summaryrefslogtreecommitdiffstats
path: root/fs/btrfs/disk-io.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/btrfs/disk-io.c')
-rw-r--r--fs/btrfs/disk-io.c229
1 files changed, 119 insertions, 110 deletions
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 6fe9197f6ee4..deb74a8c191a 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -260,15 +260,12 @@ void btrfs_csum_final(u32 crc, u8 *result)
}
/*
- * compute the csum for a btree block, and either verify it or write it
- * into the csum field of the block.
+ * Compute the csum of a btree block and store the result to provided buffer.
+ *
+ * Returns error if the extent buffer cannot be mapped.
*/
-static int csum_tree_block(struct btrfs_fs_info *fs_info,
- struct extent_buffer *buf,
- int verify)
+static int csum_tree_block(struct extent_buffer *buf, u8 *result)
{
- u16 csum_size = btrfs_super_csum_size(fs_info->super_copy);
- char result[BTRFS_CSUM_SIZE];
unsigned long len;
unsigned long cur_len;
unsigned long offset = BTRFS_CSUM_SIZE;
@@ -288,7 +285,7 @@ static int csum_tree_block(struct btrfs_fs_info *fs_info,
*/
err = map_private_extent_buffer(buf, offset, 32,
&kaddr, &map_start, &map_len);
- if (err)
+ if (WARN_ON(err))
return err;
cur_len = min(len, map_len - (offset - map_start));
crc = btrfs_csum_data(kaddr + offset - map_start,
@@ -300,23 +297,6 @@ static int csum_tree_block(struct btrfs_fs_info *fs_info,
btrfs_csum_final(crc, result);
- if (verify) {
- if (memcmp_extent_buffer(buf, result, 0, csum_size)) {
- u32 val;
- u32 found = 0;
- memcpy(&found, result, csum_size);
-
- read_extent_buffer(buf, &val, 0, csum_size);
- btrfs_warn_rl(fs_info,
- "%s checksum verify failed on %llu wanted %X found %X level %d",
- fs_info->sb->s_id, buf->start,
- val, found, btrfs_header_level(buf));
- return -EUCLEAN;
- }
- } else {
- write_extent_buffer(buf, result, 0, csum_size);
- }
-
return 0;
}
@@ -414,22 +394,21 @@ static int btrfs_check_super_csum(struct btrfs_fs_info *fs_info,
return ret;
}
-static int verify_level_key(struct btrfs_fs_info *fs_info,
- struct extent_buffer *eb, int level,
- struct btrfs_key *first_key, u64 parent_transid)
+int btrfs_verify_level_key(struct extent_buffer *eb, int level,
+ struct btrfs_key *first_key, u64 parent_transid)
{
+ struct btrfs_fs_info *fs_info = eb->fs_info;
int found_level;
struct btrfs_key found_key;
int ret;
found_level = btrfs_header_level(eb);
if (found_level != level) {
-#ifdef CONFIG_BTRFS_DEBUG
- WARN_ON(1);
+ WARN(IS_ENABLED(CONFIG_BTRFS_DEBUG),
+ KERN_ERR "BTRFS: tree level check failed\n");
btrfs_err(fs_info,
"tree level mismatch detected, bytenr=%llu level expected=%u has=%u",
eb->start, level, found_level);
-#endif
return -EIO;
}
@@ -450,9 +429,9 @@ static int verify_level_key(struct btrfs_fs_info *fs_info,
btrfs_item_key_to_cpu(eb, &found_key, 0);
ret = btrfs_comp_cpu_keys(first_key, &found_key);
-#ifdef CONFIG_BTRFS_DEBUG
if (ret) {
- WARN_ON(1);
+ WARN(IS_ENABLED(CONFIG_BTRFS_DEBUG),
+ KERN_ERR "BTRFS: tree first key check failed\n");
btrfs_err(fs_info,
"tree first key mismatch detected, bytenr=%llu parent_transid=%llu key expected=(%llu,%u,%llu) has=(%llu,%u,%llu)",
eb->start, parent_transid, first_key->objectid,
@@ -460,7 +439,6 @@ static int verify_level_key(struct btrfs_fs_info *fs_info,
found_key.objectid, found_key.type,
found_key.offset);
}
-#endif
return ret;
}
@@ -472,11 +450,11 @@ static int verify_level_key(struct btrfs_fs_info *fs_info,
* @level: expected level, mandatory check
* @first_key: expected key of first slot, skip check if NULL
*/
-static int btree_read_extent_buffer_pages(struct btrfs_fs_info *fs_info,
- struct extent_buffer *eb,
+static int btree_read_extent_buffer_pages(struct extent_buffer *eb,
