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
  ...

1 files changed, 61 insertions, 156 deletions

diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 6900da973ce2..450c918d68fc 100644
--- a/fs/ext4/super.c
+++ b/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);
-	kfree(fc);
+	if (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
-	/*
-	 * 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 ((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
+	err = ext4_check_test_dummy_encryption(fc, sb);
+	if (err)
+		return err;
 
 	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)
-		ctx->journal_ioprio =
-			sbi->s_journal->j_task->io_context->ioprio;
+	if (!(ctx->spec & EXT4_SPEC_JOURNAL_IOPRIO)) {
+		if (sbi->s_journal && sbi->s_journal->j_task->io_context)
+			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)