summaryrefslogtreecommitdiff
path: root/fs/btrfs
diff options
context:
space:
mode:
Diffstat (limited to 'fs/btrfs')
-rw-r--r--fs/btrfs/block-group.c82
-rw-r--r--fs/btrfs/block-group.h11
-rw-r--r--fs/btrfs/block-rsv.c5
-rw-r--r--fs/btrfs/ctree.h1
-rw-r--r--fs/btrfs/delayed-inode.c5
-rw-r--r--fs/btrfs/delayed-inode.h1
-rw-r--r--fs/btrfs/disk-io.c20
-rw-r--r--fs/btrfs/extent-tree.c5
-rw-r--r--fs/btrfs/extent_io.c38
-rw-r--r--fs/btrfs/extent_map.c6
-rw-r--r--fs/btrfs/free-space-tree.c24
-rw-r--r--fs/btrfs/inode.c218
-rw-r--r--fs/btrfs/qgroup.c1
-rw-r--r--fs/btrfs/raid56.c11
-rw-r--r--fs/btrfs/relocation.c45
-rw-r--r--fs/btrfs/scrub.c3
-rw-r--r--fs/btrfs/transaction.c10
-rw-r--r--fs/btrfs/tree-checker.c14
-rw-r--r--fs/btrfs/volumes.c20
-rw-r--r--fs/btrfs/zoned.c3
20 files changed, 366 insertions, 157 deletions
diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
index 48ae509f2ac2..82324c327a50 100644
--- a/fs/btrfs/block-group.c
+++ b/fs/btrfs/block-group.c
@@ -441,13 +441,23 @@ void btrfs_wait_block_group_cache_progress(struct btrfs_block_group *cache,
u64 num_bytes)
{
struct btrfs_caching_control *caching_ctl;
+ int progress;
caching_ctl = btrfs_get_caching_control(cache);
if (!caching_ctl)
return;
+ /*
+ * We've already failed to allocate from this block group, so even if
+ * there's enough space in the block group it isn't contiguous enough to
+ * allow for an allocation, so wait for at least the next wakeup tick,
+ * or for the thing to be done.
+ */
+ progress = atomic_read(&caching_ctl->progress);
+
wait_event(caching_ctl->wait, btrfs_block_group_done(cache) ||
- (cache->free_space_ctl->free_space >= num_bytes));
+ (progress != atomic_read(&caching_ctl->progress) &&
+ (cache->free_space_ctl->free_space >= num_bytes)));
btrfs_put_caching_control(caching_ctl);
}
@@ -499,12 +509,16 @@ static void fragment_free_space(struct btrfs_block_group *block_group)
* used yet since their free space will be released as soon as the transaction
* commits.
*/
-u64 add_new_free_space(struct btrfs_block_group *block_group, u64 start, u64 end)
+int add_new_free_space(struct btrfs_block_group *block_group, u64 start, u64 end,
+ u64 *total_added_ret)
{
struct btrfs_fs_info *info = block_group->fs_info;
- u64 extent_start, extent_end, size, total_added = 0;
+ u64 extent_start, extent_end, size;
int ret;
+ if (total_added_ret)
+ *total_added_ret = 0;
+
while (start < end) {
ret = find_first_extent_bit(&info->excluded_extents, start,
&extent_start, &extent_end,
@@ -517,10 +531,12 @@ u64 add_new_free_space(struct btrfs_block_group *block_group, u64 start, u64 end
start = extent_end + 1;
} else if (extent_start > start && extent_start < end) {
size = extent_start - start;
- total_added += size;
ret = btrfs_add_free_space_async_trimmed(block_group,
start, size);
- BUG_ON(ret); /* -ENOMEM or logic error */
+ if (ret)
+ return ret;
+ if (total_added_ret)
+ *total_added_ret += size;
start = extent_end + 1;
} else {
break;
@@ -529,13 +545,15 @@ u64 add_new_free_space(struct btrfs_block_group *block_group, u64 start, u64 end
if (start < end) {
size = end - start;
- total_added += size;
ret = btrfs_add_free_space_async_trimmed(block_group, start,
size);
- BUG_ON(ret); /* -ENOMEM or logic error */
+ if (ret)
+ return ret;
+ if (total_added_ret)
+ *total_added_ret += size;
}
- return total_added;
+ return 0;
}
/*
@@ -779,8 +797,13 @@ next:
if (key.type == BTRFS_EXTENT_ITEM_KEY ||
key.type == BTRFS_METADATA_ITEM_KEY) {
- total_found += add_new_free_space(block_group, last,
- key.objectid);
+ u64 space_added;
+
+ ret = add_new_free_space(block_group, last, key.objectid,
+ &space_added);
+ if (ret)
+ goto out;
+ total_found += space_added;
if (key.type == BTRFS_METADATA_ITEM_KEY)
last = key.objectid +
fs_info->nodesize;
@@ -789,17 +812,18 @@ next:
if (total_found > CACHING_CTL_WAKE_UP) {
total_found = 0;
- if (wakeup)
+ if (wakeup) {
+ atomic_inc(&caching_ctl->progress);
wake_up(&caching_ctl->wait);
+ }
}
}
path->slots[0]++;
}
- ret = 0;
-
- total_found += add_new_free_space(block_group, last,
- block_group->start + block_group->length);
+ ret = add_new_free_space(block_group, last,
+ block_group->start + block_group->length,
+ NULL);
out:
btrfs_free_path(path);
return ret;
@@ -898,6 +922,7 @@ int btrfs_cache_block_group(struct btrfs_block_group *cache, bool wait)
init_waitqueue_head(&caching_ctl->wait);
caching_ctl->block_group = cache;
refcount_set(&caching_ctl->count, 2);
+ atomic_set(&caching_ctl->progress, 0);
btrfs_init_work(&caching_ctl->work, caching_thread, NULL, NULL);
spin_lock(&cache->lock);
@@ -1640,13 +1665,14 @@ void btrfs_mark_bg_unused(struct btrfs_block_group *bg)
{
struct btrfs_fs_info *fs_info = bg->fs_info;
- trace_btrfs_add_unused_block_group(bg);
