static int found_old_backref = 0;
static LIST_HEAD(duplicate_extents);
static LIST_HEAD(delete_items);
-static int repair = 0;
static int no_holes = 0;
static int init_extent_tree = 0;
static int check_data_csum = 0;
static struct btrfs_fs_info *global_info;
static struct task_ctx ctx = { 0 };
+static struct cache_tree *roots_info_cache = NULL;
-static void *print_status_check(void *p)
-{
- struct task_ctx *priv = p;
- const char work_indicator[] = { '.', 'o', 'O', 'o' };
- uint32_t count = 0;
- static char *task_position_string[] = {
- "checking extents",
- "checking free space cache",
- "checking fs roots",
- };
-
- task_period_start(priv->info, 1000 /* 1s */);
-
- if (priv->tp == TASK_NOTHING)
- return NULL;
-
- while (1) {
- printf("%s [%c]\r", task_position_string[priv->tp],
- work_indicator[count % 4]);
- count++;
- fflush(stdout);
- task_period_wait(priv->info);
- }
- return NULL;
-}
-
-static int print_status_return(void *p)
-{
- printf("\n");
- fflush(stdout);
+enum btrfs_check_mode {
+ CHECK_MODE_ORIGINAL,
+ CHECK_MODE_LOWMEM,
+ CHECK_MODE_UNKNOWN,
+ CHECK_MODE_DEFAULT = CHECK_MODE_ORIGINAL
+};
- return 0;
-}
+static enum btrfs_check_mode check_mode = CHECK_MODE_DEFAULT;
struct extent_backref {
struct list_head list;
unsigned int broken:1;
};
+static inline struct extent_backref* to_extent_backref(struct list_head *entry)
+{
+ return list_entry(entry, struct extent_backref, list);
+}
+
struct data_backref {
struct extent_backref node;
union {
u32 found_ref;
};
+static inline struct data_backref* to_data_backref(struct extent_backref *back)
+{
+ return container_of(back, struct data_backref, node);
+}
+
/*
* Much like data_backref, just removed the undetermined members
* and change it to use list_head.
};
};
+static inline struct tree_backref* to_tree_backref(struct extent_backref *back)
+{
+ return container_of(back, struct tree_backref, node);
+}
+
+/* Explicit initialization for extent_record::flag_block_full_backref */
+enum { FLAG_UNSET = 2 };
+
struct extent_record {
struct list_head backrefs;
struct list_head dups;
u64 info_objectid;
u32 num_duplicates;
u8 info_level;
- int flag_block_full_backref;
+ unsigned int flag_block_full_backref:2;
unsigned int found_rec:1;
unsigned int content_checked:1;
unsigned int owner_ref_checked:1;
unsigned int wrong_chunk_type:1;
};
+static inline struct extent_record* to_extent_record(struct list_head *entry)
+{
+ return container_of(entry, struct extent_record, list);
+}
+
struct inode_backref {
struct list_head list;
unsigned int found_dir_item:1;
unsigned int found_dir_index:1;
unsigned int found_inode_ref:1;
- unsigned int filetype:8;
+ u8 filetype;
+ u8 ref_type;
int errors;
- unsigned int ref_type;
u64 dir;
u64 index;
u16 namelen;
char name[0];
};
+static inline struct inode_backref* to_inode_backref(struct list_head *entry)
+{
+ return list_entry(entry, struct inode_backref, list);
+}
+
struct root_item_record {
struct list_head list;
u64 objectid;
u64 len;
};
+struct inode_record {
+ struct list_head backrefs;
+ unsigned int checked:1;
+ unsigned int merging:1;
+ unsigned int found_inode_item:1;
+ unsigned int found_dir_item:1;
+ unsigned int found_file_extent:1;
+ unsigned int found_csum_item:1;
+ unsigned int some_csum_missing:1;
+ unsigned int nodatasum:1;
+ int errors;
+
+ u64 ino;
+ u32 nlink;
+ u32 imode;
+ u64 isize;
+ u64 nbytes;
+
+ u32 found_link;
+ u64 found_size;
+ u64 extent_start;
+ u64 extent_end;
+ struct rb_root holes;
+ struct list_head orphan_extents;
+
+ u32 refs;
+};
+
+#define I_ERR_NO_INODE_ITEM (1 << 0)
+#define I_ERR_NO_ORPHAN_ITEM (1 << 1)
+#define I_ERR_DUP_INODE_ITEM (1 << 2)
+#define I_ERR_DUP_DIR_INDEX (1 << 3)
+#define I_ERR_ODD_DIR_ITEM (1 << 4)
+#define I_ERR_ODD_FILE_EXTENT (1 << 5)
+#define I_ERR_BAD_FILE_EXTENT (1 << 6)
+#define I_ERR_FILE_EXTENT_OVERLAP (1 << 7)
+#define I_ERR_FILE_EXTENT_DISCOUNT (1 << 8) // 100
+#define I_ERR_DIR_ISIZE_WRONG (1 << 9)
+#define I_ERR_FILE_NBYTES_WRONG (1 << 10) // 400
+#define I_ERR_ODD_CSUM_ITEM (1 << 11)
+#define I_ERR_SOME_CSUM_MISSING (1 << 12)
+#define I_ERR_LINK_COUNT_WRONG (1 << 13)
+#define I_ERR_FILE_EXTENT_ORPHAN (1 << 14)
+
+struct root_backref {
+ struct list_head list;
+ unsigned int found_dir_item:1;
+ unsigned int found_dir_index:1;
+ unsigned int found_back_ref:1;
+ unsigned int found_forward_ref:1;
+ unsigned int reachable:1;
+ int errors;
+ u64 ref_root;
+ u64 dir;
+ u64 index;
+ u16 namelen;
+ char name[0];
+};
+
+static inline struct root_backref* to_root_backref(struct list_head *entry)
+{
+ return list_entry(entry, struct root_backref, list);
+}
+
+struct root_record {
+ struct list_head backrefs;
+ struct cache_extent cache;
+ unsigned int found_root_item:1;
+ u64 objectid;
+ u32 found_ref;
+};
+
+struct ptr_node {
+ struct cache_extent cache;
+ void *data;
+};
+
+struct shared_node {
+ struct cache_extent cache;
+ struct cache_tree root_cache;
+ struct cache_tree inode_cache;
+ struct inode_record *current;
+ u32 refs;
+};
+
+struct block_info {
+ u64 start;
+ u32 size;
+};
+
+struct walk_control {
+ struct cache_tree shared;
+ struct shared_node *nodes[BTRFS_MAX_LEVEL];
+ int active_node;
+ int root_level;
+};
+
+struct bad_item {
+ struct btrfs_key key;
+ u64 root_id;
+ struct list_head list;
+};
+
+struct extent_entry {
+ u64 bytenr;
+ u64 bytes;
+ int count;
+ int broken;
+ struct list_head list;
+};
+
+struct root_item_info {
+ /* level of the root */
+ u8 level;
+ /* number of nodes at this level, must be 1 for a root */
+ int node_count;
+ u64 bytenr;
+ u64 gen;
+ struct cache_extent cache_extent;
+};
+
+/*
+ * Error bit for low memory mode check.
+ *
+ * Currently no caller cares about it yet. Just internal use for error
+ * classification.
+ */
+#define BACKREF_MISSING (1 << 0) /* Backref missing in extent tree */
+#define BACKREF_MISMATCH (1 << 1) /* Backref exists but does not match */
+#define BYTES_UNALIGNED (1 << 2) /* Some bytes are not aligned */
+#define REFERENCER_MISSING (1 << 3) /* Referencer not found */
+#define REFERENCER_MISMATCH (1 << 4) /* Referenceer found but does not match */
+#define CROSSING_STRIPE_BOUNDARY (1 << 4) /* For kernel scrub workaround */
+#define ITEM_SIZE_MISMATCH (1 << 5) /* Bad item size */
+#define UNKNOWN_TYPE (1 << 6) /* Unknown type */
+#define ACCOUNTING_MISMATCH (1 << 7) /* Used space accounting error */
+#define CHUNK_TYPE_MISMATCH (1 << 8)
+
+static void *print_status_check(void *p)
+{
+ struct task_ctx *priv = p;
+ const char work_indicator[] = { '.', 'o', 'O', 'o' };
+ uint32_t count = 0;
+ static char *task_position_string[] = {
+ "checking extents",
+ "checking free space cache",
+ "checking fs roots",
+ };
+
+ task_period_start(priv->info, 1000 /* 1s */);
+
+ if (priv->tp == TASK_NOTHING)
+ return NULL;
+
+ while (1) {
+ printf("%s [%c]\r", task_position_string[priv->tp],
+ work_indicator[count % 4]);
+ count++;
+ fflush(stdout);
+ task_period_wait(priv->info);
+ }
+ return NULL;
+}
+
+static int print_status_return(void *p)
+{
+ printf("\n");
+ fflush(stdout);
+
+ return 0;
+}
+
+static enum btrfs_check_mode parse_check_mode(const char *str)
+{
+ if (strcmp(str, "lowmem") == 0)
+ return CHECK_MODE_LOWMEM;
+ if (strcmp(str, "orig") == 0)
+ return CHECK_MODE_ORIGINAL;
+ if (strcmp(str, "original") == 0)
+ return CHECK_MODE_ORIGINAL;
+
+ return CHECK_MODE_UNKNOWN;
+}
+
/* Compatible function to allow reuse of old codes */
static u64 first_extent_gap(struct rb_root *holes)
{
return -EEXIST;
/*
- * Now there will be no overflap, delete the hole and re-add the
+ * Now there will be no overlap, delete the hole and re-add the
* split(s) if they exists.
*/
if (start > hole->start) {
}
}
-struct inode_record {
- struct list_head backrefs;
- unsigned int checked:1;
- unsigned int merging:1;
- unsigned int found_inode_item:1;
- unsigned int found_dir_item:1;
- unsigned int found_file_extent:1;
- unsigned int found_csum_item:1;
- unsigned int some_csum_missing:1;
- unsigned int nodatasum:1;
- int errors;
-
- u64 ino;
- u32 nlink;
- u32 imode;
- u64 isize;
- u64 nbytes;
-
- u32 found_link;
- u64 found_size;
- u64 extent_start;
- u64 extent_end;
- struct rb_root holes;
- struct list_head orphan_extents;
+static void reset_cached_block_groups(struct btrfs_fs_info *fs_info);
- u32 refs;
-};
-
-#define I_ERR_NO_INODE_ITEM (1 << 0)
-#define I_ERR_NO_ORPHAN_ITEM (1 << 1)
-#define I_ERR_DUP_INODE_ITEM (1 << 2)
-#define I_ERR_DUP_DIR_INDEX (1 << 3)
-#define I_ERR_ODD_DIR_ITEM (1 << 4)
-#define I_ERR_ODD_FILE_EXTENT (1 << 5)
-#define I_ERR_BAD_FILE_EXTENT (1 << 6)
-#define I_ERR_FILE_EXTENT_OVERLAP (1 << 7)
-#define I_ERR_FILE_EXTENT_DISCOUNT (1 << 8) // 100
-#define I_ERR_DIR_ISIZE_WRONG (1 << 9)
-#define I_ERR_FILE_NBYTES_WRONG (1 << 10) // 400
-#define I_ERR_ODD_CSUM_ITEM (1 << 11)
-#define I_ERR_SOME_CSUM_MISSING (1 << 12)
-#define I_ERR_LINK_COUNT_WRONG (1 << 13)
-#define I_ERR_FILE_EXTENT_ORPHAN (1 << 14)
-
-struct root_backref {
- struct list_head list;
- unsigned int found_dir_item:1;
- unsigned int found_dir_index:1;
- unsigned int found_back_ref:1;
- unsigned int found_forward_ref:1;
- unsigned int reachable:1;
- int errors;
- u64 ref_root;
- u64 dir;
- u64 index;
- u16 namelen;
- char name[0];
-};
-
-struct root_record {
- struct list_head backrefs;
- struct cache_extent cache;
- unsigned int found_root_item:1;
- u64 objectid;
- u32 found_ref;
-};
-
-struct ptr_node {
- struct cache_extent cache;
- void *data;
-};
-
-struct shared_node {
- struct cache_extent cache;
- struct cache_tree root_cache;
- struct cache_tree inode_cache;
- struct inode_record *current;
- u32 refs;
-};
-
-struct block_info {
- u64 start;
- u32 size;
-};
-
-struct walk_control {
- struct cache_tree shared;
- struct shared_node *nodes[BTRFS_MAX_LEVEL];
- int active_node;
- int root_level;
-};
-
-struct bad_item {
- struct btrfs_key key;
- u64 root_id;
- struct list_head list;
-};
-
-static void reset_cached_block_groups(struct btrfs_fs_info *fs_info);
-
-static void record_root_in_trans(struct btrfs_trans_handle *trans,
- struct btrfs_root *root)
-{
- if (root->last_trans != trans->transid) {
- root->track_dirty = 1;
- root->last_trans = trans->transid;
- root->commit_root = root->node;
- extent_buffer_get(root->node);
- }
-}
+static void record_root_in_trans(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root)
+{
+ if (root->last_trans != trans->transid) {
+ root->track_dirty = 1;
+ root->last_trans = trans->transid;
+ root->commit_root = root->node;
+ extent_buffer_get(root->node);
+ }
+}
static u8 imode_to_type(u32 imode)
{
struct inode_backref *tmp;
struct orphan_data_extent *src_orphan;
struct orphan_data_extent *dst_orphan;
+ struct rb_node *rb;
size_t size;
int ret;
list_add_tail(&dst_orphan->list, &rec->orphan_extents);
}
ret = copy_file_extent_holes(&rec->holes, &orig_rec->holes);
- BUG_ON(ret < 0);
+ if (ret < 0)
+ goto cleanup_rb;
return rec;
+cleanup_rb:
+ rb = rb_first(&rec->holes);
+ while (rb) {
+ struct file_extent_hole *hole;
+
+ hole = rb_entry(rb, struct file_extent_hole, node);
+ rb = rb_next(rb);
+ free(hole);
+ }
+
cleanup:
if (!list_empty(&rec->backrefs))
list_for_each_entry_safe(orig, tmp, &rec->backrefs, list) {
if (errors & REF_ERR_DUP_INODE_REF)
fprintf(stderr, ", dup inode ref");
if (errors & REF_ERR_INDEX_UNMATCH)
- fprintf(stderr, ", index unmatch");
+ fprintf(stderr, ", index mismatch");
if (errors & REF_ERR_FILETYPE_UNMATCH)
- fprintf(stderr, ", filetype unmatch");
+ fprintf(stderr, ", filetype mismatch");
if (errors & REF_ERR_NAME_TOO_LONG)
fprintf(stderr, ", name too long");
if (errors & REF_ERR_NO_ROOT_REF)
return;
while (!list_empty(&rec->backrefs)) {
- backref = list_entry(rec->backrefs.next,
- struct inode_backref, list);
+ backref = to_inode_backref(rec->backrefs.next);
list_del(&backref->list);
free(backref);
}
struct cache_extent *cache;
struct inode_backref *tmp, *backref;
struct ptr_node *node;
- unsigned char filetype;
+ u8 filetype;
if (!rec->found_inode_item)
return;
static int add_inode_backref(struct cache_tree *inode_cache,
u64 ino, u64 dir, u64 index,
const char *name, int namelen,
- int filetype, int itemtype, int errors)
+ u8 filetype, u8 itemtype, int errors)
{
struct inode_record *rec;
struct inode_backref *backref;
u32 data_len;
int error;
int nritems = 0;
- int filetype;
+ u8 filetype;
struct btrfs_dir_item *di;
struct inode_record *rec;
struct cache_tree *root_cache;
return;
nritems = btrfs_header_nritems(node);
- blocksize = btrfs_level_size(root, level - 1);
+ blocksize = root->nodesize;
for (i = slot; i < nritems; i++) {
bytenr = btrfs_node_blockptr(node, i);
ptr_gen = btrfs_node_ptr_generation(node, i);
return ret;
}
+struct node_refs {
+ u64 bytenr[BTRFS_MAX_LEVEL];
+ u64 refs[BTRFS_MAX_LEVEL];
+};
+
static int walk_down_tree(struct btrfs_root *root, struct btrfs_path *path,
- struct walk_control *wc, int *level)
+ struct walk_control *wc, int *level,
+ struct node_refs *nrefs)
{
enum btrfs_tree_block_status status;
u64 bytenr;
WARN_ON(*level < 0);
WARN_ON(*level >= BTRFS_MAX_LEVEL);
- ret = btrfs_lookup_extent_info(NULL, root,
+
+ if (path->nodes[*level]->start == nrefs->bytenr[*level]) {
+ refs = nrefs->refs[*level];
+ ret = 0;
+ } else {
+ ret = btrfs_lookup_extent_info(NULL, root,
path->nodes[*level]->start,
*level, 1, &refs, NULL);
- if (ret < 0) {
- err = ret;
- goto out;
+ if (ret < 0) {
+ err = ret;
+ goto out;
+ }
+ nrefs->bytenr[*level] = path->nodes[*level]->start;
+ nrefs->refs[*level] = refs;
}
if (refs > 1) {
}
bytenr = btrfs_node_blockptr(cur, path->slots[*level]);
ptr_gen = btrfs_node_ptr_generation(cur, path->slots[*level]);
- blocksize = btrfs_level_size(root, *level - 1);
- ret = btrfs_lookup_extent_info(NULL, root, bytenr, *level - 1,
- 1, &refs, NULL);
- if (ret < 0)
- refs = 0;
+ blocksize = root->nodesize;
+
+ if (bytenr == nrefs->bytenr[*level - 1]) {
+ refs = nrefs->refs[*level - 1];
+ } else {
+ ret = btrfs_lookup_extent_info(NULL, root, bytenr,
+ *level - 1, 1, &refs, NULL);
+ if (ret < 0) {
+ refs = 0;
+ } else {
+ nrefs->bytenr[*level - 1] = bytenr;
+ nrefs->refs[*level - 1] = refs;
+ }
+ }
if (refs > 1) {
ret = enter_shared_node(root, bytenr, refs,
btrfs_add_corrupt_extent_record(root->fs_info,
&node_key,
path->nodes[*level]->start,
- root->leafsize, *level);
+ root->nodesize, *level);
err = -EIO;
goto out;
}
goto out;
if (list_empty(&rec->backrefs))
goto out;
- backref = list_entry(rec->backrefs.next, struct inode_backref, list);
+ backref = to_inode_backref(rec->backrefs.next);
if (!backref->found_inode_ref)
goto out;
if (backref->index != 0 || backref->namelen != 2 ||
struct inode_record *rec,
struct inode_backref *backref)
{
- struct btrfs_path *path;
+ struct btrfs_path path;
struct btrfs_trans_handle *trans;
struct btrfs_dir_item *dir_item;
struct extent_buffer *leaf;
u32 data_size = sizeof(*dir_item) + backref->namelen;
int ret;
- path = btrfs_alloc_path();
- if (!path)
- return -ENOMEM;
-
trans = btrfs_start_transaction(root, 1);
- if (IS_ERR(trans)) {
- btrfs_free_path(path);
+ if (IS_ERR(trans))
return PTR_ERR(trans);
- }
fprintf(stderr, "repairing missing dir index item for inode %llu\n",
(unsigned long long)rec->ino);
+
+ btrfs_init_path(&path);
key.objectid = backref->dir;
key.type = BTRFS_DIR_INDEX_KEY;
key.offset = backref->index;
-
- ret = btrfs_insert_empty_item(trans, root, path, &key, data_size);
+ ret = btrfs_insert_empty_item(trans, root, &path, &key, data_size);
BUG_ON(ret);
- leaf = path->nodes[0];
- dir_item = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_dir_item);
+ leaf = path.nodes[0];
+ dir_item = btrfs_item_ptr(leaf, path.slots[0], struct btrfs_dir_item);
disk_key.objectid = cpu_to_le64(rec->ino);
disk_key.type = BTRFS_INODE_ITEM_KEY;
name_ptr = (unsigned long)(dir_item + 1);
write_extent_buffer(leaf, backref->name, name_ptr, backref->namelen);
btrfs_mark_buffer_dirty(leaf);
- btrfs_free_path(path);
+ btrfs_release_path(&path);
btrfs_commit_transaction(trans, root);
backref->found_dir_index = 1;
{
struct btrfs_trans_handle *trans;
struct btrfs_dir_item *di;
- struct btrfs_path *path;
+ struct btrfs_path path;
int ret = 0;
- path = btrfs_alloc_path();
- if (!path)
- return -ENOMEM;
-
trans = btrfs_start_transaction(root, 1);
- if (IS_ERR(trans)) {
- btrfs_free_path(path);
+ if (IS_ERR(trans))
return PTR_ERR(trans);
- }
-
fprintf(stderr, "Deleting bad dir index [%llu,%u,%llu] root %llu\n",
(unsigned long long)backref->dir,
BTRFS_DIR_INDEX_KEY, (unsigned long long)backref->index,
(unsigned long long)root->objectid);
- di = btrfs_lookup_dir_index(trans, root, path, backref->dir,
+ btrfs_init_path(&path);
+ di = btrfs_lookup_dir_index(trans, root, &path, backref->dir,
backref->name, backref->namelen,
backref->index, -1);
if (IS_ERR(di)) {
ret = PTR_ERR(di);
- btrfs_free_path(path);
+ btrfs_release_path(&path);
btrfs_commit_transaction(trans, root);
if (ret == -ENOENT)
return 0;
}
if (!di)
- ret = btrfs_del_item(trans, root, path);
+ ret = btrfs_del_item(trans, root, &path);
else
- ret = btrfs_delete_one_dir_name(trans, root, path, di);
+ ret = btrfs_delete_one_dir_name(trans, root, &path, di);
BUG_ON(ret);
- btrfs_free_path(path);
+ btrfs_release_path(&path);
btrfs_commit_transaction(trans, root);
return ret;
}
*/
static int find_normal_file_extent(struct btrfs_root *root, u64 ino)
{
- struct btrfs_path *path;
+ struct btrfs_path path;
struct btrfs_key key;
struct btrfs_key found_key;
struct btrfs_file_extent_item *fi;
u8 type;
int ret = 0;
- path = btrfs_alloc_path();
- if (!path)
- goto out;
+ btrfs_init_path(&path);
key.objectid = ino;
key.type = BTRFS_EXTENT_DATA_KEY;
key.offset = 0;
- ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
+ ret = btrfs_search_slot(NULL, root, &key, &path, 0, 0);
if (ret < 0) {
ret = 0;
goto out;
}
- if (ret && path->slots[0] >= btrfs_header_nritems(path->nodes[0])) {
- ret = btrfs_next_leaf(root, path);
+ if (ret && path.slots[0] >= btrfs_header_nritems(path.nodes[0])) {
+ ret = btrfs_next_leaf(root, &path);
if (ret) {
ret = 0;
goto out;
}
}
while (1) {
- btrfs_item_key_to_cpu(path->nodes[0], &found_key,
- path->slots[0]);
+ btrfs_item_key_to_cpu(path.nodes[0], &found_key,
+ path.slots[0]);
if (found_key.objectid != ino ||
found_key.type != BTRFS_EXTENT_DATA_KEY)
break;
- fi = btrfs_item_ptr(path->nodes[0], path->slots[0],
+ fi = btrfs_item_ptr(path.nodes[0], path.slots[0],
struct btrfs_file_extent_item);
- type = btrfs_file_extent_type(path->nodes[0], fi);
+ type = btrfs_file_extent_type(path.nodes[0], fi);
if (type != BTRFS_FILE_EXTENT_INLINE) {
ret = 1;
goto out;
}
}
out:
- btrfs_free_path(path);
+ btrfs_release_path(&path);
return ret;
}
type_recovered = 1;
filetype = BTRFS_FT_REG_FILE;
} else{
- printf("Can't determint the filetype for inode %llu, assume it is a normal file\n",
+ printf("Can't determine the filetype for inode %llu, assume it is a normal file\n",
rec->ino);
type_recovered = 1;
filetype = BTRFS_FT_REG_FILE;
static int try_repair_inode(struct btrfs_root *root, struct inode_record *rec)
{
struct btrfs_trans_handle *trans;
- struct btrfs_path *path;
+ struct btrfs_path path;
int ret = 0;
if (!(rec->errors & (I_ERR_DIR_ISIZE_WRONG |
I_ERR_FILE_NBYTES_WRONG)))
return rec->errors;
- path = btrfs_alloc_path();
- if (!path)
- return -ENOMEM;
-
/*
* For nlink repair, it may create a dir and add link, so
* 2 for parent(256)'s dir_index and dir_item
* 2 for lost+found dir's dir_index and dir_item for the file
*/
trans = btrfs_start_transaction(root, 7);
- if (IS_ERR(trans)) {
- btrfs_free_path(path);
+ if (IS_ERR(trans))
return PTR_ERR(trans);
- }
+ btrfs_init_path(&path);
if (rec->errors & I_ERR_NO_INODE_ITEM)
- ret = repair_inode_no_item(trans, root, path, rec);
+ ret = repair_inode_no_item(trans, root, &path, rec);
if (!ret && rec->errors & I_ERR_FILE_EXTENT_ORPHAN)
- ret = repair_inode_orphan_extent(trans, root, path, rec);
+ ret = repair_inode_orphan_extent(trans, root, &path, rec);
if (!ret && rec->errors & I_ERR_FILE_EXTENT_DISCOUNT)
- ret = repair_inode_discount_extent(trans, root, path, rec);
+ ret = repair_inode_discount_extent(trans, root, &path, rec);
if (!ret && rec->errors & I_ERR_DIR_ISIZE_WRONG)
- ret = repair_inode_isize(trans, root, path, rec);
+ ret = repair_inode_isize(trans, root, &path, rec);
if (!ret && rec->errors & I_ERR_NO_ORPHAN_ITEM)
- ret = repair_inode_orphan_item(trans, root, path, rec);
+ ret = repair_inode_orphan_item(trans, root, &path, rec);
if (!ret && rec->errors & I_ERR_LINK_COUNT_WRONG)
- ret = repair_inode_nlinks(trans, root, path, rec);
+ ret = repair_inode_nlinks(trans, root, &path, rec);
if (!ret && rec->errors & I_ERR_FILE_NBYTES_WRONG)
- ret = repair_inode_nbytes(trans, root, path, rec);
+ ret = repair_inode_nbytes(trans, root, &path, rec);
btrfs_commit_transaction(trans, root);
- btrfs_free_path(path);
+ btrfs_release_path(&path);
return ret;
}
/*
* We need to record the highest inode number for later 'lost+found'
* dir creation.
