hollalinux
/
linux-sg2042
mirror of https://github.com/sophgo/linux-riscv.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Merge git://git.kernel.org/pub/scm/linux/kernel/git/mason/btrfs-unstable 

* git://git.kernel.org/pub/scm/linux/kernel/git/mason/btrfs-unstable:
  Btrfs: fix file clone ioctl for bookend extents
  Btrfs: fix uninit compiler warning in cow_file_range_nocow
  Btrfs: constify dentry_operations
  Btrfs: optimize back reference update during btrfs_drop_snapshot
  Btrfs: remove negative dentry when deleting subvolumne
  Btrfs: optimize fsync for the single writer case
  Btrfs: async delalloc flushing under space pressure
  Btrfs: release delalloc reservations on extent item insertion
  Btrfs: delay clearing EXTENT_DELALLOC for compressed extents
  Btrfs: cleanup extent_clear_unlock_delalloc flags
  Btrfs: fix possible softlockup in the allocator
  Btrfs: fix deadlock on async thread startup
This commit is contained in:
Linus Torvalds 2009-10-11 11:23:13 -07:00
parent d43c36dc6b ac6889cbb2
commit 474a503d4b
14 changed files with 447 additions and 157 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

81
fs/btrfs/async-thread.c
View File

@ -63,6 +63,51 @@ struct btrfs_worker_thread {
int idle;
};
/*
* btrfs_start_workers uses kthread_run, which can block waiting for memory
* for a very long time. It will actually throttle on page writeback,
* and so it may not make progress until after our btrfs worker threads
* process all of the pending work structs in their queue
*
* This means we can't use btrfs_start_workers from inside a btrfs worker
* thread that is used as part of cleaning dirty memory, which pretty much
* involves all of the worker threads.
*
* Instead we have a helper queue who never has more than one thread
* where we scheduler thread start operations. This worker_start struct
* is used to contain the work and hold a pointer to the queue that needs
* another worker.
*/
struct worker_start {
struct btrfs_work work;
struct btrfs_workers *queue;
};
static void start_new_worker_func(struct btrfs_work *work)
{
struct worker_start *start;
start = container_of(work, struct worker_start, work);
btrfs_start_workers(start->queue, 1);
kfree(start);
}
static int start_new_worker(struct btrfs_workers *queue)
{
struct worker_start *start;
int ret;
start = kzalloc(sizeof(*start), GFP_NOFS);
if (!start)
return -ENOMEM;
start->work.func = start_new_worker_func;
start->queue = queue;
ret = btrfs_queue_worker(queue->atomic_worker_start, &start->work);
if (ret)
kfree(start);
return ret;
}
/*
* helper function to move a thread onto the idle list after it
* has finished some requests.
@ -118,11 +163,13 @@ static void check_pending_worker_creates(struct btrfs_worker_thread *worker)
goto out;
workers->atomic_start_pending = 0;
if (workers->num_workers >= workers->max_workers)
if (workers->num_workers + workers->num_workers_starting >=
workers->max_workers)
goto out;
workers->num_workers_starting += 1;
spin_unlock_irqrestore(&workers->lock, flags);
btrfs_start_workers(workers, 1);
start_new_worker(workers);
return;
out:
@ -390,9 +437,11 @@ int btrfs_stop_workers(struct btrfs_workers *workers)
/*
* simple init on struct btrfs_workers
*/
void btrfs_init_workers(struct btrfs_workers *workers, char *name, int max)
void btrfs_init_workers(struct btrfs_workers *workers, char *name, int max,
struct btrfs_workers *async_helper)
{
workers->num_workers = 0;
workers->num_workers_starting = 0;
INIT_LIST_HEAD(&workers->worker_list);
INIT_LIST_HEAD(&workers->idle_list);
INIT_LIST_HEAD(&workers->order_list);
@ -404,14 +453,15 @@ void btrfs_init_workers(struct btrfs_workers *workers, char *name, int max)
workers->name = name;
workers->ordered = 0;
workers->atomic_start_pending = 0;
workers->atomic_worker_start = 0;
workers->atomic_worker_start = async_helper;
}
/*
* starts new worker threads. This does not enforce the max worker
* count in case you need to temporarily go past it.
*/
int btrfs_start_workers(struct btrfs_workers *workers, int num_workers)
static int __btrfs_start_workers(struct btrfs_workers *workers,
int num_workers)
{
struct btrfs_worker_thread *worker;
int ret = 0;
@ -444,6 +494,8 @@ int btrfs_start_workers(struct btrfs_workers *workers, int num_workers)
list_add_tail(&worker->worker_list, &workers->idle_list);
worker->idle = 1;
workers->num_workers++;
workers->num_workers_starting--;
WARN_ON(workers->num_workers_starting < 0);
spin_unlock_irq(&workers->lock);
}
return 0;
@ -452,6 +504,14 @@ fail:
return ret;
}
int btrfs_start_workers(struct btrfs_workers *workers, int num_workers)
{
spin_lock_irq(&workers->lock);
workers->num_workers_starting += num_workers;
spin_unlock_irq(&workers->lock);
return __btrfs_start_workers(workers, num_workers);
}
/*
* run through the list and find a worker thread that doesn't have a lot
* to do right now. This can return null if we aren't yet at the thread
@ -461,7 +521,10 @@ static struct btrfs_worker_thread *next_worker(struct btrfs_workers *workers)
{
struct btrfs_worker_thread *worker;
struct list_head *next;
int enforce_min = workers->num_workers < workers->max_workers;
int enforce_min;
enforce_min = (workers->num_workers + workers->num_workers_starting) <
workers->max_workers;
/*
* if we find an idle thread, don't move it to the end of the
@ -509,15 +572,17 @@ again:
worker = next_worker(workers);
if (!worker) {
if (workers->num_workers >= workers->max_workers) {
if (workers->num_workers + workers->num_workers_starting >=
workers->max_workers) {
goto fallback;
} else if (workers->atomic_worker_start) {
workers->atomic_start_pending = 1;
goto fallback;
} else {
workers->num_workers_starting++;
spin_unlock_irqrestore(&workers->lock, flags);
/* we're below the limit, start another worker */
btrfs_start_workers(workers, 1);
__btrfs_start_workers(workers, 1);
goto again;
}
}

