* in the wrong place.
*/
static int verify_parent_transid(struct extent_io_tree *io_tree,
- struct extent_buffer *eb, u64 parent_transid)
+ struct extent_buffer *eb, u64 parent_transid,
+ int atomic)
{
struct extent_state *cached_state = NULL;
int ret;
if (!parent_transid || btrfs_header_generation(eb) == parent_transid)
return 0;
+ if (atomic)
+ return -EAGAIN;
+
lock_extent_bits(io_tree, eb->start, eb->start + eb->len - 1,
0, &cached_state);
if (extent_buffer_uptodate(eb) &&
ret = read_extent_buffer_pages(io_tree, eb, start,
WAIT_COMPLETE,
btree_get_extent, mirror_num);
- if (!ret && !verify_parent_transid(io_tree, eb, parent_transid))
+ if (!ret && !verify_parent_transid(io_tree, eb,
+ parent_transid, 0))
break;
/*
if (test_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags))
break;
- if (!failed_mirror) {
- failed = 1;
- printk(KERN_ERR "failed mirror was %d\n", eb->failed_mirror);
- failed_mirror = eb->failed_mirror;
- }
-
num_copies = btrfs_num_copies(&root->fs_info->mapping_tree,
eb->start, eb->len);
if (num_copies == 1)
break;
+ if (!failed_mirror) {
+ failed = 1;
+ failed_mirror = eb->read_mirror;
+ }
+
mirror_num++;
if (mirror_num == failed_mirror)
mirror_num++;
}
static int btree_readpage_end_io_hook(struct page *page, u64 start, u64 end,
- struct extent_state *state)
+ struct extent_state *state, int mirror)
{
struct extent_io_tree *tree;
u64 found_start;
if (!reads_done)
goto err;
+ eb->read_mirror = mirror;
if (test_bit(EXTENT_BUFFER_IOERR, &eb->bflags)) {
ret = -EIO;
goto err;
eb = (struct extent_buffer *)page->private;
set_bit(EXTENT_BUFFER_IOERR, &eb->bflags);
- eb->failed_mirror = failed_mirror;
+ eb->read_mirror = failed_mirror;
if (test_and_clear_bit(EXTENT_BUFFER_READAHEAD, &eb->bflags))
btree_readahead_hook(root, eb, eb->start, -EIO);
return -EIO; /* we fixed nothing */
root->orphan_block_rsv = NULL;
INIT_LIST_HEAD(&root->dirty_list);
- INIT_LIST_HEAD(&root->orphan_list);
INIT_LIST_HEAD(&root->root_list);
spin_lock_init(&root->orphan_lock);
spin_lock_init(&root->inode_lock);
atomic_set(&root->log_commit[0], 0);
atomic_set(&root->log_commit[1], 0);
atomic_set(&root->log_writers, 0);
+ atomic_set(&root->orphan_inodes, 0);
root->log_batch = 0;
root->log_transid = 0;
root->last_log_commit = 0;
root->commit_root = NULL;
root->node = read_tree_block(root, btrfs_root_bytenr(&root->root_item),
blocksize, generation);
- if (!root->node || !btrfs_buffer_uptodate(root->node, generation)) {
+ if (!root->node || !btrfs_buffer_uptodate(root->node, generation, 0)) {
free_extent_buffer(root->node);
root->node = NULL;
return -EIO;
leaf = btrfs_alloc_free_block(trans, root, root->leafsize, 0,
BTRFS_TREE_LOG_OBJECTID, NULL,
- 0, 0, 0, 0);
+ 0, 0, 0);
if (IS_ERR(leaf)) {
kfree(root);
return ERR_CAST(leaf);
spin_lock_init(&fs_info->delayed_iput_lock);
spin_lock_init(&fs_info->defrag_inodes_lock);
spin_lock_init(&fs_info->free_chunk_lock);
+ spin_lock_init(&fs_info->tree_mod_seq_lock);
+ rwlock_init(&fs_info->tree_mod_log_lock);
mutex_init(&fs_info->reloc_mutex);
init_completion(&fs_info->kobj_unregister);
INIT_LIST_HEAD(&fs_info->dirty_cowonly_roots);
