mirror of
https://github.com/torvalds/linux.git
synced 2024-11-29 23:51:37 +00:00
5a0e3ad6af
percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
921 lines
24 KiB
C
921 lines
24 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"
|
|
|
|
/*
|
|
* 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)
|
|
{
|
|
if (ref1->node.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;
|
|
}
|
|
|
|
/*
|
|
* entries in the rb tree are ordered by the byte number of the extent,
|
|
* type of the delayed backrefs and content of delayed backrefs.
|
|
*/
|
|
static int comp_entry(struct btrfs_delayed_ref_node *ref2,
|
|
struct btrfs_delayed_ref_node *ref1)
|
|
{
|
|
if (ref1->bytenr < ref2->bytenr)
|
|
return -1;
|
|
if (ref1->bytenr > ref2->bytenr)
|
|
return 1;
|
|
if (ref1->is_head && ref2->is_head)
|
|
return 0;
|
|
if (ref2->is_head)
|
|
return -1;
|
|
if (ref1->is_head)
|
|
return 1;
|
|
if (ref1->type < ref2->type)
|
|
return -1;
|
|
if (ref1->type > ref2->type)
|
|
return 1;
|
|
if (ref1->type == BTRFS_TREE_BLOCK_REF_KEY ||
|
|
ref1->type == BTRFS_SHARED_BLOCK_REF_KEY) {
|
|
return comp_tree_refs(btrfs_delayed_node_to_tree_ref(ref2),
|
|
btrfs_delayed_node_to_tree_ref(ref1));
|
|
} else if (ref1->type == BTRFS_EXTENT_DATA_REF_KEY ||
|
|
ref1->type == BTRFS_SHARED_DATA_REF_KEY) {
|
|
return comp_data_refs(btrfs_delayed_node_to_data_ref(ref2),
|
|
btrfs_delayed_node_to_data_ref(ref1));
|
|
}
|
|
BUG();
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* insert a new ref into the rbtree. This returns any existing refs
|
|
* for the same (bytenr,parent) tuple, or NULL if the new node was properly
|
|
* inserted.
|
|
*/
|
|
static struct btrfs_delayed_ref_node *tree_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_node *entry;
|
|
struct btrfs_delayed_ref_node *ins;
|
|
int cmp;
|
|
|
|
ins = rb_entry(node, struct btrfs_delayed_ref_node, rb_node);
|
|
while (*p) {
|
|
parent_node = *p;
|
|
entry = rb_entry(parent_node, struct btrfs_delayed_ref_node,
|
|
rb_node);
|
|
|
|
cmp = comp_entry(entry, ins);
|
|
if (cmp < 0)
|
|
p = &(*p)->rb_left;
|
|
else if (cmp > 0)
|
|
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
|
|
*/
|
|
static struct btrfs_delayed_ref_node *find_ref_head(struct rb_root *root,
|
|
u64 bytenr,
|
|
struct btrfs_delayed_ref_node **last)
|
|
{
|
|
struct rb_node *n = root->rb_node;
|
|
struct btrfs_delayed_ref_node *entry;
|
|
int cmp;
|
|
|
|
while (n) {
|
|
entry = rb_entry(n, struct btrfs_delayed_ref_node, rb_node);
|
|
WARN_ON(!entry->in_tree);
|
|
if (last)
|
|
*last = entry;
|
|
|
|
if (bytenr < entry->bytenr)
|
|
cmp = -1;
|
|
else if (bytenr > entry->bytenr)
|
|
cmp = 1;
|
|
else if (!btrfs_delayed_ref_is_head(entry))
|
|
cmp = 1;
|
|
else
|
|
cmp = 0;
|
|
|
|
if (cmp < 0)
|
|
n = n->rb_left;
|
|
else if (cmp > 0)
|
|
n = n->rb_right;
|
|
else
|
|
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;
|
|
}
|
|
|
|
int btrfs_find_ref_cluster(struct btrfs_trans_handle *trans,
|
|
struct list_head *cluster, u64 start)
|
|
{
|
|
int count = 0;
|
|
struct btrfs_delayed_ref_root *delayed_refs;
|
|
struct rb_node *node;
|
|
struct btrfs_delayed_ref_node *ref;
|
|
struct btrfs_delayed_ref_head *head;
|
|
|
|
