UbiquitousOS
/
OpenCloudOS-Kernel
mirror of https://gitee.com/OpenCloudOS/OpenCloudOS-Kernel.git
11
0
Fork 0
Code Issues Projects Releases Wiki Activity

btrfs: convert snapshot/nocow exlcusion to drew lock 

This patch removes all haphazard code implementing nocow writers
exclusion from pending snapshot creation and switches to using the drew
lock to ensure this invariant still holds.

'Readers' are snapshot creators from create_snapshot and 'writers' are
nocow writers from buffered write path or btrfs_setsize. This locking
scheme allows for multiple snapshots to happen while any nocow writers
are blocked, since writes to page cache in the nocow path will make
snapshots inconsistent.

So for performance reasons we'd like to have the ability to run multiple
concurrent snapshots and also favors readers in this case. And in case
there aren't pending snapshots (which will be the majority of the cases)
we rely on the percpu's writers counter to avoid cacheline contention.

The main gain from using the drew lock is it's now a lot easier to
reason about the guarantees of the locking scheme and whether there is
some silent breakage lurking.

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
This commit is contained in:
Nikolay Borisov 2020-01-30 14:59:45 +02:00 committed by David Sterba
parent 2992df7326
commit dcc3eb9638
6 changed files with 25 additions and 103 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
fs/btrfs/ctree.h
View File

@ -957,11 +957,6 @@ static inline struct btrfs_fs_info *btrfs_sb(struct super_block *sb)
return sb->s_fs_info;
}
struct btrfs_subvolume_writers {
struct percpu_counter counter;
wait_queue_head_t wait;
};
/*
* The state of btrfs root
*/
@ -1133,8 +1128,9 @@ struct btrfs_root {
* root_item_lock.
*/
int dedupe_in_progress;
struct btrfs_subvolume_writers *subv_writers;
atomic_t will_be_snapshotted;
/* For exclusion of snapshot creation and nocow writes */
struct btrfs_drew_lock snapshot_lock;
atomic_t snapshot_force_cow;
/* For qgroup metadata reserved space */

45
fs/btrfs/disk-io.c
View File

@ -1104,32 +1104,6 @@ void btrfs_clean_tree_block(struct extent_buffer *buf)
}
}
static struct btrfs_subvolume_writers *btrfs_alloc_subvolume_writers(void)
{
struct btrfs_subvolume_writers *writers;
int ret;
writers = kmalloc(sizeof(*writers), GFP_NOFS);
if (!writers)
return ERR_PTR(-ENOMEM);
ret = percpu_counter_init(&writers->counter, 0, GFP_NOFS);
if (ret < 0) {
kfree(writers);
return ERR_PTR(ret);
}
init_waitqueue_head(&writers->wait);
return writers;
}
static void
btrfs_free_subvolume_writers(struct btrfs_subvolume_writers *writers)
{
percpu_counter_destroy(&writers->counter);
kfree(writers);
}
static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info,
u64 objectid)
{
@ -1178,7 +1152,6 @@ static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info,
atomic_set(&root->log_writers, 0);
atomic_set(&root->log_batch, 0);
refcount_set(&root->refs, 1);
atomic_set(&root->will_be_snapshotted, 0);
atomic_set(&root->snapshot_force_cow, 0);
atomic_set(&root->nr_swapfiles, 0);
root->log_transid = 0;
@ -1450,7 +1423,7 @@ alloc_fail:
static int btrfs_init_fs_root(struct btrfs_root *root)
{
int ret;
struct btrfs_subvolume_writers *writers;
unsigned int nofs_flag;
root->free_ino_ctl = kzalloc(sizeof(*root->free_ino_ctl), GFP_NOFS);
root->free_ino_pinned = kzalloc(sizeof(*root->free_ino_pinned),
@ -1460,12 +1433,15 @@ static int btrfs_init_fs_root(struct btrfs_root *root)
goto fail;
}
writers = btrfs_alloc_subvolume_writers();
if (IS_ERR(writers)) {
ret = PTR_ERR(writers);
/*
* We might be called under a transaction (e.g. indirect backref
* resolution) which could deadlock if it triggers memory reclaim
*/
nofs_flag = memalloc_nofs_save();
ret = btrfs_drew_lock_init(&root->snapshot_lock);
memalloc_nofs_restore(nofs_flag);
if (ret)
goto fail;
}
root->subv_writers = writers;
if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) {
set_bit(BTRFS_ROOT_REF_COWS, &root->state);
@ -3961,8 +3937,7 @@ void btrfs_free_fs_root(struct btrfs_root *root)
WARN_ON(!RB_EMPTY_ROOT(&root->inode_tree));
if (root->anon_dev)
free_anon_bdev(root->anon_dev);
if (root->subv_writers)
btrfs_free_subvolume_writers(root->subv_writers);
btrfs_drew_lock_destroy(&root->snapshot_lock);
free_extent_buffer(root->node);
free_extent_buffer(root->commit_root);
kfree(root->free_ino_ctl);

