Merge tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4

Pull ext4 updates from Ted Ts'o:
 "Add as a feature case-insensitive directories (the casefold feature)
  using Unicode 12.1.

  Also, the usual largish number of cleanups and bug fixes"

* tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (25 commits)
  ext4: export /sys/fs/ext4/feature/casefold if Unicode support is present
  ext4: fix ext4_show_options for file systems w/o journal
  unicode: refactor the rule for regenerating utf8data.h
  docs: ext4.rst: document case-insensitive directories
  ext4: Support case-insensitive file name lookups
  ext4: include charset encoding information in the superblock
  MAINTAINERS: add Unicode subsystem entry
  unicode: update unicode database unicode version 12.1.0
  unicode: introduce test module for normalized utf8 implementation
  unicode: implement higher level API for string handling
  unicode: reduce the size of utf8data[]
  unicode: introduce code for UTF-8 normalization
  unicode: introduce UTF-8 character database
  ext4: actually request zeroing of inode table after grow
  ext4: cond_resched in work-heavy group loops
  ext4: fix use-after-free race with debug_want_extra_isize
  ext4: avoid drop reference to iloc.bh twice
  ext4: ignore e_value_offs for xattrs with value-in-ea-inode
  ext4: protect journal inode's blocks using block_validity
  ext4: use BUG() instead of BUG_ON(1)
  ...

Author: torvalds

Documentation/admin-guide/ext4.rst

@@ -91,10 +91,48 @@ Currently Available
 * large block (up to pagesize) support
 * efficient new ordered mode in JBD2 and ext4 (avoid using buffer head to force
   the ordering)
+* Case-insensitive file name lookups
 
 [1] Filesystems with a block size of 1k may see a limit imposed by the
 directory hash tree having a maximum depth of two.
 
+case-insensitive file name lookups
+======================================================
+
+The case-insensitive file name lookup feature is supported on a
+per-directory basis, allowing the user to mix case-insensitive and
+case-sensitive directories in the same filesystem.  It is enabled by
+flipping the +F inode attribute of an empty directory.  The
+case-insensitive string match operation is only defined when we know how
+text in encoded in a byte sequence.  For that reason, in order to enable
+case-insensitive directories, the filesystem must have the
+casefold feature, which stores the filesystem-wide encoding
+model used.  By default, the charset adopted is the latest version of
+Unicode (12.1.0, by the time of this writing), encoded in the UTF-8
+form.  The comparison algorithm is implemented by normalizing the
+strings to the Canonical decomposition form, as defined by Unicode,
+followed by a byte per byte comparison.
+
+The case-awareness is name-preserving on the disk, meaning that the file
+name provided by userspace is a byte-per-byte match to what is actually
+written in the disk.  The Unicode normalization format used by the
+kernel is thus an internal representation, and not exposed to the
+userspace nor to the disk, with the important exception of disk hashes,
+used on large case-insensitive directories with DX feature.  On DX
+directories, the hash must be calculated using the casefolded version of
+the filename, meaning that the normalization format used actually has an
+impact on where the directory entry is stored.
+
+When we change from viewing filenames as opaque byte sequences to seeing
+them as encoded strings we need to address what happens when a program
+tries to create a file with an invalid name.  The Unicode subsystem
+within the kernel leaves the decision of what to do in this case to the
+filesystem, which select its preferred behavior by enabling/disabling
+the strict mode.  When Ext4 encounters one of those strings and the
+filesystem did not require strict mode, it falls back to considering the
+entire string as an opaque byte sequence, which still allows the user to
+operate on that file, but the case-insensitive lookups won't work.
+
 Options
 =======
 

Documentation/dontdiff

@@ -176,6 +176,7 @@ mkprep
 mkregtable
 mktables
 mktree
+mkutf8data
 modpost
 modules.builtin
 modules.order
@@ -254,6 +255,7 @@ vsyscall_32.lds
 wanxlfw.inc
 uImage
 unifdef
+utf8data.h
 wakeup.bin
 wakeup.elf
 wakeup.lds

MAINTAINERS

@@ -15984,6 +15984,12 @@ F:	drivers/uwb/
 F:	include/linux/uwb.h
 F:	include/linux/uwb/
 