- * We must select a ino not used/refered by any existing inode, or
+ * 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.
*/
rec = container_of(cache, struct root_record, cache);
while (!list_empty(&rec->backrefs)) {
- backref = list_entry(rec->backrefs.next,
- struct root_backref, list);
+ backref = to_root_backref(rec->backrefs.next);
list_del(&backref->list);
free(backref);
}
- kfree(rec);
+ free(rec);
}
FREE_EXTENT_CACHE_BASED_TREE(root_recs, free_root_record);
struct cache_tree *corrupt_blocks)
{
struct btrfs_trans_handle *trans;
- struct btrfs_path *path;
+ struct btrfs_path path;
struct btrfs_corrupt_block *corrupt;
struct cache_extent *cache;
struct btrfs_key key;
if (cache_tree_empty(corrupt_blocks))
return 0;
- path = btrfs_alloc_path();
- if (!path)
- return -ENOMEM;
-
trans = btrfs_start_transaction(root, 1);
if (IS_ERR(trans)) {
ret = PTR_ERR(trans);
fprintf(stderr, "Error starting transaction: %s\n",
strerror(-ret));
- goto out_free_path;
+ return ret;
}
+ btrfs_init_path(&path);
cache = first_cache_extent(corrupt_blocks);
while (cache) {
corrupt = container_of(cache, struct btrfs_corrupt_block,
cache);
level = corrupt->level;
- path->lowest_level = level;
+ path.lowest_level = level;
key.objectid = corrupt->key.objectid;
key.type = corrupt->key.type;
key.offset = corrupt->key.offset;
* so ins_len set to 0 here.
* Balance will be done after all corrupt node/leaf is deleted.
*/
- ret = btrfs_search_slot(trans, root, &key, path, 0, 1);
+ ret = btrfs_search_slot(trans, root, &key, &path, 0, 1);
if (ret < 0)
goto out;
- offset = btrfs_node_blockptr(path->nodes[level],
- path->slots[level]);
+ offset = btrfs_node_blockptr(path.nodes[level],
+ path.slots[level]);
/* Remove the ptr */
- ret = btrfs_del_ptr(trans, root, path, level,
- path->slots[level]);
+ ret = btrfs_del_ptr(trans, root, &path, level,
+ path.slots[level]);
if (ret < 0)
goto out;
/*
* Remove the corresponding extent
* return value is not concerned.
*/
- btrfs_release_path(path);
+ btrfs_release_path(&path);
ret = btrfs_free_extent(trans, root, offset, root->nodesize,
0, root->root_key.objectid,
level - 1, 0);
corrupt = container_of(cache, struct btrfs_corrupt_block,
cache);
memcpy(&key, &corrupt->key, sizeof(key));
- ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
+ ret = btrfs_search_slot(trans, root, &key, &path, -1, 1);
if (ret < 0)
goto out;
/* return will always >0 since it won't find the item */
ret = 0;
- btrfs_release_path(path);
+ btrfs_release_path(&path);
cache = next_cache_extent(cache);
}
out:
btrfs_commit_transaction(trans, root);
-out_free_path:
- btrfs_free_path(path);
+ btrfs_release_path(&path);
return ret;
}
struct orphan_data_extent *orphan;
struct orphan_data_extent *tmp;
enum btrfs_tree_block_status status;
+ struct node_refs nrefs;
/*
* Reuse the corrupt_block cache tree to record corrupted tree block
memset(&root_node, 0, sizeof(root_node));
cache_tree_init(&root_node.root_cache);
cache_tree_init(&root_node.inode_cache);
+ memset(&nrefs, 0, sizeof(nrefs));
/* Move the orphan extent record to corresponding inode_record */
list_for_each_entry_safe(orphan, tmp,
btrfs_disk_key_to_cpu(&key, &root_item->drop_progress);
level = root_item->drop_level;
path.lowest_level = level;
+ if (level > btrfs_header_level(root->node) ||
+ level >= BTRFS_MAX_LEVEL) {
+ error("ignoring invalid drop level: %u", level);
+ goto skip_walking;
+ }
wret = btrfs_search_slot(NULL, root, &key, &path, 0, 0);
if (wret < 0)
goto skip_walking;
}
while (1) {
- wret = walk_down_tree(root, &path, wc, &level);
+ wret = walk_down_tree(root, &path, wc, &level, &nrefs);
if (wret < 0)
ret = wret;
if (wret != 0)
int err = 0;
while(cur != &rec->backrefs) {
- back = list_entry(cur, struct extent_backref, list);
+ back = to_extent_backref(cur);
cur = cur->next;
if (!back->found_extent_tree) {
err = 1;
if (!print_errs)
goto out;
if (back->is_data) {
- dback = (struct data_backref *)back;
+ dback = to_data_backref(back);
fprintf(stderr, "Backref %llu %s %llu"
" owner %llu offset %llu num_refs %lu"
" not found in extent tree\n",
(unsigned long long)dback->offset,
(unsigned long)dback->num_refs);
} else {
- tback = (struct tree_backref *)back;
+ tback = to_tree_backref(back);
fprintf(stderr, "Backref %llu parent %llu"
" root %llu not found in extent tree\n",
(unsigned long long)rec->start,
err = 1;
if (!print_errs)
goto out;
- tback = (struct tree_backref *)back;
+ tback = to_tree_backref(back);
fprintf(stderr, "Backref %llu %s %llu not referenced back %p\n",
(unsigned long long)rec->start,
back->full_backref ? "parent" : "root",
(unsigned long long)tback->root, back);
}
if (back->is_data) {
- dback = (struct data_backref *)back;
+ dback = to_data_backref(back);
if (dback->found_ref != dback->num_refs) {
err = 1;
if (!print_errs)
if (!back->is_data) {
found += 1;
} else {
- dback = (struct data_backref *)back;
+ dback = to_data_backref(back);
found += dback->found_ref;
}
}
struct list_head *cur;
while (!list_empty(&rec->backrefs)) {
cur = rec->backrefs.next;
- back = list_entry(cur, struct extent_backref, list);
+ back = to_extent_backref(cur);
list_del(cur);
free(back);
}
continue;
if (node->full_backref)
continue;
- back = (struct tree_backref *)node;
+ back = to_tree_backref(node);
if (btrfs_header_owner(buf) == back->root)
return 0;
}
int is_extent = 0;
while(cur != &rec->backrefs) {
- node = list_entry(cur, struct extent_backref, list);
+ node = to_extent_backref(cur);
cur = cur->next;
if (node->is_data)
return 0;
- back = (struct tree_backref *)node;
+ back = to_tree_backref(node);
if (node->full_backref)
return 0;
if (back->root == BTRFS_EXTENT_TREE_OBJECTID)
struct ulist *roots;
struct ulist_node *node;
struct btrfs_root *search_root;
- struct btrfs_path *path;
+ struct btrfs_path path;
struct ulist_iterator iter;
struct btrfs_key root_key, key;
int ret;
status != BTRFS_TREE_BLOCK_INVALID_OFFSETS)
return -EIO;
- path = btrfs_alloc_path();
- if (!path)
- return -EIO;
-
- ret = btrfs_find_all_roots(NULL, root->fs_info, buf->start,
- 0, &roots);
- if (ret) {
- btrfs_free_path(path);
+ ret = btrfs_find_all_roots(NULL, root->fs_info, buf->start, 0, &roots);
+ if (ret)
return -EIO;
- }
+ btrfs_init_path(&path);
ULIST_ITER_INIT(&iter);
while ((node = ulist_next(roots, &iter))) {
root_key.objectid = node->val;
break;
}
- path->lowest_level = btrfs_header_level(buf);
- path->skip_check_block = 1;
- if (path->lowest_level)
+ path.lowest_level = btrfs_header_level(buf);
+ path.skip_check_block = 1;
+ if (path.lowest_level)
btrfs_node_key_to_cpu(buf, &key, 0);
else
btrfs_item_key_to_cpu(buf, &key, 0);
- ret = btrfs_search_slot(trans, search_root, &key, path, 0, 1);
+ ret = btrfs_search_slot(trans, search_root, &key, &path, 0, 1);
if (ret) {
ret = -EIO;
btrfs_commit_transaction(trans, search_root);
break;
}
if (status == BTRFS_TREE_BLOCK_BAD_KEY_ORDER)
- ret = fix_key_order(trans, search_root, path);
+ ret = fix_key_order(trans, search_root, &path);
else if (status == BTRFS_TREE_BLOCK_INVALID_OFFSETS)
- ret = fix_item_offset(trans, search_root, path);
+ ret = fix_item_offset(trans, search_root, &path);
if (ret) {
btrfs_commit_transaction(trans, search_root);
break;
}
- btrfs_release_path(path);
+ btrfs_release_path(&path);
btrfs_commit_transaction(trans, search_root);
}
ulist_free(roots);
- btrfs_free_path(path);
+ btrfs_release_path(&path);
return ret;
}
} else {
/*
* Signal to callers we need to start the scan over
- * again since we'll have cow'ed blocks.
+ * again since we'll have cowed blocks.
*/
ret = -EAGAIN;
}
struct tree_backref *back;
while(cur != &rec->backrefs) {
- node = list_entry(cur, struct extent_backref, list);
+ node = to_extent_backref(cur);
cur = cur->next;
if (node->is_data)
continue;
- back = (struct tree_backref *)node;
+ back = to_tree_backref(node);
if (parent > 0) {
if (!node->full_backref)
continue;
struct data_backref *back;
while(cur != &rec->backrefs) {
- node = list_entry(cur, struct extent_backref, list);
+ node = to_extent_backref(cur);
cur = cur->next;
if (!node->is_data)
continue;
- back = (struct data_backref *)node;
+ back = to_data_backref(node);
if (parent > 0) {
if (!node->full_backref)
continue;
struct tree_backref *tback;
u64 bg_type;
- node = list_entry(rec->backrefs.next, struct extent_backref,
- list);
+ node = to_extent_backref(rec->backrefs.next);
if (node->is_data) {
/* tree block shouldn't have data backref */
rec->wrong_chunk_type = 1;
}
}
+/*
+ * Allocate a new extent record, fill default values from @tmpl and insert int
+ * @extent_cache. Caller is supposed to make sure the [start,nr) is not in
+ * the cache, otherwise it fails.
+ */
+static int add_extent_rec_nolookup(struct cache_tree *extent_cache,
+ struct extent_record *tmpl)
+{
+ struct extent_record *rec;
+ int ret = 0;
+
+ rec = malloc(sizeof(*rec));
+ if (!rec)
+ return -ENOMEM;
+ rec->start = tmpl->start;
+ rec->max_size = tmpl->max_size;
+ rec->nr = max(tmpl->nr, tmpl->max_size);
+ rec->found_rec = tmpl->found_rec;
+ rec->content_checked = tmpl->content_checked;
+ rec->owner_ref_checked = tmpl->owner_ref_checked;
+ rec->num_duplicates = 0;
+ rec->metadata = tmpl->metadata;
+ rec->flag_block_full_backref = FLAG_UNSET;
+ rec->bad_full_backref = 0;
+ rec->crossing_stripes = 0;
+ rec->wrong_chunk_type = 0;
+ rec->is_root = tmpl->is_root;
+ rec->refs = tmpl->refs;
+ rec->extent_item_refs = tmpl->extent_item_refs;
+ rec->parent_generation = tmpl->parent_generation;
+ INIT_LIST_HEAD(&rec->backrefs);
+ INIT_LIST_HEAD(&rec->dups);
+ INIT_LIST_HEAD(&rec->list);
+ memcpy(&rec->parent_key, &tmpl->parent_key, sizeof(tmpl->parent_key));
+ rec->cache.start = tmpl->start;
+ rec->cache.size = tmpl->nr;
+ ret = insert_cache_extent(extent_cache, &rec->cache);
+ if (ret) {
+ free(rec);
+ return ret;
+ }
+ bytes_used += rec->nr;
+
+ if (tmpl->metadata)
+ rec->crossing_stripes = check_crossing_stripes(global_info,
+ rec->start, global_info->tree_root->nodesize);
+ check_extent_type(rec);
+ return ret;
+}
+
+/*
+ * Lookup and modify an extent, some values of @tmpl are interpreted verbatim,
+ * some are hints:
+ * - refs - if found, increase refs
+ * - is_root - if found, set
+ * - content_checked - if found, set
+ * - owner_ref_checked - if found, set
+ *
+ * If not found, create a new one, initialize and insert.
+ */
static int add_extent_rec(struct cache_tree *extent_cache,
- struct btrfs_key *parent_key, u64 parent_gen,
- u64 start, u64 nr, u64 extent_item_refs,
- int is_root, int inc_ref, int set_checked,
- int metadata, int extent_rec, u64 max_size)
+ struct extent_record *tmpl)
{
struct extent_record *rec;
struct cache_extent *cache;
int ret = 0;
int dup = 0;
- cache = lookup_cache_extent(extent_cache, start, nr);
+ cache = lookup_cache_extent(extent_cache, tmpl->start, tmpl->nr);
if (cache) {
rec = container_of(cache, struct extent_record, cache);
- if (inc_ref)
+ if (tmpl->refs)
rec->refs++;
if (rec->nr == 1)
- rec->nr = max(nr, max_size);
+ rec->nr = max(tmpl->nr, tmpl->max_size);
/*
* We need to make sure to reset nr to whatever the extent
* record says was the real size, this way we can compare it to
* the backrefs.
*/
- if (extent_rec) {
- if (start != rec->start || rec->found_rec) {
+ if (tmpl->found_rec) {
+ if (tmpl->start != rec->start || rec->found_rec) {
struct extent_record *tmp;
dup = 1;
tmp = malloc(sizeof(*tmp));
if (!tmp)
return -ENOMEM;
- tmp->start = start;
- tmp->max_size = max_size;
- tmp->nr = nr;
+ tmp->start = tmpl->start;
+ tmp->max_size = tmpl->max_size;
+ tmp->nr = tmpl->nr;
tmp->found_rec = 1;
- tmp->metadata = metadata;
- tmp->extent_item_refs = extent_item_refs;
+ tmp->metadata = tmpl->metadata;
+ tmp->extent_item_refs = tmpl->extent_item_refs;
INIT_LIST_HEAD(&tmp->list);
list_add_tail(&tmp->list, &rec->dups);
rec->num_duplicates++;
} else {
- rec->nr = nr;
+ rec->nr = tmpl->nr;
rec->found_rec = 1;
}
}
- if (extent_item_refs && !dup) {
+ if (tmpl->extent_item_refs && !dup) {
if (rec->extent_item_refs) {
fprintf(stderr, "block %llu rec "
"extent_item_refs %llu, passed %llu\n",
- (unsigned long long)start,
+ (unsigned long long)tmpl->start,
(unsigned long long)
rec->extent_item_refs,
- (unsigned long long)extent_item_refs);
+ (unsigned long long)tmpl->extent_item_refs);
}
- rec->extent_item_refs = extent_item_refs;
+ rec->extent_item_refs = tmpl->extent_item_refs;
}
- if (is_root)
+ if (tmpl->is_root)
rec->is_root = 1;
- if (set_checked) {
+ if (tmpl->content_checked)
rec->content_checked = 1;
+ if (tmpl->owner_ref_checked)
rec->owner_ref_checked = 1;
- }
-
- if (parent_key)
- btrfs_cpu_key_to_disk(&rec->parent_key, parent_key);
- if (parent_gen)
- rec->parent_generation = parent_gen;
-
- if (rec->max_size < max_size)
- rec->max_size = max_size;
+ memcpy(&rec->parent_key, &tmpl->parent_key,
+ sizeof(tmpl->parent_key));
+ if (tmpl->parent_generation)
+ rec->parent_generation = tmpl->parent_generation;
+ if (rec->max_size < tmpl->max_size)
+ rec->max_size = tmpl->max_size;
/*
* A metadata extent can't cross stripe_len boundary, otherwise
* As now stripe_len is fixed to BTRFS_STRIPE_LEN, just check
* it.
