+			data = &group->inotify_data;
+			spin_lock(&data->idr_lock);
+			idr_set_cursor(&data->idr, (unsigned int)arg);
+			spin_unlock(&data->idr_lock);
+			ret = 0;
+		}
+		break;
+#endif /* CONFIG_CHECKPOINT_RESTORE */
 	}
 
 	return ret;

fs/notify/notification.c

@@ -111,7 +111,8 @@ int fsnotify_add_event(struct fsnotify_group *group,
 		return 2;
 	}
 
-	if (group->q_len >= group->max_events) {
+	if (event == group->overflow_event ||
+	    group->q_len >= group->max_events) {
 		ret = 2;
 		/* Queue overflow event only if it isn't already queued */
 		if (!list_empty(&group->overflow_event->list)) {

fs/reiserfs/reiserfs.h

@@ -1916,7 +1916,7 @@ struct reiserfs_de_head {
 
 /* empty directory contains two entries "." and ".." and their headers */
 #define EMPTY_DIR_SIZE \
-(DEH_SIZE * 2 + ROUND_UP (strlen (".")) + ROUND_UP (strlen ("..")))
+(DEH_SIZE * 2 + ROUND_UP (sizeof(".") - 1) + ROUND_UP (sizeof("..") - 1))
 
 /* old format directories have this size when empty */
 #define EMPTY_DIR_SIZE_V1 (DEH_SIZE * 2 + 3)

fs/udf/file.c

@@ -257,12 +257,22 @@ const struct file_operations udf_file_operations = {
 static int udf_setattr(struct dentry *dentry, struct iattr *attr)
 {
 	struct inode *inode = d_inode(dentry);
+	struct super_block *sb = inode->i_sb;
 	int error;
 
 	error = setattr_prepare(dentry, attr);
 	if (error)
 		return error;
 
+	if ((attr->ia_valid & ATTR_UID) &&
+	    UDF_QUERY_FLAG(sb, UDF_FLAG_UID_SET) &&
+	    !uid_eq(attr->ia_uid, UDF_SB(sb)->s_uid))
+		return -EPERM;
+	if ((attr->ia_valid & ATTR_GID) &&
+	    UDF_QUERY_FLAG(sb, UDF_FLAG_GID_SET) &&
+	    !gid_eq(attr->ia_gid, UDF_SB(sb)->s_gid))
+		return -EPERM;
+
 	if ((attr->ia_valid & ATTR_SIZE) &&
 	    attr->ia_size != i_size_read(inode)) {
 		error = udf_setsize(inode, attr->ia_size);

fs/udf/ialloc.c

@@ -104,6 +104,10 @@ struct inode *udf_new_inode(struct inode *dir, umode_t mode)
 	}
 
 	inode_init_owner(inode, dir, mode);
+	if (UDF_QUERY_FLAG(sb, UDF_FLAG_UID_SET))
+		inode->i_uid = sbi->s_uid;
+	if (UDF_QUERY_FLAG(sb, UDF_FLAG_GID_SET))
+		inode->i_gid = sbi->s_gid;
 
 	iinfo->i_location.logicalBlockNum = block;
 	iinfo->i_location.partitionReferenceNum =

fs/udf/inode.c

@@ -1275,6 +1275,7 @@ static int udf_read_inode(struct inode *inode, bool hidden_inode)
 	unsigned int indirections = 0;
 	int bs = inode->i_sb->s_blocksize;
 	int ret = -EIO;
+	uint32_t uid, gid;
 
 reread:
 	if (iloc->partitionReferenceNum >= sbi->s_partitions) {
@@ -1400,17 +1401,19 @@ static int udf_read_inode(struct inode *inode, bool hidden_inode)
 
 	ret = -EIO;
 	read_lock(&sbi->s_cred_lock);
-	i_uid_write(inode, le32_to_cpu(fe->uid));
-	if (!uid_valid(inode->i_uid) ||
-	    UDF_QUERY_FLAG(inode->i_sb, UDF_FLAG_UID_IGNORE) ||
+	uid = le32_to_cpu(fe->uid);
+	if (uid == UDF_INVALID_ID ||
 	    UDF_QUERY_FLAG(inode->i_sb, UDF_FLAG_UID_SET))
-		inode->i_uid = UDF_SB(inode->i_sb)->s_uid;
+		inode->i_uid = sbi->s_uid;
+	else
+		i_uid_write(inode, uid);
 
