linux-stable/fs/btrfs/delayed-ref.c
Filipe Manana 2c3cf7d5f6 Btrfs: fix regression when running delayed references
In the kernel 4.2 merge window we had a refactoring/rework of the delayed
references implementation in order to fix certain problems with qgroups.
However that rework introduced one more regression that leads to the
following trace when running delayed references for metadata:

[35908.064664] kernel BUG at fs/btrfs/extent-tree.c:1832!
[35908.065201] invalid opcode: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC
[35908.065201] Modules linked in: dm_flakey dm_mod btrfs crc32c_generic xor raid6_pq nfsd auth_rpcgss oid_registry nfs_acl nfs lockd grace fscache sunrpc loop fuse parport_pc psmouse i2
[35908.065201] CPU: 14 PID: 15014 Comm: kworker/u32:9 Tainted: G        W       4.3.0-rc5-btrfs-next-17+ #1
[35908.065201] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.8.1-0-g4adadbd-20150316_085822-nilsson.home.kraxel.org 04/01/2014
[35908.065201] Workqueue: btrfs-extent-refs btrfs_extent_refs_helper [btrfs]
[35908.065201] task: ffff880114b7d780 ti: ffff88010c4c8000 task.ti: ffff88010c4c8000
[35908.065201] RIP: 0010:[<ffffffffa04928b5>]  [<ffffffffa04928b5>] insert_inline_extent_backref+0x52/0xb1 [btrfs]
[35908.065201] RSP: 0018:ffff88010c4cbb08  EFLAGS: 00010293
[35908.065201] RAX: 0000000000000000 RBX: ffff88008a661000 RCX: 0000000000000000
[35908.065201] RDX: ffffffffa04dd58f RSI: 0000000000000001 RDI: 0000000000000000
[35908.065201] RBP: ffff88010c4cbb40 R08: 0000000000001000 R09: ffff88010c4cb9f8
[35908.065201] R10: 0000000000000000 R11: 000000000000002c R12: 0000000000000000
[35908.065201] R13: ffff88020a74c578 R14: 0000000000000000 R15: 0000000000000000
[35908.065201] FS:  0000000000000000(0000) GS:ffff88023edc0000(0000) knlGS:0000000000000000
[35908.065201] CS:  0010 DS: 0000 ES: 0000 CR0: 000000008005003b
[35908.065201] CR2: 00000000015e8708 CR3: 0000000102185000 CR4: 00000000000006e0
[35908.065201] Stack:
[35908.065201]  ffff88010c4cbb18 0000000000000f37 ffff88020a74c578 ffff88015a408000
[35908.065201]  ffff880154a44000 0000000000000000 0000000000000005 ffff88010c4cbbd8
[35908.065201]  ffffffffa0492b9a 0000000000000005 0000000000000000 0000000000000000
[35908.065201] Call Trace:
[35908.065201]  [<ffffffffa0492b9a>] __btrfs_inc_extent_ref+0x8b/0x208 [btrfs]
[35908.065201]  [<ffffffffa0497117>] ? __btrfs_run_delayed_refs+0x4d4/0xd33 [btrfs]
[35908.065201]  [<ffffffffa049773d>] __btrfs_run_delayed_refs+0xafa/0xd33 [btrfs]
[35908.065201]  [<ffffffffa04a976a>] ? join_transaction.isra.10+0x25/0x41f [btrfs]
[35908.065201]  [<ffffffffa04a97ed>] ? join_transaction.isra.10+0xa8/0x41f [btrfs]
[35908.065201]  [<ffffffffa049914d>] btrfs_run_delayed_refs+0x75/0x1dd [btrfs]
[35908.065201]  [<ffffffffa04992f1>] delayed_ref_async_start+0x3c/0x7b [btrfs]
[35908.065201]  [<ffffffffa04d4b4f>] normal_work_helper+0x14c/0x32a [btrfs]
[35908.065201]  [<ffffffffa04d4e93>] btrfs_extent_refs_helper+0x12/0x14 [btrfs]
[35908.065201]  [<ffffffff81063b23>] process_one_work+0x24a/0x4ac
[35908.065201]  [<ffffffff81064285>] worker_thread+0x206/0x2c2
[35908.065201]  [<ffffffff8106407f>] ? rescuer_thread+0x2cb/0x2cb
[35908.065201]  [<ffffffff8106407f>] ? rescuer_thread+0x2cb/0x2cb
[35908.065201]  [<ffffffff8106904d>] kthread+0xef/0xf7
[35908.065201]  [<ffffffff81068f5e>] ? kthread_parkme+0x24/0x24
[35908.065201]  [<ffffffff8147d10f>] ret_from_fork+0x3f/0x70
[35908.065201]  [<ffffffff81068f5e>] ? kthread_parkme+0x24/0x24
[35908.065201] Code: 6a 01 41 56 41 54 ff 75 10 41 51 4d 89 c1 49 89 c8 48 8d 4d d0 e8 f6 f1 ff ff 48 83 c4 28 85 c0 75 2c 49 81 fc ff 00 00 00 77 02 <0f> 0b 4c 8b 45 30 8b 4d 28 45 31
[35908.065201] RIP  [<ffffffffa04928b5>] insert_inline_extent_backref+0x52/0xb1 [btrfs]
[35908.065201]  RSP <ffff88010c4cbb08>
[35908.310885] ---[ end trace fe4299baf0666457 ]---

