mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-11-01 17:08:10 +00:00
95a06077f7
The sequence number for delayed refs is needed to postpone certain delayed refs for a very short period while walking backrefs. Before the tree modification log, we thought we'd only have to hold back those references that don't have a counter operation. While now we've the tree mod log, we're rewinding fs tree blocks to a defined consistent state. We cannot know in advance for which tree block we'll be doing rewind operations later. Therefore, we must postpone all the delayed refs for fs-tree blocks, even those having a counter operation. Signed-off-by: Jan Schmidt <list.btrfs@jan-o-sch.net>
259 lines
7.6 KiB
C
259 lines
7.6 KiB
C
/*
|
|
* Copyright (C) 2008 Oracle. All rights reserved.
|
|
*
|
|
* This program is free software; you can redistribute it and/or
|
|
* modify it under the terms of the GNU General Public
|
|
* License v2 as published by the Free Software Foundation.
|
|
*
|
|
* This program is distributed in the hope that it will be useful,
|
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
|
* General Public License for more details.
|
|
*
|
|
* You should have received a copy of the GNU General Public
|
|
* License along with this program; if not, write to the
|
|
* Free Software Foundation, Inc., 59 Temple Place - Suite 330,
|
|
* Boston, MA 021110-1307, USA.
|
|
*/
|
|
#ifndef __DELAYED_REF__
|
|
#define __DELAYED_REF__
|
|
|
|
/* these are the possible values of struct btrfs_delayed_ref->action */
|
|
#define BTRFS_ADD_DELAYED_REF 1 /* add one backref to the tree */
|
|
#define BTRFS_DROP_DELAYED_REF 2 /* delete one backref from the tree */
|
|
#define BTRFS_ADD_DELAYED_EXTENT 3 /* record a full extent allocation */
|
|
#define BTRFS_UPDATE_DELAYED_HEAD 4 /* not changing ref count on head ref */
|
|
|
|
struct btrfs_delayed_ref_node {
|
|
struct rb_node rb_node;
|
|
|
|
/* the starting bytenr of the extent */
|
|
u64 bytenr;
|
|
|
|
/* the size of the extent */
|
|
u64 num_bytes;
|
|
|
|
/* seq number to keep track of insertion order */
|
|
u64 seq;
|
|
|
|
/* ref count on this data structure */
|
|
atomic_t refs;
|
|
|
|
/*
|
|
* how many refs is this entry adding or deleting. For
|
|
* head refs, this may be a negative number because it is keeping
|
|
* track of the total mods done to the reference count.
|
|
* For individual refs, this will always be a positive number
|
|
*
|
|
* It may be more than one, since it is possible for a single
|
|
* parent to have more than one ref on an extent
|
|
*/
|
|
int ref_mod;
|
|
|
|
unsigned int action:8;
|
|
unsigned int type:8;
|
|
/* is this node still in the rbtree? */
|
|
unsigned int is_head:1;
|
|
unsigned int in_tree:1;
|
|
};
|
|
|
|
struct btrfs_delayed_extent_op {
|
|
struct btrfs_disk_key key;
|
|
u64 flags_to_set;
|
|
unsigned int update_key:1;
|
|
unsigned int update_flags:1;
|
|
unsigned int is_data:1;
|
|
};
|
|
|
|
/*
|
|
* the head refs are used to hold a lock on a given extent, which allows us
|
|
* to make sure that only one process is running the delayed refs
|
|
* at a time for a single extent. They also store the sum of all the
|
|
* reference count modifications we've queued up.
|
|
*/
|
|
struct btrfs_delayed_ref_head {
|
|
struct btrfs_delayed_ref_node node;
|
|
|
|
/*
|
|
* the mutex is held while running the refs, and it is also
|
|
* held when checking the sum of reference modifications.
|
|
*/
|
|
struct mutex mutex;
|
|
|
|
struct list_head cluster;
|
|
|
|
struct btrfs_delayed_extent_op *extent_op;
|
|
/*
|
|
* when a new extent is allocated, it is just reserved in memory
|
|
* The actual extent isn't inserted into the extent allocation tree
|
|
* until the delayed ref is processed. must_insert_reserved is
|
|
* used to flag a delayed ref so the accounting can be updated
|
|
* when a full insert is done.
|
|
*
|
|
* It is possible the extent will be freed before it is ever
|
|
* inserted into the extent allocation tree. In this case
|
|
* we need to update the in ram accounting to properly reflect
|
|
* the free has happened.
|
|
*/
|
|
unsigned int must_insert_reserved:1;
|
|
unsigned int is_data:1;
|
|
};
|
|
|
|
struct btrfs_delayed_tree_ref {
|
|
struct btrfs_delayed_ref_node node;
|
|
u64 root;
|
|
u64 parent;
|
|
int level;
|
|
};
|
|
|
|
struct btrfs_delayed_data_ref {
|
|
struct btrfs_delayed_ref_node node;
|
|
u64 root;
|
|
u64 parent;
|
|
u64 objectid;
|
|
u64 offset;
|
|
};
|
|
|
|
struct btrfs_delayed_ref_root {
|
|
struct rb_root root;
|
|
|
|
/* this spin lock protects the rbtree and the entries inside */
|
|
spinlock_t lock;
|
|
|
|
/* how many delayed ref updates we've queued, used by the
|
|
* throttling code
|
|
*/
|
|
unsigned long num_entries;
|
|
|
|
/* total number of head nodes in tree */
|
|
unsigned long num_heads;
|
|
|
|
/* total number of head nodes ready for processing */
|
|
unsigned long num_heads_ready;
|
|
|
|
/*
|
|
* set when the tree is flushing before a transaction commit,
|
|
* used by the throttling code to decide if new updates need
|
|
* to be run right away
|
|
*/
|
|
int flushing;
|
|
|
|
u64 run_delayed_start;
|
|
|
|
/*
|
|
* seq number of delayed refs. We need to know if a backref was being
|
|
* added before the currently processed ref or afterwards.