delayed_refs = &trans->transaction->delayed_refs;
|
|
if (start == 0) {
|
|
node = rb_first(&delayed_refs->root);
|
|
} else {
|
|
ref = NULL;
|
|
find_ref_head(&delayed_refs->root, start, &ref);
|
|
if (ref) {
|
|
struct btrfs_delayed_ref_node *tmp;
|
|
|
|
node = rb_prev(&ref->rb_node);
|
|
while (node) {
|
|
tmp = rb_entry(node,
|
|
struct btrfs_delayed_ref_node,
|
|
rb_node);
|
|
if (tmp->bytenr < start)
|
|
break;
|
|
ref = tmp;
|
|
node = rb_prev(&ref->rb_node);
|
|
}
|
|
node = &ref->rb_node;
|
|
} else
|
|
node = rb_first(&delayed_refs->root);
|
|
}
|
|
again:
|
|
while (node && count < 32) {
|
|
ref = rb_entry(node, struct btrfs_delayed_ref_node, rb_node);
|
|
if (btrfs_delayed_ref_is_head(ref)) {
|
|
head = btrfs_delayed_node_to_head(ref);
|
|
if (list_empty(&head->cluster)) {
|
|
list_add_tail(&head->cluster, cluster);
|
|
delayed_refs->run_delayed_start =
|
|
head->node.bytenr;
|
|
count++;
|
|
|
|
WARN_ON(delayed_refs->num_heads_ready == 0);
|
|
delayed_refs->num_heads_ready--;
|
|
} else if (count) {
|
|
/* the goal of the clustering is to find extents
|
|
* that are likely to end up in the same extent
|
|
* leaf on disk. So, we don't want them spread
|
|
* all over the tree. Stop now if we've hit
|
|
* a head that was already in use
|
|
*/
|
|
break;
|
|
}
|
|
}
|
|
node = rb_next(node);
|
|
}
|
|
if (count) {
|
|
return 0;
|
|
} else if (start) {
|
|
/*
|
|
* we've gone to the end of the rbtree without finding any
|
|
* clusters. start from the beginning and try again
|
|
*/
|
|
start = 0;
|
|
node = rb_first(&delayed_refs->root);
|
|
goto again;
|
|
}
|
|
return 1;
|
|
}
|
|
|
|
/*
|
|
* This checks to see if there are any delayed refs in the
|
|
* btree for a given bytenr. It returns one if it finds any
|
|
* and zero otherwise.
|
|
*
|
|
* If it only finds a head node, it returns 0.
|
|
*
|
|
* The idea is to use this when deciding if you can safely delete an
|
|
* extent from the extent allocation tree. There may be a pending
|
|
* ref in the rbtree that adds or removes references, so as long as this
|
|
* returns one you need to leave the BTRFS_EXTENT_ITEM in the extent
|
|
* allocation tree.
|
|
*/
|
|
int btrfs_delayed_ref_pending(struct btrfs_trans_handle *trans, u64 bytenr)
|
|
{
|
|
struct btrfs_delayed_ref_node *ref;
|
|
struct btrfs_delayed_ref_root *delayed_refs;
|
|
struct rb_node *prev_node;
|
|
int ret = 0;
|
|
|
|
delayed_refs = &trans->transaction->delayed_refs;
|
|
spin_lock(&delayed_refs->lock);
|
|
|
|
ref = find_ref_head(&delayed_refs->root, bytenr, NULL);
|
|
if (ref) {
|
|
prev_node = rb_prev(&ref->rb_node);
|
|
if (!prev_node)
|
|
goto out;
|
|
ref = rb_entry(prev_node, struct btrfs_delayed_ref_node,
|
|
rb_node);
|
|
if (ref->bytenr == bytenr)
|
|
ret = 1;
|
|
}
|
|
out:
|
|
spin_unlock(&delayed_refs->lock);
|
|
return ret;
|
|
}
|
|
|
|
/*
|
|
* helper function to lookup reference count and flags of extent.
|
|
*
|
|
* the head node for delayed ref is used to store the sum of all the
|
|
* reference count modifications queued up in the rbtree. the head
|
|
* node may also store the extent flags to set. This way you can check
|
|
* to see what the reference count and extent flags would be if all of
|
|
* the delayed refs are not processed.
