#include "qgroup-verify.h"
#include "rbtree-utils.h"
#include "backref.h"
-#include "ulist.h"
+#include "kernel-shared/ulist.h"
+#include "hash.h"
+#include "help.h"
enum task_position {
TASK_EXTENTS,
u32 found_ref;
};
+#define ROOT_DIR_ERROR (1<<1) /* bad ROOT_DIR */
+#define DIR_ITEM_MISSING (1<<2) /* DIR_ITEM not found */
+#define DIR_ITEM_MISMATCH (1<<3) /* DIR_ITEM found but not match */
+#define INODE_REF_MISSING (1<<4) /* INODE_REF/INODE_EXTREF not found */
+#define INODE_ITEM_MISSING (1<<5) /* INODE_ITEM not found */
+#define INODE_ITEM_MISMATCH (1<<6) /* INODE_ITEM found but not match */
+#define FILE_EXTENT_ERROR (1<<7) /* bad FILE_EXTENT */
+#define ODD_CSUM_ITEM (1<<8) /* CSUM_ITEM error */
+#define CSUM_ITEM_MISSING (1<<9) /* CSUM_ITEM not found */
+#define LINK_COUNT_ERROR (1<<10) /* INODE_ITEM nlink count error */
+#define NBYTES_ERROR (1<<11) /* INODE_ITEM nbytes count error */
+#define ISIZE_ERROR (1<<12) /* INODE_ITEM size count error */
+#define ORPHAN_ITEM (1<<13) /* INODE_ITEM no reference */
+#define NO_INODE_ITEM (1<<14) /* no inode_item */
+#define LAST_ITEM (1<<15) /* Complete this tree traversal */
+#define ROOT_REF_MISSING (1<<16) /* ROOT_REF not found */
+#define ROOT_REF_MISMATCH (1<<17) /* ROOT_REF found but not match */
+
static inline struct data_backref* to_data_backref(struct extent_backref *back)
{
return container_of(back, struct data_backref, node);
return has_parent ? 0 : 2;
}
-static int process_dir_item(struct btrfs_root *root,
- struct extent_buffer *eb,
+static int process_dir_item(struct extent_buffer *eb,
int slot, struct btrfs_key *key,
struct shared_node *active_node)
{
switch (key.type) {
case BTRFS_DIR_ITEM_KEY:
case BTRFS_DIR_INDEX_KEY:
- ret = process_dir_item(root, eb, i, &key, active_node);
+ ret = process_dir_item(eb, i, &key, active_node);
break;
case BTRFS_INODE_REF_KEY:
ret = process_inode_ref(eb, i, &key, active_node);
return ret;
}
+struct node_refs {
+ u64 bytenr[BTRFS_MAX_LEVEL];
+ u64 refs[BTRFS_MAX_LEVEL];
+ int need_check[BTRFS_MAX_LEVEL];
+};
+
+static int update_nodes_refs(struct btrfs_root *root, u64 bytenr,
+ struct node_refs *nrefs, u64 level);
+static int check_inode_item(struct btrfs_root *root, struct btrfs_path *path,
+ unsigned int ext_ref);
+
+/*
+ * Returns >0 Found error, not fatal, should continue
+ * Returns <0 Fatal error, must exit the whole check
+ * Returns 0 No errors found
+ */
+static int process_one_leaf_v2(struct btrfs_root *root, struct btrfs_path *path,
+ struct node_refs *nrefs, int *level, int ext_ref)
+{
+ struct extent_buffer *cur = path->nodes[0];
+ struct btrfs_key key;
+ u64 cur_bytenr;
+ u32 nritems;
+ u64 first_ino = 0;
+ int root_level = btrfs_header_level(root->node);
+ int i;
+ int ret = 0; /* Final return value */
+ int err = 0; /* Positive error bitmap */
+
+ cur_bytenr = cur->start;
+
+ /* skip to first inode item or the first inode number change */
+ nritems = btrfs_header_nritems(cur);
+ for (i = 0; i < nritems; i++) {
+ btrfs_item_key_to_cpu(cur, &key, i);
+ if (i == 0)
+ first_ino = key.objectid;
+ if (key.type == BTRFS_INODE_ITEM_KEY ||
+ (first_ino && first_ino != key.objectid))
+ break;
+ }
+ if (i == nritems) {
+ path->slots[0] = nritems;
+ return 0;
+ }
+ path->slots[0] = i;
+
+again:
+ err |= check_inode_item(root, path, ext_ref);
+
+ if (err & LAST_ITEM)
+ goto out;
+
+ /* still have inode items in thie leaf */
+ if (cur->start == cur_bytenr)
+ goto again;
+
+ /*
+ * we have switched to another leaf, above nodes may
+ * have changed, here walk down the path, if a node
+ * or leaf is shared, check whether we can skip this
+ * node or leaf.
+ */
+ for (i = root_level; i >= 0; i--) {
+ if (path->nodes[i]->start == nrefs->bytenr[i])
+ continue;
+
+ ret = update_nodes_refs(root,
+ path->nodes[i]->start,
+ nrefs, i);
+ if (ret)
+ goto out;
+
+ if (!nrefs->need_check[i]) {
+ *level += 1;
+ break;
+ }
+ }
+
+ for (i = 0; i < *level; i++) {
+ free_extent_buffer(path->nodes[i]);
+ path->nodes[i] = NULL;
+ }
+out:
+ err &= ~LAST_ITEM;
+ if (err && !ret)
+ ret = err;
+ return ret;
+}
+
static void reada_walk_down(struct btrfs_root *root,
struct extent_buffer *node, int slot)
{
* which makes leaf owner check not so strong, key check should be
* sufficient enough for that case.
*/
-static int check_child_node(struct btrfs_root *root,
- struct extent_buffer *parent, int slot,
+static int check_child_node(struct extent_buffer *parent, int slot,
struct extent_buffer *child)
{
struct btrfs_key parent_key;
return ret;
}
-struct node_refs {
- u64 bytenr[BTRFS_MAX_LEVEL];
- u64 refs[BTRFS_MAX_LEVEL];
-};
+/*
+ * for a tree node or leaf, if it's shared, indeed we don't need to iterate it
+ * in every fs or file tree check. Here we find its all root ids, and only check
+ * it in the fs or file tree which has the smallest root id.
+ */
+static int need_check(struct btrfs_root *root, struct ulist *roots)
+{
+ struct rb_node *node;
+ struct ulist_node *u;
+
+ if (roots->nnodes == 1)
+ return 1;
+
+ node = rb_first(&roots->root);
+ u = rb_entry(node, struct ulist_node, rb_node);
+ /*
+ * current root id is not smallest, we skip it and let it be checked
+ * in the fs or file tree who hash the smallest root id.
+ */
+ if (root->objectid != u->val)
+ return 0;
+
+ return 1;
+}
+
+/*
+ * for a tree node or leaf, we record its reference count, so later if we still
+ * process this node or leaf, don't need to compute its reference count again.
+ */
+static int update_nodes_refs(struct btrfs_root *root, u64 bytenr,
+ struct node_refs *nrefs, u64 level)
+{
+ int check, ret;
+ u64 refs;
+ struct ulist *roots;
+
+ if (nrefs->bytenr[level] != bytenr) {
+ ret = btrfs_lookup_extent_info(NULL, root, bytenr,
+ level, 1, &refs, NULL);
+ if (ret < 0)
+ return ret;
+
+ nrefs->bytenr[level] = bytenr;
+ nrefs->refs[level] = refs;
+ if (refs > 1) {
+ ret = btrfs_find_all_roots(NULL, root->fs_info, bytenr,
+ 0, &roots);
+ if (ret)
+ return -EIO;
+
+ check = need_check(root, roots);
+ ulist_free(roots);
+ nrefs->need_check[level] = check;
+ } else {
+ nrefs->need_check[level] = 1;
+ }
+ }
+
+ return 0;
+}
static int walk_down_tree(struct btrfs_root *root, struct btrfs_path *path,
struct walk_control *wc, int *level,
}
}
- ret = check_child_node(root, cur, path->slots[*level], next);
+ ret = check_child_node(cur, path->slots[*level], next);
if (ret) {
+ free_extent_buffer(next);
err = ret;
goto out;
}
return err;
}
+static int check_inode_item(struct btrfs_root *root, struct btrfs_path *path,
+ unsigned int ext_ref);
+
+/*
+ * Returns >0 Found error, should continue
+ * Returns <0 Fatal error, must exit the whole check
+ * Returns 0 No errors found
+ */
+static int walk_down_tree_v2(struct btrfs_root *root, struct btrfs_path *path,
+ int *level, struct node_refs *nrefs, int ext_ref)
+{
+ enum btrfs_tree_block_status status;
+ u64 bytenr;
+ u64 ptr_gen;
+ struct extent_buffer *next;
+ struct extent_buffer *cur;
+ u32 blocksize;
+ int ret;
+
+ WARN_ON(*level < 0);
+ WARN_ON(*level >= BTRFS_MAX_LEVEL);
+
+ ret = update_nodes_refs(root, path->nodes[*level]->start,
+ nrefs, *level);
+ if (ret < 0)
+ return ret;
+
+ while (*level >= 0) {
+ WARN_ON(*level < 0);
+ WARN_ON(*level >= BTRFS_MAX_LEVEL);
+ cur = path->nodes[*level];
+
+ if (btrfs_header_level(cur) != *level)
+ WARN_ON(1);
+
+ if (path->slots[*level] >= btrfs_header_nritems(cur))
+ break;
+ /* Don't forgot to check leaf/node validation */
+ if (*level == 0) {
+ ret = btrfs_check_leaf(root, NULL, cur);
+ if (ret != BTRFS_TREE_BLOCK_CLEAN) {
+ ret = -EIO;
+ break;
+ }
+ ret = process_one_leaf_v2(root, path, nrefs,
+ level, ext_ref);
+ break;
+ } else {
+ ret = btrfs_check_node(root, NULL, cur);
+ if (ret != BTRFS_TREE_BLOCK_CLEAN) {
+ ret = -EIO;
+ break;
+ }
+ }
+ bytenr = btrfs_node_blockptr(cur, path->slots[*level]);
+ ptr_gen = btrfs_node_ptr_generation(cur, path->slots[*level]);
+ blocksize = root->nodesize;
+
+ ret = update_nodes_refs(root, bytenr, nrefs, *level - 1);
+ if (ret)
+ break;
+ if (!nrefs->need_check[*level - 1]) {
+ path->slots[*level]++;
+ continue;
+ }
+
+ next = btrfs_find_tree_block(root, bytenr, blocksize);
+ if (!next || !btrfs_buffer_uptodate(next, ptr_gen)) {
+ free_extent_buffer(next);
+ reada_walk_down(root, cur, path->slots[*level]);
+ next = read_tree_block(root, bytenr, blocksize,
+ ptr_gen);
+ if (!extent_buffer_uptodate(next)) {
+ struct btrfs_key node_key;
+
+ btrfs_node_key_to_cpu(path->nodes[*level],
+ &node_key,
+ path->slots[*level]);
+ btrfs_add_corrupt_extent_record(root->fs_info,
+ &node_key,
+ path->nodes[*level]->start,
+ root->nodesize, *level);
+ ret = -EIO;
+ break;
+ }
+ }
+
+ ret = check_child_node(cur, path->slots[*level], next);
+ if (ret < 0)
+ break;
+
+ if (btrfs_is_leaf(next))
+ status = btrfs_check_leaf(root, NULL, next);
+ else
+ status = btrfs_check_node(root, NULL, next);
+ if (status != BTRFS_TREE_BLOCK_CLEAN) {
+ free_extent_buffer(next);
+ ret = -EIO;
+ break;
+ }
+
+ *level = *level - 1;
+ free_extent_buffer(path->nodes[*level]);
+ path->nodes[*level] = next;
+ path->slots[*level] = 0;
+ }
+ return ret;
+}
+
static int walk_up_tree(struct btrfs_root *root, struct btrfs_path *path,
struct walk_control *wc, int *level)
{
return 1;
}
+static int walk_up_tree_v2(struct btrfs_root *root, struct btrfs_path *path,
+ int *level)
+{
+ int i;
+ struct extent_buffer *leaf;
+
+ for (i = *level; i < BTRFS_MAX_LEVEL - 1 && path->nodes[i]; i++) {
+ leaf = path->nodes[i];
+ if (path->slots[i] + 1 < btrfs_header_nritems(leaf)) {
+ path->slots[i]++;
+ *level = i;
+ return 0;
+ } else {
+ free_extent_buffer(path->nodes[*level]);
+ path->nodes[*level] = NULL;
+ *level = i + 1;
+ }
+ }
+ return 1;
+}
+
static int check_root_dir(struct inode_record *rec)
{
struct inode_backref *backref;
}
static int delete_dir_index(struct btrfs_root *root,
- struct cache_tree *inode_cache,
- struct inode_record *rec,
struct inode_backref *backref)
{
struct btrfs_trans_handle *trans;
static int create_inode_item(struct btrfs_root *root,
struct inode_record *rec,
- struct inode_backref *backref, int root_dir)
+ int root_dir)
{
struct btrfs_trans_handle *trans;
struct btrfs_inode_item inode_item;
list_for_each_entry_safe(backref, tmp, &rec->backrefs, list) {
if (!delete && rec->ino == root_dirid) {
if (!rec->found_inode_item) {
- ret = create_inode_item(root, rec, backref, 1);
+ ret = create_inode_item(root, rec, 1);
if (ret)
break;
repaired++;
((backref->found_dir_index && !backref->found_inode_ref) ||
(backref->found_dir_index && backref->found_inode_ref &&
(backref->errors & REF_ERR_INDEX_UNMATCH)))) {
- ret = delete_dir_index(root, inode_cache, rec, backref);
+ ret = delete_dir_index(root, backref);
if (ret)
break;
repaired++;
backref->found_dir_item &&
!(backref->errors & REF_ERR_INDEX_UNMATCH) &&
!rec->found_inode_item)) {
- ret = create_inode_item(root, rec, backref, 0);
+ ret = create_inode_item(root, rec, 0);
if (ret)
break;
repaired++;
return ret;
}
+static int get_highest_inode(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root,
+ struct btrfs_path *path,
+ u64 *highest_ino)
+{
+ struct btrfs_key key, found_key;
+ int ret;
+
+ btrfs_init_path(path);
+ key.objectid = BTRFS_LAST_FREE_OBJECTID;
+ key.offset = -1;
+ key.type = BTRFS_INODE_ITEM_KEY;
+ ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
+ if (ret == 1) {
+ btrfs_item_key_to_cpu(path->nodes[0], &found_key,
+ path->slots[0] - 1);
+ *highest_ino = found_key.objectid;
+ ret = 0;
+ }
+ if (*highest_ino >= BTRFS_LAST_FREE_OBJECTID)
+ ret = -EOVERFLOW;
+ btrfs_release_path(path);
+ return ret;
+}
+
static int repair_inode_nlinks(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct btrfs_path *path,
}
if (rec->found_link == 0) {
- lost_found_ino = root->highest_inode;
- if (lost_found_ino >= BTRFS_LAST_FREE_OBJECTID) {
- ret = -EOVERFLOW;
+ ret = get_highest_inode(trans, root, path, &lost_found_ino);
+ if (ret < 0)
goto out;
- }
lost_found_ino++;
ret = btrfs_mkdir(trans, root, dir_name, strlen(dir_name),
BTRFS_FIRST_FREE_OBJECTID, &lost_found_ino,
}
/*
- * We need to record the highest inode number for later 'lost+found'
- * dir creation.
