ext4: limit block allocations for indirect-block files to < 2^32

Today, the ext4 allocator will happily allocate blocks past
2^32 for indirect-block files, which results in the block
numbers getting truncated, and corruption ensues.

This patch limits such allocations to < 2^32, and adds
BUG_ONs if we do get blocks larger than that.

This should address RH Bug 519471, ext4 bitmap allocator 
must limit blocks to < 2^32

* ext4_find_goal() is modified to choose a goal < UINT_MAX,
  so that our starting point is in an acceptable range.

* ext4_xattr_block_set() is modified such that the goal block
  is < UINT_MAX, as above.

* ext4_mb_regular_allocator() is modified so that the group
  search does not continue into groups which are too high

* ext4_mb_use_preallocated() has a check that we don't use
  preallocated space which is too far out

* ext4_alloc_blocks() and ext4_xattr_block_set() add some BUG_ONs

No attempt has been made to limit inode locations to < 2^32,
so we may wind up with blocks far from their inodes.  Doing
this much already will lead to some odd ENOSPC issues when the
"lower 32" gets full, and further restricting inodes could
make that even weirder.

For high inodes, choosing a goal of the original, % UINT_MAX,
may be a bit odd, but then we're in an odd situation anyway,
and I don't know of a better heuristic.

Signed-off-by: Eric Sandeen <sandeen@redhat.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>

5 files changed, 38 insertions, 3 deletions

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 4dc64ed58d26..2a0f75d55fad 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -403,6 +403,9 @@ struct ext4_mount_options {
 #endif
 };
 
+/* Max physical block we can addres w/o extents */
+#define EXT4_MAX_BLOCK_FILE_PHYS	0xFFFFFFFF
+
 /*
  * Structure of an inode on the disk
  */
@@ -857,6 +860,7 @@ struct ext4_sb_info {
 	unsigned long s_gdb_count;	/* Number of group descriptor blocks */
 	unsigned long s_desc_per_block;	/* Number of group descriptors per block */
 	ext4_group_t s_groups_count;	/* Number of groups in the fs */
+	ext4_group_t s_blockfile_groups;/* Groups acceptable for non-extent files */
 	unsigned long s_overhead_last;  /* Last calculated overhead */
 	unsigned long s_blocks_last;    /* Last seen block count */
 	loff_t s_bitmap_maxbytes;	/* max bytes for bitmap files */
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index d04c8428bde2..5a8979259c9a 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -562,15 +562,21 @@ static ext4_fsblk_t ext4_find_near(struct inode *inode, Indirect *ind)
  *
  *	Normally this function find the preferred place for block allocation,
  *	returns it.
+ *	Because this is only used for non-extent files, we limit the block nr
+ *	to 32 bits.
  */
 static ext4_fsblk_t ext4_find_goal(struct inode *inode, ext4_lblk_t block,
 				   Indirect *partial)
 {
+	ext4_fsblk_t goal;
+
 	/*
 	 * XXX need to get goal block from mballoc's data structures
 	 */
 
-	return ext4_find_near(inode, partial);
+	goal = ext4_find_near(inode, partial);
+	goal = goal & EXT4_MAX_BLOCK_FILE_PHYS;
+	return goal;
 }
 
 /**
@@ -651,6 +657,8 @@ static int ext4_alloc_blocks(handle_t *handle, struct inode *inode,
 		if (*err)
 			goto failed_out;
 
+		BUG_ON(current_block + count > EXT4_MAX_BLOCK_FILE_PHYS);
+
 		target -= count;
 		/* allocate blocks for indirect blocks */
 		while (index < indirect_blks && count) {
@@ -685,6 +693,7 @@ static int ext4_alloc_blocks(handle_t *handle, struct inode *inode,
 		ar.flags = EXT4_MB_HINT_DATA;
 
 	current_block = ext4_mb_new_blocks(handle, &ar, err);
+	BUG_ON(current_block + ar.len > EXT4_MAX_BLOCK_FILE_PHYS);
 
 	if (*err && (target == blks)) {
 		/*
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index d23056d375b3..e9c61896d605 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -1965,6 +1965,10 @@ ext4_mb_regular_allocator(struct ext4_allocation_context *ac)
 	sb = ac->ac_sb;
 	sbi = EXT4_SB(sb);
 	ngroups = ext4_get_groups_count(sb);
+	/* non-extent files are limited to low blocks/groups */
+	if (!(EXT4_I(ac->ac_inode)->i_flags & EXT4_EXTENTS_FL))
+		ngroups = sbi->s_blockfile_groups;
+
 	BUG_ON(ac->ac_status == AC_STATUS_FOUND);
 
 	/* first, try the goal */
@@ -3382,6 +3386,11 @@ ext4_mb_use_preallocated(struct ext4_allocation_context *ac)
 			ac->ac_o_ex.fe_logical >= pa->pa_lstart + pa->pa_len)
 			continue;
 
+		/* non-extent files can't have physical blocks past 2^32 */
+		if (!(EXT4_I(ac->ac_inode)->i_flags & EXT4_EXTENTS_FL) &&
+			pa->pa_pstart + pa->pa_len > EXT4_MAX_BLOCK_FILE_PHYS)
+			continue;
+
 		/* found preallocated blocks, use them */
 		spin_lock(&pa->pa_lock);
 		if (pa->pa_deleted == 0 && pa->pa_free) {
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index af95dd8ba54b..a6b1ab734728 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -2616,6 +2616,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 		goto failed_mount;
 	}
 	sbi->s_groups_count = blocks_count;
+	sbi->s_blockfile_groups = min_t(ext4_group_t, sbi->s_groups_count,
+			(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);
 	sbi->s_group_desc = kmalloc(db_count * sizeof(struct buffer_head *),
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 62b31c246994..fed5b01d7a8d 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -810,12 +810,23 @@ inserted:
 			get_bh(new_bh);
 		} else {
 			/* We need to allocate a new block */
-			ext4_fsblk_t goal = ext4_group_first_block_no(sb,
+			ext4_fsblk_t goal, block;
+
+			goal = ext4_group_first_block_no(sb,
 						EXT4_I(inode)->i_block_group);
-			ext4_fsblk_t block = ext4_new_meta_blocks(handle, inode,
+
+			/* non-extent files can't have physical blocks past 2^32 */
+			if (!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL))
+				goal = goal & EXT4_MAX_BLOCK_FILE_PHYS;
+
+			block = ext4_new_meta_blocks(handle, inode,
 						  goal, NULL, &error);
 			if (error)
 				goto cleanup;
+
+			if (!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL))
+				BUG_ON(block > EXT4_MAX_BLOCK_FILE_PHYS);
+
 			ea_idebug(inode, "creating block %d", block);
 
 			new_bh = sb_getblk(sb, block);