#include "qgroup-verify.h"
#include "rbtree-utils.h"
#include "backref.h"
-#include "ulist.h"
+#include "kernel-shared/ulist.h"
#include "hash.h"
+#include "help.h"
enum task_position {
TASK_EXTENTS,
static u64 btree_space_waste = 0;
static u64 data_bytes_allocated = 0;
static u64 data_bytes_referenced = 0;
-static int found_old_backref = 0;
static LIST_HEAD(duplicate_extents);
static LIST_HEAD(delete_items);
static int no_holes = 0;
static enum btrfs_check_mode check_mode = CHECK_MODE_DEFAULT;
struct extent_backref {
- struct list_head list;
+ struct rb_node node;
unsigned int is_data:1;
unsigned int found_extent_tree:1;
unsigned int full_backref:1;
unsigned int broken:1;
};
-static inline struct extent_backref* to_extent_backref(struct list_head *entry)
+static inline struct extent_backref* rb_node_to_extent_backref(struct rb_node *node)
{
- return list_entry(entry, struct extent_backref, list);
+ return rb_entry(node, struct extent_backref, node);
}
struct data_backref {
u32 found_ref;
};
+#define ROOT_DIR_ERROR (1<<1) /* bad ROOT_DIR */
+#define DIR_ITEM_MISSING (1<<2) /* DIR_ITEM not found */
+#define DIR_ITEM_MISMATCH (1<<3) /* DIR_ITEM found but not match */
+#define INODE_REF_MISSING (1<<4) /* INODE_REF/INODE_EXTREF not found */
+#define INODE_ITEM_MISSING (1<<5) /* INODE_ITEM not found */
+#define INODE_ITEM_MISMATCH (1<<6) /* INODE_ITEM found but not match */
+#define FILE_EXTENT_ERROR (1<<7) /* bad FILE_EXTENT */
+#define ODD_CSUM_ITEM (1<<8) /* CSUM_ITEM error */
+#define CSUM_ITEM_MISSING (1<<9) /* CSUM_ITEM not found */
+#define LINK_COUNT_ERROR (1<<10) /* INODE_ITEM nlink count error */
+#define NBYTES_ERROR (1<<11) /* INODE_ITEM nbytes count error */
+#define ISIZE_ERROR (1<<12) /* INODE_ITEM size count error */
+#define ORPHAN_ITEM (1<<13) /* INODE_ITEM no reference */
+#define NO_INODE_ITEM (1<<14) /* no inode_item */
+#define LAST_ITEM (1<<15) /* Complete this tree traversal */
+#define ROOT_REF_MISSING (1<<16) /* ROOT_REF not found */
+#define ROOT_REF_MISMATCH (1<<17) /* ROOT_REF found but not match */
+#define DIR_INDEX_MISSING (1<<18) /* INODE_INDEX not found */
+#define DIR_INDEX_MISMATCH (1<<19) /* INODE_INDEX found but not match */
+#define DIR_COUNT_AGAIN (1<<20) /* DIR isize should be recalculated */
+#define BG_ACCOUNTING_ERROR (1<<21) /* Block group accounting error */
+
static inline struct data_backref* to_data_backref(struct extent_backref *back)
{
return container_of(back, struct data_backref, node);
}
+static int compare_data_backref(struct rb_node *node1, struct rb_node *node2)
+{
+ struct extent_backref *ext1 = rb_node_to_extent_backref(node1);
+ struct extent_backref *ext2 = rb_node_to_extent_backref(node2);
+ struct data_backref *back1 = to_data_backref(ext1);
+ struct data_backref *back2 = to_data_backref(ext2);
+
+ WARN_ON(!ext1->is_data);
+ WARN_ON(!ext2->is_data);
+
+ /* parent and root are a union, so this covers both */
+ if (back1->parent > back2->parent)
+ return 1;
+ if (back1->parent < back2->parent)
+ return -1;
+
+ /* This is a full backref and the parents match. */
+ if (back1->node.full_backref)
+ return 0;
+
+ if (back1->owner > back2->owner)
+ return 1;
+ if (back1->owner < back2->owner)
+ return -1;
+
+ if (back1->offset > back2->offset)
+ return 1;
+ if (back1->offset < back2->offset)
+ return -1;
+
+ if (back1->found_ref && back2->found_ref) {
+ if (back1->disk_bytenr > back2->disk_bytenr)
+ return 1;
+ if (back1->disk_bytenr < back2->disk_bytenr)
+ return -1;
+
+ if (back1->bytes > back2->bytes)
+ return 1;
+ if (back1->bytes < back2->bytes)
+ return -1;
+ }
+
+ return 0;
+}
+
/*
* Much like data_backref, just removed the undetermined members
* and change it to use list_head.
return container_of(back, struct tree_backref, node);
}
+static int compare_tree_backref(struct rb_node *node1, struct rb_node *node2)
+{
+ struct extent_backref *ext1 = rb_node_to_extent_backref(node1);
+ struct extent_backref *ext2 = rb_node_to_extent_backref(node2);
+ struct tree_backref *back1 = to_tree_backref(ext1);
+ struct tree_backref *back2 = to_tree_backref(ext2);
+
+ WARN_ON(ext1->is_data);
+ WARN_ON(ext2->is_data);
+
+ /* parent and root are a union, so this covers both */
+ if (back1->parent > back2->parent)
+ return 1;
+ if (back1->parent < back2->parent)
+ return -1;
+
+ return 0;
+}
+
+static int compare_extent_backref(struct rb_node *node1, struct rb_node *node2)
+{
+ struct extent_backref *ext1 = rb_node_to_extent_backref(node1);
+ struct extent_backref *ext2 = rb_node_to_extent_backref(node2);
+
+ if (ext1->is_data > ext2->is_data)
+ return 1;
+
+ if (ext1->is_data < ext2->is_data)
+ return -1;
+
+ if (ext1->full_backref > ext2->full_backref)
+ return 1;
+ if (ext1->full_backref < ext2->full_backref)
+ return -1;
+
+ if (ext1->is_data)
+ return compare_data_backref(node1, node2);
+ else
+ return compare_tree_backref(node1, node2);
+}
+
/* Explicit initialization for extent_record::flag_block_full_backref */
enum { FLAG_UNSET = 2 };
struct extent_record {
struct list_head backrefs;
struct list_head dups;
+ struct rb_root backref_tree;
struct list_head list;
struct cache_extent cache;
struct btrfs_disk_key parent_key;
u64 last_snapshot;
u8 level;
u8 drop_level;
- int level_size;
struct btrfs_key drop_key;
};
}
if (!found)
fprintf(stderr, "\tstart: 0, len: %llu\n",
- round_up(rec->isize, root->sectorsize));
+ round_up(rec->isize,
+ root->fs_info->sectorsize));
}
}
return has_parent ? 0 : 2;
}
-static int process_dir_item(struct btrfs_root *root,
- struct extent_buffer *eb,
+static int process_dir_item(struct extent_buffer *eb,
int slot, struct btrfs_key *key,
struct shared_node *active_node)
{
filetype = btrfs_dir_type(eb, di);
rec->found_size += name_len;
- if (name_len <= BTRFS_NAME_LEN) {
+ if (cur + sizeof(*di) + name_len > total ||
+ name_len > BTRFS_NAME_LEN) {
+ error = REF_ERR_NAME_TOO_LONG;
+
+ if (cur + sizeof(*di) > total)
+ break;
+ len = min_t(u32, total - cur - sizeof(*di),
+ BTRFS_NAME_LEN);
+ } else {
len = name_len;
error = 0;
- } else {
- len = BTRFS_NAME_LEN;
- error = REF_ERR_NAME_TOO_LONG;
}
+
read_extent_buffer(eb, namebuf, (unsigned long)(di + 1), len);
+ if (key->type == BTRFS_DIR_ITEM_KEY &&
+ key->offset != btrfs_name_hash(namebuf, len)) {
+ rec->errors |= I_ERR_ODD_DIR_ITEM;
+ error("DIR_ITEM[%llu %llu] name %s namelen %u filetype %u mismatch with its hash, wanted %llu have %llu",
+ key->objectid, key->offset, namebuf, len, filetype,
+ key->offset, btrfs_name_hash(namebuf, len));
+ }
+
if (location.type == BTRFS_INODE_ITEM_KEY) {
add_inode_backref(inode_cache, location.objectid,
key->objectid, key->offset, namebuf,
while (cur < total) {
name_len = btrfs_inode_ref_name_len(eb, ref);
index = btrfs_inode_ref_index(eb, ref);
- if (name_len <= BTRFS_NAME_LEN) {
+
+ /* inode_ref + namelen should not cross item boundary */
+ if (cur + sizeof(*ref) + name_len > total ||
+ name_len > BTRFS_NAME_LEN) {
+ if (total < cur + sizeof(*ref))
+ break;
+
+ /* Still try to read out the remaining part */
+ len = min_t(u32, total - cur - sizeof(*ref),
+ BTRFS_NAME_LEN);
+ error = REF_ERR_NAME_TOO_LONG;
+ } else {
len = name_len;
error = 0;
- } else {
- len = BTRFS_NAME_LEN;
- error = REF_ERR_NAME_TOO_LONG;
}
+
read_extent_buffer(eb, namebuf, (unsigned long)(ref + 1), len);
add_inode_backref(inode_cache, key->objectid, key->offset,
index, namebuf, len, 0, key->type, error);
start = key.offset;
size = btrfs_item_size_nr(leaf, path.slots[0]);
- csum_end = key.offset + (size / csum_size) * root->sectorsize;
+ csum_end = key.offset + (size / csum_size) *
+ root->fs_info->sectorsize;
if (csum_end > start) {
size = min(csum_end - start, len);
len -= size;
u64 num_bytes = 0;
u64 disk_bytenr = 0;
u64 extent_offset = 0;
- u64 mask = root->sectorsize - 1;
+ u64 mask = root->fs_info->sectorsize - 1;
int extent_type;
int ret;
switch (key.type) {
case BTRFS_DIR_ITEM_KEY:
case BTRFS_DIR_INDEX_KEY:
- ret = process_dir_item(root, eb, i, &key, active_node);
+ ret = process_dir_item(eb, i, &key, active_node);
break;
case BTRFS_INODE_REF_KEY:
ret = process_inode_ref(eb, i, &key, active_node);
return ret;
}
+struct node_refs {
+ u64 bytenr[BTRFS_MAX_LEVEL];
+ u64 refs[BTRFS_MAX_LEVEL];
+ int need_check[BTRFS_MAX_LEVEL];
+ /* field for checking all trees */
+ int checked[BTRFS_MAX_LEVEL];
+ /* the corresponding extent should be marked as full backref or not */
+ int full_backref[BTRFS_MAX_LEVEL];
+};
+
+static int update_nodes_refs(struct btrfs_root *root, u64 bytenr,
+ struct extent_buffer *eb, struct node_refs *nrefs,
+ u64 level, int check_all);
+static int check_inode_item(struct btrfs_root *root, struct btrfs_path *path,
+ unsigned int ext_ref);
+
+/*
+ * Returns >0 Found error, not fatal, should continue
+ * Returns <0 Fatal error, must exit the whole check
+ * Returns 0 No errors found
+ */
+static int process_one_leaf_v2(struct btrfs_root *root, struct btrfs_path *path,
+ struct node_refs *nrefs, int *level, int ext_ref)
+{
+ struct extent_buffer *cur = path->nodes[0];
+ struct btrfs_key key;
+ u64 cur_bytenr;
+ u32 nritems;
+ u64 first_ino = 0;
+ int root_level = btrfs_header_level(root->node);
+ int i;
+ int ret = 0; /* Final return value */
+ int err = 0; /* Positive error bitmap */
+
+ cur_bytenr = cur->start;
+
+ /* skip to first inode item or the first inode number change */
+ nritems = btrfs_header_nritems(cur);
+ for (i = 0; i < nritems; i++) {
+ btrfs_item_key_to_cpu(cur, &key, i);
+ if (i == 0)
+ first_ino = key.objectid;
+ if (key.type == BTRFS_INODE_ITEM_KEY ||
+ (first_ino && first_ino != key.objectid))
+ break;
+ }
+ if (i == nritems) {
+ path->slots[0] = nritems;
+ return 0;
+ }
+ path->slots[0] = i;
+
+again:
+ err |= check_inode_item(root, path, ext_ref);
+
+ /* modify cur since check_inode_item may change path */
+ cur = path->nodes[0];
+
+ if (err & LAST_ITEM)
+ goto out;
+
+ /* still have inode items in thie leaf */
+ if (cur->start == cur_bytenr)
+ goto again;
+
+ /*
+ * we have switched to another leaf, above nodes may
+ * have changed, here walk down the path, if a node
+ * or leaf is shared, check whether we can skip this
+ * node or leaf.
+ */
+ for (i = root_level; i >= 0; i--) {
+ if (path->nodes[i]->start == nrefs->bytenr[i])
+ continue;
+
+ ret = update_nodes_refs(root, path->nodes[i]->start,
+ path->nodes[i], nrefs, i, 0);
+ if (ret)
+ goto out;
+
+ if (!nrefs->need_check[i]) {
+ *level += 1;
+ break;
+ }
+ }
+
+ for (i = 0; i < *level; i++) {
+ free_extent_buffer(path->nodes[i]);
+ path->nodes[i] = NULL;
+ }
+out:
+ err &= ~LAST_ITEM;
+ if (err && !ret)
+ ret = err;
+ return ret;
+}
+
static void reada_walk_down(struct btrfs_root *root,
struct extent_buffer *node, int slot)
{
+ struct btrfs_fs_info *fs_info = root->fs_info;
u64 bytenr;
u64 ptr_gen;
u32 nritems;
- u32 blocksize;
int i;
int level;
return;
nritems = btrfs_header_nritems(node);
- blocksize = root->nodesize;
for (i = slot; i < nritems; i++) {
bytenr = btrfs_node_blockptr(node, i);
ptr_gen = btrfs_node_ptr_generation(node, i);
- readahead_tree_block(root, bytenr, blocksize, ptr_gen);
+ readahead_tree_block(fs_info, bytenr, ptr_gen);
}
}
* which makes leaf owner check not so strong, key check should be
* sufficient enough for that case.
*/
-static int check_child_node(struct btrfs_root *root,
- struct extent_buffer *parent, int slot,
+static int check_child_node(struct extent_buffer *parent, int slot,
struct extent_buffer *child)
{
struct btrfs_key parent_key;
return ret;
}
-struct node_refs {
- u64 bytenr[BTRFS_MAX_LEVEL];
- u64 refs[BTRFS_MAX_LEVEL];
-};
+/*
+ * for a tree node or leaf, if it's shared, indeed we don't need to iterate it
+ * in every fs or file tree check. Here we find its all root ids, and only check
+ * it in the fs or file tree which has the smallest root id.
+ */
+static int need_check(struct btrfs_root *root, struct ulist *roots)
+{
+ struct rb_node *node;
+ struct ulist_node *u;
-static int walk_down_tree(struct btrfs_root *root, struct btrfs_path *path,
- struct walk_control *wc, int *level,
- struct node_refs *nrefs)
+ if (roots->nnodes == 1)
+ return 1;
+
+ node = rb_first(&roots->root);
+ u = rb_entry(node, struct ulist_node, rb_node);
+ /*
+ * current root id is not smallest, we skip it and let it be checked
+ * in the fs or file tree who hash the smallest root id.
+ */
+ if (root->objectid != u->val)
+ return 0;
+
+ return 1;
+}
+
+static int calc_extent_flag_v2(struct btrfs_root *root, struct extent_buffer *eb,
+ u64 *flags_ret)
{
- enum btrfs_tree_block_status status;
- u64 bytenr;
- u64 ptr_gen;
- struct extent_buffer *next;
- struct extent_buffer *cur;
- u32 blocksize;
- int ret, err = 0;
- u64 refs;
+ struct btrfs_root *extent_root = root->fs_info->extent_root;
+ struct btrfs_root_item *ri = &root->root_item;
+ struct btrfs_extent_inline_ref *iref;
+ struct btrfs_extent_item *ei;
+ struct btrfs_key key;
+ struct btrfs_path *path = NULL;
+ unsigned long ptr;
+ unsigned long end;
+ u64 flags;
+ u64 owner = 0;
+ u64 offset;
+ int slot;
+ int type;
+ int ret = 0;
- WARN_ON(*level < 0);
- WARN_ON(*level >= BTRFS_MAX_LEVEL);
+ /*
+ * Except file/reloc tree, we can not have FULL BACKREF MODE
+ */
+ if (root->objectid < BTRFS_FIRST_FREE_OBJECTID)
+ goto normal;
- 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;
- }
- nrefs->bytenr[*level] = path->nodes[*level]->start;
- nrefs->refs[*level] = refs;
+ /* root node */
+ if (eb->start == btrfs_root_bytenr(ri))
+ goto normal;
+
+ if (btrfs_header_flag(eb, BTRFS_HEADER_FLAG_RELOC))
+ goto full_backref;
+
+ owner = btrfs_header_owner(eb);
+ if (owner == root->objectid)
+ goto normal;
+
+ path = btrfs_alloc_path();
+ if (!path)
+ return -ENOMEM;
+
+ key.objectid = btrfs_header_bytenr(eb);
+ key.type = (u8)-1;
+ key.offset = (u64)-1;
+
+ ret = btrfs_search_slot(NULL, extent_root, &key, path, 0, 0);
+ if (ret <= 0) {
+ ret = -EIO;
+ goto out;
}
- if (refs > 1) {
- ret = enter_shared_node(root, path->nodes[*level]->start,
- refs, wc, *level);
- if (ret > 0) {
- err = ret;
- goto out;
- }
+ if (ret > 0) {
+ ret = btrfs_previous_extent_item(extent_root, path,
+ key.objectid);
+ if (ret)
+ goto full_backref;
+
}
+ btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
- while (*level >= 0) {
- WARN_ON(*level < 0);
- WARN_ON(*level >= BTRFS_MAX_LEVEL);
- cur = path->nodes[*level];
+ eb = path->nodes[0];
+ slot = path->slots[0];
+ ei = btrfs_item_ptr(eb, slot, struct btrfs_extent_item);
- if (btrfs_header_level(cur) != *level)
- WARN_ON(1);
+ flags = btrfs_extent_flags(eb, ei);
+ if (flags & BTRFS_BLOCK_FLAG_FULL_BACKREF)
+ goto full_backref;
- if (path->slots[*level] >= btrfs_header_nritems(cur))
- break;
- if (*level == 0) {
- ret = process_one_leaf(root, cur, wc);
- if (ret < 0)
- err = ret;
- break;
- }
- bytenr = btrfs_node_blockptr(cur, path->slots[*level]);
- ptr_gen = btrfs_node_ptr_generation(cur, path->slots[*level]);
- blocksize = root->nodesize;
+ ptr = (unsigned long)(ei + 1);
+ end = (unsigned long)ei + btrfs_item_size_nr(eb, slot);
- 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 (key.type == BTRFS_EXTENT_ITEM_KEY)
+ ptr += sizeof(struct btrfs_tree_block_info);
- if (refs > 1) {
- ret = enter_shared_node(root, bytenr, refs,
- wc, *level - 1);
+next:
+ /* Reached extent item ends normally */
+ if (ptr == end)
+ goto full_backref;
+
+ /* Beyond extent item end, wrong item size */
+ if (ptr > end) {
+ error("extent item at bytenr %llu slot %d has wrong size",
+ eb->start, slot);
+ goto full_backref;
+ }
+
+ iref = (struct btrfs_extent_inline_ref *)ptr;
+ offset = btrfs_extent_inline_ref_offset(eb, iref);
+ type = btrfs_extent_inline_ref_type(eb, iref);
+
+ if (type == BTRFS_TREE_BLOCK_REF_KEY && offset == owner)
+ goto normal;
+ ptr += btrfs_extent_inline_ref_size(type);
+ goto next;
+
+normal:
+ *flags_ret &= ~BTRFS_BLOCK_FLAG_FULL_BACKREF;
+ goto out;
+
+full_backref:
+ *flags_ret |= BTRFS_BLOCK_FLAG_FULL_BACKREF;
+out:
+ btrfs_free_path(path);
+ return ret;
+}
+
+/*
+ * for a tree node or leaf, we record its reference count, so later if we still
+ * process this node or leaf, don't need to compute its reference count again.
+ *
+ * @bytenr if @bytenr == (u64)-1, only update nrefs->full_backref[level]
+ */
+static int update_nodes_refs(struct btrfs_root *root, u64 bytenr,
+ struct extent_buffer *eb, struct node_refs *nrefs,
+ u64 level, int check_all)
+{
+ struct ulist *roots;
+ u64 refs = 0;
+ u64 flags = 0;
+ int root_level = btrfs_header_level(root->node);
+ int check;
+ int ret;
+
+ if (nrefs->bytenr[level] == bytenr)
+ return 0;
+
+ if (bytenr != (u64)-1) {
+ /* the return value of this function seems a mistake */
+ ret = btrfs_lookup_extent_info(NULL, root, bytenr,
+ level, 1, &refs, &flags);
+ /* temporary fix */
+ if (ret < 0 && !check_all)
+ return ret;
+
+ nrefs->bytenr[level] = bytenr;
+ nrefs->refs[level] = refs;
+ nrefs->full_backref[level] = 0;
+ nrefs->checked[level] = 0;
+
+ if (refs > 1) {
+ ret = btrfs_find_all_roots(NULL, root->fs_info, bytenr,
+ 0, &roots);
+ if (ret)
+ return -EIO;
+
+ check = need_check(root, roots);
+ ulist_free(roots);
+ nrefs->need_check[level] = check;
+ } else {
+ if (!check_all) {
+ nrefs->need_check[level] = 1;
+ } else {
+ if (level == root_level) {
+ nrefs->need_check[level] = 1;
+ } else {
+ /*
+ * The node refs may have not been
+ * updated if upper needs checking (the
+ * lowest root_objectid) the node can
+ * be checked.
+ */
+ nrefs->need_check[level] =
+ nrefs->need_check[level + 1];
+ }
+ }
+ }
+ }
+
+ if (check_all && eb) {
+ calc_extent_flag_v2(root, eb, &flags);
+ if (flags & BTRFS_BLOCK_FLAG_FULL_BACKREF)
+ nrefs->full_backref[level] = 1;
+ }
+
+ return 0;
+}
+
+/*
+ * @level if @level == -1 means extent data item
+ * else normal treeblocl.
+ */
+static int should_check_extent_strictly(struct btrfs_root *root,
+ struct node_refs *nrefs, int level)
+{
+ int root_level = btrfs_header_level(root->node);
+
+ if (level > root_level || level < -1)
+ return 1;
+ if (level == root_level)
+ return 1;
+ /*
+ * if the upper node is marked full backref, it should contain shared
+ * backref of the parent (except owner == root->objectid).
+ */
+ while (++level <= root_level)
+ if (nrefs->refs[level] > 1)
+ return 0;
+
+ return 1;
+}
+
+static int walk_down_tree(struct btrfs_root *root, struct btrfs_path *path,
+ struct walk_control *wc, int *level,
+ struct node_refs *nrefs)
+{
+ enum btrfs_tree_block_status status;
+ u64 bytenr;
+ u64 ptr_gen;
+ struct btrfs_fs_info *fs_info = root->fs_info;
+ struct extent_buffer *next;
+ struct extent_buffer *cur;
+ int ret, err = 0;
+ u64 refs;
+
+ WARN_ON(*level < 0);
+ WARN_ON(*level >= BTRFS_MAX_LEVEL);
+
+ 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;
+ }
+ nrefs->bytenr[*level] = path->nodes[*level]->start;
+ nrefs->refs[*level] = refs;
+ }
+
+ if (refs > 1) {
+ ret = enter_shared_node(root, path->nodes[*level]->start,
+ refs, wc, *level);
+ if (ret > 0) {
+ err = ret;
+ goto out;
+ }
+ }
+
+ while (*level >= 0) {
+ WARN_ON(*level < 0);
+ WARN_ON(*level >= BTRFS_MAX_LEVEL);
+ cur = path->nodes[*level];
+
+ if (btrfs_header_level(cur) != *level)
+ WARN_ON(1);
+
+ if (path->slots[*level] >= btrfs_header_nritems(cur))
+ break;
+ if (*level == 0) {
+ ret = process_one_leaf(root, cur, wc);
+ if (ret < 0)
+ err = ret;
+ break;
+ }
+ bytenr = btrfs_node_blockptr(cur, path->slots[*level]);
+ ptr_gen = btrfs_node_ptr_generation(cur, path->slots[*level]);
+
+ 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,
+ wc, *level - 1);
if (ret > 0) {
path->slots[*level]++;
continue;
}
}
- next = btrfs_find_tree_block(root, bytenr, blocksize);
+ next = btrfs_find_tree_block(fs_info, bytenr, fs_info->nodesize);
+ if (!next || !btrfs_buffer_uptodate(next, ptr_gen)) {
+ free_extent_buffer(next);
+ reada_walk_down(root, cur, path->slots[*level]);
+ next = read_tree_block(root->fs_info, bytenr, ptr_gen);
+ if (!extent_buffer_uptodate(next)) {
+ struct btrfs_key node_key;
+
+ btrfs_node_key_to_cpu(path->nodes[*level],
+ &node_key,
+ path->slots[*level]);
+ btrfs_add_corrupt_extent_record(root->fs_info,
+ &node_key,
+ path->nodes[*level]->start,
+ root->fs_info->nodesize,
+ *level);
+ err = -EIO;
+ goto out;
+ }
+ }
+
+ ret = check_child_node(cur, path->slots[*level], next);
+ if (ret) {
+ free_extent_buffer(next);
+ err = ret;
+ goto out;
+ }
+
+ if (btrfs_is_leaf(next))
+ status = btrfs_check_leaf(root, NULL, next);
+ else
+ status = btrfs_check_node(root, NULL, next);
+ if (status != BTRFS_TREE_BLOCK_CLEAN) {
+ free_extent_buffer(next);
+ err = -EIO;
+ goto out;
+ }
+
+ *level = *level - 1;
+ free_extent_buffer(path->nodes[*level]);
+ path->nodes[*level] = next;
+ path->slots[*level] = 0;
+ }
+out:
+ path->slots[*level] = btrfs_header_nritems(path->nodes[*level]);
+ return err;
+}
+
+static int fs_root_objectid(u64 objectid);
+
+/*
+ * Update global fs information.
+ */
+static void account_bytes(struct btrfs_root *root, struct btrfs_path *path,
+ int level)
+{
+ u32 free_nrs;
+ struct extent_buffer *eb = path->nodes[level];
+
+ total_btree_bytes += eb->len;
+ if (fs_root_objectid(root->objectid))
+ total_fs_tree_bytes += eb->len;
+ if (btrfs_header_owner(eb) == BTRFS_EXTENT_TREE_OBJECTID)
+ total_extent_tree_bytes += eb->len;
+
+ if (level == 0) {
+ btree_space_waste += btrfs_leaf_free_space(root, eb);
+ } else {
+ free_nrs = (BTRFS_NODEPTRS_PER_BLOCK(root) -
+ btrfs_header_nritems(eb));
+ btree_space_waste += free_nrs * sizeof(struct btrfs_key_ptr);
+ }
+}
+
+/*
+ * This function only handles BACKREF_MISSING,
+ * If corresponding extent item exists, increase the ref, else insert an extent
+ * item and backref.