10
fs/btrfs/async-thread.h
View File

@ -64,6 +64,8 @@ struct btrfs_workers {
/* current number of running workers */
int num_workers;
int num_workers_starting;
/* max number of workers allowed. changed by btrfs_start_workers */
int max_workers;
@ -78,9 +80,10 @@ struct btrfs_workers {
/*
* are we allowed to sleep while starting workers or are we required
* to start them at a later time?
* to start them at a later time? If we can't sleep, this indicates
* which queue we need to use to schedule thread creation.
*/
int atomic_worker_start;
struct btrfs_workers *atomic_worker_start;
/* list with all the work threads. The workers on the idle thread
* may be actively servicing jobs, but they haven't yet hit the
@ -109,7 +112,8 @@ struct btrfs_workers {
int btrfs_queue_worker(struct btrfs_workers *workers, struct btrfs_work *work);
int btrfs_start_workers(struct btrfs_workers *workers, int num_workers);
int btrfs_stop_workers(struct btrfs_workers *workers);
void btrfs_init_workers(struct btrfs_workers *workers, char *name, int max);
void btrfs_init_workers(struct btrfs_workers *workers, char *name, int max,
struct btrfs_workers *async_starter);
int btrfs_requeue_work(struct btrfs_work *work);
void btrfs_set_work_high_prio(struct btrfs_work *work);
#endif

12
fs/btrfs/btrfs_inode.h
View File

@ -128,12 +128,14 @@ struct btrfs_inode {
u64 last_unlink_trans;
/*
* These two counters are for delalloc metadata reservations. We keep
* track of how many extents we've accounted for vs how many extents we
* have.
* Counters to keep track of the number of extent item's we may use due
* to delalloc and such. outstanding_extents is the number of extent
* items we think we'll end up using, and reserved_extents is the number
* of extent items we've reserved metadata for.
*/
int delalloc_reserved_extents;
int delalloc_extents;
spinlock_t accounting_lock;
int reserved_extents;
int outstanding_extents;
/*
* ordered_data_close is set by truncate when a file that used

15
fs/btrfs/ctree.h
View File

@ -691,14 +691,17 @@ struct btrfs_space_info {
struct list_head list;
/* for controlling how we free up space for allocations */
wait_queue_head_t allocate_wait;
wait_queue_head_t flush_wait;
int allocating_chunk;
int flushing;
/* for block groups in our same type */
struct list_head block_groups;
spinlock_t lock;
struct rw_semaphore groups_sem;
atomic_t caching_threads;
int allocating_chunk;
wait_queue_head_t wait;
};
/*
@ -907,6 +910,7 @@ struct btrfs_fs_info {
* A third pool does submit_bio to avoid deadlocking with the other
* two
*/
struct btrfs_workers generic_worker;
struct btrfs_workers workers;
struct btrfs_workers delalloc_workers;
struct btrfs_workers endio_workers;
@ -914,6 +918,7 @@ struct btrfs_fs_info {
struct btrfs_workers endio_meta_write_workers;
struct btrfs_workers endio_write_workers;
struct btrfs_workers submit_workers;
struct btrfs_workers enospc_workers;
/*
* fixup workers take dirty pages that didn't properly go through
* the cow mechanism and make them safe to write. It happens
@ -1005,6 +1010,8 @@ struct btrfs_root {
atomic_t log_commit[2];
unsigned long log_transid;
unsigned long log_batch;
pid_t log_start_pid;
bool log_multiple_pids;
u64 objectid;
u64 last_trans;
@ -2323,7 +2330,7 @@ int btrfs_orphan_del(struct btrfs_trans_handle *trans, struct inode *inode);
void btrfs_orphan_cleanup(struct btrfs_root *root);
int btrfs_cont_expand(struct inode *inode, loff_t size);
int btrfs_invalidate_inodes(struct btrfs_root *root);
extern struct dentry_operations btrfs_dentry_operations;
extern const struct dentry_operations btrfs_dentry_operations;
/* ioctl.c */
long btrfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg);