*/
- if (metadata && check_crossing_stripes(rec->start,
- rec->max_size))
- rec->crossing_stripes = 1;
+ if (tmpl->metadata)
+ rec->crossing_stripes = check_crossing_stripes(
+ global_info, rec->start,
+ global_info->tree_root->nodesize);
check_extent_type(rec);
maybe_free_extent_rec(extent_cache, rec);
return ret;
}
- rec = malloc(sizeof(*rec));
- if (!rec)
- return -ENOMEM;
- rec->start = start;
- rec->max_size = max_size;
- rec->nr = max(nr, max_size);
- rec->found_rec = !!extent_rec;
- rec->content_checked = 0;
- rec->owner_ref_checked = 0;
- rec->num_duplicates = 0;
- rec->metadata = metadata;
- rec->flag_block_full_backref = -1;
- rec->bad_full_backref = 0;
- rec->crossing_stripes = 0;
- rec->wrong_chunk_type = 0;
- INIT_LIST_HEAD(&rec->backrefs);
- INIT_LIST_HEAD(&rec->dups);
- INIT_LIST_HEAD(&rec->list);
-
- if (is_root)
- rec->is_root = 1;
- else
- rec->is_root = 0;
-
- if (inc_ref)
- rec->refs = 1;
- else
- rec->refs = 0;
-
- if (extent_item_refs)
- rec->extent_item_refs = extent_item_refs;
- else
- rec->extent_item_refs = 0;
-
- if (parent_key)
- btrfs_cpu_key_to_disk(&rec->parent_key, parent_key);
- else
- memset(&rec->parent_key, 0, sizeof(*parent_key));
-
- if (parent_gen)
- rec->parent_generation = parent_gen;
- else
- rec->parent_generation = 0;
- rec->cache.start = start;
- rec->cache.size = nr;
- ret = insert_cache_extent(extent_cache, &rec->cache);
- BUG_ON(ret);
- bytes_used += nr;
- if (set_checked) {
- rec->content_checked = 1;
- rec->owner_ref_checked = 1;
- }
+ ret = add_extent_rec_nolookup(extent_cache, tmpl);
- if (metadata)
- if (check_crossing_stripes(rec->start, rec->max_size))
- rec->crossing_stripes = 1;
- check_extent_type(rec);
return ret;
}
struct extent_record *rec;
struct tree_backref *back;
struct cache_extent *cache;
+ int ret;
cache = lookup_cache_extent(extent_cache, bytenr, 1);
if (!cache) {
- add_extent_rec(extent_cache, NULL, 0, bytenr,
- 1, 0, 0, 0, 0, 1, 0, 0);
+ struct extent_record tmpl;
+
+ memset(&tmpl, 0, sizeof(tmpl));
+ tmpl.start = bytenr;
+ tmpl.nr = 1;
+ tmpl.metadata = 1;
+
+ ret = add_extent_rec_nolookup(extent_cache, &tmpl);
+ if (ret)
+ return ret;
+
+ /* really a bug in cache_extent implement now */
cache = lookup_cache_extent(extent_cache, bytenr, 1);
if (!cache)
- abort();
+ return -ENOENT;
}
rec = container_of(cache, struct extent_record, cache);
if (rec->start != bytenr) {
- abort();
+ /*
+ * Several cause, from unaligned bytenr to over lapping extents
+ */
+ return -EEXIST;
}
back = find_tree_backref(rec, parent, root);
if (!back) {
back = alloc_tree_backref(rec, parent, root);
- BUG_ON(!back);
+ if (!back)
+ return -ENOMEM;
}
if (found_ref) {
struct extent_record *rec;
struct data_backref *back;
struct cache_extent *cache;
+ int ret;
cache = lookup_cache_extent(extent_cache, bytenr, 1);
if (!cache) {
- add_extent_rec(extent_cache, NULL, 0, bytenr, 1, 0, 0, 0, 0,
- 0, 0, max_size);
+ struct extent_record tmpl;
+
+ memset(&tmpl, 0, sizeof(tmpl));
+ tmpl.start = bytenr;
+ tmpl.nr = 1;
+ tmpl.max_size = max_size;
+
+ ret = add_extent_rec_nolookup(extent_cache, &tmpl);
+ if (ret)
+ return ret;
+
cache = lookup_cache_extent(extent_cache, bytenr, 1);
if (!cache)
abort();
{
struct btrfs_extent_ref_v0 *ref0;
struct btrfs_key key;
+ int ret;
btrfs_item_key_to_cpu(leaf, &key, slot);
ref0 = btrfs_item_ptr(leaf, slot, struct btrfs_extent_ref_v0);
if (btrfs_ref_objectid_v0(leaf, ref0) < BTRFS_FIRST_FREE_OBJECTID) {
- add_tree_backref(extent_cache, key.objectid, key.offset, 0, 0);
+ ret = add_tree_backref(extent_cache, key.objectid, key.offset,
+ 0, 0);
} else {
- add_data_backref(extent_cache, key.objectid, key.offset, 0,
- 0, 0, btrfs_ref_count_v0(leaf, ref0), 0, 0);
+ ret = add_data_backref(extent_cache, key.objectid, key.offset,
+ 0, 0, 0, btrfs_ref_count_v0(leaf, ref0), 0, 0);
}
- return 0;
+ return ret;
}
#endif
int slot)
{
struct chunk_record *rec;
+ struct btrfs_chunk *chunk;
int ret = 0;
+ chunk = btrfs_item_ptr(eb, slot, struct btrfs_chunk);
+ /*
+ * Do extra check for this chunk item,
+ *
+ * It's still possible one can craft a leaf with CHUNK_ITEM, with
+ * wrong onwer(3) out of chunk tree, to pass both chunk tree check
+ * and owner<->key_type check.
+ */
+ ret = btrfs_check_chunk_valid(global_info->tree_root, eb, chunk, slot,
+ key->offset);
+ if (ret < 0) {
+ error("chunk(%llu, %llu) is not valid, ignore it",
+ key->offset, btrfs_chunk_length(eb, chunk));
+ return 0;
+ }
rec = btrfs_new_chunk_record(eb, key, slot);
ret = insert_cache_extent(chunk_cache, &rec->cache);
if (ret) {
struct btrfs_extent_data_ref *dref;
struct btrfs_shared_data_ref *sref;
struct btrfs_key key;
+ struct extent_record tmpl;
unsigned long end;
unsigned long ptr;
+ int ret;
int type;
u32 item_size = btrfs_item_size_nr(eb, slot);
u64 refs = 0;
if (key.type == BTRFS_METADATA_ITEM_KEY) {
metadata = 1;
- num_bytes = root->leafsize;
+ num_bytes = root->nodesize;
} else {
num_bytes = key.offset;
}
+ if (!IS_ALIGNED(key.objectid, root->sectorsize)) {
+ error("ignoring invalid extent, bytenr %llu is not aligned to %u",
+ key.objectid, root->sectorsize);
+ return -EIO;
+ }
if (item_size < sizeof(*ei)) {
#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
struct btrfs_extent_item_v0 *ei0;
#else
BUG();
#endif
- return add_extent_rec(extent_cache, NULL, 0, key.objectid,
- num_bytes, refs, 0, 0, 0, metadata, 1,
- num_bytes);
+ memset(&tmpl, 0, sizeof(tmpl));
+ tmpl.start = key.objectid;
+ tmpl.nr = num_bytes;
+ tmpl.extent_item_refs = refs;
+ tmpl.metadata = metadata;
+ tmpl.found_rec = 1;
+ tmpl.max_size = num_bytes;
+
+ return add_extent_rec(extent_cache, &tmpl);
}
ei = btrfs_item_ptr(eb, slot, struct btrfs_extent_item);
metadata = 1;
else
metadata = 0;
+ if (metadata && num_bytes != root->nodesize) {
+ error("ignore invalid metadata extent, length %llu does not equal to %u",
+ num_bytes, root->nodesize);
+ return -EIO;
+ }
+ if (!metadata && !IS_ALIGNED(num_bytes, root->sectorsize)) {
+ error("ignore invalid data extent, length %llu is not aligned to %u",
+ num_bytes, root->sectorsize);
+ return -EIO;
+ }
- add_extent_rec(extent_cache, NULL, 0, key.objectid, num_bytes,
- refs, 0, 0, 0, metadata, 1, num_bytes);
+ memset(&tmpl, 0, sizeof(tmpl));
+ tmpl.start = key.objectid;
+ tmpl.nr = num_bytes;
+ tmpl.extent_item_refs = refs;
+ tmpl.metadata = metadata;
+ tmpl.found_rec = 1;
+ tmpl.max_size = num_bytes;
+ add_extent_rec(extent_cache, &tmpl);
ptr = (unsigned long)(ei + 1);
if (btrfs_extent_flags(eb, ei) & BTRFS_EXTENT_FLAG_TREE_BLOCK &&
offset = btrfs_extent_inline_ref_offset(eb, iref);
switch (type) {
case BTRFS_TREE_BLOCK_REF_KEY:
- add_tree_backref(extent_cache, key.objectid,
- 0, offset, 0);
+ ret = add_tree_backref(extent_cache, key.objectid,
+ 0, offset, 0);
+ if (ret < 0)
+ error("add_tree_backref failed: %s",
+ strerror(-ret));
break;
case BTRFS_SHARED_BLOCK_REF_KEY:
- add_tree_backref(extent_cache, key.objectid,
- offset, 0, 0);
+ ret = add_tree_backref(extent_cache, key.objectid,
+ offset, 0, 0);
+ if (ret < 0)
+ error("add_tree_backref failed: %s",
+ strerror(-ret));
break;
case BTRFS_EXTENT_DATA_REF_KEY:
dref = (struct btrfs_extent_data_ref *)(&iref->offset);
continue;
if (logical[nr] == offset) {
if (stripe_len >= bytes) {
- kfree(logical);
+ free(logical);
return 0;
}
bytes -= stripe_len;
} else if (logical[nr] < offset) {
if (logical[nr] + stripe_len >=
offset + bytes) {
- kfree(logical);
+ free(logical);
return 0;
}
bytes = (offset + bytes) -
offset,
logical[nr] - offset);
if (ret) {
- kfree(logical);
+ free(logical);
return ret;
}
}
}
- kfree(logical);
+ free(logical);
}
entry = btrfs_find_free_space(cache->free_space_ctl, offset, bytes);
static int verify_space_cache(struct btrfs_root *root,
struct btrfs_block_group_cache *cache)
{
- struct btrfs_path *path;
+ struct btrfs_path path;
struct extent_buffer *leaf;
struct btrfs_key key;
u64 last;
int ret = 0;
- path = btrfs_alloc_path();
- if (!path)
- return -ENOMEM;
-
root = root->fs_info->extent_root;
last = max_t(u64, cache->key.objectid, BTRFS_SUPER_INFO_OFFSET);
+ btrfs_init_path(&path);
key.objectid = last;
key.offset = 0;
key.type = BTRFS_EXTENT_ITEM_KEY;
-
- ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
+ ret = btrfs_search_slot(NULL, root, &key, &path, 0, 0);
if (ret < 0)
goto out;
ret = 0;
while (1) {
- if (path->slots[0] >= btrfs_header_nritems(path->nodes[0])) {
- ret = btrfs_next_leaf(root, path);
+ if (path.slots[0] >= btrfs_header_nritems(path.nodes[0])) {
+ ret = btrfs_next_leaf(root, &path);
if (ret < 0)
goto out;
if (ret > 0) {
break;
}
}
- leaf = path->nodes[0];
- btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
+ leaf = path.nodes[0];
+ btrfs_item_key_to_cpu(leaf, &key, path.slots[0]);
if (key.objectid >= cache->key.offset + cache->key.objectid)
break;
if (key.type != BTRFS_EXTENT_ITEM_KEY &&
key.type != BTRFS_METADATA_ITEM_KEY) {
- path->slots[0]++;
+ path.slots[0]++;
continue;
}
if (key.type == BTRFS_EXTENT_ITEM_KEY)
last = key.objectid + key.offset;
else
- last = key.objectid + root->leafsize;
- path->slots[0]++;
+ last = key.objectid + root->nodesize;
+ path.slots[0]++;
continue;
}
if (key.type == BTRFS_EXTENT_ITEM_KEY)
last = key.objectid + key.offset;
else
- last = key.objectid + root->leafsize;
- path->slots[0]++;
+ last = key.objectid + root->nodesize;
+ path.slots[0]++;
}
if (last < cache->key.objectid + cache->key.offset)
cache->key.offset - last);
out:
- btrfs_free_path(path);
+ btrfs_release_path(&path);
if (!ret &&
!RB_EMPTY_ROOT(&cache->free_space_ctl->free_space_offset)) {
ret = verify_space_cache(root, cache);
if (ret) {
- fprintf(stderr, "cache appears valid but isnt %Lu\n",
+ fprintf(stderr, "cache appears valid but isn't %Lu\n",
cache->key.objectid);
error++;
}
csum = btrfs_csum_data(NULL, (char *)data + tmp,
csum, root->sectorsize);
- btrfs_csum_final(csum, (char *)&csum);
+ btrfs_csum_final(csum, (u8 *)&csum);
csum_offset = leaf_offset +
tmp / root->sectorsize * csum_size;
static int check_extent_exists(struct btrfs_root *root, u64 bytenr,
u64 num_bytes)
{
- struct btrfs_path *path;
+ struct btrfs_path path;
struct extent_buffer *leaf;
struct btrfs_key key;
int ret;
- path = btrfs_alloc_path();
- if (!path) {
- fprintf(stderr, "Error allocing path\n");
- return -ENOMEM;
- }
-
+ btrfs_init_path(&path);
key.objectid = bytenr;
key.type = BTRFS_EXTENT_ITEM_KEY;
key.offset = (u64)-1;
again:
- ret = btrfs_search_slot(NULL, root->fs_info->extent_root, &key, path,
+ ret = btrfs_search_slot(NULL, root->fs_info->extent_root, &key, &path,
0, 0);
if (ret < 0) {
fprintf(stderr, "Error looking up extent record %d\n", ret);
- btrfs_free_path(path);
+ btrfs_release_path(&path);
return ret;
} else if (ret) {
- if (path->slots[0] > 0) {
- path->slots[0]--;
+ if (path.slots[0] > 0) {
+ path.slots[0]--;
} else {
- ret = btrfs_prev_leaf(root, path);
+ ret = btrfs_prev_leaf(root, &path);
if (ret < 0) {
goto out;
} else if (ret > 0) {
}
}
- btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
+ btrfs_item_key_to_cpu(path.nodes[0], &key, path.slots[0]);
/*
* Block group items come before extent items if they have the same
- * bytenr, so walk back one more just in case. Dear future traveler,
+ * bytenr, so walk back one more just in case. Dear future traveller,
* first congrats on mastering time travel. Now if it's not too much
* trouble could you go back to 2006 and tell Chris to make the
* BLOCK_GROUP_ITEM_KEY (and BTRFS_*_REF_KEY) lower than the
* EXTENT_ITEM_KEY please?
*/
while (key.type > BTRFS_EXTENT_ITEM_KEY) {
- if (path->slots[0] > 0) {
- path->slots[0]--;
+ if (path.slots[0] > 0) {
+ path.slots[0]--;
} else {
- ret = btrfs_prev_leaf(root, path);
+ ret = btrfs_prev_leaf(root, &path);
if (ret < 0) {
goto out;
} else if (ret > 0) {
goto out;
}
}
- btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
+ btrfs_item_key_to_cpu(path.nodes[0], &key, path.slots[0]);
}
while (num_bytes) {
- if (path->slots[0] >= btrfs_header_nritems(path->nodes[0])) {
- ret = btrfs_next_leaf(root, path);
+ if (path.slots[0] >= btrfs_header_nritems(path.nodes[0])) {
+ ret = btrfs_next_leaf(root, &path);
if (ret < 0) {
fprintf(stderr, "Error going to next leaf "
"%d\n", ret);
- btrfs_free_path(path);
+ btrfs_release_path(&path);
return ret;
} else if (ret) {
break;
}
}
- leaf = path->nodes[0];
- btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
+ leaf = path.nodes[0];
+ btrfs_item_key_to_cpu(leaf, &key, path.slots[0]);
if (key.type != BTRFS_EXTENT_ITEM_KEY) {
- path->slots[0]++;
+ path.slots[0]++;
continue;
}
if (key.objectid + key.offset < bytenr) {
- path->slots[0]++;
+ path.slots[0]++;
continue;
}
if (key.objectid > bytenr + num_bytes)
* in real life, but no harm in coding it up
* anyway just in case.
*/
- btrfs_release_path(path);
+ btrfs_release_path(&path);
ret = check_extent_exists(root, new_start,
new_bytes);
if (ret) {
}
num_bytes = key.objectid - bytenr;
}
- path->slots[0]++;
+ path.slots[0]++;
}
ret = 0;
ret = 1;
}
- btrfs_free_path(path);
+ btrfs_release_path(&path);
return ret;
}
static int check_csums(struct btrfs_root *root)
{
- struct btrfs_path *path;
+ struct btrfs_path path;
struct extent_buffer *leaf;
struct btrfs_key key;
u64 offset = 0, num_bytes = 0;
return -ENOENT;
}
+ btrfs_init_path(&path);
key.objectid = BTRFS_EXTENT_CSUM_OBJECTID;
key.type = BTRFS_EXTENT_CSUM_KEY;
key.offset = 0;
-
- path = btrfs_alloc_path();
- if (!path)
- return -ENOMEM;
-
- ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
+ ret = btrfs_search_slot(NULL, root, &key, &path, 0, 0);
if (ret < 0) {
fprintf(stderr, "Error searching csum tree %d\n", ret);
- btrfs_free_path(path);
+ btrfs_release_path(&path);
return ret;
}
- if (ret > 0 && path->slots[0])
- path->slots[0]--;
+ if (ret > 0 && path.slots[0])
+ path.slots[0]--;
ret = 0;
while (1) {
- if (path->slots[0] >= btrfs_header_nritems(path->nodes[0])) {
- ret = btrfs_next_leaf(root, path);
+ if (path.slots[0] >= btrfs_header_nritems(path.nodes[0])) {
+ ret = btrfs_next_leaf(root, &path);
if (ret < 0) {
fprintf(stderr, "Error going to next leaf "
"%d\n", ret);
if (ret)
break;
}
- leaf = path->nodes[0];
+ leaf = path.nodes[0];
- btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
+ btrfs_item_key_to_cpu(leaf, &key, path.slots[0]);
if (key.type != BTRFS_EXTENT_CSUM_KEY) {
- path->slots[0]++;
+ path.slots[0]++;
continue;
}
- data_len = (btrfs_item_size_nr(leaf, path->slots[0]) /
+ data_len = (btrfs_item_size_nr(leaf, path.slots[0]) /
csum_size) * root->sectorsize;
if (!check_data_csum)
goto skip_csum_check;
- leaf_offset = btrfs_item_ptr_offset(leaf, path->slots[0]);
+ leaf_offset = btrfs_item_ptr_offset(leaf, path.slots[0]);
ret = check_extent_csums(root, key.offset, data_len,
leaf_offset, leaf);
if (ret)
num_bytes = 0;
}
num_bytes += data_len;
- path->slots[0]++;
+ path.slots[0]++;
}
- btrfs_free_path(path);
+ btrfs_release_path(&path);
return errors;
}
* 1) If BTRFS_HEADER_FLAG_RELOC is set then we have FULL_BACKREF set.
* 2) If btrfs_header_owner(buf) no longer points to buf then we have
* FULL_BACKREF set.
