Various bug fixes and cleanups for ext4. In particular, move the

crypto related fucntions from fs/ext4/super.c into a new
 fs/ext4/crypto.c, and fix a number of bugs found by fuzzers and error
 injection tools.
 -----BEGIN PGP SIGNATURE-----
 
 iQEzBAABCAAdFiEEK2m5VNv+CHkogTfJ8vlZVpUNgaMFAmKNOh0ACgkQ8vlZVpUN
 gaP4kwf+KfqZ/iBDOOCMKV5C7/Z4ieiMLeNqzCWmvju7jceYBoSLOIz3w5MFjEV9
 5ZB/6MovMZ/vZRtm76k0K01ayHKUd1BKjwwvIaABjdNVDTar5Wg/Tq7MF0OMQ5Kw
 ec5rvOQ05VzbXwf/JOjp7IHP/9yEbtgKjAYzgVyMVGrE8jxLQ+UOSUBzzZEHv/js
 Xh7GmRGEs5V7bj+V4SuCaEKSf3wYjT/zlJNIPtsg9RJeQojOP2qlOFhcGeduF1X/
 E4OwabfHqdmlbdI0vL3ANb8nByi/bA0p8i9PGqGIDx0nRUK9UzJCjePmkPux6koT
 pPZLo8DKR8g5i0Hn/ennA9tAIXIaXg==
 =OliY
 -----END PGP SIGNATURE-----

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

Pull ext4 updates from Ted Ts'o:
 "Various bug fixes and cleanups for ext4.

  In particular, move the crypto related fucntions from fs/ext4/super.c
  into a new fs/ext4/crypto.c, and fix a number of bugs found by fuzzers
  and error injection tools"

* tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (25 commits)
  ext4: only allow test_dummy_encryption when supported
  ext4: fix bug_on in __es_tree_search
  ext4: avoid cycles in directory h-tree
  ext4: verify dir block before splitting it
  ext4: filter out EXT4_FC_REPLAY from on-disk superblock field s_state
  ext4: fix bug_on in ext4_writepages
  ext4: refactor and move ext4_ioctl_get_encryption_pwsalt()
  ext4: cleanup function defs from ext4.h into crypto.c
  ext4: move ext4 crypto code to its own file crypto.c
  ext4: fix memory leak in parse_apply_sb_mount_options()
  ext4: reject the 'commit' option on ext2 filesystems
  ext4: remove duplicated #include of dax.h in inode.c
  ext4: fix race condition between ext4_write and ext4_convert_inline_data
  ext4: convert symlink external data block mapping to bdev
  ext4: add nowait mode for ext4_getblk()
  ext4: fix journal_ioprio mount option handling
  ext4: mark group as trimmed only if it was fully scanned
  ext4: fix use-after-free in ext4_rename_dir_prepare
  ext4: add unmount filesystem message
  ext4: remove unnecessary conditionals
  ...

fs/ext4/Makefile

@@ -17,3 +17,4 @@ ext4-$(CONFIG_EXT4_FS_SECURITY)		+= xattr_security.o
 ext4-inode-test-objs			+= inode-test.o
 obj-$(CONFIG_EXT4_KUNIT_TESTS)		+= ext4-inode-test.o
 ext4-$(CONFIG_FS_VERITY)		+= verity.o
+ext4-$(CONFIG_FS_ENCRYPTION)		+= crypto.o

fs/ext4/crypto.c

@@ -0,0 +1,246 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/quotaops.h>
+#include <linux/uuid.h>
+
+#include "ext4.h"
+#include "xattr.h"
+#include "ext4_jbd2.h"
+
+static void ext4_fname_from_fscrypt_name(struct ext4_filename *dst,
+					 const struct fscrypt_name *src)
+{
+	memset(dst, 0, sizeof(*dst));
+
+	dst->usr_fname = src->usr_fname;
+	dst->disk_name = src->disk_name;
+	dst->hinfo.hash = src->hash;
+	dst->hinfo.minor_hash = src->minor_hash;
+	dst->crypto_buf = src->crypto_buf;
+}
+
+int ext4_fname_setup_filename(struct inode *dir, const struct qstr *iname,
+			      int lookup, struct ext4_filename *fname)
+{
+	struct fscrypt_name name;
+	int err;
+
+	err = fscrypt_setup_filename(dir, iname, lookup, &name);
+	if (err)
+		return err;
+
+	ext4_fname_from_fscrypt_name(fname, &name);
+
+#if IS_ENABLED(CONFIG_UNICODE)
+	err = ext4_fname_setup_ci_filename(dir, iname, fname);
+#endif
+	return err;
+}
+
+int ext4_fname_prepare_lookup(struct inode *dir, struct dentry *dentry,
+			      struct ext4_filename *fname)
+{
+	struct fscrypt_name name;
+	int err;
+
+	err = fscrypt_prepare_lookup(dir, dentry, &name);
+	if (err)
+		return err;
+
+	ext4_fname_from_fscrypt_name(fname, &name);
+
+#if IS_ENABLED(CONFIG_UNICODE)
+	err = ext4_fname_setup_ci_filename(dir, &dentry->d_name, fname);
+#endif
+	return err;
+}
+
+void ext4_fname_free_filename(struct ext4_filename *fname)
+{
+	struct fscrypt_name name;
+
+	name.crypto_buf = fname->crypto_buf;
+	fscrypt_free_filename(&name);
+
+	fname->crypto_buf.name = NULL;
+	fname->usr_fname = NULL;
+	fname->disk_name.name = NULL;
+
+#if IS_ENABLED(CONFIG_UNICODE)
+	kfree(fname->cf_name.name);
+	fname->cf_name.name = NULL;
+#endif
+}
+
+static bool uuid_is_zero(__u8 u[16])
+{
+	int i;
+
+	for (i = 0; i < 16; i++)
+		if (u[i])
+			return false;
+	return true;
+}
+
+int ext4_ioctl_get_encryption_pwsalt(struct file *filp, void __user *arg)
+{
+	struct super_block *sb = file_inode(filp)->i_sb;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	int err, err2;
+	handle_t *handle;
+
+	if (!ext4_has_feature_encrypt(sb))
+		return -EOPNOTSUPP;
+
+	if (uuid_is_zero(sbi->s_es->s_encrypt_pw_salt)) {
+		err = mnt_want_write_file(filp);
+		if (err)
+			return err;
+		handle = ext4_journal_start_sb(sb, EXT4_HT_MISC, 1);
+		if (IS_ERR(handle)) {
+			err = PTR_ERR(handle);
+			goto pwsalt_err_exit;
+		}
+		err = ext4_journal_get_write_access(handle, sb, sbi->s_sbh,
+						    EXT4_JTR_NONE);
+		if (err)
+			goto pwsalt_err_journal;
+		lock_buffer(sbi->s_sbh);
+		generate_random_uuid(sbi->s_es->s_encrypt_pw_salt);
+		ext4_superblock_csum_set(sb);
+		unlock_buffer(sbi->s_sbh);
+		err = ext4_handle_dirty_metadata(handle, NULL, sbi->s_sbh);
+pwsalt_err_journal:
+		err2 = ext4_journal_stop(handle);
+		if (err2 && !err)
+			err = err2;
+pwsalt_err_exit:
+		mnt_drop_write_file(filp);
+		if (err)
+			return err;
+	}
+
+	if (copy_to_user(arg, sbi->s_es->s_encrypt_pw_salt, 16))
+		return -EFAULT;
+	return 0;
+}
+
+static int ext4_get_context(struct inode *inode, void *ctx, size_t len)
+{
+	return ext4_xattr_get(inode, EXT4_XATTR_INDEX_ENCRYPTION,
+				 EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, ctx, len);
+}
+
+static int ext4_set_context(struct inode *inode, const void *ctx, size_t len,
+							void *fs_data)
+{
+	handle_t *handle = fs_data;
+	int res, res2, credits, retries = 0;
+
+	/*
+	 * Encrypting the root directory is not allowed because e2fsck expects
+	 * lost+found to exist and be unencrypted, and encrypting the root
+	 * directory would imply encrypting the lost+found directory as well as
+	 * the filename "lost+found" itself.
+	 */
+	if (inode->i_ino == EXT4_ROOT_INO)
+		return -EPERM;
+
+	if (WARN_ON_ONCE(IS_DAX(inode) && i_size_read(inode)))
+		return -EINVAL;
+
+	if (ext4_test_inode_flag(inode, EXT4_INODE_DAX))
+		return -EOPNOTSUPP;
+
+	res = ext4_convert_inline_data(inode);
+	if (res)
+		return res;
+
+	/*
+	 * If a journal handle was specified, then the encryption context is
+	 * being set on a new inode via inheritance and is part of a larger
+	 * transaction to create the inode.  Otherwise the encryption context is
+	 * being set on an existing inode in its own transaction.  Only in the
+	 * latter case should the "retry on ENOSPC" logic be used.
+	 */
+
+	if (handle) {
+		res = ext4_xattr_set_handle(handle, inode,
+					    EXT4_XATTR_INDEX_ENCRYPTION,
+					    EXT4_XATTR_NAME_ENCRYPTION_CONTEXT,
+					    ctx, len, 0);
+		if (!res) {
+			ext4_set_inode_flag(inode, EXT4_INODE_ENCRYPT);
+			ext4_clear_inode_state(inode,
+					EXT4_STATE_MAY_INLINE_DATA);
+			/*
+			 * Update inode->i_flags - S_ENCRYPTED will be enabled,
+			 * S_DAX may be disabled
+			 */
+			ext4_set_inode_flags(inode, false);
+		}
+		return res;
+	}
+
+	res = dquot_initialize(inode);
+	if (res)
+		return res;
+retry:
+	res = ext4_xattr_set_credits(inode, len, false /* is_create */,
+				     &credits);
+	if (res)
+		return res;
+
+	handle = ext4_journal_start(inode, EXT4_HT_MISC, credits);
+	if (IS_ERR(handle))
+		return PTR_ERR(handle);
+
+	res = ext4_xattr_set_handle(handle, inode, EXT4_XATTR_INDEX_ENCRYPTION,
+				    EXT4_XATTR_NAME_ENCRYPTION_CONTEXT,
+				    ctx, len, 0);
+	if (!res) {
+		ext4_set_inode_flag(inode, EXT4_INODE_ENCRYPT);
+		/*
+		 * Update inode->i_flags - S_ENCRYPTED will be enabled,
+		 * S_DAX may be disabled
+		 */
+		ext4_set_inode_flags(inode, false);
+		res = ext4_mark_inode_dirty(handle, inode);
+		if (res)
+			EXT4_ERROR_INODE(inode, "Failed to mark inode dirty");
+	}
+	res2 = ext4_journal_stop(handle);
+
+	if (res == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
+		goto retry;
+	if (!res)
+		res = res2;
+	return res;
+}
+
+static const union fscrypt_policy *ext4_get_dummy_policy(struct super_block *sb)
+{
+	return EXT4_SB(sb)->s_dummy_enc_policy.policy;
+}
+
+static bool ext4_has_stable_inodes(struct super_block *sb)
+{
+	return ext4_has_feature_stable_inodes(sb);
+}
+
+static void ext4_get_ino_and_lblk_bits(struct super_block *sb,
+				       int *ino_bits_ret, int *lblk_bits_ret)
+{
+	*ino_bits_ret = 8 * sizeof(EXT4_SB(sb)->s_es->s_inodes_count);
+	*lblk_bits_ret = 8 * sizeof(ext4_lblk_t);
+}
+
+const struct fscrypt_operations ext4_cryptops = {
+	.key_prefix		= "ext4:",
+	.get_context		= ext4_get_context,
+	.set_context		= ext4_set_context,
+	.get_dummy_policy	= ext4_get_dummy_policy,
+	.empty_dir		= ext4_empty_dir,
+	.has_stable_inodes	= ext4_has_stable_inodes,
+	.get_ino_and_lblk_bits	= ext4_get_ino_and_lblk_bits,
+};

