summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/afs/main.c6
-rw-r--r--fs/block_dev.c10
-rw-r--r--fs/btrfs/backref.c2
-rw-r--r--fs/btrfs/block-group.c13
-rw-r--r--fs/btrfs/ctree.h3
-rw-r--r--fs/btrfs/disk-io.c2
-rw-r--r--fs/btrfs/extent-tree.c71
-rw-r--r--fs/btrfs/extent_io.c4
-rw-r--r--fs/btrfs/free-space-tree.c10
-rw-r--r--fs/btrfs/inode.c60
-rw-r--r--fs/btrfs/print-tree.c10
-rw-r--r--fs/btrfs/print-tree.h2
-rw-r--r--fs/btrfs/relocation.c7
-rw-r--r--fs/btrfs/send.c15
-rw-r--r--fs/btrfs/space-info.c4
-rw-r--r--fs/btrfs/transaction.c8
-rw-r--r--fs/btrfs/tree-checker.c7
-rw-r--r--fs/btrfs/volumes.c4
-rw-r--r--fs/btrfs/volumes.h11
-rw-r--r--fs/cachefiles/rdwr.c2
-rw-r--r--fs/ceph/mds_client.c34
-rw-r--r--fs/cifs/cifs_dfs_ref.c12
-rw-r--r--fs/cifs/cifsfs.c2
-rw-r--r--fs/cifs/cifsproto.h6
-rw-r--r--fs/cifs/connect.c38
-rw-r--r--fs/cifs/dfs_cache.c11
-rw-r--r--fs/cifs/dir.c22
-rw-r--r--fs/cifs/fs_context.c45
-rw-r--r--fs/cifs/smb2pdu.c2
-rw-r--r--fs/cifs/smb2pdu.h4
-rw-r--r--fs/cifs/transport.c22
-rw-r--r--fs/ecryptfs/inode.c10
-rw-r--r--fs/ext4/ext4_jbd2.c17
-rw-r--r--fs/ext4/ext4_jbd2.h5
-rw-r--r--fs/ext4/fast_commit.c35
-rw-r--r--fs/ext4/file.c7
-rw-r--r--fs/ext4/inode.c6
-rw-r--r--fs/ext4/ioctl.c3
-rw-r--r--fs/ext4/namei.c27
-rw-r--r--fs/ext4/resize.c20
-rw-r--r--fs/ext4/super.c190
-rw-r--r--fs/ext4/xattr.c5
-rw-r--r--fs/fs-writeback.c24
-rw-r--r--fs/hugetlbfs/inode.c3
-rw-r--r--fs/io_uring.c209
-rw-r--r--fs/kernfs/file.c65
-rw-r--r--fs/namespace.c7
-rw-r--r--fs/nfs/delegation.c12
-rw-r--r--fs/nfs/internal.h38
-rw-r--r--fs/nfs/nfs4proc.c28
-rw-r--r--fs/nfs/nfs4super.c4
-rw-r--r--fs/nfs/pnfs.c136
-rw-r--r--fs/nfs/pnfs.h8
-rw-r--r--fs/nfs/pnfs_nfs.c22
-rw-r--r--fs/nfsd/nfs3xdr.c7
-rw-r--r--fs/nfsd/nfs4proc.c5
-rw-r--r--fs/nfsd/nfs4xdr.c56
-rw-r--r--fs/nfsd/nfssvc.c6
-rw-r--r--fs/nfsd/xdr4.h1
-rw-r--r--fs/overlayfs/copy_up.c15
-rw-r--r--fs/overlayfs/dir.c2
-rw-r--r--fs/overlayfs/file.c5
-rw-r--r--fs/overlayfs/inode.c2
-rw-r--r--fs/overlayfs/overlayfs.h1
-rw-r--r--fs/overlayfs/ovl_entry.h2
-rw-r--r--fs/overlayfs/readdir.c28
-rw-r--r--fs/overlayfs/super.c38
-rw-r--r--fs/overlayfs/util.c27
-rw-r--r--fs/pipe.c1
-rw-r--r--fs/proc/proc_sysctl.c7
-rw-r--r--fs/proc/task_mmu.c53
-rw-r--r--fs/udf/super.c7
72 files changed, 990 insertions, 603 deletions
diff --git a/fs/afs/main.c b/fs/afs/main.c
index accdd8970e7c..b2975256dadb 100644
--- a/fs/afs/main.c
+++ b/fs/afs/main.c
@@ -193,7 +193,7 @@ static int __init afs_init(void)
goto error_cache;
#endif
- ret = register_pernet_subsys(&afs_net_ops);
+ ret = register_pernet_device(&afs_net_ops);
if (ret < 0)
goto error_net;
@@ -213,7 +213,7 @@ static int __init afs_init(void)
error_proc:
afs_fs_exit();
error_fs:
- unregister_pernet_subsys(&afs_net_ops);
+ unregister_pernet_device(&afs_net_ops);
error_net:
#ifdef CONFIG_AFS_FSCACHE
fscache_unregister_netfs(&afs_cache_netfs);
@@ -244,7 +244,7 @@ static void __exit afs_exit(void)
proc_remove(afs_proc_symlink);
afs_fs_exit();
- unregister_pernet_subsys(&afs_net_ops);
+ unregister_pernet_device(&afs_net_ops);
#ifdef CONFIG_AFS_FSCACHE
fscache_unregister_netfs(&afs_cache_netfs);
#endif
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 3b8963e228a1..235b5042672e 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -130,7 +130,15 @@ EXPORT_SYMBOL(truncate_bdev_range);
static void set_init_blocksize(struct block_device *bdev)
{
- bdev->bd_inode->i_blkbits = blksize_bits(bdev_logical_block_size(bdev));
+ unsigned int bsize = bdev_logical_block_size(bdev);
+ loff_t size = i_size_read(bdev->bd_inode);
+
+ while (bsize < PAGE_SIZE) {
+ if (size & bsize)
+ break;
+ bsize <<= 1;
+ }
+ bdev->bd_inode->i_blkbits = blksize_bits(bsize);
}
int set_blocksize(struct block_device *bdev, int size)
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index 02d7d7b2563b..9cadacf3ec27 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -3117,7 +3117,7 @@ void btrfs_backref_error_cleanup(struct btrfs_backref_cache *cache,
list_del_init(&lower->list);
if (lower == node)
node = NULL;
- btrfs_backref_free_node(cache, lower);
+ btrfs_backref_drop_node(cache, lower);
}
btrfs_backref_cleanup_node(cache, node);
diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
index 52f2198d44c9..48ebc106a606 100644
--- a/fs/btrfs/block-group.c
+++ b/fs/btrfs/block-group.c
@@ -673,7 +673,15 @@ static noinline void caching_thread(struct btrfs_work *work)
wake_up(&caching_ctl->wait);
}
- if (btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE))
+ /*
+ * If we are in the transaction that populated the free space tree we
+ * can't actually cache from the free space tree as our commit root and
+ * real root are the same, so we could change the contents of the blocks
+ * while caching. Instead do the slow caching in this case, and after
+ * the transaction has committed we will be safe.
+ */
+ if (btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE) &&
+ !(test_bit(BTRFS_FS_FREE_SPACE_TREE_UNTRUSTED, &fs_info->flags)))
ret = load_free_space_tree(caching_ctl);
else
ret = load_extent_tree_free(caching_ctl);
@@ -2669,7 +2677,8 @@ again:
* Go through delayed refs for all the stuff we've just kicked off
* and then loop back (just once)
*/
- ret = btrfs_run_delayed_refs(trans, 0);
+ if (!ret)
+ ret = btrfs_run_delayed_refs(trans, 0);
if (!ret && loops == 0) {
loops++;
spin_lock(&cur_trans->dirty_bgs_lock);
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index e6e37591f1de..4debdbdde2ab 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -563,6 +563,9 @@ enum {
/* Indicate that we need to cleanup space cache v1 */
BTRFS_FS_CLEANUP_SPACE_CACHE_V1,
+
+ /* Indicate that we can't trust the free space tree for caching yet */
+ BTRFS_FS_FREE_SPACE_TREE_UNTRUSTED,
};
/*
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 1dfd4b2d0e1e..6b35b7e88136 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1457,7 +1457,7 @@ void btrfs_check_leaked_roots(struct btrfs_fs_info *fs_info)
root = list_first_entry(&fs_info->allocated_roots,
struct btrfs_root, leak_list);
btrfs_err(fs_info, "leaked root %s refcount %d",
- btrfs_root_name(root->root_key.objectid, buf),
+ btrfs_root_name(&root->root_key, buf),
refcount_read(&root->refs));
while (refcount_read(&root->refs) > 1)
btrfs_put_root(root);
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index d79b8369e6aa..0c335dae5af7 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -2602,8 +2602,6 @@ int btrfs_pin_extent_for_log_replay(struct btrfs_trans_handle *trans,
struct btrfs_block_group *cache;
int ret;
- btrfs_add_excluded_extent(trans->fs_info, bytenr, num_bytes);
-
cache = btrfs_lookup_block_group(trans->fs_info, bytenr);
if (!cache)
return -EINVAL;
@@ -2615,11 +2613,19 @@ int btrfs_pin_extent_for_log_replay(struct btrfs_trans_handle *trans,
* the pinned extents.
*/
btrfs_cache_block_group(cache, 1);
+ /*
+ * Make sure we wait until the cache is completely built in case it is
+ * missing or is invalid and therefore needs to be rebuilt.
+ */
+ ret = btrfs_wait_block_group_cache_done(cache);
+ if (ret)
+ goto out;
pin_down_extent(trans, cache, bytenr, num_bytes, 0);
/* remove us from the free space cache (if we're there at all) */
ret = btrfs_remove_free_space(cache, bytenr, num_bytes);
+out:
btrfs_put_block_group(cache);
return ret;
}
@@ -2629,50 +2635,22 @@ static int __exclude_logged_extent(struct btrfs_fs_info *fs_info,
{
int ret;
struct btrfs_block_group *block_group;
- struct btrfs_caching_control *caching_ctl;
block_group = btrfs_lookup_block_group(fs_info, start);
if (!block_group)
return -EINVAL;
- btrfs_cache_block_group(block_group, 0);
- caching_ctl = btrfs_get_caching_control(block_group);
-
- if (!caching_ctl) {
- /* Logic error */
- BUG_ON(!btrfs_block_group_done(block_group));
- ret = btrfs_remove_free_space(block_group, start, num_bytes);
- } else {
- /*
- * We must wait for v1 caching to finish, otherwise we may not
- * remove our space.
- */
- btrfs_wait_space_cache_v1_finished(block_group, caching_ctl);
- mutex_lock(&caching_ctl->mutex);
-
- if (start >= caching_ctl->progress) {
- ret = btrfs_add_excluded_extent(fs_info, start,
- num_bytes);
- } else if (start + num_bytes <= caching_ctl->progress) {
- ret = btrfs_remove_free_space(block_group,
- start, num_bytes);
- } else {
- num_bytes = caching_ctl->progress - start;
- ret = btrfs_remove_free_space(block_group,
- start, num_bytes);
- if (ret)
- goto out_lock;
+ btrfs_cache_block_group(block_group, 1);
+ /*
+ * Make sure we wait until the cache is completely built in case it is
+ * missing or is invalid and therefore needs to be rebuilt.
+ */
+ ret = btrfs_wait_block_group_cache_done(block_group);
+ if (ret)
+ goto out;
- num_bytes = (start + num_bytes) -
- caching_ctl->progress;
- start = caching_ctl->progress;
- ret = btrfs_add_excluded_extent(fs_info, start,
- num_bytes);
- }
-out_lock:
- mutex_unlock(&caching_ctl->mutex);
- btrfs_put_caching_control(caching_ctl);
- }
+ ret = btrfs_remove_free_space(block_group, start, num_bytes);
+out:
btrfs_put_block_group(block_group);
return ret;
}
@@ -2863,9 +2841,6 @@ int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans)
mutex_unlock(&fs_info->unused_bg_unpin_mutex);
break;
}
- if (test_bit(BTRFS_FS_LOG_RECOVERING, &fs_info->flags))
- clear_extent_bits(&fs_info->excluded_extents, start,
- end, EXTENT_UPTODATE);
if (btrfs_test_opt(fs_info, DISCARD_SYNC))
ret = btrfs_discard_extent(fs_info, start,
@@ -5549,7 +5524,15 @@ int btrfs_drop_snapshot(struct btrfs_root *root, int update_ref, int for_reloc)
goto out_free;
}
- trans = btrfs_start_transaction(tree_root, 0);
+ /*
+ * Use join to avoid potential EINTR from transaction
+ * start. See wait_reserve_ticket and the whole
+ * reservation callchain.
+ */
+ if (for_reloc)
+ trans = btrfs_join_transaction(tree_root);
+ else
+ trans = btrfs_start_transaction(tree_root, 0);
if (IS_ERR(trans)) {
err = PTR_ERR(trans);
goto out_free;
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 6e3b72e63e42..c9cee458e001 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -676,9 +676,7 @@ alloc_extent_state_atomic(struct extent_state *prealloc)
static void extent_io_tree_panic(struct extent_io_tree *tree, int err)
{
- struct inode *inode = tree->private_data;
-
- btrfs_panic(btrfs_sb(inode->i_sb), err,
+ btrfs_panic(tree->fs_info, err,
"locking error: extent tree was modified by another thread while locked");
}
diff --git a/fs/btrfs/free-space-tree.c b/fs/btrfs/free-space-tree.c
index e33a65bd9a0c..a33bca94d133 100644
--- a/fs/btrfs/free-space-tree.c
+++ b/fs/btrfs/free-space-tree.c
@@ -1150,6 +1150,7 @@ int btrfs_create_free_space_tree(struct btrfs_fs_info *fs_info)
return PTR_ERR(trans);
set_bit(BTRFS_FS_CREATING_FREE_SPACE_TREE, &fs_info->flags);
+ set_bit(BTRFS_FS_FREE_SPACE_TREE_UNTRUSTED, &fs_info->flags);
free_space_root = btrfs_create_tree(trans,
BTRFS_FREE_SPACE_TREE_OBJECTID);
if (IS_ERR(free_space_root)) {
@@ -1171,11 +1172,18 @@ int btrfs_create_free_space_tree(struct btrfs_fs_info *fs_info)
btrfs_set_fs_compat_ro(fs_info, FREE_SPACE_TREE);
btrfs_set_fs_compat_ro(fs_info, FREE_SPACE_TREE_VALID);
clear_bit(BTRFS_FS_CREATING_FREE_SPACE_TREE, &fs_info->flags);
+ ret = btrfs_commit_transaction(trans);
- return btrfs_commit_transaction(trans);
+ /*
+ * Now that we've committed the transaction any reading of our commit
+ * root will be safe, so we can cache from the free space tree now.
+ */
+ clear_bit(BTRFS_FS_FREE_SPACE_TREE_UNTRUSTED, &fs_info->flags);
+ return ret;
abort:
clear_bit(BTRFS_FS_CREATING_FREE_SPACE_TREE, &fs_info->flags);
+ clear_bit(BTRFS_FS_FREE_SPACE_TREE_UNTRUSTED, &fs_info->flags);
btrfs_abort_transaction(trans, ret);
btrfs_end_transaction(trans);
return ret;
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 070716650df8..a8e0a6b038d3 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -9390,7 +9390,8 @@ static struct btrfs_delalloc_work *btrfs_alloc_delalloc_work(struct inode *inode
* some fairly slow code that needs optimization. This walks the list
* of all the inodes with pending delalloc and forces them to disk.
*/
-static int start_delalloc_inodes(struct btrfs_root *root, u64 *nr, bool snapshot,
+static int start_delalloc_inodes(struct btrfs_root *root,
+ struct writeback_control *wbc, bool snapshot,
bool in_reclaim_context)
{
struct btrfs_inode *binode;
@@ -9399,6 +9400,7 @@ static int start_delalloc_inodes(struct btrfs_root *root, u64 *nr, bool snapshot
struct list_head works;
struct list_head splice;
int ret = 0;
+ bool full_flush = wbc->nr_to_write == LONG_MAX;
INIT_LIST_HEAD(&works);
INIT_LIST_HEAD(&splice);
@@ -9427,18 +9429,24 @@ static int start_delalloc_inodes(struct btrfs_root *root, u64 *nr, bool snapshot
if (snapshot)
set_bit(BTRFS_INODE_SNAPSHOT_FLUSH,
&binode->runtime_flags);
- work = btrfs_alloc_delalloc_work(inode);
- if (!work) {
- iput(inode);
- ret = -ENOMEM;
- goto out;
- }
- list_add_tail(&work->list, &works);
- btrfs_queue_work(root->fs_info->flush_workers,
- &work->work);
- if (*nr != U64_MAX) {
- (*nr)--;
- if (*nr == 0)
+ if (full_flush) {
+ work = btrfs_alloc_delalloc_work(inode);
+ if (!work) {
+ iput(inode);
+ ret = -ENOMEM;
+ goto out;
+ }
+ list_add_tail(&work->list, &works);
+ btrfs_queue_work(root->fs_info->flush_workers,
+ &work->work);
+ } else {
+ ret = sync_inode(inode, wbc);
+ if (!ret &&
+ test_bit(BTRFS_INODE_HAS_ASYNC_EXTENT,
+ &BTRFS_I(inode)->runtime_flags))
+ ret = sync_inode(inode, wbc);
+ btrfs_add_delayed_iput(inode);
+ if (ret || wbc->nr_to_write <= 0)
goto out;
}
cond_resched();
@@ -9464,18 +9472,29 @@ out:
int btrfs_start_delalloc_snapshot(struct btrfs_root *root)
{
+ struct writeback_control wbc = {
+ .nr_to_write = LONG_MAX,
+ .sync_mode = WB_SYNC_NONE,
+ .range_start = 0,
+ .range_end = LLONG_MAX,
+ };
struct btrfs_fs_info *fs_info = root->fs_info;
- u64 nr = U64_MAX;
if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state))
return -EROFS;
- return start_delalloc_inodes(root, &nr, true, false);
+ return start_delalloc_inodes(root, &wbc, true, false);
}
int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, u64 nr,
bool in_reclaim_context)
{
+ struct writeback_control wbc = {
+ .nr_to_write = (nr == U64_MAX) ? LONG_MAX : (unsigned long)nr,
+ .sync_mode = WB_SYNC_NONE,
+ .range_start = 0,
+ .range_end = LLONG_MAX,
+ };
struct btrfs_root *root;
struct list_head splice;
int ret;
@@ -9489,6 +9508,13 @@ int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, u64 nr,
spin_lock(&fs_info->delalloc_root_lock);
list_splice_init(&fs_info->delalloc_roots, &splice);
while (!list_empty(&splice) && nr) {
+ /*
+ * Reset nr_to_write here so we know that we're doing a full
+ * flush.
