summaryrefslogtreecommitdiffstats
path: root/fs/btrfs
diff options
context:
space:
mode:
Diffstat (limited to 'fs/btrfs')
-rw-r--r--fs/btrfs/backref.c2
-rw-r--r--fs/btrfs/compression.c7
-rw-r--r--fs/btrfs/ctree.h6
-rw-r--r--fs/btrfs/disk-io.c5
-rw-r--r--fs/btrfs/extent-tree.c134
-rw-r--r--fs/btrfs/extent_io.c14
-rw-r--r--fs/btrfs/file.c26
-rw-r--r--fs/btrfs/free-space-cache.c4
-rw-r--r--fs/btrfs/inode.c89
-rw-r--r--fs/btrfs/qgroup.c18
-rw-r--r--fs/btrfs/scrub.c241
-rw-r--r--fs/btrfs/tests/free-space-tests.c4
-rw-r--r--fs/btrfs/transaction.c32
-rw-r--r--fs/btrfs/transaction.h4
-rw-r--r--fs/btrfs/volumes.c38
-rw-r--r--fs/btrfs/volumes.h2
-rw-r--r--fs/btrfs/xattr.c4
17 files changed, 398 insertions, 232 deletions
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index 6dcdb2ec9211..d453d62ab0c6 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -355,7 +355,7 @@ static int __resolve_indirect_ref(struct btrfs_fs_info *fs_info,
index = srcu_read_lock(&fs_info->subvol_srcu);
- root = btrfs_read_fs_root_no_name(fs_info, &root_key);
+ root = btrfs_get_fs_root(fs_info, &root_key, false);
if (IS_ERR(root)) {
srcu_read_unlock(&fs_info->subvol_srcu, index);
ret = PTR_ERR(root);
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index 97b049ad0594..c473c42d7d6c 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -482,13 +482,12 @@ static noinline int add_ra_bio_pages(struct inode *inode,
goto next;
}
- page = __page_cache_alloc(mapping_gfp_mask(mapping) &
- ~__GFP_FS);
+ page = __page_cache_alloc(mapping_gfp_constraint(mapping,
+ ~__GFP_FS));
if (!page)
break;
- if (add_to_page_cache_lru(page, mapping, pg_index,
- GFP_NOFS)) {
+ if (add_to_page_cache_lru(page, mapping, pg_index, GFP_NOFS)) {
page_cache_release(page);
goto next;
}
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index a2e73f6053a8..35489e7129a7 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -3367,7 +3367,7 @@ static inline bool btrfs_mixed_space_info(struct btrfs_space_info *space_info)
static inline gfp_t btrfs_alloc_write_mask(struct address_space *mapping)
{
- return mapping_gfp_mask(mapping) & ~__GFP_FS;
+ return mapping_gfp_constraint(mapping, ~__GFP_FS);
}
/* extent-tree.c */
@@ -3416,6 +3416,7 @@ int btrfs_cross_ref_exist(struct btrfs_trans_handle *trans,
struct btrfs_block_group_cache *btrfs_lookup_block_group(
struct btrfs_fs_info *info,
u64 bytenr);
+void btrfs_get_block_group(struct btrfs_block_group_cache *cache);
void btrfs_put_block_group(struct btrfs_block_group_cache *cache);
int get_block_group_index(struct btrfs_block_group_cache *cache);
struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans,
@@ -3479,6 +3480,9 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans,
struct btrfs_root *root, u64 bytes_used,
u64 type, u64 chunk_objectid, u64 chunk_offset,
u64 size);
+struct btrfs_trans_handle *btrfs_start_trans_remove_block_group(
+ struct btrfs_fs_info *fs_info,
+ const u64 chunk_offset);
int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
struct btrfs_root *root, u64 group_start,
struct extent_map *em);
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 2d4667594681..974be09e7556 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -2575,7 +2575,7 @@ int open_ctree(struct super_block *sb,
fs_info->commit_interval = BTRFS_DEFAULT_COMMIT_INTERVAL;
fs_info->avg_delayed_ref_runtime = NSEC_PER_SEC >> 6; /* div by 64 */
/* readahead state */
- INIT_RADIX_TREE(&fs_info->reada_tree, GFP_NOFS & ~__GFP_WAIT);
+ INIT_RADIX_TREE(&fs_info->reada_tree, GFP_NOFS & ~__GFP_DIRECT_RECLAIM);
spin_lock_init(&fs_info->reada_lock);
fs_info->thread_pool_size = min_t(unsigned long,
@@ -3780,6 +3780,9 @@ void close_ctree(struct btrfs_root *root)
fs_info->closing = 1;
smp_mb();
+ /* wait for the qgroup rescan worker to stop */
+ btrfs_qgroup_wait_for_completion(fs_info);
+
/* wait for the uuid_scan task to finish */
down(&fs_info->uuid_tree_rescan_sem);
/* avoid complains from lockdep et al., set sem back to initial state */
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 99a8e57da8a1..4b89680a1923 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -124,7 +124,7 @@ static int block_group_bits(struct btrfs_block_group_cache *cache, u64 bits)
return (cache->flags & bits) == bits;
}
-static void btrfs_get_block_group(struct btrfs_block_group_cache *cache)
+void btrfs_get_block_group(struct btrfs_block_group_cache *cache)
{
atomic_inc(&cache->count);
}
@@ -5915,19 +5915,6 @@ static int update_block_group(struct btrfs_trans_handle *trans,
set_extent_dirty(info->pinned_extents,
bytenr, bytenr + num_bytes - 1,
GFP_NOFS | __GFP_NOFAIL);
- /*
- * No longer have used bytes in this block group, queue
- * it for deletion.
- */
- if (old_val == 0) {
- spin_lock(&info->unused_bgs_lock);
- if (list_empty(&cache->bg_list)) {
- btrfs_get_block_group(cache);
- list_add_tail(&cache->bg_list,
- &info->unused_bgs);
- }
- spin_unlock(&info->unused_bgs_lock);
- }
}
spin_lock(&trans->transaction->dirty_bgs_lock);
@@ -5939,6 +5926,22 @@ static int update_block_group(struct btrfs_trans_handle *trans,
}
spin_unlock(&trans->transaction->dirty_bgs_lock);
+ /*
+ * No longer have used bytes in this block group, queue it for
+ * deletion. We do this after adding the block group to the
+ * dirty list to avoid races between cleaner kthread and space
+ * cache writeout.
+ */
+ if (!alloc && old_val == 0) {
+ spin_lock(&info->unused_bgs_lock);
+ if (list_empty(&cache->bg_list)) {
+ btrfs_get_block_group(cache);
+ list_add_tail(&cache->bg_list,
+ &info->unused_bgs);
+ }
+ spin_unlock(&info->unused_bgs_lock);
+ }
+
btrfs_put_block_group(cache);
total -= num_bytes;
bytenr += num_bytes;
@@ -8105,21 +8108,47 @@ reada:
}
/*
- * TODO: Modify related function to add related node/leaf to dirty_extent_root,
- * for later qgroup accounting.