fs/ext4/dir.c

@@ -412,7 +412,7 @@ struct fname {
 };
 
 /*
- * This functoin implements a non-recursive way of freeing all of the
+ * This function implements a non-recursive way of freeing all of the
  * nodes in the red-black tree.
  */
 static void free_rb_tree_fname(struct rb_root *root)
@@ -515,7 +515,7 @@ int ext4_htree_store_dirent(struct file *dir_file, __u32 hash,
 
 /*
  * This is a helper function for ext4_dx_readdir.  It calls filldir
- * for all entres on the fname linked list.  (Normally there is only
+ * for all entries on the fname linked list.  (Normally there is only
  * one entry on the linked list, unless there are 62 bit hash collisions.)
  */
 static int call_filldir(struct file *file, struct dir_context *ctx,
@@ -648,7 +648,7 @@ int ext4_check_all_de(struct inode *dir, struct buffer_head *bh, void *buf,
 	unsigned int offset = 0;
 	char *top;
 
-	de = (struct ext4_dir_entry_2 *)buf;
+	de = buf;
 	top = buf + buf_size;
 	while ((char *) de < top) {
 		if (ext4_check_dir_entry(dir, NULL, de, bh,

fs/ext4/ext4.h

@@ -673,6 +673,8 @@ enum {
 	/* Caller will submit data before dropping transaction handle. This
 	 * allows jbd2 to avoid submitting data before commit. */
 #define EXT4_GET_BLOCKS_IO_SUBMIT		0x0400
+	/* Caller is in the atomic contex, find extent if it has been cached */
+#define EXT4_GET_BLOCKS_CACHED_NOWAIT		0x0800
 
 /*
  * The bit position of these flags must not overlap with any of the
@@ -1440,12 +1442,6 @@ struct ext4_super_block {
 
 #ifdef __KERNEL__
 
-#ifdef CONFIG_FS_ENCRYPTION
-#define DUMMY_ENCRYPTION_ENABLED(sbi) ((sbi)->s_dummy_enc_policy.policy != NULL)
-#else
-#define DUMMY_ENCRYPTION_ENABLED(sbi) (0)
-#endif
-
 /* Number of quota types we support */
 #define EXT4_MAXQUOTAS 3
 
@@ -2731,74 +2727,20 @@ extern int ext4_fname_setup_ci_filename(struct inode *dir,
 					 struct ext4_filename *fname);
 #endif
 
+/* ext4 encryption related stuff goes here crypto.c */
 #ifdef CONFIG_FS_ENCRYPTION
-static inline void ext4_fname_from_fscrypt_name(struct ext4_filename *dst,
+extern const struct fscrypt_operations ext4_cryptops;
-						const struct fscrypt_name *src)
-{
-	memset(dst, 0, sizeof(*dst));
 
-	dst->usr_fname = src->usr_fname;
+int ext4_fname_setup_filename(struct inode *dir, const struct qstr *iname,
-	dst->disk_name = src->disk_name;
+			      int lookup, struct ext4_filename *fname);
-	dst->hinfo.hash = src->hash;
-	dst->hinfo.minor_hash = src->minor_hash;
-	dst->crypto_buf = src->crypto_buf;
-}
 
-static inline int ext4_fname_setup_filename(struct inode *dir,
+int ext4_fname_prepare_lookup(struct inode *dir, struct dentry *dentry,
-					    const struct qstr *iname,
+			      struct ext4_filename *fname);
-					    int lookup,
-					    struct ext4_filename *fname)
-{
-	struct fscrypt_name name;
-	int err;
 
-	err = fscrypt_setup_filename(dir, iname, lookup, &name);
+void ext4_fname_free_filename(struct ext4_filename *fname);
-	if (err)
-		return err;
 
-	ext4_fname_from_fscrypt_name(fname, &name);
+int ext4_ioctl_get_encryption_pwsalt(struct file *filp, void __user *arg);
 
-#if IS_ENABLED(CONFIG_UNICODE)
-	err = ext4_fname_setup_ci_filename(dir, iname, fname);
-#endif
-	return err;
-}
-
-static inline int ext4_fname_prepare_lookup(struct inode *dir,
-					    struct dentry *dentry,
-					    struct ext4_filename *fname)
-{
-	struct fscrypt_name name;
-	int err;
-
-	err = fscrypt_prepare_lookup(dir, dentry, &name);
-	if (err)
-		return err;
-
-	ext4_fname_from_fscrypt_name(fname, &name);
-
-#if IS_ENABLED(CONFIG_UNICODE)
-	err = ext4_fname_setup_ci_filename(dir, &dentry->d_name, fname);
-#endif
-	return err;
-}
-
-static inline void ext4_fname_free_filename(struct ext4_filename *fname)
-{
-	struct fscrypt_name name;
-
-	name.crypto_buf = fname->crypto_buf;
-	fscrypt_free_filename(&name);
-
-	fname->crypto_buf.name = NULL;
-	fname->usr_fname = NULL;
-	fname->disk_name.name = NULL;
-
-#if IS_ENABLED(CONFIG_UNICODE)
-	kfree(fname->cf_name.name);
-	fname->cf_name.name = NULL;
-#endif
-}
 #else /* !CONFIG_FS_ENCRYPTION */
 static inline int ext4_fname_setup_filename(struct inode *dir,
 					    const struct qstr *iname,
@@ -2831,6 +2773,12 @@ static inline void ext4_fname_free_filename(struct ext4_filename *fname)
 	fname->cf_name.name = NULL;
 #endif
 }
+
+static inline int ext4_ioctl_get_encryption_pwsalt(struct file *filp,
+						   void __user *arg)
+{
+	return -EOPNOTSUPP;
+}
 #endif /* !CONFIG_FS_ENCRYPTION */
 