+ */
+ if (nr == U64_MAX)
+ wbc.nr_to_write = LONG_MAX;
+
root = list_first_entry(&splice, struct btrfs_root,
delalloc_root);
root = btrfs_grab_root(root);
@@ -9497,9 +9523,9 @@ int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, u64 nr,
&fs_info->delalloc_roots);
spin_unlock(&fs_info->delalloc_root_lock);
- ret = start_delalloc_inodes(root, &nr, false, in_reclaim_context);
+ ret = start_delalloc_inodes(root, &wbc, false, in_reclaim_context);
btrfs_put_root(root);
- if (ret < 0)
+ if (ret < 0 || wbc.nr_to_write <= 0)
goto out;
spin_lock(&fs_info->delalloc_root_lock);
}
diff --git a/fs/btrfs/print-tree.c b/fs/btrfs/print-tree.c
index fe5e0026129d..aae1027bd76a 100644
--- a/fs/btrfs/print-tree.c
+++ b/fs/btrfs/print-tree.c
@@ -26,22 +26,22 @@ static const struct root_name_map root_map[] = {
{ BTRFS_DATA_RELOC_TREE_OBJECTID, "DATA_RELOC_TREE" },
};
-const char *btrfs_root_name(u64 objectid, char *buf)
+const char *btrfs_root_name(const struct btrfs_key *key, char *buf)
{
int i;
- if (objectid == BTRFS_TREE_RELOC_OBJECTID) {
+ if (key->objectid == BTRFS_TREE_RELOC_OBJECTID) {
snprintf(buf, BTRFS_ROOT_NAME_BUF_LEN,
- "TREE_RELOC offset=%llu", objectid);
+ "TREE_RELOC offset=%llu", key->offset);
return buf;
}
for (i = 0; i < ARRAY_SIZE(root_map); i++) {
- if (root_map[i].id == objectid)
+ if (root_map[i].id == key->objectid)
return root_map[i].name;
}
- snprintf(buf, BTRFS_ROOT_NAME_BUF_LEN, "%llu", objectid);
+ snprintf(buf, BTRFS_ROOT_NAME_BUF_LEN, "%llu", key->objectid);
return buf;
}
diff --git a/fs/btrfs/print-tree.h b/fs/btrfs/print-tree.h
index 78b99385a503..8c3e9319ec4e 100644
--- a/fs/btrfs/print-tree.h
+++ b/fs/btrfs/print-tree.h
@@ -11,6 +11,6 @@
void btrfs_print_leaf(struct extent_buffer *l);
void btrfs_print_tree(struct extent_buffer *c, bool follow);
-const char *btrfs_root_name(u64 objectid, char *buf);
+const char *btrfs_root_name(const struct btrfs_key *key, char *buf);
#endif
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 19b7db8b2117..df63ef64c5c0 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -2975,11 +2975,16 @@ static int delete_v1_space_cache(struct extent_buffer *leaf,
return 0;
for (i = 0; i < btrfs_header_nritems(leaf); i++) {
+ u8 type;
+
btrfs_item_key_to_cpu(leaf, &key, i);
if (key.type != BTRFS_EXTENT_DATA_KEY)
continue;
ei = btrfs_item_ptr(leaf, i, struct btrfs_file_extent_item);
- if (btrfs_file_extent_type(leaf, ei) == BTRFS_FILE_EXTENT_REG &&
+ type = btrfs_file_extent_type(leaf, ei);
+
+ if ((type == BTRFS_FILE_EXTENT_REG ||
+ type == BTRFS_FILE_EXTENT_PREALLOC) &&
btrfs_file_extent_disk_bytenr(leaf, ei) == data_bytenr) {
found = true;
space_cache_ino = key.objectid;
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index ae97f4dbaff3..78a35374d492 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -5512,6 +5512,21 @@ static int clone_range(struct send_ctx *sctx,
break;
offset += clone_len;
clone_root->offset += clone_len;
+
+ /*
+ * If we are cloning from the file we are currently processing,
+ * and using the send root as the clone root, we must stop once
+ * the current clone offset reaches the current eof of the file
+ * at the receiver, otherwise we would issue an invalid clone
+ * operation (source range going beyond eof) and cause the
+ * receiver to fail. So if we reach the current eof, bail out
+ * and fallback to a regular write.
+ */
+ if (clone_root->root == sctx->send_root &&
+ clone_root->ino == sctx->cur_ino &&
+ clone_root->offset >= sctx->cur_inode_next_write_offset)
+ break;
+
data_offset += clone_len;
next:
path->slots[0]++;
diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c
index 67e55c5479b8..e8347461c8dd 100644
--- a/fs/btrfs/space-info.c
+++ b/fs/btrfs/space-info.c
@@ -532,7 +532,9 @@ static void shrink_delalloc(struct btrfs_fs_info *fs_info,
loops = 0;
while ((delalloc_bytes || dio_bytes) && loops < 3) {
- btrfs_start_delalloc_roots(fs_info, items, true);
+ u64 nr_pages = min(delalloc_bytes, to_reclaim) >> PAGE_SHIFT;
+
+ btrfs_start_delalloc_roots(fs_info, nr_pages, true);
loops++;
if (wait_ordered && !trans) {
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 8e0f7a1029c6..6af7f2bf92de 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -2265,14 +2265,6 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
btrfs_free_log_root_tree(trans, fs_info);
/*
- * commit_fs_roots() can call btrfs_save_ino_cache(), which generates
- * new delayed refs. Must handle them or qgroup can be wrong.
- */
- ret = btrfs_run_delayed_refs(trans, (unsigned long)-1);
- if (ret)
- goto unlock_tree_log;
-
- /*
* Since fs roots are all committed, we can get a quite accurate
* new_roots. So let's do quota accounting.
*/
diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c
index 028e733e42f3..582061c7b547 100644
--- a/fs/btrfs/tree-checker.c
+++ b/fs/btrfs/tree-checker.c
@@ -760,6 +760,7 @@ int btrfs_check_chunk_valid(struct extent_buffer *leaf,
{
struct btrfs_fs_info *fs_info = leaf->fs_info;
u64 length;
+ u64 chunk_end;
u64 stripe_len;
u16 num_stripes;
u16 sub_stripes;
@@ -814,6 +815,12 @@ int btrfs_check_chunk_valid(struct extent_buffer *leaf,
"invalid chunk length, have %llu", length);
return -EUCLEAN;
}
+ if (unlikely(check_add_overflow(logical, length, &chunk_end))) {
+ chunk_err(leaf, chunk, logical,
+"invalid chunk logical start and length, have logical start %llu length %llu",
+ logical, length);
+ return -EUCLEAN;
+ }
if (unlikely(!is_power_of_2(stripe_len) || stripe_len != BTRFS_STRIPE_LEN)) {
chunk_err(leaf, chunk, logical,
"invalid chunk stripe length: %llu",
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index b62be84833e9..d6c24c8ad749 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -433,7 +433,7 @@ static struct btrfs_device *__alloc_device(struct btrfs_fs_info *fs_info)
atomic_set(&dev->reada_in_flight, 0);
atomic_set(&dev->dev_stats_ccnt, 0);
- btrfs_device_data_ordered_init(dev, fs_info);
+ btrfs_device_data_ordered_init(dev);
INIT_RADIX_TREE(&dev->reada_zones, GFP_NOFS & ~__GFP_DIRECT_RECLAIM);
INIT_RADIX_TREE(&dev->reada_extents, GFP_NOFS & ~__GFP_DIRECT_RECLAIM);
extent_io_tree_init(fs_info, &dev->alloc_state,
@@ -4317,6 +4317,8 @@ int btrfs_recover_balance(struct btrfs_fs_info *fs_info)
btrfs_warn(fs_info,
"balance: cannot set exclusive op status, resume manually");
+ btrfs_release_path(path);
+
mutex_lock(&fs_info->balance_mutex);
BUG_ON(fs_info->balance_ctl);
spin_lock(&fs_info->balance_lock);
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 1997a4649a66..c43663d9c22e 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -39,10 +39,10 @@ struct btrfs_io_geometry {
#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
#include <linux/seqlock.h>
#define __BTRFS_NEED_DEVICE_DATA_ORDERED
-#define btrfs_device_data_ordered_init(device, info) \
- seqcount_mutex_init(&device->data_seqcount, &info->chunk_mutex)
+#define btrfs_device_data_ordered_init(device) \
+ seqcount_init(&device->data_seqcount)
#else
-#define btrfs_device_data_ordered_init(device, info) do { } while (0)
+#define btrfs_device_data_ordered_init(device) do { } while (0)
#endif
#define BTRFS_DEV_STATE_WRITEABLE (0)
@@ -76,8 +76,7 @@ struct btrfs_device {
blk_status_t last_flush_error;
#ifdef __BTRFS_NEED_DEVICE_DATA_ORDERED
- /* A seqcount_t with associated chunk_mutex (for lockdep) */
- seqcount_mutex_t data_seqcount;
+ seqcount_t data_seqcount;
#endif
/* the internal btrfs device id */
@@ -168,9 +167,11 @@ btrfs_device_get_##name(const struct btrfs_device *dev) \
static inline void \
btrfs_device_set_##name(struct btrfs_device *dev, u64 size) \
{ \
+ preempt_disable(); \
write_seqcount_begin(&dev->data_seqcount); \
dev->name = size; \
write_seqcount_end(&dev->data_seqcount); \
+ preempt_enable(); \
}
#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION)
#define BTRFS_DEVICE_GETSET_FUNCS(name) \
diff --git a/fs/cachefiles/rdwr.c b/fs/cachefiles/rdwr.c
index 8bda092e60c5..e027c718ca01 100644
--- a/fs/cachefiles/rdwr.c
+++ b/fs/cachefiles/rdwr.c
@@ -413,7 +413,6 @@ int cachefiles_read_or_alloc_page(struct fscache_retrieval *op,
inode = d_backing_inode(object->backer);
ASSERT(S_ISREG(inode->i_mode));
- ASSERT(inode->i_mapping->a_ops->readpages);
/* calculate the shift required to use bmap */
shift = PAGE_SHIFT - inode->i_sb->s_blocksize_bits;
@@ -713,7 +712,6 @@ int cachefiles_read_or_alloc_pages(struct fscache_retrieval *op,
inode = d_backing_inode(object->backer);
ASSERT(S_ISREG(inode->i_mode));
- ASSERT(inode->i_mapping->a_ops->readpages);
/* calculate the shift required to use bmap */
shift = PAGE_SHIFT - inode->i_sb->s_blocksize_bits;
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 840587037b59..d87bd852ed96 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -5038,7 +5038,7 @@ bad:
return;
}
-static struct ceph_connection *con_get(struct ceph_connection *con)
+static struct ceph_connection *mds_get_con(struct ceph_connection *con)
{
struct ceph_mds_session *s = con->private;
@@ -5047,7 +5047,7 @@ static struct ceph_connection *con_get(struct ceph_connection *con)
return NULL;
}
-static void con_put(struct ceph_connection *con)
+static void mds_put_con(struct ceph_connection *con)
{
struct ceph_mds_session *s = con->private;
@@ -5058,7 +5058,7 @@ static void con_put(struct ceph_connection *con)
* if the client is unresponsive for long enough, the mds will kill
* the session entirely.
*/
-static void peer_reset(struct ceph_connection *con)
+static void mds_peer_reset(struct ceph_connection *con)
{
struct ceph_mds_session *s = con->private;
struct ceph_mds_client *mdsc = s->s_mdsc;
@@ -5067,7 +5067,7 @@ static void peer_reset(struct ceph_connection *con)
send_mds_reconnect(mdsc, s);
}
-static void dispatch(struct ceph_connection *con, struct ceph_msg *msg)
+static void mds_dispatch(struct ceph_connection *con, struct ceph_msg *msg)
{
struct ceph_mds_session *s = con->private;
struct ceph_mds_client *mdsc = s->s_mdsc;
@@ -5125,8 +5125,8 @@ out:
* Note: returned pointer is the address of a structure that's
* managed separately. Caller must *not* attempt to free it.
*/
-static struct ceph_auth_handshake *get_authorizer(struct ceph_connection *con,
- int *proto, int force_new)
+static struct ceph_auth_handshake *
+mds_get_authorizer(struct ceph_connection *con, int *proto, int force_new)
{
struct ceph_mds_session *s = con->private;
struct ceph_mds_client *mdsc = s->s_mdsc;
@@ -5142,7 +5142,7 @@ static struct ceph_auth_handshake *get_authorizer(struct ceph_connection *con,
return auth;
}
-static int add_authorizer_challenge(struct ceph_connection *con,
+static int mds_add_authorizer_challenge(struct ceph_connection *con,
void *challenge_buf, int challenge_buf_len)
{
struct ceph_mds_session *s = con->private;
@@ -5153,7 +5153,7 @@ static int add_authorizer_challenge(struct ceph_connection *con,
challenge_buf, challenge_buf_len);
}
-static int verify_authorizer_reply(struct ceph_connection *con)
+static int mds_verify_authorizer_reply(struct ceph_connection *con)
{
struct ceph_mds_session *s = con->private;
struct ceph_mds_client *mdsc = s->s_mdsc;
@@ -5165,7 +5165,7 @@ static int verify_authorizer_reply(struct ceph_connection *con)
NULL, NULL, NULL, NULL);
}
-static int invalidate_authorizer(struct ceph_connection *con)
+static int mds_invalidate_authorizer(struct ceph_connection *con)
{
struct ceph_mds_session *s = con->private;
struct ceph_mds_client *mdsc = s->s_mdsc;
@@ -5288,15 +5288,15 @@ static int mds_check_message_signature(struct ceph_msg *msg)
}
static const struct ceph_connection_operations mds_con_ops = {
- .get = con_get,
- .put = con_put,
- .dispatch = dispatch,
- .get_authorizer = get_authorizer,
- .add_authorizer_challenge = add_authorizer_challenge,
- .verify_authorizer_reply = verify_authorizer_reply,
- .invalidate_authorizer = invalidate_authorizer,
- .peer_reset = peer_reset,
+ .get = mds_get_con,
+ .put = mds_put_con,
.alloc_msg = mds_alloc_msg,
+ .dispatch = mds_dispatch,
+ .peer_reset = mds_peer_reset,
+ .get_authorizer = mds_get_authorizer,
+ .add_authorizer_challenge = mds_add_authorizer_challenge,
+ .verify_authorizer_reply = mds_verify_authorizer_reply,
+ .invalidate_authorizer = mds_invalidate_authorizer,
.sign_message = mds_sign_message,
.check_message_signature = mds_check_message_signature,
.get_auth_request = mds_get_auth_request,
diff --git a/fs/cifs/cifs_dfs_ref.c b/fs/cifs/cifs_dfs_ref.c
index e4c6ae47a796..6b1ce4efb591 100644
--- a/fs/cifs/cifs_dfs_ref.c
+++ b/fs/cifs/cifs_dfs_ref.c
@@ -133,8 +133,9 @@ cifs_build_devname(char *nodename, const char *prepath)
* Caller is responsible for freeing returned value if it is not error.
*/
char *cifs_compose_mount_options(const char *sb_mountdata,
- const char *fullpath,
- const struct dfs_info3_param *ref)
+ const char *fullpath,
+ const struct dfs_info3_param *ref,
+ char **devname)
{
int rc;
char *name;
@@ -231,7 +232,10 @@ char *cifs_compose_mount_options(const char *sb_mountdata,
strcat(mountdata, "ip=");
strcat(mountdata, srvIP);
- kfree(name);
+ if (devname)
+ *devname = name;
+ else
+ kfree(name);
/*cifs_dbg(FYI, "%s: parent mountdata: %s\n", __func__, sb_mountdata);*/
/*cifs_dbg(FYI, "%s: submount mountdata: %s\n", __func__, mountdata );*/
@@ -278,7 +282,7 @@ static struct vfsmount *cifs_dfs_do_mount(struct dentry *mntpt,
/* strip first '\' from fullpath */
mountdata = cifs_compose_mount_options(cifs_sb->ctx->mount_options,
- fullpath + 1, NULL);
+ fullpath + 1, NULL, NULL);
if (IS_ERR(mountdata)) {
kfree(devname);
return (struct vfsmount *)mountdata;
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index ce0d0037fd0a..e46da536ed33 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -822,7 +822,7 @@ cifs_smb3_do_mount(struct file_system_type *fs_type,
goto out;
}
- rc = cifs_setup_volume_info(cifs_sb->ctx);
+ rc = cifs_setup_volume_info(cifs_sb->ctx, NULL, old_ctx->UNC);
if (rc) {
root = ERR_PTR(rc);
goto out;
diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h
index 340ff81ee87b..32f7a013402e 100644
--- a/fs/cifs/cifsproto.h
+++ b/fs/cifs/cifsproto.h
@@ -78,7 +78,8 @@ extern char *cifs_build_path_to_root(struct smb3_fs_context *ctx,
int add_treename);
extern char *build_wildcard_path_from_dentry(struct dentry *direntry);
extern char *cifs_compose_mount_options(const char *sb_mountdata,
- const char *fullpath, const struct dfs_info3_param *ref);
+ const char *fullpath, const struct dfs_info3_param *ref,
+ char **devname);
/* extern void renew_parental_timestamps(struct dentry *direntry);*/
extern struct mid_q_entry *AllocMidQEntry(const struct smb_hdr *smb_buffer,
struct TCP_Server_Info *server);
@@ -89,6 +90,7 @@ extern void cifs_wake_up_task(struct mid_q_entry *mid);
extern int cifs_handle_standard(struct TCP_Server_Info *server,
struct mid_q_entry *mid);
extern int smb3_parse_devname(const char *devname, struct smb3_fs_context *ctx);
+extern int smb3_parse_opt(const char *options, const char *key, char **val);
extern bool cifs_match_ipaddr(struct sockaddr *srcaddr, struct sockaddr *rhs);
extern int cifs_discard_remaining_data(struct TCP_Server_Info *server);
extern int cifs_call_async(struct TCP_Server_Info *server,
@@ -549,7 +551,7 @@ extern int SMBencrypt(unsigned char *passwd, const unsigned char *c8,
unsigned char *p24);
extern int
-cifs_setup_volume_info(struct smb3_fs_context *ctx);
+cifs_setup_volume_info(struct smb3_fs_context *ctx, const char *mntopts, const char *devname);
extern struct TCP_Server_Info *
cifs_find_tcp_session(struct smb3_fs_context *ctx);
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index b9df85506938..10fe6d6d2dee 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -2195,7 +2195,7 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb3_fs_context *ctx)
if (ses->server->capabilities & SMB2_GLOBAL_CAP_DIRECTORY_LEASING)
tcon->nohandlecache = ctx->nohandlecache;
else
- tcon->nohandlecache = 1;
+ tcon->nohandlecache = true;
tcon->nodelete = ctx->nodelete;
tcon->local_lease = ctx->local_lease;
INIT_LIST_HEAD(&tcon->pending_opens);
@@ -2628,7 +2628,7 @@ void reset_cifs_unix_caps(unsigned int xid, struct cifs_tcon *tcon,
} else if (ctx)
tcon->unix_ext = 1; /* Unix Extensions supported */
- if (tcon->unix_ext == 0) {
+ if (!tcon->unix_ext) {
cifs_dbg(FYI, "Unix extensions disabled so not set on reconnect\n");
return;
}
@@ -2972,17 +2972,20 @@ expand_dfs_referral(const unsigned int xid, struct cifs_ses *ses,
rc = dfs_cache_find(xid, ses, cifs_sb->local_nls, cifs_remap(cifs_sb),
ref_path, &referral, NULL);
if (!rc) {
+ char *fake_devname = NULL;
+
mdata = cifs_compose_mount_options(cifs_sb->ctx->mount_options,
- full_path + 1, &referral);
+ full_path + 1, &referral,
+ &fake_devname);
free_dfs_info_param(&referral);
if (IS_ERR(mdata)) {
rc = PTR_ERR(mdata);
mdata = NULL;
} else {
- smb3_cleanup_fs_context_contents(ctx);
- rc = cifs_setup_volume_info(ctx);
+ rc = cifs_setup_volume_info(ctx, mdata, fake_devname);
}
+ kfree(fake_devname);
kfree(cifs_sb->ctx->mount_options);
cifs_sb->ctx->mount_options = mdata;
}
@@ -3036,6 +3039,7 @@ static int setup_dfs_tgt_conn(const char *path, const char *full_path,
struct dfs_info3_param ref = {0};
char *mdata = NULL;
struct smb3_fs_context fake_ctx = {NULL};
+ char *fake_devname = NULL;
cifs_dbg(FYI, "%s: dfs path: %s\n", __func__, path);
@@ -3044,16 +3048,18 @@ static int setup_dfs_tgt_conn(const char *path, const char *full_path,
return rc;
mdata = cifs_compose_mount_options(cifs_sb->ctx->mount_options,
- full_path + 1, &ref);
+ full_path + 1, &ref,
+ &fake_devname);
free_dfs_info_param(&ref);
if (IS_ERR(mdata)) {
rc = PTR_ERR(mdata);
mdata = NULL;
} else
- rc = cifs_setup_volume_info(&fake_ctx);
+ rc = cifs_setup_volume_info(&fake_ctx, mdata, fake_devname);
kfree(mdata);
+ kfree(fake_devname);
if (!rc) {
/*
@@ -3122,10 +3128,24 @@ static int do_dfs_failover(const char *path, const char *full_path, struct cifs_
* we should pass a clone of the original context?
