summaryrefslogtreecommitdiffstats
path: root/fs/btrfs
diff options
context:
space:
mode:
Diffstat (limited to 'fs/btrfs')
-rw-r--r--fs/btrfs/async-thread.c122
-rw-r--r--fs/btrfs/async-thread.h4
-rw-r--r--fs/btrfs/backref.c2
-rw-r--r--fs/btrfs/ctree.c17
-rw-r--r--fs/btrfs/ctree.h11
-rw-r--r--fs/btrfs/delayed-inode.c4
-rw-r--r--fs/btrfs/disk-io.c189
-rw-r--r--fs/btrfs/extent-tree.c290
-rw-r--r--fs/btrfs/extent_io.c60
-rw-r--r--fs/btrfs/extent_io.h2
-rw-r--r--fs/btrfs/file.c8
-rw-r--r--fs/btrfs/free-space-cache.c65
-rw-r--r--fs/btrfs/inode.c208
-rw-r--r--fs/btrfs/ioctl.c45
-rw-r--r--fs/btrfs/relocation.c2
-rw-r--r--fs/btrfs/scrub.c15
-rw-r--r--fs/btrfs/super.c81
-rw-r--r--fs/btrfs/transaction.c8
-rw-r--r--fs/btrfs/volumes.c10
-rw-r--r--fs/btrfs/volumes.h6
20 files changed, 755 insertions, 394 deletions
diff --git a/fs/btrfs/async-thread.c b/fs/btrfs/async-thread.c
index 7ec14097fef1..0cc20b35c1c4 100644
--- a/fs/btrfs/async-thread.c
+++ b/fs/btrfs/async-thread.c
@@ -64,6 +64,8 @@ struct btrfs_worker_thread {
int idle;
};
+static int __btrfs_start_workers(struct btrfs_workers *workers);
+
/*
* btrfs_start_workers uses kthread_run, which can block waiting for memory
* for a very long time. It will actually throttle on page writeback,
@@ -88,27 +90,10 @@ 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);
+ __btrfs_start_workers(start->queue);
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.
@@ -153,12 +138,20 @@ static void check_busy_worker(struct btrfs_worker_thread *worker)
static void check_pending_worker_creates(struct btrfs_worker_thread *worker)
{
struct btrfs_workers *workers = worker->workers;
+ struct worker_start *start;
unsigned long flags;
rmb();
if (!workers->atomic_start_pending)
return;
+ start = kzalloc(sizeof(*start), GFP_NOFS);
+ if (!start)
+ return;
+
+ start->work.func = start_new_worker_func;
+ start->queue = workers;
+
spin_lock_irqsave(&workers->lock, flags);
if (!workers->atomic_start_pending)
goto out;
@@ -170,10 +163,11 @@ static void check_pending_worker_creates(struct btrfs_worker_thread *worker)
workers->num_workers_starting += 1;
spin_unlock_irqrestore(&workers->lock, flags);
- start_new_worker(workers);
+ btrfs_queue_worker(workers->atomic_worker_start, &start->work);
return;
out:
+ kfree(start);
spin_unlock_irqrestore(&workers->lock, flags);
}
@@ -331,7 +325,7 @@ again:
run_ordered_completions(worker->workers, work);
check_pending_worker_creates(worker);
-
+ cond_resched();
}
spin_lock_irq(&worker->lock);
@@ -340,7 +334,7 @@ again:
if (freezing(current)) {
worker->working = 0;
spin_unlock_irq(&worker->lock);
- refrigerator();
+ try_to_freeze();
} else {
spin_unlock_irq(&worker->lock);
if (!kthread_should_stop()) {
@@ -462,56 +456,55 @@ void btrfs_init_workers(struct btrfs_workers *workers, char *name, int max,
* starts new worker threads. This does not enforce the max worker
* count in case you need to temporarily go past it.
*/
-static int __btrfs_start_workers(struct btrfs_workers *workers,
- int num_workers)
+static int __btrfs_start_workers(struct btrfs_workers *workers)
{
struct btrfs_worker_thread *worker;
int ret = 0;
- int i;
- for (i = 0; i < num_workers; i++) {
- worker = kzalloc(sizeof(*worker), GFP_NOFS);
- if (!worker) {
- ret = -ENOMEM;
- goto fail;
- }
+ worker = kzalloc(sizeof(*worker), GFP_NOFS);
+ if (!worker) {
+ ret = -ENOMEM;
+ goto fail;
+ }
- INIT_LIST_HEAD(&worker->pending);
- INIT_LIST_HEAD(&worker->prio_pending);
- INIT_LIST_HEAD(&worker->worker_list);
- spin_lock_init(&worker->lock);
-
- atomic_set(&worker->num_pending, 0);
- atomic_set(&worker->refs, 1);
- worker->workers = workers;
- worker->task = kthread_run(worker_loop, worker,
- "btrfs-%s-%d", workers->name,
- workers->num_workers + i);
- if (IS_ERR(worker->task)) {
- ret = PTR_ERR(worker->task);
- kfree(worker);
- goto fail;
- }
- spin_lock_irq(&workers->lock);
- 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);
+ INIT_LIST_HEAD(&worker->pending);
+ INIT_LIST_HEAD(&worker->prio_pending);
+ INIT_LIST_HEAD(&worker->worker_list);
+ spin_lock_init(&worker->lock);
+
+ atomic_set(&worker->num_pending, 0);
+ atomic_set(&worker->refs, 1);
+ worker->workers = workers;
+ worker->task = kthread_run(worker_loop, worker,
+ "btrfs-%s-%d", workers->name,
+ workers->num_workers + 1);
+ if (IS_ERR(worker->task)) {
+ ret = PTR_ERR(worker->task);
+ kfree(worker);
+ goto fail;
}
+ spin_lock_irq(&workers->lock);
+ 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;
fail:
- btrfs_stop_workers(workers);
+ spin_lock_irq(&workers->lock);
+ workers->num_workers_starting--;
+ spin_unlock_irq(&workers->lock);
return ret;
}
-int btrfs_start_workers(struct btrfs_workers *workers, int num_workers)
+int btrfs_start_workers(struct btrfs_workers *workers)
{
spin_lock_irq(&workers->lock);
- workers->num_workers_starting += num_workers;
+ workers->num_workers_starting++;
spin_unlock_irq(&workers->lock);
- return __btrfs_start_workers(workers, num_workers);
+ return __btrfs_start_workers(workers);
}
/*
@@ -568,9 +561,10 @@ static struct btrfs_worker_thread *find_worker(struct btrfs_workers *workers)
struct btrfs_worker_thread *worker;
unsigned long flags;
struct list_head *fallback;
+ int ret;
-again:
spin_lock_irqsave(&workers->lock, flags);
+again:
worker = next_worker(workers);
if (!worker) {
@@ -584,7 +578,10 @@ again:
workers->num_workers_starting++;
spin_unlock_irqrestore(&workers->lock, flags);
/* we're below the limit, start another worker */
- __btrfs_start_workers(workers, 1);
+ ret = __btrfs_start_workers(workers);
+ spin_lock_irqsave(&workers->lock, flags);
+ if (ret)
+ goto fallback;
goto again;
}
}
@@ -665,7 +662,7 @@ void btrfs_set_work_high_prio(struct btrfs_work *work)
/*
* places a struct btrfs_work into the pending queue of one of the kthreads
*/
-int btrfs_queue_worker(struct btrfs_workers *workers, struct btrfs_work *work)
+void btrfs_queue_worker(struct btrfs_workers *workers, struct btrfs_work *work)
{
struct btrfs_worker_thread *worker;
unsigned long flags;
@@ -673,7 +670,7 @@ int btrfs_queue_worker(struct btrfs_workers *workers, struct btrfs_work *work)
/* don't requeue something already on a list */
if (test_and_set_bit(WORK_QUEUED_BIT, &work->flags))
- goto out;
+ return;
worker = find_worker(workers);
if (workers->ordered) {
@@ -712,7 +709,4 @@ int btrfs_queue_worker(struct btrfs_workers *workers, struct btrfs_work *work)
if (wake)
wake_up_process(worker->task);
spin_unlock_irqrestore(&worker->lock, flags);
-
-out:
- return 0;
}
diff --git a/fs/btrfs/async-thread.h b/fs/btrfs/async-thread.h
index 5077746cf85e..f34cc31fa3c9 100644
--- a/fs/btrfs/async-thread.h
+++ b/fs/btrfs/async-thread.h
@@ -109,8 +109,8 @@ struct btrfs_workers {
char *name;
};
-int btrfs_queue_worker(struct btrfs_workers *workers, struct btrfs_work *work);
-int btrfs_start_workers(struct btrfs_workers *workers, int num_workers);
+void btrfs_queue_worker(struct btrfs_workers *workers, struct btrfs_work *work);
+int btrfs_start_workers(struct btrfs_workers *workers);
int btrfs_stop_workers(struct btrfs_workers *workers);
void btrfs_init_workers(struct btrfs_workers *workers, char *name, int max,
struct btrfs_workers *async_starter);
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index 8855aad3929c..22c64fff1bd5 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -683,7 +683,7 @@ static int inode_to_path(u64 inum, struct btrfs_inode_ref *iref,
return PTR_ERR(fspath);
if (fspath > fspath_min) {
- ipath->fspath->val[i] = (u64)fspath;
+ ipath->fspath->val[i] = (u64)(unsigned long)fspath;
++ipath->fspath->elem_cnt;
ipath->fspath->bytes_left = fspath - fspath_min;
} else {
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 0fe615e4ea38..dede441bdeee 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -514,10 +514,25 @@ static inline int should_cow_block(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct extent_buffer *buf)
{
+ /* ensure we can see the force_cow */
+ smp_rmb();
+
+ /*
+ * We do not need to cow a block if
+ * 1) this block is not created or changed in this transaction;
+ * 2) this block does not belong to TREE_RELOC tree;
+ * 3) the root is not forced COW.
+ *
+ * What is forced COW:
+ * when we create snapshot during commiting the transaction,
+ * after we've finished coping src root, we must COW the shared
+ * block to ensure the metadata consistency.
