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

Pull ext4 updates from Ted Ts'o:
 "The first major feature for ext4 this merge window is the largedir
  feature, which allows ext4 directories to support over 2 billion
  directory entries (assuming ~64 byte file names; in practice, users
  will run into practical performance limits first.) This feature was
  originally written by the Lustre team, and credit goes to Artem
  Blagodarenko from Seagate for getting this feature upstream.

  The second major major feature allows ext4 to support extended
  attribute values up to 64k. This feature was also originally from
  Lustre, and has been enhanced by Tahsin Erdogan from Google with a
  deduplication feature so that if multiple files have the same xattr
  value (for example, Windows ACL's stored by Samba), only one copy will
  be stored on disk for encoding and caching efficiency.

  We also have the usual set of bug fixes, cleanups, and optimizations"

* tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (47 commits)
  ext4: fix spelling mistake: "prellocated" -> "preallocated"
  ext4: fix __ext4_new_inode() journal credits calculation
  ext4: skip ext4_init_security() and encryption on ea_inodes
  fs: generic_block_bmap(): initialize all of the fields in the temp bh
  ext4: change fast symlink test to not rely on i_blocks
  ext4: require key for truncate(2) of encrypted file
  ext4: don't bother checking for encryption key in ->mmap()
  ext4: check return value of kstrtoull correctly in reserved_clusters_store
  ext4: fix off-by-one fsmap error on 1k block filesystems
  ext4: return EFSBADCRC if a bad checksum error is found in ext4_find_entry()
  ext4: return EIO on read error in ext4_find_entry
  ext4: forbid encrypting root directory
  ext4: send parallel discards on commit completions
  ext4: avoid unnecessary stalls in ext4_evict_inode()
  ext4: add nombcache mount option
  ext4: strong binding of xattr inode references
  ext4: eliminate xattr entry e_hash recalculation for removes
  ext4: reserve space for xattr entries/names
  quota: add get_inode_usage callback to transfer multi-inode charges
  ext4: xattr inode deduplication
  ...

1 files changed, 83 insertions, 26 deletions

diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 18f68f09d393..0886fe82e9c4 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -373,6 +373,9 @@ static void ext4_journal_commit_callback(journal_t *journal, transaction_t *txn)
 	struct ext4_journal_cb_entry	*jce;
 
 	BUG_ON(txn->t_state == T_FINISHED);
+
+	ext4_process_freed_data(sb, txn->t_tid);
+
 	spin_lock(&sbi->s_md_lock);
 	while (!list_empty(&txn->t_private_list)) {
 		jce = list_entry(txn->t_private_list.next,
@@ -927,9 +930,13 @@ static void ext4_put_super(struct super_block *sb)
 		invalidate_bdev(sbi->journal_bdev);
 		ext4_blkdev_remove(sbi);
 	}
-	if (sbi->s_mb_cache) {
-		ext4_xattr_destroy_cache(sbi->s_mb_cache);
-		sbi->s_mb_cache = NULL;
+	if (sbi->s_ea_inode_cache) {
+		ext4_xattr_destroy_cache(sbi->s_ea_inode_cache);
+		sbi->s_ea_inode_cache = NULL;
+	}
+	if (sbi->s_ea_block_cache) {
+		ext4_xattr_destroy_cache(sbi->s_ea_block_cache);
+		sbi->s_ea_block_cache = NULL;
 	}
 	if (sbi->s_mmp_tsk)
 		kthread_stop(sbi->s_mmp_tsk);
@@ -1143,7 +1150,16 @@ 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, retries = 0;
+	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;
 
 	res = ext4_convert_inline_data(inode);
 	if (res)
@@ -1178,8 +1194,12 @@ static int ext4_set_context(struct inode *inode, const void *ctx, size_t len,
 	if (res)
 		return res;
 retry:
-	handle = ext4_journal_start(inode, EXT4_HT_MISC,
-			ext4_jbd2_credits_xattr(inode));
+	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);
 
@@ -1256,16 +1276,17 @@ static struct dquot **ext4_get_dquots(struct inode *inode)
 }
 
 static const struct dquot_operations ext4_quota_operations = {
-	.get_reserved_space = ext4_get_reserved_space,
-	.write_dquot	= ext4_write_dquot,
-	.acquire_dquot	= ext4_acquire_dquot,
-	.release_dquot	= ext4_release_dquot,
-	.mark_dirty	= ext4_mark_dquot_dirty,
-	.write_info	= ext4_write_info,
-	.alloc_dquot	= dquot_alloc,
-	.destroy_dquot	= dquot_destroy,
-	.get_projid	= ext4_get_projid,
-	.get_next_id	= ext4_get_next_id,
+	.get_reserved_space	= ext4_get_reserved_space,
+	.write_dquot		= ext4_write_dquot,
+	.acquire_dquot		= ext4_acquire_dquot,
+	.release_dquot		= ext4_release_dquot,
+	.mark_dirty		= ext4_mark_dquot_dirty,
+	.write_info		= ext4_write_info,
+	.alloc_dquot		= dquot_alloc,
+	.destroy_dquot		= dquot_destroy,
+	.get_projid		= ext4_get_projid,
+	.get_inode_usage	= ext4_get_inode_usage,
+	.get_next_id		= ext4_get_next_id,
 };
 
 static const struct quotactl_ops ext4_qctl_operations = {
@@ -1328,7 +1349,7 @@ enum {
 	Opt_inode_readahead_blks, Opt_journal_ioprio,
 	Opt_dioread_nolock, Opt_dioread_lock,
 	Opt_discard, Opt_nodiscard, Opt_init_itable, Opt_noinit_itable,
-	Opt_max_dir_size_kb, Opt_nojournal_checksum,
+	Opt_max_dir_size_kb, Opt_nojournal_checksum, Opt_nombcache,
 };
 