 /* dir.c */

fs/ext4/extents.c

@@ -372,7 +372,7 @@ static int ext4_valid_extent_entries(struct inode *inode,
 {
 	unsigned short entries;
 	ext4_lblk_t lblock = 0;
-	ext4_lblk_t prev = 0;
+	ext4_lblk_t cur = 0;
 
 	if (eh->eh_entries == 0)
 		return 1;
@@ -396,11 +396,11 @@ static int ext4_valid_extent_entries(struct inode *inode,
 
 			/* Check for overlapping extents */
 			lblock = le32_to_cpu(ext->ee_block);
-			if ((lblock <= prev) && prev) {
+			if (lblock < cur) {
 				*pblk = ext4_ext_pblock(ext);
 				return 0;
 			}
-			prev = lblock + ext4_ext_get_actual_len(ext) - 1;
+			cur = lblock + ext4_ext_get_actual_len(ext);
 			ext++;
 			entries--;
 		}
@@ -420,13 +420,13 @@ static int ext4_valid_extent_entries(struct inode *inode,
 
 			/* Check for overlapping index extents */
 			lblock = le32_to_cpu(ext_idx->ei_block);
-			if ((lblock <= prev) && prev) {
+			if (lblock < cur) {
 				*pblk = ext4_idx_pblock(ext_idx);
 				return 0;
 			}
 			ext_idx++;
 			entries--;
-			prev = lblock;
+			cur = lblock + 1;
 		}
 	}
 	return 1;
@@ -4693,15 +4693,17 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 		     FALLOC_FL_INSERT_RANGE))
 		return -EOPNOTSUPP;
 
+	inode_lock(inode);
+	ret = ext4_convert_inline_data(inode);
+	inode_unlock(inode);
+	if (ret)
+		goto exit;
+
 	if (mode & FALLOC_FL_PUNCH_HOLE) {
 		ret = ext4_punch_hole(file, offset, len);
 		goto exit;
 	}
 
-	ret = ext4_convert_inline_data(inode);
-	if (ret)
-		goto exit;
-
 	if (mode & FALLOC_FL_COLLAPSE_RANGE) {
 		ret = ext4_collapse_range(file, offset, len);
 		goto exit;

fs/ext4/fast_commit.c

@@ -970,7 +970,7 @@ static int ext4_fc_write_inode_data(struct inode *inode, u32 *crc)
 /* Submit data for all the fast commit inodes */
 static int ext4_fc_submit_inode_data_all(journal_t *journal)
 {
-	struct super_block *sb = (struct super_block *)(journal->j_private);
+	struct super_block *sb = journal->j_private;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	struct ext4_inode_info *ei;
 	int ret = 0;
@@ -1004,7 +1004,7 @@ static int ext4_fc_submit_inode_data_all(journal_t *journal)
 /* Wait for completion of data for all the fast commit inodes */
 static int ext4_fc_wait_inode_data_all(journal_t *journal)
 {
-	struct super_block *sb = (struct super_block *)(journal->j_private);
+	struct super_block *sb = journal->j_private;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	struct ext4_inode_info *pos, *n;
 	int ret = 0;
@@ -1031,7 +1031,7 @@ static int ext4_fc_commit_dentry_updates(journal_t *journal, u32 *crc)
 __acquires(&sbi->s_fc_lock)
 __releases(&sbi->s_fc_lock)
 {
-	struct super_block *sb = (struct super_block *)(journal->j_private);
+	struct super_block *sb = journal->j_private;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	struct ext4_fc_dentry_update *fc_dentry, *fc_dentry_n;
 	struct inode *inode;
@@ -1093,7 +1093,7 @@ lock_and_exit:
 
 static int ext4_fc_perform_commit(journal_t *journal)
 {
-	struct super_block *sb = (struct super_block *)(journal->j_private);
+	struct super_block *sb = journal->j_private;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	struct ext4_inode_info *iter;
 	struct ext4_fc_head head;
@@ -1198,7 +1198,7 @@ static void ext4_fc_update_stats(struct super_block *sb, int status,
  */
 int ext4_fc_commit(journal_t *journal, tid_t commit_tid)
 {
-	struct super_block *sb = (struct super_block *)(journal->j_private);
+	struct super_block *sb = journal->j_private;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	int nblks = 0, ret, bsize = journal->j_blocksize;
 	int subtid = atomic_read(&sbi->s_fc_subtid);
@@ -1659,8 +1659,7 @@ static int ext4_fc_replay_create(struct super_block *sb, struct ext4_fc_tl *tl,
 	set_nlink(inode, 1);
 	ext4_mark_inode_dirty(NULL, inode);
 out:
-	if (inode)
+	iput(inode);
-		iput(inode);
 	return ret;
 }
 

fs/ext4/inline.c

@@ -1083,14 +1083,14 @@ static void ext4_update_final_de(void *de_buf, int old_size, int new_size)
 	void *limit;
 	int de_len;
 
-	de = (struct ext4_dir_entry_2 *)de_buf;
+	de = de_buf;
 	if (old_size) {
 		limit = de_buf + old_size;
 		do {
 			prev_de = de;
 			de_len = ext4_rec_len_from_disk(de->rec_len, old_size);
 			de_buf += de_len;
-			de = (struct ext4_dir_entry_2 *)de_buf;
+			de = de_buf;
 		} while (de_buf < limit);
 
 		prev_de->rec_len = ext4_rec_len_to_disk(de_len + new_size -
@@ -1155,7 +1155,7 @@ static int ext4_finish_convert_inline_dir(handle_t *handle,
 	 * First create "." and ".." and then copy the dir information
 	 * back to the block.
 	 */
-	de = (struct ext4_dir_entry_2 *)target;
+	de = target;
 	de = ext4_init_dot_dotdot(inode, de,
 		inode->i_sb->s_blocksize, csum_size,
 		le32_to_cpu(((struct ext4_dir_entry_2 *)buf)->inode), 1);
@@ -2005,6 +2005,18 @@ int ext4_convert_inline_data(struct inode *inode)
 	if (!ext4_has_inline_data(inode)) {
 		ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA);
 		return 0;
+	} else if (!ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)) {
+		/*
+		 * Inode has inline data but EXT4_STATE_MAY_INLINE_DATA is
+		 * cleared. This means we are in the middle of moving of
+		 * inline data to delay allocated block. Just force writeout
+		 * here to finish conversion.
+		 */
+		error = filemap_flush(inode->i_mapping);
+		if (error)
+			return error;
+		if (!ext4_has_inline_data(inode))
+			return 0;
 	}
 
 	needed_blocks = ext4_writepage_trans_blocks(inode);

fs/ext4/inode.c

@@ -41,7 +41,6 @@
 #include <linux/bitops.h>
 #include <linux/iomap.h>
 #include <linux/iversion.h>
-#include <linux/dax.h>
 
 #include "ext4_jbd2.h"
 #include "xattr.h"
@@ -199,8 +198,7 @@ void ext4_evict_inode(struct inode *inode)
 		 */
 		if (inode->i_ino != EXT4_JOURNAL_INO &&
 		    ext4_should_journal_data(inode) &&
-		    (S_ISLNK(inode->i_mode) || S_ISREG(inode->i_mode)) &&
+		    S_ISREG(inode->i_mode) && inode->i_data.nrpages) {
-		    inode->i_data.nrpages) {
 			journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
 			tid_t commit_tid = EXT4_I(inode)->i_datasync_tid;
 
@@ -545,12 +543,21 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
 		} else {
 			BUG();
 		}
+
+		if (flags & EXT4_GET_BLOCKS_CACHED_NOWAIT)
+			return retval;
 #ifdef ES_AGGRESSIVE_TEST
 		ext4_map_blocks_es_recheck(handle, inode, map,
 					   &orig_map, flags);
 #endif
 		goto found;
 	}
+	/*
+	 * In the query cache no-wait mode, nothing we can do more if we
+	 * cannot find extent in the cache.
+	 */
+	if (flags & EXT4_GET_BLOCKS_CACHED_NOWAIT)
+		return 0;
 
 	/*
 	 * Try to see if we can get the block without requesting a new
@@ -837,10 +844,12 @@ struct buffer_head *ext4_getblk(handle_t *handle, struct inode *inode,
 	struct ext4_map_blocks map;
 	struct buffer_head *bh;
 	int create = map_flags & EXT4_GET_BLOCKS_CREATE;
+	bool nowait = map_flags & EXT4_GET_BLOCKS_CACHED_NOWAIT;
 	int err;
 
 	ASSERT((EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)
 		    || handle != NULL || create == 0);
+	ASSERT(create == 0 || !nowait);
 
 	map.m_lblk = block;
 	map.m_len = 1;
@@ -851,6 +860,9 @@ struct buffer_head *ext4_getblk(handle_t *handle, struct inode *inode,
 	if (err < 0)
 		return ERR_PTR(err);
 
+	if (nowait)
+		return sb_find_get_block(inode->i_sb, map.m_pblk);
+
 	bh = sb_getblk(inode->i_sb, map.m_pblk);
 	if (unlikely(!bh))
 		return ERR_PTR(-ENOMEM);
@@ -2944,8 +2956,7 @@ static int ext4_da_write_begin(struct file *file, struct address_space *mapping,
 
 	index = pos >> PAGE_SHIFT;
 