+ */
if (btrfs_header_generation(buf) == trans->transid &&
!btrfs_header_flag(buf, BTRFS_HEADER_FLAG_WRITTEN) &&
!(root->root_key.objectid != BTRFS_TREE_RELOC_OBJECTID &&
- btrfs_header_flag(buf, BTRFS_HEADER_FLAG_RELOC)))
+ btrfs_header_flag(buf, BTRFS_HEADER_FLAG_RELOC)) &&
+ !root->force_cow)
return 0;
return 1;
}
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index b9ba59ff9292..67385033323d 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -848,7 +848,8 @@ struct btrfs_free_cluster {
enum btrfs_caching_type {
BTRFS_CACHE_NO = 0,
BTRFS_CACHE_STARTED = 1,
- BTRFS_CACHE_FINISHED = 2,
+ BTRFS_CACHE_FAST = 2,
+ BTRFS_CACHE_FINISHED = 3,
};
enum btrfs_disk_cache_state {
@@ -1271,6 +1272,8 @@ struct btrfs_root {
* for stat. It may be used for more later
*/
dev_t anon_dev;
+
+ int force_cow;
};
struct btrfs_ioctl_defrag_range_args {
@@ -2366,6 +2369,9 @@ int btrfs_block_rsv_check(struct btrfs_root *root,
int btrfs_block_rsv_refill(struct btrfs_root *root,
struct btrfs_block_rsv *block_rsv,
u64 min_reserved);
+int btrfs_block_rsv_refill_noflush(struct btrfs_root *root,
+ struct btrfs_block_rsv *block_rsv,
+ u64 min_reserved);
int btrfs_block_rsv_migrate(struct btrfs_block_rsv *src_rsv,
struct btrfs_block_rsv *dst_rsv,
u64 num_bytes);
@@ -2686,7 +2692,8 @@ int btrfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf);
int btrfs_readpage(struct file *file, struct page *page);
void btrfs_evict_inode(struct inode *inode);
int btrfs_write_inode(struct inode *inode, struct writeback_control *wbc);
-void btrfs_dirty_inode(struct inode *inode, int flags);
+int btrfs_dirty_inode(struct inode *inode);
+int btrfs_update_time(struct file *file);
struct inode *btrfs_alloc_inode(struct super_block *sb);
void btrfs_destroy_inode(struct inode *inode);
int btrfs_drop_inode(struct inode *inode);
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index 5b163572e0ca..9c1eccc2c503 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -640,8 +640,8 @@ static int btrfs_delayed_inode_reserve_metadata(
* Now if src_rsv == delalloc_block_rsv we'll let it just steal since
* we're accounted for.
*/
- if (!trans->bytes_reserved &&
- src_rsv != &root->fs_info->delalloc_block_rsv) {
+ if (!src_rsv || (!trans->bytes_reserved &&
+ src_rsv != &root->fs_info->delalloc_block_rsv)) {
ret = btrfs_block_rsv_add_noflush(root, dst_rsv, num_bytes);
/*
* Since we're under a transaction reserve_metadata_bytes could
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 62afe5c5694e..f99a099a7747 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -620,7 +620,7 @@ out:
static int btree_io_failed_hook(struct bio *failed_bio,
struct page *page, u64 start, u64 end,
- u64 mirror_num, struct extent_state *state)
+ int mirror_num, struct extent_state *state)
{
struct extent_io_tree *tree;
unsigned long len;
@@ -1579,9 +1579,7 @@ static int cleaner_kthread(void *arg)
btrfs_run_defrag_inodes(root->fs_info);
}
- if (freezing(current)) {
- refrigerator();
- } else {
+ if (!try_to_freeze()) {
set_current_state(TASK_INTERRUPTIBLE);
if (!kthread_should_stop())
schedule();
@@ -1635,9 +1633,7 @@ sleep:
wake_up_process(root->fs_info->cleaner_kthread);
mutex_unlock(&root->fs_info->transaction_kthread_mutex);
- if (freezing(current)) {
- refrigerator();
- } else {
+ if (!try_to_freeze()) {
set_current_state(TASK_INTERRUPTIBLE);
if (!kthread_should_stop() &&
!btrfs_transaction_blocked(root->fs_info))
@@ -2194,19 +2190,27 @@ struct btrfs_root *open_ctree(struct super_block *sb,
fs_info->endio_meta_write_workers.idle_thresh = 2;
fs_info->readahead_workers.idle_thresh = 2;
- 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);
- btrfs_start_workers(&fs_info->endio_workers, 1);
- 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->endio_freespace_worker, 1);
- btrfs_start_workers(&fs_info->delayed_workers, 1);
- btrfs_start_workers(&fs_info->caching_workers, 1);
- btrfs_start_workers(&fs_info->readahead_workers, 1);
+ /*
+ * 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->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);
+ if (ret) {
+ ret = -ENOMEM;
+ goto fail_sb_buffer;
+ }
fs_info->bdi.ra_pages *= btrfs_super_num_devices(disk_super);
fs_info->bdi.ra_pages = max(fs_info->bdi.ra_pages,
@@ -2573,22 +2577,10 @@ static int write_dev_supers(struct btrfs_device *device,
int errors = 0;
u32 crc;
u64 bytenr;
- int last_barrier = 0;
if (max_mirrors == 0)
max_mirrors = BTRFS_SUPER_MIRROR_MAX;
- /* make sure only the last submit_bh does a barrier */
- if (do_barriers) {
- for (i = 0; i < max_mirrors; i++) {
- bytenr = btrfs_sb_offset(i);
- if (bytenr + BTRFS_SUPER_INFO_SIZE >=
- device->total_bytes)
- break;
- last_barrier = i;
- }
- }
-
for (i = 0; i < max_mirrors; i++) {
bytenr = btrfs_sb_offset(i);
if (bytenr + BTRFS_SUPER_INFO_SIZE >= device->total_bytes)
@@ -2634,17 +2626,136 @@ static int write_dev_supers(struct btrfs_device *device,
bh->b_end_io = btrfs_end_buffer_write_sync;
}
- if (i == last_barrier && do_barriers)
- ret = submit_bh(WRITE_FLUSH_FUA, bh);
- else
- ret = submit_bh(WRITE_SYNC, bh);
-
+ /*
+ * we fua the first super. The others we allow
+ * to go down lazy.
+ */
+ ret = submit_bh(WRITE_FUA, bh);
if (ret)
errors++;
}
return errors < i ? 0 : -1;
}
+/*
+ * endio for the write_dev_flush, this will wake anyone waiting
+ * for the barrier when it is done
+ */
+static void btrfs_end_empty_barrier(struct bio *bio, int err)
+{
+ if (err) {
+ if (err == -EOPNOTSUPP)
+ set_bit(BIO_EOPNOTSUPP, &bio->bi_flags);
+ clear_bit(BIO_UPTODATE, &bio->bi_flags);
+ }
+ if (bio->bi_private)
+ complete(bio->bi_private);
+ bio_put(bio);
+}
+
+/*
+ * trigger flushes for one the devices. If you pass wait == 0, the flushes are
+ * sent down. With wait == 1, it waits for the previous flush.
+ *
+ * any device where the flush fails with eopnotsupp are flagged as not-barrier
+ * capable
+ */
+static int write_dev_flush(struct btrfs_device *device, int wait)
+{
+ struct bio *bio;
+ int ret = 0;
+
+ if (device->nobarriers)
+ return 0;
+
+ if (wait) {
+ bio = device->flush_bio;
+ if (!bio)
+ return 0;
+
+ wait_for_completion(&device->flush_wait);
+
+ if (bio_flagged(bio, BIO_EOPNOTSUPP)) {
+ printk("btrfs: disabling barriers on dev %s\n",
+ device->name);
+ device->nobarriers = 1;
+ }
+ if (!bio_flagged(bio, BIO_UPTODATE)) {
+ ret = -EIO;
+ }
+
+ /* drop the reference from the wait == 0 run */
+ bio_put(bio);
+ device->flush_bio = NULL;
+
+ return ret;
+ }
+
+ /*
+ * one reference for us, and we leave it for the
+ * caller
+ */
+ device->flush_bio = NULL;;
+ bio = bio_alloc(GFP_NOFS, 0);
+ if (!bio)
+ return -ENOMEM;
+
+ bio->bi_end_io = btrfs_end_empty_barrier;
+ bio->bi_bdev = device->bdev;
+ init_completion(&device->flush_wait);
+ bio->bi_private = &device->flush_wait;
+ device->flush_bio = bio;
+
+ bio_get(bio);
+ submit_bio(WRITE_FLUSH, bio);
+
+ return 0;
+}
+
+/*
+ * send an empty flush down to each device in parallel,
+ * then wait for them
+ */
+static int barrier_all_devices(struct btrfs_fs_info *info)
+{
+ struct list_head *head;
+ struct btrfs_device *dev;
+ int errors = 0;
+ int ret;
+
+ /* send down all the barriers */
+ head = &info->fs_devices->devices;
+ list_for_each_entry_rcu(dev, head, dev_list) {
+ if (!dev->bdev) {
+ errors++;
+ continue;
+ }
+ if (!dev->in_fs_metadata || !dev->writeable)
+ continue;
+
+ ret = write_dev_flush(dev, 0);
+ if (ret)
+ errors++;
+ }
+
+ /* wait for all the barriers */
+ list_for_each_entry_rcu(dev, head, dev_list) {
+ if (!dev->bdev) {
+ errors++;
+ continue;
+ }
+ if (!dev->in_fs_metadata || !dev->writeable)
+ continue;
+
+ ret = write_dev_flush(dev, 1);
+ if (ret)
+ errors++;
+ }
+ if (errors)
+ return -EIO;
+ return 0;
+}
+
int write_all_supers(struct btrfs_root *root, int max_mirrors)
{
struct list_head *head;
@@ -2666,6 +2777,10 @@ int write_all_supers(struct btrfs_root *root, int max_mirrors)
mutex_lock(&root->fs_info->fs_devices->device_list_mutex);
head = &root->fs_info->fs_devices->devices;
+
+ if (do_barriers)
+ barrier_all_devices(root->fs_info);
+
list_for_each_entry_rcu(dev, head, dev_list) {
if (!dev->bdev) {
total_errors++;
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index b232150b5b6b..f5fbe576d2ba 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -467,13 +467,59 @@ static int cache_block_group(struct btrfs_block_group_cache *cache,
struct btrfs_root *root,
int load_cache_only)
{
+ DEFINE_WAIT(wait);
struct btrfs_fs_info *fs_info = cache->fs_info;
struct btrfs_caching_control *caching_ctl;
int ret = 0;
- smp_mb();
- if (cache->cached != BTRFS_CACHE_NO)
+ caching_ctl = kzalloc(sizeof(*caching_ctl), GFP_NOFS);
+ BUG_ON(!caching_ctl);
+
+ INIT_LIST_HEAD(&caching_ctl->list);
+ mutex_init(&caching_ctl->mutex);
+ init_waitqueue_head(&caching_ctl->wait);
+ caching_ctl->block_group = cache;
+ caching_ctl->progress = cache->key.objectid;
+ atomic_set(&caching_ctl->count, 1);
+ caching_ctl->work.func = caching_thread;
+
+ spin_lock(&cache->lock);
+ /*
+ * This should be a rare occasion, but this could happen I think in the
+ * case where one thread starts to load the space cache info, and then
+ * some other thread starts a transaction commit which tries to do an
+ * allocation while the other thread is still loading the space cache
+ * info. The previous loop should have kept us from choosing this block
+ * group, but if we've moved to the state where we will wait on caching
+ * block groups we need to first check if we're doing a fast load here,
+ * so we can wait for it to finish, otherwise we could end up allocating
+ * from a block group who's cache gets evicted for one reason or
+ * another.