spin_lock(&fs_info->unused_bgs_lock);
if (list_empty(&bg->bg_list)) {
btrfs_get_block_group(bg);
+ trace_btrfs_add_unused_block_group(bg);
list_add_tail(&bg->bg_list, &fs_info->unused_bgs);
- } else {
+ } else if (!test_bit(BLOCK_GROUP_FLAG_NEW, &bg->runtime_flags)) {
/* Pull out the block group from the reclaim_bgs list. */
+ trace_btrfs_add_unused_block_group(bg);
list_move_tail(&bg->bg_list, &fs_info->unused_bgs);
}
spin_unlock(&fs_info->unused_bgs_lock);
@@ -2087,6 +2113,7 @@ static int exclude_super_stripes(struct btrfs_block_group *cache)
/* Shouldn't have super stripes in sequential zones */
if (zoned && nr) {
+ kfree(logical);
btrfs_err(fs_info,
"zoned: block group %llu must not contain super block",
cache->start);
@@ -2292,9 +2319,11 @@ static int read_one_block_group(struct btrfs_fs_info *info,
btrfs_free_excluded_extents(cache);
} else if (cache->used == 0) {
cache->cached = BTRFS_CACHE_FINISHED;
- add_new_free_space(cache, cache->start,
- cache->start + cache->length);
+ ret = add_new_free_space(cache, cache->start,
+ cache->start + cache->length, NULL);
btrfs_free_excluded_extents(cache);
+ if (ret)
+ goto error;
}
ret = btrfs_add_block_group_cache(info, cache);
@@ -2668,6 +2697,7 @@ void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans)
next:
btrfs_delayed_refs_rsv_release(fs_info, 1);
list_del_init(&block_group->bg_list);
+ clear_bit(BLOCK_GROUP_FLAG_NEW, &block_group->runtime_flags);
}
btrfs_trans_release_chunk_metadata(trans);
}
@@ -2707,6 +2737,13 @@ struct btrfs_block_group *btrfs_make_block_group(struct btrfs_trans_handle *tran
if (!cache)
return ERR_PTR(-ENOMEM);
+ /*
+ * Mark it as new before adding it to the rbtree of block groups or any
+ * list, so that no other task finds it and calls btrfs_mark_bg_unused()
+ * before the new flag is set.
+ */
+ set_bit(BLOCK_GROUP_FLAG_NEW, &cache->runtime_flags);
+
cache->length = size;
set_free_space_tree_thresholds(cache);
cache->flags = type;
@@ -2730,9 +2767,12 @@ struct btrfs_block_group *btrfs_make_block_group(struct btrfs_trans_handle *tran
return ERR_PTR(ret);
}
- add_new_free_space(cache, chunk_offset, chunk_offset + size);
-
+ ret = add_new_free_space(cache, chunk_offset, chunk_offset + size, NULL);
btrfs_free_excluded_extents(cache);
+ if (ret) {
+ btrfs_put_block_group(cache);
+ return ERR_PTR(ret);
+ }
/*
* Ensure the corresponding space_info object is created and
diff --git a/fs/btrfs/block-group.h b/fs/btrfs/block-group.h
index f204addc3fe8..74b61e663028 100644
--- a/fs/btrfs/block-group.h
+++ b/fs/btrfs/block-group.h
@@ -70,6 +70,11 @@ enum btrfs_block_group_flags {
BLOCK_GROUP_FLAG_NEEDS_FREE_SPACE,
/* Indicate that the block group is placed on a sequential zone */
BLOCK_GROUP_FLAG_SEQUENTIAL_ZONE,
+ /*
+ * Indicate that block group is in the list of new block groups of a
+ * transaction.
+ */
+ BLOCK_GROUP_FLAG_NEW,
};
enum btrfs_caching_type {
@@ -85,6 +90,8 @@ struct btrfs_caching_control {
wait_queue_head_t wait;
struct btrfs_work work;
struct btrfs_block_group *block_group;
+ /* Track progress of caching during allocation. */
+ atomic_t progress;
refcount_t count;
};
@@ -284,8 +291,8 @@ int btrfs_cache_block_group(struct btrfs_block_group *cache, bool wait);
void btrfs_put_caching_control(struct btrfs_caching_control *ctl);
struct btrfs_caching_control *btrfs_get_caching_control(
struct btrfs_block_group *cache);
-u64 add_new_free_space(struct btrfs_block_group *block_group,
- u64 start, u64 end);
+int add_new_free_space(struct btrfs_block_group *block_group,
+ u64 start, u64 end, u64 *total_added_ret);
struct btrfs_trans_handle *btrfs_start_trans_remove_block_group(
struct btrfs_fs_info *fs_info,
const u64 chunk_offset);
diff --git a/fs/btrfs/block-rsv.c b/fs/btrfs/block-rsv.c
index 6279d200cf83..77684c5e0c8b 100644
--- a/fs/btrfs/block-rsv.c
+++ b/fs/btrfs/block-rsv.c
@@ -349,6 +349,11 @@ void btrfs_update_global_block_rsv(struct btrfs_fs_info *fs_info)
}
read_unlock(&fs_info->global_root_lock);
+ if (btrfs_fs_compat_ro(fs_info, BLOCK_GROUP_TREE)) {
+ num_bytes += btrfs_root_used(&fs_info->block_group_root->root_item);
+ min_items++;
+ }
+
/*
* But we also want to reserve enough space so we can do the fallback
* global reserve for an unlink, which is an additional
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index f2d2b313bde5..9419f4e37a58 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -443,6 +443,7 @@ struct btrfs_drop_extents_args {
struct btrfs_file_private {
void *filldir_buf;
+ u64 last_index;
struct extent_state *llseek_cached_state;
};
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index 6f8c0a9b2017..d37c066f2df7 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -1632,6 +1632,7 @@ int btrfs_inode_delayed_dir_index_count(struct btrfs_inode *inode)