48
fs/btrfs/disk-io.c
View File

@ -1746,21 +1746,25 @@ struct btrfs_root *open_ctree(struct super_block *sb,
err = -EINVAL;
goto fail_iput;
}
printk("thread pool is %d\n", fs_info->thread_pool_size);
/*
* we need to start all the end_io workers up front because the
* queue work function gets called at interrupt time, and so it
* cannot dynamically grow.
*/
btrfs_init_workers(&fs_info->generic_worker,
"genwork", 1, NULL);
btrfs_init_workers(&fs_info->workers, "worker",
fs_info->thread_pool_size);
fs_info->thread_pool_size,
&fs_info->generic_worker);
btrfs_init_workers(&fs_info->delalloc_workers, "delalloc",
fs_info->thread_pool_size);
fs_info->thread_pool_size,
&fs_info->generic_worker);
btrfs_init_workers(&fs_info->submit_workers, "submit",
min_t(u64, fs_devices->num_devices,
fs_info->thread_pool_size));
fs_info->thread_pool_size),
&fs_info->generic_worker);
btrfs_init_workers(&fs_info->enospc_workers, "enospc",
fs_info->thread_pool_size,
&fs_info->generic_worker);
/* a higher idle thresh on the submit workers makes it much more
* likely that bios will be send down in a sane order to the
@ -1774,15 +1778,20 @@ printk("thread pool is %d\n", fs_info->thread_pool_size);
fs_info->delalloc_workers.idle_thresh = 2;
fs_info->delalloc_workers.ordered = 1;
btrfs_init_workers(&fs_info->fixup_workers, "fixup", 1);
btrfs_init_workers(&fs_info->fixup_workers, "fixup", 1,
&fs_info->generic_worker);
btrfs_init_workers(&fs_info->endio_workers, "endio",
fs_info->thread_pool_size);
fs_info->thread_pool_size,
&fs_info->generic_worker);
btrfs_init_workers(&fs_info->endio_meta_workers, "endio-meta",
fs_info->thread_pool_size);
fs_info->thread_pool_size,
&fs_info->generic_worker);
btrfs_init_workers(&fs_info->endio_meta_write_workers,
"endio-meta-write", fs_info->thread_pool_size);
"endio-meta-write", fs_info->thread_pool_size,
&fs_info->generic_worker);
btrfs_init_workers(&fs_info->endio_write_workers, "endio-write",
fs_info->thread_pool_size);
fs_info->thread_pool_size,
&fs_info->generic_worker);
/*
* endios are largely parallel and should have a very
@ -1794,12 +1803,8 @@ printk("thread pool is %d\n", fs_info->thread_pool_size);
fs_info->endio_write_workers.idle_thresh = 2;
fs_info->endio_meta_write_workers.idle_thresh = 2;
fs_info->endio_workers.atomic_worker_start = 1;
fs_info->endio_meta_workers.atomic_worker_start = 1;
fs_info->endio_write_workers.atomic_worker_start = 1;
fs_info->endio_meta_write_workers.atomic_worker_start = 1;
btrfs_start_workers(&fs_info->workers, 1);
btrfs_start_workers(&fs_info->generic_worker, 1);
btrfs_start_workers(&fs_info->submit_workers, 1);
btrfs_start_workers(&fs_info->delalloc_workers, 1);
btrfs_start_workers(&fs_info->fixup_workers, 1);
@ -1807,6 +1812,7 @@ printk("thread pool is %d\n", fs_info->thread_pool_size);
btrfs_start_workers(&fs_info->endio_meta_workers, 1);
btrfs_start_workers(&fs_info->endio_meta_write_workers, 1);
btrfs_start_workers(&fs_info->endio_write_workers, 1);
btrfs_start_workers(&fs_info->enospc_workers, 1);
fs_info->bdi.ra_pages *= btrfs_super_num_devices(disk_super);
fs_info->bdi.ra_pages = max(fs_info->bdi.ra_pages,
@ -2012,6 +2018,7 @@ fail_chunk_root:
free_extent_buffer(chunk_root->node);
free_extent_buffer(chunk_root->commit_root);
fail_sb_buffer:
btrfs_stop_workers(&fs_info->generic_worker);
btrfs_stop_workers(&fs_info->fixup_workers);
btrfs_stop_workers(&fs_info->delalloc_workers);
btrfs_stop_workers(&fs_info->workers);
@ -2020,6 +2027,7 @@ fail_sb_buffer:
btrfs_stop_workers(&fs_info->endio_meta_write_workers);
btrfs_stop_workers(&fs_info->endio_write_workers);
btrfs_stop_workers(&fs_info->submit_workers);
btrfs_stop_workers(&fs_info->enospc_workers);
fail_iput:
invalidate_inode_pages2(fs_info->btree_inode->i_mapping);
iput(fs_info->btree_inode);
@ -2437,6 +2445,7 @@ int close_ctree(struct btrfs_root *root)
iput(fs_info->btree_inode);
btrfs_stop_workers(&fs_info->generic_worker);
btrfs_stop_workers(&fs_info->fixup_workers);
btrfs_stop_workers(&fs_info->delalloc_workers);
btrfs_stop_workers(&fs_info->workers);
@ -2445,6 +2454,7 @@ int close_ctree(struct btrfs_root *root)
btrfs_stop_workers(&fs_info->endio_meta_write_workers);
btrfs_stop_workers(&fs_info->endio_write_workers);
btrfs_stop_workers(&fs_info->submit_workers);
btrfs_stop_workers(&fs_info->enospc_workers);
btrfs_close_devices(fs_info->fs_devices);
btrfs_mapping_tree_free(&fs_info->mapping_tree);