- *
- * Current, this function does nothing.
+ * These may not be seen by the usual inc/dec ref code so we have to
+ * add them here.
*/
+static int record_one_subtree_extent(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root, u64 bytenr,
+ u64 num_bytes)
+{
+ struct btrfs_qgroup_extent_record *qrecord;
+ struct btrfs_delayed_ref_root *delayed_refs;
+
+ qrecord = kmalloc(sizeof(*qrecord), GFP_NOFS);
+ if (!qrecord)
+ return -ENOMEM;
+
+ qrecord->bytenr = bytenr;
+ qrecord->num_bytes = num_bytes;
+ qrecord->old_roots = NULL;
+
+ delayed_refs = &trans->transaction->delayed_refs;
+ spin_lock(&delayed_refs->lock);
+ if (btrfs_qgroup_insert_dirty_extent(delayed_refs, qrecord))
+ kfree(qrecord);
+ spin_unlock(&delayed_refs->lock);
+
+ return 0;
+}
+
static int account_leaf_items(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct extent_buffer *eb)
{
int nr = btrfs_header_nritems(eb);
- int i, extent_type;
+ int i, extent_type, ret;
struct btrfs_key key;
struct btrfs_file_extent_item *fi;
u64 bytenr, num_bytes;
+ /* We can be called directly from walk_up_proc() */
+ if (!root->fs_info->quota_enabled)
+ return 0;
+
for (i = 0; i < nr; i++) {
btrfs_item_key_to_cpu(eb, &key, i);
@@ -8138,6 +8167,10 @@ static int account_leaf_items(struct btrfs_trans_handle *trans,
continue;
num_bytes = btrfs_file_extent_disk_num_bytes(eb, fi);
+
+ ret = record_one_subtree_extent(trans, root, bytenr, num_bytes);
+ if (ret)
+ return ret;
}
return 0;
}
@@ -8206,8 +8239,6 @@ static int adjust_slots_upwards(struct btrfs_root *root,
/*
* root_eb is the subtree root and is locked before this function is called.
- * TODO: Modify this function to mark all (including complete shared node)
- * to dirty_extent_root to allow it get accounted in qgroup.
*/
static int account_shared_subtree(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
@@ -8285,6 +8316,11 @@ walk_down:
btrfs_tree_read_lock(eb);
btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK);
path->locks[level] = BTRFS_READ_LOCK_BLOCKING;
+
+ ret = record_one_subtree_extent(trans, root, child_bytenr,
+ root->nodesize);
+ if (ret)
+ goto out;
}
if (level == 0) {
@@ -10256,6 +10292,47 @@ out:
return ret;
}
+struct btrfs_trans_handle *
+btrfs_start_trans_remove_block_group(struct btrfs_fs_info *fs_info,
+ const u64 chunk_offset)
+{
+ struct extent_map_tree *em_tree = &fs_info->mapping_tree.map_tree;
+ struct extent_map *em;
+ struct map_lookup *map;
+ unsigned int num_items;
+
+ read_lock(&em_tree->lock);
+ em = lookup_extent_mapping(em_tree, chunk_offset, 1);
+ read_unlock(&em_tree->lock);
+ ASSERT(em && em->start == chunk_offset);
+
+ /*
+ * We need to reserve 3 + N units from the metadata space info in order
+ * to remove a block group (done at btrfs_remove_chunk() and at
+ * btrfs_remove_block_group()), which are used for:
+ *
+ * 1 unit for adding the free space inode's orphan (located in the tree
+ * of tree roots).
+ * 1 unit for deleting the block group item (located in the extent
+ * tree).
+ * 1 unit for deleting the free space item (located in tree of tree
+ * roots).
+ * N units for deleting N device extent items corresponding to each
+ * stripe (located in the device tree).
+ *
+ * In order to remove a block group we also need to reserve units in the
+ * system space info in order to update the chunk tree (update one or
+ * more device items and remove one chunk item), but this is done at
+ * btrfs_remove_chunk() through a call to check_system_chunk().
+ */
+ map = (struct map_lookup *)em->bdev;
+ num_items = 3 + map->num_stripes;
+ free_extent_map(em);
+
+ return btrfs_start_transaction_fallback_global_rsv(fs_info->extent_root,
+ num_items, 1);
+}
+
/*
* Process the unused_bgs list and remove any that don't have any allocated
* space inside of them.
@@ -10279,22 +10356,25 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
block_group = list_first_entry(&fs_info->unused_bgs,
struct btrfs_block_group_cache,
bg_list);
- space_info = block_group->space_info;
list_del_init(&block_group->bg_list);
+
+ space_info = block_group->space_info;
+
if (ret || btrfs_mixed_space_info(space_info)) {
btrfs_put_block_group(block_group);
continue;
}
spin_unlock(&fs_info->unused_bgs_lock);
- mutex_lock(&root->fs_info->delete_unused_bgs_mutex);
+ mutex_lock(&fs_info->delete_unused_bgs_mutex);
/* Don't want to race with allocators so take the groups_sem */
down_write(&space_info->groups_sem);
spin_lock(&block_group->lock);
if (block_group->reserved ||
btrfs_block_group_used(&block_group->item) ||
- block_group->ro) {
+ block_group->ro ||
+ list_is_singular(&block_group->list)) {
/*
* We want to bail if we made new allocations or have
* outstanding allocations in this block group. We do
@@ -10319,8 +10399,8 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
* Want to do this before we do anything else so we can recover
* properly if we fail to join the transaction.
