summaryrefslogtreecommitdiff
path: root/fs/btrfs/disk-io.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2024-07-17 12:38:04 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2024-07-17 12:38:04 -0700
commita1b547f0f217cfb06af7eb4ce8488b02d83a0370 (patch)
tree2935586a4371bfb9c5abec688dc279f99504cd08 /fs/btrfs/disk-io.c
parent6706415bf9f3dcb425f4b60a08a3a6f1d94ec0e0 (diff)
parent8e7860543a94784d744c7ce34b78a2e11beefa5c (diff)
Merge tag 'for-6.11-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux
Pull btrfs updates from David Sterba: "The highlights are new logic behind background block group reclaim, automatic removal of qgroup after removing a subvolume and new 'rescue=' mount options. The rest is optimizations, cleanups and refactoring. User visible features: - dynamic block group reclaim: - tunable framework to avoid situations where eager data allocations prevent creating new metadata chunks due to lack of unallocated space - reuse sysfs knob bg_reclaim_threshold (otherwise used only in zoned mode) for a fixed value threshold - new on/off sysfs knob "dynamic_reclaim" calculating the value based on heuristics, aiming to keep spare working space for relocating chunks but not to needlessly relocate partially utilized block groups or reclaim newly allocated ones - stats are exported in sysfs per block group type, files "reclaim_*" - this may increase IO load at unexpected times but the corner case of no allocatable block groups is known to be worse - automatically remove qgroup of deleted subvolumes: - adjust qgroup removal conditions, make sure all related subvolume data are already removed, or return EBUSY, also take into account setting of sysfs drop_subtree_threshold - also works in squota mode - mount option updates: new modes of 'rescue=' that allow to mount images (read-only) that could have been partially converted by user space tools - ignoremetacsums - invalid metadata checksums are ignored - ignoresuperflags - super block flags that track conversion in progress (like UUID or checksums) Core: - size of struct btrfs_inode is now below 1024 (on a release config), improved memory packing and other secondary effects - switch tracking of open inodes from rb-tree to xarray, minor performance improvement - reduce number of empty transaction commits when there are no dirty data/metadata - memory allocation optimizations (reduced numbers, reordering out of critical sections) - extent map structure optimizations and refactoring, more sanity checks - more subpage in zoned mode preparations or fixes - general snapshot code cleanups, improvements and documentation - tree-checker updates: more file extent ram_bytes fixes, continued - raid-stripe-tree update (not backward compatible): - remove extent encoding field from the structure, can be inferred from other information - requires btrfs-progs 6.9.1 or newer - cleanups and refactoring - error message updates - error handling improvements - return type and parameter cleanups and improvements" * tag 'for-6.11-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux: (152 commits) btrfs: fix extent map use-after-free when adding pages to compressed bio btrfs: fix bitmap leak when loading free space cache on duplicate entry btrfs: remove the BUG_ON() inside extent_range_clear_dirty_for_io() btrfs: move extent_range_clear_dirty_for_io() into inode.c btrfs: enhance compression error messages btrfs: fix data race when accessing the last_trans field of a root btrfs: rename the extra_gfp parameter of btrfs_alloc_page_array() btrfs: remove the extra_gfp parameter from btrfs_alloc_folio_array() btrfs: introduce new "rescue=ignoresuperflags" mount option btrfs: introduce new "rescue=ignoremetacsums" mount option btrfs: output the unrecognized super block flags as hex btrfs: remove unused Opt enums btrfs: tree-checker: add extra ram_bytes and disk_num_bytes check btrfs: fix the ram_bytes assignment for truncated ordered extents btrfs: make validate_extent_map() catch ram_bytes mismatch btrfs: ignore incorrect btrfs_file_extent_item::ram_bytes btrfs: cleanup the bytenr usage inside btrfs_extent_item_to_extent_map() btrfs: fix typo in error message in btrfs_validate_super() btrfs: move the direct IO code into its own file btrfs: pass a btrfs_inode to btrfs_set_prop() ...