203
fs/btrfs/extent-tree.c
View File

@ -2824,14 +2824,17 @@ int btrfs_unreserve_metadata_for_delalloc(struct btrfs_root *root,
num_items);
spin_lock(&meta_sinfo->lock);
if (BTRFS_I(inode)->delalloc_reserved_extents <=
BTRFS_I(inode)->delalloc_extents) {
spin_lock(&BTRFS_I(inode)->accounting_lock);
if (BTRFS_I(inode)->reserved_extents <=
BTRFS_I(inode)->outstanding_extents) {
spin_unlock(&BTRFS_I(inode)->accounting_lock);
spin_unlock(&meta_sinfo->lock);
return 0;
}
spin_unlock(&BTRFS_I(inode)->accounting_lock);
BTRFS_I(inode)->delalloc_reserved_extents--;
BUG_ON(BTRFS_I(inode)->delalloc_reserved_extents < 0);
BTRFS_I(inode)->reserved_extents--;
BUG_ON(BTRFS_I(inode)->reserved_extents < 0);
if (meta_sinfo->bytes_delalloc < num_bytes) {
bug = true;
@ -2864,6 +2867,107 @@ static void check_force_delalloc(struct btrfs_space_info *meta_sinfo)
meta_sinfo->force_delalloc = 0;
}
struct async_flush {
struct btrfs_root *root;
struct btrfs_space_info *info;
struct btrfs_work work;
};
static noinline void flush_delalloc_async(struct btrfs_work *work)
{
struct async_flush *async;
struct btrfs_root *root;
struct btrfs_space_info *info;
async = container_of(work, struct async_flush, work);
root = async->root;
info = async->info;
btrfs_start_delalloc_inodes(root);
wake_up(&info->flush_wait);
btrfs_wait_ordered_extents(root, 0);
spin_lock(&info->lock);
info->flushing = 0;
spin_unlock(&info->lock);
wake_up(&info->flush_wait);
kfree(async);
}
static void wait_on_flush(struct btrfs_space_info *info)
{
DEFINE_WAIT(wait);
u64 used;
while (1) {
prepare_to_wait(&info->flush_wait, &wait,
TASK_UNINTERRUPTIBLE);
spin_lock(&info->lock);
if (!info->flushing) {
spin_unlock(&info->lock);
break;
}
used = info->bytes_used + info->bytes_reserved +
info->bytes_pinned + info->bytes_readonly +
info->bytes_super + info->bytes_root +
info->bytes_may_use + info->bytes_delalloc;
if (used < info->total_bytes) {
spin_unlock(&info->lock);
break;
}
spin_unlock(&info->lock);
schedule();
}
finish_wait(&info->flush_wait, &wait);
}
static void flush_delalloc(struct btrfs_root *root,
struct btrfs_space_info *info)
{
struct async_flush *async;
bool wait = false;
spin_lock(&info->lock);
if (!info->flushing) {
info->flushing = 1;
init_waitqueue_head(&info->flush_wait);
} else {
wait = true;
}
spin_unlock(&info->lock);
if (wait) {
wait_on_flush(info);
return;
}
async = kzalloc(sizeof(*async), GFP_NOFS);
if (!async)
goto flush;
async->root = root;
async->info = info;
async->work.func = flush_delalloc_async;
btrfs_queue_worker(&root->fs_info->enospc_workers,
&async->work);
wait_on_flush(info);
return;
flush:
btrfs_start_delalloc_inodes(root);
btrfs_wait_ordered_extents(root, 0);
spin_lock(&info->lock);
info->flushing = 0;
spin_unlock(&info->lock);
wake_up(&info->flush_wait);
}
static int maybe_allocate_chunk(struct btrfs_root *root,
struct btrfs_space_info *info)
{
@ -2894,7 +2998,7 @@ static int maybe_allocate_chunk(struct btrfs_root *root,
if (!info->allocating_chunk) {
info->force_alloc = 1;
info->allocating_chunk = 1;
init_waitqueue_head(&info->wait);
init_waitqueue_head(&info->allocate_wait);
} else {
wait = true;
}
@ -2902,7 +3006,7 @@ static int maybe_allocate_chunk(struct btrfs_root *root,
spin_unlock(&info->lock);
if (wait) {
wait_event(info->wait,
wait_event(info->allocate_wait,
!info->allocating_chunk);
return 1;
}
@ -2923,7 +3027,7 @@ out:
spin_lock(&info->lock);
info->allocating_chunk = 0;
spin_unlock(&info->lock);
wake_up(&info->wait);
wake_up(&info->allocate_wait);
if (ret)
return 0;
@ -2981,21 +3085,20 @@ again:
filemap_flush(inode->i_mapping);
goto again;
} else if (flushed == 3) {
btrfs_start_delalloc_inodes(root);
btrfs_wait_ordered_extents(root, 0);
flush_delalloc(root, meta_sinfo);
goto again;
}
spin_lock(&meta_sinfo->lock);
meta_sinfo->bytes_delalloc -= num_bytes;
spin_unlock(&meta_sinfo->lock);
printk(KERN_ERR "enospc, has %d, reserved %d\n",
BTRFS_I(inode)->delalloc_extents,
BTRFS_I(inode)->delalloc_reserved_extents);
BTRFS_I(inode)->outstanding_extents,
BTRFS_I(inode)->reserved_extents);
dump_space_info(meta_sinfo, 0, 0);
return -ENOSPC;
}
BTRFS_I(inode)->delalloc_reserved_extents++;
BTRFS_I(inode)->reserved_extents++;
check_force_delalloc(meta_sinfo);
spin_unlock(&meta_sinfo->lock);
@ -3094,8 +3197,7 @@ again:
}
if (retries == 2) {
btrfs_start_delalloc_inodes(root);
btrfs_wait_ordered_extents(root, 0);
flush_delalloc(root, meta_sinfo);
goto again;
}
spin_lock(&meta_sinfo->lock);
@ -4029,6 +4131,7 @@ static noinline int find_free_extent(struct btrfs_trans_handle *trans,
int loop = 0;
bool found_uncached_bg = false;
bool failed_cluster_refill = false;
bool failed_alloc = false;
WARN_ON(num_bytes < root->sectorsize);
btrfs_set_key_type(ins, BTRFS_EXTENT_ITEM_KEY);
@ -4233,14 +4336,23 @@ refill_cluster:
offset = btrfs_find_space_for_alloc(block_group, search_start,
num_bytes, empty_size);
if (!offset && (cached || (!cached &&
loop == LOOP_CACHING_NOWAIT))) {
goto loop;
} else if (!offset && (!cached &&
loop > LOOP_CACHING_NOWAIT)) {
/*
* If we didn't find a chunk, and we haven't failed on this
* block group before, and this block group is in the middle of
* caching and we are ok with waiting, then go ahead and wait
* for progress to be made, and set failed_alloc to true.
*