}
bool btrfs_readdir_get_delayed_items(struct inode *inode,
+ u64 last_index,
struct list_head *ins_list,
struct list_head *del_list)
{
@@ -1651,14 +1652,14 @@ bool btrfs_readdir_get_delayed_items(struct inode *inode,
mutex_lock(&delayed_node->mutex);
item = __btrfs_first_delayed_insertion_item(delayed_node);
- while (item) {
+ while (item && item->index <= last_index) {
refcount_inc(&item->refs);
list_add_tail(&item->readdir_list, ins_list);
item = __btrfs_next_delayed_item(item);
}
item = __btrfs_first_delayed_deletion_item(delayed_node);
- while (item) {
+ while (item && item->index <= last_index) {
refcount_inc(&item->refs);
list_add_tail(&item->readdir_list, del_list);
item = __btrfs_next_delayed_item(item);
diff --git a/fs/btrfs/delayed-inode.h b/fs/btrfs/delayed-inode.h
index 4f21daa3dbc7..dc1085b2a397 100644
--- a/fs/btrfs/delayed-inode.h
+++ b/fs/btrfs/delayed-inode.h
@@ -148,6 +148,7 @@ void btrfs_destroy_delayed_inodes(struct btrfs_fs_info *fs_info);
/* Used for readdir() */
bool btrfs_readdir_get_delayed_items(struct inode *inode,
+ u64 last_index,
struct list_head *ins_list,
struct list_head *del_list);
void btrfs_readdir_put_delayed_items(struct inode *inode,
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 7513388b0567..a9a2c5446c18 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1103,7 +1103,8 @@ static int btrfs_init_fs_root(struct btrfs_root *root, dev_t anon_dev)
btrfs_drew_lock_init(&root->snapshot_lock);
if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID &&
- !btrfs_is_data_reloc_root(root)) {
+ !btrfs_is_data_reloc_root(root) &&
+ is_fstree(root->root_key.objectid)) {
set_bit(BTRFS_ROOT_SHAREABLE, &root->state);
btrfs_check_and_init_root_item(&root->root_item);
}
@@ -1300,6 +1301,16 @@ static struct btrfs_root *btrfs_get_root_ref(struct btrfs_fs_info *fs_info,
root = btrfs_get_global_root(fs_info, objectid);
if (root)
return root;
+
+ /*
+ * If we're called for non-subvolume trees, and above function didn't
+ * find one, do not try to read it from disk.
+ *
+ * This is namely for free-space-tree and quota tree, which can change
+ * at runtime and should only be grabbed from fs_info.
+ */
+ if (!is_fstree(objectid) && objectid != BTRFS_DATA_RELOC_TREE_OBJECTID)
+ return ERR_PTR(-ENOENT);
again:
root = btrfs_lookup_fs_root(fs_info, objectid);
if (root) {
@@ -3438,11 +3449,16 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device
* For devices supporting discard turn on discard=async automatically,
* unless it's already set or disabled. This could be turned off by
* nodiscard for the same mount.
+ *
+ * The zoned mode piggy backs on the discard functionality for
+ * resetting a zone. There is no reason to delay the zone reset as it is
+ * fast enough. So, do not enable async discard for zoned mode.
*/
if (!(btrfs_test_opt(fs_info, DISCARD_SYNC) ||
btrfs_test_opt(fs_info, DISCARD_ASYNC) ||
btrfs_test_opt(fs_info, NODISCARD)) &&
- fs_info->fs_devices->discardable) {
+ fs_info->fs_devices->discardable &&
+ !btrfs_is_zoned(fs_info)) {
btrfs_set_and_info(fs_info, DISCARD_ASYNC,
"auto enabling async discard");
}
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 911908ea5f6f..f396a9afa403 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -4310,8 +4310,11 @@ have_block_group:
ret = 0;
}
- if (unlikely(block_group->cached == BTRFS_CACHE_ERROR))
+ if (unlikely(block_group->cached == BTRFS_CACHE_ERROR)) {
+ if (!cache_block_group_error)
+ cache_block_group_error = -EIO;
goto loop;
+ }
if (!find_free_extent_check_size_class(ffe_ctl, block_group))
goto loop;
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index a91d5ad27984..90ad3006ef3a 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -902,7 +902,30 @@ static void submit_extent_page(struct btrfs_bio_ctrl *bio_ctrl,
size -= len;
pg_offset += len;
disk_bytenr += len;
- bio_ctrl->len_to_oe_boundary -= len;
+
+ /*
+ * len_to_oe_boundary defaults to U32_MAX, which isn't page or
+ * sector aligned. alloc_new_bio() then sets it to the end of
+ * our ordered extent for writes into zoned devices.
+ *
+ * When len_to_oe_boundary is tracking an ordered extent, we
+ * trust the ordered extent code to align things properly, and
+ * the check above to cap our write to the ordered extent
+ * boundary is correct.
+ *
+ * When len_to_oe_boundary is U32_MAX, the cap above would
+ * result in a 4095 byte IO for the last page right before
+ * we hit the bio limit of UINT_MAX. bio_add_page() has all
+ * the checks required to make sure we don't overflow the bio,
+ * and we should just ignore len_to_oe_boundary completely
+ * unless we're using it to track an ordered extent.
