aboutsummaryrefslogtreecommitdiffstats
path: root/fs/ceph/dir.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/ceph/dir.c')
-rw-r--r--fs/ceph/dir.c96
1 files changed, 83 insertions, 13 deletions
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 133dbd9338e7..e7e2ebac330d 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -145,7 +145,7 @@ __dcache_find_get_entry(struct dentry *parent, u64 idx,
return ERR_PTR(-EAGAIN);
}
/* reading/filling the cache are serialized by
- i_mutex, no need to use page lock */
+ i_rwsem, no need to use page lock */
unlock_page(cache_ctl->page);
cache_ctl->dentries = kmap(cache_ctl->page);
}
@@ -155,7 +155,7 @@ __dcache_find_get_entry(struct dentry *parent, u64 idx,
rcu_read_lock();
spin_lock(&parent->d_lock);
/* check i_size again here, because empty directory can be
- * marked as complete while not holding the i_mutex. */
+ * marked as complete while not holding the i_rwsem. */
if (ceph_dir_is_complete_ordered(dir) && ptr_pos < i_size_read(dir))
dentry = cache_ctl->dentries[cache_ctl->index];
else
@@ -478,8 +478,11 @@ more:
2 : (fpos_off(rde->offset) + 1);
err = note_last_dentry(dfi, rde->name, rde->name_len,
next_offset);
- if (err)
+ if (err) {
+ ceph_mdsc_put_request(dfi->last_readdir);
+ dfi->last_readdir = NULL;
return err;
+ }
} else if (req->r_reply_info.dir_end) {
dfi->next_offset = 2;
/* keep last name */
@@ -520,6 +523,12 @@ more:
if (!dir_emit(ctx, rde->name, rde->name_len,
ceph_present_ino(inode->i_sb, le64_to_cpu(rde->inode.in->ino)),
le32_to_cpu(rde->inode.in->mode) >> 12)) {
+ /*
+ * NOTE: Here no need to put the 'dfi->last_readdir',
+ * because when dir_emit stops us it's most likely
+ * doesn't have enough memory, etc. So for next readdir
+ * it will continue.
+ */
dout("filldir stopping us...\n");
return 0;
}
@@ -671,7 +680,7 @@ struct dentry *ceph_handle_snapdir(struct ceph_mds_request *req,
struct dentry *dentry)
{
struct ceph_fs_client *fsc = ceph_sb_to_client(dentry->d_sb);
- struct inode *parent = d_inode(dentry->d_parent); /* we hold i_mutex */
+ struct inode *parent = d_inode(dentry->d_parent); /* we hold i_rwsem */
/* .snap dir? */
if (ceph_snap(parent) == CEPH_NOSNAP &&
@@ -847,6 +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;
@@ -909,6 +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;
@@ -959,9 +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;
@@ -971,6 +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;
}
@@ -1028,6 +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;
@@ -1062,9 +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;
@@ -1072,7 +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 */
@@ -1080,13 +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);
}
@@ -1171,6 +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));
@@ -1178,6 +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) {
/*
@@ -1186,10 +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);
@@ -1228,6 +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);
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.