+ *
+ * Returns error bits after repair.
+ */
+static int repair_tree_block_ref(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root,
+ struct extent_buffer *node,
+ struct node_refs *nrefs, int level, int err)
+{
+ struct btrfs_fs_info *fs_info = root->fs_info;
+ struct btrfs_root *extent_root = fs_info->extent_root;
+ struct btrfs_path path;
+ struct btrfs_extent_item *ei;
+ struct btrfs_tree_block_info *bi;
+ struct btrfs_key key;
+ struct extent_buffer *eb;
+ u32 size = sizeof(*ei);
+ u32 node_size = root->fs_info->nodesize;
+ int insert_extent = 0;
+ int skinny_metadata = btrfs_fs_incompat(fs_info, SKINNY_METADATA);
+ int root_level = btrfs_header_level(root->node);
+ int generation;
+ int ret;
+ u64 owner;
+ u64 bytenr;
+ u64 flags = BTRFS_EXTENT_FLAG_TREE_BLOCK;
+ u64 parent = 0;
+
+ if ((err & BACKREF_MISSING) == 0)
+ return err;
+
+ WARN_ON(level > BTRFS_MAX_LEVEL);
+ WARN_ON(level < 0);
+
+ btrfs_init_path(&path);
+ bytenr = btrfs_header_bytenr(node);
+ owner = btrfs_header_owner(node);
+ generation = btrfs_header_generation(node);
+
+ key.objectid = bytenr;
+ key.type = (u8)-1;
+ key.offset = (u64)-1;
+
+ /* Search for the extent item */
+ ret = btrfs_search_slot(NULL, extent_root, &key, &path, 0, 0);
+ if (ret <= 0) {
+ ret = -EIO;
+ goto out;
+ }
+
+ ret = btrfs_previous_extent_item(extent_root, &path, bytenr);
+ if (ret)
+ insert_extent = 1;
+
+ /* calculate if the extent item flag is full backref or not */
+ if (nrefs->full_backref[level] != 0)
+ flags |= BTRFS_BLOCK_FLAG_FULL_BACKREF;
+
+ /* insert an extent item */
+ if (insert_extent) {
+ struct btrfs_disk_key copy_key;
+
+ generation = btrfs_header_generation(node);
+
+ if (level < root_level && nrefs->full_backref[level + 1] &&
+ owner != root->objectid) {
+ flags |= BTRFS_BLOCK_FLAG_FULL_BACKREF;
+ }
+
+ key.objectid = bytenr;
+ if (!skinny_metadata) {
+ key.type = BTRFS_EXTENT_ITEM_KEY;
+ key.offset = node_size;
+ size += sizeof(*bi);
+ } else {
+ key.type = BTRFS_METADATA_ITEM_KEY;
+ key.offset = level;
+ }
+
+ btrfs_release_path(&path);
+ ret = btrfs_insert_empty_item(trans, extent_root, &path, &key,
+ size);
+ if (ret)
+ goto out;
+
+ eb = path.nodes[0];
+ ei = btrfs_item_ptr(eb, path.slots[0], struct btrfs_extent_item);
+
+ btrfs_set_extent_refs(eb, ei, 0);
+ btrfs_set_extent_generation(eb, ei, generation);
+ btrfs_set_extent_flags(eb, ei, flags);
+
+ if (!skinny_metadata) {
+ bi = (struct btrfs_tree_block_info *)(ei + 1);
+ memset_extent_buffer(eb, 0, (unsigned long)bi,
+ sizeof(*bi));
+ btrfs_set_disk_key_objectid(©_key, root->objectid);
+ btrfs_set_disk_key_type(©_key, 0);
+ btrfs_set_disk_key_offset(©_key, 0);
+
+ btrfs_set_tree_block_level(eb, bi, level);
+ btrfs_set_tree_block_key(eb, bi, ©_key);
+ }
+ btrfs_mark_buffer_dirty(eb);
+ printf("Added an extent item [%llu %u]\n", bytenr, node_size);
+ btrfs_update_block_group(trans, extent_root, bytenr, node_size,
+ 1, 0);
+
+ nrefs->refs[level] = 0;
+ nrefs->full_backref[level] =
+ flags & BTRFS_BLOCK_FLAG_FULL_BACKREF;
+ btrfs_release_path(&path);
+ }
+
+ if (level < root_level && nrefs->full_backref[level + 1] &&
+ owner != root->objectid)
+ parent = nrefs->bytenr[level + 1];
+
+ /* increase the ref */
+ ret = btrfs_inc_extent_ref(trans, extent_root, bytenr, node_size,
+ parent, root->objectid, level, 0);
+
+ nrefs->refs[level]++;
+out:
+ btrfs_release_path(&path);
+ if (ret) {
+ error(
+ "failed to repair tree block ref start %llu root %llu due to %s",
+ bytenr, root->objectid, strerror(-ret));
+ } else {
+ printf("Added one tree block ref start %llu %s %llu\n",
+ bytenr, parent ? "parent" : "root",
+ parent ? parent : root->objectid);
+ err &= ~BACKREF_MISSING;
+ }
+
+ return err;
+}
+
+static int check_inode_item(struct btrfs_root *root, struct btrfs_path *path,
+ unsigned int ext_ref);
+static int check_tree_block_ref(struct btrfs_root *root,
+ struct extent_buffer *eb, u64 bytenr,
+ int level, u64 owner, struct node_refs *nrefs);
+static int check_leaf_items(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root, struct btrfs_path *path,
+ struct node_refs *nrefs, int account_bytes);
+
+/*
+ * @trans just for lowmem repair mode
+ * @check all if not 0 then check all tree block backrefs and items
+ * 0 then just check relationship of items in fs tree(s)
+ *
+ * Returns >0 Found error, should continue
+ * Returns <0 Fatal error, must exit the whole check
+ * Returns 0 No errors found
+ */
+static int walk_down_tree_v2(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root, struct btrfs_path *path,
+ int *level, struct node_refs *nrefs, int ext_ref,
+ int check_all)
+
+{
+ enum btrfs_tree_block_status status;
+ u64 bytenr;
+ u64 ptr_gen;
+ struct btrfs_fs_info *fs_info = root->fs_info;
+ struct extent_buffer *next;
+ struct extent_buffer *cur;
+ int ret;
+ int err = 0;
+ int check;
+ int account_file_data = 0;
+
+ WARN_ON(*level < 0);
+ WARN_ON(*level >= BTRFS_MAX_LEVEL);
+
+ ret = update_nodes_refs(root, btrfs_header_bytenr(path->nodes[*level]),
+ path->nodes[*level], nrefs, *level, check_all);
+ if (ret < 0)
+ return ret;
+
+ while (*level >= 0) {
+ WARN_ON(*level < 0);
+ WARN_ON(*level >= BTRFS_MAX_LEVEL);
+ cur = path->nodes[*level];
+ bytenr = btrfs_header_bytenr(cur);
+ check = nrefs->need_check[*level];
+
+ if (btrfs_header_level(cur) != *level)
+ WARN_ON(1);
+ /*
+ * Update bytes accounting and check tree block ref
+ * NOTE: Doing accounting and check before checking nritems
+ * is necessary because of empty node/leaf.
+ */
+ if ((check_all && !nrefs->checked[*level]) ||
+ (!check_all && nrefs->need_check[*level])) {
+ ret = check_tree_block_ref(root, cur,
+ btrfs_header_bytenr(cur), btrfs_header_level(cur),
+ btrfs_header_owner(cur), nrefs);
+
+ if (repair && ret)
+ ret = repair_tree_block_ref(trans, root,
+ path->nodes[*level], nrefs, *level, ret);
+ err |= ret;
+
+ if (check_all && nrefs->need_check[*level] &&
+ nrefs->refs[*level]) {
+ account_bytes(root, path, *level);
+ account_file_data = 1;
+ }
+ nrefs->checked[*level] = 1;
+ }
+
+ if (path->slots[*level] >= btrfs_header_nritems(cur))
+ break;
+
+ /* Don't forgot to check leaf/node validation */
+ if (*level == 0) {
+ /* skip duplicate check */
+ if (check || !check_all) {
+ ret = btrfs_check_leaf(root, NULL, cur);
+ if (ret != BTRFS_TREE_BLOCK_CLEAN) {
+ err |= -EIO;
+ break;
+ }
+ }
+
+ ret = 0;
+ if (!check_all)
+ ret = process_one_leaf_v2(root, path, nrefs,
+ level, ext_ref);
+ else
+ ret = check_leaf_items(trans, root, path,
+ nrefs, account_file_data);
+ err |= ret;
+ break;
+ } else {
+ if (check || !check_all) {
+ ret = btrfs_check_node(root, NULL, cur);
+ if (ret != BTRFS_TREE_BLOCK_CLEAN) {
+ err |= -EIO;
+ break;
+ }
+ }
+ }
+
+ bytenr = btrfs_node_blockptr(cur, path->slots[*level]);
+ ptr_gen = btrfs_node_ptr_generation(cur, path->slots[*level]);
+
+ ret = update_nodes_refs(root, bytenr, NULL, nrefs, *level - 1,
+ check_all);
+ if (ret < 0)
+ break;
+ /*
+ * check all trees in check_chunks_and_extent_v2
+ * check shared node once in check_fs_roots
+ */
+ if (!check_all && !nrefs->need_check[*level - 1]) {
+ path->slots[*level]++;
+ continue;
+ }
+
+ next = btrfs_find_tree_block(fs_info, bytenr, fs_info->nodesize);
if (!next || !btrfs_buffer_uptodate(next, ptr_gen)) {
free_extent_buffer(next);
reada_walk_down(root, cur, path->slots[*level]);
- next = read_tree_block(root, bytenr, blocksize,
- ptr_gen);
+ next = read_tree_block(fs_info, bytenr, ptr_gen);
if (!extent_buffer_uptodate(next)) {
struct btrfs_key node_key;
btrfs_node_key_to_cpu(path->nodes[*level],
&node_key,
path->slots[*level]);
- btrfs_add_corrupt_extent_record(root->fs_info,
- &node_key,
- path->nodes[*level]->start,
- root->nodesize, *level);
- err = -EIO;
- goto out;
+ btrfs_add_corrupt_extent_record(fs_info,
+ &node_key, path->nodes[*level]->start,
+ fs_info->nodesize, *level);
+ err |= -EIO;
+ break;
}
}
- ret = check_child_node(root, cur, path->slots[*level], next);
- if (ret) {
- err = ret;
- goto out;
- }
+ ret = check_child_node(cur, path->slots[*level], next);
+ err |= ret;
+ if (ret < 0)
+ break;
if (btrfs_is_leaf(next))
status = btrfs_check_leaf(root, NULL, next);
status = btrfs_check_node(root, NULL, next);
if (status != BTRFS_TREE_BLOCK_CLEAN) {
free_extent_buffer(next);
- err = -EIO;
- goto out;
+ err |= -EIO;
+ break;
}
*level = *level - 1;
free_extent_buffer(path->nodes[*level]);
path->nodes[*level] = next;
path->slots[*level] = 0;
+ account_file_data = 0;
+
+ update_nodes_refs(root, (u64)-1, next, nrefs, *level, check_all);
}
-out:
- path->slots[*level] = btrfs_header_nritems(path->nodes[*level]);
return err;
}
return 1;
}
+static int walk_up_tree_v2(struct btrfs_root *root, struct btrfs_path *path,
+ int *level)
+{
+ int i;
+ struct extent_buffer *leaf;
+
+ for (i = *level; i < BTRFS_MAX_LEVEL - 1 && path->nodes[i]; i++) {
+ leaf = path->nodes[i];
+ if (path->slots[i] + 1 < btrfs_header_nritems(leaf)) {
+ path->slots[i]++;
+ *level = i;
+ return 0;
+ } else {
+ free_extent_buffer(path->nodes[*level]);
+ path->nodes[*level] = NULL;
+ *level = i + 1;
+ }
+ }
+ return 1;
+}
+
static int check_root_dir(struct inode_record *rec)
{
struct inode_backref *backref;
}
static int delete_dir_index(struct btrfs_root *root,
- struct cache_tree *inode_cache,
- struct inode_record *rec,
struct inode_backref *backref)
{
struct btrfs_trans_handle *trans;
return ret;
}
+static int __create_inode_item(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root, u64 ino, u64 size,
+ u64 nbytes, u64 nlink, u32 mode)
+{
+ struct btrfs_inode_item ii;
+ time_t now = time(NULL);
+ int ret;
+
+ btrfs_set_stack_inode_size(&ii, size);
+ btrfs_set_stack_inode_nbytes(&ii, nbytes);
+ btrfs_set_stack_inode_nlink(&ii, nlink);
+ btrfs_set_stack_inode_mode(&ii, mode);
+ btrfs_set_stack_inode_generation(&ii, trans->transid);
+ btrfs_set_stack_timespec_nsec(&ii.atime, 0);
+ btrfs_set_stack_timespec_sec(&ii.ctime, now);
+ btrfs_set_stack_timespec_nsec(&ii.ctime, 0);
+ btrfs_set_stack_timespec_sec(&ii.mtime, now);
+ btrfs_set_stack_timespec_nsec(&ii.mtime, 0);
+ btrfs_set_stack_timespec_sec(&ii.otime, 0);
+ btrfs_set_stack_timespec_nsec(&ii.otime, 0);
+
+ ret = btrfs_insert_inode(trans, root, ino, &ii);
+ ASSERT(!ret);
+
+ warning("root %llu inode %llu recreating inode item, this may "
+ "be incomplete, please check permissions and content after "
+ "the fsck completes.\n", (unsigned long long)root->objectid,
+ (unsigned long long)ino);
+
+ return 0;
+}
+
+static int create_inode_item_lowmem(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root, u64 ino,
+ u8 filetype)
+{
+ u32 mode = (filetype == BTRFS_FT_DIR ? S_IFDIR : S_IFREG) | 0755;
+
+ return __create_inode_item(trans, root, ino, 0, 0, 0, mode);
+}
+
static int create_inode_item(struct btrfs_root *root,
- struct inode_record *rec,
- struct inode_backref *backref, int root_dir)
+ struct inode_record *rec, int root_dir)
{
struct btrfs_trans_handle *trans;
- struct btrfs_inode_item inode_item;
- time_t now = time(NULL);
+ u64 nlink = 0;
+ u32 mode = 0;
+ u64 size = 0;
int ret;
trans = btrfs_start_transaction(root, 1);
return ret;
}
- fprintf(stderr, "root %llu inode %llu recreating inode item, this may "
- "be incomplete, please check permissions and content after "
- "the fsck completes.\n", (unsigned long long)root->objectid,
- (unsigned long long)rec->ino);
-
- memset(&inode_item, 0, sizeof(inode_item));
- btrfs_set_stack_inode_generation(&inode_item, trans->transid);
- if (root_dir)
- btrfs_set_stack_inode_nlink(&inode_item, 1);
- else
- btrfs_set_stack_inode_nlink(&inode_item, rec->found_link);
- btrfs_set_stack_inode_nbytes(&inode_item, rec->found_size);
+ nlink = root_dir ? 1 : rec->found_link;
if (rec->found_dir_item) {
if (rec->found_file_extent)
fprintf(stderr, "root %llu inode %llu has both a dir "
"regular file so setting it as a directory\n",
(unsigned long long)root->objectid,
(unsigned long long)rec->ino);
- btrfs_set_stack_inode_mode(&inode_item, S_IFDIR | 0755);
- btrfs_set_stack_inode_size(&inode_item, rec->found_size);
+ mode = S_IFDIR | 0755;
+ size = rec->found_size;
} else if (!rec->found_dir_item) {
- btrfs_set_stack_inode_size(&inode_item, rec->extent_end);
- btrfs_set_stack_inode_mode(&inode_item, S_IFREG | 0755);
- }
- btrfs_set_stack_timespec_sec(&inode_item.atime, now);
- btrfs_set_stack_timespec_nsec(&inode_item.atime, 0);
- btrfs_set_stack_timespec_sec(&inode_item.ctime, now);
- btrfs_set_stack_timespec_nsec(&inode_item.ctime, 0);
- btrfs_set_stack_timespec_sec(&inode_item.mtime, now);
- btrfs_set_stack_timespec_nsec(&inode_item.mtime, 0);
- btrfs_set_stack_timespec_sec(&inode_item.otime, 0);
- btrfs_set_stack_timespec_nsec(&inode_item.otime, 0);
-
- ret = btrfs_insert_inode(trans, root, rec->ino, &inode_item);
- BUG_ON(ret);
+ size = rec->extent_end;
+ mode = S_IFREG | 0755;
+ }
+
+ ret = __create_inode_item(trans, root, rec->ino, size, rec->nbytes,
+ nlink, mode);
btrfs_commit_transaction(trans, root);
return 0;
}
list_for_each_entry_safe(backref, tmp, &rec->backrefs, list) {
if (!delete && rec->ino == root_dirid) {
if (!rec->found_inode_item) {
- ret = create_inode_item(root, rec, backref, 1);
+ ret = create_inode_item(root, rec, 1);
if (ret)
break;
repaired++;
((backref->found_dir_index && !backref->found_inode_ref) ||
(backref->found_dir_index && backref->found_inode_ref &&
(backref->errors & REF_ERR_INDEX_UNMATCH)))) {
- ret = delete_dir_index(root, inode_cache, rec, backref);
+ ret = delete_dir_index(root, backref);
if (ret)
break;
repaired++;
list_del(&backref->list);
free(backref);
+ continue;
}
if (!delete && !backref->found_dir_index &&
break;
repaired++;
if (backref->found_dir_item &&
- backref->found_dir_index &&
backref->found_dir_index) {
if (!backref->errors &&
backref->found_inode_ref) {
list_del(&backref->list);
free(backref);
+ continue;
}
}
}
backref->found_dir_item &&
!(backref->errors & REF_ERR_INDEX_UNMATCH) &&
!rec->found_inode_item)) {
- ret = create_inode_item(root, rec, backref, 0);
+ ret = create_inode_item(root, rec, 0);
if (ret)
break;
repaired++;
list_for_each_entry(backref, &rec->backrefs, list) {
ret = btrfs_add_link(trans, root, rec->ino, backref->dir,
backref->name, backref->namelen,
- backref->filetype, &backref->index, 1);
+ backref->filetype, &backref->index, 1, 0);
if (ret < 0)
goto out;
}
return ret;
}
+static int get_highest_inode(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root,
+ struct btrfs_path *path,
+ u64 *highest_ino)
+{
+ struct btrfs_key key, found_key;
+ int ret;
+
+ btrfs_init_path(path);
+ key.objectid = BTRFS_LAST_FREE_OBJECTID;
+ key.offset = -1;
+ key.type = BTRFS_INODE_ITEM_KEY;
+ ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
+ if (ret == 1) {
+ btrfs_item_key_to_cpu(path->nodes[0], &found_key,
+ path->slots[0] - 1);
+ *highest_ino = found_key.objectid;
+ ret = 0;
+ }
+ if (*highest_ino >= BTRFS_LAST_FREE_OBJECTID)
+ ret = -EOVERFLOW;
+ btrfs_release_path(path);
+ return ret;
+}
+
+/*
+ * Link inode to dir 'lost+found'. Increase @ref_count.
+ *
+ * Returns 0 means success.
+ * Returns <0 means failure.
+ */
+static int link_inode_to_lostfound(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root,
+ struct btrfs_path *path,
+ u64 ino, char *namebuf, u32 name_len,
+ u8 filetype, u64 *ref_count)
+{
+ char *dir_name = "lost+found";
+ u64 lost_found_ino;
+ int ret;
+ u32 mode = 0700;
+
+ btrfs_release_path(path);
+ ret = get_highest_inode(trans, root, path, &lost_found_ino);
+ if (ret < 0)
+ goto out;
+ lost_found_ino++;
+
+ ret = btrfs_mkdir(trans, root, dir_name, strlen(dir_name),
+ BTRFS_FIRST_FREE_OBJECTID, &lost_found_ino,
+ mode);
+ if (ret < 0) {
+ error("failed to create '%s' dir: %s", dir_name, strerror(-ret));
+ goto out;
+ }
+ ret = btrfs_add_link(trans, root, ino, lost_found_ino,
+ namebuf, name_len, filetype, NULL, 1, 0);
+ /*
+ * Add ".INO" suffix several times to handle case where
+ * "FILENAME.INO" is already taken by another file.
+ */
+ while (ret == -EEXIST) {
+ /*
+ * Conflicting file name, add ".INO" as suffix * +1 for '.'
+ */
+ if (name_len + count_digits(ino) + 1 > BTRFS_NAME_LEN) {
+ ret = -EFBIG;
+ goto out;
+ }
+ snprintf(namebuf + name_len, BTRFS_NAME_LEN - name_len,
+ ".%llu", ino);
+ name_len += count_digits(ino) + 1;
+ ret = btrfs_add_link(trans, root, ino, lost_found_ino, namebuf,
+ name_len, filetype, NULL, 1, 0);
+ }
+ if (ret < 0) {
+ error("failed to link the inode %llu to %s dir: %s",
+ ino, dir_name, strerror(-ret));
+ goto out;
+ }
+
+ ++*ref_count;
+ printf("Moving file '%.*s' to '%s' dir since it has no valid backref\n",
+ name_len, namebuf, dir_name);
+out:
+ btrfs_release_path(path);
+ if (ret)
+ error("failed to move file '%.*s' to '%s' dir", name_len,
+ namebuf, dir_name);
+ return ret;
+}
+
static int repair_inode_nlinks(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct btrfs_path *path,
struct inode_record *rec)
{
- char *dir_name = "lost+found";
char namebuf[BTRFS_NAME_LEN] = {0};
- u64 lost_found_ino;
- u32 mode = 0700;
u8 type = 0;
int namelen = 0;
int name_recovered = 0;
}
if (rec->found_link == 0) {
- lost_found_ino = root->highest_inode;
- if (lost_found_ino >= BTRFS_LAST_FREE_OBJECTID) {
- ret = -EOVERFLOW;
- goto out;
- }
- lost_found_ino++;
- ret = btrfs_mkdir(trans, root, dir_name, strlen(dir_name),
- BTRFS_FIRST_FREE_OBJECTID, &lost_found_ino,
- mode);
- if (ret < 0) {
- fprintf(stderr, "Failed to create '%s' dir: %s\n",
- dir_name, strerror(-ret));
- goto out;
- }
- ret = btrfs_add_link(trans, root, rec->ino, lost_found_ino,
- namebuf, namelen, type, NULL, 1);
- /*
- * Add ".INO" suffix several times to handle case where
- * "FILENAME.INO" is already taken by another file.
- */
- while (ret == -EEXIST) {
- /*
- * Conflicting file name, add ".INO" as suffix * +1 for '.'
- */
- if (namelen + count_digits(rec->ino) + 1 >
- BTRFS_NAME_LEN) {
- ret = -EFBIG;
- goto out;
- }
- snprintf(namebuf + namelen, BTRFS_NAME_LEN - namelen,
- ".%llu", rec->ino);
- namelen += count_digits(rec->ino) + 1;
- ret = btrfs_add_link(trans, root, rec->ino,
- lost_found_ino, namebuf,
- namelen, type, NULL, 1);
- }
- if (ret < 0) {
- fprintf(stderr,
- "Failed to link the inode %llu to %s dir: %s\n",
- rec->ino, dir_name, strerror(-ret));
+ ret = link_inode_to_lostfound(trans, root, path, rec->ino,
+ namebuf, namelen, type,
+ (u64 *)&rec->found_link);
+ if (ret)
goto out;
- }
- /*
- * Just increase the found_link, don't actually add the
- * backref. This will make things easier and this inode
- * record will be freed after the repair is done.
- * So fsck will not report problem about this inode.
- */
- rec->found_link++;
- printf("Moving file '%.*s' to '%s' dir since it has no valid backref\n",
- namelen, namebuf, dir_name);
}
printf("Fixed the nlink of inode %llu\n", rec->ino);
out:
/* special case for a file losing all its file extent */
if (!found) {
ret = btrfs_punch_hole(trans, root, rec->ino, 0,
- round_up(rec->isize, root->sectorsize));
+ round_up(rec->isize,
+ root->fs_info->sectorsize));
if (ret < 0)
goto out;
}
}
/*
- * We need to record the highest inode number for later 'lost+found'
- * dir creation.
- * We must select an ino not used/referred by any existing inode, or
- * 'lost+found' ino may be a missing ino in a corrupted leaf,
- * this may cause 'lost+found' dir has wrong nlinks.
- */
- cache = last_cache_extent(inode_cache);
- if (cache) {
- node = container_of(cache, struct ptr_node, cache);
- rec = node->data;
- if (rec->ino > root->highest_inode)
- root->highest_inode = rec->ino;
- }
-
- /*
* We need to repair backrefs first because we could change some of the
* errors in the inode recs.
*
path.slots[level]);
/* Remove the ptr */
- ret = btrfs_del_ptr(trans, root, &path, level,
- path.slots[level]);
+ ret = btrfs_del_ptr(root, &path, level, path.slots[level]);
if (ret < 0)
goto out;
/*
* return value is not concerned.
*/
btrfs_release_path(&path);
- ret = btrfs_free_extent(trans, root, offset, root->nodesize,
- 0, root->root_key.objectid,
- level - 1, 0);
+ ret = btrfs_free_extent(trans, root, offset,
+ root->fs_info->nodesize, 0,
+ root->root_key.objectid, level - 1, 0);
cache = next_cache_extent(cache);
}
return is_fstree(objectid);
}
-static int check_fs_roots(struct btrfs_root *root,
+static int check_fs_roots(struct btrfs_fs_info *fs_info,
struct cache_tree *root_cache)
{
struct btrfs_path path;
struct walk_control wc;
struct extent_buffer *leaf, *tree_node;
struct btrfs_root *tmp_root;
- struct btrfs_root *tree_root = root->fs_info->tree_root;
+ struct btrfs_root *tree_root = fs_info->tree_root;
int ret;
int err = 0;
* reflected into the free space cache yet.
