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 request includes the dax-4.0-iomap-pmd branch which is
  needed for both ext4 and xfs dax changes to use iomap for DAX. It also
  includes the fscrypt branch which is needed for ubifs encryption work
  as well as ext4 encryption and fscrypt cleanups.

  Lots of cleanups and bug fixes, especially making sure ext4 is robust
  against maliciously corrupted file systems --- especially maliciously
  corrupted xattr blocks and a maliciously corrupted superblock. Also
  fix ext4 support for 64k block sizes so it works well on ppcle. Fixed
  mbcache so we don't miss some common xattr blocks that can be merged"

* tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (86 commits)
  dax: Fix sleep in atomic contex in grab_mapping_entry()
  fscrypt: Rename FS_WRITE_PATH_FL to FS_CTX_HAS_BOUNCE_BUFFER_FL
  fscrypt: Delay bounce page pool allocation until needed
  fscrypt: Cleanup page locking requirements for fscrypt_{decrypt,encrypt}_page()
  fscrypt: Cleanup fscrypt_{decrypt,encrypt}_page()
  fscrypt: Never allocate fscrypt_ctx on in-place encryption
  fscrypt: Use correct index in decrypt path.
  fscrypt: move the policy flags and encryption mode definitions to uapi header
  fscrypt: move non-public structures and constants to fscrypt_private.h
  fscrypt: unexport fscrypt_initialize()
  fscrypt: rename get_crypt_info() to fscrypt_get_crypt_info()
  fscrypto: move ioctl processing more fully into common code
  fscrypto: remove unneeded Kconfig dependencies
  MAINTAINERS: fscrypto: recommend linux-fsdevel for fscrypto patches
  ext4: do not perform data journaling when data is encrypted
  ext4: return -ENOMEM instead of success
  ext4: reject inodes with negative size
  ext4: remove another test in ext4_alloc_file_blocks()
  Documentation: fix description of ext4's block_validity mount option
  ext4: fix checks for data=ordered and journal_async_commit options
  ...

1 files changed, 103 insertions, 49 deletions

diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index caa4147cda47..dfc8309d7755 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -863,7 +863,6 @@ static void ext4_put_super(struct super_block *sb)
 	percpu_counter_destroy(&sbi->s_dirs_counter);
 	percpu_counter_destroy(&sbi->s_dirtyclusters_counter);
 	percpu_free_rwsem(&sbi->s_journal_flag_rwsem);
-	brelse(sbi->s_sbh);
 #ifdef CONFIG_QUOTA
 	for (i = 0; i < EXT4_MAXQUOTAS; i++)
 		kfree(sbi->s_qf_names[i]);
@@ -895,6 +894,7 @@ static void ext4_put_super(struct super_block *sb)
 	}
 	if (sbi->s_mmp_tsk)
 		kthread_stop(sbi->s_mmp_tsk);
+	brelse(sbi->s_sbh);
 	sb->s_fs_info = NULL;
 	/*
 	 * Now that we are completely done shutting down the
@@ -1114,37 +1114,55 @@ static int ext4_prepare_context(struct inode *inode)
 static int ext4_set_context(struct inode *inode, const void *ctx, size_t len,
 							void *fs_data)
 {
-	handle_t *handle;
-	int res, res2;
+	handle_t *handle = fs_data;
+	int res, res2, retries = 0;
+
+	/*
+	 * 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.
+	 */
 
-	/* fs_data is null when internally used. */
-	if (fs_data) {
-		res  = ext4_xattr_set(inode, EXT4_XATTR_INDEX_ENCRYPTION,
-				EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, ctx,
-				len, 0);
+	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 - e.g. S_DAX may get disabled
+			 */
+			ext4_set_inode_flags(inode);
 		}
 		return res;
 	}
 
+retry:
 	handle = ext4_journal_start(inode, EXT4_HT_MISC,
 			ext4_jbd2_credits_xattr(inode));
 	if (IS_ERR(handle))
 		return PTR_ERR(handle);
 
-	res = ext4_xattr_set(inode, EXT4_XATTR_INDEX_ENCRYPTION,
-			EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, ctx,
-			len, 0);
+	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 - e.g. S_DAX may get disabled */
+		ext4_set_inode_flags(inode);
 		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;
@@ -1883,12 +1901,6 @@ static int parse_options(char *options, struct super_block *sb,
 			return 0;
 		}
 	}
-	if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA &&
-	    test_opt(sb, JOURNAL_ASYNC_COMMIT)) {
-		ext4_msg(sb, KERN_ERR, "can't mount with journal_async_commit "
-			 "in data=ordered mode");
-		return 0;
-	}
 	return 1;
 }
 
