#define BTRFS_FS_STATE_ERROR 0
#define BTRFS_FS_STATE_REMOUNTING 1
#define BTRFS_FS_STATE_TRANS_ABORTED 2
+ #define BTRFS_FS_STATE_DEV_REPLACING 3
/* Super block flags */
/* Errors detected */
*/
struct list_head ordered_roots;
+ struct mutex delalloc_root_mutex;
spinlock_t delalloc_root_lock;
/* all fs/file tree roots that have delalloc inodes. */
struct list_head delalloc_roots;
* 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 flush_workers;
- struct btrfs_workers endio_workers;
- struct btrfs_workers endio_meta_workers;
- struct btrfs_workers endio_raid56_workers;
- struct btrfs_workers rmw_workers;
- struct btrfs_workers endio_meta_write_workers;
- struct btrfs_workers endio_write_workers;
- struct btrfs_workers endio_freespace_worker;
- struct btrfs_workers submit_workers;
- struct btrfs_workers caching_workers;
- struct btrfs_workers readahead_workers;
+ struct btrfs_workqueue *workers;
+ struct btrfs_workqueue *delalloc_workers;
+ struct btrfs_workqueue *flush_workers;
+ struct btrfs_workqueue *endio_workers;
+ struct btrfs_workqueue *endio_meta_workers;
+ struct btrfs_workqueue *endio_raid56_workers;
+ struct btrfs_workqueue *rmw_workers;
+ struct btrfs_workqueue *endio_meta_write_workers;
+ struct btrfs_workqueue *endio_write_workers;
+ struct btrfs_workqueue *endio_freespace_worker;
+ struct btrfs_workqueue *submit_workers;
+ struct btrfs_workqueue *caching_workers;
+ struct btrfs_workqueue *readahead_workers;
/*
* fixup workers take dirty pages that didn't properly go through
* the cow mechanism and make them safe to write. It happens
* for the sys_munmap function call path
*/
- struct btrfs_workers fixup_workers;
- struct btrfs_workers delayed_workers;
+ struct btrfs_workqueue *fixup_workers;
+ struct btrfs_workqueue *delayed_workers;
struct task_struct *transaction_kthread;
struct task_struct *cleaner_kthread;
int thread_pool_size;
atomic_t scrub_cancel_req;
wait_queue_head_t scrub_pause_wait;
int scrub_workers_refcnt;
- struct btrfs_workers scrub_workers;
- struct btrfs_workers scrub_wr_completion_workers;
- struct btrfs_workers scrub_nocow_workers;
+ struct btrfs_workqueue *scrub_workers;
+ struct btrfs_workqueue *scrub_wr_completion_workers;
+ struct btrfs_workqueue *scrub_nocow_workers;
#ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY
u32 check_integrity_print_mask;
/* qgroup rescan items */
struct mutex qgroup_rescan_lock; /* protects the progress item */
struct btrfs_key qgroup_rescan_progress;
- struct btrfs_workers qgroup_rescan_workers;
+ struct btrfs_workqueue *qgroup_rescan_workers;
struct completion qgroup_rescan_completion;
struct btrfs_work qgroup_rescan_work;
atomic_t mutually_exclusive_operation_running;
+ struct percpu_counter bio_counter;
+ wait_queue_head_t replace_wait;
+
struct semaphore uuid_tree_rescan_sem;
unsigned int update_uuid_tree_gen:1;
};
+ struct btrfs_subvolume_writers {
+ struct percpu_counter counter;
+ wait_queue_head_t wait;
+ };
+
/*
* in ram representation of the tree. extent_root is used for all allocations
* and for the extent tree extent_root root.
struct mutex log_mutex;
wait_queue_head_t log_writer_wait;
wait_queue_head_t log_commit_wait[2];
+ struct list_head log_ctxs[2];
atomic_t log_writers;
atomic_t log_commit[2];
atomic_t log_batch;
- unsigned long log_transid;
- unsigned long last_log_commit;
+ int log_transid;
+ /* No matter the commit succeeds or not*/
+ int log_transid_committed;
+ /* Just be updated when the commit succeeds. */
+ int last_log_commit;
pid_t log_start_pid;
bool log_multiple_pids;
spinlock_t root_item_lock;
atomic_t refs;
+ struct mutex delalloc_mutex;
spinlock_t delalloc_lock;
/*
* all of the inodes that have delalloc bytes. It is possible for
struct list_head delalloc_inodes;
struct list_head delalloc_root;
u64 nr_delalloc_inodes;
+
+ struct mutex ordered_extent_mutex;
/*
* this is used by the balancing code to wait for all the pending
* ordered extents
* manipulation with the read-only status via SUBVOL_SETFLAGS
*/
int send_in_progress;
+ struct btrfs_subvolume_writers *subv_writers;
+ atomic_t will_be_snapshoted;
};
struct btrfs_ioctl_defrag_range_args {
int btrfs_delayed_refs_qgroup_accounting(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info);
int __get_raid_index(u64 flags);
+
+ int btrfs_start_nocow_write(struct btrfs_root *root);
+ void btrfs_end_nocow_write(struct btrfs_root *root);
/* ctree.c */
int btrfs_bin_search(struct extent_buffer *eb, struct btrfs_key *key,
int level, int *slot);
u32 min_type);
int btrfs_start_delalloc_inodes(struct btrfs_root *root, int delay_iput);
- int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, int delay_iput);
+ int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, int delay_iput,
+ int nr);
int btrfs_set_extent_delalloc(struct inode *inode, u64 start, u64 end,
struct extent_state **cached_state);
int btrfs_create_subvol_root(struct btrfs_trans_handle *trans,
/* acl.c */
#ifdef CONFIG_BTRFS_FS_POSIX_ACL
struct posix_acl *btrfs_get_acl(struct inode *inode, int type);
+int btrfs_set_acl(struct inode *inode, struct posix_acl *acl, int type);
int btrfs_init_acl(struct btrfs_trans_handle *trans,
struct inode *inode, struct inode *dir);
-int btrfs_acl_chmod(struct inode *inode);
#else
#define btrfs_get_acl NULL
+#define btrfs_set_acl NULL
static inline int btrfs_init_acl(struct btrfs_trans_handle *trans,
struct inode *inode, struct inode *dir)
{
return 0;
}
-static inline int btrfs_acl_chmod(struct inode *inode)
-{
- return 0;
-}
#endif
/* relocation.c */
struct btrfs_device *dev);
int btrfs_scrub_progress(struct btrfs_root *root, u64 devid,
struct btrfs_scrub_progress *progress);
+
+ /* dev-replace.c */
+ void btrfs_bio_counter_inc_blocked(struct btrfs_fs_info *fs_info);
+ void btrfs_bio_counter_inc_noblocked(struct btrfs_fs_info *fs_info);
+ void btrfs_bio_counter_dec(struct btrfs_fs_info *fs_info);
/* reada.c */
struct reada_control {
fs_info = end_io_wq->info;
end_io_wq->error = err;
- end_io_wq->work.func = end_workqueue_fn;
- end_io_wq->work.flags = 0;
+ btrfs_init_work(&end_io_wq->work, end_workqueue_fn, NULL, NULL);
if (bio->bi_rw & REQ_WRITE) {
if (end_io_wq->metadata == BTRFS_WQ_ENDIO_METADATA)
- btrfs_queue_worker(&fs_info->endio_meta_write_workers,
- &end_io_wq->work);
+ btrfs_queue_work(fs_info->endio_meta_write_workers,
+ &end_io_wq->work);
else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_FREE_SPACE)
- btrfs_queue_worker(&fs_info->endio_freespace_worker,
- &end_io_wq->work);
+ btrfs_queue_work(fs_info->endio_freespace_worker,
+ &end_io_wq->work);
else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56)
- btrfs_queue_worker(&fs_info->endio_raid56_workers,
- &end_io_wq->work);
+ btrfs_queue_work(fs_info->endio_raid56_workers,
+ &end_io_wq->work);
else
- btrfs_queue_worker(&fs_info->endio_write_workers,
- &end_io_wq->work);
+ btrfs_queue_work(fs_info->endio_write_workers,
+ &end_io_wq->work);
} else {
if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56)
- btrfs_queue_worker(&fs_info->endio_raid56_workers,
- &end_io_wq->work);
+ btrfs_queue_work(fs_info->endio_raid56_workers,
+ &end_io_wq->work);
else if (end_io_wq->metadata)
- btrfs_queue_worker(&fs_info->endio_meta_workers,
- &end_io_wq->work);
+ btrfs_queue_work(fs_info->endio_meta_workers,
+ &end_io_wq->work);
else
- btrfs_queue_worker(&fs_info->endio_workers,
- &end_io_wq->work);
+ btrfs_queue_work(fs_info->endio_workers,
+ &end_io_wq->work);
}
}
unsigned long btrfs_async_submit_limit(struct btrfs_fs_info *info)
{
unsigned long limit = min_t(unsigned long,
- info->workers.max_workers,
+ info->thread_pool_size,
info->fs_devices->open_devices);
return 256 * limit;
}
async->submit_bio_start = submit_bio_start;
async->submit_bio_done = submit_bio_done;
- async->work.func = run_one_async_start;
- async->work.ordered_func = run_one_async_done;
- async->work.ordered_free = run_one_async_free;
+ btrfs_init_work(&async->work, run_one_async_start,
+ run_one_async_done, run_one_async_free);
- async->work.flags = 0;
async->bio_flags = bio_flags;
async->bio_offset = bio_offset;
atomic_inc(&fs_info->nr_async_submits);
if (rw & REQ_SYNC)
- btrfs_set_work_high_prio(&async->work);
+ btrfs_set_work_high_priority(&async->work);
- btrfs_queue_worker(&fs_info->workers, &async->work);
+ btrfs_queue_work(fs_info->workers, &async->work);
while (atomic_read(&fs_info->async_submit_draining) &&
atomic_read(&fs_info->nr_async_submits)) {
