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

Pull ext4 updates from Ted Ts'o:
 "This merge window, we've added some performance improvements in how we
  handle inode locking in the read/write paths, and improving the
  performance of Direct I/O overwrites.

  We also now record the error code which caused the first and most
  recent ext4_error() report in the superblock, to make it easier to
  root cause problems in production systems.

  There are also many of the usual cleanups and miscellaneous bug fixes"

* tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (49 commits)
  jbd2: clean __jbd2_journal_abort_hard() and __journal_abort_soft()
  jbd2: make sure ESHUTDOWN to be recorded in the journal superblock
  ext4, jbd2: ensure panic when aborting with zero errno
  jbd2: switch to use jbd2_journal_abort() when failed to submit the commit record
  jbd2_seq_info_next should increase position index
  jbd2: remove pointless assertion in __journal_remove_journal_head
  ext4,jbd2: fix comment and code style
  jbd2: delete the duplicated words in the comments
  ext4: fix extent_status trace points
  ext4: fix symbolic enum printing in trace output
  ext4: choose hardlimit when softlimit is larger than hardlimit in ext4_statfs_project()
  ext4: fix race conditions in ->d_compare() and ->d_hash()
  ext4: make dioread_nolock the default
  ext4: fix extent_status fragmentation for plain files
  jbd2: clear JBD2_ABORT flag before journal_reset to update log tail info when load journal
  ext4: drop ext4_kvmalloc()
  ext4: Add EXT4_IOC_FSGETXATTR/EXT4_IOC_FSSETXATTR to compat_ioctl
  ext4: remove unused macro MPAGE_DA_EXTENT_TAIL
  ext4: add missing braces in ext4_ext_drop_refs()
  ext4: fix some nonstandard indentation in extents.c
  ...

Author: torvalds

Documentation/admin-guide/ext4.rst

@@ -92,6 +92,8 @@ Currently Available
 * efficient new ordered mode in JBD2 and ext4 (avoid using buffer head to force
   the ordering)
 * Case-insensitive file name lookups
+* file-based encryption support (fscrypt)
+* file-based verity support (fsverity)
 
 [1] Filesystems with a block size of 1k may see a limit imposed by the
 directory hash tree having a maximum depth of two.

Documentation/filesystems/fscrypt.rst

@@ -1016,9 +1016,9 @@ astute users may notice some differences in behavior:
 - Direct I/O is not supported on encrypted files.  Attempts to use
   direct I/O on such files will fall back to buffered I/O.
 
-- The fallocate operations FALLOC_FL_COLLAPSE_RANGE,
-  FALLOC_FL_INSERT_RANGE, and FALLOC_FL_ZERO_RANGE are not supported
-  on encrypted files and will fail with EOPNOTSUPP.
+- The fallocate operations FALLOC_FL_COLLAPSE_RANGE and
+  FALLOC_FL_INSERT_RANGE are not supported on encrypted files and will
+  fail with EOPNOTSUPP.
 
 - Online defragmentation of encrypted files is not supported.  The
   EXT4_IOC_MOVE_EXT and F2FS_IOC_MOVE_RANGE ioctls will fail with

fs/ext4/Kconfig

@@ -4,12 +4,7 @@
 # kernels after the removal of ext3 driver.
 config EXT3_FS
 	tristate "The Extended 3 (ext3) filesystem"
-	# These must match EXT4_FS selects...
 	select EXT4_FS
-	select JBD2
-	select CRC16
-	select CRYPTO
-	select CRYPTO_CRC32C
 	help
 	  This config option is here only for backward compatibility. ext3
 	  filesystem is now handled by the ext4 driver.
@@ -33,7 +28,6 @@ config EXT3_FS_SECURITY
 
 config EXT4_FS
 	tristate "The Extended 4 (ext4) filesystem"
-	# Please update EXT3_FS selects when changing these
 	select JBD2
 	select CRC16
 	select CRYPTO