- * We must select an ino not used/referred by any existing inode, or
- * 'lost+found' ino may be a missing ino in a corrupted leaf,
- * this may cause 'lost+found' dir has wrong nlinks.
- */
- cache = last_cache_extent(inode_cache);
- if (cache) {
- node = container_of(cache, struct ptr_node, cache);
- rec = node->data;
- if (rec->ino > root->highest_inode)
- root->highest_inode = rec->ino;
- }
-
- /*
* We need to repair backrefs first because we could change some of the
* errors in the inode recs.
*
path.slots[level]);
/* Remove the ptr */
- ret = btrfs_del_ptr(trans, root, &path, level,
- path.slots[level]);
+ ret = btrfs_del_ptr(root, &path, level, path.slots[level]);
if (ret < 0)
goto out;
/*
task_start(ctx.info);
}
- /*
- * Just in case we made any changes to the extent tree that weren't
- * reflected into the free space cache yet.
- */
- if (repair)
- reset_cached_block_groups(root->fs_info);
- memset(&wc, 0, sizeof(wc));
- cache_tree_init(&wc.shared);
- btrfs_init_path(&path);
+ /*
+ * Just in case we made any changes to the extent tree that weren't
+ * reflected into the free space cache yet.
+ */
+ if (repair)
+ reset_cached_block_groups(root->fs_info);
+ memset(&wc, 0, sizeof(wc));
+ cache_tree_init(&wc.shared);
+ btrfs_init_path(&path);
+
+again:
+ key.offset = 0;
+ key.objectid = 0;
+ key.type = BTRFS_ROOT_ITEM_KEY;
+ ret = btrfs_search_slot(NULL, tree_root, &key, &path, 0, 0);
+ if (ret < 0) {
+ err = 1;
+ goto out;
+ }
+ tree_node = tree_root->node;
+ while (1) {
+ if (tree_node != tree_root->node) {
+ free_root_recs_tree(root_cache);
+ btrfs_release_path(&path);
+ goto again;
+ }
+ leaf = path.nodes[0];
+ if (path.slots[0] >= btrfs_header_nritems(leaf)) {
+ ret = btrfs_next_leaf(tree_root, &path);
+ if (ret) {
+ if (ret < 0)
+ err = 1;
+ break;
+ }
+ leaf = path.nodes[0];
+ }
+ btrfs_item_key_to_cpu(leaf, &key, path.slots[0]);
+ if (key.type == BTRFS_ROOT_ITEM_KEY &&
+ fs_root_objectid(key.objectid)) {
+ if (key.objectid == BTRFS_TREE_RELOC_OBJECTID) {
+ tmp_root = btrfs_read_fs_root_no_cache(
+ root->fs_info, &key);
+ } else {
+ key.offset = (u64)-1;
+ tmp_root = btrfs_read_fs_root(
+ root->fs_info, &key);
+ }
+ if (IS_ERR(tmp_root)) {
+ err = 1;
+ goto next;
+ }
+ ret = check_fs_root(tmp_root, root_cache, &wc);
+ if (ret == -EAGAIN) {
+ free_root_recs_tree(root_cache);
+ btrfs_release_path(&path);
+ goto again;
+ }
+ if (ret)
+ err = 1;
+ if (key.objectid == BTRFS_TREE_RELOC_OBJECTID)
+ btrfs_free_fs_root(tmp_root);
+ } else if (key.type == BTRFS_ROOT_REF_KEY ||
+ key.type == BTRFS_ROOT_BACKREF_KEY) {
+ process_root_ref(leaf, path.slots[0], &key,
+ root_cache);
+ }
+next:
+ path.slots[0]++;
+ }
+out:
+ btrfs_release_path(&path);
+ if (err)
+ free_extent_cache_tree(&wc.shared);
+ if (!cache_tree_empty(&wc.shared))
+ fprintf(stderr, "warning line %d\n", __LINE__);
+
+ task_stop(ctx.info);
+
+ return err;
+}
+
+/*
+ * Find DIR_ITEM/DIR_INDEX for the given key and check it with the specified
+ * INODE_REF/INODE_EXTREF match.
+ *
+ * @root: the root of the fs/file tree
+ * @ref_key: the key of the INODE_REF/INODE_EXTREF
+ * @key: the key of the DIR_ITEM/DIR_INDEX
+ * @index: the index in the INODE_REF/INODE_EXTREF, be used to
+ * distinguish root_dir between normal dir/file
+ * @name: the name in the INODE_REF/INODE_EXTREF
+ * @namelen: the length of name in the INODE_REF/INODE_EXTREF
+ * @mode: the st_mode of INODE_ITEM
+ *
+ * Return 0 if no error occurred.
+ * Return ROOT_DIR_ERROR if found DIR_ITEM/DIR_INDEX for root_dir.
+ * Return DIR_ITEM_MISSING if couldn't find DIR_ITEM/DIR_INDEX for normal
+ * dir/file.
+ * Return DIR_ITEM_MISMATCH if INODE_REF/INODE_EXTREF and DIR_ITEM/DIR_INDEX
+ * not match for normal dir/file.
+ */
+static int find_dir_item(struct btrfs_root *root, struct btrfs_key *ref_key,
+ struct btrfs_key *key, u64 index, char *name,
+ u32 namelen, u32 mode)
+{
+ struct btrfs_path path;
+ struct extent_buffer *node;
+ struct btrfs_dir_item *di;
+ struct btrfs_key location;
+ char namebuf[BTRFS_NAME_LEN] = {0};
+ u32 total;
+ u32 cur = 0;
+ u32 len;
+ u32 name_len;
+ u32 data_len;
+ u8 filetype;
+ int slot;
+ int ret;
+
+ btrfs_init_path(&path);
+ ret = btrfs_search_slot(NULL, root, key, &path, 0, 0);
+ if (ret < 0) {
+ ret = DIR_ITEM_MISSING;
+ goto out;
+ }
+
+ /* Process root dir and goto out*/
+ if (index == 0) {
+ if (ret == 0) {
+ ret = ROOT_DIR_ERROR;
+ error(
+ "root %llu INODE %s[%llu %llu] ROOT_DIR shouldn't have %s",
+ root->objectid,
+ ref_key->type == BTRFS_INODE_REF_KEY ?
+ "REF" : "EXTREF",
+ ref_key->objectid, ref_key->offset,
+ key->type == BTRFS_DIR_ITEM_KEY ?
+ "DIR_ITEM" : "DIR_INDEX");
+ } else {
+ ret = 0;
+ }
+
+ goto out;
+ }
+
+ /* Process normal file/dir */
+ if (ret > 0) {
+ ret = DIR_ITEM_MISSING;
+ error(
+ "root %llu INODE %s[%llu %llu] doesn't have related %s[%llu %llu] namelen %u filename %s filetype %d",
+ root->objectid,
+ ref_key->type == BTRFS_INODE_REF_KEY ? "REF" : "EXTREF",
+ ref_key->objectid, ref_key->offset,
+ key->type == BTRFS_DIR_ITEM_KEY ?
+ "DIR_ITEM" : "DIR_INDEX",
+ key->objectid, key->offset, namelen, name,
+ imode_to_type(mode));
+ goto out;
+ }
+
+ /* Check whether inode_id/filetype/name match */
+ node = path.nodes[0];
+ slot = path.slots[0];
+ di = btrfs_item_ptr(node, slot, struct btrfs_dir_item);
+ total = btrfs_item_size_nr(node, slot);
+ while (cur < total) {
+ ret = DIR_ITEM_MISMATCH;
+ name_len = btrfs_dir_name_len(node, di);
+ data_len = btrfs_dir_data_len(node, di);
+
+ btrfs_dir_item_key_to_cpu(node, di, &location);
+ if (location.objectid != ref_key->objectid ||
+ location.type != BTRFS_INODE_ITEM_KEY ||
+ location.offset != 0)
+ goto next;
+
+ filetype = btrfs_dir_type(node, di);
+ if (imode_to_type(mode) != filetype)
+ goto next;
+
+ if (name_len <= BTRFS_NAME_LEN) {
+ len = name_len;
+ } else {
+ len = BTRFS_NAME_LEN;
+ warning("root %llu %s[%llu %llu] name too long %u, trimmed",
+ root->objectid,
+ key->type == BTRFS_DIR_ITEM_KEY ?
