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:
 "Some ext4 bug fixes (mostly to address Syzbot reports)"

* tag 'ext4_for_linus_stable' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4:
  ext4: bail out of ext4_xattr_ibody_get() fails for any reason
  ext4: add bounds checking in get_max_inline_xattr_value_size()
  ext4: add indication of ro vs r/w mounts in the mount message
  ext4: fix deadlock when converting an inline directory in nojournal mode
  ext4: improve error recovery code paths in __ext4_remount()
  ext4: improve error handling from ext4_dirhash()
  ext4: don't clear SB_RDONLY when remounting r/w until quota is re-enabled
  ext4: check iomap type only if ext4_iomap_begin() does not fail
  ext4: avoid a potential slab-out-of-bounds in ext4_group_desc_csum
  ext4: fix data races when using cached status extents
  ext4: avoid deadlock in fs reclaim with page writeback
  ext4: fix invalid free tracking in ext4_xattr_move_to_block()
  ext4: remove a BUG_ON in ext4_mb_release_group_pa()
  ext4: allow ext4_get_group_info() to fail
  ext4: fix lockdep warning when enabling MMP
  ext4: fix WARNING in mb_find_extent

fs/ext4/balloc.c

@@ -305,6 +305,38 @@ struct ext4_group_desc * ext4_get_group_desc(struct super_block *sb,
 	return desc;
 }
 
+static ext4_fsblk_t ext4_valid_block_bitmap_padding(struct super_block *sb,
+						    ext4_group_t block_group,
+						    struct buffer_head *bh)
+{
+	ext4_grpblk_t next_zero_bit;
+	unsigned long bitmap_size = sb->s_blocksize * 8;
+	unsigned int offset = num_clusters_in_group(sb, block_group);
+
+	if (bitmap_size <= offset)
+		return 0;
+
+	next_zero_bit = ext4_find_next_zero_bit(bh->b_data, bitmap_size, offset);
+
+	return (next_zero_bit < bitmap_size ? next_zero_bit : 0);
+}
+
+struct ext4_group_info *ext4_get_group_info(struct super_block *sb,
+					    ext4_group_t group)
+{
+	 struct ext4_group_info **grp_info;
+	 long indexv, indexh;
+
+	 if (unlikely(group >= EXT4_SB(sb)->s_groups_count)) {
+		 ext4_error(sb, "invalid group %u", group);
+		 return NULL;
+	 }
+	 indexv = group >> (EXT4_DESC_PER_BLOCK_BITS(sb));
+	 indexh = group & ((EXT4_DESC_PER_BLOCK(sb)) - 1);
+	 grp_info = sbi_array_rcu_deref(EXT4_SB(sb), s_group_info, indexv);
+	 return grp_info[indexh];
+}
+
 /*
  * Return the block number which was discovered to be invalid, or 0 if
  * the block bitmap is valid.
@@ -379,7 +411,7 @@ static int ext4_validate_block_bitmap(struct super_block *sb,
 
 	if (buffer_verified(bh))
 		return 0;
-	if (EXT4_MB_GRP_BBITMAP_CORRUPT(grp))
+	if (!grp || EXT4_MB_GRP_BBITMAP_CORRUPT(grp))
 		return -EFSCORRUPTED;
 
 	ext4_lock_group(sb, block_group);
@@ -402,6 +434,15 @@ static int ext4_validate_block_bitmap(struct super_block *sb,
 					EXT4_GROUP_INFO_BBITMAP_CORRUPT);
 		return -EFSCORRUPTED;
 	}
+	blk = ext4_valid_block_bitmap_padding(sb, block_group, bh);
+	if (unlikely(blk != 0)) {
+		ext4_unlock_group(sb, block_group);
+		ext4_error(sb, "bg %u: block %llu: padding at end of block bitmap is not set",
+			   block_group, blk);
+		ext4_mark_group_bitmap_corrupted(sb, block_group,
+						 EXT4_GROUP_INFO_BBITMAP_CORRUPT);
+		return -EFSCORRUPTED;
+	}
 	set_buffer_verified(bh);
 verified:
 	ext4_unlock_group(sb, block_group);

fs/ext4/ext4.h

@@ -1684,6 +1684,30 @@ static inline struct ext4_inode_info *EXT4_I(struct inode *inode)
 	return container_of(inode, struct ext4_inode_info, vfs_inode);
 }
 
+static inline int ext4_writepages_down_read(struct super_block *sb)
+{
+	percpu_down_read(&EXT4_SB(sb)->s_writepages_rwsem);
+	return memalloc_nofs_save();
+}
+
+static inline void ext4_writepages_up_read(struct super_block *sb, int ctx)
+{
+	memalloc_nofs_restore(ctx);
+	percpu_up_read(&EXT4_SB(sb)->s_writepages_rwsem);
+}
+
+static inline int ext4_writepages_down_write(struct super_block *sb)
+{
+	percpu_down_write(&EXT4_SB(sb)->s_writepages_rwsem);
+	return memalloc_nofs_save();
+}
+
+static inline void ext4_writepages_up_write(struct super_block *sb, int ctx)
+{
+	memalloc_nofs_restore(ctx);
+	percpu_up_write(&EXT4_SB(sb)->s_writepages_rwsem);
+}
+
 static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino)
 {
 	return ino == EXT4_ROOT_INO ||
@@ -2625,6 +2649,8 @@ extern void ext4_check_blocks_bitmap(struct super_block *);
 extern struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb,
 						    ext4_group_t block_group,
 						    struct buffer_head ** bh);
+extern struct ext4_group_info *ext4_get_group_info(struct super_block *sb,
+						   ext4_group_t group);
 extern int ext4_should_retry_alloc(struct super_block *sb, int *retries);
 
 extern struct buffer_head *ext4_read_block_bitmap_nowait(struct super_block *sb,
@@ -3232,19 +3258,6 @@ static inline void ext4_isize_set(struct ext4_inode *raw_inode, loff_t i_size)
 	raw_inode->i_size_high = cpu_to_le32(i_size >> 32);
 }
 
