aboutsummaryrefslogtreecommitdiff
path: root/fs/btrfs
diff options
context:
space:
mode:
Diffstat (limited to 'fs/btrfs')
-rw-r--r--fs/btrfs/acl.c2
-rw-r--r--fs/btrfs/backref.c32
-rw-r--r--fs/btrfs/backref.h4
-rw-r--r--fs/btrfs/compression.c2
-rw-r--r--fs/btrfs/ctree.c13
-rw-r--r--fs/btrfs/delayed-inode.c8
-rw-r--r--fs/btrfs/disk-io.c15
-rw-r--r--fs/btrfs/extent-tree.c33
-rw-r--r--fs/btrfs/extent_io.c5
-rw-r--r--fs/btrfs/extent_map.c2
-rw-r--r--fs/btrfs/file-item.c4
-rw-r--r--fs/btrfs/file.c56
-rw-r--r--fs/btrfs/free-space-cache.c4
-rw-r--r--fs/btrfs/inode.c63
-rw-r--r--fs/btrfs/ioctl.c17
-rw-r--r--fs/btrfs/relocation.c19
-rw-r--r--fs/btrfs/scrub.c7
-rw-r--r--fs/btrfs/send.c46
-rw-r--r--fs/btrfs/transaction.c12
-rw-r--r--fs/btrfs/tree-log.c9
-rw-r--r--fs/btrfs/ulist.c15
-rw-r--r--fs/btrfs/volumes.c34
22 files changed, 279 insertions, 123 deletions
diff --git a/fs/btrfs/acl.c b/fs/btrfs/acl.c
index e15d2b0d8d3b..0890c83643e9 100644
--- a/fs/btrfs/acl.c
+++ b/fs/btrfs/acl.c
@@ -229,7 +229,7 @@ int btrfs_init_acl(struct btrfs_trans_handle *trans,
if (ret > 0) {
/* we need an acl */
ret = btrfs_set_acl(trans, inode, acl, ACL_TYPE_ACCESS);
- } else {
+ } else if (ret < 0) {
cache_no_acl(inode);
}
} else {
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index 290e347b6db3..d85f90c92bb4 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -1347,9 +1347,10 @@ int extent_from_logical(struct btrfs_fs_info *fs_info, u64 logical,
* returns <0 on error
*/
static int __get_extent_inline_ref(unsigned long *ptr, struct extent_buffer *eb,
- struct btrfs_extent_item *ei, u32 item_size,
- struct btrfs_extent_inline_ref **out_eiref,
- int *out_type)
+ struct btrfs_key *key,
+ struct btrfs_extent_item *ei, u32 item_size,
+ struct btrfs_extent_inline_ref **out_eiref,
+ int *out_type)
{
unsigned long end;
u64 flags;
@@ -1359,19 +1360,26 @@ static int __get_extent_inline_ref(unsigned long *ptr, struct extent_buffer *eb,
/* first call */
flags = btrfs_extent_flags(eb, ei);
if (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) {
- info = (struct btrfs_tree_block_info *)(ei + 1);
- *out_eiref =
- (struct btrfs_extent_inline_ref *)(info + 1);
+ if (key->type == BTRFS_METADATA_ITEM_KEY) {
+ /* a skinny metadata extent */
+ *out_eiref =
+ (struct btrfs_extent_inline_ref *)(ei + 1);
+ } else {
+ WARN_ON(key->type != BTRFS_EXTENT_ITEM_KEY);
+ info = (struct btrfs_tree_block_info *)(ei + 1);
+ *out_eiref =
+ (struct btrfs_extent_inline_ref *)(info + 1);
+ }
} else {
*out_eiref = (struct btrfs_extent_inline_ref *)(ei + 1);
}
*ptr = (unsigned long)*out_eiref;
- if ((void *)*ptr >= (void *)ei + item_size)
+ if ((unsigned long)(*ptr) >= (unsigned long)ei + item_size)
return -ENOENT;
}
end = (unsigned long)ei + item_size;
- *out_eiref = (struct btrfs_extent_inline_ref *)*ptr;
+ *out_eiref = (struct btrfs_extent_inline_ref *)(*ptr);
*out_type = btrfs_extent_inline_ref_type(eb, *out_eiref);
*ptr += btrfs_extent_inline_ref_size(*out_type);
@@ -1390,8 +1398,8 @@ static int __get_extent_inline_ref(unsigned long *ptr, struct extent_buffer *eb,
* <0 on error.
