summaryrefslogtreecommitdiff
path: root/fs/btrfs
diff options
context:
space:
mode:
Diffstat (limited to 'fs/btrfs')
-rw-r--r--fs/btrfs/extent-tree.c48
-rw-r--r--fs/btrfs/free-space-cache.c32
-rw-r--r--fs/btrfs/inode.c1
-rw-r--r--fs/btrfs/ioctl.c12
-rw-r--r--fs/btrfs/qgroup.c1
-rw-r--r--fs/btrfs/relocation.c2
-rw-r--r--fs/btrfs/tree-log.c30
7 files changed, 100 insertions, 26 deletions
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index a72f941ca750..80cd28456f08 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -7835,6 +7835,20 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root,
buf = btrfs_find_create_tree_block(root, bytenr);
if (!buf)
return ERR_PTR(-ENOMEM);
+
+ /*
+ * Extra safety check in case the extent tree is corrupted and extent
+ * allocator chooses to use a tree block which is already used and
+ * locked.
+ */
+ if (buf->lock_owner == current->pid) {
+ btrfs_err_rl(root->fs_info,
+"tree block %llu owner %llu already locked by pid=%d, extent tree corruption detected",
+ buf->start, btrfs_header_owner(buf), current->pid);
+ free_extent_buffer(buf);
+ return ERR_PTR(-EUCLEAN);
+ }
+
btrfs_set_header_generation(buf, trans->transid);
btrfs_set_buffer_lockdep_class(root->root_key.objectid, buf, level);
btrfs_tree_lock(buf);
@@ -8704,15 +8718,14 @@ static noinline int walk_up_proc(struct btrfs_trans_handle *trans,
if (eb == root->node) {
if (wc->flags[level] & BTRFS_BLOCK_FLAG_FULL_BACKREF)
parent = eb->start;
- else
- BUG_ON(root->root_key.objectid !=
- btrfs_header_owner(eb));
+ else if (root->root_key.objectid != btrfs_header_owner(eb))
+ goto owner_mismatch;
} else {
if (wc->flags[level + 1] & BTRFS_BLOCK_FLAG_FULL_BACKREF)
parent = path->nodes[level + 1]->start;
- else
- BUG_ON(root->root_key.objectid !=
- btrfs_header_owner(path->nodes[level + 1]));
+ else if (root->root_key.objectid !=
+ btrfs_header_owner(path->nodes[level + 1]))
+ goto owner_mismatch;
}
btrfs_free_tree_block(trans, root, eb, parent, wc->refs[level] == 1);
@@ -8720,6 +8733,11 @@ out:
wc->refs[level] = 0;
wc->flags[level] = 0;
return 0;
+
+owner_mismatch:
+ btrfs_err_rl(root->fs_info, "unexpected tree owner, have %llu expect %llu",
+ btrfs_header_owner(eb), root->root_key.objectid);
+ return -EUCLEAN;
}
static noinline int walk_down_tree(struct btrfs_trans_handle *trans,
@@ -8773,6 +8791,8 @@ static noinline int walk_up_tree(struct btrfs_trans_handle *trans,
ret = walk_up_proc(trans, root, path, wc);
if (ret > 0)
return 0;
+ if (ret < 0)
+ return ret;
if (path->locks[level]) {
btrfs_tree_unlock_rw(path->nodes[level],
@@ -9501,6 +9521,7 @@ void btrfs_put_block_group_cache(struct btrfs_fs_info *info)
block_group = btrfs_lookup_first_block_group(info, last);
while (block_group) {
+ wait_block_group_cache_done(block_group);
spin_lock(&block_group->lock);
if (block_group->iref)
break;
@@ -9891,7 +9912,7 @@ error:
void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans,
struct btrfs_root *root)
{
- struct btrfs_block_group_cache *block_group, *tmp;
+ struct btrfs_block_group_cache *block_group;
struct btrfs_root *extent_root = root->fs_info->extent_root;
struct btrfs_block_group_item item;
struct btrfs_key key;
@@ -9899,7 +9920,10 @@ void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans,
bool can_flush_pending_bgs = trans->can_flush_pending_bgs;
trans->can_flush_pending_bgs = false;