|
|
*/
|
|
u64 seq;
|
|
|
|
/*
|
|
* seq_list holds a list of all seq numbers that are currently being
|
|
* added to the list. While walking backrefs (btrfs_find_all_roots,
|
|
* qgroups), which might take some time, no newer ref must be processed,
|
|
* as it might influence the outcome of the walk.
|
|
*/
|
|
struct list_head seq_head;
|
|
|
|
/*
|
|
* when the only refs we have in the list must not be processed, we want
|
|
* to wait for more refs to show up or for the end of backref walking.
|
|
*/
|
|
wait_queue_head_t seq_wait;
|
|
};
|
|
|
|
static inline void btrfs_put_delayed_ref(struct btrfs_delayed_ref_node *ref)
|
|
{
|
|
WARN_ON(atomic_read(&ref->refs) == 0);
|
|
if (atomic_dec_and_test(&ref->refs)) {
|
|
WARN_ON(ref->in_tree);
|
|
kfree(ref);
|
|
}
|
|
}
|
|
|
|
int btrfs_add_delayed_tree_ref(struct btrfs_fs_info *fs_info,
|
|
struct btrfs_trans_handle *trans,
|
|
u64 bytenr, u64 num_bytes, u64 parent,
|
|
u64 ref_root, int level, int action,
|
|
struct btrfs_delayed_extent_op *extent_op,
|
|
int for_cow);
|
|
int btrfs_add_delayed_data_ref(struct btrfs_fs_info *fs_info,
|
|
struct btrfs_trans_handle *trans,
|
|
u64 bytenr, u64 num_bytes,
|
|
u64 parent, u64 ref_root,
|
|
u64 owner, u64 offset, int action,
|
|
struct btrfs_delayed_extent_op *extent_op,
|
|
int for_cow);
|
|
int btrfs_add_delayed_extent_op(struct btrfs_fs_info *fs_info,
|
|
struct btrfs_trans_handle *trans,
|
|
u64 bytenr, u64 num_bytes,
|
|
struct btrfs_delayed_extent_op *extent_op);
|
|
|
|
struct btrfs_delayed_ref_head *
|
|
btrfs_find_delayed_ref_head(struct btrfs_trans_handle *trans, u64 bytenr);
|
|
int btrfs_delayed_ref_lock(struct btrfs_trans_handle *trans,
|
|
struct btrfs_delayed_ref_head *head);
|
|
int btrfs_find_ref_cluster(struct btrfs_trans_handle *trans,
|
|
struct list_head *cluster, u64 search_start);
|
|
|
|
static inline u64 inc_delayed_seq(struct btrfs_delayed_ref_root *delayed_refs)
|
|
{
|
|
assert_spin_locked(&delayed_refs->lock);
|
|
++delayed_refs->seq;
|
|
return delayed_refs->seq;
|
|
}
|
|
|
|
static inline void
|
|
btrfs_get_delayed_seq(struct btrfs_delayed_ref_root *delayed_refs,
|
|
struct seq_list *elem)
|
|
{
|
|
assert_spin_locked(&delayed_refs->lock);
|
|
elem->seq = delayed_refs->seq;
|
|
list_add_tail(&elem->list, &delayed_refs->seq_head);
|
|
}
|
|
|
|
static inline void
|
|
btrfs_put_delayed_seq(struct btrfs_delayed_ref_root *delayed_refs,
|
|
struct seq_list *elem)
|
|
{
|
|
spin_lock(&delayed_refs->lock);
|
|
list_del(&elem->list);
|
|
wake_up(&delayed_refs->seq_wait);
|
|
spin_unlock(&delayed_refs->lock);
|
|
}
|
|
|
|
int btrfs_check_delayed_seq(struct btrfs_delayed_ref_root *delayed_refs,
|
|
u64 seq);
|
|
|
|
/*
|
|
* a node might live in a head or a regular ref, this lets you
|
|
* test for the proper type to use.
|
|
*/
|
|
static int btrfs_delayed_ref_is_head(struct btrfs_delayed_ref_node *node)
|
|
{
|
|
return node->is_head;
|
|
}
|
|
|
|
/*
|
|
* helper functions to cast a node into its container
|
|
*/
|
|
static inline struct btrfs_delayed_tree_ref *
|
|
btrfs_delayed_node_to_tree_ref(struct btrfs_delayed_ref_node *node)
|
|
{
|
|
WARN_ON(btrfs_delayed_ref_is_head(node));
|
|
return container_of(node, struct btrfs_delayed_tree_ref, node);
|
|
}
|
|
|
|
static inline struct btrfs_delayed_data_ref *
|
|
btrfs_delayed_node_to_data_ref(struct btrfs_delayed_ref_node *node)
|
|
{
|
|
WARN_ON(btrfs_delayed_ref_is_head(node));
|
|
return container_of(node, struct btrfs_delayed_data_ref, node);
|
|
}
|
|
|
|
static inline struct btrfs_delayed_ref_head *
|
|
btrfs_delayed_node_to_head(struct btrfs_delayed_ref_node *node)
|
|
{
|
|
WARN_ON(!btrfs_delayed_ref_is_head(node));
|
|
return container_of(node, struct btrfs_delayed_ref_head, node);
|
|
}
|
|
#endif
|