+ "DIR_ITEM" : "DIR_INDEX",
+ key->objectid, key->offset, name_len);
+ }
+ read_extent_buffer(node, namebuf, (unsigned long)(di + 1), len);
+ if (len != namelen || strncmp(namebuf, name, len))
+ goto next;
+
+ ret = 0;
+ goto out;
+next:
+ len = sizeof(*di) + name_len + data_len;
+ di = (struct btrfs_dir_item *)((char *)di + len);
+ cur += len;
+ }
+ if (ret == DIR_ITEM_MISMATCH)
+ error(
+ "root %llu INODE %s[%llu %llu] and %s[%llu %llu] mismatch namelen %u filename %s filetype %d",
+ root->objectid,
+ ref_key->type == BTRFS_INODE_REF_KEY ? "REF" : "EXTREF",
+ ref_key->objectid, ref_key->offset,
+ key->type == BTRFS_DIR_ITEM_KEY ?
+ "DIR_ITEM" : "DIR_INDEX",
+ key->objectid, key->offset, namelen, name,
+ imode_to_type(mode));
+out:
+ btrfs_release_path(&path);
+ return ret;
+}
+
+/*
+ * Traverse the given INODE_REF and call find_dir_item() to find related
+ * DIR_ITEM/DIR_INDEX.
+ *
+ * @root: the root of the fs/file tree
+ * @ref_key: the key of the INODE_REF
+ * @refs: the count of INODE_REF
+ * @mode: the st_mode of INODE_ITEM
+ *
+ * Return 0 if no error occurred.
+ */
+static int check_inode_ref(struct btrfs_root *root, struct btrfs_key *ref_key,
+ struct extent_buffer *node, int slot, u64 *refs,
+ int mode)
+{
+ struct btrfs_key key;
+ struct btrfs_inode_ref *ref;
+ char namebuf[BTRFS_NAME_LEN] = {0};
+ u32 total;
+ u32 cur = 0;
+ u32 len;
+ u32 name_len;
+ u64 index;
+ int ret, err = 0;
+
+ ref = btrfs_item_ptr(node, slot, struct btrfs_inode_ref);
+ total = btrfs_item_size_nr(node, slot);
+
+next:
+ /* Update inode ref count */
+ (*refs)++;
+
+ index = btrfs_inode_ref_index(node, ref);
+ name_len = btrfs_inode_ref_name_len(node, ref);
+ if (name_len <= BTRFS_NAME_LEN) {
+ len = name_len;
+ } else {
+ len = BTRFS_NAME_LEN;
+ warning("root %llu INODE_REF[%llu %llu] name too long",
+ root->objectid, ref_key->objectid, ref_key->offset);
+ }
+
+ read_extent_buffer(node, namebuf, (unsigned long)(ref + 1), len);
+
+ /* Check root dir ref name */
+ if (index == 0 && strncmp(namebuf, "..", name_len)) {
+ error("root %llu INODE_REF[%llu %llu] ROOT_DIR name shouldn't be %s",
+ root->objectid, ref_key->objectid, ref_key->offset,
+ namebuf);
+ err |= ROOT_DIR_ERROR;
+ }
+
+ /* Find related DIR_INDEX */
+ key.objectid = ref_key->offset;
+ key.type = BTRFS_DIR_INDEX_KEY;
+ key.offset = index;
+ ret = find_dir_item(root, ref_key, &key, index, namebuf, len, mode);
+ err |= ret;
+
+ /* Find related dir_item */
+ key.objectid = ref_key->offset;
+ key.type = BTRFS_DIR_ITEM_KEY;
+ key.offset = btrfs_name_hash(namebuf, len);
+ ret = find_dir_item(root, ref_key, &key, index, namebuf, len, mode);
+ err |= ret;
+
+ len = sizeof(*ref) + name_len;
+ ref = (struct btrfs_inode_ref *)((char *)ref + len);
+ cur += len;
+ if (cur < total)
+ goto next;
+
+ return err;
+}
+
+/*
+ * Traverse the given INODE_EXTREF and call find_dir_item() to find related
+ * DIR_ITEM/DIR_INDEX.
+ *
+ * @root: the root of the fs/file tree
+ * @ref_key: the key of the INODE_EXTREF
+ * @refs: the count of INODE_EXTREF
+ * @mode: the st_mode of INODE_ITEM
+ *
+ * Return 0 if no error occurred.
+ */
+static int check_inode_extref(struct btrfs_root *root,
+ struct btrfs_key *ref_key,
+ struct extent_buffer *node, int slot, u64 *refs,
+ int mode)
+{
+ struct btrfs_key key;
+ struct btrfs_inode_extref *extref;
+ char namebuf[BTRFS_NAME_LEN] = {0};
+ u32 total;
+ u32 cur = 0;
+ u32 len;
+ u32 name_len;
+ u64 index;
+ u64 parent;
+ int ret;
+ int err = 0;
+
+ extref = btrfs_item_ptr(node, slot, struct btrfs_inode_extref);
+ total = btrfs_item_size_nr(node, slot);
+
+next:
+ /* update inode ref count */
+ (*refs)++;
+ name_len = btrfs_inode_extref_name_len(node, extref);
+ index = btrfs_inode_extref_index(node, extref);
+ parent = btrfs_inode_extref_parent(node, extref);
+ if (name_len <= BTRFS_NAME_LEN) {
+ len = name_len;
+ } else {
+ len = BTRFS_NAME_LEN;
+ warning("root %llu INODE_EXTREF[%llu %llu] name too long",
+ root->objectid, ref_key->objectid, ref_key->offset);
+ }
+ read_extent_buffer(node, namebuf, (unsigned long)(extref + 1), len);
+
+ /* Check root dir ref name */
+ if (index == 0 && strncmp(namebuf, "..", name_len)) {
+ error("root %llu INODE_EXTREF[%llu %llu] ROOT_DIR name shouldn't be %s",
+ root->objectid, ref_key->objectid, ref_key->offset,
+ namebuf);
+ err |= ROOT_DIR_ERROR;
+ }
+
+ /* find related dir_index */
+ key.objectid = parent;
+ key.type = BTRFS_DIR_INDEX_KEY;
+ key.offset = index;
+ ret = find_dir_item(root, ref_key, &key, index, namebuf, len, mode);
+ err |= ret;
+
+ /* find related dir_item */
+ key.objectid = parent;
+ key.type = BTRFS_DIR_ITEM_KEY;
+ key.offset = btrfs_name_hash(namebuf, len);
+ ret = find_dir_item(root, ref_key, &key, index, namebuf, len, mode);
+ err |= ret;
+
+ len = sizeof(*extref) + name_len;
+ extref = (struct btrfs_inode_extref *)((char *)extref + len);
+ cur += len;
+
+ if (cur < total)
+ goto next;
+
+ return err;
+}
+
+/*
+ * Find INODE_REF/INODE_EXTREF for the given key and check it with the specified
+ * DIR_ITEM/DIR_INDEX match.
+ *
+ * @root: the root of the fs/file tree
+ * @key: the key of the INODE_REF/INODE_EXTREF
+ * @name: the name in the INODE_REF/INODE_EXTREF
+ * @namelen: the length of name in the INODE_REF/INODE_EXTREF
+ * @index: the index in the INODE_REF/INODE_EXTREF, for DIR_ITEM set index
+ * to (u64)-1
+ * @ext_ref: the EXTENDED_IREF feature
+ *
+ * Return 0 if no error occurred.
+ * Return >0 for error bitmap
+ */
+static int find_inode_ref(struct btrfs_root *root, struct btrfs_key *key,
+ char *name, int namelen, u64 index,
+ unsigned int ext_ref)
+{
+ struct btrfs_path path;
+ struct btrfs_inode_ref *ref;
+ struct btrfs_inode_extref *extref;
+ struct extent_buffer *node;
+ char ref_namebuf[BTRFS_NAME_LEN] = {0};
+ u32 total;
+ u32 cur = 0;
+ u32 len;
+ u32 ref_namelen;
+ u64 ref_index;
+ u64 parent;
+ u64 dir_id;
+ int slot;
+ int ret;
+
+ btrfs_init_path(&path);
+ ret = btrfs_search_slot(NULL, root, key, &path, 0, 0);
+ if (ret) {
+ ret = INODE_REF_MISSING;
+ goto extref;
+ }
+
+ node = path.nodes[0];
+ slot = path.slots[0];
+
+ ref = btrfs_item_ptr(node, slot, struct btrfs_inode_ref);
+ total = btrfs_item_size_nr(node, slot);
+
+ /* Iterate all entry of INODE_REF */
+ while (cur < total) {
+ ret = INODE_REF_MISSING;
+
+ ref_namelen = btrfs_inode_ref_name_len(node, ref);
+ ref_index = btrfs_inode_ref_index(node, ref);
+ if (index != (u64)-1 && index != ref_index)
+ goto next_ref;
+
+ if (ref_namelen <= BTRFS_NAME_LEN) {
+ len = ref_namelen;
+ } else {
+ len = BTRFS_NAME_LEN;
+ warning("root %llu INODE %s[%llu %llu] name too long",
+ root->objectid,
+ key->type == BTRFS_INODE_REF_KEY ?
+ "REF" : "EXTREF",
+ key->objectid, key->offset);
+ }
+ read_extent_buffer(node, ref_namebuf, (unsigned long)(ref + 1),
+ len);
+
+ if (len != namelen || strncmp(ref_namebuf, name, len))
+ goto next_ref;
+
+ ret = 0;
+ goto out;
+next_ref:
+ len = sizeof(*ref) + ref_namelen;
+ ref = (struct btrfs_inode_ref *)((char *)ref + len);
+ cur += len;
+ }
+
+extref:
+ /* Skip if not support EXTENDED_IREF feature */
+ if (!ext_ref)
+ goto out;
+
+ btrfs_release_path(&path);
+ btrfs_init_path(&path);
+
+ dir_id = key->offset;
+ key->type = BTRFS_INODE_EXTREF_KEY;
+ key->offset = btrfs_extref_hash(dir_id, name, namelen);
+
+ ret = btrfs_search_slot(NULL, root, key, &path, 0, 0);
+ if (ret) {
+ ret = INODE_REF_MISSING;
+ goto out;
+ }
+
+ node = path.nodes[0];
+ slot = path.slots[0];
+
+ extref = btrfs_item_ptr(node, slot, struct btrfs_inode_extref);
+ cur = 0;
+ total = btrfs_item_size_nr(node, slot);
+
+ /* Iterate all entry of INODE_EXTREF */
+ while (cur < total) {
+ ret = INODE_REF_MISSING;
+
+ ref_namelen = btrfs_inode_extref_name_len(node, extref);
+ ref_index = btrfs_inode_extref_index(node, extref);
+ parent = btrfs_inode_extref_parent(node, extref);
+ if (index != (u64)-1 && index != ref_index)
+ goto next_extref;
+
+ if (parent != dir_id)
+ goto next_extref;
+
+ if (ref_namelen <= BTRFS_NAME_LEN) {
+ len = ref_namelen;
+ } else {
+ len = BTRFS_NAME_LEN;
+ warning("root %llu INODE %s[%llu %llu] name too long",
+ root->objectid,
+ key->type == BTRFS_INODE_REF_KEY ?
+ "REF" : "EXTREF",
+ key->objectid, key->offset);
+ }
+ read_extent_buffer(node, ref_namebuf,
+ (unsigned long)(extref + 1), len);
+
+ if (len != namelen || strncmp(ref_namebuf, name, len))
+ goto next_extref;
+
+ ret = 0;
+ goto out;
+
+next_extref:
+ len = sizeof(*extref) + ref_namelen;
+ extref = (struct btrfs_inode_extref *)((char *)extref + len);
+ cur += len;
+
+ }
+out:
+ btrfs_release_path(&path);
+ return ret;
+}
+
+/*
+ * Traverse the given DIR_ITEM/DIR_INDEX and check related INODE_ITEM and
+ * call find_inode_ref() to check related INODE_REF/INODE_EXTREF.
+ *
+ * @root: the root of the fs/file tree
+ * @key: the key of the INODE_REF/INODE_EXTREF
+ * @size: the st_size of the INODE_ITEM
+ * @ext_ref: the EXTENDED_IREF feature
+ *
+ * Return 0 if no error occurred.
