summaryrefslogtreecommitdiff
path: root/fs/btrfs
diff options
context:
space:
mode:
Diffstat (limited to 'fs/btrfs')
-rw-r--r--fs/btrfs/ctree.c2
-rw-r--r--fs/btrfs/delalloc-space.c2
-rw-r--r--fs/btrfs/delayed-ref.c4
-rw-r--r--fs/btrfs/disk-io.c29
-rw-r--r--fs/btrfs/extent-tree.c73
-rw-r--r--fs/btrfs/extent-tree.h3
-rw-r--r--fs/btrfs/extent_io.c14
-rw-r--r--fs/btrfs/file.c2
-rw-r--r--fs/btrfs/inode.c23
-rw-r--r--fs/btrfs/ioctl.c20
-rw-r--r--fs/btrfs/ordered-data.c11
-rw-r--r--fs/btrfs/qgroup.c54
-rw-r--r--fs/btrfs/qgroup.h7
-rw-r--r--fs/btrfs/raid-stripe-tree.c2
-rw-r--r--fs/btrfs/ref-verify.c2
-rw-r--r--fs/btrfs/scrub.c10
-rw-r--r--fs/btrfs/send.c2
-rw-r--r--fs/btrfs/super.c5
-rw-r--r--fs/btrfs/transaction.c4
-rw-r--r--fs/btrfs/transaction.h3
-rw-r--r--fs/btrfs/tree-checker.c39
-rw-r--r--fs/btrfs/volumes.c15
-rw-r--r--fs/btrfs/zoned.c7
23 files changed, 240 insertions, 93 deletions
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 2a9344a3fcee..35c1d24d4a78 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -432,7 +432,7 @@ static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans,
if (btrfs_block_can_be_shared(trans, root, buf)) {
ret = btrfs_lookup_extent_info(trans, fs_info, buf->start,
btrfs_header_level(buf), 1,
- &refs, &flags);
+ &refs, &flags, NULL);
if (ret)
return ret;
if (unlikely(refs == 0)) {
diff --git a/fs/btrfs/delalloc-space.c b/fs/btrfs/delalloc-space.c
index 51453d4928fa..2833e8ef4c09 100644
--- a/fs/btrfs/delalloc-space.c
+++ b/fs/btrfs/delalloc-space.c
@@ -199,7 +199,7 @@ void btrfs_free_reserved_data_space(struct btrfs_inode *inode,
start = round_down(start, fs_info->sectorsize);
btrfs_free_reserved_data_space_noquota(fs_info, len);
- btrfs_qgroup_free_data(inode, reserved, start, len);
+ btrfs_qgroup_free_data(inode, reserved, start, len, NULL);
}
/*
diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c
index 9223934d95f4..891ea2fa263c 100644
--- a/fs/btrfs/delayed-ref.c
+++ b/fs/btrfs/delayed-ref.c
@@ -1041,7 +1041,7 @@ int btrfs_add_delayed_tree_ref(struct btrfs_trans_handle *trans,
return -ENOMEM;
}
- if (btrfs_qgroup_enabled(fs_info) && !generic_ref->skip_qgroup) {
+ if (btrfs_qgroup_full_accounting(fs_info) && !generic_ref->skip_qgroup) {
record = kzalloc(sizeof(*record), GFP_NOFS);
if (!record) {
kmem_cache_free(btrfs_delayed_tree_ref_cachep, ref);
@@ -1144,7 +1144,7 @@ int btrfs_add_delayed_data_ref(struct btrfs_trans_handle *trans,
return -ENOMEM;
}
- if (btrfs_qgroup_enabled(fs_info) && !generic_ref->skip_qgroup) {
+ if (btrfs_qgroup_full_accounting(fs_info) && !generic_ref->skip_qgroup) {
record = kzalloc(sizeof(*record), GFP_NOFS);
if (!record) {
kmem_cache_free(btrfs_delayed_data_ref_cachep, ref);
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 401ea09ae4b8..62cb97f7c94f 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -3213,6 +3213,7 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device
goto fail_alloc;
}
+ btrfs_info(fs_info, "first mount of filesystem %pU", disk_super->fsid);
/*
* Verify the type first, if that or the checksum value are
* corrupted, we'll find out
@@ -4798,6 +4799,32 @@ void btrfs_cleanup_dirty_bgs(struct btrfs_transaction *cur_trans,
}
}
+static void btrfs_free_all_qgroup_pertrans(struct btrfs_fs_info *fs_info)
+{
+ struct btrfs_root *gang[8];
+ int i;
+ int ret;
+
+ spin_lock(&fs_info->fs_roots_radix_lock);
+ while (1) {
+ ret = radix_tree_gang_lookup_tag(&fs_info->fs_roots_radix,
+ (void **)gang, 0,
+ ARRAY_SIZE(gang),
+ BTRFS_ROOT_TRANS_TAG);
+ if (ret == 0)
+ break;
+ for (i = 0; i < ret; i++) {
+ struct btrfs_root *root = gang[i];
+
+ btrfs_qgroup_free_meta_all_pertrans(root);
+ radix_tree_tag_clear(&fs_info->fs_roots_radix,
+ (unsigned long)root->root_key.objectid,
+ BTRFS_ROOT_TRANS_TAG);
+ }
+ }
+ spin_unlock(&fs_info->fs_roots_radix_lock);
+}
+
void btrfs_cleanup_one_transaction(struct btrfs_transaction *cur_trans,
struct btrfs_fs_info *fs_info)
{
@@ -4826,6 +4853,8 @@ void btrfs_cleanup_one_transaction(struct btrfs_transaction *cur_trans,
EXTENT_DIRTY);
btrfs_destroy_pinned_extent(fs_info, &cur_trans->pinned_extents);
+ btrfs_free_all_qgroup_pertrans(fs_info);
+
cur_trans->state =TRANS_STATE_COMPLETED;
wake_up(&cur_trans->commit_wait);
}
