summaryrefslogtreecommitdiffstats
path: root/fs/btrfs
diff options
context:
space:
mode:
Diffstat (limited to 'fs/btrfs')
-rw-r--r--fs/btrfs/ctree.c8
-rw-r--r--fs/btrfs/ctree.h5
-rw-r--r--fs/btrfs/disk-io.c2
-rw-r--r--fs/btrfs/extent-tree.c51
-rw-r--r--fs/btrfs/extent_io.c6
-rw-r--r--fs/btrfs/file.c87
-rw-r--r--fs/btrfs/inode.c113
-rw-r--r--fs/btrfs/ordered-data.c7
-rw-r--r--fs/btrfs/qgroup.c2
-rw-r--r--fs/btrfs/send.c171
-rw-r--r--fs/btrfs/tests/inode-tests.c197
-rw-r--r--fs/btrfs/transaction.c42
-rw-r--r--fs/btrfs/tree-log.c2
-rw-r--r--fs/btrfs/xattr.c8
14 files changed, 593 insertions, 108 deletions
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 9936421..6d67f32 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -1645,14 +1645,14 @@ int btrfs_realloc_node(struct btrfs_trans_handle *trans,
parent_nritems = btrfs_header_nritems(parent);
blocksize = root->nodesize;
- end_slot = parent_nritems;
+ end_slot = parent_nritems - 1;
- if (parent_nritems == 1)
+ if (parent_nritems <= 1)
return 0;
btrfs_set_lock_blocking(parent);
- for (i = start_slot; i < end_slot; i++) {
+ for (i = start_slot; i <= end_slot; i++) {
int close = 1;
btrfs_node_key(parent, &disk_key, i);
@@ -1669,7 +1669,7 @@ int btrfs_realloc_node(struct btrfs_trans_handle *trans,
other = btrfs_node_blockptr(parent, i - 1);
close = close_blocks(blocknr, other, blocksize);
}
- if (!close && i < end_slot - 2) {
+ if (!close && i < end_slot) {
other = btrfs_node_blockptr(parent, i + 1);
close = close_blocks(blocknr, other, blocksize);
}
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 84c3b00..f9c89ca 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -3387,6 +3387,8 @@ int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans,
struct btrfs_root *root);
+int btrfs_setup_space_cache(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root);
int btrfs_extent_readonly(struct btrfs_root *root, u64 bytenr);
int btrfs_free_block_groups(struct btrfs_fs_info *info);
int btrfs_read_block_groups(struct btrfs_root *root);
@@ -3909,6 +3911,9 @@ int btrfs_prealloc_file_range_trans(struct inode *inode,
loff_t actual_len, u64 *alloc_hint);
int btrfs_inode_check_errors(struct inode *inode);
extern const struct dentry_operations btrfs_dentry_operations;
+#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
+void btrfs_test_inode_set_ops(struct inode *inode);
+#endif
/* ioctl.c */
long btrfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index f79f385..639f266 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -3921,7 +3921,7 @@ static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info,
}
if (btrfs_super_sys_array_size(sb) < sizeof(struct btrfs_disk_key)
+ sizeof(struct btrfs_chunk)) {
- printk(KERN_ERR "BTRFS: system chunk array too small %u < %lu\n",
+ printk(KERN_ERR "BTRFS: system chunk array too small %u < %zu\n",
btrfs_super_sys_array_size(sb),
sizeof(struct btrfs_disk_key)
+ sizeof(struct btrfs_chunk));
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 571f402..8b353ad 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -3208,6 +3208,8 @@ static int cache_save_setup(struct btrfs_block_group_cache *block_group,
return 0;
}
+ if (trans->aborted)
+ return 0;
again:
inode = lookup_free_space_inode(root, block_group, path);
if (IS_ERR(inode) && PTR_ERR(inode) != -ENOENT) {
@@ -3243,6 +3245,20 @@ again:
*/
BTRFS_I(inode)->generation = 0;
ret = btrfs_update_inode(trans, root, inode);
+ if (ret) {
+ /*
+ * So theoretically we could recover from this, simply set the
+ * super cache generation to 0 so we know to invalidate the
+ * cache, but then we'd have to keep track of the block groups
+ * that fail this way so we know we _have_ to reset this cache
+ * before the next commit or risk reading stale cache. So to
+ * limit our exposure to horrible edge cases lets just abort the
+ * transaction, this only happens in really bad situations
+ * anyway.