This happens because the new delayed references code no longer merges
delayed references that have different sequence values. The following
steps are an example sequence leading to this issue:

1) Transaction N starts, fs_info->tree_mod_seq has value 0;

2) Extent buffer (btree node) A is allocated, delayed reference Ref1 for
   bytenr A is created, with a value of 1 and a seq value of 0;

3) fs_info->tree_mod_seq is incremented to 1;

4) Extent buffer A is deleted through btrfs_del_items(), which calls
   btrfs_del_leaf(), which in turn calls btrfs_free_tree_block(). The
   later returns the metadata extent associated to extent buffer A to
   the free space cache (the range is not pinned), because the extent
   buffer was created in the current transaction (N) and writeback never
   happened for the extent buffer (flag BTRFS_HEADER_FLAG_WRITTEN not set
   in the extent buffer).
   This creates the delayed reference Ref2 for bytenr A, with a value
   of -1 and a seq value of 1;

5) Delayed reference Ref2 is not merged with Ref1 when we create it,
   because they have different sequence numbers (decided at
   add_delayed_ref_tail_merge());

6) fs_info->tree_mod_seq is incremented to 2;

7) Some task attempts to allocate a new extent buffer (done at
   extent-tree.c:find_free_extent()), but due to heavy fragmentation
   and running low on metadata space the clustered allocation fails
   and we fall back to unclustered allocation, which finds the
   extent at offset A, so a new extent buffer at offset A is allocated.
   This creates delayed reference Ref3 for bytenr A, with a value of 1
   and a seq value of 2;

8) Ref3 is not merged neither with Ref2 nor Ref1, again because they
   all have different seq values;

9) We start running the delayed references (__btrfs_run_delayed_refs());

10) The delayed Ref1 is the first one being applied, which ends up
    creating an inline extent backref in the extent tree;

10) Next the delayed reference Ref3 is selected for execution, and not
    Ref2, because select_delayed_ref() always gives a preference for
    positive references (that have an action of BTRFS_ADD_DELAYED_REF);

11) When running Ref3 we encounter alreay the inline extent backref
    in the extent tree at insert_inline_extent_backref(), which makes
    us hit the following BUG_ON:

        BUG_ON(owner < BTRFS_FIRST_FREE_OBJECTID);

    This is always true because owner corresponds to the level of the
    extent buffer/btree node in the btree.

For the scenario described above we hit the BUG_ON because we never merge
references that have different seq values.

We used to do the merging before the 4.2 kernel, more specifically, before
the commmits:

  c6fc245499 ("btrfs: delayed-ref: Use list to replace the ref_root in ref_head.")
  c43d160fcd ("btrfs: delayed-ref: Cleanup the unneeded functions.")

This issue became more exposed after the following change that was added
to 4.2 as well:

  cffc3374e5 ("Btrfs: fix order by which delayed references are run")

Which in turn fixed another regression by the two commits previously
mentioned.

So fix this by bringing back the delayed reference merge code, with the
proper adaptations so that it operates against the new data structure
(linked list vs old red black tree implementation).

This issue was hit running fstest btrfs/063 in a loop. Several people have
reported this issue in the mailing list when running on kernels 4.2+.

Very special thanks to Stéphane Lesimple for helping debugging this issue
and testing this fix on his multi terabyte filesystem (which took more
than one day to balance alone, plus fsck, etc).

Fixes: c6fc245499 ("btrfs: delayed-ref: Use list to replace the ref_root in ref_head.")
Reported-by: Peter Becker <floyd.net@gmail.com>
Reported-by: Stéphane Lesimple <stephane_btrfs@lesimple.fr>
Tested-by: Stéphane Lesimple <stephane_btrfs@lesimple.fr>
Reported-by: Malte Schröder <malte@tnxip.de>
Reported-by: Derek Dongray <derek@valedon.co.uk>
Reported-by: Erkki Seppala <flux-btrfs@inside.org>
Cc: stable@vger.kernel.org  # 4.2+
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: Liu Bo <bo.li.liu@oracle.com>
2015-10-25 19:52:23 +00:00