static int btree_csum_one_bio(struct bio *bio)
{
- struct bio_vec *bvec = bio->bi_io_vec;
- int bio_index = 0;
+ struct bio_vec *bvec;
struct btrfs_root *root;
- int ret = 0;
+ int i, ret = 0;
- WARN_ON(bio->bi_vcnt <= 0);
- while (bio_index < bio->bi_vcnt) {
+ bio_for_each_segment_all(bvec, bio, i) {
root = BTRFS_I(bvec->bv_page->mapping->host)->root;
ret = csum_dirty_buffer(root, bvec->bv_page);
if (ret)
break;
- bio_index++;
- bvec++;
}
+
return ret;
}
}
}
+ 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);
+ 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(u32 nodesize, u32 leafsize, u32 sectorsize,
u32 stripesize, struct btrfs_root *root,
struct btrfs_fs_info *fs_info,
spin_lock_init(&root->log_extents_lock[1]);
mutex_init(&root->objectid_mutex);
mutex_init(&root->log_mutex);
+ mutex_init(&root->ordered_extent_mutex);
+ mutex_init(&root->delalloc_mutex);
init_waitqueue_head(&root->log_writer_wait);
init_waitqueue_head(&root->log_commit_wait[0]);
init_waitqueue_head(&root->log_commit_wait[1]);
+ INIT_LIST_HEAD(&root->log_ctxs[0]);
+ INIT_LIST_HEAD(&root->log_ctxs[1]);
atomic_set(&root->log_commit[0], 0);
atomic_set(&root->log_commit[1], 0);
atomic_set(&root->log_writers, 0);
atomic_set(&root->log_batch, 0);
atomic_set(&root->orphan_inodes, 0);
atomic_set(&root->refs, 1);
+ atomic_set(&root->will_be_snapshoted, 0);
root->log_transid = 0;
+ root->log_transid_committed = -1;
root->last_log_commit = 0;
if (fs_info)
extent_io_tree_init(&root->dirty_log_pages,
WARN_ON(root->log_root);
root->log_root = log_root;
root->log_transid = 0;
+ root->log_transid_committed = -1;
root->last_log_commit = 0;
return 0;
}
int btrfs_init_fs_root(struct btrfs_root *root)
{
int ret;
+ struct btrfs_subvolume_writers *writers;
root->free_ino_ctl = kzalloc(sizeof(*root->free_ino_ctl), GFP_NOFS);
root->free_ino_pinned = kzalloc(sizeof(*root->free_ino_pinned),
goto fail;
}
+ writers = btrfs_alloc_subvolume_writers();
+ if (IS_ERR(writers)) {
+ ret = PTR_ERR(writers);
+ goto fail;
+ }
+ root->subv_writers = writers;
+
btrfs_init_free_ino_ctl(root);
mutex_init(&root->fs_commit_mutex);
spin_lock_init(&root->cache_lock);
ret = get_anon_bdev(&root->anon_dev);
if (ret)
- goto fail;
+ goto free_writers;
return 0;
+
+ free_writers:
+ btrfs_free_subvolume_writers(root->subv_writers);
fail:
kfree(root->free_ino_ctl);
kfree(root->free_ino_pinned);
bio->bi_private = end_io_wq->private;
bio->bi_end_io = end_io_wq->end_io;
kfree(end_io_wq);
- bio_endio(bio, error);
+ bio_endio_nodec(bio, error);
}
static int cleaner_kthread(void *arg)
/* helper to cleanup workers */
static void btrfs_stop_all_workers(struct btrfs_fs_info *fs_info)
{
- 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);
- btrfs_stop_workers(&fs_info->endio_workers);
- btrfs_stop_workers(&fs_info->endio_meta_workers);
- btrfs_stop_workers(&fs_info->endio_raid56_workers);
- btrfs_stop_workers(&fs_info->rmw_workers);
- btrfs_stop_workers(&fs_info->endio_meta_write_workers);
- btrfs_stop_workers(&fs_info->endio_write_workers);
- btrfs_stop_workers(&fs_info->endio_freespace_worker);
- btrfs_stop_workers(&fs_info->submit_workers);
- btrfs_stop_workers(&fs_info->delayed_workers);
- btrfs_stop_workers(&fs_info->caching_workers);
- btrfs_stop_workers(&fs_info->readahead_workers);
- btrfs_stop_workers(&fs_info->flush_workers);
- btrfs_stop_workers(&fs_info->qgroup_rescan_workers);
+ btrfs_destroy_workqueue(fs_info->fixup_workers);
+ btrfs_destroy_workqueue(fs_info->delalloc_workers);
+ btrfs_destroy_workqueue(fs_info->workers);
+ btrfs_destroy_workqueue(fs_info->endio_workers);
+ btrfs_destroy_workqueue(fs_info->endio_meta_workers);
+ btrfs_destroy_workqueue(fs_info->endio_raid56_workers);
+ btrfs_destroy_workqueue(fs_info->rmw_workers);
+ btrfs_destroy_workqueue(fs_info->endio_meta_write_workers);
+ btrfs_destroy_workqueue(fs_info->endio_write_workers);
+ btrfs_destroy_workqueue(fs_info->endio_freespace_worker);
+ btrfs_destroy_workqueue(fs_info->submit_workers);
+ btrfs_destroy_workqueue(fs_info->delayed_workers);
+ btrfs_destroy_workqueue(fs_info->caching_workers);
+ btrfs_destroy_workqueue(fs_info->readahead_workers);
+ btrfs_destroy_workqueue(fs_info->flush_workers);
+ btrfs_destroy_workqueue(fs_info->qgroup_rescan_workers);
}
static void free_root_extent_buffers(struct btrfs_root *root)
int err = -EINVAL;
int num_backups_tried = 0;
int backup_index = 0;
+ int max_active;
+ int flags = WQ_MEM_RECLAIM | WQ_FREEZABLE | WQ_UNBOUND;
bool create_uuid_tree;
bool check_uuid_tree;
goto fail_dirty_metadata_bytes;
}
+ ret = percpu_counter_init(&fs_info->bio_counter, 0);
+ if (ret) {
+ err = ret;
+ goto fail_delalloc_bytes;
+ }
+
fs_info->btree_inode = new_inode(sb);
if (!fs_info->btree_inode) {
err = -ENOMEM;
- goto fail_delalloc_bytes;
+ goto fail_bio_counter;
}
mapping_set_gfp_mask(fs_info->btree_inode->i_mapping, GFP_NOFS);
spin_lock_init(&fs_info->buffer_lock);
rwlock_init(&fs_info->tree_mod_log_lock);
mutex_init(&fs_info->reloc_mutex);
+ mutex_init(&fs_info->delalloc_root_mutex);
seqlock_init(&fs_info->profiles_lock);
init_completion(&fs_info->kobj_unregister);
atomic_set(&fs_info->scrub_pause_req, 0);
atomic_set(&fs_info->scrubs_paused, 0);
atomic_set(&fs_info->scrub_cancel_req, 0);
+ init_waitqueue_head(&fs_info->replace_wait);
init_waitqueue_head(&fs_info->scrub_pause_wait);
fs_info->scrub_workers_refcnt = 0;
#ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY
goto fail_alloc;
}
- btrfs_init_workers(&fs_info->generic_worker,
- "genwork", 1, NULL);
+ max_active = fs_info->thread_pool_size;
- btrfs_init_workers(&fs_info->workers, "worker",
- fs_info->thread_pool_size,
- &fs_info->generic_worker);
+ fs_info->workers =
+ btrfs_alloc_workqueue("worker", flags | WQ_HIGHPRI,
+ max_active, 16);
- btrfs_init_workers(&fs_info->delalloc_workers, "delalloc",
- fs_info->thread_pool_size, NULL);
+ fs_info->delalloc_workers =
+ btrfs_alloc_workqueue("delalloc", flags, max_active, 2);
- btrfs_init_workers(&fs_info->flush_workers, "flush_delalloc",
- fs_info->thread_pool_size, NULL);
+ fs_info->flush_workers =
+ btrfs_alloc_workqueue("flush_delalloc", flags, max_active, 0);
- btrfs_init_workers(&fs_info->submit_workers, "submit",
- min_t(u64, fs_devices->num_devices,
- fs_info->thread_pool_size), NULL);
+ fs_info->caching_workers =
+ btrfs_alloc_workqueue("cache", flags, max_active, 0);
- btrfs_init_workers(&fs_info->caching_workers, "cache",
- fs_info->thread_pool_size, NULL);
-
- /* a higher idle thresh on the submit workers makes it much more
+ /*
+ * 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
* devices
*/
- fs_info->submit_workers.idle_thresh = 64;
-
- fs_info->workers.idle_thresh = 16;
- fs_info->workers.ordered = 1;
-
- fs_info->delalloc_workers.idle_thresh = 2;
- fs_info->delalloc_workers.ordered = 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->generic_worker);
- btrfs_init_workers(&fs_info->endio_meta_workers, "endio-meta",
- 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,
- &fs_info->generic_worker);
- btrfs_init_workers(&fs_info->endio_raid56_workers,
- "endio-raid56", fs_info->thread_pool_size,
- &fs_info->generic_worker);
- btrfs_init_workers(&fs_info->rmw_workers,
- "rmw", 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->generic_worker);
- btrfs_init_workers(&fs_info->endio_freespace_worker, "freespace-write",
- 1, &fs_info->generic_worker);
- btrfs_init_workers(&fs_info->delayed_workers, "delayed-meta",
- fs_info->thread_pool_size,
- &fs_info->generic_worker);
- btrfs_init_workers(&fs_info->readahead_workers, "readahead",
- fs_info->thread_pool_size,
- &fs_info->generic_worker);
- btrfs_init_workers(&fs_info->qgroup_rescan_workers, "qgroup-rescan", 1,
- &fs_info->generic_worker);
+ fs_info->submit_workers =
+ btrfs_alloc_workqueue("submit", flags,
+ min_t(u64, fs_devices->num_devices,
+ max_active), 64);
+
+ fs_info->fixup_workers =
+ btrfs_alloc_workqueue("fixup", flags, 1, 0);
/*
* endios are largely parallel and should have a very
* low idle thresh
*/
- fs_info->endio_workers.idle_thresh = 4;
- fs_info->endio_meta_workers.idle_thresh = 4;
- fs_info->endio_raid56_workers.idle_thresh = 4;
- fs_info->rmw_workers.idle_thresh = 2;
-
- fs_info->endio_write_workers.idle_thresh = 2;
- fs_info->endio_meta_write_workers.idle_thresh = 2;
- fs_info->readahead_workers.idle_thresh = 2;
-
- /*
- * btrfs_start_workers can really only fail because of ENOMEM so just
- * return -ENOMEM if any of these fail.