+ */
+ btrfs_abort_transaction(trans, root, ret);
+ goto out_put;
+ }
WARN_ON(ret);
if (i_size_read(inode) > 0) {
@@ -3309,6 +3325,32 @@ out:
return ret;
}
+int btrfs_setup_space_cache(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root)
+{
+ struct btrfs_block_group_cache *cache, *tmp;
+ struct btrfs_transaction *cur_trans = trans->transaction;
+ struct btrfs_path *path;
+
+ if (list_empty(&cur_trans->dirty_bgs) ||
+ !btrfs_test_opt(root, SPACE_CACHE))
+ return 0;
+
+ path = btrfs_alloc_path();
+ if (!path)
+ return -ENOMEM;
+
+ /* Could add new block groups, use _safe just in case */
+ list_for_each_entry_safe(cache, tmp, &cur_trans->dirty_bgs,
+ dirty_list) {
+ if (cache->disk_cache_state == BTRFS_DC_CLEAR)
+ cache_save_setup(cache, trans, path);
+ }
+
+ btrfs_free_path(path);
+ return 0;
+}
+
int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans,
struct btrfs_root *root)
{
@@ -5094,7 +5136,11 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes)
num_bytes = ALIGN(num_bytes, root->sectorsize);
spin_lock(&BTRFS_I(inode)->lock);
- BTRFS_I(inode)->outstanding_extents++;
+ nr_extents = (unsigned)div64_u64(num_bytes +
+ BTRFS_MAX_EXTENT_SIZE - 1,
+ BTRFS_MAX_EXTENT_SIZE);
+ BTRFS_I(inode)->outstanding_extents += nr_extents;
+ nr_extents = 0;
if (BTRFS_I(inode)->outstanding_extents >
BTRFS_I(inode)->reserved_extents)
@@ -5239,6 +5285,9 @@ void btrfs_delalloc_release_metadata(struct inode *inode, u64 num_bytes)
if (dropped > 0)
to_free += btrfs_calc_trans_metadata_size(root, dropped);
+ if (btrfs_test_is_dummy_root(root))
+ return;
+
trace_btrfs_space_reservation(root->fs_info, "delalloc",
btrfs_ino(inode), to_free, 0);
if (root->fs_info->quota_enabled) {
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index c7233ff..d688cfe 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -4968,6 +4968,12 @@ static int release_extent_buffer(struct extent_buffer *eb)
/* Should be safe to release our pages at this point */
btrfs_release_extent_buffer_page(eb);
+#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
+ if (unlikely(test_bit(EXTENT_BUFFER_DUMMY, &eb->bflags))) {
+ __free_extent_buffer(eb);
+ return 1;
+ }
+#endif
call_rcu(&eb->rcu_head, btrfs_release_extent_buffer_rcu);
return 1;
}
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index b78bbba..30982bb 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1811,22 +1811,10 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
mutex_unlock(&inode->i_mutex);
/*
- * we want to make sure fsync finds this change
- * but we haven't joined a transaction running right now.
- *
- * Later on, someone is sure to update the inode and get the
- * real transid recorded.
- *
- * We set last_trans now to the fs_info generation + 1,
- * this will either be one more than the running transaction
- * or the generation used for the next transaction if there isn't
- * one running right now.
- *
* We also have to set last_sub_trans to the current log transid,
* otherwise subsequent syncs to a file that's been synced in this
* transaction will appear to have already occured.
*/
- BTRFS_I(inode)->last_trans = root->fs_info->generation + 1;
BTRFS_I(inode)->last_sub_trans = root->log_transid;
if (num_written > 0) {
err = generic_write_sync(file, pos, num_written);
@@ -1959,25 +1947,37 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
atomic_inc(&root->log_batch);
/*
- * check the transaction that last modified this inode
- * and see if its already been committed
- */
- if (!BTRFS_I(inode)->last_trans) {
- mutex_unlock(&inode->i_mutex);
- goto out;
- }
-
- /*
- * if the last transaction that changed this file was before
- * the current transaction, we can bail out now without any
- * syncing
+ * If the last transaction that changed this file was before the current
+ * transaction and we have the full sync flag set in our inode, we can
+ * bail out now without any syncing.
+ *
+ * Note that we can't bail out if the full sync flag isn't set. This is
+ * because when the full sync flag is set we start all ordered extents
+ * and wait for them to fully complete - when they complete they update
+ * the inode's last_trans field through:
+ *
+ * btrfs_finish_ordered_io() ->
+ * btrfs_update_inode_fallback() ->
+ * btrfs_update_inode() ->
+ * btrfs_set_inode_last_trans()
+ *
+ * So we are sure that last_trans is up to date and can do this check to
+ * bail out safely. For the fast path, when the full sync flag is not
+ * set in our inode, we can not do it because we start only our ordered
+ * extents and don't wait for them to complete (that is when
+ * btrfs_finish_ordered_io runs), so here at this point their last_trans
+ * value might be less than or equals to fs_info->last_trans_committed,
+ * and setting a speculative last_trans for an inode when a buffered
+ * write is made (such as fs_info->generation + 1 for example) would not
+ * be reliable since after setting the value and before fsync is called
+ * any number of transactions can start and commit (transaction kthread
+ * commits the current transaction periodically), and a transaction
+ * commit does not start nor waits for ordered extents to complete.
*/
smp_mb();
if (btrfs_inode_in_log(inode, root->fs_info->generation) ||
- BTRFS_I(inode)->last_trans <=
- root->fs_info->last_trans_committed) {
- BTRFS_I(inode)->last_trans = 0;
-
+ (full_sync && BTRFS_I(inode)->last_trans <=
+ root->fs_info->last_trans_committed)) {
/*
* We'v had everything committed since the last time we were
* modified so clear this flag in case it was set for whatever
@@ -2275,6 +2275,8 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
bool same_page;
bool no_holes = btrfs_fs_incompat(root->fs_info, NO_HOLES);
u64 ino_size;
+ bool truncated_page = false;
+ bool updated_inode = false;
ret = btrfs_wait_ordered_range(inode, offset, len);
if (ret)
@@ -2306,13 +2308,18 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
* entire page.
*/
if (same_page && len < PAGE_CACHE_SIZE) {
- if (offset < ino_size)
+ if (offset < ino_size) {
+ truncated_page = true;
ret = btrfs_truncate_page(inode, offset, len, 0);
+ } else {
+ ret = 0;
+ }
goto out_only_mutex;
}
/* zero back part of the first page */
if (offset < ino_size) {
+ truncated_page = true;
ret = btrfs_truncate_page(inode, offset, 0, 0);
if (ret) {
mutex_unlock(&inode->i_mutex);
@@ -2348,6 +2355,7 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
if (!ret) {
/* zero the front end of the last page */
if (tail_start + tail_len < ino_size) {
+ truncated_page = true;
ret = btrfs_truncate_page(inode,
tail_start + tail_len, 0, 1);
if (ret)
@@ -2357,8 +2365,8 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
}
if (lockend < lockstart) {
- mutex_unlock(&inode->i_mutex);
- return 0;
+ ret = 0;
+ goto out_only_mutex;
}
while (1) {
@@ -2506,6 +2514,7 @@ out_trans:
trans->block_rsv = &root->fs_info->trans_block_rsv;
ret = btrfs_update_inode(trans, root, inode);
+ updated_inode = true;
btrfs_end_transaction(trans, root);
btrfs_btree_balance_dirty(root);
out_free:
@@ -2515,6 +2524,22 @@ out:
unlock_extent_cached(&BTRFS_I(inode)->io_tree, lockstart, lockend,
&cached_state, GFP_NOFS);
out_only_mutex:
+ if (!updated_inode && truncated_page && !ret && !err) {
+ /*
+ * If we only end up zeroing part of a page, we still need to
+ * update the inode item, so that all the time fields are
+ * updated as well as the necessary btrfs inode in memory fields
+ * for detecting, at fsync time, if the inode isn't yet in the
+ * log tree or it's there but not up to date.