Diffstat (limited to 'fs/btrfs/disk-io.c')
-rw-r--r--fs/btrfs/disk-io.c128
1 files changed, 61 insertions, 67 deletions
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index cabb558dbdaa..a6f5441e62d1 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -213,7 +213,7 @@ static int btrfs_repair_eb_io_failure(const struct extent_buffer *eb,
* structure for details.
*/
int btrfs_read_extent_buffer(struct extent_buffer *eb,
- struct btrfs_tree_parent_check *check)
+ const struct btrfs_tree_parent_check *check)
{
struct btrfs_fs_info *fs_info = eb->fs_info;
int failed = 0;
@@ -358,7 +358,7 @@ static bool check_tree_block_fsid(struct extent_buffer *eb)
/* Do basic extent buffer checks at read time */
int btrfs_validate_extent_buffer(struct extent_buffer *eb,
- struct btrfs_tree_parent_check *check)
+ const struct btrfs_tree_parent_check *check)
{
struct btrfs_fs_info *fs_info = eb->fs_info;
u64 found_start;
@@ -367,6 +367,7 @@ int btrfs_validate_extent_buffer(struct extent_buffer *eb,
u8 result[BTRFS_CSUM_SIZE];
const u8 *header_csum;
int ret = 0;
+ const bool ignore_csum = btrfs_test_opt(fs_info, IGNOREMETACSUMS);
ASSERT(check);
@@ -399,13 +400,16 @@ int btrfs_validate_extent_buffer(struct extent_buffer *eb,
if (memcmp(result, header_csum, csum_size) != 0) {
btrfs_warn_rl(fs_info,
-"checksum verify failed on logical %llu mirror %u wanted " CSUM_FMT " found " CSUM_FMT " level %d",
+"checksum verify failed on logical %llu mirror %u wanted " CSUM_FMT " found " CSUM_FMT " level %d%s",
eb->start, eb->read_mirror,
CSUM_FMT_VALUE(csum_size, header_csum),
CSUM_FMT_VALUE(csum_size, result),
- btrfs_header_level(eb));
- ret = -EUCLEAN;
- goto out;
+ btrfs_header_level(eb),
+ ignore_csum ? ", ignored" : "");
+ if (!ignore_csum) {
+ ret = -EUCLEAN;
+ goto out;
+ }
}
if (found_level != check->level) {
@@ -425,7 +429,7 @@ int btrfs_validate_extent_buffer(struct extent_buffer *eb,
goto out;
}
if (check->has_first_key) {
- struct btrfs_key *expect_key = &check->first_key;
+ const struct btrfs_key *expect_key = &check->first_key;
struct btrfs_key found_key;
if (found_level)
@@ -635,10 +639,6 @@ struct extent_buffer *read_tree_block(struct btrfs_fs_info *fs_info, u64 bytenr,
free_extent_buffer_stale(buf);
return ERR_PTR(ret);
}
- if (btrfs_check_eb_owner(buf, check->owner_root)) {
- free_extent_buffer_stale(buf);
- return ERR_PTR(-EUCLEAN);
- }
return buf;
}
@@ -658,11 +658,11 @@ static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info,
root->state = 0;
RB_CLEAR_NODE(&root->rb_node);
- root->last_trans = 0;
+ btrfs_set_root_last_trans(root, 0);
root->free_objectid = 0;
root->nr_delalloc_inodes = 0;
root->nr_ordered_extents = 0;