- */
- ret = btrfs_start_workers(&fs_info->workers);
- ret |= btrfs_start_workers(&fs_info->generic_worker);
- ret |= btrfs_start_workers(&fs_info->submit_workers);
- ret |= btrfs_start_workers(&fs_info->delalloc_workers);
- ret |= btrfs_start_workers(&fs_info->fixup_workers);
- ret |= btrfs_start_workers(&fs_info->endio_workers);
- ret |= btrfs_start_workers(&fs_info->endio_meta_workers);
- ret |= btrfs_start_workers(&fs_info->rmw_workers);
- ret |= btrfs_start_workers(&fs_info->endio_raid56_workers);
- ret |= btrfs_start_workers(&fs_info->endio_meta_write_workers);
- ret |= btrfs_start_workers(&fs_info->endio_write_workers);
- ret |= btrfs_start_workers(&fs_info->endio_freespace_worker);
- ret |= btrfs_start_workers(&fs_info->delayed_workers);
- ret |= btrfs_start_workers(&fs_info->caching_workers);
- ret |= btrfs_start_workers(&fs_info->readahead_workers);
- ret |= btrfs_start_workers(&fs_info->flush_workers);
- ret |= btrfs_start_workers(&fs_info->qgroup_rescan_workers);
- if (ret) {
+ fs_info->endio_workers =
+ btrfs_alloc_workqueue("endio", flags, max_active, 4);
+ fs_info->endio_meta_workers =
+ btrfs_alloc_workqueue("endio-meta", flags, max_active, 4);
+ fs_info->endio_meta_write_workers =
+ btrfs_alloc_workqueue("endio-meta-write", flags, max_active, 2);
+ fs_info->endio_raid56_workers =
+ btrfs_alloc_workqueue("endio-raid56", flags, max_active, 4);
+ fs_info->rmw_workers =
+ btrfs_alloc_workqueue("rmw", flags, max_active, 2);
+ fs_info->endio_write_workers =
+ btrfs_alloc_workqueue("endio-write", flags, max_active, 2);
+ fs_info->endio_freespace_worker =
+ btrfs_alloc_workqueue("freespace-write", flags, max_active, 0);
+ fs_info->delayed_workers =
+ btrfs_alloc_workqueue("delayed-meta", flags, max_active, 0);
+ fs_info->readahead_workers =
+ btrfs_alloc_workqueue("readahead", flags, max_active, 2);
+ fs_info->qgroup_rescan_workers =
+ btrfs_alloc_workqueue("qgroup-rescan", flags, 1, 0);
+
+ if (!(fs_info->workers && fs_info->delalloc_workers &&
+ fs_info->submit_workers && fs_info->flush_workers &&
+ fs_info->endio_workers && fs_info->endio_meta_workers &&
+ fs_info->endio_meta_write_workers &&
+ fs_info->endio_write_workers && fs_info->endio_raid56_workers &&
+ fs_info->endio_freespace_worker && fs_info->rmw_workers &&
+ fs_info->caching_workers && fs_info->readahead_workers &&
+ fs_info->fixup_workers && fs_info->delayed_workers &&
+ fs_info->qgroup_rescan_workers)) {
err = -ENOMEM;
goto fail_sb_buffer;
}
btrfs_mapping_tree_free(&fs_info->mapping_tree);
iput(fs_info->btree_inode);
+ fail_bio_counter:
+ percpu_counter_destroy(&fs_info->bio_counter);
fail_delalloc_bytes:
percpu_counter_destroy(&fs_info->delalloc_bytes);
fail_dirty_metadata_bytes:
/* send down all the barriers */
head = &info->fs_devices->devices;
list_for_each_entry_rcu(dev, head, dev_list) {
+ if (dev->missing)
+ continue;
if (!dev->bdev) {
errors_send++;
continue;
/* wait for all the barriers */
list_for_each_entry_rcu(dev, head, dev_list) {
+ if (dev->missing)
+ continue;
if (!dev->bdev) {
errors_wait++;
continue;
root->orphan_block_rsv = NULL;
if (root->anon_dev)
free_anon_bdev(root->anon_dev);
+ if (root->subv_writers)
+ btrfs_free_subvolume_writers(root->subv_writers);
free_extent_buffer(root->node);
free_extent_buffer(root->commit_root);
kfree(root->free_ino_ctl);
percpu_counter_destroy(&fs_info->dirty_metadata_bytes);
percpu_counter_destroy(&fs_info->delalloc_bytes);
+ percpu_counter_destroy(&fs_info->bio_counter);
bdi_destroy(&fs_info->bdi);
cleanup_srcu_struct(&fs_info->subvol_srcu);
list_move_tail(&root->ordered_root,
&fs_info->ordered_roots);
+ spin_unlock(&fs_info->ordered_root_lock);
btrfs_destroy_ordered_extents(root);
- cond_resched_lock(&fs_info->ordered_root_lock);
+ cond_resched();
+ spin_lock(&fs_info->ordered_root_lock);
}
spin_unlock(&fs_info->ordered_root_lock);
}
}
}
- static struct rb_node *tree_insert(struct rb_root *root, u64 offset,
+ static struct rb_node *tree_insert(struct rb_root *root,
+ struct rb_node *search_start,
+ u64 offset,
struct rb_node *node,
struct rb_node ***p_in,
struct rb_node **parent_in)
{
- struct rb_node **p = &root->rb_node;
+ struct rb_node **p;
struct rb_node *parent = NULL;
struct tree_entry *entry;
goto do_insert;
}
+ p = search_start ? &search_start : &root->rb_node;
while (*p) {
parent = *p;
entry = rb_entry(parent, struct tree_entry, rb_node);
set_state_bits(tree, state, bits);
- node = tree_insert(&tree->state, end, &state->rb_node, p, parent);
+ node = tree_insert(&tree->state, NULL, end, &state->rb_node, p, parent);
if (node) {
struct extent_state *found;
found = rb_entry(node, struct extent_state, rb_node);
prealloc->state = orig->state;
orig->start = split;
- node = tree_insert(&tree->state, prealloc->end, &prealloc->rb_node,
- NULL, NULL);
+ node = tree_insert(&tree->state, &orig->rb_node, prealloc->end,
+ &prealloc->rb_node, NULL, NULL);
if (node) {
free_extent_state(prealloc);
return -EEXIST;
bio = btrfs_io_bio_alloc(GFP_NOFS, 1);
if (!bio)
return -EIO;
- bio->bi_size = 0;
+ bio->bi_iter.bi_size = 0;
map_length = length;
ret = btrfs_map_block(fs_info, WRITE, logical,
}
BUG_ON(mirror_num != bbio->mirror_num);
sector = bbio->stripes[mirror_num-1].physical >> 9;
- bio->bi_sector = sector;
+ bio->bi_iter.bi_sector = sector;
dev = bbio->stripes[mirror_num-1].dev;
kfree(bbio);
if (!dev || !dev->bdev || !dev->writeable) {
return -EIO;
}
bio->bi_end_io = failed_bio->bi_end_io;
- bio->bi_sector = failrec->logical >> 9;
+ bio->bi_iter.bi_sector = failrec->logical >> 9;
bio->bi_bdev = BTRFS_I(inode)->root->fs_info->fs_devices->latest_bdev;
- bio->bi_size = 0;
+ bio->bi_iter.bi_size = 0;
btrfs_failed_bio = btrfs_io_bio(failed_bio);
if (btrfs_failed_bio->csum) {
*/
static void end_bio_extent_writepage(struct bio *bio, int err)
{
- struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1;
+ struct bio_vec *bvec;
u64 start;
u64 end;
+ int i;
- do {
+ bio_for_each_segment_all(bvec, bio, i) {
struct page *page = bvec->bv_page;
/* We always issue full-page reads, but if some block
start = page_offset(page);
end = start + bvec->bv_offset + bvec->bv_len - 1;
- if (--bvec >= bio->bi_io_vec)
- prefetchw(&bvec->bv_page->flags);
-
if (end_extent_writepage(page, err, start, end))
continue;
end_page_writeback(page);
- } while (bvec >= bio->bi_io_vec);
+ }
bio_put(bio);
}
*/
static void end_bio_extent_readpage(struct bio *bio, int err)
{
+ struct bio_vec *bvec;
int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
- struct bio_vec *bvec_end = bio->bi_io_vec + bio->bi_vcnt - 1;
- struct bio_vec *bvec = bio->bi_io_vec;
struct btrfs_io_bio *io_bio = btrfs_io_bio(bio);
struct extent_io_tree *tree;
u64 offset = 0;
u64 extent_len = 0;
int mirror;
int ret;
+ int i;
if (err)
uptodate = 0;
- do {
+ bio_for_each_segment_all(bvec, bio, i) {
struct page *page = bvec->bv_page;
struct inode *inode = page->mapping->host;
pr_debug("end_bio_extent_readpage: bi_sector=%llu, err=%d, "
- "mirror=%lu\n", (u64)bio->bi_sector, err,
+ "mirror=%lu\n", (u64)bio->bi_iter.bi_sector, err,
io_bio->mirror_num);
tree = &BTRFS_I(inode)->io_tree;
end = start + bvec->bv_offset + bvec->bv_len - 1;
len = bvec->bv_len;
- if (++bvec <= bvec_end)
- prefetchw(&bvec->bv_page->flags);
-
mirror = io_bio->mirror_num;
if (likely(uptodate && tree->ops &&
tree->ops->readpage_end_io_hook)) {
extent_start = start;
extent_len = end + 1 - start;
}
- } while (bvec <= bvec_end);
+ }
if (extent_len)
endio_readpage_release_extent(tree, extent_start, extent_len,
}
if (bio) {
- bio->bi_size = 0;
bio->bi_bdev = bdev;
- bio->bi_sector = first_sector;
+ bio->bi_iter.bi_sector = first_sector;
btrfs_bio = btrfs_io_bio(bio);
btrfs_bio->csum = NULL;
btrfs_bio->csum_allocated = NULL;
if (bio_ret && *bio_ret) {
bio = *bio_ret;
if (old_compressed)
- contig = bio->bi_sector == sector;
+ contig = bio->bi_iter.bi_sector == sector;
else
contig = bio_end_sector(bio) == sector;
if (em_cached && *em_cached) {
em = *em_cached;
- if (em->in_tree && start >= em->start &&
+ if (extent_map_in_tree(em) && start >= em->start &&
start < extent_map_end(em)) {
atomic_inc(&em->refs);
return em;
static void end_bio_extent_buffer_writepage(struct bio *bio, int err)
{
- int uptodate = err == 0;
- struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1;
+ struct bio_vec *bvec;
struct extent_buffer *eb;
- int done;
+ int i, done;
- do {
+ bio_for_each_segment_all(bvec, bio, i) {
struct page *page = bvec->bv_page;
- bvec--;
eb = (struct extent_buffer *)page->private;
BUG_ON(!eb);
done = atomic_dec_and_test(&eb->io_pages);
- if (!uptodate || test_bit(EXTENT_BUFFER_IOERR, &eb->bflags)) {
+ if (err || test_bit(EXTENT_BUFFER_IOERR, &eb->bflags)) {
set_bit(EXTENT_BUFFER_IOERR, &eb->bflags);
ClearPageUptodate(page);
SetPageError(page);
continue;
end_extent_buffer_writeback(eb);
- } while (bvec >= bio->bi_io_vec);
+ }
bio_put(bio);
-
}
static int write_one_eb(struct extent_buffer *eb,
clear_bit(EXTENT_FLAG_PINNED, &em->flags);
clear_bit(EXTENT_FLAG_LOGGING, &flags);
modified = !list_empty(&em->list);
- remove_extent_mapping(em_tree, em);
if (no_splits)
goto next;
split->bdev = em->bdev;
split->flags = flags;
split->compress_type = em->compress_type;
- ret = add_extent_mapping(em_tree, split, modified);
- BUG_ON(ret); /* Logic error */
+ replace_extent_mapping(em_tree, em, split, modified);
free_extent_map(split);
split = split2;
split2 = NULL;
split->orig_block_len = 0;
}
- ret = add_extent_mapping(em_tree, split, modified);
- BUG_ON(ret); /* Logic error */
+ if (extent_map_in_tree(em)) {
+ replace_extent_mapping(em_tree, em, split,
+ modified);
+ } else {
+ ret = add_extent_mapping(em_tree, split,
+ modified);
+ ASSERT(ret == 0); /* Logic error */
+ }
free_extent_map(split);
split = NULL;
}
next:
+ if (extent_map_in_tree(em))
+ remove_extent_mapping(em_tree, em);
write_unlock(&em_tree->lock);
/* once for us */
if (drop_cache)
btrfs_drop_extent_cache(inode, start, end - 1, 0);
- if (start >= BTRFS_I(inode)->disk_i_size)
+ if (start >= BTRFS_I(inode)->disk_i_size && !replace_extent)
modify_tree = 0;
while (1) {
*/
if (start > key.offset && end < extent_end) {
BUG_ON(del_nr > 0);
- BUG_ON(extent_type == BTRFS_FILE_EXTENT_INLINE);
+ if (extent_type == BTRFS_FILE_EXTENT_INLINE) {
+ ret = -EINVAL;
+ break;
+ }
memcpy(&new_key, &key, sizeof(new_key));
new_key.offset = start;
* | -------- extent -------- |
*/
if (start <= key.offset && end < extent_end) {
- BUG_ON(extent_type == BTRFS_FILE_EXTENT_INLINE);
+ if (extent_type == BTRFS_FILE_EXTENT_INLINE) {
+ ret = -EINVAL;
+ break;
+ }
memcpy(&new_key, &key, sizeof(new_key));
new_key.offset = end;
*/
if (start > key.offset && end >= extent_end) {
BUG_ON(del_nr > 0);
- BUG_ON(extent_type == BTRFS_FILE_EXTENT_INLINE);
+ if (extent_type == BTRFS_FILE_EXTENT_INLINE) {
+ ret = -EINVAL;
+ break;
+ }
btrfs_set_file_extent_num_bytes(leaf, fi,
start - key.offset);
* Set path->slots[0] to first slot, so that after the delete
* if items are move off from our leaf to its immediate left or
* right neighbor leafs, we end up with a correct and adjusted
- * path->slots[0] for our insertion.
+ * path->slots[0] for our insertion (if replace_extent != 0).
*/
path->slots[0] = del_slot;
ret = btrfs_del_items(trans, root, path, del_slot, del_nr);
if (ret)
btrfs_abort_transaction(trans, root, ret);
+ }
- leaf = path->nodes[0];
- /*
- * leaf eb has flag EXTENT_BUFFER_STALE if it was deleted (that
- * is, its contents got pushed to its neighbors), in which case
- * it means path->locks[0] == 0
- */
- if (!ret && replace_extent && leafs_visited == 1 &&
- path->locks[0] &&
- btrfs_leaf_free_space(root, leaf) >=
- sizeof(struct btrfs_item) + extent_item_size) {
-
- key.objectid = ino;
- key.type = BTRFS_EXTENT_DATA_KEY;
- key.offset = start;
- setup_items_for_insert(root, path, &key,
- &extent_item_size,
- extent_item_size,
- sizeof(struct btrfs_item) +
- extent_item_size, 1);
- *key_inserted = 1;
+ leaf = path->nodes[0];
+ /*
+ * If btrfs_del_items() was called, it might have deleted a leaf, in
+ * which case it unlocked our path, so check path->locks[0] matches a
+ * write lock.