- * 3) We cow'ed the block walking down a reloc tree. This is impossible to tell
+ * 3) We cowed the block walking down a reloc tree. This is impossible to tell
* if it happened after the relocation occurred since we'll have dropped the
* reloc root, so it's entirely possible to have FULL_BACKREF set on buf and
* have no real way to know for sure.
cache = lookup_cache_extent(extent_cache, buf->start, 1);
/* we have added this extent before */
- BUG_ON(!cache);
+ if (!cache)
+ return -ENOENT;
+
rec = container_of(cache, struct extent_record, cache);
/*
goto full_backref;
normal:
*flags = 0;
- if (rec->flag_block_full_backref != -1 &&
+ if (rec->flag_block_full_backref != FLAG_UNSET &&
rec->flag_block_full_backref != 0)
rec->bad_full_backref = 1;
return 0;
full_backref:
*flags |= BTRFS_BLOCK_FLAG_FULL_BACKREF;
- if (rec->flag_block_full_backref != -1 &&
+ if (rec->flag_block_full_backref != FLAG_UNSET &&
rec->flag_block_full_backref != 1)
rec->bad_full_backref = 1;
return 0;
}
+static void report_mismatch_key_root(u8 key_type, u64 rootid)
+{
+ fprintf(stderr, "Invalid key type(");
+ print_key_type(stderr, 0, key_type);
+ fprintf(stderr, ") found in root(");
+ print_objectid(stderr, rootid, 0);
+ fprintf(stderr, ")\n");
+}
+
+/*
+ * Check if the key is valid with its extent buffer.
+ *
+ * This is a early check in case invalid key exists in a extent buffer
+ * This is not comprehensive yet, but should prevent wrong key/item passed
+ * further
+ */
+static int check_type_with_root(u64 rootid, u8 key_type)
+{
+ switch (key_type) {
+ /* Only valid in chunk tree */
+ case BTRFS_DEV_ITEM_KEY:
+ case BTRFS_CHUNK_ITEM_KEY:
+ if (rootid != BTRFS_CHUNK_TREE_OBJECTID)
+ goto err;
+ break;
+ /* valid in csum and log tree */
+ case BTRFS_CSUM_TREE_OBJECTID:
+ if (!(rootid == BTRFS_TREE_LOG_OBJECTID ||
+ is_fstree(rootid)))
+ goto err;
+ break;
+ case BTRFS_EXTENT_ITEM_KEY:
+ case BTRFS_METADATA_ITEM_KEY:
+ case BTRFS_BLOCK_GROUP_ITEM_KEY:
+ if (rootid != BTRFS_EXTENT_TREE_OBJECTID)
+ goto err;
+ break;
+ case BTRFS_ROOT_ITEM_KEY:
+ if (rootid != BTRFS_ROOT_TREE_OBJECTID)
+ goto err;
+ break;
+ case BTRFS_DEV_EXTENT_KEY:
+ if (rootid != BTRFS_DEV_TREE_OBJECTID)
+ goto err;
+ break;
+ }
+ return 0;
+err:
+ report_mismatch_key_root(key_type, rootid);
+ return -EINVAL;
+}
+
static int run_next_block(struct btrfs_root *root,
struct block_info *bits,
int bits_nr,
for (i = 0; i < nritems; i++) {
struct btrfs_file_extent_item *fi;
btrfs_item_key_to_cpu(buf, &key, i);
+ /*
+ * Check key type against the leaf owner.
+ * Could filter quite a lot of early error if
+ * owner is correct
+ */
+ if (check_type_with_root(btrfs_header_owner(buf),
+ key.type)) {
+ fprintf(stderr, "ignoring invalid key\n");
+ continue;
+ }
if (key.type == BTRFS_EXTENT_ITEM_KEY) {
process_extent_item(root, extent_cache, buf,
i);
}
if (key.type == BTRFS_TREE_BLOCK_REF_KEY) {
- add_tree_backref(extent_cache, key.objectid, 0,
- key.offset, 0);
+ ret = add_tree_backref(extent_cache,
+ key.objectid, 0, key.offset, 0);
+ if (ret < 0)
+ error("add_tree_backref failed: %s",
+ strerror(-ret));
continue;
}
if (key.type == BTRFS_SHARED_BLOCK_REF_KEY) {
- add_tree_backref(extent_cache, key.objectid,
- key.offset, 0, 0);
+ ret = add_tree_backref(extent_cache,
+ key.objectid, key.offset, 0, 0);
+ if (ret < 0)
+ error("add_tree_backref failed: %s",
+ strerror(-ret));
continue;
}
if (key.type == BTRFS_EXTENT_DATA_REF_KEY) {
btrfs_item_key_to_cpu(buf, &first_key, 0);
level = btrfs_header_level(buf);
for (i = 0; i < nritems; i++) {
+ struct extent_record tmpl;
+
ptr = btrfs_node_blockptr(buf, i);
- size = btrfs_level_size(root, level - 1);
+ size = root->nodesize;
btrfs_node_key_to_cpu(buf, &key, i);
if (ri != NULL) {
if ((level == ri->drop_level)
continue;
}
}
- ret = add_extent_rec(extent_cache, &key,
- btrfs_node_ptr_generation(buf, i),
- ptr, size, 0, 0, 1, 0, 1, 0,
- size);
- BUG_ON(ret);
- add_tree_backref(extent_cache, ptr, parent, owner, 1);
+ memset(&tmpl, 0, sizeof(tmpl));
+ btrfs_cpu_key_to_disk(&tmpl.parent_key, &key);
+ tmpl.parent_generation = btrfs_node_ptr_generation(buf, i);
+ tmpl.start = ptr;
+ tmpl.nr = size;
+ tmpl.refs = 1;
+ tmpl.metadata = 1;
+ tmpl.max_size = size;
+ ret = add_extent_rec(extent_cache, &tmpl);
+ if (ret < 0)
+ goto out;
+
+ ret = add_tree_backref(extent_cache, ptr, parent,
+ owner, 1);
+ if (ret < 0) {
+ error("add_tree_backref failed: %s",
+ strerror(-ret));
+ continue;
+ }
if (level > 1) {
add_pending(nodes, seen, ptr, size);
struct cache_tree *nodes,
u64 objectid)
{
+ struct extent_record tmpl;
+ int ret;
+
if (btrfs_header_level(buf) > 0)
add_pending(nodes, seen, buf->start, buf->len);
else
add_pending(pending, seen, buf->start, buf->len);
- add_extent_rec(extent_cache, NULL, 0, buf->start, buf->len,
- 0, 1, 1, 0, 1, 0, buf->len);
+
+ memset(&tmpl, 0, sizeof(tmpl));
+ tmpl.start = buf->start;
+ tmpl.nr = buf->len;
+ tmpl.is_root = 1;
+ tmpl.refs = 1;
+ tmpl.metadata = 1;
+ tmpl.max_size = buf->len;
+ add_extent_rec(extent_cache, &tmpl);
if (objectid == BTRFS_TREE_RELOC_OBJECTID ||
btrfs_header_backref_rev(buf) < BTRFS_MIXED_BACKREF_REV)
- add_tree_backref(extent_cache, buf->start, buf->start,
- 0, 1);
+ ret = add_tree_backref(extent_cache, buf->start, buf->start,
+ 0, 1);
else
- add_tree_backref(extent_cache, buf->start, 0, objectid, 1);
- return 0;
+ ret = add_tree_backref(extent_cache, buf->start, 0, objectid,
+ 1);
+ return ret;
}
/* as we fix the tree, we might be deleting blocks that
if (found_key.type == BTRFS_EXTENT_ITEM_KEY ||
found_key.type == BTRFS_METADATA_ITEM_KEY) {
u64 bytes = (found_key.type == BTRFS_EXTENT_ITEM_KEY) ?
- found_key.offset : root->leafsize;
+ found_key.offset : root->nodesize;
ret = btrfs_update_block_group(trans, root, bytenr,
bytes, 0, 0);
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;
if (!back->is_data)
rec->max_size = max_t(u64, rec->max_size,
- info->extent_root->leafsize);
+ info->extent_root->nodesize);
if (!allocated) {
u32 item_size = sizeof(*ei);
} else {
struct btrfs_disk_key copy_key;;
- tback = (struct tree_backref *)back;
bi = (struct btrfs_tree_block_info *)(ei + 1);
memset_extent_buffer(leaf, 0, (unsigned long)bi,
sizeof(*bi));
u64 parent;
int i;
- dback = (struct data_backref *)back;
+ dback = to_data_backref(back);
if (back->full_backref)
parent = dback->parent;
else
dback->found_ref);
} else {
u64 parent;
+ struct tree_backref *tback;
- tback = (struct tree_backref *)back;
+ tback = to_tree_backref(back);
if (back->full_backref)
parent = tback->parent;
else
return ret;
}
-struct extent_entry {
- u64 bytenr;
- u64 bytes;
- int count;
- int broken;
- struct list_head list;
-};
-
static struct extent_entry *find_entry(struct list_head *entries,
u64 bytenr, u64 bytes)
{
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.
*/
if (back->full_backref || !back->is_data)
continue;
- dback = (struct data_backref *)back;
+ dback = to_data_backref(back);
/*
* We only pay attention to backrefs that we found a real
if (back->full_backref || !back->is_data)
continue;
- dback = (struct data_backref *)back;
+ dback = to_data_backref(back);
/*
* Still ignoring backrefs that don't have a real ref attached
*/
remove_cache_extent(extent_cache, &rec->cache);
- good = list_entry(rec->dups.next, struct extent_record, list);
+ good = to_extent_record(rec->dups.next);
list_del_init(&good->list);
INIT_LIST_HEAD(&good->backrefs);
INIT_LIST_HEAD(&good->dups);
{
struct btrfs_trans_handle *trans;
LIST_HEAD(delete_list);
- struct btrfs_path *path;
+ struct btrfs_path path;
struct extent_record *tmp, *good, *n;
int nr_del = 0;
int ret = 0, err;
struct btrfs_key key;
- path = btrfs_alloc_path();
- if (!path) {
- ret = -ENOMEM;
- goto out;
- }
+ btrfs_init_path(&path);
good = rec;
/* Find the record that covers all of the duplicates. */
if (tmp->start + tmp->nr < good->start + good->nr) {
fprintf(stderr, "Ok we have overlapping extents that "
- "aren't completely covered by eachother, this "
+ "aren't completely covered by each other, this "
"is going to require more careful thought. "
"The extents are [%Lu-%Lu] and [%Lu-%Lu]\n",
tmp->start, tmp->nr, good->start, good->nr);
abort();
}
- ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
+ ret = btrfs_search_slot(trans, root, &key, &path, -1, 1);
if (ret) {
if (ret > 0)
ret = -EINVAL;
break;
}
- ret = btrfs_del_item(trans, root, path);
+ ret = btrfs_del_item(trans, root, &path);
if (ret)
break;
- btrfs_release_path(path);
+ btrfs_release_path(&path);
nr_del++;
}
err = btrfs_commit_transaction(trans, root);
ret = err;
out:
while (!list_empty(&delete_list)) {
- tmp = list_entry(delete_list.next, struct extent_record, list);
+ tmp = to_extent_record(delete_list.next);
list_del_init(&tmp->list);
if (tmp == rec)
continue;
}
while (!list_empty(&rec->dups)) {
- tmp = list_entry(rec->dups.next, struct extent_record, list);
+ tmp = to_extent_record(rec->dups.next);
list_del_init(&tmp->list);
free(tmp);
}
- btrfs_free_path(path);
+ btrfs_release_path(&path);
if (!ret && !nr_del)
rec->num_duplicates = 0;
if (back->full_backref || !back->is_data)
continue;
- dback = (struct data_backref *)back;
+ dback = to_data_backref(back);
/* We found this one, we don't need to do a lookup */
if (dback->found_ref)
struct extent_backref *back;
struct data_backref *dback;
struct orphan_data_extent *orphan;
- struct btrfs_path *path;
+ struct btrfs_path path;
int recorded_data_ref = 0;
int ret = 0;
if (rec->metadata)
return 1;
- path = btrfs_alloc_path();
- if (!path)
- return -ENOMEM;
+ btrfs_init_path(&path);
list_for_each_entry(back, &rec->backrefs, list) {
if (back->full_backref || !back->is_data ||
!back->found_extent_tree)
continue;
- dback = (struct data_backref *)back;
+ dback = to_data_backref(back);
if (dback->found_ref)
continue;
key.objectid = dback->root;
key.type = BTRFS_EXTENT_DATA_KEY;
key.offset = dback->offset;
- ret = btrfs_search_slot(NULL, dest_root, &key, path, 0, 0);
+ ret = btrfs_search_slot(NULL, dest_root, &key, &path, 0, 0);
+ btrfs_release_path(&path);
/*
* For ret < 0, it's OK since the fs-tree may be corrupted,
* we need to record it for inode/file extent rebuild.
recorded_data_ref = 1;
}
out:
- btrfs_free_path(path);
+ btrfs_release_path(&path);
if (!ret)
return !recorded_data_ref;
else
{
struct btrfs_trans_handle *trans = NULL;
int ret;
- struct btrfs_path *path;
+ struct btrfs_path path;
struct list_head *cur = rec->backrefs.next;
struct cache_extent *cache;
struct extent_backref *back;
if (rec->flag_block_full_backref)
flags |= BTRFS_BLOCK_FLAG_FULL_BACKREF;
- path = btrfs_alloc_path();
- if (!path)
- return -ENOMEM;
-
+ btrfs_init_path(&path);
if (rec->refs != rec->extent_item_refs && !rec->metadata) {
/*
* Sometimes the backrefs themselves are so broken they don't
* them into the list if we find the backref so that
* verify_backrefs can figure out what to do.
*/
- ret = find_possible_backrefs(info, path, extent_cache, rec);
+ ret = find_possible_backrefs(info, &path, extent_cache, rec);
if (ret < 0)
goto out;
}
/* step one, make sure all of the backrefs agree */
- ret = verify_backrefs(info, path, rec);
+ ret = verify_backrefs(info, &path, rec);
if (ret < 0)
goto out;
}
/* step two, delete all the existing records */
- ret = delete_extent_records(trans, info->extent_root, path,
+ ret = delete_extent_records(trans, info->extent_root, &path,
rec->start, rec->max_size);
if (ret < 0)
/* step three, recreate all the refs we did find */
while(cur != &rec->backrefs) {
- back = list_entry(cur, struct extent_backref, list);
+ back = to_extent_backref(cur);
cur = cur->next;
/*
continue;
rec->bad_full_backref = 0;
- ret = record_extent(trans, info, path, rec, back, allocated, flags);
+ ret = record_extent(trans, info, &path, rec, back, allocated, flags);
allocated = 1;
if (ret)
ret = err;
}
- btrfs_free_path(path);
+ btrfs_release_path(&path);
return ret;
}
{
struct btrfs_trans_handle *trans;
struct btrfs_root *root = fs_info->extent_root;
- struct btrfs_path *path;
+ struct btrfs_path path;
struct btrfs_extent_item *ei;
struct btrfs_key key;
u64 flags;
key.offset = rec->max_size;
}
- path = btrfs_alloc_path();
- if (!path)
- return -ENOMEM;
-
trans = btrfs_start_transaction(root, 0);
- if (IS_ERR(trans)) {
- btrfs_free_path(path);
+ if (IS_ERR(trans))
return PTR_ERR(trans);
- }
- ret = btrfs_search_slot(trans, root, &key, path, 0, 1);
+ btrfs_init_path(&path);
+ ret = btrfs_search_slot(trans, root, &key, &path, 0, 1);
if (ret < 0) {
- btrfs_free_path(path);
+ btrfs_release_path(&path);
btrfs_commit_transaction(trans, root);
return ret;
} else if (ret) {
fprintf(stderr, "Didn't find extent for %llu\n",
(unsigned long long)rec->start);
- btrfs_free_path(path);
+ btrfs_release_path(&path);
btrfs_commit_transaction(trans, root);
return -ENOENT;
}
- ei = btrfs_item_ptr(path->nodes[0], path->slots[0],
+ ei = btrfs_item_ptr(path.nodes[0], path.slots[0],
struct btrfs_extent_item);
- flags = btrfs_extent_flags(path->nodes[0], ei);
+ flags = btrfs_extent_flags(path.nodes[0], ei);
if (rec->flag_block_full_backref) {
fprintf(stderr, "setting full backref on %llu\n",
(unsigned long long)key.objectid);
(unsigned long long)key.objectid);
flags &= ~BTRFS_BLOCK_FLAG_FULL_BACKREF;
}
- btrfs_set_extent_flags(path->nodes[0], ei, flags);
- btrfs_mark_buffer_dirty(path->nodes[0]);
- btrfs_free_path(path);
+ 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);
}
* belong to a different extent item and not the weird duplicate one.
*/
while (repair && !list_empty(&duplicate_extents)) {
- rec = list_entry(duplicate_extents.next, struct extent_record,
- list);
+ rec = to_extent_record(duplicate_extents.next);
list_del_init(&rec->list);
/* Sometimes we can find a backref before we find an actual
ret = -EIO;
break;
}
- add_root_to_pending(buf, extent_cache, pending,
+ ret = add_root_to_pending(buf, extent_cache, pending,
seen, nodes, rec->objectid);
+ if (ret < 0)
+ break;
/*
* To rebuild extent tree, we need deal with snapshot
* one by one, otherwise we deal with node firstly which
level = btrfs_header_level(root1->node);
ret = add_root_item_to_list(&normal_trees, root1->root_key.objectid,
root1->node->start, 0, level, 0,
- btrfs_level_size(root1, level), NULL);
+ root1->nodesize, NULL);
if (ret < 0)
goto out;
root1 = root->fs_info->chunk_root;
level = btrfs_header_level(root1->node);
ret = add_root_item_to_list(&normal_trees, root1->root_key.objectid,
root1->node->start, 0, level, 0,
- btrfs_level_size(root1, level), NULL);
+ root1->nodesize, NULL);
if (ret < 0)
goto out;
btrfs_init_path(&path);
key.offset = 0;
key.objectid = 0;
- btrfs_set_key_type(&key, BTRFS_ROOT_ITEM_KEY);
+ key.type = BTRFS_ROOT_ITEM_KEY;
ret = btrfs_search_slot(NULL, root->fs_info->tree_root,
&key, &path, 0, 0);
if (ret < 0)
slot = path.slots[0];
}
btrfs_item_key_to_cpu(leaf, &found_key, path.slots[0]);
- if (btrfs_key_type(&found_key) == BTRFS_ROOT_ITEM_KEY) {
+ if (found_key.type == BTRFS_ROOT_ITEM_KEY) {
unsigned long offset;
u64 last_snapshot;
last_snapshot = btrfs_root_last_snapshot(&ri);
if (btrfs_disk_key_objectid(&ri.drop_progress) == 0) {
level = btrfs_root_level(&ri);
- level_size = btrfs_level_size(root, level);
+ level_size = root->nodesize;
ret = add_root_item_to_list(&normal_trees,
found_key.objectid,
btrfs_root_bytenr(&ri),
goto out;
} else {
level = btrfs_root_level(&ri);
- level_size = btrfs_level_size(root, level);
+ level_size = root->nodesize;
objectid = found_key.objectid;
btrfs_disk_key_to_cpu(&found_key,
&ri.drop_progress);
err = ret;
}
- ret = check_extent_refs(root, &extent_cache);
- if (ret < 0) {
- if (ret == -EAGAIN)
- goto loop;
+ ret = check_extent_refs(root, &extent_cache);
+ if (ret < 0) {
+ if (ret == -EAGAIN)
+ goto loop;
+ goto out;
+ }
+
+ ret = check_devices(&dev_cache, &dev_extent_cache);
+ if (ret && err)
+ ret = err;
+
+out:
+ task_stop(ctx.info);
+ if (repair) {
+ free_corrupt_blocks_tree(root->fs_info->corrupt_blocks);
+ extent_io_tree_cleanup(&excluded_extents);
+ root->fs_info->fsck_extent_cache = NULL;
+ root->fs_info->free_extent_hook = NULL;
+ root->fs_info->corrupt_blocks = NULL;
+ root->fs_info->excluded_extents = NULL;
+ }
+ free(bits);
+ free_chunk_cache_tree(&chunk_cache);
+ free_device_cache_tree(&dev_cache);
+ free_block_group_tree(&block_group_cache);
+ free_device_extent_tree(&dev_extent_cache);
+ free_extent_cache_tree(&seen);
+ free_extent_cache_tree(&pending);
+ free_extent_cache_tree(&reada);
+ free_extent_cache_tree(&nodes);
+ return ret;
+loop:
+ free_corrupt_blocks_tree(root->fs_info->corrupt_blocks);
+ free_extent_cache_tree(&seen);
+ free_extent_cache_tree(&pending);
+ free_extent_cache_tree(&reada);
+ free_extent_cache_tree(&nodes);
+ free_chunk_cache_tree(&chunk_cache);
+ 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_root_item_list(&normal_trees);
+ free_root_item_list(&dropping_trees);
+ extent_io_tree_cleanup(&excluded_extents);
+ goto again;
+}
+
+/*
+ * Check backrefs of a tree block given by @bytenr or @eb.