+ */
+ while (cache->cached == BTRFS_CACHE_FAST) {
+ struct btrfs_caching_control *ctl;
+
+ ctl = cache->caching_ctl;
+ atomic_inc(&ctl->count);
+ prepare_to_wait(&ctl->wait, &wait, TASK_UNINTERRUPTIBLE);
+ spin_unlock(&cache->lock);
+
+ schedule();
+
+ finish_wait(&ctl->wait, &wait);
+ put_caching_control(ctl);
+ spin_lock(&cache->lock);
+ }
+
+ if (cache->cached != BTRFS_CACHE_NO) {
+ spin_unlock(&cache->lock);
+ kfree(caching_ctl);
return 0;
+ }
+ WARN_ON(cache->caching_ctl);
+ cache->caching_ctl = caching_ctl;
+ cache->cached = BTRFS_CACHE_FAST;
+ spin_unlock(&cache->lock);
/*
* We can't do the read from on-disk cache during a commit since we need
@@ -484,56 +530,51 @@ static int cache_block_group(struct btrfs_block_group_cache *cache,
if (trans && (!trans->transaction->in_commit) &&
(root && root != root->fs_info->tree_root) &&
btrfs_test_opt(root, SPACE_CACHE)) {
- spin_lock(&cache->lock);
- if (cache->cached != BTRFS_CACHE_NO) {
- spin_unlock(&cache->lock);
- return 0;
- }
- cache->cached = BTRFS_CACHE_STARTED;
- spin_unlock(&cache->lock);
-
ret = load_free_space_cache(fs_info, cache);
spin_lock(&cache->lock);
if (ret == 1) {
+ cache->caching_ctl = NULL;
cache->cached = BTRFS_CACHE_FINISHED;
cache->last_byte_to_unpin = (u64)-1;
} else {
- cache->cached = BTRFS_CACHE_NO;
+ if (load_cache_only) {
+ cache->caching_ctl = NULL;
+ cache->cached = BTRFS_CACHE_NO;
+ } else {
+ cache->cached = BTRFS_CACHE_STARTED;
+ }
}
spin_unlock(&cache->lock);
+ wake_up(&caching_ctl->wait);
if (ret == 1) {
+ put_caching_control(caching_ctl);
free_excluded_extents(fs_info->extent_root, cache);
return 0;
}
+ } else {
+ /*
+ * We are not going to do the fast caching, set cached to the
+ * appropriate value and wakeup any waiters.
+ */
+ spin_lock(&cache->lock);
+ if (load_cache_only) {
+ cache->caching_ctl = NULL;
+ cache->cached = BTRFS_CACHE_NO;
+ } else {
+ cache->cached = BTRFS_CACHE_STARTED;
+ }
+ spin_unlock(&cache->lock);
+ wake_up(&caching_ctl->wait);
}
- if (load_cache_only)
- return 0;
-
- caching_ctl = kzalloc(sizeof(*caching_ctl), GFP_NOFS);
- BUG_ON(!caching_ctl);
-
- INIT_LIST_HEAD(&caching_ctl->list);
- mutex_init(&caching_ctl->mutex);
- init_waitqueue_head(&caching_ctl->wait);
- caching_ctl->block_group = cache;
- caching_ctl->progress = cache->key.objectid;
- /* one for caching kthread, one for caching block group list */
- atomic_set(&caching_ctl->count, 2);
- caching_ctl->work.func = caching_thread;
-
- spin_lock(&cache->lock);
- if (cache->cached != BTRFS_CACHE_NO) {
- spin_unlock(&cache->lock);
- kfree(caching_ctl);
+ if (load_cache_only) {
+ put_caching_control(caching_ctl);
return 0;
}
- cache->caching_ctl = caching_ctl;
- cache->cached = BTRFS_CACHE_STARTED;
- spin_unlock(&cache->lock);
down_write(&fs_info->extent_commit_sem);
+ atomic_inc(&caching_ctl->count);
list_add_tail(&caching_ctl->list, &fs_info->caching_block_groups);
up_write(&fs_info->extent_commit_sem);
@@ -2781,7 +2822,7 @@ out_free:
btrfs_release_path(path);
out:
spin_lock(&block_group->lock);
- if (!ret)
+ if (!ret && dcs == BTRFS_DC_SETUP)
block_group->cache_generation = trans->transid;
block_group->disk_cache_state = dcs;
spin_unlock(&block_group->lock);
@@ -3847,9 +3888,9 @@ int btrfs_block_rsv_check(struct btrfs_root *root,
return ret;
}
-int btrfs_block_rsv_refill(struct btrfs_root *root,
- struct btrfs_block_rsv *block_rsv,
- u64 min_reserved)
+static inline int __btrfs_block_rsv_refill(struct btrfs_root *root,
+ struct btrfs_block_rsv *block_rsv,
+ u64 min_reserved, int flush)
{
u64 num_bytes = 0;
int ret = -ENOSPC;
@@ -3868,7 +3909,7 @@ int btrfs_block_rsv_refill(struct btrfs_root *root,
if (!ret)
return 0;
- ret = reserve_metadata_bytes(root, block_rsv, num_bytes, 1);
+ ret = reserve_metadata_bytes(root, block_rsv, num_bytes, flush);
if (!ret) {
block_rsv_add_bytes(block_rsv, num_bytes, 0);
return 0;
@@ -3877,6 +3918,20 @@ int btrfs_block_rsv_refill(struct btrfs_root *root,
return ret;
}
+int btrfs_block_rsv_refill(struct btrfs_root *root,
+ struct btrfs_block_rsv *block_rsv,
+ u64 min_reserved)
+{
+ return __btrfs_block_rsv_refill(root, block_rsv, min_reserved, 1);
+}
+
+int btrfs_block_rsv_refill_noflush(struct btrfs_root *root,
+ struct btrfs_block_rsv *block_rsv,
+ u64 min_reserved)
+{
+ return __btrfs_block_rsv_refill(root, block_rsv, min_reserved, 0);
+}
+
int btrfs_block_rsv_migrate(struct btrfs_block_rsv *src_rsv,
struct btrfs_block_rsv *dst_rsv,
u64 num_bytes)
@@ -4149,12 +4204,17 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes)
struct btrfs_root *root = BTRFS_I(inode)->root;
struct btrfs_block_rsv *block_rsv = &root->fs_info->delalloc_block_rsv;
u64 to_reserve = 0;
+ u64 csum_bytes;
unsigned nr_extents = 0;
+ int extra_reserve = 0;
int flush = 1;
int ret;
+ /* Need to be holding the i_mutex here if we aren't free space cache */
if (btrfs_is_free_space_inode(root, inode))
flush = 0;
+ else
+ WARN_ON(!mutex_is_locked(&inode->i_mutex));
if (flush && btrfs_transaction_in_commit(root->fs_info))
schedule_timeout(1);
@@ -4165,11 +4225,9 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes)
BTRFS_I(inode)->outstanding_extents++;
if (BTRFS_I(inode)->outstanding_extents >
- BTRFS_I(inode)->reserved_extents) {
+ BTRFS_I(inode)->reserved_extents)
nr_extents = BTRFS_I(inode)->outstanding_extents -
BTRFS_I(inode)->reserved_extents;
- BTRFS_I(inode)->reserved_extents += nr_extents;
- }
/*
* Add an item to reserve for updating the inode when we complete the
@@ -4177,11 +4235,12 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes)
*/
if (!BTRFS_I(inode)->delalloc_meta_reserved) {
nr_extents++;
- BTRFS_I(inode)->delalloc_meta_reserved = 1;
+ extra_reserve = 1;
}
to_reserve = btrfs_calc_trans_metadata_size(root, nr_extents);
to_reserve += calc_csum_metadata_size(inode, num_bytes, 1);
+ csum_bytes = BTRFS_I(inode)->csum_bytes;
spin_unlock(&BTRFS_I(inode)->lock);
ret = reserve_metadata_bytes(root, block_rsv, to_reserve, flush);
@@ -4191,22 +4250,35 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes)
spin_lock(&BTRFS_I(inode)->lock);
dropped = drop_outstanding_extent(inode);
- to_free = calc_csum_metadata_size(inode, num_bytes, 0);
- spin_unlock(&BTRFS_I(inode)->lock);
- to_free += btrfs_calc_trans_metadata_size(root, dropped);
-
/*
- * Somebody could have come in and twiddled with the
- * reservation, so if we have to free more than we would have
- * reserved from this reservation go ahead and release those
- * bytes.
+ * If the inodes csum_bytes is the same as the original
+ * csum_bytes then we know we haven't raced with any free()ers
+ * so we can just reduce our inodes csum bytes and carry on.
+ * Otherwise we have to do the normal free thing to account for
+ * the case that the free side didn't free up its reserve
+ * because of this outstanding reservation.