+UNICODE SUBSYSTEM:
+M:	Gabriel Krisman Bertazi <[email protected]>
+L:	[email protected]
+S:	Supported
+F:	fs/unicode/
+
 UNICORE32 ARCHITECTURE:
 M:	Guan Xuetao <[email protected]>
 W:	http://mprc.pku.edu.cn/~guanxuetao/linux

fs/Kconfig

@@ -317,5 +317,6 @@ endif # NETWORK_FILESYSTEMS
 
 source "fs/nls/Kconfig"
 source "fs/dlm/Kconfig"
+source "fs/unicode/Kconfig"
 
 endmenu

fs/Makefile

@@ -92,6 +92,7 @@ obj-$(CONFIG_EXPORTFS)		+= exportfs/
 obj-$(CONFIG_NFSD)		+= nfsd/
 obj-$(CONFIG_LOCKD)		+= lockd/
 obj-$(CONFIG_NLS)		+= nls/
+obj-$(CONFIG_UNICODE)		+= unicode/
 obj-$(CONFIG_SYSV_FS)		+= sysv/
 obj-$(CONFIG_CIFS)		+= cifs/
 obj-$(CONFIG_HPFS_FS)		+= hpfs/

fs/ext4/block_validity.c

@@ -137,6 +137,48 @@ static void debug_print_tree(struct ext4_sb_info *sbi)
 	printk(KERN_CONT "\n");
 }
 
+static int ext4_protect_reserved_inode(struct super_block *sb, u32 ino)
+{
+	struct inode *inode;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct ext4_map_blocks map;
+	u32 i = 0, err = 0, num, n;
+
+	if ((ino < EXT4_ROOT_INO) ||
+	    (ino > le32_to_cpu(sbi->s_es->s_inodes_count)))
+		return -EINVAL;
+	inode = ext4_iget(sb, ino, EXT4_IGET_SPECIAL);
+	if (IS_ERR(inode))
+		return PTR_ERR(inode);
+	num = (inode->i_size + sb->s_blocksize - 1) >> sb->s_blocksize_bits;
+	while (i < num) {
+		map.m_lblk = i;
+		map.m_len = num - i;
+		n = ext4_map_blocks(NULL, inode, &map, 0);
+		if (n < 0) {
+			err = n;
+			break;
+		}
+		if (n == 0) {
+			i++;
+		} else {
+			if (!ext4_data_block_valid(sbi, map.m_pblk, n)) {
+				ext4_error(sb, "blocks %llu-%llu from inode %u "
+					   "overlap system zone", map.m_pblk,
+					   map.m_pblk + map.m_len - 1, ino);
+				err = -EFSCORRUPTED;
+				break;
+			}
+			err = add_system_zone(sbi, map.m_pblk, n);
+			if (err < 0)
+				break;
+			i += n;
+		}
+	}
+	iput(inode);
+	return err;
+}
+
 int ext4_setup_system_zone(struct super_block *sb)
 {
 	ext4_group_t ngroups = ext4_get_groups_count(sb);
@@ -155,6 +197,7 @@ int ext4_setup_system_zone(struct super_block *sb)
 		return 0;
 
 	for (i=0; i < ngroups; i++) {
+		cond_resched();
 		if (ext4_bg_has_super(sb, i) &&
 		    ((i < 5) || ((i % flex_size) == 0)))
 			add_system_zone(sbi, ext4_group_first_block_no(sb, i),
@@ -171,6 +214,12 @@ int ext4_setup_system_zone(struct super_block *sb)
 		if (ret)
 			return ret;
 	}
+	if (ext4_has_feature_journal(sb) && sbi->s_es->s_journal_inum) {
+		ret = ext4_protect_reserved_inode(sb,
+				le32_to_cpu(sbi->s_es->s_journal_inum));
+		if (ret)
+			return ret;
+	}
 
 	if (test_opt(sb, DEBUG))
 		debug_print_tree(sbi);

fs/ext4/dir.c

@@ -26,6 +26,7 @@
 #include <linux/buffer_head.h>
 #include <linux/slab.h>
 #include <linux/iversion.h>
+#include <linux/unicode.h>
 #include "ext4.h"
 #include "xattr.h"
 
@@ -660,3 +661,50 @@ const struct file_operations ext4_dir_operations = {
 	.open		= ext4_dir_open,
 	.release	= ext4_release_dir,
 };
+
+#ifdef CONFIG_UNICODE
+static int ext4_d_compare(const struct dentry *dentry, unsigned int len,
+			  const char *str, const struct qstr *name)
+{
+	struct qstr qstr = {.name = str, .len = len };
+
+	if (!IS_CASEFOLDED(dentry->d_parent->d_inode)) {
+		if (len != name->len)
+			return -1;
+		return !memcmp(str, name, len);
+	}
+
+	return ext4_ci_compare(dentry->d_parent->d_inode, name, &qstr);
+}
+
+static int ext4_d_hash(const struct dentry *dentry, struct qstr *str)
+{
+	const struct ext4_sb_info *sbi = EXT4_SB(dentry->d_sb);
+	const struct unicode_map *um = sbi->s_encoding;
+	unsigned char *norm;
+	int len, ret = 0;
+
+	if (!IS_CASEFOLDED(dentry->d_inode))
+		return 0;
+
+	norm = kmalloc(PATH_MAX, GFP_ATOMIC);
+	if (!norm)
+		return -ENOMEM;
+
+	len = utf8_casefold(um, str, norm, PATH_MAX);
+	if (len < 0) {
+		if (ext4_has_strict_mode(sbi))
+			ret = -EINVAL;
+		goto out;
+	}
+	str->hash = full_name_hash(dentry, norm, len);
+out:
+	kfree(norm);
+	return ret;
+}
+
+const struct dentry_operations ext4_dentry_ops = {
+	.d_hash = ext4_d_hash,
+	.d_compare = ext4_d_compare,
+};
+#endif