@@ -2330,7 +2342,7 @@ static void ext4_orphan_cleanup(struct super_block *sb,
 				struct ext4_super_block *es)
 {
 	unsigned int s_flags = sb->s_flags;
-	int nr_orphans = 0, nr_truncates = 0;
+	int ret, nr_orphans = 0, nr_truncates = 0;
 #ifdef CONFIG_QUOTA
 	int i;
 #endif
@@ -2412,7 +2424,9 @@ static void ext4_orphan_cleanup(struct super_block *sb,
 				  inode->i_ino, inode->i_size);
 			inode_lock(inode);
 			truncate_inode_pages(inode->i_mapping, inode->i_size);
-			ext4_truncate(inode);
+			ret = ext4_truncate(inode);
+			if (ret)
+				ext4_std_error(inode->i_sb, ret);
 			inode_unlock(inode);
 			nr_truncates++;
 		} else {
@@ -3193,10 +3207,15 @@ static int count_overhead(struct super_block *sb, ext4_group_t grp,
 			ext4_set_bit(s++, buf);
 			count++;
 		}
-		for (j = ext4_bg_num_gdb(sb, grp); j > 0; j--) {
-			ext4_set_bit(EXT4_B2C(sbi, s++), buf);
-			count++;
+		j = ext4_bg_num_gdb(sb, grp);
+		if (s + j > EXT4_BLOCKS_PER_GROUP(sb)) {
+			ext4_error(sb, "Invalid number of block group "
+				   "descriptor blocks: %d", j);
+			j = EXT4_BLOCKS_PER_GROUP(sb) - s;
 		}
+		count += j;
+		for (; j > 0; j--)
+			ext4_set_bit(EXT4_B2C(sbi, s++), buf);
 	}
 	if (!count)
 		return 0;
@@ -3301,7 +3320,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	char *orig_data = kstrdup(data, GFP_KERNEL);
 	struct buffer_head *bh;
 	struct ext4_super_block *es = NULL;
-	struct ext4_sb_info *sbi;
+	struct ext4_sb_info *sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
 	ext4_fsblk_t block;
 	ext4_fsblk_t sb_block = get_sb_block(&data);
 	ext4_fsblk_t logical_sb_block;
@@ -3320,16 +3339,14 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	unsigned int journal_ioprio = DEFAULT_JOURNAL_IOPRIO;
 	ext4_group_t first_not_zeroed;
 
-	sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
-	if (!sbi)
-		goto out_free_orig;
+	if ((data && !orig_data) || !sbi)
+		goto out_free_base;
 
 	sbi->s_blockgroup_lock =
 		kzalloc(sizeof(struct blockgroup_lock), GFP_KERNEL);
-	if (!sbi->s_blockgroup_lock) {
-		kfree(sbi);
-		goto out_free_orig;
-	}
+	if (!sbi->s_blockgroup_lock)
+		goto out_free_base;
+
 	sb->s_fs_info = sbi;
 	sbi->s_sb = sb;
 	sbi->s_inode_readahead_blks = EXT4_DEF_INODE_READAHEAD_BLKS;
@@ -3475,11 +3492,19 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	 */
 	sbi->s_li_wait_mult = EXT4_DEF_LI_WAIT_MULT;
 
-	if (!parse_options((char *) sbi->s_es->s_mount_opts, sb,
-			   &journal_devnum, &journal_ioprio, 0)) {
-		ext4_msg(sb, KERN_WARNING,
-			 "failed to parse options in superblock: %s",
-			 sbi->s_es->s_mount_opts);
+	if (sbi->s_es->s_mount_opts[0]) {
+		char *s_mount_opts = kstrndup(sbi->s_es->s_mount_opts,
+					      sizeof(sbi->s_es->s_mount_opts),
+					      GFP_KERNEL);
+		if (!s_mount_opts)
+			goto failed_mount;
+		if (!parse_options(s_mount_opts, sb, &journal_devnum,
+				   &journal_ioprio, 0)) {
+			ext4_msg(sb, KERN_WARNING,
+				 "failed to parse options in superblock: %s",
+				 s_mount_opts);
+		}
+		kfree(s_mount_opts);
 	}
 	sbi->s_def_mount_opt = sbi->s_mount_opt;
 	if (!parse_options((char *) data, sb, &journal_devnum,
@@ -3505,6 +3530,11 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 				 "both data=journal and dax");
 			goto failed_mount;
 		}
+		if (ext4_has_feature_encrypt(sb)) {
+			ext4_msg(sb, KERN_WARNING,
+				 "encrypted files will use data=ordered "
+				 "instead of data journaling mode");
+		}
 		if (test_opt(sb, DELALLOC))
 			clear_opt(sb, DELALLOC);
 	} else {
@@ -3660,12 +3690,16 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 
 	sbi->s_blocks_per_group = le32_to_cpu(es->s_blocks_per_group);
 	sbi->s_inodes_per_group = le32_to_cpu(es->s_inodes_per_group);
-	if (EXT4_INODE_SIZE(sb) == 0 || EXT4_INODES_PER_GROUP(sb) == 0)
-		goto cantfind_ext4;
 
 	sbi->s_inodes_per_block = blocksize / EXT4_INODE_SIZE(sb);
 	if (sbi->s_inodes_per_block == 0)
 		goto cantfind_ext4;
+	if (sbi->s_inodes_per_group < sbi->s_inodes_per_block ||
+	    sbi->s_inodes_per_group > blocksize * 8) {
+		ext4_msg(sb, KERN_ERR, "invalid inodes per group: %lu\n",
+			 sbi->s_blocks_per_group);
+		goto failed_mount;
+	}
 	sbi->s_itb_per_group = sbi->s_inodes_per_group /
 					sbi->s_inodes_per_block;
 	sbi->s_desc_per_block = blocksize / EXT4_DESC_SIZE(sb);
@@ -3748,13 +3782,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	}
 	sbi->s_cluster_ratio = clustersize / blocksize;
 