+ *
+ * It's pretty hard to make a bio sized U32_MAX, but it can
+ * happen when the page cache is able to feed us contiguous
+ * pages for large extents.
+ */
+ if (bio_ctrl->len_to_oe_boundary != U32_MAX)
+ bio_ctrl->len_to_oe_boundary -= len;
/* Ordered extent boundary: move on to a new bio. */
if (bio_ctrl->len_to_oe_boundary == 0)
@@ -2145,6 +2168,12 @@ retry:
continue;
}
+ if (!folio_test_dirty(folio)) {
+ /* Someone wrote it for us. */
+ folio_unlock(folio);
+ continue;
+ }
+
if (wbc->sync_mode != WB_SYNC_NONE) {
if (folio_test_writeback(folio))
submit_write_bio(bio_ctrl, 0);
@@ -2164,11 +2193,12 @@ retry:
}
/*
- * the filesystem may choose to bump up nr_to_write.
+ * The filesystem may choose to bump up nr_to_write.
* We have to make sure to honor the new nr_to_write
- * at any time
+ * at any time.
*/
- nr_to_write_done = wbc->nr_to_write <= 0;
+ nr_to_write_done = (wbc->sync_mode == WB_SYNC_NONE &&
+ wbc->nr_to_write <= 0);
}
folio_batch_release(&fbatch);
cond_resched();
diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c
index 0cdb3e86f29b..a6d8368ed0ed 100644
--- a/fs/btrfs/extent_map.c
+++ b/fs/btrfs/extent_map.c
@@ -760,8 +760,6 @@ void btrfs_drop_extent_map_range(struct btrfs_inode *inode, u64 start, u64 end,
if (skip_pinned && test_bit(EXTENT_FLAG_PINNED, &em->flags)) {
start = em_end;
- if (end != (u64)-1)
- len = start + len - em_end;
goto next;
}
@@ -829,8 +827,8 @@ void btrfs_drop_extent_map_range(struct btrfs_inode *inode, u64 start, u64 end,
if (!split)
goto remove_em;
}
- split->start = start + len;
- split->len = em_end - (start + len);
+ split->start = end;
+ split->len = em_end - end;
split->block_start = em->block_start;
split->flags = flags;
split->compress_type = em->compress_type;
diff --git a/fs/btrfs/free-space-tree.c b/fs/btrfs/free-space-tree.c
index 045ddce32eca..f169378e2ca6 100644
--- a/fs/btrfs/free-space-tree.c
+++ b/fs/btrfs/free-space-tree.c
@@ -1515,9 +1515,13 @@ static int load_free_space_bitmaps(struct btrfs_caching_control *caching_ctl,
if (prev_bit == 0 && bit == 1) {
extent_start = offset;
} else if (prev_bit == 1 && bit == 0) {
- total_found += add_new_free_space(block_group,
- extent_start,
- offset);
+ u64 space_added;
+
+ ret = add_new_free_space(block_group, extent_start,
+ offset, &space_added);
+ if (ret)
+ goto out;
+ total_found += space_added;
if (total_found > CACHING_CTL_WAKE_UP) {
total_found = 0;
wake_up(&caching_ctl->wait);
@@ -1529,8 +1533,9 @@ static int load_free_space_bitmaps(struct btrfs_caching_control *caching_ctl,
}
}
if (prev_bit == 1) {
- total_found += add_new_free_space(block_group, extent_start,
- end);
+ ret = add_new_free_space(block_group, extent_start, end, NULL);
+ if (ret)
+ goto out;
extent_count++;
}
@@ -1569,6 +1574,8 @@ static int load_free_space_extents(struct btrfs_caching_control *caching_ctl,
end = block_group->start + block_group->length;
while (1) {
+ u64 space_added;
+
ret = btrfs_next_item(root, path);
if (ret < 0)
goto out;
@@ -1583,8 +1590,11 @@ static int load_free_space_extents(struct btrfs_caching_control *caching_ctl,
ASSERT(key.type == BTRFS_FREE_SPACE_EXTENT_KEY);
ASSERT(key.objectid < end && key.objectid + key.offset <= end);
- total_found += add_new_free_space(block_group, key.objectid,
- key.objectid + key.offset);
+ ret = add_new_free_space(block_group, key.objectid,
+ key.objectid + key.offset, &space_added);
+ if (ret)
+ goto out;
+ total_found += space_added;
if (total_found > CACHING_CTL_WAKE_UP) {
total_found = 0;
wake_up(&caching_ctl->wait);
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 0964c66411a1..4e987fe6d648 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -1654,8 +1654,6 @@ out_unlock:
clear_bits,
page_ops);
start += cur_alloc_size;
- if (start >= end)
- return ret;
}
/*
@@ -1664,9 +1662,11 @@ out_unlock:
* space_info's bytes_may_use counter, reserved in
* btrfs_check_data_free_space().
*/
- extent_clear_unlock_delalloc(inode, start, end, locked_page,
- clear_bits | EXTENT_CLEAR_DATA_RESV,
- page_ops);
+ if (start < end) {
+ clear_bits |= EXTENT_CLEAR_DATA_RESV;
+ extent_clear_unlock_delalloc(inode, start, end, locked_page,
+ clear_bits, page_ops);
+ }
return ret;
}
@@ -3482,15 +3482,21 @@ zeroit:
void btrfs_add_delayed_iput(struct btrfs_inode *inode)
{
struct btrfs_fs_info *fs_info = inode->root->fs_info;
+ unsigned long flags;
if (atomic_add_unless(&inode->vfs_inode.i_count, -1, 1))
return;
atomic_inc(&fs_info->nr_delayed_iputs);
- spin_lock(&fs_info->delayed_iput_lock);
+ /*
+ * Need to be irq safe here because we can be called from either an irq
+ * context (see bio.c and btrfs_put_ordered_extent()) or a non-irq
+ * context.