*/
int
-cifs_setup_volume_info(struct smb3_fs_context *ctx)
+cifs_setup_volume_info(struct smb3_fs_context *ctx, const char *mntopts, const char *devname)
{
int rc = 0;
+ smb3_parse_devname(devname, ctx);
+
+ if (mntopts) {
+ char *ip;
+
+ cifs_dbg(FYI, "%s: mntopts=%s\n", __func__, mntopts);
+ rc = smb3_parse_opt(mntopts, "ip", &ip);
+ if (!rc && !cifs_convert_address((struct sockaddr *)&ctx->dstaddr, ip,
+ strlen(ip))) {
+ cifs_dbg(VFS, "%s: failed to convert ip address\n", __func__);
+ return -EINVAL;
+ }
+ }
+
if (ctx->nullauth) {
cifs_dbg(FYI, "Anonymous login\n");
kfree(ctx->username);
@@ -3740,7 +3760,7 @@ cifs_setup_session(const unsigned int xid, struct cifs_ses *ses,
if (!ses->binding) {
ses->capabilities = server->capabilities;
- if (linuxExtEnabled == 0)
+ if (!linuxExtEnabled)
ses->capabilities &= (~server->vals->cap_unix);
if (ses->auth_key.response) {
diff --git a/fs/cifs/dfs_cache.c b/fs/cifs/dfs_cache.c
index 6ad6ba5f6ebe..4950ab0486ae 100644
--- a/fs/cifs/dfs_cache.c
+++ b/fs/cifs/dfs_cache.c
@@ -1260,7 +1260,8 @@ void dfs_cache_del_vol(const char *fullpath)
vi = find_vol(fullpath);
spin_unlock(&vol_list_lock);
- kref_put(&vi->refcnt, vol_release);
+ if (!IS_ERR(vi))
+ kref_put(&vi->refcnt, vol_release);
}
/**
@@ -1416,7 +1417,7 @@ static struct cifs_ses *find_root_ses(struct vol_info *vi,
int rc;
struct cache_entry *ce;
struct dfs_info3_param ref = {0};
- char *mdata = NULL;
+ char *mdata = NULL, *devname = NULL;
struct TCP_Server_Info *server;
struct cifs_ses *ses;
struct smb3_fs_context ctx = {NULL};
@@ -1443,7 +1444,8 @@ static struct cifs_ses *find_root_ses(struct vol_info *vi,
up_read(&htable_rw_lock);
- mdata = cifs_compose_mount_options(vi->mntdata, rpath, &ref);
+ mdata = cifs_compose_mount_options(vi->mntdata, rpath, &ref,
+ &devname);
free_dfs_info_param(&ref);
if (IS_ERR(mdata)) {
@@ -1452,7 +1454,7 @@ static struct cifs_ses *find_root_ses(struct vol_info *vi,
goto out;
}
- rc = cifs_setup_volume_info(&ctx);
+ rc = cifs_setup_volume_info(&ctx, NULL, devname);
if (rc) {
ses = ERR_PTR(rc);
@@ -1471,6 +1473,7 @@ out:
smb3_cleanup_fs_context_contents(&ctx);
kfree(mdata);
kfree(rpath);
+ kfree(devname);
return ses;
}
diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c
index 68900f1629bf..97ac363b5df1 100644
--- a/fs/cifs/dir.c
+++ b/fs/cifs/dir.c
@@ -737,6 +737,7 @@ static int
cifs_d_revalidate(struct dentry *direntry, unsigned int flags)
{
struct inode *inode;
+ int rc;
if (flags & LOOKUP_RCU)
return -ECHILD;
@@ -746,8 +747,25 @@ cifs_d_revalidate(struct dentry *direntry, unsigned int flags)
if ((flags & LOOKUP_REVAL) && !CIFS_CACHE_READ(CIFS_I(inode)))
CIFS_I(inode)->time = 0; /* force reval */
- if (cifs_revalidate_dentry(direntry))
- return 0;
+ rc = cifs_revalidate_dentry(direntry);
+ if (rc) {
+ cifs_dbg(FYI, "cifs_revalidate_dentry failed with rc=%d", rc);
+ switch (rc) {
+ case -ENOENT:
+ case -ESTALE:
+ /*
+ * Those errors mean the dentry is invalid
+ * (file was deleted or recreated)
+ */
+ return 0;
+ default:
+ /*
+ * Otherwise some unexpected error happened
+ * report it as-is to VFS layer
+ */
+ return rc;
+ }
+ }
else {
/*
* If the inode wasn't known to be a dfs entry when
diff --git a/fs/cifs/fs_context.c b/fs/cifs/fs_context.c
index 0afccbbed2e6..5111aadfdb6b 100644
--- a/fs/cifs/fs_context.c
+++ b/fs/cifs/fs_context.c
@@ -175,8 +175,10 @@ const struct fs_parameter_spec smb3_fs_parameters[] = {
fsparam_flag_no("exec", Opt_ignore),
fsparam_flag_no("dev", Opt_ignore),
fsparam_flag_no("mand", Opt_ignore),
+ fsparam_flag_no("auto", Opt_ignore),
fsparam_string("cred", Opt_ignore),
fsparam_string("credentials", Opt_ignore),
+ fsparam_string("prefixpath", Opt_ignore),
{}
};
@@ -303,8 +305,6 @@ do { \
int
smb3_fs_context_dup(struct smb3_fs_context *new_ctx, struct smb3_fs_context *ctx)
{
- int rc = 0;
-
memcpy(new_ctx, ctx, sizeof(*ctx));
new_ctx->prepath = NULL;
new_ctx->mount_options = NULL;
@@ -327,7 +327,7 @@ smb3_fs_context_dup(struct smb3_fs_context *new_ctx, struct smb3_fs_context *ctx
DUP_CTX_STR(nodename);
DUP_CTX_STR(iocharset);
- return rc;
+ return 0;
}
static int
@@ -401,6 +401,37 @@ cifs_parse_smb_version(char *value, struct smb3_fs_context *ctx, bool is_smb3)
return 0;
}
+int smb3_parse_opt(const char *options, const char *key, char **val)
+{
+ int rc = -ENOENT;
+ char *opts, *orig, *p;
+
+ orig = opts = kstrdup(options, GFP_KERNEL);
+ if (!opts)
+ return -ENOMEM;
+
+ while ((p = strsep(&opts, ","))) {
+ char *nval;
+
+ if (!*p)
+ continue;
+ if (strncasecmp(p, key, strlen(key)))
+ continue;
+ nval = strchr(p, '=');
+ if (nval) {
+ if (nval == p)
+ continue;
+ *nval++ = 0;
+ *val = kstrndup(nval, strlen(nval), GFP_KERNEL);
+ rc = !*val ? -ENOMEM : 0;
+ goto out;
+ }
+ }
+out:
+ kfree(orig);
+ return rc;
+}
+
/*
* Parse a devname into substrings and populate the ctx->UNC and ctx->prepath
* fields with the result. Returns 0 on success and an error otherwise
@@ -533,7 +564,7 @@ static int smb3_fs_context_validate(struct fs_context *fc)
if (ctx->rdma && ctx->vals->protocol_id < SMB30_PROT_ID) {
cifs_dbg(VFS, "SMB Direct requires Version >=3.0\n");
- return -1;
+ return -EOPNOTSUPP;
}
#ifndef CONFIG_KEYS
@@ -556,7 +587,7 @@ static int smb3_fs_context_validate(struct fs_context *fc)
/* make sure UNC has a share name */
if (strlen(ctx->UNC) < 3 || !strchr(ctx->UNC + 3, '\\')) {
cifs_dbg(VFS, "Malformed UNC. Unable to find share name.\n");
- return -1;
+ return -ENOENT;
}
if (!ctx->got_ip) {
@@ -570,7 +601,7 @@ static int smb3_fs_context_validate(struct fs_context *fc)
if (!cifs_convert_address((struct sockaddr *)&ctx->dstaddr,
&ctx->UNC[2], len)) {
pr_err("Unable to determine destination address\n");
- return -1;
+ return -EHOSTUNREACH;
}
}
@@ -1265,7 +1296,7 @@ static int smb3_fs_context_parse_param(struct fs_context *fc,
return 0;
cifs_parse_mount_err:
- return 1;
+ return -EINVAL;
}
int smb3_init_fs_context(struct fs_context *fc)
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 067eb44c7baa..794fc3b68b4f 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -3248,7 +3248,7 @@ close_exit:
free_rsp_buf(resp_buftype, rsp);
/* retry close in a worker thread if this one is interrupted */
- if (rc == -EINTR) {
+ if (is_interrupt_error(rc)) {
int tmp_rc;
tmp_rc = smb2_handle_cancelled_close(tcon, persistent_fid,
diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h
index 204a622b89ed..a5a9e33c0d73 100644
--- a/fs/cifs/smb2pdu.h
+++ b/fs/cifs/smb2pdu.h
@@ -286,7 +286,7 @@ struct smb2_negotiate_req {
__le32 NegotiateContextOffset; /* SMB3.1.1 only. MBZ earlier */
__le16 NegotiateContextCount; /* SMB3.1.1 only. MBZ earlier */
__le16 Reserved2;
- __le16 Dialects[1]; /* One dialect (vers=) at a time for now */
+ __le16 Dialects[4]; /* BB expand this if autonegotiate > 4 dialects */
} __packed;
/* Dialects */
@@ -424,7 +424,7 @@ struct smb2_rdma_transform_capabilities_context {
__le16 TransformCount;
__u16 Reserved1;
__u32 Reserved2;
- __le16 RDMATransformIds[1];
+ __le16 RDMATransformIds[];
} __packed;
/* Signing algorithms */
diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c
index e9abb41aa89b..4a2b836eb017 100644
--- a/fs/cifs/transport.c
+++ b/fs/cifs/transport.c
@@ -338,7 +338,7 @@ __smb_send_rqst(struct TCP_Server_Info *server, int num_rqst,
if (ssocket == NULL)
return -EAGAIN;
- if (signal_pending(current)) {
+ if (fatal_signal_pending(current)) {
cifs_dbg(FYI, "signal pending before send request\n");
return -ERESTARTSYS;
}
@@ -429,7 +429,7 @@ unmask:
if (signal_pending(current) && (total_len != send_length)) {
cifs_dbg(FYI, "signal is pending after attempt to send\n");
- rc = -EINTR;
+ rc = -ERESTARTSYS;
}
/* uncork it */
@@ -666,10 +666,22 @@ wait_for_compound_request(struct TCP_Server_Info *server, int num,
if (*credits < num) {
/*
- * Return immediately if not too many requests in flight since
- * we will likely be stuck on waiting for credits.
+ * If the server is tight on resources or just gives us less
+ * credits for other reasons (e.g. requests are coming out of
+ * order and the server delays granting more credits until it
+ * processes a missing mid) and we exhausted most available
+ * credits there may be situations when we try to send
+ * a compound request but we don't have enough credits. At this
+ * point the client needs to decide if it should wait for
+ * additional credits or fail the request. If at least one
+ * request is in flight there is a high probability that the
+ * server will return enough credits to satisfy this compound
+ * request.
+ *
+ * Return immediately if no requests in flight since we will be
+ * stuck on waiting for credits.
*/
- if (server->in_flight < num - *credits) {
+ if (server->in_flight == 0) {
spin_unlock(&server->req_lock);
trace_smb3_insufficient_credits(server->CurrentMid,
server->hostname, scredits, sin_flight);
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index e23752d9a79f..58d0f7187997 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -1016,15 +1016,19 @@ ecryptfs_setxattr(struct dentry *dentry, struct inode *inode,
{
int rc;
struct dentry *lower_dentry;
+ struct inode *lower_inode;
lower_dentry = ecryptfs_dentry_to_lower(dentry);
- if (!(d_inode(lower_dentry)->i_opflags & IOP_XATTR)) {
+ lower_inode = d_inode(lower_dentry);
+ if (!(lower_inode->i_opflags & IOP_XATTR)) {
rc = -EOPNOTSUPP;
goto out;
}
- rc = vfs_setxattr(lower_dentry, name, value, size, flags);
+ inode_lock(lower_inode);
+ rc = __vfs_setxattr_locked(lower_dentry, name, value, size, flags, NULL);
+ inode_unlock(lower_inode);
if (!rc && inode)
- fsstack_copy_attr_all(inode, d_inode(lower_dentry));
+ fsstack_copy_attr_all(inode, lower_inode);
out:
return rc;
}
diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c
index 1a0a827a7f34..be799040a415 100644
--- a/fs/ext4/ext4_jbd2.c
+++ b/fs/ext4/ext4_jbd2.c
@@ -372,20 +372,3 @@ int __ext4_handle_dirty_metadata(const char *where, unsigned int line,
}
return err;
}
-
-int __ext4_handle_dirty_super(const char *where, unsigned int line,
- handle_t *handle, struct super_block *sb)
-{
- struct buffer_head *bh = EXT4_SB(sb)->s_sbh;
- int err = 0;
-
- ext4_superblock_csum_set(sb);
- if (ext4_handle_valid(handle)) {
- err = jbd2_journal_dirty_metadata(handle, bh);
- if (err)
- ext4_journal_abort_handle(where, line, __func__,
- bh, handle, err);
- } else
- mark_buffer_dirty(bh);
- return err;
-}
diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h
index a124c68b0c75..0d2fa423b7ad 100644
--- a/fs/ext4/ext4_jbd2.h
+++ b/fs/ext4/ext4_jbd2.h
@@ -244,9 +244,6 @@ int __ext4_handle_dirty_metadata(const char *where, unsigned int line,
handle_t *handle, struct inode *inode,
struct buffer_head *bh);
-int __ext4_handle_dirty_super(const char *where, unsigned int line,
- handle_t *handle, struct super_block *sb);
-
#define ext4_journal_get_write_access(handle, bh) \
__ext4_journal_get_write_access(__func__, __LINE__, (handle), (bh))
#define ext4_forget(handle, is_metadata, inode, bh, block_nr) \
@@ -257,8 +254,6 @@ int __ext4_handle_dirty_super(const char *where, unsigned int line,
#define ext4_handle_dirty_metadata(handle, inode, bh) \
__ext4_handle_dirty_metadata(__func__, __LINE__, (handle), (inode), \
(bh))
-#define ext4_handle_dirty_super(handle, sb) \
- __ext4_handle_dirty_super(__func__, __LINE__, (handle), (sb))
handle_t *__ext4_journal_start_sb(struct super_block *sb, unsigned int line,
int type, int blocks, int rsv_blocks,
diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c
index 4fcc21c25e79..0a14a7c87bf8 100644
--- a/fs/ext4/fast_commit.c
+++ b/fs/ext4/fast_commit.c
@@ -604,13 +604,13 @@ void ext4_fc_track_range(handle_t *handle, struct inode *inode, ext4_lblk_t star
trace_ext4_fc_track_range(inode, start, end, ret);
}
-static void ext4_fc_submit_bh(struct super_block *sb)
+static void ext4_fc_submit_bh(struct super_block *sb, bool is_tail)
{
int write_flags = REQ_SYNC;
struct buffer_head *bh = EXT4_SB(sb)->s_fc_bh;
- /* TODO: REQ_FUA | REQ_PREFLUSH is unnecessarily expensive. */
- if (test_opt(sb, BARRIER))
+ /* Add REQ_FUA | REQ_PREFLUSH only its tail */
+ if (test_opt(sb, BARRIER) && is_tail)
write_flags |= REQ_FUA | REQ_PREFLUSH;
lock_buffer(bh);
set_buffer_dirty(bh);
@@ -684,7 +684,7 @@ static u8 *ext4_fc_reserve_space(struct super_block *sb, int len, u32 *crc)
*crc = ext4_chksum(sbi, *crc, tl, sizeof(*tl));
if (pad_len > 0)
ext4_fc_memzero(sb, tl + 1, pad_len, crc);
- ext4_fc_submit_bh(sb);
+ ext4_fc_submit_bh(sb, false);
ret = jbd2_fc_get_buf(EXT4_SB(sb)->s_journal, &bh);
if (ret)
@@ -741,7 +741,7 @@ static int ext4_fc_write_tail(struct super_block *sb, u32 crc)
tail.fc_crc = cpu_to_le32(crc);
ext4_fc_memcpy(sb, dst, &tail.fc_crc, sizeof(tail.fc_crc), NULL);
- ext4_fc_submit_bh(sb);
+ ext4_fc_submit_bh(sb, true);
return 0;
}
@@ -1268,7 +1268,7 @@ static void ext4_fc_cleanup(journal_t *journal, int full)
list_splice_init(&sbi->s_fc_dentry_q[FC_Q_STAGING],
&sbi->s_fc_dentry_q[FC_Q_MAIN]);
list_splice_init(&sbi->s_fc_q[FC_Q_STAGING],
- &sbi->s_fc_q[FC_Q_STAGING]);
+ &sbi->s_fc_q[FC_Q_MAIN]);
ext4_clear_mount_flag(sb, EXT4_MF_FC_COMMITTING);
ext4_clear_mount_flag(sb, EXT4_MF_FC_INELIGIBLE);
@@ -1318,14 +1318,14 @@ static int ext4_fc_replay_unlink(struct super_block *sb, struct ext4_fc_tl *tl)
entry.len = darg.dname_len;
inode = ext4_iget(sb, darg.ino, EXT4_IGET_NORMAL);
- if (IS_ERR_OR_NULL(inode)) {
+ if (IS_ERR(inode)) {
jbd_debug(1, "Inode %d not found", darg.ino);
return 0;
}
old_parent = ext4_iget(sb, darg.parent_ino,
EXT4_IGET_NORMAL);
- if (IS_ERR_OR_NULL(old_parent)) {
+ if (IS_ERR(old_parent)) {
jbd_debug(1, "Dir with inode %d not found", darg.parent_ino);
iput(inode);
return 0;
@@ -1410,7 +1410,7 @@ static int ext4_fc_replay_link(struct super_block *sb, struct ext4_fc_tl *tl)
darg.parent_ino, darg.dname_len);
inode = ext4_iget(sb, darg.ino, EXT4_IGET_NORMAL);
- if (IS_ERR_OR_NULL(inode)) {
+ if (IS_ERR(inode)) {
jbd_debug(1, "Inode not found.");
return 0;
}
@@ -1466,10 +1466,11 @@ static int ext4_fc_replay_inode(struct super_block *sb, struct ext4_fc_tl *tl)
trace_ext4_fc_replay(sb, tag, ino, 0, 0);
inode = ext4_iget(sb, ino, EXT4_IGET_NORMAL);
- if (!IS_ERR_OR_NULL(inode)) {
+ if (!IS_ERR(inode)) {
ext4_ext_clear_bb(inode);
iput(inode);
}
+ inode = NULL;
ext4_fc_record_modified_inode(sb, ino);
@@ -1512,7 +1513,7 @@ static int ext4_fc_replay_inode(struct super_block *sb, struct ext4_fc_tl *tl)
/* Given that we just wrote the inode on disk, this SHOULD succeed. */
inode = ext4_iget(sb, ino, EXT4_IGET_NORMAL);
- if (IS_ERR_OR_NULL(inode)) {
+ if (IS_ERR(inode)) {
jbd_debug(1, "Inode not found.");
return -EFSCORRUPTED;
}
@@ -1564,7 +1565,7 @@ static int ext4_fc_replay_create(struct super_block *sb, struct ext4_fc_tl *tl)
goto out;
inode = ext4_iget(sb, darg.ino, EXT4_IGET_NORMAL);
- if (IS_ERR_OR_NULL(inode)) {
+ if (IS_ERR(inode)) {
jbd_debug(1, "inode %d not found.", darg.ino);
inode = NULL;
ret = -EINVAL;
@@ -1577,7 +1578,7 @@ static int ext4_fc_replay_create(struct super_block *sb, struct ext4_fc_tl *tl)
* dot and dot dot dirents are setup properly.