976 lines
26 KiB
C

/*
* Copyright (C) 2009 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.
*/
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/sort.h>
#include "ctree.h"
#include "delayed-ref.h"
#include "transaction.h"
#include "qgroup.h"
struct kmem_cache *btrfs_delayed_ref_head_cachep;
struct kmem_cache *btrfs_delayed_tree_ref_cachep;
struct kmem_cache *btrfs_delayed_data_ref_cachep;
struct kmem_cache *btrfs_delayed_extent_op_cachep;
/*
* delayed back reference update tracking. For subvolume trees
* we queue up extent allocations and backref maintenance for
* delayed processing. This avoids deep call chains where we
* add extents in the middle of btrfs_search_slot, and it allows
* us to buffer up frequently modified backrefs in an rb tree instead
* of hammering updates on the extent allocation tree.
*/
/*
* compare two delayed tree backrefs with same bytenr and type
*/
static int comp_tree_refs(struct btrfs_delayed_tree_ref *ref2,
struct btrfs_delayed_tree_ref *ref1, int type)
{
if (type == BTRFS_TREE_BLOCK_REF_KEY) {
if (ref1->root < ref2->root)
return -1;
if (ref1->root > ref2->root)
return 1;
} else {
if (ref1->parent < ref2->parent)
return -1;
if (ref1->parent > ref2->parent)
return 1;
}
return 0;
}
/*
* compare two delayed data backrefs with same bytenr and type
*/
static int comp_data_refs(struct btrfs_delayed_data_ref *ref2,
struct btrfs_delayed_data_ref *ref1)
{
if (ref1->node.type == BTRFS_EXTENT_DATA_REF_KEY) {
if (ref1->root < ref2->root)
return -1;
if (ref1->root > ref2->root)
return 1;
if (ref1->objectid < ref2->objectid)
return -1;
if (ref1->objectid > ref2->objectid)
return 1;
if (ref1->offset < ref2->offset)
return -1;
if (ref1->offset > ref2->offset)
return 1;
} else {
if (ref1->parent < ref2->parent)
return -1;
if (ref1->parent > ref2->parent)
return 1;
}
return 0;
}
/* insert a new ref to head ref rbtree */
static struct btrfs_delayed_ref_head *htree_insert(struct rb_root *root,
struct rb_node *node)
{
struct rb_node **p = &root->rb_node;
struct rb_node *parent_node = NULL;
struct btrfs_delayed_ref_head *entry;
struct btrfs_delayed_ref_head *ins;
u64 bytenr;
ins = rb_entry(node, struct btrfs_delayed_ref_head, href_node);
bytenr = ins->node.bytenr;
while (*p) {
parent_node = *p;
entry = rb_entry(parent_node, struct btrfs_delayed_ref_head,
href_node);
if (bytenr < entry->node.bytenr)
p = &(*p)->rb_left;
else if (bytenr > entry->node.bytenr)
p = &(*p)->rb_right;
else
return entry;
}
rb_link_node(node, parent_node, p);
rb_insert_color(node, root);
return NULL;
}
/*
* find an head entry based on bytenr. This returns the delayed ref
* head if it was able to find one, or NULL if nothing was in that spot.
* If return_bigger is given, the next bigger entry is returned if no exact
* match is found.
*/
static struct btrfs_delayed_ref_head *
find_ref_head(struct rb_root *root, u64 bytenr,
int return_bigger)
{
struct rb_node *n;
struct btrfs_delayed_ref_head *entry;
n = root->rb_node;
entry = NULL;
while (n) {
entry = rb_entry(n, struct btrfs_delayed_ref_head, href_node);
if (bytenr < entry->node.bytenr)
n = n->rb_left;
else if (bytenr > entry->node.bytenr)
n = n->rb_right;
else
return entry;
}
if (entry && return_bigger) {
if (bytenr > entry->node.bytenr) {
n = rb_next(&entry->href_node);
if (!n)
n = rb_first(root);
entry = rb_entry(n, struct btrfs_delayed_ref_head,
href_node);
return entry;
}
return entry;
}
return NULL;
}
int btrfs_delayed_ref_lock(struct btrfs_trans_handle *trans,
struct btrfs_delayed_ref_head *head)
{
struct btrfs_delayed_ref_root *delayed_refs;
delayed_refs = &trans->transaction->delayed_refs;
assert_spin_locked(&delayed_refs->lock);
if (mutex_trylock(&head->mutex))
return 0;
atomic_inc(&head->node.refs);
spin_unlock(&delayed_refs->lock);
mutex_lock(&head->mutex);
spin_lock(&delayed_refs->lock);
if (!head->node.in_tree) {
mutex_unlock(&head->mutex);
btrfs_put_delayed_ref(&head->node);
return -EAGAIN;
}
btrfs_put_delayed_ref(&head->node);
return 0;
}
static inline void drop_delayed_ref(struct btrfs_trans_handle *trans,
