btrfs: tree-checker: Verify block_group_item

A crafted image with invalid block group items could make free space cache
code to cause panic.

We could detect such invalid block group item by checking:
1) Item size
   Known fixed value.
2) Block group size (key.offset)
   We have an upper limit on block group item (10G)
3) Chunk objectid
   Known fixed value.
4) Type
   Only 4 valid type values, DATA, METADATA, SYSTEM and DATA|METADATA.
   No more than 1 bit set for profile type.
5) Used space
   No more than the block group size.

This should allow btrfs to detect and refuse to mount the crafted image.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=199849
Reported-by: Xu Wen <wen.xu@gatech.edu>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: Gu Jinxiang <gujx@cn.fujitsu.com>
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Tested-by: Gu Jinxiang <gujx@cn.fujitsu.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>

diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c
index 8d40e7dd8c309d0f7bdd460f439f20382c64fd20..3bade2ad39e8160d1ff2662c8930a35ad813d5ea 100644 (file)
--- a/fs/btrfs/tree-checker.c
+++ b/fs/btrfs/tree-checker.c
@@ -19,6 +19,7 @@
 #include "tree-checker.h"
 #include "disk-io.h"
 #include "compression.h"
+#include "volumes.h"
 
 /*
  * Error message should follow the following format:
@@ -353,6 +354,102 @@ static int check_dir_item(struct btrfs_fs_info *fs_info,
        return 0;
 }
 
+__printf(4, 5)
+__cold
+static void block_group_err(const struct btrfs_fs_info *fs_info,
+                           const struct extent_buffer *eb, int slot,
+                           const char *fmt, ...)
+{
+       struct btrfs_key key;
+       struct va_format vaf;
+       va_list args;
+
+       btrfs_item_key_to_cpu(eb, &key, slot);
+       va_start(args, fmt);
+
+       vaf.fmt = fmt;
+       vaf.va = &args;
+
+       btrfs_crit(fs_info,
+       "corrupt %s: root=%llu block=%llu slot=%d bg_start=%llu bg_len=%llu, %pV",
+               btrfs_header_level(eb) == 0 ? "leaf" : "node",
+               btrfs_header_owner(eb), btrfs_header_bytenr(eb), slot,
+               key.objectid, key.offset, &vaf);
+       va_end(args);
+}
+
+static int check_block_group_item(struct btrfs_fs_info *fs_info,
+                                 struct extent_buffer *leaf,
+                                 struct btrfs_key *key, int slot)
+{
+       struct btrfs_block_group_item bgi;
+       u32 item_size = btrfs_item_size_nr(leaf, slot);
+       u64 flags;
+       u64 type;
+
+       /*
+        * Here we don't really care about alignment since extent allocator can
+        * handle it.  We care more about the size, as if one block group is
+        * larger than maximum size, it's must be some obvious corruption.
+        */
+       if (key->offset > BTRFS_MAX_DATA_CHUNK_SIZE || key->offset == 0) {
+               block_group_err(fs_info, leaf, slot,
+                       "invalid block group size, have %llu expect (0, %llu]",
+                               key->offset, BTRFS_MAX_DATA_CHUNK_SIZE);
+               return -EUCLEAN;
+       }
+
+       if (item_size != sizeof(bgi)) {
+               block_group_err(fs_info, leaf, slot,
+                       "invalid item size, have %u expect %zu",
+                               item_size, sizeof(bgi));
+               return -EUCLEAN;
+       }
+
+       read_extent_buffer(leaf, &bgi, btrfs_item_ptr_offset(leaf, slot),
+                          sizeof(bgi));
+       if (btrfs_block_group_chunk_objectid(&bgi) !=
+           BTRFS_FIRST_CHUNK_TREE_OBJECTID) {
+               block_group_err(fs_info, leaf, slot,
+               "invalid block group chunk objectid, have %llu expect %llu",
+                               btrfs_block_group_chunk_objectid(&bgi),
+                               BTRFS_FIRST_CHUNK_TREE_OBJECTID);
+               return -EUCLEAN;
+       }
+
+       if (btrfs_block_group_used(&bgi) > key->offset) {
+               block_group_err(fs_info, leaf, slot,
+                       "invalid block group used, have %llu expect [0, %llu)",
+                               btrfs_block_group_used(&bgi), key->offset);
+               return -EUCLEAN;
+       }
+
+       flags = btrfs_block_group_flags(&bgi);
+       if (hweight64(flags & BTRFS_BLOCK_GROUP_PROFILE_MASK) > 1) {
+               block_group_err(fs_info, leaf, slot,
+"invalid profile flags, have 0x%llx (%lu bits set) expect no more than 1 bit set",
+                       flags & BTRFS_BLOCK_GROUP_PROFILE_MASK,
+                       hweight64(flags & BTRFS_BLOCK_GROUP_PROFILE_MASK));
+               return -EUCLEAN;
+       }
+
+       type = flags & BTRFS_BLOCK_GROUP_TYPE_MASK;
+       if (type != BTRFS_BLOCK_GROUP_DATA &&
+           type != BTRFS_BLOCK_GROUP_METADATA &&
+           type != BTRFS_BLOCK_GROUP_SYSTEM &&
+           type != (BTRFS_BLOCK_GROUP_METADATA |
+                          BTRFS_BLOCK_GROUP_DATA)) {
+               block_group_err(fs_info, leaf, slot,
+"invalid type, have 0x%llx (%lu bits set) expect either 0x%llx, 0x%llx, 0x%llu or 0x%llx",
+                       type, hweight64(type),
+                       BTRFS_BLOCK_GROUP_DATA, BTRFS_BLOCK_GROUP_METADATA,
+                       BTRFS_BLOCK_GROUP_SYSTEM,
+                       BTRFS_BLOCK_GROUP_METADATA | BTRFS_BLOCK_GROUP_DATA);
+               return -EUCLEAN;
+       }
+       return 0;
+}
+
 /*
  * Common point to switch the item-specific validation.
  */
@@ -374,6 +471,9 @@ static int check_leaf_item(struct btrfs_fs_info *fs_info,
        case BTRFS_XATTR_ITEM_KEY:
                ret = check_dir_item(fs_info, leaf, key, slot);
                break;
+       case BTRFS_BLOCK_GROUP_ITEM_KEY:
+               ret = check_block_group_item(fs_info, leaf, key, slot);
+               break;
        }
        return ret;
 }

diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index fe497937933f2300d8200c4f611d47a160e0bbca..256e57eec8ecb342c80f5e0299c25dba18a75985 100644 (file)
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -4692,7 +4692,7 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
 
        if (type & BTRFS_BLOCK_GROUP_DATA) {
                max_stripe_size = SZ_1G;
-               max_chunk_size = 10 * max_stripe_size;
+               max_chunk_size = BTRFS_MAX_DATA_CHUNK_SIZE;
                if (!devs_max)
                        devs_max = BTRFS_MAX_DEVS(info);
        } else if (type & BTRFS_BLOCK_GROUP_METADATA) {

diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index df2d8bdf8c9a042fcf2fde434657e303f3855e29..275c31c730cf203dd74869425cdda98589e27638 100644 (file)
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -11,6 +11,8 @@
 #include <linux/btrfs.h>
 #include "async-thread.h"
 
+#define BTRFS_MAX_DATA_CHUNK_SIZE      (10ULL * SZ_1G)
+
 extern struct mutex uuid_mutex;
 
 #define BTRFS_STRIPE_LEN       SZ_64K