+ */
+ if (!ret && replace_extent && leafs_visited == 1 &&
+ (path->locks[0] == BTRFS_WRITE_LOCK_BLOCKING ||
+ path->locks[0] == BTRFS_WRITE_LOCK) &&
+ btrfs_leaf_free_space(root, leaf) >=
+ sizeof(struct btrfs_item) + extent_item_size) {
+
+ key.objectid = ino;
+ key.type = BTRFS_EXTENT_DATA_KEY;
+ key.offset = start;
+ if (!del_nr && path->slots[0] < btrfs_header_nritems(leaf)) {
+ struct btrfs_key slot_key;
+
+ btrfs_item_key_to_cpu(leaf, &slot_key, path->slots[0]);
+ if (btrfs_comp_cpu_keys(&key, &slot_key) > 0)
+ path->slots[0]++;
}
+ setup_items_for_insert(root, path, &key,
+ &extent_item_size,
+ extent_item_size,
+ sizeof(struct btrfs_item) +
+ extent_item_size, 1);
+ *key_inserted = 1;
}
if (!replace_extent || !(*key_inserted))
struct btrfs_ordered_extent *ordered;
lock_extent_bits(&BTRFS_I(inode)->io_tree,
start_pos, last_pos, 0, cached_state);
- ordered = btrfs_lookup_first_ordered_extent(inode, last_pos);
+ ordered = btrfs_lookup_ordered_range(inode, start_pos,
+ last_pos - start_pos + 1);
if (ordered &&
ordered->file_offset + ordered->len > start_pos &&
ordered->file_offset <= last_pos) {
- btrfs_put_ordered_extent(ordered);
unlock_extent_cached(&BTRFS_I(inode)->io_tree,
start_pos, last_pos,
cached_state, GFP_NOFS);
unlock_page(pages[i]);
page_cache_release(pages[i]);
}
- ret = btrfs_wait_ordered_range(inode, start_pos,
- last_pos - start_pos + 1);
- if (ret)
- return ret;
- else
- return -EAGAIN;
+ btrfs_start_ordered_extent(inode, ordered, 1);
+ btrfs_put_ordered_extent(ordered);
+ return -EAGAIN;
}
if (ordered)
btrfs_put_ordered_extent(ordered);
u64 num_bytes;
int ret;
+ ret = btrfs_start_nocow_write(root);
+ if (!ret)
+ return -ENOSPC;
+
lockstart = round_down(pos, root->sectorsize);
- lockend = lockstart + round_up(*write_bytes, root->sectorsize) - 1;
+ lockend = round_up(pos + *write_bytes, root->sectorsize) - 1;
while (1) {
lock_extent(&BTRFS_I(inode)->io_tree, lockstart, lockend);
ret = can_nocow_extent(inode, lockstart, &num_bytes, NULL, NULL, NULL);
if (ret <= 0) {
ret = 0;
+ btrfs_end_nocow_write(root);
} else {
- clear_extent_bit(&BTRFS_I(inode)->io_tree, lockstart, lockend,
- EXTENT_DIRTY | EXTENT_DELALLOC |
- EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG, 0, 0,
- NULL, GFP_NOFS);
- *write_bytes = min_t(size_t, *write_bytes, num_bytes);
+ *write_bytes = min_t(size_t, *write_bytes ,
+ num_bytes - pos + lockstart);
}
unlock_extent(&BTRFS_I(inode)->io_tree, lockstart, lockend);
if (!only_release_metadata)
btrfs_free_reserved_data_space(inode,
reserve_bytes);
+ else
+ btrfs_end_nocow_write(root);
break;
}
}
release_bytes = 0;
+ if (only_release_metadata)
+ btrfs_end_nocow_write(root);
+
if (only_release_metadata && copied > 0) {
u64 lockstart = round_down(pos, root->sectorsize);
u64 lockend = lockstart +
kfree(pages);
if (release_bytes) {
- if (only_release_metadata)
+ if (only_release_metadata) {
+ btrfs_end_nocow_write(root);
btrfs_delalloc_release_metadata(inode, release_bytes);
- else
+ } else {
btrfs_delalloc_release_space(inode, release_bytes);
+ }
}
return num_written ? num_written : ret;
BTRFS_I(inode)->last_sub_trans = root->log_transid;
if (num_written > 0) {
err = generic_write_sync(file, pos, num_written);
- if (err < 0 && num_written > 0)
+ if (err < 0)
num_written = err;
}
struct dentry *dentry = file->f_path.dentry;
struct inode *inode = dentry->d_inode;
struct btrfs_root *root = BTRFS_I(inode)->root;
- int ret = 0;
struct btrfs_trans_handle *trans;
+ struct btrfs_log_ctx ctx;
+ int ret = 0;
bool full_sync = 0;
trace_btrfs_sync_file(file, datasync);
}
trans->sync = true;
- ret = btrfs_log_dentry_safe(trans, root, dentry);
+ btrfs_init_log_ctx(&ctx);
+
+ ret = btrfs_log_dentry_safe(trans, root, dentry, &ctx);
if (ret < 0) {
/* Fallthrough and commit/free transaction. */
ret = 1;
if (ret != BTRFS_NO_LOG_SYNC) {
if (!ret) {
- ret = btrfs_sync_log(trans, root);
+ ret = btrfs_sync_log(trans, root, &ctx);
if (!ret) {
ret = btrfs_end_transaction(trans, root);
goto out;
bool same_page = ((offset >> PAGE_CACHE_SHIFT) ==
((offset + len - 1) >> PAGE_CACHE_SHIFT));
bool no_holes = btrfs_fs_incompat(root->fs_info, NO_HOLES);
+ u64 ino_size = round_up(inode->i_size, PAGE_CACHE_SIZE);
ret = btrfs_wait_ordered_range(inode, offset, len);
if (ret)
* entire page.
*/
if (same_page && len < PAGE_CACHE_SIZE) {
- if (offset < round_up(inode->i_size, PAGE_CACHE_SIZE))
+ if (offset < ino_size)
ret = btrfs_truncate_page(inode, offset, len, 0);
mutex_unlock(&inode->i_mutex);
return ret;
}
/* zero back part of the first page */
- if (offset < round_up(inode->i_size, PAGE_CACHE_SIZE)) {
+ if (offset < ino_size) {
ret = btrfs_truncate_page(inode, offset, 0, 0);
if (ret) {
mutex_unlock(&inode->i_mutex);
}
/* zero the front end of the last page */
- if (offset + len < round_up(inode->i_size, PAGE_CACHE_SIZE)) {
+ if (offset + len < ino_size) {
ret = btrfs_truncate_page(inode, offset + len, 0, 1);
if (ret) {
mutex_unlock(&inode->i_mutex);
trans->block_rsv = &root->fs_info->trans_block_rsv;
- ret = fill_holes(trans, inode, path, cur_offset, drop_end);
- if (ret) {
- err = ret;
- break;
+ if (cur_offset < ino_size) {
+ ret = fill_holes(trans, inode, path, cur_offset,
+ drop_end);
+ if (ret) {
+ err = ret;
+ break;
+ }
}
cur_offset = drop_end;
}
trans->block_rsv = &root->fs_info->trans_block_rsv;
- ret = fill_holes(trans, inode, path, cur_offset, drop_end);
- if (ret) {
- err = ret;
- goto out_trans;
+ if (cur_offset < ino_size) {
+ ret = fill_holes(trans, inode, path, cur_offset, drop_end);
+ if (ret) {
+ err = ret;
+ goto out_trans;
+ }
}
out_trans:
if (btrfs_is_free_space_inode(inode)) {
WARN_ON_ONCE(1);
- return -EINVAL;
+ ret = -EINVAL;
+ goto out_unlock;
}
num_bytes = ALIGN(end - start + 1, blocksize);
async_cow->end = cur_end;
INIT_LIST_HEAD(&async_cow->extents);
- async_cow->work.func = async_cow_start;
- async_cow->work.ordered_func = async_cow_submit;
- async_cow->work.ordered_free = async_cow_free;
- async_cow->work.flags = 0;
+ btrfs_init_work(&async_cow->work, async_cow_start,
+ async_cow_submit, async_cow_free);
nr_pages = (cur_end - start + PAGE_CACHE_SIZE) >>
PAGE_CACHE_SHIFT;
atomic_add(nr_pages, &root->fs_info->async_delalloc_pages);
- btrfs_queue_worker(&root->fs_info->delalloc_workers,
- &async_cow->work);
+ btrfs_queue_work(root->fs_info->delalloc_workers,
+ &async_cow->work);
if (atomic_read(&root->fs_info->async_delalloc_pages) > limit) {
wait_event(root->fs_info->async_submit_wait,
unsigned long bio_flags)
{
struct btrfs_root *root = BTRFS_I(page->mapping->host)->root;
- u64 logical = (u64)bio->bi_sector << 9;
+ u64 logical = (u64)bio->bi_iter.bi_sector << 9;
u64 length = 0;
u64 map_length;
int ret;
if (bio_flags & EXTENT_BIO_COMPRESSED)
return 0;
- length = bio->bi_size;
+ length = bio->bi_iter.bi_size;
map_length = length;
ret = btrfs_map_block(root->fs_info, rw, logical,
&map_length, NULL, 0);
SetPageChecked(page);
page_cache_get(page);
- fixup->work.func = btrfs_writepage_fixup_worker;
+ btrfs_init_work(&fixup->work, btrfs_writepage_fixup_worker, NULL, NULL);
fixup->page = page;
- btrfs_queue_worker(&root->fs_info->fixup_workers, &fixup->work);
+ btrfs_queue_work(root->fs_info->fixup_workers, &fixup->work);
return -EBUSY;
}
return PTR_ERR(root);
}
+ if (btrfs_root_readonly(root)) {
+ srcu_read_unlock(&fs_info->subvol_srcu, index);
+ return 0;
+ }
+
/* step 2: get inode */
key.objectid = backref->inum;
key.type = BTRFS_INODE_ITEM_KEY;
struct inode *inode = page->mapping->host;
struct btrfs_root *root = BTRFS_I(inode)->root;
struct btrfs_ordered_extent *ordered_extent = NULL;
- struct btrfs_workers *workers;
+ struct btrfs_workqueue *workers;
trace_btrfs_writepage_end_io_hook(page, start, end, uptodate);
end - start + 1, uptodate))
return 0;
- ordered_extent->work.func = finish_ordered_fn;
- ordered_extent->work.flags = 0;
+ btrfs_init_work(&ordered_extent->work, finish_ordered_fn, NULL, NULL);
if (btrfs_is_free_space_inode(inode))
- workers = &root->fs_info->endio_freespace_worker;
+ workers = root->fs_info->endio_freespace_worker;
else
- workers = &root->fs_info->endio_write_workers;
- btrfs_queue_worker(workers, &ordered_extent->work);
+ workers = root->fs_info->endio_write_workers;
+ btrfs_queue_work(workers, &ordered_extent->work);
return 0;
}
* these flags set. For all other operations the VFS set these flags
* explicitly if it wants a timestamp update.
