summaryrefslogtreecommitdiff
path: root/fs/ceph/dir.c
diff options
context:
space:
mode:
authorXiubo Li <xiubli@redhat.com>2022-05-10 04:47:01 +0300
committerIlya Dryomov <idryomov@gmail.com>2022-08-03 01:54:12 +0300
commit4868e537fa867f82e38e37429d61d7bb8357d79b (patch)
treebadea4f6181c6755959c8a44c4b84f527da23cad /fs/ceph/dir.c
parent4f48d5da81ee7004a789c8aac2d0dfb2514c37f1 (diff)
downloadlinux-4868e537fa867f82e38e37429d61d7bb8357d79b.tar.xz
ceph: wait for the first reply of inflight async unlink
In async unlink case the kclient won't wait for the first reply from MDS and just drop all the links and unhash the dentry and then succeeds immediately. For any new create/link/rename,etc requests followed by using the same file names we must wait for the first reply of the inflight unlink request, or the MDS possibly will fail these following requests with -EEXIST if the inflight async unlink request was delayed for some reasons. And the worst case is that for the none async openc request it will successfully open the file if the CDentry hasn't been unlinked yet, but later the previous delayed async unlink request will remove the CDenty. That means the just created file is possiblly deleted later by accident. We need to wait for the inflight async unlink requests to finish when creating new files/directories by using the same file names. Link: https://tracker.ceph.com/issues/55332 Signed-off-by: Xiubo Li <xiubli@redhat.com> Reviewed-by: Jeff Layton <jlayton@kernel.org> Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Diffstat (limited to 'fs/ceph/dir.c')
-rw-r--r--fs/ceph/dir.c79
1 files changed, 70 insertions, 9 deletions
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index eae417d71136..e7e2ebac330d 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -856,6 +856,10 @@ static int ceph_mknod(struct user_namespace *mnt_userns, struct inode *dir,
if (ceph_snap(dir) != CEPH_NOSNAP)
return -EROFS;
+ err = ceph_wait_on_conflict_unlink(dentry);
+ if (err)
+ return err;
+
if (ceph_quota_is_max_files_exceeded(dir)) {
err = -EDQUOT;
goto out;
@@ -918,6 +922,10 @@ static int ceph_symlink(struct user_namespace *mnt_userns, struct inode *dir,
if (ceph_snap(dir) != CEPH_NOSNAP)
return -EROFS;
+ err = ceph_wait_on_conflict_unlink(dentry);
+ if (err)
+ return err;
+
if (ceph_quota_is_max_files_exceeded(dir)) {
err = -EDQUOT;
goto out;
@@ -968,9 +976,13 @@ static int ceph_mkdir(struct user_namespace *mnt_userns, struct inode *dir,
struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(dir->i_sb);
struct ceph_mds_request *req;
struct ceph_acl_sec_ctx as_ctx = {};
- int err = -EROFS;
+ int err;
int op;
+ err = ceph_wait_on_conflict_unlink(dentry);
+ if (err)
+ return err;
+
if (ceph_snap(dir) == CEPH_SNAPDIR) {
/* mkdir .snap/foo is a MKSNAP */
op = CEPH_MDS_OP_MKSNAP;
@@ -980,6 +992,7 @@ static int ceph_mkdir(struct user_namespace *mnt_userns, struct inode *dir,
dout("mkdir dir %p dn %p mode 0%ho\n", dir, dentry, mode);
op = CEPH_MDS_OP_MKDIR;
} else {
+ err = -EROFS;
goto out;
}
@@ -1037,6 +1050,10 @@ static int ceph_link(struct dentry *old_dentry, struct inode *dir,
struct ceph_mds_request *req;
int err;
+ err = ceph_wait_on_conflict_unlink(dentry);
+ if (err)
+ return err;
+
if (ceph_snap(dir) != CEPH_NOSNAP)
return -EROFS;
@@ -1071,9 +1088,27 @@ static int ceph_link(struct dentry *old_dentry, struct inode *dir,
static void ceph_async_unlink_cb(struct ceph_mds_client *mdsc,
struct ceph_mds_request *req)
