summaryrefslogtreecommitdiff
path: root/fs/btrfs
diff options
context:
space:
mode:
Diffstat (limited to 'fs/btrfs')
-rw-r--r--fs/btrfs/delayed-inode.c32
-rw-r--r--fs/btrfs/disk-io.c1
-rw-r--r--fs/btrfs/extent_io.c8
-rw-r--r--fs/btrfs/inode.c63
-rw-r--r--fs/btrfs/qgroup.c21
-rw-r--r--fs/btrfs/super.c12
-rw-r--r--fs/btrfs/transaction.c11
-rw-r--r--fs/btrfs/tree-log.c8
8 files changed, 102 insertions, 54 deletions
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index ce6e9f8812e0..4b7d9015e0da 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -152,37 +152,39 @@ again:
return ERR_PTR(-ENOMEM);
btrfs_init_delayed_node(node, root, ino);
+ /* Cached in the inode and can be accessed. */
+ refcount_set(&node->refs, 2);
+ btrfs_delayed_node_ref_tracker_alloc(node, tracker, GFP_NOFS);
+ btrfs_delayed_node_ref_tracker_alloc(node, &node->inode_cache_tracker, GFP_NOFS);
+
/* Allocate and reserve the slot, from now it can return a NULL from xa_load(). */
ret = xa_reserve(&root->delayed_nodes, ino, GFP_NOFS);
- if (ret == -ENOMEM) {
- btrfs_delayed_node_ref_tracker_dir_exit(node);
- kmem_cache_free(delayed_node_cache, node);
- return ERR_PTR(-ENOMEM);
- }
+ if (ret == -ENOMEM)
+ goto cleanup;
+
xa_lock(&root->delayed_nodes);
ptr = xa_load(&root->delayed_nodes, ino);
if (ptr) {
/* Somebody inserted it, go back and read it. */
xa_unlock(&root->delayed_nodes);
- btrfs_delayed_node_ref_tracker_dir_exit(node);
- kmem_cache_free(delayed_node_cache, node);
- node = NULL;
- goto again;
+ goto cleanup;
}
ptr = __xa_store(&root->delayed_nodes, ino, node, GFP_ATOMIC);
ASSERT(xa_err(ptr) != -EINVAL);
ASSERT(xa_err(ptr) != -ENOMEM);
ASSERT(ptr == NULL);
-
- /* Cached in the inode and can be accessed. */
- refcount_set(&node->refs, 2);
- btrfs_delayed_node_ref_tracker_alloc(node, tracker, GFP_ATOMIC);
- btrfs_delayed_node_ref_tracker_alloc(node, &node->inode_cache_tracker, GFP_ATOMIC);
-
btrfs_inode->delayed_node = node;
xa_unlock(&root->delayed_nodes);
return node;
+cleanup:
+ btrfs_delayed_node_ref_tracker_free(node, tracker);
+ btrfs_delayed_node_ref_tracker_free(node, &node->inode_cache_tracker);
+ btrfs_delayed_node_ref_tracker_dir_exit(node);
+ kmem_cache_free(delayed_node_cache, node);
+ if (ret)
+ return ERR_PTR(ret);
+ goto again;
}
/*
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 89149fac804c..d8ca5b6e88e0 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -2255,6 +2255,7 @@ static int btrfs_read_roots(struct btrfs_fs_info *fs_info)
BTRFS_DATA_RELOC_TREE_OBJECTID, true);
if (IS_ERR(root)) {
if (!btrfs_test_opt(fs_info, IGNOREBADROOTS)) {
+ location.objectid = BTRFS_DATA_RELOC_TREE_OBJECTID;
ret = PTR_ERR(root);
goto out;
}
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 629fd5af4286..a4b74023618d 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -1728,7 +1728,7 @@ static noinline_for_stack int extent_writepage_io(struct btrfs_inode *inode,
struct btrfs_ordered_extent *ordered;
ordered = btrfs_lookup_first_ordered_range(inode, cur,
- folio_end - cur);
+ fs_info->sectorsize);
/*
* We have just run delalloc before getting here, so
* there must be an ordered extent.
@@ -1742,7 +1742,7 @@ static noinline_for_stack int extent_writepage_io(struct btrfs_inode *inode,
btrfs_put_ordered_extent(ordered);
btrfs_mark_ordered_io_finished(inode, folio, cur,
- end - cur, true);
+ fs_info->sectorsize, true);
/*
* This range is beyond i_size, thus we don't need to
* bother writing back.
@@ -1751,8 +1751,8 @@ static noinline_for_stack int extent_writepage_io(struct btrfs_inode *inode,
* writeback the sectors with subpage dirty bits,
* causing writeback without ordered extent.