*/
- if (newsize != oldsize && (!(mask & (ATTR_CTIME | ATTR_MTIME))))
- inode->i_ctime = inode->i_mtime = current_fs_time(inode->i_sb);
+ if (newsize != oldsize) {
+ inode_inc_iversion(inode);
+ if (!(mask & (ATTR_CTIME | ATTR_MTIME)))
+ inode->i_ctime = inode->i_mtime =
+ current_fs_time(inode->i_sb);
+ }
if (newsize > oldsize) {
truncate_pagecache(inode, newsize);
err = btrfs_dirty_inode(inode);
if (!err && attr->ia_valid & ATTR_MODE)
- err = btrfs_acl_chmod(inode);
+ err = posix_acl_chmod(inode, inode->i_mode);
}
return err;
struct rb_node *node;
ASSERT(inode->i_state & I_FREEING);
- truncate_inode_pages(&inode->i_data, 0);
+ truncate_inode_pages_final(&inode->i_data);
write_lock(&map_tree->lock);
while (!RB_EMPTY_ROOT(&map_tree->map)) {
struct inode *inode;
u64 objectid = 0;
- WARN_ON(btrfs_root_refs(&root->root_item) != 0);
+ if (!test_bit(BTRFS_FS_STATE_ERROR, &root->fs_info->fs_state))
+ WARN_ON(btrfs_root_refs(&root->root_item) != 0);
spin_lock(&root->inode_lock);
again:
}
out_unlock:
btrfs_end_transaction(trans, root);
+ btrfs_balance_delayed_items(root);
btrfs_btree_balance_dirty(root);
if (drop_inode) {
inode_dec_link_count(inode);
inode_dec_link_count(inode);
iput(inode);
}
+ btrfs_balance_delayed_items(root);
btrfs_btree_balance_dirty(root);
return err;
}
}
btrfs_end_transaction(trans, root);
+ btrfs_balance_delayed_items(root);
fail:
if (drop_inode) {
inode_dec_link_count(inode);
btrfs_end_transaction(trans, root);
if (drop_on_err)
iput(inode);
+ btrfs_balance_delayed_items(root);
btrfs_btree_balance_dirty(root);
return err;
}
int ret;
struct extent_buffer *leaf;
struct btrfs_root *root = BTRFS_I(inode)->root;
+ struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
struct btrfs_file_extent_item *fi;
struct btrfs_key key;
u64 disk_bytenr;
if (btrfs_extent_readonly(root, disk_bytenr))
goto out;
+
+ num_bytes = min(offset + *len, extent_end) - offset;
+ if (!nocow && found_type == BTRFS_FILE_EXTENT_PREALLOC) {
+ u64 range_end;
+
+ range_end = round_up(offset + num_bytes, root->sectorsize) - 1;
+ ret = test_range_bit(io_tree, offset, range_end,
+ EXTENT_DELALLOC, 0, NULL);
+ if (ret) {
+ ret = -EAGAIN;
+ goto out;
+ }
+ }
+
btrfs_release_path(path);
/*
*/
disk_bytenr += backref_offset;
disk_bytenr += offset - key.offset;
- num_bytes = min(offset + *len, extent_end) - offset;
if (csum_exist_in_range(root, disk_bytenr, num_bytes))
goto out;
/*
static void btrfs_endio_direct_read(struct bio *bio, int err)
{
struct btrfs_dio_private *dip = bio->bi_private;
- struct bio_vec *bvec_end = bio->bi_io_vec + bio->bi_vcnt - 1;
- struct bio_vec *bvec = bio->bi_io_vec;
+ struct bio_vec *bvec;
struct inode *inode = dip->inode;
struct btrfs_root *root = BTRFS_I(inode)->root;
struct bio *dio_bio;
u32 *csums = (u32 *)dip->csum;
- int index = 0;
u64 start;
+ int i;
start = dip->logical_offset;
- do {
+ bio_for_each_segment_all(bvec, bio, i) {
if (!(BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM)) {
struct page *page = bvec->bv_page;
char *kaddr;
local_irq_restore(flags);
flush_dcache_page(bvec->bv_page);
- if (csum != csums[index]) {
+ if (csum != csums[i]) {
btrfs_err(root->fs_info, "csum failed ino %llu off %llu csum %u expected csum %u",
btrfs_ino(inode), start, csum,
- csums[index]);
+ csums[i]);
err = -EIO;
}
}
start += bvec->bv_len;
- bvec++;
- index++;
- } while (bvec <= bvec_end);
+ }
unlock_extent(&BTRFS_I(inode)->io_tree, dip->logical_offset,
dip->logical_offset + dip->bytes - 1);
if (!ret)
goto out_test;
- ordered->work.func = finish_ordered_fn;
- ordered->work.flags = 0;
- btrfs_queue_worker(&root->fs_info->endio_write_workers,
- &ordered->work);
+ btrfs_init_work(&ordered->work, finish_ordered_fn, NULL, NULL);
+ btrfs_queue_work(root->fs_info->endio_write_workers,
+ &ordered->work);
out_test:
/*
* our bio might span multiple ordered extents. If we haven't
btrfs_err(BTRFS_I(dip->inode)->root->fs_info,
"direct IO failed ino %llu rw %lu sector %#Lx len %u err no %d",
btrfs_ino(dip->inode), bio->bi_rw,
- (unsigned long long)bio->bi_sector, bio->bi_size, err);
+ (unsigned long long)bio->bi_iter.bi_sector,
+ bio->bi_iter.bi_size, err);
dip->errors = 1;
/*
struct bio *bio;
struct bio *orig_bio = dip->orig_bio;
struct bio_vec *bvec = orig_bio->bi_io_vec;
- u64 start_sector = orig_bio->bi_sector;
+ u64 start_sector = orig_bio->bi_iter.bi_sector;
u64 file_offset = dip->logical_offset;
u64 submit_len = 0;
u64 map_length;
int ret = 0;
int async_submit = 0;
- map_length = orig_bio->bi_size;
+ map_length = orig_bio->bi_iter.bi_size;
ret = btrfs_map_block(root->fs_info, rw, start_sector << 9,
&map_length, NULL, 0);
if (ret) {
return -EIO;
}
- if (map_length >= orig_bio->bi_size) {
+ if (map_length >= orig_bio->bi_iter.bi_size) {
bio = orig_bio;
goto submit;
}
bio->bi_private = dip;
bio->bi_end_io = btrfs_end_dio_bio;
- map_length = orig_bio->bi_size;
+ map_length = orig_bio->bi_iter.bi_size;
ret = btrfs_map_block(root->fs_info, rw,
start_sector << 9,
&map_length, NULL, 0);
if (!skip_sum && !write) {
csum_size = btrfs_super_csum_size(root->fs_info->super_copy);
- sum_len = dio_bio->bi_size >> inode->i_sb->s_blocksize_bits;
+ sum_len = dio_bio->bi_iter.bi_size >>
+ inode->i_sb->s_blocksize_bits;
sum_len *= csum_size;
} else {
sum_len = 0;
dip->private = dio_bio->bi_private;
dip->inode = inode;
dip->logical_offset = file_offset;
- dip->bytes = dio_bio->bi_size;
- dip->disk_bytenr = (u64)dio_bio->bi_sector << 9;
+ dip->bytes = dio_bio->bi_iter.bi_size;
+ dip->disk_bytenr = (u64)dio_bio->bi_iter.bi_sector << 9;
io_bio->bi_private = dip;
dip->errors = 0;
dip->orig_bio = io_bio;
smp_mb__after_atomic_inc();
/*
- * The generic stuff only does filemap_write_and_wait_range, which isn't
- * enough if we've written compressed pages to this area, so we need to
- * call btrfs_wait_ordered_range to make absolutely sure that any
- * outstanding dirty pages are on disk.
+ * The generic stuff only does filemap_write_and_wait_range, which
+ * isn't enough if we've written compressed pages to this area, so
+ * we need to flush the dirty pages again to make absolutely sure
+ * that any outstanding dirty pages are on disk.
*/
count = iov_length(iov, nr_segs);
- ret = btrfs_wait_ordered_range(inode, offset, count);
- if (ret)
- return ret;
+ if (test_bit(BTRFS_INODE_HAS_ASYNC_EXTENT,
+ &BTRFS_I(inode)->runtime_flags))
+ filemap_fdatawrite_range(inode->i_mapping, offset, count);
if (rw & WRITE) {
/*
work->inode = inode;
work->wait = wait;
work->delay_iput = delay_iput;
- work->work.func = btrfs_run_delalloc_work;
+ btrfs_init_work(&work->work, btrfs_run_delalloc_work, NULL, NULL);
return work;
}
* some fairly slow code that needs optimization. This walks the list
* of all the inodes with pending delalloc and forces them to disk.
*/
- static int __start_delalloc_inodes(struct btrfs_root *root, int delay_iput)
+ static int __start_delalloc_inodes(struct btrfs_root *root, int delay_iput,
+ int nr)
{
struct btrfs_inode *binode;
struct inode *inode;
INIT_LIST_HEAD(&works);
INIT_LIST_HEAD(&splice);
+ mutex_lock(&root->delalloc_mutex);
spin_lock(&root->delalloc_lock);
list_splice_init(&root->delalloc_inodes, &splice);
while (!list_empty(&splice)) {
else
iput(inode);
ret = -ENOMEM;
- goto out;
+ break;
}
list_add_tail(&work->list, &works);
- btrfs_queue_worker(&root->fs_info->flush_workers,
- &work->work);
-
+ btrfs_queue_work(root->fs_info->flush_workers,
+ &work->work);
+ ret++;
+ if (nr != -1 && ret >= nr)
+ break;
cond_resched();
spin_lock(&root->delalloc_lock);
}
spin_unlock(&root->delalloc_lock);
- list_for_each_entry_safe(work, next, &works, list) {
- list_del_init(&work->list);
- btrfs_wait_and_free_delalloc_work(work);
- }
- return 0;
- out:
list_for_each_entry_safe(work, next, &works, list) {
list_del_init(&work->list);
btrfs_wait_and_free_delalloc_work(work);
list_splice_tail(&splice, &root->delalloc_inodes);
spin_unlock(&root->delalloc_lock);
}
+ mutex_unlock(&root->delalloc_mutex);
return ret;
}
if (test_bit(BTRFS_FS_STATE_ERROR, &root->fs_info->fs_state))
return -EROFS;
- ret = __start_delalloc_inodes(root, delay_iput);
+ ret = __start_delalloc_inodes(root, delay_iput, -1);
+ if (ret > 0)
+ ret = 0;
/*
* the filemap_flush will queue IO into the worker threads, but
* we have to make sure the IO is actually started and that
return ret;
}
- int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, int delay_iput)
+ int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, int delay_iput,
+ int nr)
{
struct btrfs_root *root;
struct list_head splice;
INIT_LIST_HEAD(&splice);
+ mutex_lock(&fs_info->delalloc_root_mutex);
spin_lock(&fs_info->delalloc_root_lock);
list_splice_init(&fs_info->delalloc_roots, &splice);
- while (!list_empty(&splice)) {
+ while (!list_empty(&splice) && nr) {
root = list_first_entry(&splice, struct btrfs_root,
delalloc_root);
root = btrfs_grab_fs_root(root);
&fs_info->delalloc_roots);
spin_unlock(&fs_info->delalloc_root_lock);
- ret = __start_delalloc_inodes(root, delay_iput);
+ ret = __start_delalloc_inodes(root, delay_iput, nr);
btrfs_put_fs_root(root);
- if (ret)
+ if (ret < 0)
goto out;
+ if (nr != -1) {
+ nr -= ret;
+ WARN_ON(nr < 0);
+ }
spin_lock(&fs_info->delalloc_root_lock);
}
spin_unlock(&fs_info->delalloc_root_lock);
+ ret = 0;
atomic_inc(&fs_info->async_submit_draining);
while (atomic_read(&fs_info->nr_async_submits) ||
atomic_read(&fs_info->async_delalloc_pages)) {
atomic_read(&fs_info->async_delalloc_pages) == 0));
}
atomic_dec(&fs_info->async_submit_draining);
- return 0;
out:
if (!list_empty_careful(&splice)) {
spin_lock(&fs_info->delalloc_root_lock);
list_splice_tail(&splice, &fs_info->delalloc_roots);
spin_unlock(&fs_info->delalloc_root_lock);
}
+ mutex_unlock(&fs_info->delalloc_root_mutex);
return ret;
}
.removexattr = btrfs_removexattr,
.permission = btrfs_permission,
.get_acl = btrfs_get_acl,
+ .set_acl = btrfs_set_acl,
.update_time = btrfs_update_time,
};
static const struct inode_operations btrfs_dir_ro_inode_operations = {
.lookup = btrfs_lookup,
.permission = btrfs_permission,
.get_acl = btrfs_get_acl,
+ .set_acl = btrfs_set_acl,
.update_time = btrfs_update_time,
};
.permission = btrfs_permission,
.fiemap = btrfs_fiemap,
.get_acl = btrfs_get_acl,
+ .set_acl = btrfs_set_acl,
.update_time = btrfs_update_time,
};
static const struct inode_operations btrfs_special_inode_operations = {
.listxattr = btrfs_listxattr,
.removexattr = btrfs_removexattr,
.get_acl = btrfs_get_acl,
+ .set_acl = btrfs_set_acl,
.update_time = btrfs_update_time,
};
static const struct inode_operations btrfs_symlink_inode_operations = {
.getxattr = btrfs_getxattr,
.listxattr = btrfs_listxattr,
.removexattr = btrfs_removexattr,
- .get_acl = btrfs_get_acl,
.update_time = btrfs_update_time,
};
#include "props.h"
#include "sysfs.h"
+ #ifdef CONFIG_64BIT
+ /* If we have a 32-bit userspace and 64-bit kernel, then the UAPI
+ * structures are incorrect, as the timespec structure from userspace
+ * is 4 bytes too small. We define these alternatives here to teach
+ * the kernel about the 32-bit struct packing.