* If failed_alloc is true then we've already waited on this
* block group once and should move on to the next block group.
*/
if (!offset && !failed_alloc && !cached &&
loop > LOOP_CACHING_NOWAIT) {
wait_block_group_cache_progress(block_group,
num_bytes + empty_size);
failed_alloc = true;
goto have_block_group;
} else if (!offset) {
goto loop;
}
checks:
search_start = stripe_align(root, offset);
@ -4288,6 +4400,7 @@ checks:
break;
loop:
failed_cluster_refill = false;
failed_alloc = false;
btrfs_put_block_group(block_group);
}
up_read(&space_info->groups_sem);
@ -4799,6 +4912,7 @@ static noinline void reada_walk_down(struct btrfs_trans_handle *trans,
u64 bytenr;
u64 generation;
u64 refs;
u64 flags;
u64 last = 0;
u32 nritems;
u32 blocksize;
@ -4836,15 +4950,19 @@ static noinline void reada_walk_down(struct btrfs_trans_handle *trans,
generation <= root->root_key.offset)
continue;
if (wc->stage == DROP_REFERENCE) {
ret = btrfs_lookup_extent_info(trans, root,
bytenr, blocksize,
&refs, NULL);
/* We don't lock the tree block, it's OK to be racy here */
ret = btrfs_lookup_extent_info(trans, root, bytenr, blocksize,
&refs, &flags);
BUG_ON(ret);
BUG_ON(refs == 0);
if (wc->stage == DROP_REFERENCE) {
if (refs == 1)
goto reada;
if (wc->level == 1 &&
(flags & BTRFS_BLOCK_FLAG_FULL_BACKREF))
continue;
if (!wc->update_ref ||
generation <= root->root_key.offset)
continue;
@ -4853,6 +4971,10 @@ static noinline void reada_walk_down(struct btrfs_trans_handle *trans,
&wc->update_progress);
if (ret < 0)
continue;
} else {
if (wc->level == 1 &&
(flags & BTRFS_BLOCK_FLAG_FULL_BACKREF))
continue;
}
reada:
ret = readahead_tree_block(root, bytenr, blocksize,
@ -4876,7 +4998,7 @@ reada:
static noinline int walk_down_proc(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct btrfs_path *path,
struct walk_control *wc)
struct walk_control *wc, int lookup_info)
{
int level = wc->level;
struct extent_buffer *eb = path->nodes[level];
@ -4891,8 +5013,9 @@ static noinline int walk_down_proc(struct btrfs_trans_handle *trans,
* when reference count of tree block is 1, it won't increase
* again. once full backref flag is set, we never clear it.
*/
if ((wc->stage == DROP_REFERENCE && wc->refs[level] != 1) ||
(wc->stage == UPDATE_BACKREF && !(wc->flags[level] & flag))) {
if (lookup_info &&
((wc->stage == DROP_REFERENCE && wc->refs[level] != 1) ||
(wc->stage == UPDATE_BACKREF && !(wc->flags[level] & flag)))) {
BUG_ON(!path->locks[level]);
ret = btrfs_lookup_extent_info(trans, root,
eb->start, eb->len,
@ -4953,7 +5076,7 @@ static noinline int walk_down_proc(struct btrfs_trans_handle *trans,
static noinline int do_walk_down(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct btrfs_path *path,
struct walk_control *wc)
struct walk_control *wc, int *lookup_info)
{
u64 bytenr;
u64 generation;
@ -4973,8 +5096,10 @@ static noinline int do_walk_down(struct btrfs_trans_handle *trans,
* for the subtree
*/
if (wc->stage == UPDATE_BACKREF &&
generation <= root->root_key.offset)
generation <= root->root_key.offset) {
*lookup_info = 1;
return 1;
}
bytenr = btrfs_node_blockptr(path->nodes[level], path->slots[level]);
blocksize = btrfs_level_size(root, level - 1);
@ -4987,14 +5112,19 @@ static noinline int do_walk_down(struct btrfs_trans_handle *trans,
btrfs_tree_lock(next);
btrfs_set_lock_blocking(next);
if (wc->stage == DROP_REFERENCE) {
ret = btrfs_lookup_extent_info(trans, root, bytenr, blocksize,
&wc->refs[level - 1],
&wc->flags[level - 1]);
BUG_ON(ret);
BUG_ON(wc->refs[level - 1] == 0);
*lookup_info = 0;
if (wc->stage == DROP_REFERENCE) {
if (wc->refs[level - 1] > 1) {
if (level == 1 &&
(wc->flags[0] & BTRFS_BLOCK_FLAG_FULL_BACKREF))
goto skip;
if (!wc->update_ref ||
generation <= root->root_key.offset)
goto skip;
@ -5008,12 +5138,17 @@ static noinline int do_walk_down(struct btrfs_trans_handle *trans,
wc->stage = UPDATE_BACKREF;
wc->shared_level = level - 1;
}
} else {
if (level == 1 &&
(wc->flags[0] & BTRFS_BLOCK_FLAG_FULL_BACKREF))
goto skip;
}
if (!btrfs_buffer_uptodate(next, generation)) {
btrfs_tree_unlock(next);
free_extent_buffer(next);
next = NULL;
*lookup_info = 1;
}
if (!next) {
@ -5036,7 +5171,7 @@ static noinline int do_walk_down(struct btrfs_trans_handle *trans,
skip:
wc->refs[level - 1] = 0;
wc->flags[level - 1] = 0;
if (wc->stage == DROP_REFERENCE) {
if (wc->flags[level] & BTRFS_BLOCK_FLAG_FULL_BACKREF) {
parent = path->nodes[level]->start;
} else {
@ -5048,9 +5183,10 @@ skip:
ret = btrfs_free_extent(trans, root, bytenr, blocksize, parent,
root->root_key.objectid, level - 1, 0);
BUG_ON(ret);
}
btrfs_tree_unlock(next);
free_extent_buffer(next);
*lookup_info = 1;
return 1;
}
@ -5164,6 +5300,7 @@ static noinline int walk_down_tree(struct btrfs_trans_handle *trans,
struct walk_control *wc)
{
int level = wc->level;
int lookup_info = 1;
int ret;
while (level >= 0) {
@ -5171,14 +5308,14 @@ static noinline int walk_down_tree(struct btrfs_trans_handle *trans,
btrfs_header_nritems(path->nodes[level]))
break;
ret = walk_down_proc(trans, root, path, wc);
ret = walk_down_proc(trans, root, path, wc, lookup_info);
if (ret > 0)
break;
if (level == 0)
break;
ret = do_walk_down(trans, root, path, wc);
ret = do_walk_down(trans, root, path, wc, &lookup_info);
if (ret > 0) {
path->slots[level]++;
continue;

