vfs: allow mkdir to wait for delegation break on parent

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.

Add a new delegated_inode parameter to vfs_mkdir. All of the existing
callers set that to NULL for now, except for do_mkdirat which will
properly block until the lease is gone.

Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: NeilBrown <neil@brown.name>
Signed-off-by: Jeff Layton <jlayton@kernel.org>
Link: https://patch.msgid.link/20251111-dir-deleg-ro-v6-6-52f3feebb2f2@kernel.org
Signed-off-by: Christian Brauner <brauner@kernel.org>

diff --git a/drivers/base/devtmpfs.c b/drivers/base/devtmpfs.c
index 9d4e46ad8352257a6a65d85526ebdbf9bf2d4b19..0e79621cb0f79870003b867ca384199171ded4e0 100644 (file)
--- 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 d1edb2ac38376c4f9d2a18026450bb3c774f7824..50c0f9c76d1fd4c05db90d7d0d1bad574523ead0 100644 (file)
--- a/fs/cachefiles/namei.c
+++ b/fs/cachefiles/namei.c
@@ -130,7 +130,7 @@ retry:
                        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 ed1394da8d6bd7065f2a074378331f13fcda17f9..35830b3144f8f71374a78b3e7463b864f4fc216e 100644 (file)
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -508,7 +508,7 @@ 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 07f592ccdba868509d0f3aaf9936d8d890fdbec5..895f8a09a71acfd03e11164e3b441a7d4e2de146 100644 (file)
--- a/fs/init.c
+++ b/fs/init.c
@@ -233,7 +233,7 @@ 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 5bcf3e93d350ffd290f72725c378d3dffeeae364..76c0587d991ff7307e3dde69497719d716c8d7b8 100644 (file)
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -4407,10 +4407,11 @@ 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 parent inode, if the inode is delegated.
  *
  * Create a directory.
  *
@@ -4427,7 +4428,8 @@ 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 delegated_inode *delegated_inode)
 {
        int error;
        unsigned max_links = dir->i_sb->s_max_links;
@@ -4450,6 +4452,10 @@ 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))
@@ -4473,6 +4479,7 @@ int do_mkdirat(int dfd, struct filename *name, umode_t mode)
        struct path path;
        int error;
        unsigned int lookup_flags = LOOKUP_DIRECTORY;
+       struct delegated_inode delegated_inode = { };
 
 retry:
        dentry = filename_create(dfd, name, &path, lookup_flags);
@@ -4484,11 +4491,16 @@ retry:
                        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);
        }
        end_creating_path(&path, dentry);
+       if (is_delegated(&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 e2b9472e5c78c9f03731090ffdfb26eb5de38fe0..1f56834b2072fcee1d0d400bbb554b0c949ecab4 100644 (file)
--- a/fs/nfsd/nfs4recover.c
+++ b/fs/nfsd/nfs4recover.c
@@ -213,7 +213,7 @@ 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 9cb20d4aeab159ef3ba3584d1a3a33ef16ba4dea..97aef140cbf5fca4c41738fdcaccba3b57886463 100644 (file)
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -1558,7 +1558,7 @@ 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 c8fd5951fc5ece1ae6b3e2a0801ca15f9faf7d72..0f65f9a5d54d4786b39e4f4f30f416d5b9016e70 100644 (file)
--- 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 891ed2dc2b7351a5cb14a2241d71095ffdd03f08..3d2190f26623b23ea79c63410905a3c3ad684048 100644 (file)
--- a/fs/smb/server/vfs.c
+++ b/fs/smb/server/vfs.c
@@ -230,7 +230,7 @@ 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 (file)
--- 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 909a88e3979d4f1ba3104f3d05145e1096ed44d5..20bb4c8a4e8e1be7e11047d228c05920ea6c388d 100644 (file)
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2114,7 +2114,7 @@ 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 delegated_inode *);
 int vfs_mknod(struct mnt_idmap *, struct inode *, struct dentry *,
               umode_t, dev_t);
 int vfs_symlink(struct mnt_idmap *, struct inode *,