+ */
+ spin_lock_irqsave(&fs_info->delayed_iput_lock, flags);
ASSERT(list_empty(&inode->delayed_iput));
list_add_tail(&inode->delayed_iput, &fs_info->delayed_iputs);
- spin_unlock(&fs_info->delayed_iput_lock);
+ spin_unlock_irqrestore(&fs_info->delayed_iput_lock, flags);
if (!test_bit(BTRFS_FS_CLEANER_RUNNING, &fs_info->flags))
wake_up_process(fs_info->cleaner_kthread);
}
@@ -3499,37 +3505,46 @@ static void run_delayed_iput_locked(struct btrfs_fs_info *fs_info,
struct btrfs_inode *inode)
{
list_del_init(&inode->delayed_iput);
- spin_unlock(&fs_info->delayed_iput_lock);
+ spin_unlock_irq(&fs_info->delayed_iput_lock);
iput(&inode->vfs_inode);
if (atomic_dec_and_test(&fs_info->nr_delayed_iputs))
wake_up(&fs_info->delayed_iputs_wait);
- spin_lock(&fs_info->delayed_iput_lock);
+ spin_lock_irq(&fs_info->delayed_iput_lock);
}
static void btrfs_run_delayed_iput(struct btrfs_fs_info *fs_info,
struct btrfs_inode *inode)
{
if (!list_empty(&inode->delayed_iput)) {
- spin_lock(&fs_info->delayed_iput_lock);
+ spin_lock_irq(&fs_info->delayed_iput_lock);
if (!list_empty(&inode->delayed_iput))
run_delayed_iput_locked(fs_info, inode);
- spin_unlock(&fs_info->delayed_iput_lock);
+ spin_unlock_irq(&fs_info->delayed_iput_lock);
}
}
void btrfs_run_delayed_iputs(struct btrfs_fs_info *fs_info)
{
-
- spin_lock(&fs_info->delayed_iput_lock);
+ /*
+ * btrfs_put_ordered_extent() can run in irq context (see bio.c), which
+ * calls btrfs_add_delayed_iput() and that needs to lock
+ * fs_info->delayed_iput_lock. So we need to disable irqs here to
+ * prevent a deadlock.
+ */
+ spin_lock_irq(&fs_info->delayed_iput_lock);
while (!list_empty(&fs_info->delayed_iputs)) {
struct btrfs_inode *inode;
inode = list_first_entry(&fs_info->delayed_iputs,
struct btrfs_inode, delayed_iput);
run_delayed_iput_locked(fs_info, inode);
- cond_resched_lock(&fs_info->delayed_iput_lock);
+ if (need_resched()) {
+ spin_unlock_irq(&fs_info->delayed_iput_lock);
+ cond_resched();
+ spin_lock_irq(&fs_info->delayed_iput_lock);
+ }
}
- spin_unlock(&fs_info->delayed_iput_lock);
+ spin_unlock_irq(&fs_info->delayed_iput_lock);
}
/*
@@ -3659,11 +3674,14 @@ int btrfs_orphan_cleanup(struct btrfs_root *root)
found_key.type = BTRFS_INODE_ITEM_KEY;
found_key.offset = 0;
inode = btrfs_iget(fs_info->sb, last_objectid, root);
- ret = PTR_ERR_OR_ZERO(inode);
- if (ret && ret != -ENOENT)
- goto out;
+ if (IS_ERR(inode)) {
+ ret = PTR_ERR(inode);
+ inode = NULL;
+ if (ret != -ENOENT)
+ goto out;
+ }
- if (ret == -ENOENT && root == fs_info->tree_root) {
+ if (!inode && root == fs_info->tree_root) {
struct btrfs_root *dead_root;
int is_dead_root = 0;
@@ -3724,17 +3742,17 @@ int btrfs_orphan_cleanup(struct btrfs_root *root)
* deleted but wasn't. The inode number may have been reused,
* but either way, we can delete the orphan item.
*/
- if (ret == -ENOENT || inode->i_nlink) {
- if (!ret) {
+ if (!inode || inode->i_nlink) {
+ if (inode) {
ret = btrfs_drop_verity_items(BTRFS_I(inode));
iput(inode);
+ inode = NULL;
if (ret)
goto out;
}
trans = btrfs_start_transaction(root, 1);
if (IS_ERR(trans)) {
ret = PTR_ERR(trans);
- iput(inode);
goto out;
}
btrfs_debug(fs_info, "auto deleting %Lu",
@@ -3742,10 +3760,8 @@ int btrfs_orphan_cleanup(struct btrfs_root *root)
ret = btrfs_del_orphan_item(trans, root,
found_key.objectid);
btrfs_end_transaction(trans);
- if (ret) {
- iput(inode);
+ if (ret)
goto out;
- }
continue;
}
@@ -4845,9 +4861,6 @@ again:
ret = -ENOMEM;
goto out;
}
- ret = set_page_extent_mapped(page);
- if (ret < 0)
- goto out_unlock;
if (!PageUptodate(page)) {
ret = btrfs_read_folio(NULL, page_folio(page));
@@ -4862,6 +4875,17 @@ again:
goto out_unlock;
}
}
+
+ /*
+ * We unlock the page after the io is completed and then re-lock it
+ * above. release_folio() could have come in between that and cleared
+ * PagePrivate(), but left the page in the mapping. Set the page mapped
+ * here to make sure it's properly set for the subpage stuff.
+ */
+ ret = set_page_extent_mapped(page);
+ if (ret < 0)
+ goto out_unlock;
+
wait_on_page_writeback(page);
lock_extent(io_tree, block_start, block_end, &cached_state);
@@ -5845,6 +5869,74 @@ static struct dentry *btrfs_lookup(struct inode *dir, struct dentry *dentry,
}
/*
+ * Find the highest existing sequence number in a directory and then set the
+ * in-memory index_cnt variable to the first free sequence number.