u64 parent_transid, int level,
struct btrfs_key *first_key)
{
+ struct btrfs_fs_info *fs_info = eb->fs_info;
struct extent_io_tree *io_tree;
int failed = 0;
int ret;
@@ -487,14 +465,13 @@ static int btree_read_extent_buffer_pages(struct btrfs_fs_info *fs_info,
io_tree = &BTRFS_I(fs_info->btree_inode)->io_tree;
while (1) {
clear_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags);
- ret = read_extent_buffer_pages(io_tree, eb, WAIT_COMPLETE,
- mirror_num);
+ ret = read_extent_buffer_pages(eb, WAIT_COMPLETE, mirror_num);
if (!ret) {
if (verify_parent_transid(io_tree, eb,
parent_transid, 0))
ret = -EIO;
- else if (verify_level_key(fs_info, eb, level,
- first_key, parent_transid))
+ else if (btrfs_verify_level_key(eb, level,
+ first_key, parent_transid))
ret = -EUCLEAN;
else
break;
@@ -519,7 +496,7 @@ static int btree_read_extent_buffer_pages(struct btrfs_fs_info *fs_info,
}
if (failed && !ret && failed_mirror)
- repair_eb_io_failure(fs_info, eb, failed_mirror);
+ btrfs_repair_eb_io_failure(eb, failed_mirror);
return ret;
}
@@ -533,7 +510,10 @@ static int csum_dirty_buffer(struct btrfs_fs_info *fs_info, struct page *page)
{
u64 start = page_offset(page);
u64 found_start;
+ u8 result[BTRFS_CSUM_SIZE];
+ u16 csum_size = btrfs_super_csum_size(fs_info->super_copy);
struct extent_buffer *eb;
+ int ret;
eb = (struct extent_buffer *)page->private;
if (page != eb->pages[0])
@@ -552,12 +532,28 @@ static int csum_dirty_buffer(struct btrfs_fs_info *fs_info, struct page *page)
ASSERT(memcmp_extent_buffer(eb, fs_info->fs_devices->metadata_uuid,
btrfs_header_fsid(), BTRFS_FSID_SIZE) == 0);
- return csum_tree_block(fs_info, eb, 0);
+ if (csum_tree_block(eb, result))
+ return -EINVAL;
+
+ if (btrfs_header_level(eb))
+ ret = btrfs_check_node(eb);
+ else
+ ret = btrfs_check_leaf_full(eb);
+
+ if (ret < 0) {
+ btrfs_err(fs_info,
+ "block=%llu write time tree block corruption detected",
+ eb->start);
+ return ret;
+ }
+ write_extent_buffer(eb, result, 0, csum_size);
+
+ return 0;
}
-static int check_tree_block_fsid(struct btrfs_fs_info *fs_info,
- struct extent_buffer *eb)
+static int check_tree_block_fsid(struct extent_buffer *eb)
{
+ struct btrfs_fs_info *fs_info = eb->fs_info;
struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
u8 fsid[BTRFS_FSID_SIZE];
int ret = 1;
@@ -595,7 +591,9 @@ static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio,
struct extent_buffer *eb;
struct btrfs_root *root = BTRFS_I(page->mapping->host)->root;
struct btrfs_fs_info *fs_info = root->fs_info;
+ u16 csum_size = btrfs_super_csum_size(fs_info->super_copy);
int ret = 0;
+ u8 result[BTRFS_CSUM_SIZE];
int reads_done;
if (!page->private)
@@ -625,7 +623,7 @@ static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio,
ret = -EIO;
goto err;
}
- if (check_tree_block_fsid(fs_info, eb)) {
+ if (check_tree_block_fsid(eb)) {
btrfs_err_rl(fs_info, "bad fsid on block %llu",
eb->start);
ret = -EIO;
@@ -642,25 +640,44 @@ static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio,
btrfs_set_buffer_lockdep_class(btrfs_header_owner(eb),
eb, found_level);
- ret = csum_tree_block(fs_info, eb, 1);
+ ret = csum_tree_block(eb, result);
if (ret)
goto err;
+ if (memcmp_extent_buffer(eb, result, 0, csum_size)) {
+ u32 val;
+ u32 found = 0;
+
+ memcpy(&found, result, csum_size);
+
+ read_extent_buffer(eb, &val, 0, csum_size);
+ btrfs_warn_rl(fs_info,
+ "%s checksum verify failed on %llu wanted %x found %x level %d",
+ fs_info->sb->s_id, eb->start,
+ val, found, btrfs_header_level(eb));
+ ret = -EUCLEAN;
+ goto err;
+ }
+
/*
* If this is a leaf block and it is corrupt, set the corrupt bit so
* that we don't try and read the other copies of this block, just
* return -EIO.