- list_for_each_entry_safe(block_group, tmp, &trans->new_bgs, bg_list) {
+ while (!list_empty(&trans->new_bgs)) {
+ block_group = list_first_entry(&trans->new_bgs,
+ struct btrfs_block_group_cache,
+ bg_list);
if (ret)
goto next;
@@ -10609,6 +10633,10 @@ static int btrfs_trim_free_extents(struct btrfs_device *device,
*trimmed = 0;
+ /* Discard not supported = nothing to do. */
+ if (!blk_queue_discard(bdev_get_queue(device->bdev)))
+ return 0;
+
/* Not writeable = nothing to do. */
if (!device->writeable)
return 0;
@@ -10731,8 +10759,8 @@ int btrfs_trim_fs(struct btrfs_root *root, struct fstrim_range *range)
}
mutex_lock(&root->fs_info->fs_devices->device_list_mutex);
- devices = &root->fs_info->fs_devices->alloc_list;
- list_for_each_entry(device, devices, dev_alloc_list) {
+ devices = &root->fs_info->fs_devices->devices;
+ list_for_each_entry(device, devices, dev_list) {
ret = btrfs_trim_free_extents(device, range->minlen,
&group_trimmed);
if (ret)
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index 45934deacfd7..1aa897dd9ce3 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -1699,6 +1699,8 @@ static inline void __bitmap_clear_bits(struct btrfs_free_space_ctl *ctl,
bitmap_clear(info->bitmap, start, count);
info->bytes -= bytes;
+ if (info->max_extent_size > ctl->unit)
+ info->max_extent_size = 0;
}
static void bitmap_clear_bits(struct btrfs_free_space_ctl *ctl,
@@ -1782,6 +1784,13 @@ static int search_bitmap(struct btrfs_free_space_ctl *ctl,
return -1;
}
+static inline u64 get_max_extent_size(struct btrfs_free_space *entry)
+{
+ if (entry->bitmap)
+ return entry->max_extent_size;
+ return entry->bytes;
+}
+
/* Cache the size of the max extent in bytes */
static struct btrfs_free_space *
find_free_space(struct btrfs_free_space_ctl *ctl, u64 *offset, u64 *bytes,
@@ -1803,8 +1812,8 @@ find_free_space(struct btrfs_free_space_ctl *ctl, u64 *offset, u64 *bytes,
for (node = &entry->offset_index; node; node = rb_next(node)) {
entry = rb_entry(node, struct btrfs_free_space, offset_index);
if (entry->bytes < *bytes) {
- if (entry->bytes > *max_extent_size)
- *max_extent_size = entry->bytes;
+ *max_extent_size = max(get_max_extent_size(entry),
+ *max_extent_size);
continue;
}
@@ -1822,8 +1831,8 @@ find_free_space(struct btrfs_free_space_ctl *ctl, u64 *offset, u64 *bytes,
}
if (entry->bytes < *bytes + align_off) {
- if (entry->bytes > *max_extent_size)
- *max_extent_size = entry->bytes;
+ *max_extent_size = max(get_max_extent_size(entry),
+ *max_extent_size);
continue;
}
@@ -1835,8 +1844,10 @@ find_free_space(struct btrfs_free_space_ctl *ctl, u64 *offset, u64 *bytes,
*offset = tmp;
*bytes = size;
return entry;
- } else if (size > *max_extent_size) {
- *max_extent_size = size;
+ } else {
+ *max_extent_size =
+ max(get_max_extent_size(entry),
+ *max_extent_size);
}
continue;
}
@@ -2694,8 +2705,8 @@ static u64 btrfs_alloc_from_bitmap(struct btrfs_block_group_cache *block_group,
err = search_bitmap(ctl, entry, &search_start, &search_bytes, true);
if (err) {
- if (search_bytes > *max_extent_size)
- *max_extent_size = search_bytes;
+ *max_extent_size = max(get_max_extent_size(entry),
+ *max_extent_size);
return 0;
}
@@ -2732,8 +2743,9 @@ u64 btrfs_alloc_from_cluster(struct btrfs_block_group_cache *block_group,
entry = rb_entry(node, struct btrfs_free_space, offset_index);
while (1) {
- if (entry->bytes < bytes && entry->bytes > *max_extent_size)