*/
- /* 1 for btrfs_orphan_reserve_metadata() */
- trans = btrfs_start_transaction(root, 1);
+ trans = btrfs_start_trans_remove_block_group(fs_info,
+ block_group->key.objectid);
if (IS_ERR(trans)) {
btrfs_dec_block_group_ro(root, block_group);
ret = PTR_ERR(trans);
@@ -10410,7 +10490,7 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
end_trans:
btrfs_end_transaction(trans, root);
next:
- mutex_unlock(&root->fs_info->delete_unused_bgs_mutex);
+ mutex_unlock(&fs_info->delete_unused_bgs_mutex);
btrfs_put_block_group(block_group);
spin_lock(&fs_info->unused_bgs_lock);
}
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 33a01ea41465..9abe18763a7f 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -616,7 +616,7 @@ static int __clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
if (bits & (EXTENT_IOBITS | EXTENT_BOUNDARY))
clear = 1;
again:
- if (!prealloc && (mask & __GFP_WAIT)) {
+ if (!prealloc && gfpflags_allow_blocking(mask)) {
/*
* Don't care for allocation failure here because we might end
* up not needing the pre-allocated extent state at all, which
@@ -741,7 +741,7 @@ search_again:
if (start > end)
goto out;
spin_unlock(&tree->lock);
- if (mask & __GFP_WAIT)
+ if (gfpflags_allow_blocking(mask))
cond_resched();
goto again;
}
@@ -874,7 +874,7 @@ __set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
bits |= EXTENT_FIRST_DELALLOC;
again:
- if (!prealloc && (mask & __GFP_WAIT)) {
+ if (!prealloc && gfpflags_allow_blocking(mask)) {
prealloc = alloc_extent_state(mask);
BUG_ON(!prealloc);
}
@@ -1052,7 +1052,7 @@ search_again:
if (start > end)
goto out;
spin_unlock(&tree->lock);
- if (mask & __GFP_WAIT)
+ if (gfpflags_allow_blocking(mask))
cond_resched();
goto again;
}
@@ -1100,7 +1100,7 @@ int convert_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
btrfs_debug_check_extent_io_range(tree, start, end);
again:
- if (!prealloc && (mask & __GFP_WAIT)) {
+ if (!prealloc && gfpflags_allow_blocking(mask)) {
/*
* Best effort, don't worry if extent state allocation fails
* here for the first iteration. We might have a cached state
@@ -1278,7 +1278,7 @@ search_again:
if (start > end)
goto out;
spin_unlock(&tree->lock);
- if (mask & __GFP_WAIT)
+ if (gfpflags_allow_blocking(mask))
cond_resched();
first_iteration = false;
goto again;
@@ -4386,7 +4386,7 @@ int try_release_extent_mapping(struct extent_map_tree *map,
u64 start = page_offset(page);
u64 end = start + PAGE_CACHE_SIZE - 1;
- if ((mask & __GFP_WAIT) &&
+ if (gfpflags_allow_blocking(mask) &&
page->mapping->host->i_size > 16 * 1024 * 1024) {
u64 len;
while (start <= end) {
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 6bd5ce9d75f0..72e73461c064 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -756,8 +756,16 @@ next_slot:
}
btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
- if (key.objectid > ino ||
- key.type > BTRFS_EXTENT_DATA_KEY || key.offset >= end)
+
+ if (key.objectid > ino)
+ break;
+ if (WARN_ON_ONCE(key.objectid < ino) ||
+ key.type < BTRFS_EXTENT_DATA_KEY) {
+ ASSERT(del_nr == 0);
+ path->slots[0]++;
+ goto next_slot;
+ }
+ if (key.type > BTRFS_EXTENT_DATA_KEY || key.offset >= end)
break;
fi = btrfs_item_ptr(leaf, path->slots[0],
@@ -776,8 +784,8 @@ next_slot:
btrfs_file_extent_inline_len(leaf,
path->slots[0], fi);
} else {
- WARN_ON(1);
- extent_end = search_start;
+ /* can't happen */
+ BUG();
}
/*
@@ -1874,8 +1882,13 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
struct btrfs_log_ctx ctx;
int ret = 0;
bool full_sync = 0;
- const u64 len = end - start + 1;
+ u64 len;
+ /*
+ * The range length can be represented by u64, we have to do the typecasts
+ * to avoid signed overflow if it's [0, LLONG_MAX] eg. from fsync()
+ */
+ len = (u64)end - (u64)start + 1;
trace_btrfs_sync_file(file, datasync);
/*
@@ -2063,8 +2076,7 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
}
}
if (!full_sync) {
- ret = btrfs_wait_ordered_range(inode, start,
- end - start + 1);
+ ret = btrfs_wait_ordered_range(inode, start, len);
if (ret) {
btrfs_end_transaction(trans, root);
goto out;
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index 0948d34cb84a..85a1f8621b51 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -85,8 +85,8 @@ static struct inode *__lookup_free_space_inode(struct btrfs_root *root,
}
mapping_set_gfp_mask(inode->i_mapping,
- mapping_gfp_mask(inode->i_mapping) &
- ~(__GFP_FS | __GFP_HIGHMEM));
+ mapping_gfp_constraint(inode->i_mapping,
+ ~(__GFP_FS | __GFP_HIGHMEM)));
return inode;
}
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 4439fbb4ff45..a70c5790f8f5 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -1304,8 +1304,14 @@ next_slot:
num_bytes = 0;
btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]);
- if (found_key.objectid > ino ||
- found_key.type > BTRFS_EXTENT_DATA_KEY ||
+ if (found_key.objectid > ino)
+ break;
+ if (WARN_ON_ONCE(found_key.objectid < ino) ||
+ found_key.type < BTRFS_EXTENT_DATA_KEY) {
+ path->slots[0]++;
+ goto next_slot;
+ }
+ if (found_key.type > BTRFS_EXTENT_DATA_KEY ||
found_key.offset > end)
break;
@@ -4040,9 +4046,7 @@ int btrfs_unlink_inode(struct btrfs_trans_handle *trans,
*/
static struct btrfs_trans_handle *__unlink_start_trans(struct inode *dir)
{
- struct btrfs_trans_handle *trans;
struct btrfs_root *root = BTRFS_I(dir)->root;
- int ret;
/*
* 1 for the possible orphan item
@@ -4051,27 +4055,7 @@ static struct btrfs_trans_handle *__unlink_start_trans(struct inode *dir)
* 1 for the inode ref
* 1 for the inode
*/
- trans = btrfs_start_transaction(root, 5);
- if (!IS_ERR(trans) || PTR_ERR(trans) != -ENOSPC)
- return trans;
-
- if (PTR_ERR(trans) == -ENOSPC) {
- u64 num_bytes = btrfs_calc_trans_metadata_size(root, 5);
-
- trans = btrfs_start_transaction(root, 0);
- if (IS_ERR(trans))
- return trans;
- ret = btrfs_cond_migrate_bytes(root->fs_info,
- &root->fs_info->trans_block_rsv,
- num_bytes, 5);
- if (ret) {
- btrfs_end_transaction(trans, root);
- return ERR_PTR(ret);
- }
- trans->block_rsv = &root->fs_info->trans_block_rsv;
- trans->bytes_reserved = num_bytes;
- }
- return trans;
+ return btrfs_start_transaction_fallback_global_rsv(root, 5, 5);
}
static int btrfs_unlink(struct inode *dir, struct dentry *dentry)
@@ -6360,9 +6344,6 @@ static int btrfs_mknod(struct inode *dir, struct dentry *dentry,
u64 objectid;
u64 index = 0;
- if (!new_valid_dev(rdev))
- return -EINVAL;
-
/*
* 2 for inode item and ref
* 2 for dir items
@@ -7506,6 +7487,28 @@ struct btrfs_dio_data {
u64 reserve;
};
+static void adjust_dio_outstanding_extents(struct inode *inode,
+ struct btrfs_dio_data *dio_data,
+ const u64 len)
+{
+ unsigned num_extents;
+
+ num_extents = (unsigned) div64_u64(len + BTRFS_MAX_EXTENT_SIZE - 1,
+ BTRFS_MAX_EXTENT_SIZE);
+ /*
+ * If we have an outstanding_extents count still set then we're
+ * within our reservation, otherwise we need to adjust our inode
+ * counter appropriately.
