On Wed, Feb 16, 2022 at 10:28:20AM +0100, Miklos Szeredi wrote: > So this is a fairly special situation. How about adding a new rwsem > (could possibly be global or per-fs)? > > - acquired for read in lock_rename() before inode locks > - acquired for write in do_linkat before inode locks, but only on retry Something like this: diff --git a/fs/namei.c b/fs/namei.c index 3f1829b3ab5b..dd6908cee49d 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -122,6 +122,8 @@ * PATH_MAX includes the nul terminator --RR. */ +static DECLARE_RWSEM(link_rwsem); + #define EMBEDDED_NAME_MAX (PATH_MAX - offsetof(struct filename, iname)) struct filename * @@ -2961,6 +2963,8 @@ struct dentry *lock_rename(struct dentry *p1, struct dentry *p2) { struct dentry *p; + down_read(&link_rwsem); + if (p1 == p2) { inode_lock_nested(p1->d_inode, I_MUTEX_PARENT); return NULL; @@ -2995,6 +2999,8 @@ void unlock_rename(struct dentry *p1, struct dentry *p2) inode_unlock(p2->d_inode); mutex_unlock(&p1->d_sb->s_vfs_rename_mutex); } + + up_read(&link_rwsem); } EXPORT_SYMBOL(unlock_rename); @@ -4456,6 +4462,7 @@ int do_linkat(int olddfd, struct filename *old, int newdfd, struct path old_path, new_path; struct inode *delegated_inode = NULL; int how = 0; + bool lock = false; int error; if ((flags & ~(AT_SYMLINK_FOLLOW | AT_EMPTY_PATH)) != 0) { @@ -4474,10 +4481,13 @@ int do_linkat(int olddfd, struct filename *old, int newdfd, if (flags & AT_SYMLINK_FOLLOW) how |= LOOKUP_FOLLOW; +retry_lock: + if (lock) + down_write(&link_rwsem); retry: error = filename_lookup(olddfd, old, how, &old_path, NULL); if (error) - goto out_putnames; + goto out_unlock_link; new_dentry = filename_create(newdfd, new, &new_path, (how & LOOKUP_REVAL)); @@ -4511,8 +4521,16 @@ int do_linkat(int olddfd, struct filename *old, int newdfd, how |= LOOKUP_REVAL; goto retry; } + if (!lock && error == -ENOENT) { + path_put(&old_path); + lock = true; + goto retry_lock; + } out_putpath: path_put(&old_path); +out_unlock_link: + if (lock) + up_write(&link_rwsem); out_putnames: putname(old); putname(new);