Merge tag 'ext4_for_linus_stable' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4

Pull ext4 fixes from Ted Ts'o:
 "Miscellaneous ext4 bug fixes for 5.1"

* tag 'ext4_for_linus_stable' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4:
  ext4: prohibit fstrim in norecovery mode
  ext4: cleanup bh release code in ext4_ind_remove_space()
  ext4: brelse all indirect buffer in ext4_ind_remove_space()
  ext4: report real fs size after failed resize
  ext4: add missing brelse() in add_new_gdb_meta_bg()
  ext4: remove useless ext4_pin_inode()
  ext4: avoid panic during forced reboot
  ext4: fix data corruption caused by unaligned direct AIO
  ext4: fix NULL pointer dereference while journal is aborted

Author: torvalds

fs/ext4/ext4_jbd2.h

@@ -384,7 +384,7 @@ static inline void ext4_update_inode_fsync_trans(handle_t *handle,
 {
 	struct ext4_inode_info *ei = EXT4_I(inode);
 
-	if (ext4_handle_valid(handle)) {
+	if (ext4_handle_valid(handle) && !is_handle_aborted(handle)) {
 		ei->i_sync_tid = handle->h_transaction->t_tid;
 		if (datasync)
 			ei->i_datasync_tid = handle->h_transaction->t_tid;

fs/ext4/file.c

@@ -125,7 +125,7 @@ ext4_unaligned_aio(struct inode *inode, struct iov_iter *from, loff_t pos)
 	struct super_block *sb = inode->i_sb;
 	int blockmask = sb->s_blocksize - 1;
 
-	if (pos >= i_size_read(inode))
+	if (pos >= ALIGN(i_size_read(inode), sb->s_blocksize))
 		return 0;
 
 	if ((pos | iov_iter_alignment(from)) & blockmask)

fs/ext4/indirect.c

@@ -1222,6 +1222,7 @@ int ext4_ind_remove_space(handle_t *handle, struct inode *inode,
 	ext4_lblk_t offsets[4], offsets2[4];
 	Indirect chain[4], chain2[4];
 	Indirect *partial, *partial2;
+	Indirect *p = NULL, *p2 = NULL;
 	ext4_lblk_t max_block;
 	__le32 nr = 0, nr2 = 0;
 	int n = 0, n2 = 0;
@@ -1263,7 +1264,7 @@ int ext4_ind_remove_space(handle_t *handle, struct inode *inode,
 		}
 
 
-		partial = ext4_find_shared(inode, n, offsets, chain, &nr);
+		partial = p = ext4_find_shared(inode, n, offsets, chain, &nr);
 		if (nr) {
 			if (partial == chain) {
 				/* Shared branch grows from the inode */
@@ -1288,13 +1289,11 @@ int ext4_ind_remove_space(handle_t *handle, struct inode *inode,
 				partial->p + 1,
 				(__le32 *)partial->bh->b_data+addr_per_block,
 				(chain+n-1) - partial);
-			BUFFER_TRACE(partial->bh, "call brelse");
-			brelse(partial->bh);
 			partial--;
 		}
 
 end_range:
-		partial2 = ext4_find_shared(inode, n2, offsets2, chain2, &nr2);
+		partial2 = p2 = ext4_find_shared(inode, n2, offsets2, chain2, &nr2);
 		if (nr2) {
 			if (partial2 == chain2) {
 				/*
@@ -1324,16 +1323,14 @@ int ext4_ind_remove_space(handle_t *handle, struct inode *inode,
 					   (__le32 *)partial2->bh->b_data,
 					   partial2->p,
 					   (chain2+n2-1) - partial2);
-			BUFFER_TRACE(partial2->bh, "call brelse");
-			brelse(partial2->bh);
 			partial2--;
 		}
 		goto do_indirects;
 	}
 
 	/* Punch happened within the same level (n == n2) */
-	partial = ext4_find_shared(inode, n, offsets, chain, &nr);
-	partial2 = ext4_find_shared(inode, n2, offsets2, chain2, &nr2);
+	partial = p = ext4_find_shared(inode, n, offsets, chain, &nr);
+	partial2 = p2 = ext4_find_shared(inode, n2, offsets2, chain2, &nr2);
 