+ */
+ struct btrfs_ioctl_timespec_32 {
+ __u64 sec;
+ __u32 nsec;
+ } __attribute__ ((__packed__));
+
+ struct btrfs_ioctl_received_subvol_args_32 {
+ char uuid[BTRFS_UUID_SIZE]; /* in */
+ __u64 stransid; /* in */
+ __u64 rtransid; /* out */
+ struct btrfs_ioctl_timespec_32 stime; /* in */
+ struct btrfs_ioctl_timespec_32 rtime; /* out */
+ __u64 flags; /* in */
+ __u64 reserved[16]; /* in */
+ } __attribute__ ((__packed__));
+
+ #define BTRFS_IOC_SET_RECEIVED_SUBVOL_32 _IOWR(BTRFS_IOCTL_MAGIC, 37, \
+ struct btrfs_ioctl_received_subvol_args_32)
+ #endif
+
+
static int btrfs_clone(struct inode *src, struct inode *inode,
u64 off, u64 olen, u64 olen_aligned, u64 destoff);
return ret;
}
+ static void btrfs_wait_nocow_write(struct btrfs_root *root)
+ {
+ s64 writers;
+ DEFINE_WAIT(wait);
+
+ do {
+ prepare_to_wait(&root->subv_writers->wait, &wait,
+ TASK_UNINTERRUPTIBLE);
+
+ writers = percpu_counter_sum(&root->subv_writers->counter);
+ if (writers)
+ schedule();
+
+ finish_wait(&root->subv_writers->wait, &wait);
+ } while (writers);
+ }
+
static int create_snapshot(struct btrfs_root *root, struct inode *dir,
struct dentry *dentry, char *name, int namelen,
u64 *async_transid, bool readonly,
if (!root->ref_cows)
return -EINVAL;
+ atomic_inc(&root->will_be_snapshoted);
+ smp_mb__after_atomic_inc();
+ btrfs_wait_nocow_write(root);
+
ret = btrfs_start_delalloc_inodes(root, 0);
if (ret)
- return ret;
+ goto out;
btrfs_wait_ordered_extents(root, -1);
pending_snapshot = kzalloc(sizeof(*pending_snapshot), GFP_NOFS);
- if (!pending_snapshot)
- return -ENOMEM;
+ if (!pending_snapshot) {
+ ret = -ENOMEM;
+ goto out;
+ }
btrfs_init_block_rsv(&pending_snapshot->block_rsv,
BTRFS_BLOCK_RSV_TEMP);
&pending_snapshot->qgroup_reserved,
false);
if (ret)
- goto out;
+ goto free;
pending_snapshot->dentry = dentry;
pending_snapshot->root = root;
btrfs_subvolume_release_metadata(BTRFS_I(dir)->root,
&pending_snapshot->block_rsv,
pending_snapshot->qgroup_reserved);
- out:
+ free:
kfree(pending_snapshot);
+ out:
+ atomic_dec(&root->will_be_snapshoted);
return ret;
}
min_key.type = BTRFS_EXTENT_DATA_KEY;
min_key.offset = *off;
- path->keep_locks = 1;
-
while (1) {
+ path->keep_locks = 1;
ret = btrfs_search_forward(root, &min_key, path, newer_than);
if (ret != 0)
goto none;
+ path->keep_locks = 0;
+ btrfs_unlock_up_safe(path, 1);
+ process_slot:
if (min_key.objectid != ino)
goto none;
if (min_key.type != BTRFS_EXTENT_DATA_KEY)
return 0;
}
+ path->slots[0]++;
+ if (path->slots[0] < btrfs_header_nritems(leaf)) {
+ btrfs_item_key_to_cpu(leaf, &min_key, path->slots[0]);
+ goto process_slot;
+ }
+
if (min_key.offset == (u64)-1)
goto none;
read_unlock(&em_tree->lock);
if (!em) {
+ struct extent_state *cached = NULL;
+ u64 end = start + len - 1;
+
/* get the big lock and read metadata off disk */
- lock_extent(io_tree, start, start + len - 1);
+ lock_extent_bits(io_tree, start, end, 0, &cached);
em = btrfs_get_extent(inode, NULL, 0, start, len, 0);
- unlock_extent(io_tree, start, start + len - 1);
+ unlock_extent_cached(io_tree, start, end, &cached, GFP_NOFS);
if (IS_ERR(em))
return NULL;
return false;
next = defrag_lookup_extent(inode, em->start + em->len);
- if (!next || next->block_start >= EXTENT_MAP_LAST_BYTE)
+ if (!next || next->block_start >= EXTENT_MAP_LAST_BYTE ||
+ (em->block_start + em->block_len == next->block_start))
ret = false;
free_extent_map(next);
page_start = page_offset(page);
page_end = page_start + PAGE_CACHE_SIZE - 1;
while (1) {
- lock_extent(tree, page_start, page_end);
+ lock_extent_bits(tree, page_start, page_end,
+ 0, &cached_state);
ordered = btrfs_lookup_ordered_extent(inode,
page_start);
- unlock_extent(tree, page_start, page_end);
+ unlock_extent_cached(tree, page_start, page_end,
+ &cached_state, GFP_NOFS);
if (!ordered)
break;
}
}
- if ((range->flags & BTRFS_DEFRAG_RANGE_START_IO))
+ if ((range->flags & BTRFS_DEFRAG_RANGE_START_IO)) {
filemap_flush(inode->i_mapping);
+ if (test_bit(BTRFS_INODE_HAS_ASYNC_EXTENT,
+ &BTRFS_I(inode)->runtime_flags))
+ filemap_flush(inode->i_mapping);
+ }
if ((range->flags & BTRFS_DEFRAG_RANGE_COMPRESS)) {
/* the filemap_flush will queue IO into the worker threads, but
if (src_inode->i_sb != file_inode(file)->i_sb) {
btrfs_info(BTRFS_I(src_inode)->root->fs_info,
"Snapshot src from another FS");
- ret = -EINVAL;
+ ret = -EXDEV;
} else if (!inode_owner_or_capable(src_inode)) {
/*
* Subvolume creation is not restricted, but snapshots
if (di && !IS_ERR(di)) {
btrfs_dir_item_key_to_cpu(path->nodes[0], di, &key);
if (key.objectid == root->root_key.objectid) {
- ret = -ENOTEMPTY;
+ ret = -EPERM;
+ btrfs_err(root->fs_info, "deleting default subvolume "
+ "%llu is not allowed", key.objectid);
goto out;
}
btrfs_release_path(path);
#define BTRFS_MAX_DEDUPE_LEN (16 * 1024 * 1024)
static long btrfs_ioctl_file_extent_same(struct file *file,
- void __user *argp)
+ struct btrfs_ioctl_same_args __user *argp)
{
- struct btrfs_ioctl_same_args tmp;
struct btrfs_ioctl_same_args *same;
struct btrfs_ioctl_same_extent_info *info;
- struct inode *src = file->f_dentry->d_inode;
- struct file *dst_file = NULL;
- struct inode *dst;
+ struct inode *src = file_inode(file);
u64 off;
u64 len;
int i;
unsigned long size;
u64 bs = BTRFS_I(src)->root->fs_info->sb->s_blocksize;
bool is_admin = capable(CAP_SYS_ADMIN);
+ u16 count;
if (!(file->f_mode & FMODE_READ))
return -EINVAL;
if (ret)
return ret;
- if (copy_from_user(&tmp,
- (struct btrfs_ioctl_same_args __user *)argp,
- sizeof(tmp))) {
+ if (get_user(count, &argp->dest_count)) {
ret = -EFAULT;
goto out;
}
- size = sizeof(tmp) +
- tmp.dest_count * sizeof(struct btrfs_ioctl_same_extent_info);
+ size = offsetof(struct btrfs_ioctl_same_args __user, info[count]);
- same = memdup_user((struct btrfs_ioctl_same_args __user *)argp, size);
+ same = memdup_user(argp, size);
if (IS_ERR(same)) {
ret = PTR_ERR(same);
goto out;
/* pre-format output fields to sane values */
- for (i = 0; i < same->dest_count; i++) {
+ for (i = 0; i < count; i++) {
same->info[i].bytes_deduped = 0ULL;
same->info[i].status = 0;
}
- ret = 0;
- for (i = 0; i < same->dest_count; i++) {
- info = &same->info[i];
-
- dst_file = fget(info->fd);
- if (!dst_file) {
+ for (i = 0, info = same->info; i < count; i++, info++) {
+ struct inode *dst;
+ struct fd dst_file = fdget(info->fd);
+ if (!dst_file.file) {
info->status = -EBADF;
- goto next;
+ continue;
}
+ dst = file_inode(dst_file.file);
- if (!(is_admin || (dst_file->f_mode & FMODE_WRITE))) {
+ if (!(is_admin || (dst_file.file->f_mode & FMODE_WRITE))) {
info->status = -EINVAL;
- goto next;
- }
-
- info->status = -EXDEV;
- if (file->f_path.mnt != dst_file->f_path.mnt)
- goto next;
-
- dst = dst_file->f_dentry->d_inode;
- if (src->i_sb != dst->i_sb)
- goto next;
-
- if (S_ISDIR(dst->i_mode)) {
+ } else if (file->f_path.mnt != dst_file.file->f_path.mnt) {
+ info->status = -EXDEV;
+ } else if (S_ISDIR(dst->i_mode)) {
info->status = -EISDIR;
- goto next;
- }
-
- if (!S_ISREG(dst->i_mode)) {
+ } else if (!S_ISREG(dst->i_mode)) {
info->status = -EACCES;
- goto next;
+ } else {
+ info->status = btrfs_extent_same(src, off, len, dst,
+ info->logical_offset);
+ if (info->status == 0)
+ info->bytes_deduped += len;
}
-
- info->status = btrfs_extent_same(src, off, len, dst,
- info->logical_offset);
- if (info->status == 0)
- info->bytes_deduped += len;
-
-next:
- if (dst_file)
- fput(dst_file);
+ fdput(dst_file);
}
ret = copy_to_user(argp, same, size);
new_key.offset + datal,
1);
if (ret) {
- btrfs_abort_transaction(trans, root,
- ret);
+ if (ret != -EINVAL)
+ btrfs_abort_transaction(trans,
+ root, ret);
btrfs_end_transaction(trans, root);
goto out;
}
* decompress into destination's address_space (the file offset
* may change, so source mapping won't do), then recompress (or
* otherwise reinsert) a subrange.