*/
- to_free -= to_reserve;
+ if (BTRFS_I(inode)->csum_bytes == csum_bytes)
+ calc_csum_metadata_size(inode, num_bytes, 0);
+ else
+ to_free = calc_csum_metadata_size(inode, num_bytes, 0);
+ spin_unlock(&BTRFS_I(inode)->lock);
+ if (dropped)
+ to_free += btrfs_calc_trans_metadata_size(root, dropped);
+
if (to_free)
btrfs_block_rsv_release(root, block_rsv, to_free);
return ret;
}
+ spin_lock(&BTRFS_I(inode)->lock);
+ if (extra_reserve) {
+ BTRFS_I(inode)->delalloc_meta_reserved = 1;
+ nr_extents--;
+ }
+ BTRFS_I(inode)->reserved_extents += nr_extents;
+ spin_unlock(&BTRFS_I(inode)->lock);
+
block_rsv_add_bytes(block_rsv, to_reserve, 1);
return 0;
@@ -5052,11 +5124,11 @@ static noinline int find_free_extent(struct btrfs_trans_handle *trans,
struct btrfs_root *root = orig_root->fs_info->extent_root;
struct btrfs_free_cluster *last_ptr = NULL;
struct btrfs_block_group_cache *block_group = NULL;
+ struct btrfs_block_group_cache *used_block_group;
int empty_cluster = 2 * 1024 * 1024;
int allowed_chunk_alloc = 0;
int done_chunk_alloc = 0;
struct btrfs_space_info *space_info;
- int last_ptr_loop = 0;
int loop = 0;
int index = 0;
int alloc_type = (data & BTRFS_BLOCK_GROUP_DATA) ?
@@ -5118,6 +5190,7 @@ static noinline int find_free_extent(struct btrfs_trans_handle *trans,
ideal_cache:
block_group = btrfs_lookup_block_group(root->fs_info,
search_start);
+ used_block_group = block_group;
/*
* we don't want to use the block group if it doesn't match our
* allocation bits, or if its not cached.
@@ -5155,6 +5228,7 @@ search:
u64 offset;
int cached;
+ used_block_group = block_group;
btrfs_get_block_group(block_group);
search_start = block_group->key.objectid;
@@ -5178,13 +5252,15 @@ search:
}
have_block_group:
- if (unlikely(block_group->cached == BTRFS_CACHE_NO)) {
+ cached = block_group_cache_done(block_group);
+ if (unlikely(!cached)) {
u64 free_percent;
+ found_uncached_bg = true;
ret = cache_block_group(block_group, trans,
orig_root, 1);
if (block_group->cached == BTRFS_CACHE_FINISHED)
- goto have_block_group;
+ goto alloc;
free_percent = btrfs_block_group_used(&block_group->item);
free_percent *= 100;
@@ -5206,7 +5282,6 @@ have_block_group:
orig_root, 0);
BUG_ON(ret);
}
- found_uncached_bg = true;
/*
* If loop is set for cached only, try the next block
@@ -5216,94 +5291,80 @@ have_block_group:
goto loop;
}
- cached = block_group_cache_done(block_group);
- if (unlikely(!cached))
- found_uncached_bg = true;
-
+alloc:
if (unlikely(block_group->ro))
goto loop;
spin_lock(&block_group->free_space_ctl->tree_lock);
if (cached &&
block_group->free_space_ctl->free_space <
- num_bytes + empty_size) {
+ num_bytes + empty_cluster + empty_size) {
spin_unlock(&block_group->free_space_ctl->tree_lock);
goto loop;
}
spin_unlock(&block_group->free_space_ctl->tree_lock);
/*
- * Ok we want to try and use the cluster allocator, so lets look
- * there, unless we are on LOOP_NO_EMPTY_SIZE, since we will
- * have tried the cluster allocator plenty of times at this
- * point and not have found anything, so we are likely way too
- * fragmented for the clustering stuff to find anything, so lets
- * just skip it and let the allocator find whatever block it can
- * find
+ * Ok we want to try and use the cluster allocator, so
+ * lets look there
*/
- if (last_ptr && loop < LOOP_NO_EMPTY_SIZE) {
+ if (last_ptr) {
/*
* the refill lock keeps out other
* people trying to start a new cluster
*/
spin_lock(&last_ptr->refill_lock);
- if (last_ptr->block_group &&
- (last_ptr->block_group->ro ||
- !block_group_bits(last_ptr->block_group, data))) {
- offset = 0;
+ used_block_group = last_ptr->block_group;
+ if (used_block_group != block_group &&
+ (!used_block_group ||
+ used_block_group->ro ||
+ !block_group_bits(used_block_group, data))) {
+ used_block_group = block_group;
goto refill_cluster;
}
- offset = btrfs_alloc_from_cluster(block_group, last_ptr,
- num_bytes, search_start);
+ if (used_block_group != block_group)
+ btrfs_get_block_group(used_block_group);
+
+ offset = btrfs_alloc_from_cluster(used_block_group,
+ last_ptr, num_bytes, used_block_group->key.objectid);
if (offset) {
/* we have a block, we're done */
spin_unlock(&last_ptr->refill_lock);
goto checks;
}
- spin_lock(&last_ptr->lock);
- /*
- * whoops, this cluster doesn't actually point to
- * this block group. Get a ref on the block
- * group is does point to and try again
- */
- if (!last_ptr_loop && last_ptr->block_group &&
- last_ptr->block_group != block_group &&
- index <=
- get_block_group_index(last_ptr->block_group)) {
-
- btrfs_put_block_group(block_group);
- block_group = last_ptr->block_group;
- btrfs_get_block_group(block_group);
- spin_unlock(&last_ptr->lock);
- spin_unlock(&last_ptr->refill_lock);
-
- last_ptr_loop = 1;
- search_start = block_group->key.objectid;
- /*
- * we know this block group is properly
- * in the list because
- * btrfs_remove_block_group, drops the
- * cluster before it removes the block
- * group from the list
- */
- goto have_block_group;
+ WARN_ON(last_ptr->block_group != used_block_group);
+ if (used_block_group != block_group) {
+ btrfs_put_block_group(used_block_group);
+ used_block_group = block_group;
}
- spin_unlock(&last_ptr->lock);
refill_cluster:
+ BUG_ON(used_block_group != block_group);
+ /* If we are on LOOP_NO_EMPTY_SIZE, we can't
+ * set up a new clusters, so lets just skip it
+ * and let the allocator find whatever block
+ * it can find. If we reach this point, we
+ * will have tried the cluster allocator
+ * plenty of times and not have found
+ * anything, so we are likely way too
+ * fragmented for the clustering stuff to find
+ * anything. */
+ if (loop >= LOOP_NO_EMPTY_SIZE) {
+ spin_unlock(&last_ptr->refill_lock);
+ goto unclustered_alloc;
+ }
+
/*
* this cluster didn't work out, free it and
* start over
*/
btrfs_return_cluster_to_free_space(NULL, last_ptr);
- last_ptr_loop = 0;
-
/* allocate a cluster in this block group */
ret = btrfs_find_space_cluster(trans, root,
block_group, last_ptr,
- offset, num_bytes,
+ search_start, num_bytes,
empty_cluster + empty_size);
if (ret == 0) {
/*
@@ -5339,6 +5400,7 @@ refill_cluster:
goto loop;
}
+unclustered_alloc:
offset = btrfs_find_space_for_alloc(block_group, search_start,
num_bytes, empty_size);
/*
@@ -5365,14 +5427,14 @@ checks:
search_start = stripe_align(root, offset);
/* move on to the next group */
if (search_start + num_bytes >= search_end) {
- btrfs_add_free_space(block_group, offset, num_bytes);
+ btrfs_add_free_space(used_block_group, offset, num_bytes);
goto loop;
}
/* move on to the next group */
if (search_start + num_bytes >
- block_group->key.objectid + block_group->key.offset) {
- btrfs_add_free_space(block_group, offset, num_bytes);
+ used_block_group->key.objectid + used_block_group->key.offset) {
+ btrfs_add_free_space(used_block_group, offset, num_bytes);
goto loop;
}
@@ -5380,14 +5442,14 @@ checks:
ins->offset = num_bytes;
if (offset < search_start)
- btrfs_add_free_space(block_group, offset,
+ btrfs_add_free_space(used_block_group, offset,
search_start - offset);
BUG_ON(offset > search_start);
- ret = btrfs_update_reserved_bytes(block_group, num_bytes,
+ ret = btrfs_update_reserved_bytes(used_block_group, num_bytes,
alloc_type);
if (ret == -EAGAIN) {
- btrfs_add_free_space(block_group, offset, num_bytes);
+ btrfs_add_free_space(used_block_group, offset, num_bytes);
goto loop;
}
@@ -5396,15 +5458,19 @@ checks:
ins->offset = num_bytes;
if (offset < search_start)
- btrfs_add_free_space(block_group, offset,
+ btrfs_add_free_space(used_block_group, offset,
search_start - offset);
BUG_ON(offset > search_start);
+ if (used_block_group != block_group)
+ btrfs_put_block_group(used_block_group);
btrfs_put_block_group(block_group);
break;
loop:
failed_cluster_refill = false;
failed_alloc = false;
BUG_ON(index != get_block_group_index(block_group));
+ if (used_block_group != block_group)
+ btrfs_put_block_group(used_block_group);
btrfs_put_block_group(block_group);
}
up_read(&space_info->groups_sem);
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 1f87c4d0e7a0..49f3c9dc09f4 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -935,8 +935,10 @@ again:
node = tree_search(tree, start);
if (!node) {
prealloc = alloc_extent_state_atomic(prealloc);
- if (!prealloc)
- return -ENOMEM;
+ if (!prealloc) {
+ err = -ENOMEM;
+ goto out;
+ }
err = insert_state(tree, prealloc, start, end, &bits);
prealloc = NULL;
BUG_ON(err == -EEXIST);
@@ -992,8 +994,10 @@ hit_next:
*/
if (state->start < start) {
prealloc = alloc_extent_state_atomic(prealloc);
- if (!prealloc)
- return -ENOMEM;
+ if (!prealloc) {
+ err = -ENOMEM;
+ goto out;
+ }
err = split_state(tree, state, prealloc, start);
BUG_ON(err == -EEXIST);
prealloc = NULL;
@@ -1024,8 +1028,10 @@ hit_next:
this_end = last_start - 1;
prealloc = alloc_extent_state_atomic(prealloc);
- if (!prealloc)
- return -ENOMEM;
+ if (!prealloc) {
+ err = -ENOMEM;
+ goto out;
+ }
/*
* Avoid to free 'prealloc' if it can be merged with
@@ -1051,8 +1057,10 @@ hit_next:
*/
if (state->start <= end && state->end > end) {
prealloc = alloc_extent_state_atomic(prealloc);
- if (!prealloc)
- return -ENOMEM;
+ if (!prealloc) {
+ err = -ENOMEM;
+ goto out;
+ }
err = split_state(tree, state, prealloc, end + 1);
BUG_ON(err == -EEXIST);
@@ -2285,16 +2293,22 @@ static void end_bio_extent_readpage(struct bio *bio, int err)
clean_io_failure(start, page);
}
if (!uptodate) {
- u64 failed_mirror;
- failed_mirror = (u64)bio->bi_bdev;
- if (tree->ops && tree->ops->readpage_io_failed_hook)
- ret = tree->ops->readpage_io_failed_hook(
- bio, page, start, end,
- failed_mirror, state);
- else
- ret = bio_readpage_error(bio, page, start, end,
- failed_mirror, NULL);
+ int failed_mirror;
+ failed_mirror = (int)(unsigned long)bio->bi_bdev;
+ /*
+ * The generic bio_readpage_error handles errors the
+ * following way: If possible, new read requests are
+ * created and submitted and will end up in
+ * end_bio_extent_readpage as well (if we're lucky, not
+ * in the !uptodate case). In that case it returns 0 and
+ * we just go on with the next page in our bio. If it
+ * can't handle the error it will return -EIO and we
+ * remain responsible for that page.
