Commit 5b21f2ed authored by Zheng Yan's avatar Zheng Yan Committed by Chris Mason
Browse files

Btrfs: extent_map and data=ordered fixes for space balancing 



* Add an EXTENT_BOUNDARY state bit to keep the writepage code
from merging data extents that are in the process of being
relocated.  This allows us to do accounting for them properly.

* The balancing code relocates data extents indepdent of the underlying
inode.  The extent_map code was modified to properly account for
things moving around (invalidating extent_map caches in the inode).

* Don't take the drop_mutex in the create_subvol ioctl.  It isn't
required.

* Fix walking of the ordered extent list to avoid races with sys_unlink

* Change the lock ordering rules.  Transaction start goes outside
the drop_mutex.  This allows btrfs_commit_transaction to directly
drop the relocation trees.

Signed-off-by: default avatarChris Mason <chris.mason@oracle.com>
parent e4657689

fs/btrfs/ctree.c

+5 −4
Original line number Diff line number Diff line
@@ -290,7 +290,6 @@ int noinline btrfs_cow_block(struct btrfs_trans_handle *trans, 
		    struct extent_buffer **cow_ret, u64 prealloc_dest)

{

	u64 search_start;

	u64 header_trans;

	int ret;



	if (trans->transaction != root->fs_info->running_transaction) {
@@ -304,9 +303,9 @@ int noinline btrfs_cow_block(struct btrfs_trans_handle *trans, 
		WARN_ON(1);

	}



	header_trans = btrfs_header_generation(buf);

	spin_lock(&root->fs_info->hash_lock);

	if (header_trans == trans->transid &&

	if (btrfs_header_generation(buf) == trans->transid &&

	    btrfs_header_owner(buf) == root->root_key.objectid &&

	    !btrfs_header_flag(buf, BTRFS_HEADER_FLAG_WRITTEN)) {

		*cow_ret = buf;

		spin_unlock(&root->fs_info->hash_lock);
@@ -1300,6 +1299,7 @@ again: 
			/* is a cow on this block not required */

			spin_lock(&root->fs_info->hash_lock);

			if (btrfs_header_generation(b) == trans->transid &&

			    btrfs_header_owner(b) == root->root_key.objectid &&

			    !btrfs_header_flag(b, BTRFS_HEADER_FLAG_WRITTEN)) {

				spin_unlock(&root->fs_info->hash_lock);

				goto cow_done;
@@ -1396,7 +1396,8 @@ cow_done: 


			/* this is only true while dropping a snapshot */

			if (level == lowest_level) {

				break;

				ret = 0;

				goto done;

			}



			blocknr = btrfs_node_blockptr(b, slot);

fs/btrfs/ctree.h

+10 −1
Original line number Diff line number Diff line
@@ -1486,6 +1486,9 @@ static inline struct dentry *fdentry(struct file *file) 


/* extent-tree.c */

int btrfs_lookup_extent(struct btrfs_root *root, u64 start, u64 len);

int btrfs_lookup_extent_ref(struct btrfs_trans_handle *trans,

			    struct btrfs_root *root, u64 bytenr,

			    u64 num_bytes, u32 *refs);

int btrfs_update_pinned_extents(struct btrfs_root *root,

				u64 bytenr, u64 num, int pin);

int btrfs_drop_leaf_ref(struct btrfs_trans_handle *trans,
@@ -1812,6 +1815,8 @@ void btrfs_destroy_inode(struct inode *inode); 
int btrfs_init_cachep(void);

void btrfs_destroy_cachep(void);

long btrfs_ioctl_trans_end(struct file *file);

struct inode *btrfs_ilookup(struct super_block *s, u64 objectid,

			    struct btrfs_root *root, int wait);

struct inode *btrfs_iget_locked(struct super_block *s, u64 objectid,

				struct btrfs_root *root);

struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location,
@@ -1824,13 +1829,17 @@ struct extent_map *btrfs_get_extent(struct inode *inode, struct page *page, 
int btrfs_update_inode(struct btrfs_trans_handle *trans,

			      struct btrfs_root *root,

			      struct inode *inode);

int btrfs_orphan_add(struct btrfs_trans_handle *trans, struct inode *inode);

int btrfs_orphan_del(struct btrfs_trans_handle *trans, struct inode *inode);

void btrfs_orphan_cleanup(struct btrfs_root *root);



/* ioctl.c */

long btrfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg);



/* file.c */

int btrfs_sync_file(struct file *file, struct dentry *dentry, int datasync);

int btrfs_drop_extent_cache(struct inode *inode, u64 start, u64 end);

int btrfs_drop_extent_cache(struct inode *inode, u64 start, u64 end,

			    int skip_pinned);

int btrfs_check_file(struct btrfs_root *root, struct inode *inode);

extern struct file_operations btrfs_file_operations;

int btrfs_drop_extents(struct btrfs_trans_handle *trans,

fs/btrfs/extent_io.c

+9 −4
Original line number Diff line number Diff line
@@ -292,7 +292,7 @@ static int merge_state(struct extent_io_tree *tree, 
	struct extent_state *other;

	struct rb_node *other_node;



	if (state->state & EXTENT_IOBITS)

	if (state->state & (EXTENT_IOBITS | EXTENT_BOUNDARY))

		return 0;



	other_node = rb_prev(&state->rb_node);
@@ -1070,7 +1070,8 @@ search_again: 


	while(1) {

		state = rb_entry(node, struct extent_state, rb_node);

		if (found && state->start != cur_start) {

		if (found && (state->start != cur_start ||

			      (state->state & EXTENT_BOUNDARY))) {

			goto out;