44
fs/btrfs/extent-tree.c
View File

@ -5740,47 +5740,3 @@ int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range *range)
return bg_ret;
return dev_ret;
}
/*
* btrfs_{start,end}_write_no_snapshotting() are similar to
* mnt_{want,drop}_write(), they are used to prevent some tasks from writing
* data into the page cache through nocow before the subvolume is snapshoted,
* but flush the data into disk after the snapshot creation, or to prevent
* operations while snapshotting is ongoing and that cause the snapshot to be
* inconsistent (writes followed by expanding truncates for example).
*/
void btrfs_end_write_no_snapshotting(struct btrfs_root *root)
{
percpu_counter_dec(&root->subv_writers->counter);
cond_wake_up(&root->subv_writers->wait);
}
int btrfs_start_write_no_snapshotting(struct btrfs_root *root)
{
if (atomic_read(&root->will_be_snapshotted))
return 0;
percpu_counter_inc(&root->subv_writers->counter);
/*
* Make sure counter is updated before we check for snapshot creation.
*/
smp_mb();
if (atomic_read(&root->will_be_snapshotted)) {
btrfs_end_write_no_snapshotting(root);
return 0;
}
return 1;
}
void btrfs_wait_for_snapshot_creation(struct btrfs_root *root)
{
while (true) {
int ret;
ret = btrfs_start_write_no_snapshotting(root);
if (ret)
break;
wait_var_event(&root->will_be_snapshotted,
!atomic_read(&root->will_be_snapshotted));
}
}

11
fs/btrfs/file.c
View File

@ -1553,8 +1553,7 @@ static noinline int check_can_nocow(struct btrfs_inode *inode, loff_t pos,
u64 num_bytes;
int ret;
ret = btrfs_start_write_no_snapshotting(root);
if (!ret)
if (!btrfs_drew_try_write_lock(&root->snapshot_lock))
return -EAGAIN;
lockstart = round_down(pos, fs_info->sectorsize);
@ -1569,7 +1568,7 @@ static noinline int check_can_nocow(struct btrfs_inode *inode, loff_t pos,
NULL, NULL, NULL);
if (ret <= 0) {
ret = 0;
btrfs_end_write_no_snapshotting(root);
btrfs_drew_write_unlock(&root->snapshot_lock);
} else {
*write_bytes = min_t(size_t, *write_bytes ,
num_bytes - pos + lockstart);
@ -1675,7 +1674,7 @@ static noinline ssize_t btrfs_buffered_write(struct kiocb *iocb,
data_reserved, pos,
write_bytes);
else
btrfs_end_write_no_snapshotting(root);
btrfs_drew_write_unlock(&root->snapshot_lock);
break;
}
@ -1779,7 +1778,7 @@ again:
release_bytes = 0;
if (only_release_metadata)
btrfs_end_write_no_snapshotting(root);
btrfs_drew_write_unlock(&root->snapshot_lock);
if (only_release_metadata && copied > 0) {
lockstart = round_down(pos,
@ -1808,7 +1807,7 @@ again:
if (release_bytes) {
if (only_release_metadata) {
btrfs_end_write_no_snapshotting(root);
btrfs_drew_write_unlock(&root->snapshot_lock);
btrfs_delalloc_release_metadata(BTRFS_I(inode),
release_bytes, true);
} else {

8
fs/btrfs/inode.c
View File

@ -4726,16 +4726,16 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr)
* truncation, it must capture all writes that happened before
* this truncation.
*/
btrfs_wait_for_snapshot_creation(root);
btrfs_drew_write_lock(&root->snapshot_lock);
ret = btrfs_cont_expand(inode, oldsize, newsize);
if (ret) {
btrfs_end_write_no_snapshotting(root);
btrfs_drew_write_unlock(&root->snapshot_lock);
return ret;
}
trans = btrfs_start_transaction(root, 1);
if (IS_ERR(trans)) {
btrfs_end_write_no_snapshotting(root);
btrfs_drew_write_unlock(&root->snapshot_lock);
return PTR_ERR(trans);
}
@ -4743,7 +4743,7 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr)
btrfs_inode_safe_disk_i_size_write(inode, 0);
pagecache_isize_extended(inode, oldsize, newsize);
ret = btrfs_update_inode(trans, root, inode);
btrfs_end_write_no_snapshotting(root);
btrfs_drew_write_unlock(&root->snapshot_lock);
btrfs_end_transaction(trans);
} else {

10
fs/btrfs/ioctl.c
View File

@ -791,11 +791,7 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir,
* possible. This is to avoid later writeback (running dealloc) to
* fallback to COW mode and unexpectedly fail with ENOSPC.
*/
atomic_inc(&root->will_be_snapshotted);
smp_mb__after_atomic();
/* wait for no snapshot writes */
wait_event(root->subv_writers->wait,
percpu_counter_sum(&root->subv_writers->counter) == 0);
btrfs_drew_read_lock(&root->snapshot_lock);
ret = btrfs_start_delalloc_snapshot(root);
if (ret)
@ -876,8 +872,8 @@ fail:
dec_and_free:
if (snapshot_force_cow)
atomic_dec(&root->snapshot_force_cow);
if (atomic_dec_and_test(&root->will_be_snapshotted))
wake_up_var(&root->will_be_snapshotted);
btrfs_drew_read_unlock(&root->snapshot_lock);
free_pending:
kfree(pending_snapshot->root_item);
btrfs_free_path(pending_snapshot->path);