*/
int tree_backref_for_extent(unsigned long *ptr, struct extent_buffer *eb,
- struct btrfs_extent_item *ei, u32 item_size,
- u64 *out_root, u8 *out_level)
+ struct btrfs_key *key, struct btrfs_extent_item *ei,
+ u32 item_size, u64 *out_root, u8 *out_level)
{
int ret;
int type;
@@ -1402,8 +1410,8 @@ int tree_backref_for_extent(unsigned long *ptr, struct extent_buffer *eb,
return 1;
while (1) {
- ret = __get_extent_inline_ref(ptr, eb, ei, item_size,
- &eiref, &type);
+ ret = __get_extent_inline_ref(ptr, eb, key, ei, item_size,
+ &eiref, &type);
if (ret < 0)
return ret;
diff --git a/fs/btrfs/backref.h b/fs/btrfs/backref.h
index 0f446d7ca2c0..526d09e70c93 100644
--- a/fs/btrfs/backref.h
+++ b/fs/btrfs/backref.h
@@ -42,8 +42,8 @@ int extent_from_logical(struct btrfs_fs_info *fs_info, u64 logical,
u64 *flags);
int tree_backref_for_extent(unsigned long *ptr, struct extent_buffer *eb,
- struct btrfs_extent_item *ei, u32 item_size,
- u64 *out_root, u8 *out_level);
+ struct btrfs_key *key, struct btrfs_extent_item *ei,
+ u32 item_size, u64 *out_root, u8 *out_level);
int iterate_extent_inodes(struct btrfs_fs_info *fs_info,
u64 extent_item_objectid,
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index b189bd1e7a3e..ce7067881d36 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -1009,6 +1009,8 @@ int btrfs_decompress_buf2page(char *buf, unsigned long buf_start,
bytes = min(bytes, working_bytes);
kaddr = kmap_atomic(page_out);
memcpy(kaddr + *pg_offset, buf + buf_offset, bytes);
+ if (*pg_index == (vcnt - 1) && *pg_offset == 0)
+ memset(kaddr + bytes, 0, PAGE_CACHE_SIZE - bytes);
kunmap_atomic(kaddr);
flush_dcache_page(page_out);
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 02fae7f7e42c..7fb054ba1b60 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -1089,7 +1089,8 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans,
btrfs_set_node_ptr_generation(parent, parent_slot,
trans->transid);
btrfs_mark_buffer_dirty(parent);
- tree_mod_log_free_eb(root->fs_info, buf);
+ if (last_ref)
+ tree_mod_log_free_eb(root->fs_info, buf);
btrfs_free_tree_block(trans, root, buf, parent_start,
last_ref);
}
@@ -1161,8 +1162,8 @@ __tree_mod_log_oldest_root(struct btrfs_fs_info *fs_info,
* time_seq).
*/
static void
-__tree_mod_log_rewind(struct extent_buffer *eb, u64 time_seq,
- struct tree_mod_elem *first_tm)
+__tree_mod_log_rewind(struct btrfs_fs_info *fs_info, struct extent_buffer *eb,
+ u64 time_seq, struct tree_mod_elem *first_tm)
{
u32 n;
struct rb_node *next;
@@ -1172,6 +1173,7 @@ __tree_mod_log_rewind(struct extent_buffer *eb, u64 time_seq,
unsigned long p_size = sizeof(struct btrfs_key_ptr);
n = btrfs_header_nritems(eb);
+ tree_mod_log_read_lock(fs_info);
while (tm && tm->seq >= time_seq) {
/*
* all the operations are recorded with the operator used for
@@ -1226,6 +1228,7 @@ __tree_mod_log_rewind(struct extent_buffer *eb, u64 time_seq,
if (tm->index != first_tm->index)
break;
}
+ tree_mod_log_read_unlock(fs_info);
btrfs_set_header_nritems(eb, n);
}
@@ -1274,7 +1277,7 @@ tree_mod_log_rewind(struct btrfs_fs_info *fs_info, struct extent_buffer *eb,
extent_buffer_get(eb_rewin);
btrfs_tree_read_lock(eb_rewin);
- __tree_mod_log_rewind(eb_rewin, time_seq, tm);
+ __tree_mod_log_rewind(fs_info, eb_rewin, time_seq, tm);
WARN_ON(btrfs_header_nritems(eb_rewin) >
BTRFS_NODEPTRS_PER_BLOCK(fs_info->tree_root));
@@ -1350,7 +1353,7 @@ get_old_root(struct btrfs_root *root, u64 time_seq)
btrfs_set_header_generation(eb, old_generation);
}
if (tm)
- __tree_mod_log_rewind(eb, time_seq, tm);
+ __tree_mod_log_rewind(root->fs_info, eb, time_seq, tm);
else
WARN_ON(btrfs_header_level(eb) != 0);
WARN_ON(btrfs_header_nritems(eb) > BTRFS_NODEPTRS_PER_BLOCK(root));
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index f26f38ccd194..019fc5a68a14 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -1843,6 +1843,14 @@ int btrfs_delayed_update_inode(struct btrfs_trans_handle *trans,
struct btrfs_delayed_node *delayed_node;
int ret = 0;
+ /*
+ * we don't do delayed inode updates during log recovery because it
+ * leads to enospc problems. This means we also can't do
+ * delayed inode refs
+ */
+ if (BTRFS_I(inode)->root->fs_info->log_root_recovering)
+ return -EAGAIN;
+
delayed_node = btrfs_get_or_create_delayed_node(inode);
if (IS_ERR(delayed_node))
return PTR_ERR(delayed_node);
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index b8b60b660c8f..7360f03ddbe1 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -3161,6 +3161,8 @@ static int barrier_all_devices(struct btrfs_fs_info *info)
/* send down all the barriers */
head = &info->fs_devices->devices;
list_for_each_entry_rcu(dev, head, dev_list) {
+ if (dev->missing)
+ continue;
if (!dev->bdev) {
errors_send++;
continue;
@@ -3175,6 +3177,8 @@ static int barrier_all_devices(struct btrfs_fs_info *info)
/* wait for all the barriers */
list_for_each_entry_rcu(dev, head, dev_list) {
+ if (dev->missing)
+ continue;
if (!dev->bdev) {
errors_wait++;
continue;
@@ -3514,6 +3518,11 @@ int close_ctree(struct btrfs_root *root)
btrfs_free_block_groups(fs_info);
+ /*
+ * we must make sure there is not any read request to
+ * submit after we stopping all workers.