+ *
+ * @root: the root containing the @bytenr or @eb
+ * @eb: tree block extent buffer, can be NULL
+ * @bytenr: bytenr of the tree block to search
+ * @level: tree level of the tree block
+ * @owner: owner of the tree block
+ *
+ * Return >0 for any error found and output error message
+ * Return 0 for no error found
+ */
+static int check_tree_block_ref(struct btrfs_root *root,
+ struct extent_buffer *eb, u64 bytenr,
+ int level, u64 owner)
+{
+ struct btrfs_key key;
+ struct btrfs_root *extent_root = root->fs_info->extent_root;
+ struct btrfs_path path;
+ struct btrfs_extent_item *ei;
+ struct btrfs_extent_inline_ref *iref;
+ struct extent_buffer *leaf;
+ unsigned long end;
+ unsigned long ptr;
+ int slot;
+ int skinny_level;
+ int type;
+ u32 nodesize = root->nodesize;
+ u32 item_size;
+ u64 offset;
+ int found_ref = 0;
+ int err = 0;
+ int ret;
+
+ btrfs_init_path(&path);
+ key.objectid = bytenr;
+ if (btrfs_fs_incompat(root->fs_info,
+ BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA))
+ key.type = BTRFS_METADATA_ITEM_KEY;
+ else
+ key.type = BTRFS_EXTENT_ITEM_KEY;
+ key.offset = (u64)-1;
+
+ /* Search for the backref in extent tree */
+ ret = btrfs_search_slot(NULL, extent_root, &key, &path, 0, 0);
+ if (ret < 0) {
+ err |= BACKREF_MISSING;
+ goto out;
+ }
+ ret = btrfs_previous_extent_item(extent_root, &path, bytenr);
+ if (ret) {
+ err |= BACKREF_MISSING;
+ goto out;
+ }
+
+ leaf = path.nodes[0];
+ slot = path.slots[0];
+ btrfs_item_key_to_cpu(leaf, &key, slot);
+
+ ei = btrfs_item_ptr(leaf, slot, struct btrfs_extent_item);
+
+ if (key.type == BTRFS_METADATA_ITEM_KEY) {
+ skinny_level = (int)key.offset;
+ iref = (struct btrfs_extent_inline_ref *)(ei + 1);
+ } else {
+ struct btrfs_tree_block_info *info;
+
+ info = (struct btrfs_tree_block_info *)(ei + 1);
+ skinny_level = btrfs_tree_block_level(leaf, info);
+ iref = (struct btrfs_extent_inline_ref *)(info + 1);
+ }
+
+ if (eb) {
+ u64 header_gen;
+ u64 extent_gen;
+
+ if (!(btrfs_extent_flags(leaf, ei) &
+ BTRFS_EXTENT_FLAG_TREE_BLOCK)) {
+ error(
+ "extent[%llu %u] backref type mismatch, missing bit: %llx",
+ key.objectid, nodesize,
+ BTRFS_EXTENT_FLAG_TREE_BLOCK);
+ err = BACKREF_MISMATCH;
+ }
+ header_gen = btrfs_header_generation(eb);
+ extent_gen = btrfs_extent_generation(leaf, ei);
+ if (header_gen != extent_gen) {
+ error(
+ "extent[%llu %u] backref generation mismatch, wanted: %llu, have: %llu",
+ key.objectid, nodesize, header_gen,
+ extent_gen);
+ err = BACKREF_MISMATCH;
+ }
+ if (level != skinny_level) {
+ error(
+ "extent[%llu %u] level mismatch, wanted: %u, have: %u",
+ key.objectid, nodesize, level, skinny_level);
+ err = BACKREF_MISMATCH;
+ }
+ if (!is_fstree(owner) && btrfs_extent_refs(leaf, ei) != 1) {
+ error(
+ "extent[%llu %u] is referred by other roots than %llu",
+ key.objectid, nodesize, root->objectid);
+ err = BACKREF_MISMATCH;
+ }
+ }
+
+ /*
+ * Iterate the extent/metadata item to find the exact backref
+ */
+ item_size = btrfs_item_size_nr(leaf, slot);
+ ptr = (unsigned long)iref;
+ end = (unsigned long)ei + item_size;
+ while (ptr < end) {
+ iref = (struct btrfs_extent_inline_ref *)ptr;
+ type = btrfs_extent_inline_ref_type(leaf, iref);
+ offset = btrfs_extent_inline_ref_offset(leaf, iref);
+
+ if (type == BTRFS_TREE_BLOCK_REF_KEY &&
+ (offset == root->objectid || offset == owner)) {
+ found_ref = 1;
+ } else if (type == BTRFS_SHARED_BLOCK_REF_KEY) {
+ /* Check if the backref points to valid referencer */
+ found_ref = !check_tree_block_ref(root, NULL, offset,
+ level + 1, owner);
+ }
+
+ if (found_ref)
+ break;
+ ptr += btrfs_extent_inline_ref_size(type);
+ }
+
+ /*
+ * Inlined extent item doesn't have what we need, check
+ * TREE_BLOCK_REF_KEY
+ */
+ if (!found_ref) {
+ btrfs_release_path(&path);
+ key.objectid = bytenr;
+ key.type = BTRFS_TREE_BLOCK_REF_KEY;
+ key.offset = root->objectid;
+
+ ret = btrfs_search_slot(NULL, extent_root, &key, &path, 0, 0);
+ if (!ret)
+ found_ref = 1;
+ }
+ if (!found_ref)
+ err |= BACKREF_MISSING;
+out:
+ btrfs_release_path(&path);
+ if (eb && (err & BACKREF_MISSING))
+ error("extent[%llu %u] backref lost (owner: %llu, level: %u)",
+ bytenr, nodesize, owner, level);
+ return err;
+}
+
+/*
+ * Check EXTENT_DATA item, mainly for its dbackref in extent tree
+ *
+ * Return >0 any error found and output error message
+ * Return 0 for no error found
+ */
+static int check_extent_data_item(struct btrfs_root *root,
+ struct extent_buffer *eb, int slot)
+{
+ struct btrfs_file_extent_item *fi;
+ struct btrfs_path path;
+ struct btrfs_root *extent_root = root->fs_info->extent_root;
+ struct btrfs_key fi_key;
+ struct btrfs_key dbref_key;
+ struct extent_buffer *leaf;
+ struct btrfs_extent_item *ei;
+ 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;
+ int type;
+ u64 ref_root;
+ int found_dbackref = 0;
+ int err = 0;
+ int ret;
+
+ 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 ||
+ btrfs_file_extent_disk_bytenr(eb, fi) == 0)
+ return 0;
+
+ disk_bytenr = btrfs_file_extent_disk_bytenr(eb, fi);
+ disk_num_bytes = btrfs_file_extent_disk_num_bytes(eb, fi);
+ extent_num_bytes = btrfs_file_extent_num_bytes(eb, fi);
+
+ /* Check unaligned disk_num_bytes and num_bytes */
+ if (!IS_ALIGNED(disk_num_bytes, root->sectorsize)) {
+ error(
+"file extent [%llu, %llu] has unaligned disk num bytes: %llu, should be aligned to %u",
+ fi_key.objectid, fi_key.offset, disk_num_bytes,
+ root->sectorsize);
+ err |= BYTES_UNALIGNED;
+ } else {
+ data_bytes_allocated += disk_num_bytes;
+ }
+ if (!IS_ALIGNED(extent_num_bytes, root->sectorsize)) {
+ error(
+"file extent [%llu, %llu] has unaligned num bytes: %llu, should be aligned to %u",
+ fi_key.objectid, fi_key.offset, extent_num_bytes,
+ root->sectorsize);
+ err |= BYTES_UNALIGNED;
+ } else {
+ data_bytes_referenced += extent_num_bytes;
+ }
+ owner = btrfs_header_owner(eb);
+
+ /* Check the extent item of the file extent in extent tree */
+ btrfs_init_path(&path);
+ dbref_key.objectid = btrfs_file_extent_disk_bytenr(eb, fi);
+ dbref_key.type = BTRFS_EXTENT_ITEM_KEY;
+ 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;
+ }
+
+ 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(
+ "extent[%llu %llu] backref type mismatch, wanted bit: %llx",
+ disk_bytenr, disk_num_bytes,
+ BTRFS_EXTENT_FLAG_DATA);
+ 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 = (unsigned long)iref;
+ end = (unsigned long)ei + item_size;
+ while (ptr < end) {
+ iref = (struct btrfs_extent_inline_ref *)ptr;
+ type = btrfs_extent_inline_ref_type(leaf, iref);
+ dref = (struct btrfs_extent_data_ref *)(&iref->offset);
+
+ if (type == BTRFS_EXTENT_DATA_REF_KEY) {
+ ref_root = btrfs_extent_data_ref_root(leaf, dref);
+ if (ref_root == owner || ref_root == root->objectid)
+ found_dbackref = 1;
+ } else if (type == BTRFS_SHARED_DATA_REF_KEY) {
+ found_dbackref = !check_tree_block_ref(root, NULL,
+ btrfs_extent_inline_ref_offset(leaf, iref),
+ 0, owner);
+ }
+
+ if (found_dbackref)
+ break;
+ 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);
+ 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,
+ fi_key.objectid, fi_key.offset);
+
+ ret = btrfs_search_slot(NULL, root->fs_info->extent_root,
+ &dbref_key, &path, 0, 0);
+ if (!ret)
+ found_dbackref = 1;
+ }
+
+ if (!found_dbackref)
+ err |= BACKREF_MISSING;
+error:
+ btrfs_release_path(&path);
+ if (err & BACKREF_MISSING) {
+ error("data extent[%llu %llu] backref lost",
+ disk_bytenr, disk_num_bytes);
+ }
+ return err;
+}
+
+/*
+ * Get real tree block level for the case like shared block
+ * Return >= 0 as tree level
+ * Return <0 for error
+ */
+static int query_tree_block_level(struct btrfs_fs_info *fs_info, u64 bytenr)
+{
+ struct extent_buffer *eb;
+ struct btrfs_path path;
+ struct btrfs_key key;
+ struct btrfs_extent_item *ei;
+ u64 flags;
+ u64 transid;
+ u32 nodesize = btrfs_super_nodesize(fs_info->super_copy);
+ u8 backref_level;
+ u8 header_level;
+ int ret;
+
+ /* Search extent tree for extent generation and level */
+ key.objectid = bytenr;
+ key.type = BTRFS_METADATA_ITEM_KEY;
+ key.offset = (u64)-1;
+
+ btrfs_init_path(&path);
+ ret = btrfs_search_slot(NULL, fs_info->extent_root, &key, &path, 0, 0);
+ if (ret < 0)
+ goto release_out;
+ ret = btrfs_previous_extent_item(fs_info->extent_root, &path, bytenr);
+ if (ret < 0)
+ goto release_out;
+ if (ret > 0) {
+ ret = -ENOENT;
+ goto release_out;
+ }
+
+ btrfs_item_key_to_cpu(path.nodes[0], &key, path.slots[0]);
+ ei = btrfs_item_ptr(path.nodes[0], path.slots[0],
+ struct btrfs_extent_item);
+ flags = btrfs_extent_flags(path.nodes[0], ei);
+ if (!(flags & BTRFS_EXTENT_FLAG_TREE_BLOCK)) {
+ ret = -ENOENT;
+ goto release_out;
+ }
+
+ /* Get transid for later read_tree_block() check */
+ transid = btrfs_extent_generation(path.nodes[0], ei);
+
+ /* Get backref level as one source */
+ if (key.type == BTRFS_METADATA_ITEM_KEY) {
+ backref_level = key.offset;
+ } else {
+ struct btrfs_tree_block_info *info;
+
+ info = (struct btrfs_tree_block_info *)(ei + 1);
+ backref_level = btrfs_tree_block_level(path.nodes[0], info);
+ }
+ btrfs_release_path(&path);
+
+ /* Get level from tree block as an alternative source */
+ eb = read_tree_block_fs_info(fs_info, bytenr, nodesize, transid);
+ if (!extent_buffer_uptodate(eb)) {
+ free_extent_buffer(eb);
+ return -EIO;
+ }
+ header_level = btrfs_header_level(eb);
+ free_extent_buffer(eb);
+
+ if (header_level != backref_level)
+ return -EIO;
+ return header_level;
+
+release_out:
+ btrfs_release_path(&path);
+ return ret;
+}
+
+/*
+ * Check if a tree block backref is valid (points to a valid tree block)
+ * if level == -1, level will be resolved
+ * Return >0 for any error found and print error message
+ */
+static int check_tree_block_backref(struct btrfs_fs_info *fs_info, u64 root_id,
+ u64 bytenr, int level)
+{
+ struct btrfs_root *root;
+ struct btrfs_key key;
+ struct btrfs_path path;
+ struct extent_buffer *eb;
+ struct extent_buffer *node;
+ u32 nodesize = btrfs_super_nodesize(fs_info->super_copy);
+ int err = 0;
+ int ret;
+
+ /* Query level for level == -1 special case */
+ if (level == -1)
+ level = query_tree_block_level(fs_info, bytenr);
+ if (level < 0) {
+ err |= REFERENCER_MISSING;
+ goto out;
+ }
+
+ key.objectid = root_id;
+ key.type = BTRFS_ROOT_ITEM_KEY;
+ key.offset = (u64)-1;
+
+ root = btrfs_read_fs_root(fs_info, &key);
+ if (IS_ERR(root)) {
+ err |= REFERENCER_MISSING;
+ goto out;
+ }
+
+ /* Read out the tree block to get item/node key */
+ eb = read_tree_block(root, bytenr, root->nodesize, 0);
+ if (!extent_buffer_uptodate(eb)) {
+ err |= REFERENCER_MISSING;
+ free_extent_buffer(eb);
+ goto out;
+ }
+
+ /* Empty tree, no need to check key */
+ if (!btrfs_header_nritems(eb) && !level) {
+ free_extent_buffer(eb);
+ goto out;
+ }
+
+ if (level)
+ btrfs_node_key_to_cpu(eb, &key, 0);
+ else
+ btrfs_item_key_to_cpu(eb, &key, 0);
+
+ free_extent_buffer(eb);
+
+ btrfs_init_path(&path);
+ path.lowest_level = level;
+ /* Search with the first key, to ensure we can reach it */
+ ret = btrfs_search_slot(NULL, root, &key, &path, 0, 0);
+ if (ret < 0) {
+ err |= REFERENCER_MISSING;
+ goto release_out;
+ }
+
+ node = path.nodes[level];
+ if (btrfs_header_bytenr(node) != bytenr) {
+ error(
+ "extent [%llu %d] referencer bytenr mismatch, wanted: %llu, have: %llu",
+ bytenr, nodesize, bytenr,
+ btrfs_header_bytenr(node));
+ err |= REFERENCER_MISMATCH;
+ }
+ if (btrfs_header_level(node) != level) {
+ error(
+ "extent [%llu %d] referencer level mismatch, wanted: %d, have: %d",
+ bytenr, nodesize, level,
+ btrfs_header_level(node));
+ err |= REFERENCER_MISMATCH;
+ }
+
+release_out:
+ btrfs_release_path(&path);
+out:
+ if (err & REFERENCER_MISSING) {
+ if (level < 0)
+ error("extent [%llu %d] lost referencer (owner: %llu)",
+ bytenr, nodesize, root_id);
+ else
+ error(
+ "extent [%llu %d] lost referencer (owner: %llu, level: %u)",
+ bytenr, nodesize, root_id, level);
+ }
+
+ return err;
+}
+
+/*
+ * Check referencer for shared block backref
+ * If level == -1, this function will resolve the level.
+ */
+static int check_shared_block_backref(struct btrfs_fs_info *fs_info,
+ u64 parent, u64 bytenr, int level)
+{
+ struct extent_buffer *eb;
+ u32 nodesize = btrfs_super_nodesize(fs_info->super_copy);
+ u32 nr;
+ int found_parent = 0;
+ int i;
+
+ eb = read_tree_block_fs_info(fs_info, parent, nodesize, 0);
+ if (!extent_buffer_uptodate(eb))
+ goto out;
+
+ if (level == -1)
+ level = query_tree_block_level(fs_info, bytenr);
+ if (level < 0)
+ goto out;
+
+ if (level + 1 != btrfs_header_level(eb))
+ goto out;
+
+ nr = btrfs_header_nritems(eb);
+ for (i = 0; i < nr; i++) {
+ if (bytenr == btrfs_node_blockptr(eb, i)) {
+ found_parent = 1;
+ break;
+ }
+ }
+out:
+ free_extent_buffer(eb);
+ if (!found_parent) {
+ error(
+ "shared extent[%llu %u] lost its parent (parent: %llu, level: %u)",
+ bytenr, nodesize, parent, level);
+ return REFERENCER_MISSING;
+ }
+ return 0;
+}
+
+/*
+ * Check referencer for normal (inlined) data ref
+ * If len == 0, it will be resolved by searching in extent tree
+ */
+static int check_extent_data_backref(struct btrfs_fs_info *fs_info,
+ u64 root_id, u64 objectid, u64 offset,
+ u64 bytenr, u64 len, u32 count)
+{
+ struct btrfs_root *root;
+ struct btrfs_root *extent_root = fs_info->extent_root;
+ struct btrfs_key key;
+ struct btrfs_path path;
+ struct extent_buffer *leaf;
+ struct btrfs_file_extent_item *fi;
+ u32 found_count = 0;
+ int slot;
+ int ret = 0;
+
+ if (!len) {
+ key.objectid = bytenr;
+ key.type = BTRFS_EXTENT_ITEM_KEY;
+ key.offset = (u64)-1;
+
+ btrfs_init_path(&path);
+ ret = btrfs_search_slot(NULL, extent_root, &key, &path, 0, 0);
+ if (ret < 0)
+ goto out;
+ ret = btrfs_previous_extent_item(extent_root, &path, bytenr);
+ if (ret)
+ goto out;
+ btrfs_item_key_to_cpu(path.nodes[0], &key, path.slots[0]);
+ if (key.objectid != bytenr ||
+ key.type != BTRFS_EXTENT_ITEM_KEY)
+ goto out;
+ len = key.offset;
+ btrfs_release_path(&path);
+ }
+ key.objectid = root_id;
+ key.type = BTRFS_ROOT_ITEM_KEY;
+ key.offset = (u64)-1;
+ btrfs_init_path(&path);
+
+ root = btrfs_read_fs_root(fs_info, &key);
+ if (IS_ERR(root))
+ goto out;
+
+ key.objectid = objectid;
+ key.type = BTRFS_EXTENT_DATA_KEY;
+ /*
+ * It can be nasty as data backref offset is
+ * file offset - file extent offset, which is smaller or
+ * equal to original backref offset. The only special case is
+ * overflow. So we need to special check and do further search.
+ */
+ key.offset = offset & (1ULL << 63) ? 0 : offset;
+
+ ret = btrfs_search_slot(NULL, root, &key, &path, 0, 0);
+ if (ret < 0)
+ goto out;
+
+ /*
+ * Search afterwards to get correct one
+ * NOTE: As we must do a comprehensive check on the data backref to
+ * make sure the dref count also matches, we must iterate all file
+ * extents for that inode.
+ */
+ while (1) {
+ leaf = path.nodes[0];
+ slot = path.slots[0];
+
+ btrfs_item_key_to_cpu(leaf, &key, slot);
+ if (key.objectid != objectid || key.type != BTRFS_EXTENT_DATA_KEY)
+ break;
+ fi = btrfs_item_ptr(leaf, slot, struct btrfs_file_extent_item);
+ /*
+ * Except normal disk bytenr and disk num bytes, we still
+ * need to do extra check on dbackref offset as
+ * dbackref offset = file_offset - file_extent_offset
+ */
+ if (btrfs_file_extent_disk_bytenr(leaf, fi) == bytenr &&
+ btrfs_file_extent_disk_num_bytes(leaf, fi) == len &&
+ (u64)(key.offset - btrfs_file_extent_offset(leaf, fi)) ==
+ offset)
+ found_count++;
+
+ ret = btrfs_next_item(root, &path);
+ if (ret)
+ break;
+ }
+out:
+ btrfs_release_path(&path);
+ if (found_count != count) {
+ error(
+"extent[%llu, %llu] referencer count mismatch (root: %llu, owner: %llu, offset: %llu) wanted: %u, have: %u",
+ bytenr, len, root_id, objectid, offset, count, found_count);
+ return REFERENCER_MISSING;
+ }
+ return 0;
+}
+
+/*
+ * Check if the referencer of a shared data backref exists
+ */
+static int check_shared_data_backref(struct btrfs_fs_info *fs_info,
+ u64 parent, u64 bytenr)
+{
+ struct extent_buffer *eb;
+ struct btrfs_key key;
+ struct btrfs_file_extent_item *fi;
+ u32 nodesize = btrfs_super_nodesize(fs_info->super_copy);
+ u32 nr;
+ int found_parent = 0;
+ int i;
+
+ eb = read_tree_block_fs_info(fs_info, parent, nodesize, 0);
+ if (!extent_buffer_uptodate(eb))
+ goto out;
+
+ nr = btrfs_header_nritems(eb);
+ for (i = 0; i < nr; i++) {
+ btrfs_item_key_to_cpu(eb, &key, i);
+ if (key.type != BTRFS_EXTENT_DATA_KEY)
+ continue;
+
+ fi = btrfs_item_ptr(eb, i, struct btrfs_file_extent_item);
+ if (btrfs_file_extent_type(eb, fi) == BTRFS_FILE_EXTENT_INLINE)
+ continue;
+
+ if (btrfs_file_extent_disk_bytenr(eb, fi) == bytenr) {
+ found_parent = 1;
+ break;
+ }
+ }
+
+out:
+ free_extent_buffer(eb);
+ if (!found_parent) {
+ error("shared extent %llu referencer lost (parent: %llu)",
+ bytenr, parent);
+ return REFERENCER_MISSING;
+ }
+ return 0;
+}
+
+/*
+ * This function will check a given extent item, including its backref and
+ * itself (like crossing stripe boundary and type)
+ *
+ * Since we don't use extent_record anymore, introduce new error bit
+ */
+static int check_extent_item(struct btrfs_fs_info *fs_info,
+ struct extent_buffer *eb, int slot)
+{
+ struct btrfs_extent_item *ei;
+ struct btrfs_extent_inline_ref *iref;
+ struct btrfs_extent_data_ref *dref;
+ unsigned long end;
+ unsigned long ptr;
+ int type;
+ u32 nodesize = btrfs_super_nodesize(fs_info->super_copy);
+ u32 item_size = btrfs_item_size_nr(eb, slot);
+ u64 flags;
+ u64 offset;
+ int metadata = 0;
+ int level;
+ struct btrfs_key key;
+ int ret;
+ int err = 0;
+
+ btrfs_item_key_to_cpu(eb, &key, slot);
+ if (key.type == BTRFS_EXTENT_ITEM_KEY)
+ bytes_used += key.offset;
+ else
+ bytes_used += nodesize;
+
+ if (item_size < sizeof(*ei)) {
+ /*
+ * COMPAT_EXTENT_TREE_V0 case, but it's already a super
+ * old thing when on disk format is still un-determined.