-	if (ext4_nonda_switch(inode->i_sb) || S_ISLNK(inode->i_mode) ||
+	if (ext4_nonda_switch(inode->i_sb) || ext4_verity_in_progress(inode)) {
-	    ext4_verity_in_progress(inode)) {
 		*fsdata = (void *)FALL_BACK_TO_NONDELALLOC;
 		return ext4_write_begin(file, mapping, pos,
 					len, flags, pagep, fsdata);
@@ -3967,15 +3978,6 @@ int ext4_punch_hole(struct file *file, loff_t offset, loff_t length)
 
 	trace_ext4_punch_hole(inode, offset, length, 0);
 
-	ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA);
-	if (ext4_has_inline_data(inode)) {
-		filemap_invalidate_lock(mapping);
-		ret = ext4_convert_inline_data(inode);
-		filemap_invalidate_unlock(mapping);
-		if (ret)
-			return ret;
-	}
-
 	/*
 	 * Write out all dirty pages to avoid race conditions
 	 * Then release them.
@@ -4991,7 +4993,6 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino,
 		}
 		if (IS_ENCRYPTED(inode)) {
 			inode->i_op = &ext4_encrypted_symlink_inode_operations;
-			ext4_set_aops(inode);
 		} else if (ext4_inode_is_fast_symlink(inode)) {
 			inode->i_link = (char *)ei->i_data;
 			inode->i_op = &ext4_fast_symlink_inode_operations;
@@ -4999,9 +5000,7 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino,
 				sizeof(ei->i_data) - 1);
 		} else {
 			inode->i_op = &ext4_symlink_inode_operations;
-			ext4_set_aops(inode);
 		}
-		inode_nohighmem(inode);
 	} else if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode) ||
 	      S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode)) {
 		inode->i_op = &ext4_special_inode_operations;
@@ -5398,6 +5397,7 @@ int ext4_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
 	if (attr->ia_valid & ATTR_SIZE) {
 		handle_t *handle;
 		loff_t oldsize = inode->i_size;
+		loff_t old_disksize;
 		int shrink = (attr->ia_size < inode->i_size);
 
 		if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) {
@@ -5469,6 +5469,7 @@ int ext4_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
 					inode->i_sb->s_blocksize_bits);
 
 			down_write(&EXT4_I(inode)->i_data_sem);
+			old_disksize = EXT4_I(inode)->i_disksize;
 			EXT4_I(inode)->i_disksize = attr->ia_size;
 			rc = ext4_mark_inode_dirty(handle, inode);
 			if (!error)
@@ -5480,6 +5481,8 @@ int ext4_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
 			 */
 			if (!error)
 				i_size_write(inode, attr->ia_size);
+			else
+				EXT4_I(inode)->i_disksize = old_disksize;
 			up_write(&EXT4_I(inode)->i_data_sem);
 			ext4_journal_stop(handle);
 			if (error)

fs/ext4/ioctl.c

@@ -16,7 +16,6 @@
 #include <linux/file.h>
 #include <linux/quotaops.h>
 #include <linux/random.h>
-#include <linux/uuid.h>
 #include <linux/uaccess.h>
 #include <linux/delay.h>
 #include <linux/iversion.h>
@@ -504,18 +503,6 @@ journal_err_out:
 	return err;
 }
 
-#ifdef CONFIG_FS_ENCRYPTION
-static int uuid_is_zero(__u8 u[16])
-{
-	int	i;
-
-	for (i = 0; i < 16; i++)
-		if (u[i])
-			return 0;
-	return 1;
-}
-#endif
-
 /*
  * If immutable is set and we are not clearing it, we're not allowed to change
  * anything else in the inode.  Don't error out if we're only trying to set
@@ -1428,51 +1415,9 @@ resizefs_out:
 			return -EOPNOTSUPP;
 		return fscrypt_ioctl_set_policy(filp, (const void __user *)arg);
 
-	case FS_IOC_GET_ENCRYPTION_PWSALT: {
+	case FS_IOC_GET_ENCRYPTION_PWSALT:
-#ifdef CONFIG_FS_ENCRYPTION
+		return ext4_ioctl_get_encryption_pwsalt(filp, (void __user *)arg);
-		int err, err2;
-		struct ext4_sb_info *sbi = EXT4_SB(sb);
-		handle_t *handle;
 
-		if (!ext4_has_feature_encrypt(sb))
-			return -EOPNOTSUPP;
-		if (uuid_is_zero(sbi->s_es->s_encrypt_pw_salt)) {
-			err = mnt_want_write_file(filp);
-			if (err)
-				return err;
-			handle = ext4_journal_start_sb(sb, EXT4_HT_MISC, 1);
-			if (IS_ERR(handle)) {
-				err = PTR_ERR(handle);
-				goto pwsalt_err_exit;
-			}
-			err = ext4_journal_get_write_access(handle, sb,
-							    sbi->s_sbh,
-							    EXT4_JTR_NONE);
-			if (err)
-				goto pwsalt_err_journal;
-			lock_buffer(sbi->s_sbh);
-			generate_random_uuid(sbi->s_es->s_encrypt_pw_salt);
-			ext4_superblock_csum_set(sb);
-			unlock_buffer(sbi->s_sbh);
-			err = ext4_handle_dirty_metadata(handle, NULL,
-							 sbi->s_sbh);
-		pwsalt_err_journal:
-			err2 = ext4_journal_stop(handle);
-			if (err2 && !err)
-				err = err2;
-		pwsalt_err_exit:
-			mnt_drop_write_file(filp);
-			if (err)
-				return err;
-		}
-		if (copy_to_user((void __user *) arg,
-				 sbi->s_es->s_encrypt_pw_salt, 16))
-			return -EFAULT;
-		return 0;
-#else
-		return -EOPNOTSUPP;
-#endif
-	}
 	case FS_IOC_GET_ENCRYPTION_POLICY:
 		if (!ext4_has_feature_encrypt(sb))
 			return -EOPNOTSUPP;

fs/ext4/mballoc.c

@@ -695,13 +695,10 @@ static int __mb_check_buddy(struct ext4_buddy *e4b, char *file,
 		for (i = 0; i < max; i++) {
 
 			if (mb_test_bit(i, buddy)) {
-				/* only single bit in buddy2 may be 1 */
+				/* only single bit in buddy2 may be 0 */
 				if (!mb_test_bit(i << 1, buddy2)) {
 					MB_CHECK_ASSERT(
 						mb_test_bit((i<<1)+1, buddy2));
-				} else if (!mb_test_bit((i << 1) + 1, buddy2)) {
-					MB_CHECK_ASSERT(
-						mb_test_bit(i << 1, buddy2));
 				}
 				continue;
 			}
@@ -2919,7 +2916,7 @@ const struct seq_operations ext4_mb_seq_groups_ops = {
 
 int ext4_seq_mb_stats_show(struct seq_file *seq, void *offset)
 {
-	struct super_block *sb = (struct super_block *)seq->private;
+	struct super_block *sb = seq->private;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 
 	seq_puts(seq, "mballoc:\n");
@@ -6398,6 +6395,7 @@ __releases(ext4_group_lock_ptr(sb, e4b->bd_group))
  * @start:		first group block to examine
  * @max:		last group block to examine
  * @minblocks:		minimum extent block count
+ * @set_trimmed:	set the trimmed flag if at least one block is trimmed
  *
  * ext4_trim_all_free walks through group's block bitmap searching for free
  * extents. When the free extent is found, mark it as used in group buddy
@@ -6407,7 +6405,7 @@ __releases(ext4_group_lock_ptr(sb, e4b->bd_group))
 static ext4_grpblk_t
 ext4_trim_all_free(struct super_block *sb, ext4_group_t group,
 		   ext4_grpblk_t start, ext4_grpblk_t max,
-		   ext4_grpblk_t minblocks)
+		   ext4_grpblk_t minblocks, bool set_trimmed)
 {
 	struct ext4_buddy e4b;
 	int ret;
@@ -6426,7 +6424,7 @@ ext4_trim_all_free(struct super_block *sb, ext4_group_t group,
 	if (!EXT4_MB_GRP_WAS_TRIMMED(e4b.bd_info) ||
 	    minblocks < EXT4_SB(sb)->s_last_trim_minblks) {
 		ret = ext4_try_to_trim_range(sb, &e4b, start, max, minblocks);
-		if (ret >= 0)
+		if (ret >= 0 && set_trimmed)
 			EXT4_MB_GRP_SET_TRIMMED(e4b.bd_info);
 	} else {
 		ret = 0;
@@ -6463,6 +6461,7 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
 	ext4_fsblk_t first_data_blk =
 			le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block);
 	ext4_fsblk_t max_blks = ext4_blocks_count(EXT4_SB(sb)->s_es);
+	bool whole_group, eof = false;
 	int ret = 0;
 
 	start = range->start >> sb->s_blocksize_bits;
@@ -6481,8 +6480,10 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
 		if (minlen > EXT4_CLUSTERS_PER_GROUP(sb))
 			goto out;
 	}
-	if (end >= max_blks)
+	if (end >= max_blks - 1) {
 		end = max_blks - 1;
+		eof = true;
+	}
 	if (end <= first_data_blk)
 		goto out;
 	if (start < first_data_blk)
@@ -6496,6 +6497,7 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
 