-	if (sbi->s_inodes_per_group > blocksize * 8) {
-		ext4_msg(sb, KERN_ERR,
-		       "#inodes per group too big: %lu",
-		       sbi->s_inodes_per_group);
-		goto failed_mount;
-	}
-
 	/* Do we have standard group size of clustersize * 8 blocks ? */
 	if (sbi->s_blocks_per_group == clustersize << 3)
 		set_opt2(sb, STD_GROUP_SIZE);
@@ -3814,6 +3841,15 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 			(EXT4_MAX_BLOCK_FILE_PHYS / EXT4_BLOCKS_PER_GROUP(sb)));
 	db_count = (sbi->s_groups_count + EXT4_DESC_PER_BLOCK(sb) - 1) /
 		   EXT4_DESC_PER_BLOCK(sb);
+	if (ext4_has_feature_meta_bg(sb)) {
+		if (le32_to_cpu(es->s_first_meta_bg) >= db_count) {
+			ext4_msg(sb, KERN_WARNING,
+				 "first meta block group too large: %u "
+				 "(group descriptor block count %u)",
+				 le32_to_cpu(es->s_first_meta_bg), db_count);
+			goto failed_mount;
+		}
+	}
 	sbi->s_group_desc = ext4_kvmalloc(db_count *
 					  sizeof(struct buffer_head *),
 					  GFP_KERNEL);
@@ -3967,6 +4003,14 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	default:
 		break;
 	}
+
+	if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA &&
+	    test_opt(sb, JOURNAL_ASYNC_COMMIT)) {
+		ext4_msg(sb, KERN_ERR, "can't mount with "
+			"journal_async_commit in data=ordered mode");
+		goto failed_mount_wq;
+	}
+
 	set_task_ioprio(sbi->s_journal->j_task, journal_ioprio);
 
 	sbi->s_journal->j_commit_callback = ext4_journal_commit_callback;
@@ -4160,7 +4204,9 @@ no_journal:
 
 	if (___ratelimit(&ext4_mount_msg_ratelimit, "EXT4-fs mount"))
 		ext4_msg(sb, KERN_INFO, "mounted filesystem with%s. "
-			 "Opts: %s%s%s", descr, sbi->s_es->s_mount_opts,
+			 "Opts: %.*s%s%s", descr,
+			 (int) sizeof(sbi->s_es->s_mount_opts),
+			 sbi->s_es->s_mount_opts,
 			 *sbi->s_es->s_mount_opts ? "; " : "", orig_data);
 
 	if (es->s_error_count)
@@ -4239,8 +4285,8 @@ failed_mount:
 out_fail:
 	sb->s_fs_info = NULL;
 	kfree(sbi->s_blockgroup_lock);
+out_free_base:
 	kfree(sbi);
-out_free_orig:
 	kfree(orig_data);
 	return err ? err : ret;
 }
@@ -4550,7 +4596,8 @@ static int ext4_commit_super(struct super_block *sb, int sync)
 				&EXT4_SB(sb)->s_freeinodes_counter));
 	BUFFER_TRACE(sbh, "marking dirty");
 	ext4_superblock_csum_set(sb);
-	lock_buffer(sbh);
+	if (sync)
+		lock_buffer(sbh);
 	if (buffer_write_io_error(sbh)) {
 		/*
 		 * Oh, dear.  A previous attempt to write the
@@ -4566,8 +4613,8 @@ static int ext4_commit_super(struct super_block *sb, int sync)
 		set_buffer_uptodate(sbh);
 	}
 	mark_buffer_dirty(sbh);
-	unlock_buffer(sbh);
 	if (sync) {
+		unlock_buffer(sbh);
 		error = __sync_dirty_buffer(sbh,
 			test_opt(sb, BARRIER) ? REQ_FUA : REQ_SYNC);
 		if (error)
@@ -4857,6 +4904,13 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 			err = -EINVAL;
 			goto restore_opts;
 		}
+	} else if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA) {
+		if (test_opt(sb, JOURNAL_ASYNC_COMMIT)) {
+			ext4_msg(sb, KERN_ERR, "can't mount with "
+				"journal_async_commit in data=ordered mode");
+			err = -EINVAL;
+			goto restore_opts;
+		}
 	}
 
 	if ((sbi->s_mount_opt ^ old_opts.s_mount_opt) & EXT4_MOUNT_DAX) {
@@ -5366,7 +5420,7 @@ static int ext4_quota_off(struct super_block *sb, int type)
 	handle = ext4_journal_start(inode, EXT4_HT_QUOTA, 1);
 	if (IS_ERR(handle))
 		goto out;
-	inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+	inode->i_mtime = inode->i_ctime = current_time(inode);
 	ext4_mark_inode_dirty(handle, inode);
 	ext4_journal_stop(handle);