+ * No need to care about it anymore
+ */
+ error("unsupported COMPAT_EXTENT_TREE_V0 detected");
+ return -ENOTTY;
+ }
+
+ ei = btrfs_item_ptr(eb, slot, struct btrfs_extent_item);
+ flags = btrfs_extent_flags(eb, ei);
+
+ if (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK)
+ metadata = 1;
+ if (metadata && check_crossing_stripes(global_info, key.objectid,
+ eb->len)) {
+ error("bad metadata [%llu, %llu) crossing stripe boundary",
+ key.objectid, key.objectid + nodesize);
+ err |= CROSSING_STRIPE_BOUNDARY;
+ }
+
+ ptr = (unsigned long)(ei + 1);
+
+ if (metadata && key.type == BTRFS_EXTENT_ITEM_KEY) {
+ /* Old EXTENT_ITEM metadata */
+ struct btrfs_tree_block_info *info;
+
+ info = (struct btrfs_tree_block_info *)ptr;
+ level = btrfs_tree_block_level(eb, info);
+ ptr += sizeof(struct btrfs_tree_block_info);
+ } else {
+ /* New METADATA_ITEM */
+ level = key.offset;
+ }
+ end = (unsigned long)ei + item_size;
+
+ if (ptr >= end) {
+ err |= ITEM_SIZE_MISMATCH;
+ 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);
+ switch (type) {
+ case BTRFS_TREE_BLOCK_REF_KEY:
+ ret = check_tree_block_backref(fs_info, offset, key.objectid,
+ level);
+ err |= ret;
+ break;
+ case BTRFS_SHARED_BLOCK_REF_KEY:
+ ret = check_shared_block_backref(fs_info, offset, key.objectid,
+ level);
+ err |= ret;
+ break;
+ case BTRFS_EXTENT_DATA_REF_KEY:
+ dref = (struct btrfs_extent_data_ref *)(&iref->offset);
+ ret = check_extent_data_backref(fs_info,
+ btrfs_extent_data_ref_root(eb, dref),
+ btrfs_extent_data_ref_objectid(eb, dref),
+ btrfs_extent_data_ref_offset(eb, dref),
+ key.objectid, key.offset,
+ btrfs_extent_data_ref_count(eb, dref));
+ err |= ret;
+ break;
+ case BTRFS_SHARED_DATA_REF_KEY:
+ ret = check_shared_data_backref(fs_info, offset, key.objectid);
+ err |= ret;
+ break;
+ default:
+ error("extent[%llu %d %llu] has unknown ref type: %d",
+ key.objectid, key.type, key.offset, type);
+ err |= UNKNOWN_TYPE;
+ goto out;
+ }
+
+ ptr += btrfs_extent_inline_ref_size(type);
+ if (ptr < end)
+ goto next;
+
+out:
+ return err;
+}
+
+/*
+ * Check if a dev extent item is referred correctly by its chunk
+ */
+static int check_dev_extent_item(struct btrfs_fs_info *fs_info,
+ struct extent_buffer *eb, int slot)
+{
+ struct btrfs_root *chunk_root = fs_info->chunk_root;
+ struct btrfs_dev_extent *ptr;
+ struct btrfs_path path;
+ struct btrfs_key chunk_key;
+ struct btrfs_key devext_key;
+ struct btrfs_chunk *chunk;
+ struct extent_buffer *l;
+ int num_stripes;
+ u64 length;
+ int i;
+ int found_chunk = 0;
+ int ret;
+
+ btrfs_item_key_to_cpu(eb, &devext_key, slot);
+ ptr = btrfs_item_ptr(eb, slot, struct btrfs_dev_extent);
+ length = btrfs_dev_extent_length(eb, ptr);
+
+ chunk_key.objectid = btrfs_dev_extent_chunk_objectid(eb, ptr);
+ chunk_key.type = BTRFS_CHUNK_ITEM_KEY;
+ chunk_key.offset = btrfs_dev_extent_chunk_offset(eb, ptr);
+
+ btrfs_init_path(&path);
+ ret = btrfs_search_slot(NULL, chunk_root, &chunk_key, &path, 0, 0);
+ if (ret)
+ goto out;
+
+ l = path.nodes[0];
+ chunk = btrfs_item_ptr(l, path.slots[0], struct btrfs_chunk);
+ if (btrfs_chunk_length(l, chunk) != length)
+ goto out;
+
+ num_stripes = btrfs_chunk_num_stripes(l, chunk);
+ for (i = 0; i < num_stripes; i++) {
+ u64 devid = btrfs_stripe_devid_nr(l, chunk, i);
+ u64 offset = btrfs_stripe_offset_nr(l, chunk, i);
+
+ if (devid == devext_key.objectid &&
+ offset == devext_key.offset) {
+ found_chunk = 1;
+ break;
+ }
+ }
+out:
+ btrfs_release_path(&path);
+ if (!found_chunk) {
+ error(
+ "device extent[%llu, %llu, %llu] did not find the related chunk",
+ devext_key.objectid, devext_key.offset, length);
+ return REFERENCER_MISSING;
+ }
+ return 0;
+}
+
+/*
+ * Check if the used space is correct with the dev item
+ */
+static int check_dev_item(struct btrfs_fs_info *fs_info,
+ struct extent_buffer *eb, int slot)
+{
+ struct btrfs_root *dev_root = fs_info->dev_root;
+ struct btrfs_dev_item *dev_item;
+ struct btrfs_path path;
+ struct btrfs_key key;
+ struct btrfs_dev_extent *ptr;
+ u64 dev_id;
+ u64 used;
+ u64 total = 0;
+ int ret;
+
+ dev_item = btrfs_item_ptr(eb, slot, struct btrfs_dev_item);
+ dev_id = btrfs_device_id(eb, dev_item);
+ used = btrfs_device_bytes_used(eb, dev_item);
+
+ key.objectid = dev_id;
+ key.type = BTRFS_DEV_EXTENT_KEY;
+ key.offset = 0;
+
+ btrfs_init_path(&path);
+ ret = btrfs_search_slot(NULL, dev_root, &key, &path, 0, 0);
+ if (ret < 0) {
+ btrfs_item_key_to_cpu(eb, &key, slot);
+ error("cannot find any related dev extent for dev[%llu, %u, %llu]",
+ key.objectid, key.type, key.offset);
+ btrfs_release_path(&path);
+ return REFERENCER_MISSING;
+ }
+
+ /* 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 (key.objectid > dev_id)
+ break;
+ if (key.type != BTRFS_DEV_EXTENT_KEY || key.objectid != dev_id)
+ goto next;
+
+ ptr = btrfs_item_ptr(path.nodes[0], path.slots[0],
+ struct btrfs_dev_extent);
+ total += btrfs_dev_extent_length(path.nodes[0], ptr);
+next:
+ ret = btrfs_next_item(dev_root, &path);
+ if (ret)
+ break;
+ }
+ btrfs_release_path(&path);
+
+ if (used != total) {
+ btrfs_item_key_to_cpu(eb, &key, slot);
+ error(
+"Dev extent's total-byte %llu is not equal to bytes-used %llu in dev[%llu, %u, %llu]",
+ total, used, BTRFS_ROOT_TREE_OBJECTID,
+ BTRFS_DEV_EXTENT_KEY, dev_id);
+ return ACCOUNTING_MISMATCH;
+ }
+ return 0;
+}
+
+/*
+ * Check a block group item with its referener (chunk) and its used space
+ * with extent/metadata item
+ */
+static int check_block_group_item(struct btrfs_fs_info *fs_info,
+ struct extent_buffer *eb, int slot)
+{
+ struct btrfs_root *extent_root = fs_info->extent_root;
+ struct btrfs_root *chunk_root = fs_info->chunk_root;
+ struct btrfs_block_group_item *bi;
+ struct btrfs_block_group_item bg_item;
+ struct btrfs_path path;
+ struct btrfs_key bg_key;
+ struct btrfs_key chunk_key;
+ struct btrfs_key extent_key;
+ struct btrfs_chunk *chunk;
+ struct extent_buffer *leaf;
+ struct btrfs_extent_item *ei;
+ u32 nodesize = btrfs_super_nodesize(fs_info->super_copy);
+ u64 flags;
+ u64 bg_flags;
+ u64 used;
+ u64 total = 0;
+ int ret;
+ int err = 0;
+
+ btrfs_item_key_to_cpu(eb, &bg_key, slot);
+ bi = btrfs_item_ptr(eb, slot, struct btrfs_block_group_item);
+ read_extent_buffer(eb, &bg_item, (unsigned long)bi, sizeof(bg_item));
+ used = btrfs_block_group_used(&bg_item);
+ bg_flags = btrfs_block_group_flags(&bg_item);
+
+ chunk_key.objectid = BTRFS_FIRST_CHUNK_TREE_OBJECTID;
+ chunk_key.type = BTRFS_CHUNK_ITEM_KEY;
+ chunk_key.offset = bg_key.objectid;
+
+ btrfs_init_path(&path);
+ /* Search for the referencer chunk */
+ ret = btrfs_search_slot(NULL, chunk_root, &chunk_key, &path, 0, 0);
+ if (ret) {
+ error(
+ "block group[%llu %llu] did not find the related chunk item",
+ bg_key.objectid, bg_key.offset);
+ err |= REFERENCER_MISSING;
+ } else {
+ chunk = btrfs_item_ptr(path.nodes[0], path.slots[0],
+ struct btrfs_chunk);
+ if (btrfs_chunk_length(path.nodes[0], chunk) !=
+ bg_key.offset) {
+ error(
+ "block group[%llu %llu] related chunk item length does not match",
+ bg_key.objectid, bg_key.offset);
+ err |= REFERENCER_MISMATCH;
+ }
+ }
+ btrfs_release_path(&path);
+
+ /* Search from the block group bytenr */
+ extent_key.objectid = bg_key.objectid;
+ extent_key.type = 0;
+ extent_key.offset = 0;
+
+ btrfs_init_path(&path);
+ ret = btrfs_search_slot(NULL, extent_root, &extent_key, &path, 0, 0);
+ if (ret < 0)
+ goto out;
+
+ /* Iterate extent tree to account used space */
+ while (1) {
+ leaf = path.nodes[0];
+ btrfs_item_key_to_cpu(leaf, &extent_key, path.slots[0]);
+ if (extent_key.objectid >= bg_key.objectid + bg_key.offset)
+ break;
+
+ if (extent_key.type != BTRFS_METADATA_ITEM_KEY &&
+ extent_key.type != BTRFS_EXTENT_ITEM_KEY)
+ goto next;
+ if (extent_key.objectid < bg_key.objectid)
+ goto next;
+
+ if (extent_key.type == BTRFS_METADATA_ITEM_KEY)
+ total += nodesize;
+ else
+ total += extent_key.offset;
+
+ ei = btrfs_item_ptr(leaf, path.slots[0],
+ struct btrfs_extent_item);
+ flags = btrfs_extent_flags(leaf, ei);
+ if (flags & BTRFS_EXTENT_FLAG_DATA) {
+ if (!(bg_flags & BTRFS_BLOCK_GROUP_DATA)) {
+ error(
+ "bad extent[%llu, %llu) type mismatch with chunk",
+ extent_key.objectid,
+ extent_key.objectid + extent_key.offset);
+ err |= CHUNK_TYPE_MISMATCH;
+ }
+ } else if (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) {
+ if (!(bg_flags & (BTRFS_BLOCK_GROUP_SYSTEM |
+ BTRFS_BLOCK_GROUP_METADATA))) {
+ error(
+ "bad extent[%llu, %llu) type mismatch with chunk",
+ extent_key.objectid,
+ extent_key.objectid + nodesize);
+ err |= CHUNK_TYPE_MISMATCH;
+ }
+ }
+next:
+ ret = btrfs_next_item(extent_root, &path);
+ if (ret)
+ break;
+ }
+
+out:
+ btrfs_release_path(&path);
+
+ if (total != used) {
+ error(
+ "block group[%llu %llu] used %llu but extent items used %llu",
+ bg_key.objectid, bg_key.offset, used, total);
+ err |= ACCOUNTING_MISMATCH;
+ }
+ return err;
+}
+
+/*
+ * Check a chunk item.
+ * Including checking all referred dev_extents and block group
+ */
+static int check_chunk_item(struct btrfs_fs_info *fs_info,
+ struct extent_buffer *eb, int slot)
+{
+ struct btrfs_root *extent_root = fs_info->extent_root;
+ struct btrfs_root *dev_root = fs_info->dev_root;
+ struct btrfs_path path;
+ struct btrfs_key chunk_key;
+ struct btrfs_key bg_key;
+ struct btrfs_key devext_key;
+ struct btrfs_chunk *chunk;
+ struct extent_buffer *leaf;
+ struct btrfs_block_group_item *bi;
+ struct btrfs_block_group_item bg_item;
+ struct btrfs_dev_extent *ptr;
+ u32 sectorsize = btrfs_super_sectorsize(fs_info->super_copy);
+ u64 length;
+ u64 chunk_end;
+ u64 type;
+ u64 profile;
+ int num_stripes;
+ u64 offset;
+ u64 objectid;
+ int i;
+ int ret;
+ int err = 0;
+
+ btrfs_item_key_to_cpu(eb, &chunk_key, slot);
+ chunk = btrfs_item_ptr(eb, slot, struct btrfs_chunk);
+ length = btrfs_chunk_length(eb, chunk);
+ chunk_end = chunk_key.offset + length;
+ if (!IS_ALIGNED(length, sectorsize)) {
+ error("chunk[%llu %llu) not aligned to %u",
+ chunk_key.offset, chunk_end, sectorsize);
+ err |= BYTES_UNALIGNED;
+ goto out;
+ }
+
+ type = btrfs_chunk_type(eb, chunk);
+ profile = type & BTRFS_BLOCK_GROUP_PROFILE_MASK;
+ if (!(type & BTRFS_BLOCK_GROUP_TYPE_MASK)) {
+ error("chunk[%llu %llu) has no chunk type",
+ chunk_key.offset, chunk_end);
+ err |= UNKNOWN_TYPE;
+ }
+ if (profile && (profile & (profile - 1))) {
+ error("chunk[%llu %llu) multiple profiles detected: %llx",
+ chunk_key.offset, chunk_end, profile);
+ err |= UNKNOWN_TYPE;
+ }
+
+ bg_key.objectid = chunk_key.offset;
+ bg_key.type = BTRFS_BLOCK_GROUP_ITEM_KEY;
+ bg_key.offset = length;
+
+ btrfs_init_path(&path);
+ ret = btrfs_search_slot(NULL, extent_root, &bg_key, &path, 0, 0);
+ if (ret) {
+ error(
+ "chunk[%llu %llu) did not find the related block group item",
+ chunk_key.offset, chunk_end);
+ err |= REFERENCER_MISSING;
+ } else{
+ leaf = path.nodes[0];
+ bi = btrfs_item_ptr(leaf, path.slots[0],
+ struct btrfs_block_group_item);
+ read_extent_buffer(leaf, &bg_item, (unsigned long)bi,
+ sizeof(bg_item));
+ if (btrfs_block_group_flags(&bg_item) != type) {
+ error(
+"chunk[%llu %llu) related block group item flags mismatch, wanted: %llu, have: %llu",
+ chunk_key.offset, chunk_end, type,
+ btrfs_block_group_flags(&bg_item));
+ err |= REFERENCER_MISSING;
+ }
+ }
+
+ num_stripes = btrfs_chunk_num_stripes(eb, chunk);
+ for (i = 0; i < num_stripes; i++) {
+ btrfs_release_path(&path);
+ btrfs_init_path(&path);
+ devext_key.objectid = btrfs_stripe_devid_nr(eb, chunk, i);
+ devext_key.type = BTRFS_DEV_EXTENT_KEY;
+ devext_key.offset = btrfs_stripe_offset_nr(eb, chunk, i);
+
+ ret = btrfs_search_slot(NULL, dev_root, &devext_key, &path,
+ 0, 0);
+ if (ret)
+ goto not_match_dev;
+
+ leaf = path.nodes[0];
+ ptr = btrfs_item_ptr(leaf, path.slots[0],
+ struct btrfs_dev_extent);
+ objectid = btrfs_dev_extent_chunk_objectid(leaf, ptr);
+ offset = btrfs_dev_extent_chunk_offset(leaf, ptr);
+ if (objectid != chunk_key.objectid ||
+ offset != chunk_key.offset ||
+ btrfs_dev_extent_length(leaf, ptr) != length)
+ goto not_match_dev;
+ continue;
+not_match_dev:
+ err |= BACKREF_MISSING;
+ error(
+ "chunk[%llu %llu) stripe %d did not find the related dev extent",
+ chunk_key.objectid, chunk_end, i);
+ continue;
+ }
+ btrfs_release_path(&path);
+out:
+ return err;
+}
+
+/*
+ * Main entry function to check known items and update related accounting info
+ */
+static int check_leaf_items(struct btrfs_root *root, struct extent_buffer *eb)
+{
+ struct btrfs_fs_info *fs_info = root->fs_info;
+ struct btrfs_key key;
+ int slot = 0;
+ int type;
+ struct btrfs_extent_data_ref *dref;
+ int ret;
+ int err = 0;
+
+next:
+ btrfs_item_key_to_cpu(eb, &key, slot);
+ type = key.type;
+
+ switch (type) {
+ case BTRFS_EXTENT_DATA_KEY:
+ ret = check_extent_data_item(root, eb, slot);
+ err |= ret;
+ break;
+ case BTRFS_BLOCK_GROUP_ITEM_KEY:
+ ret = check_block_group_item(fs_info, eb, slot);
+ err |= ret;
+ break;
+ case BTRFS_DEV_ITEM_KEY:
+ ret = check_dev_item(fs_info, eb, slot);
+ err |= ret;
+ break;
+ case BTRFS_CHUNK_ITEM_KEY:
+ ret = check_chunk_item(fs_info, eb, slot);
+ err |= ret;
+ break;
+ case BTRFS_DEV_EXTENT_KEY:
+ ret = check_dev_extent_item(fs_info, eb, slot);
+ err |= ret;
+ break;
+ case BTRFS_EXTENT_ITEM_KEY:
+ case BTRFS_METADATA_ITEM_KEY:
+ ret = check_extent_item(fs_info, eb, slot);
+ err |= ret;
+ break;
+ case BTRFS_EXTENT_CSUM_KEY:
+ total_csum_bytes += btrfs_item_size_nr(eb, slot);
+ break;
+ case BTRFS_TREE_BLOCK_REF_KEY:
+ ret = check_tree_block_backref(fs_info, key.offset,
+ key.objectid, -1);
+ err |= ret;
+ break;
+ case BTRFS_EXTENT_DATA_REF_KEY:
+ dref = btrfs_item_ptr(eb, slot, struct btrfs_extent_data_ref);
+ ret = check_extent_data_backref(fs_info,
+ btrfs_extent_data_ref_root(eb, dref),
+ btrfs_extent_data_ref_objectid(eb, dref),
+ btrfs_extent_data_ref_offset(eb, dref),
+ key.objectid, 0,
+ btrfs_extent_data_ref_count(eb, dref));
+ err |= ret;
+ break;
+ case BTRFS_SHARED_BLOCK_REF_KEY:
+ ret = check_shared_block_backref(fs_info, key.offset,
+ key.objectid, -1);
+ err |= ret;
+ break;
+ case BTRFS_SHARED_DATA_REF_KEY:
+ ret = check_shared_data_backref(fs_info, key.offset,
+ key.objectid);
+ err |= ret;
+ break;
+ default:
+ break;
+ }
+
+ if (++slot < btrfs_header_nritems(eb))
+ goto next;
+
+ return err;
+}
+
+/*
+ * Helper function for later fs/subvol tree check. To determine if a tree
+ * block should be checked.