*/
- if (found_level == 0 && btrfs_check_leaf_full(fs_info, eb)) {
+ if (found_level == 0 && btrfs_check_leaf_full(eb)) {
set_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags);
ret = -EIO;
}
- if (found_level > 0 && btrfs_check_node(fs_info, eb))
+ if (found_level > 0 && btrfs_check_node(eb))
ret = -EIO;
if (!ret)
set_extent_buffer_uptodate(eb);
+ else
+ btrfs_err(fs_info,
+ "block=%llu read time tree block corruption detected",
+ eb->start);
err:
if (reads_done &&
test_and_clear_bit(EXTENT_BUFFER_READAHEAD, &eb->bflags))
@@ -832,11 +849,11 @@ static blk_status_t btree_csum_one_bio(struct bio *bio)
{
struct bio_vec *bvec;
struct btrfs_root *root;
- int i, ret = 0;
+ int ret = 0;
struct bvec_iter_all iter_all;
ASSERT(!bio_flagged(bio, BIO_CLONED));
- bio_for_each_segment_all(bvec, bio, i, iter_all) {
+ bio_for_each_segment_all(bvec, bio, iter_all) {
root = BTRFS_I(bvec->bv_page->mapping->host)->root;
ret = csum_dirty_buffer(root->fs_info, bvec->bv_page);
if (ret)
@@ -867,11 +884,10 @@ static int check_async_write(struct btrfs_inode *bi)
return 1;
}
-static blk_status_t btree_submit_bio_hook(void *private_data, struct bio *bio,
- int mirror_num, unsigned long bio_flags,
- u64 bio_offset)
+static blk_status_t btree_submit_bio_hook(struct inode *inode, struct bio *bio,
+ int mirror_num,
+ unsigned long bio_flags)
{
- struct inode *inode = private_data;
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
int async = check_async_write(BTRFS_I(inode));
blk_status_t ret;
@@ -897,8 +913,7 @@ static blk_status_t btree_submit_bio_hook(void *private_data, struct bio *bio,
* checksumming can happen in parallel across all CPUs
*/
ret = btrfs_wq_submit_bio(fs_info, bio, mirror_num, 0,
- bio_offset, private_data,
- btree_submit_bio_start);
+ 0, inode, btree_submit_bio_start);
}
if (ret)
@@ -1017,22 +1032,23 @@ static const struct address_space_operations btree_aops = {
void readahead_tree_block(struct btrfs_fs_info *fs_info, u64 bytenr)
{
struct extent_buffer *buf = NULL;
- struct inode *btree_inode = fs_info->btree_inode;
+ int ret;
buf = btrfs_find_create_tree_block(fs_info, bytenr);
if (IS_ERR(buf))
return;
- read_extent_buffer_pages(&BTRFS_I(btree_inode)->io_tree,
- buf, WAIT_NONE, 0);
- free_extent_buffer(buf);
+
+ ret = read_extent_buffer_pages(buf, WAIT_NONE, 0);
+ if (ret < 0)
+ free_extent_buffer_stale(buf);
+ else
+ free_extent_buffer(buf);
}
int reada_tree_block_flagged(struct btrfs_fs_info *fs_info, u64 bytenr,
int mirror_num, struct extent_buffer **eb)
{
struct extent_buffer *buf = NULL;
- struct inode *btree_inode = fs_info->btree_inode;
- struct extent_io_tree *io_tree = &BTRFS_I(btree_inode)->io_tree;
int ret;
buf = btrfs_find_create_tree_block(fs_info, bytenr);
@@ -1041,15 +1057,14 @@ int reada_tree_block_flagged(struct btrfs_fs_info *fs_info, u64 bytenr,