-static inline
-struct ext4_group_info *ext4_get_group_info(struct super_block *sb,
-					    ext4_group_t group)
-{
-	 struct ext4_group_info **grp_info;
-	 long indexv, indexh;
-	 BUG_ON(group >= EXT4_SB(sb)->s_groups_count);
-	 indexv = group >> (EXT4_DESC_PER_BLOCK_BITS(sb));
-	 indexh = group & ((EXT4_DESC_PER_BLOCK(sb)) - 1);
-	 grp_info = sbi_array_rcu_deref(EXT4_SB(sb), s_group_info, indexv);
-	 return grp_info[indexh];
-}
-
 /*
  * Reading s_groups_count requires using smp_rmb() afterwards.  See
  * the locking protocol documented in the comments of ext4_group_add()

fs/ext4/extents_status.c

@@ -267,14 +267,12 @@ static void __es_find_extent_range(struct inode *inode,
 
 	/* see if the extent has been cached */
 	es->es_lblk = es->es_len = es->es_pblk = 0;
-	if (tree->cache_es) {
-		es1 = tree->cache_es;
-		if (in_range(lblk, es1->es_lblk, es1->es_len)) {
-			es_debug("%u cached by [%u/%u) %llu %x\n",
-				 lblk, es1->es_lblk, es1->es_len,
-				 ext4_es_pblock(es1), ext4_es_status(es1));
-			goto out;
-		}
+	es1 = READ_ONCE(tree->cache_es);
+	if (es1 && in_range(lblk, es1->es_lblk, es1->es_len)) {
+		es_debug("%u cached by [%u/%u) %llu %x\n",
+			 lblk, es1->es_lblk, es1->es_len,
+			 ext4_es_pblock(es1), ext4_es_status(es1));
+		goto out;
 	}
 
 	es1 = __es_tree_search(&tree->root, lblk);
@@ -293,7 +291,7 @@ static void __es_find_extent_range(struct inode *inode,
 	}
 
 	if (es1 && matching_fn(es1)) {
-		tree->cache_es = es1;
+		WRITE_ONCE(tree->cache_es, es1);
 		es->es_lblk = es1->es_lblk;
 		es->es_len = es1->es_len;
 		es->es_pblk = es1->es_pblk;
@@ -931,14 +929,12 @@ int ext4_es_lookup_extent(struct inode *inode, ext4_lblk_t lblk,
 
 	/* find extent in cache firstly */
 	es->es_lblk = es->es_len = es->es_pblk = 0;
-	if (tree->cache_es) {
-		es1 = tree->cache_es;
-		if (in_range(lblk, es1->es_lblk, es1->es_len)) {
-			es_debug("%u cached by [%u/%u)\n",
-				 lblk, es1->es_lblk, es1->es_len);
-			found = 1;
-			goto out;
-		}
+	es1 = READ_ONCE(tree->cache_es);
+	if (es1 && in_range(lblk, es1->es_lblk, es1->es_len)) {
+		es_debug("%u cached by [%u/%u)\n",
+			 lblk, es1->es_lblk, es1->es_len);
+		found = 1;
+		goto out;
 	}
 
 	node = tree->root.rb_node;

fs/ext4/hash.c

@@ -277,7 +277,11 @@ static int __ext4fs_dirhash(const struct inode *dir, const char *name, int len,
 	}
 	default:
 		hinfo->hash = 0;
-		return -1;
+		hinfo->minor_hash = 0;
+		ext4_warning(dir->i_sb,
+			     "invalid/unsupported hash tree version %u",
+			     hinfo->hash_version);
+		return -EINVAL;
 	}
 	hash = hash & ~1;
 	if (hash == (EXT4_HTREE_EOF_32BIT << 1))

fs/ext4/ialloc.c

@@ -91,7 +91,7 @@ static int ext4_validate_inode_bitmap(struct super_block *sb,
 
 	if (buffer_verified(bh))
 		return 0;
-	if (EXT4_MB_GRP_IBITMAP_CORRUPT(grp))
+	if (!grp || EXT4_MB_GRP_IBITMAP_CORRUPT(grp))
 		return -EFSCORRUPTED;
 
 	ext4_lock_group(sb, block_group);
@@ -293,7 +293,7 @@ void ext4_free_inode(handle_t *handle, struct inode *inode)
 	}
 	if (!(sbi->s_mount_state & EXT4_FC_REPLAY)) {
 		grp = ext4_get_group_info(sb, block_group);
-		if (unlikely(EXT4_MB_GRP_IBITMAP_CORRUPT(grp))) {
+		if (!grp || unlikely(EXT4_MB_GRP_IBITMAP_CORRUPT(grp))) {
 			fatal = -EFSCORRUPTED;
 			goto error_return;
 		}
@@ -1046,7 +1046,7 @@ struct inode *__ext4_new_inode(struct mnt_idmap *idmap,
 			 * Skip groups with already-known suspicious inode
 			 * tables
 			 */
-			if (EXT4_MB_GRP_IBITMAP_CORRUPT(grp))
+			if (!grp || EXT4_MB_GRP_IBITMAP_CORRUPT(grp))
 				goto next_group;
 		}
 
@@ -1183,6 +1183,10 @@ struct inode *__ext4_new_inode(struct mnt_idmap *idmap,
 
 		if (!(sbi->s_mount_state & EXT4_FC_REPLAY)) {
 			grp = ext4_get_group_info(sb, group);
+			if (!grp) {
+				err = -EFSCORRUPTED;
+				goto out;
+			}
 			down_read(&grp->alloc_sem); /*
 						     * protect vs itable
 						     * lazyinit
@@ -1526,7 +1530,7 @@ int ext4_init_inode_table(struct super_block *sb, ext4_group_t group,
 	}
 
 	gdp = ext4_get_group_desc(sb, group, &group_desc_bh);
-	if (!gdp)
+	if (!gdp || !grp)
 		goto out;
 