fs/ext4/ext4.h

@@ -399,10 +399,11 @@ struct flex_groups {
 #define EXT4_EOFBLOCKS_FL		0x00400000 /* Blocks allocated beyond EOF */
 #define EXT4_INLINE_DATA_FL		0x10000000 /* Inode has inline data. */
 #define EXT4_PROJINHERIT_FL		0x20000000 /* Create with parents projid */
+#define EXT4_CASEFOLD_FL		0x40000000 /* Casefolded file */
 #define EXT4_RESERVED_FL		0x80000000 /* reserved for ext4 lib */
 
-#define EXT4_FL_USER_VISIBLE		0x304BDFFF /* User visible flags */
-#define EXT4_FL_USER_MODIFIABLE		0x204BC0FF /* User modifiable flags */
+#define EXT4_FL_USER_VISIBLE		0x704BDFFF /* User visible flags */
+#define EXT4_FL_USER_MODIFIABLE		0x604BC0FF /* User modifiable flags */
 
 /* Flags we can manipulate with through EXT4_IOC_FSSETXATTR */
 #define EXT4_FL_XFLAG_VISIBLE		(EXT4_SYNC_FL | \
@@ -417,10 +418,10 @@ struct flex_groups {
 			   EXT4_SYNC_FL | EXT4_NODUMP_FL | EXT4_NOATIME_FL |\
 			   EXT4_NOCOMPR_FL | EXT4_JOURNAL_DATA_FL |\
 			   EXT4_NOTAIL_FL | EXT4_DIRSYNC_FL |\
-			   EXT4_PROJINHERIT_FL)
+			   EXT4_PROJINHERIT_FL | EXT4_CASEFOLD_FL)
 
 /* Flags that are appropriate for regular files (all but dir-specific ones). */
-#define EXT4_REG_FLMASK (~(EXT4_DIRSYNC_FL | EXT4_TOPDIR_FL))
+#define EXT4_REG_FLMASK (~(EXT4_DIRSYNC_FL | EXT4_TOPDIR_FL | EXT4_CASEFOLD_FL))
 
 /* Flags that are appropriate for non-directories/regular files. */
 #define EXT4_OTHER_FLMASK (EXT4_NODUMP_FL | EXT4_NOATIME_FL)
@@ -1313,7 +1314,9 @@ struct ext4_super_block {
 	__u8	s_first_error_time_hi;
 	__u8	s_last_error_time_hi;
 	__u8	s_pad[2];
-	__le32	s_reserved[96];		/* Padding to the end of the block */
+	__le16  s_encoding;		/* Filename charset encoding */
+	__le16  s_encoding_flags;	/* Filename charset encoding flags */
+	__le32	s_reserved[95];		/* Padding to the end of the block */
 	__le32	s_checksum;		/* crc32c(superblock) */
 };
 
@@ -1338,6 +1341,16 @@ struct ext4_super_block {
 /* Number of quota types we support */
 #define EXT4_MAXQUOTAS 3
 
+#define EXT4_ENC_UTF8_12_1	1
+
+/*
+ * Flags for ext4_sb_info.s_encoding_flags.
+ */
+#define EXT4_ENC_STRICT_MODE_FL	(1 << 0)
+
+#define ext4_has_strict_mode(sbi) \
+	(sbi->s_encoding_flags & EXT4_ENC_STRICT_MODE_FL)
+
 /*
  * fourth extended-fs super-block data in memory
  */
@@ -1387,6 +1400,10 @@ struct ext4_sb_info {
 	struct kobject s_kobj;
 	struct completion s_kobj_unregister;
 	struct super_block *s_sb;
+#ifdef CONFIG_UNICODE
+	struct unicode_map *s_encoding;
+	__u16 s_encoding_flags;
+#endif
 
 	/* Journaling */
 	struct journal_s *s_journal;
@@ -1592,9 +1609,6 @@ static inline void ext4_clear_state_flags(struct ext4_inode_info *ei)
 #define EXT4_SB(sb)	(sb)
 #endif
 