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index c8e5b4715b49..01423670bc8a 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -102,7 +102,8 @@ int btrfs_lookup_data_extent(struct btrfs_fs_info *fs_info, u64 start, u64 len)
*/
int btrfs_lookup_extent_info(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info, u64 bytenr,
- u64 offset, int metadata, u64 *refs, u64 *flags)
+ u64 offset, int metadata, u64 *refs, u64 *flags,
+ u64 *owning_root)
{
struct btrfs_root *extent_root;
struct btrfs_delayed_ref_head *head;
@@ -114,6 +115,7 @@ int btrfs_lookup_extent_info(struct btrfs_trans_handle *trans,
u32 item_size;
u64 num_refs;
u64 extent_flags;
+ u64 owner = 0;
int ret;
/*
@@ -167,6 +169,8 @@ search_again:
struct btrfs_extent_item);
num_refs = btrfs_extent_refs(leaf, ei);
extent_flags = btrfs_extent_flags(leaf, ei);
+ owner = btrfs_get_extent_owner_root(fs_info, leaf,
+ path->slots[0]);
} else {
ret = -EUCLEAN;
btrfs_err(fs_info,
@@ -226,6 +230,8 @@ out:
*refs = num_refs;
if (flags)
*flags = extent_flags;
+ if (owning_root)
+ *owning_root = owner;
out_free:
btrfs_free_path(path);
return ret;
@@ -1541,6 +1547,23 @@ out:
return ret;
}
+static void free_head_ref_squota_rsv(struct btrfs_fs_info *fs_info,
+ struct btrfs_delayed_ref_head *href)
+{
+ u64 root = href->owning_root;
+
+ /*
+ * Don't check must_insert_reserved, as this is called from contexts
+ * where it has already been unset.
+ */
+ if (btrfs_qgroup_mode(fs_info) != BTRFS_QGROUP_MODE_SIMPLE ||
+ !href->is_data || !is_fstree(root))
+ return;
+
+ btrfs_qgroup_free_refroot(fs_info, root, href->reserved_bytes,
+ BTRFS_QGROUP_RSV_DATA);
+}
+
static int run_delayed_data_ref(struct btrfs_trans_handle *trans,
struct btrfs_delayed_ref_head *href,
struct btrfs_delayed_ref_node *node,
@@ -1563,7 +1586,6 @@ static int run_delayed_data_ref(struct btrfs_trans_handle *trans,
struct btrfs_squota_delta delta = {
.root = href->owning_root,
.num_bytes = node->num_bytes,
- .rsv_bytes = href->reserved_bytes,
.is_data = true,
.is_inc = true,
.generation = trans->transid,
@@ -1580,11 +1602,9 @@ static int run_delayed_data_ref(struct btrfs_trans_handle *trans,
flags, ref->objectid,
ref->offset, &key,
node->ref_mod, href->owning_root);
+ free_head_ref_squota_rsv(trans->fs_info, href);
if (!ret)
ret = btrfs_record_squota_delta(trans->fs_info, &delta);
- else
- btrfs_qgroup_free_refroot(trans->fs_info, delta.root,
- delta.rsv_bytes, BTRFS_QGROUP_RSV_DATA);
} else if (node->action == BTRFS_ADD_DELAYED_REF) {
ret = __btrfs_inc_extent_ref(trans, node, parent, ref->root,
ref->objectid, ref->offset,
@@ -1736,7 +1756,6 @@ static int run_delayed_tree_ref(struct btrfs_trans_handle *trans,
struct btrfs_squota_delta delta = {
.root = href->owning_root,
.num_bytes = fs_info->nodesize,
- .rsv_bytes = 0,
.is_data = false,
.is_inc = true,
.generation = trans->transid,
@@ -1768,8 +1787,10 @@ static int run_one_delayed_ref(struct btrfs_trans_handle *trans,
int ret = 0;
if (TRANS_ABORTED(trans)) {
- if (insert_reserved)
+ if (insert_reserved) {
btrfs_pin_extent(trans, node->bytenr, node->num_bytes, 1);
+ free_head_ref_squota_rsv(trans->fs_info, href);
+ }
return 0;
}
@@ -1865,6 +1886,8 @@ u64 btrfs_cleanup_ref_head_accounting(struct btrfs_fs_info *fs_info,
struct btrfs_delayed_ref_root *delayed_refs,
struct btrfs_delayed_ref_head *head)
{
+ u64 ret = 0;
+
/*
* We had csum deletions accounted for in our delayed refs rsv, we need
* to drop the csum leaves for this update from our delayed_refs_rsv.
@@ -1879,14 +1902,13 @@ u64 btrfs_cleanup_ref_head_accounting(struct btrfs_fs_info *fs_info,
btrfs_delayed_refs_rsv_release(fs_info, 0, nr_csums);
- return btrfs_calc_delayed_ref_csum_bytes(fs_info, nr_csums);
+ ret = btrfs_calc_delayed_ref_csum_bytes(fs_info, nr_csums);
}
- if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_SIMPLE &&
- head->must_insert_reserved && head->is_data)
- btrfs_qgroup_free_refroot(fs_info, head->owning_root,
- head->reserved_bytes, BTRFS_QGROUP_RSV_DATA);
+ /* must_insert_reserved can be set only if we didn't run the head ref. */
+ if (head->must_insert_reserved)
+ free_head_ref_squota_rsv(fs_info, head);
- return 0;
+ return ret;
}
static int cleanup_ref_head(struct btrfs_trans_handle *trans,
@@ -2027,6 +2049,12 @@ static int btrfs_run_delayed_refs_for_head(struct btrfs_trans_handle *trans,
* spin lock.