42
fs/btrfs/extent_io.c
View File

@ -460,7 +460,8 @@ static int clear_state_bit(struct extent_io_tree *tree,
struct extent_state *state, int bits, int wake,
int delete)
{
int ret = state->state & bits;
int bits_to_clear = bits & ~EXTENT_DO_ACCOUNTING;
int ret = state->state & bits_to_clear;
if ((bits & EXTENT_DIRTY) && (state->state & EXTENT_DIRTY)) {
u64 range = state->end - state->start + 1;
@ -468,7 +469,7 @@ static int clear_state_bit(struct extent_io_tree *tree,
tree->dirty_bytes -= range;
}
clear_state_cb(tree, state, bits);
state->state &= ~bits;
state->state &= ~bits_to_clear;
if (wake)
wake_up(&state->wq);
if (delete || state->state == 0) {
@ -956,7 +957,8 @@ int clear_extent_dirty(struct extent_io_tree *tree, u64 start, u64 end,
gfp_t mask)
{
return clear_extent_bit(tree, start, end,
EXTENT_DIRTY | EXTENT_DELALLOC, 0, 0,
EXTENT_DIRTY | EXTENT_DELALLOC |
EXTENT_DO_ACCOUNTING, 0, 0,
NULL, mask);
}
@ -1401,12 +1403,7 @@ out_failed:
int extent_clear_unlock_delalloc(struct inode *inode,
struct extent_io_tree *tree,
u64 start, u64 end, struct page *locked_page,
int unlock_pages,
int clear_unlock,
int clear_delalloc, int clear_dirty,
int set_writeback,
int end_writeback,
int set_private2)
unsigned long op)
{
int ret;
struct page *pages[16];
@ -1416,17 +1413,21 @@ int extent_clear_unlock_delalloc(struct inode *inode,
int i;
int clear_bits = 0;
if (clear_unlock)
if (op & EXTENT_CLEAR_UNLOCK)
clear_bits |= EXTENT_LOCKED;
if (clear_dirty)
if (op & EXTENT_CLEAR_DIRTY)
clear_bits |= EXTENT_DIRTY;
if (clear_delalloc)
if (op & EXTENT_CLEAR_DELALLOC)
clear_bits |= EXTENT_DELALLOC;
if (op & EXTENT_CLEAR_ACCOUNTING)
clear_bits |= EXTENT_DO_ACCOUNTING;
clear_extent_bit(tree, start, end, clear_bits, 1, 0, NULL, GFP_NOFS);
if (!(unlock_pages || clear_dirty || set_writeback || end_writeback ||
set_private2))
if (!(op & (EXTENT_CLEAR_UNLOCK_PAGE | EXTENT_CLEAR_DIRTY |
EXTENT_SET_WRITEBACK | EXTENT_END_WRITEBACK |
EXTENT_SET_PRIVATE2)))
return 0;
while (nr_pages > 0) {
@ -1435,20 +1436,20 @@ int extent_clear_unlock_delalloc(struct inode *inode,
nr_pages, ARRAY_SIZE(pages)), pages);
for (i = 0; i < ret; i++) {
if (set_private2)
if (op & EXTENT_SET_PRIVATE2)
SetPagePrivate2(pages[i]);
if (pages[i] == locked_page) {
page_cache_release(pages[i]);
continue;
}
if (clear_dirty)
if (op & EXTENT_CLEAR_DIRTY)
clear_page_dirty_for_io(pages[i]);
if (set_writeback)
if (op & EXTENT_SET_WRITEBACK)
set_page_writeback(pages[i]);
if (end_writeback)
if (op & EXTENT_END_WRITEBACK)
end_page_writeback(pages[i]);
if (unlock_pages)
if (op & EXTENT_CLEAR_UNLOCK_PAGE)
unlock_page(pages[i]);
page_cache_release(pages[i]);
}
@ -2714,7 +2715,8 @@ int extent_invalidatepage(struct extent_io_tree *tree,
lock_extent(tree, start, end, GFP_NOFS);
wait_on_page_writeback(page);
clear_extent_bit(tree, start, end,
EXTENT_LOCKED | EXTENT_DIRTY | EXTENT_DELALLOC,
EXTENT_LOCKED | EXTENT_DIRTY | EXTENT_DELALLOC |
EXTENT_DO_ACCOUNTING,
1, 1, NULL, GFP_NOFS);
return 0;
}

18
fs/btrfs/extent_io.h
View File

@ -15,6 +15,7 @@
#define EXTENT_BUFFER_FILLED (1 << 8)
#define EXTENT_BOUNDARY (1 << 9)
#define EXTENT_NODATASUM (1 << 10)
#define EXTENT_DO_ACCOUNTING (1 << 11)
#define EXTENT_IOBITS (EXTENT_LOCKED | EXTENT_WRITEBACK)
/* flags for bio submission */
@ -25,6 +26,16 @@
#define EXTENT_BUFFER_BLOCKING 1
#define EXTENT_BUFFER_DIRTY 2
/* these are flags for extent_clear_unlock_delalloc */
#define EXTENT_CLEAR_UNLOCK_PAGE 0x1
#define EXTENT_CLEAR_UNLOCK 0x2
#define EXTENT_CLEAR_DELALLOC 0x4
#define EXTENT_CLEAR_DIRTY 0x8
#define EXTENT_SET_WRITEBACK 0x10
#define EXTENT_END_WRITEBACK 0x20
#define EXTENT_SET_PRIVATE2 0x40
#define EXTENT_CLEAR_ACCOUNTING 0x80
/*
* page->private values. Every page that is controlled by the extent
* map has page->private set to one.
@ -288,10 +299,5 @@ int extent_range_uptodate(struct extent_io_tree *tree,
int extent_clear_unlock_delalloc(struct inode *inode,
struct extent_io_tree *tree,
u64 start, u64 end, struct page *locked_page,
int unlock_page,
int clear_unlock,
int clear_delalloc, int clear_dirty,
int set_writeback,
int end_writeback,
int set_private2);
unsigned long op);
#endif

3
fs/btrfs/file.c
View File

@ -878,7 +878,8 @@ again:
btrfs_put_ordered_extent(ordered);
clear_extent_bits(&BTRFS_I(inode)->io_tree, start_pos,
last_pos - 1, EXTENT_DIRTY | EXTENT_DELALLOC,
last_pos - 1, EXTENT_DIRTY | EXTENT_DELALLOC |
EXTENT_DO_ACCOUNTING,
GFP_NOFS);
unlock_extent(&BTRFS_I(inode)->io_tree,
start_pos, last_pos - 1, GFP_NOFS);