 	/*

fs/ext4/inline.c

@@ -34,6 +34,7 @@ static int get_max_inline_xattr_value_size(struct inode *inode,
 	struct ext4_xattr_ibody_header *header;
 	struct ext4_xattr_entry *entry;
 	struct ext4_inode *raw_inode;
+	void *end;
 	int free, min_offs;
 
 	if (!EXT4_INODE_HAS_XATTR_SPACE(inode))
@@ -57,14 +58,23 @@ static int get_max_inline_xattr_value_size(struct inode *inode,
 	raw_inode = ext4_raw_inode(iloc);
 	header = IHDR(inode, raw_inode);
 	entry = IFIRST(header);
+	end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size;
 
 	/* Compute min_offs. */
-	for (; !IS_LAST_ENTRY(entry); entry = EXT4_XATTR_NEXT(entry)) {
+	while (!IS_LAST_ENTRY(entry)) {
+		void *next = EXT4_XATTR_NEXT(entry);
+
+		if (next >= end) {
+			EXT4_ERROR_INODE(inode,
+					 "corrupt xattr in inline inode");
+			return 0;
+		}
 		if (!entry->e_value_inum && entry->e_value_size) {
 			size_t offs = le16_to_cpu(entry->e_value_offs);
 			if (offs < min_offs)
 				min_offs = offs;
 		}
+		entry = next;
 	}
 	free = min_offs -
 		((void *)entry - (void *)IFIRST(header)) - sizeof(__u32);
@@ -350,7 +360,7 @@ static int ext4_update_inline_data(handle_t *handle, struct inode *inode,
 
 	error = ext4_xattr_ibody_get(inode, i.name_index, i.name,
 				     value, len);
-	if (error == -ENODATA)
+	if (error < 0)
 		goto out;
 
 	BUFFER_TRACE(is.iloc.bh, "get_write_access");
@@ -1175,6 +1185,7 @@ static int ext4_finish_convert_inline_dir(handle_t *handle,
 		ext4_initialize_dirent_tail(dir_block,
 					    inode->i_sb->s_blocksize);
 	set_buffer_uptodate(dir_block);
+	unlock_buffer(dir_block);
 	err = ext4_handle_dirty_dirblock(handle, inode, dir_block);
 	if (err)
 		return err;
@@ -1249,6 +1260,7 @@ static int ext4_convert_inline_data_nolock(handle_t *handle,
 	if (!S_ISDIR(inode->i_mode)) {
 		memcpy(data_bh->b_data, buf, inline_size);
 		set_buffer_uptodate(data_bh);
+		unlock_buffer(data_bh);
 		error = ext4_handle_dirty_metadata(handle,
 						   inode, data_bh);
 	} else {
@@ -1256,7 +1268,6 @@ static int ext4_convert_inline_data_nolock(handle_t *handle,
 						       buf, inline_size);
 	}
 
-	unlock_buffer(data_bh);
 out_restore:
 	if (error)
 		ext4_restore_inline_data(handle, inode, iloc, buf, inline_size);

fs/ext4/inode.c

@@ -2783,11 +2783,12 @@ static int ext4_writepages(struct address_space *mapping,
 		.can_map = 1,
 	};
 	int ret;
+	int alloc_ctx;
 
 	if (unlikely(ext4_forced_shutdown(EXT4_SB(sb))))
 		return -EIO;
 
-	percpu_down_read(&EXT4_SB(sb)->s_writepages_rwsem);
+	alloc_ctx = ext4_writepages_down_read(sb);
 	ret = ext4_do_writepages(&mpd);
 	/*
 	 * For data=journal writeback we could have come across pages marked
@@ -2796,7 +2797,7 @@ static int ext4_writepages(struct address_space *mapping,
 	 */
 	if (!ret && mpd.journalled_more_data)
 		ret = ext4_do_writepages(&mpd);
-	percpu_up_read(&EXT4_SB(sb)->s_writepages_rwsem);
+	ext4_writepages_up_read(sb, alloc_ctx);
 
 	return ret;
 }
@@ -2824,17 +2825,18 @@ static int ext4_dax_writepages(struct address_space *mapping,
 	long nr_to_write = wbc->nr_to_write;
 	struct inode *inode = mapping->host;
 	struct ext4_sb_info *sbi = EXT4_SB(mapping->host->i_sb);
+	int alloc_ctx;
 
 	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
 		return -EIO;
 
-	percpu_down_read(&sbi->s_writepages_rwsem);
+	alloc_ctx = ext4_writepages_down_read(inode->i_sb);
 	trace_ext4_writepages(inode, wbc);
 
 	ret = dax_writeback_mapping_range(mapping, sbi->s_daxdev, wbc);
 	trace_ext4_writepages_result(inode, wbc, ret,
 				     nr_to_write - wbc->nr_to_write);
-	percpu_up_read(&sbi->s_writepages_rwsem);
+	ext4_writepages_up_read(inode->i_sb, alloc_ctx);
 	return ret;
 }
 
@@ -3375,7 +3377,7 @@ static int ext4_iomap_overwrite_begin(struct inode *inode, loff_t offset,
 	 */
 	flags &= ~IOMAP_WRITE;
 	ret = ext4_iomap_begin(inode, offset, length, flags, iomap, srcmap);
-	WARN_ON_ONCE(iomap->type != IOMAP_MAPPED);
+	WARN_ON_ONCE(!ret && iomap->type != IOMAP_MAPPED);
 	return ret;
 }
 
@@ -5928,7 +5930,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val)
 	journal_t *journal;
 	handle_t *handle;
 	int err;
-	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+	int alloc_ctx;
 
 	/*
 	 * We have to be very careful here: changing a data block's
@@ -5966,7 +5968,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val)
 		}
 	}
 