+ * This function will ensure only the direct referencer with lowest rootid to
+ * check a fs/subvolume tree block.
+ *
+ * Backref check at extent tree would detect errors like missing subvolume
+ * tree, so we can do aggressive check to reduce duplicated checks.
+ */
+static int should_check(struct btrfs_root *root, struct extent_buffer *eb)
+{
+ struct btrfs_root *extent_root = root->fs_info->extent_root;
+ struct btrfs_key key;
+ struct btrfs_path path;
+ struct extent_buffer *leaf;
+ int slot;
+ struct btrfs_extent_item *ei;
+ unsigned long ptr;
+ unsigned long end;
+ int type;
+ u32 item_size;
+ u64 offset;
+ struct btrfs_extent_inline_ref *iref;
+ int ret;
+
+ btrfs_init_path(&path);
+ key.objectid = btrfs_header_bytenr(eb);
+ key.type = BTRFS_METADATA_ITEM_KEY;
+ key.offset = (u64)-1;
+
+ /*
+ * Any failure in backref resolving means we can't determine
+ * whom the tree block belongs to.
+ * So in that case, we need to check that tree block
+ */
+ ret = btrfs_search_slot(NULL, extent_root, &key, &path, 0, 0);
+ if (ret < 0)
+ goto need_check;
+
+ ret = btrfs_previous_extent_item(extent_root, &path,
+ btrfs_header_bytenr(eb));
+ if (ret)
+ goto need_check;
+
+ leaf = path.nodes[0];
+ slot = path.slots[0];
+ btrfs_item_key_to_cpu(leaf, &key, slot);
+ ei = btrfs_item_ptr(leaf, slot, struct btrfs_extent_item);
+
+ if (key.type == BTRFS_METADATA_ITEM_KEY) {
+ iref = (struct btrfs_extent_inline_ref *)(ei + 1);
+ } else {
+ struct btrfs_tree_block_info *info;
+
+ info = (struct btrfs_tree_block_info *)(ei + 1);
+ iref = (struct btrfs_extent_inline_ref *)(info + 1);
+ }
+
+ item_size = btrfs_item_size_nr(leaf, slot);
+ ptr = (unsigned long)iref;
+ end = (unsigned long)ei + item_size;
+ while (ptr < end) {
+ iref = (struct btrfs_extent_inline_ref *)ptr;
+ type = btrfs_extent_inline_ref_type(leaf, iref);
+ offset = btrfs_extent_inline_ref_offset(leaf, iref);
+
+ /*
+ * We only check the tree block if current root is
+ * the lowest referencer of it.
+ */
+ if (type == BTRFS_TREE_BLOCK_REF_KEY &&
+ offset < root->objectid) {
+ btrfs_release_path(&path);
+ return 0;
+ }
+
+ ptr += btrfs_extent_inline_ref_size(type);
+ }
+ /*
+ * Normally we should also check keyed tree block ref, but that may be
+ * very time consuming. Inlined ref should already make us skip a lot
+ * of refs now. So skip search keyed tree block ref.
+ */
+
+need_check:
+ btrfs_release_path(&path);
+ return 1;
+}
+
+/*
+ * Traversal function for tree block. We will do:
+ * 1) Skip shared fs/subvolume tree blocks
+ * 2) Update related bytes accounting
+ * 3) Pre-order traversal
+ */
+static int traverse_tree_block(struct btrfs_root *root,
+ struct extent_buffer *node)
+{
+ struct extent_buffer *eb;
+ struct btrfs_key key;
+ struct btrfs_key drop_key;
+ int level;
+ u64 nr;
+ int i;
+ int err = 0;
+ int ret;
+
+ /*
+ * Skip shared fs/subvolume tree block, in that case they will
+ * be checked by referencer with lowest rootid
+ */
+ if (is_fstree(root->objectid) && !should_check(root, node))
+ return 0;
+
+ /* Update bytes accounting */
+ total_btree_bytes += node->len;
+ if (fs_root_objectid(btrfs_header_owner(node)))
+ total_fs_tree_bytes += node->len;
+ if (btrfs_header_owner(node) == BTRFS_EXTENT_TREE_OBJECTID)
+ total_extent_tree_bytes += node->len;
+ if (!found_old_backref &&
+ btrfs_header_owner(node) == BTRFS_TREE_RELOC_OBJECTID &&
+ btrfs_header_backref_rev(node) == BTRFS_MIXED_BACKREF_REV &&
+ !btrfs_header_flag(node, BTRFS_HEADER_FLAG_RELOC))
+ found_old_backref = 1;
+
+ /* pre-order tranversal, check itself first */
+ level = btrfs_header_level(node);
+ ret = check_tree_block_ref(root, node, btrfs_header_bytenr(node),
+ btrfs_header_level(node),
+ btrfs_header_owner(node));
+ err |= ret;
+ if (err)
+ error(
+ "check %s failed root %llu bytenr %llu level %d, force continue check",
+ level ? "node":"leaf", root->objectid,
+ btrfs_header_bytenr(node), btrfs_header_level(node));
+
+ if (!level) {
+ btree_space_waste += btrfs_leaf_free_space(root, node);
+ ret = check_leaf_items(root, node);
+ err |= ret;
+ return err;
+ }
+
+ nr = btrfs_header_nritems(node);
+ btrfs_disk_key_to_cpu(&drop_key, &root->root_item.drop_progress);
+ btree_space_waste += (BTRFS_NODEPTRS_PER_BLOCK(root) - nr) *
+ sizeof(struct btrfs_key_ptr);
+
+ /* Then check all its children */
+ for (i = 0; i < nr; i++) {
+ u64 blocknr = btrfs_node_blockptr(node, i);
+
+ btrfs_node_key_to_cpu(node, &key, i);
+ if (level == root->root_item.drop_level &&
+ is_dropped_key(&key, &drop_key))
+ continue;
+
+ /*
+ * As a btrfs tree has most 8 levels (0..7), so it's quite safe
+ * to call the function itself.
+ */
+ eb = read_tree_block(root, blocknr, root->nodesize, 0);
+ if (extent_buffer_uptodate(eb)) {
+ ret = traverse_tree_block(root, eb);
+ err |= ret;
+ }
+ free_extent_buffer(eb);
+ }
+
+ return err;
+}
+
+/*
+ * Low memory usage version check_chunks_and_extents.
+ */
+static int check_chunks_and_extents_v2(struct btrfs_root *root)
+{
+ struct btrfs_path path;
+ struct btrfs_key key;
+ struct btrfs_root *root1;
+ struct btrfs_root *cur_root;
+ int err = 0;
+ int ret;
+
+ root1 = root->fs_info->chunk_root;
+ ret = traverse_tree_block(root1, root1->node);
+ err |= ret;
+
+ root1 = root->fs_info->tree_root;
+ ret = traverse_tree_block(root1, root1->node);
+ err |= ret;
+
+ btrfs_init_path(&path);
+ key.objectid = BTRFS_EXTENT_TREE_OBJECTID;
+ key.offset = 0;
+ key.type = BTRFS_ROOT_ITEM_KEY;
+
+ ret = btrfs_search_slot(NULL, root1, &key, &path, 0, 0);
+ if (ret) {
+ error("cannot find extent treet in tree_root");
goto out;
}
- ret = check_devices(&dev_cache, &dev_extent_cache);
- if (ret && err)
- ret = err;
+ while (1) {
+ btrfs_item_key_to_cpu(path.nodes[0], &key, path.slots[0]);
+ if (key.type != BTRFS_ROOT_ITEM_KEY)
+ goto next;
+ key.offset = (u64)-1;
-out:
- task_stop(ctx.info);
- if (repair) {
- free_corrupt_blocks_tree(root->fs_info->corrupt_blocks);
- extent_io_tree_cleanup(&excluded_extents);
- root->fs_info->fsck_extent_cache = NULL;
- root->fs_info->free_extent_hook = NULL;
- root->fs_info->corrupt_blocks = NULL;
- root->fs_info->excluded_extents = NULL;
+ 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;
+
+next:
+ ret = btrfs_next_item(root1, &path);
+ if (ret)
+ goto out;
}
- free(bits);
- free_chunk_cache_tree(&chunk_cache);
- free_device_cache_tree(&dev_cache);
- free_block_group_tree(&block_group_cache);
- free_device_extent_tree(&dev_extent_cache);
- free_extent_cache_tree(&seen);
- free_extent_cache_tree(&pending);
- free_extent_cache_tree(&reada);
- free_extent_cache_tree(&nodes);
- return ret;
-loop:
- free_corrupt_blocks_tree(root->fs_info->corrupt_blocks);
- free_extent_cache_tree(&seen);
- free_extent_cache_tree(&pending);
- free_extent_cache_tree(&reada);
- free_extent_cache_tree(&nodes);
- free_chunk_cache_tree(&chunk_cache);
- 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_root_item_list(&normal_trees);
- free_root_item_list(&dropping_trees);
- extent_io_tree_cleanup(&excluded_extents);
- goto again;
+
+out:
+ btrfs_release_path(&path);
+ return err;
}
static int btrfs_fsck_reinit_root(struct btrfs_trans_handle *trans,
goto init;
}
c = btrfs_alloc_free_block(trans, root,
- btrfs_level_size(root, 0),
+ root->nodesize,
root->root_key.objectid,
&disk_key, level, 0, 0);
if (IS_ERR(c)) {
struct btrfs_root_item *ri;
struct btrfs_key key;
u64 bytenr;
- u32 leafsize;
+ u32 nodesize;
int level = btrfs_header_level(eb);
int nritems;
int ret;
btrfs_pin_extent(fs_info, eb->start, eb->len);
- leafsize = btrfs_super_leafsize(fs_info->super_copy);
+ nodesize = btrfs_super_nodesize(fs_info->super_copy);
nritems = btrfs_header_nritems(eb);
for (i = 0; i < nritems; i++) {
if (level == 0) {
* just pass in extent_root.
*/
tmp = read_tree_block(fs_info->extent_root, bytenr,
- leafsize, 0);
+ nodesize, 0);
if (!extent_buffer_uptodate(tmp)) {
fprintf(stderr, "Error reading root block\n");
return -EIO;
/* If we aren't the tree root don't read the block */
if (level == 1 && !tree_root) {
- btrfs_pin_extent(fs_info, bytenr, leafsize);
+ btrfs_pin_extent(fs_info, bytenr, nodesize);
continue;
}
tmp = read_tree_block(fs_info->extent_root, bytenr,
- leafsize, 0);
+ nodesize, 0);
if (!extent_buffer_uptodate(tmp)) {
fprintf(stderr, "Error reading tree block\n");
return -EIO;
static int reset_block_groups(struct btrfs_fs_info *fs_info)
{
struct btrfs_block_group_cache *cache;
- struct btrfs_path *path;
+ struct btrfs_path path;
struct extent_buffer *leaf;
struct btrfs_chunk *chunk;
struct btrfs_key key;
int ret;
u64 start;
- path = btrfs_alloc_path();
- if (!path)
- return -ENOMEM;
-
+ btrfs_init_path(&path);
key.objectid = 0;
key.type = BTRFS_CHUNK_ITEM_KEY;
key.offset = 0;
-
- ret = btrfs_search_slot(NULL, fs_info->chunk_root, &key, path, 0, 0);
+ ret = btrfs_search_slot(NULL, fs_info->chunk_root, &key, &path, 0, 0);
if (ret < 0) {
- btrfs_free_path(path);
+ btrfs_release_path(&path);
return ret;
}
/* First we need to create the in-memory block groups */
while (1) {
- if (path->slots[0] >= btrfs_header_nritems(path->nodes[0])) {
- ret = btrfs_next_leaf(fs_info->chunk_root, path);
+ if (path.slots[0] >= btrfs_header_nritems(path.nodes[0])) {
+ ret = btrfs_next_leaf(fs_info->chunk_root, &path);
if (ret < 0) {
- btrfs_free_path(path);
+ btrfs_release_path(&path);
return ret;
}
if (ret) {
break;
}
}
- leaf = path->nodes[0];
- btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
+ leaf = path.nodes[0];
+ btrfs_item_key_to_cpu(leaf, &key, path.slots[0]);
if (key.type != BTRFS_CHUNK_ITEM_KEY) {
- path->slots[0]++;
+ path.slots[0]++;
continue;
}
- chunk = btrfs_item_ptr(leaf, path->slots[0],
- struct btrfs_chunk);
+ chunk = btrfs_item_ptr(leaf, path.slots[0], struct btrfs_chunk);
btrfs_add_block_group(fs_info, 0,
btrfs_chunk_type(leaf, chunk),
key.objectid, key.offset,
set_extent_dirty(&fs_info->free_space_cache, key.offset,
key.offset + btrfs_chunk_length(leaf, chunk),
GFP_NOFS);
- path->slots[0]++;
+ path.slots[0]++;
}
start = 0;
while (1) {
start = cache->key.objectid + cache->key.offset;
}
- btrfs_free_path(path);
+ btrfs_release_path(&path);
return 0;
}
struct btrfs_fs_info *fs_info)
{
struct btrfs_root *root = fs_info->tree_root;
- struct btrfs_path *path;
+ struct btrfs_path path;
struct extent_buffer *leaf;
struct btrfs_key key;
int del_slot, del_nr = 0;
int ret;
int found = 0;
- path = btrfs_alloc_path();
- if (!path)
- return -ENOMEM;
-
+ btrfs_init_path(&path);
key.objectid = BTRFS_BALANCE_OBJECTID;
key.type = BTRFS_BALANCE_ITEM_KEY;
key.offset = 0;
-
- ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
+ ret = btrfs_search_slot(trans, root, &key, &path, -1, 1);
if (ret) {
if (ret > 0)
ret = 0;
goto out;
}
- ret = btrfs_del_item(trans, root, path);
+ ret = btrfs_del_item(trans, root, &path);
if (ret)
goto out;
- btrfs_release_path(path);
+ btrfs_release_path(&path);
key.objectid = BTRFS_TREE_RELOC_OBJECTID;
key.type = BTRFS_ROOT_ITEM_KEY;
key.offset = 0;
-
- ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
+ ret = btrfs_search_slot(trans, root, &key, &path, -1, 1);
if (ret < 0)
goto out;
while (1) {
- if (path->slots[0] >= btrfs_header_nritems(path->nodes[0])) {
+ if (path.slots[0] >= btrfs_header_nritems(path.nodes[0])) {
if (!found)
break;
if (del_nr) {
- ret = btrfs_del_items(trans, root, path,
+ ret = btrfs_del_items(trans, root, &path,
del_slot, del_nr);
del_nr = 0;
if (ret)
goto out;
}
key.offset++;
- btrfs_release_path(path);
+ btrfs_release_path(&path);
found = 0;
- ret = btrfs_search_slot(trans, root, &key, path,
+ ret = btrfs_search_slot(trans, root, &key, &path,
-1, 1);
if (ret < 0)
goto out;
continue;
}
found = 1;
- leaf = path->nodes[0];
- btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
+ leaf = path.nodes[0];
+ btrfs_item_key_to_cpu(leaf, &key, path.slots[0]);
if (key.objectid > BTRFS_TREE_RELOC_OBJECTID)
break;
if (key.objectid != BTRFS_TREE_RELOC_OBJECTID) {
- path->slots[0]++;
+ path.slots[0]++;
continue;
}
if (!del_nr) {
- del_slot = path->slots[0];
+ del_slot = path.slots[0];
del_nr = 1;
} else {
del_nr++;
}
- path->slots[0]++;
+ path.slots[0]++;
}
if (del_nr) {
- ret = btrfs_del_items(trans, root, path, del_slot, del_nr);
+ ret = btrfs_del_items(trans, root, &path, del_slot, del_nr);
if (ret)
goto out;
}
- btrfs_release_path(path);
+ btrfs_release_path(&path);
reinit_data_reloc:
key.objectid = BTRFS_DATA_RELOC_TREE_OBJECTID;
goto out;
ret = btrfs_make_root_dir(trans, root, BTRFS_FIRST_FREE_OBJECTID);
out:
- btrfs_free_path(path);
+ btrfs_release_path(&path);
return ret;
}
ret = reset_balance(trans, fs_info);
if (ret)
- fprintf(stderr, "error reseting the pending balance\n");
+ fprintf(stderr, "error resetting the pending balance\n");
return ret;
}
static int recow_extent_buffer(struct btrfs_root *root, struct extent_buffer *eb)
{
- struct btrfs_path *path;
+ struct btrfs_path path;
struct btrfs_trans_handle *trans;
struct btrfs_key key;
int ret;
return PTR_ERR(root);
}
- path = btrfs_alloc_path();
- if (!path)
- return -ENOMEM;
-
trans = btrfs_start_transaction(root, 1);
- if (IS_ERR(trans)) {
- btrfs_free_path(path);
+ if (IS_ERR(trans))
return PTR_ERR(trans);
- }
- path->lowest_level = btrfs_header_level(eb);
- if (path->lowest_level)
+ btrfs_init_path(&path);
+ path.lowest_level = btrfs_header_level(eb);
+ if (path.lowest_level)
btrfs_node_key_to_cpu(eb, &key, 0);
else
btrfs_item_key_to_cpu(eb, &key, 0);
- ret = btrfs_search_slot(trans, root, &key, path, 0, 1);
+ ret = btrfs_search_slot(trans, root, &key, &path, 0, 1);
btrfs_commit_transaction(trans, root);
- btrfs_free_path(path);
+ btrfs_release_path(&path);
return ret;
}
static int delete_bad_item(struct btrfs_root *root, struct bad_item *bad)
{
- struct btrfs_path *path;
+ struct btrfs_path path;
struct btrfs_trans_handle *trans;
struct btrfs_key key;
int ret;
return PTR_ERR(root);
}
- path = btrfs_alloc_path();
- if (!path)
- return -ENOMEM;
-
trans = btrfs_start_transaction(root, 1);
- if (IS_ERR(trans)) {
- btrfs_free_path(path);
+ if (IS_ERR(trans))
return PTR_ERR(trans);
- }
- ret = btrfs_search_slot(trans, root, &bad->key, path, -1, 1);
+ btrfs_init_path(&path);
+ ret = btrfs_search_slot(trans, root, &bad->key, &path, -1, 1);
if (ret) {
if (ret > 0)
ret = 0;
goto out;
}
- ret = btrfs_del_item(trans, root, path);
+ ret = btrfs_del_item(trans, root, &path);
out:
btrfs_commit_transaction(trans, root);
- btrfs_free_path(path);
+ btrfs_release_path(&path);
return ret;
}
struct btrfs_root *csum_root,
struct btrfs_root *cur_root)
{
- struct btrfs_path *path;
+ struct btrfs_path path;
struct btrfs_key key;
struct extent_buffer *node;
struct btrfs_file_extent_item *fi;
int slot = 0;
int ret = 0;
- path = btrfs_alloc_path();
- if (!path)
- return -ENOMEM;
buf = malloc(cur_root->fs_info->csum_root->sectorsize);
- if (!buf) {
- ret = -ENOMEM;
- goto out;
- }
+ if (!buf)
+ return -ENOMEM;
+ btrfs_init_path(&path);
key.objectid = 0;
key.offset = 0;
key.type = 0;
-
- ret = btrfs_search_slot(NULL, cur_root, &key, path, 0, 0);
+ ret = btrfs_search_slot(NULL, cur_root, &key, &path, 0, 0);
if (ret < 0)
goto out;
/* Iterate all regular file extents and fill its csum */
while (1) {
- btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
+ btrfs_item_key_to_cpu(path.nodes[0], &key, path.slots[0]);
if (key.type != BTRFS_EXTENT_DATA_KEY)
goto next;
- node = path->nodes[0];
- slot = path->slots[0];
+ node = path.nodes[0];
+ slot = path.slots[0];
fi = btrfs_item_ptr(node, slot, struct btrfs_file_extent_item);
if (btrfs_file_extent_type(node, fi) != BTRFS_FILE_EXTENT_REG)
goto next;
* TODO: if next leaf is corrupted, jump to nearest next valid
* leaf.