89
fs/btrfs/inode.c
View File

@ -425,8 +425,11 @@ again:
*/
extent_clear_unlock_delalloc(inode,
&BTRFS_I(inode)->io_tree,
start, end, NULL, 1, 0,
0, 1, 1, 1, 0);
start, end, NULL,
EXTENT_CLEAR_UNLOCK_PAGE | EXTENT_CLEAR_DIRTY |
EXTENT_CLEAR_DELALLOC |
EXTENT_CLEAR_ACCOUNTING |
EXTENT_SET_WRITEBACK | EXTENT_END_WRITEBACK);
ret = 0;
goto free_pages_out;
}
@ -641,7 +644,10 @@ static noinline int submit_compressed_extents(struct inode *inode,
async_extent->start,
async_extent->start +
async_extent->ram_size - 1,
NULL, 1, 1, 0, 1, 1, 0, 0);
NULL, EXTENT_CLEAR_UNLOCK_PAGE |
EXTENT_CLEAR_UNLOCK |
EXTENT_CLEAR_DELALLOC |
EXTENT_CLEAR_DIRTY | EXTENT_SET_WRITEBACK);
ret = btrfs_submit_compressed_write(inode,
async_extent->start,
@ -713,8 +719,14 @@ static noinline int cow_file_range(struct inode *inode,
if (ret == 0) {
extent_clear_unlock_delalloc(inode,
&BTRFS_I(inode)->io_tree,
start, end, NULL, 1, 1,
1, 1, 1, 1, 0);
start, end, NULL,
EXTENT_CLEAR_UNLOCK_PAGE |
EXTENT_CLEAR_UNLOCK |
EXTENT_CLEAR_DELALLOC |
EXTENT_CLEAR_ACCOUNTING |
EXTENT_CLEAR_DIRTY |
EXTENT_SET_WRITEBACK |
EXTENT_END_WRITEBACK);
*nr_written = *nr_written +
(end - start + PAGE_CACHE_SIZE) / PAGE_CACHE_SIZE;
*page_started = 1;
@ -738,6 +750,8 @@ static noinline int cow_file_range(struct inode *inode,
btrfs_drop_extent_cache(inode, start, start + num_bytes - 1, 0);
while (disk_num_bytes > 0) {
unsigned long op;
cur_alloc_size = min(disk_num_bytes, root->fs_info->max_extent);
ret = btrfs_reserve_extent(trans, root, cur_alloc_size,
root->sectorsize, 0, alloc_hint,
@ -789,10 +803,13 @@ static noinline int cow_file_range(struct inode *inode,
* Do set the Private2 bit so we know this page was properly
* setup for writepage
*/
op = unlock ? EXTENT_CLEAR_UNLOCK_PAGE : 0;
op |= EXTENT_CLEAR_UNLOCK | EXTENT_CLEAR_DELALLOC |
EXTENT_SET_PRIVATE2;
extent_clear_unlock_delalloc(inode, &BTRFS_I(inode)->io_tree,
start, start + ram_size - 1,
locked_page, unlock, 1,
1, 0, 0, 0, 1);
locked_page, op);
disk_num_bytes -= cur_alloc_size;
num_bytes -= cur_alloc_size;
alloc_hint = ins.objectid + ins.offset;
@ -864,8 +881,8 @@ static int cow_file_range_async(struct inode *inode, struct page *locked_page,
u64 cur_end;
int limit = 10 * 1024 * 1042;
clear_extent_bit(&BTRFS_I(inode)->io_tree, start, end, EXTENT_LOCKED |
EXTENT_DELALLOC, 1, 0, NULL, GFP_NOFS);
clear_extent_bit(&BTRFS_I(inode)->io_tree, start, end, EXTENT_LOCKED,
1, 0, NULL, GFP_NOFS);
while (start < end) {
async_cow = kmalloc(sizeof(*async_cow), GFP_NOFS);
async_cow->inode = inode;
@ -1006,6 +1023,7 @@ next_slot:
if (found_key.offset > cur_offset) {
extent_end = found_key.offset;
extent_type = 0;
goto out_check;
}
@ -1113,7 +1131,9 @@ out_check:
extent_clear_unlock_delalloc(inode, &BTRFS_I(inode)->io_tree,
cur_offset, cur_offset + num_bytes - 1,
locked_page, 1, 1, 1, 0, 0, 0, 1);
locked_page, EXTENT_CLEAR_UNLOCK_PAGE |
EXTENT_CLEAR_UNLOCK | EXTENT_CLEAR_DELALLOC |
EXTENT_SET_PRIVATE2);
cur_offset = extent_end;
if (cur_offset > end)
break;
@ -1178,15 +1198,17 @@ static int btrfs_split_extent_hook(struct inode *inode,
root->fs_info->max_extent);
/*
* if we break a large extent up then leave delalloc_extents be,
* since we've already accounted for the large extent.
* if we break a large extent up then leave oustanding_extents
* be, since we've already accounted for the large extent.
*/
if (div64_u64(new_size + root->fs_info->max_extent - 1,
root->fs_info->max_extent) < num_extents)
return 0;
}
BTRFS_I(inode)->delalloc_extents++;
spin_lock(&BTRFS_I(inode)->accounting_lock);
BTRFS_I(inode)->outstanding_extents++;
spin_unlock(&BTRFS_I(inode)->accounting_lock);
return 0;
}
@ -1217,7 +1239,9 @@ static int btrfs_merge_extent_hook(struct inode *inode,
/* we're not bigger than the max, unreserve the space and go */
if (new_size <= root->fs_info->max_extent) {
BTRFS_I(inode)->delalloc_extents--;
spin_lock(&BTRFS_I(inode)->accounting_lock);
BTRFS_I(inode)->outstanding_extents--;
spin_unlock(&BTRFS_I(inode)->accounting_lock);
return 0;
}
@ -1231,7 +1255,9 @@ static int btrfs_merge_extent_hook(struct inode *inode,
root->fs_info->max_extent) > num_extents)
return 0;
BTRFS_I(inode)->delalloc_extents--;
spin_lock(&BTRFS_I(inode)->accounting_lock);
BTRFS_I(inode)->outstanding_extents--;
spin_unlock(&BTRFS_I(inode)->accounting_lock);
return 0;
}
@ -1253,7 +1279,9 @@ static int btrfs_set_bit_hook(struct inode *inode, u64 start, u64 end,
if (!(old & EXTENT_DELALLOC) && (bits & EXTENT_DELALLOC)) {
struct btrfs_root *root = BTRFS_I(inode)->root;
BTRFS_I(inode)->delalloc_extents++;
spin_lock(&BTRFS_I(inode)->accounting_lock);
BTRFS_I(inode)->outstanding_extents++;
spin_unlock(&BTRFS_I(inode)->accounting_lock);
btrfs_delalloc_reserve_space(root, inode, end - start + 1);
spin_lock(&root->fs_info->delalloc_lock);
BTRFS_I(inode)->delalloc_bytes += end - start + 1;
@ -1281,8 +1309,12 @@ static int btrfs_clear_bit_hook(struct inode *inode,
if ((state->state & EXTENT_DELALLOC) && (bits & EXTENT_DELALLOC)) {
struct btrfs_root *root = BTRFS_I(inode)->root;
BTRFS_I(inode)->delalloc_extents--;
if (bits & EXTENT_DO_ACCOUNTING) {
spin_lock(&BTRFS_I(inode)->accounting_lock);
BTRFS_I(inode)->outstanding_extents--;
spin_unlock(&BTRFS_I(inode)->accounting_lock);
btrfs_unreserve_metadata_for_delalloc(root, inode, 1);
}
spin_lock(&root->fs_info->delalloc_lock);
if (state->end - state->start + 1 >
@ -3598,12 +3630,14 @@ static int btrfs_dentry_delete(struct dentry *dentry)
{
struct btrfs_root *root;
if (!dentry->d_inode)
return 0;
if (!dentry->d_inode && !IS_ROOT(dentry))
dentry = dentry->d_parent;
if (dentry->d_inode) {
root = BTRFS_I(dentry->d_inode)->root;
if (btrfs_root_refs(&root->root_item) == 0)
return 1;
}
return 0;
}
@ -4808,7 +4842,8 @@ static void btrfs_invalidatepage(struct page *page, unsigned long offset)
*/
clear_extent_bit(tree, page_start, page_end,
EXTENT_DIRTY | EXTENT_DELALLOC |
EXTENT_LOCKED, 1, 0, NULL, GFP_NOFS);
EXTENT_LOCKED | EXTENT_DO_ACCOUNTING, 1, 0,
NULL, GFP_NOFS);
/*
* whoever cleared the private bit is responsible
* for the finish_ordered_io
@ -4821,8 +4856,8 @@ static void btrfs_invalidatepage(struct page *page, unsigned long offset)
lock_extent(tree, page_start, page_end, GFP_NOFS);
}
clear_extent_bit(tree, page_start, page_end,
EXTENT_LOCKED | EXTENT_DIRTY | EXTENT_DELALLOC,
1, 1, NULL, GFP_NOFS);
EXTENT_LOCKED | EXTENT_DIRTY | EXTENT_DELALLOC |
EXTENT_DO_ACCOUNTING, 1, 1, NULL, GFP_NOFS);
__btrfs_releasepage(page, GFP_NOFS);
ClearPageChecked(page);
@ -4917,7 +4952,8 @@ again:
* prepare_pages in the normal write path.
*/
clear_extent_bits(&BTRFS_I(inode)->io_tree, page_start, page_end,
EXTENT_DIRTY | EXTENT_DELALLOC, GFP_NOFS);
EXTENT_DIRTY | EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING,
GFP_NOFS);
ret = btrfs_set_extent_delalloc(inode, page_start, page_end);
if (ret) {
@ -5065,8 +5101,9 @@ struct inode *btrfs_alloc_inode(struct super_block *sb)
return NULL;
ei->last_trans = 0;
ei->logged_trans = 0;
ei->delalloc_extents = 0;
ei->delalloc_reserved_extents = 0;
ei->outstanding_extents = 0;
ei->reserved_extents = 0;
spin_lock_init(&ei->accounting_lock);
btrfs_ordered_inode_tree_init(&ei->ordered_tree);
INIT_LIST_HEAD(&ei->i_orphan);
INIT_LIST_HEAD(&ei->ordered_operations);
@ -5805,6 +5842,6 @@ static const struct inode_operations btrfs_symlink_inode_operations = {
.removexattr = btrfs_removexattr,
};
struct dentry_operations btrfs_dentry_operations = {
const struct dentry_operations btrfs_dentry_operations = {
.d_delete = btrfs_dentry_delete,
};