+ */
+ trans = btrfs_start_transaction(root, 1);
+ if (IS_ERR(trans)) {
+ err = PTR_ERR(trans);
+ } else {
+ err = btrfs_update_inode(trans, root, inode);
+ ret = btrfs_end_transaction(trans, root);
+ }
+ }
mutex_unlock(&inode->i_mutex);
if (ret && !err)
err = ret;
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index a85c23d..d2e732d 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -108,6 +108,13 @@ static struct extent_map *create_pinned_em(struct inode *inode, u64 start,
static int btrfs_dirty_inode(struct inode *inode);
+#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
+void btrfs_test_inode_set_ops(struct inode *inode)
+{
+ BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops;
+}
+#endif
+
static int btrfs_init_inode_security(struct btrfs_trans_handle *trans,
struct inode *inode, struct inode *dir,
const struct qstr *qstr)
@@ -1542,30 +1549,17 @@ static void btrfs_split_extent_hook(struct inode *inode,
u64 new_size;
/*
- * We need the largest size of the remaining extent to see if we
- * need to add a new outstanding extent. Think of the following
- * case
- *
- * [MEAX_EXTENT_SIZEx2 - 4k][4k]
- *
- * The new_size would just be 4k and we'd think we had enough
- * outstanding extents for this if we only took one side of the
- * split, same goes for the other direction. We need to see if
- * the larger size still is the same amount of extents as the
- * original size, because if it is we need to add a new
- * outstanding extent. But if we split up and the larger size
- * is less than the original then we are good to go since we've
- * already accounted for the extra extent in our original
- * accounting.
+ * See the explanation in btrfs_merge_extent_hook, the same
+ * applies here, just in reverse.
*/
new_size = orig->end - split + 1;
- if ((split - orig->start) > new_size)
- new_size = split - orig->start;
-
- num_extents = div64_u64(size + BTRFS_MAX_EXTENT_SIZE - 1,
+ num_extents = div64_u64(new_size + BTRFS_MAX_EXTENT_SIZE - 1,
BTRFS_MAX_EXTENT_SIZE);
- if (div64_u64(new_size + BTRFS_MAX_EXTENT_SIZE - 1,
- BTRFS_MAX_EXTENT_SIZE) < num_extents)
+ new_size = split - orig->start;
+ num_extents += div64_u64(new_size + BTRFS_MAX_EXTENT_SIZE - 1,
+ BTRFS_MAX_EXTENT_SIZE);
+ if (div64_u64(size + BTRFS_MAX_EXTENT_SIZE - 1,
+ BTRFS_MAX_EXTENT_SIZE) >= num_extents)
return;
}
@@ -1591,8 +1585,10 @@ static void btrfs_merge_extent_hook(struct inode *inode,
if (!(other->state & EXTENT_DELALLOC))
return;
- old_size = other->end - other->start + 1;
- new_size = old_size + (new->end - new->start + 1);
+ if (new->start > other->start)
+ new_size = new->end - other->start + 1;
+ else
+ new_size = other->end - new->start + 1;
/* we're not bigger than the max, unreserve the space and go */
if (new_size <= BTRFS_MAX_EXTENT_SIZE) {
@@ -1603,13 +1599,32 @@ static void btrfs_merge_extent_hook(struct inode *inode,
}
/*
- * If we grew by another max_extent, just return, we want to keep that
- * reserved amount.
+ * We have to add up either side to figure out how many extents were
+ * accounted for before we merged into one big extent. If the number of
+ * extents we accounted for is <= the amount we need for the new range
+ * then we can return, otherwise drop. Think of it like this
+ *
+ * [ 4k][MAX_SIZE]
+ *
+ * So we've grown the extent by a MAX_SIZE extent, this would mean we
+ * need 2 outstanding extents, on one side we have 1 and the other side
+ * we have 1 so they are == and we can return. But in this case
+ *
+ * [MAX_SIZE+4k][MAX_SIZE+4k]
+ *
+ * Each range on their own accounts for 2 extents, but merged together
+ * they are only 3 extents worth of accounting, so we need to drop in
+ * this case.