*/
if (repair)
- reset_cached_block_groups(root->fs_info);
+ reset_cached_block_groups(fs_info);
memset(&wc, 0, sizeof(wc));
cache_tree_init(&wc.shared);
btrfs_init_path(&path);
fs_root_objectid(key.objectid)) {
if (key.objectid == BTRFS_TREE_RELOC_OBJECTID) {
tmp_root = btrfs_read_fs_root_no_cache(
- root->fs_info, &key);
+ fs_info, &key);
} else {
key.offset = (u64)-1;
tmp_root = btrfs_read_fs_root(
- root->fs_info, &key);
+ fs_info, &key);
}
if (IS_ERR(tmp_root)) {
err = 1;
return err;
}
-#define ROOT_DIR_ERROR (1<<1) /* bad ROOT_DIR */
-#define DIR_ITEM_MISSING (1<<2) /* DIR_ITEM not found */
-#define DIR_ITEM_MISMATCH (1<<3) /* DIR_ITEM found but not match */
-#define INODE_REF_MISSING (1<<4) /* INODE_REF/INODE_EXTREF not found */
-#define INODE_ITEM_MISSING (1<<5) /* INODE_ITEM not found */
-#define INODE_ITEM_MISMATCH (1<<6) /* INODE_ITEM found but not match */
-#define FILE_EXTENT_ERROR (1<<7) /* bad FILE_EXTENT */
-#define ODD_CSUM_ITEM (1<<8) /* CSUM_ITEM error */
-#define CSUM_ITEM_MISSING (1<<9) /* CSUM_ITEM not found */
-#define LINK_COUNT_ERROR (1<<10) /* INODE_ITEM nlink count error */
-#define NBYTES_ERROR (1<<11) /* INODE_ITEM nbytes count error */
-#define ISIZE_ERROR (1<<12) /* INODE_ITEM size count error */
-#define ORPHAN_ITEM (1<<13) /* INODE_ITEM no reference */
-#define NO_INODE_ITEM (1<<14) /* no inode_item */
-#define LAST_ITEM (1<<15) /* Complete this tree traversal */
-#define ROOT_REF_MISSING (1<<16) /* ROOT_REF not found */
-#define ROOT_REF_MISMATCH (1<<17) /* ROOT_REF found but not match */
+/*
+ * Find the @index according by @ino and name.
+ * Notice:time efficiency is O(N)
+ *
+ * @root: the root of the fs/file tree
+ * @index_ret: the index as return value
+ * @namebuf: the name to match
+ * @name_len: the length of name to match
+ * @file_type: the file_type of INODE_ITEM to match
+ *
+ * Returns 0 if found and *@index_ret will be modified with right value
+ * Returns< 0 not found and *@index_ret will be (u64)-1
+ */
+static int find_dir_index(struct btrfs_root *root, u64 dirid, u64 location_id,
+ u64 *index_ret, char *namebuf, u32 name_len,
+ u8 file_type)
+{
+ struct btrfs_path path;
+ struct extent_buffer *node;
+ struct btrfs_dir_item *di;
+ struct btrfs_key key;
+ struct btrfs_key location;
+ char name[BTRFS_NAME_LEN] = {0};
+
+ u32 total;
+ u32 cur = 0;
+ u32 len;
+ u32 data_len;
+ u8 filetype;
+ int slot;
+ int ret;
+
+ ASSERT(index_ret);
+
+ /* search from the last index */
+ key.objectid = dirid;
+ key.offset = (u64)-1;
+ key.type = BTRFS_DIR_INDEX_KEY;
+
+ btrfs_init_path(&path);
+ ret = btrfs_search_slot(NULL, root, &key, &path, 0, 0);
+ if (ret < 0)
+ return ret;
+
+loop:
+ ret = btrfs_previous_item(root, &path, dirid, BTRFS_DIR_INDEX_KEY);
+ if (ret) {
+ ret = -ENOENT;
+ *index_ret = (64)-1;
+ goto out;
+ }
+ /* Check whether inode_id/filetype/name match */
+ node = path.nodes[0];
+ slot = path.slots[0];
+ di = btrfs_item_ptr(node, slot, struct btrfs_dir_item);
+ total = btrfs_item_size_nr(node, slot);
+ while (cur < total) {
+ ret = -ENOENT;
+ len = btrfs_dir_name_len(node, di);
+ data_len = btrfs_dir_data_len(node, di);
+
+ btrfs_dir_item_key_to_cpu(node, di, &location);
+ if (location.objectid != location_id ||
+ location.type != BTRFS_INODE_ITEM_KEY ||
+ location.offset != 0)
+ goto next;
+
+ filetype = btrfs_dir_type(node, di);
+ if (file_type != filetype)
+ goto next;
+
+ if (len > BTRFS_NAME_LEN)
+ len = BTRFS_NAME_LEN;
+
+ read_extent_buffer(node, name, (unsigned long)(di + 1), len);
+ if (len != name_len || strncmp(namebuf, name, len))
+ goto next;
+
+ btrfs_item_key_to_cpu(path.nodes[0], &key, path.slots[0]);
+ *index_ret = key.offset;
+ ret = 0;
+ goto out;
+next:
+ len += sizeof(*di) + data_len;
+ di = (struct btrfs_dir_item *)((char *)di + len);
+ cur += len;
+ }
+ goto loop;
+
+out:
+ btrfs_release_path(&path);
+ return ret;
+}
/*
* Find DIR_ITEM/DIR_INDEX for the given key and check it with the specified
* INODE_REF/INODE_EXTREF match.
*
* @root: the root of the fs/file tree
- * @ref_key: the key of the INODE_REF/INODE_EXTREF
- * @key: the key of the DIR_ITEM/DIR_INDEX
- * @index: the index in the INODE_REF/INODE_EXTREF, be used to
- * distinguish root_dir between normal dir/file
- * @name: the name in the INODE_REF/INODE_EXTREF
- * @namelen: the length of name in the INODE_REF/INODE_EXTREF
- * @mode: the st_mode of INODE_ITEM
+ * @key: the key of the DIR_ITEM/DIR_INDEX, key->offset will be right
+ * value while find index
+ * @location_key: location key of the struct btrfs_dir_item to match
+ * @name: the name to match
+ * @namelen: the length of name
+ * @file_type: the type of file to math
*
* Return 0 if no error occurred.
- * Return ROOT_DIR_ERROR if found DIR_ITEM/DIR_INDEX for root_dir.
- * Return DIR_ITEM_MISSING if couldn't find DIR_ITEM/DIR_INDEX for normal
- * dir/file.
- * Return DIR_ITEM_MISMATCH if INODE_REF/INODE_EXTREF and DIR_ITEM/DIR_INDEX
- * not match for normal dir/file.
+ * Return DIR_ITEM_MISSING/DIR_INDEX_MISSING if couldn't find
+ * DIR_ITEM/DIR_INDEX
+ * Return DIR_ITEM_MISMATCH/DIR_INDEX_MISMATCH if INODE_REF/INODE_EXTREF
+ * and DIR_ITEM/DIR_INDEX mismatch
*/
-static int find_dir_item(struct btrfs_root *root, struct btrfs_key *ref_key,
- struct btrfs_key *key, u64 index, char *name,
- u32 namelen, u32 mode)
+static int find_dir_item(struct btrfs_root *root, struct btrfs_key *key,
+ struct btrfs_key *location_key, char *name,
+ u32 namelen, u8 file_type)
{
struct btrfs_path path;
struct extent_buffer *node;
u32 total;
u32 cur = 0;
u32 len;
- u32 name_len;
u32 data_len;
u8 filetype;
int slot;
int ret;
- btrfs_init_path(&path);
- ret = btrfs_search_slot(NULL, root, key, &path, 0, 0);
- if (ret < 0) {
- ret = DIR_ITEM_MISSING;
- goto out;
- }
-
- /* Process root dir and goto out*/
- if (index == 0) {
- if (ret == 0) {
- ret = ROOT_DIR_ERROR;
- error(
- "root %llu INODE %s[%llu %llu] ROOT_DIR shouldn't have %s",
- root->objectid,
- ref_key->type == BTRFS_INODE_REF_KEY ?
- "REF" : "EXTREF",
- ref_key->objectid, ref_key->offset,
- key->type == BTRFS_DIR_ITEM_KEY ?
- "DIR_ITEM" : "DIR_INDEX");
- } else {
- ret = 0;
- }
-
- goto out;
+ /* get the index by traversing all index */
+ if (key->type == BTRFS_DIR_INDEX_KEY && key->offset == (u64)-1) {
+ ret = find_dir_index(root, key->objectid,
+ location_key->objectid, &key->offset,
+ name, namelen, file_type);
+ if (ret)
+ ret = DIR_INDEX_MISSING;
+ return ret;
}
- /* Process normal file/dir */
- if (ret > 0) {
- ret = DIR_ITEM_MISSING;
- error(
- "root %llu INODE %s[%llu %llu] doesn't have related %s[%llu %llu] namelen %u filename %s filetype %d",
- root->objectid,
- ref_key->type == BTRFS_INODE_REF_KEY ? "REF" : "EXTREF",
- ref_key->objectid, ref_key->offset,
- key->type == BTRFS_DIR_ITEM_KEY ?
- "DIR_ITEM" : "DIR_INDEX",
- key->objectid, key->offset, namelen, name,
- imode_to_type(mode));
+ btrfs_init_path(&path);
+ ret = btrfs_search_slot(NULL, root, key, &path, 0, 0);
+ if (ret) {
+ ret = key->type == BTRFS_DIR_ITEM_KEY ? DIR_ITEM_MISSING :
+ DIR_INDEX_MISSING;
goto out;
}
di = btrfs_item_ptr(node, slot, struct btrfs_dir_item);
total = btrfs_item_size_nr(node, slot);
while (cur < total) {
- ret = DIR_ITEM_MISMATCH;
- name_len = btrfs_dir_name_len(node, di);
+ ret = key->type == BTRFS_DIR_ITEM_KEY ?
+ DIR_ITEM_MISMATCH : DIR_INDEX_MISMATCH;
+
+ len = btrfs_dir_name_len(node, di);
data_len = btrfs_dir_data_len(node, di);
btrfs_dir_item_key_to_cpu(node, di, &location);
- if (location.objectid != ref_key->objectid ||
- location.type != BTRFS_INODE_ITEM_KEY ||
- location.offset != 0)
+ if (location.objectid != location_key->objectid ||
+ location.type != location_key->type ||
+ location.offset != location_key->offset)
goto next;
filetype = btrfs_dir_type(node, di);
- if (imode_to_type(mode) != filetype)
+ if (file_type != filetype)
goto next;
- if (name_len <= BTRFS_NAME_LEN) {
- len = name_len;
- } else {
+ if (len > BTRFS_NAME_LEN) {
len = BTRFS_NAME_LEN;
warning("root %llu %s[%llu %llu] name too long %u, trimmed",
root->objectid,
key->type == BTRFS_DIR_ITEM_KEY ?
"DIR_ITEM" : "DIR_INDEX",
- key->objectid, key->offset, name_len);
+ key->objectid, key->offset, len);
}
- read_extent_buffer(node, namebuf, (unsigned long)(di + 1), len);
+ read_extent_buffer(node, namebuf, (unsigned long)(di + 1),
+ len);
if (len != namelen || strncmp(namebuf, name, len))
goto next;
ret = 0;
goto out;
next:
- len = sizeof(*di) + name_len + data_len;
+ len += sizeof(*di) + data_len;
di = (struct btrfs_dir_item *)((char *)di + len);
cur += len;
}
- if (ret == DIR_ITEM_MISMATCH)
+
+out:
+ btrfs_release_path(&path);
+ return ret;
+}
+
+/*
+ * Prints inode ref error message
+ */
+static void print_inode_ref_err(struct btrfs_root *root, struct btrfs_key *key,
+ u64 index, const char *namebuf, int name_len,
+ u8 filetype, int err)
+{
+ if (!err)
+ return;
+
+ /* root dir error */
+ if (key->objectid == BTRFS_FIRST_FREE_OBJECTID) {
error(
- "root %llu INODE %s[%llu %llu] and %s[%llu %llu] mismatch namelen %u filename %s filetype %d",
- root->objectid,
- ref_key->type == BTRFS_INODE_REF_KEY ? "REF" : "EXTREF",
- ref_key->objectid, ref_key->offset,
- key->type == BTRFS_DIR_ITEM_KEY ?
- "DIR_ITEM" : "DIR_INDEX",
- key->objectid, key->offset, namelen, name,
- imode_to_type(mode));
+ "root %llu root dir shouldn't have INODE REF[%llu %llu] name %s",
+ root->objectid, key->objectid, key->offset, namebuf);
+ return;
+ }
+
+ /* normal error */
+ if (err & (DIR_ITEM_MISMATCH | DIR_ITEM_MISSING))
+ error("root %llu DIR ITEM[%llu %llu] %s name %s filetype %u",
+ root->objectid, key->offset,
+ btrfs_name_hash(namebuf, name_len),
+ err & DIR_ITEM_MISMATCH ? "mismatch" : "missing",
+ namebuf, filetype);
+ if (err & (DIR_INDEX_MISMATCH | DIR_INDEX_MISSING))
+ error("root %llu DIR INDEX[%llu %llu] %s name %s filetype %u",
+ root->objectid, key->offset, index,
+ err & DIR_ITEM_MISMATCH ? "mismatch" : "missing",
+ namebuf, filetype);
+}
+
+/*
+ * Insert the missing inode item.
+ *
+ * Returns 0 means success.
+ * Returns <0 means error.
+ */
+static int repair_inode_item_missing(struct btrfs_root *root, u64 ino,
+ u8 filetype)
+{
+ struct btrfs_key key;
+ struct btrfs_trans_handle *trans;
+ struct btrfs_path path;
+ int ret;
+
+ key.objectid = ino;
+ key.type = BTRFS_INODE_ITEM_KEY;
+ key.offset = 0;
+
+ btrfs_init_path(&path);
+ trans = btrfs_start_transaction(root, 1);
+ if (IS_ERR(trans)) {
+ ret = -EIO;
+ goto out;
+ }
+
+ ret = btrfs_search_slot(trans, root, &key, &path, 1, 1);
+ if (ret < 0 || !ret)
+ goto fail;
+
+ /* insert inode item */
+ create_inode_item_lowmem(trans, root, ino, filetype);
+ ret = 0;
+fail:
+ btrfs_commit_transaction(trans, root);
out:
+ if (ret)
+ error("failed to repair root %llu INODE ITEM[%llu] missing",
+ root->objectid, ino);
btrfs_release_path(&path);
return ret;
}
/*
+ * The ternary means dir item, dir index and relative inode ref.
+ * The function handles errs: INODE_MISSING, DIR_INDEX_MISSING
+ * DIR_INDEX_MISMATCH, DIR_ITEM_MISSING, DIR_ITEM_MISMATCH by the follow
+ * strategy:
+ * If two of three is missing or mismatched, delete the existing one.
+ * If one of three is missing or mismatched, add the missing one.
+ *
+ * returns 0 means success.
+ * returns not 0 means on error;
+ */
+int repair_ternary_lowmem(struct btrfs_root *root, u64 dir_ino, u64 ino,
+ u64 index, char *name, int name_len, u8 filetype,
+ int err)
+{
+ struct btrfs_trans_handle *trans;
+ int stage = 0;
+ int ret = 0;
+
+ /*
+ * stage shall be one of following valild values:
+ * 0: Fine, nothing to do.
+ * 1: One of three is wrong, so add missing one.
+ * 2: Two of three is wrong, so delete existed one.
+ */
+ if (err & (DIR_INDEX_MISMATCH | DIR_INDEX_MISSING))
+ stage++;
+ if (err & (DIR_ITEM_MISMATCH | DIR_ITEM_MISSING))
+ stage++;
+ if (err & (INODE_REF_MISSING))
+ stage++;
+
+ /* stage must be smllarer than 3 */
+ ASSERT(stage < 3);
+
+ trans = btrfs_start_transaction(root, 1);
+ if (stage == 2) {
+ ret = btrfs_unlink(trans, root, ino, dir_ino, index, name,
+ name_len, 0);
+ goto out;
+ }
+ if (stage == 1) {
+ ret = btrfs_add_link(trans, root, ino, dir_ino, name, name_len,
+ filetype, &index, 1, 1);
+ goto out;
+ }
+out:
+ btrfs_commit_transaction(trans, root);
+
+ if (ret)
+ error("fail to repair inode %llu name %s filetype %u",
+ ino, name, filetype);
+ else
+ printf("%s ref/dir_item of inode %llu name %s filetype %u\n",
+ stage == 2 ? "Delete" : "Add",
+ ino, name, filetype);
+
+ return ret;
+}
+
+/*
* Traverse the given INODE_REF and call find_dir_item() to find related
* DIR_ITEM/DIR_INDEX.
*
* @root: the root of the fs/file tree
* @ref_key: the key of the INODE_REF
+ * @path the path provides node and slot
* @refs: the count of INODE_REF
* @mode: the st_mode of INODE_ITEM
+ * @name_ret: returns with the first ref's name
+ * @name_len_ret: len of the name_ret
*
* Return 0 if no error occurred.
*/
static int check_inode_ref(struct btrfs_root *root, struct btrfs_key *ref_key,
- struct extent_buffer *node, int slot, u64 *refs,
- int mode)
+ struct btrfs_path *path, char *name_ret,
+ u32 *namelen_ret, u64 *refs_ret, int mode)
{
struct btrfs_key key;
+ struct btrfs_key location;
struct btrfs_inode_ref *ref;
+ struct extent_buffer *node;
char namebuf[BTRFS_NAME_LEN] = {0};
u32 total;
u32 cur = 0;
u32 len;
u32 name_len;
u64 index;
- int ret, err = 0;
+ int ret;
+ int err = 0;
+ int tmp_err;
+ int slot;
+ int need_research = 0;
+ u64 refs;
+
+begin:
+ err = 0;
+ cur = 0;
+ refs = *refs_ret;
+
+ /* since after repair, path and the dir item may be changed */
+ if (need_research) {
+ need_research = 0;
+ btrfs_release_path(path);
+ ret = btrfs_search_slot(NULL, root, ref_key, path, 0, 0);
+ /* the item was deleted, let path point to the last checked item */
+ if (ret > 0) {
+ if (path->slots[0] == 0)
+ btrfs_prev_leaf(root, path);
+ else
+ path->slots[0]--;
+ }
+ if (ret)
+ goto out;
+ }
+ location.objectid = ref_key->objectid;
+ location.type = BTRFS_INODE_ITEM_KEY;
+ location.offset = 0;
+ node = path->nodes[0];
+ slot = path->slots[0];
+
+ memset(namebuf, 0, sizeof(namebuf) / sizeof(*namebuf));
ref = btrfs_item_ptr(node, slot, struct btrfs_inode_ref);
total = btrfs_item_size_nr(node, slot);
next:
/* Update inode ref count */
- (*refs)++;
-
+ refs++;
+ tmp_err = 0;
index = btrfs_inode_ref_index(node, ref);
name_len = btrfs_inode_ref_name_len(node, ref);
+
if (name_len <= BTRFS_NAME_LEN) {
len = name_len;
} else {
read_extent_buffer(node, namebuf, (unsigned long)(ref + 1), len);
- /* Check root dir ref name */
- if (index == 0 && strncmp(namebuf, "..", name_len)) {
- error("root %llu INODE_REF[%llu %llu] ROOT_DIR name shouldn't be %s",
- root->objectid, ref_key->objectid, ref_key->offset,
- namebuf);
- err |= ROOT_DIR_ERROR;
+ /* copy the first name found to name_ret */
+ if (refs == 1 && name_ret) {
+ memcpy(name_ret, namebuf, len);
+ *namelen_ret = len;
+ }
+
+ /* Check root dir ref */
+ if (ref_key->objectid == BTRFS_FIRST_FREE_OBJECTID) {
+ if (index != 0 || len != strlen("..") ||
+ strncmp("..", namebuf, len) ||
+ ref_key->offset != BTRFS_FIRST_FREE_OBJECTID) {
+ /* set err bits then repair will delete the ref */
+ err |= DIR_INDEX_MISSING;
+ err |= DIR_ITEM_MISSING;
+ }
+ goto end;
}
/* Find related DIR_INDEX */
key.objectid = ref_key->offset;
key.type = BTRFS_DIR_INDEX_KEY;
key.offset = index;
- ret = find_dir_item(root, ref_key, &key, index, namebuf, len, mode);
- err |= ret;
+ tmp_err |= find_dir_item(root, &key, &location, namebuf, len,
+ imode_to_type(mode));
/* Find related dir_item */
key.objectid = ref_key->offset;
key.type = BTRFS_DIR_ITEM_KEY;
key.offset = btrfs_name_hash(namebuf, len);
- ret = find_dir_item(root, ref_key, &key, index, namebuf, len, mode);
- err |= ret;
-
+ tmp_err |= find_dir_item(root, &key, &location, namebuf, len,
+ imode_to_type(mode));
+end:
+ if (tmp_err && repair) {
+ ret = repair_ternary_lowmem(root, ref_key->offset,
+ ref_key->objectid, index, namebuf,
+ name_len, imode_to_type(mode),
+ tmp_err);
+ if (!ret) {
+ need_research = 1;
+ goto begin;
+ }
+ }
+ print_inode_ref_err(root, ref_key, index, namebuf, name_len,
+ imode_to_type(mode), tmp_err);
+ err |= tmp_err;
len = sizeof(*ref) + name_len;
ref = (struct btrfs_inode_ref *)((char *)ref + len);
cur += len;
if (cur < total)
goto next;
+out:
+ *refs_ret = refs;
return err;
}
int mode)
{
struct btrfs_key key;
+ struct btrfs_key location;
struct btrfs_inode_extref *extref;
char namebuf[BTRFS_NAME_LEN] = {0};
u32 total;
int ret;
int err = 0;
+ location.objectid = ref_key->objectid;
+ location.type = BTRFS_INODE_ITEM_KEY;
+ location.offset = 0;
+
extref = btrfs_item_ptr(node, slot, struct btrfs_inode_extref);
total = btrfs_item_size_nr(node, slot);
key.objectid = parent;
key.type = BTRFS_DIR_INDEX_KEY;
key.offset = index;
- ret = find_dir_item(root, ref_key, &key, index, namebuf, len, mode);
+ ret = find_dir_item(root, &key, &location, namebuf, len, mode);
err |= ret;
/* find related dir_item */
key.objectid = parent;
key.type = BTRFS_DIR_ITEM_KEY;
key.offset = btrfs_name_hash(namebuf, len);
- ret = find_dir_item(root, ref_key, &key, index, namebuf, len, mode);
+ ret = find_dir_item(root, &key, &location, namebuf, len, mode);
err |= ret;
len = sizeof(*extref) + name_len;
/*
* Find INODE_REF/INODE_EXTREF for the given key and check it with the specified
* DIR_ITEM/DIR_INDEX match.
+ * Return with @index_ret.
*
* @root: the root of the fs/file tree
* @key: the key of the INODE_REF/INODE_EXTREF
* @name: the name in the INODE_REF/INODE_EXTREF
* @namelen: the length of name in the INODE_REF/INODE_EXTREF
- * @index: the index in the INODE_REF/INODE_EXTREF, for DIR_ITEM set index
- * to (u64)-1
+ * @index_ret: the index in the INODE_REF/INODE_EXTREF,
+ * value (64)-1 means do not check index
* @ext_ref: the EXTENDED_IREF feature
*
* Return 0 if no error occurred.
* Return >0 for error bitmap
*/
static int find_inode_ref(struct btrfs_root *root, struct btrfs_key *key,
- char *name, int namelen, u64 index,
+ char *name, int namelen, u64 *index_ret,
unsigned int ext_ref)
{
struct btrfs_path path;
int slot;
int ret;
+ ASSERT(index_ret);
+
btrfs_init_path(&path);
ret = btrfs_search_slot(NULL, root, key, &path, 0, 0);
if (ret) {
ref_namelen = btrfs_inode_ref_name_len(node, ref);
ref_index = btrfs_inode_ref_index(node, ref);
- if (index != (u64)-1 && index != ref_index)
+ if (*index_ret != (u64)-1 && *index_ret != ref_index)
goto next_ref;
- if (ref_namelen <= BTRFS_NAME_LEN) {
- len = ref_namelen;
- } else {
- len = BTRFS_NAME_LEN;
+ if (cur + sizeof(*ref) + ref_namelen > total ||
+ ref_namelen > BTRFS_NAME_LEN) {
warning("root %llu INODE %s[%llu %llu] name too long",
root->objectid,
key->type == BTRFS_INODE_REF_KEY ?
"REF" : "EXTREF",
key->objectid, key->offset);
+
+ if (cur + sizeof(*ref) > total)
+ break;
+ len = min_t(u32, total - cur - sizeof(*ref),
+ BTRFS_NAME_LEN);
+ } else {
+ len = ref_namelen;
}
+
read_extent_buffer(node, ref_namebuf, (unsigned long)(ref + 1),
len);
if (len != namelen || strncmp(ref_namebuf, name, len))
goto next_ref;
+ *index_ret = ref_index;
ret = 0;
goto out;
next_ref:
ref_namelen = btrfs_inode_extref_name_len(node, extref);
ref_index = btrfs_inode_extref_index(node, extref);
parent = btrfs_inode_extref_parent(node, extref);
- if (index != (u64)-1 && index != ref_index)
+ if (*index_ret != (u64)-1 && *index_ret != ref_index)
goto next_extref;
if (parent != dir_id)
len = ref_namelen;
} else {
len = BTRFS_NAME_LEN;
- warning("Warning: root %llu INODE %s[%llu %llu] name too long\n",
+ warning("root %llu INODE %s[%llu %llu] name too long",
root->objectid,
key->type == BTRFS_INODE_REF_KEY ?
