summaryrefslogtreecommitdiff
path: root/fs/btrfs/backref.c
diff options
context:
space:
mode:
authorAndré Fabian Silva Delgado <emulatorman@parabola.nu>2015-08-05 17:04:01 -0300
committerAndré Fabian Silva Delgado <emulatorman@parabola.nu>2015-08-05 17:04:01 -0300
commit57f0f512b273f60d52568b8c6b77e17f5636edc0 (patch)
tree5e910f0e82173f4ef4f51111366a3f1299037a7b /fs/btrfs/backref.c
Initial import
Diffstat (limited to 'fs/btrfs/backref.c')
-rw-r--r--fs/btrfs/backref.c1978
1 files changed, 1978 insertions, 0 deletions
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
new file mode 100644
index 000000000..614aaa196
--- /dev/null
+++ b/fs/btrfs/backref.c
@@ -0,0 +1,1978 @@
+/*
+ * Copyright (C) 2011 STRATO. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License v2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public
+ * License along with this program; if not, write to the
+ * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
+ * Boston, MA 021110-1307, USA.
+ */
+
+#include <linux/vmalloc.h>
+#include "ctree.h"
+#include "disk-io.h"
+#include "backref.h"
+#include "ulist.h"
+#include "transaction.h"
+#include "delayed-ref.h"
+#include "locking.h"
+
+/* Just an arbitrary number so we can be sure this happened */
+#define BACKREF_FOUND_SHARED 6
+
+struct extent_inode_elem {
+ u64 inum;
+ u64 offset;
+ struct extent_inode_elem *next;
+};
+
+static int check_extent_in_eb(struct btrfs_key *key, struct extent_buffer *eb,
+ struct btrfs_file_extent_item *fi,
+ u64 extent_item_pos,
+ struct extent_inode_elem **eie)
+{
+ u64 offset = 0;
+ struct extent_inode_elem *e;
+
+ if (!btrfs_file_extent_compression(eb, fi) &&
+ !btrfs_file_extent_encryption(eb, fi) &&
+ !btrfs_file_extent_other_encoding(eb, fi)) {
+ u64 data_offset;
+ u64 data_len;
+
+ data_offset = btrfs_file_extent_offset(eb, fi);
+ data_len = btrfs_file_extent_num_bytes(eb, fi);
+
+ if (extent_item_pos < data_offset ||
+ extent_item_pos >= data_offset + data_len)
+ return 1;
+ offset = extent_item_pos - data_offset;
+ }
+
+ e = kmalloc(sizeof(*e), GFP_NOFS);
+ if (!e)
+ return -ENOMEM;
+
+ e->next = *eie;
+ e->inum = key->objectid;
+ e->offset = key->offset + offset;
+ *eie = e;
+
+ return 0;
+}
+
+static void free_inode_elem_list(struct extent_inode_elem *eie)
+{
+ struct extent_inode_elem *eie_next;
+
+ for (; eie; eie = eie_next) {
+ eie_next = eie->next;
+ kfree(eie);
+ }
+}
+
+static int find_extent_in_eb(struct extent_buffer *eb, u64 wanted_disk_byte,
+ u64 extent_item_pos,
+ struct extent_inode_elem **eie)
+{
+ u64 disk_byte;
+ struct btrfs_key key;
+ struct btrfs_file_extent_item *fi;
+ int slot;
+ int nritems;
+ int extent_type;
+ int ret;
+
+ /*
+ * from the shared data ref, we only have the leaf but we need
+ * the key. thus, we must look into all items and see that we
+ * find one (some) with a reference to our extent item.
+ */
+ nritems = btrfs_header_nritems(eb);
+ for (slot = 0; slot < nritems; ++slot) {
+ btrfs_item_key_to_cpu(eb, &key, slot);
+ if (key.type != BTRFS_EXTENT_DATA_KEY)
+ continue;
+ fi = btrfs_item_ptr(eb, slot, struct btrfs_file_extent_item);
+ extent_type = btrfs_file_extent_type(eb, fi);
+ if (extent_type == BTRFS_FILE_EXTENT_INLINE)
+ continue;
+ /* don't skip BTRFS_FILE_EXTENT_PREALLOC, we can handle that */
+ disk_byte = btrfs_file_extent_disk_bytenr(eb, fi);
+ if (disk_byte != wanted_disk_byte)
+ continue;
+
+ ret = check_extent_in_eb(&key, eb, fi, extent_item_pos, eie);
+ if (ret < 0)
+ return ret;
+ }
+
+ return 0;
+}
+
+/*
+ * this structure records all encountered refs on the way up to the root
+ */
+struct __prelim_ref {
+ struct list_head list;
+ u64 root_id;
+ struct btrfs_key key_for_search;
+ int level;
+ int count;
+ struct extent_inode_elem *inode_list;
+ u64 parent;
+ u64 wanted_disk_byte;
+};
+
+static struct kmem_cache *btrfs_prelim_ref_cache;
+
+int __init btrfs_prelim_ref_init(void)
+{
+ btrfs_prelim_ref_cache = kmem_cache_create("btrfs_prelim_ref",
+ sizeof(struct __prelim_ref),
+ 0,
+ SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD,
+ NULL);
+ if (!btrfs_prelim_ref_cache)
+ return -ENOMEM;
+ return 0;
+}
+
+void btrfs_prelim_ref_exit(void)
+{
+ if (btrfs_prelim_ref_cache)
+ kmem_cache_destroy(btrfs_prelim_ref_cache);
+}
+
+/*
+ * the rules for all callers of this function are:
+ * - obtaining the parent is the goal
+ * - if you add a key, you must know that it is a correct key
+ * - if you cannot add the parent or a correct key, then we will look into the
+ * block later to set a correct key
+ *
+ * delayed refs
+ * ============
+ * backref type | shared | indirect | shared | indirect
+ * information | tree | tree | data | data
+ * --------------------+--------+----------+--------+----------
+ * parent logical | y | - | - | -
+ * key to resolve | - | y | y | y
+ * tree block logical | - | - | - | -
+ * root for resolving | y | y | y | y
+ *
+ * - column 1: we've the parent -> done
+ * - column 2, 3, 4: we use the key to find the parent
+ *
+ * on disk refs (inline or keyed)
+ * ==============================
+ * backref type | shared | indirect | shared | indirect
+ * information | tree | tree | data | data
+ * --------------------+--------+----------+--------+----------
+ * parent logical | y | - | y | -
+ * key to resolve | - | - | - | y
+ * tree block logical | y | y | y | y
+ * root for resolving | - | y | y | y
+ *
+ * - column 1, 3: we've the parent -> done
+ * - column 2: we take the first key from the block to find the parent
+ * (see __add_missing_keys)
+ * - column 4: we use the key to find the parent
+ *
+ * additional information that's available but not required to find the parent
+ * block might help in merging entries to gain some speed.
+ */
+
+static int __add_prelim_ref(struct list_head *head, u64 root_id,
+ struct btrfs_key *key, int level,
+ u64 parent, u64 wanted_disk_byte, int count,
+ gfp_t gfp_mask)
+{
+ struct __prelim_ref *ref;
+
+ if (root_id == BTRFS_DATA_RELOC_TREE_OBJECTID)
+ return 0;
+
+ ref = kmem_cache_alloc(btrfs_prelim_ref_cache, gfp_mask);
+ if (!ref)
+ return -ENOMEM;
+
+ ref->root_id = root_id;
+ if (key)
+ ref->key_for_search = *key;
+ else
+ memset(&ref->key_for_search, 0, sizeof(ref->key_for_search));
+
+ ref->inode_list = NULL;
+ ref->level = level;
+ ref->count = count;
+ ref->parent = parent;
+ ref->wanted_disk_byte = wanted_disk_byte;
+ list_add_tail(&ref->list, head);
+
+ return 0;
+}
+
+static int add_all_parents(struct btrfs_root *root, struct btrfs_path *path,
+ struct ulist *parents, struct __prelim_ref *ref,
+ int level, u64 time_seq, const u64 *extent_item_pos,
+ u64 total_refs)
+{
+ int ret = 0;
+ int slot;
+ struct extent_buffer *eb;
+ struct btrfs_key key;
+ struct btrfs_key *key_for_search = &ref->key_for_search;
+ struct btrfs_file_extent_item *fi;
+ struct extent_inode_elem *eie = NULL, *old = NULL;
+ u64 disk_byte;
+ u64 wanted_disk_byte = ref->wanted_disk_byte;
+ u64 count = 0;
+
+ if (level != 0) {
+ eb = path->nodes[level];
+ ret = ulist_add(parents, eb->start, 0, GFP_NOFS);
+ if (ret < 0)
+ return ret;
+ return 0;
+ }
+
+ /*
+ * We normally enter this function with the path already pointing to
+ * the first item to check. But sometimes, we may enter it with
+ * slot==nritems. In that case, go to the next leaf before we continue.
