[PATCH v3 04/38] vfs: allow mkdir to wait for delegation break on parent
From: Jeff Layton <jlayton@kernel.org>
Date: 2025-09-24 18:06:28
Also in:
linux-cifs, linux-doc, linux-fsdevel, linux-nfs, linux-unionfs, linux-xfs, lkml, netfs
Subsystem:
cachefiles: fs-cache backend for caching on mounted filesystems, driver core, kobjects, debugfs and sysfs, ecrypt file system, filesystems (vfs and infrastructure), kernel nfsd, sunrpc, and lockd servers, kernel smb3 server (ksmbd), overlay filesystem, the rest, xfs filesystem · Maintainers:
David Howells, Greg Kroah-Hartman, "Rafael J. Wysocki", Danilo Krummrich, Tyler Hicks, Alexander Viro, Christian Brauner, Chuck Lever, Jeff Layton, Namjae Jeon, Steve French, Miklos Szeredi, Amir Goldstein, Linus Torvalds, Carlos Maiolino
In order to add directory delegation support, we need to break delegations on the parent whenever there is going to be a change in the directory. Rename the existing vfs_mkdir to __vfs_mkdir, make it static and add a new delegated_inode parameter. Add a new exported vfs_mkdir wrapper around it that passes a NULL pointer for delegated_inode. Signed-off-by: Jeff Layton <jlayton@kernel.org> --- drivers/base/devtmpfs.c | 2 +- fs/cachefiles/namei.c | 2 +- fs/ecryptfs/inode.c | 2 +- fs/init.c | 2 +- fs/namei.c | 24 ++++++++++++++++++------ fs/nfsd/nfs4recover.c | 2 +- fs/nfsd/vfs.c | 2 +- fs/overlayfs/overlayfs.h | 2 +- fs/smb/server/vfs.c | 2 +- fs/xfs/scrub/orphanage.c | 2 +- include/linux/fs.h | 2 +- 11 files changed, 28 insertions(+), 16 deletions(-)
diff --git a/drivers/base/devtmpfs.c b/drivers/base/devtmpfs.c
index 31bfb3194b4c29a1d6a002449045bf4e4141911d..a57da600ce7523e9e2755b78f75342bf4fa56ef6 100644
--- a/drivers/base/devtmpfs.c
+++ b/drivers/base/devtmpfs.c@@ -180,7 +180,7 @@ static int dev_mkdir(const char *name, umode_t mode) if (IS_ERR(dentry)) return PTR_ERR(dentry); - dentry = vfs_mkdir(&nop_mnt_idmap, d_inode(path.dentry), dentry, mode); + dentry = vfs_mkdir(&nop_mnt_idmap, d_inode(path.dentry), dentry, mode, NULL); if (!IS_ERR(dentry)) /* mark as kernel-created inode */ d_inode(dentry)->i_private = &thread;
diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c
index 91dfd02318772fa63050ecf40fa5625ab48ad589..b3dac91efec622261186fbba8e704ae9e782bea0 100644
--- a/fs/cachefiles/namei.c
+++ b/fs/cachefiles/namei.c@@ -130,7 +130,7 @@ struct dentry *cachefiles_get_directory(struct cachefiles_cache *cache, goto mkdir_error; ret = cachefiles_inject_write_error(); if (ret == 0) - subdir = vfs_mkdir(&nop_mnt_idmap, d_inode(dir), subdir, 0700); + subdir = vfs_mkdir(&nop_mnt_idmap, d_inode(dir), subdir, 0700, NULL); else subdir = ERR_PTR(ret); if (IS_ERR(subdir)) {
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index 72fbe1316ab8831bb4228d573278f32fe52b6b25..00f54c125b102856c33ffff24627475f40dcbc7b 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c@@ -517,7 +517,7 @@ static struct dentry *ecryptfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, goto out; lower_dentry = vfs_mkdir(&nop_mnt_idmap, lower_dir, - lower_dentry, mode); + lower_dentry, mode, NULL); rc = PTR_ERR(lower_dentry); if (IS_ERR(lower_dentry)) goto out;