+ */
+ invalidate_inode_pages2(fs_info->btree_inode->i_mapping);
btrfs_stop_all_workers(fs_info);
del_fs_roots(fs_info);
@@ -3848,12 +3857,6 @@ again:
if (ret)
break;
- /* opt_discard */
- if (btrfs_test_opt(root, DISCARD))
- ret = btrfs_error_discard_extent(root, start,
- end + 1 - start,
- NULL);
-
clear_extent_dirty(unpin, start, end, GFP_NOFS);
btrfs_error_unpin_extent_range(root, start, end);
cond_resched();
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index df472ab1b5ac..07f167a1d271 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -2402,6 +2402,8 @@ static noinline int run_clustered_refs(struct btrfs_trans_handle *trans,
default:
WARN_ON(1);
}
+ } else {
+ list_del_init(&locked_ref->cluster);
}
spin_unlock(&delayed_refs->lock);
@@ -2424,7 +2426,6 @@ static noinline int run_clustered_refs(struct btrfs_trans_handle *trans,
* list before we release it.
*/
if (btrfs_delayed_ref_is_head(ref)) {
- list_del_init(&locked_ref->cluster);
btrfs_delayed_ref_unlock(locked_ref);
locked_ref = NULL;
}
@@ -5276,7 +5277,8 @@ void btrfs_prepare_extent_commit(struct btrfs_trans_handle *trans,
update_global_block_rsv(fs_info);
}
-static int unpin_extent_range(struct btrfs_root *root, u64 start, u64 end)
+static int unpin_extent_range(struct btrfs_root *root, u64 start, u64 end,
+ const bool return_free_space)
{
struct btrfs_fs_info *fs_info = root->fs_info;
struct btrfs_block_group_cache *cache = NULL;
@@ -5300,7 +5302,8 @@ static int unpin_extent_range(struct btrfs_root *root, u64 start, u64 end)
if (start < cache->last_byte_to_unpin) {
len = min(len, cache->last_byte_to_unpin - start);
- btrfs_add_free_space(cache, start, len);
+ if (return_free_space)
+ btrfs_add_free_space(cache, start, len);
}
start += len;
@@ -5363,7 +5366,7 @@ int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans,
end + 1 - start, NULL);
clear_extent_dirty(unpin, start, end, GFP_NOFS);
- unpin_extent_range(root, start, end);
+ unpin_extent_range(root, start, end, true);
cond_resched();
}
@@ -6360,12 +6363,11 @@ static int __btrfs_free_reserved_extent(struct btrfs_root *root,
return -ENOSPC;
}
- if (btrfs_test_opt(root, DISCARD))
- ret = btrfs_discard_extent(root, start, len, NULL);
-
if (pin)
pin_down_extent(root, cache, start, len, 1);
else {
+ if (btrfs_test_opt(root, DISCARD))
+ ret = btrfs_discard_extent(root, start, len, NULL);
btrfs_add_free_space(cache, start, len);
btrfs_update_reserved_bytes(cache, len, RESERVE_FREE);
}
@@ -7298,6 +7300,7 @@ int btrfs_drop_snapshot(struct btrfs_root *root,
int err = 0;
int ret;
int level;
+ bool root_dropped = false;
path = btrfs_alloc_path();
if (!path) {
@@ -7355,6 +7358,7 @@ int btrfs_drop_snapshot(struct btrfs_root *root,
while (1) {
btrfs_tree_lock(path->nodes[level]);
btrfs_set_lock_blocking(path->nodes[level]);
+ path->locks[level] = BTRFS_WRITE_LOCK_BLOCKING;
ret = btrfs_lookup_extent_info(trans, root,
path->nodes[level]->start,
@@ -7370,6 +7374,7 @@ int btrfs_drop_snapshot(struct btrfs_root *root,
break;
btrfs_tree_unlock(path->nodes[level]);
+ path->locks[level] = 0;
WARN_ON(wc->refs[level] != 1);
level--;
}
@@ -7471,13 +7476,23 @@ int btrfs_drop_snapshot(struct btrfs_root *root,
free_extent_buffer(root->commit_root);
kfree(root);
}
+ root_dropped = true;
out_end_trans:
btrfs_end_transaction_throttle(trans, tree_root);
out_free:
kfree(wc);
btrfs_free_path(path);
out:
- if (err)
+ /*
+ * So if we need to stop dropping the snapshot for whatever reason we
+ * need to make sure to add it back to the dead root list so that we
+ * keep trying to do the work later. This also cleans up roots if we
+ * don't have it in the radix (like when we recover after a power fail
+ * or unmount) so we don't leak memory.