{
+ struct dentry *dentry = req->r_dentry;
+ struct ceph_fs_client *fsc = ceph_sb_to_client(dentry->d_sb);
+ struct ceph_dentry_info *di = ceph_dentry(dentry);
int result = req->r_err ? req->r_err :
le32_to_cpu(req->r_reply_info.head->result);
+ if (!test_bit(CEPH_DENTRY_ASYNC_UNLINK_BIT, &di->flags))
+ pr_warn("%s dentry %p:%pd async unlink bit is not set\n",
+ __func__, dentry, dentry);
+
+ spin_lock(&fsc->async_unlink_conflict_lock);
+ hash_del_rcu(&di->hnode);
+ spin_unlock(&fsc->async_unlink_conflict_lock);
+
+ spin_lock(&dentry->d_lock);
+ di->flags &= ~CEPH_DENTRY_ASYNC_UNLINK;
+ wake_up_bit(&di->flags, CEPH_DENTRY_ASYNC_UNLINK_BIT);
+ spin_unlock(&dentry->d_lock);
+
+ synchronize_rcu();
+
if (result == -EJUKEBOX)
goto out;
@@ -1081,7 +1116,7 @@ static void ceph_async_unlink_cb(struct ceph_mds_client *mdsc,
if (result) {
int pathlen = 0;
u64 base = 0;
- char *path = ceph_mdsc_build_path(req->r_dentry, &pathlen,
+ char *path = ceph_mdsc_build_path(dentry, &pathlen,
&base, 0);
/* mark error on parent + clear complete */
@@ -1089,13 +1124,13 @@ static void ceph_async_unlink_cb(struct ceph_mds_client *mdsc,
ceph_dir_clear_complete(req->r_parent);
/* drop the dentry -- we don't know its status */
- if (!d_unhashed(req->r_dentry))
- d_drop(req->r_dentry);
+ if (!d_unhashed(dentry))
+ d_drop(dentry);
/* mark inode itself for an error (since metadata is bogus) */
mapping_set_error(req->r_old_inode->i_mapping, result);
- pr_warn("ceph: async unlink failure path=(%llx)%s result=%d!\n",
+ pr_warn("async unlink failure path=(%llx)%s result=%d!\n",
base, IS_ERR(path) ? "<<bad>>" : path, result);
ceph_mdsc_free_path(path, pathlen);
}
@@ -1180,6 +1215,8 @@ retry:
if (try_async && op == CEPH_MDS_OP_UNLINK &&
(req->r_dir_caps = get_caps_for_async_unlink(dir, dentry))) {
+ struct ceph_dentry_info *di = ceph_dentry(dentry);
+
dout("async unlink on %llu/%.*s caps=%s", ceph_ino(dir),
dentry->d_name.len, dentry->d_name.name,
ceph_cap_string(req->r_dir_caps));
@@ -1187,6 +1224,16 @@ retry:
req->r_callback = ceph_async_unlink_cb;
req->r_old_inode = d_inode(dentry);
ihold(req->r_old_inode);
+
+ spin_lock(&dentry->d_lock);
+ di->flags |= CEPH_DENTRY_ASYNC_UNLINK;
+ spin_unlock(&dentry->d_lock);
+
+ spin_lock(&fsc->async_unlink_conflict_lock);
+ hash_add_rcu(fsc->async_unlink_conflict, &di->hnode,
+ dentry->d_name.hash);
+ spin_unlock(&fsc->async_unlink_conflict_lock);
+
err = ceph_mdsc_submit_request(mdsc, dir, req);
if (!err) {
/*
@@ -1195,10 +1242,20 @@ retry:
*/
drop_nlink(inode);
d_delete(dentry);
- } else if (err == -EJUKEBOX) {
- try_async = false;
- ceph_mdsc_put_request(req);
- goto retry;
+ } else {
+ spin_lock(&fsc->async_unlink_conflict_lock);
+ hash_del_rcu(&di->hnode);
+ spin_unlock(&fsc->async_unlink_conflict_lock);
+
+ spin_lock(&dentry->d_lock);
+ di->flags &= ~CEPH_DENTRY_ASYNC_UNLINK;
+ spin_unlock(&dentry->d_lock);
+
+ if (err == -EJUKEBOX) {
+ try_async = false;
+ ceph_mdsc_put_request(req);
+ goto retry;
+ }
}
} else {
set_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags);
@@ -1237,6 +1294,10 @@ static int ceph_rename(struct user_namespace *mnt_userns, struct inode *old_dir,
(!ceph_quota_is_same_realm(old_dir, new_dir)))
return -EXDEV;
+ err = ceph_wait_on_conflict_unlink(new_dentry);
+ if (err)
+ return err;
+
dout("rename dir %p dentry %p to dir %p dentry %p\n",
old_dir, old_dentry, new_dir, new_dentry);
req = ceph_mdsc_create_request(mdsc, op, USE_AUTH_MDS);