struct btrfs_delayed_ref_root *delayed_refs,
struct btrfs_delayed_ref_head *head,
struct btrfs_delayed_ref_node *ref)
{
if (btrfs_delayed_ref_is_head(ref)) {
head = btrfs_delayed_node_to_head(ref);
rb_erase(&head->href_node, &delayed_refs->href_root);
} else {
assert_spin_locked(&head->lock);
list_del(&ref->list);
}
ref->in_tree = 0;
btrfs_put_delayed_ref(ref);
atomic_dec(&delayed_refs->num_entries);
if (trans->delayed_ref_updates)
trans->delayed_ref_updates--;
}
static bool merge_ref(struct btrfs_trans_handle *trans,
struct btrfs_delayed_ref_root *delayed_refs,
struct btrfs_delayed_ref_head *head,
struct btrfs_delayed_ref_node *ref,
u64 seq)
{
struct btrfs_delayed_ref_node *next;
bool done = false;
next = list_first_entry(&head->ref_list, struct btrfs_delayed_ref_node,
list);
while (!done && &next->list != &head->ref_list) {
int mod;
struct btrfs_delayed_ref_node *next2;
next2 = list_next_entry(next, list);
if (next == ref)
goto next;
if (seq && next->seq >= seq)
goto next;
if (next->type != ref->type || next->no_quota != ref->no_quota)
goto next;
if ((ref->type == BTRFS_TREE_BLOCK_REF_KEY ||
ref->type == BTRFS_SHARED_BLOCK_REF_KEY) &&
comp_tree_refs(btrfs_delayed_node_to_tree_ref(ref),
btrfs_delayed_node_to_tree_ref(next),
ref->type))
goto next;
if ((ref->type == BTRFS_EXTENT_DATA_REF_KEY ||
ref->type == BTRFS_SHARED_DATA_REF_KEY) &&
comp_data_refs(btrfs_delayed_node_to_data_ref(ref),
btrfs_delayed_node_to_data_ref(next)))
goto next;
if (ref->action == next->action) {
mod = next->ref_mod;
} else {
if (ref->ref_mod < next->ref_mod) {
swap(ref, next);
done = true;
}
mod = -next->ref_mod;
}
drop_delayed_ref(trans, delayed_refs, head, next);
ref->ref_mod += mod;
if (ref->ref_mod == 0) {
drop_delayed_ref(trans, delayed_refs, head, ref);
done = true;
} else {
/*
* Can't have multiples of the same ref on a tree block.
*/
WARN_ON(ref->type == BTRFS_TREE_BLOCK_REF_KEY ||
ref->type == BTRFS_SHARED_BLOCK_REF_KEY);
}
next:
next = next2;
}
return done;
}
void btrfs_merge_delayed_refs(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info,
struct btrfs_delayed_ref_root *delayed_refs,
struct btrfs_delayed_ref_head *head)
{
struct btrfs_delayed_ref_node *ref;
u64 seq = 0;
assert_spin_locked(&head->lock);
if (list_empty(&head->ref_list))
return;
/* We don't have too many refs to merge for data. */
if (head->is_data)
return;
spin_lock(&fs_info->tree_mod_seq_lock);
if (!list_empty(&fs_info->tree_mod_seq_list)) {
struct seq_list *elem;
elem = list_first_entry(&fs_info->tree_mod_seq_list,
struct seq_list, list);
seq = elem->seq;
}
spin_unlock(&fs_info->tree_mod_seq_lock);
ref = list_first_entry(&head->ref_list, struct btrfs_delayed_ref_node,
list);
while (&ref->list != &head->ref_list) {
if (seq && ref->seq >= seq)
goto next;
if (merge_ref(trans, delayed_refs, head, ref, seq)) {
if (list_empty(&head->ref_list))
break;
ref = list_first_entry(&head->ref_list,
struct btrfs_delayed_ref_node,
list);
continue;
}
next:
ref = list_next_entry(ref, list);
}
}
int btrfs_check_delayed_seq(struct btrfs_fs_info *fs_info,
struct btrfs_delayed_ref_root *delayed_refs,
u64 seq)
{
struct seq_list *elem;
int ret = 0;
spin_lock(&fs_info->tree_mod_seq_lock);
if (!list_empty(&fs_info->tree_mod_seq_list)) {
elem = list_first_entry(&fs_info->tree_mod_seq_list,
struct seq_list, list);
if (seq >= elem->seq) {
pr_debug("holding back delayed_ref %#x.%x, lowest is %#x.%x (%p)\n",
(u32)(seq >> 32), (u32)seq,
(u32)(elem->seq >> 32), (u32)elem->seq,
delayed_refs);
ret = 1;
}
}
spin_unlock(&fs_info->tree_mod_seq_lock);
return ret;
}
struct btrfs_delayed_ref_head *
btrfs_select_ref_head(struct btrfs_trans_handle *trans)
{
struct btrfs_delayed_ref_root *delayed_refs;
struct btrfs_delayed_ref_head *head;
u64 start;
bool loop = false;
delayed_refs = &trans->transaction->delayed_refs;
again:
start = delayed_refs->run_delayed_start;
head = find_ref_head(&delayed_refs->href_root, start, 1);
if (!head && !loop) {
delayed_refs->run_delayed_start = 0;
start = 0;
loop = true;