+ */
+static int check_dir_item(struct btrfs_root *root, struct btrfs_key *key,
+ struct extent_buffer *node, int slot, u64 *size,
+ unsigned int ext_ref)
+{
+ struct btrfs_dir_item *di;
+ struct btrfs_inode_item *ii;
+ struct btrfs_path path;
+ struct btrfs_key location;
+ char namebuf[BTRFS_NAME_LEN] = {0};
+ u32 total;
+ u32 cur = 0;
+ u32 len;
+ u32 name_len;
+ u32 data_len;
+ u8 filetype;
+ u32 mode;
+ u64 index;
+ int ret;
+ int err = 0;
+
+ /*
+ * For DIR_ITEM set index to (u64)-1, so that find_inode_ref
+ * ignore index check.
+ */
+ index = (key->type == BTRFS_DIR_INDEX_KEY) ? key->offset : (u64)-1;
+
+ di = btrfs_item_ptr(node, slot, struct btrfs_dir_item);
+ total = btrfs_item_size_nr(node, slot);
+
+ while (cur < total) {
+ data_len = btrfs_dir_data_len(node, di);
+ if (data_len)
+ error("root %llu %s[%llu %llu] data_len shouldn't be %u",
+ root->objectid, key->type == BTRFS_DIR_ITEM_KEY ?
+ "DIR_ITEM" : "DIR_INDEX",
+ key->objectid, key->offset, data_len);
+
+ name_len = btrfs_dir_name_len(node, di);
+ if (name_len <= BTRFS_NAME_LEN) {
+ len = name_len;
+ } else {
+ len = BTRFS_NAME_LEN;
+ warning("root %llu %s[%llu %llu] name too long",
+ root->objectid,
+ key->type == BTRFS_DIR_ITEM_KEY ?
+ "DIR_ITEM" : "DIR_INDEX",
+ key->objectid, key->offset);
+ }
+ (*size) += name_len;
+
+ read_extent_buffer(node, namebuf, (unsigned long)(di + 1), len);
+ filetype = btrfs_dir_type(node, di);
+
+ btrfs_init_path(&path);
+ btrfs_dir_item_key_to_cpu(node, di, &location);
+
+ /* Ignore related ROOT_ITEM check */
+ if (location.type == BTRFS_ROOT_ITEM_KEY)
+ goto next;
+
+ /* Check relative INODE_ITEM(existence/filetype) */
+ ret = btrfs_search_slot(NULL, root, &location, &path, 0, 0);
+ if (ret) {
+ err |= INODE_ITEM_MISSING;
+ error("root %llu %s[%llu %llu] couldn't find relative INODE_ITEM[%llu] namelen %u filename %s filetype %x",
+ root->objectid, key->type == BTRFS_DIR_ITEM_KEY ?
+ "DIR_ITEM" : "DIR_INDEX", key->objectid,
+ key->offset, location.objectid, name_len,
+ namebuf, filetype);
+ goto next;
+ }
+
+ ii = btrfs_item_ptr(path.nodes[0], path.slots[0],
+ struct btrfs_inode_item);
+ mode = btrfs_inode_mode(path.nodes[0], ii);
+
+ if (imode_to_type(mode) != filetype) {
+ err |= INODE_ITEM_MISMATCH;
+ error("root %llu %s[%llu %llu] relative INODE_ITEM filetype mismatch namelen %u filename %s filetype %d",
+ root->objectid, key->type == BTRFS_DIR_ITEM_KEY ?
+ "DIR_ITEM" : "DIR_INDEX", key->objectid,
+ key->offset, name_len, namebuf, filetype);
+ }
+
+ /* Check relative INODE_REF/INODE_EXTREF */
+ location.type = BTRFS_INODE_REF_KEY;
+ location.offset = key->objectid;
+ ret = find_inode_ref(root, &location, namebuf, len,
+ index, ext_ref);
+ err |= ret;
+ if (ret & INODE_REF_MISSING)
+ error("root %llu %s[%llu %llu] relative INODE_REF missing namelen %u filename %s filetype %d",
+ root->objectid, key->type == BTRFS_DIR_ITEM_KEY ?
+ "DIR_ITEM" : "DIR_INDEX", key->objectid,
+ key->offset, name_len, namebuf, filetype);
+
+next:
+ btrfs_release_path(&path);
+ len = sizeof(*di) + name_len + data_len;
+ di = (struct btrfs_dir_item *)((char *)di + len);
+ cur += len;
+
+ if (key->type == BTRFS_DIR_INDEX_KEY && cur < total) {
+ error("root %llu DIR_INDEX[%llu %llu] should contain only one entry",
+ root->objectid, key->objectid, key->offset);
+ break;
+ }
+ }
+
+ return err;
+}
+
+/*
+ * Check file extent datasum/hole, update the size of the file extents,
+ * check and update the last offset of the file extent.
+ *
+ * @root: the root of fs/file tree.
+ * @fkey: the key of the file extent.
+ * @nodatasum: INODE_NODATASUM feature.
+ * @size: the sum of all EXTENT_DATA items size for this inode.
+ * @end: the offset of the last extent.
+ *
+ * Return 0 if no error occurred.
+ */
+static int check_file_extent(struct btrfs_root *root, struct btrfs_key *fkey,
+ struct extent_buffer *node, int slot,
+ unsigned int nodatasum, u64 *size, u64 *end)
+{
+ struct btrfs_file_extent_item *fi;
+ u64 disk_bytenr;
+ u64 disk_num_bytes;
+ u64 extent_num_bytes;
+ u64 extent_offset;
+ u64 csum_found; /* In byte size, sectorsize aligned */
+ u64 search_start; /* Logical range start we search for csum */
+ u64 search_len; /* Logical range len we search for csum */
+ unsigned int extent_type;
+ unsigned int is_hole;
+ int compressed = 0;
+ int ret;
+ int err = 0;
+
+ fi = btrfs_item_ptr(node, slot, struct btrfs_file_extent_item);
+
+ /* Check inline extent */
+ extent_type = btrfs_file_extent_type(node, fi);
+ if (extent_type == BTRFS_FILE_EXTENT_INLINE) {
+ struct btrfs_item *e = btrfs_item_nr(slot);
+ u32 item_inline_len;
+
+ item_inline_len = btrfs_file_extent_inline_item_len(node, e);
+ extent_num_bytes = btrfs_file_extent_inline_len(node, slot, fi);
+ compressed = btrfs_file_extent_compression(node, fi);
+ if (extent_num_bytes == 0) {
+ error(
+ "root %llu EXTENT_DATA[%llu %llu] has empty inline extent",
+ root->objectid, fkey->objectid, fkey->offset);
+ err |= FILE_EXTENT_ERROR;
+ }
+ if (!compressed && extent_num_bytes != item_inline_len) {
+ error(
+ "root %llu EXTENT_DATA[%llu %llu] wrong inline size, have: %llu, expected: %u",
+ root->objectid, fkey->objectid, fkey->offset,
+ extent_num_bytes, item_inline_len);
+ err |= FILE_EXTENT_ERROR;
+ }
+ *size += extent_num_bytes;
+ return err;
+ }
+
+ /* Check extent type */
+ if (extent_type != BTRFS_FILE_EXTENT_REG &&
+ extent_type != BTRFS_FILE_EXTENT_PREALLOC) {
+ err |= FILE_EXTENT_ERROR;
+ error("root %llu EXTENT_DATA[%llu %llu] type bad",
+ root->objectid, fkey->objectid, fkey->offset);
+ return err;
+ }
+
+ /* Check REG_EXTENT/PREALLOC_EXTENT */
+ disk_bytenr = btrfs_file_extent_disk_bytenr(node, fi);
+ disk_num_bytes = btrfs_file_extent_disk_num_bytes(node, fi);
+ extent_num_bytes = btrfs_file_extent_num_bytes(node, fi);
+ extent_offset = btrfs_file_extent_offset(node, fi);
+ compressed = btrfs_file_extent_compression(node, fi);
+ is_hole = (disk_bytenr == 0) && (disk_num_bytes == 0);
+
+ /*
+ * Check EXTENT_DATA csum
+ *
+ * For plain (uncompressed) extent, we should only check the range
+ * we're referring to, as it's possible that part of prealloc extent
+ * has been written, and has csum:
+ *
+ * |<--- Original large preallocated extent A ---->|
+ * |<- Prealloc File Extent ->|<- Regular Extent ->|
+ * No csum Has csum
+ *
+ * For compressed extent, we should check the whole range.
+ */
+ if (!compressed) {
+ search_start = disk_bytenr + extent_offset;
+ search_len = extent_num_bytes;
+ } else {
+ search_start = disk_bytenr;
+ search_len = disk_num_bytes;
+ }
+ ret = count_csum_range(root, search_start, search_len, &csum_found);
+ if (csum_found > 0 && nodatasum) {
+ err |= ODD_CSUM_ITEM;
+ error("root %llu EXTENT_DATA[%llu %llu] nodatasum shouldn't have datasum",
+ root->objectid, fkey->objectid, fkey->offset);
+ } else if (extent_type == BTRFS_FILE_EXTENT_REG && !nodatasum &&
+ !is_hole && (ret < 0 || csum_found < search_len)) {
+ err |= CSUM_ITEM_MISSING;
+ error("root %llu EXTENT_DATA[%llu %llu] csum missing, have: %llu, expected: %llu",
+ root->objectid, fkey->objectid, fkey->offset,
+ csum_found, search_len);
+ } else if (extent_type == BTRFS_FILE_EXTENT_PREALLOC && csum_found > 0) {
+ err |= ODD_CSUM_ITEM;
+ error("root %llu EXTENT_DATA[%llu %llu] prealloc shouldn't have csum, but has: %llu",
+ root->objectid, fkey->objectid, fkey->offset, csum_found);
+ }
+
+ /* Check EXTENT_DATA hole */
+ if (no_holes && is_hole) {
+ err |= FILE_EXTENT_ERROR;
+ error("root %llu EXTENT_DATA[%llu %llu] shouldn't be hole",
+ root->objectid, fkey->objectid, fkey->offset);
+ } else if (!no_holes && *end != fkey->offset) {
+ err |= FILE_EXTENT_ERROR;
+ error("root %llu EXTENT_DATA[%llu %llu] interrupt",
+ root->objectid, fkey->objectid, fkey->offset);
+ }
+
+ *end += extent_num_bytes;
+ if (!is_hole)
+ *size += extent_num_bytes;
+
+ return err;
+}
+
+/*
+ * Check INODE_ITEM and related ITEMs (the same inode number)
+ * 1. check link count
+ * 2. check inode ref/extref
+ * 3. check dir item/index
+ *
+ * @ext_ref: the EXTENDED_IREF feature
+ *
+ * Return 0 if no error occurred.