- *max_extent_size = entry->bytes;
+ if (entry->bytes < bytes)
+ *max_extent_size = max(get_max_extent_size(entry),
+ *max_extent_size);
if (entry->bytes < bytes ||
(!entry->bitmap && entry->offset < min_start)) {
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index beade8d381c2..d2c3edb50702 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -481,6 +481,7 @@ again:
pages = kcalloc(nr_pages, sizeof(struct page *), GFP_NOFS);
if (!pages) {
/* just bail out to the uncompressed code */
+ nr_pages = 0;
goto cont;
}
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 6caeb946fc1d..150d3c891815 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -3950,9 +3950,17 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
goto out_unlock;
if (len == 0)
olen = len = src->i_size - off;
- /* if we extend to eof, continue to block boundary */
- if (off + len == src->i_size)
+ /*
+ * If we extend to eof, continue to block boundary if and only if the
+ * destination end offset matches the destination file's size, otherwise
+ * we would be corrupting data by placing the eof block into the middle
+ * of a file.
+ */
+ if (off + len == src->i_size) {
+ if (!IS_ALIGNED(len, bs) && destoff + len < inode->i_size)
+ goto out_unlock;
len = ALIGN(src->i_size, bs) - off;
+ }
if (len == 0) {
ret = 0;
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index a751937dded5..90e29d40aa82 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -2446,6 +2446,7 @@ qgroup_rescan_zero_tracking(struct btrfs_fs_info *fs_info)
qgroup->rfer_cmpr = 0;
qgroup->excl = 0;
qgroup->excl_cmpr = 0;
+ qgroup_dirty(fs_info, qgroup);
}
spin_unlock(&fs_info->qgroup_lock);
}
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index cfe913d2d3df..d6ccfb31aef0 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -1318,7 +1318,7 @@ static void __del_reloc_root(struct btrfs_root *root)
struct mapping_node *node = NULL;
struct reloc_control *rc = root->fs_info->reloc_ctl;
- if (rc) {
+ if (rc && root->node) {
spin_lock(&rc->reloc_root_tree.lock);
rb_node = tree_search(&rc->reloc_root_tree.rb_root,
root->node->start);
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 2c7f9a5f8717..63f59f17c97e 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -5240,9 +5240,33 @@ static int btrfs_log_all_parents(struct btrfs_trans_handle *trans,
dir_inode = btrfs_iget(root->fs_info->sb, &inode_key,
root, NULL);
- /* If parent inode was deleted, skip it. */
- if (IS_ERR(dir_inode))
- continue;
+ /*
+ * If the parent inode was deleted, return an error to
+ * fallback to a transaction commit. This is to prevent
+ * getting an inode that was moved from one parent A to
+ * a parent B, got its former parent A deleted and then
+ * it got fsync'ed, from existing at both parents after
+ * a log replay (and the old parent still existing).
+ * Example:
+ *
+ * mkdir /mnt/A
+ * mkdir /mnt/B
+ * touch /mnt/B/bar
+ * sync
+ * mv /mnt/B/bar /mnt/A/bar
+ * mv -T /mnt/A /mnt/B
+ * fsync /mnt/B/bar
+ * <power fail>
+ *
+ * If we ignore the old parent B which got deleted,
+ * after a log replay we would have file bar linked
+ * at both parents and the old parent B would still
+ * exist.
+ */
+ if (IS_ERR(dir_inode)) {
+ ret = PTR_ERR(dir_inode);
+ goto out;
+ }
ret = btrfs_log_inode(trans, root, dir_inode,
LOG_INODE_ALL, 0, LLONG_MAX, ctx);
generated by cgit v1.2.3 (git 2.39.1) at 2024-10-18 02:21:47 +0000