head = find_ref_head(&delayed_refs->href_root, start, 1);
if (!head)
return NULL;
} else if (!head && loop) {
return NULL;
}
while (head->processing) {
struct rb_node *node;
node = rb_next(&head->href_node);
if (!node) {
if (loop)
return NULL;
delayed_refs->run_delayed_start = 0;
start = 0;
loop = true;
goto again;
}
head = rb_entry(node, struct btrfs_delayed_ref_head,
href_node);
}
head->processing = 1;
WARN_ON(delayed_refs->num_heads_ready == 0);
delayed_refs->num_heads_ready--;
delayed_refs->run_delayed_start = head->node.bytenr +
head->node.num_bytes;
return head;
}
/*
* Helper to insert the ref_node to the tail or merge with tail.
*
* Return 0 for insert.
* Return >0 for merge.
*/
static int
add_delayed_ref_tail_merge(struct btrfs_trans_handle *trans,
struct btrfs_delayed_ref_root *root,
struct btrfs_delayed_ref_head *href,
struct btrfs_delayed_ref_node *ref)
{
struct btrfs_delayed_ref_node *exist;
int mod;
int ret = 0;
spin_lock(&href->lock);
/* Check whether we can merge the tail node with ref */
if (list_empty(&href->ref_list))
goto add_tail;
exist = list_entry(href->ref_list.prev, struct btrfs_delayed_ref_node,
list);
/* No need to compare bytenr nor is_head */
if (exist->type != ref->type || exist->no_quota != ref->no_quota ||
exist->seq != ref->seq)
goto add_tail;
if ((exist->type == BTRFS_TREE_BLOCK_REF_KEY ||
exist->type == BTRFS_SHARED_BLOCK_REF_KEY) &&
comp_tree_refs(btrfs_delayed_node_to_tree_ref(exist),
btrfs_delayed_node_to_tree_ref(ref),
ref->type))
goto add_tail;
if ((exist->type == BTRFS_EXTENT_DATA_REF_KEY ||
exist->type == BTRFS_SHARED_DATA_REF_KEY) &&
comp_data_refs(btrfs_delayed_node_to_data_ref(exist),
btrfs_delayed_node_to_data_ref(ref)))
goto add_tail;
/* Now we are sure we can merge */
ret = 1;
if (exist->action == ref->action) {
mod = ref->ref_mod;
} else {
/* Need to change action */
if (exist->ref_mod < ref->ref_mod) {
exist->action = ref->action;
mod = -exist->ref_mod;
exist->ref_mod = ref->ref_mod;
} else
mod = -ref->ref_mod;
}
exist->ref_mod += mod;
/* remove existing tail if its ref_mod is zero */
if (exist->ref_mod == 0)
drop_delayed_ref(trans, root, href, exist);
spin_unlock(&href->lock);
return ret;
add_tail:
list_add_tail(&ref->list, &href->ref_list);
atomic_inc(&root->num_entries);
trans->delayed_ref_updates++;
spin_unlock(&href->lock);
return ret;
}
/*
* helper function to update the accounting in the head ref
* existing and update must have the same bytenr
*/
static noinline void
update_existing_head_ref(struct btrfs_delayed_ref_root *delayed_refs,
struct btrfs_delayed_ref_node *existing,
struct btrfs_delayed_ref_node *update)
{
struct btrfs_delayed_ref_head *existing_ref;
struct btrfs_delayed_ref_head *ref;
int old_ref_mod;
existing_ref = btrfs_delayed_node_to_head(existing);
ref = btrfs_delayed_node_to_head(update);
BUG_ON(existing_ref->is_data != ref->is_data);
spin_lock(&existing_ref->lock);
if (ref->must_insert_reserved) {
/* if the extent was freed and then
* reallocated before the delayed ref
* entries were processed, we can end up
* with an existing head ref without
* the must_insert_reserved flag set.
* Set it again here
*/
existing_ref->must_insert_reserved = ref->must_insert_reserved;
/*
* update the num_bytes so we make sure the accounting
* is done correctly
*/
existing->num_bytes = update->num_bytes;
}
if (ref->extent_op) {
if (!existing_ref->extent_op) {
existing_ref->extent_op = ref->extent_op;
} else {
if (ref->extent_op->update_key) {
memcpy(&existing_ref->extent_op->key,
&ref->extent_op->key,
sizeof(ref->extent_op->key));
existing_ref->extent_op->update_key = 1;
}
if (ref->extent_op->update_flags) {
existing_ref->extent_op->flags_to_set |=
ref->extent_op->flags_to_set;
existing_ref->extent_op->update_flags = 1;
}
btrfs_free_delayed_extent_op(ref->extent_op);
}
}
/*
* update the reference mod on the head to reflect this new operation,
* only need the lock for this case cause we could be processing it
* currently, for refs we just added we know we're a-ok.
*/
old_ref_mod = existing_ref->total_ref_mod;