fs/ext4/balloc.c

@@ -371,7 +371,8 @@ static int ext4_validate_block_bitmap(struct super_block *sb,
 	if (buffer_verified(bh))
 		goto verified;
 	if (unlikely(!ext4_block_bitmap_csum_verify(sb, block_group,
-			desc, bh))) {
+						    desc, bh) ||
+		     ext4_simulate_fail(sb, EXT4_SIM_BBITMAP_CRC))) {
 		ext4_unlock_group(sb, block_group);
 		ext4_error(sb, "bg %u: bad block bitmap checksum", block_group);
 		ext4_mark_group_bitmap_corrupted(sb, block_group,
@@ -505,7 +506,9 @@ int ext4_wait_block_bitmap(struct super_block *sb, ext4_group_t block_group,
 	if (!desc)
 		return -EFSCORRUPTED;
 	wait_on_buffer(bh);
+	ext4_simulate_fail_bh(sb, bh, EXT4_SIM_BBITMAP_EIO);
 	if (!buffer_uptodate(bh)) {
+		ext4_set_errno(sb, EIO);
 		ext4_error(sb, "Cannot read block bitmap - "
 			   "block_group = %u, block_bitmap = %llu",
 			   block_group, (unsigned long long) bh->b_blocknr);

fs/ext4/dir.c

@@ -462,7 +462,6 @@ int ext4_htree_store_dirent(struct file *dir_file, __u32 hash,
 	new_fn->name_len = ent_name->len;
 	new_fn->file_type = dirent->file_type;
 	memcpy(new_fn->name, ent_name->name, ent_name->len);
-	new_fn->name[ent_name->len] = 0;
 
 	while (*p) {
 		parent = *p;
@@ -672,9 +671,11 @@ 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 };
-	struct inode *inode = dentry->d_parent->d_inode;
+	const struct dentry *parent = READ_ONCE(dentry->d_parent);
+	const struct inode *inode = READ_ONCE(parent->d_inode);
 
-	if (!IS_CASEFOLDED(inode) || !EXT4_SB(inode->i_sb)->s_encoding) {
+	if (!inode || !IS_CASEFOLDED(inode) ||
+	    !EXT4_SB(inode->i_sb)->s_encoding) {
 		if (len != name->len)
 			return -1;
 		return memcmp(str, name->name, len);
@@ -687,10 +688,11 @@ 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;
+	const struct inode *inode = READ_ONCE(dentry->d_inode);
 	unsigned char *norm;
 	int len, ret = 0;
 
-	if (!IS_CASEFOLDED(dentry->d_inode) || !um)
+	if (!inode || !IS_CASEFOLDED(inode) || !um)
 		return 0;
 
 	norm = kmalloc(PATH_MAX, GFP_ATOMIC);

fs/ext4/ext4.h

@@ -1052,8 +1052,6 @@ struct ext4_inode_info {
 	/* allocation reservation info for delalloc */
 	/* In case of bigalloc, this refer to clusters rather than blocks */
 	unsigned int i_reserved_data_blocks;
-	ext4_lblk_t i_da_metadata_calc_last_lblock;
-	int i_da_metadata_calc_len;
 
 	/* pending cluster reservations for bigalloc file systems */
 	struct ext4_pending_tree i_pending_tree;
@@ -1343,7 +1341,8 @@ struct ext4_super_block {
 	__u8	s_lastcheck_hi;
 	__u8	s_first_error_time_hi;
 	__u8	s_last_error_time_hi;
-	__u8	s_pad[2];
+	__u8	s_first_error_errcode;
+	__u8    s_last_error_errcode;
 	__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 */
@@ -1556,6 +1555,9 @@ struct ext4_sb_info {
 	/* Barrier between changing inodes' journal flags and writepages ops. */
 	struct percpu_rw_semaphore s_journal_flag_rwsem;
 	struct dax_device *s_daxdev;
+#ifdef CONFIG_EXT4_DEBUG
+	unsigned long s_simulate_fail;
+#endif
 };
 
 static inline struct ext4_sb_info *EXT4_SB(struct super_block *sb)
@@ -1574,6 +1576,66 @@ static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino)
 		 ino <= le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count));
 }
 