*/
+ old_size = other->end - other->start + 1;
num_extents = div64_u64(old_size + BTRFS_MAX_EXTENT_SIZE - 1,
BTRFS_MAX_EXTENT_SIZE);
+ old_size = new->end - new->start + 1;
+ num_extents += div64_u64(old_size + BTRFS_MAX_EXTENT_SIZE - 1,
+ BTRFS_MAX_EXTENT_SIZE);
+
if (div64_u64(new_size + BTRFS_MAX_EXTENT_SIZE - 1,
- BTRFS_MAX_EXTENT_SIZE) > num_extents)
+ BTRFS_MAX_EXTENT_SIZE) >= num_extents)
return;
spin_lock(&BTRFS_I(inode)->lock);
@@ -1686,6 +1701,10 @@ static void btrfs_set_bit_hook(struct inode *inode,
spin_unlock(&BTRFS_I(inode)->lock);
}
+ /* For sanity tests */
+ if (btrfs_test_is_dummy_root(root))
+ return;
+
__percpu_counter_add(&root->fs_info->delalloc_bytes, len,
root->fs_info->delalloc_batch);
spin_lock(&BTRFS_I(inode)->lock);
@@ -1741,6 +1760,10 @@ static void btrfs_clear_bit_hook(struct inode *inode,
root != root->fs_info->tree_root)
btrfs_delalloc_release_metadata(inode, len);
+ /* For sanity tests. */
+ if (btrfs_test_is_dummy_root(root))
+ return;
+
if (root->root_key.objectid != BTRFS_DATA_RELOC_TREE_OBJECTID
&& do_list && !(state->state & EXTENT_NORESERVE))
btrfs_free_reserved_data_space(inode, len);
@@ -7213,7 +7236,7 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock,
u64 start = iblock << inode->i_blkbits;
u64 lockstart, lockend;
u64 len = bh_result->b_size;
- u64 orig_len = len;
+ u64 *outstanding_extents = NULL;
int unlock_bits = EXTENT_LOCKED;
int ret = 0;
@@ -7225,6 +7248,16 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock,
lockstart = start;
lockend = start + len - 1;
+ if (current->journal_info) {
+ /*
+ * Need to pull our outstanding extents and set journal_info to NULL so
+ * that anything that needs to check if there's a transction doesn't get
+ * confused.
+ */
+ outstanding_extents = current->journal_info;
+ current->journal_info = NULL;
+ }
+
/*
* If this errors out it's because we couldn't invalidate pagecache for
* this range and we need to fallback to buffered.
@@ -7285,7 +7318,6 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock,
((BTRFS_I(inode)->flags & BTRFS_INODE_NODATACOW) &&
em->block_start != EXTENT_MAP_HOLE)) {
int type;
- int ret;
u64 block_start, orig_start, orig_block_len, ram_bytes;
if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
@@ -7349,11 +7381,20 @@ unlock:
if (start + len > i_size_read(inode))
i_size_write(inode, start + len);
- if (len < orig_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 (*outstanding_extents) {
+ (*outstanding_extents)--;
+ } else {
spin_lock(&BTRFS_I(inode)->lock);
BTRFS_I(inode)->outstanding_extents++;
spin_unlock(&BTRFS_I(inode)->lock);
}
+
+ current->journal_info = outstanding_extents;
btrfs_free_reserved_data_space(inode, len);
}
@@ -7377,6 +7418,8 @@ unlock:
unlock_err:
clear_extent_bit(&BTRFS_I(inode)->io_tree, lockstart, lockend,
unlock_bits, 1, 0, &cached_state, GFP_NOFS);
+ if (outstanding_extents)
+ current->journal_info = outstanding_extents;
return ret;
}
@@ -8076,6 +8119,7 @@ static ssize_t btrfs_direct_IO(int rw, struct kiocb *iocb,
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
+ u64 outstanding_extents = 0;
size_t count = 0;
int flags = 0;
bool wakeup = true;
@@ -8113,6 +8157,16 @@ static ssize_t btrfs_direct_IO(int rw, struct kiocb *iocb,
ret = btrfs_delalloc_reserve_space(inode, count);
if (ret)
goto out;
+ outstanding_extents = div64_u64(count +
+ BTRFS_MAX_EXTENT_SIZE - 1,
+ BTRFS_MAX_EXTENT_SIZE);
+
+ /*
+ * We need to know how many extents we reserved so that we can
+ * do the accounting properly if we go over the number we
+ * originally calculated. Abuse current->journal_info for this.
+ */
+ current->journal_info = &outstanding_extents;
} else if (test_bit(BTRFS_INODE_READDIO_NEED_LOCK,
&BTRFS_I(inode)->runtime_flags)) {
inode_dio_done(inode);
@@ -8125,6 +8179,7 @@ static ssize_t btrfs_direct_IO(int rw, struct kiocb *iocb,
iter, offset, btrfs_get_blocks_direct, NULL,
btrfs_submit_direct, flags);
if (rw & WRITE) {
+ current->journal_info = NULL;
if (ret < 0 && ret != -EIOCBQUEUED)
btrfs_delalloc_release_space(inode, count);
else if (ret >= 0 && (size_t)ret < count)
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index 534544e..157cc54 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -452,9 +452,7 @@ void btrfs_get_logged_extents(struct inode *inode,
continue;
if (entry_end(ordered) <= start)
break;
- if (!list_empty(&ordered->log_list))
- continue;
- if (test_bit(BTRFS_ORDERED_LOGGED, &ordered->flags))
+ if (test_and_set_bit(BTRFS_ORDERED_LOGGED, &ordered->flags))
continue;
list_add(&ordered->log_list, logged_list);
atomic_inc(&ordered->refs);
@@ -511,8 +509,7 @@ void btrfs_wait_logged_extents(struct btrfs_trans_handle *trans,
wait_event(ordered->wait, test_bit(BTRFS_ORDERED_IO_DONE,
&ordered->flags));
- if (!test_and_set_bit(BTRFS_ORDERED_LOGGED, &ordered->flags))
- list_add_tail(&ordered->trans_list, &trans->ordered);
+ list_add_tail(&ordered->trans_list, &trans->ordered);