- root->inode_tree = RB_ROOT;
+ xa_init(&root->inodes);
xa_init(&root->delayed_nodes);
btrfs_init_root_block_rsv(root);
@@ -674,7 +674,6 @@ static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info,
INIT_LIST_HEAD(&root->ordered_extents);
INIT_LIST_HEAD(&root->ordered_root);
INIT_LIST_HEAD(&root->reloc_dirty_list);
- spin_lock_init(&root->inode_lock);
spin_lock_init(&root->delalloc_lock);
spin_lock_init(&root->ordered_extent_lock);
spin_lock_init(&root->accounting_lock);
@@ -847,13 +846,6 @@ struct btrfs_root *btrfs_extent_root(struct btrfs_fs_info *fs_info, u64 bytenr)
return btrfs_global_root(fs_info, &key);
}
-struct btrfs_root *btrfs_block_group_root(struct btrfs_fs_info *fs_info)
-{
- if (btrfs_fs_compat_ro(fs_info, BLOCK_GROUP_TREE))
- return fs_info->block_group_root;
- return btrfs_extent_root(fs_info, 0);
-}
-
struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans,
u64 objectid)
{
@@ -1010,7 +1002,7 @@ int btrfs_add_log_tree(struct btrfs_trans_handle *trans,
return ret;
}
- log_root->last_trans = trans->transid;
+ btrfs_set_root_last_trans(log_root, trans->transid);
log_root->root_key.offset = btrfs_root_id(root);
inode_item = &log_root->root_item.inode;
@@ -1033,7 +1025,7 @@ int btrfs_add_log_tree(struct btrfs_trans_handle *trans,
static struct btrfs_root *read_tree_root_path(struct btrfs_root *tree_root,
struct btrfs_path *path,
- struct btrfs_key *key)
+ const struct btrfs_key *key)
{
struct btrfs_root *root;
struct btrfs_tree_parent_check check = { 0 };
@@ -1095,7 +1087,7 @@ fail:
}
struct btrfs_root *btrfs_read_tree_root(struct btrfs_root *tree_root,
- struct btrfs_key *key)
+ const struct btrfs_key *key)
{
struct btrfs_root *root;
struct btrfs_path *path;
@@ -1230,7 +1222,7 @@ int btrfs_insert_fs_root(struct btrfs_fs_info *fs_info,
return ret;
}
-void btrfs_check_leaked_roots(struct btrfs_fs_info *fs_info)
+void btrfs_check_leaked_roots(const struct btrfs_fs_info *fs_info)
{
#ifdef CONFIG_BTRFS_DEBUG
struct btrfs_root *root;
@@ -1854,7 +1846,8 @@ void btrfs_put_root(struct btrfs_root *root)
return;
if (refcount_dec_and_test(&root->refs)) {
- WARN_ON(!RB_EMPTY_ROOT(&root->inode_tree));
+ if (WARN_ON(!xa_empty(&root->inodes)))
+ xa_destroy(&root->inodes);
WARN_ON(test_bit(BTRFS_ROOT_DEAD_RELOC_TREE, &root->state));
if (root->anon_dev)
free_anon_bdev(root->anon_dev);
@@ -1928,7 +1921,7 @@ static int btrfs_init_btree_inode(struct super_block *sb)
if (!inode)
return -ENOMEM;
- inode->i_ino = BTRFS_BTREE_INODE_OBJECTID;
+ btrfs_set_inode_number(BTRFS_I(inode), BTRFS_BTREE_INODE_OBJECTID);
set_nlink(inode, 1);
/*
* we set the i_size on the btree inode to the max possible int.