+ */
+static int btrfs_set_inode_index_count(struct btrfs_inode *inode)
+{
+ struct btrfs_root *root = inode->root;
+ struct btrfs_key key, found_key;
+ struct btrfs_path *path;
+ struct extent_buffer *leaf;
+ int ret;
+
+ key.objectid = btrfs_ino(inode);
+ key.type = BTRFS_DIR_INDEX_KEY;
+ key.offset = (u64)-1;
+
+ path = btrfs_alloc_path();
+ if (!path)
+ return -ENOMEM;
+
+ ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
+ if (ret < 0)
+ goto out;
+ /* FIXME: we should be able to handle this */
+ if (ret == 0)
+ goto out;
+ ret = 0;
+
+ if (path->slots[0] == 0) {
+ inode->index_cnt = BTRFS_DIR_START_INDEX;
+ goto out;
+ }
+
+ path->slots[0]--;
+
+ leaf = path->nodes[0];
+ btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]);
+
+ if (found_key.objectid != btrfs_ino(inode) ||
+ found_key.type != BTRFS_DIR_INDEX_KEY) {
+ inode->index_cnt = BTRFS_DIR_START_INDEX;
+ goto out;
+ }
+
+ inode->index_cnt = found_key.offset + 1;
+out:
+ btrfs_free_path(path);
+ return ret;
+}
+
+static int btrfs_get_dir_last_index(struct btrfs_inode *dir, u64 *index)
+{
+ if (dir->index_cnt == (u64)-1) {
+ int ret;
+
+ ret = btrfs_inode_delayed_dir_index_count(dir);
+ if (ret) {
+ ret = btrfs_set_inode_index_count(dir);
+ if (ret)
+ return ret;
+ }
+ }
+
+ *index = dir->index_cnt;
+
+ return 0;
+}
+
+/*
* All this infrastructure exists because dir_emit can fault, and we are holding
* the tree lock when doing readdir. For now just allocate a buffer and copy
* our information into that, and then dir_emit from the buffer. This is
@@ -5856,10 +5948,17 @@ static struct dentry *btrfs_lookup(struct inode *dir, struct dentry *dentry,
static int btrfs_opendir(struct inode *inode, struct file *file)
{
struct btrfs_file_private *private;
+ u64 last_index;
+ int ret;
+
+ ret = btrfs_get_dir_last_index(BTRFS_I(inode), &last_index);
+ if (ret)
+ return ret;
private = kzalloc(sizeof(struct btrfs_file_private), GFP_KERNEL);
if (!private)
return -ENOMEM;
+ private->last_index = last_index;
private->filldir_buf = kzalloc(PAGE_SIZE, GFP_KERNEL);
if (!private->filldir_buf) {
kfree(private);
@@ -5926,7 +6025,8 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx)
INIT_LIST_HEAD(&ins_list);
INIT_LIST_HEAD(&del_list);
- put = btrfs_readdir_get_delayed_items(inode, &ins_list, &del_list);
+ put = btrfs_readdir_get_delayed_items(inode, private->last_index,
+ &ins_list, &del_list);
again:
key.type = BTRFS_DIR_INDEX_KEY;
@@ -5944,6 +6044,8 @@ again:
break;
if (found_key.offset < ctx->pos)
continue;
+ if (found_key.offset > private->last_index)
+ break;
if (btrfs_should_delete_dir_index(&del_list, found_key.offset))
continue;
di = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_dir_item);
@@ -6072,57 +6174,6 @@ static int btrfs_update_time(struct inode *inode, int flags)
}
/*
- * find the highest existing sequence number in a directory
- * and then set the in-memory index_cnt variable to reflect
- * free sequence numbers
- */
-static int btrfs_set_inode_index_count(struct btrfs_inode *inode)
-{
- struct btrfs_root *root = inode->root;
- struct btrfs_key key, found_key;
- struct btrfs_path *path;
- struct extent_buffer *leaf;
- int ret;
-
- key.objectid = btrfs_ino(inode);
- key.type = BTRFS_DIR_INDEX_KEY;
- key.offset = (u64)-1;
-
- path = btrfs_alloc_path();
- if (!path)
- return -ENOMEM;
-
- ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
- if (ret < 0)
- goto out;
- /* FIXME: we should be able to handle this */
- if (ret == 0)
- goto out;
- ret = 0;
-
- if (path->slots[0] == 0) {
- inode->index_cnt = BTRFS_DIR_START_INDEX;
- goto out;
- }
-
- path->slots[0]--;
-
- leaf = path->nodes[0];
- btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]);
-
- if (found_key.objectid != btrfs_ino(inode) ||
- found_key.type != BTRFS_DIR_INDEX_KEY) {
- inode->index_cnt = BTRFS_DIR_START_INDEX;
- goto out;
- }
-
- inode->index_cnt = found_key.offset + 1;
-out:
- btrfs_free_path(path);
- return ret;
-}
-
-/*
* helper to find a free sequence number in a given directory. This current
* code is very simple, later versions will do smarter things in the btree
*/
@@ -7834,8 +7885,11 @@ static void btrfs_dio_submit_io(const struct iomap_iter *iter, struct bio *bio,
ret = btrfs_extract_ordered_extent(bbio, dio_data->ordered);
if (ret) {
- bbio->bio.bi_status = errno_to_blk_status(ret);
- btrfs_dio_end_io(bbio);
+ btrfs_finish_ordered_extent(dio_data->ordered, NULL,
+ file_offset, dip->bytes,
+ !ret);
+ bio->bi_status = errno_to_blk_status(ret);
+ iomap_dio_bio_end_io(bio);