spin_lock_irq(&log->log_extents_lock[index]);
}
spin_unlock_irq(&log->log_extents_lock[index]);
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 97159a8..058c79e 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -1259,7 +1259,7 @@ static int comp_oper(struct btrfs_qgroup_operation *oper1,
if (oper1->seq < oper2->seq)
return -1;
if (oper1->seq > oper2->seq)
- return -1;
+ return 1;
if (oper1->ref_root < oper2->ref_root)
return -1;
if (oper1->ref_root > oper2->ref_root)
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index fe58572..d6033f5 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -230,6 +230,7 @@ struct pending_dir_move {
u64 parent_ino;
u64 ino;
u64 gen;
+ bool is_orphan;
struct list_head update_refs;
};
@@ -2984,7 +2985,8 @@ static int add_pending_dir_move(struct send_ctx *sctx,
u64 ino_gen,
u64 parent_ino,
struct list_head *new_refs,
- struct list_head *deleted_refs)
+ struct list_head *deleted_refs,
+ const bool is_orphan)
{
struct rb_node **p = &sctx->pending_dir_moves.rb_node;
struct rb_node *parent = NULL;
@@ -2999,6 +3001,7 @@ static int add_pending_dir_move(struct send_ctx *sctx,
pm->parent_ino = parent_ino;
pm->ino = ino;
pm->gen = ino_gen;
+ pm->is_orphan = is_orphan;
INIT_LIST_HEAD(&pm->list);
INIT_LIST_HEAD(&pm->update_refs);
RB_CLEAR_NODE(&pm->node);
@@ -3131,16 +3134,20 @@ static int apply_dir_move(struct send_ctx *sctx, struct pending_dir_move *pm)
rmdir_ino = dm->rmdir_ino;
free_waiting_dir_move(sctx, dm);
- ret = get_first_ref(sctx->parent_root, pm->ino,
- &parent_ino, &parent_gen, name);
- if (ret < 0)
- goto out;
-
- ret = get_cur_path(sctx, parent_ino, parent_gen,
- from_path);
- if (ret < 0)
- goto out;
- ret = fs_path_add_path(from_path, name);
+ if (pm->is_orphan) {
+ ret = gen_unique_name(sctx, pm->ino,
+ pm->gen, from_path);
+ } else {
+ ret = get_first_ref(sctx->parent_root, pm->ino,
+ &parent_ino, &parent_gen, name);
+ if (ret < 0)
+ goto out;
+ ret = get_cur_path(sctx, parent_ino, parent_gen,
+ from_path);
+ if (ret < 0)
+ goto out;
+ ret = fs_path_add_path(from_path, name);
+ }
if (ret < 0)
goto out;
@@ -3150,7 +3157,8 @@ static int apply_dir_move(struct send_ctx *sctx, struct pending_dir_move *pm)
LIST_HEAD(deleted_refs);
ASSERT(ancestor > BTRFS_FIRST_FREE_OBJECTID);
ret = add_pending_dir_move(sctx, pm->ino, pm->gen, ancestor,
- &pm->update_refs, &deleted_refs);
+ &pm->update_refs, &deleted_refs,
+ pm->is_orphan);
if (ret < 0)
goto out;
if (rmdir_ino) {
@@ -3283,6 +3291,127 @@ out:
return ret;
}
+/*
+ * We might need to delay a directory rename even when no ancestor directory
+ * (in the send root) with a higher inode number than ours (sctx->cur_ino) was
+ * renamed. This happens when we rename a directory to the old name (the name
+ * in the parent root) of some other unrelated directory that got its rename
+ * delayed due to some ancestor with higher number that got renamed.
+ *
+ * Example:
+ *
+ * Parent snapshot:
+ * . (ino 256)
+ * |---- a/ (ino 257)
+ * | |---- file (ino 260)
+ * |
+ * |---- b/ (ino 258)
+ * |---- c/ (ino 259)
+ *
+ * Send snapshot:
+ * . (ino 256)
+ * |---- a/ (ino 258)
+ * |---- x/ (ino 259)
+ * |---- y/ (ino 257)
+ * |----- file (ino 260)
+ *
+ * Here we can not rename 258 from 'b' to 'a' without the rename of inode 257
+ * from 'a' to 'x/y' happening first, which in turn depends on the rename of
+ * inode 259 from 'c' to 'x'. So the order of rename commands the send stream
+ * must issue is:
+ *
+ * 1 - rename 259 from 'c' to 'x'
+ * 2 - rename 257 from 'a' to 'x/y'
+ * 3 - rename 258 from 'b' to 'a'
+ *
+ * Returns 1 if the rename of sctx->cur_ino needs to be delayed, 0 if it can
+ * be done right away and < 0 on error.
+ */
+static int wait_for_dest_dir_move(struct send_ctx *sctx,
+ struct recorded_ref *parent_ref,
+ const bool is_orphan)
+{
+ struct btrfs_path *path;
+ struct btrfs_key key;
+ struct btrfs_key di_key;
+ struct btrfs_dir_item *di;
+ u64 left_gen;
+ u64 right_gen;
+ int ret = 0;
+
+ if (RB_EMPTY_ROOT(&sctx->waiting_dir_moves))
+ return 0;
+
+ path = alloc_path_for_send();
+ if (!path)
+ return -ENOMEM;
+
+ key.objectid = parent_ref->dir;
+ key.type = BTRFS_DIR_ITEM_KEY;
+ key.offset = btrfs_name_hash(parent_ref->name, parent_ref->name_len);
+
+ ret = btrfs_search_slot(NULL, sctx->parent_root, &key, path, 0, 0);
+ if (ret < 0) {
+ goto out;
+ } else if (ret > 0) {
+ ret = 0;
+ goto out;
+ }
+
+ di = btrfs_match_dir_item_name(sctx->parent_root, path,
+ parent_ref->name, parent_ref->name_len);
+ if (!di) {
+ ret = 0;
+ goto out;
+ }
+ /*
+ * di_key.objectid has the number of the inode that has a dentry in the
+ * parent directory with the same name that sctx->cur_ino is being
+ * renamed to. We need to check if that inode is in the send root as
+ * well and if it is currently marked as an inode with a pending rename,
+ * if it is, we need to delay the rename of sctx->cur_ino as well, so
+ * that it happens after that other inode is renamed.