+/*
+ * Simulate_fail codes
+ */
+#define EXT4_SIM_BBITMAP_EIO	1
+#define EXT4_SIM_BBITMAP_CRC	2
+#define EXT4_SIM_IBITMAP_EIO	3
+#define EXT4_SIM_IBITMAP_CRC	4
+#define EXT4_SIM_INODE_EIO	5
+#define EXT4_SIM_INODE_CRC	6
+#define EXT4_SIM_DIRBLOCK_EIO	7
+#define EXT4_SIM_DIRBLOCK_CRC	8
+
+static inline bool ext4_simulate_fail(struct super_block *sb,
+				     unsigned long code)
+{
+#ifdef CONFIG_EXT4_DEBUG
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+
+	if (unlikely(sbi->s_simulate_fail == code)) {
+		sbi->s_simulate_fail = 0;
+		return true;
+	}
+#endif
+	return false;
+}
+
+static inline void ext4_simulate_fail_bh(struct super_block *sb,
+					 struct buffer_head *bh,
+					 unsigned long code)
+{
+	if (!IS_ERR(bh) && ext4_simulate_fail(sb, code))
+		clear_buffer_uptodate(bh);
+}
+
+/*
+ * Error number codes for s_{first,last}_error_errno
+ *
+ * Linux errno numbers are architecture specific, so we need to translate
+ * them into something which is architecture independent.   We don't define
+ * codes for all errno's; just the ones which are most likely to be the cause
+ * of an ext4_error() call.
+ */
+#define EXT4_ERR_UNKNOWN	 1
+#define EXT4_ERR_EIO		 2
+#define EXT4_ERR_ENOMEM		 3
+#define EXT4_ERR_EFSBADCRC	 4
+#define EXT4_ERR_EFSCORRUPTED	 5
+#define EXT4_ERR_ENOSPC		 6
+#define EXT4_ERR_ENOKEY		 7
+#define EXT4_ERR_EROFS		 8
+#define EXT4_ERR_EFBIG		 9
+#define EXT4_ERR_EEXIST		10
+#define EXT4_ERR_ERANGE		11
+#define EXT4_ERR_EOVERFLOW	12
+#define EXT4_ERR_EBUSY		13
+#define EXT4_ERR_ENOTDIR	14
+#define EXT4_ERR_ENOTEMPTY	15
+#define EXT4_ERR_ESHUTDOWN	16
+#define EXT4_ERR_EFAULT		17
+
 /*
  * Inode dynamic state flags
  */
@@ -2628,7 +2690,6 @@ extern int ext4_issue_zeroout(struct inode *inode, ext4_lblk_t lblk,
 /* indirect.c */
 extern int ext4_ind_map_blocks(handle_t *handle, struct inode *inode,
 				struct ext4_map_blocks *map, int flags);
-extern int ext4_ind_calc_metadata_amount(struct inode *inode, sector_t lblock);
 extern int ext4_ind_trans_blocks(struct inode *inode, int nrblocks);
 extern void ext4_ind_truncate(handle_t *, struct inode *inode);
 extern int ext4_ind_remove_space(handle_t *handle, struct inode *inode,
@@ -2679,15 +2740,14 @@ extern struct buffer_head *ext4_sb_bread(struct super_block *sb,
 extern int ext4_seq_options_show(struct seq_file *seq, void *offset);
 extern int ext4_calculate_overhead(struct super_block *sb);
 extern void ext4_superblock_csum_set(struct super_block *sb);
-extern void *ext4_kvmalloc(size_t size, gfp_t flags);
-extern void *ext4_kvzalloc(size_t size, gfp_t flags);
 extern int ext4_alloc_flex_bg_array(struct super_block *sb,
 				    ext4_group_t ngroup);
 extern const char *ext4_decode_error(struct super_block *sb, int errno,
 				     char nbuf[16]);
 extern void ext4_mark_group_bitmap_corrupted(struct super_block *sb,
 					     ext4_group_t block_group,
 					     unsigned int flags);
+extern void ext4_set_errno(struct super_block *sb, int err);
 