+ */
+ if (root_dropped == false)
+ btrfs_add_dead_root(root);
+ if (err && err != -EAGAIN)
btrfs_std_error(root->fs_info, err);
return err;
}
@@ -8550,7 +8565,7 @@ out:
int btrfs_error_unpin_extent_range(struct btrfs_root *root, u64 start, u64 end)
{
- return unpin_extent_range(root, start, end);
+ return unpin_extent_range(root, start, end, false);
}
int btrfs_error_discard_extent(struct btrfs_root *root, u64 bytenr,
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index e7e7afb4a872..84ceff6abbc1 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -1624,6 +1624,7 @@ again:
* shortening the size of the delalloc range we're searching
*/
free_extent_state(cached_state);
+ cached_state = NULL;
if (!loops) {
unsigned long offset = (*start) & (PAGE_CACHE_SIZE - 1);
max_bytes = PAGE_CACHE_SIZE - offset;
@@ -2356,7 +2357,7 @@ int end_extent_writepage(struct page *page, int err, u64 start, u64 end)
{
int uptodate = (err == 0);
struct extent_io_tree *tree;
- int ret;
+ int ret = 0;
tree = &BTRFS_I(page->mapping->host)->io_tree;
@@ -2370,6 +2371,8 @@ int end_extent_writepage(struct page *page, int err, u64 start, u64 end)
if (!uptodate) {
ClearPageUptodate(page);
SetPageError(page);
+ ret = ret < 0 ? ret : -EIO;
+ mapping_set_error(page->mapping, ret);
}
return 0;
}
diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c
index a4a7a1a8da95..0a3809500599 100644
--- a/fs/btrfs/extent_map.c
+++ b/fs/btrfs/extent_map.c
@@ -263,8 +263,6 @@ int unpin_extent_cache(struct extent_map_tree *tree, u64 start, u64 len,
if (!em)
goto out;
- if (!test_bit(EXTENT_FLAG_LOGGING, &em->flags))
- list_move(&em->list, &tree->modified_extents);
em->generation = gen;
clear_bit(EXTENT_FLAG_PINNED, &em->flags);
em->mod_start = em->start;
diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index b193bf324a41..e4bcfec7787e 100644
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -403,7 +403,7 @@ int btrfs_lookup_csums_range(struct btrfs_root *root, u64 start, u64 end,
ret = 0;
fail:
while (ret < 0 && !list_empty(&tmplist)) {
- sums = list_entry(&tmplist, struct btrfs_ordered_sum, list);
+ sums = list_entry(tmplist.next, struct btrfs_ordered_sum, list);
list_del(&sums->list);
kfree(sums);
}
@@ -754,7 +754,7 @@ again:
found_next = 1;
if (ret != 0)
goto insert;
- slot = 0;
+ slot = path->slots[0];
}
btrfs_item_key_to_cpu(path->nodes[0], &found_key, slot);
if (found_key.objectid != BTRFS_EXTENT_CSUM_OBJECTID ||
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 4205ba752d40..caaf30f9f27f 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1593,22 +1593,10 @@ static ssize_t btrfs_file_aio_write(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 || num_written == -EIOCBQUEUED) {
err = generic_write_sync(file, pos, num_written);
@@ -1706,25 +1694,37 @@ 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
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index e53009657f0e..0cbe95dc8113 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -835,7 +835,7 @@ int load_free_space_cache(struct btrfs_fs_info *fs_info,
if (!matched) {
__btrfs_remove_free_space_cache(ctl);
- btrfs_err(fs_info, "block group %llu has wrong amount of free space",
+ btrfs_warn(fs_info, "block group %llu has wrong amount of free space",
block_group->key.objectid);
ret = -1;
}
@@ -847,7 +847,7 @@ out:
spin_unlock(&block_group->lock);
ret = 0;
- btrfs_err(fs_info, "failed to load free space cache for block group %llu",
+ btrfs_warn(fs_info, "failed to load free space cache for block group %llu, rebuild it now",