"REF" : "EXTREF",
read_extent_buffer(node, ref_namebuf,
(unsigned long)(extref + 1), len);
- if (len != namelen || strncmp(ref_namebuf, name, len))
- goto next_extref;
+ if (len != namelen || strncmp(ref_namebuf, name, len))
+ goto next_extref;
+
+ *index_ret = ref_index;
+ ret = 0;
+ goto out;
+
+next_extref:
+ len = sizeof(*extref) + ref_namelen;
+ extref = (struct btrfs_inode_extref *)((char *)extref + len);
+ cur += len;
+
+ }
+out:
+ btrfs_release_path(&path);
+ return ret;
+}
+
+static void print_dir_item_err(struct btrfs_root *root, struct btrfs_key *key,
+ u64 ino, u64 index, const char *namebuf,
+ int name_len, u8 filetype, int err)
+{
+ if (err & (DIR_ITEM_MISMATCH | DIR_ITEM_MISSING)) {
+ error("root %llu DIR ITEM[%llu %llu] name %s filetype %d %s",
+ root->objectid, key->objectid, key->offset, namebuf,
+ filetype,
+ err & DIR_ITEM_MISMATCH ? "mismath" : "missing");
+ }
+
+ if (err & (DIR_INDEX_MISMATCH | DIR_INDEX_MISSING)) {
+ error("root %llu DIR INDEX[%llu %llu] name %s filetype %d %s",
+ root->objectid, key->objectid, index, namebuf, filetype,
+ err & DIR_ITEM_MISMATCH ? "mismath" : "missing");
+ }
+
+ if (err & (INODE_ITEM_MISSING | INODE_ITEM_MISMATCH)) {
+ error(
+ "root %llu INODE_ITEM[%llu] index %llu name %s filetype %d %s",
+ root->objectid, ino, index, namebuf, filetype,
+ err & INODE_ITEM_MISMATCH ? "mismath" : "missing");
+ }
+
+ if (err & INODE_REF_MISSING)
+ error(
+ "root %llu INODE REF[%llu, %llu] name %s filetype %u missing",
+ root->objectid, ino, key->objectid, namebuf, filetype);
+
+}
+
+/*
+ * Call repair_inode_item_missing and repair_ternary_lowmem to repair
+ *
+ * Returns error after repair
+ */
+static int repair_dir_item(struct btrfs_root *root, u64 dirid, u64 ino,
+ u64 index, u8 filetype, char *namebuf, u32 name_len,
+ int err)
+{
+ int ret;
+
+ if (err & INODE_ITEM_MISSING) {
+ ret = repair_inode_item_missing(root, ino, filetype);
+ if (!ret)
+ err &= ~(INODE_ITEM_MISMATCH | INODE_ITEM_MISSING);
+ }
+
+ if (err & ~(INODE_ITEM_MISMATCH | INODE_ITEM_MISSING)) {
+ ret = repair_ternary_lowmem(root, dirid, ino, index, namebuf,
+ name_len, filetype, err);
+ if (!ret) {
+ err &= ~(DIR_INDEX_MISMATCH | DIR_INDEX_MISSING);
+ err &= ~(DIR_ITEM_MISMATCH | DIR_ITEM_MISSING);
+ err &= ~(INODE_REF_MISSING);
+ }
+ }
+ return err;
+}
+
+static int __count_dir_isize(struct btrfs_root *root, u64 ino, int type,
+ u64 *size_ret)
+{
+ struct btrfs_key key;
+ struct btrfs_path path;
+ u32 len;
+ struct btrfs_dir_item *di;
+ int ret;
+ int cur = 0;
+ int total = 0;
+
+ ASSERT(size_ret);
+ *size_ret = 0;
+
+ key.objectid = ino;
+ key.type = type;
+ key.offset = (u64)-1;
+
+ btrfs_init_path(&path);
+ ret = btrfs_search_slot(NULL, root, &key, &path, 0, 0);
+ if (ret < 0) {
+ ret = -EIO;
+ goto out;
+ }
+ /* if found, go to spacial case */
+ if (ret == 0)
+ goto special_case;
+
+loop:
+ ret = btrfs_previous_item(root, &path, ino, type);
+
+ if (ret) {
+ ret = 0;
+ goto out;
+ }
+
+special_case:
+ di = btrfs_item_ptr(path.nodes[0], path.slots[0], struct btrfs_dir_item);
+ cur = 0;
+ total = btrfs_item_size_nr(path.nodes[0], path.slots[0]);
+
+ while (cur < total) {
+ len = btrfs_dir_name_len(path.nodes[0], di);
+ if (len > BTRFS_NAME_LEN)
+ len = BTRFS_NAME_LEN;
+ *size_ret += len;
+
+ len += btrfs_dir_data_len(path.nodes[0], di);
+ len += sizeof(*di);
+ di = (struct btrfs_dir_item *)((char *)di + len);
+ cur += len;
+ }
+ goto loop;
+
+out:
+ btrfs_release_path(&path);
+ return ret;
+}
+
+static int count_dir_isize(struct btrfs_root *root, u64 ino, u64 *size)
+{
+ u64 item_size;
+ u64 index_size;
+ int ret;
+
+ ASSERT(size);
+ ret = __count_dir_isize(root, ino, BTRFS_DIR_ITEM_KEY, &item_size);
+ if (ret)
+ goto out;
- ret = 0;
+ ret = __count_dir_isize(root, ino, BTRFS_DIR_INDEX_KEY, &index_size);
+ if (ret)
goto out;
-next_extref:
- len = sizeof(*extref) + ref_namelen;
- extref = (struct btrfs_inode_extref *)((char *)extref + len);
- cur += len;
+ *size = item_size + index_size;
- }
out:
- btrfs_release_path(&path);
+ if (ret)
+ error("failed to count root %llu INODE[%llu] root size",
+ root->objectid, ino);
return ret;
}
*
* @root: the root of the fs/file tree
* @key: the key of the INODE_REF/INODE_EXTREF
+ * @path: the path
* @size: the st_size of the INODE_ITEM
* @ext_ref: the EXTENDED_IREF feature
*
* Return 0 if no error occurred.
+ * Return DIR_COUNT_AGAIN if the isize of the inode should be recalculated.
*/
-static int check_dir_item(struct btrfs_root *root, struct btrfs_key *key,
- struct extent_buffer *node, int slot, u64 *size,
+static int check_dir_item(struct btrfs_root *root, struct btrfs_key *di_key,
+ struct btrfs_path *path, u64 *size,
unsigned int ext_ref)
{
struct btrfs_dir_item *di;
struct btrfs_inode_item *ii;
- struct btrfs_path path;
+ struct btrfs_key key;
struct btrfs_key location;
+ struct extent_buffer *node;
+ int slot;
char namebuf[BTRFS_NAME_LEN] = {0};
u32 total;
u32 cur = 0;
u32 name_len;
u32 data_len;
u8 filetype;
- u32 mode;
+ u32 mode = 0;
u64 index;
int ret;
- int err = 0;
+ int err;
+ int tmp_err;
+ int need_research = 0;
/*
* For DIR_ITEM set index to (u64)-1, so that find_inode_ref
* ignore index check.
*/
- index = (key->type == BTRFS_DIR_INDEX_KEY) ? key->offset : (u64)-1;
+ if (di_key->type == BTRFS_DIR_INDEX_KEY)
+ index = di_key->offset;
+ else
+ index = (u64)-1;
+begin:
+ err = 0;
+ cur = 0;
+
+ /* since after repair, path and the dir item may be changed */
+ if (need_research) {
+ need_research = 0;
+ err |= DIR_COUNT_AGAIN;
+ btrfs_release_path(path);
+ ret = btrfs_search_slot(NULL, root, di_key, path, 0, 0);
+ /* the item was deleted, let path point the last checked item */
+ if (ret > 0) {
+ if (path->slots[0] == 0)
+ btrfs_prev_leaf(root, path);
+ else
+ path->slots[0]--;
+ }
+ if (ret)
+ goto out;
+ }
+
+ node = path->nodes[0];
+ slot = path->slots[0];
di = btrfs_item_ptr(node, slot, struct btrfs_dir_item);
total = btrfs_item_size_nr(node, slot);
+ memset(namebuf, 0, sizeof(namebuf) / sizeof(*namebuf));
while (cur < total) {
data_len = btrfs_dir_data_len(node, di);
+ tmp_err = 0;
if (data_len)
error("root %llu %s[%llu %llu] data_len shouldn't be %u",
- root->objectid, key->type == BTRFS_DIR_ITEM_KEY ?
- "DIR_ITEM" : "DIR_INDEX",
- key->objectid, key->offset, data_len);
+ root->objectid,
+ di_key->type == BTRFS_DIR_ITEM_KEY ? "DIR_ITEM" : "DIR_INDEX",
+ di_key->objectid, di_key->offset, data_len);
name_len = btrfs_dir_name_len(node, di);
if (name_len <= BTRFS_NAME_LEN) {
len = BTRFS_NAME_LEN;
warning("root %llu %s[%llu %llu] name too long",
root->objectid,
- key->type == BTRFS_DIR_ITEM_KEY ?
- "DIR_ITEM" : "DIR_INDEX",
- key->objectid, key->offset);
+ di_key->type == BTRFS_DIR_ITEM_KEY ? "DIR_ITEM" : "DIR_INDEX",
+ di_key->objectid, di_key->offset);
}
(*size) += name_len;
-
- read_extent_buffer(node, namebuf, (unsigned long)(di + 1), len);
+ read_extent_buffer(node, namebuf, (unsigned long)(di + 1),
+ len);
filetype = btrfs_dir_type(node, di);
- btrfs_init_path(&path);
- btrfs_dir_item_key_to_cpu(node, di, &location);
+ if (di_key->type == BTRFS_DIR_ITEM_KEY &&
+ di_key->offset != btrfs_name_hash(namebuf, len)) {
+ err |= -EIO;
+ error("root %llu DIR_ITEM[%llu %llu] name %s namelen %u filetype %u mismatch with its hash, wanted %llu have %llu",
+ root->objectid, di_key->objectid, di_key->offset,
+ namebuf, len, filetype, di_key->offset,
+ btrfs_name_hash(namebuf, len));
+ }
+ btrfs_dir_item_key_to_cpu(node, di, &location);
/* Ignore related ROOT_ITEM check */
if (location.type == BTRFS_ROOT_ITEM_KEY)
goto next;
+ btrfs_release_path(path);
/* Check relative INODE_ITEM(existence/filetype) */
- ret = btrfs_search_slot(NULL, root, &location, &path, 0, 0);
+ ret = btrfs_search_slot(NULL, root, &location, path, 0, 0);
if (ret) {
- err |= INODE_ITEM_MISSING;
- error("root %llu %s[%llu %llu] couldn't find relative INODE_ITEM[%llu] namelen %u filename %s filetype %x",
- root->objectid, key->type == BTRFS_DIR_ITEM_KEY ?
- "DIR_ITEM" : "DIR_INDEX", key->objectid,
- key->offset, location.objectid, name_len,
- namebuf, filetype);
+ tmp_err |= INODE_ITEM_MISSING;
goto next;
}
- ii = btrfs_item_ptr(path.nodes[0], path.slots[0],
+ ii = btrfs_item_ptr(path->nodes[0], path->slots[0],
struct btrfs_inode_item);
- mode = btrfs_inode_mode(path.nodes[0], ii);
-
+ mode = btrfs_inode_mode(path->nodes[0], ii);
if (imode_to_type(mode) != filetype) {
- err |= INODE_ITEM_MISMATCH;
- error("root %llu %s[%llu %llu] relative INODE_ITEM filetype mismatch namelen %u filename %s filetype %d",
- root->objectid, key->type == BTRFS_DIR_ITEM_KEY ?
- "DIR_ITEM" : "DIR_INDEX", key->objectid,
- key->offset, name_len, namebuf, filetype);
+ tmp_err |= INODE_ITEM_MISMATCH;
+ goto next;
}
/* Check relative INODE_REF/INODE_EXTREF */
- location.type = BTRFS_INODE_REF_KEY;
- location.offset = key->objectid;
- ret = find_inode_ref(root, &location, namebuf, len,
- index, ext_ref);
- err |= ret;
- if (ret & INODE_REF_MISSING)
- error("root %llu %s[%llu %llu] relative INODE_REF missing namelen %u filename %s filetype %d",
- root->objectid, key->type == BTRFS_DIR_ITEM_KEY ?
- "DIR_ITEM" : "DIR_INDEX", key->objectid,
- key->offset, name_len, namebuf, filetype);
+ key.objectid = location.objectid;
+ key.type = BTRFS_INODE_REF_KEY;
+ key.offset = di_key->objectid;
+ tmp_err |= find_inode_ref(root, &key, namebuf, len,
+ &index, ext_ref);
+
+ /* check relative INDEX/ITEM */
+ key.objectid = di_key->objectid;
+ if (key.type == BTRFS_DIR_ITEM_KEY) {
+ key.type = BTRFS_DIR_INDEX_KEY;
+ key.offset = index;
+ } else {
+ key.type = BTRFS_DIR_ITEM_KEY;
+ key.offset = btrfs_name_hash(namebuf, name_len);
+ }
+ tmp_err |= find_dir_item(root, &key, &location, namebuf,
+ name_len, filetype);
+ /* find_dir_item may find index */
+ if (key.type == BTRFS_DIR_INDEX_KEY)
+ index = key.offset;
next:
- btrfs_release_path(&path);
+
+ if (tmp_err && repair) {
+ ret = repair_dir_item(root, di_key->objectid,
+ location.objectid, index,
+ imode_to_type(mode), namebuf,
+ name_len, tmp_err);
+ if (ret != tmp_err) {
+ need_research = 1;
+ goto begin;
+ }
+ }
+ btrfs_release_path(path);
+ print_dir_item_err(root, di_key, location.objectid, index,
+ namebuf, name_len, filetype, tmp_err);
+ err |= tmp_err;
len = sizeof(*di) + name_len + data_len;
di = (struct btrfs_dir_item *)((char *)di + len);
cur += len;
- if (key->type == BTRFS_DIR_INDEX_KEY && cur < total) {
+ if (di_key->type == BTRFS_DIR_INDEX_KEY && cur < total) {
error("root %llu DIR_INDEX[%llu %llu] should contain only one entry",
- root->objectid, key->objectid, key->offset);
+ root->objectid, di_key->objectid,
+ di_key->offset);
break;
}
}
-
+out:
+ /* research path */
+ btrfs_release_path(path);
+ ret = btrfs_search_slot(NULL, root, di_key, path, 0, 0);
+ if (ret)
+ err |= ret > 0 ? -ENOENT : ret;
return err;
}
/*
+ * Wrapper function of btrfs_punch_hole.
+ *
+ * Returns 0 means success.
+ * Returns not 0 means error.
+ */
+static int punch_extent_hole(struct btrfs_root *root, u64 ino, u64 start,
+ u64 len)
+{
+ struct btrfs_trans_handle *trans;
+ int ret = 0;
+
+ trans = btrfs_start_transaction(root, 1);
+ if (IS_ERR(trans))
+ return PTR_ERR(trans);
+
+ ret = btrfs_punch_hole(trans, root, ino, start, len);
+ if (ret)
+ error("failed to add hole [%llu, %llu] in inode [%llu]",
+ start, len, ino);
+ else
+ printf("Add a hole [%llu, %llu] in inode [%llu]\n", start, len,
+ ino);
+
+ btrfs_commit_transaction(trans, root);
+ return ret;
+}
+
+/*
* Check file extent datasum/hole, update the size of the file extents,
* check and update the last offset of the file extent.
*
u64 disk_bytenr;
u64 disk_num_bytes;
u64 extent_num_bytes;
- u64 found;
+ u64 extent_offset;
+ u64 csum_found; /* In byte size, sectorsize aligned */
+ u64 search_start; /* Logical range start we search for csum */
+ u64 search_len; /* Logical range len we search for csum */
unsigned int extent_type;
unsigned int is_hole;
+ int compressed = 0;
int ret;
int err = 0;
fi = btrfs_item_ptr(node, slot, struct btrfs_file_extent_item);
+ /* Check inline extent */
extent_type = btrfs_file_extent_type(node, fi);
- /* Skip if file extent is inline */
if (extent_type == BTRFS_FILE_EXTENT_INLINE) {
struct btrfs_item *e = btrfs_item_nr(slot);
u32 item_inline_len;
item_inline_len = btrfs_file_extent_inline_item_len(node, e);
extent_num_bytes = btrfs_file_extent_inline_len(node, slot, fi);
- if (extent_num_bytes == 0 ||
- extent_num_bytes != item_inline_len)
+ compressed = btrfs_file_extent_compression(node, fi);
+ if (extent_num_bytes == 0) {
+ error(
+ "root %llu EXTENT_DATA[%llu %llu] has empty inline extent",
+ root->objectid, fkey->objectid, fkey->offset);
+ err |= FILE_EXTENT_ERROR;
+ }
+ if (!compressed && extent_num_bytes != item_inline_len) {
+ error(
+ "root %llu EXTENT_DATA[%llu %llu] wrong inline size, have: %llu, expected: %u",
+ root->objectid, fkey->objectid, fkey->offset,
+ extent_num_bytes, item_inline_len);
err |= FILE_EXTENT_ERROR;
+ }
+ *end += extent_num_bytes;
*size += extent_num_bytes;
return err;
}
disk_bytenr = btrfs_file_extent_disk_bytenr(node, fi);
disk_num_bytes = btrfs_file_extent_disk_num_bytes(node, fi);
extent_num_bytes = btrfs_file_extent_num_bytes(node, fi);
+ extent_offset = btrfs_file_extent_offset(node, fi);
+ compressed = btrfs_file_extent_compression(node, fi);
is_hole = (disk_bytenr == 0) && (disk_num_bytes == 0);
- /* Check EXTENT_DATA datasum */
- ret = count_csum_range(root, disk_bytenr, disk_num_bytes, &found);
- if (found > 0 && nodatasum) {
+ /*
+ * Check EXTENT_DATA csum
+ *
+ * For plain (uncompressed) extent, we should only check the range
+ * we're referring to, as it's possible that part of prealloc extent
+ * has been written, and has csum:
+ *
+ * |<--- Original large preallocated extent A ---->|
+ * |<- Prealloc File Extent ->|<- Regular Extent ->|
+ * No csum Has csum
+ *
+ * For compressed extent, we should check the whole range.
+ */
+ if (!compressed) {
+ search_start = disk_bytenr + extent_offset;
+ search_len = extent_num_bytes;
+ } else {
+ search_start = disk_bytenr;
+ search_len = disk_num_bytes;
+ }
+ ret = count_csum_range(root, search_start, search_len, &csum_found);
+ if (csum_found > 0 && nodatasum) {
err |= ODD_CSUM_ITEM;
error("root %llu EXTENT_DATA[%llu %llu] nodatasum shouldn't have datasum",
root->objectid, fkey->objectid, fkey->offset);
} else if (extent_type == BTRFS_FILE_EXTENT_REG && !nodatasum &&
- !is_hole &&
- (ret < 0 || found == 0 || found < disk_num_bytes)) {
+ !is_hole && (ret < 0 || csum_found < search_len)) {
err |= CSUM_ITEM_MISSING;
- error("root %llu EXTENT_DATA[%llu %llu] datasum missing",
- root->objectid, fkey->objectid, fkey->offset);
- } else if (extent_type == BTRFS_FILE_EXTENT_PREALLOC && found > 0) {
+ error("root %llu EXTENT_DATA[%llu %llu] csum missing, have: %llu, expected: %llu",
+ root->objectid, fkey->objectid, fkey->offset,
+ csum_found, search_len);
+ } else if (extent_type == BTRFS_FILE_EXTENT_PREALLOC && csum_found > 0) {
err |= ODD_CSUM_ITEM;
- error("root %llu EXTENT_DATA[%llu %llu] prealloc shouldn't have datasum",
- root->objectid, fkey->objectid, fkey->offset);
+ error("root %llu EXTENT_DATA[%llu %llu] prealloc shouldn't have csum, but has: %llu",
+ root->objectid, fkey->objectid, fkey->offset, csum_found);
+ }
+
+ /* Check EXTENT_DATA hole */
+ if (!no_holes && *end != fkey->offset) {
+ if (repair)
+ ret = punch_extent_hole(root, fkey->objectid,
+ *end, fkey->offset - *end);
+ if (!repair || ret) {
+ err |= FILE_EXTENT_ERROR;
+ error(
+ "root %llu EXTENT_DATA[%llu %llu] interrupt, should start at %llu",
+ root->objectid, fkey->objectid, fkey->offset, *end);
+ }
+ }
+
+ *end += extent_num_bytes;
+ if (!is_hole)
+ *size += extent_num_bytes;
+
+ return err;
+}
+
+/*
+ * Set inode item nbytes to @nbytes
+ *
+ * Returns 0 on success
+ * Returns != 0 on error
+ */
+static int repair_inode_nbytes_lowmem(struct btrfs_root *root,
+ struct btrfs_path *path,
+ u64 ino, u64 nbytes)
+{
+ struct btrfs_trans_handle *trans;
+ struct btrfs_inode_item *ii;
+ struct btrfs_key key;
+ struct btrfs_key research_key;
+ int err = 0;
+ int ret;
+
+ btrfs_item_key_to_cpu(path->nodes[0], &research_key, path->slots[0]);
+
+ key.objectid = ino;
+ key.type = BTRFS_INODE_ITEM_KEY;
+ key.offset = 0;
+
+ trans = btrfs_start_transaction(root, 1);
+ if (IS_ERR(trans)) {
+ ret = PTR_ERR(trans);
+ err |= ret;
+ goto out;
+ }
+
+ btrfs_release_path(path);
+ ret = btrfs_search_slot(trans, root, &key, path, 0, 1);
+ if (ret > 0)
+ ret = -ENOENT;
+ if (ret) {
+ err |= ret;
+ goto fail;
+ }
+
+ ii = btrfs_item_ptr(path->nodes[0], path->slots[0],
+ struct btrfs_inode_item);
+ btrfs_set_inode_nbytes(path->nodes[0], ii, nbytes);
+ btrfs_mark_buffer_dirty(path->nodes[0]);
+fail:
+ btrfs_commit_transaction(trans, root);
+out:
+ if (ret)
+ error("failed to set nbytes in inode %llu root %llu",
+ ino, root->root_key.objectid);
+ else
+ printf("Set nbytes in inode item %llu root %llu\n to %llu", ino,
+ root->root_key.objectid, nbytes);
+
+ /* research path */
+ btrfs_release_path(path);
+ ret = btrfs_search_slot(NULL, root, &research_key, path, 0, 0);
+ err |= ret;
+
+ return err;
+}
+
+/*
+ * Set directory inode isize to @isize.
+ *
+ * Returns 0 on success.
+ * Returns != 0 on error.
+ */
+static int repair_dir_isize_lowmem(struct btrfs_root *root,
+ struct btrfs_path *path,
+ u64 ino, u64 isize)
+{
+ struct btrfs_trans_handle *trans;
+ struct btrfs_inode_item *ii;
+ struct btrfs_key key;
+ struct btrfs_key research_key;
+ int ret;
+ int err = 0;
+
+ btrfs_item_key_to_cpu(path->nodes[0], &research_key, path->slots[0]);
+
+ key.objectid = ino;
+ key.type = BTRFS_INODE_ITEM_KEY;
+ key.offset = 0;
+
+ trans = btrfs_start_transaction(root, 1);
+ if (IS_ERR(trans)) {
+ ret = PTR_ERR(trans);
+ err |= ret;
+ goto out;
+ }
+
+ btrfs_release_path(path);
+ ret = btrfs_search_slot(trans, root, &key, path, 0, 1);
+ if (ret > 0)
+ ret = -ENOENT;
+ if (ret) {
+ err |= ret;
+ goto fail;
+ }
+
+ ii = btrfs_item_ptr(path->nodes[0], path->slots[0],
+ struct btrfs_inode_item);
+ btrfs_set_inode_size(path->nodes[0], ii, isize);
+ btrfs_mark_buffer_dirty(path->nodes[0]);
+fail:
+ btrfs_commit_transaction(trans, root);
+out:
+ if (ret)
+ error("failed to set isize in inode %llu root %llu",
+ ino, root->root_key.objectid);
+ else
+ printf("Set isize in inode %llu root %llu to %llu\n",
+ ino, root->root_key.objectid, isize);
+
+ btrfs_release_path(path);
+ ret = btrfs_search_slot(NULL, root, &research_key, path, 0, 0);
+ err |= ret;
+
+ return err;
+}
+
+/*
+ * Wrapper function for btrfs_add_orphan_item().
+ *
+ * Returns 0 on success.
+ * Returns != 0 on error.
+ */
+static int repair_inode_orphan_item_lowmem(struct btrfs_root *root,
+ struct btrfs_path *path, u64 ino)
+{
+ struct btrfs_trans_handle *trans;
+ struct btrfs_key research_key;
+ int ret;
+ int err = 0;
+
+ btrfs_item_key_to_cpu(path->nodes[0], &research_key, path->slots[0]);
+
+ trans = btrfs_start_transaction(root, 1);
+ if (IS_ERR(trans)) {
+ ret = PTR_ERR(trans);
+ err |= ret;
+ goto out;
+ }
+
+ btrfs_release_path(path);
+ ret = btrfs_add_orphan_item(trans, root, path, ino);
+ err |= ret;
+ btrfs_commit_transaction(trans, root);
+out:
+ if (ret)
+ error("failed to add inode %llu as orphan item root %llu",
+ ino, root->root_key.objectid);
+ else
+ printf("Added inode %llu as orphan item root %llu\n",
+ ino, root->root_key.objectid);
+
+ btrfs_release_path(path);
+ ret = btrfs_search_slot(NULL, root, &research_key, path, 0, 0);
+ err |= ret;
+
+ return err;
+}
+
+/* Set inode_item nlink to @ref_count.
+ * If @ref_count == 0, move it to "lost+found" and increase @ref_count.
+ *
+ * Returns 0 on success
+ */
+static int repair_inode_nlinks_lowmem(struct btrfs_root *root,
+ struct btrfs_path *path, u64 ino,
+ const char *name, u32 namelen,
+ u64 ref_count, u8 filetype, u64 *nlink)
+{
+ struct btrfs_trans_handle *trans;
+ struct btrfs_inode_item *ii;
+ struct btrfs_key key;
+ struct btrfs_key old_key;
+ char namebuf[BTRFS_NAME_LEN] = {0};
+ int name_len;
+ int ret;
+ int ret2;
+
+ /* save the key */
+ btrfs_item_key_to_cpu(path->nodes[0], &old_key, path->slots[0]);
+
+ if (name && namelen) {
+ ASSERT(namelen <= BTRFS_NAME_LEN);
+ memcpy(namebuf, name, namelen);
+ name_len = namelen;
+ } else {
+ sprintf(namebuf, "%llu", ino);
+ name_len = count_digits(ino);
+ printf("Can't find file name for inode %llu, use %s instead\n",
+ ino, namebuf);
+ }
+
+ trans = btrfs_start_transaction(root, 1);
+ if (IS_ERR(trans)) {
+ ret = PTR_ERR(trans);
+ goto out;
+ }
+
+ btrfs_release_path(path);
+ /* if refs is 0, put it into lostfound */
+ if (ref_count == 0) {
+ ret = link_inode_to_lostfound(trans, root, path, ino, namebuf,
+ name_len, filetype, &ref_count);
+ if (ret)
+ goto fail;
}
- /* Check EXTENT_DATA hole */
- if (no_holes && is_hole) {
- err |= FILE_EXTENT_ERROR;
- error("root %llu EXTENT_DATA[%llu %llu] shouldn't be hole",
- root->objectid, fkey->objectid, fkey->offset);
- } else if (!no_holes && *end != fkey->offset) {
- err |= FILE_EXTENT_ERROR;
- error("root %llu EXTENT_DATA[%llu %llu] interrupt",
- root->objectid, fkey->objectid, fkey->offset);
- }
+ /* reset inode_item's nlink to ref_count */
+ key.objectid = ino;
+ key.type = BTRFS_INODE_ITEM_KEY;
+ key.offset = 0;
+
+ btrfs_release_path(path);
+ ret = btrfs_search_slot(trans, root, &key, path, 0, 1);
+ if (ret > 0)
+ ret = -ENOENT;
+ if (ret)
+ goto fail;
+
+ ii = btrfs_item_ptr(path->nodes[0], path->slots[0],
+ struct btrfs_inode_item);
+ btrfs_set_inode_nlink(path->nodes[0], ii, ref_count);
+ btrfs_mark_buffer_dirty(path->nodes[0]);
- *end += extent_num_bytes;
- if (!is_hole)
- *size += extent_num_bytes;
+ if (nlink)
+ *nlink = ref_count;
+fail:
+ btrfs_commit_transaction(trans, root);
+out:
+ if (ret)
+ error(
+ "fail to repair nlink of inode %llu root %llu name %s filetype %u",
+ root->objectid, ino, namebuf, filetype);
+ else
+ printf("Fixed nlink of inode %llu root %llu name %s filetype %u\n",
+ root->objectid, ino, namebuf, filetype);
- return err;
+ /* research */
+ btrfs_release_path(path);
+ ret2 = btrfs_search_slot(NULL, root, &old_key, path, 0, 0);
+ if (ret2 < 0)
+ return ret |= ret2;
+ return ret;
}
/*
struct extent_buffer *node;
struct btrfs_inode_item *ii;
struct btrfs_key key;
+ struct btrfs_key last_key;
u64 inode_id;
u32 mode;
u64 nlink;
int slot;
int ret;
int err = 0;
+ char namebuf[BTRFS_NAME_LEN] = {0};
+ u32 name_len = 0;
node = path->nodes[0];
slot = path->slots[0];
nodatasum = btrfs_inode_flags(node, ii) & BTRFS_INODE_NODATASUM;
while (1) {
+ btrfs_item_key_to_cpu(path->nodes[0], &last_key, path->slots[0]);
ret = btrfs_next_item(root, path);
if (ret < 0) {
/* out will fill 'err' rusing current statistics */
switch (key.type) {
case BTRFS_INODE_REF_KEY:
- ret = check_inode_ref(root, &key, node, slot, &refs,
- mode);
+ ret = check_inode_ref(root, &key, path, namebuf,
+ &name_len, &refs, mode);
err |= ret;
break;
case BTRFS_INODE_EXTREF_KEY:
imode_to_type(mode), key.objectid,
key.offset);
}
- ret = check_dir_item(root, &key, node, slot, &size,
- ext_ref);
+ ret = check_dir_item(root, &key, path, &size, ext_ref);
err |= ret;
break;
case BTRFS_EXTENT_DATA_KEY:
}
out:
+ if (err & LAST_ITEM) {
+ btrfs_release_path(path);
+ ret = btrfs_search_slot(NULL, root, &last_key, path, 0, 0);
+ if (ret)
+ return err;
+ }
+
/* verify INODE_ITEM nlink/isize/nbytes */
if (dir) {
+ if (repair && (err & DIR_COUNT_AGAIN)) {
+ err &= ~DIR_COUNT_AGAIN;
+ count_dir_isize(root, inode_id, &size);
+ }
+
+ if ((nlink != 1 || refs != 1) && repair) {
+ ret = repair_inode_nlinks_lowmem(root, path, inode_id,
+ namebuf, name_len, refs, imode_to_type(mode),
+ &nlink);
+ }
+
if (nlink != 1) {
err |= LINK_COUNT_ERROR;
error("root %llu DIR INODE[%llu] shouldn't have more than one link(%llu)",
* Just a warning, as dir inode nbytes is just an
* instructive value.