*/
- btrfs_folio_clear_dirty(fs_info, folio, cur, end - cur);
- break;
+ btrfs_folio_clear_dirty(fs_info, folio, cur, fs_info->sectorsize);
+ continue;
}
ret = submit_one_sector(inode, folio, cur, bio_ctrl, i_size);
if (unlikely(ret < 0)) {
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 317db7d10a21..d2b302ac6af9 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -481,13 +481,15 @@ static int insert_inline_extent(struct btrfs_trans_handle *trans,
ASSERT(size <= sectorsize);
/*
- * The compressed size also needs to be no larger than a sector.
- * That's also why we only need one page as the parameter.
+ * The compressed size also needs to be no larger than a page.
+ * That's also why we only need one folio as the parameter.
*/
- if (compressed_folio)
+ if (compressed_folio) {
ASSERT(compressed_size <= sectorsize);
- else
+ ASSERT(compressed_size <= PAGE_SIZE);
+ } else {
ASSERT(compressed_size == 0);
+ }
if (compressed_size && compressed_folio)
cur_size = compressed_size;
@@ -574,6 +576,18 @@ static bool can_cow_file_range_inline(struct btrfs_inode *inode,
if (offset != 0)
return false;
+ /*
+ * Even for bs > ps cases, cow_file_range_inline() can only accept a
+ * single folio.
+ *
+ * This can be problematic and cause access beyond page boundary if a
+ * page sized folio is passed into that function.
+ * And encoded write is doing exactly that.
+ * So here limits the inlined extent size to PAGE_SIZE.
+ */
+ if (size > PAGE_SIZE || compressed_size > PAGE_SIZE)
+ return false;
+
/* Inline extents are limited to sectorsize. */
if (size > fs_info->sectorsize)
return false;
@@ -618,19 +632,22 @@ static noinline int __cow_file_range_inline(struct btrfs_inode *inode,
struct btrfs_drop_extents_args drop_args = { 0 };
struct btrfs_root *root = inode->root;
struct btrfs_fs_info *fs_info = root->fs_info;
- struct btrfs_trans_handle *trans;
+ struct btrfs_trans_handle *trans = NULL;
u64 data_len = (compressed_size ?: size);
int ret;
struct btrfs_path *path;
path = btrfs_alloc_path();
- if (!path)
- return -ENOMEM;
+ if (!path) {
+ ret = -ENOMEM;
+ goto out;
+ }
trans = btrfs_join_transaction(root);
if (IS_ERR(trans)) {
- btrfs_free_path(path);
- return PTR_ERR(trans);
+ ret = PTR_ERR(trans);
+ trans = NULL;
+ goto out;
}
trans->block_rsv = &inode->block_rsv;
@@ -674,10 +691,15 @@ out:
* it won't count as data extent, free them directly here.
* And at reserve time, it's always aligned to page size, so
* just free one page here.
+ *
+ * If we fallback to non-inline (ret == 1) due to -ENOSPC, then we need
+ * to keep the data reservation.
*/
- btrfs_qgroup_free_data(inode, NULL, 0, fs_info->sectorsize, NULL);
+ if (ret <= 0)
+ btrfs_qgroup_free_data(inode, NULL, 0, fs_info->sectorsize, NULL);
btrfs_free_path(path);
- btrfs_end_transaction(trans);
+ if (trans)
+ btrfs_end_transaction(trans);
return ret;
}
@@ -4026,11 +4048,6 @@ static int btrfs_read_locked_inode(struct btrfs_inode *inode, struct btrfs_path
btrfs_set_inode_mapping_order(inode);
cache_index:
- ret = btrfs_init_file_extent_tree(inode);
- if (ret)
- goto out;
- btrfs_inode_set_file_extent_range(inode, 0,
- round_up(i_size_read(vfs_inode), fs_info->sectorsize));
/*
* If we were modified in the current generation and evicted from memory
* and then re-read we need to do a full sync since we don't have any
@@ -4117,6 +4134,20 @@ cache_acl:
btrfs_ino(inode), btrfs_root_id(root), ret);
}
+ /*
+ * We don't need the path anymore, so release it to avoid holding a read
+ * lock on a leaf while calling btrfs_init_file_extent_tree(), which can
+ * allocate memory that triggers reclaim (GFP_KERNEL) and cause a locking
+ * dependency.