block_group->key.objectid);
}
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 17f3064b4a3e..d20db6437723 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -2419,10 +2419,23 @@ out_unlock:
return ret;
}
+static void free_sa_defrag_extent(struct new_sa_defrag_extent *new)
+{
+ struct old_sa_defrag_extent *old, *tmp;
+
+ if (!new)
+ return;
+
+ list_for_each_entry_safe(old, tmp, &new->head, list) {
+ list_del(&old->list);
+ kfree(old);
+ }
+ kfree(new);
+}
+
static void relink_file_extents(struct new_sa_defrag_extent *new)
{
struct btrfs_path *path;
- struct old_sa_defrag_extent *old, *tmp;
struct sa_defrag_extent_backref *backref;
struct sa_defrag_extent_backref *prev = NULL;
struct inode *inode;
@@ -2465,16 +2478,11 @@ static void relink_file_extents(struct new_sa_defrag_extent *new)
kfree(prev);
btrfs_free_path(path);
-
- list_for_each_entry_safe(old, tmp, &new->head, list) {
- list_del(&old->list);
- kfree(old);
- }
out:
+ free_sa_defrag_extent(new);
+
atomic_dec(&root->fs_info->defrag_running);
wake_up(&root->fs_info->transaction_wait);
-
- kfree(new);
}
static struct new_sa_defrag_extent *
@@ -2484,7 +2492,7 @@ record_old_file_extents(struct inode *inode,
struct btrfs_root *root = BTRFS_I(inode)->root;
struct btrfs_path *path;
struct btrfs_key key;
- struct old_sa_defrag_extent *old, *tmp;
+ struct old_sa_defrag_extent *old;
struct new_sa_defrag_extent *new;
int ret;
@@ -2532,7 +2540,7 @@ record_old_file_extents(struct inode *inode,
if (slot >= btrfs_header_nritems(l)) {
ret = btrfs_next_leaf(root, path);
if (ret < 0)
- goto out_free_list;
+ goto out_free_path;
else if (ret > 0)
break;
continue;
@@ -2561,7 +2569,7 @@ record_old_file_extents(struct inode *inode,
old = kmalloc(sizeof(*old), GFP_NOFS);
if (!old)
- goto out_free_list;
+ goto out_free_path;
offset = max(new->file_pos, key.offset);
end = min(new->file_pos + new->len, key.offset + num_bytes);
@@ -2583,15 +2591,10 @@ next:
return new;
-out_free_list:
- list_for_each_entry_safe(old, tmp, &new->head, list) {
- list_del(&old->list);
- kfree(old);
- }
out_free_path:
btrfs_free_path(path);
out_kfree:
- kfree(new);
+ free_sa_defrag_extent(new);
return NULL;
}
@@ -2652,7 +2655,7 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
EXTENT_DEFRAG, 1, cached_state);
if (ret) {
u64 last_snapshot = btrfs_root_last_snapshot(&root->root_item);
- if (last_snapshot >= BTRFS_I(inode)->generation)
+ if (0 && last_snapshot >= BTRFS_I(inode)->generation)
/* the inode is shared */
new = record_old_file_extents(inode, ordered_extent);
@@ -2743,8 +2746,14 @@ out:
btrfs_remove_ordered_extent(inode, ordered_extent);
/* for snapshot-aware defrag */
- if (new)
- relink_file_extents(new);
+ if (new) {
+ if (ret) {
+ free_sa_defrag_extent(new);
+ atomic_dec(&root->fs_info->defrag_running);
+ } else {
+ relink_file_extents(new);
+ }
+ }
/* once for us */
btrfs_put_ordered_extent(ordered_extent);
@@ -3536,7 +3545,8 @@ noinline int btrfs_update_inode(struct btrfs_trans_handle *trans,
* without delay
*/
if (!btrfs_is_free_space_inode(inode)
- && root->root_key.objectid != BTRFS_DATA_RELOC_TREE_OBJECTID) {
+ && root->root_key.objectid != BTRFS_DATA_RELOC_TREE_OBJECTID
+ && !root->fs_info->log_root_recovering) {
btrfs_update_root_times(trans, root);
ret = btrfs_delayed_update_inode(trans, root, inode);
@@ -4518,8 +4528,12 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr)
* these flags set. For all other operations the VFS set these flags
* explicitly if it wants a timestamp update.