+ */
+ ret = bio_readpage_error(bio, page, start, end,
+ failed_mirror, NULL);
if (ret == 0) {
+error_handled:
uptodate =
test_bit(BIO_UPTODATE, &bio->bi_flags);
if (err)
@@ -2302,6 +2316,13 @@ static void end_bio_extent_readpage(struct bio *bio, int err)
uncache_state(&cached);
continue;
}
+ if (tree->ops && tree->ops->readpage_io_failed_hook) {
+ ret = tree->ops->readpage_io_failed_hook(
+ bio, page, start, end,
+ failed_mirror, state);
+ if (ret == 0)
+ goto error_handled;
+ }
}
if (uptodate) {
@@ -3366,6 +3387,9 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
return -ENOMEM;
path->leave_spinning = 1;
+ start = ALIGN(start, BTRFS_I(inode)->root->sectorsize);
+ len = ALIGN(len, BTRFS_I(inode)->root->sectorsize);
+
/*
* lookup the last file extent. We're not using i_size here
* because there might be preallocation past i_size
@@ -3413,7 +3437,7 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
lock_extent_bits(&BTRFS_I(inode)->io_tree, start, start + len, 0,
&cached_state, GFP_NOFS);
- em = get_extent_skip_holes(inode, off, last_for_get_extent,
+ em = get_extent_skip_holes(inode, start, last_for_get_extent,
get_extent);
if (!em)
goto out;
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index feb9be0e23bc..7604c3001322 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -70,7 +70,7 @@ struct extent_io_ops {
unsigned long bio_flags);
int (*readpage_io_hook)(struct page *page, u64 start, u64 end);
int (*readpage_io_failed_hook)(struct bio *bio, struct page *page,
- u64 start, u64 end, u64 failed_mirror,
+ u64 start, u64 end, int failed_mirror,
struct extent_state *state);
int (*writepage_io_failed_hook)(struct bio *bio, struct page *page,
u64 start, u64 end,
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index dafdfa059bf6..97fbe939c050 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1167,6 +1167,8 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
nrptrs = min((iov_iter_count(i) + PAGE_CACHE_SIZE - 1) /
PAGE_CACHE_SIZE, PAGE_CACHE_SIZE /
(sizeof(struct page *)));
+ nrptrs = min(nrptrs, current->nr_dirtied_pause - current->nr_dirtied);
+ nrptrs = max(nrptrs, 8);
pages = kmalloc(nrptrs * sizeof(struct page *), GFP_KERNEL);
if (!pages)
return -ENOMEM;
@@ -1387,7 +1389,11 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
goto out;
}
- file_update_time(file);
+ err = btrfs_update_time(file);
+ if (err) {
+ mutex_unlock(&inode->i_mutex);
+ goto out;
+ }
BTRFS_I(inode)->sequence++;
start_pos = round_down(pos, root->sectorsize);
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index 75a7b1147764..9a897bf79538 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -351,6 +351,11 @@ static int io_ctl_prepare_pages(struct io_ctl *io_ctl, struct inode *inode,
}
}
+ for (i = 0; i < io_ctl->num_pages; i++) {
+ clear_page_dirty_for_io(io_ctl->pages[i]);
+ set_page_extent_mapped(io_ctl->pages[i]);
+ }
+
return 0;
}
@@ -1465,6 +1470,7 @@ static void add_new_bitmap(struct btrfs_free_space_ctl *ctl,
{
info->offset = offset_to_bitmap(ctl, offset);
info->bytes = 0;
+ INIT_LIST_HEAD(&info->list);
link_free_space(ctl, info);
ctl->total_bitmaps++;
@@ -1844,7 +1850,13 @@ again:
info = tree_search_offset(ctl, offset_to_bitmap(ctl, offset),
1, 0);
if (!info) {
- WARN_ON(1);
+ /* the tree logging code might be calling us before we
+ * have fully loaded the free space rbtree for this
+ * block group. So it is possible the entry won't
+ * be in the rbtree yet at all. The caching code
+ * will make sure not to put it in the rbtree if
+ * the logging code has pinned it.
+ */
goto out_lock;
}
}
@@ -2308,6 +2320,7 @@ again:
if (!found) {
start = i;
+ cluster->max_size = 0;
found = true;
}
@@ -2451,16 +2464,23 @@ setup_cluster_bitmap(struct btrfs_block_group_cache *block_group,
{
struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
struct btrfs_free_space *entry;
- struct rb_node *node;
int ret = -ENOSPC;
+ u64 bitmap_offset = offset_to_bitmap(ctl, offset);
if (ctl->total_bitmaps == 0)
return -ENOSPC;
/*
- * First check our cached list of bitmaps and see if there is an entry
- * here that will work.
+ * The bitmap that covers offset won't be in the list unless offset
+ * is just its start offset.
*/
+ entry = list_first_entry(bitmaps, struct btrfs_free_space, list);
+ if (entry->offset != bitmap_offset) {
+ entry = tree_search_offset(ctl, bitmap_offset, 1, 0);
+ if (entry && list_empty(&entry->list))
+ list_add(&entry->list, bitmaps);
+ }
+
list_for_each_entry(entry, bitmaps, list) {
if (entry->bytes < min_bytes)
continue;
@@ -2471,38 +2491,10 @@ setup_cluster_bitmap(struct btrfs_block_group_cache *block_group,
}
/*
- * If we do have entries on our list and we are here then we didn't find
- * anything, so go ahead and get the next entry after the last entry in
- * this list and start the search from there.
+ * The bitmaps list has all the bitmaps that record free space
+ * starting after offset, so no more search is required.
*/
- if (!list_empty(bitmaps)) {
- entry = list_entry(bitmaps->prev, struct btrfs_free_space,
- list);
- node = rb_next(&entry->offset_index);
- if (!node)
- return -ENOSPC;
- entry = rb_entry(node, struct btrfs_free_space, offset_index);
- goto search;
- }
-
- entry = tree_search_offset(ctl, offset_to_bitmap(ctl, offset), 0, 1);
- if (!entry)
- return -ENOSPC;
-
-search:
- node = &entry->offset_index;
- do {
- entry = rb_entry(node, struct btrfs_free_space, offset_index);
- node = rb_next(&entry->offset_index);
- if (!entry->bitmap)
- continue;
- if (entry->bytes < min_bytes)
- continue;
- ret = btrfs_bitmap_cluster(block_group, entry, cluster, offset,
- bytes, min_bytes);
- } while (ret && node);
-
- return ret;
+ return -ENOSPC;
}
/*
@@ -2520,8 +2512,8 @@ int btrfs_find_space_cluster(struct btrfs_trans_handle *trans,
u64 offset, u64 bytes, u64 empty_size)
{
struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
- struct list_head bitmaps;
struct btrfs_free_space *entry, *tmp;
+ LIST_HEAD(bitmaps);
u64 min_bytes;
int ret;
@@ -2560,7 +2552,6 @@ int btrfs_find_space_cluster(struct btrfs_trans_handle *trans,
goto out;
}
- INIT_LIST_HEAD(&bitmaps);
ret = setup_cluster_no_bitmap(block_group, cluster, &bitmaps, offset,
bytes, min_bytes);
if (ret)
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index c3308c38ae75..81b235a61f8c 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -38,6 +38,7 @@
#include <linux/falloc.h>
#include <linux/slab.h>
#include <linux/ratelimit.h>
+#include <linux/mount.h>
#include "compat.h"
#include "ctree.h"
#include "disk-io.h"
@@ -2031,7 +2032,7 @@ int btrfs_orphan_add(struct btrfs_trans_handle *trans, struct inode *inode)
/* insert an orphan item to track this unlinked/truncated file */
if (insert >= 1) {
ret = btrfs_insert_orphan_item(trans, root, btrfs_ino(inode));
- BUG_ON(ret);
+ BUG_ON(ret && ret != -EEXIST);
}
/* insert an orphan item to track subvolume contains orphan files */
@@ -2158,6 +2159,38 @@ int btrfs_orphan_cleanup(struct btrfs_root *root)
if (ret && ret != -ESTALE)
goto out;
+ if (ret == -ESTALE && root == root->fs_info->tree_root) {
+ struct btrfs_root *dead_root;
+ struct btrfs_fs_info *fs_info = root->fs_info;
+ int is_dead_root = 0;
+
+ /*
+ * this is an orphan in the tree root. Currently these
+ * could come from 2 sources:
+ * a) a snapshot deletion in progress
+ * b) a free space cache inode
+ * We need to distinguish those two, as the snapshot
+ * orphan must not get deleted.
+ * find_dead_roots already ran before us, so if this
+ * is a snapshot deletion, we should find the root
+ * in the dead_roots list
+ */
+ spin_lock(&fs_info->trans_lock);
+ list_for_each_entry(dead_root, &fs_info->dead_roots,
+ root_list) {
+ if (dead_root->root_key.objectid ==
+ found_key.objectid) {
+ is_dead_root = 1;
+ break;
+ }
+ }
+ spin_unlock(&fs_info->trans_lock);
+ if (is_dead_root) {
+ /* prevent this orphan from being found again */
+ key.offset = found_key.objectid - 1;
+ continue;
+ }
+ }
/*
* Inode is already gone but the orphan item is still there,
* kill the orphan item.
@@ -2191,7 +2224,14 @@ int btrfs_orphan_cleanup(struct btrfs_root *root)
continue;
}
nr_truncate++;
+ /*
+ * Need to hold the imutex for reservation purposes, not
+ * a huge deal here but I have a WARN_ON in
+ * btrfs_delalloc_reserve_space to catch offenders.