set_bit(EXTENT_BUFFER_READAHEAD, &buf->bflags);
- ret = read_extent_buffer_pages(io_tree, buf, WAIT_PAGE_LOCK,
- mirror_num);
+ ret = read_extent_buffer_pages(buf, WAIT_PAGE_LOCK, mirror_num);
if (ret) {
- free_extent_buffer(buf);
+ free_extent_buffer_stale(buf);
return ret;
}
if (test_bit(EXTENT_BUFFER_CORRUPT, &buf->bflags)) {
- free_extent_buffer(buf);
+ free_extent_buffer_stale(buf);
return -EIO;
} else if (extent_buffer_uptodate(buf)) {
*eb = buf;
@@ -1068,19 +1083,6 @@ struct extent_buffer *btrfs_find_create_tree_block(
return alloc_extent_buffer(fs_info, bytenr);
}
-
-int btrfs_write_tree_block(struct extent_buffer *buf)
-{
- return filemap_fdatawrite_range(buf->pages[0]->mapping, buf->start,
- buf->start + buf->len - 1);
-}
-
-void btrfs_wait_tree_block_writeback(struct extent_buffer *buf)
-{
- filemap_fdatawait_range(buf->pages[0]->mapping,
- buf->start, buf->start + buf->len - 1);
-}
-
/*
* Read tree block at logical address @bytenr and do variant basic but critical
* verification.
@@ -1100,19 +1102,19 @@ struct extent_buffer *read_tree_block(struct btrfs_fs_info *fs_info, u64 bytenr,
if (IS_ERR(buf))
return buf;
- ret = btree_read_extent_buffer_pages(fs_info, buf, parent_transid,
+ ret = btree_read_extent_buffer_pages(buf, parent_transid,
level, first_key);
if (ret) {
- free_extent_buffer(buf);
+ free_extent_buffer_stale(buf);
return ERR_PTR(ret);
}
return buf;
}
-void clean_tree_block(struct btrfs_fs_info *fs_info,
- struct extent_buffer *buf)
+void btrfs_clean_tree_block(struct extent_buffer *buf)
{
+ struct btrfs_fs_info *fs_info = buf->fs_info;
if (btrfs_header_generation(buf) ==
fs_info->running_transaction->transid) {
btrfs_assert_tree_locked(buf);
@@ -1208,7 +1210,8 @@ static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info,
root->log_transid_committed = -1;
root->last_log_commit = 0;
if (!dummy)
- extent_io_tree_init(&root->dirty_log_pages, NULL);
+ extent_io_tree_init(fs_info, &root->dirty_log_pages,
+ IO_TREE_ROOT_DIRTY_LOG_PAGES, NULL);
memset(&root->root_key, 0, sizeof(root->root_key));
memset(&root->root_item, 0, sizeof(root->root_item));
@@ -1255,9 +1258,9 @@ struct btrfs_root *btrfs_alloc_dummy_root(struct btrfs_fs_info *fs_info)
#endif
struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans,
- struct btrfs_fs_info *fs_info,
u64 objectid)
{
+ struct btrfs_fs_info *fs_info = trans->fs_info;
struct extent_buffer *leaf;
struct btrfs_root *tree_root = fs_info->tree_root;
struct btrfs_root *root;
@@ -2138,8 +2141,9 @@ static void btrfs_init_btree_inode(struct btrfs_fs_info *fs_info)
inode->i_mapping->a_ops = &btree_aops;
RB_CLEAR_NODE(&BTRFS_I(inode)->rb_node);
- extent_io_tree_init(&BTRFS_I(inode)->io_tree, inode);
- BTRFS_I(inode)->io_tree.track_uptodate = 0;