 	/* end now represents the last cluster to discard in this group */
 	end = EXT4_CLUSTERS_PER_GROUP(sb) - 1;
+	whole_group = true;
 
 	for (group = first_group; group <= last_group; group++) {
 		grp = ext4_get_group_info(sb, group);
@@ -6512,12 +6514,13 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
 		 * change it for the last group, note that last_cluster is
 		 * already computed earlier by ext4_get_group_no_and_offset()
 		 */
-		if (group == last_group)
+		if (group == last_group) {
 			end = last_cluster;
-
+			whole_group = eof ? true : end == EXT4_CLUSTERS_PER_GROUP(sb) - 1;
+		}
 		if (grp->bb_free >= minlen) {
 			cnt = ext4_trim_all_free(sb, group, first_cluster,
-						end, minlen);
+						 end, minlen, whole_group);
 			if (cnt < 0) {
 				ret = cnt;
 				break;

fs/ext4/mmp.c

@@ -127,7 +127,7 @@ void __dump_mmp_msg(struct super_block *sb, struct mmp_struct *mmp,
  */
 static int kmmpd(void *data)
 {
-	struct super_block *sb = (struct super_block *) data;
+	struct super_block *sb = data;
 	struct ext4_super_block *es = EXT4_SB(sb)->s_es;
 	struct buffer_head *bh = EXT4_SB(sb)->s_mmp_bh;
 	struct mmp_struct *mmp;

fs/ext4/namei.c

@@ -277,9 +277,9 @@ static struct dx_frame *dx_probe(struct ext4_filename *fname,
 				 struct dx_hash_info *hinfo,
 				 struct dx_frame *frame);
 static void dx_release(struct dx_frame *frames);
-static int dx_make_map(struct inode *dir, struct ext4_dir_entry_2 *de,
+static int dx_make_map(struct inode *dir, struct buffer_head *bh,
-		       unsigned blocksize, struct dx_hash_info *hinfo,
+		       struct dx_hash_info *hinfo,
-		       struct dx_map_entry map[]);
+		       struct dx_map_entry *map_tail);
 static void dx_sort_map(struct dx_map_entry *map, unsigned count);
 static struct ext4_dir_entry_2 *dx_move_dirents(struct inode *dir, char *from,
 					char *to, struct dx_map_entry *offsets,
@@ -777,12 +777,14 @@ static struct dx_frame *
 dx_probe(struct ext4_filename *fname, struct inode *dir,
 	 struct dx_hash_info *hinfo, struct dx_frame *frame_in)
 {
-	unsigned count, indirect;
+	unsigned count, indirect, level, i;
 	struct dx_entry *at, *entries, *p, *q, *m;
 	struct dx_root *root;
 	struct dx_frame *frame = frame_in;
 	struct dx_frame *ret_err = ERR_PTR(ERR_BAD_DX_DIR);
 	u32 hash;
+	ext4_lblk_t block;
+	ext4_lblk_t blocks[EXT4_HTREE_LEVEL];
 
 	memset(frame_in, 0, EXT4_HTREE_LEVEL * sizeof(frame_in[0]));
 	frame->bh = ext4_read_dirblock(dir, 0, INDEX);
@@ -854,6 +856,8 @@ dx_probe(struct ext4_filename *fname, struct inode *dir,
 	}
 
 	dxtrace(printk("Look up %x", hash));
+	level = 0;
+	blocks[0] = 0;
 	while (1) {
 		count = dx_get_count(entries);
 		if (!count || count > dx_get_limit(entries)) {
@@ -882,15 +886,27 @@ dx_probe(struct ext4_filename *fname, struct inode *dir,
 			       dx_get_block(at)));
 		frame->entries = entries;
 		frame->at = at;
-		if (!indirect--)
+
+		block = dx_get_block(at);
+		for (i = 0; i <= level; i++) {
+			if (blocks[i] == block) {
+				ext4_warning_inode(dir,
+					"dx entry: tree cycle block %u points back to block %u",
+					blocks[level], block);
+				goto fail;
+			}
+		}
+		if (++level > indirect)
 			return frame;
+		blocks[level] = block;
 		frame++;
-		frame->bh = ext4_read_dirblock(dir, dx_get_block(at), INDEX);
+		frame->bh = ext4_read_dirblock(dir, block, INDEX);
 		if (IS_ERR(frame->bh)) {
 			ret_err = (struct dx_frame *) frame->bh;
 			frame->bh = NULL;
 			goto fail;
 		}
+
 		entries = ((struct dx_node *) frame->bh->b_data)->entries;
 
 		if (dx_get_limit(entries) != dx_node_limit(dir)) {
@@ -1249,15 +1265,23 @@ static inline int search_dirblock(struct buffer_head *bh,
  * Create map of hash values, offsets, and sizes, stored at end of block.
  * Returns number of entries mapped.
  */
-static int dx_make_map(struct inode *dir, struct ext4_dir_entry_2 *de,
+static int dx_make_map(struct inode *dir, struct buffer_head *bh,
-		       unsigned blocksize, struct dx_hash_info *hinfo,
+		       struct dx_hash_info *hinfo,
 		       struct dx_map_entry *map_tail)
 {
 	int count = 0;
-	char *base = (char *) de;
+	struct ext4_dir_entry_2 *de = (struct ext4_dir_entry_2 *)bh->b_data;
+	unsigned int buflen = bh->b_size;
+	char *base = bh->b_data;
 	struct dx_hash_info h = *hinfo;
 
-	while ((char *) de < base + blocksize) {
+	if (ext4_has_metadata_csum(dir->i_sb))
+		buflen -= sizeof(struct ext4_dir_entry_tail);
+
+	while ((char *) de < base + buflen) {
+		if (ext4_check_dir_entry(dir, NULL, de, bh, base, buflen,
+					 ((char *)de) - base))
+			return -EFSCORRUPTED;
 		if (de->name_len && de->inode) {
 			if (ext4_hash_in_dirent(dir))
 				h.hash = EXT4_DIRENT_HASH(de);
@@ -1270,8 +1294,7 @@ static int dx_make_map(struct inode *dir, struct ext4_dir_entry_2 *de,
 			count++;
 			cond_resched();
 		}
-		/* XXX: do we need to check rec_len == 0 case? -Chris */
+		de = ext4_next_entry(de, dir->i_sb->s_blocksize);
-		de = ext4_next_entry(de, blocksize);
 	}
 	return count;
 }
@@ -1943,8 +1966,11 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir,
 
 	/* create map in the end of data2 block */
 	map = (struct dx_map_entry *) (data2 + blocksize);
-	count = dx_make_map(dir, (struct ext4_dir_entry_2 *) data1,
+	count = dx_make_map(dir, *bh, hinfo, map);
-			     blocksize, hinfo, map);
+	if (count < 0) {
+		err = count;
+		goto journal_error;
+	}
 	map -= count;
 	dx_sort_map(map, count);
 	/* Ensure that neither split block is over half full */
@@ -2031,7 +2057,7 @@ int ext4_find_dest_de(struct inode *dir, struct inode *inode,
 	unsigned int offset = 0;
 	char *top;
 
-	de = (struct ext4_dir_entry_2 *)buf;
+	de = buf;
 	top = buf + buf_size - reclen;
 	while ((char *) de <= top) {
 		if (ext4_check_dir_entry(dir, NULL, de, bh,
@@ -2587,7 +2613,7 @@ int ext4_generic_delete_entry(struct inode *dir,
 
 	i = 0;
 	pde = NULL;
-	de = (struct ext4_dir_entry_2 *)entry_buf;
+	de = entry_buf;
 	while (i < buf_size - csum_size) {
 		if (ext4_check_dir_entry(dir, NULL, de, bh,
 					 entry_buf, buf_size, i))
@@ -3249,6 +3275,32 @@ out_trace:
 	return retval;
 }
 