+ */
+ if (path->slots[0] >= btrfs_header_nritems(path->nodes[0]))
+ ret = btrfs_next_old_leaf(root, path, time_seq);
+
+ while (!ret && count < total_refs) {
+ eb = path->nodes[0];
+ slot = path->slots[0];
+
+ btrfs_item_key_to_cpu(eb, &key, slot);
+
+ if (key.objectid != key_for_search->objectid ||
+ key.type != BTRFS_EXTENT_DATA_KEY)
+ break;
+
+ fi = btrfs_item_ptr(eb, slot, struct btrfs_file_extent_item);
+ disk_byte = btrfs_file_extent_disk_bytenr(eb, fi);
+
+ if (disk_byte == wanted_disk_byte) {
+ eie = NULL;
+ old = NULL;
+ count++;
+ if (extent_item_pos) {
+ ret = check_extent_in_eb(&key, eb, fi,
+ *extent_item_pos,
+ &eie);
+ if (ret < 0)
+ break;
+ }
+ if (ret > 0)
+ goto next;
+ ret = ulist_add_merge_ptr(parents, eb->start,
+ eie, (void **)&old, GFP_NOFS);
+ if (ret < 0)
+ break;
+ if (!ret && extent_item_pos) {
+ while (old->next)
+ old = old->next;
+ old->next = eie;
+ }
+ eie = NULL;
+ }
+next:
+ ret = btrfs_next_old_item(root, path, time_seq);
+ }
+
+ if (ret > 0)
+ ret = 0;
+ else if (ret < 0)
+ free_inode_elem_list(eie);
+ return ret;
+}
+
+/*
+ * resolve an indirect backref in the form (root_id, key, level)
+ * to a logical address
+ */
+static int __resolve_indirect_ref(struct btrfs_fs_info *fs_info,
+ struct btrfs_path *path, u64 time_seq,
+ struct __prelim_ref *ref,
+ struct ulist *parents,
+ const u64 *extent_item_pos, u64 total_refs)
+{
+ struct btrfs_root *root;
+ struct btrfs_key root_key;
+ struct extent_buffer *eb;
+ int ret = 0;
+ int root_level;
+ int level = ref->level;
+ int index;
+
+ root_key.objectid = ref->root_id;
+ root_key.type = BTRFS_ROOT_ITEM_KEY;
+ root_key.offset = (u64)-1;
+
+ index = srcu_read_lock(&fs_info->subvol_srcu);
+
+ root = btrfs_read_fs_root_no_name(fs_info, &root_key);
+ if (IS_ERR(root)) {
+ srcu_read_unlock(&fs_info->subvol_srcu, index);
+ ret = PTR_ERR(root);
+ goto out;
+ }
+
+ if (path->search_commit_root)
+ root_level = btrfs_header_level(root->commit_root);
+ else
+ root_level = btrfs_old_root_level(root, time_seq);
+
+ if (root_level + 1 == level) {
+ srcu_read_unlock(&fs_info->subvol_srcu, index);
+ goto out;
+ }
+
+ path->lowest_level = level;
+ ret = btrfs_search_old_slot(root, &ref->key_for_search, path, time_seq);
+
+ /* root node has been locked, we can release @subvol_srcu safely here */
+ srcu_read_unlock(&fs_info->subvol_srcu, index);
+
+ pr_debug("search slot in root %llu (level %d, ref count %d) returned "
+ "%d for key (%llu %u %llu)\n",
+ ref->root_id, level, ref->count, ret,
+ ref->key_for_search.objectid, ref->key_for_search.type,
+ ref->key_for_search.offset);
+ if (ret < 0)
+ goto out;
+
+ eb = path->nodes[level];
+ while (!eb) {
+ if (WARN_ON(!level)) {
+ ret = 1;
+ goto out;
+ }
+ level--;
+ eb = path->nodes[level];
+ }
+
+ ret = add_all_parents(root, path, parents, ref, level, time_seq,
+ extent_item_pos, total_refs);
+out:
+ path->lowest_level = 0;
+ btrfs_release_path(path);
+ return ret;
+}
+
+/*
+ * resolve all indirect backrefs from the list
+ */
+static int __resolve_indirect_refs(struct btrfs_fs_info *fs_info,
+ struct btrfs_path *path, u64 time_seq,
+ struct list_head *head,
+ const u64 *extent_item_pos, u64 total_refs,
+ u64 root_objectid)
+{
+ int err;
+ int ret = 0;
+ struct __prelim_ref *ref;
+ struct __prelim_ref *ref_safe;
+ struct __prelim_ref *new_ref;
+ struct ulist *parents;
+ struct ulist_node *node;
+ struct ulist_iterator uiter;
+
+ parents = ulist_alloc(GFP_NOFS);
+ if (!parents)
+ return -ENOMEM;
+
+ /*
+ * _safe allows us to insert directly after the current item without
+ * iterating over the newly inserted items.
+ * we're also allowed to re-assign ref during iteration.
+ */
+ list_for_each_entry_safe(ref, ref_safe, head, list) {
+ if (ref->parent) /* already direct */
+ continue;
+ if (ref->count == 0)
+ continue;
+ if (root_objectid && ref->root_id != root_objectid) {
+ ret = BACKREF_FOUND_SHARED;
+ goto out;
+ }
+ err = __resolve_indirect_ref(fs_info, path, time_seq, ref,
+ parents, extent_item_pos,
+ total_refs);
+ /*
+ * we can only tolerate ENOENT,otherwise,we should catch error
+ * and return directly.
+ */
+ if (err == -ENOENT) {
+ continue;
+ } else if (err) {
+ ret = err;
+ goto out;
+ }
+
+ /* we put the first parent into the ref at hand */
+ ULIST_ITER_INIT(&uiter);
+ node = ulist_next(parents, &uiter);
+ ref->parent = node ? node->val : 0;
+ ref->inode_list = node ?
+ (struct extent_inode_elem *)(uintptr_t)node->aux : NULL;
+
+ /* additional parents require new refs being added here */
+ while ((node = ulist_next(parents, &uiter))) {
+ new_ref = kmem_cache_alloc(btrfs_prelim_ref_cache,
+ GFP_NOFS);
+ if (!new_ref) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ memcpy(new_ref, ref, sizeof(*ref));
+ new_ref->parent = node->val;
+ new_ref->inode_list = (struct extent_inode_elem *)
+ (uintptr_t)node->aux;
+ list_add(&new_ref->list, &ref->list);
+ }
+ ulist_reinit(parents);
+ }
+out:
+ ulist_free(parents);
+ return ret;
+}
+
+static inline int ref_for_same_block(struct __prelim_ref *ref1,
+ struct __prelim_ref *ref2)
+{
+ if (ref1->level != ref2->level)
+ return 0;
+ if (ref1->root_id != ref2->root_id)
+ return 0;
+ if (ref1->key_for_search.type != ref2->key_for_search.type)
+ return 0;
+ if (ref1->key_for_search.objectid != ref2->key_for_search.objectid)
+ return 0;
+ if (ref1->key_for_search.offset != ref2->key_for_search.offset)
+ return 0;
+ if (ref1->parent != ref2->parent)
+ return 0;
+
+ return 1;
+}
+
+/*
+ * read tree blocks and add keys where required.
+ */
+static int __add_missing_keys(struct btrfs_fs_info *fs_info,
+ struct list_head *head)
+{
+ struct list_head *pos;
+ struct extent_buffer *eb;
+
+ list_for_each(pos, head) {
+ struct __prelim_ref *ref;
+ ref = list_entry(pos, struct __prelim_ref, list);
+
+ if (ref->parent)
+ continue;
+ if (ref->key_for_search.type)
+ continue;
+ BUG_ON(!ref->wanted_disk_byte);
+ eb = read_tree_block(fs_info->tree_root, ref->wanted_disk_byte,
+ 0);
+ if (!eb || !extent_buffer_uptodate(eb)) {
+ free_extent_buffer(eb);
+ return -EIO;
+ }
+ btrfs_tree_read_lock(eb);
+ if (btrfs_header_level(eb) == 0)
+ btrfs_item_key_to_cpu(eb, &ref->key_for_search, 0);
+ else
+ btrfs_node_key_to_cpu(eb, &ref->key_for_search, 0);
+ btrfs_tree_read_unlock(eb);
+ free_extent_buffer(eb);
+ }
+ return 0;
+}
+
+/*
+ * merge two lists of backrefs and adjust counts accordingly
+ *
+ * mode = 1: merge identical keys, if key is set
+ * FIXME: if we add more keys in __add_prelim_ref, we can merge more here.