+ extent_io_tree_init(fs_info, &BTRFS_I(inode)->io_tree,
+ IO_TREE_INODE_IO, inode);
+ BTRFS_I(inode)->io_tree.track_uptodate = false;
extent_map_tree_init(&BTRFS_I(inode)->extent_tree);
BTRFS_I(inode)->io_tree.ops = &btree_extent_io_ops;
@@ -2162,7 +2166,6 @@ static void btrfs_init_qgroup(struct btrfs_fs_info *fs_info)
spin_lock_init(&fs_info->qgroup_lock);
mutex_init(&fs_info->qgroup_ioctl_lock);
fs_info->qgroup_tree = RB_ROOT;
- fs_info->qgroup_op_tree = RB_ROOT;
INIT_LIST_HEAD(&fs_info->dirty_qgroups);
fs_info->qgroup_seq = 1;
fs_info->qgroup_ulist = NULL;
@@ -2630,11 +2633,17 @@ int open_ctree(struct super_block *sb,
goto fail;
}
- ret = percpu_counter_init(&fs_info->dirty_metadata_bytes, 0, GFP_KERNEL);
+ ret = percpu_counter_init(&fs_info->dio_bytes, 0, GFP_KERNEL);
if (ret) {
err = ret;
goto fail_srcu;
}
+
+ ret = percpu_counter_init(&fs_info->dirty_metadata_bytes, 0, GFP_KERNEL);
+ if (ret) {
+ err = ret;
+ goto fail_dio_bytes;
+ }
fs_info->dirty_metadata_batch = PAGE_SIZE *
(1 + ilog2(nr_cpu_ids));
@@ -2667,7 +2676,6 @@ int open_ctree(struct super_block *sb,
spin_lock_init(&fs_info->defrag_inodes_lock);
spin_lock_init(&fs_info->tree_mod_seq_lock);
spin_lock_init(&fs_info->super_lock);
- spin_lock_init(&fs_info->qgroup_op_lock);
spin_lock_init(&fs_info->buffer_lock);
spin_lock_init(&fs_info->unused_bgs_lock);
rwlock_init(&fs_info->tree_mod_log_lock);
@@ -2694,7 +2702,6 @@ int open_ctree(struct super_block *sb,
atomic_set(&fs_info->async_delalloc_pages, 0);
atomic_set(&fs_info->defrag_running, 0);
- atomic_set(&fs_info->qgroup_op_seq, 0);
atomic_set(&fs_info->reada_works_cnt, 0);
atomic_set(&fs_info->nr_delayed_iputs, 0);
atomic64_set(&fs_info->tree_mod_seq, 0);
@@ -2748,8 +2755,10 @@ int open_ctree(struct super_block *sb,
fs_info->block_group_cache_tree = RB_ROOT;
fs_info->first_logical_byte = (u64)-1;
- extent_io_tree_init(&fs_info->freed_extents[0], NULL);
- extent_io_tree_init(&fs_info->freed_extents[1], NULL);
+ extent_io_tree_init(fs_info, &fs_info->freed_extents[0],
+ IO_TREE_FS_INFO_FREED_EXTENTS0, NULL);
+ extent_io_tree_init(fs_info, &fs_info->freed_extents[1],
+ IO_TREE_FS_INFO_FREED_EXTENTS1, NULL);
fs_info->pinned_extents = &fs_info->freed_extents[0];
set_bit(BTRFS_FS_BARRIER, &fs_info->flags);
@@ -2776,8 +2785,6 @@ int open_ctree(struct super_block *sb,
init_waitqueue_head(&fs_info->async_submit_wait);
init_waitqueue_head(&fs_info->delayed_iputs_wait);
- INIT_LIST_HEAD(&fs_info->pinned_chunks);
-
/* Usable values until the real ones are cached from the superblock */
fs_info->nodesize = 4096;
fs_info->sectorsize = 4096;
@@ -3335,6 +3342,8 @@ fail_delalloc_bytes:
percpu_counter_destroy(&fs_info->delalloc_bytes);
fail_dirty_metadata_bytes:
percpu_counter_destroy(&fs_info->dirty_metadata_bytes);