*/
dir = ext4_iget(sb, darg.parent_ino, EXT4_IGET_NORMAL);
- if (IS_ERR_OR_NULL(dir)) {
+ if (IS_ERR(dir)) {
jbd_debug(1, "Dir %d not found.", darg.ino);
goto out;
}
@@ -1653,7 +1654,7 @@ static int ext4_fc_replay_add_range(struct super_block *sb,
inode = ext4_iget(sb, le32_to_cpu(fc_add_ex->fc_ino),
EXT4_IGET_NORMAL);
- if (IS_ERR_OR_NULL(inode)) {
+ if (IS_ERR(inode)) {
jbd_debug(1, "Inode not found.");
return 0;
}
@@ -1777,7 +1778,7 @@ ext4_fc_replay_del_range(struct super_block *sb, struct ext4_fc_tl *tl)
le32_to_cpu(lrange->fc_ino), cur, remaining);
inode = ext4_iget(sb, le32_to_cpu(lrange->fc_ino), EXT4_IGET_NORMAL);
- if (IS_ERR_OR_NULL(inode)) {
+ if (IS_ERR(inode)) {
jbd_debug(1, "Inode %d not found", le32_to_cpu(lrange->fc_ino));
return 0;
}
@@ -1832,7 +1833,7 @@ static void ext4_fc_set_bitmaps_and_counters(struct super_block *sb)
for (i = 0; i < state->fc_modified_inodes_used; i++) {
inode = ext4_iget(sb, state->fc_modified_inodes[i],
EXT4_IGET_NORMAL);
- if (IS_ERR_OR_NULL(inode)) {
+ if (IS_ERR(inode)) {
jbd_debug(1, "Inode %d not found.",
state->fc_modified_inodes[i]);
continue;
@@ -1849,7 +1850,7 @@ static void ext4_fc_set_bitmaps_and_counters(struct super_block *sb)
if (ret > 0) {
path = ext4_find_extent(inode, map.m_lblk, NULL, 0);
- if (!IS_ERR_OR_NULL(path)) {
+ if (!IS_ERR(path)) {
for (j = 0; j < path->p_depth; j++)
ext4_mb_mark_bb(inode->i_sb,
path[j].p_block, 1, 1);
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 3ed8c048fb12..349b27f0dda0 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -809,9 +809,12 @@ static int ext4_sample_last_mounted(struct super_block *sb,
err = ext4_journal_get_write_access(handle, sbi->s_sbh);
if (err)
goto out_journal;
- strlcpy(sbi->s_es->s_last_mounted, cp,
+ lock_buffer(sbi->s_sbh);
+ strncpy(sbi->s_es->s_last_mounted, cp,
sizeof(sbi->s_es->s_last_mounted));
- ext4_handle_dirty_super(handle, sb);
+ ext4_superblock_csum_set(sb);
+ unlock_buffer(sbi->s_sbh);
+ ext4_handle_dirty_metadata(handle, NULL, sbi->s_sbh);
out_journal:
ext4_journal_stop(handle);
out:
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 27946882d4ce..c173c8405856 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -5150,9 +5150,13 @@ static int ext4_do_update_inode(handle_t *handle,
err = ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh);
if (err)
goto out_brelse;
+ lock_buffer(EXT4_SB(sb)->s_sbh);
ext4_set_feature_large_file(sb);
+ ext4_superblock_csum_set(sb);
+ unlock_buffer(EXT4_SB(sb)->s_sbh);
ext4_handle_sync(handle);
- err = ext4_handle_dirty_super(handle, sb);
+ err = ext4_handle_dirty_metadata(handle, NULL,
+ EXT4_SB(sb)->s_sbh);
}
ext4_update_inode_fsync_trans(handle, inode, need_datasync);
out_brelse:
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index 524e13432447..d9665d2f82db 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -1157,7 +1157,10 @@ resizefs_out:
err = ext4_journal_get_write_access(handle, sbi->s_sbh);
if (err)
goto pwsalt_err_journal;
+ lock_buffer(sbi->s_sbh);
generate_random_uuid(sbi->s_es->s_encrypt_pw_salt);
+ ext4_superblock_csum_set(sb);
+ unlock_buffer(sbi->s_sbh);
err = ext4_handle_dirty_metadata(handle, NULL,
sbi->s_sbh);
pwsalt_err_journal:
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index b17a082b7db1..cf652ba3e74d 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -2976,14 +2976,17 @@ int ext4_orphan_add(handle_t *handle, struct inode *inode)
(le32_to_cpu(sbi->s_es->s_inodes_count))) {
/* Insert this inode at the head of the on-disk orphan list */
NEXT_ORPHAN(inode) = le32_to_cpu(sbi->s_es->s_last_orphan);
+ lock_buffer(sbi->s_sbh);
sbi->s_es->s_last_orphan = cpu_to_le32(inode->i_ino);
+ ext4_superblock_csum_set(sb);
+ unlock_buffer(sbi->s_sbh);
dirty = true;
}
list_add(&EXT4_I(inode)->i_orphan, &sbi->s_orphan);
mutex_unlock(&sbi->s_orphan_lock);
if (dirty) {
- err = ext4_handle_dirty_super(handle, sb);
+ err = ext4_handle_dirty_metadata(handle, NULL, sbi->s_sbh);
rc = ext4_mark_iloc_dirty(handle, inode, &iloc);
if (!err)
err = rc;
@@ -3059,9 +3062,12 @@ int ext4_orphan_del(handle_t *handle, struct inode *inode)
mutex_unlock(&sbi->s_orphan_lock);
goto out_brelse;
}
+ lock_buffer(sbi->s_sbh);
sbi->s_es->s_last_orphan = cpu_to_le32(ino_next);
+ ext4_superblock_csum_set(inode->i_sb);
+ unlock_buffer(sbi->s_sbh);
mutex_unlock(&sbi->s_orphan_lock);
- err = ext4_handle_dirty_super(handle, inode->i_sb);
+ err = ext4_handle_dirty_metadata(handle, NULL, sbi->s_sbh);
} else {
struct ext4_iloc iloc2;
struct inode *i_prev =
@@ -3593,9 +3599,6 @@ static int ext4_setent(handle_t *handle, struct ext4_renament *ent,
return retval2;
}
}
- brelse(ent->bh);
- ent->bh = NULL;
-
return retval;
}
@@ -3794,6 +3797,7 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
}
}
+ old_file_type = old.de->file_type;
if (IS_DIRSYNC(old.dir) || IS_DIRSYNC(new.dir))
ext4_handle_sync(handle);
@@ -3821,7 +3825,6 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
force_reread = (new.dir->i_ino == old.dir->i_ino &&
ext4_test_inode_flag(new.dir, EXT4_INODE_INLINE_DATA));
- old_file_type = old.de->file_type;
if (whiteout) {
/*
* Do this before adding a new entry, so the old entry is sure
@@ -3919,15 +3922,19 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
retval = 0;
end_rename:
- brelse(old.dir_bh);
- brelse(old.bh);
- brelse(new.bh);
if (whiteout) {
- if (retval)
+ if (retval) {
+ ext4_setent(handle, &old,
+ old.inode->i_ino, old_file_type);
drop_nlink(whiteout);
+ }
unlock_new_inode(whiteout);
iput(whiteout);
+
}
+ brelse(old.dir_bh);
+ brelse(old.bh);
+ brelse(new.bh);
if (handle)
ext4_journal_stop(handle);
return retval;
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index 928700d57eb6..bd0d185654f3 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -899,8 +899,11 @@ static int add_new_gdb(handle_t *handle, struct inode *inode,
EXT4_SB(sb)->s_gdb_count++;
ext4_kvfree_array_rcu(o_group_desc);
+ lock_buffer(EXT4_SB(sb)->s_sbh);
le16_add_cpu(&es->s_reserved_gdt_blocks, -1);
- err = ext4_handle_dirty_super(handle, sb);
+ ext4_superblock_csum_set(sb);
+ unlock_buffer(EXT4_SB(sb)->s_sbh);
+ err = ext4_handle_dirty_metadata(handle, NULL, EXT4_SB(sb)->s_sbh);
if (err)
ext4_std_error(sb, err);
return err;
@@ -1384,6 +1387,7 @@ static void ext4_update_super(struct super_block *sb,
reserved_blocks *= blocks_count;
do_div(reserved_blocks, 100);
+ lock_buffer(sbi->s_sbh);
ext4_blocks_count_set(es, ext4_blocks_count(es) + blocks_count);
ext4_free_blocks_count_set(es, ext4_free_blocks_count(es) + free_blocks);
le32_add_cpu(&es->s_inodes_count, EXT4_INODES_PER_GROUP(sb) *
@@ -1421,6 +1425,8 @@ static void ext4_update_super(struct super_block *sb,
* active. */
ext4_r_blocks_count_set(es, ext4_r_blocks_count(es) +
reserved_blocks);
+ ext4_superblock_csum_set(sb);
+ unlock_buffer(sbi->s_sbh);
/* Update the free space counts */
percpu_counter_add(&sbi->s_freeclusters_counter,
@@ -1515,7 +1521,7 @@ static int ext4_flex_group_add(struct super_block *sb,
ext4_update_super(sb, flex_gd);
- err = ext4_handle_dirty_super(handle, sb);
+ err = ext4_handle_dirty_metadata(handle, NULL, sbi->s_sbh);
exit_journal:
err2 = ext4_journal_stop(handle);
@@ -1717,15 +1723,18 @@ static int ext4_group_extend_no_check(struct super_block *sb,
goto errout;
}
+ lock_buffer(EXT4_SB(sb)->s_sbh);
ext4_blocks_count_set(es, o_blocks_count + add);
ext4_free_blocks_count_set(es, ext4_free_blocks_count(es) + add);
+ ext4_superblock_csum_set(sb);
+ unlock_buffer(EXT4_SB(sb)->s_sbh);
ext4_debug("freeing blocks %llu through %llu\n", o_blocks_count,
o_blocks_count + add);
/* We add the blocks to the bitmap and set the group need init bit */
err = ext4_group_add_blocks(handle, sb, o_blocks_count, add);
if (err)
goto errout;
- ext4_handle_dirty_super(handle, sb);
+ ext4_handle_dirty_metadata(handle, NULL, EXT4_SB(sb)->s_sbh);
ext4_debug("freed blocks %llu through %llu\n", o_blocks_count,
o_blocks_count + add);
errout:
@@ -1874,12 +1883,15 @@ static int ext4_convert_meta_bg(struct super_block *sb, struct inode *inode)
if (err)
goto errout;
+ lock_buffer(sbi->s_sbh);
ext4_clear_feature_resize_inode(sb);
ext4_set_feature_meta_bg(sb);
sbi->s_es->s_first_meta_bg =
cpu_to_le32(num_desc_blocks(sb, sbi->s_groups_count));
+ ext4_superblock_csum_set(sb);
+ unlock_buffer(sbi->s_sbh);
- err = ext4_handle_dirty_super(handle, sb);
+ err = ext4_handle_dirty_metadata(handle, NULL, sbi->s_sbh);
if (err) {
ext4_std_error(sb, err);
goto errout;
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 21121787c874..9a6f9875aa34 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -65,7 +65,8 @@ static struct ratelimit_state ext4_mount_msg_ratelimit;
static int ext4_load_journal(struct super_block *, struct ext4_super_block *,
unsigned long journal_devnum);
static int ext4_show_options(struct seq_file *seq, struct dentry *root);
-static int ext4_commit_super(struct super_block *sb, int sync);
+static void ext4_update_super(struct super_block *sb);
+static int ext4_commit_super(struct super_block *sb);
static int ext4_mark_recovery_complete(struct super_block *sb,
struct ext4_super_block *es);
static int ext4_clear_journal_err(struct super_block *sb,
@@ -586,15 +587,12 @@ static int ext4_errno_to_code(int errno)
return EXT4_ERR_UNKNOWN;
}
-static void __save_error_info(struct super_block *sb, int error,
- __u32 ino, __u64 block,
- const char *func, unsigned int line)
+static void save_error_info(struct super_block *sb, int error,
+ __u32 ino, __u64 block,
+ const char *func, unsigned int line)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
- EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
- if (bdev_read_only(sb->s_bdev))
- return;
/* We default to EFSCORRUPTED error... */
if (error == 0)
error = EFSCORRUPTED;
@@ -618,15 +616,6 @@ static void __save_error_info(struct super_block *sb, int error,
spin_unlock(&sbi->s_error_lock);
}
-static void save_error_info(struct super_block *sb, int error,
- __u32 ino, __u64 block,
- const char *func, unsigned int line)
-{
- __save_error_info(sb, error, ino, block, func, line);
- if (!bdev_read_only(sb->s_bdev))
- ext4_commit_super(sb, 1);
-}
-
/* Deal with the reporting of failure conditions on a filesystem such as
* inconsistencies detected or read IO failures.
*
@@ -647,19 +636,40 @@ static void save_error_info(struct super_block *sb, int error,
* used to deal with unrecoverable failures such as journal IO errors or ENOMEM
* at a critical moment in log management.
*/
-static void ext4_handle_error(struct super_block *sb, bool force_ro)
+static void ext4_handle_error(struct super_block *sb, bool force_ro, int error,
+ __u32 ino, __u64 block,
+ const char *func, unsigned int line)
{
journal_t *journal = EXT4_SB(sb)->s_journal;
+ bool continue_fs = !force_ro && test_opt(sb, ERRORS_CONT);
+ EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
if (test_opt(sb, WARN_ON_ERROR))
WARN_ON_ONCE(1);
- if (sb_rdonly(sb) || (!force_ro && test_opt(sb, ERRORS_CONT)))
+ if (!continue_fs && !sb_rdonly(sb)) {
+ ext4_set_mount_flag(sb, EXT4_MF_FS_ABORTED);
+ if (journal)
+ jbd2_journal_abort(journal, -EIO);
+ }
+
+ if (!bdev_read_only(sb->s_bdev)) {
+ save_error_info(sb, error, ino, block, func, line);
+ /*
+ * In case the fs should keep running, we need to writeout
+ * superblock through the journal. Due to lock ordering
+ * constraints, it may not be safe to do it right here so we
+ * defer superblock flushing to a workqueue.
+ */
+ if (continue_fs)
+ schedule_work(&EXT4_SB(sb)->s_error_work);
+ else
+ ext4_commit_super(sb);
+ }
+
+ if (sb_rdonly(sb) || continue_fs)
return;
- ext4_set_mount_flag(sb, EXT4_MF_FS_ABORTED);
- if (journal)
- jbd2_journal_abort(journal, -EIO);
/*
* We force ERRORS_RO behavior when system is rebooting. Otherwise we
* could panic during 'reboot -f' as the underlying device got already
@@ -682,8 +692,39 @@ static void flush_stashed_error_work(struct work_struct *work)
{
struct ext4_sb_info *sbi = container_of(work, struct ext4_sb_info,
s_error_work);
+ journal_t *journal = sbi->s_journal;
+ handle_t *handle;
- ext4_commit_super(sbi->s_sb, 1);
+ /*
+ * If the journal is still running, we have to write out superblock
+ * through the journal to avoid collisions of other journalled sb
+ * updates.
+ *
+ * We use directly jbd2 functions here to avoid recursing back into
+ * ext4 error handling code during handling of previous errors.
+ */
+ if (!sb_rdonly(sbi->s_sb) && journal) {
+ handle = jbd2_journal_start(journal, 1);
+ if (IS_ERR(handle))
+ goto write_directly;
+ if (jbd2_journal_get_write_access(handle, sbi->s_sbh)) {
+ jbd2_journal_stop(handle);
+ goto write_directly;
+ }
+ ext4_update_super(sbi->s_sb);
+ if (jbd2_journal_dirty_metadata(handle, sbi->s_sbh)) {
+ jbd2_journal_stop(handle);
+ goto write_directly;
+ }
+ jbd2_journal_stop(handle);
+ return;
+ }
+write_directly:
+ /*
+ * Write through journal failed. Write sb directly to get error info
+ * out and hope for the best.