+ */
+ if (dio_data->outstanding_extents) {
+ dio_data->outstanding_extents -= num_extents;
+ } else {
+ spin_lock(&BTRFS_I(inode)->lock);
+ BTRFS_I(inode)->outstanding_extents += num_extents;
+ spin_unlock(&BTRFS_I(inode)->lock);
+ }
+}
+
static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create)
{
@@ -7541,8 +7544,11 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock,
* If this errors out it's because we couldn't invalidate pagecache for
* this range and we need to fallback to buffered.
*/
- if (lock_extent_direct(inode, lockstart, lockend, &cached_state, create))
- return -ENOTBLK;
+ if (lock_extent_direct(inode, lockstart, lockend, &cached_state,
+ create)) {
+ ret = -ENOTBLK;
+ goto err;
+ }
em = btrfs_get_extent(inode, NULL, 0, start, len, 0);
if (IS_ERR(em)) {
@@ -7660,19 +7666,7 @@ unlock:
if (start + len > i_size_read(inode))
i_size_write(inode, start + len);
- /*
- * If we have an outstanding_extents count still set then we're
- * within our reservation, otherwise we need to adjust our inode
- * counter appropriately.
- */
- if (dio_data->outstanding_extents) {
- (dio_data->outstanding_extents)--;
- } else {
- spin_lock(&BTRFS_I(inode)->lock);
- BTRFS_I(inode)->outstanding_extents++;
- spin_unlock(&BTRFS_I(inode)->lock);
- }
-
+ adjust_dio_outstanding_extents(inode, dio_data, len);
btrfs_free_reserved_data_space(inode, start, len);
WARN_ON(dio_data->reserve < len);
dio_data->reserve -= len;
@@ -7699,8 +7693,17 @@ unlock:
unlock_err:
clear_extent_bit(&BTRFS_I(inode)->io_tree, lockstart, lockend,
unlock_bits, 1, 0, &cached_state, GFP_NOFS);
+err:
if (dio_data)
current->journal_info = dio_data;
+ /*
+ * Compensate the delalloc release we do in btrfs_direct_IO() when we
+ * write less data then expected, so that we don't underflow our inode's
+ * outstanding extents counter.
+ */
+ if (create && dio_data)
+ adjust_dio_outstanding_extents(inode, dio_data, len);
+
return ret;
}
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 46476c226395..5279fdae7142 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -993,9 +993,10 @@ int btrfs_quota_disable(struct btrfs_trans_handle *trans,
mutex_lock(&fs_info->qgroup_ioctl_lock);
if (!fs_info->quota_root)
goto out;
- spin_lock(&fs_info->qgroup_lock);
fs_info->quota_enabled = 0;
fs_info->pending_quota_state = 0;
+ btrfs_qgroup_wait_for_completion(fs_info);
+ spin_lock(&fs_info->qgroup_lock);
quota_root = fs_info->quota_root;
fs_info->quota_root = NULL;
fs_info->qgroup_flags &= ~BTRFS_QGROUP_STATUS_FLAG_ON;
@@ -1461,6 +1462,8 @@ struct btrfs_qgroup_extent_record
struct btrfs_qgroup_extent_record *entry;
u64 bytenr = record->bytenr;
+ assert_spin_locked(&delayed_refs->lock);
+
while (*p) {
parent_node = *p;
entry = rb_entry(parent_node, struct btrfs_qgroup_extent_record,
@@ -2198,7 +2201,6 @@ qgroup_rescan_leaf(struct btrfs_fs_info *fs_info, struct btrfs_path *path,
int slot;
int ret;
- path->leave_spinning = 1;
mutex_lock(&fs_info->qgroup_rescan_lock);
ret = btrfs_search_slot_for_read(fs_info->extent_root,
&fs_info->qgroup_rescan_progress,
@@ -2286,7 +2288,7 @@ static void btrfs_qgroup_rescan_worker(struct btrfs_work *work)
goto out;
err = 0;
- while (!err) {
+ while (!err && !btrfs_fs_closing(fs_info)) {
trans = btrfs_start_transaction(fs_info->fs_root, 0);
if (IS_ERR(trans)) {
err = PTR_ERR(trans);
@@ -2307,7 +2309,8 @@ out:
btrfs_free_path(path);
mutex_lock(&fs_info->qgroup_rescan_lock);
- fs_info->qgroup_flags &= ~BTRFS_QGROUP_STATUS_FLAG_RESCAN;
+ if (!btrfs_fs_closing(fs_info))
+ fs_info->qgroup_flags &= ~BTRFS_QGROUP_STATUS_FLAG_RESCAN;
if (err > 0 &&
fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT) {
@@ -2336,7 +2339,9 @@ out:
}
btrfs_end_transaction(trans, fs_info->quota_root);
- if (err >= 0) {
+ if (btrfs_fs_closing(fs_info)) {
+ btrfs_info(fs_info, "qgroup scan paused");
+ } else if (err >= 0) {
btrfs_info(fs_info, "qgroup scan completed%s",
err > 0 ? " (inconsistency flag cleared)" : "");
} else {
@@ -2384,12 +2389,11 @@ qgroup_rescan_init(struct btrfs_fs_info *fs_info, u64 progress_objectid,
memset(&fs_info->qgroup_rescan_progress, 0,
sizeof(fs_info->qgroup_rescan_progress));
fs_info->qgroup_rescan_progress.objectid = progress_objectid;
+ init_completion(&fs_info->qgroup_rescan_completion);
spin_unlock(&fs_info->qgroup_lock);
mutex_unlock(&fs_info->qgroup_rescan_lock);
- init_completion(&fs_info->qgroup_rescan_completion);
-
memset(&fs_info->qgroup_rescan_work, 0,
sizeof(fs_info->qgroup_rescan_work));
btrfs_init_work(&fs_info->qgroup_rescan_work,
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 550de89a8661..b091d94ceef6 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -248,14 +248,9 @@ static int scrub_handle_errored_block(struct scrub_block *sblock_to_check);
static int scrub_setup_recheck_block(struct scrub_block *original_sblock,
struct scrub_block *sblocks_for_recheck);
static void scrub_recheck_block(struct btrfs_fs_info *fs_info,
- struct scrub_block *sblock, int is_metadata,
- int have_csum, u8 *csum, u64 generation,
- u16 csum_size, int retry_failed_mirror);
-static void scrub_recheck_block_checksum(struct btrfs_fs_info *fs_info,
- struct scrub_block *sblock,
- int is_metadata, int have_csum,
- const u8 *csum, u64 generation,
- u16 csum_size);
+ struct scrub_block *sblock,
+ int retry_failed_mirror);
+static void scrub_recheck_block_checksum(struct scrub_block *sblock);
static int scrub_repair_block_from_good_copy(struct scrub_block *sblock_bad,
struct scrub_block *sblock_good);
static int scrub_repair_page_from_good_copy(struct scrub_block *sblock_bad,
@@ -889,11 +884,9 @@ static int scrub_handle_errored_block(struct scrub_block *sblock_to_check)
struct btrfs_fs_info *fs_info;
u64 length;
u64 logical;
- u64 generation;
unsigned int failed_mirror_index;
unsigned int is_metadata;
unsigned int have_csum;
- u8 *csum;
struct scrub_block *sblocks_for_recheck; /* holds one for each mirror */
struct scrub_block *sblock_bad;
int ret;