-	i_gid_write(inode, le32_to_cpu(fe->gid));
-	if (!gid_valid(inode->i_gid) ||
-	    UDF_QUERY_FLAG(inode->i_sb, UDF_FLAG_GID_IGNORE) ||
+	gid = le32_to_cpu(fe->gid);
+	if (gid == UDF_INVALID_ID ||
 	    UDF_QUERY_FLAG(inode->i_sb, UDF_FLAG_GID_SET))
-		inode->i_gid = UDF_SB(inode->i_sb)->s_gid;
+		inode->i_gid = sbi->s_gid;
+	else
+		i_gid_write(inode, gid);
 
 	if (fe->icbTag.fileType != ICBTAG_FILE_TYPE_DIRECTORY &&
 			sbi->s_fmode != UDF_INVALID_MODE)
@@ -1655,12 +1658,12 @@ static int udf_update_inode(struct inode *inode, int do_sync)
 	}
 
 	if (UDF_QUERY_FLAG(inode->i_sb, UDF_FLAG_UID_FORGET))
-		fe->uid = cpu_to_le32(-1);
+		fe->uid = cpu_to_le32(UDF_INVALID_ID);
 	else
 		fe->uid = cpu_to_le32(i_uid_read(inode));
 
 	if (UDF_QUERY_FLAG(inode->i_sb, UDF_FLAG_GID_FORGET))
-		fe->gid = cpu_to_le32(-1);
+		fe->gid = cpu_to_le32(UDF_INVALID_ID);
 	else
 		fe->gid = cpu_to_le32(i_gid_read(inode));
 

fs/udf/udf_sb.h

@@ -23,14 +23,13 @@
 #define UDF_FLAG_NLS_MAP		9
 #define UDF_FLAG_UTF8			10
 #define UDF_FLAG_UID_FORGET     11    /* save -1 for uid to disk */
-#define UDF_FLAG_UID_IGNORE     12    /* use sb uid instead of on disk uid */
-#define UDF_FLAG_GID_FORGET     13
-#define UDF_FLAG_GID_IGNORE     14
-#define UDF_FLAG_UID_SET	15
-#define UDF_FLAG_GID_SET	16
-#define UDF_FLAG_SESSION_SET	17
-#define UDF_FLAG_LASTBLOCK_SET	18
-#define UDF_FLAG_BLOCKSIZE_SET	19
+#define UDF_FLAG_GID_FORGET     12
+#define UDF_FLAG_UID_SET	13
+#define UDF_FLAG_GID_SET	14
+#define UDF_FLAG_SESSION_SET	15
+#define UDF_FLAG_LASTBLOCK_SET	16
+#define UDF_FLAG_BLOCKSIZE_SET	17
+#define UDF_FLAG_INCONSISTENT	18
 
 #define UDF_PART_FLAG_UNALLOC_BITMAP	0x0001
 #define UDF_PART_FLAG_UNALLOC_TABLE	0x0002

fs/udf/udfdecl.h

@@ -48,6 +48,8 @@ extern __printf(3, 4) void _udf_warn(struct super_block *sb,
 #define UDF_EXTENT_LENGTH_MASK	0x3FFFFFFF
 #define UDF_EXTENT_FLAG_MASK	0xC0000000
 
+#define UDF_INVALID_ID ((uint32_t)-1)
+
 #define UDF_NAME_PAD		4
 #define UDF_NAME_LEN		254
 #define UDF_NAME_LEN_CS0	255

include/linux/fsnotify_backend.h

@@ -331,6 +331,12 @@ extern int fsnotify_add_event(struct fsnotify_group *group,
 			      struct fsnotify_event *event,
 			      int (*merge)(struct list_head *,
 					   struct fsnotify_event *));
+/* Queue overflow event to a notification group */
+static inline void fsnotify_queue_overflow(struct fsnotify_group *group)
+{
+	fsnotify_add_event(group, group->overflow_event, NULL);
+}
+
 /* true if the group notification queue is empty */
 extern bool fsnotify_notify_queue_is_empty(struct fsnotify_group *group);
 /* return, but do not dequeue the first event on the notification queue */

include/linux/quota.h

@@ -267,7 +267,6 @@ struct dqstats {
 	struct percpu_counter counter[_DQST_DQSTAT_LAST];
 };
 
-extern struct dqstats *dqstats_pcpu;
 extern struct dqstats dqstats;
 
 static inline void dqstats_inc(unsigned int type)

include/uapi/linux/inotify.h

@@ -71,5 +71,13 @@ struct inotify_event {
 #define IN_CLOEXEC O_CLOEXEC
 #define IN_NONBLOCK O_NONBLOCK
 
+/*
+ * ioctl numbers: inotify uses 'I' prefix for all ioctls,
+ * except historical FIONREAD, which is based on 'T'.
+ *
+ * INOTIFY_IOC_SETNEXTWD: set desired number of next created
+ * watch descriptor.
+ */
+#define INOTIFY_IOC_SETNEXTWD	_IOW('I', 0, __s32)
 
 #endif /* _UAPI_LINUX_INOTIFY_H */