-	percpu_down_write(&sbi->s_writepages_rwsem);
+	alloc_ctx = ext4_writepages_down_write(inode->i_sb);
 	jbd2_journal_lock_updates(journal);
 
 	/*
@@ -5983,7 +5985,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val)
 		err = jbd2_journal_flush(journal, 0);
 		if (err < 0) {
 			jbd2_journal_unlock_updates(journal);
-			percpu_up_write(&sbi->s_writepages_rwsem);
+			ext4_writepages_up_write(inode->i_sb, alloc_ctx);
 			return err;
 		}
 		ext4_clear_inode_flag(inode, EXT4_INODE_JOURNAL_DATA);
@@ -5991,7 +5993,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val)
 	ext4_set_aops(inode);
 
 	jbd2_journal_unlock_updates(journal);
-	percpu_up_write(&sbi->s_writepages_rwsem);
+	ext4_writepages_up_write(inode->i_sb, alloc_ctx);
 
 	if (val)
 		filemap_invalidate_unlock(inode->i_mapping);

fs/ext4/mballoc.c

@@ -745,6 +745,8 @@ static int __mb_check_buddy(struct ext4_buddy *e4b, char *file,
 	MB_CHECK_ASSERT(e4b->bd_info->bb_fragments == fragments);
 
 	grp = ext4_get_group_info(sb, e4b->bd_group);
+	if (!grp)
+		return NULL;
 	list_for_each(cur, &grp->bb_prealloc_list) {
 		ext4_group_t groupnr;
 		struct ext4_prealloc_space *pa;
@@ -1060,9 +1062,9 @@ mb_set_largest_free_order(struct super_block *sb, struct ext4_group_info *grp)
 
 static noinline_for_stack
 void ext4_mb_generate_buddy(struct super_block *sb,
-				void *buddy, void *bitmap, ext4_group_t group)
+			    void *buddy, void *bitmap, ext4_group_t group,
+			    struct ext4_group_info *grp)
 {
-	struct ext4_group_info *grp = ext4_get_group_info(sb, group);
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	ext4_grpblk_t max = EXT4_CLUSTERS_PER_GROUP(sb);
 	ext4_grpblk_t i = 0;
@@ -1181,6 +1183,8 @@ static int ext4_mb_init_cache(struct page *page, char *incore, gfp_t gfp)
 			break;
 
 		grinfo = ext4_get_group_info(sb, group);
+		if (!grinfo)
+			continue;
 		/*
 		 * If page is uptodate then we came here after online resize
 		 * which added some new uninitialized group info structs, so
@@ -1246,6 +1250,10 @@ static int ext4_mb_init_cache(struct page *page, char *incore, gfp_t gfp)
 				group, page->index, i * blocksize);
 			trace_ext4_mb_buddy_bitmap_load(sb, group);
 			grinfo = ext4_get_group_info(sb, group);
+			if (!grinfo) {
+				err = -EFSCORRUPTED;
+				goto out;
+			}
 			grinfo->bb_fragments = 0;
 			memset(grinfo->bb_counters, 0,
 			       sizeof(*grinfo->bb_counters) *
@@ -1256,7 +1264,7 @@ static int ext4_mb_init_cache(struct page *page, char *incore, gfp_t gfp)
 			ext4_lock_group(sb, group);
 			/* init the buddy */
 			memset(data, 0xff, blocksize);
-			ext4_mb_generate_buddy(sb, data, incore, group);
+			ext4_mb_generate_buddy(sb, data, incore, group, grinfo);
 			ext4_unlock_group(sb, group);
 			incore = NULL;
 		} else {
@@ -1370,6 +1378,9 @@ int ext4_mb_init_group(struct super_block *sb, ext4_group_t group, gfp_t gfp)
 	might_sleep();
 	mb_debug(sb, "init group %u\n", group);
 	this_grp = ext4_get_group_info(sb, group);
+	if (!this_grp)
+		return -EFSCORRUPTED;
+
 	/*
 	 * This ensures that we don't reinit the buddy cache
 	 * page which map to the group from which we are already
@@ -1444,6 +1455,8 @@ ext4_mb_load_buddy_gfp(struct super_block *sb, ext4_group_t group,
 
 	blocks_per_page = PAGE_SIZE / sb->s_blocksize;
 	grp = ext4_get_group_info(sb, group);
+	if (!grp)
+		return -EFSCORRUPTED;
 
 	e4b->bd_blkbits = sb->s_blocksize_bits;
 	e4b->bd_info = grp;
@@ -2159,6 +2172,8 @@ int ext4_mb_find_by_goal(struct ext4_allocation_context *ac,
 	struct ext4_group_info *grp = ext4_get_group_info(ac->ac_sb, group);
 	struct ext4_free_extent ex;
 
+	if (!grp)
+		return -EFSCORRUPTED;
 	if (!(ac->ac_flags & (EXT4_MB_HINT_TRY_GOAL | EXT4_MB_HINT_GOAL_ONLY)))
 		return 0;
 	if (grp->bb_free == 0)
@@ -2385,7 +2400,7 @@ static bool ext4_mb_good_group(struct ext4_allocation_context *ac,
 
 	BUG_ON(cr < 0 || cr >= 4);
 
-	if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(grp)))
+	if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(grp) || !grp))
 		return false;
 
 	free = grp->bb_free;
@@ -2454,6 +2469,8 @@ static int ext4_mb_good_group_nolock(struct ext4_allocation_context *ac,
 	ext4_grpblk_t free;
 	int ret = 0;
 