- * - allow ranges within the same file to be cloned (provided
- * they don't overlap)?
+ *
+ * - split destination inode's inline extents. The inline extents can
+ * be either compressed or non-compressed.
*/
/* the destination must be opened for writing */
return btrfs_qgroup_wait_for_completion(root->fs_info);
}
- static long btrfs_ioctl_set_received_subvol(struct file *file,
- void __user *arg)
+ static long _btrfs_ioctl_set_received_subvol(struct file *file,
+ struct btrfs_ioctl_received_subvol_args *sa)
{
- struct btrfs_ioctl_received_subvol_args *sa = NULL;
struct inode *inode = file_inode(file);
struct btrfs_root *root = BTRFS_I(inode)->root;
struct btrfs_root_item *root_item = &root->root_item;
goto out;
}
- sa = memdup_user(arg, sizeof(*sa));
- if (IS_ERR(sa)) {
- ret = PTR_ERR(sa);
- sa = NULL;
- goto out;
- }
-
/*
* 1 - root item
* 2 - uuid items (received uuid + subvol uuid)
goto out;
}
+ out:
+ up_write(&root->fs_info->subvol_sem);
+ mnt_drop_write_file(file);
+ return ret;
+ }
+
+ #ifdef CONFIG_64BIT
+ static long btrfs_ioctl_set_received_subvol_32(struct file *file,
+ void __user *arg)
+ {
+ struct btrfs_ioctl_received_subvol_args_32 *args32 = NULL;
+ struct btrfs_ioctl_received_subvol_args *args64 = NULL;
+ int ret = 0;
+
+ args32 = memdup_user(arg, sizeof(*args32));
+ if (IS_ERR(args32)) {
+ ret = PTR_ERR(args32);
+ args32 = NULL;
+ goto out;
+ }
+
+ args64 = kmalloc(sizeof(*args64), GFP_NOFS);
+ if (IS_ERR(args64)) {
+ ret = PTR_ERR(args64);
+ args64 = NULL;
+ goto out;
+ }
+
+ memcpy(args64->uuid, args32->uuid, BTRFS_UUID_SIZE);
+ args64->stransid = args32->stransid;
+ args64->rtransid = args32->rtransid;
+ args64->stime.sec = args32->stime.sec;
+ args64->stime.nsec = args32->stime.nsec;
+ args64->rtime.sec = args32->rtime.sec;
+ args64->rtime.nsec = args32->rtime.nsec;
+ args64->flags = args32->flags;
+
+ ret = _btrfs_ioctl_set_received_subvol(file, args64);
+ if (ret)
+ goto out;
+
+ memcpy(args32->uuid, args64->uuid, BTRFS_UUID_SIZE);
+ args32->stransid = args64->stransid;
+ args32->rtransid = args64->rtransid;
+ args32->stime.sec = args64->stime.sec;
+ args32->stime.nsec = args64->stime.nsec;
+ args32->rtime.sec = args64->rtime.sec;
+ args32->rtime.nsec = args64->rtime.nsec;
+ args32->flags = args64->flags;
+
+ ret = copy_to_user(arg, args32, sizeof(*args32));
+ if (ret)
+ ret = -EFAULT;
+
+ out:
+ kfree(args32);
+ kfree(args64);
+ return ret;
+ }
+ #endif
+
+ static long btrfs_ioctl_set_received_subvol(struct file *file,
+ void __user *arg)
+ {
+ struct btrfs_ioctl_received_subvol_args *sa = NULL;
+ int ret = 0;
+
+ sa = memdup_user(arg, sizeof(*sa));
+ if (IS_ERR(sa)) {
+ ret = PTR_ERR(sa);
+ sa = NULL;
+ goto out;
+ }
+
+ ret = _btrfs_ioctl_set_received_subvol(file, sa);
+
+ if (ret)
+ goto out;
+
ret = copy_to_user(arg, sa, sizeof(*sa));
if (ret)
ret = -EFAULT;
out:
kfree(sa);
- up_write(&root->fs_info->subvol_sem);
- mnt_drop_write_file(file);
return ret;
}
case BTRFS_IOC_SYNC: {
int ret;
- ret = btrfs_start_delalloc_roots(root->fs_info, 0);
+ ret = btrfs_start_delalloc_roots(root->fs_info, 0, -1);
if (ret)
return ret;
ret = btrfs_sync_fs(file->f_dentry->d_sb, 1);
return btrfs_ioctl_balance_progress(root, argp);
case BTRFS_IOC_SET_RECEIVED_SUBVOL:
return btrfs_ioctl_set_received_subvol(file, argp);
+ #ifdef CONFIG_64BIT
+ case BTRFS_IOC_SET_RECEIVED_SUBVOL_32:
+ return btrfs_ioctl_set_received_subvol_32(file, argp);
+ #endif
case BTRFS_IOC_SEND:
return btrfs_ioctl_send(file, argp);
case BTRFS_IOC_GET_DEV_STATS:
/* see if we can add this page onto our existing bio */
if (last) {
- last_end = (u64)last->bi_sector << 9;
- last_end += last->bi_size;
+ last_end = (u64)last->bi_iter.bi_sector << 9;
+ last_end += last->bi_iter.bi_size;
/*
* we can't merge these if they are from different
if (!bio)
return -ENOMEM;
- bio->bi_size = 0;
+ bio->bi_iter.bi_size = 0;
bio->bi_bdev = stripe->dev->bdev;
- bio->bi_sector = disk_start >> 9;
+ bio->bi_iter.bi_sector = disk_start >> 9;
set_bit(BIO_UPTODATE, &bio->bi_flags);
bio_add_page(bio, page, PAGE_CACHE_SIZE, 0);
spin_lock_irq(&rbio->bio_list_lock);
bio_list_for_each(bio, &rbio->bio_list) {
- start = (u64)bio->bi_sector << 9;
+ start = (u64)bio->bi_iter.bi_sector << 9;
stripe_offset = start - rbio->raid_map[0];
page_index = stripe_offset >> PAGE_CACHE_SHIFT;
static int find_bio_stripe(struct btrfs_raid_bio *rbio,
struct bio *bio)
{
- u64 physical = bio->bi_sector;
+ u64 physical = bio->bi_iter.bi_sector;
u64 stripe_start;
int i;
struct btrfs_bio_stripe *stripe;
static int find_logical_bio_stripe(struct btrfs_raid_bio *rbio,
struct bio *bio)
{
- u64 logical = bio->bi_sector;
+ u64 logical = bio->bi_iter.bi_sector;
u64 stripe_start;
int i;
static void async_rmw_stripe(struct btrfs_raid_bio *rbio)
{
- rbio->work.flags = 0;
- rbio->work.func = rmw_work;
+ btrfs_init_work(&rbio->work, rmw_work, NULL, NULL);
- btrfs_queue_worker(&rbio->fs_info->rmw_workers,
- &rbio->work);
+ btrfs_queue_work(rbio->fs_info->rmw_workers,
+ &rbio->work);
}
static void async_read_rebuild(struct btrfs_raid_bio *rbio)
{
- rbio->work.flags = 0;
- rbio->work.func = read_rebuild_work;
+ btrfs_init_work(&rbio->work, read_rebuild_work, NULL, NULL);
- btrfs_queue_worker(&rbio->fs_info->rmw_workers,
- &rbio->work);
+ btrfs_queue_work(rbio->fs_info->rmw_workers,
+ &rbio->work);
}
/*
plug_list);
struct btrfs_raid_bio *rb = container_of(b, struct btrfs_raid_bio,
plug_list);
- u64 a_sector = ra->bio_list.head->bi_sector;
- u64 b_sector = rb->bio_list.head->bi_sector;
+ u64 a_sector = ra->bio_list.head->bi_iter.bi_sector;
+ u64 b_sector = rb->bio_list.head->bi_iter.bi_sector;
if (a_sector < b_sector)
return -1;
plug = container_of(cb, struct btrfs_plug_cb, cb);
if (from_schedule) {
- plug->work.flags = 0;
- plug->work.func = unplug_work;
- btrfs_queue_worker(&plug->info->rmw_workers,
- &plug->work);
+ btrfs_init_work(&plug->work, unplug_work, NULL, NULL);
+ btrfs_queue_work(plug->info->rmw_workers,
+ &plug->work);
return;
}
run_plug(plug);
if (IS_ERR(rbio))
return PTR_ERR(rbio);
bio_list_add(&rbio->bio_list, bio);
- rbio->bio_list_bytes = bio->bi_size;
+ rbio->bio_list_bytes = bio->bi_iter.bi_size;
/*
* don't plug on full rbios, just get them out the door
rbio->read_rebuild = 1;
bio_list_add(&rbio->bio_list, bio);
- rbio->bio_list_bytes = bio->bi_size;
+ rbio->bio_list_bytes = bio->bi_iter.bi_size;
rbio->faila = find_logical_bio_stripe(rbio, bio);
if (rbio->faila == -1) {
atomic_inc(&fs_info->scrubs_running);
atomic_inc(&fs_info->scrubs_paused);
mutex_unlock(&fs_info->scrub_lock);
+
+ /*
+ * check if @scrubs_running=@scrubs_paused condition
+ * inside wait_event() is not an atomic operation.
+ * which means we may inc/dec @scrub_running/paused
+ * at any time. Let's wake up @scrub_pause_wait as
+ * much as we can to let commit transaction blocked less.
+ */
+ wake_up(&fs_info->scrub_pause_wait);
+
atomic_inc(&sctx->workers_pending);
}
sbio->index = i;
sbio->sctx = sctx;
sbio->page_count = 0;
- sbio->work.func = scrub_bio_end_io_worker;
+ btrfs_init_work(&sbio->work, scrub_bio_end_io_worker,
+ NULL, NULL);
if (i != SCRUB_BIOS_PER_SCTX - 1)
sctx->bios[i]->next_free = i + 1;
fixup_nodatasum->root = fs_info->extent_root;
fixup_nodatasum->mirror_num = failed_mirror_index + 1;
scrub_pending_trans_workers_inc(sctx);
- fixup_nodatasum->work.func = scrub_fixup_nodatasum;
- btrfs_queue_worker(&fs_info->scrub_workers,
- &fixup_nodatasum->work);
+ btrfs_init_work(&fixup_nodatasum->work, scrub_fixup_nodatasum,
+ NULL, NULL);
+ btrfs_queue_work(fs_info->scrub_workers,
+ &fixup_nodatasum->work);
goto out;
}
continue;
}
bio->bi_bdev = page->dev->bdev;
- bio->bi_sector = page->physical >> 9;
+ bio->bi_iter.bi_sector = page->physical >> 9;
bio_add_page(bio, page->page, PAGE_SIZE, 0);
if (btrfsic_submit_bio_wait(READ, bio))
if (!bio)
return -EIO;
bio->bi_bdev = page_bad->dev->bdev;
- bio->bi_sector = page_bad->physical >> 9;
+ bio->bi_iter.bi_sector = page_bad->physical >> 9;
ret = bio_add_page(bio, page_good->page, PAGE_SIZE, 0);
if (PAGE_SIZE != ret) {
bio->bi_private = sbio;
bio->bi_end_io = scrub_wr_bio_end_io;
bio->bi_bdev = sbio->dev->bdev;
- bio->bi_sector = sbio->physical >> 9;
+ bio->bi_iter.bi_sector = sbio->physical >> 9;
sbio->err = 0;
} else if (sbio->physical + sbio->page_count * PAGE_SIZE !=
spage->physical_for_dev_replace ||
sbio->err = err;
sbio->bio = bio;
- sbio->work.func = scrub_wr_bio_end_io_worker;
- btrfs_queue_worker(&fs_info->scrub_wr_completion_workers, &sbio->work);
+ btrfs_init_work(&sbio->work, scrub_wr_bio_end_io_worker, NULL, NULL);
+ btrfs_queue_work(fs_info->scrub_wr_completion_workers, &sbio->work);
}
static void scrub_wr_bio_end_io_worker(struct btrfs_work *work)
bio->bi_private = sbio;
bio->bi_end_io = scrub_bio_end_io;
bio->bi_bdev = sbio->dev->bdev;
- bio->bi_sector = sbio->physical >> 9;
+ bio->bi_iter.bi_sector = sbio->physical >> 9;
sbio->err = 0;
} else if (sbio->physical + sbio->page_count * PAGE_SIZE !=
spage->physical ||
sbio->err = err;
sbio->bio = bio;
- btrfs_queue_worker(&fs_info->scrub_workers, &sbio->work);
+ btrfs_queue_work(fs_info->scrub_workers, &sbio->work);
}
static void scrub_bio_end_io_worker(struct btrfs_work *work)
wait_event(sctx->list_wait,
atomic_read(&sctx->bios_in_flight) == 0);
- atomic_set(&sctx->wr_ctx.flush_all_writes, 0);
+ atomic_inc(&fs_info->scrubs_paused);
+ wake_up(&fs_info->scrub_pause_wait);
+
+ /*
+ * must be called before we decrease @scrub_paused.