*/
- if (!IS_ALIGNED(nbytes, root->nodesize)) {
+ if (!IS_ALIGNED(nbytes, root->fs_info->nodesize)) {
warning("root %llu DIR INODE[%llu] nbytes should be aligned to %u",
- root->objectid, inode_id, root->nodesize);
+ root->objectid, inode_id,
+ root->fs_info->nodesize);
}
if (isize != size) {
- err |= ISIZE_ERROR;
- error("root %llu DIR INODE [%llu] size(%llu) not equal to %llu",
- root->objectid, inode_id, isize, size);
+ if (repair)
+ ret = repair_dir_isize_lowmem(root, path,
+ inode_id, size);
+ if (!repair || ret) {
+ err |= ISIZE_ERROR;
+ error(
+ "root %llu DIR INODE [%llu] size %llu not equal to %llu",
+ root->objectid, inode_id, isize, size);
+ }
}
} else {
if (nlink != refs) {
- err |= LINK_COUNT_ERROR;
- error("root %llu INODE[%llu] nlink(%llu) not equal to inode_refs(%llu)",
- root->objectid, inode_id, nlink, refs);
+ if (repair)
+ ret = repair_inode_nlinks_lowmem(root, path,
+ inode_id, namebuf, name_len, refs,
+ imode_to_type(mode), &nlink);
+ if (!repair || ret) {
+ err |= LINK_COUNT_ERROR;
+ error(
+ "root %llu INODE[%llu] nlink(%llu) not equal to inode_refs(%llu)",
+ root->objectid, inode_id, nlink, refs);
+ }
} else if (!nlink) {
- err |= ORPHAN_ITEM;
+ if (repair)
+ ret = repair_inode_orphan_item_lowmem(root,
+ path, inode_id);
+ if (!repair || ret) {
+ err |= ORPHAN_ITEM;
+ error("root %llu INODE[%llu] is orphan item",
+ root->objectid, inode_id);
+ }
}
if (!nbytes && !no_holes && extent_end < isize) {
- err |= NBYTES_ERROR;
- error("root %llu INODE[%llu] size (%llu) should have a file extent hole",
- root->objectid, inode_id, isize);
+ if (repair)
+ ret = punch_extent_hole(root, inode_id,
+ extent_end, isize - extent_end);
+ if (!repair || ret) {
+ err |= NBYTES_ERROR;
+ error(
+ "root %llu INODE[%llu] size %llu should have a file extent hole",
+ root->objectid, inode_id, isize);
+ }
}
if (nbytes != extent_size) {
- err |= NBYTES_ERROR;
- error("root %llu INODE[%llu] nbytes(%llu) not equal to extent_size(%llu)",
- root->objectid, inode_id, nbytes, extent_size);
+ if (repair)
+ ret = repair_inode_nbytes_lowmem(root, path,
+ inode_id, extent_size);
+ if (!repair || ret) {
+ err |= NBYTES_ERROR;
+ error(
+ "root %llu INODE[%llu] nbytes %llu not equal to extent_size %llu",
+ root->objectid, inode_id, nbytes,
+ extent_size);
+ }
}
}
+ if (err & LAST_ITEM)
+ btrfs_next_item(root, path);
return err;
}
/*
- * Iterate all item on the tree and call check_inode_item() to check.
+ * Insert the missing inode item and inode ref.
*
- * @root: the root of the tree to be checked.
- * @ext_ref: the EXTENDED_IREF feature
+ * Normal INODE_ITEM_MISSING and INODE_REF_MISSING are handled in backref * dir.
+ * Root dir should be handled specially because root dir is the root of fs.
*
- * Return 0 if no error found.
- * Return <0 for error.
- * All internal error bitmap will be converted to -EIO, to avoid
- * mixing negative and postive return value.
+ * returns err (>0 or 0) after repair
*/
-static int check_fs_root_v2(struct btrfs_root *root, unsigned int ext_ref)
+static int repair_fs_first_inode(struct btrfs_root *root, int err)
{
- struct btrfs_path *path;
+ struct btrfs_trans_handle *trans;
struct btrfs_key key;
- u64 inode_id;
- int ret, err = 0;
+ struct btrfs_path path;
+ int filetype = BTRFS_FT_DIR;
+ int ret = 0;
- path = btrfs_alloc_path();
- if (!path)
- return -ENOMEM;
+ btrfs_init_path(&path);
- key.objectid = 0;
- key.type = 0;
+ if (err & INODE_REF_MISSING) {
+ key.objectid = BTRFS_FIRST_FREE_OBJECTID;
+ key.type = BTRFS_INODE_REF_KEY;
+ key.offset = BTRFS_FIRST_FREE_OBJECTID;
+
+ trans = btrfs_start_transaction(root, 1);
+ if (IS_ERR(trans)) {
+ ret = PTR_ERR(trans);
+ goto out;
+ }
+
+ btrfs_release_path(&path);
+ ret = btrfs_search_slot(trans, root, &key, &path, 1, 1);
+ if (ret)
+ goto trans_fail;
+
+ ret = btrfs_insert_inode_ref(trans, root, "..", 2,
+ BTRFS_FIRST_FREE_OBJECTID,
+ BTRFS_FIRST_FREE_OBJECTID, 0);
+ if (ret)
+ goto trans_fail;
+
+ printf("Add INODE_REF[%llu %llu] name %s\n",
+ BTRFS_FIRST_FREE_OBJECTID, BTRFS_FIRST_FREE_OBJECTID,
+ "..");
+ err &= ~INODE_REF_MISSING;
+trans_fail:
+ if (ret)
+ error("fail to insert first inode's ref");
+ btrfs_commit_transaction(trans, root);
+ }
+
+ if (err & INODE_ITEM_MISSING) {
+ ret = repair_inode_item_missing(root,
+ BTRFS_FIRST_FREE_OBJECTID, filetype);
+ if (ret)
+ goto out;
+ err &= ~INODE_ITEM_MISSING;
+ }
+out:
+ if (ret)
+ error("fail to repair first inode");
+ btrfs_release_path(&path);
+ return err;
+}
+
+/*
+ * check first root dir's inode_item and inode_ref
+ *
+ * returns 0 means no error
+ * returns >0 means error
+ * returns <0 means fatal error
+ */
+static int check_fs_first_inode(struct btrfs_root *root, unsigned int ext_ref)
+{
+ struct btrfs_path path;
+ struct btrfs_key key;
+ struct btrfs_inode_item *ii;
+ u64 index;
+ u32 mode;
+ int err = 0;
+ int ret;
+
+ key.objectid = BTRFS_FIRST_FREE_OBJECTID;
+ key.type = BTRFS_INODE_ITEM_KEY;
key.offset = 0;
- ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
+ /* For root being dropped, we don't need to check first inode */
+ if (btrfs_root_refs(&root->root_item) == 0 &&
+ btrfs_disk_key_objectid(&root->root_item.drop_progress) >=
+ BTRFS_FIRST_FREE_OBJECTID)
+ return 0;
+
+ btrfs_init_path(&path);
+ ret = btrfs_search_slot(NULL, root, &key, &path, 0, 0);
if (ret < 0)
goto out;
+ if (ret > 0) {
+ ret = 0;
+ err |= INODE_ITEM_MISSING;
+ } else {
+ ii = btrfs_item_ptr(path.nodes[0], path.slots[0],
+ struct btrfs_inode_item);
+ mode = btrfs_inode_mode(path.nodes[0], ii);
+ if (imode_to_type(mode) != BTRFS_FT_DIR)
+ err |= INODE_ITEM_MISMATCH;
+ }
- while (1) {
- btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
+ /* lookup first inode ref */
+ key.offset = BTRFS_FIRST_FREE_OBJECTID;
+ key.type = BTRFS_INODE_REF_KEY;
+ /* special index value */
+ index = 0;
- /*
- * All check must start with inode item, skip if not
- */
- if (key.type == BTRFS_INODE_ITEM_KEY) {
- ret = check_inode_item(root, path, ext_ref);
- err |= ret;
- if (err & LAST_ITEM)
- goto out;
- continue;
- }
- error("root %llu ITEM[%llu %u %llu] isn't INODE_ITEM, skip to next inode",
- root->objectid, key.objectid, key.type,
- key.offset);
+ ret = find_inode_ref(root, &key, "..", strlen(".."), &index, ext_ref);
+ if (ret < 0)
+ goto out;
+ err |= ret;
+
+out:
+ btrfs_release_path(&path);
+
+ if (err && repair)
+ err = repair_fs_first_inode(root, err);
+
+ if (err & (INODE_ITEM_MISSING | INODE_ITEM_MISMATCH))
+ error("root dir INODE_ITEM is %s",
+ err & INODE_ITEM_MISMATCH ? "mismatch" : "missing");
+ if (err & INODE_REF_MISSING)
+ error("root dir INODE_REF is missing");
+
+ return ret < 0 ? ret : err;
+}
+
+static struct tree_backref *find_tree_backref(struct extent_record *rec,
+ u64 parent, u64 root)
+{
+ struct rb_node *node;
+ struct tree_backref *back = NULL;
+ struct tree_backref match = {
+ .node = {
+ .is_data = 0,
+ },
+ };
+
+ if (parent) {
+ match.parent = parent;
+ match.node.full_backref = 1;
+ } else {
+ match.root = root;
+ }
+
+ node = rb_search(&rec->backref_tree, &match.node.node,
+ (rb_compare_keys)compare_extent_backref, NULL);
+ if (node)
+ back = to_tree_backref(rb_node_to_extent_backref(node));
+
+ return back;
+}
+
+static struct data_backref *find_data_backref(struct extent_record *rec,
+ u64 parent, u64 root,
+ u64 owner, u64 offset,
+ int found_ref,
+ u64 disk_bytenr, u64 bytes)
+{
+ struct rb_node *node;
+ struct data_backref *back = NULL;
+ struct data_backref match = {
+ .node = {
+ .is_data = 1,
+ },
+ .owner = owner,
+ .offset = offset,
+ .bytes = bytes,
+ .found_ref = found_ref,
+ .disk_bytenr = disk_bytenr,
+ };
+
+ if (parent) {
+ match.parent = parent;
+ match.node.full_backref = 1;
+ } else {
+ match.root = root;
+ }
+
+ node = rb_search(&rec->backref_tree, &match.node.node,
+ (rb_compare_keys)compare_extent_backref, NULL);
+ if (node)
+ back = to_data_backref(rb_node_to_extent_backref(node));
+
+ return back;
+}
+/*
+ * This function calls walk_down_tree_v2 and walk_up_tree_v2 to check tree
+ * blocks and integrity of fs tree items.
+ *
+ * @root: the root of the tree to be checked.
+ * @ext_ref feature EXTENDED_IREF is enable or not.
+ * @account if NOT 0 means check the tree (including tree)'s treeblocks.
+ * otherwise means check fs tree(s) items relationship and
+ * @root MUST be a fs tree root.
+ * Returns 0 represents OK.
+ * Returns not 0 represents error.
+ */
+static int check_btrfs_root(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root, unsigned int ext_ref,
+ int check_all)
- err |= NO_INODE_ITEM;
- inode_id = key.objectid;
+{
+ struct btrfs_path path;
+ struct node_refs nrefs;
+ struct btrfs_root_item *root_item = &root->root_item;
+ int ret;
+ int level;
+ int err = 0;
+ memset(&nrefs, 0, sizeof(nrefs));
+ if (!check_all) {
/*
- * skip to next inode
- * TODO: Maybe search_slot() will be faster?
+ * We need to manually check the first inode item (256)
+ * As the following traversal function will only start from
+ * the first inode item in the leaf, if inode item (256) is
+ * missing we will skip it forever.
*/
- do {
- ret = btrfs_next_item(root, path);
- if (ret > 0) {
- goto out;
- } else if (ret < 0) {
- err = ret;
- goto out;
- }
- btrfs_item_key_to_cpu(path->nodes[0], &key,
- path->slots[0]);
- } while (inode_id == key.objectid);
+ ret = check_fs_first_inode(root, ext_ref);
+ if (ret < 0)
+ return ret;
+ }
+
+
+ level = btrfs_header_level(root->node);
+ btrfs_init_path(&path);
+
+ if (btrfs_root_refs(root_item) > 0 ||
+ btrfs_disk_key_objectid(&root_item->drop_progress) == 0) {
+ path.nodes[level] = root->node;
+ path.slots[level] = 0;
+ extent_buffer_get(root->node);
+ } else {
+ struct btrfs_key key;
+
+ btrfs_disk_key_to_cpu(&key, &root_item->drop_progress);
+ level = root_item->drop_level;
+ path.lowest_level = level;
+ ret = btrfs_search_slot(NULL, root, &key, &path, 0, 0);
+ if (ret < 0)
+ goto out;
+ ret = 0;
+ }
+
+ while (1) {
+ ret = walk_down_tree_v2(trans, root, &path, &level, &nrefs,
+ ext_ref, check_all);
+
+ err |= !!ret;
+
+ /* if ret is negative, walk shall stop */
+ if (ret < 0) {
+ ret = err;
+ break;
+ }
+
+ ret = walk_up_tree_v2(root, &path, &level);
+ if (ret != 0) {
+ /* Normal exit, reset ret to err */
+ ret = err;
+ break;
+ }
}
out:
- err &= ~LAST_ITEM;
- if (err && !ret)
- ret = -EIO;
- btrfs_free_path(path);
+ btrfs_release_path(&path);
return ret;
}
+static int pin_metadata_blocks(struct btrfs_fs_info *fs_info);
+
+/*
+ * Iterate all items in the tree and call check_inode_item() to check.
+ *
+ * @root: the root of the tree to be checked.
+ * @ext_ref: the EXTENDED_IREF feature
+ *
+ * Return 0 if no error found.
+ * Return <0 for error.
+ */
+static int check_fs_root_v2(struct btrfs_root *root, unsigned int ext_ref)
+{
+ reset_cached_block_groups(root->fs_info);
+ return check_btrfs_root(NULL, root, ext_ref, 0);
+}
+
/*
* Find the relative ref for root_ref and root_backref.
*
static int check_root_ref(struct btrfs_root *root, struct btrfs_key *ref_key,
struct extent_buffer *node, int slot)
{
- struct btrfs_path *path;
+ struct btrfs_path path;
struct btrfs_key key;
struct btrfs_root_ref *ref;
struct btrfs_root_ref *backref;
key.type = BTRFS_ROOT_BACKREF_KEY + BTRFS_ROOT_REF_KEY - ref_key->type;
key.offset = ref_key->objectid;
- path = btrfs_alloc_path();
- ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
+ btrfs_init_path(&path);
+ ret = btrfs_search_slot(NULL, root, &key, &path, 0, 0);
if (ret) {
err |= ROOT_REF_MISSING;
error("%s[%llu %llu] couldn't find relative ref",
goto out;
}
- backref = btrfs_item_ptr(path->nodes[0], path->slots[0],
+ backref = btrfs_item_ptr(path.nodes[0], path.slots[0],
struct btrfs_root_ref);
- backref_dirid = btrfs_root_ref_dirid(path->nodes[0], backref);
- backref_seq = btrfs_root_ref_sequence(path->nodes[0], backref);
- backref_namelen = btrfs_root_ref_name_len(path->nodes[0], backref);
+ backref_dirid = btrfs_root_ref_dirid(path.nodes[0], backref);
+ backref_seq = btrfs_root_ref_sequence(path.nodes[0], backref);
+ backref_namelen = btrfs_root_ref_name_len(path.nodes[0], backref);
if (backref_namelen <= BTRFS_NAME_LEN) {
len = backref_namelen;
"ROOT_REF" : "ROOT_BACKREF",
key.objectid, key.offset);
}
- read_extent_buffer(path->nodes[0], backref_name,
+ read_extent_buffer(path.nodes[0], backref_name,
(unsigned long)(backref + 1), len);
if (ref_dirid != backref_dirid || ref_seq != backref_seq ||
ref_key->objectid, ref_key->offset);
}
out:
- btrfs_free_path(path);
+ btrfs_release_path(&path);
return err;
}
{
struct btrfs_root *tree_root = fs_info->tree_root;
struct btrfs_root *cur_root = NULL;
- struct btrfs_path *path;
+ struct btrfs_path path;
struct btrfs_key key;
struct extent_buffer *node;
unsigned int ext_ref;
int ret;
int err = 0;
- ext_ref = btrfs_fs_incompat(fs_info,
- BTRFS_FEATURE_INCOMPAT_EXTENDED_IREF);
-
- path = btrfs_alloc_path();
- if (!path)
- return -ENOMEM;
+ ext_ref = btrfs_fs_incompat(fs_info, EXTENDED_IREF);
+ 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) {
err = ret;
goto out;
}
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;
err |= ret;
}
next:
- ret = btrfs_next_item(tree_root, path);
+ ret = btrfs_next_item(tree_root, &path);
if (ret > 0)
goto out;
if (ret < 0) {
}
out:
- btrfs_free_path(path);
+ btrfs_release_path(&path);
return err;
}
+static int do_check_fs_roots(struct btrfs_fs_info *fs_info,
+ struct cache_tree *root_cache)
+{
+ int ret;
+
+ if (!ctx.progress_enabled)
+ fprintf(stderr, "checking fs roots\n");
+ if (check_mode == CHECK_MODE_LOWMEM)
+ ret = check_fs_roots_v2(fs_info);
+ else
+ ret = check_fs_roots(fs_info, root_cache);
+
+ return ret;
+}
+
static int all_backpointers_checked(struct extent_record *rec, int print_errs)
{
- struct list_head *cur = rec->backrefs.next;
- struct extent_backref *back;
+ struct extent_backref *back, *tmp;
struct tree_backref *tback;
struct data_backref *dback;
u64 found = 0;
int err = 0;
- while(cur != &rec->backrefs) {
- back = to_extent_backref(cur);
- cur = cur->next;
+ rbtree_postorder_for_each_entry_safe(back, tmp,
+ &rec->backref_tree, node) {
if (!back->found_extent_tree) {
err = 1;
if (!print_errs)
goto out;
if (back->is_data) {
dback = to_data_backref(back);
- fprintf(stderr, "Backref %llu %s %llu"
+ fprintf(stderr, "Data backref %llu %s %llu"
" owner %llu offset %llu num_refs %lu"
" not found in extent tree\n",
(unsigned long long)rec->start,
(unsigned long)dback->num_refs);
} else {
tback = to_tree_backref(back);
- fprintf(stderr, "Backref %llu parent %llu"
+ fprintf(stderr, "Tree backref %llu parent %llu"
" root %llu not found in extent tree\n",
(unsigned long long)rec->start,
(unsigned long long)tback->parent,
return err;
}
-static int free_all_extent_backrefs(struct extent_record *rec)
+static void __free_one_backref(struct rb_node *node)
{
- struct extent_backref *back;
- struct list_head *cur;
- while (!list_empty(&rec->backrefs)) {
- cur = rec->backrefs.next;
- back = to_extent_backref(cur);
- list_del(cur);
- free(back);
- }
- return 0;
+ struct extent_backref *back = rb_node_to_extent_backref(node);
+
+ free(back);
+}
+
+static void free_all_extent_backrefs(struct extent_record *rec)
+{
+ rb_free_nodes(&rec->backref_tree, __free_one_backref);
}
-static void free_extent_record_cache(struct btrfs_fs_info *fs_info,
- struct cache_tree *extent_cache)
+static void free_extent_record_cache(struct cache_tree *extent_cache)
{
struct cache_extent *cache;
struct extent_record *rec;
struct extent_record *rec,
struct extent_buffer *buf)
{
- struct extent_backref *node;
+ struct extent_backref *node, *tmp;
struct tree_backref *back;
struct btrfs_root *ref_root;
struct btrfs_key key;
int found = 0;
int ret;
- list_for_each_entry(node, &rec->backrefs, list) {
+ rbtree_postorder_for_each_entry_safe(node, tmp,
+ &rec->backref_tree, node) {
if (node->is_data)
continue;
if (!node->found_ref)
static int is_extent_tree_record(struct extent_record *rec)
{
- struct list_head *cur = rec->backrefs.next;
- struct extent_backref *node;
+ struct extent_backref *node, *tmp;
struct tree_backref *back;
int is_extent = 0;
- while(cur != &rec->backrefs) {
- node = to_extent_backref(cur);
- cur = cur->next;
+ rbtree_postorder_for_each_entry_safe(node, tmp,
+ &rec->backref_tree, node) {
if (node->is_data)
return 0;
back = to_tree_backref(node);
return 0;
}
-static int fix_key_order(struct btrfs_trans_handle *trans,
- struct btrfs_root *root,
- struct btrfs_path *path)
+static int fix_key_order(struct btrfs_root *root, struct btrfs_path *path)
{
struct extent_buffer *buf;
struct btrfs_key k1, k2;
return ret;
}
-static int delete_bogus_item(struct btrfs_trans_handle *trans,
- struct btrfs_root *root,
+static int delete_bogus_item(struct btrfs_root *root,
struct btrfs_path *path,
struct extent_buffer *buf, int slot)
{
return 0;
}
-static int fix_item_offset(struct btrfs_trans_handle *trans,
- struct btrfs_root *root,
- struct btrfs_path *path)
+static int fix_item_offset(struct btrfs_root *root, struct btrfs_path *path)
{
struct extent_buffer *buf;
int i;
BTRFS_LEAF_DATA_SIZE(root)) {
if (btrfs_item_end_nr(buf, i) >
BTRFS_LEAF_DATA_SIZE(root)) {
- ret = delete_bogus_item(trans, root, path,
- buf, i);
+ ret = delete_bogus_item(root, path, buf, i);
if (!ret)
goto again;
fprintf(stderr, "item is off the end of the "
btrfs_item_offset_nr(buf, i - 1)) {
if (btrfs_item_end_nr(buf, i) >
btrfs_item_offset_nr(buf, i - 1)) {
- ret = delete_bogus_item(trans, root, path,
- buf, i);
+ ret = delete_bogus_item(root, path, buf, i);
if (!ret)
goto again;
fprintf(stderr, "items overlap, can't fix\n");
break;
}
if (status == BTRFS_TREE_BLOCK_BAD_KEY_ORDER)
- ret = fix_key_order(trans, search_root, &path);
+ ret = fix_key_order(search_root, &path);
else if (status == BTRFS_TREE_BLOCK_INVALID_OFFSETS)
- ret = fix_item_offset(trans, search_root, &path);
+ ret = fix_item_offset(search_root, &path);
if (ret) {
btrfs_commit_transaction(trans, search_root);
break;
return ret;
}
+#if 0
static struct tree_backref *find_tree_backref(struct extent_record *rec,
u64 parent, u64 root)
{
}
return NULL;
}
+#endif
static struct tree_backref *alloc_tree_backref(struct extent_record *rec,
u64 parent, u64 root)
ref->root = root;
ref->node.full_backref = 0;
}
- list_add_tail(&ref->node.list, &rec->backrefs);
return ref;
}
+#if 0
static struct data_backref *find_data_backref(struct extent_record *rec,
u64 parent, u64 root,
u64 owner, u64 offset,
}
return NULL;
}
+#endif
static struct data_backref *alloc_data_backref(struct extent_record *rec,
u64 parent, u64 root,
ref->bytes = max_size;
ref->found_ref = 0;
ref->num_refs = 0;
- list_add_tail(&ref->node.list, &rec->backrefs);
if (max_size > rec->max_size)
rec->max_size = max_size;
return ref;
* Check SYSTEM extent, as it's also marked as metadata, we can only
* make sure it's a SYSTEM extent by its backref
*/
- if (!list_empty(&rec->backrefs)) {
+ if (!RB_EMPTY_ROOT(&rec->backref_tree)) {
struct extent_backref *node;
struct tree_backref *tback;
u64 bg_type;
- node = to_extent_backref(rec->backrefs.next);
+ node = rb_node_to_extent_backref(rb_first(&rec->backref_tree));
if (node->is_data) {
/* tree block shouldn't have data backref */
rec->wrong_chunk_type = 1;
struct extent_record *rec;
int ret = 0;
+ BUG_ON(tmpl->max_size == 0);
rec = malloc(sizeof(*rec));
if (!rec)
return -ENOMEM;
INIT_LIST_HEAD(&rec->backrefs);
INIT_LIST_HEAD(&rec->dups);
INIT_LIST_HEAD(&rec->list);
+ rec->backref_tree = RB_ROOT;
memcpy(&rec->parent_key, &tmpl->parent_key, sizeof(tmpl->parent_key));
rec->cache.start = tmpl->start;
rec->cache.size = tmpl->nr;
if (tmpl->metadata)
rec->crossing_stripes = check_crossing_stripes(global_info,
- rec->start, global_info->tree_root->nodesize);
+ rec->start, global_info->nodesize);
check_extent_type(rec);
return ret;
}
if (tmpl->metadata)
rec->crossing_stripes = check_crossing_stripes(