diff --git a/fs/init.c b/fs/init.c
index eef5124885e372ac020d2923692116c5e884b3cf..dd5240ce8ad41f02367a54ddf1b6ac0aa28e9721 100644
--- a/fs/init.c
+++ b/fs/init.c@@ -232,7 +232,7 @@ int __init init_mkdir(const char *pathname, umode_t mode) error = security_path_mkdir(&path, dentry, mode); if (!error) { dentry = vfs_mkdir(mnt_idmap(path.mnt), path.dentry->d_inode, - dentry, mode); + dentry, mode, NULL); if (IS_ERR(dentry)) error = PTR_ERR(dentry); }
diff --git a/fs/namei.c b/fs/namei.c
index cd517eb232317d326e6d2fc5a60cb4c7569a137d..c939a58f16f9c4edded424475aff52f2c423d301 100644
--- a/fs/namei.c
+++ b/fs/namei.c@@ -4320,10 +4320,11 @@ SYSCALL_DEFINE3(mknod, const char __user *, filename, umode_t, mode, unsigned, d /** * vfs_mkdir - create directory returning correct dentry if possible - * @idmap: idmap of the mount the inode was found from - * @dir: inode of the parent directory - * @dentry: dentry of the child directory - * @mode: mode of the child directory + * @idmap: idmap of the mount the inode was found from + * @dir: inode of the parent directory + * @dentry: dentry of the child directory + * @mode: mode of the child directory + * @delegated_inode: returns victim inode, if the inode is delegated. * * Create a directory. *
@@ -4340,7 +4341,8 @@ SYSCALL_DEFINE3(mknod, const char __user *, filename, umode_t, mode, unsigned, d * In case of an error the dentry is dput() and an ERR_PTR() is returned. */ struct dentry *vfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, - struct dentry *dentry, umode_t mode) + struct dentry *dentry, umode_t mode, + struct inode **delegated_inode) { int error; unsigned max_links = dir->i_sb->s_max_links;
@@ -4363,6 +4365,10 @@ struct dentry *vfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, if (max_links && dir->i_nlink >= max_links) goto err; + error = try_break_deleg(dir, delegated_inode); + if (error) + goto err; + de = dir->i_op->mkdir(idmap, dir, dentry, mode); error = PTR_ERR(de); if (IS_ERR(de))
@@ -4386,6 +4392,7 @@ int do_mkdirat(int dfd, struct filename *name, umode_t mode) struct path path; int error; unsigned int lookup_flags = LOOKUP_DIRECTORY; + struct inode *delegated_inode = NULL; retry: dentry = filename_create(dfd, name, &path, lookup_flags);
@@ -4397,11 +4404,16 @@ int do_mkdirat(int dfd, struct filename *name, umode_t mode) mode_strip_umask(path.dentry->d_inode, mode)); if (!error) { dentry = vfs_mkdir(mnt_idmap(path.mnt), path.dentry->d_inode, - dentry, mode); + dentry, mode, &delegated_inode); if (IS_ERR(dentry)) error = PTR_ERR(dentry); } done_path_create(&path, dentry); + if (delegated_inode) { + error = break_deleg_wait(&delegated_inode); + if (!error) + goto retry; + } if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry;
diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c
index b1005abcb9035b2cf743200808a251b00af7e3f4..423dd102b51198ea7c447be2b9a0a5020c950dba 100644
--- a/fs/nfsd/nfs4recover.c