+ * Return >0 for error or hit the traversal is done(by error bitmap)
+ */
+static int check_inode_item(struct btrfs_root *root, struct btrfs_path *path,
+ unsigned int ext_ref)
+{
+ struct extent_buffer *node;
+ struct btrfs_inode_item *ii;
+ struct btrfs_key key;
+ u64 inode_id;
+ u32 mode;
+ u64 nlink;
+ u64 nbytes;
+ u64 isize;
+ u64 size = 0;
+ u64 refs = 0;
+ u64 extent_end = 0;
+ u64 extent_size = 0;
+ unsigned int dir;
+ unsigned int nodatasum;
+ int slot;
+ int ret;
+ int err = 0;
+
+ node = path->nodes[0];
+ slot = path->slots[0];
+
+ btrfs_item_key_to_cpu(node, &key, slot);
+ inode_id = key.objectid;
+
+ if (inode_id == BTRFS_ORPHAN_OBJECTID) {
+ ret = btrfs_next_item(root, path);
+ if (ret > 0)
+ err |= LAST_ITEM;
+ return err;
+ }
+
+ ii = btrfs_item_ptr(node, slot, struct btrfs_inode_item);
+ isize = btrfs_inode_size(node, ii);
+ nbytes = btrfs_inode_nbytes(node, ii);
+ mode = btrfs_inode_mode(node, ii);
+ dir = imode_to_type(mode) == BTRFS_FT_DIR;
+ nlink = btrfs_inode_nlink(node, ii);
+ nodatasum = btrfs_inode_flags(node, ii) & BTRFS_INODE_NODATASUM;
+
+ while (1) {
+ ret = btrfs_next_item(root, path);
+ if (ret < 0) {
+ /* out will fill 'err' rusing current statistics */
+ goto out;
+ } else if (ret > 0) {
+ err |= LAST_ITEM;
+ goto out;
+ }
+
+ node = path->nodes[0];
+ slot = path->slots[0];
+ btrfs_item_key_to_cpu(node, &key, slot);
+ if (key.objectid != inode_id)
+ goto out;
+
+ switch (key.type) {
+ case BTRFS_INODE_REF_KEY:
+ ret = check_inode_ref(root, &key, node, slot, &refs,
+ mode);
+ err |= ret;
+ break;
+ case BTRFS_INODE_EXTREF_KEY:
+ if (key.type == BTRFS_INODE_EXTREF_KEY && !ext_ref)
+ warning("root %llu EXTREF[%llu %llu] isn't supported",
+ root->objectid, key.objectid,
+ key.offset);
+ ret = check_inode_extref(root, &key, node, slot, &refs,
+ mode);
+ err |= ret;
+ break;
+ case BTRFS_DIR_ITEM_KEY:
+ case BTRFS_DIR_INDEX_KEY:
+ if (!dir) {
+ warning("root %llu INODE[%llu] mode %u shouldn't have DIR_INDEX[%llu %llu]",
+ root->objectid, inode_id,
+ imode_to_type(mode), key.objectid,
+ key.offset);
+ }
+ ret = check_dir_item(root, &key, node, slot, &size,
+ ext_ref);
+ err |= ret;
+ break;
+ case BTRFS_EXTENT_DATA_KEY:
+ if (dir) {
+ warning("root %llu DIR INODE[%llu] shouldn't EXTENT_DATA[%llu %llu]",
+ root->objectid, inode_id, key.objectid,
+ key.offset);
+ }
+ ret = check_file_extent(root, &key, node, slot,
+ nodatasum, &extent_size,
+ &extent_end);
+ err |= ret;
+ break;
+ case BTRFS_XATTR_ITEM_KEY:
+ break;
+ default:
+ error("ITEM[%llu %u %llu] UNKNOWN TYPE",
+ key.objectid, key.type, key.offset);
+ }
+ }
+
+out:
+ /* verify INODE_ITEM nlink/isize/nbytes */
+ if (dir) {
+ if (nlink != 1) {
+ err |= LINK_COUNT_ERROR;
+ error("root %llu DIR INODE[%llu] shouldn't have more than one link(%llu)",
+ root->objectid, inode_id, nlink);
+ }
+
+ /*
+ * Just a warning, as dir inode nbytes is just an
+ * instructive value.
+ */
+ if (!IS_ALIGNED(nbytes, root->nodesize)) {
+ warning("root %llu DIR INODE[%llu] nbytes should be aligned to %u",
+ root->objectid, inode_id, root->nodesize);
+ }
+
+ if (isize != size) {
+ err |= ISIZE_ERROR;
+ error("root %llu DIR INODE [%llu] size(%llu) not equal to %llu",
+ root->objectid, inode_id, isize, size);
+ }
+ } else {
+ if (nlink != refs) {
+ err |= LINK_COUNT_ERROR;
+ error("root %llu INODE[%llu] nlink(%llu) not equal to inode_refs(%llu)",
+ root->objectid, inode_id, nlink, refs);
+ } else if (!nlink) {
+ err |= ORPHAN_ITEM;
+ }
+
+ if (!nbytes && !no_holes && extent_end < isize) {
+ err |= NBYTES_ERROR;
+ error("root %llu INODE[%llu] size (%llu) should have a file extent hole",
+ root->objectid, inode_id, isize);
+ }
+
+ if (nbytes != extent_size) {
+ err |= NBYTES_ERROR;
+ error("root %llu INODE[%llu] nbytes(%llu) not equal to extent_size(%llu)",
+ root->objectid, inode_id, nbytes, extent_size);
+ }
+ }
+
+ return err;
+}
+
+static int check_fs_first_inode(struct btrfs_root *root, unsigned int ext_ref)
+{
+ struct btrfs_path path;
+ struct btrfs_key key;
+ int err = 0;
+ int ret;
+
+ key.objectid = BTRFS_FIRST_FREE_OBJECTID;
+ key.type = BTRFS_INODE_ITEM_KEY;
+ key.offset = 0;
+
+ /* For root being dropped, we don't need to check first inode */
+ if (btrfs_root_refs(&root->root_item) == 0 &&
+ btrfs_disk_key_objectid(&root->root_item.drop_progress) >=
+ key.objectid)
+ return 0;
+
+ btrfs_init_path(&path);
+
+ ret = btrfs_search_slot(NULL, root, &key, &path, 0, 0);
+ if (ret < 0)
+ goto out;
+ if (ret > 0) {
+ ret = 0;
+ err |= INODE_ITEM_MISSING;
+ error("first inode item of root %llu is missing",
+ root->objectid);
+ }
+
+ err |= check_inode_item(root, &path, ext_ref);
+ err &= ~LAST_ITEM;
+ if (err && !ret)
+ ret = -EIO;
+out:
+ btrfs_release_path(&path);
+ return ret;
+}
+
+/*
+ * Iterate all item on the tree and call check_inode_item() to check.
+ *
+ * @root: the root of the tree to be checked.
+ * @ext_ref: the EXTENDED_IREF feature
+ *
+ * Return 0 if no error found.
+ * Return <0 for error.
+ */
+static int check_fs_root_v2(struct btrfs_root *root, unsigned int ext_ref)
+{
+ struct btrfs_path path;
+ struct node_refs nrefs;
+ struct btrfs_root_item *root_item = &root->root_item;
+ int ret;
+ int level;
+ int err = 0;
+
+ /*
+ * We need to manually check the first inode item(256)
+ * As the following traversal function will only start from
+ * the first inode item in the leaf, if inode item(256) is missing
+ * we will just skip it forever.
+ */
+ ret = check_fs_first_inode(root, ext_ref);
+ if (ret < 0)
+ return ret;
+
+ memset(&nrefs, 0, sizeof(nrefs));
+ level = btrfs_header_level(root->node);
+ btrfs_init_path(&path);
+
+ if (btrfs_root_refs(root_item) > 0 ||
+ btrfs_disk_key_objectid(&root_item->drop_progress) == 0) {
+ path.nodes[level] = root->node;
+ path.slots[level] = 0;
+ extent_buffer_get(root->node);
+ } else {
+ struct btrfs_key key;
+
+ btrfs_disk_key_to_cpu(&key, &root_item->drop_progress);
+ level = root_item->drop_level;
+ path.lowest_level = level;
+ ret = btrfs_search_slot(NULL, root, &key, &path, 0, 0);
+ if (ret < 0)
+ goto out;
+ ret = 0;
+ }
+
+ while (1) {
+ ret = walk_down_tree_v2(root, &path, &level, &nrefs, ext_ref);
+ err |= !!ret;
+
+ /* if ret is negative, walk shall stop */
+ if (ret < 0) {
+ ret = err;
+ break;
+ }
+
+ ret = walk_up_tree_v2(root, &path, &level);
+ if (ret != 0) {
+ /* Normal exit, reset ret to err */
+ ret = err;
+ break;
+ }
+ }
+
+out:
+ btrfs_release_path(&path);
+ return ret;
+}
+
+/*
+ * Find the relative ref for root_ref and root_backref.
+ *
+ * @root: the root of the root tree.
+ * @ref_key: the key of the root ref.
+ *
+ * Return 0 if no error occurred.
+ */
+static int check_root_ref(struct btrfs_root *root, struct btrfs_key *ref_key,
+ struct extent_buffer *node, int slot)
+{
+ struct btrfs_path path;
+ struct btrfs_key key;
+ struct btrfs_root_ref *ref;
+ struct btrfs_root_ref *backref;
+ char ref_name[BTRFS_NAME_LEN] = {0};
+ char backref_name[BTRFS_NAME_LEN] = {0};
+ u64 ref_dirid;
+ u64 ref_seq;
+ u32 ref_namelen;
+ u64 backref_dirid;
+ u64 backref_seq;
+ u32 backref_namelen;
+ u32 len;
+ int ret;
+ int err = 0;
+
+ ref = btrfs_item_ptr(node, slot, struct btrfs_root_ref);
+ ref_dirid = btrfs_root_ref_dirid(node, ref);
+ ref_seq = btrfs_root_ref_sequence(node, ref);
+ ref_namelen = btrfs_root_ref_name_len(node, ref);
+
+ if (ref_namelen <= BTRFS_NAME_LEN) {
+ len = ref_namelen;
+ } else {
+ len = BTRFS_NAME_LEN;
+ warning("%s[%llu %llu] ref_name too long",
+ ref_key->type == BTRFS_ROOT_REF_KEY ?
+ "ROOT_REF" : "ROOT_BACKREF", ref_key->objectid,
+ ref_key->offset);
+ }
+ read_extent_buffer(node, ref_name, (unsigned long)(ref + 1), len);
+
+ /* Find relative root_ref */
+ key.objectid = ref_key->offset;
+ key.type = BTRFS_ROOT_BACKREF_KEY + BTRFS_ROOT_REF_KEY - ref_key->type;
+ key.offset = ref_key->objectid;
+
+ btrfs_init_path(&path);
+ ret = btrfs_search_slot(NULL, root, &key, &path, 0, 0);
+ if (ret) {
+ err |= ROOT_REF_MISSING;
+ error("%s[%llu %llu] couldn't find relative ref",
+ ref_key->type == BTRFS_ROOT_REF_KEY ?
+ "ROOT_REF" : "ROOT_BACKREF",
+ ref_key->objectid, ref_key->offset);
+ goto out;
+ }
+
+ backref = btrfs_item_ptr(path.nodes[0], path.slots[0],
+ struct btrfs_root_ref);
+ backref_dirid = btrfs_root_ref_dirid(path.nodes[0], backref);
+ backref_seq = btrfs_root_ref_sequence(path.nodes[0], backref);
+ backref_namelen = btrfs_root_ref_name_len(path.nodes[0], backref);
+
+ if (backref_namelen <= BTRFS_NAME_LEN) {
+ len = backref_namelen;
+ } else {
+ len = BTRFS_NAME_LEN;
+ warning("%s[%llu %llu] ref_name too long",
+ key.type == BTRFS_ROOT_REF_KEY ?
+ "ROOT_REF" : "ROOT_BACKREF",
+ key.objectid, key.offset);
+ }
+ read_extent_buffer(path.nodes[0], backref_name,
+ (unsigned long)(backref + 1), len);
+
+ if (ref_dirid != backref_dirid || ref_seq != backref_seq ||
+ ref_namelen != backref_namelen ||
+ strncmp(ref_name, backref_name, len)) {
+ err |= ROOT_REF_MISMATCH;
+ error("%s[%llu %llu] mismatch relative ref",
+ ref_key->type == BTRFS_ROOT_REF_KEY ?
+ "ROOT_REF" : "ROOT_BACKREF",
+ ref_key->objectid, ref_key->offset);
+ }
+out:
+ btrfs_release_path(&path);
+ return err;
+}
+
+/*
+ * Check all fs/file tree in low_memory mode.
+ *
+ * 1. for fs tree root item, call check_fs_root_v2()
+ * 2. for fs tree root ref/backref, call check_root_ref()
+ *
+ * Return 0 if no error occurred.