+ */
+ mutex_lock(&inode->i_mutex);
ret = btrfs_truncate(inode);
+ mutex_unlock(&inode->i_mutex);
} else {
nr_unlink++;
}
@@ -3327,7 +3367,7 @@ int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size)
u64 hint_byte = 0;
hole_size = last_byte - cur_offset;
- trans = btrfs_start_transaction(root, 2);
+ trans = btrfs_start_transaction(root, 3);
if (IS_ERR(trans)) {
err = PTR_ERR(trans);
break;
@@ -3337,6 +3377,7 @@ int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size)
cur_offset + hole_size,
&hint_byte, 1);
if (err) {
+ btrfs_update_inode(trans, root, inode);
btrfs_end_transaction(trans, root);
break;
}
@@ -3346,6 +3387,7 @@ int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size)
0, hole_size, 0, hole_size,
0, 0, 0);
if (err) {
+ btrfs_update_inode(trans, root, inode);
btrfs_end_transaction(trans, root);
break;
}
@@ -3353,6 +3395,7 @@ int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size)
btrfs_drop_extent_cache(inode, hole_start,
last_byte - 1, 0);
+ btrfs_update_inode(trans, root, inode);
btrfs_end_transaction(trans, root);
}
free_extent_map(em);
@@ -3370,6 +3413,8 @@ int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size)
static int btrfs_setsize(struct inode *inode, loff_t newsize)
{
+ struct btrfs_root *root = BTRFS_I(inode)->root;
+ struct btrfs_trans_handle *trans;
loff_t oldsize = i_size_read(inode);
int ret;
@@ -3377,16 +3422,19 @@ static int btrfs_setsize(struct inode *inode, loff_t newsize)
return 0;
if (newsize > oldsize) {
- i_size_write(inode, newsize);
- btrfs_ordered_update_i_size(inode, i_size_read(inode), NULL);
truncate_pagecache(inode, oldsize, newsize);
ret = btrfs_cont_expand(inode, oldsize, newsize);
- if (ret) {
- btrfs_setsize(inode, oldsize);
+ if (ret)
return ret;
- }
- mark_inode_dirty(inode);
+ trans = btrfs_start_transaction(root, 1);
+ if (IS_ERR(trans))
+ return PTR_ERR(trans);
+
+ i_size_write(inode, newsize);
+ btrfs_ordered_update_i_size(inode, i_size_read(inode), NULL);
+ ret = btrfs_update_inode(trans, root, inode);
+ btrfs_end_transaction_throttle(trans, root);
} else {
/*
@@ -3426,9 +3474,9 @@ static int btrfs_setattr(struct dentry *dentry, struct iattr *attr)
if (attr->ia_valid) {
setattr_copy(inode, attr);
- mark_inode_dirty(inode);
+ err = btrfs_dirty_inode(inode);
- if (attr->ia_valid & ATTR_MODE)
+ if (!err && attr->ia_valid & ATTR_MODE)
err = btrfs_acl_chmod(inode);
}
@@ -3490,7 +3538,7 @@ void btrfs_evict_inode(struct inode *inode)
* doing the truncate.
*/
while (1) {
- ret = btrfs_block_rsv_refill(root, rsv, min_size);
+ ret = btrfs_block_rsv_refill_noflush(root, rsv, min_size);
/*
* Try and steal from the global reserve since we will
@@ -4204,42 +4252,80 @@ int btrfs_write_inode(struct inode *inode, struct writeback_control *wbc)
* FIXME, needs more benchmarking...there are no reasons other than performance
* to keep or drop this code.
*/
-void btrfs_dirty_inode(struct inode *inode, int flags)
+int btrfs_dirty_inode(struct inode *inode)
{
struct btrfs_root *root = BTRFS_I(inode)->root;
struct btrfs_trans_handle *trans;
int ret;
if (BTRFS_I(inode)->dummy_inode)
- return;
+ return 0;
trans = btrfs_join_transaction(root);
- BUG_ON(IS_ERR(trans));
+ if (IS_ERR(trans))
+ return PTR_ERR(trans);
ret = btrfs_update_inode(trans, root, inode);
if (ret && ret == -ENOSPC) {
/* whoops, lets try again with the full transaction */
btrfs_end_transaction(trans, root);
trans = btrfs_start_transaction(root, 1);
- if (IS_ERR(trans)) {
- printk_ratelimited(KERN_ERR "btrfs: fail to "
- "dirty inode %llu error %ld\n",
- (unsigned long long)btrfs_ino(inode),
- PTR_ERR(trans));
- return;
- }
+ if (IS_ERR(trans))
+ return PTR_ERR(trans);
ret = btrfs_update_inode(trans, root, inode);
- if (ret) {
- printk_ratelimited(KERN_ERR "btrfs: fail to "
- "dirty inode %llu error %d\n",
- (unsigned long long)btrfs_ino(inode),
- ret);
- }
}
btrfs_end_transaction(trans, root);
if (BTRFS_I(inode)->delayed_node)
btrfs_balance_delayed_items(root);
+
+ return ret;
+}
+
+/*
+ * This is a copy of file_update_time. We need this so we can return error on
+ * ENOSPC for updating the inode in the case of file write and mmap writes.
+ */
+int btrfs_update_time(struct file *file)
+{
+ struct inode *inode = file->f_path.dentry->d_inode;
+ struct timespec now;
+ int ret;
+ enum { S_MTIME = 1, S_CTIME = 2, S_VERSION = 4 } sync_it = 0;
+
+ /* First try to exhaust all avenues to not sync */
+ if (IS_NOCMTIME(inode))
+ return 0;
+
+ now = current_fs_time(inode->i_sb);
+ if (!timespec_equal(&inode->i_mtime, &now))
+ sync_it = S_MTIME;
+
+ if (!timespec_equal(&inode->i_ctime, &now))
+ sync_it |= S_CTIME;
+
+ if (IS_I_VERSION(inode))
+ sync_it |= S_VERSION;
+
+ if (!sync_it)
+ return 0;
+
+ /* Finally allowed to write? Takes lock. */
+ if (mnt_want_write_file(file))
+ return 0;
+
+ /* Only change inode inside the lock region */
+ if (sync_it & S_VERSION)
+ inode_inc_iversion(inode);
+ if (sync_it & S_CTIME)
+ inode->i_ctime = now;
+ if (sync_it & S_MTIME)
+ inode->i_mtime = now;
+ ret = btrfs_dirty_inode(inode);
+ if (!ret)
+ mark_inode_dirty_sync(inode);
+ mnt_drop_write(file->f_path.mnt);
+ return ret;
}
/*
@@ -4326,8 +4412,8 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct inode *dir,
const char *name, int name_len,
- u64 ref_objectid, u64 objectid, int mode,
- u64 *index)
+ u64 ref_objectid, u64 objectid,
+ umode_t mode, u64 *index)
{
struct inode *inode;
struct btrfs_inode_item *inode_item;
@@ -4504,17 +4590,13 @@ static int btrfs_add_nondir(struct btrfs_trans_handle *trans,
int err = btrfs_add_link(trans, dir, inode,
dentry->d_name.name, dentry->d_name.len,
backref, index);
- if (!err) {
- d_instantiate(dentry, inode);
- return 0;
- }
if (err > 0)
err = -EEXIST;
return err;
}
static int btrfs_mknod(struct inode *dir, struct dentry *dentry,
- int mode, dev_t rdev)
+ umode_t mode, dev_t rdev)
{
struct btrfs_trans_handle *trans;
struct btrfs_root *root = BTRFS_I(dir)->root;
@@ -4555,13 +4637,21 @@ static int btrfs_mknod(struct inode *dir, struct dentry *dentry,
goto out_unlock;
}
+ /*
+ * If the active LSM wants to access the inode during
+ * d_instantiate it needs these. Smack checks to see
+ * if the filesystem supports xattrs by looking at the
+ * ops vector.
+ */
+
+ inode->i_op = &btrfs_special_inode_operations;
err = btrfs_add_nondir(trans, dir, dentry, inode, 0, index);
if (err)
drop_inode = 1;
else {
- inode->i_op = &btrfs_special_inode_operations;
init_special_inode(inode, inode->i_mode, rdev);
btrfs_update_inode(trans, root, inode);
+ d_instantiate(dentry, inode);
}
out_unlock:
nr = trans->blocks_used;
@@ -4575,7 +4665,7 @@ out_unlock:
}
static int btrfs_create(struct inode *dir, struct dentry *dentry,
- int mode, struct nameidata *nd)
+ umode_t mode, struct nameidata *nd)
{
struct btrfs_trans_handle *trans;
struct btrfs_root *root = BTRFS_I(dir)->root;
@@ -4613,15 +4703,23 @@ static int btrfs_create(struct inode *dir, struct dentry *dentry,
goto out_unlock;
}
+ /*
+ * If the active LSM wants to access the inode during
+ * d_instantiate it needs these. Smack checks to see
+ * if the filesystem supports xattrs by looking at the
+ * ops vector.