+	if (!grp)
+		return -EFSCORRUPTED;
 	if (sbi->s_mb_stats)
 		atomic64_inc(&sbi->s_bal_cX_groups_considered[ac->ac_criteria]);
 	if (should_lock) {
@@ -2534,7 +2551,7 @@ ext4_group_t ext4_mb_prefetch(struct super_block *sb, ext4_group_t group,
 		 * prefetch once, so we avoid getblk() call, which can
 		 * be expensive.
 		 */
-		if (!EXT4_MB_GRP_TEST_AND_SET_READ(grp) &&
+		if (gdp && grp && !EXT4_MB_GRP_TEST_AND_SET_READ(grp) &&
 		    EXT4_MB_GRP_NEED_INIT(grp) &&
 		    ext4_free_group_clusters(sb, gdp) > 0 &&
 		    !(ext4_has_group_desc_csum(sb) &&
@@ -2578,7 +2595,7 @@ void ext4_mb_prefetch_fini(struct super_block *sb, ext4_group_t group,
 		gdp = ext4_get_group_desc(sb, group, NULL);
 		grp = ext4_get_group_info(sb, group);
 
-		if (EXT4_MB_GRP_NEED_INIT(grp) &&
+		if (grp && gdp && EXT4_MB_GRP_NEED_INIT(grp) &&
 		    ext4_free_group_clusters(sb, gdp) > 0 &&
 		    !(ext4_has_group_desc_csum(sb) &&
 		      (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)))) {
@@ -2837,6 +2854,8 @@ static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v)
 		sizeof(struct ext4_group_info);
 
 	grinfo = ext4_get_group_info(sb, group);
+	if (!grinfo)
+		return 0;
 	/* Load the group info in memory only if not already loaded. */
 	if (unlikely(EXT4_MB_GRP_NEED_INIT(grinfo))) {
 		err = ext4_mb_load_buddy(sb, group, &e4b);
@@ -2847,7 +2866,7 @@ static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v)
 		buddy_loaded = 1;
 	}
 
-	memcpy(&sg, ext4_get_group_info(sb, group), i);
+	memcpy(&sg, grinfo, i);
 
 	if (buddy_loaded)
 		ext4_mb_unload_buddy(&e4b);
@@ -3208,8 +3227,12 @@ static int ext4_mb_init_backend(struct super_block *sb)
 
 err_freebuddy:
 	cachep = get_groupinfo_cache(sb->s_blocksize_bits);
-	while (i-- > 0)
-		kmem_cache_free(cachep, ext4_get_group_info(sb, i));
+	while (i-- > 0) {
+		struct ext4_group_info *grp = ext4_get_group_info(sb, i);
+
+		if (grp)
+			kmem_cache_free(cachep, grp);
+	}
 	i = sbi->s_group_info_size;
 	rcu_read_lock();
 	group_info = rcu_dereference(sbi->s_group_info);
@@ -3522,6 +3545,8 @@ int ext4_mb_release(struct super_block *sb)
 		for (i = 0; i < ngroups; i++) {
 			cond_resched();
 			grinfo = ext4_get_group_info(sb, i);
+			if (!grinfo)
+				continue;
 			mb_group_bb_bitmap_free(grinfo);
 			ext4_lock_group(sb, i);
 			count = ext4_mb_cleanup_pa(grinfo);
@@ -4606,6 +4631,8 @@ static void ext4_mb_generate_from_freelist(struct super_block *sb, void *bitmap,
 	struct ext4_free_data *entry;
 
 	grp = ext4_get_group_info(sb, group);
+	if (!grp)
+		return;
 	n = rb_first(&(grp->bb_free_root));
 
 	while (n) {
@@ -4633,6 +4660,9 @@ void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap,
 	int preallocated = 0;
 	int len;
 
+	if (!grp)
+		return;
+
 	/* all form of preallocation discards first load group,
 	 * so the only competing code is preallocation use.
 	 * we don't need any locking here
@@ -4869,6 +4899,8 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac)
 
 	ei = EXT4_I(ac->ac_inode);
 	grp = ext4_get_group_info(sb, ac->ac_b_ex.fe_group);
+	if (!grp)
+		return;
 
 	pa->pa_node_lock.inode_lock = &ei->i_prealloc_lock;
 	pa->pa_inode = ac->ac_inode;
@@ -4918,6 +4950,8 @@ ext4_mb_new_group_pa(struct ext4_allocation_context *ac)
 	atomic_add(pa->pa_free, &EXT4_SB(sb)->s_mb_preallocated);
 
 	grp = ext4_get_group_info(sb, ac->ac_b_ex.fe_group);
+	if (!grp)
+		return;
 	lg = ac->ac_lg;
 	BUG_ON(lg == NULL);
 
@@ -5013,7 +5047,11 @@ ext4_mb_release_group_pa(struct ext4_buddy *e4b,
 	trace_ext4_mb_release_group_pa(sb, pa);
 	BUG_ON(pa->pa_deleted == 0);
 	ext4_get_group_no_and_offset(sb, pa->pa_pstart, &group, &bit);
-	BUG_ON(group != e4b->bd_group && pa->pa_len != 0);
+	if (unlikely(group != e4b->bd_group && pa->pa_len != 0)) {
+		ext4_warning(sb, "bad group: expected %u, group %u, pa_start %llu",
+			     e4b->bd_group, group, pa->pa_pstart);
+		return 0;
+	}
 	mb_free_blocks(pa->pa_inode, e4b, bit, pa->pa_len);
 	atomic_add(pa->pa_len, &EXT4_SB(sb)->s_mb_discarded);
 	trace_ext4_mballoc_discard(sb, NULL, group, bit, pa->pa_len);
@@ -5043,6 +5081,8 @@ ext4_mb_discard_group_preallocations(struct super_block *sb,
 	int err;
 	int free = 0;
 