*/
must_insert_reserved = locked_ref->must_insert_reserved;
+ /*
+ * Unsetting this on the head ref relinquishes ownership of
+ * the rsv_bytes, so it is critical that every possible code
+ * path from here forward frees all reserves including qgroup
+ * reserve.
+ */
locked_ref->must_insert_reserved = false;
extent_op = locked_ref->extent_op;
@@ -3286,7 +3314,6 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
struct btrfs_squota_delta delta = {
.root = delayed_ref_root,
.num_bytes = num_bytes,
- .rsv_bytes = 0,
.is_data = is_data,
.is_inc = false,
.generation = btrfs_extent_generation(leaf, ei),
@@ -4931,7 +4958,6 @@ int btrfs_alloc_logged_file_extent(struct btrfs_trans_handle *trans,
.root = root_objectid,
.num_bytes = ins->offset,
.generation = trans->transid,
- .rsv_bytes = 0,
.is_data = true,
.is_inc = true,
};
@@ -5234,7 +5260,7 @@ static noinline void reada_walk_down(struct btrfs_trans_handle *trans,
/* We don't lock the tree block, it's OK to be racy here */
ret = btrfs_lookup_extent_info(trans, fs_info, bytenr,
wc->level - 1, 1, &refs,
- &flags);
+ &flags, NULL);
/* We don't care about errors in readahead. */
if (ret < 0)
continue;
@@ -5301,7 +5327,8 @@ static noinline int walk_down_proc(struct btrfs_trans_handle *trans,
ret = btrfs_lookup_extent_info(trans, fs_info,
eb->start, level, 1,
&wc->refs[level],
- &wc->flags[level]);
+ &wc->flags[level],
+ NULL);
BUG_ON(ret == -ENOMEM);
if (ret)
return ret;
@@ -5391,6 +5418,7 @@ static noinline int do_walk_down(struct btrfs_trans_handle *trans,
u64 bytenr;
u64 generation;
u64 parent;
+ u64 owner_root = 0;
struct btrfs_tree_parent_check check = { 0 };
struct btrfs_key key;
struct btrfs_ref ref = { 0 };
@@ -5434,7 +5462,8 @@ static noinline int do_walk_down(struct btrfs_trans_handle *trans,
ret = btrfs_lookup_extent_info(trans, fs_info, bytenr, level - 1, 1,
&wc->refs[level - 1],
- &wc->flags[level - 1]);
+ &wc->flags[level - 1],
+ &owner_root);
if (ret < 0)
goto out_unlock;
@@ -5567,8 +5596,7 @@ skip:
find_next_key(path, level, &wc->drop_progress);
btrfs_init_generic_ref(&ref, BTRFS_DROP_DELAYED_REF, bytenr,
- fs_info->nodesize, parent,
- btrfs_header_owner(next));
+ fs_info->nodesize, parent, owner_root);
btrfs_init_tree_ref(&ref, level - 1, root->root_key.objectid,
0, false);
ret = btrfs_free_extent(trans, &ref);
@@ -5635,7 +5663,8 @@ static noinline int walk_up_proc(struct btrfs_trans_handle *trans,
ret = btrfs_lookup_extent_info(trans, fs_info,
eb->start, level, 1,
&wc->refs[level],
- &wc->flags[level]);
+ &wc->flags[level],
+ NULL);
if (ret < 0) {
btrfs_tree_unlock_rw(eb, path->locks[level]);
path->locks[level] = 0;
@@ -5880,7 +5909,7 @@ int btrfs_drop_snapshot(struct btrfs_root *root, int update_ref, int for_reloc)
ret = btrfs_lookup_extent_info(trans, fs_info,
path->nodes[level]->start,
level, 1, &wc->refs[level],
- &wc->flags[level]);
+ &wc->flags[level], NULL);
if (ret < 0) {
err = ret;
goto out_end_trans;
diff --git a/fs/btrfs/extent-tree.h b/fs/btrfs/extent-tree.h
index 0716f65d9753..2e066035ccee 100644
--- a/fs/btrfs/extent-tree.h
+++ b/fs/btrfs/extent-tree.h
@@ -99,7 +99,8 @@ u64 btrfs_cleanup_ref_head_accounting(struct btrfs_fs_info *fs_info,
int btrfs_lookup_data_extent(struct btrfs_fs_info *fs_info, u64 start, u64 len);
int btrfs_lookup_extent_info(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info, u64 bytenr,
- u64 offset, int metadata, u64 *refs, u64 *flags);
+ u64 offset, int metadata, u64 *refs, u64 *flags,
+ u64 *owner_root);
int btrfs_pin_extent(struct btrfs_trans_handle *trans, u64 bytenr, u64 num,
int reserved);
int btrfs_pin_extent_for_log_replay(struct btrfs_trans_handle *trans,
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 03cef28d9e37..8f724c54fc8e 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -674,8 +674,8 @@ static void end_bio_extent_readpage(struct btrfs_bio *bbio)
* the array will be skipped
*
* Return: 0 if all pages were able to be allocated;
- * -ENOMEM otherwise, and the caller is responsible for freeing all
- * non-null page pointers in the array.
+ * -ENOMEM otherwise, the partially allocated pages would be freed and
+ * the array slots zeroed
*/
int btrfs_alloc_page_array(unsigned int nr_pages, struct page **page_array)
{
@@ -694,8 +694,13 @@ int btrfs_alloc_page_array(unsigned int nr_pages, struct page **page_array)
* though alloc_pages_bulk_array() falls back to alloc_page()
* if it could not bulk-allocate. So we must be out of memory.
