btrfs: move tree block parentness check into validate_extent_buffer()
[BACKGROUND]
Although both btrfs metadata and data has their read time verification
done at endio time (btrfs_validate_metadata_buffer() and
btrfs_verify_data_csum()), metadata has extra verification, mostly
parentness check including first key/transid/owner_root/level, done at
read_tree_block() and btrfs_read_extent_buffer().
On the other hand, all the data verification is done at endio context.
[ENHANCEMENT]
This patch will make a new union in btrfs_bio, taking the space of the
old data checksums, thus it will not increase the memory usage.
With that extra btrfs_tree_parent_check inside btrfs_bio, we can just
pass the check parameter into read_extent_buffer_pages(), and before
submitting the bio, we can copy the check structure into btrfs_bio.
And finally at endio time, we can grab btrfs_bio::parent_check and pass
it to validate_extent_buffer(), to move the remaining checks into it.
This brings the following benefits:
- Much simpler btrfs_read_extent_buffer()
Now it only needs to iterate through all mirrors.
- Simpler read-time transid check
Previously we go verify_parent_transid() after reading out the extent
buffer.
Now the transid check is done inside the endio function, no other
code can modify the content.
Thus no need to use the extent lock anymore.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 2f944a7..559e7f3 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -266,7 +266,6 @@ int btrfs_read_extent_buffer(struct extent_buffer *eb,
struct btrfs_tree_parent_check *check)
{
struct btrfs_fs_info *fs_info = eb->fs_info;
- struct extent_io_tree *io_tree;
int failed = 0;
int ret;
int num_copies = 0;
@@ -275,21 +274,11 @@ int btrfs_read_extent_buffer(struct extent_buffer *eb,
ASSERT(check);
- io_tree = &BTRFS_I(fs_info->btree_inode)->io_tree;
while (1) {
clear_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags);
- ret = read_extent_buffer_pages(eb, WAIT_COMPLETE, mirror_num);
- if (!ret) {
- if (verify_parent_transid(io_tree, eb, check->transid, 0))
- ret = -EIO;
- else if (btrfs_verify_level_key(eb, check->level,
- check->has_first_key ?
- &check->first_key : NULL,
- check->transid))
- ret = -EUCLEAN;
- else
- break;
- }
+ ret = read_extent_buffer_pages(eb, WAIT_COMPLETE, mirror_num, check);
+ if (!ret)
+ break;
num_copies = btrfs_num_copies(fs_info,
eb->start, eb->len);
@@ -465,7 +454,8 @@ static int check_tree_block_fsid(struct extent_buffer *eb)
}
/* Do basic extent buffer checks at read time */
-static int validate_extent_buffer(struct extent_buffer *eb)
+static int validate_extent_buffer(struct extent_buffer *eb,
+ struct btrfs_tree_parent_check *check)
{
struct btrfs_fs_info *fs_info = eb->fs_info;
u64 found_start;
@@ -475,6 +465,8 @@ static int validate_extent_buffer(struct extent_buffer *eb)
const u8 *header_csum;
int ret = 0;
+ ASSERT(check);
+
found_start = btrfs_header_bytenr(eb);
if (found_start != eb->start) {
btrfs_err_rl(fs_info,
@@ -513,6 +505,45 @@ static int validate_extent_buffer(struct extent_buffer *eb)
goto out;
}
+ if (found_level != check->level) {
+ ret = -EIO;
+ goto out;
+ }
+ if (unlikely(check->transid &&
+ btrfs_header_generation(eb) != check->transid)) {
+ btrfs_err_rl(eb->fs_info,
+"parent transid verify failed on logical %llu mirror %u wanted %llu found %llu",
+ eb->start, eb->read_mirror, check->transid,
+ btrfs_header_generation(eb));
+ ret = -EIO;
+ goto out;
+ }
+ if (check->has_first_key) {
+ struct btrfs_key *expect_key = &check->first_key;
+ struct btrfs_key found_key;
+
+ if (found_level)
+ btrfs_node_key_to_cpu(eb, &found_key, 0);
+ else
+ btrfs_item_key_to_cpu(eb, &found_key, 0);
+ if (unlikely(btrfs_comp_cpu_keys(expect_key, &found_key))) {
+ 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, check->transid,
+ expect_key->objectid,
+ expect_key->type, expect_key->offset,
+ found_key.objectid, found_key.type,
+ found_key.offset);
+ ret = -EUCLEAN;
+ goto out;
+ }
+ }
+ if (check->owner_root) {
+ ret = btrfs_check_eb_owner(eb, check->owner_root);
+ if (ret < 0)
+ goto out;
+ }
+
/*
* 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
@@ -537,13 +568,15 @@ static int validate_extent_buffer(struct extent_buffer *eb)
}
static int validate_subpage_buffer(struct page *page, u64 start, u64 end,
- int mirror)
+ int mirror, struct btrfs_tree_parent_check *check)
{
struct btrfs_fs_info *fs_info = btrfs_sb(page->mapping->host->i_sb);
struct extent_buffer *eb;
bool reads_done;
int ret = 0;
+ ASSERT(check);
+
/*
* We don't allow bio merge for subpage metadata read, so we should
* only get one eb for each endio hook.
@@ -567,7 +600,7 @@ static int validate_subpage_buffer(struct page *page, u64 start, u64 end,
ret = -EIO;
goto err;
}
- ret = validate_extent_buffer(eb);
+ ret = validate_extent_buffer(eb, check);
if (ret < 0)
goto err;
@@ -597,7 +630,8 @@ int btrfs_validate_metadata_buffer(struct btrfs_bio *bbio,
ASSERT(page->private);
if (btrfs_sb(page->mapping->host->i_sb)->nodesize < PAGE_SIZE)
- return validate_subpage_buffer(page, start, end, mirror);
+ return validate_subpage_buffer(page, start, end, mirror,
+ &bbio->parent_check);
eb = (struct extent_buffer *)page->private;
@@ -616,7 +650,7 @@ int btrfs_validate_metadata_buffer(struct btrfs_bio *bbio,
ret = -EIO;
goto err;
}
- ret = validate_extent_buffer(eb);
+ ret = validate_extent_buffer(eb, &bbio->parent_check);
err:
if (ret) {
/*
@@ -774,6 +808,7 @@ void btrfs_submit_metadata_bio(struct btrfs_inode *inode, struct bio *bio, int m
blk_status_t ret;
bio->bi_opf |= REQ_META;
+ bbio->is_metadata = 1;
if (btrfs_op(bio) != BTRFS_MAP_WRITE) {
btrfs_submit_bio(fs_info, bio, mirror_num);