+ */
+ ext4_commit_super(sbi->s_sb);
}
#define ext4_error_ratelimit(sb) \
@@ -710,8 +751,7 @@ void __ext4_error(struct super_block *sb, const char *function,
sb->s_id, function, line, current->comm, &vaf);
va_end(args);
}
- save_error_info(sb, error, 0, block, function, line);
- ext4_handle_error(sb, force_ro);
+ ext4_handle_error(sb, force_ro, error, 0, block, function, line);
}
void __ext4_error_inode(struct inode *inode, const char *function,
@@ -741,9 +781,8 @@ void __ext4_error_inode(struct inode *inode, const char *function,
current->comm, &vaf);
va_end(args);
}
- save_error_info(inode->i_sb, error, inode->i_ino, block,
- function, line);
- ext4_handle_error(inode->i_sb, false);
+ ext4_handle_error(inode->i_sb, false, error, inode->i_ino, block,
+ function, line);
}
void __ext4_error_file(struct file *file, const char *function,
@@ -780,9 +819,8 @@ void __ext4_error_file(struct file *file, const char *function,
current->comm, path, &vaf);
va_end(args);
}
- save_error_info(inode->i_sb, EFSCORRUPTED, inode->i_ino, block,
- function, line);
- ext4_handle_error(inode->i_sb, false);
+ ext4_handle_error(inode->i_sb, false, EFSCORRUPTED, inode->i_ino, block,
+ function, line);
}
const char *ext4_decode_error(struct super_block *sb, int errno,
@@ -849,8 +887,7 @@ void __ext4_std_error(struct super_block *sb, const char *function,
sb->s_id, function, line, errstr);
}
- save_error_info(sb, -errno, 0, 0, function, line);
- ext4_handle_error(sb, false);
+ ext4_handle_error(sb, false, -errno, 0, 0, function, line);
}
void __ext4_msg(struct super_block *sb,
@@ -944,13 +981,16 @@ __acquires(bitlock)
if (test_opt(sb, ERRORS_CONT)) {
if (test_opt(sb, WARN_ON_ERROR))
WARN_ON_ONCE(1);
- __save_error_info(sb, EFSCORRUPTED, ino, block, function, line);
- schedule_work(&EXT4_SB(sb)->s_error_work);
+ EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
+ if (!bdev_read_only(sb->s_bdev)) {
+ save_error_info(sb, EFSCORRUPTED, ino, block, function,
+ line);
+ schedule_work(&EXT4_SB(sb)->s_error_work);
+ }
return;
}
ext4_unlock_group(sb, grp);
- save_error_info(sb, EFSCORRUPTED, ino, block, function, line);
- ext4_handle_error(sb, false);
+ ext4_handle_error(sb, false, EFSCORRUPTED, ino, block, function, line);
/*
* We only get here in the ERRORS_RO case; relocking the group
* may be dangerous, but nothing bad will happen since the
@@ -1152,7 +1192,7 @@ static void ext4_put_super(struct super_block *sb)
es->s_state = cpu_to_le16(sbi->s_mount_state);
}
if (!sb_rdonly(sb))
- ext4_commit_super(sb, 1);
+ ext4_commit_super(sb);
rcu_read_lock();
group_desc = rcu_dereference(sbi->s_group_desc);
@@ -2642,7 +2682,7 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es,
if (sbi->s_journal)
ext4_set_feature_journal_needs_recovery(sb);
- err = ext4_commit_super(sb, 1);
+ err = ext4_commit_super(sb);
done:
if (test_opt(sb, DEBUG))
printk(KERN_INFO "[EXT4 FS bs=%lu, gc=%u, "
@@ -4868,7 +4908,7 @@ no_journal:
if (DUMMY_ENCRYPTION_ENABLED(sbi) && !sb_rdonly(sb) &&
!ext4_has_feature_encrypt(sb)) {
ext4_set_feature_encrypt(sb);
- ext4_commit_super(sb, 1);
+ ext4_commit_super(sb);
}
/*
@@ -5418,7 +5458,7 @@ static int ext4_load_journal(struct super_block *sb,
es->s_journal_dev = cpu_to_le32(journal_devnum);
/* Make sure we flush the recovery flag to disk. */
- ext4_commit_super(sb, 1);
+ ext4_commit_super(sb);
}
return 0;
@@ -5428,16 +5468,14 @@ err_out:
return err;
}
-static int ext4_commit_super(struct super_block *sb, int sync)
+/* Copy state of EXT4_SB(sb) into buffer for on-disk superblock */
+static void ext4_update_super(struct super_block *sb)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
- struct ext4_super_block *es = EXT4_SB(sb)->s_es;
- struct buffer_head *sbh = EXT4_SB(sb)->s_sbh;
- int error = 0;
-
- if (!sbh || block_device_ejected(sb))
- return error;
+ struct ext4_super_block *es = sbi->s_es;
+ struct buffer_head *sbh = sbi->s_sbh;
+ lock_buffer(sbh);
/*
* If the file system is mounted read-only, don't update the
* superblock write time. This avoids updating the superblock
@@ -5451,17 +5489,17 @@ static int ext4_commit_super(struct super_block *sb, int sync)
if (!(sb->s_flags & SB_RDONLY))
ext4_update_tstamp(es, s_wtime);
es->s_kbytes_written =
- cpu_to_le64(EXT4_SB(sb)->s_kbytes_written +
+ cpu_to_le64(sbi->s_kbytes_written +
((part_stat_read(sb->s_bdev, sectors[STAT_WRITE]) -
- EXT4_SB(sb)->s_sectors_written_start) >> 1));
- if (percpu_counter_initialized(&EXT4_SB(sb)->s_freeclusters_counter))
+ sbi->s_sectors_written_start) >> 1));
+ if (percpu_counter_initialized(&sbi->s_freeclusters_counter))
ext4_free_blocks_count_set(es,
- EXT4_C2B(EXT4_SB(sb), percpu_counter_sum_positive(
- &EXT4_SB(sb)->s_freeclusters_counter)));
- if (percpu_counter_initialized(&EXT4_SB(sb)->s_freeinodes_counter))
+ EXT4_C2B(sbi, percpu_counter_sum_positive(
+ &sbi->s_freeclusters_counter)));
+ if (percpu_counter_initialized(&sbi->s_freeinodes_counter))
es->s_free_inodes_count =
cpu_to_le32(percpu_counter_sum_positive(
- &EXT4_SB(sb)->s_freeinodes_counter));
+ &sbi->s_freeinodes_counter));
/* Copy error information to the on-disk superblock */
spin_lock(&sbi->s_error_lock);
if (sbi->s_add_error_count > 0) {
@@ -5502,10 +5540,20 @@ static int ext4_commit_super(struct super_block *sb, int sync)
}
spin_unlock(&sbi->s_error_lock);
- BUFFER_TRACE(sbh, "marking dirty");
ext4_superblock_csum_set(sb);
- if (sync)
- lock_buffer(sbh);
+ unlock_buffer(sbh);
+}
+
+static int ext4_commit_super(struct super_block *sb)
+{
+ struct buffer_head *sbh = EXT4_SB(sb)->s_sbh;
+ int error = 0;
+
+ if (!sbh || block_device_ejected(sb))
+ return error;
+
+ ext4_update_super(sb);
+
if (buffer_write_io_error(sbh) || !buffer_uptodate(sbh)) {
/*
* Oh, dear. A previous attempt to write the
@@ -5520,17 +5568,15 @@ static int ext4_commit_super(struct super_block *sb, int sync)
clear_buffer_write_io_error(sbh);
set_buffer_uptodate(sbh);
}
+ BUFFER_TRACE(sbh, "marking dirty");
mark_buffer_dirty(sbh);
- if (sync) {
- unlock_buffer(sbh);
- error = __sync_dirty_buffer(sbh,
- REQ_SYNC | (test_opt(sb, BARRIER) ? REQ_FUA : 0));
- if (buffer_write_io_error(sbh)) {
- ext4_msg(sb, KERN_ERR, "I/O error while writing "
- "superblock");
- clear_buffer_write_io_error(sbh);
- set_buffer_uptodate(sbh);
- }
+ error = __sync_dirty_buffer(sbh,
+ REQ_SYNC | (test_opt(sb, BARRIER) ? REQ_FUA : 0));
+ if (buffer_write_io_error(sbh)) {
+ ext4_msg(sb, KERN_ERR, "I/O error while writing "
+ "superblock");
+ clear_buffer_write_io_error(sbh);
+ set_buffer_uptodate(sbh);
}
return error;
}
@@ -5561,7 +5607,7 @@ static int ext4_mark_recovery_complete(struct super_block *sb,
if (ext4_has_feature_journal_needs_recovery(sb) && sb_rdonly(sb)) {
ext4_clear_feature_journal_needs_recovery(sb);
- ext4_commit_super(sb, 1);
+ ext4_commit_super(sb);
}
out:
jbd2_journal_unlock_updates(journal);
@@ -5603,7 +5649,7 @@ static int ext4_clear_journal_err(struct super_block *sb,
EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
es->s_state |= cpu_to_le16(EXT4_ERROR_FS);
- ext4_commit_super(sb, 1);
+ ext4_commit_super(sb);
jbd2_journal_clear_err(journal);
jbd2_journal_update_sb_errno(journal);
@@ -5705,7 +5751,7 @@ static int ext4_freeze(struct super_block *sb)
ext4_clear_feature_journal_needs_recovery(sb);
}
- error = ext4_commit_super(sb, 1);
+ error = ext4_commit_super(sb);
out:
if (journal)
/* we rely on upper layer to stop further updates */
@@ -5727,7 +5773,7 @@ static int ext4_unfreeze(struct super_block *sb)
ext4_set_feature_journal_needs_recovery(sb);
}
- ext4_commit_super(sb, 1);
+ ext4_commit_super(sb);
return 0;
}
@@ -5987,7 +6033,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
}
if (sbi->s_journal == NULL && !(old_sb_flags & SB_RDONLY)) {
- err = ext4_commit_super(sb, 1);
+ err = ext4_commit_super(sb);
if (err)
goto restore_opts;
}
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 4e3b1f8c2e81..372208500f4e 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -792,8 +792,11 @@ static void ext4_xattr_update_super_block(handle_t *handle,
BUFFER_TRACE(EXT4_SB(sb)->s_sbh, "get_write_access");
if (ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh) == 0) {
+ lock_buffer(EXT4_SB(sb)->s_sbh);
ext4_set_feature_xattr(sb);
- ext4_handle_dirty_super(handle, sb);
+ ext4_superblock_csum_set(sb);
+ unlock_buffer(EXT4_SB(sb)->s_sbh);
+ ext4_handle_dirty_metadata(handle, NULL, EXT4_SB(sb)->s_sbh);
}
}
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index acfb55834af2..c41cb887eb7d 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -1474,21 +1474,25 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
}
/*
- * Some filesystems may redirty the inode during the writeback
- * due to delalloc, clear dirty metadata flags right before
- * write_inode()
+ * If the inode has dirty timestamps and we need to write them, call
+ * mark_inode_dirty_sync() to notify the filesystem about it and to
+ * change I_DIRTY_TIME into I_DIRTY_SYNC.
*/
- spin_lock(&inode->i_lock);
-
- dirty = inode->i_state & I_DIRTY;
if ((inode->i_state & I_DIRTY_TIME) &&
- ((dirty & I_DIRTY_INODE) ||
- wbc->sync_mode == WB_SYNC_ALL || wbc->for_sync ||
+ (wbc->sync_mode == WB_SYNC_ALL || wbc->for_sync ||
time_after(jiffies, inode->dirtied_time_when +
dirtytime_expire_interval * HZ))) {
- dirty |= I_DIRTY_TIME;
trace_writeback_lazytime(inode);
+ mark_inode_dirty_sync(inode);
}
+
+ /*
+ * Some filesystems may redirty the inode during the writeback
+ * due to delalloc, clear dirty metadata flags right before
+ * write_inode()
+ */
+ spin_lock(&inode->i_lock);
+ dirty = inode->i_state & I_DIRTY;
inode->i_state &= ~dirty;
/*
@@ -1509,8 +1513,6 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
spin_unlock(&inode->i_lock);
- if (dirty & I_DIRTY_TIME)
- mark_inode_dirty_sync(inode);
/* Don't write the inode if only I_DIRTY_PAGES was set */
if (dirty & ~I_DIRTY_PAGES) {
int err = write_inode(inode, wbc);
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index b5c109703daa..21c20fd5f9ee 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -735,9 +735,10 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset,
mutex_unlock(&hugetlb_fault_mutex_table[hash]);
+ set_page_huge_active(page);
/*
* unlock_page because locked by add_to_page_cache()
- * page_put due to reference from alloc_huge_page()
+ * put_page() due to reference from alloc_huge_page()
*/
unlock_page(page);
put_page(page);
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 2f305c097bd5..1f68105a41ed 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -354,6 +354,7 @@ struct io_ring_ctx {
unsigned cq_entries;
unsigned cq_mask;
atomic_t cq_timeouts;
+ unsigned cq_last_tm_flush;
unsigned long cq_check_overflow;
struct wait_queue_head cq_wait;
struct fasync_struct *cq_fasync;
@@ -1024,6 +1025,8 @@ static ssize_t io_import_iovec(int rw, struct io_kiocb *req,
static int io_setup_async_rw(struct io_kiocb *req, const struct iovec *iovec,
const struct iovec *fast_iov,
struct iov_iter *iter, bool force);
+static void io_req_drop_files(struct io_kiocb *req);
+static void io_req_task_queue(struct io_kiocb *req);
static struct kmem_cache *req_cachep;
@@ -1047,8 +1050,7 @@ EXPORT_SYMBOL(io_uring_get_socket);
static inline void io_clean_op(struct io_kiocb *req)
{
- if (req->flags & (REQ_F_NEED_CLEANUP | REQ_F_BUFFER_SELECTED |
- REQ_F_INFLIGHT))
+ if (req->flags & (REQ_F_NEED_CLEANUP | REQ_F_BUFFER_SELECTED))
__io_clean_op(req);
}
@@ -1068,14 +1070,21 @@ static bool io_match_task(struct io_kiocb *head,
{
struct io_kiocb *req;
- if (task && head->task != task)
+ if (task && head->task != task) {
+ /* in terms of cancelation, always match if req task is dead */
+ if (head->task->flags & PF_EXITING)
+ return true;
return false;
+ }
if (!files)
return true;
io_for_each_link(req, head) {
- if ((req->flags & REQ_F_WORK_INITIALIZED) &&
- (req->work.flags & IO_WQ_WORK_FILES) &&
+ if (!(req->flags & REQ_F_WORK_INITIALIZED))
+ continue;
+ if (req->file && req->file->f_op == &io_uring_fops)
+ return true;
+ if ((req->work.flags & IO_WQ_WORK_FILES) &&
req->work.identity->files == files)
return true;
}
@@ -1106,6 +1115,9 @@ static void io_sq_thread_drop_mm_files(void)
static int __io_sq_thread_acquire_files(struct io_ring_ctx *ctx)
{
+ if (current->flags & PF_EXITING)
+ return -EFAULT;
+
if (!current->files) {
struct files_struct *files;
struct nsproxy *nsproxy;
@@ -1133,6 +1145,8 @@ static int __io_sq_thread_acquire_mm(struct io_ring_ctx *ctx)
{
struct mm_struct *mm;
+ if (current->flags & PF_EXITING)
+ return -EFAULT;
if (current->mm)
return 0;
@@ -1388,6 +1402,8 @@ static void io_req_clean_work(struct io_kiocb *req)
free_fs_struct(fs);
req->work.flags &= ~IO_WQ_WORK_FS;
}
+ if (req->flags & REQ_F_INFLIGHT)
+ io_req_drop_files(req);
io_put_identity(req->task->io_uring, req);
}
@@ -1497,11 +1513,14 @@ static bool io_grab_identity(struct io_kiocb *req)
return false;
atomic_inc(&id->files->count);
get_nsproxy(id->nsproxy);
- req->flags |= REQ_F_INFLIGHT;
- spin_lock_irq(&ctx->inflight_lock);
- list_add(&req->inflight_entry, &ctx->inflight_list);
- spin_unlock_irq(&ctx->inflight_lock);
+ if (!(req->flags & REQ_F_INFLIGHT)) {
+ req->flags |= REQ_F_INFLIGHT;
+
+ spin_lock_irq(&ctx->inflight_lock);
+ list_add(&req->inflight_entry, &ctx->inflight_list);
+ spin_unlock_irq(&ctx->inflight_lock);
+ }
req->work.flags |= IO_WQ_WORK_FILES;
}
if (!(req->work.flags & IO_WQ_WORK_MM) &&
@@ -1616,37 +1635,49 @@ static void __io_queue_deferred(struct io_ring_ctx *ctx)
do {
struct io_defer_entry *de = list_first_entry(&ctx->defer_list,
struct io_defer_entry, list);
- struct io_kiocb *link;
if (req_need_defer(de->req, de->seq))
break;
list_del_init(&de->list);
- /* punt-init is done before queueing for defer */
- link = __io_queue_async_work(de->req);
- if (link) {
- __io_queue_linked_timeout(link);
- /* drop submission reference */
- io_put_req_deferred(link, 1);
- }
+ io_req_task_queue(de->req);
kfree(de);
} while (!list_empty(&ctx->defer_list));
}
static void io_flush_timeouts(struct io_ring_ctx *ctx)
{
- while (!list_empty(&ctx->timeout_list)) {
+ u32 seq;
+
+ if (list_empty(&ctx->timeout_list))
+ return;
+
+ seq = ctx->cached_cq_tail - atomic_read(&ctx->cq_timeouts);
+
+ do {
+ u32 events_needed, events_got;
struct io_kiocb *req = list_first_entry(&ctx->timeout_list,
struct io_kiocb, timeout.list);
if (io_is_timeout_noseq(req))
break;
- if (req->timeout.target_seq != ctx->cached_cq_tail
- - atomic_read(&ctx->cq_timeouts))
+
+ /*
+ * Since seq can easily wrap around over time, subtract
+ * the last seq at which timeouts were flushed before comparing.
+ * Assuming not more than 2^31-1 events have happened since,
+ * these subtractions won't have wrapped, so we can check if
+ * target is in [last_seq, current_seq] by comparing the two.
+ */
+ events_needed = req->timeout.target_seq - ctx->cq_last_tm_flush;
+ events_got = seq - ctx->cq_last_tm_flush;
+ if (events_got < events_needed)
break;
list_del_init(&req->timeout.list);
io_kill_timeout(req);
- }
+ } while (!list_empty(&ctx->timeout_list));
+
+ ctx->cq_last_tm_flush = seq;
}
static void io_commit_cqring(struct io_ring_ctx *ctx)
@@ -1742,12 +1773,13 @@ static bool __io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force,
struct io_kiocb *req, *tmp;
struct io_uring_cqe *cqe;
unsigned long flags;
- bool all_flushed;
+ bool all_flushed, posted;
LIST_HEAD(list);
if (!force && __io_cqring_events(ctx) == rings->cq_ring_entries)
return false;
+ posted = false;
spin_lock_irqsave(&ctx->completion_lock, flags);
list_for_each_entry_safe(req, tmp, &ctx->cq_overflow_list, compl.list) {
if (!io_match_task(req, tsk, files))
@@ -1767,6 +1799,7 @@ static bool __io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force,
WRITE_ONCE(ctx->rings->cq_overflow,
ctx->cached_cq_overflow);
}
+ posted = true;
}
all_flushed = list_empty(&ctx->cq_overflow_list);
@@ -1776,9 +1809,11 @@ static bool __io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force,
ctx->rings->sq_flags &= ~IORING_SQ_CQ_OVERFLOW;
}
- io_commit_cqring(ctx);
+ if (posted)
+ io_commit_cqring(ctx);
spin_unlock_irqrestore(&ctx->completion_lock, flags);
- io_cqring_ev_posted(ctx);
+ if (posted)
+ io_cqring_ev_posted(ctx);
while (!list_empty(&list)) {
req = list_first_entry(&list, struct io_kiocb, compl.list);
@@ -2170,6 +2205,9 @@ static void __io_req_task_submit(struct io_kiocb *req)
else
__io_req_task_cancel(req, -EFAULT);
mutex_unlock(&ctx->uring_lock);
+
+ if (ctx->flags & IORING_SETUP_SQPOLL)
+ io_sq_thread_drop_mm_files();
}
static void io_req_task_submit(struct callback_head *cb)
@@ -2245,6 +2283,8 @@ static void io_req_free_batch_finish(struct io_ring_ctx *ctx,
struct io_uring_task *tctx = rb->task->io_uring;
percpu_counter_sub(&tctx->inflight, rb->task_refs);
+ if (atomic_read(&tctx->in_idle))
+ wake_up(&tctx->wait);
put_task_struct_many(rb->task, rb->task_refs);
rb->task = NULL;
}
@@ -2263,6 +2303,8 @@ static void io_req_free_batch(struct req_batch *rb, struct io_kiocb *req)
struct io_uring_task *tctx = rb->task->io_uring;
percpu_counter_sub(&tctx->inflight, rb->task_refs);
+ if (atomic_read(&tctx->in_idle))
+ wake_up(&tctx->wait);
put_task_struct_many(rb->task, rb->task_refs);
}
rb->task = req->task;
@@ -3523,7 +3565,7 @@ static int io_read(struct io_kiocb *req, bool force_nonblock,
/* read it all, or we did blocking attempt. no retry. */
if (!iov_iter_count(iter) || !force_nonblock ||
- (req->file->f_flags & O_NONBLOCK))
+ (req->file->f_flags & O_NONBLOCK) || !(req->flags & REQ_F_ISREG))
goto done;
io_size -= ret;
@@ -4443,7 +4485,6 @@ static int io_close_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
* io_wq_work.flags, so initialize io_wq_work firstly.
*/
io_req_init_async(req);
- req->work.flags |= IO_WQ_WORK_NO_CANCEL;
if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
return -EINVAL;
@@ -4476,6 +4517,8 @@ static int io_close(struct io_kiocb *req, bool force_nonblock,
/* if the file has a flush method, be safe and punt to async */
if (close->put_file->f_op->flush && force_nonblock) {
+ /* not safe to cancel at this point */
+ req->work.flags |= IO_WQ_WORK_NO_CANCEL;
/* was never set, but play safe */
req->flags &= ~REQ_F_NOWAIT;
/* avoid grabbing files - we don't need the files */
@@ -5832,6 +5875,12 @@ static int io_timeout(struct io_kiocb *req)
tail = ctx->cached_cq_tail - atomic_read(&ctx->cq_timeouts);
req->timeout.target_seq = tail + off;
+ /* Update the last seq here in case io_flush_timeouts() hasn't.
+ * This is safe because ->completion_lock is held, and submissions
+ * and completions are never mixed in the same ->completion_lock section.
+ */
+ ctx->cq_last_tm_flush = tail;
+
/*
* Insertion sort, ensuring the first entry in the list is always
* the one we need first.