|
|
*/
|
|
int btrfs_lookup_extent_info(struct btrfs_trans_handle *trans,
|
|
struct btrfs_root *root, u64 bytenr,
|
|
u64 num_bytes, u64 *refs, u64 *flags)
|
|
{
|
|
struct btrfs_delayed_ref_node *ref;
|
|
struct btrfs_delayed_ref_head *head;
|
|
struct btrfs_delayed_ref_root *delayed_refs;
|
|
struct btrfs_path *path;
|
|
struct btrfs_extent_item *ei;
|
|
struct extent_buffer *leaf;
|
|
struct btrfs_key key;
|
|
u32 item_size;
|
|
u64 num_refs;
|
|
u64 extent_flags;
|
|
int ret;
|
|
|
|
path = btrfs_alloc_path();
|
|
if (!path)
|
|
return -ENOMEM;
|
|
|
|
key.objectid = bytenr;
|
|
key.type = BTRFS_EXTENT_ITEM_KEY;
|
|
key.offset = num_bytes;
|
|
delayed_refs = &trans->transaction->delayed_refs;
|
|
again:
|
|
ret = btrfs_search_slot(trans, root->fs_info->extent_root,
|
|
&key, path, 0, 0);
|
|
if (ret < 0)
|
|
goto out;
|
|
|
|
if (ret == 0) {
|
|
leaf = path->nodes[0];
|
|
item_size = btrfs_item_size_nr(leaf, path->slots[0]);
|
|
if (item_size >= sizeof(*ei)) {
|
|
ei = btrfs_item_ptr(leaf, path->slots[0],
|
|
struct btrfs_extent_item);
|
|
num_refs = btrfs_extent_refs(leaf, ei);
|
|
extent_flags = btrfs_extent_flags(leaf, ei);
|
|
} else {
|
|
#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
|
|
struct btrfs_extent_item_v0 *ei0;
|
|
BUG_ON(item_size != sizeof(*ei0));
|
|
ei0 = btrfs_item_ptr(leaf, path->slots[0],
|
|
struct btrfs_extent_item_v0);
|
|
num_refs = btrfs_extent_refs_v0(leaf, ei0);
|
|
/* FIXME: this isn't correct for data */
|
|
extent_flags = BTRFS_BLOCK_FLAG_FULL_BACKREF;
|
|
#else
|
|
BUG();
|
|
#endif
|
|
}
|
|
BUG_ON(num_refs == 0);
|
|
} else {
|
|
num_refs = 0;
|
|
extent_flags = 0;
|
|
ret = 0;
|
|
}
|
|
|
|
spin_lock(&delayed_refs->lock);
|
|
ref = find_ref_head(&delayed_refs->root, bytenr, NULL);
|
|
if (ref) {
|
|
head = btrfs_delayed_node_to_head(ref);
|
|
if (!mutex_trylock(&head->mutex)) {
|
|
atomic_inc(&ref->refs);
|
|
spin_unlock(&delayed_refs->lock);
|
|
|
|
btrfs_release_path(root->fs_info->extent_root, path);
|
|
|
|
mutex_lock(&head->mutex);
|
|
mutex_unlock(&head->mutex);
|
|
btrfs_put_delayed_ref(ref);
|
|
goto again;
|
|
}
|
|
if (head->extent_op && head->extent_op->update_flags)
|
|
extent_flags |= head->extent_op->flags_to_set;
|
|
else
|
|
BUG_ON(num_refs == 0);
|
|
|
|
num_refs += ref->ref_mod;
|
|
mutex_unlock(&head->mutex);
|
|
}
|
|
WARN_ON(num_refs == 0);
|
|
if (refs)
|
|
*refs = num_refs;
|
|
if (flags)
|
|
*flags = extent_flags;
|
|
out:
|
|
spin_unlock(&delayed_refs->lock);
|
|
btrfs_free_path(path);
|
|
return ret;
|
|
}
|
|
|
|
/*
|
|
* helper function to update an extent delayed ref in the
|
|
* rbtree. existing and update must both have the same
|
|
* bytenr and parent
|
|
*
|
|
* This may free existing if the update cancels out whatever
|
|
* operation it was doing.
|
|
*/
|
|
static noinline void
|
|
update_existing_ref(struct btrfs_trans_handle *trans,
|
|
struct btrfs_delayed_ref_root *delayed_refs,
|
|
struct btrfs_delayed_ref_node *existing,
|
|
struct btrfs_delayed_ref_node *update)
|
|
{
|
|
if (update->action != existing->action) {
|
|
/*
|
|
* this is effectively undoing either an add or a
|
|
* drop. We decrement the ref_mod, and if it goes
|
|
* down to zero we just delete the entry without
|
|
* every changing the extent allocation tree.