INIT_LIST_HEAD(&fs_info->space_info);
+ INIT_LIST_HEAD(&fs_info->tree_mod_seq_list);
btrfs_mapping_init(&fs_info->mapping_tree);
btrfs_init_block_rsv(&fs_info->global_block_rsv);
btrfs_init_block_rsv(&fs_info->delalloc_block_rsv);
atomic_set(&fs_info->async_submit_draining, 0);
atomic_set(&fs_info->nr_async_bios, 0);
atomic_set(&fs_info->defrag_running, 0);
+ atomic_set(&fs_info->tree_mod_seq, 0);
fs_info->sb = sb;
fs_info->max_inline = 8192 * 1024;
fs_info->metadata_ratio = 0;
fs_info->defrag_inodes = RB_ROOT;
fs_info->trans_no_join = 0;
fs_info->free_chunk_space = 0;
+ fs_info->tree_mod_log = RB_ROOT;
/* readahead state */
INIT_RADIX_TREE(&fs_info->reada_tree, GFP_NOFS & ~__GFP_WAIT);
BTRFS_I(fs_info->btree_inode)->root = tree_root;
memset(&BTRFS_I(fs_info->btree_inode)->location, 0,
sizeof(struct btrfs_key));
- BTRFS_I(fs_info->btree_inode)->dummy_inode = 1;
+ set_bit(BTRFS_INODE_DUMMY,
+ &BTRFS_I(fs_info->btree_inode)->runtime_flags);
insert_inode_hash(fs_info->btree_inode);
spin_lock_init(&fs_info->block_group_cache_lock);
goto fail_sb_buffer;
}
- if (sectorsize < PAGE_SIZE) {
- printk(KERN_WARNING "btrfs: Incompatible sector size "
- "found on %s\n", sb->s_id);
+ if (sectorsize != PAGE_SIZE) {
+ printk(KERN_WARNING "btrfs: Incompatible sector size(%lu) "
+ "found on %s\n", (unsigned long)sectorsize, sb->s_id);
goto fail_sb_buffer;
}
fs_info->generation = generation;
fs_info->last_trans_committed = generation;
+ ret = btrfs_init_dev_stats(fs_info);
+ if (ret) {
+ printk(KERN_ERR "btrfs: failed to init dev_stats: %d\n",
+ ret);
+ goto fail_block_groups;
+ }
+
ret = btrfs_init_space_info(fs_info);
if (ret) {
printk(KERN_ERR "Failed to initial space info: %d\n", ret);
static void btrfs_end_buffer_write_sync(struct buffer_head *bh, int uptodate)
{
- char b[BDEVNAME_SIZE];
-
if (uptodate) {
set_buffer_uptodate(bh);
} else {
+ struct btrfs_device *device = (struct btrfs_device *)
+ bh->b_private;
+
printk_ratelimited(KERN_WARNING "lost page write due to "
- "I/O error on %s\n",
- bdevname(bh->b_bdev, b));
+ "I/O error on %s\n", device->name);
/* note, we dont' set_buffer_write_io_error because we have
* our own ways of dealing with the IO errors
*/
clear_buffer_uptodate(bh);
+ btrfs_dev_stat_inc_and_print(device, BTRFS_DEV_STAT_WRITE_ERRS);
}
unlock_buffer(bh);
put_bh(bh);
set_buffer_uptodate(bh);
lock_buffer(bh);
bh->b_end_io = btrfs_end_buffer_write_sync;
+ bh->b_private = device;
}
/*
}
if (!bio_flagged(bio, BIO_UPTODATE)) {
ret = -EIO;
+ if (!bio_flagged(bio, BIO_EOPNOTSUPP))
+ btrfs_dev_stat_inc_and_print(device,
+ BTRFS_DEV_STAT_FLUSH_ERRS);
}
/* drop the reference from the wait == 0 run */
return ret;
}
-/* Kill all outstanding I/O */
-void btrfs_abort_devices(struct btrfs_root *root)
-{
- struct list_head *head;
- struct btrfs_device *dev;
- mutex_lock(&root->fs_info->fs_devices->device_list_mutex);
- head = &root->fs_info->fs_devices->devices;
- list_for_each_entry_rcu(dev, head, dev_list) {
- blk_abort_queue(dev->bdev->bd_disk->queue);
- }
- mutex_unlock(&root->fs_info->fs_devices->device_list_mutex);
-}
-
void btrfs_free_fs_root(struct btrfs_fs_info *fs_info, struct btrfs_root *root)