existing->ref_mod += update->ref_mod;
existing_ref->total_ref_mod += update->ref_mod;
/*
* If we are going to from a positive ref mod to a negative or vice
* versa we need to make sure to adjust pending_csums accordingly.
*/
if (existing_ref->is_data) {
if (existing_ref->total_ref_mod >= 0 && old_ref_mod < 0)
delayed_refs->pending_csums -= existing->num_bytes;
if (existing_ref->total_ref_mod < 0 && old_ref_mod >= 0)
delayed_refs->pending_csums += existing->num_bytes;
}
spin_unlock(&existing_ref->lock);
}
/*
* helper function to actually insert a head node into the rbtree.
* this does all the dirty work in terms of maintaining the correct
* overall modification count.
*/
static noinline struct btrfs_delayed_ref_head *
add_delayed_ref_head(struct btrfs_fs_info *fs_info,
struct btrfs_trans_handle *trans,
struct btrfs_delayed_ref_node *ref,
struct btrfs_qgroup_extent_record *qrecord,
u64 bytenr, u64 num_bytes, int action, int is_data)
{
struct btrfs_delayed_ref_head *existing;
struct btrfs_delayed_ref_head *head_ref = NULL;
struct btrfs_delayed_ref_root *delayed_refs;
struct btrfs_qgroup_extent_record *qexisting;
int count_mod = 1;
int must_insert_reserved = 0;
/*
* the head node stores the sum of all the mods, so dropping a ref
* should drop the sum in the head node by one.
*/
if (action == BTRFS_UPDATE_DELAYED_HEAD)
count_mod = 0;
else if (action == BTRFS_DROP_DELAYED_REF)
count_mod = -1;
/*
* BTRFS_ADD_DELAYED_EXTENT means that we need to update
* the reserved accounting when the extent is finally added, or
* if a later modification deletes the delayed ref without ever
* inserting the extent into the extent allocation tree.
* ref->must_insert_reserved is the flag used to record
* that accounting mods are required.
*
* Once we record must_insert_reserved, switch the action to
* BTRFS_ADD_DELAYED_REF because other special casing is not required.
*/
if (action == BTRFS_ADD_DELAYED_EXTENT)
must_insert_reserved = 1;
else
must_insert_reserved = 0;
delayed_refs = &trans->transaction->delayed_refs;
/* first set the basic ref node struct up */
atomic_set(&ref->refs, 1);
ref->bytenr = bytenr;
ref->num_bytes = num_bytes;
ref->ref_mod = count_mod;
ref->type = 0;
ref->action = 0;
ref->is_head = 1;
ref->in_tree = 1;
ref->seq = 0;
head_ref = btrfs_delayed_node_to_head(ref);
head_ref->must_insert_reserved = must_insert_reserved;
head_ref->is_data = is_data;
INIT_LIST_HEAD(&head_ref->ref_list);
head_ref->processing = 0;
head_ref->total_ref_mod = count_mod;
head_ref->qgroup_reserved = 0;
head_ref->qgroup_ref_root = 0;
/* Record qgroup extent info if provided */
if (qrecord) {
qrecord->bytenr = bytenr;
qrecord->num_bytes = num_bytes;
qrecord->old_roots = NULL;
qexisting = btrfs_qgroup_insert_dirty_extent(delayed_refs,
qrecord);
if (qexisting)
kfree(qrecord);
}
spin_lock_init(&head_ref->lock);
mutex_init(&head_ref->mutex);
trace_add_delayed_ref_head(ref, head_ref, action);
existing = htree_insert(&delayed_refs->href_root,
&head_ref->href_node);
if (existing) {
update_existing_head_ref(delayed_refs, &existing->node, ref);
/*
* we've updated the existing ref, free the newly
* allocated ref
*/
kmem_cache_free(btrfs_delayed_ref_head_cachep, head_ref);
head_ref = existing;
} else {
if (is_data && count_mod < 0)
delayed_refs->pending_csums += num_bytes;
delayed_refs->num_heads++;
delayed_refs->num_heads_ready++;
atomic_inc(&delayed_refs->num_entries);
trans->delayed_ref_updates++;
}
return head_ref;
}
/*
* helper to insert a delayed tree ref into the rbtree.
*/
static noinline void
add_delayed_tree_ref(struct btrfs_fs_info *fs_info,
struct btrfs_trans_handle *trans,
struct btrfs_delayed_ref_head *head_ref,
struct btrfs_delayed_ref_node *ref, u64 bytenr,
u64 num_bytes, u64 parent, u64 ref_root, int level,
int action, int no_quota)
{
struct btrfs_delayed_tree_ref *full_ref;
struct btrfs_delayed_ref_root *delayed_refs;
u64 seq = 0;
int ret;
if (action == BTRFS_ADD_DELAYED_EXTENT)
action = BTRFS_ADD_DELAYED_REF;
if (is_fstree(ref_root))
seq = atomic64_read(&fs_info->tree_mod_seq);