-/*
- * Returns true if the inode is inode is encrypted
- */
 #define NEXT_ORPHAN(inode) EXT4_I(inode)->i_dtime
 
 /*
@@ -1663,6 +1677,7 @@ static inline void ext4_clear_state_flags(struct ext4_inode_info *ei)
 #define EXT4_FEATURE_INCOMPAT_LARGEDIR		0x4000 /* >2GB or 3-lvl htree */
 #define EXT4_FEATURE_INCOMPAT_INLINE_DATA	0x8000 /* data in inode */
 #define EXT4_FEATURE_INCOMPAT_ENCRYPT		0x10000
+#define EXT4_FEATURE_INCOMPAT_CASEFOLD		0x20000
 
 extern void ext4_update_dynamic_rev(struct super_block *sb);
 
@@ -1756,6 +1771,7 @@ EXT4_FEATURE_INCOMPAT_FUNCS(csum_seed,		CSUM_SEED)
 EXT4_FEATURE_INCOMPAT_FUNCS(largedir,		LARGEDIR)
 EXT4_FEATURE_INCOMPAT_FUNCS(inline_data,	INLINE_DATA)
 EXT4_FEATURE_INCOMPAT_FUNCS(encrypt,		ENCRYPT)
+EXT4_FEATURE_INCOMPAT_FUNCS(casefold,		CASEFOLD)
 
 #define EXT2_FEATURE_COMPAT_SUPP	EXT4_FEATURE_COMPAT_EXT_ATTR
 #define EXT2_FEATURE_INCOMPAT_SUPP	(EXT4_FEATURE_INCOMPAT_FILETYPE| \
@@ -1783,6 +1799,7 @@ EXT4_FEATURE_INCOMPAT_FUNCS(encrypt,		ENCRYPT)
 					 EXT4_FEATURE_INCOMPAT_MMP | \
 					 EXT4_FEATURE_INCOMPAT_INLINE_DATA | \
 					 EXT4_FEATURE_INCOMPAT_ENCRYPT | \
+					 EXT4_FEATURE_INCOMPAT_CASEFOLD | \
 					 EXT4_FEATURE_INCOMPAT_CSUM_SEED | \
 					 EXT4_FEATURE_INCOMPAT_LARGEDIR)
 #define EXT4_FEATURE_RO_COMPAT_SUPP	(EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER| \
@@ -2376,8 +2393,8 @@ extern int ext4_check_all_de(struct inode *dir, struct buffer_head *bh,
 extern int ext4_sync_file(struct file *, loff_t, loff_t, int);
 
 /* hash.c */
-extern int ext4fs_dirhash(const char *name, int len, struct
-			  dx_hash_info *hinfo);
+extern int ext4fs_dirhash(const struct inode *dir, const char *name, int len,
+			  struct dx_hash_info *hinfo);
 
 /* ialloc.c */
 extern struct inode *__ext4_new_inode(handle_t *, struct inode *, umode_t,
@@ -2973,6 +2990,10 @@ static inline void ext4_unlock_group(struct super_block *sb,
 /* dir.c */
 extern const struct file_operations ext4_dir_operations;
 
+#ifdef CONFIG_UNICODE
+extern const struct dentry_operations ext4_dentry_ops;
+#endif
+
 /* file.c */
 extern const struct inode_operations ext4_file_inode_operations;
 extern const struct file_operations ext4_file_operations;
@@ -3065,6 +3086,10 @@ extern void initialize_dirent_tail(struct ext4_dir_entry_tail *t,
 extern int ext4_handle_dirty_dirent_node(handle_t *handle,
 					 struct inode *inode,
 					 struct buffer_head *bh);
+extern int ext4_ci_compare(const struct inode *parent,
+			   const struct qstr *name,
+			   const struct qstr *entry);
+
 #define S_SHIFT 12
 static const unsigned char ext4_type_by_mode[(S_IFMT >> S_SHIFT) + 1] = {
 	[S_IFREG >> S_SHIFT]	= EXT4_FT_REG_FILE,

fs/ext4/extents_status.c

@@ -711,7 +711,7 @@ static void ext4_es_insert_extent_ind_check(struct inode *inode,
 			 * We don't need to check unwritten extent because
 			 * indirect-based file doesn't have it.
 			 */
-			BUG_ON(1);
+			BUG();
 		}
 	} else if (retval == 0) {
 		if (ext4_es_is_written(es)) {
@@ -780,7 +780,7 @@ static int __es_insert_extent(struct inode *inode, struct extent_status *newes)
 			}
 			p = &(*p)->rb_right;
 		} else {
-			BUG_ON(1);
+			BUG();
 			return -EINVAL;
 		}
 	}