@@ -6126,8 +6175,10 @@ static void io_req_drop_files(struct io_kiocb *req)
struct io_uring_task *tctx = req->task->io_uring;
unsigned long flags;
- put_files_struct(req->work.identity->files);
- put_nsproxy(req->work.identity->nsproxy);
+ if (req->work.flags & IO_WQ_WORK_FILES) {
+ put_files_struct(req->work.identity->files);
+ put_nsproxy(req->work.identity->nsproxy);
+ }
spin_lock_irqsave(&ctx->inflight_lock, flags);
list_del(&req->inflight_entry);
spin_unlock_irqrestore(&ctx->inflight_lock, flags);
@@ -6194,9 +6245,6 @@ static void __io_clean_op(struct io_kiocb *req)
}
req->flags &= ~REQ_F_NEED_CLEANUP;
}
-
- if (req->flags & REQ_F_INFLIGHT)
- io_req_drop_files(req);
}
static int io_issue_sqe(struct io_kiocb *req, bool force_nonblock,
@@ -6415,6 +6463,16 @@ static struct file *io_file_get(struct io_submit_state *state,
file = __io_file_get(state, fd);
}
+ if (file && file->f_op == &io_uring_fops &&
+ !(req->flags & REQ_F_INFLIGHT)) {
+ io_req_init_async(req);
+ req->flags |= REQ_F_INFLIGHT;
+
+ spin_lock_irq(&ctx->inflight_lock);
+ list_add(&req->inflight_entry, &ctx->inflight_list);
+ spin_unlock_irq(&ctx->inflight_lock);
+ }
+
return file;
}
@@ -7056,6 +7114,7 @@ static int io_sq_thread(void *data)
if (sqt_spin || !time_after(jiffies, timeout)) {
io_run_task_work();
+ io_sq_thread_drop_mm_files();
cond_resched();
if (sqt_spin)
timeout = jiffies + sqd->sq_thread_idle;
@@ -7093,6 +7152,7 @@ static int io_sq_thread(void *data)
}
io_run_task_work();
+ io_sq_thread_drop_mm_files();
if (cur_css)
io_sq_thread_unassociate_blkcg();
@@ -7212,14 +7272,18 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
TASK_INTERRUPTIBLE);
/* make sure we run task_work before checking for signals */
ret = io_run_task_work_sig();
- if (ret > 0)
+ if (ret > 0) {
+ finish_wait(&ctx->wait, &iowq.wq);
continue;
+ }
else if (ret < 0)
break;
if (io_should_wake(&iowq))
break;
- if (test_bit(0, &ctx->cq_check_overflow))
+ if (test_bit(0, &ctx->cq_check_overflow)) {
+ finish_wait(&ctx->wait, &iowq.wq);
continue;
+ }
if (uts) {
timeout = schedule_timeout(timeout);
if (timeout == 0) {
@@ -8811,39 +8875,44 @@ static void io_cancel_defer_files(struct io_ring_ctx *ctx,
}
}
+static int io_uring_count_inflight(struct io_ring_ctx *ctx,
+ struct task_struct *task,
+ struct files_struct *files)
+{
+ struct io_kiocb *req;
+ int cnt = 0;
+
+ spin_lock_irq(&ctx->inflight_lock);
+ list_for_each_entry(req, &ctx->inflight_list, inflight_entry)
+ cnt += io_match_task(req, task, files);
+ spin_unlock_irq(&ctx->inflight_lock);
+ return cnt;
+}
+
static void io_uring_cancel_files(struct io_ring_ctx *ctx,
struct task_struct *task,
struct files_struct *files)
{
while (!list_empty_careful(&ctx->inflight_list)) {
struct io_task_cancel cancel = { .task = task, .files = files };
- struct io_kiocb *req;
DEFINE_WAIT(wait);
- bool found = false;
-
- spin_lock_irq(&ctx->inflight_lock);
- list_for_each_entry(req, &ctx->inflight_list, inflight_entry) {
- if (req->task != task ||
- req->work.identity->files != files)
- continue;
- found = true;
- break;
- }
- if (found)
- prepare_to_wait(&task->io_uring->wait, &wait,
- TASK_UNINTERRUPTIBLE);
- spin_unlock_irq(&ctx->inflight_lock);
+ int inflight;
- /* We need to keep going until we don't find a matching req */
- if (!found)
+ inflight = io_uring_count_inflight(ctx, task, files);
+ if (!inflight)
break;
io_wq_cancel_cb(ctx->io_wq, io_cancel_task_cb, &cancel, true);
io_poll_remove_all(ctx, task, files);
io_kill_timeouts(ctx, task, files);
+ io_cqring_overflow_flush(ctx, true, task, files);
/* cancellations _may_ trigger task work */
io_run_task_work();
- schedule();
+
+ prepare_to_wait(&task->io_uring->wait, &wait,
+ TASK_UNINTERRUPTIBLE);
+ if (inflight == io_uring_count_inflight(ctx, task, files))
+ schedule();
finish_wait(&task->io_uring->wait, &wait);
}
}
@@ -8881,14 +8950,13 @@ static void __io_uring_cancel_task_requests(struct io_ring_ctx *ctx,
static void io_disable_sqo_submit(struct io_ring_ctx *ctx)
{
- WARN_ON_ONCE(ctx->sqo_task != current);
-
mutex_lock(&ctx->uring_lock);
ctx->sqo_dead = 1;
mutex_unlock(&ctx->uring_lock);
/* make sure callers enter the ring to get error */
- io_ring_set_wakeup_flag(ctx);
+ if (ctx->rings)
+ io_ring_set_wakeup_flag(ctx);
}
/*
@@ -8902,7 +8970,6 @@ static void io_uring_cancel_task_requests(struct io_ring_ctx *ctx,
struct task_struct *task = current;
if ((ctx->flags & IORING_SETUP_SQPOLL) && ctx->sq_data) {
- /* for SQPOLL only sqo_task has task notes */
io_disable_sqo_submit(ctx);
task = ctx->sq_data->thread;
atomic_inc(&task->io_uring->in_idle);
@@ -8912,19 +8979,12 @@ static void io_uring_cancel_task_requests(struct io_ring_ctx *ctx,
io_cancel_defer_files(ctx, task, files);
io_cqring_overflow_flush(ctx, true, task, files);
+ io_uring_cancel_files(ctx, task, files);
if (!files)
__io_uring_cancel_task_requests(ctx, task);
- else
- io_uring_cancel_files(ctx, task, files);
if ((ctx->flags & IORING_SETUP_SQPOLL) && ctx->sq_data) {
atomic_dec(&task->io_uring->in_idle);
- /*
- * If the files that are going away are the ones in the thread
- * identity, clear them out.
- */
- if (task->io_uring->identity->files == files)
- task->io_uring->identity->files = NULL;
io_sq_thread_unpark(ctx->sq_data);
}
}
@@ -9048,6 +9108,10 @@ void __io_uring_task_cancel(void)
/* make sure overflow events are dropped */
atomic_inc(&tctx->in_idle);
+ /* trigger io_disable_sqo_submit() */
+ if (tctx->sqpoll)
+ __io_uring_files_cancel(NULL);
+
do {
/* read completions before cancelations */
inflight = tctx_inflight(tctx);
@@ -9058,12 +9122,12 @@ void __io_uring_task_cancel(void)
prepare_to_wait(&tctx->wait, &wait, TASK_UNINTERRUPTIBLE);
/*
- * If we've seen completions, retry. This avoids a race where
- * a completion comes in before we did prepare_to_wait().
+ * If we've seen completions, retry without waiting. This
+ * avoids a race where a completion comes in before we did
+ * prepare_to_wait().
*/
- if (inflight != tctx_inflight(tctx))
- continue;
- schedule();
+ if (inflight == tctx_inflight(tctx))
+ schedule();
finish_wait(&tctx->wait, &wait);
} while (1);
@@ -9077,6 +9141,9 @@ static int io_uring_flush(struct file *file, void *data)
struct io_uring_task *tctx = current->io_uring;
struct io_ring_ctx *ctx = file->private_data;
+ if (fatal_signal_pending(current) || (current->flags & PF_EXITING))
+ io_uring_cancel_task_requests(ctx, NULL);
+
if (!tctx)
return 0;
@@ -9093,7 +9160,10 @@ static int io_uring_flush(struct file *file, void *data)
if (ctx->flags & IORING_SETUP_SQPOLL) {
/* there is only one file note, which is owned by sqo_task */
- WARN_ON_ONCE((ctx->sqo_task == current) ==
+ WARN_ON_ONCE(ctx->sqo_task != current &&
+ xa_load(&tctx->xa, (unsigned long)file));
+ /* sqo_dead check is for when this happens after cancellation */
+ WARN_ON_ONCE(ctx->sqo_task == current && !ctx->sqo_dead &&
!xa_load(&tctx->xa, (unsigned long)file));
io_disable_sqo_submit(ctx);
@@ -9700,6 +9770,7 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p,
*/
ret = io_uring_install_fd(ctx, file);
if (ret < 0) {
+ io_disable_sqo_submit(ctx);
/* fput will clean it up */
fput(file);
return ret;
diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c
index f277d023ebcd..c75719312147 100644
--- a/fs/kernfs/file.c
+++ b/fs/kernfs/file.c
@@ -14,6 +14,7 @@
#include <linux/pagemap.h>
#include <linux/sched/mm.h>
#include <linux/fsnotify.h>
+#include <linux/uio.h>
#include "kernfs-internal.h"
@@ -180,11 +181,10 @@ static const struct seq_operations kernfs_seq_ops = {
* it difficult to use seq_file. Implement simplistic custom buffering for
* bin files.
*/
-static ssize_t kernfs_file_direct_read(struct kernfs_open_file *of,
- char __user *user_buf, size_t count,
- loff_t *ppos)
+static ssize_t kernfs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
{
- ssize_t len = min_t(size_t, count, PAGE_SIZE);
+ struct kernfs_open_file *of = kernfs_of(iocb->ki_filp);
+ ssize_t len = min_t(size_t, iov_iter_count(iter), PAGE_SIZE);
const struct kernfs_ops *ops;
char *buf;
@@ -210,7 +210,7 @@ static ssize_t kernfs_file_direct_read(struct kernfs_open_file *of,
of->event = atomic_read(&of->kn->attr.open->event);
ops = kernfs_ops(of->kn);
if (ops->read)
- len = ops->read(of, buf, len, *ppos);
+ len = ops->read(of, buf, len, iocb->ki_pos);
else
len = -EINVAL;
@@ -220,12 +220,12 @@ static ssize_t kernfs_file_direct_read(struct kernfs_open_file *of,
if (len < 0)
goto out_free;
- if (copy_to_user(user_buf, buf, len)) {
+ if (copy_to_iter(buf, len, iter) != len) {
len = -EFAULT;
goto out_free;
}
- *ppos += len;
+ iocb->ki_pos += len;
out_free:
if (buf == of->prealloc_buf)
@@ -235,31 +235,14 @@ static ssize_t kernfs_file_direct_read(struct kernfs_open_file *of,
return len;
}
-/**
- * kernfs_fop_read - kernfs vfs read callback
- * @file: file pointer
- * @user_buf: data to write
- * @count: number of bytes
- * @ppos: starting offset
- */
-static ssize_t kernfs_fop_read(struct file *file, char __user *user_buf,
- size_t count, loff_t *ppos)
+static ssize_t kernfs_fop_read_iter(struct kiocb *iocb, struct iov_iter *iter)
{
- struct kernfs_open_file *of = kernfs_of(file);
-
- if (of->kn->flags & KERNFS_HAS_SEQ_SHOW)
- return seq_read(file, user_buf, count, ppos);
- else
- return kernfs_file_direct_read(of, user_buf, count, ppos);
+ if (kernfs_of(iocb->ki_filp)->kn->flags & KERNFS_HAS_SEQ_SHOW)
+ return seq_read_iter(iocb, iter);
+ return kernfs_file_read_iter(iocb, iter);
}
-/**
- * kernfs_fop_write - kernfs vfs write callback
- * @file: file pointer
- * @user_buf: data to write
- * @count: number of bytes
- * @ppos: starting offset
- *
+/*
* Copy data in from userland and pass it to the matching kernfs write
* operation.
*
@@ -269,20 +252,18 @@ static ssize_t kernfs_fop_read(struct file *file, char __user *user_buf,
* modify only the the value you're changing, then write entire buffer
* back.
*/
-static ssize_t kernfs_fop_write(struct file *file, const char __user *user_buf,
- size_t count, loff_t *ppos)
+static ssize_t kernfs_fop_write_iter(struct kiocb *iocb, struct iov_iter *iter)
{
- struct kernfs_open_file *of = kernfs_of(file);
+ struct kernfs_open_file *of = kernfs_of(iocb->ki_filp);
+ ssize_t len = iov_iter_count(iter);
const struct kernfs_ops *ops;
- ssize_t len;
char *buf;
if (of->atomic_write_len) {
- len = count;
if (len > of->atomic_write_len)
return -E2BIG;
} else {
- len = min_t(size_t, count, PAGE_SIZE);
+ len = min_t(size_t, len, PAGE_SIZE);
}
buf = of->prealloc_buf;
@@ -293,7 +274,7 @@ static ssize_t kernfs_fop_write(struct file *file, const char __user *user_buf,
if (!buf)
return -ENOMEM;
- if (copy_from_user(buf, user_buf, len)) {
+ if (copy_from_iter(buf, len, iter) != len) {
len = -EFAULT;
goto out_free;
}
@@ -312,7 +293,7 @@ static ssize_t kernfs_fop_write(struct file *file, const char __user *user_buf,
ops = kernfs_ops(of->kn);
if (ops->write)
- len = ops->write(of, buf, len, *ppos);
+ len = ops->write(of, buf, len, iocb->ki_pos);
else
len = -EINVAL;
@@ -320,7 +301,7 @@ static ssize_t kernfs_fop_write(struct file *file, const char __user *user_buf,
mutex_unlock(&of->mutex);
if (len > 0)
- *ppos += len;
+ iocb->ki_pos += len;
out_free:
if (buf == of->prealloc_buf)
@@ -673,7 +654,7 @@ static int kernfs_fop_open(struct inode *inode, struct file *file)
/*
* Write path needs to atomic_write_len outside active reference.
- * Cache it in open_file. See kernfs_fop_write() for details.
+ * Cache it in open_file. See kernfs_fop_write_iter() for details.
*/
of->atomic_write_len = ops->atomic_write_len;
@@ -960,14 +941,16 @@ void kernfs_notify(struct kernfs_node *kn)
EXPORT_SYMBOL_GPL(kernfs_notify);
const struct file_operations kernfs_file_fops = {
- .read = kernfs_fop_read,
- .write = kernfs_fop_write,
+ .read_iter = kernfs_fop_read_iter,
+ .write_iter = kernfs_fop_write_iter,
.llseek = generic_file_llseek,
.mmap = kernfs_fop_mmap,
.open = kernfs_fop_open,
.release = kernfs_fop_release,
.poll = kernfs_fop_poll,
.fsync = noop_fsync,
+ .splice_read = generic_file_splice_read,
+ .splice_write = iter_file_splice_write,
};
/**
diff --git a/fs/namespace.c b/fs/namespace.c
index d2db7dfe232b..9d33909d0f9e 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -1713,8 +1713,6 @@ static int can_umount(const struct path *path, int flags)
{
struct mount *mnt = real_mount(path->mnt);
- if (flags & ~(MNT_FORCE | MNT_DETACH | MNT_EXPIRE | UMOUNT_NOFOLLOW))
- return -EINVAL;
if (!may_mount())
return -EPERM;
if (path->dentry != path->mnt->mnt_root)
@@ -1728,6 +1726,7 @@ static int can_umount(const struct path *path, int flags)
return 0;
}
+// caller is responsible for flags being sane
int path_umount(struct path *path, int flags)
{
struct mount *mnt = real_mount(path->mnt);
@@ -1749,6 +1748,10 @@ static int ksys_umount(char __user *name, int flags)
struct path path;
int ret;
+ // basic validity checks done first
+ if (flags & ~(MNT_FORCE | MNT_DETACH | MNT_EXPIRE | UMOUNT_NOFOLLOW))
+ return -EINVAL;
+
if (!(flags & UMOUNT_NOFOLLOW))
lookup_flags |= LOOKUP_FOLLOW;
ret = user_path_at(AT_FDCWD, name, lookup_flags, &path);
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index 816e1427f17e..04bf8066980c 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -1011,22 +1011,24 @@ nfs_delegation_find_inode_server(struct nfs_server *server,
const struct nfs_fh *fhandle)
{
struct nfs_delegation *delegation;
- struct inode *freeme, *res = NULL;
+ struct super_block *freeme = NULL;
+ struct inode *res = NULL;
list_for_each_entry_rcu(delegation, &server->delegations, super_list) {
spin_lock(&delegation->lock);
if (delegation->inode != NULL &&
!test_bit(NFS_DELEGATION_REVOKED, &delegation->flags) &&
nfs_compare_fh(fhandle, &NFS_I(delegation->inode)->fh) == 0) {
- freeme = igrab(delegation->inode);
- if (freeme && nfs_sb_active(freeme->i_sb))
- res = freeme;
+ if (nfs_sb_active(server->super)) {
+ freeme = server->super;
+ res = igrab(delegation->inode);
+ }
spin_unlock(&delegation->lock);
if (res != NULL)
return res;
if (freeme) {
rcu_read_unlock();
- iput(freeme);
+ nfs_sb_deactive(freeme);
rcu_read_lock();
}
return ERR_PTR(-EAGAIN);
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index b840d0a91c9d..62d3189745cd 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -136,9 +136,29 @@ struct nfs_fs_context {
} clone_data;
};
-#define nfs_errorf(fc, fmt, ...) errorf(fc, fmt, ## __VA_ARGS__)
-#define nfs_invalf(fc, fmt, ...) invalf(fc, fmt, ## __VA_ARGS__)
-#define nfs_warnf(fc, fmt, ...) warnf(fc, fmt, ## __VA_ARGS__)
+#define nfs_errorf(fc, fmt, ...) ((fc)->log.log ? \
+ errorf(fc, fmt, ## __VA_ARGS__) : \
+ ({ dprintk(fmt "\n", ## __VA_ARGS__); }))
+
+#define nfs_ferrorf(fc, fac, fmt, ...) ((fc)->log.log ? \
+ errorf(fc, fmt, ## __VA_ARGS__) : \
+ ({ dfprintk(fac, fmt "\n", ## __VA_ARGS__); }))
+
+#define nfs_invalf(fc, fmt, ...) ((fc)->log.log ? \
+ invalf(fc, fmt, ## __VA_ARGS__) : \
+ ({ dprintk(fmt "\n", ## __VA_ARGS__); -EINVAL; }))
+
+#define nfs_finvalf(fc, fac, fmt, ...) ((fc)->log.log ? \
+ invalf(fc, fmt, ## __VA_ARGS__) : \
+ ({ dfprintk(fac, fmt "\n", ## __VA_ARGS__); -EINVAL; }))
+
+#define nfs_warnf(fc, fmt, ...) ((fc)->log.log ? \
+ warnf(fc, fmt, ## __VA_ARGS__) : \
+ ({ dprintk(fmt "\n", ## __VA_ARGS__); }))
+
+#define nfs_fwarnf(fc, fac, fmt, ...) ((fc)->log.log ? \
+ warnf(fc, fmt, ## __VA_ARGS__) : \
+ ({ dfprintk(fac, fmt "\n", ## __VA_ARGS__); }))
static inline struct nfs_fs_context *nfs_fc2context(const struct fs_context *fc)
{
@@ -579,12 +599,14 @@ extern void nfs4_test_session_trunk(struct rpc_clnt *clnt,
static inline struct inode *nfs_igrab_and_active(struct inode *inode)
{
- inode = igrab(inode);
- if (inode != NULL && !nfs_sb_active(inode->i_sb)) {
- iput(inode);
- inode = NULL;
+ struct super_block *sb = inode->i_sb;
+
+ if (sb && nfs_sb_active(sb)) {
+ if (igrab(inode))
+ return inode;
+ nfs_sb_deactive(sb);
}
- return inode;
+ return NULL;
}
static inline void nfs_iput_and_deactive(struct inode *inode)
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 0ce04e0e5d82..2f4679a62712 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -3536,10 +3536,8 @@ static void nfs4_close_done(struct rpc_task *task, void *data)
trace_nfs4_close(state, &calldata->arg, &calldata->res, task->tk_status);
/* Handle Layoutreturn errors */
- if (pnfs_roc_done(task, calldata->inode,
- &calldata->arg.lr_args,
- &calldata->res.lr_res,
- &calldata->res.lr_ret) == -EAGAIN)
+ if (pnfs_roc_done(task, &calldata->arg.lr_args, &calldata->res.lr_res,
+ &calldata->res.lr_ret) == -EAGAIN)
goto out_restart;
/* hmm. we are done with the inode, and in the process of freeing
@@ -6384,10 +6382,8 @@ static void nfs4_delegreturn_done(struct rpc_task *task, void *calldata)
trace_nfs4_delegreturn_exit(&data->args, &data->res, task->tk_status);
/* Handle Layoutreturn errors */
- if (pnfs_roc_done(task, data->inode,
- &data->args.lr_args,
- &data->res.lr_res,
- &data->res.lr_ret) == -EAGAIN)
+ if (pnfs_roc_done(task, &data->args.lr_args, &data->res.lr_res,
+ &data->res.lr_ret) == -EAGAIN)
goto out_restart;
switch (task->tk_status) {
@@ -6441,10 +6437,10 @@ static void nfs4_delegreturn_release(void *calldata)
struct nfs4_delegreturndata *data = calldata;
struct inode *inode = data->inode;
+ if (data->lr.roc)
+ pnfs_roc_release(&data->lr.arg, &data->lr.res,
+ data->res.lr_ret);
if (inode) {
- if (data->lr.roc)
- pnfs_roc_release(&data->lr.arg, &data->lr.res,
- data->res.lr_ret);
nfs_post_op_update_inode_force_wcc(inode, &data->fattr);
nfs_iput_and_deactive(inode);
}
@@ -6520,16 +6516,14 @@ static int _nfs4_proc_delegreturn(struct inode *inode, const struct cred *cred,
nfs_fattr_init(data->res.fattr);
data->timestamp = jiffies;
data->rpc_status = 0;
- data->lr.roc = pnfs_roc(inode, &data->lr.arg, &data->lr.res, cred);
data->inode = nfs_igrab_and_active(inode);
- if (data->inode) {
+ if (data->inode || issync) {
+ data->lr.roc = pnfs_roc(inode, &data->lr.arg, &data->lr.res,
+ cred);
if (data->lr.roc) {
data->args.lr_args = &data->lr.arg;
data->res.lr_res = &data->lr.res;
}
- } else if (data->lr.roc) {
- pnfs_roc_release(&data->lr.arg, &data->lr.res, 0);
- data->lr.roc = false;
}
task_setup_data.callback_data = data;
@@ -7111,9 +7105,9 @@ static int _nfs4_do_setlk(struct nfs4_state *state, int cmd, struct file_lock *f
data->arg.new_lock_owner, ret);
} else
data->cancelled = true;
+ trace_nfs4_set_lock(fl, state, &data->res.stateid, cmd, ret);
rpc_put_task(task);
dprintk("%s: done, ret = %d!\n", __func__, ret);
- trace_nfs4_set_lock(fl, state, &data->res.stateid, cmd, ret);
return ret;
}
diff --git a/fs/nfs/nfs4super.c b/fs/nfs/nfs4super.c
index 984cc42ee54d..d09bcfd7db89 100644
--- a/fs/nfs/nfs4super.c
+++ b/fs/nfs/nfs4super.c
@@ -227,7 +227,7 @@ int nfs4_try_get_tree(struct fs_context *fc)
fc, ctx->nfs_server.hostname,
ctx->nfs_server.export_path);
if (err) {
- nfs_errorf(fc, "NFS4: Couldn't follow remote path");
+ nfs_ferrorf(fc, MOUNT, "NFS4: Couldn't follow remote path");
dfprintk(MOUNT, "<-- nfs4_try_get_tree() = %d [error]\n", err);
} else {
dfprintk(MOUNT, "<-- nfs4_try_get_tree() = 0\n");
@@ -250,7 +250,7 @@ int nfs4_get_referral_tree(struct fs_context *fc)
fc, ctx->nfs_server.hostname,
ctx->nfs_server.export_path);
if (err) {
- nfs_errorf(fc, "NFS4: Couldn't follow remote path");
+ nfs_ferrorf(fc, MOUNT, "NFS4: Couldn't follow remote path");
dfprintk(MOUNT, "<-- nfs4_get_referral_tree() = %d [error]\n", err);
} else {
dfprintk(MOUNT, "<-- nfs4_get_referral_tree() = 0\n");
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 07f59dc8cb2e..af64b4e6fd1f 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -324,6 +324,21 @@ pnfs_grab_inode_layout_hdr(struct pnfs_layout_hdr *lo)
return NULL;
}
+/*
+ * Compare 2 layout stateid sequence ids, to see which is newer,
+ * taking into account wraparound issues.