global_info, rec->start,
- global_info->tree_root->nodesize);
+ global_info->nodesize);
check_extent_type(rec);
maybe_free_extent_rec(extent_cache, rec);
return ret;
struct tree_backref *back;
struct cache_extent *cache;
int ret;
+ bool insert = false;
cache = lookup_cache_extent(extent_cache, bytenr, 1);
if (!cache) {
tmpl.start = bytenr;
tmpl.nr = 1;
tmpl.metadata = 1;
+ tmpl.max_size = 1;
ret = add_extent_rec_nolookup(extent_cache, &tmpl);
if (ret)
back = alloc_tree_backref(rec, parent, root);
if (!back)
return -ENOMEM;
+ insert = true;
}
if (found_ref) {
}
back->node.found_extent_tree = 1;
}
+ if (insert)
+ WARN_ON(rb_insert(&rec->backref_tree, &back->node.node,
+ compare_extent_backref));
check_extent_type(rec);
maybe_free_extent_rec(extent_cache, rec);
return 0;
struct data_backref *back;
struct cache_extent *cache;
int ret;
+ bool insert = false;
cache = lookup_cache_extent(extent_cache, bytenr, 1);
if (!cache) {
back = alloc_data_backref(rec, parent, root, owner, offset,
max_size);
BUG_ON(!back);
+ insert = true;
}
if (found_ref) {
BUG_ON(back->bytes != max_size);
back->node.found_ref = 1;
back->found_ref += 1;
- back->bytes = max_size;
- back->disk_bytenr = bytenr;
+ if (back->bytes != max_size || back->disk_bytenr != bytenr) {
+ back->bytes = max_size;
+ back->disk_bytenr = bytenr;
+
+ /* Need to reinsert if not already in the tree */
+ if (!insert) {
+ rb_erase(&back->node.node, &rec->backref_tree);
+ insert = true;
+ }
+ }
rec->refs += 1;
rec->content_checked = 1;
rec->owner_ref_checked = 1;
back->num_refs = num_refs;
back->node.found_extent_tree = 1;
}
+ if (insert)
+ WARN_ON(rb_insert(&rec->backref_tree, &back->node.node,
+ compare_extent_backref));
+
maybe_free_extent_rec(extent_cache, rec);
return 0;
}
* 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,
+ ret = btrfs_check_chunk_valid(global_info, eb, chunk, slot,
key->offset);
if (ret < 0) {
error("chunk(%llu, %llu) is not valid, ignore it",
if (key.type == BTRFS_METADATA_ITEM_KEY) {
metadata = 1;
- num_bytes = root->nodesize;
+ num_bytes = root->fs_info->nodesize;
} else {
num_bytes = key.offset;
}
- if (!IS_ALIGNED(key.objectid, root->sectorsize)) {
+ if (!IS_ALIGNED(key.objectid, root->fs_info->sectorsize)) {
error("ignoring invalid extent, bytenr %llu is not aligned to %u",
- key.objectid, root->sectorsize);
+ key.objectid, root->fs_info->sectorsize);
return -EIO;
}
if (item_size < sizeof(*ei)) {
metadata = 1;
else
metadata = 0;
- if (metadata && num_bytes != root->nodesize) {
+ if (metadata && num_bytes != root->fs_info->nodesize) {
error("ignore invalid metadata extent, length %llu does not equal to %u",
- num_bytes, root->nodesize);
+ num_bytes, root->fs_info->nodesize);
return -EIO;
}
- if (!metadata && !IS_ALIGNED(num_bytes, root->sectorsize)) {
+ if (!metadata && !IS_ALIGNED(num_bytes, root->fs_info->sectorsize)) {
error("ignore invalid data extent, length %llu is not aligned to %u",
- num_bytes, root->sectorsize);
+ num_bytes, root->fs_info->sectorsize);
return -EIO;
}
ret = add_tree_backref(extent_cache, key.objectid,
0, offset, 0);
if (ret < 0)
- error("add_tree_backref failed: %s",
+ error(
+ "add_tree_backref failed (extent items tree block): %s",
strerror(-ret));
break;
case BTRFS_SHARED_BLOCK_REF_KEY:
ret = add_tree_backref(extent_cache, key.objectid,
offset, 0, 0);
if (ret < 0)
- error("add_tree_backref failed: %s",
+ error(
+ "add_tree_backref failed (extent items shared block): %s",
strerror(-ret));
break;
case BTRFS_EXTENT_DATA_REF_KEY:
for (i = 0; i < BTRFS_SUPER_MIRROR_MAX; i++) {
bytenr = btrfs_sb_offset(i);
- ret = btrfs_rmap_block(&root->fs_info->mapping_tree,
+ ret = btrfs_rmap_block(root->fs_info,
cache->key.objectid, bytenr, 0,
&logical, &nr, &stripe_len);
if (ret)
if (key.type == BTRFS_EXTENT_ITEM_KEY)
last = key.objectid + key.offset;
else
- last = key.objectid + root->nodesize;
+ last = key.objectid + root->fs_info->nodesize;
path.slots[0]++;
continue;
}
if (key.type == BTRFS_EXTENT_ITEM_KEY)
last = key.objectid + key.offset;
else
- last = key.objectid + root->nodesize;
+ last = key.objectid + root->fs_info->nodesize;
path.slots[0]++;
}
start = cache->key.objectid + cache->key.offset;
if (!cache->free_space_ctl) {
if (btrfs_init_free_space_ctl(cache,
- root->sectorsize)) {
+ root->fs_info->sectorsize)) {
ret = -ENOMEM;
break;
}
btrfs_remove_free_space_cache(cache);
}
- if (btrfs_fs_compat_ro(root->fs_info,
- BTRFS_FEATURE_COMPAT_RO_FREE_SPACE_TREE)) {
+ if (btrfs_fs_compat_ro(root->fs_info, FREE_SPACE_TREE)) {
ret = exclude_super_stripes(root, cache);
if (ret) {
fprintf(stderr, "could not exclude super stripes: %s\n",
u64 num_bytes, unsigned long leaf_offset,
struct extent_buffer *eb) {
+ struct btrfs_fs_info *fs_info = root->fs_info;
u64 offset = 0;
- u16 csum_size = btrfs_super_csum_size(root->fs_info->super_copy);
+ u16 csum_size = btrfs_super_csum_size(fs_info->super_copy);
char *data;
unsigned long csum_offset;
u32 csum;
int mirror;
int num_copies;
- if (num_bytes % root->sectorsize)
+ if (num_bytes % fs_info->sectorsize)
return -EINVAL;
data = malloc(num_bytes);
again:
read_len = num_bytes - offset;
/* read as much space once a time */
- ret = read_extent_data(root, data + offset,
+ ret = read_extent_data(fs_info, data + offset,
bytenr + offset, &read_len, mirror);
if (ret)
goto out;
csum = ~(u32)0;
tmp = offset + data_checked;
- csum = btrfs_csum_data(NULL, (char *)data + tmp,
- csum, root->sectorsize);
+ csum = btrfs_csum_data((char *)data + tmp,
+ csum, fs_info->sectorsize);
btrfs_csum_final(csum, (u8 *)&csum);
csum_offset = leaf_offset +
- tmp / root->sectorsize * csum_size;
+ tmp / fs_info->sectorsize * csum_size;
read_extent_buffer(eb, (char *)&csum_expected,
csum_offset, csum_size);
/* try another mirror */
fprintf(stderr, "mirror %d bytenr %llu csum %u expected csum %u\n",
mirror, bytenr + tmp,
csum, csum_expected);
- num_copies = btrfs_num_copies(
- &root->fs_info->mapping_tree,
+ num_copies = btrfs_num_copies(root->fs_info,
bytenr, num_bytes);
if (mirror < num_copies - 1) {
mirror += 1;
goto again;
}
}
- data_checked += root->sectorsize;
+ data_checked += fs_info->sectorsize;
}
offset += read_len;
}
}
data_len = (btrfs_item_size_nr(leaf, path.slots[0]) /
- csum_size) * root->sectorsize;
+ csum_size) * root->fs_info->sectorsize;
if (!check_data_csum)
goto skip_csum_check;
leaf_offset = btrfs_item_ptr_offset(leaf, path.slots[0]);
* assumption and simply indicate that we _think_ that the FULL BACKREF needs to
* be set or not and then we can check later once we've gathered all the refs.
*/
-static int calc_extent_flag(struct btrfs_root *root,
- struct cache_tree *extent_cache,
+static int calc_extent_flag(struct cache_tree *extent_cache,
struct extent_buffer *buf,
struct root_item_record *ri,
u64 *flags)
struct device_extent_tree *dev_extent_cache,
struct root_item_record *ri)
{
+ struct btrfs_fs_info *fs_info = root->fs_info;
struct extent_buffer *buf;
struct extent_record *rec = NULL;
u64 bytenr;
continue;
/* fixme, get the parent transid */
- readahead_tree_block(root, bits[i].start,
- bits[i].size, 0);
+ readahead_tree_block(fs_info, bits[i].start, 0);
}
}
*last = bits[0].start;
}
/* fixme, get the real parent transid */
- buf = read_tree_block(root, bytenr, size, gen);
+ buf = read_tree_block(root->fs_info, bytenr, gen);
if (!extent_buffer_uptodate(buf)) {
record_bad_block_io(root->fs_info,
extent_cache, bytenr, size);
btrfs_header_level(buf), 1, NULL,
&flags);
if (ret < 0) {
- ret = calc_extent_flag(root, extent_cache, buf, ri, &flags);
+ ret = calc_extent_flag(extent_cache, buf, ri, &flags);
if (ret < 0) {
fprintf(stderr, "Couldn't calc extent flags\n");
flags |= BTRFS_BLOCK_FLAG_FULL_BACKREF;
}
} else {
flags = 0;
- ret = calc_extent_flag(root, extent_cache, buf, ri, &flags);
+ ret = calc_extent_flag(extent_cache, buf, ri, &flags);
if (ret < 0) {
fprintf(stderr, "Couldn't calc extent flags\n");
flags |= BTRFS_BLOCK_FLAG_FULL_BACKREF;
ret = add_tree_backref(extent_cache,
key.objectid, 0, key.offset, 0);
if (ret < 0)
- error("add_tree_backref failed: %s",
+ error(
+ "add_tree_backref failed (leaf tree block): %s",
strerror(-ret));
continue;
}
ret = add_tree_backref(extent_cache,
key.objectid, key.offset, 0, 0);
if (ret < 0)
- error("add_tree_backref failed: %s",
+ error(
+ "add_tree_backref failed (leaf shared block): %s",
strerror(-ret));
continue;
}
ref),
btrfs_extent_data_ref_offset(buf, ref),
btrfs_extent_data_ref_count(buf, ref),
- 0, root->sectorsize);
+ 0, root->fs_info->sectorsize);
continue;
}
if (key.type == BTRFS_SHARED_DATA_REF_KEY) {
add_data_backref(extent_cache,
key.objectid, key.offset, 0, 0, 0,
btrfs_shared_data_ref_count(buf, ref),
- 0, root->sectorsize);
+ 0, root->fs_info->sectorsize);
continue;
}
if (key.type == BTRFS_ORPHAN_ITEM_KEY) {
data_bytes_allocated +=
btrfs_file_extent_disk_num_bytes(buf, fi);
- if (data_bytes_allocated < root->sectorsize) {
+ if (data_bytes_allocated < root->fs_info->sectorsize) {
abort();
}
data_bytes_referenced +=
struct extent_record tmpl;
ptr = btrfs_node_blockptr(buf, i);
- size = root->nodesize;
+ size = root->fs_info->nodesize;
btrfs_node_key_to_cpu(buf, &key, i);
if (ri != NULL) {
if ((level == ri->drop_level)
ret = add_tree_backref(extent_cache, ptr, parent,
owner, 1);
if (ret < 0) {
- error("add_tree_backref failed: %s",
+ error(
+ "add_tree_backref failed (non-leaf block): %s",
strerror(-ret));
continue;
}
total_fs_tree_bytes += buf->len;
if (btrfs_header_owner(buf) == BTRFS_EXTENT_TREE_OBJECTID)
total_extent_tree_bytes += buf->len;
- if (!found_old_backref &&
- btrfs_header_owner(buf) == BTRFS_TREE_RELOC_OBJECTID &&
- btrfs_header_backref_rev(buf) == BTRFS_MIXED_BACKREF_REV &&
- !btrfs_header_flag(buf, BTRFS_HEADER_FLAG_RELOC))
- found_old_backref = 1;
out:
free_extent_buffer(buf);
return ret;
back->node.found_extent_tree = 0;
if (!back->node.found_extent_tree && back->node.found_ref) {
- list_del(&back->node.list);
+ rb_erase(&back->node.node, &rec->backref_tree);
free(back);
}
} else {
back->node.found_extent_tree = 0;
}
if (!back->node.found_extent_tree && back->node.found_ref) {
- list_del(&back->node.list);
+ rb_erase(&back->node.node, &rec->backref_tree);
free(back);
}
}
static int delete_extent_records(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct btrfs_path *path,
- u64 bytenr, u64 new_len)
+ u64 bytenr)
{
struct btrfs_key key;
struct btrfs_key found_key;
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->nodesize;
+ found_key.offset : root->fs_info->nodesize;
ret = btrfs_update_block_group(trans, root, bytenr,
bytes, 0, 0);
struct extent_backref *back,
int allocated, u64 flags)
{
- int ret;
+ int ret = 0;
struct btrfs_root *extent_root = info->extent_root;
struct extent_buffer *leaf;
struct btrfs_key ins_key;
if (!back->is_data)
rec->max_size = max_t(u64, rec->max_size,
- info->extent_root->nodesize);
+ info->nodesize);
if (!allocated) {
u32 item_size = sizeof(*ei);
static int verify_backrefs(struct btrfs_fs_info *info, struct btrfs_path *path,
struct extent_record *rec)
{
- struct extent_backref *back;
+ struct extent_backref *back, *tmp;
struct data_backref *dback;
struct extent_entry *entry, *best = NULL;
LIST_HEAD(entries);
if (rec->metadata)
return 0;
- list_for_each_entry(back, &rec->backrefs, list) {
+ rbtree_postorder_for_each_entry_safe(back, tmp,
+ &rec->backref_tree, node) {
if (back->full_backref || !back->is_data)
continue;
* Ok great we all agreed on an extent record, let's go find the real
* references and fix up the ones that don't match.
*/
- list_for_each_entry(back, &rec->backrefs, list) {
+ rbtree_postorder_for_each_entry_safe(back, tmp,
+ &rec->backref_tree, node) {
if (back->full_backref || !back->is_data)
continue;
return ret;
}
-static int process_duplicates(struct btrfs_root *root,
- struct cache_tree *extent_cache,
+static int process_duplicates(struct cache_tree *extent_cache,
struct extent_record *rec)
{
struct extent_record *good, *tmp;
struct extent_record *rec)
{
struct btrfs_root *root;
- struct extent_backref *back;
+ struct extent_backref *back, *tmp;
struct data_backref *dback;
struct cache_extent *cache;
struct btrfs_file_extent_item *fi;
u64 bytenr, bytes;
int ret;
- list_for_each_entry(back, &rec->backrefs, list) {
+ rbtree_postorder_for_each_entry_safe(back, tmp,
+ &rec->backref_tree, node) {
/* Don't care about full backrefs (poor unloved backrefs) */
if (back->full_backref || !back->is_data)
continue;
{
struct btrfs_key key;
struct btrfs_root *dest_root;
- struct extent_backref *back;
+ struct extent_backref *back, *tmp;
struct data_backref *dback;
struct orphan_data_extent *orphan;
struct btrfs_path path;
if (rec->metadata)
return 1;
btrfs_init_path(&path);
- list_for_each_entry(back, &rec->backrefs, list) {
+ rbtree_postorder_for_each_entry_safe(back, tmp,
+ &rec->backref_tree, node) {
if (back->full_backref || !back->is_data ||
!back->found_extent_tree)
continue;
struct btrfs_trans_handle *trans = NULL;
int ret;
struct btrfs_path path;
- struct list_head *cur = rec->backrefs.next;
struct cache_extent *cache;
- struct extent_backref *back;
+ struct extent_backref *back, *tmp;
int allocated = 0;
u64 flags = 0;
/* step two, delete all the existing records */
ret = delete_extent_records(trans, info->extent_root, &path,
- rec->start, rec->max_size);
+ rec->start);
if (ret < 0)
goto out;
}
/* step three, recreate all the refs we did find */
- while(cur != &rec->backrefs) {
- back = to_extent_backref(cur);
- cur = cur->next;
-
+ rbtree_postorder_for_each_entry_safe(back, tmp,
+ &rec->backref_tree, node) {
/*
* if we didn't find any references, don't create a
* new extent record
ret = err;
}
+ if (!ret)
+ fprintf(stderr, "Repaired extent references for %llu\n",
+ (unsigned long long)rec->start);
+
btrfs_release_path(&path);
return ret;
}
btrfs_set_extent_flags(path.nodes[0], ei, flags);
btrfs_mark_buffer_dirty(path.nodes[0]);
btrfs_release_path(&path);
- return btrfs_commit_transaction(trans, root);
+ ret = btrfs_commit_transaction(trans, root);
+ if (!ret)
+ fprintf(stderr, "Repaired extent flags for %llu\n",
+ (unsigned long long)rec->start);
+
+ return ret;
}
/* right now we only prune from the extent allocation tree */
del_ptr:
printk("deleting pointer to block %Lu\n", corrupt->cache.start);
- ret = btrfs_del_ptr(trans, info->extent_root, &path, level, slot);
+ ret = btrfs_del_ptr(info->extent_root, &path, level, slot);
out:
btrfs_release_path(&path);
&start, &end, EXTENT_DIRTY);
if (ret)
break;
- clear_extent_dirty(&fs_info->free_space_cache, start, end,
- GFP_NOFS);
+ clear_extent_dirty(&fs_info->free_space_cache, start, end);
}
start = 0;
{
struct extent_record *rec;
struct cache_extent *cache;
- int err = 0;
int ret = 0;
- int fixed = 0;
int had_dups = 0;
- int recorded = 0;
+ int err = 0;
if (repair) {
/*
rec = container_of(cache, struct extent_record, cache);
set_extent_dirty(root->fs_info->excluded_extents,
rec->start,
- rec->start + rec->max_size - 1,
- GFP_NOFS);
+ rec->start + rec->max_size - 1);
cache = next_cache_extent(cache);
}
while(cache) {
set_extent_dirty(root->fs_info->excluded_extents,
cache->start,
- cache->start + cache->size - 1,
- GFP_NOFS);
+ cache->start + cache->size - 1);
cache = next_cache_extent(cache);
}
prune_corrupt_blocks(root->fs_info);
* process_duplicates() will return 0, otherwise it will return
* 1 and we
*/
- if (process_duplicates(root, extent_cache, rec))
+ if (process_duplicates(extent_cache, rec))
continue;
ret = delete_duplicate_records(root, rec);
if (ret < 0)
while(1) {
int cur_err = 0;
+ int fix = 0;
- fixed = 0;
- recorded = 0;
cache = search_cache_extent(extent_cache, 0);
if (!cache)
break;
if (rec->num_duplicates) {
fprintf(stderr, "extent item %llu has multiple extent "
"items\n", (unsigned long long)rec->start);
- err = 1;
cur_err = 1;
}
ret = record_orphan_data_extents(root->fs_info, rec);
if (ret < 0)
goto repair_abort;
- if (ret == 0) {
- recorded = 1;
- } else {
- /*
- * we can't use the extent to repair file
- * extent, let the fallback method handle it.
- */
- if (!fixed && repair) {
- ret = fixup_extent_refs(
- root->fs_info,
- extent_cache, rec);
- if (ret)
- goto repair_abort;
- fixed = 1;
- }
- }
- err = 1;
+ fix = ret;
cur_err = 1;
}
if (all_backpointers_checked(rec, 1)) {
fprintf(stderr, "backpointer mismatch on [%llu %llu]\n",
(unsigned long long)rec->start,
(unsigned long long)rec->nr);
-
- if (!fixed && !recorded && repair) {
- ret = fixup_extent_refs(root->fs_info,
- extent_cache, rec);
- if (ret)
- goto repair_abort;
- fixed = 1;
- }
+ fix = 1;
cur_err = 1;
- err = 1;
}
if (!rec->owner_ref_checked) {
fprintf(stderr, "owner ref check failed [%llu %llu]\n",
(unsigned long long)rec->start,
(unsigned long long)rec->nr);
- if (!fixed && !recorded && repair) {
- ret = fixup_extent_refs(root->fs_info,
- extent_cache, rec);
- if (ret)
- goto repair_abort;
- fixed = 1;
- }
- err = 1;
+ fix = 1;
cur_err = 1;
}
+
+ if (repair && fix) {
+ ret = fixup_extent_refs(root->fs_info, extent_cache, rec);
+ if (ret)
+ goto repair_abort;
+ }
+
+
if (rec->bad_full_backref) {
fprintf(stderr, "bad full backref, on [%llu]\n",
(unsigned long long)rec->start);
ret = fixup_extent_flags(root->fs_info, rec);
if (ret)
goto repair_abort;
- fixed = 1;
+ fix = 1;
}
- err = 1;
cur_err = 1;
}
/*
fprintf(stderr,
"bad metadata [%llu, %llu) crossing stripe boundary\n",
rec->start, rec->start + rec->max_size);
- err = 1;
cur_err = 1;
}
fprintf(stderr,
"bad extent [%llu, %llu), type mismatch with chunk\n",
rec->start, rec->start + rec->max_size);
- err = 1;
cur_err = 1;
}
+ err = cur_err;
remove_cache_extent(extent_cache, cache);
free_all_extent_backrefs(rec);
- if (!init_extent_tree && repair && (!cur_err || fixed))
+ if (!init_extent_tree && repair && (!cur_err || fix))
clear_extent_dirty(root->fs_info->excluded_extents,
rec->start,
- rec->start + rec->max_size - 1,
- GFP_NOFS);
+ rec->start + rec->max_size - 1);
free(rec);
}
repair_abort:
goto repair_abort;
}
- btrfs_fix_block_accounting(trans, root);
+ ret = btrfs_fix_block_accounting(trans, root);
+ if (ret)
+ goto repair_abort;
ret = btrfs_commit_transaction(trans, root);
if (ret)
goto repair_abort;
}
- if (err)
- fprintf(stderr, "repaired damaged extent references\n");
return ret;
}
+
+ if (err)
+ err = -EIO;
return err;
}
}
}
+/*
+ * Extra (optional) check for dev_item size to report possbile problem on a new
+ * kernel.
+ */
+static void check_dev_size_alignment(u64 devid, u64 total_bytes, u32 sectorsize)
+{
+ if (!IS_ALIGNED(total_bytes, sectorsize)) {
+ warning(
+"unaligned total_bytes detected for devid %llu, have %llu should be aligned to %u",
+ devid, total_bytes, sectorsize);
+ warning(
+"this is OK for older kernel, but may cause kernel warning for newer kernels");
+ warning("this can be fixed by 'btrfs rescue fix-device-size'");
+ }
+}
+
+/*
+ * Unlike device size alignment check above, some super total_bytes check
+ * failure can lead to mount failure for newer kernel.
+ *
+ * So this function will return the error for a fatal super total_bytes problem.
+ */
+static bool is_super_size_valid(struct btrfs_fs_info *fs_info)
+{
+ struct btrfs_device *dev;
+ struct list_head *dev_list = &fs_info->fs_devices->devices;
+ u64 total_bytes = 0;
+ u64 super_bytes = btrfs_super_total_bytes(fs_info->super_copy);
+
+ list_for_each_entry(dev, dev_list, dev_list)
+ total_bytes += dev->total_bytes;
+
+ /* Important check, which can cause unmountable fs */
+ if (super_bytes < total_bytes) {
+ error("super total bytes %llu smaller than real device(s) size %llu",
+ super_bytes, total_bytes);
+ error("mounting this fs may fail for newer kernels");
+ error("this can be fixed by 'btrfs rescue fix-device-size'");
+ return false;
+ }
+
+ /*
+ * Optional check, just to make everything aligned and match with each
+ * other.
+ *
+ * For a btrfs-image restored fs, we don't need to check it anyway.