 static const match_table_t tokens = {
@@ -1411,6 +1432,8 @@ static const match_table_t tokens = {
 	{Opt_noinit_itable, "noinit_itable"},
 	{Opt_max_dir_size_kb, "max_dir_size_kb=%u"},
 	{Opt_test_dummy_encryption, "test_dummy_encryption"},
+	{Opt_nombcache, "nombcache"},
+	{Opt_nombcache, "no_mbcache"},	/* for backward compatibility */
 	{Opt_removed, "check=none"},	/* mount option from ext2/3 */
 	{Opt_removed, "nocheck"},	/* mount option from ext2/3 */
 	{Opt_removed, "reservation"},	/* mount option from ext2/3 */
@@ -1618,6 +1641,7 @@ static const struct mount_opts {
 	{Opt_jqfmt_vfsv1, QFMT_VFS_V1, MOPT_QFMT},
 	{Opt_max_dir_size_kb, 0, MOPT_GTE0},
 	{Opt_test_dummy_encryption, 0, MOPT_GTE0},
+	{Opt_nombcache, EXT4_MOUNT_NO_MBCACHE, MOPT_SET},
 	{Opt_err, 0, 0}
 };
 
@@ -3445,7 +3469,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	}
 
 	/* Load the checksum driver */
-	if (ext4_has_feature_metadata_csum(sb)) {
+	if (ext4_has_feature_metadata_csum(sb) ||
+	    ext4_has_feature_ea_inode(sb)) {
 		sbi->s_chksum_driver = crypto_alloc_shash("crc32c", 0, 0);
 		if (IS_ERR(sbi->s_chksum_driver)) {
 			ext4_msg(sb, KERN_ERR, "Cannot load crc32c driver.");
@@ -3467,7 +3492,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	/* Precompute checksum seed for all metadata */
 	if (ext4_has_feature_csum_seed(sb))
 		sbi->s_csum_seed = le32_to_cpu(es->s_checksum_seed);
-	else if (ext4_has_metadata_csum(sb))
+	else if (ext4_has_metadata_csum(sb) || ext4_has_feature_ea_inode(sb))
 		sbi->s_csum_seed = ext4_chksum(sbi, ~0, es->s_uuid,
 					       sizeof(es->s_uuid));
 
@@ -3597,6 +3622,16 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 				 "The Hurd can't support 64-bit file systems");
 			goto failed_mount;
 		}
+
+		/*
+		 * ea_inode feature uses l_i_version field which is not
+		 * available in HURD_COMPAT mode.
+		 */
+		if (ext4_has_feature_ea_inode(sb)) {
+			ext4_msg(sb, KERN_ERR,
+				 "ea_inode feature is not supported for Hurd");
+			goto failed_mount;
+		}
 	}
 
 	if (IS_EXT2_SB(sb)) {
@@ -4061,10 +4096,22 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	sbi->s_journal->j_commit_callback = ext4_journal_commit_callback;
 
 no_journal:
-	sbi->s_mb_cache = ext4_xattr_create_cache();
-	if (!sbi->s_mb_cache) {
-		ext4_msg(sb, KERN_ERR, "Failed to create an mb_cache");
-		goto failed_mount_wq;
+	if (!test_opt(sb, NO_MBCACHE)) {
+		sbi->s_ea_block_cache = ext4_xattr_create_cache();
+		if (!sbi->s_ea_block_cache) {
+			ext4_msg(sb, KERN_ERR,
+				 "Failed to create ea_block_cache");
+			goto failed_mount_wq;
+		}
+
+		if (ext4_has_feature_ea_inode(sb)) {
+			sbi->s_ea_inode_cache = ext4_xattr_create_cache();
+			if (!sbi->s_ea_inode_cache) {
+				ext4_msg(sb, KERN_ERR,
+					 "Failed to create ea_inode_cache");
+				goto failed_mount_wq;
+			}
+		}
 	}
 
 	if ((DUMMY_ENCRYPTION_ENABLED(sbi) || ext4_has_feature_encrypt(sb)) &&
@@ -4296,9 +4343,13 @@ failed_mount4:
 	if (EXT4_SB(sb)->rsv_conversion_wq)
 		destroy_workqueue(EXT4_SB(sb)->rsv_conversion_wq);
 failed_mount_wq:
-	if (sbi->s_mb_cache) {
-		ext4_xattr_destroy_cache(sbi->s_mb_cache);
-		sbi->s_mb_cache = NULL;
+	if (sbi->s_ea_inode_cache) {
+		ext4_xattr_destroy_cache(sbi->s_ea_inode_cache);
+		sbi->s_ea_inode_cache = NULL;
+	}
+	if (sbi->s_ea_block_cache) {
+		ext4_xattr_destroy_cache(sbi->s_ea_block_cache);
+		sbi->s_ea_block_cache = NULL;
 	}
 	if (sbi->s_journal) {
 		jbd2_journal_destroy(sbi->s_journal);
@@ -4957,6 +5008,12 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 		}
 	}
 
+	if ((sbi->s_mount_opt ^ old_opts.s_mount_opt) & EXT4_MOUNT_NO_MBCACHE) {
+		ext4_msg(sb, KERN_ERR, "can't enable nombcache during remount");
+		err = -EINVAL;
+		goto restore_opts;
+	}
+
 	if ((sbi->s_mount_opt ^ old_opts.s_mount_opt) & EXT4_MOUNT_DAX) {
 		ext4_msg(sb, KERN_WARNING, "warning: refusing change of "
 			"dax flag with busy inodes while remounting");