*/
- if (newsize != oldsize && (!(mask & (ATTR_CTIME | ATTR_MTIME))))
- inode->i_ctime = inode->i_mtime = current_fs_time(inode->i_sb);
+ if (newsize != oldsize) {
+ inode_inc_iversion(inode);
+ if (!(mask & (ATTR_CTIME | ATTR_MTIME)))
+ inode->i_ctime = inode->i_mtime =
+ current_fs_time(inode->i_sb);
+ }
if (newsize > oldsize) {
truncate_pagecache(inode, oldsize, newsize);
@@ -6811,7 +6825,6 @@ 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))
@@ -8146,7 +8159,7 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
/* check for collisions, even if the name isn't there */
- ret = btrfs_check_dir_item_collision(root, new_dir->i_ino,
+ ret = btrfs_check_dir_item_collision(dest, new_dir->i_ino,
new_dentry->d_name.name,
new_dentry->d_name.len);
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 0f81d67cdc8d..dbefa6c609f4 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -1528,6 +1528,12 @@ static noinline int btrfs_ioctl_snap_create_transid(struct file *file,
printk(KERN_INFO "btrfs: Snapshot src from "
"another FS\n");
ret = -EINVAL;
+ } else if (!inode_owner_or_capable(src_inode)) {
+ /*
+ * Subvolume creation is not restricted, but snapshots
+ * are limited to own subvolumes only
+ */
+ ret = -EPERM;
} else {
ret = btrfs_mksubvol(&file->f_path, name, namelen,
BTRFS_I(src_inode)->root,
@@ -2093,7 +2099,7 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
err = mutex_lock_killable_nested(&dir->i_mutex, I_MUTEX_PARENT);
if (err == -EINTR)
- goto out;
+ goto out_drop_write;
dentry = lookup_one_len(vol_args->name, parent, namelen);
if (IS_ERR(dentry)) {
err = PTR_ERR(dentry);
@@ -2235,6 +2241,7 @@ out_dput:
dput(dentry);
out_unlock_dir:
mutex_unlock(&dir->i_mutex);
+out_drop_write:
mnt_drop_write_file(file);
out:
kfree(vol_args);
@@ -2565,6 +2572,11 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
if (off + len == src->i_size)
len = ALIGN(src->i_size, bs) - off;
+ if (len == 0) {
+ ret = 0;
+ goto out_unlock;
+ }
+
/* verify the end result is block aligned */
if (!IS_ALIGNED(off, bs) || !IS_ALIGNED(off + len, bs) ||
!IS_ALIGNED(destoff, bs))
@@ -3299,6 +3311,9 @@ static long btrfs_ioctl_dev_replace(struct btrfs_root *root, void __user *arg)
switch (p->cmd) {
case BTRFS_IOCTL_DEV_REPLACE_CMD_START:
+ if (root->fs_info->sb->s_flags & MS_RDONLY)
+ return -EROFS;
+
if (atomic_xchg(
&root->fs_info->mutually_exclusive_operation_running,
1)) {
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 4febca4fc2de..0e7f7765b3bb 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -691,6 +691,7 @@ struct backref_node *build_backref_tree(struct reloc_control *rc,
int cowonly;
int ret;
int err = 0;
+ bool need_check = true;
path1 = btrfs_alloc_path();
path2 = btrfs_alloc_path();
@@ -914,6 +915,7 @@ again:
cur->bytenr);
lower = cur;
+ need_check = true;
for (; level < BTRFS_MAX_LEVEL; level++) {
if (!path2->nodes[level]) {
BUG_ON(btrfs_root_bytenr(&root->root_item) !=
@@ -957,18 +959,19 @@ again:
/*
* add the block to pending list if we
- * need check its backrefs. only block
- * at 'cur->level + 1' is added to the
- * tail of pending list. this guarantees
- * we check backrefs from lower level
- * blocks to upper level blocks.
+ * need check its backrefs, we only do this once
+ * while walking up a tree as we will catch
+ * anything else later on.