 	/* Free top, but only if partial2 isn't its subtree. */
 	if (nr) {
@@ -1390,11 +1387,7 @@ int ext4_ind_remove_space(handle_t *handle, struct inode *inode,
 					   partial->p + 1,
 					   partial2->p,
 					   (chain+n-1) - partial);
-			BUFFER_TRACE(partial->bh, "call brelse");
-			brelse(partial->bh);
-			BUFFER_TRACE(partial2->bh, "call brelse");
-			brelse(partial2->bh);
-			return 0;
+			goto cleanup;
 		}
 
 		/*
@@ -1409,28 +1402,36 @@ int ext4_ind_remove_space(handle_t *handle, struct inode *inode,
 					   partial->p + 1,
 					   (__le32 *)partial->bh->b_data+addr_per_block,
 					   (chain+n-1) - partial);
-			BUFFER_TRACE(partial->bh, "call brelse");
-			brelse(partial->bh);
 			partial--;
 		}
 		if (partial2 > chain2 && depth2 <= depth) {
 			ext4_free_branches(handle, inode, partial2->bh,
 					   (__le32 *)partial2->bh->b_data,
 					   partial2->p,
 					   (chain2+n2-1) - partial2);
-			BUFFER_TRACE(partial2->bh, "call brelse");
-			brelse(partial2->bh);
 			partial2--;
 		}
 	}
+
+cleanup:
+	while (p && p > chain) {
+		BUFFER_TRACE(p->bh, "call brelse");
+		brelse(p->bh);
+		p--;
+	}
+	while (p2 && p2 > chain2) {
+		BUFFER_TRACE(p2->bh, "call brelse");
+		brelse(p2->bh);
+		p2--;
+	}
 	return 0;
 
 do_indirects:
 	/* Kill the remaining (whole) subtrees */
 	switch (offsets[0]) {
 	default:
 		if (++n >= n2)
-			return 0;
+			break;
 		nr = i_data[EXT4_IND_BLOCK];
 		if (nr) {
 			ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 1);
@@ -1439,7 +1440,7 @@ int ext4_ind_remove_space(handle_t *handle, struct inode *inode,
 		/* fall through */
 	case EXT4_IND_BLOCK:
 		if (++n >= n2)
-			return 0;
+			break;
 		nr = i_data[EXT4_DIND_BLOCK];
 		if (nr) {
 			ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 2);
@@ -1448,7 +1449,7 @@ int ext4_ind_remove_space(handle_t *handle, struct inode *inode,
 		/* fall through */
 	case EXT4_DIND_BLOCK:
 		if (++n >= n2)
-			return 0;
+			break;
 		nr = i_data[EXT4_TIND_BLOCK];
 		if (nr) {
 			ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 3);
@@ -1458,5 +1459,5 @@ int ext4_ind_remove_space(handle_t *handle, struct inode *inode,
 	case EXT4_TIND_BLOCK:
 		;
 	}
-	return 0;
+	goto cleanup;
 }

fs/ext4/inode.c

@@ -6080,36 +6080,6 @@ void ext4_dirty_inode(struct inode *inode, int flags)
 	return;
 }
 
-#if 0
-/*
- * Bind an inode's backing buffer_head into this transaction, to prevent
- * it from being flushed to disk early.  Unlike
- * ext4_reserve_inode_write, this leaves behind no bh reference and
- * returns no iloc structure, so the caller needs to repeat the iloc
- * lookup to mark the inode dirty later.
- */
-static int ext4_pin_inode(handle_t *handle, struct inode *inode)
-{
-	struct ext4_iloc iloc;
-
-	int err = 0;
-	if (handle) {
-		err = ext4_get_inode_loc(inode, &iloc);
-		if (!err) {
-			BUFFER_TRACE(iloc.bh, "get_write_access");
-			err = jbd2_journal_get_write_access(handle, iloc.bh);
-			if (!err)
-				err = ext4_handle_dirty_metadata(handle,
-								 NULL,
-								 iloc.bh);
-			brelse(iloc.bh);
-		}
-	}
-	ext4_std_error(inode->i_sb, err);
-	return err;
-}
-#endif
-
 int ext4_change_inode_journal_flag(struct inode *inode, int val)
 {
 	journal_t *journal;

fs/ext4/ioctl.c

@@ -1000,6 +1000,13 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 		if (!blk_queue_discard(q))
 			return -EOPNOTSUPP;
 