+	if (!grp)
+		return 0;
 	mb_debug(sb, "discard preallocation for group %u\n", group);
 	if (list_empty(&grp->bb_prealloc_list))
 		goto out_dbg;
@@ -5297,6 +5337,9 @@ static inline void ext4_mb_show_pa(struct super_block *sb)
 		struct ext4_prealloc_space *pa;
 		ext4_grpblk_t start;
 		struct list_head *cur;
+
+		if (!grp)
+			continue;
 		ext4_lock_group(sb, i);
 		list_for_each(cur, &grp->bb_prealloc_list) {
 			pa = list_entry(cur, struct ext4_prealloc_space,
@@ -6064,6 +6107,7 @@ static void ext4_mb_clear_bb(handle_t *handle, struct inode *inode,
 	struct buffer_head *bitmap_bh = NULL;
 	struct super_block *sb = inode->i_sb;
 	struct ext4_group_desc *gdp;
+	struct ext4_group_info *grp;
 	unsigned int overflow;
 	ext4_grpblk_t bit;
 	struct buffer_head *gd_bh;
@@ -6089,8 +6133,8 @@ static void ext4_mb_clear_bb(handle_t *handle, struct inode *inode,
 	overflow = 0;
 	ext4_get_group_no_and_offset(sb, block, &block_group, &bit);
 
-	if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(
-			ext4_get_group_info(sb, block_group))))
+	grp = ext4_get_group_info(sb, block_group);
+	if (unlikely(!grp || EXT4_MB_GRP_BBITMAP_CORRUPT(grp)))
 		return;
 
 	/*
@@ -6692,6 +6736,8 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
 
 	for (group = first_group; group <= last_group; group++) {
 		grp = ext4_get_group_info(sb, group);
+		if (!grp)
+			continue;
 		/* We only do this if the grp has never been initialized */
 		if (unlikely(EXT4_MB_GRP_NEED_INIT(grp))) {
 			ret = ext4_mb_init_group(sb, group, GFP_NOFS);

fs/ext4/migrate.c

@@ -408,7 +408,6 @@ static int free_ext_block(handle_t *handle, struct inode *inode)
 
 int ext4_ext_migrate(struct inode *inode)
 {
-	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 	handle_t *handle;
 	int retval = 0, i;
 	__le32 *i_data;
@@ -418,6 +417,7 @@ int ext4_ext_migrate(struct inode *inode)
 	unsigned long max_entries;
 	__u32 goal, tmp_csum_seed;
 	uid_t owner[2];
+	int alloc_ctx;
 
 	/*
 	 * If the filesystem does not support extents, or the inode
@@ -434,7 +434,7 @@ int ext4_ext_migrate(struct inode *inode)
 		 */
 		return retval;
 
-	percpu_down_write(&sbi->s_writepages_rwsem);
+	alloc_ctx = ext4_writepages_down_write(inode->i_sb);
 
 	/*
 	 * Worst case we can touch the allocation bitmaps and a block
@@ -586,7 +586,7 @@ int ext4_ext_migrate(struct inode *inode)
 	unlock_new_inode(tmp_inode);
 	iput(tmp_inode);
 out_unlock:
-	percpu_up_write(&sbi->s_writepages_rwsem);
+	ext4_writepages_up_write(inode->i_sb, alloc_ctx);
 	return retval;
 }
 
@@ -605,6 +605,7 @@ int ext4_ind_migrate(struct inode *inode)
 	ext4_fsblk_t			blk;
 	handle_t			*handle;
 	int				ret, ret2 = 0;
+	int				alloc_ctx;
 
 	if (!ext4_has_feature_extents(inode->i_sb) ||
 	    (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
@@ -621,7 +622,7 @@ int ext4_ind_migrate(struct inode *inode)
 	if (test_opt(inode->i_sb, DELALLOC))
 		ext4_alloc_da_blocks(inode);
 
-	percpu_down_write(&sbi->s_writepages_rwsem);
+	alloc_ctx = ext4_writepages_down_write(inode->i_sb);
 
 	handle = ext4_journal_start(inode, EXT4_HT_MIGRATE, 1);
 	if (IS_ERR(handle)) {
@@ -665,6 +666,6 @@ int ext4_ind_migrate(struct inode *inode)
 	ext4_journal_stop(handle);
 	up_write(&EXT4_I(inode)->i_data_sem);
 out_unlock:
-	percpu_up_write(&sbi->s_writepages_rwsem);
+	ext4_writepages_up_write(inode->i_sb, alloc_ctx);
 	return ret;
 }

fs/ext4/mmp.c

@@ -39,28 +39,36 @@ static void ext4_mmp_csum_set(struct super_block *sb, struct mmp_struct *mmp)
  * Write the MMP block using REQ_SYNC to try to get the block on-disk
  * faster.
  */
-static int write_mmp_block(struct super_block *sb, struct buffer_head *bh)
+static int write_mmp_block_thawed(struct super_block *sb,
+				  struct buffer_head *bh)
 {
 	struct mmp_struct *mmp = (struct mmp_struct *)(bh->b_data);
 
-	/*
-	 * We protect against freezing so that we don't create dirty buffers
-	 * on frozen filesystem.
-	 */
-	sb_start_write(sb);
 	ext4_mmp_csum_set(sb, mmp);
 	lock_buffer(bh);
 	bh->b_end_io = end_buffer_write_sync;
 	get_bh(bh);
 	submit_bh(REQ_OP_WRITE | REQ_SYNC | REQ_META | REQ_PRIO, bh);
 	wait_on_buffer(bh);
-	sb_end_write(sb);
 	if (unlikely(!buffer_uptodate(bh)))
 		return -EIO;
-
 	return 0;
 }
 
+static int write_mmp_block(struct super_block *sb, struct buffer_head *bh)
+{
+	int err;
+
+	/*
+	 * We protect against freezing so that we don't create dirty buffers
+	 * on frozen filesystem.
+	 */
+	sb_start_write(sb);
+	err = write_mmp_block_thawed(sb, bh);
+	sb_end_write(sb);
+	return err;
+}
+
 /*
  * Read the MMP block. It _must_ be read from disk and hence we clear the
  * uptodate flag on the buffer.
@@ -344,7 +352,11 @@ int ext4_multi_mount_protect(struct super_block *sb,
 	seq = mmp_new_seq();
 	mmp->mmp_seq = cpu_to_le32(seq);
 