+ */
+ btrfs_dir_item_key_to_cpu(path->nodes[0], di, &di_key);
+ if (di_key.type != BTRFS_INODE_ITEM_KEY) {
+ ret = 0;
+ goto out;
+ }
+
+ ret = get_inode_info(sctx->parent_root, di_key.objectid, NULL,
+ &left_gen, NULL, NULL, NULL, NULL);
+ if (ret < 0)
+ goto out;
+ ret = get_inode_info(sctx->send_root, di_key.objectid, NULL,
+ &right_gen, NULL, NULL, NULL, NULL);
+ if (ret < 0) {
+ if (ret == -ENOENT)
+ ret = 0;
+ goto out;
+ }
+
+ /* Different inode, no need to delay the rename of sctx->cur_ino */
+ if (right_gen != left_gen) {
+ ret = 0;
+ goto out;
+ }
+
+ if (is_waiting_for_move(sctx, di_key.objectid)) {
+ ret = add_pending_dir_move(sctx,
+ sctx->cur_ino,
+ sctx->cur_inode_gen,
+ di_key.objectid,
+ &sctx->new_refs,
+ &sctx->deleted_refs,
+ is_orphan);
+ if (!ret)
+ ret = 1;
+ }
+out:
+ btrfs_free_path(path);
+ return ret;
+}
+
static int wait_for_parent_move(struct send_ctx *sctx,
struct recorded_ref *parent_ref)
{
@@ -3349,7 +3478,8 @@ out:
sctx->cur_inode_gen,
ino,
&sctx->new_refs,
- &sctx->deleted_refs);
+ &sctx->deleted_refs,
+ false);
if (!ret)
ret = 1;
}
@@ -3372,6 +3502,7 @@ static int process_recorded_refs(struct send_ctx *sctx, int *pending_move)
int did_overwrite = 0;
int is_orphan = 0;
u64 last_dir_ino_rm = 0;
+ bool can_rename = true;
verbose_printk("btrfs: process_recorded_refs %llu\n", sctx->cur_ino);
@@ -3490,12 +3621,22 @@ verbose_printk("btrfs: process_recorded_refs %llu\n", sctx->cur_ino);
}
}
+ if (S_ISDIR(sctx->cur_inode_mode) && sctx->parent_root) {
+ ret = wait_for_dest_dir_move(sctx, cur, is_orphan);
+ if (ret < 0)
+ goto out;
+ if (ret == 1) {
+ can_rename = false;
+ *pending_move = 1;
+ }
+ }
+
/*
* link/move the ref to the new place. If we have an orphan
* inode, move it and update valid_path. If not, link or move
* it depending on the inode mode.
*/
- if (is_orphan) {
+ if (is_orphan && can_rename) {
ret = send_rename(sctx, valid_path, cur->full_path);
if (ret < 0)
goto out;
@@ -3503,7 +3644,7 @@ verbose_printk("btrfs: process_recorded_refs %llu\n", sctx->cur_ino);
ret = fs_path_copy(valid_path, cur->full_path);
if (ret < 0)
goto out;
- } else {
+ } else if (can_rename) {
if (S_ISDIR(sctx->cur_inode_mode)) {
/*
* Dirs can't be linked, so move it. For moved
diff --git a/fs/btrfs/tests/inode-tests.c b/fs/btrfs/tests/inode-tests.c
index a116b55..054fc0d 100644
--- a/fs/btrfs/tests/inode-tests.c
+++ b/fs/btrfs/tests/inode-tests.c
@@ -911,6 +911,197 @@ out:
return ret;
}
+static int test_extent_accounting(void)
+{
+ struct inode *inode = NULL;
+ struct btrfs_root *root = NULL;
+ int ret = -ENOMEM;
+
+ inode = btrfs_new_test_inode();
+ if (!inode) {
+ test_msg("Couldn't allocate inode\n");
+ return ret;
+ }
+
+ root = btrfs_alloc_dummy_root();
+ if (IS_ERR(root)) {
+ test_msg("Couldn't allocate root\n");
+ goto out;
+ }
+
+ root->fs_info = btrfs_alloc_dummy_fs_info();
+ if (!root->fs_info) {
+ test_msg("Couldn't allocate dummy fs info\n");
+ goto out;
+ }
+
+ BTRFS_I(inode)->root = root;
+ btrfs_test_inode_set_ops(inode);
+
+ /* [BTRFS_MAX_EXTENT_SIZE] */
+ BTRFS_I(inode)->outstanding_extents++;
+ ret = btrfs_set_extent_delalloc(inode, 0, BTRFS_MAX_EXTENT_SIZE - 1,
+ NULL);
+ if (ret) {
+ test_msg("btrfs_set_extent_delalloc returned %d\n", ret);
+ goto out;
+ }
+ if (BTRFS_I(inode)->outstanding_extents != 1) {
+ ret = -EINVAL;
+ test_msg("Miscount, wanted 1, got %u\n",