+ * additionally, we could even add a key range for the blocks we
+ * looked into to merge even more (-> replace unresolved refs by those
+ * having a parent).
+ * mode = 2: merge identical parents
+ */
+static void __merge_refs(struct list_head *head, int mode)
+{
+ struct list_head *pos1;
+
+ list_for_each(pos1, head) {
+ struct list_head *n2;
+ struct list_head *pos2;
+ struct __prelim_ref *ref1;
+
+ ref1 = list_entry(pos1, struct __prelim_ref, list);
+
+ for (pos2 = pos1->next, n2 = pos2->next; pos2 != head;
+ pos2 = n2, n2 = pos2->next) {
+ struct __prelim_ref *ref2;
+ struct __prelim_ref *xchg;
+ struct extent_inode_elem *eie;
+
+ ref2 = list_entry(pos2, struct __prelim_ref, list);
+
+ if (mode == 1) {
+ if (!ref_for_same_block(ref1, ref2))
+ continue;
+ if (!ref1->parent && ref2->parent) {
+ xchg = ref1;
+ ref1 = ref2;
+ ref2 = xchg;
+ }
+ } else {
+ if (ref1->parent != ref2->parent)
+ continue;
+ }
+
+ eie = ref1->inode_list;
+ while (eie && eie->next)
+ eie = eie->next;
+ if (eie)
+ eie->next = ref2->inode_list;
+ else
+ ref1->inode_list = ref2->inode_list;
+ ref1->count += ref2->count;
+
+ list_del(&ref2->list);
+ kmem_cache_free(btrfs_prelim_ref_cache, ref2);
+ }
+
+ }
+}
+
+/*
+ * add all currently queued delayed refs from this head whose seq nr is
+ * smaller or equal that seq to the list
+ */
+static int __add_delayed_refs(struct btrfs_delayed_ref_head *head, u64 seq,
+ struct list_head *prefs, u64 *total_refs,
+ u64 inum)
+{
+ struct btrfs_delayed_extent_op *extent_op = head->extent_op;
+ struct rb_node *n = &head->node.rb_node;
+ struct btrfs_key key;
+ struct btrfs_key op_key = {0};
+ int sgn;
+ int ret = 0;
+
+ if (extent_op && extent_op->update_key)
+ btrfs_disk_key_to_cpu(&op_key, &extent_op->key);
+
+ spin_lock(&head->lock);
+ n = rb_first(&head->ref_root);
+ while (n) {
+ struct btrfs_delayed_ref_node *node;
+ node = rb_entry(n, struct btrfs_delayed_ref_node,
+ rb_node);
+ n = rb_next(n);
+ if (node->seq > seq)
+ continue;
+
+ switch (node->action) {
+ case BTRFS_ADD_DELAYED_EXTENT:
+ case BTRFS_UPDATE_DELAYED_HEAD:
+ WARN_ON(1);
+ continue;
+ case BTRFS_ADD_DELAYED_REF:
+ sgn = 1;
+ break;
+ case BTRFS_DROP_DELAYED_REF:
+ sgn = -1;
+ break;
+ default:
+ BUG_ON(1);
+ }
+ *total_refs += (node->ref_mod * sgn);
+ switch (node->type) {
+ case BTRFS_TREE_BLOCK_REF_KEY: {
+ struct btrfs_delayed_tree_ref *ref;
+
+ ref = btrfs_delayed_node_to_tree_ref(node);
+ ret = __add_prelim_ref(prefs, ref->root, &op_key,
+ ref->level + 1, 0, node->bytenr,
+ node->ref_mod * sgn, GFP_ATOMIC);
+ break;
+ }
+ case BTRFS_SHARED_BLOCK_REF_KEY: {
+ struct btrfs_delayed_tree_ref *ref;
+
+ ref = btrfs_delayed_node_to_tree_ref(node);
+ ret = __add_prelim_ref(prefs, ref->root, NULL,
+ ref->level + 1, ref->parent,
+ node->bytenr,
+ node->ref_mod * sgn, GFP_ATOMIC);
+ break;
+ }
+ case BTRFS_EXTENT_DATA_REF_KEY: {
+ struct btrfs_delayed_data_ref *ref;
+ ref = btrfs_delayed_node_to_data_ref(node);
+
+ key.objectid = ref->objectid;
+ key.type = BTRFS_EXTENT_DATA_KEY;
+ key.offset = ref->offset;
+
+ /*
+ * Found a inum that doesn't match our known inum, we
+ * know it's shared.
+ */
+ if (inum && ref->objectid != inum) {
+ ret = BACKREF_FOUND_SHARED;
+ break;
+ }
+
+ ret = __add_prelim_ref(prefs, ref->root, &key, 0, 0,
+ node->bytenr,
+ node->ref_mod * sgn, GFP_ATOMIC);
+ break;
+ }
+ case BTRFS_SHARED_DATA_REF_KEY: {
+ struct btrfs_delayed_data_ref *ref;
+
+ ref = btrfs_delayed_node_to_data_ref(node);
+
+ key.objectid = ref->objectid;
+ key.type = BTRFS_EXTENT_DATA_KEY;
+ key.offset = ref->offset;
+ ret = __add_prelim_ref(prefs, ref->root, &key, 0,
+ ref->parent, node->bytenr,
+ node->ref_mod * sgn, GFP_ATOMIC);
+ break;
+ }
+ default:
+ WARN_ON(1);
+ }
+ if (ret)
+ break;
+ }
+ spin_unlock(&head->lock);
+ return ret;
+}
+
+/*
+ * add all inline backrefs for bytenr to the list
+ */
+static int __add_inline_refs(struct btrfs_fs_info *fs_info,
+ struct btrfs_path *path, u64 bytenr,
+ int *info_level, struct list_head *prefs,
+ u64 *total_refs, u64 inum)
+{
+ int ret = 0;
+ int slot;
+ struct extent_buffer *leaf;
+ struct btrfs_key key;
+ struct btrfs_key found_key;
+ unsigned long ptr;
+ unsigned long end;
+ struct btrfs_extent_item *ei;
+ u64 flags;
+ u64 item_size;
+
+ /*
+ * enumerate all inline refs
+ */
+ leaf = path->nodes[0];
+ slot = path->slots[0];
+
+ item_size = btrfs_item_size_nr(leaf, slot);
+ BUG_ON(item_size < sizeof(*ei));
+
+ ei = btrfs_item_ptr(leaf, slot, struct btrfs_extent_item);
+ flags = btrfs_extent_flags(leaf, ei);
+ *total_refs += btrfs_extent_refs(leaf, ei);
+ btrfs_item_key_to_cpu(leaf, &found_key, slot);
+
+ ptr = (unsigned long)(ei + 1);
+ end = (unsigned long)ei + item_size;
+
+ if (found_key.type == BTRFS_EXTENT_ITEM_KEY &&
+ flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) {
+ struct btrfs_tree_block_info *info;
+
+ info = (struct btrfs_tree_block_info *)ptr;
+ *info_level = btrfs_tree_block_level(leaf, info);
+ ptr += sizeof(struct btrfs_tree_block_info);
+ BUG_ON(ptr > end);
+ } else if (found_key.type == BTRFS_METADATA_ITEM_KEY) {