+static int ext4_init_symlink_block(handle_t *handle, struct inode *inode,
+				   struct fscrypt_str *disk_link)
+{
+	struct buffer_head *bh;
+	char *kaddr;
+	int err = 0;
+
+	bh = ext4_bread(handle, inode, 0, EXT4_GET_BLOCKS_CREATE);
+	if (IS_ERR(bh))
+		return PTR_ERR(bh);
+
+	BUFFER_TRACE(bh, "get_write_access");
+	err = ext4_journal_get_write_access(handle, inode->i_sb, bh, EXT4_JTR_NONE);
+	if (err)
+		goto out;
+
+	kaddr = (char *)bh->b_data;
+	memcpy(kaddr, disk_link->name, disk_link->len);
+	inode->i_size = disk_link->len - 1;
+	EXT4_I(inode)->i_disksize = inode->i_size;
+	err = ext4_handle_dirty_metadata(handle, inode, bh);
+out:
+	brelse(bh);
+	return err;
+}
+
 static int ext4_symlink(struct user_namespace *mnt_userns, struct inode *dir,
 			struct dentry *dentry, const char *symname)
 {
@@ -3257,6 +3309,7 @@ static int ext4_symlink(struct user_namespace *mnt_userns, struct inode *dir,
 	int err, len = strlen(symname);
 	int credits;
 	struct fscrypt_str disk_link;
+	int retries = 0;
 
 	if (unlikely(ext4_forced_shutdown(EXT4_SB(dir->i_sb))))
 		return -EIO;
@@ -3270,26 +3323,15 @@ static int ext4_symlink(struct user_namespace *mnt_userns, struct inode *dir,
 	if (err)
 		return err;
 
-	if ((disk_link.len > EXT4_N_BLOCKS * 4)) {
+	/*
-		/*
+	 * EXT4_INDEX_EXTRA_TRANS_BLOCKS for addition of entry into the
-		 * For non-fast symlinks, we just allocate inode and put it on
+	 * directory. +3 for inode, inode bitmap, group descriptor allocation.
-		 * orphan list in the first transaction => we need bitmap,
+	 * EXT4_DATA_TRANS_BLOCKS for the data block allocation and
-		 * group descriptor, sb, inode block, quota blocks, and
+	 * modification.
-		 * possibly selinux xattr blocks.
+	 */
-		 */
+	credits = EXT4_DATA_TRANS_BLOCKS(dir->i_sb) +
-		credits = 4 + EXT4_MAXQUOTAS_INIT_BLOCKS(dir->i_sb) +
+		  EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3;
-			  EXT4_XATTR_TRANS_BLOCKS;
+retry:
-	} else {
-		/*
-		 * Fast symlink. We have to add entry to directory
-		 * (EXT4_DATA_TRANS_BLOCKS + EXT4_INDEX_EXTRA_TRANS_BLOCKS),
-		 * allocate new inode (bitmap, group descriptor, inode block,
-		 * quota blocks, sb is already counted in previous macros).
-		 */
-		credits = EXT4_DATA_TRANS_BLOCKS(dir->i_sb) +
-			  EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3;
-	}
-
 	inode = ext4_new_inode_start_handle(mnt_userns, dir, S_IFLNK|S_IRWXUGO,
 					    &dentry->d_name, 0, NULL,
 					    EXT4_HT_DIR, credits);
@@ -3297,7 +3339,8 @@ static int ext4_symlink(struct user_namespace *mnt_userns, struct inode *dir,
 	if (IS_ERR(inode)) {
 		if (handle)
 			ext4_journal_stop(handle);
-		return PTR_ERR(inode);
+		err = PTR_ERR(inode);
+		goto out_retry;
 	}
 
 	if (IS_ENCRYPTED(inode)) {
@@ -3305,75 +3348,44 @@ static int ext4_symlink(struct user_namespace *mnt_userns, struct inode *dir,
 		if (err)
 			goto err_drop_inode;
 		inode->i_op = &ext4_encrypted_symlink_inode_operations;
+	} else {
+		if ((disk_link.len > EXT4_N_BLOCKS * 4)) {
+			inode->i_op = &ext4_symlink_inode_operations;
+		} else {
+			inode->i_op = &ext4_fast_symlink_inode_operations;
+			inode->i_link = (char *)&EXT4_I(inode)->i_data;
+		}
 	}
 
 	if ((disk_link.len > EXT4_N_BLOCKS * 4)) {
-		if (!IS_ENCRYPTED(inode))
+		/* alloc symlink block and fill it */
-			inode->i_op = &ext4_symlink_inode_operations;
+		err = ext4_init_symlink_block(handle, inode, &disk_link);
-		inode_nohighmem(inode);
-		ext4_set_aops(inode);
-		/*
-		 * We cannot call page_symlink() with transaction started
-		 * because it calls into ext4_write_begin() which can wait
-		 * for transaction commit if we are running out of space
-		 * and thus we deadlock. So we have to stop transaction now
-		 * and restart it when symlink contents is written.
-		 *
-		 * To keep fs consistent in case of crash, we have to put inode
-		 * to orphan list in the mean time.
-		 */
-		drop_nlink(inode);
-		err = ext4_orphan_add(handle, inode);
-		if (handle)
-			ext4_journal_stop(handle);
-		handle = NULL;
-		if (err)
-			goto err_drop_inode;
-		err = __page_symlink(inode, disk_link.name, disk_link.len, 1);
-		if (err)
-			goto err_drop_inode;
-		/*
-		 * Now inode is being linked into dir (EXT4_DATA_TRANS_BLOCKS
-		 * + EXT4_INDEX_EXTRA_TRANS_BLOCKS), inode is also modified
-		 */
-		handle = ext4_journal_start(dir, EXT4_HT_DIR,
-				EXT4_DATA_TRANS_BLOCKS(dir->i_sb) +
-				EXT4_INDEX_EXTRA_TRANS_BLOCKS + 1);
-		if (IS_ERR(handle)) {
-			err = PTR_ERR(handle);
-			handle = NULL;
-			goto err_drop_inode;
-		}
-		set_nlink(inode, 1);
-		err = ext4_orphan_del(handle, inode);
 		if (err)
 			goto err_drop_inode;
 	} else {
 		/* clear the extent format for fast symlink */
 		ext4_clear_inode_flag(inode, EXT4_INODE_EXTENTS);
-		if (!IS_ENCRYPTED(inode)) {
-			inode->i_op = &ext4_fast_symlink_inode_operations;
-			inode->i_link = (char *)&EXT4_I(inode)->i_data;
-		}
 		memcpy((char *)&EXT4_I(inode)->i_data, disk_link.name,
 		       disk_link.len);
 		inode->i_size = disk_link.len - 1;
+		EXT4_I(inode)->i_disksize = inode->i_size;
 	}
-	EXT4_I(inode)->i_disksize = inode->i_size;
 	err = ext4_add_nondir(handle, dentry, &inode);
 	if (handle)
 		ext4_journal_stop(handle);
-	if (inode)
+	iput(inode);
-		iput(inode);
+	goto out_retry;
-	goto out_free_encrypted_link;
 
 err_drop_inode:
+	clear_nlink(inode);
+	ext4_orphan_add(handle, inode);
+	unlock_new_inode(inode);
 	if (handle)
 		ext4_journal_stop(handle);
-	clear_nlink(inode);
-	unlock_new_inode(inode);
 	iput(inode);
-out_free_encrypted_link:
+out_retry:
+	if (err == -ENOSPC && ext4_should_retry_alloc(dir->i_sb, &retries))
+		goto retry;
 	if (disk_link.name != (unsigned char *)symname)
 		kfree(disk_link.name);
 	return err;
@@ -3455,6 +3467,9 @@ static struct buffer_head *ext4_get_first_dir_block(handle_t *handle,
 	struct buffer_head *bh;
 
 	if (!ext4_has_inline_data(inode)) {
+		struct ext4_dir_entry_2 *de;
+		unsigned int offset;
+
 		/* The first directory block must not be a hole, so
 		 * treat it as DIRENT_HTREE
 		 */
@@ -3463,9 +3478,30 @@ static struct buffer_head *ext4_get_first_dir_block(handle_t *handle,
 			*retval = PTR_ERR(bh);
 			return NULL;
 		}
-		*parent_de = ext4_next_entry(
+
-					(struct ext4_dir_entry_2 *)bh->b_data,
+		de = (struct ext4_dir_entry_2 *) bh->b_data;
-					inode->i_sb->s_blocksize);
+		if (ext4_check_dir_entry(inode, NULL, de, bh, bh->b_data,
+					 bh->b_size, 0) ||
+		    le32_to_cpu(de->inode) != inode->i_ino ||
+		    strcmp(".", de->name)) {
+			EXT4_ERROR_INODE(inode, "directory missing '.'");
+			brelse(bh);
+			*retval = -EFSCORRUPTED;
+			return NULL;
+		}
+		offset = ext4_rec_len_from_disk(de->rec_len,
+						inode->i_sb->s_blocksize);
+		de = ext4_next_entry(de, inode->i_sb->s_blocksize);
+		if (ext4_check_dir_entry(inode, NULL, de, bh, bh->b_data,
+					 bh->b_size, offset) ||
+		    le32_to_cpu(de->inode) == 0 || strcmp("..", de->name)) {
+			EXT4_ERROR_INODE(inode, "directory missing '..'");
+			brelse(bh);
+			*retval = -EFSCORRUPTED;
+			return NULL;
+		}
+		*parent_de = de;
+
 		return bh;
 	}
 

fs/ext4/super.c

@@ -1211,6 +1211,9 @@ static void ext4_put_super(struct super_block *sb)
 	 */
 	ext4_unregister_sysfs(sb);
 