+ BTRFS_I(inode)->outstanding_extents);
+ goto out;
+ }
+
+ /* [BTRFS_MAX_EXTENT_SIZE][4k] */
+ BTRFS_I(inode)->outstanding_extents++;
+ ret = btrfs_set_extent_delalloc(inode, BTRFS_MAX_EXTENT_SIZE,
+ BTRFS_MAX_EXTENT_SIZE + 4095, NULL);
+ if (ret) {
+ test_msg("btrfs_set_extent_delalloc returned %d\n", ret);
+ goto out;
+ }
+ if (BTRFS_I(inode)->outstanding_extents != 2) {
+ ret = -EINVAL;
+ test_msg("Miscount, wanted 2, got %u\n",
+ BTRFS_I(inode)->outstanding_extents);
+ goto out;
+ }
+
+ /* [BTRFS_MAX_EXTENT_SIZE/2][4K HOLE][the rest] */
+ ret = clear_extent_bit(&BTRFS_I(inode)->io_tree,
+ BTRFS_MAX_EXTENT_SIZE >> 1,
+ (BTRFS_MAX_EXTENT_SIZE >> 1) + 4095,
+ EXTENT_DELALLOC | EXTENT_DIRTY |
+ EXTENT_UPTODATE | EXTENT_DO_ACCOUNTING, 0, 0,
+ NULL, GFP_NOFS);
+ if (ret) {
+ test_msg("clear_extent_bit returned %d\n", ret);
+ goto out;
+ }
+ if (BTRFS_I(inode)->outstanding_extents != 2) {
+ ret = -EINVAL;
+ test_msg("Miscount, wanted 2, got %u\n",
+ BTRFS_I(inode)->outstanding_extents);
+ goto out;
+ }
+
+ /* [BTRFS_MAX_EXTENT_SIZE][4K] */
+ BTRFS_I(inode)->outstanding_extents++;
+ ret = btrfs_set_extent_delalloc(inode, BTRFS_MAX_EXTENT_SIZE >> 1,
+ (BTRFS_MAX_EXTENT_SIZE >> 1) + 4095,
+ NULL);
+ if (ret) {
+ test_msg("btrfs_set_extent_delalloc returned %d\n", ret);
+ goto out;
+ }
+ if (BTRFS_I(inode)->outstanding_extents != 2) {
+ ret = -EINVAL;
+ test_msg("Miscount, wanted 2, got %u\n",
+ BTRFS_I(inode)->outstanding_extents);
+ goto out;
+ }
+
+ /*
+ * [BTRFS_MAX_EXTENT_SIZE+4K][4K HOLE][BTRFS_MAX_EXTENT_SIZE+4K]
+ *
+ * I'm artificially adding 2 to outstanding_extents because in the
+ * buffered IO case we'd add things up as we go, but I don't feel like
+ * doing that here, this isn't the interesting case we want to test.
+ */
+ BTRFS_I(inode)->outstanding_extents += 2;
+ ret = btrfs_set_extent_delalloc(inode, BTRFS_MAX_EXTENT_SIZE + 8192,
+ (BTRFS_MAX_EXTENT_SIZE << 1) + 12287,
+ NULL);
+ if (ret) {
+ test_msg("btrfs_set_extent_delalloc returned %d\n", ret);
+ goto out;
+ }
+ if (BTRFS_I(inode)->outstanding_extents != 4) {
+ ret = -EINVAL;
+ test_msg("Miscount, wanted 4, got %u\n",
+ BTRFS_I(inode)->outstanding_extents);
+ goto out;
+ }
+
+ /* [BTRFS_MAX_EXTENT_SIZE+4k][4k][BTRFS_MAX_EXTENT_SIZE+4k] */
+ BTRFS_I(inode)->outstanding_extents++;
+ ret = btrfs_set_extent_delalloc(inode, BTRFS_MAX_EXTENT_SIZE+4096,
+ BTRFS_MAX_EXTENT_SIZE+8191, NULL);
+ if (ret) {
+ test_msg("btrfs_set_extent_delalloc returned %d\n", ret);
+ goto out;
+ }
+ if (BTRFS_I(inode)->outstanding_extents != 3) {
+ ret = -EINVAL;
+ test_msg("Miscount, wanted 3, got %u\n",
+ BTRFS_I(inode)->outstanding_extents);
+ goto out;
+ }
+
+ /* [BTRFS_MAX_EXTENT_SIZE+4k][4K HOLE][BTRFS_MAX_EXTENT_SIZE+4k] */
+ ret = clear_extent_bit(&BTRFS_I(inode)->io_tree,
+ BTRFS_MAX_EXTENT_SIZE+4096,
+ BTRFS_MAX_EXTENT_SIZE+8191,
+ EXTENT_DIRTY | EXTENT_DELALLOC |
+ EXTENT_DO_ACCOUNTING | EXTENT_UPTODATE, 0, 0,
+ NULL, GFP_NOFS);
+ if (ret) {
+ test_msg("clear_extent_bit returned %d\n", ret);
+ goto out;
+ }
+ if (BTRFS_I(inode)->outstanding_extents != 4) {
+ ret = -EINVAL;
+ test_msg("Miscount, wanted 4, got %u\n",
+ BTRFS_I(inode)->outstanding_extents);
+ goto out;
+ }
+
+ /*
+ * Refill the hole again just for good measure, because I thought it
+ * might fail and I'd rather satisfy my paranoia at this point.