return;
}
}
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index da1f84a0eb29..2637d6b157ff 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -4445,4 +4445,5 @@ void btrfs_qgroup_destroy_extent_records(struct btrfs_transaction *trans)
ulist_free(entry->old_roots);
kfree(entry);
}
+ *root = RB_ROOT;
}
diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index f37b925d587f..0249ea52bb80 100644
--- a/fs/btrfs/raid56.c
+++ b/fs/btrfs/raid56.c
@@ -71,7 +71,7 @@ static void rmw_rbio_work_locked(struct work_struct *work);
static void index_rbio_pages(struct btrfs_raid_bio *rbio);
static int alloc_rbio_pages(struct btrfs_raid_bio *rbio);
-static int finish_parity_scrub(struct btrfs_raid_bio *rbio, int need_check);
+static int finish_parity_scrub(struct btrfs_raid_bio *rbio);
static void scrub_rbio_work_locked(struct work_struct *work);
static void free_raid_bio_pointers(struct btrfs_raid_bio *rbio)
@@ -2404,7 +2404,7 @@ static int alloc_rbio_essential_pages(struct btrfs_raid_bio *rbio)
return 0;
}
-static int finish_parity_scrub(struct btrfs_raid_bio *rbio, int need_check)
+static int finish_parity_scrub(struct btrfs_raid_bio *rbio)
{
struct btrfs_io_context *bioc = rbio->bioc;
const u32 sectorsize = bioc->fs_info->sectorsize;
@@ -2445,9 +2445,6 @@ static int finish_parity_scrub(struct btrfs_raid_bio *rbio, int need_check)
*/
clear_bit(RBIO_CACHE_READY_BIT, &rbio->flags);
- if (!need_check)
- goto writeback;
-
p_sector.page = alloc_page(GFP_NOFS);
if (!p_sector.page)
return -ENOMEM;
@@ -2516,7 +2513,6 @@ static int finish_parity_scrub(struct btrfs_raid_bio *rbio, int need_check)
q_sector.page = NULL;
}
-writeback:
/*
* time to start writing. Make bios for everything from the
* higher layers (the bio_list in our rbio) and our p/q. Ignore
@@ -2699,7 +2695,6 @@ static int scrub_assemble_read_bios(struct btrfs_raid_bio *rbio)
static void scrub_rbio(struct btrfs_raid_bio *rbio)
{
- bool need_check = false;
int sector_nr;
int ret;
@@ -2722,7 +2717,7 @@ static void scrub_rbio(struct btrfs_raid_bio *rbio)
* We have every sector properly prepared. Can finish the scrub
* and writeback the good content.
*/
- ret = finish_parity_scrub(rbio, need_check);
+ ret = finish_parity_scrub(rbio);
wait_event(rbio->io_wait, atomic_read(&rbio->stripes_pending) == 0);
for (sector_nr = 0; sector_nr < rbio->stripe_nsectors; sector_nr++) {
int found_errors;
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 25a3361caedc..46c3c1d57266 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -1916,7 +1916,39 @@ again:
err = PTR_ERR(root);
break;
}
- ASSERT(root->reloc_root == reloc_root);
+
+ if (unlikely(root->reloc_root != reloc_root)) {
+ if (root->reloc_root) {
+ btrfs_err(fs_info,
+"reloc tree mismatch, root %lld has reloc root key (%lld %u %llu) gen %llu, expect reloc root key (%lld %u %llu) gen %llu",
+ root->root_key.objectid,
+ root->reloc_root->root_key.objectid,
+ root->reloc_root->root_key.type,
+ root->reloc_root->root_key.offset,
+ btrfs_root_generation(
+ &root->reloc_root->root_item),
+ reloc_root->root_key.objectid,
+ reloc_root->root_key.type,
+ reloc_root->root_key.offset,
+ btrfs_root_generation(
+ &reloc_root->root_item));
+ } else {
+ btrfs_err(fs_info,
+"reloc tree mismatch, root %lld has no reloc root, expect reloc root key (%lld %u %llu) gen %llu",
+ root->root_key.objectid,
+ reloc_root->root_key.objectid,
+ reloc_root->root_key.type,
+ reloc_root->root_key.offset,
+ btrfs_root_generation(
+ &reloc_root->root_item));
+ }
+ list_add(&reloc_root->root_list, &reloc_roots);
+ btrfs_put_root(root);
+ btrfs_abort_transaction(trans, -EUCLEAN);
+ if (!err)
+ err = -EUCLEAN;
+ break;
+ }
/*
* set reference count to 1, so btrfs_recover_relocation
@@ -1989,7 +2021,7 @@ again:
root = btrfs_get_fs_root(fs_info, reloc_root->root_key.offset,
false);
if (btrfs_root_refs(&reloc_root->root_item) > 0) {
- if (IS_ERR(root)) {
+ if (WARN_ON(IS_ERR(root))) {
/*
* For recovery we read the fs roots on mount,
* and if we didn't find the root then we marked
@@ -1998,17 +2030,14 @@ again:
* memory. However there's no reason we can't
* handle the error properly here just in case.
*/
- ASSERT(0);
ret = PTR_ERR(root);
goto out;
}
- if (root->reloc_root != reloc_root) {
+ if (WARN_ON(root->reloc_root != reloc_root)) {
/*
- * This is actually impossible without something
- * going really wrong (like weird race condition
- * or cosmic rays).
+ * This can happen if on-disk metadata has some
+ * corruption, e.g. bad reloc tree key offset.