*/
- if (!upper->checked &&
- level == cur->level + 1) {
+ if (!upper->checked && need_check) {
+ need_check = false;
list_add_tail(&edge->list[UPPER],
&list);
- } else
+ } else {
+ if (upper->checked)
+ need_check = true;
INIT_LIST_HEAD(&edge->list[UPPER]);
+ }
} else {
upper = rb_entry(rb_node, struct backref_node,
rb_node);
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 79bd479317cb..e4f69e3b78b9 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -545,8 +545,9 @@ static void scrub_print_warning(const char *errstr, struct scrub_block *sblock)
if (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) {
do {
- ret = tree_backref_for_extent(&ptr, eb, ei, item_size,
- &ref_root, &ref_level);
+ ret = tree_backref_for_extent(&ptr, eb, &found_key, ei,
+ item_size, &ref_root,
+ &ref_level);
printk_in_rcu(KERN_WARNING
"btrfs: %s at logical %llu on dev %s, "
"sector %llu: metadata %s (level %d) in tree "
@@ -2501,7 +2502,7 @@ again:
ret = scrub_extent(sctx, extent_logical, extent_len,
extent_physical, extent_dev, flags,
generation, extent_mirror_num,
- extent_physical);
+ extent_logical - logical + physical);
if (ret)
goto out;
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index ff40f1c00ce3..414c1b9eb896 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -1550,6 +1550,10 @@ static int lookup_dir_item_inode(struct btrfs_root *root,
goto out;
}
btrfs_dir_item_key_to_cpu(path->nodes[0], di, &key);
+ if (key.type == BTRFS_ROOT_ITEM_KEY) {
+ ret = -ENOENT;
+ goto out;
+ }
*found_inode = key.objectid;
*found_type = btrfs_dir_type(path->nodes[0], di);
@@ -2524,7 +2528,8 @@ static int did_create_dir(struct send_ctx *sctx, u64 dir)
di = btrfs_item_ptr(eb, slot, struct btrfs_dir_item);
btrfs_dir_item_key_to_cpu(eb, di, &di_key);
- if (di_key.objectid < sctx->send_progress) {
+ if (di_key.type != BTRFS_ROOT_ITEM_KEY &&
+ di_key.objectid < sctx->send_progress) {
ret = 1;
goto out;
}
@@ -4579,6 +4584,41 @@ long btrfs_ioctl_send(struct file *mnt_file, void __user *arg_)
send_root = BTRFS_I(file_inode(mnt_file))->root;
fs_info = send_root->fs_info;
+ /*
+ * This is done when we lookup the root, it should already be complete
+ * by the time we get here.
+ */
+ WARN_ON(send_root->orphan_cleanup_state != ORPHAN_CLEANUP_DONE);
+
+ /*
+ * If we just created this root we need to make sure that the orphan
+ * cleanup has been done and committed since we search the commit root,
+ * so check its commit root transid with our otransid and if they match
+ * commit the transaction to make sure everything is updated.
+ */
+ down_read(&send_root->fs_info->extent_commit_sem);
+ if (btrfs_header_generation(send_root->commit_root) ==
+ btrfs_root_otransid(&send_root->root_item)) {
+ struct btrfs_trans_handle *trans;
+
+ up_read(&send_root->fs_info->extent_commit_sem);
+
+ trans = btrfs_attach_transaction_barrier(send_root);
+ if (IS_ERR(trans)) {
+ if (PTR_ERR(trans) != -ENOENT) {
+ ret = PTR_ERR(trans);
+ goto out;
+ }
+ /* ENOENT means theres no transaction */
+ } else {
+ ret = btrfs_commit_transaction(trans, send_root);
+ if (ret)
+ goto out;
+ }
+ } else {
+ up_read(&send_root->fs_info->extent_commit_sem);
+ }
+
arg = memdup_user(arg_, sizeof(*arg));
if (IS_ERR(arg)) {
ret = PTR_ERR(arg);
@@ -4587,8 +4627,8 @@ long btrfs_ioctl_send(struct file *mnt_file, void __user *arg_)
}
if (!access_ok(VERIFY_READ, arg->clone_sources,
- sizeof(*arg->clone_sources *
- arg->clone_sources_count))) {
+ sizeof(*arg->clone_sources) *
+ arg->clone_sources_count)) {
ret = -EFAULT;
goto out;
}
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 0544587d74f4..1f214689fa5e 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -524,7 +524,6 @@ int btrfs_wait_for_commit(struct btrfs_root *root, u64 transid)
if (transid <= root->fs_info->last_trans_committed)
goto out;
- ret = -EINVAL;
/* find specified transaction */
spin_lock(&root->fs_info->trans_lock);
list_for_each_entry(t, &root->fs_info->trans_list, list) {
@@ -540,9 +539,16 @@ int btrfs_wait_for_commit(struct btrfs_root *root, u64 transid)
}
}
spin_unlock(&root->fs_info->trans_lock);
- /* The specified transaction doesn't exist */
- if (!cur_trans)
+
+ /*
+ * The specified transaction doesn't exist, or we
+ * raced with btrfs_commit_transaction
+ */
+ if (!cur_trans) {
+ if (transid > root->fs_info->last_trans_committed)
+ ret = -EINVAL;
goto out;
+ }
} else {
/* find newest transaction that is committing | committed */