*/
- if (allocated == last)
+ if (allocated == last) {
+ for (int i = 0; i < allocated; i++) {
+ __free_page(page_array[i]);
+ page_array[i] = NULL;
+ }
return -ENOMEM;
+ }
memalloc_retry_wait(GFP_NOFS);
}
@@ -2297,7 +2302,8 @@ static int try_release_extent_state(struct extent_io_tree *tree,
ret = 0;
} else {
u32 clear_bits = ~(EXTENT_LOCKED | EXTENT_NODATASUM |
- EXTENT_DELALLOC_NEW | EXTENT_CTLBITS);
+ EXTENT_DELALLOC_NEW | EXTENT_CTLBITS |
+ EXTENT_QGROUP_RESERVED);
/*
* At this point we can safely clear everything except the
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index f47731c45bb5..32611a4edd6b 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -3192,7 +3192,7 @@ static long btrfs_fallocate(struct file *file, int mode,
qgroup_reserved -= range->len;
} else if (qgroup_reserved > 0) {
btrfs_qgroup_free_data(BTRFS_I(inode), data_reserved,
- range->start, range->len);
+ range->start, range->len, NULL);
qgroup_reserved -= range->len;
}
list_del(&range->list);
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 5e3fccddde0c..fb3c3f43c3fa 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -688,7 +688,7 @@ out:
* And at reserve time, it's always aligned to page size, so
* just free one page here.
*/
- btrfs_qgroup_free_data(inode, NULL, 0, PAGE_SIZE);
+ btrfs_qgroup_free_data(inode, NULL, 0, PAGE_SIZE, NULL);
btrfs_free_path(path);
btrfs_end_transaction(trans);
return ret;
@@ -5132,7 +5132,7 @@ static void evict_inode_truncate_pages(struct inode *inode)
*/
if (state_flags & EXTENT_DELALLOC)
btrfs_qgroup_free_data(BTRFS_I(inode), NULL, start,
- end - start + 1);
+ end - start + 1, NULL);
clear_extent_bit(io_tree, start, end,
EXTENT_CLEAR_ALL_BITS | EXTENT_DO_ACCOUNTING,
@@ -6983,8 +6983,15 @@ static struct extent_map *btrfs_new_extent_direct(struct btrfs_inode *inode,
int ret;
alloc_hint = get_extent_allocation_hint(inode, start, len);
+again:
ret = btrfs_reserve_extent(root, len, len, fs_info->sectorsize,
0, alloc_hint, &ins, 1, 1);
+ if (ret == -EAGAIN) {
+ ASSERT(btrfs_is_zoned(fs_info));
+ wait_on_bit_io(&inode->root->fs_info->flags, BTRFS_FS_NEED_ZONE_FINISH,
+ TASK_UNINTERRUPTIBLE);
+ goto again;
+ }
if (ret)
return ERR_PTR(ret);
@@ -8052,7 +8059,7 @@ next:
* reserved data space.
* Since the IO will never happen for this page.
*/
- btrfs_qgroup_free_data(inode, NULL, cur, range_end + 1 - cur);
+ btrfs_qgroup_free_data(inode, NULL, cur, range_end + 1 - cur, NULL);
if (!inode_evicting) {
clear_extent_bit(tree, cur, range_end, EXTENT_LOCKED |
EXTENT_DELALLOC | EXTENT_UPTODATE |
@@ -9484,7 +9491,7 @@ static struct btrfs_trans_handle *insert_prealloc_file_extent(
struct btrfs_path *path;
u64 start = ins->objectid;
u64 len = ins->offset;
- int qgroup_released;
+ u64 qgroup_released = 0;
int ret;
memset(&stack_fi, 0, sizeof(stack_fi));
@@ -9497,9 +9504,9 @@ static struct btrfs_trans_handle *insert_prealloc_file_extent(
btrfs_set_stack_file_extent_compression(&stack_fi, BTRFS_COMPRESS_NONE);
/* Encryption and other encoding is reserved and all 0 */
- qgroup_released = btrfs_qgroup_release_data(inode, file_offset, len);
- if (qgroup_released < 0)
- return ERR_PTR(qgroup_released);
+ ret = btrfs_qgroup_release_data(inode, file_offset, len, &qgroup_released);
+ if (ret < 0)
+ return ERR_PTR(ret);
if (trans) {
ret = insert_reserved_file_extent(trans, inode,
@@ -10394,7 +10401,7 @@ out_delalloc_release:
btrfs_delalloc_release_metadata(inode, disk_num_bytes, ret < 0);
out_qgroup_free_data:
if (ret < 0)
- btrfs_qgroup_free_data(inode, data_reserved, start, num_bytes);
+ btrfs_qgroup_free_data(inode, data_reserved, start, num_bytes, NULL);
out_free_data_space:
/*
* If btrfs_reserve_extent() succeeded, then we already decremented
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 752acff2c734..a1743904202b 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -1290,6 +1290,15 @@ static noinline int __btrfs_ioctl_snap_create(struct file *file,
* are limited to own subvolumes only
*/
ret = -EPERM;
+ } else if (btrfs_ino(BTRFS_I(src_inode)) != BTRFS_FIRST_FREE_OBJECTID) {
+ /*
+ * Snapshots must be made with the src_inode referring
+ * to the subvolume inode, otherwise the permission
+ * checking above is useless because we may have
+ * permission on a lower directory but not the subvol
+ * itself.