|
|
*/
|
|
existing->ref_mod--;
|
|
if (existing->ref_mod == 0) {
|
|
rb_erase(&existing->rb_node,
|
|
&delayed_refs->root);
|
|
existing->in_tree = 0;
|
|
btrfs_put_delayed_ref(existing);
|
|
delayed_refs->num_entries--;
|
|
if (trans->delayed_ref_updates)
|
|
trans->delayed_ref_updates--;
|
|
} else {
|
|
WARN_ON(existing->type == BTRFS_TREE_BLOCK_REF_KEY ||
|
|
existing->type == BTRFS_SHARED_BLOCK_REF_KEY);
|
|
}
|
|
} else {
|
|
WARN_ON(existing->type == BTRFS_TREE_BLOCK_REF_KEY ||
|
|
existing->type == BTRFS_SHARED_BLOCK_REF_KEY);
|
|
/*
|
|
* the action on the existing ref matches
|
|
* the action on the ref we're trying to add.
|
|
* Bump the ref_mod by one so the backref that
|
|
* is eventually added/removed has the correct
|
|
* reference count
|
|
*/
|
|
existing->ref_mod += update->ref_mod;
|
|
}
|
|
}
|
|
|
|
/*
|
|
* 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_node *existing,
|
|
struct btrfs_delayed_ref_node *update)
|
|
{
|
|
struct btrfs_delayed_ref_head *existing_ref;
|
|
struct btrfs_delayed_ref_head *ref;
|
|
|
|
existing_ref = btrfs_delayed_node_to_head(existing);
|
|
ref = btrfs_delayed_node_to_head(update);
|
|
BUG_ON(existing_ref->is_data != ref->is_data);
|
|
|
|
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;
|
|
}
|
|
kfree(ref->extent_op);
|
|
}
|
|
}
|
|
/*
|
|
* update the reference mod on the head to reflect this new operation
|
|
*/
|
|
existing->ref_mod += update->ref_mod;
|
|
}
|
|
|
|
/*
|
|
* 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 int add_delayed_ref_head(struct btrfs_trans_handle *trans,
|
|
struct btrfs_delayed_ref_node *ref,
|
|
u64 bytenr, u64 num_bytes,
|
|
int action, int is_data)
|
|
{
|
|
struct btrfs_delayed_ref_node *existing;
|
|
struct btrfs_delayed_ref_head *head_ref = NULL;
|
|
struct btrfs_delayed_ref_root *delayed_refs;
|
|
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;
|
|
|
|
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->cluster);
|
|
mutex_init(&head_ref->mutex);
|
|
|
|
existing = tree_insert(&delayed_refs->root, &ref->rb_node);
|
|
|
|
if (existing) {
|
|
update_existing_head_ref(existing, ref);
|
|
/*
|
|
* we've updated the existing ref, free the newly
|
|
* allocated ref
|
|
*/
|
|
kfree(ref);
|
|
} else {
|
|
delayed_refs->num_heads++;
|
|
delayed_refs->num_heads_ready++;
|
|
delayed_refs->num_entries++;
|
|
trans->delayed_ref_updates++;
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* helper to insert a delayed tree ref into the rbtree.
|
|
*/
|
|
static noinline int add_delayed_tree_ref(struct btrfs_trans_handle *trans,
|
|
struct btrfs_delayed_ref_node *ref,
|
|
u64 bytenr, u64 num_bytes, u64 parent,
|
|
u64 ref_root, int level, int action)
|
|
{
|
|
struct btrfs_delayed_ref_node *existing;
|
|
struct btrfs_delayed_tree_ref *full_ref;
|
|
struct btrfs_delayed_ref_root *delayed_refs;
|
|
|
|
if (action == BTRFS_ADD_DELAYED_EXTENT)
|
|
action = BTRFS_ADD_DELAYED_REF;
|
|
|
|
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;
|
|
|
|
full_ref = btrfs_delayed_node_to_tree_ref(ref);
|
|
if (parent) {
|
|
full_ref->parent = parent;
|
|
ref->type = BTRFS_SHARED_BLOCK_REF_KEY;
|
|
} else {
|
|
full_ref->root = ref_root;
|
|
ref->type = BTRFS_TREE_BLOCK_REF_KEY;
|
|
}
|
|
full_ref->level = level;
|
|
|
|
existing = tree_insert(&delayed_refs->root, &ref->rb_node);
|
|
|
|
if (existing) {
|
|
update_existing_ref(trans, delayed_refs, existing, ref);
|
|
/*
|
|
* we've updated the existing ref, free the newly
|
|
* allocated ref
|
|
*/
|
|
kfree(ref);
|
|
} else {
|
|
delayed_refs->num_entries++;
|
|
trans->delayed_ref_updates++;
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* helper to insert a delayed data ref into the rbtree.