+ */
+ inode->i_fop = &btrfs_file_operations;
+ inode->i_op = &btrfs_file_inode_operations;
+
err = btrfs_add_nondir(trans, dir, dentry, inode, 0, index);
if (err)
drop_inode = 1;
else {
inode->i_mapping->a_ops = &btrfs_aops;
inode->i_mapping->backing_dev_info = &root->fs_info->bdi;
- inode->i_fop = &btrfs_file_operations;
- inode->i_op = &btrfs_file_inode_operations;
BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops;
+ d_instantiate(dentry, inode);
}
out_unlock:
nr = trans->blocks_used;
@@ -4679,6 +4777,7 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir,
struct dentry *parent = dentry->d_parent;
err = btrfs_update_inode(trans, root, inode);
BUG_ON(err);
+ d_instantiate(dentry, inode);
btrfs_log_new_name(trans, inode, NULL, parent);
}
@@ -4693,7 +4792,7 @@ fail:
return err;
}
-static int btrfs_mkdir(struct inode *dir, struct dentry *dentry, int mode)
+static int btrfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
{
struct inode *inode = NULL;
struct btrfs_trans_handle *trans;
@@ -6303,7 +6402,12 @@ int btrfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
u64 page_start;
u64 page_end;
+ /* Need this to keep space reservations serialized */
+ mutex_lock(&inode->i_mutex);
ret = btrfs_delalloc_reserve_space(inode, PAGE_CACHE_SIZE);
+ mutex_unlock(&inode->i_mutex);
+ if (!ret)
+ ret = btrfs_update_time(vma->vm_file);
if (ret) {
if (ret == -ENOMEM)
ret = VM_FAULT_OOM;
@@ -6515,8 +6619,9 @@ static int btrfs_truncate(struct inode *inode)
/* Just need the 1 for updating the inode */
trans = btrfs_start_transaction(root, 1);
if (IS_ERR(trans)) {
- err = PTR_ERR(trans);
- goto out;
+ ret = err = PTR_ERR(trans);
+ trans = NULL;
+ break;
}
}
@@ -6656,7 +6761,6 @@ struct inode *btrfs_alloc_inode(struct super_block *sb)
static void btrfs_i_callback(struct rcu_head *head)
{
struct inode *inode = container_of(head, struct inode, i_rcu);
- INIT_LIST_HEAD(&inode->i_dentry);
kmem_cache_free(btrfs_inode_cachep, BTRFS_I(inode));
}
@@ -6794,11 +6898,13 @@ static int btrfs_getattr(struct vfsmount *mnt,
struct dentry *dentry, struct kstat *stat)
{
struct inode *inode = dentry->d_inode;
+ u32 blocksize = inode->i_sb->s_blocksize;
+
generic_fillattr(inode, stat);
stat->dev = BTRFS_I(inode)->root->anon_dev;
stat->blksize = PAGE_CACHE_SIZE;
- stat->blocks = (inode_get_bytes(inode) +
- BTRFS_I(inode)->delalloc_bytes) >> 9;
+ stat->blocks = (ALIGN(inode_get_bytes(inode), blocksize) +
+ ALIGN(BTRFS_I(inode)->delalloc_bytes, blocksize)) >> 9;
return 0;
}
@@ -7074,14 +7180,21 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry,
goto out_unlock;
}
+ /*
+ * If the active LSM wants to access the inode during
+ * d_instantiate it needs these. Smack checks to see
+ * if the filesystem supports xattrs by looking at the
+ * ops vector.
+ */
+ inode->i_fop = &btrfs_file_operations;
+ inode->i_op = &btrfs_file_inode_operations;
+
err = btrfs_add_nondir(trans, dir, dentry, inode, 0, index);
if (err)
drop_inode = 1;
else {
inode->i_mapping->a_ops = &btrfs_aops;
inode->i_mapping->backing_dev_info = &root->fs_info->bdi;
- inode->i_fop = &btrfs_file_operations;
- inode->i_op = &btrfs_file_inode_operations;
BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops;
}
if (drop_inode)
@@ -7130,6 +7243,8 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry,
drop_inode = 1;
out_unlock:
+ if (!err)
+ d_instantiate(dentry, inode);
nr = trans->blocks_used;
btrfs_end_transaction_throttle(trans, root);
if (drop_inode) {
@@ -7351,6 +7466,7 @@ static const struct inode_operations btrfs_symlink_inode_operations = {
.follow_link = page_follow_link_light,
.put_link = page_put_link,
.getattr = btrfs_getattr,
+ .setattr = btrfs_setattr,
.permission = btrfs_permission,
.setxattr = btrfs_setxattr,
.getxattr = btrfs_getxattr,
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 4a34c472f126..5441ff1480fd 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -201,7 +201,7 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
}
}
- ret = mnt_want_write(file->f_path.mnt);
+ ret = mnt_want_write_file(file);
if (ret)
goto out_unlock;
@@ -252,14 +252,14 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
trans = btrfs_join_transaction(root);
BUG_ON(IS_ERR(trans));
+ btrfs_update_iflags(inode);
+ inode->i_ctime = CURRENT_TIME;
ret = btrfs_update_inode(trans, root, inode);
BUG_ON(ret);
- btrfs_update_iflags(inode);
- inode->i_ctime = CURRENT_TIME;
btrfs_end_transaction(trans, root);
- mnt_drop_write(file->f_path.mnt);
+ mnt_drop_write_file(file);
ret = 0;
out_unlock:
@@ -858,8 +858,10 @@ static int cluster_pages_for_defrag(struct inode *inode,
return 0;
file_end = (isize - 1) >> PAGE_CACHE_SHIFT;
+ mutex_lock(&inode->i_mutex);
ret = btrfs_delalloc_reserve_space(inode,
num_pages << PAGE_CACHE_SHIFT);
+ mutex_unlock(&inode->i_mutex);
if (ret)
return ret;
again:
@@ -1216,12 +1218,12 @@ static noinline int btrfs_ioctl_resize(struct btrfs_root *root,
*devstr = '\0';
devstr = vol_args->name;
devid = simple_strtoull(devstr, &end, 10);
- printk(KERN_INFO "resizing devid %llu\n",
+ printk(KERN_INFO "btrfs: resizing devid %llu\n",
(unsigned long long)devid);
}
device = btrfs_find_device(root, devid, NULL, NULL);
if (!device) {
- printk(KERN_INFO "resizer unable to find device %llu\n",
+ printk(KERN_INFO "btrfs: resizer unable to find device %llu\n",
(unsigned long long)devid);
ret = -EINVAL;
goto out_unlock;
@@ -1267,7 +1269,7 @@ static noinline int btrfs_ioctl_resize(struct btrfs_root *root,
do_div(new_size, root->sectorsize);
new_size *= root->sectorsize;
- printk(KERN_INFO "new size for %s is %llu\n",
+ printk(KERN_INFO "btrfs: new size for %s is %llu\n",
device->name, (unsigned long long)new_size);
if (new_size > old_size) {
@@ -1278,7 +1280,7 @@ static noinline int btrfs_ioctl_resize(struct btrfs_root *root,
}
ret = btrfs_grow_device(trans, device, new_size);
btrfs_commit_transaction(trans, root);
- } else {
+ } else if (new_size < old_size) {
ret = btrfs_shrink_device(device, new_size);
}
@@ -1853,7 +1855,7 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
goto out;
}
- err = mnt_want_write(file->f_path.mnt);
+ err = mnt_want_write_file(file);
if (err)
goto out;
@@ -1969,7 +1971,7 @@ out_dput:
dput(dentry);
out_unlock_dir:
mutex_unlock(&dir->i_mutex);
- mnt_drop_write(file->f_path.mnt);
+ mnt_drop_write_file(file);
out:
kfree(vol_args);
return err;
@@ -1985,7 +1987,7 @@ static int btrfs_ioctl_defrag(struct file *file, void __user *argp)
if (btrfs_root_readonly(root))
return -EROFS;
- ret = mnt_want_write(file->f_path.mnt);
+ ret = mnt_want_write_file(file);
if (ret)
return ret;
@@ -2038,7 +2040,7 @@ static int btrfs_ioctl_defrag(struct file *file, void __user *argp)
ret = -EINVAL;
}
out:
- mnt_drop_write(file->f_path.mnt);
+ mnt_drop_write_file(file);
return ret;
}
@@ -2193,7 +2195,7 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
if (btrfs_root_readonly(root))
return -EROFS;
- ret = mnt_want_write(file->f_path.mnt);
+ ret = mnt_want_write_file(file);
if (ret)
return ret;
@@ -2508,7 +2510,7 @@ out_unlock:
out_fput:
fput(src_file);
out_drop_write:
- mnt_drop_write(file->f_path.mnt);
+ mnt_drop_write_file(file);
return ret;
}
@@ -2547,7 +2549,7 @@ static long btrfs_ioctl_trans_start(struct file *file)
if (btrfs_root_readonly(root))
goto out;
- ret = mnt_want_write(file->f_path.mnt);
+ ret = mnt_want_write_file(file);
if (ret)
goto out;
@@ -2563,7 +2565,7 @@ static long btrfs_ioctl_trans_start(struct file *file)
out_drop:
atomic_dec(&root->fs_info->open_ioctl_trans);
- mnt_drop_write(file->f_path.mnt);
+ mnt_drop_write_file(file);
out:
return ret;
}
@@ -2798,7 +2800,7 @@ long btrfs_ioctl_trans_end(struct file *file)
atomic_dec(&root->fs_info->open_ioctl_trans);
- mnt_drop_write(file->f_path.mnt);
+ mnt_drop_write_file(file);
return 0;
}
@@ -2930,11 +2932,13 @@ static long btrfs_ioctl_ino_to_path(struct btrfs_root *root, void __user *arg)
goto out;
for (i = 0; i < ipath->fspath->elem_cnt; ++i) {
- rel_ptr = ipath->fspath->val[i] - (u64)ipath->fspath->val;
+ rel_ptr = ipath->fspath->val[i] -
+ (u64)(unsigned long)ipath->fspath->val;
ipath->fspath->val[i] = rel_ptr;
}
- ret = copy_to_user((void *)ipa->fspath, (void *)ipath->fspath, size);
+ ret = copy_to_user((void *)(unsigned long)ipa->fspath,
+ (void *)(unsigned long)ipath->fspath, size);
if (ret) {
ret = -EFAULT;
goto out;
@@ -3017,7 +3021,8 @@ static long btrfs_ioctl_logical_to_ino(struct btrfs_root *root,
if (ret < 0)
goto out;
- ret = copy_to_user((void *)loi->inodes, (void *)inodes, size);
+ ret = copy_to_user((void *)(unsigned long)loi->inodes,
+ (void *)(unsigned long)inodes, size);
if (ret)
ret = -EFAULT;
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index dff29d5e151a..cfb55434a469 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -2947,7 +2947,9 @@ static int relocate_file_extent_cluster(struct inode *inode,
index = (cluster->start - offset) >> PAGE_CACHE_SHIFT;
last_index = (cluster->end - offset) >> PAGE_CACHE_SHIFT;
while (index <= last_index) {
+ mutex_lock(&inode->i_mutex);