+ */
+static bool pnfs_seqid_is_newer(u32 s1, u32 s2)
+{
+ return (s32)(s1 - s2) > 0;
+}
+
+static void pnfs_barrier_update(struct pnfs_layout_hdr *lo, u32 newseq)
+{
+ if (pnfs_seqid_is_newer(newseq, lo->plh_barrier))
+ lo->plh_barrier = newseq;
+}
+
static void
pnfs_set_plh_return_info(struct pnfs_layout_hdr *lo, enum pnfs_iomode iomode,
u32 seq)
@@ -335,6 +350,7 @@ pnfs_set_plh_return_info(struct pnfs_layout_hdr *lo, enum pnfs_iomode iomode,
if (seq != 0) {
WARN_ON_ONCE(lo->plh_return_seq != 0 && lo->plh_return_seq != seq);
lo->plh_return_seq = seq;
+ pnfs_barrier_update(lo, seq);
}
}
@@ -639,15 +655,6 @@ static int mark_lseg_invalid(struct pnfs_layout_segment *lseg,
return rv;
}
-/*
- * Compare 2 layout stateid sequence ids, to see which is newer,
- * taking into account wraparound issues.
- */
-static bool pnfs_seqid_is_newer(u32 s1, u32 s2)
-{
- return (s32)(s1 - s2) > 0;
-}
-
static bool
pnfs_should_free_range(const struct pnfs_layout_range *lseg_range,
const struct pnfs_layout_range *recall_range)
@@ -984,8 +991,7 @@ pnfs_set_layout_stateid(struct pnfs_layout_hdr *lo, const nfs4_stateid *new,
new_barrier = be32_to_cpu(new->seqid);
else if (new_barrier == 0)
return;
- if (pnfs_seqid_is_newer(new_barrier, lo->plh_barrier))
- lo->plh_barrier = new_barrier;
+ pnfs_barrier_update(lo, new_barrier);
}
static bool
@@ -994,7 +1000,7 @@ pnfs_layout_stateid_blocked(const struct pnfs_layout_hdr *lo,
{
u32 seqid = be32_to_cpu(stateid->seqid);
- return !pnfs_seqid_is_newer(seqid, lo->plh_barrier);
+ return !pnfs_seqid_is_newer(seqid, lo->plh_barrier) && lo->plh_barrier;
}
/* lget is set to 1 if called from inside send_layoutget call chain */
@@ -1152,7 +1158,7 @@ void pnfs_layoutreturn_free_lsegs(struct pnfs_layout_hdr *lo,
LIST_HEAD(freeme);
spin_lock(&inode->i_lock);
- if (!pnfs_layout_is_valid(lo) || !arg_stateid ||
+ if (!pnfs_layout_is_valid(lo) ||
!nfs4_stateid_match_other(&lo->plh_stateid, arg_stateid))
goto out_unlock;
if (stateid) {
@@ -1183,20 +1189,17 @@ pnfs_prepare_layoutreturn(struct pnfs_layout_hdr *lo,
return false;
set_bit(NFS_LAYOUT_RETURN, &lo->plh_flags);
pnfs_get_layout_hdr(lo);
+ nfs4_stateid_copy(stateid, &lo->plh_stateid);
+ *cred = get_cred(lo->plh_lc_cred);
if (test_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags)) {
- nfs4_stateid_copy(stateid, &lo->plh_stateid);
- *cred = get_cred(lo->plh_lc_cred);
if (lo->plh_return_seq != 0)
stateid->seqid = cpu_to_be32(lo->plh_return_seq);
if (iomode != NULL)
*iomode = lo->plh_return_iomode;
pnfs_clear_layoutreturn_info(lo);
- return true;
- }
- nfs4_stateid_copy(stateid, &lo->plh_stateid);
- *cred = get_cred(lo->plh_lc_cred);
- if (iomode != NULL)
+ } else if (iomode != NULL)
*iomode = IOMODE_ANY;
+ pnfs_barrier_update(lo, be32_to_cpu(stateid->seqid));
return true;
}
@@ -1509,10 +1512,8 @@ out_noroc:
return false;
}
-int pnfs_roc_done(struct rpc_task *task, struct inode *inode,
- struct nfs4_layoutreturn_args **argpp,
- struct nfs4_layoutreturn_res **respp,
- int *ret)
+int pnfs_roc_done(struct rpc_task *task, struct nfs4_layoutreturn_args **argpp,
+ struct nfs4_layoutreturn_res **respp, int *ret)
{
struct nfs4_layoutreturn_args *arg = *argpp;
int retval = -EAGAIN;
@@ -1545,7 +1546,7 @@ int pnfs_roc_done(struct rpc_task *task, struct inode *inode,
return 0;
case -NFS4ERR_OLD_STATEID:
if (!nfs4_layout_refresh_old_stateid(&arg->stateid,
- &arg->range, inode))
+ &arg->range, arg->inode))
break;
*ret = -NFS4ERR_NOMATCHING_LAYOUT;
return -EAGAIN;
@@ -1560,23 +1561,28 @@ void pnfs_roc_release(struct nfs4_layoutreturn_args *args,
int ret)
{
struct pnfs_layout_hdr *lo = args->layout;
- const nfs4_stateid *arg_stateid = NULL;
+ struct inode *inode = args->inode;
const nfs4_stateid *res_stateid = NULL;
struct nfs4_xdr_opaque_data *ld_private = args->ld_private;
switch (ret) {
case -NFS4ERR_NOMATCHING_LAYOUT:
+ spin_lock(&inode->i_lock);
+ if (pnfs_layout_is_valid(lo) &&
+ nfs4_stateid_match_other(&args->stateid, &lo->plh_stateid))
+ pnfs_set_plh_return_info(lo, args->range.iomode, 0);
+ pnfs_clear_layoutreturn_waitbit(lo);
+ spin_unlock(&inode->i_lock);
break;
case 0:
if (res->lrs_present)
res_stateid = &res->stateid;
fallthrough;
default:
- arg_stateid = &args->stateid;
+ pnfs_layoutreturn_free_lsegs(lo, &args->stateid, &args->range,
+ res_stateid);
}
trace_nfs4_layoutreturn_on_close(args->inode, &args->stateid, ret);
- pnfs_layoutreturn_free_lsegs(lo, arg_stateid, &args->range,
- res_stateid);
if (ld_private && ld_private->ops && ld_private->ops->free)
ld_private->ops->free(ld_private);
pnfs_put_layout_hdr(lo);
@@ -1906,6 +1912,11 @@ static void nfs_layoutget_end(struct pnfs_layout_hdr *lo)
wake_up_var(&lo->plh_outstanding);
}
+static bool pnfs_is_first_layoutget(struct pnfs_layout_hdr *lo)
+{
+ return test_bit(NFS_LAYOUT_FIRST_LAYOUTGET, &lo->plh_flags);
+}
+
static void pnfs_clear_first_layoutget(struct pnfs_layout_hdr *lo)
{
unsigned long *bitlock = &lo->plh_flags;
@@ -2015,6 +2026,27 @@ lookup_again:
goto lookup_again;
}
+ /*
+ * Because we free lsegs when sending LAYOUTRETURN, we need to wait
+ * for LAYOUTRETURN.
+ */
+ if (test_bit(NFS_LAYOUT_RETURN, &lo->plh_flags)) {
+ spin_unlock(&ino->i_lock);
+ dprintk("%s wait for layoutreturn\n", __func__);
+ lseg = ERR_PTR(pnfs_prepare_to_retry_layoutget(lo));
+ if (!IS_ERR(lseg)) {
+ pnfs_put_layout_hdr(lo);
+ dprintk("%s retrying\n", __func__);
+ trace_pnfs_update_layout(ino, pos, count, iomode, lo,
+ lseg,
+ PNFS_UPDATE_LAYOUT_RETRY);
+ goto lookup_again;
+ }
+ trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg,
+ PNFS_UPDATE_LAYOUT_RETURN);
+ goto out_put_layout_hdr;
+ }
+
lseg = pnfs_find_lseg(lo, &arg, strict_iomode);
if (lseg) {
trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg,
@@ -2067,28 +2099,6 @@ lookup_again:
nfs4_stateid_copy(&stateid, &lo->plh_stateid);
}
- /*
- * Because we free lsegs before sending LAYOUTRETURN, we need to wait
- * for LAYOUTRETURN even if first is true.
- */
- if (test_bit(NFS_LAYOUT_RETURN, &lo->plh_flags)) {
- spin_unlock(&ino->i_lock);
- dprintk("%s wait for layoutreturn\n", __func__);
- lseg = ERR_PTR(pnfs_prepare_to_retry_layoutget(lo));
- if (!IS_ERR(lseg)) {
- if (first)
- pnfs_clear_first_layoutget(lo);
- pnfs_put_layout_hdr(lo);
- dprintk("%s retrying\n", __func__);
- trace_pnfs_update_layout(ino, pos, count, iomode, lo,
- lseg, PNFS_UPDATE_LAYOUT_RETRY);
- goto lookup_again;
- }
- trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg,
- PNFS_UPDATE_LAYOUT_RETURN);
- goto out_put_layout_hdr;
- }
-
if (pnfs_layoutgets_blocked(lo)) {
trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg,
PNFS_UPDATE_LAYOUT_BLOCKED);
@@ -2242,6 +2252,7 @@ static void _lgopen_prepare_attached(struct nfs4_opendata *data,
&rng, GFP_KERNEL);
if (!lgp) {
pnfs_clear_first_layoutget(lo);
+ nfs_layoutget_end(lo);
pnfs_put_layout_hdr(lo);
return;
}
@@ -2380,23 +2391,34 @@ pnfs_layout_process(struct nfs4_layoutget *lgp)
goto out_forget;
}
- if (!pnfs_layout_is_valid(lo)) {
- /* We have a completely new layout */
- pnfs_set_layout_stateid(lo, &res->stateid, lgp->cred, true);
- } else if (nfs4_stateid_match_other(&lo->plh_stateid, &res->stateid)) {
+ if (nfs4_stateid_match_other(&lo->plh_stateid, &res->stateid)) {
/* existing state ID, make sure the sequence number matches. */
if (pnfs_layout_stateid_blocked(lo, &res->stateid)) {
+ if (!pnfs_layout_is_valid(lo) &&
+ pnfs_is_first_layoutget(lo))
+ lo->plh_barrier = 0;
dprintk("%s forget reply due to sequence\n", __func__);
goto out_forget;
}
pnfs_set_layout_stateid(lo, &res->stateid, lgp->cred, false);
- } else {
+ } else if (pnfs_layout_is_valid(lo)) {
/*
* We got an entirely new state ID. Mark all segments for the
* inode invalid, and retry the layoutget
*/
- pnfs_mark_layout_stateid_invalid(lo, &free_me);
+ struct pnfs_layout_range range = {
+ .iomode = IOMODE_ANY,
+ .length = NFS4_MAX_UINT64,
+ };
+ pnfs_set_plh_return_info(lo, IOMODE_ANY, 0);
+ pnfs_mark_matching_lsegs_return(lo, &lo->plh_return_segs,
+ &range, 0);
goto out_forget;
+ } else {
+ /* We have a completely new layout */
+ if (!pnfs_is_first_layoutget(lo))
+ goto out_forget;
+ pnfs_set_layout_stateid(lo, &res->stateid, lgp->cred, true);
}
pnfs_get_lseg(lseg);
diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
index bbd3de1025f2..d810ae674f4e 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -297,10 +297,8 @@ bool pnfs_roc(struct inode *ino,
struct nfs4_layoutreturn_args *args,
struct nfs4_layoutreturn_res *res,
const struct cred *cred);
-int pnfs_roc_done(struct rpc_task *task, struct inode *inode,
- struct nfs4_layoutreturn_args **argpp,
- struct nfs4_layoutreturn_res **respp,
- int *ret);
+int pnfs_roc_done(struct rpc_task *task, struct nfs4_layoutreturn_args **argpp,
+ struct nfs4_layoutreturn_res **respp, int *ret);
void pnfs_roc_release(struct nfs4_layoutreturn_args *args,
struct nfs4_layoutreturn_res *res,
int ret);
@@ -772,7 +770,7 @@ pnfs_roc(struct inode *ino,
}
static inline int
-pnfs_roc_done(struct rpc_task *task, struct inode *inode,
+pnfs_roc_done(struct rpc_task *task,
struct nfs4_layoutreturn_args **argpp,
struct nfs4_layoutreturn_res **respp,
int *ret)
diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c
index 2efcfdd348a1..49d3389bd813 100644
--- a/fs/nfs/pnfs_nfs.c
+++ b/fs/nfs/pnfs_nfs.c
@@ -78,22 +78,18 @@ void
pnfs_generic_clear_request_commit(struct nfs_page *req,
struct nfs_commit_info *cinfo)
{
- struct pnfs_layout_segment *freeme = NULL;
+ struct pnfs_commit_bucket *bucket = NULL;
if (!test_and_clear_bit(PG_COMMIT_TO_DS, &req->wb_flags))
goto out;
cinfo->ds->nwritten--;
- if (list_is_singular(&req->wb_list)) {
- struct pnfs_commit_bucket *bucket;
-
+ if (list_is_singular(&req->wb_list))
bucket = list_first_entry(&req->wb_list,
- struct pnfs_commit_bucket,
- written);
- freeme = pnfs_free_bucket_lseg(bucket);
- }
+ struct pnfs_commit_bucket, written);
out:
nfs_request_remove_commit_list(req, cinfo);
- pnfs_put_lseg(freeme);
+ if (bucket)
+ pnfs_put_lseg(pnfs_free_bucket_lseg(bucket));
}
EXPORT_SYMBOL_GPL(pnfs_generic_clear_request_commit);
@@ -407,12 +403,16 @@ pnfs_bucket_get_committing(struct list_head *head,
struct pnfs_commit_bucket *bucket,
struct nfs_commit_info *cinfo)
{
+ struct pnfs_layout_segment *lseg;
struct list_head *pos;
list_for_each(pos, &bucket->committing)
cinfo->ds->ncommitting--;
list_splice_init(&bucket->committing, head);
- return pnfs_free_bucket_lseg(bucket);
+ lseg = pnfs_free_bucket_lseg(bucket);
+ if (!lseg)
+ lseg = pnfs_get_lseg(bucket->lseg);
+ return lseg;
}
static struct nfs_commit_data *
@@ -424,8 +424,6 @@ pnfs_bucket_fetch_commitdata(struct pnfs_commit_bucket *bucket,
if (!data)
return NULL;
data->lseg = pnfs_bucket_get_committing(&data->pages, bucket, cinfo);
- if (!data->lseg)
- data->lseg = pnfs_get_lseg(bucket->lseg);
return data;
}
diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c
index 821db21ba072..34b880211e5e 100644
--- a/fs/nfsd/nfs3xdr.c
+++ b/fs/nfsd/nfs3xdr.c
@@ -865,9 +865,14 @@ compose_entry_fh(struct nfsd3_readdirres *cd, struct svc_fh *fhp,
if (isdotent(name, namlen)) {
if (namlen == 2) {
dchild = dget_parent(dparent);
- /* filesystem root - cannot return filehandle for ".." */
+ /*
+ * Don't return filehandle for ".." if we're at
+ * the filesystem or export root:
+ */
if (dchild == dparent)
goto out;
+ if (dparent == exp->ex_path.dentry)
+ goto out;
} else
dchild = dget(dparent);
} else
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 4727b7f03c5b..8d6d2678abad 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -50,6 +50,11 @@
#include "pnfs.h"
#include "trace.h"
+static bool inter_copy_offload_enable;
+module_param(inter_copy_offload_enable, bool, 0644);
+MODULE_PARM_DESC(inter_copy_offload_enable,
+ "Enable inter server to server copy offload. Default: false");
+
#ifdef CONFIG_NFSD_V4_SECURITY_LABEL
#include <linux/security.h>
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 45ee6b12ce5b..eaaa1605b5b5 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -147,6 +147,25 @@ svcxdr_dupstr(struct nfsd4_compoundargs *argp, void *buf, u32 len)
return p;
}
+static void *
+svcxdr_savemem(struct nfsd4_compoundargs *argp, __be32 *p, u32 len)
+{
+ __be32 *tmp;
+
+ /*
+ * The location of the decoded data item is stable,
+ * so @p is OK to use. This is the common case.