+	if (___ratelimit(&ext4_mount_msg_ratelimit, "EXT4-fs unmount"))
+		ext4_msg(sb, KERN_INFO, "unmounting filesystem.");
+
 	ext4_unregister_li_request(sb);
 	ext4_quota_off_umount(sb);
 
@@ -1397,7 +1400,7 @@ static void ext4_destroy_inode(struct inode *inode)
 
 static void init_once(void *foo)
 {
-	struct ext4_inode_info *ei = (struct ext4_inode_info *) foo;
+	struct ext4_inode_info *ei = foo;
 
 	INIT_LIST_HEAD(&ei->i_orphan);
 	init_rwsem(&ei->xattr_sem);
@@ -1492,128 +1495,6 @@ static int ext4_nfs_commit_metadata(struct inode *inode)
 	return ext4_write_inode(inode, &wbc);
 }
 
-#ifdef CONFIG_FS_ENCRYPTION
-static int ext4_get_context(struct inode *inode, void *ctx, size_t len)
-{
-	return ext4_xattr_get(inode, EXT4_XATTR_INDEX_ENCRYPTION,
-				 EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, ctx, len);
-}
-
-static int ext4_set_context(struct inode *inode, const void *ctx, size_t len,
-							void *fs_data)
-{
-	handle_t *handle = fs_data;
-	int res, res2, credits, retries = 0;
-
-	/*
-	 * Encrypting the root directory is not allowed because e2fsck expects
-	 * lost+found to exist and be unencrypted, and encrypting the root
-	 * directory would imply encrypting the lost+found directory as well as
-	 * the filename "lost+found" itself.
-	 */
-	if (inode->i_ino == EXT4_ROOT_INO)
-		return -EPERM;
-
-	if (WARN_ON_ONCE(IS_DAX(inode) && i_size_read(inode)))
-		return -EINVAL;
-
-	if (ext4_test_inode_flag(inode, EXT4_INODE_DAX))
-		return -EOPNOTSUPP;
-
-	res = ext4_convert_inline_data(inode);
-	if (res)
-		return res;
-
-	/*
-	 * If a journal handle was specified, then the encryption context is
-	 * being set on a new inode via inheritance and is part of a larger
-	 * transaction to create the inode.  Otherwise the encryption context is
-	 * being set on an existing inode in its own transaction.  Only in the
-	 * latter case should the "retry on ENOSPC" logic be used.
-	 */
-
-	if (handle) {
-		res = ext4_xattr_set_handle(handle, inode,
-					    EXT4_XATTR_INDEX_ENCRYPTION,
-					    EXT4_XATTR_NAME_ENCRYPTION_CONTEXT,
-					    ctx, len, 0);
-		if (!res) {
-			ext4_set_inode_flag(inode, EXT4_INODE_ENCRYPT);
-			ext4_clear_inode_state(inode,
-					EXT4_STATE_MAY_INLINE_DATA);
-			/*
-			 * Update inode->i_flags - S_ENCRYPTED will be enabled,
-			 * S_DAX may be disabled
-			 */
-			ext4_set_inode_flags(inode, false);
-		}
-		return res;
-	}
-
-	res = dquot_initialize(inode);
-	if (res)
-		return res;
-retry:
-	res = ext4_xattr_set_credits(inode, len, false /* is_create */,
-				     &credits);
-	if (res)
-		return res;
-
-	handle = ext4_journal_start(inode, EXT4_HT_MISC, credits);
-	if (IS_ERR(handle))
-		return PTR_ERR(handle);
-
-	res = ext4_xattr_set_handle(handle, inode, EXT4_XATTR_INDEX_ENCRYPTION,
-				    EXT4_XATTR_NAME_ENCRYPTION_CONTEXT,
-				    ctx, len, 0);
-	if (!res) {
-		ext4_set_inode_flag(inode, EXT4_INODE_ENCRYPT);
-		/*
-		 * Update inode->i_flags - S_ENCRYPTED will be enabled,
-		 * S_DAX may be disabled
-		 */
-		ext4_set_inode_flags(inode, false);
-		res = ext4_mark_inode_dirty(handle, inode);
-		if (res)
-			EXT4_ERROR_INODE(inode, "Failed to mark inode dirty");
-	}
-	res2 = ext4_journal_stop(handle);
-
-	if (res == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
-		goto retry;
-	if (!res)
-		res = res2;
-	return res;
-}
-
-static const union fscrypt_policy *ext4_get_dummy_policy(struct super_block *sb)
-{
-	return EXT4_SB(sb)->s_dummy_enc_policy.policy;
-}
-
-static bool ext4_has_stable_inodes(struct super_block *sb)
-{
-	return ext4_has_feature_stable_inodes(sb);
-}
-
-static void ext4_get_ino_and_lblk_bits(struct super_block *sb,
-				       int *ino_bits_ret, int *lblk_bits_ret)
-{
-	*ino_bits_ret = 8 * sizeof(EXT4_SB(sb)->s_es->s_inodes_count);
-	*lblk_bits_ret = 8 * sizeof(ext4_lblk_t);
-}
-
-static const struct fscrypt_operations ext4_cryptops = {
-	.key_prefix		= "ext4:",
-	.get_context		= ext4_get_context,
-	.set_context		= ext4_set_context,
-	.get_dummy_policy	= ext4_get_dummy_policy,
-	.empty_dir		= ext4_empty_dir,
-	.has_stable_inodes	= ext4_has_stable_inodes,
-	.get_ino_and_lblk_bits	= ext4_get_ino_and_lblk_bits,
-};
-#endif
-
 #ifdef CONFIG_QUOTA
 static const char * const quotatypes[] = INITQFNAMES;
 #define QTYPE2NAME(t) (quotatypes[t])
@@ -1867,7 +1748,6 @@ static const struct fs_parameter_spec ext4_param_specs[] = {
 };
 
 #define DEFAULT_JOURNAL_IOPRIO (IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, 3))
-#define DEFAULT_MB_OPTIMIZE_SCAN	(-1)
 
 static const char deprecated_msg[] =
 	"Mount option \"%s\" will be removed by %s\n"
@@ -1913,6 +1793,7 @@ static const struct mount_opts {
 	 MOPT_EXT4_ONLY | MOPT_CLEAR},
 	{Opt_warn_on_error, EXT4_MOUNT_WARN_ON_ERROR, MOPT_SET},
 	{Opt_nowarn_on_error, EXT4_MOUNT_WARN_ON_ERROR, MOPT_CLEAR},
+	{Opt_commit, 0, MOPT_NO_EXT2},
 	{Opt_nojournal_checksum, EXT4_MOUNT_JOURNAL_CHECKSUM,
 	 MOPT_EXT4_ONLY | MOPT_CLEAR},
 	{Opt_journal_checksum, EXT4_MOUNT_JOURNAL_CHECKSUM,
@@ -2427,11 +2308,12 @@ static int ext4_parse_param(struct fs_context *fc, struct fs_parameter *param)
 		ctx->spec |= EXT4_SPEC_DUMMY_ENCRYPTION;
 		ctx->test_dummy_enc_arg = kmemdup_nul(param->string, param->size,
 						      GFP_KERNEL);
+		return 0;
 #else
 		ext4_msg(NULL, KERN_WARNING,
-			 "Test dummy encryption mount option ignored");
+			 "test_dummy_encryption option not supported");
+		return -EINVAL;
 #endif
-		return 0;
 	case Opt_dax:
 	case Opt_dax_type:
 #ifdef CONFIG_FS_DAX
@@ -2625,8 +2507,10 @@ parse_failed:
 	ret = ext4_apply_options(fc, sb);
 
 out_free:
-	kfree(s_ctx);
+	if (fc) {
-	kfree(fc);
+		ext4_fc_free(fc);
+		kfree(fc);
+	}
 	kfree(s_mount_opts);
 	return ret;
 }
@@ -2786,12 +2670,44 @@ err_jquota_specified:
 #endif
 }
 
+static int ext4_check_test_dummy_encryption(const struct fs_context *fc,
+					    struct super_block *sb)
+{
+#ifdef CONFIG_FS_ENCRYPTION
+	const struct ext4_fs_context *ctx = fc->fs_private;
+	const struct ext4_sb_info *sbi = EXT4_SB(sb);
+
+	if (!(ctx->spec & EXT4_SPEC_DUMMY_ENCRYPTION))
+		return 0;
+
+	if (!ext4_has_feature_encrypt(sb)) {
+		ext4_msg(NULL, KERN_WARNING,
+			 "test_dummy_encryption requires encrypt feature");
+		return -EINVAL;
+	}
+	/*
+	 * This mount option is just for testing, and it's not worthwhile to
+	 * implement the extra complexity (e.g. RCU protection) that would be
+	 * needed to allow it to be set or changed during remount.  We do allow
+	 * it to be specified during remount, but only if there is no change.
+	 */
+	if (fc->purpose == FS_CONTEXT_FOR_RECONFIGURE &&
+	    !sbi->s_dummy_enc_policy.policy) {
+		ext4_msg(NULL, KERN_WARNING,
+			 "Can't set test_dummy_encryption on remount");
+		return -EINVAL;
+	}
+#endif /* CONFIG_FS_ENCRYPTION */
+	return 0;
+}
+
 static int ext4_check_opt_consistency(struct fs_context *fc,
 				      struct super_block *sb)
 {
 	struct ext4_fs_context *ctx = fc->fs_private;
 	struct ext4_sb_info *sbi = fc->s_fs_info;
 	int is_remount = fc->purpose == FS_CONTEXT_FOR_RECONFIGURE;
+	int err;
 
 	if ((ctx->opt_flags & MOPT_NO_EXT2) && IS_EXT2_SB(sb)) {
 		ext4_msg(NULL, KERN_ERR,
@@ -2821,20 +2737,9 @@ static int ext4_check_opt_consistency(struct fs_context *fc,
 				 "for blocksize < PAGE_SIZE");
 	}
 