+ */
+static int check_fs_roots_v2(struct btrfs_fs_info *fs_info)
+{
+ struct btrfs_root *tree_root = fs_info->tree_root;
+ struct btrfs_root *cur_root = NULL;
+ struct btrfs_path path;
+ struct btrfs_key key;
+ struct extent_buffer *node;
+ unsigned int ext_ref;
+ int slot;
+ int ret;
+ int err = 0;
+
+ ext_ref = btrfs_fs_incompat(fs_info, EXTENDED_IREF);
-again:
+ btrfs_init_path(&path);
+ key.objectid = BTRFS_FS_TREE_OBJECTID;
key.offset = 0;
- key.objectid = 0;
key.type = BTRFS_ROOT_ITEM_KEY;
+
ret = btrfs_search_slot(NULL, tree_root, &key, &path, 0, 0);
if (ret < 0) {
- err = 1;
+ err = ret;
+ goto out;
+ } else if (ret > 0) {
+ err = -ENOENT;
goto out;
}
- tree_node = tree_root->node;
+
while (1) {
- if (tree_node != tree_root->node) {
- free_root_recs_tree(root_cache);
- btrfs_release_path(&path);
- goto again;
- }
- leaf = path.nodes[0];
- if (path.slots[0] >= btrfs_header_nritems(leaf)) {
- ret = btrfs_next_leaf(tree_root, &path);
- if (ret) {
- if (ret < 0)
- err = 1;
- break;
- }
- leaf = path.nodes[0];
- }
- btrfs_item_key_to_cpu(leaf, &key, path.slots[0]);
+ node = path.nodes[0];
+ slot = path.slots[0];
+ btrfs_item_key_to_cpu(node, &key, slot);
+ if (key.objectid > BTRFS_LAST_FREE_OBJECTID)
+ goto out;
if (key.type == BTRFS_ROOT_ITEM_KEY &&
fs_root_objectid(key.objectid)) {
if (key.objectid == BTRFS_TREE_RELOC_OBJECTID) {
- tmp_root = btrfs_read_fs_root_no_cache(
- root->fs_info, &key);
+ cur_root = btrfs_read_fs_root_no_cache(fs_info,
+ &key);
} else {
key.offset = (u64)-1;
- tmp_root = btrfs_read_fs_root(
- root->fs_info, &key);
+ cur_root = btrfs_read_fs_root(fs_info, &key);
}
- if (IS_ERR(tmp_root)) {
- err = 1;
+
+ if (IS_ERR(cur_root)) {
+ error("Fail to read fs/subvol tree: %lld",
+ key.objectid);
+ err = -EIO;
goto next;
}
- ret = check_fs_root(tmp_root, root_cache, &wc);
- if (ret == -EAGAIN) {
- free_root_recs_tree(root_cache);
- btrfs_release_path(&path);
- goto again;
- }
- if (ret)
- err = 1;
+
+ ret = check_fs_root_v2(cur_root, ext_ref);
+ err |= ret;
+
if (key.objectid == BTRFS_TREE_RELOC_OBJECTID)
- btrfs_free_fs_root(tmp_root);
+ btrfs_free_fs_root(cur_root);
} else if (key.type == BTRFS_ROOT_REF_KEY ||
- key.type == BTRFS_ROOT_BACKREF_KEY) {
- process_root_ref(leaf, path.slots[0], &key,
- root_cache);
+ key.type == BTRFS_ROOT_BACKREF_KEY) {
+ ret = check_root_ref(tree_root, &key, node, slot);
+ err |= ret;
}
next:
- path.slots[0]++;
+ ret = btrfs_next_item(tree_root, &path);
+ if (ret > 0)
+ goto out;
+ if (ret < 0) {
+ err = ret;
+ goto out;
+ }
}
+
out:
btrfs_release_path(&path);
- if (err)
- free_extent_cache_tree(&wc.shared);
- if (!cache_tree_empty(&wc.shared))
- fprintf(stderr, "warning line %d\n", __LINE__);
-
- task_stop(ctx.info);
-
return err;
}
return 0;
}
-static void free_extent_record_cache(struct btrfs_fs_info *fs_info,
- struct cache_tree *extent_cache)
+static void free_extent_record_cache(struct cache_tree *extent_cache)
{
struct cache_extent *cache;
struct extent_record *rec;
return 0;
}
-static int fix_key_order(struct btrfs_trans_handle *trans,
- struct btrfs_root *root,
- struct btrfs_path *path)
+static int fix_key_order(struct btrfs_root *root, struct btrfs_path *path)
{
struct extent_buffer *buf;
struct btrfs_key k1, k2;
return ret;
}
-static int delete_bogus_item(struct btrfs_trans_handle *trans,
- struct btrfs_root *root,
+static int delete_bogus_item(struct btrfs_root *root,
struct btrfs_path *path,
struct extent_buffer *buf, int slot)
{
return 0;
}
-static int fix_item_offset(struct btrfs_trans_handle *trans,
- struct btrfs_root *root,
- struct btrfs_path *path)
+static int fix_item_offset(struct btrfs_root *root, struct btrfs_path *path)
{
struct extent_buffer *buf;
int i;
BTRFS_LEAF_DATA_SIZE(root)) {
if (btrfs_item_end_nr(buf, i) >
BTRFS_LEAF_DATA_SIZE(root)) {
- ret = delete_bogus_item(trans, root, path,
- buf, i);
+ ret = delete_bogus_item(root, path, buf, i);
if (!ret)
goto again;
fprintf(stderr, "item is off the end of the "
btrfs_item_offset_nr(buf, i - 1)) {
if (btrfs_item_end_nr(buf, i) >
btrfs_item_offset_nr(buf, i - 1)) {
- ret = delete_bogus_item(trans, root, path,
- buf, i);
+ ret = delete_bogus_item(root, path, buf, i);
if (!ret)
goto again;
fprintf(stderr, "items overlap, can't fix\n");
break;
}
if (status == BTRFS_TREE_BLOCK_BAD_KEY_ORDER)
- ret = fix_key_order(trans, search_root, &path);
+ ret = fix_key_order(search_root, &path);
else if (status == BTRFS_TREE_BLOCK_INVALID_OFFSETS)
- ret = fix_item_offset(trans, search_root, &path);
+ ret = fix_item_offset(search_root, &path);
if (ret) {
btrfs_commit_transaction(trans, search_root);
break;
btrfs_remove_free_space_cache(cache);
}
- if (btrfs_fs_compat_ro(root->fs_info,
- BTRFS_FEATURE_COMPAT_RO_FREE_SPACE_TREE)) {
+ if (btrfs_fs_compat_ro(root->fs_info, FREE_SPACE_TREE)) {
ret = exclude_super_stripes(root, cache);
if (ret) {
fprintf(stderr, "could not exclude super stripes: %s\n",
csum = ~(u32)0;
tmp = offset + data_checked;
- csum = btrfs_csum_data(NULL, (char *)data + tmp,
+ csum = btrfs_csum_data((char *)data + tmp,
csum, root->sectorsize);
btrfs_csum_final(csum, (u8 *)&csum);
* assumption and simply indicate that we _think_ that the FULL BACKREF needs to
* be set or not and then we can check later once we've gathered all the refs.
*/
-static int calc_extent_flag(struct btrfs_root *root,
- struct cache_tree *extent_cache,
+static int calc_extent_flag(struct cache_tree *extent_cache,
struct extent_buffer *buf,
struct root_item_record *ri,
u64 *flags)
btrfs_header_level(buf), 1, NULL,
&flags);
if (ret < 0) {
- ret = calc_extent_flag(root, extent_cache, buf, ri, &flags);
+ ret = calc_extent_flag(extent_cache, buf, ri, &flags);
if (ret < 0) {
fprintf(stderr, "Couldn't calc extent flags\n");
flags |= BTRFS_BLOCK_FLAG_FULL_BACKREF;
}
} else {
flags = 0;
- ret = calc_extent_flag(root, extent_cache, buf, ri, &flags);
+ ret = calc_extent_flag(extent_cache, buf, ri, &flags);
if (ret < 0) {
fprintf(stderr, "Couldn't calc extent flags\n");
flags |= BTRFS_BLOCK_FLAG_FULL_BACKREF;
static int delete_extent_records(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct btrfs_path *path,
- u64 bytenr, u64 new_len)
+ u64 bytenr)
{
struct btrfs_key key;
struct btrfs_key found_key;
struct extent_backref *back,
int allocated, u64 flags)
{
- int ret;
+ int ret = 0;
struct btrfs_root *extent_root = info->extent_root;
struct extent_buffer *leaf;
struct btrfs_key ins_key;
struct btrfs_extent_item *ei;
- struct tree_backref *tback;
struct data_backref *dback;
struct btrfs_tree_block_info *bi;
} else {
struct btrfs_disk_key copy_key;;
- tback = to_tree_backref(back);
bi = (struct btrfs_tree_block_info *)(ei + 1);
memset_extent_buffer(leaf, 0, (unsigned long)bi,
sizeof(*bi));
dback->found_ref);
} else {
u64 parent;
+ struct tree_backref *tback;
tback = to_tree_backref(back);
if (back->full_backref)
struct extent_entry *entry, *best = NULL, *prev = NULL;
list_for_each_entry(entry, entries, list) {
- if (!prev) {
- prev = entry;
- continue;
- }
-
/*
* If there are as many broken entries as entries then we know
* not to trust this particular entry.
continue;
/*
+ * Special case, when there are only two entries and 'best' is
+ * the first one
+ */
+ if (!prev) {
+ best = entry;
+ prev = entry;
+ continue;
+ }
+
+ /*
* If our current entry == best then we can't be sure our best
* is really the best, so we need to keep searching.
*/
return ret;
}
-static int process_duplicates(struct btrfs_root *root,
- struct cache_tree *extent_cache,
+static int process_duplicates(struct cache_tree *extent_cache,
struct extent_record *rec)
{
struct extent_record *good, *tmp;
/* step two, delete all the existing records */
ret = delete_extent_records(trans, info->extent_root, &path,
- rec->start, rec->max_size);
+ rec->start);
if (ret < 0)
goto out;
ret = err;
}
+ if (!ret)
+ fprintf(stderr, "Repaired extent references for %llu\n",
+ (unsigned long long)rec->start);
+
btrfs_release_path(&path);
return ret;
}
btrfs_set_extent_flags(path.nodes[0], ei, flags);
btrfs_mark_buffer_dirty(path.nodes[0]);
btrfs_release_path(&path);
- return btrfs_commit_transaction(trans, root);
+ ret = btrfs_commit_transaction(trans, root);
+ if (!ret)
+ fprintf(stderr, "Repaired extent flags for %llu\n",
+ (unsigned long long)rec->start);
+
+ return ret;
}
/* right now we only prune from the extent allocation tree */
del_ptr:
printk("deleting pointer to block %Lu\n", corrupt->cache.start);
- ret = btrfs_del_ptr(trans, info->extent_root, &path, level, slot);
+ ret = btrfs_del_ptr(info->extent_root, &path, level, slot);
out:
btrfs_release_path(&path);
&start, &end, EXTENT_DIRTY);
if (ret)
break;
- clear_extent_dirty(&fs_info->free_space_cache, start, end,
- GFP_NOFS);
+ clear_extent_dirty(&fs_info->free_space_cache, start, end);
}
start = 0;
{
struct extent_record *rec;
struct cache_extent *cache;
- int err = 0;
int ret = 0;
- int fixed = 0;
int had_dups = 0;
- int recorded = 0;
if (repair) {
/*
rec = container_of(cache, struct extent_record, cache);
set_extent_dirty(root->fs_info->excluded_extents,
rec->start,
- rec->start + rec->max_size - 1,
- GFP_NOFS);
+ rec->start + rec->max_size - 1);
cache = next_cache_extent(cache);
}
while(cache) {
set_extent_dirty(root->fs_info->excluded_extents,
cache->start,
- cache->start + cache->size - 1,
- GFP_NOFS);
+ cache->start + cache->size - 1);
cache = next_cache_extent(cache);
}
prune_corrupt_blocks(root->fs_info);
* process_duplicates() will return 0, otherwise it will return
* 1 and we
*/
- if (process_duplicates(root, extent_cache, rec))
+ if (process_duplicates(extent_cache, rec))
continue;
ret = delete_duplicate_records(root, rec);
if (ret < 0)
while(1) {
int cur_err = 0;
+ int fix = 0;
- fixed = 0;
- recorded = 0;
cache = search_cache_extent(extent_cache, 0);
if (!cache)
break;
if (rec->num_duplicates) {
fprintf(stderr, "extent item %llu has multiple extent "
"items\n", (unsigned long long)rec->start);
- err = 1;
cur_err = 1;
}
ret = record_orphan_data_extents(root->fs_info, rec);
if (ret < 0)
goto repair_abort;
- if (ret == 0) {
- recorded = 1;
- } else {
- /*
- * we can't use the extent to repair file
- * extent, let the fallback method handle it.