@@ -1939,15 +1932,11 @@ static int btrfs_init_btree_inode(struct super_block *sb)
inode->i_mapping->a_ops = &btree_aops;
mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS);
- RB_CLEAR_NODE(&BTRFS_I(inode)->rb_node);
extent_io_tree_init(fs_info, &BTRFS_I(inode)->io_tree,
IO_TREE_BTREE_INODE_IO);
extent_map_tree_init(&BTRFS_I(inode)->extent_tree);
BTRFS_I(inode)->root = btrfs_grab_root(fs_info->tree_root);
- BTRFS_I(inode)->location.objectid = BTRFS_BTREE_INODE_OBJECTID;
- BTRFS_I(inode)->location.type = 0;
- BTRFS_I(inode)->location.offset = 0;
set_bit(BTRFS_INODE_DUMMY, &BTRFS_I(inode)->runtime_flags);
__insert_inode_hash(inode, hash);
fs_info->btree_inode = inode;
@@ -2146,7 +2135,7 @@ static int load_global_roots_objectid(struct btrfs_root *tree_root,
/* If we have IGNOREDATACSUMS skip loading these roots. */
if (objectid == BTRFS_CSUM_TREE_OBJECTID &&
btrfs_test_opt(fs_info, IGNOREDATACSUMS)) {
- set_bit(BTRFS_FS_STATE_NO_CSUMS, &fs_info->fs_state);
+ set_bit(BTRFS_FS_STATE_NO_DATA_CSUMS, &fs_info->fs_state);
return 0;
}
@@ -2199,7 +2188,7 @@ static int load_global_roots_objectid(struct btrfs_root *tree_root,
if (!found || ret) {
if (objectid == BTRFS_CSUM_TREE_OBJECTID)
- set_bit(BTRFS_FS_STATE_NO_CSUMS, &fs_info->fs_state);
+ set_bit(BTRFS_FS_STATE_NO_DATA_CSUMS, &fs_info->fs_state);
if (!btrfs_test_opt(fs_info, IGNOREBADROOTS))
ret = ret ? ret : -ENOENT;
@@ -2350,21 +2339,29 @@ out:
* 1, 2 2nd and 3rd backup copy
* -1 skip bytenr check
*/
-int btrfs_validate_super(struct btrfs_fs_info *fs_info,
- struct btrfs_super_block *sb, int mirror_num)
+int btrfs_validate_super(const struct btrfs_fs_info *fs_info,
+ const struct btrfs_super_block *sb, int mirror_num)
{
u64 nodesize = btrfs_super_nodesize(sb);
u64 sectorsize = btrfs_super_sectorsize(sb);
int ret = 0;
+ const bool ignore_flags = btrfs_test_opt(fs_info, IGNORESUPERFLAGS);
if (btrfs_super_magic(sb) != BTRFS_MAGIC) {
btrfs_err(fs_info, "no valid FS found");
ret = -EINVAL;
}
- if (btrfs_super_flags(sb) & ~BTRFS_SUPER_FLAG_SUPP) {
- btrfs_err(fs_info, "unrecognized or unsupported super flag: %llu",
- btrfs_super_flags(sb) & ~BTRFS_SUPER_FLAG_SUPP);
- ret = -EINVAL;
+ if ((btrfs_super_flags(sb) & ~BTRFS_SUPER_FLAG_SUPP)) {
+ if (!ignore_flags) {
+ btrfs_err(fs_info,
+ "unrecognized or unsupported super flag 0x%llx",
+ btrfs_super_flags(sb) & ~BTRFS_SUPER_FLAG_SUPP);
+ ret = -EINVAL;
+ } else {
+ btrfs_info(fs_info,
+ "unrecognized or unsupported super flags: 0x%llx, ignored",
+ btrfs_super_flags(sb) & ~BTRFS_SUPER_FLAG_SUPP);
+ }
}
if (btrfs_super_root_level(sb) >= BTRFS_MAX_LEVEL) {
btrfs_err(fs_info, "tree_root level too big: %d >= %d",
@@ -2467,7 +2464,7 @@ int btrfs_validate_super(struct btrfs_fs_info *fs_info,
(!btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE_VALID) ||
!btrfs_fs_incompat(fs_info, NO_HOLES))) {
btrfs_err(fs_info,
- "block-group-tree feature requires fres-space-tree and no-holes");
+ "block-group-tree feature requires free-space-tree and no-holes");
ret = -EINVAL;
}
@@ -2882,6 +2879,8 @@ static int init_mount_fs_info(struct btrfs_fs_info *fs_info, struct super_block
if (sb_rdonly(sb))