+ */
+ BTRFS_I(inode)->outstanding_extents++;
+ ret = btrfs_set_extent_delalloc(inode, BTRFS_MAX_EXTENT_SIZE+4096,
+ BTRFS_MAX_EXTENT_SIZE+8191, NULL);
+ if (ret) {
+ test_msg("btrfs_set_extent_delalloc returned %d\n", ret);
+ goto out;
+ }
+ if (BTRFS_I(inode)->outstanding_extents != 3) {
+ ret = -EINVAL;
+ test_msg("Miscount, wanted 3, got %u\n",
+ BTRFS_I(inode)->outstanding_extents);
+ goto out;
+ }
+
+ /* Empty */
+ ret = clear_extent_bit(&BTRFS_I(inode)->io_tree, 0, (u64)-1,
+ EXTENT_DIRTY | EXTENT_DELALLOC |
+ EXTENT_DO_ACCOUNTING | EXTENT_UPTODATE, 0, 0,
+ NULL, GFP_NOFS);
+ if (ret) {
+ test_msg("clear_extent_bit returned %d\n", ret);
+ goto out;
+ }
+ if (BTRFS_I(inode)->outstanding_extents) {
+ ret = -EINVAL;
+ test_msg("Miscount, wanted 0, got %u\n",
+ BTRFS_I(inode)->outstanding_extents);
+ goto out;
+ }
+ ret = 0;
+out:
+ if (ret)
+ clear_extent_bit(&BTRFS_I(inode)->io_tree, 0, (u64)-1,
+ EXTENT_DIRTY | EXTENT_DELALLOC |
+ EXTENT_DO_ACCOUNTING | EXTENT_UPTODATE, 0, 0,
+ NULL, GFP_NOFS);
+ iput(inode);
+ btrfs_free_dummy_root(root);
+ return ret;
+}
+
int btrfs_test_inodes(void)
{
int ret;
@@ -924,5 +1115,9 @@ int btrfs_test_inodes(void)
if (ret)
return ret;
test_msg("Running hole first btrfs_get_extent test\n");
- return test_hole_first();
+ ret = test_hole_first();
+ if (ret)
+ return ret;
+ test_msg("Running outstanding_extents tests\n");
+ return test_extent_accounting();
}
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 7e80f32..8be4278 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -1023,17 +1023,13 @@ static int update_cowonly_root(struct btrfs_trans_handle *trans,
u64 old_root_bytenr;
u64 old_root_used;
struct btrfs_root *tree_root = root->fs_info->tree_root;
- bool extent_root = (root->objectid == BTRFS_EXTENT_TREE_OBJECTID);
old_root_used = btrfs_root_used(&root->root_item);
- btrfs_write_dirty_block_groups(trans, root);
while (1) {
old_root_bytenr = btrfs_root_bytenr(&root->root_item);
if (old_root_bytenr == root->node->start &&
- old_root_used == btrfs_root_used(&root->root_item) &&
- (!extent_root ||
- list_empty(&trans->transaction->dirty_bgs)))
+ old_root_used == btrfs_root_used(&root->root_item))
break;
btrfs_set_root_node(&root->root_item, root->node);
@@ -1044,17 +1040,6 @@ static int update_cowonly_root(struct btrfs_trans_handle *trans,
return ret;
old_root_used = btrfs_root_used(&root->root_item);
- if (extent_root) {
- ret = btrfs_write_dirty_block_groups(trans, root);
- if (ret)
- return ret;
- }
- ret = btrfs_run_delayed_refs(trans, root, (unsigned long)-1);
- if (ret)
- return ret;
- ret = btrfs_run_delayed_refs(trans, root, (unsigned long)-1);
- if (ret)
- return ret;
}
return 0;
@@ -1071,6 +1056,7 @@ static noinline int commit_cowonly_roots(struct btrfs_trans_handle *trans,
struct btrfs_root *root)
{
struct btrfs_fs_info *fs_info = root->fs_info;
+ struct list_head *dirty_bgs = &trans->transaction->dirty_bgs;
struct list_head *next;
struct extent_buffer *eb;
int ret;
@@ -1098,11 +1084,15 @@ static noinline int commit_cowonly_roots(struct btrfs_trans_handle *trans,
if (ret)
return ret;
+ ret = btrfs_setup_space_cache(trans, root);
+ if (ret)
+ return ret;
+
/* run_qgroups might have added some more refs */
ret = btrfs_run_delayed_refs(trans, root, (unsigned long)-1);
if (ret)
return ret;
-
+again:
while (!list_empty(&fs_info->dirty_cowonly_roots)) {
next = fs_info->dirty_cowonly_roots.next;
list_del_init(next);
@@ -1115,8 +1105,23 @@ static noinline int commit_cowonly_roots(struct btrfs_trans_handle *trans,
ret = update_cowonly_root(trans, root);
if (ret)
return ret;
+ ret = btrfs_run_delayed_refs(trans, root, (unsigned long)-1);
+ if (ret)
+ return ret;
}
+ while (!list_empty(dirty_bgs)) {
+ ret = btrfs_write_dirty_block_groups(trans, root);
+ if (ret)
+ return ret;
+ ret = btrfs_run_delayed_refs(trans, root, (unsigned long)-1);
+ if (ret)
+ return ret;
+ }
+
+ if (!list_empty(&fs_info->dirty_cowonly_roots))
+ goto again;
+
list_add_tail(&fs_info->extent_root->dirty_list,
&trans->transaction->switch_commits);
btrfs_after_dev_replace_commit(fs_info);
@@ -1814,6 +1819,9 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
wait_for_commit(root, cur_trans);
+ if (unlikely(cur_trans->aborted))
+ ret = cur_trans->aborted;
+
btrfs_put_transaction(cur_trans);
return ret;
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 9a37f8b..c5b8ba3 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -1012,7 +1012,7 @@ again:
base = btrfs_item_ptr_offset(leaf, path->slots[0]);
while (cur_offset < item_size) {
- extref = (struct btrfs_inode_extref *)base + cur_offset;
+ extref = (struct btrfs_inode_extref *)(base + cur_offset);
victim_name_len = btrfs_inode_extref_name_len(leaf, extref);
diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c
index 47b1946..883b936 100644
--- a/fs/btrfs/xattr.c
+++ b/fs/btrfs/xattr.c
@@ -111,6 +111,8 @@ static int do_setxattr(struct btrfs_trans_handle *trans,
name, name_len, -1);
if (!di && (flags & XATTR_REPLACE))
ret = -ENODATA;
+ else if (IS_ERR(di))
+ ret = PTR_ERR(di);
else if (di)
ret = btrfs_delete_one_dir_name(trans, root, path, di);
goto out;
@@ -127,10 +129,12 @@ static int do_setxattr(struct btrfs_trans_handle *trans,
ASSERT(mutex_is_locked(&inode->i_mutex));
di = btrfs_lookup_xattr(NULL, root, path, btrfs_ino(inode),
name, name_len, 0);
- if (!di) {
+ if (!di)
ret = -ENODATA;
+ else if (IS_ERR(di))
+ ret = PTR_ERR(di);
+ if (ret)
goto out;
- }
btrfs_release_path(path);
di = NULL;
}
OpenPOWER on IntegriCloud