-#ifdef CONFIG_FS_ENCRYPTION
+	err = ext4_check_test_dummy_encryption(fc, sb);
-	/*
+	if (err)
-	 * This mount option is just for testing, and it's not worthwhile to
+		return err;
-	 * implement the extra complexity (e.g. RCU protection) that would be
-	 * needed to allow it to be set or changed during remount.  We do allow
-	 * it to be specified during remount, but only if there is no change.
-	 */
-	if ((ctx->spec & EXT4_SPEC_DUMMY_ENCRYPTION) &&
-	    is_remount && !sbi->s_dummy_enc_policy.policy) {
-		ext4_msg(NULL, KERN_WARNING,
-			 "Can't set test_dummy_encryption on remount");
-		return -1;
-	}
-#endif
 
 	if ((ctx->spec & EXT4_SPEC_DATAJ) && is_remount) {
 		if (!sbi->s_journal) {
@@ -3837,7 +3742,7 @@ static struct task_struct *ext4_lazyinit_task;
  */
 static int ext4_lazyinit_thread(void *arg)
 {
-	struct ext4_lazy_init *eli = (struct ext4_lazy_init *)arg;
+	struct ext4_lazy_init *eli = arg;
 	struct list_head *pos, *n;
 	struct ext4_li_request *elr;
 	unsigned long next_wakeup, cur;
@@ -4409,7 +4314,8 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb)
 	int silent = fc->sb_flags & SB_SILENT;
 
 	/* Set defaults for the variables that will be set during parsing */
-	ctx->journal_ioprio = DEFAULT_JOURNAL_IOPRIO;
+	if (!(ctx->spec & EXT4_SPEC_JOURNAL_IOPRIO))
+		ctx->journal_ioprio = DEFAULT_JOURNAL_IOPRIO;
 
 	sbi->s_inode_readahead_blks = EXT4_DEF_INODE_READAHEAD_BLKS;
 	sbi->s_sectors_written_start =
@@ -4886,7 +4792,7 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb)
 					sbi->s_inodes_per_block;
 	sbi->s_desc_per_block = blocksize / EXT4_DESC_SIZE(sb);
 	sbi->s_sbh = bh;
-	sbi->s_mount_state = le16_to_cpu(es->s_state);
+	sbi->s_mount_state = le16_to_cpu(es->s_state) & ~EXT4_FC_REPLAY;
 	sbi->s_addr_per_block_bits = ilog2(EXT4_ADDR_PER_BLOCK(sb));
 	sbi->s_desc_per_block_bits = ilog2(EXT4_DESC_PER_BLOCK(sb));
 
@@ -5279,12 +5185,6 @@ no_journal:
 		goto failed_mount_wq;
 	}
 
-	if (DUMMY_ENCRYPTION_ENABLED(sbi) && !sb_rdonly(sb) &&
-	    !ext4_has_feature_encrypt(sb)) {
-		ext4_set_feature_encrypt(sb);
-		ext4_commit_super(sb);
-	}
-
 	/*
 	 * Get the # of file system overhead blocks from the
 	 * superblock if present.
@@ -6272,7 +6172,6 @@ static int __ext4_remount(struct fs_context *fc, struct super_block *sb)
 	char *to_free[EXT4_MAXQUOTAS];
 #endif
 
-	ctx->journal_ioprio = DEFAULT_JOURNAL_IOPRIO;
 
 	/* Store the original options */
 	old_sb_flags = sb->s_flags;
@@ -6298,9 +6197,14 @@ static int __ext4_remount(struct fs_context *fc, struct super_block *sb)
 		} else
 			old_opts.s_qf_names[i] = NULL;
 #endif
-	if (sbi->s_journal && sbi->s_journal->j_task->io_context)
+	if (!(ctx->spec & EXT4_SPEC_JOURNAL_IOPRIO)) {
-		ctx->journal_ioprio =
+		if (sbi->s_journal && sbi->s_journal->j_task->io_context)
-			sbi->s_journal->j_task->io_context->ioprio;
+			ctx->journal_ioprio =
+				sbi->s_journal->j_task->io_context->ioprio;
+		else
+			ctx->journal_ioprio = DEFAULT_JOURNAL_IOPRIO;
+
+	}
 
 	ext4_apply_options(fc, sb);
 
@@ -6441,7 +6345,8 @@ static int __ext4_remount(struct fs_context *fc, struct super_block *sb)
 				if (err)
 					goto restore_opts;
 			}
-			sbi->s_mount_state = le16_to_cpu(es->s_state);
+			sbi->s_mount_state = (le16_to_cpu(es->s_state) &
+					      ~EXT4_FC_REPLAY);
 
 			err = ext4_setup_super(sb, es, 0);
 			if (err)

fs/ext4/symlink.c

@@ -27,7 +27,7 @@ static const char *ext4_encrypted_get_link(struct dentry *dentry,
 					   struct inode *inode,
 					   struct delayed_call *done)
 {
-	struct page *cpage = NULL;
+	struct buffer_head *bh = NULL;
 	const void *caddr;
 	unsigned int max_size;
 	const char *paddr;
@@ -39,16 +39,19 @@ static const char *ext4_encrypted_get_link(struct dentry *dentry,
 		caddr = EXT4_I(inode)->i_data;
 		max_size = sizeof(EXT4_I(inode)->i_data);
 	} else {
-		cpage = read_mapping_page(inode->i_mapping, 0, NULL);
+		bh = ext4_bread(NULL, inode, 0, 0);
-		if (IS_ERR(cpage))
+		if (IS_ERR(bh))
-			return ERR_CAST(cpage);
+			return ERR_CAST(bh);
-		caddr = page_address(cpage);
+		if (!bh) {
+			EXT4_ERROR_INODE(inode, "bad symlink.");
+			return ERR_PTR(-EFSCORRUPTED);
+		}
+		caddr = bh->b_data;
 		max_size = inode->i_sb->s_blocksize;
 	}
 
 	paddr = fscrypt_get_symlink(inode, caddr, max_size, done);
-	if (cpage)
+	brelse(bh);
-		put_page(cpage);
 	return paddr;
 }
 
@@ -62,6 +65,38 @@ static int ext4_encrypted_symlink_getattr(struct user_namespace *mnt_userns,
 	return fscrypt_symlink_getattr(path, stat);
 }
 
+static void ext4_free_link(void *bh)
+{
+	brelse(bh);
+}
+
+static const char *ext4_get_link(struct dentry *dentry, struct inode *inode,
+				 struct delayed_call *callback)
+{
+	struct buffer_head *bh;
+
+	if (!dentry) {
+		bh = ext4_getblk(NULL, inode, 0, EXT4_GET_BLOCKS_CACHED_NOWAIT);
+		if (IS_ERR(bh))
+			return ERR_CAST(bh);
+		if (!bh || !ext4_buffer_uptodate(bh))
+			return ERR_PTR(-ECHILD);
+	} else {
+		bh = ext4_bread(NULL, inode, 0, 0);
+		if (IS_ERR(bh))
+			return ERR_CAST(bh);
+		if (!bh) {
+			EXT4_ERROR_INODE(inode, "bad symlink.");
+			return ERR_PTR(-EFSCORRUPTED);
+		}
+	}
+
+	set_delayed_call(callback, ext4_free_link, bh);
+	nd_terminate_link(bh->b_data, inode->i_size,
+			  inode->i_sb->s_blocksize - 1);
+	return bh->b_data;
+}
+
 const struct inode_operations ext4_encrypted_symlink_inode_operations = {
 	.get_link	= ext4_encrypted_get_link,
 	.setattr	= ext4_setattr,
@@ -70,7 +105,7 @@ const struct inode_operations ext4_encrypted_symlink_inode_operations = {
 };
 
 const struct inode_operations ext4_symlink_inode_operations = {
-	.get_link	= page_get_link,
+	.get_link	= ext4_get_link,
 	.setattr	= ext4_setattr,
 	.getattr	= ext4_getattr,
 	.listxattr	= ext4_listxattr,