+ */
+ if (btrfs_super_flags(fs_info->super_copy) &
+ (BTRFS_SUPER_FLAG_METADUMP | BTRFS_SUPER_FLAG_METADUMP_V2))
+ return true;
+ if (!IS_ALIGNED(super_bytes, fs_info->sectorsize) ||
+ !IS_ALIGNED(total_bytes, fs_info->sectorsize) ||
+ super_bytes != total_bytes) {
+ warning("minor unaligned/mismatch device size detected");
+ warning(
+ "recommended to use 'btrfs rescue fix-device-size' to fix it");
+ }
+ return true;
+}
+
/* check btrfs_dev_item -> btrfs_dev_extent */
static int check_devices(struct rb_root *dev_cache,
struct device_extent_tree *dev_extent_cache)
if (err)
ret = err;
+ check_dev_size_alignment(dev_rec->devid, dev_rec->total_byte,
+ global_info->sectorsize);
dev_node = rb_next(dev_node);
}
list_for_each_entry(dext_rec, &dev_extent_cache->no_device_orphans,
static int add_root_item_to_list(struct list_head *head,
u64 objectid, u64 bytenr, u64 last_snapshot,
u8 level, u8 drop_level,
- int level_size, struct btrfs_key *drop_key)
+ struct btrfs_key *drop_key)
{
struct root_item_record *ri_rec;
ri_rec->bytenr = bytenr;
ri_rec->objectid = objectid;
ri_rec->level = level;
- ri_rec->level_size = level_size;
ri_rec->drop_level = drop_level;
ri_rec->last_snapshot = last_snapshot;
if (drop_key)
rec = list_entry(list->next,
struct root_item_record, list);
last = 0;
- buf = read_tree_block(root->fs_info->tree_root,
- rec->bytenr, rec->level_size, 0);
+ buf = read_tree_block(root->fs_info, rec->bytenr, 0);
if (!extent_buffer_uptodate(buf)) {
free_extent_buffer(buf);
ret = -EIO;
return ret;
}
-static int check_chunks_and_extents(struct btrfs_root *root)
+static int check_chunks_and_extents(struct btrfs_fs_info *fs_info)
{
struct rb_root dev_cache;
struct cache_tree chunk_cache;
struct list_head dropping_trees;
struct list_head normal_trees;
struct btrfs_root *root1;
+ struct btrfs_root *root;
u64 objectid;
- u32 level_size;
u8 level;
+ root = fs_info->fs_root;
dev_cache = RB_ROOT;
cache_tree_init(&chunk_cache);
block_group_tree_init(&block_group_cache);
INIT_LIST_HEAD(&normal_trees);
if (repair) {
- root->fs_info->excluded_extents = &excluded_extents;
- root->fs_info->fsck_extent_cache = &extent_cache;
- root->fs_info->free_extent_hook = free_extent_hook;
- root->fs_info->corrupt_blocks = &corrupt_blocks;
+ fs_info->excluded_extents = &excluded_extents;
+ fs_info->fsck_extent_cache = &extent_cache;
+ fs_info->free_extent_hook = free_extent_hook;
+ fs_info->corrupt_blocks = &corrupt_blocks;
}
bits_nr = 1024;
}
again:
- root1 = root->fs_info->tree_root;
+ root1 = fs_info->tree_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,
- root1->nodesize, NULL);
+ root1->node->start, 0, level, 0, NULL);
if (ret < 0)
goto out;
- root1 = root->fs_info->chunk_root;
+ root1 = 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,
- root1->nodesize, NULL);
+ root1->node->start, 0, level, 0, NULL);
if (ret < 0)
goto out;
btrfs_init_path(&path);
key.offset = 0;
key.objectid = 0;
key.type = BTRFS_ROOT_ITEM_KEY;
- ret = btrfs_search_slot(NULL, root->fs_info->tree_root,
- &key, &path, 0, 0);
+ ret = btrfs_search_slot(NULL, fs_info->tree_root, &key, &path, 0, 0);
if (ret < 0)
goto out;
while(1) {
last_snapshot = btrfs_root_last_snapshot(&ri);
if (btrfs_disk_key_objectid(&ri.drop_progress) == 0) {
level = btrfs_root_level(&ri);
- level_size = root->nodesize;
ret = add_root_item_to_list(&normal_trees,
found_key.objectid,
btrfs_root_bytenr(&ri),
last_snapshot, level,
- 0, level_size, NULL);
+ 0, NULL);
if (ret < 0)
goto out;
} else {
level = btrfs_root_level(&ri);
- level_size = root->nodesize;
objectid = found_key.objectid;
btrfs_disk_key_to_cpu(&found_key,
&ri.drop_progress);
objectid,
btrfs_root_bytenr(&ri),
last_snapshot, level,
- ri.drop_level,
- level_size, &found_key);
+ ri.drop_level, &found_key);
if (ret < 0)
goto out;
}
out:
task_stop(ctx.info);
if (repair) {
- free_corrupt_blocks_tree(root->fs_info->corrupt_blocks);
+ free_corrupt_blocks_tree(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;
+ fs_info->fsck_extent_cache = NULL;
+ fs_info->free_extent_hook = NULL;
+ fs_info->corrupt_blocks = NULL;
+ fs_info->excluded_extents = NULL;
}
free(bits);
free_chunk_cache_tree(&chunk_cache);
free_extent_cache_tree(&pending);
free_extent_cache_tree(&reada);
free_extent_cache_tree(&nodes);
+ free_root_item_list(&normal_trees);
+ free_root_item_list(&dropping_trees);
return ret;
loop:
- free_corrupt_blocks_tree(root->fs_info->corrupt_blocks);
+ free_corrupt_blocks_tree(fs_info->corrupt_blocks);
free_extent_cache_tree(&seen);
free_extent_cache_tree(&pending);
free_extent_cache_tree(&reada);
free_block_group_tree(&block_group_cache);
free_device_cache_tree(&dev_cache);
free_device_extent_tree(&dev_extent_cache);
- free_extent_record_cache(root->fs_info, &extent_cache);
+ free_extent_record_cache(&extent_cache);
free_root_item_list(&normal_trees);
free_root_item_list(&dropping_trees);
extent_io_tree_cleanup(&excluded_extents);
goto again;
}
+static int check_extent_inline_ref(struct extent_buffer *eb,
+ struct btrfs_key *key, struct btrfs_extent_inline_ref *iref)
+{
+ int ret;
+ u8 type = btrfs_extent_inline_ref_type(eb, iref);
+
+ switch (type) {
+ case BTRFS_TREE_BLOCK_REF_KEY:
+ case BTRFS_EXTENT_DATA_REF_KEY:
+ case BTRFS_SHARED_BLOCK_REF_KEY:
+ case BTRFS_SHARED_DATA_REF_KEY:
+ ret = 0;
+ break;
+ default:
+ error("extent[%llu %u %llu] has unknown ref type: %d",
+ key->objectid, key->type, key->offset, type);
+ ret = UNKNOWN_TYPE;
+ break;
+ }
+
+ return ret;
+}
+
/*
* Check backrefs of a tree block given by @bytenr or @eb.
*
*/
static int check_tree_block_ref(struct btrfs_root *root,
struct extent_buffer *eb, u64 bytenr,
- int level, u64 owner)
+ int level, u64 owner, struct node_refs *nrefs)
{
struct btrfs_key key;
struct btrfs_root *extent_root = root->fs_info->extent_root;
unsigned long ptr;
int slot;
int skinny_level;
+ int root_level = btrfs_header_level(root->node);
int type;
- u32 nodesize = root->nodesize;
+ u32 nodesize = root->fs_info->nodesize;
u32 item_size;
u64 offset;
+ int tree_reloc_root = 0;
int found_ref = 0;
int err = 0;
int ret;
+ int strict = 1;
+ int parent = 0;
+ if (root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID &&
+ btrfs_header_bytenr(root->node) == bytenr)
+ tree_reloc_root = 1;
btrfs_init_path(&path);
key.objectid = bytenr;
- if (btrfs_fs_incompat(root->fs_info,
- BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA))
+ if (btrfs_fs_incompat(root->fs_info, SKINNY_METADATA))
key.type = BTRFS_METADATA_ITEM_KEY;
else
key.type = BTRFS_EXTENT_ITEM_KEY;
iref = (struct btrfs_extent_inline_ref *)(info + 1);
}
+
if (eb) {
u64 header_gen;
u64 extent_gen;
+ /*
+ * Due to the feature of shared tree blocks, if the upper node
+ * is a fs root or shared node, the extent of checked node may
+ * not be updated until the next CoW.
+ */
+ if (nrefs)
+ strict = should_check_extent_strictly(root, nrefs,
+ level);
if (!(btrfs_extent_flags(leaf, ei) &
BTRFS_EXTENT_FLAG_TREE_BLOCK)) {
error(
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;
+ ret = check_extent_inline_ref(leaf, &key, iref);
+ if (ret) {
+ err |= ret;
+ break;
+ }
+ if (type == BTRFS_TREE_BLOCK_REF_KEY) {
+ if (offset == root->objectid)
+ found_ref = 1;
+ if (!strict && owner == offset)
+ 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);
+ /*
+ * Backref of tree reloc root points to itself, no need
+ * to check backref any more.
+ */
+ if (tree_reloc_root) {
+ found_ref = 1;
+ } else {
+ /*
+ * Check if the backref points to valid
+ * referencer
+ */
+ found_ref = !check_tree_block_ref( root, NULL,
+ offset, level + 1, owner,
+ NULL);
+ }
}
if (found_ref)
err |= BACKREF_MISSING;
out:
btrfs_release_path(&path);
+ if (nrefs && strict &&
+ level < root_level && nrefs->full_backref[level + 1])
+ parent = nrefs->bytenr[level + 1];
if (eb && (err & BACKREF_MISSING))
- error("extent[%llu %u] backref lost (owner: %llu, level: %u)",
- bytenr, nodesize, owner, level);
+ error(
+ "extent[%llu %u] backref lost (owner: %llu, level: %u) %s %llu",
+ bytenr, nodesize, owner, level,
+ parent ? "parent" : "root",
+ parent ? parent : root->objectid);
+ return err;
+}
+
+/*
+ * If @err contains BACKREF_MISSING then add extent of the
+ * file_extent_data_item.
+ *
+ * Returns error bits after reapir.
+ */
+static int repair_extent_data_item(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root,
+ struct btrfs_path *pathp,
+ struct node_refs *nrefs,
+ int err)
+{
+ struct btrfs_file_extent_item *fi;
+ struct btrfs_key fi_key;
+ struct btrfs_key key;
+ struct btrfs_extent_item *ei;
+ struct btrfs_path path;
+ struct btrfs_root *extent_root = root->fs_info->extent_root;
+ struct extent_buffer *eb;
+ u64 size;
+ u64 disk_bytenr;
+ u64 num_bytes;
+ u64 parent;
+ u64 offset;
+ u64 extent_offset;
+ u64 file_offset;
+ int generation;
+ int slot;
+ int ret = 0;
+
+ eb = pathp->nodes[0];
+ slot = pathp->slots[0];
+ btrfs_item_key_to_cpu(eb, &fi_key, slot);
+ fi = btrfs_item_ptr(eb, slot, struct btrfs_file_extent_item);
+
+ if (btrfs_file_extent_type(eb, fi) == BTRFS_FILE_EXTENT_INLINE ||
+ btrfs_file_extent_disk_bytenr(eb, fi) == 0)
+ return err;
+
+ file_offset = fi_key.offset;
+ generation = btrfs_file_extent_generation(eb, fi);
+ disk_bytenr = btrfs_file_extent_disk_bytenr(eb, fi);
+ num_bytes = btrfs_file_extent_disk_num_bytes(eb, fi);
+ extent_offset = btrfs_file_extent_offset(eb, fi);
+ offset = file_offset - extent_offset;
+
+ /* now repair only adds backref */
+ if ((err & BACKREF_MISSING) == 0)
+ return err;
+
+ /* search extent item */
+ key.objectid = disk_bytenr;
+ key.type = BTRFS_EXTENT_ITEM_KEY;
+ key.offset = num_bytes;
+
+ btrfs_init_path(&path);
+ ret = btrfs_search_slot(NULL, extent_root, &key, &path, 0, 0);
+ if (ret < 0) {
+ ret = -EIO;
+ goto out;
+ }
+
+ /* insert an extent item */
+ if (ret > 0) {
+ key.objectid = disk_bytenr;
+ key.type = BTRFS_EXTENT_ITEM_KEY;
+ key.offset = num_bytes;
+ size = sizeof(*ei);
+
+ btrfs_release_path(&path);
+ ret = btrfs_insert_empty_item(trans, extent_root, &path, &key,
+ size);
+ if (ret)
+ goto out;
+ eb = path.nodes[0];
+ ei = btrfs_item_ptr(eb, path.slots[0], struct btrfs_extent_item);
+
+ btrfs_set_extent_refs(eb, ei, 0);
+ btrfs_set_extent_generation(eb, ei, generation);
+ btrfs_set_extent_flags(eb, ei, BTRFS_EXTENT_FLAG_DATA);
+
+ btrfs_mark_buffer_dirty(eb);
+ ret = btrfs_update_block_group(trans, extent_root, disk_bytenr,
+ num_bytes, 1, 0);
+ btrfs_release_path(&path);
+ }
+
+ if (nrefs->full_backref[0])
+ parent = btrfs_header_bytenr(eb);
+ else
+ parent = 0;
+
+ ret = btrfs_inc_extent_ref(trans, root, disk_bytenr, num_bytes, parent,
+ root->objectid,
+ parent ? BTRFS_FIRST_FREE_OBJECTID : fi_key.objectid,
+ offset);
+ if (ret) {
+ error(
+ "failed to increase extent data backref[%llu %llu] root %llu",
+ disk_bytenr, num_bytes, root->objectid);
+ goto out;
+ } else {
+ printf("Add one extent data backref [%llu %llu]\n",
+ disk_bytenr, num_bytes);
+ }
+
+ err &= ~BACKREF_MISSING;
+out:
+ if (ret)
+ error("can't repair root %llu extent data item[%llu %llu]",
+ root->objectid, disk_bytenr, num_bytes);
return err;
}
* Return 0 for no error found
*/
static int check_extent_data_item(struct btrfs_root *root,
- struct extent_buffer *eb, int slot)
+ struct btrfs_path *pathp,
+ struct node_refs *nrefs, int account_bytes)
{
struct btrfs_file_extent_item *fi;
+ struct extent_buffer *eb = pathp->nodes[0];
struct btrfs_path path;
struct btrfs_root *extent_root = root->fs_info->extent_root;
struct btrfs_key fi_key;
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 slot = pathp->slots[0];
int err = 0;
int ret;
+ int strict;
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 ||
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)) {
+ if (!IS_ALIGNED(disk_num_bytes, root->fs_info->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);
+ root->fs_info->sectorsize);
err |= BYTES_UNALIGNED;
- } else {
+ } else if (account_bytes) {
data_bytes_allocated += disk_num_bytes;
}
- if (!IS_ALIGNED(extent_num_bytes, root->sectorsize)) {
+ if (!IS_ALIGNED(extent_num_bytes, root->fs_info->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);
+ root->fs_info->sectorsize);
err |= BYTES_UNALIGNED;
- } else {
+ } else if (account_bytes) {
data_bytes_referenced += extent_num_bytes;
}
owner = btrfs_header_owner(eb);
dbref_key.offset = btrfs_file_extent_disk_num_bytes(eb, fi);
ret = btrfs_search_slot(NULL, extent_root, &dbref_key, &path, 0, 0);
- if (ret) {
- err |= BACKREF_MISSING;
- goto error;
- }
+ if (ret)
+ goto out;
leaf = path.nodes[0];
slot = path.slots[0];
ei = btrfs_item_ptr(leaf, slot, struct btrfs_extent_item);
extent_flags = btrfs_extent_flags(leaf, ei);
- extent_gen = btrfs_extent_generation(leaf, ei);
if (!(extent_flags & BTRFS_EXTENT_FLAG_DATA)) {
error(
err |= BACKREF_MISMATCH;
}
- if (file_extent_gen < extent_gen) {
- error(
-"extent[%llu %llu] backref generation mismatch, wanted: <=%llu, have: %llu",
- disk_bytenr, disk_num_bytes, file_extent_gen,
- extent_gen);
- err |= BACKREF_MISMATCH;
- }
-
/* Check data backref inside that extent item */
item_size = btrfs_item_size_nr(leaf, path.slots[0]);
iref = (struct btrfs_extent_inline_ref *)(ei + 1);
ptr = (unsigned long)iref;
end = (unsigned long)ei + item_size;
+ strict = should_check_extent_strictly(root, nrefs, -1);
+
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);
+ ret = check_extent_inline_ref(leaf, &dbref_key, iref);
+ if (ret) {
+ err |= ret;
+ break;
+ }
if (type == BTRFS_EXTENT_DATA_REF_KEY) {
ref_root = btrfs_extent_data_ref_root(leaf, dref);
- if (ref_root == owner || ref_root == root->objectid)
+ if (ref_root == root->objectid)
+ found_dbackref = 1;
+ else if (!strict && owner == ref_root)
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);
+ 0, owner, NULL);
}
if (found_dbackref)
ptr += btrfs_extent_inline_ref_size(type);
}
- /* Didn't found inlined data backref, try EXTENT_DATA_REF_KEY */
if (!found_dbackref) {
btrfs_release_path(&path);
- btrfs_init_path(&path);
+ /* Didn't find inlined data backref, try EXTENT_DATA_REF_KEY */
dbref_key.objectid = btrfs_file_extent_disk_bytenr(eb, fi);
dbref_key.type = BTRFS_EXTENT_DATA_REF_KEY;
dbref_key.offset = hash_extent_data_ref(root->objectid,
ret = btrfs_search_slot(NULL, root->fs_info->extent_root,
&dbref_key, &path, 0, 0);
- if (!ret)
+ if (!ret) {
+ found_dbackref = 1;
+ goto out;
+ }
+
+ btrfs_release_path(&path);
+
+ /*
+ * Neither inlined nor EXTENT_DATA_REF found, try
+ * SHARED_DATA_REF as last chance.
+ */
+ dbref_key.objectid = disk_bytenr;
+ dbref_key.type = BTRFS_SHARED_DATA_REF_KEY;
+ dbref_key.offset = eb->start;
+
+ ret = btrfs_search_slot(NULL, root->fs_info->extent_root,
+ &dbref_key, &path, 0, 0);
+ if (!ret) {
found_dbackref = 1;
+ goto out;
+ }
}
+out:
if (!found_dbackref)
err |= BACKREF_MISSING;
-error:
btrfs_release_path(&path);
if (err & BACKREF_MISSING) {
error("data extent[%llu %llu] backref lost",
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;
btrfs_release_path(&path);
/* Get level from tree block as an alternative source */
- eb = read_tree_block_fs_info(fs_info, bytenr, nodesize, transid);
+ eb = read_tree_block(fs_info, bytenr, transid);
if (!extent_buffer_uptodate(eb)) {
free_extent_buffer(eb);
return -EIO;
}
/* Read out the tree block to get item/node key */
- eb = read_tree_block(root, bytenr, root->nodesize, 0);
+ eb = read_tree_block(fs_info, bytenr, 0);
if (!extent_buffer_uptodate(eb)) {
err |= REFERENCER_MISSING;
free_extent_buffer(eb);
}
/*
+ * Check if tree block @eb is tree reloc root.
+ * Return 0 if it's not or any problem happens
+ * Return 1 if it's a tree reloc root
+ */
+static int is_tree_reloc_root(struct btrfs_fs_info *fs_info,
+ struct extent_buffer *eb)
+{
+ struct btrfs_root *tree_reloc_root;
+ struct btrfs_key key;
+ u64 bytenr = btrfs_header_bytenr(eb);
+ u64 owner = btrfs_header_owner(eb);
+ int ret = 0;
+
+ key.objectid = BTRFS_TREE_RELOC_OBJECTID;
+ key.offset = owner;
+ key.type = BTRFS_ROOT_ITEM_KEY;
+
+ tree_reloc_root = btrfs_read_fs_root_no_cache(fs_info, &key);
+ if (IS_ERR(tree_reloc_root))
+ return 0;
+
+ if (bytenr == btrfs_header_bytenr(tree_reloc_root->node))
+ ret = 1;
+ btrfs_free_fs_root(tree_reloc_root);
+ return ret;
+}
+
+/*
* Check referencer for shared block backref
* If level == -1, this function will resolve the level.
*/
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);
+ eb = read_tree_block(fs_info, parent, 0);
if (!extent_buffer_uptodate(eb))
goto out;
if (level < 0)
goto out;
+ /* It's possible it's a tree reloc root */
+ if (parent == bytenr) {
+ if (is_tree_reloc_root(fs_info, eb))
+ found_parent = 1;
+ goto out;
+ }
+
if (level + 1 != btrfs_header_level(eb))
goto out;
if (!found_parent) {
error(
"shared extent[%llu %u] lost its parent (parent: %llu, level: %u)",
- bytenr, nodesize, parent, level);
+ bytenr, fs_info->nodesize, parent, level);
return REFERENCER_MISSING;
}
return 0;
leaf = path.nodes[0];
slot = path.slots[0];
+ if (slot >= btrfs_header_nritems(leaf) ||
+ btrfs_header_owner(leaf) != root_id)
+ goto next;
btrfs_item_key_to_cpu(leaf, &key, slot);
if (key.objectid != objectid || key.type != BTRFS_EXTENT_DATA_KEY)
break;
offset)
found_count++;
+next:
ret = btrfs_next_item(root, &path);
if (ret)
break;
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);
+ eb = read_tree_block(fs_info, parent, 0);
if (!extent_buffer_uptodate(eb))
goto out;
}
/*
+ * Only delete backref if REFERENCER_MISSING now
+ *
+ * Returns <0 the extent was deleted
+ * Returns >0 the backref was deleted but extent still exists, returned value
+ * means error after repair
+ * Returns 0 nothing happened
+ */
+static int repair_extent_item(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root, struct btrfs_path *path,
+ u64 bytenr, u64 num_bytes, u64 parent, u64 root_objectid,
+ u64 owner, u64 offset, int err)
+{
+ struct btrfs_key old_key;
+ int freed = 0;
+ int ret;
+
+ btrfs_item_key_to_cpu(path->nodes[0], &old_key, path->slots[0]);
+
+ if (err & (REFERENCER_MISSING | REFERENCER_MISMATCH)) {
+ /* delete the backref */
+ ret = btrfs_free_extent(trans, root->fs_info->fs_root, bytenr,
+ num_bytes, parent, root_objectid, owner, offset);
+ if (!ret) {
+ freed = 1;
+ err &= ~REFERENCER_MISSING;
+ printf("Delete backref in extent [%llu %llu]\n",
+ bytenr, num_bytes);
+ } else {
+ error("fail to delete backref in extent [%llu %llu]",
+ bytenr, num_bytes);
+ }
+ }
+
+ /* btrfs_free_extent may delete the extent */
+ btrfs_release_path(path);
+ ret = btrfs_search_slot(NULL, root, &old_key, path, 0, 0);
+
+ if (ret)
+ ret = -ENOENT;
+ else if (freed)
+ ret = err;
+ return ret;
+}
+
+/*
* 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)
+static int check_extent_item(struct btrfs_trans_handle *trans,
+ struct btrfs_fs_info *fs_info,
+ struct btrfs_path *path)
{
struct btrfs_extent_item *ei;
struct btrfs_extent_inline_ref *iref;
struct btrfs_extent_data_ref *dref;
+ struct extent_buffer *eb = path->nodes[0];
unsigned long end;
unsigned long ptr;
+ int slot = path->slots[0];
int type;
u32 nodesize = btrfs_super_nodesize(fs_info->super_copy);
u32 item_size = btrfs_item_size_nr(eb, slot);
u64 flags;
u64 offset;
+ u64 parent;
+ u64 num_bytes;
+ u64 root_objectid;
+ u64 owner;
+ u64 owner_offset;
int metadata = 0;
int level;
struct btrfs_key key;
int err = 0;
btrfs_item_key_to_cpu(eb, &key, slot);
- if (key.type == BTRFS_EXTENT_ITEM_KEY)
+ if (key.type == BTRFS_EXTENT_ITEM_KEY) {
bytes_used += key.offset;
- else
+ num_bytes = key.offset;
+ } else {
bytes_used += nodesize;
+ num_bytes = nodesize;
+ }
if (item_size < sizeof(*ei)) {
/*
}
end = (unsigned long)ei + item_size;
- if (ptr >= end) {
+next:
+ /* Reached extent item end normally */
+ if (ptr == end)
+ goto out;
+
+ /* Beyond extent item end, wrong item size */
+ if (ptr > end) {
err |= ITEM_SIZE_MISMATCH;
+ error("extent item at bytenr %llu slot %d has wrong size",
+ eb->start, slot);
goto out;
}
+ parent = 0;
+ root_objectid = 0;
+ owner = 0;
+ owner_offset = 0;
/* 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:
+ root_objectid = offset;
+ owner = level;
ret = check_tree_block_backref(fs_info, offset, key.objectid,
level);
err |= ret;
break;
case BTRFS_SHARED_BLOCK_REF_KEY:
+ parent = offset;
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));
+ root_objectid = btrfs_extent_data_ref_root(eb, dref);
+ owner = btrfs_extent_data_ref_objectid(eb, dref);
+ owner_offset = btrfs_extent_data_ref_offset(eb, dref);
+ ret = check_extent_data_backref(fs_info, root_objectid, owner,
+ owner_offset, key.objectid, key.offset,
+ btrfs_extent_data_ref_count(eb, dref));
err |= ret;
break;
case BTRFS_SHARED_DATA_REF_KEY:
+ parent = offset;
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;
+ ret = UNKNOWN_TYPE;
+ err |= ret;
goto out;
}
+ if (err && repair) {
+ ret = repair_extent_item(trans, fs_info->extent_root, path,
+ key.objectid, num_bytes, parent, root_objectid,
+ owner, owner_offset, ret);
+ if (ret < 0)
+ goto out;
+ if (ret) {
+ goto next;
+ err = ret;
+ }
+ }
+
ptr += btrfs_extent_inline_ref_size(type);
- if (ptr < end)
- goto next;
+ goto next;
out:
return err;
l = path.nodes[0];
chunk = btrfs_item_ptr(l, path.slots[0], struct btrfs_chunk);
- if (btrfs_chunk_length(l, chunk) != length)
+ ret = btrfs_check_chunk_valid(fs_info, l, chunk, path.slots[0],
+ chunk_key.offset);
+ if (ret < 0)
+ goto out;
+
+ if (btrfs_stripe_length(fs_info, l, chunk) != length)
goto out;
num_stripes = btrfs_chunk_num_stripes(l, chunk);
struct btrfs_path path;
struct btrfs_key key;
struct btrfs_dev_extent *ptr;
+ u64 total_bytes;
u64 dev_id;
u64 used;
u64 total = 0;
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);
+ total_bytes = btrfs_device_total_bytes(eb, dev_item);
key.objectid = dev_id;
key.type = BTRFS_DEV_EXTENT_KEY;
/* Iterate dev_extents to calculate the used space of a device */
while (1) {
- btrfs_item_key_to_cpu(path.nodes[0], &key, path.slots[0]);
+ if (path.slots[0] >= btrfs_header_nritems(path.nodes[0]))
+ goto next;
+ btrfs_item_key_to_cpu(path.nodes[0], &key, path.slots[0]);
if (key.objectid > dev_id)
break;
if (key.type != BTRFS_DEV_EXTENT_KEY || key.objectid != dev_id)
BTRFS_DEV_EXTENT_KEY, dev_id);
return ACCOUNTING_MISMATCH;
}
+ check_dev_size_alignment(dev_id, total_bytes, fs_info->sectorsize);
+
return 0;
}
/* Iterate extent tree to account used space */
while (1) {
leaf = path.nodes[0];
+
+ /* Search slot can point to the last item beyond leaf nritems */
+ if (path.slots[0] >= btrfs_header_nritems(leaf))
+ goto next;
+
btrfs_item_key_to_cpu(leaf, &extent_key, path.slots[0]);
if (extent_key.objectid >= bg_key.objectid + bg_key.offset)
break;
error(
"block group[%llu %llu] used %llu but extent items used %llu",
bg_key.objectid, bg_key.offset, used, total);
- err |= ACCOUNTING_MISMATCH;
+ err |= BG_ACCOUNTING_ERROR;
+ }
+ return err;
+}
+
+/*
+ * Add block group item to the extent tree if @err contains REFERENCER_MISSING.
+ * FIXME: We still need to repair error of dev_item.
+ *
+ * Returns error after repair.