+ */
+ ret = -EINVAL;
} else {
ret = btrfs_mksnapshot(&file->f_path, idmap,
name, namelen,
@@ -1528,7 +1537,7 @@ static noinline int key_in_sk(struct btrfs_key *key,
static noinline int copy_to_sk(struct btrfs_path *path,
struct btrfs_key *key,
struct btrfs_ioctl_search_key *sk,
- size_t *buf_size,
+ u64 *buf_size,
char __user *ubuf,
unsigned long *sk_offset,
int *num_found)
@@ -1660,7 +1669,7 @@ out:
static noinline int search_ioctl(struct inode *inode,
struct btrfs_ioctl_search_key *sk,
- size_t *buf_size,
+ u64 *buf_size,
char __user *ubuf)
{
struct btrfs_fs_info *info = btrfs_sb(inode->i_sb);
@@ -1733,7 +1742,7 @@ static noinline int btrfs_ioctl_tree_search(struct inode *inode,
struct btrfs_ioctl_search_args __user *uargs = argp;
struct btrfs_ioctl_search_key sk;
int ret;
- size_t buf_size;
+ u64 buf_size;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
@@ -1763,8 +1772,8 @@ static noinline int btrfs_ioctl_tree_search_v2(struct inode *inode,
struct btrfs_ioctl_search_args_v2 __user *uarg = argp;
struct btrfs_ioctl_search_args_v2 args;
int ret;
- size_t buf_size;
- const size_t buf_limit = SZ_16M;
+ u64 buf_size;
+ const u64 buf_limit = SZ_16M;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
@@ -4356,6 +4365,7 @@ static int _btrfs_ioctl_send(struct inode *inode, void __user *argp, bool compat
arg->clone_sources = compat_ptr(args32.clone_sources);
arg->parent_root = args32.parent_root;
arg->flags = args32.flags;
+ arg->version = args32.version;
memcpy(arg->reserved, args32.reserved,
sizeof(args32.reserved));
#else
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index 574e8a55e24a..a82e1417c4d2 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -152,11 +152,12 @@ static struct btrfs_ordered_extent *alloc_ordered_extent(
{
struct btrfs_ordered_extent *entry;
int ret;
+ u64 qgroup_rsv = 0;
if (flags &
((1 << BTRFS_ORDERED_NOCOW) | (1 << BTRFS_ORDERED_PREALLOC))) {
/* For nocow write, we can release the qgroup rsv right now */
- ret = btrfs_qgroup_free_data(inode, NULL, file_offset, num_bytes);
+ ret = btrfs_qgroup_free_data(inode, NULL, file_offset, num_bytes, &qgroup_rsv);
if (ret < 0)
return ERR_PTR(ret);
} else {
@@ -164,7 +165,7 @@ static struct btrfs_ordered_extent *alloc_ordered_extent(
* The ordered extent has reserved qgroup space, release now
* and pass the reserved number for qgroup_record to free.
*/
- ret = btrfs_qgroup_release_data(inode, file_offset, num_bytes);
+ ret = btrfs_qgroup_release_data(inode, file_offset, num_bytes, &qgroup_rsv);
if (ret < 0)
return ERR_PTR(ret);
}
@@ -182,7 +183,7 @@ static struct btrfs_ordered_extent *alloc_ordered_extent(
entry->inode = igrab(&inode->vfs_inode);
entry->compress_type = compress_type;
entry->truncated_len = (u64)-1;
- entry->qgroup_rsv = ret;
+ entry->qgroup_rsv = qgroup_rsv;
entry->flags = flags;
refcount_set(&entry->refs, 1);
init_waitqueue_head(&entry->wait);
@@ -599,7 +600,9 @@ void btrfs_remove_ordered_extent(struct btrfs_inode *btrfs_inode,
release = entry->disk_num_bytes;
else
release = entry->num_bytes;
- btrfs_delalloc_release_metadata(btrfs_inode, release, false);
+ btrfs_delalloc_release_metadata(btrfs_inode, release,
+ test_bit(BTRFS_ORDERED_IOERR,
+ &entry->flags));
}
percpu_counter_add_batch(&fs_info->ordered_bytes, -entry->num_bytes,
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index edb84cc03237..e46774e8f49f 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -1888,7 +1888,7 @@ int btrfs_qgroup_trace_extent_nolock(struct btrfs_fs_info *fs_info,
u64 bytenr = record->bytenr;
if (!btrfs_qgroup_full_accounting(fs_info))
- return 0;
+ return 1;
lockdep_assert_held(&delayed_refs->lock);
trace_btrfs_qgroup_trace_extent(fs_info, record);
@@ -2875,12 +2875,18 @@ int btrfs_qgroup_account_extent(struct btrfs_trans_handle *trans, u64 bytenr,
num_bytes, seq);
/*
+ * We're done using the iterator, release all its qgroups while holding
+ * fs_info->qgroup_lock so that we don't race with btrfs_remove_qgroup()
+ * and trigger use-after-free accesses to qgroups.
+ */
+ qgroup_iterator_nested_clean(&qgroups);
+
+ /*
* Bump qgroup_seq to avoid seq overlap
*/
fs_info->qgroup_seq += max(nr_old_roots, nr_new_roots) + 1;
spin_unlock(&fs_info->qgroup_lock);
out_free:
- qgroup_iterator_nested_clean(&qgroups);
ulist_free(old_roots);
ulist_free(new_roots);
return ret;
@@ -4051,13 +4057,14 @@ int btrfs_qgroup_reserve_data(struct btrfs_inode *inode,
/* Free ranges specified by @reserved, normally in error path */
static int qgroup_free_reserved_data(struct btrfs_inode *inode,
- struct extent_changeset *reserved, u64 start, u64 len)
+ struct extent_changeset *reserved,
+ u64 start, u64 len, u64 *freed_ret)
{
struct btrfs_root *root = inode->root;
struct ulist_node *unode;
struct ulist_iterator uiter;
struct extent_changeset changeset;
- int freed = 0;
+ u64 freed = 0;
int ret;
extent_changeset_init(&changeset);
@@ -4098,7 +4105,9 @@ static int qgroup_free_reserved_data(struct btrfs_inode *inode,
}
btrfs_qgroup_free_refroot(root->fs_info, root->root_key.objectid, freed,
BTRFS_QGROUP_RSV_DATA);
- ret = freed;
+ if (freed_ret)
+ *freed_ret = freed;
+ ret = 0;
out:
extent_changeset_release(&changeset);
return ret;
@@ -4106,7 +4115,7 @@ out:
static int __btrfs_qgroup_release_data(struct btrfs_inode *inode,
struct extent_changeset *reserved, u64 start, u64 len,
- int free)
+ u64 *released, int free)
{
struct extent_changeset changeset;
int trace_op = QGROUP_RELEASE;
@@ -4122,7 +4131,7 @@ static int __btrfs_qgroup_release_data(struct btrfs_inode *inode,
/* In release case, we shouldn't have @reserved */
WARN_ON(!free && reserved);
if (free && reserved)
- return qgroup_free_reserved_data(inode, reserved, start, len);
+ return qgroup_free_reserved_data(inode, reserved, start, len, released);
extent_changeset_init(&changeset);
ret = clear_record_extent_bits(&inode->io_tree, start, start + len -1,
EXTENT_QGROUP_RESERVED, &changeset);
@@ -4137,7 +4146,8 @@ static int __btrfs_qgroup_release_data(struct btrfs_inode *inode,
btrfs_qgroup_free_refroot(inode->root->fs_info,
inode->root->root_key.objectid,
changeset.bytes_changed, BTRFS_QGROUP_RSV_DATA);
- ret = changeset.bytes_changed;
+ if (released)
+ *released = changeset.bytes_changed;
out:
extent_changeset_release(&changeset);
return ret;
@@ -4156,9 +4166,10 @@ out:
* NOTE: This function may sleep for memory allocation.