+ */
+ btrfs_release_path(path);
+
+ ret = btrfs_init_file_extent_tree(inode);
+ if (ret)
+ goto out;
+ btrfs_inode_set_file_extent_range(inode, 0,
+ round_up(i_size_read(vfs_inode), fs_info->sectorsize));
+
if (!maybe_acls)
cache_no_acl(vfs_inode);
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index d9d8d9968a58..206587820fec 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -3208,9 +3208,15 @@ static int qgroup_snapshot_quick_inherit(struct btrfs_fs_info *fs_info,
{
struct btrfs_qgroup *src;
struct btrfs_qgroup *parent;
+ struct btrfs_qgroup *qgroup;
struct btrfs_qgroup_list *list;
+ LIST_HEAD(qgroup_list);
+ const u32 nodesize = fs_info->nodesize;
int nr_parents = 0;
+ if (btrfs_qgroup_mode(fs_info) != BTRFS_QGROUP_MODE_FULL)
+ return 0;
+
src = find_qgroup_rb(fs_info, srcid);
if (!src)
return -ENOENT;
@@ -3245,8 +3251,19 @@ static int qgroup_snapshot_quick_inherit(struct btrfs_fs_info *fs_info,
if (parent->excl != parent->rfer)
return 1;
- parent->excl += fs_info->nodesize;
- parent->rfer += fs_info->nodesize;
+ qgroup_iterator_add(&qgroup_list, parent);
+ list_for_each_entry(qgroup, &qgroup_list, iterator) {
+ qgroup->rfer += nodesize;
+ qgroup->rfer_cmpr += nodesize;
+ qgroup->excl += nodesize;
+ qgroup->excl_cmpr += nodesize;
+ qgroup_dirty(fs_info, qgroup);
+
+ /* Append parent qgroups to @qgroup_list. */
+ list_for_each_entry(list, &qgroup->groups, next_group)
+ qgroup_iterator_add(&qgroup_list, list->group);
+ }
+ qgroup_iterator_clean(&qgroup_list);
return 0;
}
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 1999533b52be..af56fdbba65d 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -736,14 +736,12 @@ bool btrfs_check_options(const struct btrfs_fs_info *info,
*/
void btrfs_set_free_space_cache_settings(struct btrfs_fs_info *fs_info)
{
- if (fs_info->sectorsize < PAGE_SIZE) {
+ if (fs_info->sectorsize != PAGE_SIZE && btrfs_test_opt(fs_info, SPACE_CACHE)) {
+ btrfs_info(fs_info,
+ "forcing free space tree for sector size %u with page size %lu",
+ fs_info->sectorsize, PAGE_SIZE);
btrfs_clear_opt(fs_info->mount_opt, SPACE_CACHE);
- if (!btrfs_test_opt(fs_info, FREE_SPACE_TREE)) {
- btrfs_info(fs_info,
- "forcing free space tree for sector size %u with page size %lu",
- fs_info->sectorsize, PAGE_SIZE);
- btrfs_set_opt(fs_info->mount_opt, FREE_SPACE_TREE);
- }
+ btrfs_set_opt(fs_info->mount_opt, FREE_SPACE_TREE);
}
/*
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 05ee4391c83a..bd03f465e2d3 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -520,13 +520,14 @@ static inline int is_transaction_blocked(struct btrfs_transaction *trans)
* when this is done, it is safe to start a new transaction, but the current
* transaction might not be fully on disk.
*/
-static void wait_current_trans(struct btrfs_fs_info *fs_info)
+static void wait_current_trans(struct btrfs_fs_info *fs_info, unsigned int type)
{
struct btrfs_transaction *cur_trans;
spin_lock(&fs_info->trans_lock);
cur_trans = fs_info->running_transaction;
- if (cur_trans && is_transaction_blocked(cur_trans)) {
+ if (cur_trans && is_transaction_blocked(cur_trans) &&
+ (btrfs_blocked_trans_types[cur_trans->state] & type)) {
refcount_inc(&cur_trans->use_count);
spin_unlock(&fs_info->trans_lock);
@@ -701,12 +702,12 @@ again:
sb_start_intwrite(fs_info->sb);
if (may_wait_transaction(fs_info, type))
- wait_current_trans(fs_info);
+ wait_current_trans(fs_info, type);
do {
ret = join_transaction(fs_info, type);
if (ret == -EBUSY) {
- wait_current_trans(fs_info);
+ wait_current_trans(fs_info, type);
if (unlikely(type == TRANS_ATTACH ||
type == TRANS_JOIN_NOSTART))
ret = -ENOENT;
@@ -1003,7 +1004,7 @@ out:
void btrfs_throttle(struct btrfs_fs_info *fs_info)
{
- wait_current_trans(fs_info);
+ wait_current_trans(fs_info, TRANS_START);
}
bool btrfs_should_end_transaction(struct btrfs_trans_handle *trans)
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 31edc93a383e..2d9d38b82daa 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -190,7 +190,7 @@ static void do_abort_log_replay(struct walk_control *wc, const char *function,
btrfs_abort_transaction(wc->trans, error);
- if (wc->subvol_path->nodes[0]) {
+ if (wc->subvol_path && wc->subvol_path->nodes[0]) {
btrfs_crit(fs_info,
"subvolume (root %llu) leaf currently being processed:",
btrfs_root_id(wc->root));
@@ -6341,10 +6341,8 @@ again:
* and no keys greater than that, so bail out.
*/
break;
- } else if ((min_key->type == BTRFS_INODE_REF_KEY ||
- min_key->type == BTRFS_INODE_EXTREF_KEY) &&
- (inode->generation == trans->transid ||
- ctx->logging_conflict_inodes)) {
+ } else if (min_key->type == BTRFS_INODE_REF_KEY ||
+ min_key->type == BTRFS_INODE_EXTREF_KEY) {
u64 other_ino = 0;
u64 other_parent = 0;