7
fs/btrfs/ioctl.c
View File

@ -830,6 +830,7 @@ out_up_write:
out_unlock:
mutex_unlock(&inode->i_mutex);
if (!err) {
shrink_dcache_sb(root->fs_info->sb);
btrfs_invalidate_inodes(dest);
d_delete(dentry);
}
@ -1122,8 +1123,10 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
datao += off - key.offset;
datal -= off - key.offset;
}
if (key.offset + datao + datal > off + len)
datal = off + len - key.offset - datao;
if (key.offset + datal > off + len)
datal = off + len - key.offset;
/* disko == 0 means it's a hole */
if (!disko)
datao = 0;

6
fs/btrfs/ordered-data.c
View File

@ -306,6 +306,12 @@ int btrfs_remove_ordered_extent(struct inode *inode,
tree->last = NULL;
set_bit(BTRFS_ORDERED_COMPLETE, &entry->flags);
spin_lock(&BTRFS_I(inode)->accounting_lock);
BTRFS_I(inode)->outstanding_extents--;
spin_unlock(&BTRFS_I(inode)->accounting_lock);
btrfs_unreserve_metadata_for_delalloc(BTRFS_I(inode)->root,
inode, 1);
spin_lock(&BTRFS_I(inode)->root->fs_info->ordered_extent_lock);
list_del_init(&entry->root_extent_list);

4
fs/btrfs/relocation.c
View File

@ -3518,7 +3518,7 @@ int btrfs_relocate_block_group(struct btrfs_root *extent_root, u64 group_start)
BUG_ON(!rc->block_group);
btrfs_init_workers(&rc->workers, "relocate",
fs_info->thread_pool_size);
fs_info->thread_pool_size, NULL);
rc->extent_root = extent_root;
btrfs_prepare_block_group_relocation(extent_root, rc->block_group);
@ -3701,7 +3701,7 @@ int btrfs_recover_relocation(struct btrfs_root *root)
mapping_tree_init(&rc->reloc_root_tree);
INIT_LIST_HEAD(&rc->reloc_roots);
btrfs_init_workers(&rc->workers, "relocate",
root->fs_info->thread_pool_size);
root->fs_info->thread_pool_size, NULL);
rc->extent_root = root->fs_info->extent_root;
set_reloc_control(rc);

12
fs/btrfs/tree-log.c
View File

@ -137,11 +137,20 @@ static int start_log_trans(struct btrfs_trans_handle *trans,
mutex_lock(&root->log_mutex);
if (root->log_root) {
if (!root->log_start_pid) {
root->log_start_pid = current->pid;
root->log_multiple_pids = false;
} else if (root->log_start_pid != current->pid) {
root->log_multiple_pids = true;
}
root->log_batch++;
atomic_inc(&root->log_writers);
mutex_unlock(&root->log_mutex);
return 0;
}
root->log_multiple_pids = false;
root->log_start_pid = current->pid;
mutex_lock(&root->fs_info->tree_log_mutex);
if (!root->fs_info->log_root_tree) {
ret = btrfs_init_log_root_tree(trans, root->fs_info);
@ -1985,7 +1994,7 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
if (atomic_read(&root->log_commit[(index1 + 1) % 2]))
wait_log_commit(trans, root, root->log_transid - 1);
while (1) {
while (root->log_multiple_pids) {
unsigned long batch = root->log_batch;
mutex_unlock(&root->log_mutex);
schedule_timeout_uninterruptible(1);
@ -2011,6 +2020,7 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
root->log_batch = 0;
root->log_transid++;
log->log_transid = root->log_transid;
root->log_start_pid = 0;
smp_mb();
/*
* log tree has been flushed to disk, new modifications of