+		/*
+		 * We haven't replayed the journal, so we cannot use our
+		 * block-bitmap-guided storage zapping commands.
+		 */
+		if (test_opt(sb, NOLOAD) && ext4_has_feature_journal(sb))
+			return -EROFS;
+
 		if (copy_from_user(&range, (struct fstrim_range __user *)arg,
 		    sizeof(range)))
 			return -EFAULT;

fs/ext4/resize.c

@@ -932,11 +932,18 @@ static int add_new_gdb_meta_bg(struct super_block *sb,
 	memcpy(n_group_desc, o_group_desc,
 	       EXT4_SB(sb)->s_gdb_count * sizeof(struct buffer_head *));
 	n_group_desc[gdb_num] = gdb_bh;
+
+	BUFFER_TRACE(gdb_bh, "get_write_access");
+	err = ext4_journal_get_write_access(handle, gdb_bh);
+	if (err) {
+		kvfree(n_group_desc);
+		brelse(gdb_bh);
+		return err;
+	}
+
 	EXT4_SB(sb)->s_group_desc = n_group_desc;
 	EXT4_SB(sb)->s_gdb_count++;
 	kvfree(o_group_desc);
-	BUFFER_TRACE(gdb_bh, "get_write_access");
-	err = ext4_journal_get_write_access(handle, gdb_bh);
 	return err;
 }
 
@@ -2073,6 +2080,10 @@ int ext4_resize_fs(struct super_block *sb, ext4_fsblk_t n_blocks_count)
 		free_flex_gd(flex_gd);
 	if (resize_inode != NULL)
 		iput(resize_inode);
-	ext4_msg(sb, KERN_INFO, "resized filesystem to %llu", n_blocks_count);
+	if (err)
+		ext4_warning(sb, "error (%d) occurred during "
+			     "file system resize", err);
+	ext4_msg(sb, KERN_INFO, "resized filesystem to %llu",
+		 ext4_blocks_count(es));
 	return err;
 }

fs/ext4/super.c

@@ -430,6 +430,12 @@ static void ext4_journal_commit_callback(journal_t *journal, transaction_t *txn)
 	spin_unlock(&sbi->s_md_lock);
 }
 
+static bool system_going_down(void)
+{
+	return system_state == SYSTEM_HALT || system_state == SYSTEM_POWER_OFF
+		|| system_state == SYSTEM_RESTART;
+}
+
 /* Deal with the reporting of failure conditions on a filesystem such as
  * inconsistencies detected or read IO failures.
  *
@@ -460,16 +466,20 @@ static void ext4_handle_error(struct super_block *sb)
 		if (journal)
 			jbd2_journal_abort(journal, -EIO);
 	}
-	if (test_opt(sb, ERRORS_RO)) {
+	/*
+	 * We force ERRORS_RO behavior when system is rebooting. Otherwise we
+	 * could panic during 'reboot -f' as the underlying device got already
+	 * disabled.
+	 */
+	if (test_opt(sb, ERRORS_RO) || system_going_down()) {
 		ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only");
 		/*
 		 * Make sure updated value of ->s_mount_flags will be visible
 		 * before ->s_flags update
 		 */
 		smp_wmb();
 		sb->s_flags |= SB_RDONLY;
-	}
-	if (test_opt(sb, ERRORS_PANIC)) {
+	} else if (test_opt(sb, ERRORS_PANIC)) {
 		if (EXT4_SB(sb)->s_journal &&
 		  !(EXT4_SB(sb)->s_journal->j_flags & JBD2_REC_ERR))
 			return;