*/
int btrfs_qgroup_free_data(struct btrfs_inode *inode,
- struct extent_changeset *reserved, u64 start, u64 len)
+ struct extent_changeset *reserved,
+ u64 start, u64 len, u64 *freed)
{
- return __btrfs_qgroup_release_data(inode, reserved, start, len, 1);
+ return __btrfs_qgroup_release_data(inode, reserved, start, len, freed, 1);
}
/*
@@ -4176,9 +4187,9 @@ int btrfs_qgroup_free_data(struct btrfs_inode *inode,
*
* NOTE: This function may sleep for memory allocation.
*/
-int btrfs_qgroup_release_data(struct btrfs_inode *inode, u64 start, u64 len)
+int btrfs_qgroup_release_data(struct btrfs_inode *inode, u64 start, u64 len, u64 *released)
{
- return __btrfs_qgroup_release_data(inode, NULL, start, len, 0);
+ return __btrfs_qgroup_release_data(inode, NULL, start, len, released, 0);
}
static void add_root_meta_rsv(struct btrfs_root *root, int num_bytes,
@@ -4326,8 +4337,9 @@ static void qgroup_convert_meta(struct btrfs_fs_info *fs_info, u64 ref_root,
qgroup_rsv_release(fs_info, qgroup, num_bytes,
BTRFS_QGROUP_RSV_META_PREALLOC);
- qgroup_rsv_add(fs_info, qgroup, num_bytes,
- BTRFS_QGROUP_RSV_META_PERTRANS);
+ if (!sb_rdonly(fs_info->sb))
+ qgroup_rsv_add(fs_info, qgroup, num_bytes,
+ BTRFS_QGROUP_RSV_META_PERTRANS);
list_for_each_entry(glist, &qgroup->groups, next_group)
qgroup_iterator_add(&qgroup_list, glist->group);
@@ -4649,6 +4661,17 @@ void btrfs_qgroup_destroy_extent_records(struct btrfs_transaction *trans)
*root = RB_ROOT;
}
+void btrfs_free_squota_rsv(struct btrfs_fs_info *fs_info, u64 root, u64 rsv_bytes)
+{
+ if (btrfs_qgroup_mode(fs_info) != BTRFS_QGROUP_MODE_SIMPLE)
+ return;
+
+ if (!is_fstree(root))
+ return;
+
+ btrfs_qgroup_free_refroot(fs_info, root, rsv_bytes, BTRFS_QGROUP_RSV_DATA);
+}
+
int btrfs_record_squota_delta(struct btrfs_fs_info *fs_info,
struct btrfs_squota_delta *delta)
{
@@ -4693,8 +4716,5 @@ int btrfs_record_squota_delta(struct btrfs_fs_info *fs_info,
out:
spin_unlock(&fs_info->qgroup_lock);
- if (!ret && delta->rsv_bytes)
- btrfs_qgroup_free_refroot(fs_info, root, delta->rsv_bytes,
- BTRFS_QGROUP_RSV_DATA);
return ret;
}
diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h
index 855a4f978761..be18c862e64e 100644
--- a/fs/btrfs/qgroup.h
+++ b/fs/btrfs/qgroup.h
@@ -274,8 +274,6 @@ struct btrfs_squota_delta {
u64 root;
/* The number of bytes in the extent being counted. */
u64 num_bytes;
- /* The number of bytes reserved for this extent. */
- u64 rsv_bytes;
/* The generation the extent was created in. */
u64 generation;
/* Whether we are using or freeing the extent. */
@@ -358,10 +356,10 @@ int btrfs_verify_qgroup_counts(struct btrfs_fs_info *fs_info, u64 qgroupid,
/* New io_tree based accurate qgroup reserve API */
int btrfs_qgroup_reserve_data(struct btrfs_inode *inode,
struct extent_changeset **reserved, u64 start, u64 len);
-int btrfs_qgroup_release_data(struct btrfs_inode *inode, u64 start, u64 len);
+int btrfs_qgroup_release_data(struct btrfs_inode *inode, u64 start, u64 len, u64 *released);
int btrfs_qgroup_free_data(struct btrfs_inode *inode,
struct extent_changeset *reserved, u64 start,
- u64 len);
+ u64 len, u64 *freed);
int btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes,
enum btrfs_qgroup_rsv_type type, bool enforce);
int __btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes,
@@ -422,6 +420,7 @@ int btrfs_qgroup_trace_subtree_after_cow(struct btrfs_trans_handle *trans,
struct btrfs_root *root, struct extent_buffer *eb);
void btrfs_qgroup_destroy_extent_records(struct btrfs_transaction *trans);
bool btrfs_check_quota_leak(struct btrfs_fs_info *fs_info);
+void btrfs_free_squota_rsv(struct btrfs_fs_info *fs_info, u64 root, u64 rsv_bytes);
int btrfs_record_squota_delta(struct btrfs_fs_info *fs_info,
struct btrfs_squota_delta *delta);
diff --git a/fs/btrfs/raid-stripe-tree.c b/fs/btrfs/raid-stripe-tree.c
index 944e8f1862aa..9589362acfbf 100644
--- a/fs/btrfs/raid-stripe-tree.c
+++ b/fs/btrfs/raid-stripe-tree.c
@@ -145,7 +145,7 @@ int btrfs_insert_raid_extent(struct btrfs_trans_handle *trans,
btrfs_put_bioc(bioc);
}
- return ret;
+ return 0;
}
int btrfs_get_raid_extent_offset(struct btrfs_fs_info *fs_info,
diff --git a/fs/btrfs/ref-verify.c b/fs/btrfs/ref-verify.c
index 1f62976bee82..6486f0d7e993 100644
--- a/fs/btrfs/ref-verify.c
+++ b/fs/btrfs/ref-verify.c
@@ -794,6 +794,7 @@ int btrfs_ref_tree_mod(struct btrfs_fs_info *fs_info,