- */
- if (!fixed && repair) {
- ret = fixup_extent_refs(
- root->fs_info,
- extent_cache, rec);
- if (ret)
- goto repair_abort;
- fixed = 1;
- }
- }
- err = 1;
+ fix = ret;
cur_err = 1;
}
if (all_backpointers_checked(rec, 1)) {
fprintf(stderr, "backpointer mismatch on [%llu %llu]\n",
(unsigned long long)rec->start,
(unsigned long long)rec->nr);
-
- if (!fixed && !recorded && repair) {
- ret = fixup_extent_refs(root->fs_info,
- extent_cache, rec);
- if (ret)
- goto repair_abort;
- fixed = 1;
- }
+ fix = 1;
cur_err = 1;
- err = 1;
}
if (!rec->owner_ref_checked) {
fprintf(stderr, "owner ref check failed [%llu %llu]\n",
(unsigned long long)rec->start,
(unsigned long long)rec->nr);
- if (!fixed && !recorded && repair) {
- ret = fixup_extent_refs(root->fs_info,
- extent_cache, rec);
- if (ret)
- goto repair_abort;
- fixed = 1;
- }
- err = 1;
+ fix = 1;
cur_err = 1;
}
+
+ if (repair && fix) {
+ ret = fixup_extent_refs(root->fs_info, extent_cache, rec);
+ if (ret)
+ goto repair_abort;
+ }
+
+
if (rec->bad_full_backref) {
fprintf(stderr, "bad full backref, on [%llu]\n",
(unsigned long long)rec->start);
ret = fixup_extent_flags(root->fs_info, rec);
if (ret)
goto repair_abort;
- fixed = 1;
+ fix = 1;
}
- err = 1;
cur_err = 1;
}
/*
fprintf(stderr,
"bad metadata [%llu, %llu) crossing stripe boundary\n",
rec->start, rec->start + rec->max_size);
- err = 1;
cur_err = 1;
}
fprintf(stderr,
"bad extent [%llu, %llu), type mismatch with chunk\n",
rec->start, rec->start + rec->max_size);
- err = 1;
cur_err = 1;
}
remove_cache_extent(extent_cache, cache);
free_all_extent_backrefs(rec);
- if (!init_extent_tree && repair && (!cur_err || fixed))
+ if (!init_extent_tree && repair && (!cur_err || fix))
clear_extent_dirty(root->fs_info->excluded_extents,
rec->start,
- rec->start + rec->max_size - 1,
- GFP_NOFS);
+ rec->start + rec->max_size - 1);
free(rec);
}
repair_abort:
if (ret)
goto repair_abort;
}
- if (err)
- fprintf(stderr, "repaired damaged extent references\n");
return ret;
}
- return err;
+ return 0;
}
u64 calc_stripe_length(u64 type, u64 length, int num_stripes)
free_extent_cache_tree(&pending);
free_extent_cache_tree(&reada);
free_extent_cache_tree(&nodes);
+ free_root_item_list(&normal_trees);
+ free_root_item_list(&dropping_trees);
return ret;
loop:
free_corrupt_blocks_tree(root->fs_info->corrupt_blocks);
free_block_group_tree(&block_group_cache);
free_device_cache_tree(&dev_cache);
free_device_extent_tree(&dev_extent_cache);
- free_extent_record_cache(root->fs_info, &extent_cache);
+ free_extent_record_cache(&extent_cache);
free_root_item_list(&normal_trees);
free_root_item_list(&dropping_trees);
extent_io_tree_cleanup(&excluded_extents);
u32 nodesize = root->nodesize;
u32 item_size;
u64 offset;
+ int tree_reloc_root = 0;
int found_ref = 0;
int err = 0;
int ret;
+ if (root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID &&
+ btrfs_header_bytenr(root->node) == bytenr)
+ tree_reloc_root = 1;
+
btrfs_init_path(&path);
key.objectid = bytenr;
- if (btrfs_fs_incompat(root->fs_info,
- BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA))
+ if (btrfs_fs_incompat(root->fs_info, SKINNY_METADATA))
key.type = BTRFS_METADATA_ITEM_KEY;
else
key.type = BTRFS_EXTENT_ITEM_KEY;
(offset == root->objectid || offset == owner)) {
found_ref = 1;
} else if (type == BTRFS_SHARED_BLOCK_REF_KEY) {
+ /*
+ * Backref of tree reloc root points to itself, no need
+ * to check backref any more.
+ */
+ if (tree_reloc_root)
+ found_ref = 1;
+ else
/* Check if the backref points to valid referencer */
- found_ref = !check_tree_block_ref(root, NULL, offset,
- level + 1, owner);
+ found_ref = !check_tree_block_ref(root, NULL,
+ offset, level + 1, owner);
}
if (found_ref)
struct btrfs_extent_inline_ref *iref;
struct btrfs_extent_data_ref *dref;
u64 owner;
- u64 file_extent_gen;
u64 disk_bytenr;
u64 disk_num_bytes;
u64 extent_num_bytes;
u64 extent_flags;
- u64 extent_gen;
u32 item_size;
unsigned long end;
unsigned long ptr;
btrfs_item_key_to_cpu(eb, &fi_key, slot);
fi = btrfs_item_ptr(eb, slot, struct btrfs_file_extent_item);
- file_extent_gen = btrfs_file_extent_generation(eb, fi);
/* Nothing to check for hole and inline data extents */
if (btrfs_file_extent_type(eb, fi) == BTRFS_FILE_EXTENT_INLINE ||
dbref_key.offset = btrfs_file_extent_disk_num_bytes(eb, fi);
ret = btrfs_search_slot(NULL, extent_root, &dbref_key, &path, 0, 0);
- if (ret) {
- err |= BACKREF_MISSING;
- goto error;
- }
+ if (ret)
+ goto out;
leaf = path.nodes[0];
slot = path.slots[0];
ei = btrfs_item_ptr(leaf, slot, struct btrfs_extent_item);
extent_flags = btrfs_extent_flags(leaf, ei);
- extent_gen = btrfs_extent_generation(leaf, ei);
if (!(extent_flags & BTRFS_EXTENT_FLAG_DATA)) {
error(
err |= BACKREF_MISMATCH;
}
- if (file_extent_gen < extent_gen) {
- error(
-"extent[%llu %llu] backref generation mismatch, wanted: <=%llu, have: %llu",
- disk_bytenr, disk_num_bytes, file_extent_gen,
- extent_gen);
- err |= BACKREF_MISMATCH;
- }
-
/* Check data backref inside that extent item */
item_size = btrfs_item_size_nr(leaf, path.slots[0]);
iref = (struct btrfs_extent_inline_ref *)(ei + 1);
ptr += btrfs_extent_inline_ref_size(type);
}
- /* Didn't found inlined data backref, try EXTENT_DATA_REF_KEY */
if (!found_dbackref) {
btrfs_release_path(&path);
- btrfs_init_path(&path);
+ /* Didn't find inlined data backref, try EXTENT_DATA_REF_KEY */
dbref_key.objectid = btrfs_file_extent_disk_bytenr(eb, fi);
dbref_key.type = BTRFS_EXTENT_DATA_REF_KEY;
dbref_key.offset = hash_extent_data_ref(root->objectid,
ret = btrfs_search_slot(NULL, root->fs_info->extent_root,
&dbref_key, &path, 0, 0);
- if (!ret)
+ if (!ret) {
+ found_dbackref = 1;
+ goto out;
+ }
+
+ btrfs_release_path(&path);
+
+ /*
+ * Neither inlined nor EXTENT_DATA_REF found, try
+ * SHARED_DATA_REF as last chance.
+ */
+ dbref_key.objectid = disk_bytenr;
+ dbref_key.type = BTRFS_SHARED_DATA_REF_KEY;
+ dbref_key.offset = eb->start;
+
+ ret = btrfs_search_slot(NULL, root->fs_info->extent_root,
+ &dbref_key, &path, 0, 0);
+ if (!ret) {
found_dbackref = 1;
+ goto out;
+ }
}
+out:
if (!found_dbackref)
err |= BACKREF_MISSING;
-error:
btrfs_release_path(&path);
if (err & BACKREF_MISSING) {
error("data extent[%llu %llu] backref lost",
}
/*
+ * Check if tree block @eb is tree reloc root.
+ * Return 0 if it's not or any problem happens
+ * Return 1 if it's a tree reloc root
+ */
+static int is_tree_reloc_root(struct btrfs_fs_info *fs_info,
+ struct extent_buffer *eb)
+{
+ struct btrfs_root *tree_reloc_root;
+ struct btrfs_key key;
+ u64 bytenr = btrfs_header_bytenr(eb);
+ u64 owner = btrfs_header_owner(eb);
+ int ret = 0;
+
+ key.objectid = BTRFS_TREE_RELOC_OBJECTID;
+ key.offset = owner;
+ key.type = BTRFS_ROOT_ITEM_KEY;
+
+ tree_reloc_root = btrfs_read_fs_root_no_cache(fs_info, &key);
+ if (IS_ERR(tree_reloc_root))
+ return 0;
+
+ if (bytenr == btrfs_header_bytenr(tree_reloc_root->node))
+ ret = 1;
+ btrfs_free_fs_root(tree_reloc_root);
+ return ret;
+}
+
+/*
* Check referencer for shared block backref
* If level == -1, this function will resolve the level.
*/
if (level < 0)
goto out;
+ /* It's possible it's a tree reloc root */
+ if (parent == bytenr) {
+ if (is_tree_reloc_root(fs_info, eb))
+ found_parent = 1;
+ goto out;
+ }
+
if (level + 1 != btrfs_header_level(eb))
goto out;
leaf = path.nodes[0];
slot = path.slots[0];
+ if (slot >= btrfs_header_nritems(leaf))
+ goto next;
btrfs_item_key_to_cpu(leaf, &key, slot);
if (key.objectid != objectid || key.type != BTRFS_EXTENT_DATA_KEY)
break;
offset)
found_count++;
+next:
ret = btrfs_next_item(root, &path);
if (ret)
break;
}
end = (unsigned long)ei + item_size;
- if (ptr >= end) {
+next:
+ /* Reached extent item end normally */
+ if (ptr == end)
+ goto out;
+
+ /* Beyond extent item end, wrong item size */
+ if (ptr > end) {
err |= ITEM_SIZE_MISMATCH;
+ error("extent item at bytenr %llu slot %d has wrong size",
+ eb->start, slot);
goto out;
}
/* Now check every backref in this extent item */
-next:
iref = (struct btrfs_extent_inline_ref *)ptr;
type = btrfs_extent_inline_ref_type(eb, iref);
offset = btrfs_extent_inline_ref_offset(eb, iref);
}
ptr += btrfs_extent_inline_ref_size(type);
- if (ptr < end)
- goto next;
+ goto next;
out:
return err;
/* Iterate dev_extents to calculate the used space of a device */
while (1) {
- btrfs_item_key_to_cpu(path.nodes[0], &key, path.slots[0]);
+ if (path.slots[0] >= btrfs_header_nritems(path.nodes[0]))
+ goto next;
+ btrfs_item_key_to_cpu(path.nodes[0], &key, path.slots[0]);
if (key.objectid > dev_id)
break;
if (key.type != BTRFS_DEV_EXTENT_KEY || key.objectid != dev_id)
/* Iterate extent tree to account used space */
while (1) {
leaf = path.nodes[0];
+
+ /* Search slot can point to the last item beyond leaf nritems */
+ if (path.slots[0] >= btrfs_header_nritems(leaf))
+ goto next;
+
btrfs_item_key_to_cpu(leaf, &extent_key, path.slots[0]);
if (extent_key.objectid >= bg_key.objectid + bg_key.offset)
break;
goto next;
key.offset = (u64)-1;
- cur_root = btrfs_read_fs_root(root->fs_info, &key);
+ if (key.objectid == BTRFS_TREE_RELOC_OBJECTID)
+ cur_root = btrfs_read_fs_root_no_cache(root->fs_info,
+ &key);
+ else
+ cur_root = btrfs_read_fs_root(root->fs_info, &key);
if (IS_ERR(cur_root) || !cur_root) {
error("failed to read tree: %lld", key.objectid);
goto next;
ret = traverse_tree_block(cur_root, cur_root->node);
err |= ret;
+ if (key.objectid == BTRFS_TREE_RELOC_OBJECTID)
+ btrfs_free_fs_root(cur_root);
next:
ret = btrfs_next_item(root1, &path);
if (ret)
key.objectid, key.offset,
btrfs_chunk_length(leaf, chunk));
set_extent_dirty(&fs_info->free_space_cache, key.offset,
- key.offset + btrfs_chunk_length(leaf, chunk),
- GFP_NOFS);
+ key.offset + btrfs_chunk_length(leaf, chunk));
path.slots[0]++;
}
start = 0;
* the leaves of any fs roots and pin down the bytes for any file
* extents we find. Not hard but why do it if we don't have to?