@@ -918,13 +911,11 @@ static int scrub_handle_errored_block(struct scrub_block *sblock_to_check)
}
length = sblock_to_check->page_count * PAGE_SIZE;
logical = sblock_to_check->pagev[0]->logical;
- generation = sblock_to_check->pagev[0]->generation;
BUG_ON(sblock_to_check->pagev[0]->mirror_num < 1);
failed_mirror_index = sblock_to_check->pagev[0]->mirror_num - 1;
is_metadata = !(sblock_to_check->pagev[0]->flags &
BTRFS_EXTENT_FLAG_DATA);
have_csum = sblock_to_check->pagev[0]->have_csum;
- csum = sblock_to_check->pagev[0]->csum;
dev = sblock_to_check->pagev[0]->dev;
if (sctx->is_dev_replace && !is_metadata && !have_csum) {
@@ -987,8 +978,7 @@ static int scrub_handle_errored_block(struct scrub_block *sblock_to_check)
sblock_bad = sblocks_for_recheck + failed_mirror_index;
/* build and submit the bios for the failed mirror, check checksums */
- scrub_recheck_block(fs_info, sblock_bad, is_metadata, have_csum,
- csum, generation, sctx->csum_size, 1);
+ scrub_recheck_block(fs_info, sblock_bad, 1);
if (!sblock_bad->header_error && !sblock_bad->checksum_error &&
sblock_bad->no_io_error_seen) {
@@ -1101,9 +1091,7 @@ nodatasum_case:
sblock_other = sblocks_for_recheck + mirror_index;
/* build and submit the bios, check checksums */
- scrub_recheck_block(fs_info, sblock_other, is_metadata,
- have_csum, csum, generation,
- sctx->csum_size, 0);
+ scrub_recheck_block(fs_info, sblock_other, 0);
if (!sblock_other->header_error &&
!sblock_other->checksum_error &&
@@ -1215,9 +1203,7 @@ nodatasum_case:
* is verified, but most likely the data comes out
* of the page cache.
*/
- scrub_recheck_block(fs_info, sblock_bad,
- is_metadata, have_csum, csum,
- generation, sctx->csum_size, 1);
+ scrub_recheck_block(fs_info, sblock_bad, 1);
if (!sblock_bad->header_error &&
!sblock_bad->checksum_error &&
sblock_bad->no_io_error_seen)
@@ -1318,6 +1304,9 @@ static int scrub_setup_recheck_block(struct scrub_block *original_sblock,
struct btrfs_fs_info *fs_info = sctx->dev_root->fs_info;
u64 length = original_sblock->page_count * PAGE_SIZE;
u64 logical = original_sblock->pagev[0]->logical;
+ u64 generation = original_sblock->pagev[0]->generation;
+ u64 flags = original_sblock->pagev[0]->flags;
+ u64 have_csum = original_sblock->pagev[0]->have_csum;
struct scrub_recover *recover;
struct btrfs_bio *bbio;
u64 sublen;
@@ -1372,6 +1361,7 @@ static int scrub_setup_recheck_block(struct scrub_block *original_sblock,
sblock = sblocks_for_recheck + mirror_index;
sblock->sctx = sctx;
+
page = kzalloc(sizeof(*page), GFP_NOFS);
if (!page) {
leave_nomem:
@@ -1383,7 +1373,15 @@ leave_nomem:
}
scrub_page_get(page);
sblock->pagev[page_index] = page;
+ page->sblock = sblock;
+ page->flags = flags;
+ page->generation = generation;
page->logical = logical;
+ page->have_csum = have_csum;
+ if (have_csum)
+ memcpy(page->csum,
+ original_sblock->pagev[0]->csum,
+ sctx->csum_size);
scrub_stripe_index_and_offset(logical,
bbio->map_type,
@@ -1474,15 +1472,12 @@ static int scrub_submit_raid56_bio_wait(struct btrfs_fs_info *fs_info,
* the pages that are errored in the just handled mirror can be repaired.
*/
static void scrub_recheck_block(struct btrfs_fs_info *fs_info,
- struct scrub_block *sblock, int is_metadata,
- int have_csum, u8 *csum, u64 generation,
- u16 csum_size, int retry_failed_mirror)
+ struct scrub_block *sblock,
+ int retry_failed_mirror)
{
int page_num;
sblock->no_io_error_seen = 1;
- sblock->header_error = 0;
- sblock->checksum_error = 0;
for (page_num = 0; page_num < sblock->page_count; page_num++) {
struct bio *bio;
@@ -1518,9 +1513,7 @@ static void scrub_recheck_block(struct btrfs_fs_info *fs_info,
}
if (sblock->no_io_error_seen)
- scrub_recheck_block_checksum(fs_info, sblock, is_metadata,
- have_csum, csum, generation,
- csum_size);
+ scrub_recheck_block_checksum(sblock);
return;
}
@@ -1535,61 +1528,16 @@ static inline int scrub_check_fsid(u8 fsid[],
return !ret;
}
-static void scrub_recheck_block_checksum(struct btrfs_fs_info *fs_info,
- struct scrub_block *sblock,
- int is_metadata, int have_csum,
- const u8 *csum, u64 generation,
- u16 csum_size)
+static void scrub_recheck_block_checksum(struct scrub_block *sblock)
{
- int page_num;
- u8 calculated_csum[BTRFS_CSUM_SIZE];
- u32 crc = ~(u32)0;
- void *mapped_buffer;
-
- WARN_ON(!sblock->pagev[0]->page);
- if (is_metadata) {
- struct btrfs_header *h;
-
- mapped_buffer = kmap_atomic(sblock->pagev[0]->page);
- h = (struct btrfs_header *)mapped_buffer;
-
- if (sblock->pagev[0]->logical != btrfs_stack_header_bytenr(h) ||
- !scrub_check_fsid(h->fsid, sblock->pagev[0]) ||
- memcmp(h->chunk_tree_uuid, fs_info->chunk_tree_uuid,
- BTRFS_UUID_SIZE)) {
- sblock->header_error = 1;
- } else if (generation != btrfs_stack_header_generation(h)) {
- sblock->header_error = 1;
- sblock->generation_error = 1;
- }
- csum = h->csum;
- } else {
- if (!have_csum)
- return;
-
- mapped_buffer = kmap_atomic(sblock->pagev[0]->page);
- }
-
- for (page_num = 0;;) {
- if (page_num == 0 && is_metadata)
- crc = btrfs_csum_data(
- ((u8 *)mapped_buffer) + BTRFS_CSUM_SIZE,
- crc, PAGE_SIZE - BTRFS_CSUM_SIZE);
- else
- crc = btrfs_csum_data(mapped_buffer, crc, PAGE_SIZE);
-
- kunmap_atomic(mapped_buffer);
- page_num++;
- if (page_num >= sblock->page_count)
- break;
- WARN_ON(!sblock->pagev[page_num]->page);
-
- mapped_buffer = kmap_atomic(sblock->pagev[page_num]->page);
- }
+ sblock->header_error = 0;
+ sblock->checksum_error = 0;
+ sblock->generation_error = 0;
- btrfs_csum_final(crc, calculated_csum);
- if (memcmp(calculated_csum, csum, csum_size))
- sblock->checksum_error = 1;
+ if (sblock->pagev[0]->flags & BTRFS_EXTENT_FLAG_DATA)
+ scrub_checksum_data(sblock);
+ else
+ scrub_checksum_tree_block(sblock);
}
static int scrub_repair_block_from_good_copy(struct scrub_block *sblock_bad,
@@ -1833,6 +1781,18 @@ static int scrub_checksum(struct scrub_block *sblock)
u64 flags;
int ret;
+ /*
+ * No need to initialize these stats currently,
+ * because this function only use return value
+ * instead of these stats value.