dump_ref_action(fs_info, ra);
kfree(ref);
kfree(ra);
+ kfree(re);
goto out_unlock;
} else if (be->num_refs == 0) {
btrfs_err(fs_info,
@@ -803,6 +804,7 @@ int btrfs_ref_tree_mod(struct btrfs_fs_info *fs_info,
dump_ref_action(fs_info, ra);
kfree(ref);
kfree(ra);
+ kfree(re);
goto out_unlock;
}
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 9ce5be21b036..f62a408671cb 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -1868,6 +1868,9 @@ static int queue_scrub_stripe(struct scrub_ctx *sctx, struct btrfs_block_group *
*/
ASSERT(sctx->cur_stripe < SCRUB_TOTAL_STRIPES);
+ /* @found_logical_ret must be specified. */
+ ASSERT(found_logical_ret);
+
stripe = &sctx->stripes[sctx->cur_stripe];
scrub_reset_stripe(stripe);
ret = scrub_find_fill_first_stripe(bg, &sctx->extent_path,
@@ -1876,8 +1879,7 @@ static int queue_scrub_stripe(struct scrub_ctx *sctx, struct btrfs_block_group *
/* Either >0 as no more extents or <0 for error. */
if (ret)
return ret;
- if (found_logical_ret)
- *found_logical_ret = stripe->logical;
+ *found_logical_ret = stripe->logical;
sctx->cur_stripe++;
/* We filled one group, submit it. */
@@ -2080,7 +2082,7 @@ static int scrub_simple_mirror(struct scrub_ctx *sctx,
/* Go through each extent items inside the logical range */
while (cur_logical < logical_end) {
- u64 found_logical;
+ u64 found_logical = U64_MAX;
u64 cur_physical = physical + cur_logical - logical_start;
/* Canceled? */
@@ -2115,6 +2117,8 @@ static int scrub_simple_mirror(struct scrub_ctx *sctx,
if (ret < 0)
break;
+ /* queue_scrub_stripe() returned 0, @found_logical must be updated. */
+ ASSERT(found_logical != U64_MAX);
cur_logical = found_logical + BTRFS_STRIPE_LEN;
/* Don't hold CPU for too long time */
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 3b929f0e8f04..4e36550618e5 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -8158,7 +8158,7 @@ long btrfs_ioctl_send(struct inode *inode, struct btrfs_ioctl_send_args *arg)
}
sctx->send_filp = fget(arg->send_fd);
- if (!sctx->send_filp) {
+ if (!sctx->send_filp || !(sctx->send_filp->f_mode & FMODE_WRITE)) {
ret = -EBADF;
goto out;
}
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index f638dc339693..ef256b944c72 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -80,7 +80,10 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data);
static void btrfs_put_super(struct super_block *sb)
{
- close_ctree(btrfs_sb(sb));
+ struct btrfs_fs_info *fs_info = btrfs_sb(sb);
+
+ btrfs_info(fs_info, "last unmount of filesystem %pU", fs_info->fs_devices->fsid);
+ close_ctree(fs_info);
}
enum {
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 6e63816dddcb..5b3333ceef04 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -37,8 +37,6 @@
static struct kmem_cache *btrfs_trans_handle_cachep;
-#define BTRFS_ROOT_TRANS_TAG 0
-
/*
* Transaction states and transitions
*
@@ -1774,7 +1772,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
btrfs_release_path(path);
ret = btrfs_create_qgroup(trans, objectid);
- if (ret) {
+ if (ret && ret != -EEXIST) {
btrfs_abort_transaction(trans, ret);
goto fail;
}
diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h
index 18c4f6e83b78..2bf8bbdfd0b3 100644
--- a/fs/btrfs/transaction.h
+++ b/fs/btrfs/transaction.h
@@ -12,6 +12,9 @@
#include "ctree.h"
#include "misc.h"
+/* Radix-tree tag for roots that are part of the trasaction. */
+#define BTRFS_ROOT_TRANS_TAG 0
+
enum btrfs_trans_state {
TRANS_STATE_RUNNING,
TRANS_STATE_COMMIT_PREP,
diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c
index a416cbea75d1..50fdc69fdddf 100644
--- a/fs/btrfs/tree-checker.c
+++ b/fs/btrfs/tree-checker.c
@@ -31,6 +31,7 @@
#include "inode-item.h"
#include "dir-item.h"
#include "raid-stripe-tree.h"
+#include "extent-tree.h"
/*
* Error message should follow the following format:
@@ -1276,6 +1277,8 @@ static int check_extent_item(struct extent_buffer *leaf,
unsigned long ptr; /* Current pointer inside inline refs */
unsigned long end; /* Extent item end */
const u32 item_size = btrfs_item_size(leaf, slot);
+ u8 last_type = 0;
+ u64 last_seq = U64_MAX;
u64 flags;
u64 generation;
u64 total_refs; /* Total refs in btrfs_extent_item */
@@ -1322,6 +1325,18 @@ static int check_extent_item(struct extent_buffer *leaf,
* 2.2) Ref type specific data
* Either using btrfs_extent_inline_ref::offset, or specific
* data structure.