*/
- ASSERT(0);
ret = -EINVAL;
goto out;
}
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 4cae41bd6de0..7289f5bff397 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -605,7 +605,8 @@ static void scrub_verify_one_metadata(struct scrub_stripe *stripe, int sector_nr
btrfs_stack_header_bytenr(header), logical);
return;
}
- if (memcmp(header->fsid, fs_info->fs_devices->fsid, BTRFS_FSID_SIZE) != 0) {
+ if (memcmp(header->fsid, fs_info->fs_devices->metadata_uuid,
+ BTRFS_FSID_SIZE) != 0) {
bitmap_set(&stripe->meta_error_bitmap, sector_nr, sectors_per_tree);
bitmap_set(&stripe->error_bitmap, sector_nr, sectors_per_tree);
btrfs_warn_rl(fs_info,
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index f6e4016a343e..a10e38c2609f 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -826,8 +826,13 @@ btrfs_attach_transaction_barrier(struct btrfs_root *root)
trans = start_transaction(root, 0, TRANS_ATTACH,
BTRFS_RESERVE_NO_FLUSH, true);
- if (trans == ERR_PTR(-ENOENT))
- btrfs_wait_for_commit(root->fs_info, 0);
+ if (trans == ERR_PTR(-ENOENT)) {
+ int ret;
+
+ ret = btrfs_wait_for_commit(root->fs_info, 0);
+ if (ret)
+ return ERR_PTR(ret);
+ }
return trans;
}
@@ -931,6 +936,7 @@ int btrfs_wait_for_commit(struct btrfs_fs_info *fs_info, u64 transid)
}
wait_for_commit(cur_trans, TRANS_STATE_COMPLETED);
+ ret = cur_trans->aborted;
btrfs_put_transaction(cur_trans);
out:
return ret;
diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c
index 038dfa8f1788..ab08a0b01311 100644
--- a/fs/btrfs/tree-checker.c
+++ b/fs/btrfs/tree-checker.c
@@ -446,6 +446,20 @@ static int check_root_key(struct extent_buffer *leaf, struct btrfs_key *key,
btrfs_item_key_to_cpu(leaf, &item_key, slot);
is_root_item = (item_key.type == BTRFS_ROOT_ITEM_KEY);
+ /*
+ * Bad rootid for reloc trees.
+ *
+ * Reloc trees are only for subvolume trees, other trees only need
+ * to be COWed to be relocated.
+ */
+ if (unlikely(is_root_item && key->objectid == BTRFS_TREE_RELOC_OBJECTID &&
+ !is_fstree(key->offset))) {
+ generic_err(leaf, slot,
+ "invalid reloc tree for root %lld, root id is not a subvolume tree",
+ key->offset);
+ return -EUCLEAN;
+ }
+
/* No such tree id */
if (unlikely(key->objectid == 0)) {
if (is_root_item)
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 264c71590370..f6718999d183 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -4076,14 +4076,6 @@ static int alloc_profile_is_valid(u64 flags, int extended)
return has_single_bit_set(flags);
}
-static inline int balance_need_close(struct btrfs_fs_info *fs_info)
-{
- /* cancel requested || normal exit path */
- return atomic_read(&fs_info->balance_cancel_req) ||
- (atomic_read(&fs_info->balance_pause_req) == 0 &&
- atomic_read(&fs_info->balance_cancel_req) == 0);
-}
-
/*
* Validate target profile against allowed profiles and return true if it's OK.
* Otherwise print the error message and return false.
@@ -4273,6 +4265,7 @@ int btrfs_balance(struct btrfs_fs_info *fs_info,
u64 num_devices;
unsigned seq;
bool reducing_redundancy;
+ bool paused = false;
int i;
if (btrfs_fs_closing(fs_info) ||
@@ -4403,6 +4396,7 @@ int btrfs_balance(struct btrfs_fs_info *fs_info,
if (ret == -ECANCELED && atomic_read(&fs_info->balance_pause_req)) {
btrfs_info(fs_info, "balance: paused");
btrfs_exclop_balance(fs_info, BTRFS_EXCLOP_BALANCE_PAUSED);
+ paused = true;
}
/*
* Balance can be canceled by:
@@ -4431,8 +4425,8 @@ int btrfs_balance(struct btrfs_fs_info *fs_info,
btrfs_update_ioctl_balance_args(fs_info, bargs);
}
- if ((ret && ret != -ECANCELED && ret != -ENOSPC) ||
- balance_need_close(fs_info)) {
+ /* We didn't pause, we can clean everything up. */
+ if (!paused) {
reset_balance_state(fs_info);
btrfs_exclop_finish(fs_info);
}
@@ -4642,8 +4636,7 @@ int btrfs_cancel_balance(struct btrfs_fs_info *fs_info)
}
}
- BUG_ON(fs_info->balance_ctl ||
- test_bit(BTRFS_FS_BALANCE_RUNNING, &fs_info->flags));
+ ASSERT(!test_bit(BTRFS_FS_BALANCE_RUNNING, &fs_info->flags));
atomic_dec(&fs_info->balance_cancel_req);
mutex_unlock(&fs_info->balance_mutex);
return 0;
@@ -6402,7 +6395,8 @@ int btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
(op == BTRFS_MAP_READ || !dev_replace_is_ongoing ||
!dev_replace->tgtdev)) {
set_io_stripe(smap, map, stripe_index, stripe_offset, stripe_nr);
- *mirror_num_ret = mirror_num;
+ if (mirror_num_ret)
+ *mirror_num_ret = mirror_num;
*bioc_ret = NULL;
ret = 0;
goto out;
diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index 85b8b332add9..72b90bc19a19 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -805,6 +805,9 @@ int btrfs_check_mountopts_zoned(struct btrfs_fs_info *info)
return -EINVAL;
}
+ btrfs_clear_and_info(info, DISCARD_ASYNC,
+ "zoned: async discard ignored and disabled for zoned mode");
+
return 0;
}
generated by cgit (git 2.34.1) at 2024-07-05 19:16:25 +0000