+ *
+ * Todo:
+ * always use stats
+ */
+ sblock->header_error = 0;
+ sblock->generation_error = 0;
+ sblock->checksum_error = 0;
+
WARN_ON(sblock->page_count < 1);
flags = sblock->pagev[0]->flags;
ret = 0;
@@ -1858,7 +1818,6 @@ static int scrub_checksum_data(struct scrub_block *sblock)
struct page *page;
void *buffer;
u32 crc = ~(u32)0;
- int fail = 0;
u64 len;
int index;
@@ -1889,9 +1848,9 @@ static int scrub_checksum_data(struct scrub_block *sblock)
btrfs_csum_final(crc, csum);
if (memcmp(csum, on_disk_csum, sctx->csum_size))
- fail = 1;
+ sblock->checksum_error = 1;
- return fail;
+ return sblock->checksum_error;
}
static int scrub_checksum_tree_block(struct scrub_block *sblock)
@@ -1907,8 +1866,6 @@ static int scrub_checksum_tree_block(struct scrub_block *sblock)
u64 mapped_size;
void *p;
u32 crc = ~(u32)0;
- int fail = 0;
- int crc_fail = 0;
u64 len;
int index;
@@ -1923,19 +1880,20 @@ static int scrub_checksum_tree_block(struct scrub_block *sblock)
* a) don't have an extent buffer and
* b) the page is already kmapped
*/
-
if (sblock->pagev[0]->logical != btrfs_stack_header_bytenr(h))
- ++fail;
+ sblock->header_error = 1;
- if (sblock->pagev[0]->generation != btrfs_stack_header_generation(h))
- ++fail;
+ if (sblock->pagev[0]->generation != btrfs_stack_header_generation(h)) {
+ sblock->header_error = 1;
+ sblock->generation_error = 1;
+ }
if (!scrub_check_fsid(h->fsid, sblock->pagev[0]))
- ++fail;
+ sblock->header_error = 1;
if (memcmp(h->chunk_tree_uuid, fs_info->chunk_tree_uuid,
BTRFS_UUID_SIZE))
- ++fail;
+ sblock->header_error = 1;
len = sctx->nodesize - BTRFS_CSUM_SIZE;
mapped_size = PAGE_SIZE - BTRFS_CSUM_SIZE;
@@ -1960,9 +1918,9 @@ static int scrub_checksum_tree_block(struct scrub_block *sblock)
btrfs_csum_final(crc, calculated_csum);
if (memcmp(calculated_csum, on_disk_csum, sctx->csum_size))
- ++crc_fail;
+ sblock->checksum_error = 1;
- return fail || crc_fail;
+ return sblock->header_error || sblock->checksum_error;
}
static int scrub_checksum_super(struct scrub_block *sblock)
@@ -2176,39 +2134,27 @@ static void scrub_missing_raid56_worker(struct btrfs_work *work)
{
struct scrub_block *sblock = container_of(work, struct scrub_block, work);
struct scrub_ctx *sctx = sblock->sctx;
- struct btrfs_fs_info *fs_info = sctx->dev_root->fs_info;
- unsigned int is_metadata;
- unsigned int have_csum;
- u8 *csum;
- u64 generation;
u64 logical;
struct btrfs_device *dev;
- is_metadata = !(sblock->pagev[0]->flags & BTRFS_EXTENT_FLAG_DATA);
- have_csum = sblock->pagev[0]->have_csum;
- csum = sblock->pagev[0]->csum;
- generation = sblock->pagev[0]->generation;
logical = sblock->pagev[0]->logical;
dev = sblock->pagev[0]->dev;
- if (sblock->no_io_error_seen) {
- scrub_recheck_block_checksum(fs_info, sblock, is_metadata,
- have_csum, csum, generation,
- sctx->csum_size);
- }
+ if (sblock->no_io_error_seen)
+ scrub_recheck_block_checksum(sblock);
if (!sblock->no_io_error_seen) {
spin_lock(&sctx->stat_lock);
sctx->stat.read_errors++;
spin_unlock(&sctx->stat_lock);
- btrfs_err_rl_in_rcu(fs_info,
+ btrfs_err_rl_in_rcu(sctx->dev_root->fs_info,
"IO error rebuilding logical %llu for dev %s",
logical, rcu_str_deref(dev->name));
} else if (sblock->header_error || sblock->checksum_error) {
spin_lock(&sctx->stat_lock);
sctx->stat.uncorrectable_errors++;
spin_unlock(&sctx->stat_lock);
- btrfs_err_rl_in_rcu(fs_info,
+ btrfs_err_rl_in_rcu(sctx->dev_root->fs_info,
"failed to rebuild valid logical %llu for dev %s",
logical, rcu_str_deref(dev->name));
} else {
@@ -2500,8 +2446,7 @@ static void scrub_block_complete(struct scrub_block *sblock)
}
}
-static int scrub_find_csum(struct scrub_ctx *sctx, u64 logical, u64 len,
- u8 *csum)
+static int scrub_find_csum(struct scrub_ctx *sctx, u64 logical, u8 *csum)
{
struct btrfs_ordered_sum *sum = NULL;
unsigned long index;
@@ -2565,7 +2510,7 @@ static int scrub_extent(struct scrub_ctx *sctx, u64 logical, u64 len,
if (flags & BTRFS_EXTENT_FLAG_DATA) {
/* push csums to sbio */
- have_csum = scrub_find_csum(sctx, logical, l, csum);
+ have_csum = scrub_find_csum(sctx, logical, csum);
if (have_csum == 0)
++sctx->stat.no_csum;
if (sctx->is_dev_replace && !have_csum) {
@@ -2703,7 +2648,7 @@ static int scrub_extent_for_parity(struct scrub_parity *sparity,
if (flags & BTRFS_EXTENT_FLAG_DATA) {
/* push csums to sbio */
- have_csum = scrub_find_csum(sctx, logical, l, csum);
+ have_csum = scrub_find_csum(sctx, logical, csum);
if (have_csum == 0)
goto skip;
}
@@ -3012,6 +2957,9 @@ static noinline_for_stack int scrub_raid56_parity(struct scrub_ctx *sctx,
logic_start + map->stripe_len)) {
btrfs_err(fs_info, "scrub: tree block %llu spanning stripes, ignored. logical=%llu",
key.objectid, logic_start);
+ spin_lock(&sctx->stat_lock);
+ sctx->stat.uncorrectable_errors++;
+ spin_unlock(&sctx->stat_lock);
goto next;
}
again:
@@ -3361,6 +3309,9 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx,
"scrub: tree block %llu spanning "
"stripes, ignored. logical=%llu",
key.objectid, logical);
+ spin_lock(&sctx->stat_lock);
+ sctx->stat.uncorrectable_errors++;
+ spin_unlock(&sctx->stat_lock);
goto next;
}
@@ -3481,7 +3432,9 @@ out:
static noinline_for_stack int scrub_chunk(struct scrub_ctx *sctx,
struct btrfs_device *scrub_dev,
u64 chunk_offset, u64 length,
- u64 dev_offset, int is_dev_replace)
+ u64 dev_offset,
+ struct btrfs_block_group_cache *cache,
+ int is_dev_replace)
{
struct btrfs_mapping_tree *map_tree =
&sctx->dev_root->fs_info->mapping_tree;
@@ -3494,8 +3447,18 @@ static noinline_for_stack int scrub_chunk(struct scrub_ctx *sctx,
em = lookup_extent_mapping(&map_tree->map_tree, chunk_offset, 1);
read_unlock(&map_tree->map_tree.lock);
- if (!em)
- return -EINVAL;
+ if (!em) {
+ /*
+ * Might have been an unused block group deleted by the cleaner
+ * kthread or relocation.