set_bit(BTRFS_FS_STATE_RO, &fs_info->fs_state);
+ if (btrfs_test_opt(fs_info, IGNOREMETACSUMS))
+ set_bit(BTRFS_FS_STATE_SKIP_META_CSUMS, &fs_info->fs_state);
return btrfs_alloc_stripe_hash_table(fs_info);
}
@@ -2927,22 +2926,22 @@ static int btrfs_cleanup_fs_roots(struct btrfs_fs_info *fs_info)
{
u64 root_objectid = 0;
struct btrfs_root *gang[8];
- int i = 0;
- int err = 0;
- unsigned int ret = 0;
+ int ret = 0;
while (1) {
+ unsigned int found;
+
spin_lock(&fs_info->fs_roots_radix_lock);
- ret = radix_tree_gang_lookup(&fs_info->fs_roots_radix,
+ found = radix_tree_gang_lookup(&fs_info->fs_roots_radix,
(void **)gang, root_objectid,
ARRAY_SIZE(gang));
- if (!ret) {
+ if (!found) {
spin_unlock(&fs_info->fs_roots_radix_lock);
break;
}
- root_objectid = btrfs_root_id(gang[ret - 1]) + 1;
+ root_objectid = btrfs_root_id(gang[found - 1]) + 1;
- for (i = 0; i < ret; i++) {
+ for (int i = 0; i < found; i++) {
/* Avoid to grab roots in dead_roots. */
if (btrfs_root_refs(&gang[i]->root_item) == 0) {
gang[i] = NULL;
@@ -2953,24 +2952,25 @@ static int btrfs_cleanup_fs_roots(struct btrfs_fs_info *fs_info)
}
spin_unlock(&fs_info->fs_roots_radix_lock);
- for (i = 0; i < ret; i++) {
+ for (int i = 0; i < found; i++) {
if (!gang[i])
continue;
root_objectid = btrfs_root_id(gang[i]);
- err = btrfs_orphan_cleanup(gang[i]);
- if (err)
- goto out;
+ /*
+ * Continue to release the remaining roots after the first
+ * error without cleanup and preserve the first error
+ * for the return.
+ */
+ if (!ret)
+ ret = btrfs_orphan_cleanup(gang[i]);
btrfs_put_root(gang[i]);
}
+ if (ret)
+ break;
+
root_objectid++;
}
-out:
- /* Release the uncleaned roots due to error. */
- for (; i < ret; i++) {
- if (gang[i])
- btrfs_put_root(gang[i]);
- }
- return err;
+ return ret;
}
/*
@@ -3204,7 +3204,7 @@ int btrfs_check_features(struct btrfs_fs_info *fs_info, bool is_rw_mount)
}
int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_devices,
- char *options)
+ const char *options)
{
u32 sectorsize;
u32 nodesize;
@@ -4157,9 +4157,6 @@ void btrfs_drop_and_free_fs_root(struct btrfs_fs_info *fs_info,
int btrfs_commit_super(struct btrfs_fs_info *fs_info)
{
- struct btrfs_root *root = fs_info->tree_root;
- struct btrfs_trans_handle *trans;
-
mutex_lock(&fs_info->cleaner_mutex);
btrfs_run_delayed_iputs(fs_info);
mutex_unlock(&fs_info->cleaner_mutex);
@@ -4169,10 +4166,7 @@ int btrfs_commit_super(struct btrfs_fs_info *fs_info)
down_write(&fs_info->cleanup_work_sem);
up_write(&fs_info->cleanup_work_sem);
- trans = btrfs_join_transaction(root);
- if (IS_ERR(trans))
- return PTR_ERR(trans);
- return btrfs_commit_transaction(trans);
+ return btrfs_commit_current_transaction(fs_info->tree_root);
}
static void warn_about_uncommitted_trans(struct btrfs_fs_info *fs_info)
@@ -4533,7 +4527,7 @@ static void btrfs_destroy_all_ordered_extents(struct btrfs_fs_info *fs_info)
* extents that haven't had their dirty pages IO start writeout yet
* actually get run and error out properly.
*/
- btrfs_wait_ordered_roots(fs_info, U64_MAX, 0, (u64)-1);
+ btrfs_wait_ordered_roots(fs_info, U64_MAX, NULL);
}
static void btrfs_destroy_delayed_refs(struct btrfs_transaction *trans,