 extern __printf(4, 5)
 void __ext4_error(struct super_block *, const char *, unsigned int,
@@ -3254,7 +3314,6 @@ struct ext4_extent;
 #define EXT_MAX_BLOCKS	0xffffffff
 
 extern int ext4_ext_tree_init(handle_t *handle, struct inode *);
-extern int ext4_ext_writepage_trans_blocks(struct inode *, int);
 extern int ext4_ext_index_trans_blocks(struct inode *inode, int extents);
 extern int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 			       struct ext4_map_blocks *map, int flags);
@@ -3271,14 +3330,9 @@ extern int ext4_convert_unwritten_io_end_vec(handle_t *handle,
 					     ext4_io_end_t *io_end);
 extern int ext4_map_blocks(handle_t *handle, struct inode *inode,
 			   struct ext4_map_blocks *map, int flags);
-extern int ext4_ext_calc_metadata_amount(struct inode *inode,
-					 ext4_lblk_t lblocks);
 extern int ext4_ext_calc_credits_for_single_extent(struct inode *inode,
 						   int num,
 						   struct ext4_ext_path *path);
-extern int ext4_can_extents_be_merged(struct inode *inode,
-				      struct ext4_extent *ex1,
-				      struct ext4_extent *ex2);
 extern int ext4_ext_insert_extent(handle_t *, struct inode *,
 				  struct ext4_ext_path **,
 				  struct ext4_extent *, int);
@@ -3294,8 +3348,6 @@ extern int ext4_get_es_cache(struct inode *inode,
 			     struct fiemap_extent_info *fieinfo,
 			     __u64 start, __u64 len);
 extern int ext4_ext_precache(struct inode *inode);
-extern int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len);
-extern int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len);
 extern int ext4_swap_extents(handle_t *handle, struct inode *inode1,
 				struct inode *inode2, ext4_lblk_t lblk1,
 			     ext4_lblk_t lblk2,  ext4_lblk_t count,
@@ -3390,6 +3442,7 @@ static inline void ext4_clear_io_unwritten_flag(ext4_io_end_t *io_end)
 }
 
 extern const struct iomap_ops ext4_iomap_ops;
+extern const struct iomap_ops ext4_iomap_overwrite_ops;
 extern const struct iomap_ops ext4_iomap_report_ops;
 
 static inline int ext4_buffer_uptodate(struct buffer_head *bh)

fs/ext4/ext4_extents.h

@@ -267,10 +267,5 @@ static inline void ext4_idx_store_pblock(struct ext4_extent_idx *ix,
 				     0xffff);
 }
 
-#define ext4_ext_dirty(handle, inode, path) \
-		__ext4_ext_dirty(__func__, __LINE__, (handle), (inode), (path))
-int __ext4_ext_dirty(const char *where, unsigned int line, handle_t *handle,
-		     struct inode *inode, struct ext4_ext_path *path);
-
 #endif /* _EXT4_EXTENTS */
 