+ */
+static int repair_chunk_item(struct btrfs_trans_handle *trans,
+ struct btrfs_root *chunk_root,
+ struct btrfs_path *path, int err)
+{
+ struct btrfs_chunk *chunk;
+ struct btrfs_key chunk_key;
+ struct extent_buffer *eb = path->nodes[0];
+ u64 length;
+ int slot = path->slots[0];
+ u64 type;
+ int ret = 0;
+
+ btrfs_item_key_to_cpu(eb, &chunk_key, slot);
+ if (chunk_key.type != BTRFS_CHUNK_ITEM_KEY)
+ return err;
+ chunk = btrfs_item_ptr(eb, slot, struct btrfs_chunk);
+ type = btrfs_chunk_type(path->nodes[0], chunk);
+ length = btrfs_chunk_length(eb, chunk);
+
+ if (err & REFERENCER_MISSING) {
+ ret = btrfs_make_block_group(trans, chunk_root->fs_info, 0,
+ type, chunk_key.objectid, chunk_key.offset, length);
+ if (ret) {
+ error("fail to add block group item[%llu %llu]",
+ chunk_key.offset, length);
+ goto out;
+ } else {
+ err &= ~REFERENCER_MISSING;
+ printf("Added block group item[%llu %llu]\n",
+ chunk_key.offset, length);
+ }
}
+
+out:
return err;
}
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 stripe_len;
u64 type;
- u64 profile;
int num_stripes;
u64 offset;
u64 objectid;
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;
+ ret = btrfs_check_chunk_valid(fs_info, eb, chunk, slot,
+ chunk_key.offset);
+ if (ret < 0) {
+ error("chunk[%llu %llu) is invalid", chunk_key.offset,
+ chunk_end);
+ err |= BYTES_UNALIGNED | UNKNOWN_TYPE;
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;
}
num_stripes = btrfs_chunk_num_stripes(eb, chunk);
+ stripe_len = btrfs_stripe_length(fs_info, eb, chunk);
for (i = 0; i < num_stripes; i++) {
btrfs_release_path(&path);
btrfs_init_path(&path);
offset = btrfs_dev_extent_chunk_offset(leaf, ptr);
if (objectid != chunk_key.objectid ||
offset != chunk_key.offset ||
- btrfs_dev_extent_length(leaf, ptr) != length)
+ btrfs_dev_extent_length(leaf, ptr) != stripe_len)
goto not_match_dev;
continue;
not_match_dev:
return err;
}
+static int delete_extent_tree_item(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root,
+ struct btrfs_path *path)
+{
+ struct btrfs_key key;
+ int ret = 0;
+
+ btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
+ btrfs_release_path(path);
+ ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
+ if (ret) {
+ ret = -ENOENT;
+ goto out;
+ }
+
+ ret = btrfs_del_item(trans, root, path);
+ if (ret)
+ goto out;
+
+ if (path->slots[0] == 0)
+ btrfs_prev_leaf(root, path);
+ else
+ path->slots[0]--;
+out:
+ if (ret)
+ error("failed to delete root %llu item[%llu, %u, %llu]",
+ root->objectid, key.objectid, key.type, key.offset);
+ else
+ printf("Deleted root %llu item[%llu, %u, %llu]\n",
+ root->objectid, key.objectid, key.type, key.offset);
+ return ret;
+}
+
/*
* 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)
+static int check_leaf_items(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root, struct btrfs_path *path,
+ struct node_refs *nrefs, int account_bytes)
{
struct btrfs_fs_info *fs_info = root->fs_info;
struct btrfs_key key;
- int slot = 0;
+ struct extent_buffer *eb;
+ int slot;
int type;
struct btrfs_extent_data_ref *dref;
- int ret;
+ int ret = 0;
int err = 0;
-next:
+again:
+ eb = path->nodes[0];
+ slot = path->slots[0];
+ if (slot >= btrfs_header_nritems(eb)) {
+ if (slot == 0) {
+ error("empty leaf [%llu %u] root %llu", eb->start,
+ root->fs_info->nodesize, root->objectid);
+ err |= EIO;
+ }
+ goto out;
+ }
+
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);
+ ret = check_extent_data_item(root, path, nrefs, account_bytes);
+ if (repair && ret)
+ ret = repair_extent_data_item(trans, root, path, nrefs,
+ ret);
err |= ret;
break;
case BTRFS_BLOCK_GROUP_ITEM_KEY:
ret = check_block_group_item(fs_info, eb, slot);
+ if (repair &&
+ ret & REFERENCER_MISSING)
+ ret = delete_extent_tree_item(trans, root, path);
err |= ret;
break;
case BTRFS_DEV_ITEM_KEY:
break;
case BTRFS_CHUNK_ITEM_KEY:
ret = check_chunk_item(fs_info, eb, slot);
+ if (repair && ret)
+ ret = repair_chunk_item(trans, root, path, ret);
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);
+ break;
+ case BTRFS_EXTENT_ITEM_KEY:
+ case BTRFS_METADATA_ITEM_KEY:
+ ret = check_extent_item(trans, fs_info, path);
+ err |= ret;
+ break;
+ case BTRFS_EXTENT_CSUM_KEY:
+ total_csum_bytes += btrfs_item_size_nr(eb, slot);
+ err |= ret;
+ break;
+ case BTRFS_TREE_BLOCK_REF_KEY:
+ ret = check_tree_block_backref(fs_info, key.offset,
+ key.objectid, -1);
+ if (repair &&
+ ret & (REFERENCER_MISMATCH | REFERENCER_MISSING))
+ ret = delete_extent_tree_item(trans, root, path);
+ 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));
+ if (repair &&
+ ret & (REFERENCER_MISMATCH | REFERENCER_MISSING))
+ ret = delete_extent_tree_item(trans, root, path);
+ err |= ret;
+ break;
+ case BTRFS_SHARED_BLOCK_REF_KEY:
+ ret = check_shared_block_backref(fs_info, key.offset,
+ key.objectid, -1);
+ if (repair &&
+ ret & (REFERENCER_MISMATCH | REFERENCER_MISSING))
+ ret = delete_extent_tree_item(trans, root, path);
+ err |= ret;
+ break;
+ case BTRFS_SHARED_DATA_REF_KEY:
+ ret = check_shared_data_backref(fs_info, key.offset,
+ key.objectid);
+ if (repair &&
+ ret & (REFERENCER_MISMATCH | REFERENCER_MISSING))
+ ret = delete_extent_tree_item(trans, root, path);
+ err |= ret;
+ break;
+ default:
+ break;
}
+ ++path->slots[0];
+ goto again;
+out:
return err;
}
+static int pin_metadata_blocks(struct btrfs_fs_info *fs_info);
+
/*
* Low memory usage version check_chunks_and_extents.
*/
-static int check_chunks_and_extents_v2(struct btrfs_root *root)
+static int check_chunks_and_extents_v2(struct btrfs_fs_info *fs_info)
{
+ struct btrfs_trans_handle *trans = NULL;
struct btrfs_path path;
+ struct btrfs_key old_key;
struct btrfs_key key;
struct btrfs_root *root1;
+ struct btrfs_root *root;
struct btrfs_root *cur_root;
int err = 0;
int ret;
+ root = fs_info->fs_root;
+
+ if (repair) {
+ /* pin every tree block to avoid extent overwrite */
+ ret = pin_metadata_blocks(fs_info);
+ if (ret) {
+ error("failed to pin metadata blocks");
+ return ret;
+ }
+ trans = btrfs_start_transaction(fs_info->extent_root, 1);
+ if (IS_ERR(trans)) {
+ error("failed to start transaction before check");
+ return PTR_ERR(trans);
+ }
+ }
+
root1 = root->fs_info->chunk_root;
- ret = traverse_tree_block(root1, root1->node);
+ ret = check_btrfs_root(trans, root1, 0, 1);
err |= ret;
root1 = root->fs_info->tree_root;
- ret = traverse_tree_block(root1, root1->node);
+ ret = check_btrfs_root(trans, root1, 0, 1);
err |= ret;
btrfs_init_path(&path);
ret = btrfs_search_slot(NULL, root1, &key, &path, 0, 0);
if (ret) {
- error("cannot find extent treet in tree_root");
+ error("cannot find extent tree in tree_root");
goto out;
}
btrfs_item_key_to_cpu(path.nodes[0], &key, path.slots[0]);
if (key.type != BTRFS_ROOT_ITEM_KEY)
goto next;
+ old_key = key;
key.offset = (u64)-1;
- cur_root = btrfs_read_fs_root(root->fs_info, &key);
+ if (key.objectid == BTRFS_TREE_RELOC_OBJECTID)
+ cur_root = btrfs_read_fs_root_no_cache(root->fs_info,
+ &key);
+ else
+ cur_root = btrfs_read_fs_root(root->fs_info, &key);
if (IS_ERR(cur_root) || !cur_root) {
error("failed to read tree: %lld", key.objectid);
goto next;
}
- ret = traverse_tree_block(cur_root, cur_root->node);
+ ret = check_btrfs_root(trans, cur_root, 0, 1);
err |= ret;
+ if (key.objectid == BTRFS_TREE_RELOC_OBJECTID)
+ btrfs_free_fs_root(cur_root);
+
+ btrfs_release_path(&path);
+ ret = btrfs_search_slot(NULL, root->fs_info->tree_root,
+ &old_key, &path, 0, 0);
+ if (ret)
+ goto out;
next:
ret = btrfs_next_item(root1, &path);
if (ret)
goto out;
}
-
out:
+
+ /* if repair, update block accounting */
+ if (repair) {
+ ret = btrfs_fix_block_accounting(trans, root);
+ if (ret)
+ err |= ret;
+ else
+ err &= ~BG_ACCOUNTING_ERROR;
+ }
+
+ if (trans)
+ btrfs_commit_transaction(trans, root->fs_info->extent_root);
+
btrfs_release_path(&path);
+
return err;
}
+static int do_check_chunks_and_extents(struct btrfs_fs_info *fs_info)
+{
+ int ret;
+
+ if (!ctx.progress_enabled)
+ fprintf(stderr, "checking extents\n");
+ if (check_mode == CHECK_MODE_LOWMEM)
+ ret = check_chunks_and_extents_v2(fs_info);
+ else
+ ret = check_chunks_and_extents(fs_info);
+
+ /* Also repair device size related problems */
+ if (repair && !ret) {
+ ret = btrfs_fix_device_and_super_size(fs_info);
+ if (ret > 0)
+ ret = 0;
+ }
+ return ret;
+}
+
static int btrfs_fsck_reinit_root(struct btrfs_trans_handle *trans,
struct btrfs_root *root, int overwrite)
{
goto init;
}
c = btrfs_alloc_free_block(trans, root,
- root->nodesize,
+ root->fs_info->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 nodesize;
int level = btrfs_header_level(eb);
int nritems;
int ret;
btrfs_pin_extent(fs_info, eb->start, eb->len);
- nodesize = btrfs_super_nodesize(fs_info->super_copy);
nritems = btrfs_header_nritems(eb);
for (i = 0; i < nritems; i++) {
if (level == 0) {
* in, but for now this doesn't actually use the root so
* just pass in extent_root.
*/
- tmp = read_tree_block(fs_info->extent_root, bytenr,
- nodesize, 0);
+ tmp = read_tree_block(fs_info, bytenr, 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, nodesize);
+ btrfs_pin_extent(fs_info, bytenr,
+ fs_info->nodesize);
continue;
}
- tmp = read_tree_block(fs_info->extent_root, bytenr,
- nodesize, 0);
+ tmp = read_tree_block(fs_info, bytenr, 0);
if (!extent_buffer_uptodate(tmp)) {
fprintf(stderr, "Error reading tree block\n");
return -EIO;
key.objectid, key.offset,
btrfs_chunk_length(leaf, chunk));
set_extent_dirty(&fs_info->free_space_cache, key.offset,
- key.offset + btrfs_chunk_length(leaf, chunk),
- GFP_NOFS);
+ key.offset + btrfs_chunk_length(leaf, chunk));
path.slots[0]++;
}
start = 0;
* the leaves of any fs roots and pin down the bytes for any file
* extents we find. Not hard but why do it if we don't have to?
*/
- if (btrfs_fs_incompat(fs_info, BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS)) {
+ if (btrfs_fs_incompat(fs_info, MIXED_GROUPS)) {
fprintf(stderr, "We don't support re-initing the extent tree "
"for mixed block groups yet, please notify a btrfs "
"developer you want to do this so they can add this "
struct btrfs_root *csum_root, char *buf, u64 start,
u64 len)
{
+ struct btrfs_fs_info *fs_info = csum_root->fs_info;
u64 offset = 0;
u64 sectorsize;
int ret = 0;
while (offset < len) {
- sectorsize = csum_root->sectorsize;
- ret = read_extent_data(csum_root, buf, start + offset,
+ sectorsize = fs_info->sectorsize;
+ ret = read_extent_data(fs_info, buf, start + offset,
§orsize, 0);
if (ret)
break;
int slot = 0;
int ret = 0;
- buf = malloc(cur_root->fs_info->csum_root->sectorsize);
+ buf = malloc(cur_root->fs_info->sectorsize);
if (!buf)
return -ENOMEM;
return ret;
}
- buf = malloc(csum_root->sectorsize);
+ buf = malloc(csum_root->fs_info->sectorsize);
if (!buf) {
btrfs_release_path(&path);
return -ENOMEM;
return ret;
}
-static int maybe_repair_root_item(struct btrfs_fs_info *info,
- struct btrfs_path *path,
+static int maybe_repair_root_item(struct btrfs_path *path,
const struct btrfs_key *root_key,
const int read_only_mode)
{
if (found_key.objectid == BTRFS_TREE_RELOC_OBJECTID)
goto next;
- ret = maybe_repair_root_item(info, &path, &found_key,
- trans ? 0 : 1);
+ ret = maybe_repair_root_item(&path, &found_key, trans ? 0 : 1);
if (ret < 0)
goto out;
if (ret) {
return ret;
}
+static int do_clear_free_space_cache(struct btrfs_fs_info *fs_info,
+ int clear_version)
+{
+ int ret = 0;
+
+ if (clear_version == 1) {
+ if (btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE)) {
+ error(
+ "free space cache v2 detected, use --clear-space-cache v2");
+ ret = 1;
+ goto close_out;
+ }
+ printf("Clearing free space cache\n");
+ ret = clear_free_space_cache(fs_info);
+ if (ret) {
+ error("failed to clear free space cache");
+ ret = 1;
+ } else {
+ printf("Free space cache cleared\n");
+ }
+ } else if (clear_version == 2) {
+ if (!btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE)) {
+ printf("no free space cache v2 to clear\n");
+ ret = 0;
+ goto close_out;
+ }
+ printf("Clear free space cache v2\n");
+ ret = btrfs_clear_free_space_tree(fs_info);
+ if (ret) {
+ error("failed to clear free space cache v2: %d", ret);
+ ret = 1;
+ } else {
+ printf("free space cache v2 cleared\n");
+ }
+ }
+close_out:
+ return ret;
+}
+
const char * const cmd_check_usage[] = {
"btrfs check [options] <device>",
"Check structural integrity of a filesystem (unmounted).",
"",
"-s|--super <superblock> use this superblock copy",
"-b|--backup use the first valid backup root copy",
+ "--force skip mount checks, repair is not possible",
"--repair try to repair the filesystem",
"--readonly run in read-only mode (default)",
"--init-csum-tree create a new CRC tree",
u64 tree_root_bytenr = 0;
u64 chunk_root_bytenr = 0;
char uuidbuf[BTRFS_UUID_UNPARSED_SIZE];
- int ret;
+ int ret = 0;
+ int err = 0;
u64 num;
int init_csum_tree = 0;
int readonly = 0;
int qgroup_report = 0;
int qgroups_repaired = 0;
unsigned ctree_flags = OPEN_CTREE_EXCLUSIVE;
+ int force = 0;
while(1) {
int c;
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 };
+ GETOPT_VAL_MODE, GETOPT_VAL_CLEAR_SPACE_CACHE,
+ GETOPT_VAL_FORCE };
static const struct option long_options[] = {
{ "super", required_argument, NULL, 's' },
{ "repair", no_argument, NULL, GETOPT_VAL_REPAIR },
GETOPT_VAL_MODE },
{ "clear-space-cache", required_argument, NULL,
GETOPT_VAL_CLEAR_SPACE_CACHE},
+ { "force", no_argument, NULL, GETOPT_VAL_FORCE },
{ NULL, 0, NULL, 0}
};
- c = getopt_long(argc, argv, "as:br:p", long_options, NULL);
+ c = getopt_long(argc, argv, "as:br:pEQ", long_options, NULL);
if (c < 0)
break;
switch(c) {
}
ctree_flags |= OPEN_CTREE_WRITES;
break;
+ case GETOPT_VAL_FORCE:
+ force = 1;
+ break;
}
}
}
/*
- * Not supported yet
+ * experimental and dangerous
*/
- if (repair && check_mode == CHECK_MODE_LOWMEM) {
- error("low memory mode doesn't support repair yet");
- exit(1);
- }
+ if (repair && check_mode == CHECK_MODE_LOWMEM)
+ warning("low-memory mode repair support is only partial");
radix_tree_init();
cache_tree_init(&root_cache);
- if((ret = check_mounted(argv[optind])) < 0) {
- error("could not check mount status: %s", strerror(-ret));
- goto err_out;
- } else if(ret) {
- error("%s is currently mounted, aborting", argv[optind]);
- ret = -EBUSY;
- goto err_out;
+ ret = check_mounted(argv[optind]);
+ if (!force) {
+ if (ret < 0) {
+ error("could not check mount status: %s",
+ strerror(-ret));
+ err |= !!ret;
+ goto err_out;
+ } else if (ret) {
+ error(
+"%s is currently mounted, use --force if you really intend to check the filesystem",
+ argv[optind]);
+ ret = -EBUSY;
+ err |= !!ret;
+ goto err_out;
+ }
+ } else {
+ if (repair) {
+ error("repair and --force is not yet supported");
+ ret = 1;
+ err |= !!ret;
+ goto err_out;
+ }
+ if (ret < 0) {
+ warning(
+"cannot check mount status of %s, the filesystem could be mounted, continuing because of --force",
+ argv[optind]);
+ } else if (ret) {
+ warning(
+ "filesystem mounted, continuing because of --force");
+ }
+ /* A block device is mounted in exclusive mode by kernel */
+ ctree_flags &= ~OPEN_CTREE_EXCLUSIVE;
}
/* only allow partial opening under repair mode */
if (!info) {
error("cannot open file system");
ret = -EIO;
+ err |= !!ret;
goto err_out;
}
global_info = info;
root = info->fs_root;
- if (clear_space_cache == 1) {
- if (btrfs_fs_compat_ro(info,
- BTRFS_FEATURE_COMPAT_RO_FREE_SPACE_TREE)) {
- error(
- "free space cache v2 detected, use --clear-space-cache v2");
- 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");
- }
+ uuid_unparse(info->super_copy->fsid, uuidbuf);
+
+ printf("Checking filesystem on %s\nUUID: %s\n", argv[optind], uuidbuf);
+
+ /*
+ * Check the bare minimum before starting anything else that could rely
+ * on it, namely the tree roots, any local consistency checks
+ */
+ if (!extent_buffer_uptodate(info->tree_root->node) ||
+ !extent_buffer_uptodate(info->dev_root->node) ||
+ !extent_buffer_uptodate(info->chunk_root->node)) {
+ error("critical roots corrupted, unable to check the filesystem");
+ err |= !!ret;
+ ret = -EIO;
goto close_out;
- } else if (clear_space_cache == 2) {
- if (!btrfs_fs_compat_ro(info,
- BTRFS_FEATURE_COMPAT_RO_FREE_SPACE_TREE)) {
- printf("no free space cache v2 to clear\n");
- ret = 0;
- goto close_out;
- }
- printf("Clear free space cache v2\n");
- ret = btrfs_clear_free_space_tree(info);
- if (ret) {
- error("failed to clear free space cache v2: %d", ret);
- ret = 1;
- } else {
- printf("free space cache v2 cleared\n");
- }
+ }
+
+ if (clear_space_cache) {
+ ret = do_clear_free_space_cache(info, clear_space_cache);
+ err |= !!ret;
goto close_out;
}
ret = ask_user("repair mode will force to clear out log tree, are you sure?");
if (!ret) {
ret = 1;
+ err |= !!ret;
goto close_out;
}
ret = zero_log_tree(root);
+ err |= !!ret;
if (ret) {
error("failed to zero log tree: %d", ret);
goto close_out;
}
}
- uuid_unparse(info->super_copy->fsid, uuidbuf);
if (qgroup_report) {
printf("Print quota groups for %s\nUUID: %s\n", argv[optind],
uuidbuf);
ret = qgroup_verify_all(info);
+ err |= !!ret;
if (ret == 0)
report_qgroups(1);
goto close_out;
printf("Print extent state for subvolume %llu on %s\nUUID: %s\n",
subvolid, argv[optind], uuidbuf);
ret = print_extent_state(info, subvolid);
- goto close_out;
- }
- printf("Checking filesystem on %s\nUUID: %s\n", argv[optind], uuidbuf);
-
- if (!extent_buffer_uptodate(info->tree_root->node) ||
- !extent_buffer_uptodate(info->dev_root->node) ||
- !extent_buffer_uptodate(info->chunk_root->node)) {
- error("critical roots corrupted, unable to check the filesystem");
- ret = -EIO;
+ err |= !!ret;
goto close_out;
}
if (IS_ERR(trans)) {
error("error starting transaction");
ret = PTR_ERR(trans);
+ err |= !!ret;
goto close_out;
}
if (init_extent_tree) {
printf("Creating a new extent tree\n");
ret = reinit_extent_tree(trans, info);
+ err |= !!ret;
if (ret)
goto close_out;
}
error("checksum tree initialization failed: %d",
ret);
ret = -EIO;
+ err |= !!ret;
goto close_out;
}
ret = fill_csum_tree(trans, info->csum_root,
init_extent_tree);
+ err |= !!ret;
if (ret) {
error("checksum tree refilling failed: %d", ret);
return -EIO;
* extent entries for all of the items it finds.
*/
ret = btrfs_commit_transaction(trans, info->extent_root);
+ err |= !!ret;
if (ret)
goto close_out;
}
if (!extent_buffer_uptodate(info->extent_root->node)) {
error("critical: extent_root, unable to check the filesystem");
ret = -EIO;
+ err |= !!ret;
goto close_out;
}
if (!extent_buffer_uptodate(info->csum_root->node)) {
error("critical: csum_root, unable to check the filesystem");
ret = -EIO;
+ err |= !!ret;
goto close_out;
}
- if (!ctx.progress_enabled)
- fprintf(stderr, "checking extents\n");
- if (check_mode == CHECK_MODE_LOWMEM)
- ret = check_chunks_and_extents_v2(root);
- else
- ret = check_chunks_and_extents(root);
+ if (!init_extent_tree) {
+ ret = repair_root_items(info);
+ if (ret < 0) {
+ err = !!ret;
+ error("failed to repair root items: %s", strerror(-ret));
+ goto close_out;
+ }
+ if (repair) {
+ fprintf(stderr, "Fixed %d roots.\n", ret);
+ ret = 0;
+ } else if (ret > 0) {
+ fprintf(stderr,
+ "Found %d roots with an outdated root item.\n",
+ ret);
+ fprintf(stderr,
+ "Please run a filesystem check with the option --repair to fix them.\n");
+ ret = 1;
+ err |= ret;
+ goto close_out;
+ }
+ }
+
+ ret = do_check_chunks_and_extents(info);
+ err |= !!ret;
if (ret)
error(
"errors found in extent allocation tree or chunk allocation");
- ret = repair_root_items(info);
- if (ret < 0)
- goto close_out;
- if (repair) {
- fprintf(stderr, "Fixed %d roots.\n", ret);
- ret = 0;
- } else if (ret > 0) {
- fprintf(stderr,
- "Found %d roots with an outdated root item.\n",
- ret);
- fprintf(stderr,
- "Please run a filesystem check with the option --repair to fix them.\n");
- ret = 1;
- goto close_out;
- }
+ /* Only re-check super size after we checked and repaired the fs */
+ err |= !is_super_size_valid(info);
if (!ctx.progress_enabled) {
- if (btrfs_fs_compat_ro(info, BTRFS_FEATURE_COMPAT_RO_FREE_SPACE_TREE))
+ if (btrfs_fs_compat_ro(info, FREE_SPACE_TREE))
fprintf(stderr, "checking free space tree\n");
else
fprintf(stderr, "checking free space cache\n");
}
ret = check_space_cache(root);
- if (ret)
+ err |= !!ret;
+ if (ret) {
+ if (btrfs_fs_compat_ro(info, FREE_SPACE_TREE))
+ error("errors found in free space tree");
+ else
+ error("errors found in free space cache");
goto out;
+ }
/*
* We used to have to have these hole extents in between our real
* are no gaps in the file extents for inodes, otherwise we can just
* ignore it when this happens.
*/
- no_holes = btrfs_fs_incompat(root->fs_info,
- BTRFS_FEATURE_INCOMPAT_NO_HOLES);
- if (!ctx.progress_enabled)
- fprintf(stderr, "checking fs roots\n");
- if (check_mode == CHECK_MODE_LOWMEM)
- ret = check_fs_roots_v2(root->fs_info);
- else
- ret = check_fs_roots(root, &root_cache);
- if (ret)
+ no_holes = btrfs_fs_incompat(root->fs_info, NO_HOLES);
+ ret = do_check_fs_roots(info, &root_cache);
+ err |= !!ret;
+ if (ret) {
+ error("errors found in fs roots");
goto out;
+ }
fprintf(stderr, "checking csums\n");
ret = check_csums(root);
- if (ret)
+ err |= !!ret;
+ if (ret) {
+ error("errors found in csum tree");
goto out;
+ }
fprintf(stderr, "checking root refs\n");
/* For low memory mode, check_fs_roots_v2 handles root refs */
if (check_mode != CHECK_MODE_LOWMEM) {
ret = check_root_refs(root, &root_cache);
- if (ret)
+ err |= !!ret;
+ if (ret) {
+ error("errors found in root refs");
goto out;
+ }
}
while (repair && !list_empty(&root->fs_info->recow_ebs)) {
struct extent_buffer, recow);
list_del_init(&eb->recow);
ret = recow_extent_buffer(root, eb);
- if (ret)
+ err |= !!ret;
+ if (ret) {
+ error("fails to fix transid errors");
break;
+ }
}
while (!list_empty(&delete_items)) {
bad = list_first_entry(&delete_items, struct bad_item, list);
list_del_init(&bad->list);
- if (repair)
+ if (repair) {
ret = delete_bad_item(root, bad);
+ err |= !!ret;
+ }
free(bad);
}
if (info->quota_enabled) {
- int err;
fprintf(stderr, "checking quota groups\n");
- err = qgroup_verify_all(info);
- if (err)
+ ret = qgroup_verify_all(info);
+ err |= !!ret;
+ if (ret) {
+ error("failed to check quota groups");
goto out;
+ }
report_qgroups(0);
- err = repair_qgroups(info, &qgroups_repaired);
- if (err)
+ ret = repair_qgroups(info, &qgroups_repaired);
+ err |= !!ret;
+ if (err) {
+ error("failed to repair quota groups");
goto out;
+ }
+ ret = 0;
}
if (!list_empty(&root->fs_info->recow_ebs)) {
error("transid errors in file system");
ret = 1;
+ err |= !!ret;
}
out:
- /* Don't override original ret */
- if (!ret && qgroups_repaired)
- ret = qgroups_repaired;
-
- if (found_old_backref) { /*
- * there was a disk format change when mixed
- * backref was in testing tree. The old format
- * existed about one week.
- */
- printf("\n * Found old mixed backref format. "
- "The old format is not supported! *"
- "\n * Please mount the FS in readonly mode, "
- "backup data and re-format the FS. *\n\n");
- ret = 1;
- }
- printf("found %llu bytes used err is %d\n",
- (unsigned long long)bytes_used, ret);
+ printf("found %llu bytes used, ",
+ (unsigned long long)bytes_used);
+ if (err)
+ printf("error(s) found\n");
+ else
+ printf("no error found\n");
printf("total csum bytes: %llu\n",(unsigned long long)total_csum_bytes);
printf("total tree bytes: %llu\n",
(unsigned long long)total_btree_bytes);
if (ctx.progress_enabled)
task_deinit(ctx.info);
- return ret;
+ return err;
}