		}

		if (!(state->state & EXTENT_DELALLOC)) {
@@ -1078,7 +1079,7 @@ search_again: 
				*end = state->end;

			goto out;

		}

		if (!found) {

		if (!found && !(state->state & EXTENT_BOUNDARY)) {

			struct extent_state *prev_state;

			struct rb_node *prev_node = node;

			while(1) {
@@ -1088,7 +1089,11 @@ search_again: 
				prev_state = rb_entry(prev_node,

						      struct extent_state,

						      rb_node);

				if (!(prev_state->state & EXTENT_DELALLOC))

				if ((prev_state->end + 1 != state->start) ||

				    !(prev_state->state & EXTENT_DELALLOC))

					break;

				if ((cur_start - prev_state->start) * 2 >

				     max_bytes)

					break;

				state = prev_state;

				node = prev_node;

fs/btrfs/extent_io.h

+1 −0
Original line number Diff line number Diff line
@@ -15,6 +15,7 @@ 
#define EXTENT_BUFFER_FILLED (1 << 8)

#define EXTENT_ORDERED (1 << 9)

#define EXTENT_ORDERED_METADATA (1 << 10)

#define EXTENT_BOUNDARY (1 << 11)

#define EXTENT_IOBITS (EXTENT_LOCKED | EXTENT_WRITEBACK)



/*

fs/btrfs/file.c

+25 −6
Original line number Diff line number Diff line
@@ -294,7 +294,7 @@ static int noinline dirty_and_release_pages(struct btrfs_trans_handle *trans, 
						       last_pos_in_file,

						       0, 0, hole_size, 0);

			btrfs_drop_extent_cache(inode, last_pos_in_file,

					last_pos_in_file + hole_size -1);

					last_pos_in_file + hole_size - 1, 0);

			mutex_unlock(&BTRFS_I(inode)->extent_mutex);

			btrfs_check_file(root, inode);

		}
@@ -337,7 +337,7 @@ static int noinline dirty_and_release_pages(struct btrfs_trans_handle *trans, 
		inline_size -= start_pos;

		err = insert_inline_extent(trans, root, inode, start_pos,

					   inline_size, pages, 0, num_pages);

		btrfs_drop_extent_cache(inode, start_pos, aligned_end - 1);

		btrfs_drop_extent_cache(inode, start_pos, aligned_end - 1, 0);

		BUG_ON(err);

		mutex_unlock(&BTRFS_I(inode)->extent_mutex);
@@ -362,7 +362,8 @@ out_unlock: 
	return err;

}



int noinline btrfs_drop_extent_cache(struct inode *inode, u64 start, u64 end)

int btrfs_drop_extent_cache(struct inode *inode, u64 start, u64 end,

			    int skip_pinned)

{

	struct extent_map *em;

	struct extent_map *split = NULL;
@@ -371,6 +372,7 @@ int noinline btrfs_drop_extent_cache(struct inode *inode, u64 start, u64 end) 
	u64 len = end - start + 1;

	int ret;

	int testend = 1;

	unsigned long flags;



	WARN_ON(end < start);

	if (end == (u64)-1) {
@@ -389,6 +391,23 @@ int noinline btrfs_drop_extent_cache(struct inode *inode, u64 start, u64 end) 
			spin_unlock(&em_tree->lock);

			break;

		}

		flags = em->flags;

		if (skip_pinned && test_bit(EXTENT_FLAG_PINNED, &em->flags)) {

			spin_unlock(&em_tree->lock);

			if (em->start <= start &&

			    (!testend || em->start + em->len >= start + len)) {

				free_extent_map(em);

				break;

			}

			if (start < em->start) {

				len = em->start - start;

			} else {

				len = start + len - (em->start + em->len);

				start = em->start + em->len;

			}

			free_extent_map(em);

			continue;

		}

		clear_bit(EXTENT_FLAG_PINNED, &em->flags);

		remove_extent_mapping(em_tree, em);
@@ -398,7 +417,7 @@ int noinline btrfs_drop_extent_cache(struct inode *inode, u64 start, u64 end) 
			split->len = start - em->start;

			split->block_start = em->block_start;

			split->bdev = em->bdev;

			split->flags = em->flags;

			split->flags = flags;

			ret = add_extent_mapping(em_tree, split);

			BUG_ON(ret);

			free_extent_map(split);
@@ -412,7 +431,7 @@ int noinline btrfs_drop_extent_cache(struct inode *inode, u64 start, u64 end) 
			split->start = start + len;

			split->len = em->start + em->len - (start + len);

			split->bdev = em->bdev;

			split->flags = em->flags;

			split->flags = flags;



			split->block_start = em->block_start + diff;
@@ -541,7 +560,7 @@ int noinline btrfs_drop_extents(struct btrfs_trans_handle *trans, 
	int recow;

	int ret;



	btrfs_drop_extent_cache(inode, start, end - 1);

	btrfs_drop_extent_cache(inode, start, end - 1, 0);



	path = btrfs_alloc_path();

	if (!path)

CRA Git | Maintained and supported by SUSTech CRA and CCSE