spin_lock(&root->fs_info->trans_lock);
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index c276ac9a0ec3..7d3331cbccba 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -943,7 +943,7 @@ 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);
@@ -3314,7 +3314,7 @@ static int log_one_extent(struct btrfs_trans_handle *trans,
btrfs_set_token_file_extent_type(leaf, fi,
BTRFS_FILE_EXTENT_REG,
&token);
- if (em->block_start == 0)
+ if (em->block_start == EXTENT_MAP_HOLE)
skip_csum = true;
}
@@ -3728,8 +3728,9 @@ next_slot:
}
log_extents:
+ btrfs_release_path(path);
+ btrfs_release_path(dst_path);
if (fast_search) {
- btrfs_release_path(dst_path);
ret = btrfs_log_changed_extents(trans, root, inode, dst_path);
if (ret) {
err = ret;
@@ -3746,8 +3747,6 @@ log_extents:
}
if (inode_only == LOG_INODE_ALL && S_ISDIR(inode->i_mode)) {
- btrfs_release_path(path);
- btrfs_release_path(dst_path);
ret = log_directory_changes(trans, root, inode, path, dst_path);
if (ret) {
err = ret;
diff --git a/fs/btrfs/ulist.c b/fs/btrfs/ulist.c
index 7b417e20efe2..b0a523b2c60e 100644
--- a/fs/btrfs/ulist.c
+++ b/fs/btrfs/ulist.c
@@ -205,6 +205,10 @@ int ulist_add_merge(struct ulist *ulist, u64 val, u64 aux,
u64 new_alloced = ulist->nodes_alloced + 128;
struct ulist_node *new_nodes;
void *old = NULL;
+ int i;
+
+ for (i = 0; i < ulist->nnodes; i++)
+ rb_erase(&ulist->nodes[i].rb_node, &ulist->root);
/*
* if nodes_alloced == ULIST_SIZE no memory has been allocated
@@ -224,6 +228,17 @@ int ulist_add_merge(struct ulist *ulist, u64 val, u64 aux,
ulist->nodes = new_nodes;
ulist->nodes_alloced = new_alloced;
+
+ /*
+ * krealloc actually uses memcpy, which does not copy rb_node
+ * pointers, so we have to do it ourselves. Otherwise we may
+ * be bitten by crashes.
+ */
+ for (i = 0; i < ulist->nnodes; i++) {
+ ret = ulist_rbtree_insert(ulist, &ulist->nodes[i]);
+ if (ret < 0)
+ return ret;
+ }
}
ulist->nodes[ulist->nnodes].val = val;
ulist->nodes[ulist->nnodes].aux = aux;
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 8bffb9174afb..7fc774639a78 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -1384,6 +1384,22 @@ out:
return ret;
}
+/*
+ * Function to update ctime/mtime for a given device path.
+ * Mainly used for ctime/mtime based probe like libblkid.
+ */
+static void update_dev_time(char *path_name)
+{
+ struct file *filp;
+
+ filp = filp_open(path_name, O_RDWR, 0);
+ if (!filp)
+ return;
+ file_update_time(filp);
+ filp_close(filp, NULL);
+ return;
+}
+
static int btrfs_rm_dev_item(struct btrfs_root *root,
struct btrfs_device *device)
{
@@ -1612,11 +1628,12 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path)
struct btrfs_fs_devices *fs_devices;
fs_devices = root->fs_info->fs_devices;
while (fs_devices) {
- if (fs_devices->seed == cur_devices)
+ if (fs_devices->seed == cur_devices) {
+ fs_devices->seed = cur_devices->seed;
break;
+ }
fs_devices = fs_devices->seed;
}
- fs_devices->seed = cur_devices->seed;
cur_devices->seed = NULL;
lock_chunks(root);
__btrfs_close_devices(cur_devices);
@@ -1642,10 +1659,14 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path)
ret = 0;
- /* Notify udev that device has changed */
- if (bdev)
+ if (bdev) {
+ /* Notify udev that device has changed */
btrfs_kobject_uevent(bdev, KOBJ_CHANGE);
+ /* Update ctime/mtime for device path for libblkid */
+ update_dev_time(device_path);
+ }
+
error_brelse:
brelse(bh);
if (bdev)
@@ -1817,7 +1838,6 @@ static int btrfs_prepare_sprout(struct btrfs_root *root)
fs_devices->seeding = 0;
fs_devices->num_devices = 0;
fs_devices->open_devices = 0;
- fs_devices->total_devices = 0;
fs_devices->seed = seed_devices;
generate_random_uuid(fs_devices->fsid);
@@ -2089,6 +2109,8 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path)
ret = btrfs_commit_transaction(trans, root);
}
+ /* Update ctime/mtime for libblkid */
+ update_dev_time(device_path);
return ret;
error_trans:
@@ -4248,6 +4270,7 @@ int btrfs_num_copies(struct btrfs_fs_info *fs_info, u64 logical, u64 len)
btrfs_emerg(fs_info, "Invalid mapping for %Lu-%Lu, got "
"%Lu-%Lu\n", logical, logical+len, em->start,
em->start + em->len);
+ free_extent_map(em);
return 1;
}
@@ -4429,6 +4452,7 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
btrfs_crit(fs_info, "found a bad mapping, wanted %Lu, "
"found %Lu-%Lu\n", logical, em->start,
em->start + em->len);
+ free_extent_map(em);
return -EINVAL;
}
generated by cgit v1.2.3 (git 2.25.1) at 2024-04-27 21:38:40 +0000