delayed_refs = &trans->transaction->delayed_refs;
/* first set the basic ref node struct up */
atomic_set(&ref->refs, 1);
ref->bytenr = bytenr;
ref->num_bytes = num_bytes;
ref->ref_mod = 1;
ref->action = action;
ref->is_head = 0;
ref->in_tree = 1;
ref->no_quota = no_quota;
ref->seq = seq;
full_ref = btrfs_delayed_node_to_tree_ref(ref);
full_ref->parent = parent;
full_ref->root = ref_root;
if (parent)
ref->type = BTRFS_SHARED_BLOCK_REF_KEY;
else
ref->type = BTRFS_TREE_BLOCK_REF_KEY;
full_ref->level = level;
trace_add_delayed_tree_ref(ref, full_ref, action);
ret = add_delayed_ref_tail_merge(trans, delayed_refs, head_ref, ref);
/*
* XXX: memory should be freed at the same level allocated.
* But bad practice is anywhere... Follow it now. Need cleanup.
*/
if (ret > 0)
kmem_cache_free(btrfs_delayed_tree_ref_cachep, full_ref);
}
/*
* helper to insert a delayed data ref into the rbtree.
*/
static noinline void
add_delayed_data_ref(struct btrfs_fs_info *fs_info,
struct btrfs_trans_handle *trans,
struct btrfs_delayed_ref_head *head_ref,
struct btrfs_delayed_ref_node *ref, u64 bytenr,
u64 num_bytes, u64 parent, u64 ref_root, u64 owner,
u64 offset, int action, int no_quota)
{
struct btrfs_delayed_data_ref *full_ref;
struct btrfs_delayed_ref_root *delayed_refs;
u64 seq = 0;
int ret;
if (action == BTRFS_ADD_DELAYED_EXTENT)
action = BTRFS_ADD_DELAYED_REF;
delayed_refs = &trans->transaction->delayed_refs;
if (is_fstree(ref_root))
seq = atomic64_read(&fs_info->tree_mod_seq);
/* first set the basic ref node struct up */
atomic_set(&ref->refs, 1);
ref->bytenr = bytenr;
ref->num_bytes = num_bytes;
ref->ref_mod = 1;
ref->action = action;
ref->is_head = 0;
ref->in_tree = 1;
ref->no_quota = no_quota;
ref->seq = seq;
full_ref = btrfs_delayed_node_to_data_ref(ref);
full_ref->parent = parent;
full_ref->root = ref_root;
if (parent)
ref->type = BTRFS_SHARED_DATA_REF_KEY;
else
ref->type = BTRFS_EXTENT_DATA_REF_KEY;
full_ref->objectid = owner;
full_ref->offset = offset;
trace_add_delayed_data_ref(ref, full_ref, action);
ret = add_delayed_ref_tail_merge(trans, delayed_refs, head_ref, ref);
if (ret > 0)
kmem_cache_free(btrfs_delayed_data_ref_cachep, full_ref);
}
/*
* add a delayed tree ref. This does all of the accounting required
* to make sure the delayed ref is eventually processed before this
* transaction commits.
*/
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 no_quota)
{
struct btrfs_delayed_tree_ref *ref;
struct btrfs_delayed_ref_head *head_ref;
struct btrfs_delayed_ref_root *delayed_refs;
struct btrfs_qgroup_extent_record *record = NULL;
if (!is_fstree(ref_root) || !fs_info->quota_enabled)
no_quota = 0;
BUG_ON(extent_op && extent_op->is_data);
ref = kmem_cache_alloc(btrfs_delayed_tree_ref_cachep, GFP_NOFS);
if (!ref)
return -ENOMEM;
head_ref = kmem_cache_alloc(btrfs_delayed_ref_head_cachep, GFP_NOFS);
if (!head_ref)
goto free_ref;
if (fs_info->quota_enabled && is_fstree(ref_root)) {
record = kmalloc(sizeof(*record), GFP_NOFS);
if (!record)
goto free_head_ref;
}
head_ref->extent_op = extent_op;
delayed_refs = &trans->transaction->delayed_refs;
spin_lock(&delayed_refs->lock);
/*
* insert both the head node and the new ref without dropping
* the spin lock
*/
head_ref = add_delayed_ref_head(fs_info, trans, &head_ref->node, record,
bytenr, num_bytes, action, 0);
add_delayed_tree_ref(fs_info, trans, head_ref, &ref->node, bytenr,
num_bytes, parent, ref_root, level, action,
no_quota);
spin_unlock(&delayed_refs->lock);
return 0;
free_head_ref:
kmem_cache_free(btrfs_delayed_ref_head_cachep, head_ref);
free_ref:
kmem_cache_free(btrfs_delayed_tree_ref_cachep, ref);
return -ENOMEM;
}
/*
* add a delayed data ref. it's similar to btrfs_add_delayed_tree_ref.
*/
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 no_quota)
{
struct btrfs_delayed_data_ref *ref;
struct btrfs_delayed_ref_head *head_ref;
struct btrfs_delayed_ref_root *delayed_refs;
struct btrfs_qgroup_extent_record *record = NULL;
if (!is_fstree(ref_root) || !fs_info->quota_enabled)
no_quota = 0;
BUG_ON(extent_op && !extent_op->is_data);