{
spin_lock(&fs_info->fs_roots_radix_lock);
return 0;
}
-int btrfs_buffer_uptodate(struct extent_buffer *buf, u64 parent_transid)
+int btrfs_buffer_uptodate(struct extent_buffer *buf, u64 parent_transid,
+ int atomic)
{
int ret;
struct inode *btree_inode = buf->pages[0]->mapping->host;
return ret;
ret = verify_parent_transid(&BTRFS_I(btree_inode)->io_tree, buf,
- parent_transid);
+ parent_transid, atomic);
+ if (ret == -EAGAIN)
+ return ret;
return !ret;
}
delayed_refs = &trans->delayed_refs;
-again:
spin_lock(&delayed_refs->lock);
if (delayed_refs->num_entries == 0) {
spin_unlock(&delayed_refs->lock);
return ret;
}
- node = rb_first(&delayed_refs->root);
- while (node) {
+ while ((node = rb_first(&delayed_refs->root)) != NULL) {
ref = rb_entry(node, struct btrfs_delayed_ref_node, rb_node);
- node = rb_next(node);
-
- ref->in_tree = 0;
- rb_erase(&ref->rb_node, &delayed_refs->root);
- delayed_refs->num_entries--;
atomic_set(&ref->refs, 1);
if (btrfs_delayed_ref_is_head(ref)) {
struct btrfs_delayed_ref_head *head;
head = btrfs_delayed_node_to_head(ref);
- spin_unlock(&delayed_refs->lock);
- mutex_lock(&head->mutex);
+ if (!mutex_trylock(&head->mutex)) {
+ atomic_inc(&ref->refs);
+ spin_unlock(&delayed_refs->lock);
+
+ /* Need to wait for the delayed ref to run */
+ mutex_lock(&head->mutex);
+ mutex_unlock(&head->mutex);
+ btrfs_put_delayed_ref(ref);
+
+ continue;
+ }
+
kfree(head->extent_op);
delayed_refs->num_heads--;
if (list_empty(&head->cluster))
delayed_refs->num_heads_ready--;
list_del_init(&head->cluster);
- mutex_unlock(&head->mutex);
- btrfs_put_delayed_ref(ref);
- goto again;
}
+ ref->in_tree = 0;
+ rb_erase(&ref->rb_node, &delayed_refs->root);
+ delayed_refs->num_entries--;
+
spin_unlock(&delayed_refs->lock);
btrfs_put_delayed_ref(ref);
/* FIXME: cleanup wait for commit */
cur_trans->in_commit = 1;
cur_trans->blocked = 1;
- if (waitqueue_active(&root->fs_info->transaction_blocked_wait))
- wake_up(&root->fs_info->transaction_blocked_wait);
+ wake_up(&root->fs_info->transaction_blocked_wait);
cur_trans->blocked = 0;
- if (waitqueue_active(&root->fs_info->transaction_wait))
- wake_up(&root->fs_info->transaction_wait);
+ wake_up(&root->fs_info->transaction_wait);
cur_trans->commit_done = 1;
- if (waitqueue_active(&cur_trans->commit_wait))
- wake_up(&cur_trans->commit_wait);
+ wake_up(&cur_trans->commit_wait);
btrfs_destroy_pending_snapshots(cur_trans);
return 0;
}
-static int btree_writepage_io_failed_hook(struct bio *bio, struct page *page,
- u64 start, u64 end,
- struct extent_state *state)
-{
- struct super_block *sb = page->mapping->host->i_sb;
- struct btrfs_fs_info *fs_info = btrfs_sb(sb);
- btrfs_error(fs_info, -EIO,
- "Error occured while writing out btree at %llu", start);
- return -EIO;
-}
-
static struct extent_io_ops btree_extent_io_ops = {
.write_cache_pages_lock_hook = btree_lock_page_hook,
.readpage_end_io_hook = btree_readpage_end_io_hook,
.submit_bio_hook = btree_submit_bio_hook,
/* note we're sharing with inode.c for the merge bio hook */
.merge_bio_hook = btrfs_merge_bio_hook,
- .writepage_io_failed_hook = btree_writepage_io_failed_hook,
};