*/
- ret = btrfs_next_item(cur_root, path);
+ ret = btrfs_next_item(cur_root, &path);
if (ret < 0)
goto out;
if (ret > 0) {
}
out:
- btrfs_free_path(path);
+ btrfs_release_path(&path);
free(buf);
return ret;
}
struct btrfs_root *csum_root)
{
struct btrfs_fs_info *fs_info = csum_root->fs_info;
- struct btrfs_path *path;
+ struct btrfs_path path;
struct btrfs_root *tree_root = fs_info->tree_root;
struct btrfs_root *cur_root;
struct extent_buffer *node;
int slot = 0;
int ret = 0;
- path = btrfs_alloc_path();
- if (!path)
- return -ENOMEM;
-
+ btrfs_init_path(&path);
key.objectid = BTRFS_FS_TREE_OBJECTID;
key.offset = 0;
key.type = BTRFS_ROOT_ITEM_KEY;
-
- ret = btrfs_search_slot(NULL, tree_root, &key, path, 0, 0);
+ ret = btrfs_search_slot(NULL, tree_root, &key, &path, 0, 0);
if (ret < 0)
goto out;
if (ret > 0) {
}
while (1) {
- node = path->nodes[0];
- slot = 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 (ret < 0)
goto out;
next:
- ret = btrfs_next_item(tree_root, path);
+ ret = btrfs_next_item(tree_root, &path);
if (ret > 0) {
ret = 0;
goto out;
}
out:
- btrfs_free_path(path);
+ btrfs_release_path(&path);
return ret;
}
struct btrfs_root *csum_root)
{
struct btrfs_root *extent_root = csum_root->fs_info->extent_root;
- struct btrfs_path *path;
+ struct btrfs_path path;
struct btrfs_extent_item *ei;
struct extent_buffer *leaf;
char *buf;
struct btrfs_key key;
int ret;
- path = btrfs_alloc_path();
- if (!path)
- return -ENOMEM;
-
+ btrfs_init_path(&path);
key.objectid = 0;
key.type = BTRFS_EXTENT_ITEM_KEY;
key.offset = 0;
-
- ret = btrfs_search_slot(NULL, extent_root, &key, path, 0, 0);
+ ret = btrfs_search_slot(NULL, extent_root, &key, &path, 0, 0);
if (ret < 0) {
- btrfs_free_path(path);
+ btrfs_release_path(&path);
return ret;
}
buf = malloc(csum_root->sectorsize);
if (!buf) {
- btrfs_free_path(path);
+ btrfs_release_path(&path);
return -ENOMEM;
}
while (1) {
- if (path->slots[0] >= btrfs_header_nritems(path->nodes[0])) {
- ret = btrfs_next_leaf(extent_root, path);
+ if (path.slots[0] >= btrfs_header_nritems(path.nodes[0])) {
+ ret = btrfs_next_leaf(extent_root, &path);
if (ret < 0)
break;
if (ret) {
break;
}
}
- leaf = path->nodes[0];
+ leaf = path.nodes[0];
- btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
+ btrfs_item_key_to_cpu(leaf, &key, path.slots[0]);
if (key.type != BTRFS_EXTENT_ITEM_KEY) {
- path->slots[0]++;
+ path.slots[0]++;
continue;
}
- ei = btrfs_item_ptr(leaf, path->slots[0],
+ ei = btrfs_item_ptr(leaf, path.slots[0],
struct btrfs_extent_item);
if (!(btrfs_extent_flags(leaf, ei) &
BTRFS_EXTENT_FLAG_DATA)) {
- path->slots[0]++;
+ path.slots[0]++;
continue;
}
key.offset);
if (ret)
break;
- path->slots[0]++;
+ path.slots[0]++;
}
- btrfs_free_path(path);
+ btrfs_release_path(&path);
free(buf);
return ret;
}
return fill_csum_tree_from_extent(trans, csum_root);
}
-struct root_item_info {
- /* level of the root */
- u8 level;
- /* number of nodes at this level, must be 1 for a root */
- int node_count;
- u64 bytenr;
- u64 gen;
- struct cache_extent cache_extent;
-};
-
-static struct cache_tree *roots_info_cache = NULL;
-
static void free_roots_info_cache(void)
{
if (!roots_info_cache)
int ret = 0;
struct btrfs_key key;
struct extent_buffer *leaf;
- struct btrfs_path *path;
+ struct btrfs_path path;
if (!roots_info_cache) {
roots_info_cache = malloc(sizeof(*roots_info_cache));
cache_tree_init(roots_info_cache);
}
- path = btrfs_alloc_path();
- if (!path)
- return -ENOMEM;
-
+ btrfs_init_path(&path);
key.objectid = 0;
key.type = BTRFS_EXTENT_ITEM_KEY;
key.offset = 0;
-
- ret = btrfs_search_slot(NULL, info->extent_root, &key, path, 0, 0);
+ ret = btrfs_search_slot(NULL, info->extent_root, &key, &path, 0, 0);
if (ret < 0)
goto out;
- leaf = path->nodes[0];
+ leaf = path.nodes[0];
while (1) {
struct btrfs_key found_key;
struct btrfs_extent_item *ei;
struct btrfs_extent_inline_ref *iref;
- int slot = path->slots[0];
+ int slot = path.slots[0];
int type;
u64 flags;
u64 root_id;
struct root_item_info *rii;
if (slot >= btrfs_header_nritems(leaf)) {
- ret = btrfs_next_leaf(info->extent_root, path);
+ ret = btrfs_next_leaf(info->extent_root, &path);
if (ret < 0) {
break;
} else if (ret) {
ret = 0;
break;
}
- leaf = path->nodes[0];
- slot = path->slots[0];
+ leaf = path.nodes[0];
+ slot = path.slots[0];
}
- btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]);
+ btrfs_item_key_to_cpu(leaf, &found_key, path.slots[0]);
if (found_key.type != BTRFS_EXTENT_ITEM_KEY &&
found_key.type != BTRFS_METADATA_ITEM_KEY)
rii->node_count++;
}
next:
- path->slots[0]++;
+ path.slots[0]++;
}
out:
- btrfs_free_path(path);
+ btrfs_release_path(&path);
return ret;
}
*/
static int repair_root_items(struct btrfs_fs_info *info)
{
- struct btrfs_path *path = NULL;
+ struct btrfs_path path;
struct btrfs_key key;
struct extent_buffer *leaf;
struct btrfs_trans_handle *trans = NULL;
int bad_roots = 0;
int need_trans = 0;
+ btrfs_init_path(&path);
+
ret = build_roots_info_cache(info);
if (ret)
goto out;
- path = btrfs_alloc_path();
- if (!path) {
- ret = -ENOMEM;
- goto out;
- }
-
key.objectid = BTRFS_FIRST_FREE_OBJECTID;
key.type = BTRFS_ROOT_ITEM_KEY;
key.offset = 0;
}
}
- ret = btrfs_search_slot(trans, info->tree_root, &key, path,
+ ret = btrfs_search_slot(trans, info->tree_root, &key, &path,
0, trans ? 1 : 0);
if (ret < 0)
goto out;
- leaf = path->nodes[0];
+ leaf = path.nodes[0];
while (1) {
struct btrfs_key found_key;
- if (path->slots[0] >= btrfs_header_nritems(leaf)) {
- int no_more_keys = find_next_key(path, &key);
+ if (path.slots[0] >= btrfs_header_nritems(leaf)) {
+ int no_more_keys = find_next_key(&path, &key);
- btrfs_release_path(path);
+ btrfs_release_path(&path);
if (trans) {
ret = btrfs_commit_transaction(trans,
info->tree_root);
goto again;
}
- btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]);
+ btrfs_item_key_to_cpu(leaf, &found_key, path.slots[0]);
if (found_key.type != BTRFS_ROOT_ITEM_KEY)
goto next;
if (found_key.objectid == BTRFS_TREE_RELOC_OBJECTID)
goto next;
- ret = maybe_repair_root_item(info, path, &found_key,
+ ret = maybe_repair_root_item(info, &path, &found_key,
trans ? 0 : 1);
if (ret < 0)
goto out;
if (!trans && repair) {
need_trans = 1;
key = found_key;
- btrfs_release_path(path);
+ btrfs_release_path(&path);
goto again;
}
bad_roots++;
}
next:
- path->slots[0]++;
+ path.slots[0]++;
}
ret = 0;
out:
free_roots_info_cache();
- btrfs_free_path(path);
+ btrfs_release_path(&path);
if (trans)
btrfs_commit_transaction(trans, info->tree_root);
if (ret < 0)
return bad_roots;
}
+static int clear_free_space_cache(struct btrfs_fs_info *fs_info)
+{
+ struct btrfs_trans_handle *trans;
+ struct btrfs_block_group_cache *bg_cache;
+ u64 current = 0;
+ int ret = 0;
+
+ /* Clear all free space cache inodes and its extent data */
+ while (1) {
+ bg_cache = btrfs_lookup_first_block_group(fs_info, current);
+ if (!bg_cache)
+ break;
+ ret = btrfs_clear_free_space_cache(fs_info, bg_cache);
+ if (ret < 0)
+ return ret;
+ current = bg_cache->key.objectid + bg_cache->key.offset;
+ }
+
+ /* Don't forget to set cache_generation to -1 */
+ trans = btrfs_start_transaction(fs_info->tree_root, 0);
+ if (IS_ERR(trans)) {
+ error("failed to update super block cache generation");
+ return PTR_ERR(trans);
+ }
+ btrfs_set_super_cache_generation(fs_info->super_copy, (u64)-1);
+ btrfs_commit_transaction(trans, fs_info->tree_root);
+
+ return ret;
+}
+
const char * const cmd_check_usage[] = {
"btrfs check [options] <device>",
- "Check structural inegrity of a filesystem (unmounted).",
- "Check structural inegrity of an unmounted filesystem. Verify internal",
+ "Check structural integrity of a filesystem (unmounted).",
+ "Check structural integrity of an unmounted filesystem. Verify internal",
"trees' consistency and item connectivity. In the repair mode try to",
- "fix the problems found.",
+ "fix the problems found. ",
"WARNING: the repair mode is considered dangerous",
"",
"-s|--super <superblock> use this superblock copy",
- "-b|--backup use the backup root copy",
+ "-b|--backup use the first valid backup root copy",
"--repair try to repair the filesystem",
"--readonly run in read-only mode (default)",
"--init-csum-tree create a new CRC tree",
"--init-extent-tree create a new extent tree",
- "--check-data-csum verify checkums of data blocks",
- "-Q|--qgroup-report print a report on qgroup consistency",
+ "--mode <MODE> allows choice of memory/IO trade-offs",
+ " where MODE is one of:",
+ " original - read inodes and extents to memory (requires",
+ " more memory, does less IO)",
+ " lowmem - try to use less memory but read blocks again",
+ " when needed",
+ "--check-data-csum verify checksums of data blocks",
+ "-Q|--qgroup-report print a report on qgroup consistency",
"-E|--subvol-extents <subvolid>",
" print subvolume extents and sharing state",
"-r|--tree-root <bytenr> use the given bytenr for the tree root",
+ "--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 bytenr = 0;
u64 subvolid = 0;
u64 tree_root_bytenr = 0;
+ u64 chunk_root_bytenr = 0;
char uuidbuf[BTRFS_UUID_UNPARSED_SIZE];
int ret;
u64 num;
int init_csum_tree = 0;
int readonly = 0;
+ int clear_space_cache = 0;
int qgroup_report = 0;
- enum btrfs_open_ctree_flags ctree_flags = OPEN_CTREE_EXCLUSIVE;
+ int qgroups_repaired = 0;
+ unsigned ctree_flags = OPEN_CTREE_EXCLUSIVE;
while(1) {
int c;
- enum { OPT_REPAIR = 257, OPT_INIT_CSUM, OPT_INIT_EXTENT,
- OPT_CHECK_CSUM, OPT_READONLY };
+ enum { GETOPT_VAL_REPAIR = 257, GETOPT_VAL_INIT_CSUM,
+ GETOPT_VAL_INIT_EXTENT, GETOPT_VAL_CHECK_CSUM,
+ GETOPT_VAL_READONLY, GETOPT_VAL_CHUNK_TREE,
+ GETOPT_VAL_MODE, GETOPT_VAL_CLEAR_SPACE_CACHE };
static const struct option long_options[] = {
{ "super", required_argument, NULL, 's' },
- { "repair", no_argument, NULL, OPT_REPAIR },
- { "readonly", no_argument, NULL, OPT_READONLY },
- { "init-csum-tree", no_argument, NULL, OPT_INIT_CSUM },
- { "init-extent-tree", no_argument, NULL, OPT_INIT_EXTENT },
- { "check-data-csum", no_argument, NULL, OPT_CHECK_CSUM },
+ { "repair", no_argument, NULL, GETOPT_VAL_REPAIR },
+ { "readonly", no_argument, NULL, GETOPT_VAL_READONLY },
+ { "init-csum-tree", no_argument, NULL,
+ GETOPT_VAL_INIT_CSUM },
+ { "init-extent-tree", no_argument, NULL,
+ GETOPT_VAL_INIT_EXTENT },
+ { "check-data-csum", no_argument, NULL,
+ GETOPT_VAL_CHECK_CSUM },
{ "backup", no_argument, NULL, 'b' },
{ "subvol-extents", required_argument, NULL, 'E' },
{ "qgroup-report", no_argument, NULL, 'Q' },
{ "tree-root", required_argument, NULL, 'r' },
+ { "chunk-root", required_argument, NULL,
+ GETOPT_VAL_CHUNK_TREE },
{ "progress", no_argument, NULL, 'p' },
+ { "mode", required_argument, NULL,
+ GETOPT_VAL_MODE },
+ { "clear-space-cache", required_argument, NULL,
+ GETOPT_VAL_CLEAR_SPACE_CACHE},
{ NULL, 0, NULL, 0}
};
case 's':
num = arg_strtou64(optarg);
if (num >= BTRFS_SUPER_MIRROR_MAX) {
- fprintf(stderr,
- "ERROR: super mirror should be less than: %d\n",
+ error(
+ "super mirror should be less than %d",
BTRFS_SUPER_MIRROR_MAX);
exit(1);
}
case 'r':
tree_root_bytenr = arg_strtou64(optarg);
break;
+ case GETOPT_VAL_CHUNK_TREE:
+ chunk_root_bytenr = arg_strtou64(optarg);
+ break;
case 'p':
ctx.progress_enabled = true;
break;
case '?':
case 'h':
usage(cmd_check_usage);
- case OPT_REPAIR:
+ case GETOPT_VAL_REPAIR:
printf("enabling repair mode\n");
repair = 1;
ctree_flags |= OPEN_CTREE_WRITES;
break;
- case OPT_READONLY:
+ case GETOPT_VAL_READONLY:
readonly = 1;
break;
- case OPT_INIT_CSUM:
+ case GETOPT_VAL_INIT_CSUM:
printf("Creating a new CRC tree\n");
init_csum_tree = 1;
repair = 1;
ctree_flags |= OPEN_CTREE_WRITES;
break;
- case OPT_INIT_EXTENT:
+ case GETOPT_VAL_INIT_EXTENT:
init_extent_tree = 1;
ctree_flags |= (OPEN_CTREE_WRITES |
OPEN_CTREE_NO_BLOCK_GROUPS);
repair = 1;
break;
- case OPT_CHECK_CSUM:
+ case GETOPT_VAL_CHECK_CSUM:
check_data_csum = 1;
break;
+ case GETOPT_VAL_MODE:
+ check_mode = parse_check_mode(optarg);
+ if (check_mode == CHECK_MODE_UNKNOWN) {
+ error("unknown mode: %s", optarg);
+ exit(1);
+ }
+ break;
+ case GETOPT_VAL_CLEAR_SPACE_CACHE:
+ if (strcmp(optarg, "v1") != 0) {
+ error(
+ "only v1 support implmented, unrecognized value %s",
+ optarg);
+ exit(1);
+ }
+ clear_space_cache = 1;
+ ctree_flags |= OPEN_CTREE_WRITES;
+ break;
}
}
/* This check is the only reason for --readonly to exist */
if (readonly && repair) {
- fprintf(stderr, "Repair options are not compatible with --readonly\n");
+ error("repair options are not compatible with --readonly");
+ exit(1);
+ }
+
+ /*
+ * Not supported yet
+ */
+ if (repair && check_mode == CHECK_MODE_LOWMEM) {
+ error("low memory mode doesn't support repair yet");
exit(1);
}
cache_tree_init(&root_cache);
if((ret = check_mounted(argv[optind])) < 0) {
- fprintf(stderr, "Could not check mount status: %s\n", strerror(-ret));
+ error("could not check mount status: %s", strerror(-ret));
goto err_out;
} else if(ret) {
- fprintf(stderr, "%s is currently mounted. Aborting.\n", argv[optind]);
+ error("%s is currently mounted, aborting", argv[optind]);
ret = -EBUSY;
goto err_out;
}
ctree_flags |= OPEN_CTREE_PARTIAL;
info = open_ctree_fs_info(argv[optind], bytenr, tree_root_bytenr,
- ctree_flags);
+ chunk_root_bytenr, ctree_flags);
if (!info) {
- fprintf(stderr, "Couldn't open file system\n");
+ error("cannot open file system");
ret = -EIO;
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)) {
+ error(
+ "free space cache v2 detected, clearing not implemented");
+ ret = 1;
+ goto close_out;
+ }
+ printf("Clearing free space cache\n");
+ ret = clear_free_space_cache(info);
+ if (ret) {
+ error("failed to clear free space cache");
+ ret = 1;
+ } else {
+ printf("Free space cache cleared\n");
+ }
+ goto close_out;
+ }
/*
* repair mode will force us to commit transaction which
* will make us fail to load log tree when mounting.
*/
if (repair && btrfs_super_log_root(info->super_copy)) {
- ret = ask_user("repair mode will force to clear out log tree, Are you sure?");
+ ret = ask_user("repair mode will force to clear out log tree, are you sure?");
if (!ret) {
ret = 1;
goto close_out;
}
ret = zero_log_tree(root);
if (ret) {
- fprintf(stderr, "fail to zero log tree\n");
+ error("failed to zero log tree: %d", ret);
goto close_out;
}
}
uuidbuf);
ret = qgroup_verify_all(info);
if (ret == 0)
- print_qgroup_report(1);
+ report_qgroups(1);
goto close_out;
}
if (subvolid) {
if (!extent_buffer_uptodate(info->tree_root->node) ||
!extent_buffer_uptodate(info->dev_root->node) ||
!extent_buffer_uptodate(info->chunk_root->node)) {
- fprintf(stderr, "Critical roots corrupted, unable to fsck the FS\n");
+ error("critical roots corrupted, unable to check the filesystem");
ret = -EIO;
goto close_out;
}
trans = btrfs_start_transaction(info->extent_root, 0);
if (IS_ERR(trans)) {
- fprintf(stderr, "Error starting transaction\n");
+ error("error starting transaction");
ret = PTR_ERR(trans);
goto close_out;
}
}
if (init_csum_tree) {
- fprintf(stderr, "Reinit crc root\n");
+ printf("Reinitialize checksum tree\n");
ret = btrfs_fsck_reinit_root(trans, info->csum_root, 0);
if (ret) {
- fprintf(stderr, "crc root initialization failed\n");
+ error("checksum tree initialization failed: %d",
+ ret);
ret = -EIO;
goto close_out;
}
ret = fill_csum_tree(trans, info->csum_root,
init_extent_tree);
if (ret) {
- fprintf(stderr, "crc refilling failed\n");
+ error("checksum tree refilling failed: %d", ret);
return -EIO;
}
}
goto close_out;
}
if (!extent_buffer_uptodate(info->extent_root->node)) {
- fprintf(stderr, "Critical roots corrupted, unable to fsck the FS\n");
+ error("critical: extent_root, unable to check the filesystem");
ret = -EIO;
goto close_out;
}
if (!extent_buffer_uptodate(info->csum_root->node)) {
- fprintf(stderr, "Checksum root corrupted, rerun with --init-csum-tree option\n");
+ error("critical: csum_root, unable to check the filesystem");
ret = -EIO;
goto close_out;
}
if (!ctx.progress_enabled)
- fprintf(stderr, "checking extents\n");
- ret = check_chunks_and_extents(root);
+ printf("checking extents");
+ if (check_mode == CHECK_MODE_LOWMEM)
+ ret = check_chunks_and_extents_v2(root);
+ else
+ ret = check_chunks_and_extents(root);
if (ret)
- fprintf(stderr, "Errors found in extent allocation tree or chunk allocation\n");
+ printf("Errors found in extent allocation tree or chunk allocation");
ret = repair_root_items(info);
if (ret < 0)
err = qgroup_verify_all(info);
if (err)
goto out;
+ report_qgroups(0);
+ err = repair_qgroups(info, &qgroups_repaired);
+ if (err)
+ goto out;
}
if (!list_empty(&root->fs_info->recow_ebs)) {
- fprintf(stderr, "Transid errors in file system\n");
+ error("transid errors in file system");
ret = 1;
}
out:
- print_qgroup_report(0);
+ /* 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
(unsigned long long)data_bytes_allocated,
(unsigned long long)data_bytes_referenced);
+ free_qgroup_counts();
free_root_recs_tree(&root_cache);
close_out:
close_ctree(root);
projects / platform / upstream / btrfs-progs.git / blobdiff