+ *info_level = found_key.offset;
+ } else {
+ BUG_ON(!(flags & BTRFS_EXTENT_FLAG_DATA));
+ }
+
+ while (ptr < end) {
+ struct btrfs_extent_inline_ref *iref;
+ u64 offset;
+ int type;
+
+ iref = (struct btrfs_extent_inline_ref *)ptr;
+ type = btrfs_extent_inline_ref_type(leaf, iref);
+ offset = btrfs_extent_inline_ref_offset(leaf, iref);
+
+ switch (type) {
+ case BTRFS_SHARED_BLOCK_REF_KEY:
+ ret = __add_prelim_ref(prefs, 0, NULL,
+ *info_level + 1, offset,
+ bytenr, 1, GFP_NOFS);
+ break;
+ case BTRFS_SHARED_DATA_REF_KEY: {
+ struct btrfs_shared_data_ref *sdref;
+ int count;
+
+ sdref = (struct btrfs_shared_data_ref *)(iref + 1);
+ count = btrfs_shared_data_ref_count(leaf, sdref);
+ ret = __add_prelim_ref(prefs, 0, NULL, 0, offset,
+ bytenr, count, GFP_NOFS);
+ break;
+ }
+ case BTRFS_TREE_BLOCK_REF_KEY:
+ ret = __add_prelim_ref(prefs, offset, NULL,
+ *info_level + 1, 0,
+ bytenr, 1, GFP_NOFS);
+ break;
+ case BTRFS_EXTENT_DATA_REF_KEY: {
+ struct btrfs_extent_data_ref *dref;
+ int count;
+ u64 root;
+
+ dref = (struct btrfs_extent_data_ref *)(&iref->offset);
+ count = btrfs_extent_data_ref_count(leaf, dref);
+ key.objectid = btrfs_extent_data_ref_objectid(leaf,
+ dref);
+ key.type = BTRFS_EXTENT_DATA_KEY;
+ key.offset = btrfs_extent_data_ref_offset(leaf, dref);
+
+ if (inum && key.objectid != inum) {
+ ret = BACKREF_FOUND_SHARED;
+ break;
+ }
+
+ root = btrfs_extent_data_ref_root(leaf, dref);
+ ret = __add_prelim_ref(prefs, root, &key, 0, 0,
+ bytenr, count, GFP_NOFS);
+ break;
+ }
+ default:
+ WARN_ON(1);
+ }
+ if (ret)
+ return ret;
+ ptr += btrfs_extent_inline_ref_size(type);
+ }
+
+ return 0;
+}
+
+/*
+ * add all non-inline backrefs for bytenr to the list
+ */
+static int __add_keyed_refs(struct btrfs_fs_info *fs_info,
+ struct btrfs_path *path, u64 bytenr,
+ int info_level, struct list_head *prefs, u64 inum)
+{
+ struct btrfs_root *extent_root = fs_info->extent_root;
+ int ret;
+ int slot;
+ struct extent_buffer *leaf;
+ struct btrfs_key key;
+
+ while (1) {
+ ret = btrfs_next_item(extent_root, path);
+ if (ret < 0)
+ break;
+ if (ret) {
+ ret = 0;
+ break;
+ }
+
+ slot = path->slots[0];
+ leaf = path->nodes[0];
+ btrfs_item_key_to_cpu(leaf, &key, slot);
+
+ if (key.objectid != bytenr)
+ break;
+ if (key.type < BTRFS_TREE_BLOCK_REF_KEY)
+ continue;
+ if (key.type > BTRFS_SHARED_DATA_REF_KEY)
+ break;
+
+ switch (key.type) {
+ case BTRFS_SHARED_BLOCK_REF_KEY:
+ ret = __add_prelim_ref(prefs, 0, NULL,
+ info_level + 1, key.offset,
+ bytenr, 1, GFP_NOFS);
+ break;
+ case BTRFS_SHARED_DATA_REF_KEY: {
+ struct btrfs_shared_data_ref *sdref;
+ int count;
+
+ sdref = btrfs_item_ptr(leaf, slot,
+ struct btrfs_shared_data_ref);
+ count = btrfs_shared_data_ref_count(leaf, sdref);
+ ret = __add_prelim_ref(prefs, 0, NULL, 0, key.offset,
+ bytenr, count, GFP_NOFS);
+ break;
+ }
+ case BTRFS_TREE_BLOCK_REF_KEY:
+ ret = __add_prelim_ref(prefs, key.offset, NULL,
+ info_level + 1, 0,
+ bytenr, 1, GFP_NOFS);
+ break;
+ case BTRFS_EXTENT_DATA_REF_KEY: {
+ struct btrfs_extent_data_ref *dref;
+ int count;
+ u64 root;
+
+ dref = btrfs_item_ptr(leaf, slot,
+ struct btrfs_extent_data_ref);
+ count = btrfs_extent_data_ref_count(leaf, dref);
+ key.objectid = btrfs_extent_data_ref_objectid(leaf,
+ dref);
+ key.type = BTRFS_EXTENT_DATA_KEY;
+ key.offset = btrfs_extent_data_ref_offset(leaf, dref);
+
+ if (inum && key.objectid != inum) {
+ ret = BACKREF_FOUND_SHARED;
+ break;
+ }
+
+ root = btrfs_extent_data_ref_root(leaf, dref);
+ ret = __add_prelim_ref(prefs, root, &key, 0, 0,
+ bytenr, count, GFP_NOFS);
+ break;
+ }
+ default:
+ WARN_ON(1);
+ }
+ if (ret)
+ return ret;
+
+ }
+
+ return ret;
+}
+
+/*
+ * this adds all existing backrefs (inline backrefs, backrefs and delayed
+ * refs) for the given bytenr to the refs list, merges duplicates and resolves
+ * indirect refs to their parent bytenr.
+ * When roots are found, they're added to the roots list
+ *
+ * NOTE: This can return values > 0
+ *
+ * FIXME some caching might speed things up
+ */
+static int find_parent_nodes(struct btrfs_trans_handle *trans,
+ struct btrfs_fs_info *fs_info, u64 bytenr,
+ u64 time_seq, struct ulist *refs,
+ struct ulist *roots, const u64 *extent_item_pos,
+ u64 root_objectid, u64 inum)
+{
+ struct btrfs_key key;
+ struct btrfs_path *path;
+ struct btrfs_delayed_ref_root *delayed_refs = NULL;
+ struct btrfs_delayed_ref_head *head;
+ int info_level = 0;
+ int ret;
+ struct list_head prefs_delayed;
+ struct list_head prefs;
+ struct __prelim_ref *ref;
+ struct extent_inode_elem *eie = NULL;
+ u64 total_refs = 0;
+
+ INIT_LIST_HEAD(&prefs);
+ INIT_LIST_HEAD(&prefs_delayed);
+
+ key.objectid = bytenr;
+ key.offset = (u64)-1;
+ if (btrfs_fs_incompat(fs_info, SKINNY_METADATA))
+ key.type = BTRFS_METADATA_ITEM_KEY;
+ else
+ key.type = BTRFS_EXTENT_ITEM_KEY;
+
+ path = btrfs_alloc_path();
+ if (!path)
+ return -ENOMEM;
+ if (!trans) {
+ path->search_commit_root = 1;
+ path->skip_locking = 1;
+ }
+
+ /*
+ * grab both a lock on the path and a lock on the delayed ref head.