-	retval = write_mmp_block(sb, bh);
+	/*
+	 * On mount / remount we are protected against fs freezing (by s_umount
+	 * semaphore) and grabbing freeze protection upsets lockdep
+	 */
+	retval = write_mmp_block_thawed(sb, bh);
 	if (retval)
 		goto failed;
 

fs/ext4/namei.c

@@ -674,7 +674,7 @@ static struct stats dx_show_leaf(struct inode *dir,
 				len = de->name_len;
 				if (!IS_ENCRYPTED(dir)) {
 					/* Directory is not encrypted */
-					ext4fs_dirhash(dir, de->name,
+					(void) ext4fs_dirhash(dir, de->name,
 						de->name_len, &h);
 					printk("%*.s:(U)%x.%u ", len,
 					       name, h.hash,
@@ -709,8 +709,9 @@ static struct stats dx_show_leaf(struct inode *dir,
 					if (IS_CASEFOLDED(dir))
 						h.hash = EXT4_DIRENT_HASH(de);
 					else
-						ext4fs_dirhash(dir, de->name,
-						       de->name_len, &h);
+						(void) ext4fs_dirhash(dir,
+							de->name,
+							de->name_len, &h);
 					printk("%*.s:(E)%x.%u ", len, name,
 					       h.hash, (unsigned) ((char *) de
 								   - base));
@@ -720,7 +721,8 @@ static struct stats dx_show_leaf(struct inode *dir,
 #else
 				int len = de->name_len;
 				char *name = de->name;
-				ext4fs_dirhash(dir, de->name, de->name_len, &h);
+				(void) ext4fs_dirhash(dir, de->name,
+						      de->name_len, &h);
 				printk("%*.s:%x.%u ", len, name, h.hash,
 				       (unsigned) ((char *) de - base));
 #endif
@@ -849,8 +851,14 @@ dx_probe(struct ext4_filename *fname, struct inode *dir,
 	hinfo->seed = EXT4_SB(dir->i_sb)->s_hash_seed;
 	/* hash is already computed for encrypted casefolded directory */
 	if (fname && fname_name(fname) &&
-				!(IS_ENCRYPTED(dir) && IS_CASEFOLDED(dir)))
-		ext4fs_dirhash(dir, fname_name(fname), fname_len(fname), hinfo);
+	    !(IS_ENCRYPTED(dir) && IS_CASEFOLDED(dir))) {
+		int ret = ext4fs_dirhash(dir, fname_name(fname),
+					 fname_len(fname), hinfo);
+		if (ret < 0) {
+			ret_err = ERR_PTR(ret);
+			goto fail;
+		}
+	}
 	hash = hinfo->hash;
 
 	if (root->info.unused_flags & 1) {
@@ -1111,7 +1119,12 @@ static int htree_dirblock_to_tree(struct file *dir_file,
 				hinfo->minor_hash = 0;
 			}
 		} else {
-			ext4fs_dirhash(dir, de->name, de->name_len, hinfo);
+			err = ext4fs_dirhash(dir, de->name,
+					     de->name_len, hinfo);
+			if (err < 0) {
+				count = err;
+				goto errout;
+			}
 		}
 		if ((hinfo->hash < start_hash) ||
 		    ((hinfo->hash == start_hash) &&
@@ -1313,8 +1326,12 @@ static int dx_make_map(struct inode *dir, struct buffer_head *bh,
 		if (de->name_len && de->inode) {
 			if (ext4_hash_in_dirent(dir))
 				h.hash = EXT4_DIRENT_HASH(de);
-			else
-				ext4fs_dirhash(dir, de->name, de->name_len, &h);
+			else {
+				int err = ext4fs_dirhash(dir, de->name,
+						     de->name_len, &h);
+				if (err < 0)
+					return err;
+			}
 			map_tail--;
 			map_tail->hash = h.hash;
 			map_tail->offs = ((char *) de - base)>>2;
@@ -1452,10 +1469,9 @@ int ext4_fname_setup_ci_filename(struct inode *dir, const struct qstr *iname,
 	hinfo->hash_version = DX_HASH_SIPHASH;
 	hinfo->seed = NULL;
 	if (cf_name->name)
-		ext4fs_dirhash(dir, cf_name->name, cf_name->len, hinfo);
+		return ext4fs_dirhash(dir, cf_name->name, cf_name->len, hinfo);
 	else
-		ext4fs_dirhash(dir, iname->name, iname->len, hinfo);
-	return 0;
+		return ext4fs_dirhash(dir, iname->name, iname->len, hinfo);
 }
 #endif
 
@@ -2298,10 +2314,15 @@ static int make_indexed_dir(handle_t *handle, struct ext4_filename *fname,
 	fname->hinfo.seed = EXT4_SB(dir->i_sb)->s_hash_seed;
 
 	/* casefolded encrypted hashes are computed on fname setup */
-	if (!ext4_hash_in_dirent(dir))
-		ext4fs_dirhash(dir, fname_name(fname),
-				fname_len(fname), &fname->hinfo);
-
+	if (!ext4_hash_in_dirent(dir)) {
+		int err = ext4fs_dirhash(dir, fname_name(fname),
+					 fname_len(fname), &fname->hinfo);
+		if (err < 0) {
+			brelse(bh2);
+			brelse(bh);
+			return err;
+		}
+	}
 	memset(frames, 0, sizeof(frames));
 	frame = frames;
 	frame->entries = entries;

fs/ext4/super.c

@@ -1048,6 +1048,8 @@ void ext4_mark_group_bitmap_corrupted(struct super_block *sb,
 	struct ext4_group_desc *gdp = ext4_get_group_desc(sb, group, NULL);
 	int ret;
 