fs/ext4/ext4_jbd2.c

@@ -7,6 +7,28 @@
 
 #include <trace/events/ext4.h>
 
+int ext4_inode_journal_mode(struct inode *inode)
+{
+	if (EXT4_JOURNAL(inode) == NULL)
+		return EXT4_INODE_WRITEBACK_DATA_MODE;	/* writeback */
+	/* We do not support data journalling with delayed allocation */
+	if (!S_ISREG(inode->i_mode) ||
+	    ext4_test_inode_flag(inode, EXT4_INODE_EA_INODE) ||
+	    test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA ||
+	    (ext4_test_inode_flag(inode, EXT4_INODE_JOURNAL_DATA) &&
+	    !test_opt(inode->i_sb, DELALLOC))) {
+		/* We do not support data journalling for encrypted data */
+		if (S_ISREG(inode->i_mode) && IS_ENCRYPTED(inode))
+			return EXT4_INODE_ORDERED_DATA_MODE;  /* ordered */
+		return EXT4_INODE_JOURNAL_DATA_MODE;	/* journal data */
+	}
+	if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA)
+		return EXT4_INODE_ORDERED_DATA_MODE;	/* ordered */
+	if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA)
+		return EXT4_INODE_WRITEBACK_DATA_MODE;	/* writeback */
+	BUG();
+}
+
 /* Just increment the non-pointer handle value */
 static handle_t *ext4_get_nojournal(void)
 {
@@ -58,6 +80,7 @@ static int ext4_journal_check_start(struct super_block *sb)
 	 * take the FS itself readonly cleanly.
 	 */
 	if (journal && is_journal_aborted(journal)) {
+		ext4_set_errno(sb, -journal->j_errno);
 		ext4_abort(sb, "Detected aborted journal");
 		return -EROFS;
 	}
@@ -249,6 +272,7 @@ int __ext4_forget(const char *where, unsigned int line, handle_t *handle,
 	if (err) {
 		ext4_journal_abort_handle(where, line, __func__,
 					  bh, handle, err);
+		ext4_set_errno(inode->i_sb, -err);
 		__ext4_abort(inode->i_sb, where, line,
 			   "error %d when attempting revoke", err);
 	}
@@ -320,6 +344,7 @@ int __ext4_handle_dirty_metadata(const char *where, unsigned int line,
 				es = EXT4_SB(inode->i_sb)->s_es;
 				es->s_last_error_block =
 					cpu_to_le64(bh->b_blocknr);
+				ext4_set_errno(inode->i_sb, EIO);
 				ext4_error_inode(inode, where, line,
 						 bh->b_blocknr,
 					"IO error syncing itable block");

fs/ext4/ext4_jbd2.h

@@ -463,27 +463,7 @@ int ext4_force_commit(struct super_block *sb);
 #define EXT4_INODE_ORDERED_DATA_MODE	0x02 /* ordered data mode */
 #define EXT4_INODE_WRITEBACK_DATA_MODE	0x04 /* writeback data mode */
 
-static inline int ext4_inode_journal_mode(struct inode *inode)
-{
-	if (EXT4_JOURNAL(inode) == NULL)
-		return EXT4_INODE_WRITEBACK_DATA_MODE;	/* writeback */
-	/* We do not support data journalling with delayed allocation */
-	if (!S_ISREG(inode->i_mode) ||
-	    ext4_test_inode_flag(inode, EXT4_INODE_EA_INODE) ||
-	    test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA ||
-	    (ext4_test_inode_flag(inode, EXT4_INODE_JOURNAL_DATA) &&
-	    !test_opt(inode->i_sb, DELALLOC))) {
-		/* We do not support data journalling for encrypted data */
-		if (S_ISREG(inode->i_mode) && IS_ENCRYPTED(inode))
-			return EXT4_INODE_ORDERED_DATA_MODE;  /* ordered */
-		return EXT4_INODE_JOURNAL_DATA_MODE;	/* journal data */
-	}
-	if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA)
-		return EXT4_INODE_ORDERED_DATA_MODE;	/* ordered */
-	if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA)
-		return EXT4_INODE_WRITEBACK_DATA_MODE;	/* writeback */
-	BUG();
-}
+int ext4_inode_journal_mode(struct inode *inode);
 
 static inline int ext4_should_journal_data(struct inode *inode)
 {