+fail_dio_bytes:
+ percpu_counter_destroy(&fs_info->dio_bytes);
fail_srcu:
cleanup_srcu_struct(&fs_info->subvol_srcu);
fail:
@@ -4016,6 +4025,10 @@ void close_ctree(struct btrfs_fs_info *fs_info)
percpu_counter_sum(&fs_info->delalloc_bytes));
}
+ if (percpu_counter_sum(&fs_info->dio_bytes))
+ btrfs_info(fs_info, "at unmount dio bytes count %lld",
+ percpu_counter_sum(&fs_info->dio_bytes));
+
btrfs_sysfs_remove_mounted(fs_info);
btrfs_sysfs_remove_fsid(fs_info->fs_devices);
@@ -4042,25 +4055,17 @@ void close_ctree(struct btrfs_fs_info *fs_info)
btrfsic_unmount(fs_info->fs_devices);
#endif
- btrfs_close_devices(fs_info->fs_devices);
btrfs_mapping_tree_free(&fs_info->mapping_tree);
+ btrfs_close_devices(fs_info->fs_devices);
percpu_counter_destroy(&fs_info->dirty_metadata_bytes);
percpu_counter_destroy(&fs_info->delalloc_bytes);
+ percpu_counter_destroy(&fs_info->dio_bytes);
percpu_counter_destroy(&fs_info->dev_replace.bio_counter);
cleanup_srcu_struct(&fs_info->subvol_srcu);
btrfs_free_stripe_hash_table(fs_info);
btrfs_free_ref_cache(fs_info);
-
- while (!list_empty(&fs_info->pinned_chunks)) {
- struct extent_map *em;
-
- em = list_first_entry(&fs_info->pinned_chunks,
- struct extent_map, list);
- list_del_init(&em->list);
- free_extent_map(em);
- }
}
int btrfs_buffer_uptodate(struct extent_buffer *buf, u64 parent_transid,
@@ -4114,7 +4119,7 @@ void btrfs_mark_buffer_dirty(struct extent_buffer *buf)
* So here we should only check item pointers, not item data.
*/
if (btrfs_header_level(buf) == 0 &&
- btrfs_check_leaf_relaxed(fs_info, buf)) {
+ btrfs_check_leaf_relaxed(buf)) {
btrfs_print_leaf(buf);
ASSERT(0);
}
@@ -4157,10 +4162,7 @@ void btrfs_btree_balance_dirty_nodelay(struct btrfs_fs_info *fs_info)
int btrfs_read_buffer(struct extent_buffer *buf, u64 parent_transid, int level,
struct btrfs_key *first_key)
{
- struct btrfs_root *root = BTRFS_I(buf->pages[0]->mapping->host)->root;
- struct btrfs_fs_info *fs_info = root->fs_info;
-
- return btree_read_extent_buffer_pages(fs_info, buf, parent_transid,
+ return btree_read_extent_buffer_pages(buf, parent_transid,
level, first_key);
}
@@ -4484,10 +4486,17 @@ void btrfs_cleanup_dirty_bgs(struct btrfs_transaction *cur_trans,
void btrfs_cleanup_one_transaction(struct btrfs_transaction *cur_trans,
struct btrfs_fs_info *fs_info)
{
+ struct btrfs_device *dev, *tmp;
+
btrfs_cleanup_dirty_bgs(cur_trans, fs_info);
ASSERT(list_empty(&cur_trans->dirty_bgs));
ASSERT(list_empty(&cur_trans->io_bgs));
+ list_for_each_entry_safe(dev, tmp, &cur_trans->dev_update_list,
+ post_commit_list) {
+ list_del_init(&dev->post_commit_list);
+ }
+
btrfs_destroy_delayed_refs(cur_trans, fs_info);
cur_trans->state = TRANS_STATE_COMMIT_START;
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-29 12:20:16 +0100