+ */
+ if (p != argp->xdr->scratch.iov_base)
+ return p;
+
+ tmp = svcxdr_tmpalloc(argp, len);
+ if (!tmp)
+ return NULL;
+ memcpy(tmp, p, len);
+ return tmp;
+}
+
/*
* NFSv4 basic data type decoders
*/
@@ -183,11 +202,10 @@ nfsd4_decode_opaque(struct nfsd4_compoundargs *argp, struct xdr_netobj *o)
p = xdr_inline_decode(argp->xdr, len);
if (!p)
return nfserr_bad_xdr;
- o->data = svcxdr_tmpalloc(argp, len);
+ o->data = svcxdr_savemem(argp, p, len);
if (!o->data)
return nfserr_jukebox;
o->len = len;
- memcpy(o->data, p, len);
return nfs_ok;
}
@@ -205,10 +223,9 @@ nfsd4_decode_component4(struct nfsd4_compoundargs *argp, char **namp, u32 *lenp)
status = check_filename((char *)p, *lenp);
if (status)
return status;
- *namp = svcxdr_tmpalloc(argp, *lenp);
+ *namp = svcxdr_savemem(argp, p, *lenp);
if (!*namp)
return nfserr_jukebox;
- memcpy(*namp, p, *lenp);
return nfs_ok;
}
@@ -1200,10 +1217,9 @@ nfsd4_decode_putfh(struct nfsd4_compoundargs *argp, struct nfsd4_putfh *putfh)
p = xdr_inline_decode(argp->xdr, putfh->pf_fhlen);
if (!p)
return nfserr_bad_xdr;
- putfh->pf_fhval = svcxdr_tmpalloc(argp, putfh->pf_fhlen);
+ putfh->pf_fhval = svcxdr_savemem(argp, p, putfh->pf_fhlen);
if (!putfh->pf_fhval)
return nfserr_jukebox;
- memcpy(putfh->pf_fhval, p, putfh->pf_fhlen);
return nfs_ok;
}
@@ -1318,24 +1334,20 @@ nfsd4_decode_setclientid(struct nfsd4_compoundargs *argp, struct nfsd4_setclient
p = xdr_inline_decode(argp->xdr, setclientid->se_callback_netid_len);
if (!p)
return nfserr_bad_xdr;
- setclientid->se_callback_netid_val = svcxdr_tmpalloc(argp,
+ setclientid->se_callback_netid_val = svcxdr_savemem(argp, p,
setclientid->se_callback_netid_len);
if (!setclientid->se_callback_netid_val)
return nfserr_jukebox;
- memcpy(setclientid->se_callback_netid_val, p,
- setclientid->se_callback_netid_len);
if (xdr_stream_decode_u32(argp->xdr, &setclientid->se_callback_addr_len) < 0)
return nfserr_bad_xdr;
p = xdr_inline_decode(argp->xdr, setclientid->se_callback_addr_len);
if (!p)
return nfserr_bad_xdr;
- setclientid->se_callback_addr_val = svcxdr_tmpalloc(argp,
+ setclientid->se_callback_addr_val = svcxdr_savemem(argp, p,
setclientid->se_callback_addr_len);
if (!setclientid->se_callback_addr_val)
return nfserr_jukebox;
- memcpy(setclientid->se_callback_addr_val, p,
- setclientid->se_callback_addr_len);
if (xdr_stream_decode_u32(argp->xdr, &setclientid->se_callback_ident) < 0)
return nfserr_bad_xdr;
@@ -1375,10 +1387,9 @@ nfsd4_decode_verify(struct nfsd4_compoundargs *argp, struct nfsd4_verify *verify
p = xdr_inline_decode(argp->xdr, verify->ve_attrlen);
if (!p)
return nfserr_bad_xdr;
- verify->ve_attrval = svcxdr_tmpalloc(argp, verify->ve_attrlen);
+ verify->ve_attrval = svcxdr_savemem(argp, p, verify->ve_attrlen);
if (!verify->ve_attrval)
return nfserr_jukebox;
- memcpy(verify->ve_attrval, p, verify->ve_attrlen);
return nfs_ok;
}
@@ -2333,10 +2344,9 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp)
p = xdr_inline_decode(argp->xdr, argp->taglen);
if (!p)
return 0;
- argp->tag = svcxdr_tmpalloc(argp, argp->taglen);
+ argp->tag = svcxdr_savemem(argp, p, argp->taglen);
if (!argp->tag)
return 0;
- memcpy(argp->tag, p, argp->taglen);
max_reply += xdr_align_size(argp->taglen);
}
@@ -4756,6 +4766,7 @@ nfsd4_encode_read_plus_data(struct nfsd4_compoundres *resp,
resp->rqstp->rq_vec, read->rd_vlen, maxcount, eof);
if (nfserr)
return nfserr;
+ xdr_truncate_encode(xdr, starting_len + 16 + xdr_align_size(*maxcount));
tmp = htonl(NFS4_CONTENT_DATA);
write_bytes_to_xdr_buf(xdr->buf, starting_len, &tmp, 4);
@@ -4763,6 +4774,10 @@ nfsd4_encode_read_plus_data(struct nfsd4_compoundres *resp,
write_bytes_to_xdr_buf(xdr->buf, starting_len + 4, &tmp64, 8);
tmp = htonl(*maxcount);
write_bytes_to_xdr_buf(xdr->buf, starting_len + 12, &tmp, 4);
+
+ tmp = xdr_zero;
+ write_bytes_to_xdr_buf(xdr->buf, starting_len + 16 + *maxcount, &tmp,
+ xdr_pad_size(*maxcount));
return nfs_ok;
}
@@ -4855,14 +4870,15 @@ out:
if (nfserr && segments == 0)
xdr_truncate_encode(xdr, starting_len);
else {
- tmp = htonl(eof);
- write_bytes_to_xdr_buf(xdr->buf, starting_len, &tmp, 4);
- tmp = htonl(segments);
- write_bytes_to_xdr_buf(xdr->buf, starting_len + 4, &tmp, 4);
if (nfserr) {
xdr_truncate_encode(xdr, last_segment);
nfserr = nfs_ok;
+ eof = 0;
}
+ tmp = htonl(eof);
+ write_bytes_to_xdr_buf(xdr->buf, starting_len, &tmp, 4);
+ tmp = htonl(segments);
+ write_bytes_to_xdr_buf(xdr->buf, starting_len + 4, &tmp, 4);
}
return nfserr;
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index 00384c332f9b..f9c9f4c63cc7 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -33,12 +33,6 @@
#define NFSDDBG_FACILITY NFSDDBG_SVC
-bool inter_copy_offload_enable;
-EXPORT_SYMBOL_GPL(inter_copy_offload_enable);
-module_param(inter_copy_offload_enable, bool, 0644);
-MODULE_PARM_DESC(inter_copy_offload_enable,
- "Enable inter server to server copy offload. Default: false");
-
extern struct svc_program nfsd_program;
static int nfsd(void *vrqstp);
#if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL)
diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h
index a60ff5ce1a37..c300885ae75d 100644
--- a/fs/nfsd/xdr4.h
+++ b/fs/nfsd/xdr4.h
@@ -568,7 +568,6 @@ struct nfsd4_copy {
struct nfs_fh c_fh;
nfs4_stateid stateid;
};
-extern bool inter_copy_offload_enable;
struct nfsd4_seek {
/* request */
diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
index e5b616c93e11..0fed532efa68 100644
--- a/fs/overlayfs/copy_up.c
+++ b/fs/overlayfs/copy_up.c
@@ -84,6 +84,14 @@ int ovl_copy_xattr(struct super_block *sb, struct dentry *old,
if (ovl_is_private_xattr(sb, name))
continue;
+
+ error = security_inode_copy_up_xattr(name);
+ if (error < 0 && error != -EOPNOTSUPP)
+ break;
+ if (error == 1) {
+ error = 0;
+ continue; /* Discard */
+ }
retry:
size = vfs_getxattr(old, name, value, value_size);
if (size == -ERANGE)
@@ -107,13 +115,6 @@ retry:
goto retry;
}
- error = security_inode_copy_up_xattr(name);
- if (error < 0 && error != -EOPNOTSUPP)
- break;
- if (error == 1) {
- error = 0;
- continue; /* Discard */
- }
error = vfs_setxattr(new, name, value, size, 0);
if (error) {
if (error != -EOPNOTSUPP || ovl_must_copy_xattr(name))
diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c
index 28a075b5f5b2..d1efa3a5a503 100644
--- a/fs/overlayfs/dir.c
+++ b/fs/overlayfs/dir.c
@@ -992,8 +992,8 @@ static char *ovl_get_redirect(struct dentry *dentry, bool abs_redirect)
buflen -= thislen;
memcpy(&buf[buflen], name, thislen);
- tmp = dget_dlock(d->d_parent);
spin_unlock(&d->d_lock);
+ tmp = dget_parent(d);
dput(d);
d = tmp;
diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c
index bd9dd38347ae..077d3ad343f6 100644
--- a/fs/overlayfs/file.c
+++ b/fs/overlayfs/file.c
@@ -398,8 +398,9 @@ static int ovl_fsync(struct file *file, loff_t start, loff_t end, int datasync)
const struct cred *old_cred;
int ret;
- if (!ovl_should_sync(OVL_FS(file_inode(file)->i_sb)))
- return 0;
+ ret = ovl_sync_status(OVL_FS(file_inode(file)->i_sb));
+ if (ret <= 0)
+ return ret;
ret = ovl_real_fdget_meta(file, &real, !datasync);
if (ret)
diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c
index d739e14c6814..cf41bcb664bc 100644
--- a/fs/overlayfs/inode.c
+++ b/fs/overlayfs/inode.c
@@ -352,7 +352,9 @@ int ovl_xattr_set(struct dentry *dentry, struct inode *inode, const char *name,
goto out;
if (!value && !upperdentry) {
+ old_cred = ovl_override_creds(dentry->d_sb);
err = vfs_getxattr(realdentry, name, NULL, 0);
+ revert_creds(old_cred);
if (err < 0)
goto out_drop_write;
}
diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h
index b487e48c7fd4..cb4e2d60ecf9 100644
--- a/fs/overlayfs/overlayfs.h
+++ b/fs/overlayfs/overlayfs.h
@@ -324,6 +324,7 @@ int ovl_check_metacopy_xattr(struct ovl_fs *ofs, struct dentry *dentry);
bool ovl_is_metacopy_dentry(struct dentry *dentry);
char *ovl_get_redirect_xattr(struct ovl_fs *ofs, struct dentry *dentry,
int padding);
+int ovl_sync_status(struct ovl_fs *ofs);
static inline bool ovl_is_impuredir(struct super_block *sb,
struct dentry *dentry)
diff --git a/fs/overlayfs/ovl_entry.h b/fs/overlayfs/ovl_entry.h
index fbd5e27ce66b..63efee554f69 100644
--- a/fs/overlayfs/ovl_entry.h
+++ b/fs/overlayfs/ovl_entry.h
@@ -81,6 +81,8 @@ struct ovl_fs {
atomic_long_t last_ino;
/* Whiteout dentry cache */
struct dentry *whiteout;
+ /* r/o snapshot of upperdir sb's only taken on volatile mounts */
+ errseq_t errseq;
};
static inline struct vfsmount *ovl_upper_mnt(struct ovl_fs *ofs)
diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c
index 01620ebae1bd..f404a78e6b60 100644
--- a/fs/overlayfs/readdir.c
+++ b/fs/overlayfs/readdir.c
@@ -865,7 +865,7 @@ struct file *ovl_dir_real_file(const struct file *file, bool want_upper)
struct ovl_dir_file *od = file->private_data;
struct dentry *dentry = file->f_path.dentry;
- struct file *realfile = od->realfile;
+ struct file *old, *realfile = od->realfile;
if (!OVL_TYPE_UPPER(ovl_path_type(dentry)))
return want_upper ? NULL : realfile;
@@ -874,29 +874,20 @@ struct file *ovl_dir_real_file(const struct file *file, bool want_upper)
* Need to check if we started out being a lower dir, but got copied up
*/
if (!od->is_upper) {
- struct inode *inode = file_inode(file);
-
realfile = READ_ONCE(od->upperfile);
if (!realfile) {
struct path upperpath;
ovl_path_upper(dentry, &upperpath);
realfile = ovl_dir_open_realfile(file, &upperpath);
+ if (IS_ERR(realfile))
+ return realfile;
- inode_lock(inode);
- if (!od->upperfile) {
- if (IS_ERR(realfile)) {
- inode_unlock(inode);
- return realfile;
- }
- smp_store_release(&od->upperfile, realfile);
- } else {
- /* somebody has beaten us to it */
- if (!IS_ERR(realfile))
- fput(realfile);
- realfile = od->upperfile;
+ old = cmpxchg_release(&od->upperfile, NULL, realfile);
+ if (old) {
+ fput(realfile);
+ realfile = old;
}
- inode_unlock(inode);
}
}
@@ -909,8 +900,9 @@ static int ovl_dir_fsync(struct file *file, loff_t start, loff_t end,
struct file *realfile;
int err;
- if (!ovl_should_sync(OVL_FS(file->f_path.dentry->d_sb)))
- return 0;
+ err = ovl_sync_status(OVL_FS(file->f_path.dentry->d_sb));
+ if (err <= 0)
+ return err;
realfile = ovl_dir_real_file(file, true);
err = PTR_ERR_OR_ZERO(realfile);
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index 2bd570cbe8a4..d58b8f2bf9d0 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -264,11 +264,20 @@ static int ovl_sync_fs(struct super_block *sb, int wait)
struct super_block *upper_sb;
int ret;
- if (!ovl_upper_mnt(ofs))
- return 0;
+ ret = ovl_sync_status(ofs);
+ /*
+ * We have to always set the err, because the return value isn't
+ * checked in syncfs, and instead indirectly return an error via
+ * the sb's writeback errseq, which VFS inspects after this call.
+ */
+ if (ret < 0) {
+ errseq_set(&sb->s_wb_err, -EIO);
+ return -EIO;
+ }
+
+ if (!ret)
+ return ret;
- if (!ovl_should_sync(ofs))
- return 0;
/*
* Not called for sync(2) call or an emergency sync (SB_I_SKIP_SYNC).
* All the super blocks will be iterated, including upper_sb.
@@ -1923,6 +1932,10 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
unsigned int numlower;
int err;
+ err = -EIO;
+ if (WARN_ON(sb->s_user_ns != current_user_ns()))
+ goto out;
+
sb->s_d_op = &ovl_dentry_operations;
err = -ENOMEM;
@@ -1989,6 +2002,8 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
sb->s_op = &ovl_super_operations;
if (ofs->config.upperdir) {
+ struct super_block *upper_sb;
+
if (!ofs->config.workdir) {
pr_err("missing 'workdir'\n");
goto out_err;
@@ -1998,6 +2013,16 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
if (err)
goto out_err;
+ upper_sb = ovl_upper_mnt(ofs)->mnt_sb;
+ if (!ovl_should_sync(ofs)) {
+ ofs->errseq = errseq_sample(&upper_sb->s_wb_err);
+ if (errseq_check(&upper_sb->s_wb_err, ofs->errseq)) {
+ err = -EIO;
+ pr_err("Cannot mount volatile when upperdir has an unseen error. Sync upperdir fs to clear state.\n");
+ goto out_err;
+ }
+ }
+
err = ovl_get_workdir(sb, ofs, &upperpath);
if (err)
goto out_err;
@@ -2005,9 +2030,8 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
if (!ofs->workdir)
sb->s_flags |= SB_RDONLY;
- sb->s_stack_depth = ovl_upper_mnt(ofs)->mnt_sb->s_stack_depth;
- sb->s_time_gran = ovl_upper_mnt(ofs)->mnt_sb->s_time_gran;
-
+ sb->s_stack_depth = upper_sb->s_stack_depth;
+ sb->s_time_gran = upper_sb->s_time_gran;
}
oe = ovl_get_lowerstack(sb, splitlower, numlower, ofs, layers);
err = PTR_ERR(oe);
diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c
index 6569031af3cd..9826b003f1d2 100644
--- a/fs/overlayfs/util.c
+++ b/fs/overlayfs/util.c
@@ -962,3 +962,30 @@ err_free:
kfree(buf);
return ERR_PTR(res);
}
+
+/*
+ * ovl_sync_status() - Check fs sync status for volatile mounts
+ *
+ * Returns 1 if this is not a volatile mount and a real sync is required.
+ *
+ * Returns 0 if syncing can be skipped because mount is volatile, and no errors
+ * have occurred on the upperdir since the mount.
+ *
+ * Returns -errno if it is a volatile mount, and the error that occurred since
+ * the last mount. If the error code changes, it'll return the latest error
+ * code.
+ */
+
+int ovl_sync_status(struct ovl_fs *ofs)
+{
+ struct vfsmount *mnt;
+
+ if (ovl_should_sync(ofs))
+ return 1;
+
+ mnt = ovl_upper_mnt(ofs);
+ if (!mnt)
+ return 0;
+
+ return errseq_check(&mnt->mnt_sb->s_wb_err, ofs->errseq);
+}
diff --git a/fs/pipe.c b/fs/pipe.c
index c5989cfd564d..39c96845a72f 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -1206,6 +1206,7 @@ const struct file_operations pipefifo_fops = {
.unlocked_ioctl = pipe_ioctl,
.release = pipe_release,
.fasync = pipe_fasync,
+ .splice_write = iter_file_splice_write,
};
/*
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index 317899222d7f..d2018f70d1fa 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -1770,6 +1770,12 @@ static int process_sysctl_arg(char *param, char *val,
return 0;
}
+ if (!val)
+ return -EINVAL;
+ len = strlen(val);
+ if (len == 0)
+ return -EINVAL;
+
/*
* To set sysctl options, we use a temporary mount of proc, look up the
* respective sys/ file and write to it. To avoid mounting it when no
@@ -1811,7 +1817,6 @@ static int process_sysctl_arg(char *param, char *val,
file, param, val);
goto out;
}
- len = strlen(val);
wret = kernel_write(file, val, len, &pos);
if (wret < 0) {
err = wret;
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index ee5a235b3056..602e3a52884d 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -1035,6 +1035,25 @@ struct clear_refs_private {
};
#ifdef CONFIG_MEM_SOFT_DIRTY
+
+#define is_cow_mapping(flags) (((flags) & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE)
+
+static inline bool pte_is_pinned(struct vm_area_struct *vma, unsigned long addr, pte_t pte)
+{
+ struct page *page;
+
+ if (!pte_write(pte))
+ return false;
+ if (!is_cow_mapping(vma->vm_flags))
+ return false;
+ if (likely(!atomic_read(&vma->vm_mm->has_pinned)))
+ return false;
+ page = vm_normal_page(vma, addr, pte);
+ if (!page)
+ return false;
+ return page_maybe_dma_pinned(page);
+}
+
static inline void clear_soft_dirty(struct vm_area_struct *vma,
unsigned long addr, pte_t *pte)
{
@@ -1049,6 +1068,8 @@ static inline void clear_soft_dirty(struct vm_area_struct *vma,
if (pte_present(ptent)) {
pte_t old_pte;
+ if (pte_is_pinned(vma, addr, ptent))
+ return;
old_pte = ptep_modify_prot_start(vma, addr, pte);
ptent = pte_wrprotect(old_pte);
ptent = pte_clear_soft_dirty(ptent);
@@ -1215,41 +1236,26 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
.type = type,
};
+ if (mmap_write_lock_killable(mm)) {
+ count = -EINTR;
+ goto out_mm;
+ }
if (type == CLEAR_REFS_MM_HIWATER_RSS) {
- if (mmap_write_lock_killable(mm)) {
- count = -EINTR;
- goto out_mm;
- }
-
/*
* Writing 5 to /proc/pid/clear_refs resets the peak
* resident set size to this mm's current rss value.
*/
reset_mm_hiwater_rss(mm);
- mmap_write_unlock(mm);
- goto out_mm;
+ goto out_unlock;
}
- if (mmap_read_lock_killable(mm)) {
- count = -EINTR;
- goto out_mm;
- }
tlb_gather_mmu(&tlb, mm, 0, -1);
if (type == CLEAR_REFS_SOFT_DIRTY) {
for (vma = mm->mmap; vma; vma = vma->vm_next) {
if (!(vma->vm_flags & VM_SOFTDIRTY))
continue;
- mmap_read_unlock(mm);
- if (mmap_write_lock_killable(mm)) {
- count = -EINTR;
- goto out_mm;
- }
- for (vma = mm->mmap; vma; vma = vma->vm_next) {
- vma->vm_flags &= ~VM_SOFTDIRTY;
- vma_set_page_prot(vma);
- }
- mmap_write_downgrade(mm);
- break;
+ vma->vm_flags &= ~VM_SOFTDIRTY;
+ vma_set_page_prot(vma);
}
mmu_notifier_range_init(&range, MMU_NOTIFY_SOFT_DIRTY,
@@ -1261,7 +1267,8 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
if (type == CLEAR_REFS_SOFT_DIRTY)
mmu_notifier_invalidate_range_end(&range);
tlb_finish_mmu(&tlb, 0, -1);
- mmap_read_unlock(mm);
+out_unlock:
+ mmap_write_unlock(mm);
out_mm:
mmput(mm);
}
diff --git a/fs/udf/super.c b/fs/udf/super.c
index 5bef3a68395d..d0df217f4712 100644
--- a/fs/udf/super.c
+++ b/fs/udf/super.c
@@ -705,6 +705,7 @@ static int udf_check_vsd(struct super_block *sb)
struct buffer_head *bh = NULL;
int nsr = 0;
struct udf_sb_info *sbi;
+ loff_t session_offset;
sbi = UDF_SB(sb);
if (sb->s_blocksize < sizeof(struct volStructDesc))
@@ -712,7 +713,8 @@ static int udf_check_vsd(struct super_block *sb)
else
sectorsize = sb->s_blocksize;
- sector += (((loff_t)sbi->s_session) << sb->s_blocksize_bits);
+ session_offset = (loff_t)sbi->s_session << sb->s_blocksize_bits;
+ sector += session_offset;
udf_debug("Starting at sector %u (%lu byte sectors)\n",
(unsigned int)(sector >> sb->s_blocksize_bits),
@@ -757,8 +759,7 @@ static int udf_check_vsd(struct super_block *sb)
if (nsr > 0)
return 1;
- else if (!bh && sector - (sbi->s_session << sb->s_blocksize_bits) ==
- VSD_FIRST_SECTOR_OFFSET)
+ else if (!bh && sector - session_offset == VSD_FIRST_SECTOR_OFFSET)
return -1;
else
return 0;