+++ b/fs/nfsd/nfs4recover.c@@ -202,7 +202,7 @@ nfsd4_create_clid_dir(struct nfs4_client *clp) * as well be forgiving and just succeed silently. */ goto out_put; - dentry = vfs_mkdir(&nop_mnt_idmap, d_inode(dir), dentry, S_IRWXU); + dentry = vfs_mkdir(&nop_mnt_idmap, d_inode(dir), dentry, 0700, NULL); if (IS_ERR(dentry)) status = PTR_ERR(dentry); out_put:
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 2026431500ecbc0cf5fb5d4af1a7632c611ce4f4..6f1275fdc8ac831aa0ea8da588f751eddff88df1 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c@@ -1560,7 +1560,7 @@ nfsd_create_locked(struct svc_rqst *rqstp, struct svc_fh *fhp, nfsd_check_ignore_resizing(iap); break; case S_IFDIR: - dchild = vfs_mkdir(&nop_mnt_idmap, dirp, dchild, iap->ia_mode); + dchild = vfs_mkdir(&nop_mnt_idmap, dirp, dchild, iap->ia_mode, NULL); if (IS_ERR(dchild)) { host_err = PTR_ERR(dchild); } else if (d_is_negative(dchild)) {
diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h
index bb0d7ded8e763a4a7a6fc506d966ed2f3bdb4f06..4a3a22f422c37d45e49a762cd3c9957aa2c6a485 100644
--- a/fs/overlayfs/overlayfs.h
+++ b/fs/overlayfs/overlayfs.h@@ -248,7 +248,7 @@ static inline struct dentry *ovl_do_mkdir(struct ovl_fs *ofs, { struct dentry *ret; - ret = vfs_mkdir(ovl_upper_mnt_idmap(ofs), dir, dentry, mode); + ret = vfs_mkdir(ovl_upper_mnt_idmap(ofs), dir, dentry, mode, NULL); pr_debug("mkdir(%pd2, 0%o) = %i\n", dentry, mode, PTR_ERR_OR_ZERO(ret)); return ret; }
diff --git a/fs/smb/server/vfs.c b/fs/smb/server/vfs.c
index 04539037108c93e285f4e9d6aa61f93a507ae5da..b0fb73b277876a56797f5cc8a5aa53f156bb7a26 100644
--- a/fs/smb/server/vfs.c
+++ b/fs/smb/server/vfs.c@@ -229,7 +229,7 @@ int ksmbd_vfs_mkdir(struct ksmbd_work *work, const char *name, umode_t mode) idmap = mnt_idmap(path.mnt); mode |= S_IFDIR; d = dentry; - dentry = vfs_mkdir(idmap, d_inode(path.dentry), dentry, mode); + dentry = vfs_mkdir(idmap, d_inode(path.dentry), dentry, mode, NULL); if (IS_ERR(dentry)) err = PTR_ERR(dentry); else if (d_is_negative(dentry))
diff --git a/fs/xfs/scrub/orphanage.c b/fs/xfs/scrub/orphanage.c
index 9c12cb8442311ca26b169e4d1567939ae44a5be0..91c9d07b97f306f57aebb9b69ba564b0c2cb8c17 100644
--- a/fs/xfs/scrub/orphanage.c
+++ b/fs/xfs/scrub/orphanage.c@@ -167,7 +167,7 @@ xrep_orphanage_create( */ if (d_really_is_negative(orphanage_dentry)) { orphanage_dentry = vfs_mkdir(&nop_mnt_idmap, root_inode, - orphanage_dentry, 0750); + orphanage_dentry, 0750, NULL); error = PTR_ERR(orphanage_dentry); if (IS_ERR(orphanage_dentry)) goto out_unlock_root;
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 74f2bfc519263c6411a8e3427e1bd6680a1121db..24a091509f12ce65a2c8343d438fccf423d3062b 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h@@ -1997,7 +1997,7 @@ bool inode_owner_or_capable(struct mnt_idmap *idmap, int vfs_create(struct mnt_idmap *, struct inode *, struct dentry *, umode_t, bool); struct dentry *vfs_mkdir(struct mnt_idmap *, struct inode *, - struct dentry *, umode_t); + struct dentry *, umode_t, struct inode **); int vfs_mknod(struct mnt_idmap *, struct inode *, struct dentry *, umode_t, dev_t); int vfs_symlink(struct mnt_idmap *, struct inode *,
--
2.51.0