|
|
*/
|
|
static noinline int add_delayed_data_ref(struct btrfs_trans_handle *trans,
|
|
struct btrfs_delayed_ref_node *ref,
|
|
u64 bytenr, u64 num_bytes, u64 parent,
|
|
u64 ref_root, u64 owner, u64 offset,
|
|
int action)
|
|
{
|
|
struct btrfs_delayed_ref_node *existing;
|
|
struct btrfs_delayed_data_ref *full_ref;
|
|
struct btrfs_delayed_ref_root *delayed_refs;
|
|
|
|
if (action == BTRFS_ADD_DELAYED_EXTENT)
|
|
action = BTRFS_ADD_DELAYED_REF;
|
|
|
|
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;
|
|
|
|
full_ref = btrfs_delayed_node_to_data_ref(ref);
|
|
if (parent) {
|
|
full_ref->parent = parent;
|
|
ref->type = BTRFS_SHARED_DATA_REF_KEY;
|
|
} else {
|
|
full_ref->root = ref_root;
|
|
ref->type = BTRFS_EXTENT_DATA_REF_KEY;
|
|
}
|
|
full_ref->objectid = owner;
|
|
full_ref->offset = offset;
|
|
|
|
existing = tree_insert(&delayed_refs->root, &ref->rb_node);
|
|
|
|
if (existing) {
|
|
update_existing_ref(trans, delayed_refs, existing, ref);
|
|
/*
|
|
* we've updated the existing ref, free the newly
|
|
* allocated ref
|
|
*/
|
|
kfree(ref);
|
|
} else {
|
|
delayed_refs->num_entries++;
|
|
trans->delayed_ref_updates++;
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* 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_trans_handle *trans,
|
|
u64 bytenr, u64 num_bytes, u64 parent,
|
|
u64 ref_root, int level, int action,
|
|
struct btrfs_delayed_extent_op *extent_op)
|
|
{
|
|
struct btrfs_delayed_tree_ref *ref;
|
|
struct btrfs_delayed_ref_head *head_ref;
|
|
struct btrfs_delayed_ref_root *delayed_refs;
|
|
int ret;
|
|
|
|
BUG_ON(extent_op && extent_op->is_data);
|
|
ref = kmalloc(sizeof(*ref), GFP_NOFS);
|
|
if (!ref)
|
|
return -ENOMEM;
|
|
|
|
head_ref = kmalloc(sizeof(*head_ref), GFP_NOFS);
|
|
if (!head_ref) {
|
|
kfree(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
|
|
*/
|
|
ret = add_delayed_ref_head(trans, &head_ref->node, bytenr, num_bytes,
|
|
action, 0);
|
|
BUG_ON(ret);
|
|
|
|
ret = add_delayed_tree_ref(trans, &ref->node, bytenr, num_bytes,
|
|
parent, ref_root, level, action);
|
|
BUG_ON(ret);
|
|
spin_unlock(&delayed_refs->lock);
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* add a delayed data ref. it's similar to btrfs_add_delayed_tree_ref.