+ * We need both to get a consistent picture of how the refs look
+ * at a specified point in time
+ */
+again:
+ head = NULL;
+
+ ret = btrfs_search_slot(trans, fs_info->extent_root, &key, path, 0, 0);
+ if (ret < 0)
+ goto out;
+ BUG_ON(ret == 0);
+
+#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
+ if (trans && likely(trans->type != __TRANS_DUMMY)) {
+#else
+ if (trans) {
+#endif
+ /*
+ * look if there are updates for this ref queued and lock the
+ * head
+ */
+ delayed_refs = &trans->transaction->delayed_refs;
+ spin_lock(&delayed_refs->lock);
+ head = btrfs_find_delayed_ref_head(trans, bytenr);
+ if (head) {
+ if (!mutex_trylock(&head->mutex)) {
+ atomic_inc(&head->node.refs);
+ spin_unlock(&delayed_refs->lock);
+
+ btrfs_release_path(path);
+
+ /*
+ * Mutex was contended, block until it's
+ * released and try again
+ */
+ mutex_lock(&head->mutex);
+ mutex_unlock(&head->mutex);
+ btrfs_put_delayed_ref(&head->node);
+ goto again;
+ }
+ spin_unlock(&delayed_refs->lock);
+ ret = __add_delayed_refs(head, time_seq,
+ &prefs_delayed, &total_refs,
+ inum);
+ mutex_unlock(&head->mutex);
+ if (ret)
+ goto out;
+ } else {
+ spin_unlock(&delayed_refs->lock);
+ }
+ }
+
+ if (path->slots[0]) {
+ struct extent_buffer *leaf;
+ int slot;
+
+ path->slots[0]--;
+ leaf = path->nodes[0];
+ slot = path->slots[0];
+ btrfs_item_key_to_cpu(leaf, &key, slot);
+ if (key.objectid == bytenr &&
+ (key.type == BTRFS_EXTENT_ITEM_KEY ||
+ key.type == BTRFS_METADATA_ITEM_KEY)) {
+ ret = __add_inline_refs(fs_info, path, bytenr,
+ &info_level, &prefs,
+ &total_refs, inum);
+ if (ret)
+ goto out;
+ ret = __add_keyed_refs(fs_info, path, bytenr,
+ info_level, &prefs, inum);
+ if (ret)
+ goto out;
+ }
+ }
+ btrfs_release_path(path);
+
+ list_splice_init(&prefs_delayed, &prefs);
+
+ ret = __add_missing_keys(fs_info, &prefs);
+ if (ret)
+ goto out;
+
+ __merge_refs(&prefs, 1);
+
+ ret = __resolve_indirect_refs(fs_info, path, time_seq, &prefs,
+ extent_item_pos, total_refs,
+ root_objectid);
+ if (ret)
+ goto out;
+
+ __merge_refs(&prefs, 2);
+
+ while (!list_empty(&prefs)) {
+ ref = list_first_entry(&prefs, struct __prelim_ref, list);
+ WARN_ON(ref->count < 0);
+ if (roots && ref->count && ref->root_id && ref->parent == 0) {
+ if (root_objectid && ref->root_id != root_objectid) {
+ ret = BACKREF_FOUND_SHARED;
+ goto out;
+ }
+
+ /* no parent == root of tree */
+ ret = ulist_add(roots, ref->root_id, 0, GFP_NOFS);
+ if (ret < 0)
+ goto out;
+ }
+ if (ref->count && ref->parent) {
+ if (extent_item_pos && !ref->inode_list &&
+ ref->level == 0) {
+ struct extent_buffer *eb;
+
+ eb = read_tree_block(fs_info->extent_root,
+ ref->parent, 0);
+ if (!eb || !extent_buffer_uptodate(eb)) {
+ free_extent_buffer(eb);
+ ret = -EIO;
+ goto out;
+ }
+ btrfs_tree_read_lock(eb);
+ btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK);
+ ret = find_extent_in_eb(eb, bytenr,
+ *extent_item_pos, &eie);
+ btrfs_tree_read_unlock_blocking(eb);
+ free_extent_buffer(eb);
+ if (ret < 0)
+ goto out;
+ ref->inode_list = eie;
+ }
+ ret = ulist_add_merge_ptr(refs, ref->parent,
+ ref->inode_list,
+ (void **)&eie, GFP_NOFS);
+ if (ret < 0)
+ goto out;
+ if (!ret && extent_item_pos) {
+ /*
+ * we've recorded that parent, so we must extend
+ * its inode list here
+ */
+ BUG_ON(!eie);
+ while (eie->next)
+ eie = eie->next;
+ eie->next = ref->inode_list;
+ }
+ eie = NULL;
+ }
+ list_del(&ref->list);
+ kmem_cache_free(btrfs_prelim_ref_cache, ref);
+ }
+
+out:
+ btrfs_free_path(path);
+ while (!list_empty(&prefs)) {
+ ref = list_first_entry(&prefs, struct __prelim_ref, list);
+ list_del(&ref->list);
+ kmem_cache_free(btrfs_prelim_ref_cache, ref);
+ }
+ while (!list_empty(&prefs_delayed)) {
+ ref = list_first_entry(&prefs_delayed, struct __prelim_ref,
+ list);
+ list_del(&ref->list);
+ kmem_cache_free(btrfs_prelim_ref_cache, ref);
+ }
+ if (ret < 0)
+ free_inode_elem_list(eie);
+ return ret;
+}
+
+static void free_leaf_list(struct ulist *blocks)
+{
+ struct ulist_node *node = NULL;
+ struct extent_inode_elem *eie;
+ struct ulist_iterator uiter;
+
+ ULIST_ITER_INIT(&uiter);
+ while ((node = ulist_next(blocks, &uiter))) {
+ if (!node->aux)
+ continue;
+ eie = (struct extent_inode_elem *)(uintptr_t)node->aux;
+ free_inode_elem_list(eie);
+ node->aux = 0;
+ }
+
+ ulist_free(blocks);
+}
+
+/*
+ * Finds all leafs with a reference to the specified combination of bytenr and
+ * offset. key_list_head will point to a list of corresponding keys (caller must
+ * free each list element). The leafs will be stored in the leafs ulist, which
+ * must be freed with ulist_free.
+ *
+ * returns 0 on success, <0 on error
+ */
+static int btrfs_find_all_leafs(struct btrfs_trans_handle *trans,
+ struct btrfs_fs_info *fs_info, u64 bytenr,
+ u64 time_seq, struct ulist **leafs,
+ const u64 *extent_item_pos)
+{
+ int ret;
+
+ *leafs = ulist_alloc(GFP_NOFS);
+ if (!*leafs)
+ return -ENOMEM;
+
+ ret = find_parent_nodes(trans, fs_info, bytenr,
+ time_seq, *leafs, NULL, extent_item_pos, 0, 0);
+ if (ret < 0 && ret != -ENOENT) {
+ free_leaf_list(*leafs);
+ return ret;
+ }
+
+ return 0;
+}
+
+/*
+ * walk all backrefs for a given extent to find all roots that reference this
+ * extent. Walking a backref means finding all extents that reference this
+ * extent and in turn walk the backrefs of those, too. Naturally this is a
+ * recursive process, but here it is implemented in an iterative fashion: We
+ * find all referencing extents for the extent in question and put them on a
+ * list. In turn, we find all referencing extents for those, further appending
+ * to the list. The way we iterate the list allows adding more elements after
+ * the current while iterating. The process stops when we reach the end of the
+ * list. Found roots are added to the roots list.
+ *
+ * returns 0 on success, < 0 on error.
+ */
+static int __btrfs_find_all_roots(struct btrfs_trans_handle *trans,
+ struct btrfs_fs_info *fs_info, u64 bytenr,
+ u64 time_seq, struct ulist **roots)
+{
+ struct ulist *tmp;
+ struct ulist_node *node = NULL;
+ struct ulist_iterator uiter;
+ int ret;
+
+ tmp = ulist_alloc(GFP_NOFS);
+ if (!tmp)
+ return -ENOMEM;
+ *roots = ulist_alloc(GFP_NOFS);
+ if (!*roots) {
+ ulist_free(tmp);
+ return -ENOMEM;
+ }
+
+ ULIST_ITER_INIT(&uiter);
+ while (1) {
+ ret = find_parent_nodes(trans, fs_info, bytenr,
+ time_seq, tmp, *roots, NULL, 0, 0);
+ if (ret < 0 && ret != -ENOENT) {
+ ulist_free(tmp);
+ ulist_free(*roots);
+ return ret;
+ }
+ node = ulist_next(tmp, &uiter);
+ if (!node)
+ break;
+ bytenr = node->val;
+ cond_resched();
+ }
+
+ ulist_free(tmp);
+ return 0;
+}
+
+int btrfs_find_all_roots(struct btrfs_trans_handle *trans,
+ struct btrfs_fs_info *fs_info, u64 bytenr,
+ u64 time_seq, struct ulist **roots)
+{
+ int ret;
+
+ if (!trans)
+ down_read(&fs_info->commit_root_sem);
+ ret = __btrfs_find_all_roots(trans, fs_info, bytenr, time_seq, roots);
+ if (!trans)
+ up_read(&fs_info->commit_root_sem);
+ return ret;
+}
+
+/**
+ * btrfs_check_shared - tell us whether an extent is shared
+ *
+ * @trans: optional trans handle
+ *
+ * btrfs_check_shared uses the backref walking code but will short
+ * circuit as soon as it finds a root or inode that doesn't match the
+ * one passed in. This provides a significant performance benefit for
+ * callers (such as fiemap) which want to know whether the extent is
+ * shared but do not need a ref count.
+ *
+ * Return: 0 if extent is not shared, 1 if it is shared, < 0 on error.