*/
- if (btrfs_fs_incompat(fs_info, BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS)) {
+ if (btrfs_fs_incompat(fs_info, MIXED_GROUPS)) {
fprintf(stderr, "We don't support re-initing the extent tree "
"for mixed block groups yet, please notify a btrfs "
"developer you want to do this so they can add this "
return ret;
}
-static int maybe_repair_root_item(struct btrfs_fs_info *info,
- struct btrfs_path *path,
+static int maybe_repair_root_item(struct btrfs_path *path,
const struct btrfs_key *root_key,
const int read_only_mode)
{
if (found_key.objectid == BTRFS_TREE_RELOC_OBJECTID)
goto next;
- ret = maybe_repair_root_item(info, &path, &found_key,
- trans ? 0 : 1);
+ ret = maybe_repair_root_item(&path, &found_key, trans ? 0 : 1);
if (ret < 0)
goto out;
if (ret) {
"--chunk-root <bytenr> use the given bytenr for the chunk tree root",
"-p|--progress indicate progress",
"--clear-space-cache v1|v2 clear space cache for v1 or v2",
- " NOTE: v1 support implemented",
NULL
};
u64 chunk_root_bytenr = 0;
char uuidbuf[BTRFS_UUID_UNPARSED_SIZE];
int ret;
+ int err = 0;
u64 num;
int init_csum_tree = 0;
int readonly = 0;
}
break;
case GETOPT_VAL_CLEAR_SPACE_CACHE:
- if (strcmp(optarg, "v1") != 0) {
+ if (strcmp(optarg, "v1") == 0) {
+ clear_space_cache = 1;
+ } else if (strcmp(optarg, "v2") == 0) {
+ clear_space_cache = 2;
+ ctree_flags |= OPEN_CTREE_INVALIDATE_FST;
+ } else {
error(
- "only v1 support implmented, unrecognized value %s",
- optarg);
+ "invalid argument to --clear-space-cache, must be v1 or v2");
exit(1);
}
- clear_space_cache = 1;
ctree_flags |= OPEN_CTREE_WRITES;
break;
}
if((ret = check_mounted(argv[optind])) < 0) {
error("could not check mount status: %s", strerror(-ret));
+ err |= !!ret;
goto err_out;
} else if(ret) {
error("%s is currently mounted, aborting", argv[optind]);
ret = -EBUSY;
+ err |= !!ret;
goto err_out;
}
if (!info) {
error("cannot open file system");
ret = -EIO;
+ err |= !!ret;
goto err_out;
}
global_info = info;
root = info->fs_root;
- if (clear_space_cache) {
- if (btrfs_fs_compat_ro(info,
- BTRFS_FEATURE_COMPAT_RO_FREE_SPACE_TREE)) {
+ if (clear_space_cache == 1) {
+ if (btrfs_fs_compat_ro(info, FREE_SPACE_TREE)) {
error(
- "free space cache v2 detected, clearing not implemented");
+ "free space cache v2 detected, use --clear-space-cache v2");
ret = 1;
goto close_out;
}
printf("Free space cache cleared\n");
}
goto close_out;
+ } else if (clear_space_cache == 2) {
+ if (!btrfs_fs_compat_ro(info, FREE_SPACE_TREE)) {
+ printf("no free space cache v2 to clear\n");
+ ret = 0;
+ goto close_out;
+ }
+ printf("Clear free space cache v2\n");
+ ret = btrfs_clear_free_space_tree(info);
+ if (ret) {
+ error("failed to clear free space cache v2: %d", ret);
+ ret = 1;
+ } else {
+ printf("free space cache v2 cleared\n");
+ }
+ goto close_out;
}
/*
ret = ask_user("repair mode will force to clear out log tree, are you sure?");
if (!ret) {
ret = 1;
+ err |= !!ret;
goto close_out;
}
ret = zero_log_tree(root);
+ err |= !!ret;
if (ret) {
error("failed to zero log tree: %d", ret);
goto close_out;
printf("Print quota groups for %s\nUUID: %s\n", argv[optind],
uuidbuf);
ret = qgroup_verify_all(info);
+ err |= !!ret;
if (ret == 0)
report_qgroups(1);
goto close_out;
printf("Print extent state for subvolume %llu on %s\nUUID: %s\n",
subvolid, argv[optind], uuidbuf);
ret = print_extent_state(info, subvolid);
+ err |= !!ret;
goto close_out;
}
printf("Checking filesystem on %s\nUUID: %s\n", argv[optind], uuidbuf);
!extent_buffer_uptodate(info->dev_root->node) ||
!extent_buffer_uptodate(info->chunk_root->node)) {
error("critical roots corrupted, unable to check the filesystem");
+ err |= !!ret;
ret = -EIO;
goto close_out;
}
if (IS_ERR(trans)) {
error("error starting transaction");
ret = PTR_ERR(trans);
+ err |= !!ret;
goto close_out;
}
if (init_extent_tree) {
printf("Creating a new extent tree\n");
ret = reinit_extent_tree(trans, info);
+ err |= !!ret;
if (ret)
goto close_out;
}
error("checksum tree initialization failed: %d",
ret);
ret = -EIO;
+ err |= !!ret;
goto close_out;
}
ret = fill_csum_tree(trans, info->csum_root,
init_extent_tree);
+ err |= !!ret;
if (ret) {
error("checksum tree refilling failed: %d", ret);
return -EIO;
* extent entries for all of the items it finds.
*/
ret = btrfs_commit_transaction(trans, info->extent_root);
+ err |= !!ret;
if (ret)
goto close_out;
}
if (!extent_buffer_uptodate(info->extent_root->node)) {
error("critical: extent_root, unable to check the filesystem");
ret = -EIO;
+ err |= !!ret;
goto close_out;
}
if (!extent_buffer_uptodate(info->csum_root->node)) {
error("critical: csum_root, unable to check the filesystem");
ret = -EIO;
+ err |= !!ret;
goto close_out;
}
if (!ctx.progress_enabled)
- printf("checking extents");
+ fprintf(stderr, "checking extents\n");
if (check_mode == CHECK_MODE_LOWMEM)
ret = check_chunks_and_extents_v2(root);
else
ret = check_chunks_and_extents(root);
+ err |= !!ret;
if (ret)
- printf("Errors found in extent allocation tree or chunk allocation");
+ error(
+ "errors found in extent allocation tree or chunk allocation");
ret = repair_root_items(info);
- if (ret < 0)
+ err |= !!ret;
+ if (ret < 0) {
+ error("failed to repair root items: %s", strerror(-ret));
goto close_out;
+ }
if (repair) {
fprintf(stderr, "Fixed %d roots.\n", ret);
ret = 0;
fprintf(stderr,
"Please run a filesystem check with the option --repair to fix them.\n");
ret = 1;
+ err |= !!ret;
goto close_out;
}
if (!ctx.progress_enabled) {
- if (btrfs_fs_compat_ro(info, BTRFS_FEATURE_COMPAT_RO_FREE_SPACE_TREE))
+ if (btrfs_fs_compat_ro(info, FREE_SPACE_TREE))
fprintf(stderr, "checking free space tree\n");
else
fprintf(stderr, "checking free space cache\n");
}
ret = check_space_cache(root);
- if (ret)
+ err |= !!ret;
+ if (ret) {
+ if (btrfs_fs_compat_ro(info, FREE_SPACE_TREE))
+ error("errors found in free space tree");
+ else
+ error("errors found in free space cache");
goto out;
+ }
/*
* We used to have to have these hole extents in between our real
* are no gaps in the file extents for inodes, otherwise we can just
* ignore it when this happens.
*/
- no_holes = btrfs_fs_incompat(root->fs_info,
- BTRFS_FEATURE_INCOMPAT_NO_HOLES);
+ no_holes = btrfs_fs_incompat(root->fs_info, NO_HOLES);
if (!ctx.progress_enabled)
fprintf(stderr, "checking fs roots\n");
- ret = check_fs_roots(root, &root_cache);
- if (ret)
+ if (check_mode == CHECK_MODE_LOWMEM)
+ ret = check_fs_roots_v2(root->fs_info);
+ else
+ ret = check_fs_roots(root, &root_cache);
+ err |= !!ret;
+ if (ret) {
+ error("errors found in fs roots");
goto out;
+ }
fprintf(stderr, "checking csums\n");
ret = check_csums(root);
- if (ret)
+ err |= !!ret;
+ if (ret) {
+ error("errors found in csum tree");
goto out;
+ }
fprintf(stderr, "checking root refs\n");
- ret = check_root_refs(root, &root_cache);
- if (ret)
- goto out;
+ /* For low memory mode, check_fs_roots_v2 handles root refs */
+ if (check_mode != CHECK_MODE_LOWMEM) {
+ ret = check_root_refs(root, &root_cache);
+ err |= !!ret;
+ if (ret) {
+ error("errors found in root refs");
+ goto out;
+ }
+ }
while (repair && !list_empty(&root->fs_info->recow_ebs)) {
struct extent_buffer *eb;
struct extent_buffer, recow);
list_del_init(&eb->recow);
ret = recow_extent_buffer(root, eb);
- if (ret)
+ err |= !!ret;
+ if (ret) {
+ error("fails to fix transid errors");
break;
+ }
}
while (!list_empty(&delete_items)) {
bad = list_first_entry(&delete_items, struct bad_item, list);
list_del_init(&bad->list);
- if (repair)
+ if (repair) {
ret = delete_bad_item(root, bad);
+ err |= !!ret;
+ }
free(bad);
}
if (info->quota_enabled) {
- int err;
fprintf(stderr, "checking quota groups\n");
- err = qgroup_verify_all(info);
- if (err)
+ ret = qgroup_verify_all(info);
+ err |= !!ret;
+ if (ret) {
+ error("failed to check quota groups");
goto out;
+ }
report_qgroups(0);
- err = repair_qgroups(info, &qgroups_repaired);
- if (err)
+ ret = repair_qgroups(info, &qgroups_repaired);
+ err |= !!ret;
+ if (err) {
+ error("failed to repair quota groups");
goto out;
+ }
+ ret = 0;
}
if (!list_empty(&root->fs_info->recow_ebs)) {
error("transid errors in file system");
ret = 1;
+ err |= !!ret;
}
out:
- /* Don't override original ret */
- if (!ret && qgroups_repaired)
- ret = qgroups_repaired;
-
if (found_old_backref) { /*
* there was a disk format change when mixed
* backref was in testing tree. The old format
"The old format is not supported! *"
"\n * Please mount the FS in readonly mode, "
"backup data and re-format the FS. *\n\n");
- ret = 1;
+ err |= 1;
}
- printf("found %llu bytes used err is %d\n",
- (unsigned long long)bytes_used, ret);
+ printf("found %llu bytes used, ",
+ (unsigned long long)bytes_used);
+ if (err)
+ printf("error(s) found\n");
+ else
+ printf("no error found\n");
printf("total csum bytes: %llu\n",(unsigned long long)total_csum_bytes);
printf("total tree bytes: %llu\n",
(unsigned long long)total_btree_bytes);
if (ctx.progress_enabled)
task_deinit(ctx.info);
- return ret;
+ return err;
}