+ */
+ spin_lock(&cache->lock);
+ if (!cache->removed)
+ ret = -EINVAL;
+ spin_unlock(&cache->lock);
+
+ return ret;
+ }
map = (struct map_lookup *)em->bdev;
if (em->start != chunk_offset)
@@ -3532,6 +3495,7 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
u64 length;
u64 chunk_offset;
int ret = 0;
+ int ro_set;
int slot;
struct extent_buffer *l;
struct btrfs_key key;
@@ -3617,7 +3581,21 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
scrub_pause_on(fs_info);
ret = btrfs_inc_block_group_ro(root, cache);
scrub_pause_off(fs_info);
- if (ret) {
+
+ if (ret == 0) {
+ ro_set = 1;
+ } else if (ret == -ENOSPC) {
+ /*
+ * btrfs_inc_block_group_ro return -ENOSPC when it
+ * failed in creating new chunk for metadata.
+ * It is not a problem for scrub/replace, because
+ * metadata are always cowed, and our scrub paused
+ * commit_transactions.
+ */
+ ro_set = 0;
+ } else {
+ btrfs_warn(fs_info, "failed setting block group ro, ret=%d\n",
+ ret);
btrfs_put_block_group(cache);
break;
}
@@ -3626,7 +3604,7 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
dev_replace->cursor_left = found_key.offset;
dev_replace->item_needs_writeback = 1;
ret = scrub_chunk(sctx, scrub_dev, chunk_offset, length,
- found_key.offset, is_dev_replace);
+ found_key.offset, cache, is_dev_replace);
/*
* flush, submit all pending read and write bios, afterwards
@@ -3660,7 +3638,30 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
scrub_pause_off(fs_info);
- btrfs_dec_block_group_ro(root, cache);
+ if (ro_set)
+ btrfs_dec_block_group_ro(root, cache);
+
+ /*
+ * We might have prevented the cleaner kthread from deleting
+ * this block group if it was already unused because we raced
+ * and set it to RO mode first. So add it back to the unused
+ * list, otherwise it might not ever be deleted unless a manual
+ * balance is triggered or it becomes used and unused again.
+ */
+ spin_lock(&cache->lock);
+ if (!cache->removed && !cache->ro && cache->reserved == 0 &&
+ btrfs_block_group_used(&cache->item) == 0) {
+ spin_unlock(&cache->lock);
+ spin_lock(&fs_info->unused_bgs_lock);
+ if (list_empty(&cache->bg_list)) {
+ btrfs_get_block_group(cache);
+ list_add_tail(&cache->bg_list,
+ &fs_info->unused_bgs);
+ }
+ spin_unlock(&fs_info->unused_bgs_lock);
+ } else {
+ spin_unlock(&cache->lock);
+ }
btrfs_put_block_group(cache);
if (ret)
diff --git a/fs/btrfs/tests/free-space-tests.c b/fs/btrfs/tests/free-space-tests.c
index c8c3d70c31ff..8b72b005bfb9 100644
--- a/fs/btrfs/tests/free-space-tests.c
+++ b/fs/btrfs/tests/free-space-tests.c
@@ -898,8 +898,10 @@ int btrfs_test_free_space_cache(void)
}
root = btrfs_alloc_dummy_root();
- if (!root)
+ if (IS_ERR(root)) {
+ ret = PTR_ERR(root);
goto out;
+ }
root->fs_info = btrfs_alloc_dummy_fs_info();
if (!root->fs_info)
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 418c6a2ad7d8..3367a3c6f214 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -592,6 +592,38 @@ struct btrfs_trans_handle *btrfs_start_transaction(struct btrfs_root *root,
return start_transaction(root, num_items, TRANS_START,
BTRFS_RESERVE_FLUSH_ALL);
}
+struct btrfs_trans_handle *btrfs_start_transaction_fallback_global_rsv(
+ struct btrfs_root *root,
+ unsigned int num_items,
+ int min_factor)
+{
+ struct btrfs_trans_handle *trans;
+ u64 num_bytes;
+ int ret;
+
+ trans = btrfs_start_transaction(root, num_items);
+ if (!IS_ERR(trans) || PTR_ERR(trans) != -ENOSPC)
+ return trans;
+
+ trans = btrfs_start_transaction(root, 0);
+ if (IS_ERR(trans))
+ return trans;
+
+ num_bytes = btrfs_calc_trans_metadata_size(root, num_items);
+ ret = btrfs_cond_migrate_bytes(root->fs_info,
+ &root->fs_info->trans_block_rsv,
+ num_bytes,
+ min_factor);
+ if (ret) {
+ btrfs_end_transaction(trans, root);
+ return ERR_PTR(ret);
+ }
+
+ trans->block_rsv = &root->fs_info->trans_block_rsv;
+ trans->bytes_reserved = num_bytes;
+
+ return trans;
+}
struct btrfs_trans_handle *btrfs_start_transaction_lflush(
struct btrfs_root *root,
diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h
index b05b2f64d913..0da21ca9b3fb 100644
--- a/fs/btrfs/transaction.h
+++ b/fs/btrfs/transaction.h
@@ -185,6 +185,10 @@ int btrfs_end_transaction(struct btrfs_trans_handle *trans,
struct btrfs_root *root);
struct btrfs_trans_handle *btrfs_start_transaction(struct btrfs_root *root,
unsigned int num_items);
+struct btrfs_trans_handle *btrfs_start_transaction_fallback_global_rsv(
+ struct btrfs_root *root,
+ unsigned int num_items,
+ int min_factor);
struct btrfs_trans_handle *btrfs_start_transaction_lflush(