+ */
+int btrfs_check_shared(struct btrfs_trans_handle *trans,
+ struct btrfs_fs_info *fs_info, u64 root_objectid,
+ u64 inum, u64 bytenr)
+{
+ struct ulist *tmp = NULL;
+ struct ulist *roots = NULL;
+ struct ulist_iterator uiter;
+ struct ulist_node *node;
+ struct seq_list elem = SEQ_LIST_INIT(elem);
+ int ret = 0;
+
+ tmp = ulist_alloc(GFP_NOFS);
+ roots = ulist_alloc(GFP_NOFS);
+ if (!tmp || !roots) {
+ ulist_free(tmp);
+ ulist_free(roots);
+ return -ENOMEM;
+ }
+
+ if (trans)
+ btrfs_get_tree_mod_seq(fs_info, &elem);
+ else
+ down_read(&fs_info->commit_root_sem);
+ ULIST_ITER_INIT(&uiter);
+ while (1) {
+ ret = find_parent_nodes(trans, fs_info, bytenr, elem.seq, tmp,
+ roots, NULL, root_objectid, inum);
+ if (ret == BACKREF_FOUND_SHARED) {
+ /* this is the only condition under which we return 1 */
+ ret = 1;
+ break;
+ }
+ if (ret < 0 && ret != -ENOENT)
+ break;
+ ret = 0;
+ node = ulist_next(tmp, &uiter);
+ if (!node)
+ break;
+ bytenr = node->val;
+ cond_resched();
+ }
+ if (trans)
+ btrfs_put_tree_mod_seq(fs_info, &elem);
+ else
+ up_read(&fs_info->commit_root_sem);
+ ulist_free(tmp);
+ ulist_free(roots);
+ return ret;
+}
+
+int btrfs_find_one_extref(struct btrfs_root *root, u64 inode_objectid,
+ u64 start_off, struct btrfs_path *path,
+ struct btrfs_inode_extref **ret_extref,
+ u64 *found_off)
+{
+ int ret, slot;
+ struct btrfs_key key;
+ struct btrfs_key found_key;
+ struct btrfs_inode_extref *extref;
+ struct extent_buffer *leaf;
+ unsigned long ptr;
+
+ key.objectid = inode_objectid;
+ key.type = BTRFS_INODE_EXTREF_KEY;
+ key.offset = start_off;
+
+ ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
+ if (ret < 0)
+ return ret;
+
+ while (1) {
+ leaf = path->nodes[0];
+ slot = path->slots[0];
+ if (slot >= btrfs_header_nritems(leaf)) {
+ /*
+ * If the item at offset is not found,
+ * btrfs_search_slot will point us to the slot
+ * where it should be inserted. In our case
+ * that will be the slot directly before the
+ * next INODE_REF_KEY_V2 item. In the case
+ * that we're pointing to the last slot in a
+ * leaf, we must move one leaf over.
+ */
+ ret = btrfs_next_leaf(root, path);
+ if (ret) {
+ if (ret >= 1)
+ ret = -ENOENT;
+ break;
+ }
+ continue;
+ }
+
+ btrfs_item_key_to_cpu(leaf, &found_key, slot);
+
+ /*
+ * Check that we're still looking at an extended ref key for
+ * this particular objectid. If we have different
+ * objectid or type then there are no more to be found
+ * in the tree and we can exit.
+ */
+ ret = -ENOENT;
+ if (found_key.objectid != inode_objectid)
+ break;
+ if (found_key.type != BTRFS_INODE_EXTREF_KEY)
+ break;
+
+ ret = 0;
+ ptr = btrfs_item_ptr_offset(leaf, path->slots[0]);
+ extref = (struct btrfs_inode_extref *)ptr;
+ *ret_extref = extref;
+ if (found_off)
+ *found_off = found_key.offset;
+ break;
+ }
+
+ return ret;
+}
+
+/*
+ * this iterates to turn a name (from iref/extref) into a full filesystem path.
+ * Elements of the path are separated by '/' and the path is guaranteed to be
+ * 0-terminated. the path is only given within the current file system.
+ * Therefore, it never starts with a '/'. the caller is responsible to provide
+ * "size" bytes in "dest". the dest buffer will be filled backwards. finally,
+ * the start point of the resulting string is returned. this pointer is within
+ * dest, normally.
+ * in case the path buffer would overflow, the pointer is decremented further
+ * as if output was written to the buffer, though no more output is actually
+ * generated. that way, the caller can determine how much space would be
+ * required for the path to fit into the buffer. in that case, the returned
+ * value will be smaller than dest. callers must check this!
+ */
+char *btrfs_ref_to_path(struct btrfs_root *fs_root, struct btrfs_path *path,
+ u32 name_len, unsigned long name_off,
+ struct extent_buffer *eb_in, u64 parent,
+ char *dest, u32 size)
+{
+ int slot;
+ u64 next_inum;
+ int ret;
+ s64 bytes_left = ((s64)size) - 1;
+ struct extent_buffer *eb = eb_in;
+ struct btrfs_key found_key;
+ int leave_spinning = path->leave_spinning;
+ struct btrfs_inode_ref *iref;
+
+ if (bytes_left >= 0)
+ dest[bytes_left] = '\0';
+
+ path->leave_spinning = 1;
+ while (1) {
+ bytes_left -= name_len;
+ if (bytes_left >= 0)
+ read_extent_buffer(eb, dest + bytes_left,
+ name_off, name_len);
+ if (eb != eb_in) {
+ btrfs_tree_read_unlock_blocking(eb);
+ free_extent_buffer(eb);
+ }
+ ret = btrfs_find_item(fs_root, path, parent, 0,
+ BTRFS_INODE_REF_KEY, &found_key);
+ if (ret > 0)
+ ret = -ENOENT;
+ if (ret)
+ break;
+
+ next_inum = found_key.offset;
+
+ /* regular exit ahead */
+ if (parent == next_inum)
+ break;
+
+ slot = path->slots[0];
+ eb = path->nodes[0];
+ /* make sure we can use eb after releasing the path */
+ if (eb != eb_in) {
+ atomic_inc(&eb->refs);
+ btrfs_tree_read_lock(eb);
+ btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK);
+ }
+ btrfs_release_path(path);
+ iref = btrfs_item_ptr(eb, slot, struct btrfs_inode_ref);
+
+ name_len = btrfs_inode_ref_name_len(eb, iref);
+ name_off = (unsigned long)(iref + 1);
+
+ parent = next_inum;
+ --bytes_left;
+ if (bytes_left >= 0)
+ dest[bytes_left] = '/';
+ }
+
+ btrfs_release_path(path);
+ path->leave_spinning = leave_spinning;
+
+ if (ret)
+ return ERR_PTR(ret);
+
+ return dest + bytes_left;
+}
+
+/*
+ * this makes the path point to (logical EXTENT_ITEM *)
+ * returns BTRFS_EXTENT_FLAG_DATA for data, BTRFS_EXTENT_FLAG_TREE_BLOCK for
+ * tree blocks and <0 on error.
+ */
+int extent_from_logical(struct btrfs_fs_info *fs_info, u64 logical,
+ struct btrfs_path *path, struct btrfs_key *found_key,
+ u64 *flags_ret)
+{
+ int ret;
+ u64 flags;
+ u64 size = 0;
+ u32 item_size;
+ struct extent_buffer *eb;
+ struct btrfs_extent_item *ei;
+ struct btrfs_key key;
+
+ if (btrfs_fs_incompat(fs_info, SKINNY_METADATA))
+ key.type = BTRFS_METADATA_ITEM_KEY;
+ else
+ key.type = BTRFS_EXTENT_ITEM_KEY;
+ key.objectid = logical;
+ key.offset = (u64)-1;
+
+ ret = btrfs_search_slot(NULL, fs_info->extent_root, &key, path, 0, 0);
+ if (ret < 0)
+ return ret;
+
+ ret = btrfs_previous_extent_item(fs_info->extent_root, path, 0);
+ if (ret) {
+ if (ret > 0)
+ ret = -ENOENT;
+ return ret;
+ }
+ btrfs_item_key_to_cpu(path->nodes[0], found_key, path->slots[0]);
+ if (found_key->type == BTRFS_METADATA_ITEM_KEY)
+ size = fs_info->extent_root->nodesize;
+ else if (found_key->type == BTRFS_EXTENT_ITEM_KEY)
+ size = found_key->offset;
+
+ if (found_key->objectid > logical ||
+ found_key->objectid + size <= logical) {
+ pr_debug("logical %llu is not within any extent\n", logical);
+ return -ENOENT;
+ }
+
+ eb = path->nodes[0];
+ item_size = btrfs_item_size_nr(eb, path->slots[0]);
+ BUG_ON(item_size < sizeof(*ei));
+
+ ei = btrfs_item_ptr(eb, path->slots[0], struct btrfs_extent_item);
+ flags = btrfs_extent_flags(eb, ei);
+
+ pr_debug("logical %llu is at position %llu within the extent (%llu "
+ "EXTENT_ITEM %llu) flags %#llx size %u\n",
+ logical, logical - found_key->objectid, found_key->objectid,
+ found_key->offset, flags, item_size);
+
+ WARN_ON(!flags_ret);
+ if (flags_ret) {
+ if (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK)
+ *flags_ret = BTRFS_EXTENT_FLAG_TREE_BLOCK;
+ else if (flags & BTRFS_EXTENT_FLAG_DATA)
+ *flags_ret = BTRFS_EXTENT_FLAG_DATA;
+ else
+ BUG_ON(1);
+ return 0;
+ }
+
+ return -EIO;
+}
+
+/*
+ * helper function to iterate extent inline refs. ptr must point to a 0 value
+ * for the first call and may be modified. it is used to track state.