ref = kmem_cache_alloc(btrfs_delayed_data_ref_cachep, GFP_NOFS);
if (!ref)
return -ENOMEM;
head_ref = kmem_cache_alloc(btrfs_delayed_ref_head_cachep, GFP_NOFS);
if (!head_ref) {
kmem_cache_free(btrfs_delayed_data_ref_cachep, ref);
return -ENOMEM;
}
if (fs_info->quota_enabled && is_fstree(ref_root)) {
record = kmalloc(sizeof(*record), GFP_NOFS);
if (!record) {
kmem_cache_free(btrfs_delayed_data_ref_cachep, ref);
kmem_cache_free(btrfs_delayed_ref_head_cachep,
head_ref);
return -ENOMEM;
}
}
head_ref->extent_op = extent_op;
delayed_refs = &trans->transaction->delayed_refs;
spin_lock(&delayed_refs->lock);
/*
* insert both the head node and the new ref without dropping
* the spin lock
*/
head_ref = add_delayed_ref_head(fs_info, trans, &head_ref->node, record,
bytenr, num_bytes, action, 1);
add_delayed_data_ref(fs_info, trans, head_ref, &ref->node, bytenr,
num_bytes, parent, ref_root, owner, offset,
action, no_quota);
spin_unlock(&delayed_refs->lock);
return 0;
}
int btrfs_add_delayed_qgroup_reserve(struct btrfs_fs_info *fs_info,
struct btrfs_trans_handle *trans,
u64 ref_root, u64 bytenr, u64 num_bytes)
{
struct btrfs_delayed_ref_root *delayed_refs;
struct btrfs_delayed_ref_head *ref_head;
int ret = 0;
if (!fs_info->quota_enabled || !is_fstree(ref_root))
return 0;
delayed_refs = &trans->transaction->delayed_refs;
spin_lock(&delayed_refs->lock);
ref_head = find_ref_head(&delayed_refs->href_root, bytenr, 0);
if (!ref_head) {
ret = -ENOENT;
goto out;
}
WARN_ON(ref_head->qgroup_reserved || ref_head->qgroup_ref_root);
ref_head->qgroup_ref_root = ref_root;
ref_head->qgroup_reserved = num_bytes;
out:
spin_unlock(&delayed_refs->lock);
return ret;
}
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 *head_ref;
struct btrfs_delayed_ref_root *delayed_refs;
head_ref = kmem_cache_alloc(btrfs_delayed_ref_head_cachep, GFP_NOFS);
if (!head_ref)
return -ENOMEM;
head_ref->extent_op = extent_op;
delayed_refs = &trans->transaction->delayed_refs;
spin_lock(&delayed_refs->lock);
add_delayed_ref_head(fs_info, trans, &head_ref->node, NULL, bytenr,
num_bytes, BTRFS_UPDATE_DELAYED_HEAD,
extent_op->is_data);
spin_unlock(&delayed_refs->lock);
return 0;
}
/*
* this does a simple search for the head node for a given extent.
* It must be called with the delayed ref spinlock held, and it returns
* the head node if any where found, or NULL if not.
*/
struct btrfs_delayed_ref_head *
btrfs_find_delayed_ref_head(struct btrfs_trans_handle *trans, u64 bytenr)
{
struct btrfs_delayed_ref_root *delayed_refs;
delayed_refs = &trans->transaction->delayed_refs;
return find_ref_head(&delayed_refs->href_root, bytenr, 0);
}
void btrfs_delayed_ref_exit(void)
{
if (btrfs_delayed_ref_head_cachep)
kmem_cache_destroy(btrfs_delayed_ref_head_cachep);
if (btrfs_delayed_tree_ref_cachep)
kmem_cache_destroy(btrfs_delayed_tree_ref_cachep);
if (btrfs_delayed_data_ref_cachep)
kmem_cache_destroy(btrfs_delayed_data_ref_cachep);
if (btrfs_delayed_extent_op_cachep)
kmem_cache_destroy(btrfs_delayed_extent_op_cachep);
}
int btrfs_delayed_ref_init(void)
{
btrfs_delayed_ref_head_cachep = kmem_cache_create(
"btrfs_delayed_ref_head",
sizeof(struct btrfs_delayed_ref_head), 0,
SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD, NULL);
if (!btrfs_delayed_ref_head_cachep)
goto fail;
btrfs_delayed_tree_ref_cachep = kmem_cache_create(
"btrfs_delayed_tree_ref",
sizeof(struct btrfs_delayed_tree_ref), 0,
SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD, NULL);
if (!btrfs_delayed_tree_ref_cachep)
goto fail;
btrfs_delayed_data_ref_cachep = kmem_cache_create(
"btrfs_delayed_data_ref",
sizeof(struct btrfs_delayed_data_ref), 0,
SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD, NULL);
if (!btrfs_delayed_data_ref_cachep)
goto fail;
btrfs_delayed_extent_op_cachep = kmem_cache_create(
"btrfs_delayed_extent_op",
sizeof(struct btrfs_delayed_extent_op), 0,
SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD, NULL);
if (!btrfs_delayed_extent_op_cachep)
goto fail;
return 0;
fail:
btrfs_delayed_ref_exit();
return -ENOMEM;
}