+ *
+ * All above inline items should follow the order:
+ *
+ * - All btrfs_extent_inline_ref::type should be in an ascending
+ * order
+ *
+ * - Within the same type, the items should follow a descending
+ * order by their sequence number. The sequence number is
+ * determined by:
+ * * btrfs_extent_inline_ref::offset for all types other than
+ * EXTENT_DATA_REF
+ * * hash_extent_data_ref() for EXTENT_DATA_REF
*/
if (unlikely(item_size < sizeof(*ei))) {
extent_err(leaf, slot,
@@ -1403,6 +1418,7 @@ static int check_extent_item(struct extent_buffer *leaf,
struct btrfs_extent_inline_ref *iref;
struct btrfs_extent_data_ref *dref;
struct btrfs_shared_data_ref *sref;
+ u64 seq;
u64 dref_offset;
u64 inline_offset;
u8 inline_type;
@@ -1416,6 +1432,7 @@ static int check_extent_item(struct extent_buffer *leaf,
iref = (struct btrfs_extent_inline_ref *)ptr;
inline_type = btrfs_extent_inline_ref_type(leaf, iref);
inline_offset = btrfs_extent_inline_ref_offset(leaf, iref);
+ seq = inline_offset;
if (unlikely(ptr + btrfs_extent_inline_ref_size(inline_type) > end)) {
extent_err(leaf, slot,
"inline ref item overflows extent item, ptr %lu iref size %u end %lu",
@@ -1446,6 +1463,10 @@ static int check_extent_item(struct extent_buffer *leaf,
case BTRFS_EXTENT_DATA_REF_KEY:
dref = (struct btrfs_extent_data_ref *)(&iref->offset);
dref_offset = btrfs_extent_data_ref_offset(leaf, dref);
+ seq = hash_extent_data_ref(
+ btrfs_extent_data_ref_root(leaf, dref),
+ btrfs_extent_data_ref_objectid(leaf, dref),
+ btrfs_extent_data_ref_offset(leaf, dref));
if (unlikely(!IS_ALIGNED(dref_offset,
fs_info->sectorsize))) {
extent_err(leaf, slot,
@@ -1475,6 +1496,24 @@ static int check_extent_item(struct extent_buffer *leaf,
inline_type);
return -EUCLEAN;
}
+ if (inline_type < last_type) {
+ extent_err(leaf, slot,
+ "inline ref out-of-order: has type %u, prev type %u",
+ inline_type, last_type);
+ return -EUCLEAN;
+ }
+ /* Type changed, allow the sequence starts from U64_MAX again. */
+ if (inline_type > last_type)
+ last_seq = U64_MAX;
+ if (seq > last_seq) {
+ extent_err(leaf, slot,
+"inline ref out-of-order: has type %u offset %llu seq 0x%llx, prev type %u seq 0x%llx",
+ inline_type, inline_offset, seq,
+ last_type, last_seq);
+ return -EUCLEAN;
+ }
+ last_type = inline_type;
+ last_seq = seq;
ptr += btrfs_extent_inline_ref_size(inline_type);
}
/* No padding is allowed */
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index c87e18827a0a..f627674b37db 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -748,13 +748,13 @@ static noinline struct btrfs_device *device_list_add(const char *path,
if (!fs_devices) {
fs_devices = alloc_fs_devices(disk_super->fsid);
+ if (IS_ERR(fs_devices))
+ return ERR_CAST(fs_devices);
+
if (has_metadata_uuid)
memcpy(fs_devices->metadata_uuid,
disk_super->metadata_uuid, BTRFS_FSID_SIZE);
- if (IS_ERR(fs_devices))
- return ERR_CAST(fs_devices);
-
if (same_fsid_diff_dev) {
generate_random_uuid(fs_devices->fsid);
fs_devices->temp_fsid = true;
@@ -3006,15 +3006,16 @@ struct extent_map *btrfs_get_chunk_map(struct btrfs_fs_info *fs_info,
read_unlock(&em_tree->lock);
if (!em) {
- btrfs_crit(fs_info, "unable to find logical %llu length %llu",
+ btrfs_crit(fs_info,
+ "unable to find chunk map for logical %llu length %llu",
logical, length);
return ERR_PTR(-EINVAL);
}
- if (em->start > logical || em->start + em->len < logical) {
+ if (em->start > logical || em->start + em->len <= logical) {
btrfs_crit(fs_info,
- "found a bad mapping, wanted %llu-%llu, found %llu-%llu",
- logical, length, em->start, em->start + em->len);
+ "found a bad chunk map, wanted %llu-%llu, found %llu-%llu",
+ logical, logical + length, em->start, em->start + em->len);
free_extent_map(em);
return ERR_PTR(-EINVAL);
}
diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index 3504ade30cb0..188378ca19c7 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -1661,13 +1661,6 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new)
}
out:
- if (cache->alloc_offset > fs_info->zone_size) {
- btrfs_err(fs_info,
- "zoned: invalid write pointer %llu in block group %llu",
- cache->alloc_offset, cache->start);
- ret = -EIO;
- }
-
if (cache->alloc_offset > cache->zone_capacity) {
btrfs_err(fs_info,
"zoned: invalid write pointer %llu (larger than zone capacity %llu) in block group %llu",
generated by cgit (git 2.34.1) at 2024-06-12 17:18:04 +0000