+ * if more refs exist, 0 is returned and the next call to
+ * __get_extent_inline_ref must pass the modified ptr parameter to get the
+ * next ref. after the last ref was processed, 1 is returned.
+ * returns <0 on error
+ */
+static int __get_extent_inline_ref(unsigned long *ptr, struct extent_buffer *eb,
+ struct btrfs_key *key,
+ struct btrfs_extent_item *ei, u32 item_size,
+ struct btrfs_extent_inline_ref **out_eiref,
+ int *out_type)
+{
+ unsigned long end;
+ u64 flags;
+ struct btrfs_tree_block_info *info;
+
+ if (!*ptr) {
+ /* first call */
+ flags = btrfs_extent_flags(eb, ei);
+ if (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) {
+ if (key->type == BTRFS_METADATA_ITEM_KEY) {
+ /* a skinny metadata extent */
+ *out_eiref =
+ (struct btrfs_extent_inline_ref *)(ei + 1);
+ } else {
+ WARN_ON(key->type != BTRFS_EXTENT_ITEM_KEY);
+ info = (struct btrfs_tree_block_info *)(ei + 1);
+ *out_eiref =
+ (struct btrfs_extent_inline_ref *)(info + 1);
+ }
+ } else {
+ *out_eiref = (struct btrfs_extent_inline_ref *)(ei + 1);
+ }
+ *ptr = (unsigned long)*out_eiref;
+ if ((unsigned long)(*ptr) >= (unsigned long)ei + item_size)
+ return -ENOENT;
+ }
+
+ end = (unsigned long)ei + item_size;
+ *out_eiref = (struct btrfs_extent_inline_ref *)(*ptr);
+ *out_type = btrfs_extent_inline_ref_type(eb, *out_eiref);
+
+ *ptr += btrfs_extent_inline_ref_size(*out_type);
+ WARN_ON(*ptr > end);
+ if (*ptr == end)
+ return 1; /* last */
+
+ return 0;
+}
+
+/*
+ * reads the tree block backref for an extent. tree level and root are returned
+ * through out_level and out_root. ptr must point to a 0 value for the first
+ * call and may be modified (see __get_extent_inline_ref comment).
+ * returns 0 if data was provided, 1 if there was no more data to provide or
+ * <0 on error.
+ */
+int tree_backref_for_extent(unsigned long *ptr, struct extent_buffer *eb,
+ struct btrfs_key *key, struct btrfs_extent_item *ei,
+ u32 item_size, u64 *out_root, u8 *out_level)
+{
+ int ret;
+ int type;
+ struct btrfs_extent_inline_ref *eiref;
+
+ if (*ptr == (unsigned long)-1)
+ return 1;
+
+ while (1) {
+ ret = __get_extent_inline_ref(ptr, eb, key, ei, item_size,
+ &eiref, &type);
+ if (ret < 0)
+ return ret;
+
+ if (type == BTRFS_TREE_BLOCK_REF_KEY ||
+ type == BTRFS_SHARED_BLOCK_REF_KEY)
+ break;
+
+ if (ret == 1)
+ return 1;
+ }
+
+ /* we can treat both ref types equally here */
+ *out_root = btrfs_extent_inline_ref_offset(eb, eiref);
+
+ if (key->type == BTRFS_EXTENT_ITEM_KEY) {
+ struct btrfs_tree_block_info *info;
+
+ info = (struct btrfs_tree_block_info *)(ei + 1);
+ *out_level = btrfs_tree_block_level(eb, info);
+ } else {
+ ASSERT(key->type == BTRFS_METADATA_ITEM_KEY);
+ *out_level = (u8)key->offset;
+ }
+
+ if (ret == 1)
+ *ptr = (unsigned long)-1;
+
+ return 0;
+}
+
+static int iterate_leaf_refs(struct extent_inode_elem *inode_list,
+ u64 root, u64 extent_item_objectid,
+ iterate_extent_inodes_t *iterate, void *ctx)
+{
+ struct extent_inode_elem *eie;
+ int ret = 0;
+
+ for (eie = inode_list; eie; eie = eie->next) {
+ pr_debug("ref for %llu resolved, key (%llu EXTEND_DATA %llu), "
+ "root %llu\n", extent_item_objectid,
+ eie->inum, eie->offset, root);
+ ret = iterate(eie->inum, eie->offset, root, ctx);
+ if (ret) {
+ pr_debug("stopping iteration for %llu due to ret=%d\n",
+ extent_item_objectid, ret);
+ break;
+ }
+ }
+
+ return ret;
+}
+
+/*
+ * calls iterate() for every inode that references the extent identified by
+ * the given parameters.
+ * when the iterator function returns a non-zero value, iteration stops.
+ */
+int iterate_extent_inodes(struct btrfs_fs_info *fs_info,
+ u64 extent_item_objectid, u64 extent_item_pos,
+ int search_commit_root,
+ iterate_extent_inodes_t *iterate, void *ctx)
+{
+ int ret;
+ struct btrfs_trans_handle *trans = NULL;
+ struct ulist *refs = NULL;
+ struct ulist *roots = NULL;
+ struct ulist_node *ref_node = NULL;
+ struct ulist_node *root_node = NULL;
+ struct seq_list tree_mod_seq_elem = SEQ_LIST_INIT(tree_mod_seq_elem);
+ struct ulist_iterator ref_uiter;
+ struct ulist_iterator root_uiter;
+
+ pr_debug("resolving all inodes for extent %llu\n",
+ extent_item_objectid);
+
+ if (!search_commit_root) {
+ trans = btrfs_join_transaction(fs_info->extent_root);
+ if (IS_ERR(trans))
+ return PTR_ERR(trans);
+ btrfs_get_tree_mod_seq(fs_info, &tree_mod_seq_elem);
+ } else {
+ down_read(&fs_info->commit_root_sem);
+ }
+
+ ret = btrfs_find_all_leafs(trans, fs_info, extent_item_objectid,
+ tree_mod_seq_elem.seq, &refs,
+ &extent_item_pos);
+ if (ret)
+ goto out;
+
+ ULIST_ITER_INIT(&ref_uiter);
+ while (!ret && (ref_node = ulist_next(refs, &ref_uiter))) {
+ ret = __btrfs_find_all_roots(trans, fs_info, ref_node->val,
+ tree_mod_seq_elem.seq, &roots);
+ if (ret)
+ break;
+ ULIST_ITER_INIT(&root_uiter);
+ while (!ret && (root_node = ulist_next(roots, &root_uiter))) {
+ pr_debug("root %llu references leaf %llu, data list "
+ "%#llx\n", root_node->val, ref_node->val,
+ ref_node->aux);
+ ret = iterate_leaf_refs((struct extent_inode_elem *)
+ (uintptr_t)ref_node->aux,
+ root_node->val,
+ extent_item_objectid,
+ iterate, ctx);
+ }
+ ulist_free(roots);
+ }
+
+ free_leaf_list(refs);
+out:
+ if (!search_commit_root) {
+ btrfs_put_tree_mod_seq(fs_info, &tree_mod_seq_elem);
+ btrfs_end_transaction(trans, fs_info->extent_root);
+ } else {
+ up_read(&fs_info->commit_root_sem);
+ }
+
+ return ret;
+}
+
+int iterate_inodes_from_logical(u64 logical, struct btrfs_fs_info *fs_info,
+ struct btrfs_path *path,
+ iterate_extent_inodes_t *iterate, void *ctx)
+{
+ int ret;
+ u64 extent_item_pos;
+ u64 flags = 0;
+ struct btrfs_key found_key;
+ int search_commit_root = path->search_commit_root;
+
+ ret = extent_from_logical(fs_info, logical, path, &found_key, &flags);
+ btrfs_release_path(path);
+ if (ret < 0)
+ return ret;
+ if (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK)
+ return -EINVAL;
+
+ extent_item_pos = logical - found_key.objectid;
+ ret = iterate_extent_inodes(fs_info, found_key.objectid,
+ extent_item_pos, search_commit_root,
+ iterate, ctx);
+
+ return ret;
+}
+
+typedef int (iterate_irefs_t)(u64 parent, u32 name_len, unsigned long name_off,
+ struct extent_buffer *eb, void *ctx);
+
+static int iterate_inode_refs(u64 inum, struct btrfs_root *fs_root,
+ struct btrfs_path *path,
+ iterate_irefs_t *iterate, void *ctx)
+{
+ int ret = 0;
+ int slot;
+ u32 cur;
+ u32 len;
+ u32 name_len;
+ u64 parent = 0;
+ int found = 0;