ret = btrfs_delalloc_reserve_metadata(inode, PAGE_CACHE_SIZE);
+ mutex_unlock(&inode->i_mutex);
if (ret)
goto out;
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index f4190f22edfb..ddf2c90d3fc0 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -256,6 +256,11 @@ static int scrub_print_warning_inode(u64 inum, u64 offset, u64 root, void *ctx)
btrfs_release_path(swarn->path);
ipath = init_ipath(4096, local_root, swarn->path);
+ if (IS_ERR(ipath)) {
+ ret = PTR_ERR(ipath);
+ ipath = NULL;
+ goto err;
+ }
ret = paths_from_inode(inum, ipath);
if (ret < 0)
@@ -272,7 +277,7 @@ static int scrub_print_warning_inode(u64 inum, u64 offset, u64 root, void *ctx)
swarn->logical, swarn->dev->name,
(unsigned long long)swarn->sector, root, inum, offset,
min(isize - offset, (u64)PAGE_SIZE), nlink,
- (char *)ipath->fspath->val[i]);
+ (char *)(unsigned long)ipath->fspath->val[i]);
free_ipath(ipath);
return 0;
@@ -1530,18 +1535,22 @@ static noinline_for_stack int scrub_supers(struct scrub_dev *sdev)
static noinline_for_stack int scrub_workers_get(struct btrfs_root *root)
{
struct btrfs_fs_info *fs_info = root->fs_info;
+ int ret = 0;
mutex_lock(&fs_info->scrub_lock);
if (fs_info->scrub_workers_refcnt == 0) {
btrfs_init_workers(&fs_info->scrub_workers, "scrub",
fs_info->thread_pool_size, &fs_info->generic_worker);
fs_info->scrub_workers.idle_thresh = 4;
- btrfs_start_workers(&fs_info->scrub_workers, 1);
+ ret = btrfs_start_workers(&fs_info->scrub_workers);
+ if (ret)
+ goto out;
}
++fs_info->scrub_workers_refcnt;
+out:
mutex_unlock(&fs_info->scrub_lock);
- return 0;
+ return ret;
}
static noinline_for_stack void scrub_workers_put(struct btrfs_root *root)
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 8bd9d6d0e07a..ae488aa1966a 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -40,7 +40,7 @@
#include <linux/magic.h>
#include <linux/slab.h>
#include <linux/cleancache.h>
-#include <linux/mnt_namespace.h>
+#include <linux/ratelimit.h>
#include "compat.h"
#include "delayed-inode.h"
#include "ctree.h"
@@ -661,9 +661,9 @@ int btrfs_sync_fs(struct super_block *sb, int wait)
return ret;
}
-static int btrfs_show_options(struct seq_file *seq, struct vfsmount *vfs)
+static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry)
{
- struct btrfs_root *root = btrfs_sb(vfs->mnt_sb);
+ struct btrfs_root *root = btrfs_sb(dentry->d_sb);
struct btrfs_fs_info *info = root->fs_info;
char *compress_type;
@@ -825,13 +825,9 @@ static char *setup_root_args(char *args)
static struct dentry *mount_subvol(const char *subvol_name, int flags,
const char *device_name, char *data)
{
- struct super_block *s;
struct dentry *root;
struct vfsmount *mnt;
- struct mnt_namespace *ns_private;
char *newargs;
- struct path path;
- int error;
newargs = setup_root_args(data);
if (!newargs)
@@ -842,39 +838,17 @@ static struct dentry *mount_subvol(const char *subvol_name, int flags,
if (IS_ERR(mnt))
return ERR_CAST(mnt);
- ns_private = create_mnt_ns(mnt);
- if (IS_ERR(ns_private)) {
- mntput(mnt);
- return ERR_CAST(ns_private);
- }
+ root = mount_subtree(mnt, subvol_name);
- /*
- * This will trigger the automount of the subvol so we can just
- * drop the mnt we have here and return the dentry that we
- * found.
- */
- error = vfs_path_lookup(mnt->mnt_root, mnt, subvol_name,
- LOOKUP_FOLLOW, &path);
- put_mnt_ns(ns_private);
- if (error)
- return ERR_PTR(error);
-
- if (!is_subvolume_inode(path.dentry->d_inode)) {
- path_put(&path);
- mntput(mnt);
- error = -EINVAL;
+ if (!IS_ERR(root) && !is_subvolume_inode(root->d_inode)) {
+ struct super_block *s = root->d_sb;
+ dput(root);
+ root = ERR_PTR(-EINVAL);
+ deactivate_locked_super(s);
printk(KERN_ERR "btrfs: '%s' is not a valid subvolume\n",
subvol_name);
- return ERR_PTR(-EINVAL);
}
- /* Get a ref to the sb and the dentry we found and return it */
- s = path.mnt->mnt_sb;
- atomic_inc(&s->s_active);
- root = dget(path.dentry);
- path_put(&path);
- down_write(&s->s_umount);
-
return root;
}
@@ -1079,11 +1053,11 @@ static int btrfs_calc_avail_data_space(struct btrfs_root *root, u64 *free_bytes)
u64 avail_space;
u64 used_space;
u64 min_stripe_size;
- int min_stripes = 1;
+ int min_stripes = 1, num_stripes = 1;
int i = 0, nr_devices;
int ret;
- nr_devices = fs_info->fs_devices->rw_devices;
+ nr_devices = fs_info->fs_devices->open_devices;
BUG_ON(!nr_devices);
devices_info = kmalloc(sizeof(*devices_info) * nr_devices,
@@ -1093,20 +1067,24 @@ static int btrfs_calc_avail_data_space(struct btrfs_root *root, u64 *free_bytes)
/* calc min stripe number for data space alloction */
type = btrfs_get_alloc_profile(root, 1);
- if (type & BTRFS_BLOCK_GROUP_RAID0)
+ if (type & BTRFS_BLOCK_GROUP_RAID0) {
min_stripes = 2;
- else if (type & BTRFS_BLOCK_GROUP_RAID1)
+ num_stripes = nr_devices;
+ } else if (type & BTRFS_BLOCK_GROUP_RAID1) {
min_stripes = 2;
- else if (type & BTRFS_BLOCK_GROUP_RAID10)
+ num_stripes = 2;
+ } else if (type & BTRFS_BLOCK_GROUP_RAID10) {
min_stripes = 4;
+ num_stripes = 4;
+ }
if (type & BTRFS_BLOCK_GROUP_DUP)
min_stripe_size = 2 * BTRFS_STRIPE_LEN;
else
min_stripe_size = BTRFS_STRIPE_LEN;
- list_for_each_entry(device, &fs_devices->alloc_list, dev_alloc_list) {
- if (!device->in_fs_metadata)
+ list_for_each_entry(device, &fs_devices->devices, dev_list) {
+ if (!device->in_fs_metadata || !device->bdev)
continue;
avail_space = device->total_bytes - device->bytes_used;
@@ -1167,13 +1145,16 @@ static int btrfs_calc_avail_data_space(struct btrfs_root *root, u64 *free_bytes)
i = nr_devices - 1;
avail_space = 0;
while (nr_devices >= min_stripes) {
+ if (num_stripes > nr_devices)
+ num_stripes = nr_devices;
+
if (devices_info[i].max_avail >= min_stripe_size) {
int j;
u64 alloc_size;
- avail_space += devices_info[i].max_avail * min_stripes;
+ avail_space += devices_info[i].max_avail * num_stripes;
alloc_size = devices_info[i].max_avail;
- for (j = i + 1 - min_stripes; j <= i; j++)
+ for (j = i + 1 - num_stripes; j <= i; j++)
devices_info[j].max_avail -= alloc_size;
}
i--;
@@ -1290,6 +1271,16 @@ static int btrfs_unfreeze(struct super_block *sb)
return 0;
}
+static void btrfs_fs_dirty_inode(struct inode *inode, int flags)
+{
+ int ret;
+
+ ret = btrfs_dirty_inode(inode);
+ if (ret)
+ printk_ratelimited(KERN_ERR "btrfs: fail to dirty inode %Lu "
+ "error %d\n", btrfs_ino(inode), ret);
+}
+
static const struct super_operations btrfs_super_ops = {
.drop_inode = btrfs_drop_inode,
.evict_inode = btrfs_evict_inode,
@@ -1297,7 +1288,7 @@ static const struct super_operations btrfs_super_ops = {
.sync_fs = btrfs_sync_fs,
.show_options = btrfs_show_options,
.write_inode = btrfs_write_inode,
- .dirty_inode = btrfs_dirty_inode,
+ .dirty_inode = btrfs_fs_dirty_inode,
.alloc_inode = btrfs_alloc_inode,
.destroy_inode = btrfs_destroy_inode,
.statfs = btrfs_statfs,
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 6a0574e923bc..81376d94cd3c 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -785,6 +785,10 @@ static noinline int commit_fs_roots(struct btrfs_trans_handle *trans,
btrfs_save_ino_cache(root, trans);
+ /* see comments in should_cow_block() */
+ root->force_cow = 0;
+ smp_wmb();
+
if (root->commit_root != root->node) {
mutex_lock(&root->fs_commit_mutex);
switch_commit_root(root);
@@ -947,6 +951,10 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
btrfs_tree_unlock(old);
free_extent_buffer(old);
+ /* see comments in should_cow_block() */
+ root->force_cow = 1;
+ smp_wmb();
+
btrfs_set_root_node(new_root_item, tmp);
/* record when the snapshot was created in key.offset */
key.offset = trans->transid;
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index c37433d3cd82..f4b839fd3c9d 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -295,6 +295,12 @@ loop_lock:
btrfs_requeue_work(&device->work);
goto done;
}
+ /* unplug every 64 requests just for good measure */
+ if (batch_run % 64 == 0) {
+ blk_finish_plug(&plug);
+ blk_start_plug(&plug);
+ sync_pending = 0;
+ }
}
cond_resched();
@@ -1611,7 +1617,7 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path)
if ((sb->s_flags & MS_RDONLY) && !root->fs_info->fs_devices->seeding)
return -EINVAL;
- bdev = blkdev_get_by_path(device_path, FMODE_EXCL,
+ bdev = blkdev_get_by_path(device_path, FMODE_WRITE | FMODE_EXCL,
root->fs_info->bdev_holder);
if (IS_ERR(bdev))
return PTR_ERR(bdev);
@@ -3258,7 +3264,7 @@ static void btrfs_end_bio(struct bio *bio, int err)
*/
if (atomic_read(&bbio->error) > bbio->max_errors) {
err = -EIO;
- } else if (err) {
+ } else {
/*
* this bio is actually up to date, we didn't
* go over the max number of errors
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index ab5b1c49f352..78f2d4d4f37f 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -100,6 +100,12 @@ struct btrfs_device {
struct reada_zone *reada_curr_zone;
struct radix_tree_root reada_zones;
struct radix_tree_root reada_extents;
+
+ /* for sending down flush barriers */
+ struct bio *flush_bio;
+ struct completion flush_wait;
+ int nobarriers;
+
};
struct btrfs_fs_devices {
OpenPOWER on IntegriCloud