|
|
*/
|
|
int btrfs_add_delayed_data_ref(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)
|
|
{
|
|
struct btrfs_delayed_data_ref *ref;
|
|
struct btrfs_delayed_ref_head *head_ref;
|
|
struct btrfs_delayed_ref_root *delayed_refs;
|
|
int ret;
|
|
|
|
BUG_ON(extent_op && !extent_op->is_data);
|
|
ref = kmalloc(sizeof(*ref), GFP_NOFS);
|
|
if (!ref)
|
|
return -ENOMEM;
|
|
|
|
head_ref = kmalloc(sizeof(*head_ref), GFP_NOFS);
|
|
if (!head_ref) {
|
|
kfree(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
|
|
*/
|
|
ret = add_delayed_ref_head(trans, &head_ref->node, bytenr, num_bytes,
|
|
action, 1);
|
|
BUG_ON(ret);
|
|
|
|
ret = add_delayed_data_ref(trans, &ref->node, bytenr, num_bytes,
|
|
parent, ref_root, owner, offset, action);
|
|
BUG_ON(ret);
|
|
spin_unlock(&delayed_refs->lock);
|
|
return 0;
|
|
}
|
|
|
|
int btrfs_add_delayed_extent_op(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;
|
|
int ret;
|
|
|
|
head_ref = kmalloc(sizeof(*head_ref), GFP_NOFS);
|
|
if (!head_ref)
|
|
return -ENOMEM;
|
|
|
|
head_ref->extent_op = extent_op;
|
|
|
|
delayed_refs = &trans->transaction->delayed_refs;
|
|
spin_lock(&delayed_refs->lock);
|
|
|
|
ret = add_delayed_ref_head(trans, &head_ref->node, bytenr,
|
|
num_bytes, BTRFS_UPDATE_DELAYED_HEAD,
|
|
extent_op->is_data);
|
|
BUG_ON(ret);
|
|
|
|
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_node *ref;
|
|
struct btrfs_delayed_ref_root *delayed_refs;
|
|
|
|
delayed_refs = &trans->transaction->delayed_refs;
|
|
ref = find_ref_head(&delayed_refs->root, bytenr, NULL);
|
|
if (ref)
|
|
return btrfs_delayed_node_to_head(ref);
|
|
return NULL;
|
|
}
|
|
|
|
/*
|
|
* add a delayed ref to the tree. This does all of the accounting required
|
|
* to make sure the delayed ref is eventually processed before this
|
|
* transaction commits.
|
|
*
|
|
* The main point of this call is to add and remove a backreference in a single
|
|
* shot, taking the lock only once, and only searching for the head node once.
|
|
*
|
|
* It is the same as doing a ref add and delete in two separate calls.
|
|
*/
|
|
#if 0
|
|
int btrfs_update_delayed_ref(struct btrfs_trans_handle *trans,
|
|
u64 bytenr, u64 num_bytes, u64 orig_parent,
|
|
u64 parent, u64 orig_ref_root, u64 ref_root,
|
|
u64 orig_ref_generation, u64 ref_generation,
|
|
u64 owner_objectid, int pin)
|
|
{
|
|
struct btrfs_delayed_ref *ref;
|
|
struct btrfs_delayed_ref *old_ref;
|
|
struct btrfs_delayed_ref_head *head_ref;
|
|
struct btrfs_delayed_ref_root *delayed_refs;
|
|
int ret;
|
|
|
|
ref = kmalloc(sizeof(*ref), GFP_NOFS);
|
|
if (!ref)
|
|
return -ENOMEM;
|
|
|
|
old_ref = kmalloc(sizeof(*old_ref), GFP_NOFS);
|
|
if (!old_ref) {
|
|
kfree(ref);
|
|
return -ENOMEM;
|
|
}
|
|
|
|
/*
|
|
* the parent = 0 case comes from cases where we don't actually
|
|
* know the parent yet. It will get updated later via a add/drop
|
|
* pair.
|
|
*/
|
|
if (parent == 0)
|
|
parent = bytenr;
|
|
if (orig_parent == 0)
|
|
orig_parent = bytenr;
|
|
|
|
head_ref = kmalloc(sizeof(*head_ref), GFP_NOFS);
|
|
if (!head_ref) {
|
|
kfree(ref);
|
|
kfree(old_ref);
|
|
return -ENOMEM;
|
|
}
|
|
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
|
|
*/
|
|
ret = __btrfs_add_delayed_ref(trans, &head_ref->node, bytenr, num_bytes,
|
|
(u64)-1, 0, 0, 0,
|
|
BTRFS_UPDATE_DELAYED_HEAD, 0);
|
|
BUG_ON(ret);
|
|
|
|
ret = __btrfs_add_delayed_ref(trans, &ref->node, bytenr, num_bytes,
|
|
parent, ref_root, ref_generation,
|
|
owner_objectid, BTRFS_ADD_DELAYED_REF, 0);
|
|
BUG_ON(ret);
|
|
|
|
ret = __btrfs_add_delayed_ref(trans, &old_ref->node, bytenr, num_bytes,
|
|
orig_parent, orig_ref_root,
|
|
orig_ref_generation, owner_objectid,
|
|
BTRFS_DROP_DELAYED_REF, pin);
|
|
BUG_ON(ret);
|
|
spin_unlock(&delayed_refs->lock);
|
|
return 0;
|
|
}
|
|
#endif
|