+ struct extent_buffer *eb;
+ struct btrfs_item *item;
+ struct btrfs_inode_ref *iref;
+ struct btrfs_key found_key;
+
+ while (!ret) {
+ ret = btrfs_find_item(fs_root, path, inum,
+ parent ? parent + 1 : 0, BTRFS_INODE_REF_KEY,
+ &found_key);
+
+ if (ret < 0)
+ break;
+ if (ret) {
+ ret = found ? 0 : -ENOENT;
+ break;
+ }
+ ++found;
+
+ parent = found_key.offset;
+ slot = path->slots[0];
+ eb = btrfs_clone_extent_buffer(path->nodes[0]);
+ if (!eb) {
+ ret = -ENOMEM;
+ break;
+ }
+ extent_buffer_get(eb);
+ btrfs_tree_read_lock(eb);
+ btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK);
+ btrfs_release_path(path);
+
+ item = btrfs_item_nr(slot);
+ iref = btrfs_item_ptr(eb, slot, struct btrfs_inode_ref);
+
+ for (cur = 0; cur < btrfs_item_size(eb, item); cur += len) {
+ name_len = btrfs_inode_ref_name_len(eb, iref);
+ /* path must be released before calling iterate()! */
+ pr_debug("following ref at offset %u for inode %llu in "
+ "tree %llu\n", cur, found_key.objectid,
+ fs_root->objectid);
+ ret = iterate(parent, name_len,
+ (unsigned long)(iref + 1), eb, ctx);
+ if (ret)
+ break;
+ len = sizeof(*iref) + name_len;
+ iref = (struct btrfs_inode_ref *)((char *)iref + len);
+ }
+ btrfs_tree_read_unlock_blocking(eb);
+ free_extent_buffer(eb);
+ }
+
+ btrfs_release_path(path);
+
+ return ret;
+}
+
+static int iterate_inode_extrefs(u64 inum, struct btrfs_root *fs_root,
+ struct btrfs_path *path,
+ iterate_irefs_t *iterate, void *ctx)
+{
+ int ret;
+ int slot;
+ u64 offset = 0;
+ u64 parent;
+ int found = 0;
+ struct extent_buffer *eb;
+ struct btrfs_inode_extref *extref;
+ struct extent_buffer *leaf;
+ u32 item_size;
+ u32 cur_offset;
+ unsigned long ptr;
+
+ while (1) {
+ ret = btrfs_find_one_extref(fs_root, inum, offset, path, &extref,
+ &offset);
+ if (ret < 0)
+ break;
+ if (ret) {
+ ret = found ? 0 : -ENOENT;
+ break;
+ }
+ ++found;
+
+ slot = path->slots[0];
+ eb = btrfs_clone_extent_buffer(path->nodes[0]);
+ if (!eb) {
+ ret = -ENOMEM;
+ break;
+ }
+ extent_buffer_get(eb);
+
+ btrfs_tree_read_lock(eb);
+ btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK);
+ btrfs_release_path(path);
+
+ leaf = path->nodes[0];
+ item_size = btrfs_item_size_nr(leaf, slot);
+ ptr = btrfs_item_ptr_offset(leaf, slot);
+ cur_offset = 0;
+
+ while (cur_offset < item_size) {
+ u32 name_len;
+
+ extref = (struct btrfs_inode_extref *)(ptr + cur_offset);
+ parent = btrfs_inode_extref_parent(eb, extref);
+ name_len = btrfs_inode_extref_name_len(eb, extref);
+ ret = iterate(parent, name_len,
+ (unsigned long)&extref->name, eb, ctx);
+ if (ret)
+ break;
+
+ cur_offset += btrfs_inode_extref_name_len(leaf, extref);
+ cur_offset += sizeof(*extref);
+ }
+ btrfs_tree_read_unlock_blocking(eb);
+ free_extent_buffer(eb);
+
+ offset++;
+ }
+
+ btrfs_release_path(path);
+
+ return ret;
+}
+
+static int iterate_irefs(u64 inum, struct btrfs_root *fs_root,
+ struct btrfs_path *path, iterate_irefs_t *iterate,
+ void *ctx)
+{
+ int ret;
+ int found_refs = 0;
+
+ ret = iterate_inode_refs(inum, fs_root, path, iterate, ctx);
+ if (!ret)
+ ++found_refs;
+ else if (ret != -ENOENT)
+ return ret;
+
+ ret = iterate_inode_extrefs(inum, fs_root, path, iterate, ctx);
+ if (ret == -ENOENT && found_refs)
+ return 0;
+
+ return ret;
+}
+
+/*
+ * returns 0 if the path could be dumped (probably truncated)
+ * returns <0 in case of an error
+ */
+static int inode_to_path(u64 inum, u32 name_len, unsigned long name_off,
+ struct extent_buffer *eb, void *ctx)
+{
+ struct inode_fs_paths *ipath = ctx;
+ char *fspath;
+ char *fspath_min;
+ int i = ipath->fspath->elem_cnt;
+ const int s_ptr = sizeof(char *);
+ u32 bytes_left;
+
+ bytes_left = ipath->fspath->bytes_left > s_ptr ?
+ ipath->fspath->bytes_left - s_ptr : 0;
+
+ fspath_min = (char *)ipath->fspath->val + (i + 1) * s_ptr;
+ fspath = btrfs_ref_to_path(ipath->fs_root, ipath->btrfs_path, name_len,
+ name_off, eb, inum, fspath_min, bytes_left);
+ if (IS_ERR(fspath))
+ return PTR_ERR(fspath);
+
+ if (fspath > fspath_min) {
+ ipath->fspath->val[i] = (u64)(unsigned long)fspath;
+ ++ipath->fspath->elem_cnt;
+ ipath->fspath->bytes_left = fspath - fspath_min;
+ } else {
+ ++ipath->fspath->elem_missed;
+ ipath->fspath->bytes_missing += fspath_min - fspath;
+ ipath->fspath->bytes_left = 0;
+ }
+
+ return 0;
+}
+
+/*
+ * this dumps all file system paths to the inode into the ipath struct, provided
+ * is has been created large enough. each path is zero-terminated and accessed
+ * from ipath->fspath->val[i].
+ * when it returns, there are ipath->fspath->elem_cnt number of paths available
+ * in ipath->fspath->val[]. when the allocated space wasn't sufficient, the
+ * number of missed paths in recored in ipath->fspath->elem_missed, otherwise,
+ * it's zero. ipath->fspath->bytes_missing holds the number of bytes that would
+ * have been needed to return all paths.
+ */
+int paths_from_inode(u64 inum, struct inode_fs_paths *ipath)
+{
+ return iterate_irefs(inum, ipath->fs_root, ipath->btrfs_path,
+ inode_to_path, ipath);
+}
+
+struct btrfs_data_container *init_data_container(u32 total_bytes)
+{
+ struct btrfs_data_container *data;
+ size_t alloc_bytes;
+
+ alloc_bytes = max_t(size_t, total_bytes, sizeof(*data));
+ data = vmalloc(alloc_bytes);
+ if (!data)
+ return ERR_PTR(-ENOMEM);
+
+ if (total_bytes >= sizeof(*data)) {
+ data->bytes_left = total_bytes - sizeof(*data);
+ data->bytes_missing = 0;
+ } else {
+ data->bytes_missing = sizeof(*data) - total_bytes;
+ data->bytes_left = 0;
+ }
+
+ data->elem_cnt = 0;
+ data->elem_missed = 0;
+
+ return data;
+}
+
+/*
+ * allocates space to return multiple file system paths for an inode.
+ * total_bytes to allocate are passed, note that space usable for actual path
+ * information will be total_bytes - sizeof(struct inode_fs_paths).
+ * the returned pointer must be freed with free_ipath() in the end.
+ */
+struct inode_fs_paths *init_ipath(s32 total_bytes, struct btrfs_root *fs_root,
+ struct btrfs_path *path)
+{
+ struct inode_fs_paths *ifp;
+ struct btrfs_data_container *fspath;
+
+ fspath = init_data_container(total_bytes);
+ if (IS_ERR(fspath))
+ return (void *)fspath;
+
+ ifp = kmalloc(sizeof(*ifp), GFP_NOFS);
+ if (!ifp) {
+ kfree(fspath);
+ return ERR_PTR(-ENOMEM);
+ }
+
+ ifp->btrfs_path = path;
+ ifp->fspath = fspath;
+ ifp->fs_root = fs_root;
+
+ return ifp;
+}
+
+void free_ipath(struct inode_fs_paths *ipath)
+{
+ if (!ipath)
+ return;
+ vfree(ipath->fspath);
+ kfree(ipath);
+}