+	if (!grp || !gdp)
+		return;
 	if (flags & EXT4_GROUP_INFO_BBITMAP_CORRUPT) {
 		ret = ext4_test_and_set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT,
 					    &grp->bb_state);
@@ -3238,11 +3240,9 @@ static __le16 ext4_group_desc_csum(struct super_block *sb, __u32 block_group,
 	crc = crc16(crc, (__u8 *)gdp, offset);
 	offset += sizeof(gdp->bg_checksum); /* skip checksum */
 	/* for checksum of struct ext4_group_desc do the rest...*/
-	if (ext4_has_feature_64bit(sb) &&
-	    offset < le16_to_cpu(sbi->s_es->s_desc_size))
+	if (ext4_has_feature_64bit(sb) && offset < sbi->s_desc_size)
 		crc = crc16(crc, (__u8 *)gdp + offset,
-			    le16_to_cpu(sbi->s_es->s_desc_size) -
-				offset);
+			    sbi->s_desc_size - offset);
 
 out:
 	return cpu_to_le16(crc);
@@ -5684,8 +5684,9 @@ static int ext4_fill_super(struct super_block *sb, struct fs_context *fc)
 		descr = "out journal";
 
 	if (___ratelimit(&ext4_mount_msg_ratelimit, "EXT4-fs mount"))
-		ext4_msg(sb, KERN_INFO, "mounted filesystem %pU with%s. "
-			 "Quota mode: %s.", &sb->s_uuid, descr,
+		ext4_msg(sb, KERN_INFO, "mounted filesystem %pU %s with%s. "
+			 "Quota mode: %s.", &sb->s_uuid,
+			 sb_rdonly(sb) ? "ro" : "r/w", descr,
 			 ext4_quota_mode(sb));
 
 	/* Update the s_overhead_clusters if necessary */
@@ -6387,6 +6388,7 @@ static int __ext4_remount(struct fs_context *fc, struct super_block *sb)
 	struct ext4_mount_options old_opts;
 	ext4_group_t g;
 	int err = 0;
+	int enable_rw = 0;
 #ifdef CONFIG_QUOTA
 	int enable_quota = 0;
 	int i, j;
@@ -6573,7 +6575,7 @@ static int __ext4_remount(struct fs_context *fc, struct super_block *sb)
 			if (err)
 				goto restore_opts;
 
-			sb->s_flags &= ~SB_RDONLY;
+			enable_rw = 1;
 			if (ext4_has_feature_mmp(sb)) {
 				err = ext4_multi_mount_protect(sb,
 						le64_to_cpu(es->s_mmp_block));
@@ -6616,9 +6618,6 @@ static int __ext4_remount(struct fs_context *fc, struct super_block *sb)
 	}
 
 #ifdef CONFIG_QUOTA
-	/* Release old quota file names */
-	for (i = 0; i < EXT4_MAXQUOTAS; i++)
-		kfree(old_opts.s_qf_names[i]);
 	if (enable_quota) {
 		if (sb_any_quota_suspended(sb))
 			dquot_resume(sb, -1);
@@ -6628,16 +6627,29 @@ static int __ext4_remount(struct fs_context *fc, struct super_block *sb)
 				goto restore_opts;
 		}
 	}
+	/* Release old quota file names */
+	for (i = 0; i < EXT4_MAXQUOTAS; i++)
+		kfree(old_opts.s_qf_names[i]);
 #endif
 	if (!test_opt(sb, BLOCK_VALIDITY) && sbi->s_system_blks)
 		ext4_release_system_zone(sb);
 
+	if (enable_rw)
+		sb->s_flags &= ~SB_RDONLY;
+
 	if (!ext4_has_feature_mmp(sb) || sb_rdonly(sb))
 		ext4_stop_mmpd(sbi);
 
 	return 0;
 
 restore_opts:
+	/*
+	 * If there was a failing r/w to ro transition, we may need to
+	 * re-enable quota
+	 */
+	if ((sb->s_flags & SB_RDONLY) && !(old_sb_flags & SB_RDONLY) &&
+	    sb_any_quota_suspended(sb))
+		dquot_resume(sb, -1);
 	sb->s_flags = old_sb_flags;
 	sbi->s_mount_opt = old_opts.s_mount_opt;
 	sbi->s_mount_opt2 = old_opts.s_mount_opt2;
@@ -6678,8 +6690,9 @@ static int ext4_reconfigure(struct fs_context *fc)
 	if (ret < 0)
 		return ret;
 
-	ext4_msg(sb, KERN_INFO, "re-mounted %pU. Quota mode: %s.",
-		 &sb->s_uuid, ext4_quota_mode(sb));
+	ext4_msg(sb, KERN_INFO, "re-mounted %pU %s. Quota mode: %s.",
+		 &sb->s_uuid, sb_rdonly(sb) ? "ro" : "r/w",
+		 ext4_quota_mode(sb));
 
 	return 0;
 }

fs/ext4/xattr.c

@@ -2614,6 +2614,7 @@ static int ext4_xattr_move_to_block(handle_t *handle, struct inode *inode,
 		.in_inode = !!entry->e_value_inum,
 	};
 	struct ext4_xattr_ibody_header *header = IHDR(inode, raw_inode);
+	int needs_kvfree = 0;
 	int error;
 
 	is = kzalloc(sizeof(struct ext4_xattr_ibody_find), GFP_NOFS);
@@ -2636,7 +2637,7 @@ static int ext4_xattr_move_to_block(handle_t *handle, struct inode *inode,
 			error = -ENOMEM;
 			goto out;
 		}
-
+		needs_kvfree = 1;
 		error = ext4_xattr_inode_get(inode, entry, buffer, value_size);
 		if (error)
 			goto out;
@@ -2675,7 +2676,7 @@ static int ext4_xattr_move_to_block(handle_t *handle, struct inode *inode,
 
 out:
 	kfree(b_entry_name);
-	if (entry->e_value_inum && buffer)
+	if (needs_kvfree && buffer)
 		kvfree(buffer);
 	if (is)
 		brelse(is->iloc.bh);