struct btrfs_root *root,
unsigned int num_items);
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 17ed76d18eb6..456452206609 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -232,8 +232,8 @@ static struct btrfs_device *__alloc_device(void)
spin_lock_init(&dev->reada_lock);
atomic_set(&dev->reada_in_flight, 0);
atomic_set(&dev->dev_stats_ccnt, 0);
- INIT_RADIX_TREE(&dev->reada_zones, GFP_NOFS & ~__GFP_WAIT);
- INIT_RADIX_TREE(&dev->reada_extents, GFP_NOFS & ~__GFP_WAIT);
+ INIT_RADIX_TREE(&dev->reada_zones, GFP_NOFS & ~__GFP_DIRECT_RECLAIM);
+ INIT_RADIX_TREE(&dev->reada_extents, GFP_NOFS & ~__GFP_DIRECT_RECLAIM);
return dev;
}
@@ -1973,8 +1973,7 @@ void btrfs_rm_dev_replace_remove_srcdev(struct btrfs_fs_info *fs_info,
if (srcdev->writeable) {
fs_devices->rw_devices--;
/* zero out the old super if it is writable */
- btrfs_scratch_superblocks(srcdev->bdev,
- rcu_str_deref(srcdev->name));
+ btrfs_scratch_superblocks(srcdev->bdev, srcdev->name->str);
}
if (srcdev->bdev)
@@ -2024,8 +2023,7 @@ void btrfs_destroy_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
btrfs_sysfs_rm_device_link(fs_info->fs_devices, tgtdev);
if (tgtdev->bdev) {
- btrfs_scratch_superblocks(tgtdev->bdev,
- rcu_str_deref(tgtdev->name));
+ btrfs_scratch_superblocks(tgtdev->bdev, tgtdev->name->str);
fs_info->fs_devices->open_devices--;
}
fs_info->fs_devices->num_devices--;
@@ -2853,7 +2851,8 @@ static int btrfs_relocate_chunk(struct btrfs_root *root, u64 chunk_offset)
if (ret)
return ret;
- trans = btrfs_start_transaction(root, 0);
+ trans = btrfs_start_trans_remove_block_group(root->fs_info,
+ chunk_offset);
if (IS_ERR(trans)) {
ret = PTR_ERR(trans);
btrfs_std_error(root->fs_info, ret, NULL);
@@ -3123,7 +3122,7 @@ static int chunk_profiles_filter(u64 chunk_type,
return 1;
}
-static int chunk_usage_filter(struct btrfs_fs_info *fs_info, u64 chunk_offset,
+static int chunk_usage_range_filter(struct btrfs_fs_info *fs_info, u64 chunk_offset,
struct btrfs_balance_args *bargs)
{
struct btrfs_block_group_cache *cache;
@@ -3156,7 +3155,7 @@ static int chunk_usage_filter(struct btrfs_fs_info *fs_info, u64 chunk_offset,
return ret;
}
-static int chunk_usage_range_filter(struct btrfs_fs_info *fs_info,
+static int chunk_usage_filter(struct btrfs_fs_info *fs_info,
u64 chunk_offset, struct btrfs_balance_args *bargs)
{
struct btrfs_block_group_cache *cache;
@@ -3400,6 +3399,7 @@ static int __btrfs_balance(struct btrfs_fs_info *fs_info)
u32 count_data = 0;
u32 count_meta = 0;
u32 count_sys = 0;
+ int chunk_reserved = 0;
/* step one make some room on all the devices */
devices = &fs_info->fs_devices->devices;
@@ -3501,6 +3501,7 @@ again:
ret = should_balance_chunk(chunk_root, leaf, chunk,
found_key.offset);
+
btrfs_release_path(path);
if (!ret) {
mutex_unlock(&fs_info->delete_unused_bgs_mutex);
@@ -3537,6 +3538,25 @@ again:
goto loop;
}
+ if ((chunk_type & BTRFS_BLOCK_GROUP_DATA) && !chunk_reserved) {
+ trans = btrfs_start_transaction(chunk_root, 0);
+ if (IS_ERR(trans)) {
+ mutex_unlock(&fs_info->delete_unused_bgs_mutex);
+ ret = PTR_ERR(trans);
+ goto error;
+ }
+
+ ret = btrfs_force_chunk_alloc(trans, chunk_root,
+ BTRFS_BLOCK_GROUP_DATA);
+ if (ret < 0) {
+ mutex_unlock(&fs_info->delete_unused_bgs_mutex);
+ goto error;
+ }
+
+ btrfs_end_transaction(trans, chunk_root);
+ chunk_reserved = 1;
+ }
+
ret = btrfs_relocate_chunk(chunk_root,
found_key.offset);
mutex_unlock(&fs_info->delete_unused_bgs_mutex);
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index ec5712372732..d5c84f6b1353 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -382,7 +382,7 @@ struct map_lookup {
#define BTRFS_BALANCE_ARGS_LIMIT (1ULL << 5)
#define BTRFS_BALANCE_ARGS_LIMIT_RANGE (1ULL << 6)
#define BTRFS_BALANCE_ARGS_STRIPES_RANGE (1ULL << 7)
-#define BTRFS_BALANCE_ARGS_USAGE_RANGE (1ULL << 8)
+#define BTRFS_BALANCE_ARGS_USAGE_RANGE (1ULL << 10)
#define BTRFS_BALANCE_ARGS_MASK \
(BTRFS_BALANCE_ARGS_PROFILES | \
diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c
index 6f518c90e1c1..1fcd7b6e7564 100644
--- a/fs/btrfs/xattr.c
+++ b/fs/btrfs/xattr.c
@@ -313,8 +313,10 @@ ssize_t btrfs_listxattr(struct dentry *dentry, char *buffer, size_t size)
/* check to make sure this item is what we want */
if (found_key.objectid != key.objectid)
break;
- if (found_key.type != BTRFS_XATTR_ITEM_KEY)
+ if (found_key.type > BTRFS_XATTR_ITEM_KEY)
break;
+ if (found_key.type < BTRFS_XATTR_ITEM_KEY)
+ goto next;
di = btrfs_item_ptr(leaf, slot, struct btrfs_dir_item);
if (verify_dir_item(root, leaf, di))
OpenPOWER on IntegriCloud