+ * make sure we don't block transaction commit while
+ * we are waiting pending workers finished.
+ */
wait_event(sctx->list_wait,
atomic_read(&sctx->workers_pending) == 0);
- scrub_blocked_if_needed(fs_info);
+ atomic_set(&sctx->wr_ctx.flush_all_writes, 0);
+
+ mutex_lock(&fs_info->scrub_lock);
+ __scrub_blocked_if_needed(fs_info);
+ atomic_dec(&fs_info->scrubs_paused);
+ mutex_unlock(&fs_info->scrub_lock);
+ wake_up(&fs_info->scrub_pause_wait);
btrfs_put_block_group(cache);
if (ret)
int is_dev_replace)
{
int ret = 0;
+ int flags = WQ_FREEZABLE | WQ_UNBOUND;
+ int max_active = fs_info->thread_pool_size;
if (fs_info->scrub_workers_refcnt == 0) {
if (is_dev_replace)
- btrfs_init_workers(&fs_info->scrub_workers, "scrub", 1,
- &fs_info->generic_worker);
+ fs_info->scrub_workers =
+ btrfs_alloc_workqueue("btrfs-scrub", flags,
+ 1, 4);
else
- btrfs_init_workers(&fs_info->scrub_workers, "scrub",
- fs_info->thread_pool_size,
- &fs_info->generic_worker);
- fs_info->scrub_workers.idle_thresh = 4;
- ret = btrfs_start_workers(&fs_info->scrub_workers);
- if (ret)
+ fs_info->scrub_workers =
+ btrfs_alloc_workqueue("btrfs-scrub", flags,
+ max_active, 4);
+ if (!fs_info->scrub_workers) {
+ ret = -ENOMEM;
goto out;
- btrfs_init_workers(&fs_info->scrub_wr_completion_workers,
- "scrubwrc",
- fs_info->thread_pool_size,
- &fs_info->generic_worker);
- fs_info->scrub_wr_completion_workers.idle_thresh = 2;
- ret = btrfs_start_workers(
- &fs_info->scrub_wr_completion_workers);
- if (ret)
+ }
+ fs_info->scrub_wr_completion_workers =
+ btrfs_alloc_workqueue("btrfs-scrubwrc", flags,
+ max_active, 2);
+ if (!fs_info->scrub_wr_completion_workers) {
+ ret = -ENOMEM;
goto out;
- btrfs_init_workers(&fs_info->scrub_nocow_workers, "scrubnc", 1,
- &fs_info->generic_worker);
- ret = btrfs_start_workers(&fs_info->scrub_nocow_workers);
- if (ret)
+ }
+ fs_info->scrub_nocow_workers =
+ btrfs_alloc_workqueue("btrfs-scrubnc", flags, 1, 0);
+ if (!fs_info->scrub_nocow_workers) {
+ ret = -ENOMEM;
goto out;
+ }
}
++fs_info->scrub_workers_refcnt;
out:
static noinline_for_stack void scrub_workers_put(struct btrfs_fs_info *fs_info)
{
if (--fs_info->scrub_workers_refcnt == 0) {
- btrfs_stop_workers(&fs_info->scrub_workers);
- btrfs_stop_workers(&fs_info->scrub_wr_completion_workers);
- btrfs_stop_workers(&fs_info->scrub_nocow_workers);
+ btrfs_destroy_workqueue(fs_info->scrub_workers);
+ btrfs_destroy_workqueue(fs_info->scrub_wr_completion_workers);
+ btrfs_destroy_workqueue(fs_info->scrub_nocow_workers);
}
WARN_ON(fs_info->scrub_workers_refcnt < 0);
}
nocow_ctx->len = len;
nocow_ctx->mirror_num = mirror_num;
nocow_ctx->physical_for_dev_replace = physical_for_dev_replace;
- nocow_ctx->work.func = copy_nocow_pages_worker;
+ btrfs_init_work(&nocow_ctx->work, copy_nocow_pages_worker, NULL, NULL);
INIT_LIST_HEAD(&nocow_ctx->inodes);
- btrfs_queue_worker(&fs_info->scrub_nocow_workers,
- &nocow_ctx->work);
+ btrfs_queue_work(fs_info->scrub_nocow_workers,
+ &nocow_ctx->work);
return 0;
}
spin_unlock(&sctx->stat_lock);
return -ENOMEM;
}
- bio->bi_size = 0;
- bio->bi_sector = physical_for_dev_replace >> 9;
+ bio->bi_iter.bi_size = 0;
+ bio->bi_iter.bi_sector = physical_for_dev_replace >> 9;
bio->bi_bdev = dev->bdev;
ret = bio_add_page(bio, page, PAGE_CACHE_SIZE, 0);
if (ret != PAGE_CACHE_SIZE) {
device->running_pending = 1;
spin_unlock(&device->io_lock);
- btrfs_requeue_work(&device->work);
+ btrfs_queue_work(fs_info->submit_workers,
+ &device->work);
goto done;
}
/* unplug every 64 requests just for good measure */
static void btrfs_end_bio(struct bio *bio, int err)
{
struct btrfs_bio *bbio = bio->bi_private;
+ struct btrfs_device *dev = bbio->stripes[0].dev;
int is_orig_bio = 0;
if (err) {
if (err == -EIO || err == -EREMOTEIO) {
unsigned int stripe_index =
btrfs_io_bio(bio)->stripe_index;
- struct btrfs_device *dev;
BUG_ON(stripe_index >= bbio->num_stripes);
dev = bbio->stripes[stripe_index].dev;
if (bio == bbio->orig_bio)
is_orig_bio = 1;
+ btrfs_bio_counter_dec(bbio->fs_info);
+
if (atomic_dec_and_test(&bbio->stripes_pending)) {
if (!is_orig_bio) {
bio_put(bio);
bio = bbio->orig_bio;
}
+
+ /*
+ * We have original bio now. So increment bi_remaining to
+ * account for it in endio
+ */
+ atomic_inc(&bio->bi_remaining);
+
bio->bi_private = bbio->private;
bio->bi_end_io = bbio->end_io;
btrfs_io_bio(bio)->mirror_num = bbio->mirror_num;
}
}
- struct async_sched {
- struct bio *bio;
- int rw;
- struct btrfs_fs_info *info;
- struct btrfs_work work;
- };
-
/*
* see run_scheduled_bios for a description of why bios are collected for
* async submit.
spin_unlock(&device->io_lock);
if (should_queue)
- btrfs_queue_worker(&root->fs_info->submit_workers,
- &device->work);
+ btrfs_queue_work(root->fs_info->submit_workers,
+ &device->work);
}
static int bio_size_ok(struct block_device *bdev, struct bio *bio,
if (!q->merge_bvec_fn)
return 1;
- bvm.bi_size = bio->bi_size - prev->bv_len;
+ bvm.bi_size = bio->bi_iter.bi_size - prev->bv_len;
if (q->merge_bvec_fn(q, &bvm, prev) < prev->bv_len)
return 0;
return 1;
bio->bi_private = bbio;
btrfs_io_bio(bio)->stripe_index = dev_nr;
bio->bi_end_io = btrfs_end_bio;
- bio->bi_sector = physical >> 9;
+ bio->bi_iter.bi_sector = physical >> 9;
#ifdef DEBUG
{
struct rcu_string *name;
}
#endif
bio->bi_bdev = dev->bdev;
+
+ btrfs_bio_counter_inc_noblocked(root->fs_info);
+
if (async)
btrfs_schedule_bio(root, dev, rw, bio);
else
while (bvec <= (first_bio->bi_io_vec + first_bio->bi_vcnt - 1)) {
if (bio_add_page(bio, bvec->bv_page, bvec->bv_len,
bvec->bv_offset) < bvec->bv_len) {
- u64 len = bio->bi_size;
+ u64 len = bio->bi_iter.bi_size;
atomic_inc(&bbio->stripes_pending);
submit_stripe_bio(root, bbio, bio, physical, dev_nr,
bio->bi_private = bbio->private;
bio->bi_end_io = bbio->end_io;
btrfs_io_bio(bio)->mirror_num = bbio->mirror_num;
- bio->bi_sector = logical >> 9;
+ bio->bi_iter.bi_sector = logical >> 9;
kfree(bbio);
bio_endio(bio, -EIO);
}
{
struct btrfs_device *dev;
struct bio *first_bio = bio;
- u64 logical = (u64)bio->bi_sector << 9;
+ u64 logical = (u64)bio->bi_iter.bi_sector << 9;
u64 length = 0;
u64 map_length;
u64 *raid_map = NULL;
int total_devs = 1;
struct btrfs_bio *bbio = NULL;
- length = bio->bi_size;
+ length = bio->bi_iter.bi_size;
map_length = length;
+ btrfs_bio_counter_inc_blocked(root->fs_info);
ret = __btrfs_map_block(root->fs_info, rw, logical, &map_length, &bbio,
mirror_num, &raid_map);
- if (ret) /* -ENOMEM */
+ if (ret) {
+ btrfs_bio_counter_dec(root->fs_info);
return ret;
+ }
total_devs = bbio->num_stripes;
bbio->orig_bio = first_bio;
bbio->private = first_bio->bi_private;
bbio->end_io = first_bio->bi_end_io;
+ bbio->fs_info = root->fs_info;
atomic_set(&bbio->stripes_pending, bbio->num_stripes);
if (raid_map) {
/* In this case, map_length has been set to the length of
a single stripe; not the whole write */
if (rw & WRITE) {
- return raid56_parity_write(root, bio, bbio,
- raid_map, map_length);
+ ret = raid56_parity_write(root, bio, bbio,
+ raid_map, map_length);
} else {
- return raid56_parity_recover(root, bio, bbio,
- raid_map, map_length,
- mirror_num);
+ ret = raid56_parity_recover(root, bio, bbio,
+ raid_map, map_length,
+ mirror_num);
}
+ /*
+ * FIXME, replace dosen't support raid56 yet, please fix
+ * it in the future.
+ */
+ btrfs_bio_counter_dec(root->fs_info);
+ return ret;
}
if (map_length < length) {
async_submit);
dev_nr++;
}
+ btrfs_bio_counter_dec(root->fs_info);
return 0;
}
else
generate_random_uuid(dev->uuid);
- dev->work.func = pending_bios_fn;
+ btrfs_init_work(&dev->work, pending_bios_fn, NULL, NULL);
return dev;
}
projects / cascardo / linux.git / commitdiff