fs: add a new SB_I_NOUMASK flag

SB_POSIXACL must be set when a filesystem supports POSIX ACLs, but NFSv4
also sets this flag to prevent the VFS from applying the umask on
newly-created files. NFSv4 doesn't support POSIX ACLs however, which
causes confusion when other subsystems try to test for them.

Add a new SB_I_NOUMASK flag that allows filesystems to opt-in to umask
stripping without advertising support for POSIX ACLs. Set the new flag
on NFSv4 instead of SB_POSIXACL.

Also, move mode_strip_umask to namei.h and convert init_mknod and
init_mkdir to use it.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
Message-Id: <20230911-acl-fix-v3-1-b25315333f6c@kernel.org>
Signed-off-by: Christian Brauner <brauner@kernel.org>

diff --git a/fs/init.c b/fs/init.c
index 9684406a8416481b66039582edaefc3cbaecf310..e9387b6c4f304860f66feb6470de00b8b80f9e05 100644 (file)
--- a/fs/init.c
+++ b/fs/init.c
@@ -153,8 +153,7 @@ int __init init_mknod(const char *filename, umode_t mode, unsigned int dev)
        if (IS_ERR(dentry))
                return PTR_ERR(dentry);
 
-       if (!IS_POSIXACL(path.dentry->d_inode))
-               mode &= ~current_umask();
+       mode = mode_strip_umask(d_inode(path.dentry), mode);
        error = security_path_mknod(&path, dentry, mode, dev);
        if (!error)
                error = vfs_mknod(mnt_idmap(path.mnt), path.dentry->d_inode,
@@ -229,8 +228,7 @@ int __init init_mkdir(const char *pathname, umode_t mode)
        dentry = kern_path_create(AT_FDCWD, pathname, &path, LOOKUP_DIRECTORY);
        if (IS_ERR(dentry))
                return PTR_ERR(dentry);
-       if (!IS_POSIXACL(path.dentry->d_inode))
-               mode &= ~current_umask();
+       mode = mode_strip_umask(d_inode(path.dentry), mode);
        error = security_path_mkdir(&path, dentry, mode);
        if (!error)
                error = vfs_mkdir(mnt_idmap(path.mnt), path.dentry->d_inode,

diff --git a/fs/namei.c b/fs/namei.c
index 567ee547492bc24096cad45c9c64aef84491fe42..94b27370f468c8cfd4c96aa06be7741f43e75abb 100644 (file)
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -3103,25 +3103,6 @@ void unlock_rename(struct dentry *p1, struct dentry *p2)
 }
 EXPORT_SYMBOL(unlock_rename);
 
-/**
- * mode_strip_umask - handle vfs umask stripping
- * @dir:       parent directory of the new inode
- * @mode:      mode of the new inode to be created in @dir
- *
- * Umask stripping depends on whether or not the filesystem supports POSIX
- * ACLs. If the filesystem doesn't support it umask stripping is done directly
- * in here. If the filesystem does support POSIX ACLs umask stripping is
- * deferred until the filesystem calls posix_acl_create().
- *
- * Returns: mode
- */
-static inline umode_t mode_strip_umask(const struct inode *dir, umode_t mode)
-{
-       if (!IS_POSIXACL(dir))
-               mode &= ~current_umask();
-       return mode;
-}
-
 /**
  * vfs_prepare_mode - prepare the mode to be used for a new inode
  * @idmap:     idmap of the mount the inode was found from

diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 0d6473cb00cb3e0fd2736e7aeccd95ad588c8642..9b1cfca8112ae2e2e0b91d6634bffa01c1d1f0c7 100644 (file)
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -1071,7 +1071,7 @@ static void nfs_fill_super(struct super_block *sb, struct nfs_fs_context *ctx)
                sb->s_export_op = &nfs_export_ops;
                break;
        case 4:
-               sb->s_flags |= SB_POSIXACL;
+               sb->s_iflags |= SB_I_NOUMASK;
                sb->s_time_gran = 1;
                sb->s_time_min = S64_MIN;
                sb->s_time_max = S64_MAX;

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 4aeb3fa1192771cdd8e1e1ebdf18f9b08c983166..58dea591a341b3d1113ff4b09ac74885ee9de0de 100644 (file)
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1119,7 +1119,7 @@ extern int send_sigurg(struct fown_struct *fown);
 #define SB_NOATIME      BIT(10)        /* Do not update access times. */
 #define SB_NODIRATIME   BIT(11)        /* Do not update directory access times */
 #define SB_SILENT       BIT(15)
-#define SB_POSIXACL     BIT(16)        /* VFS does not apply the umask */
+#define SB_POSIXACL     BIT(16)        /* Supports POSIX ACLs */
 #define SB_INLINECRYPT  BIT(17)        /* Use blk-crypto for encrypted files */
 #define SB_KERNMOUNT    BIT(22)        /* this is a kern_mount call */
 #define SB_I_VERSION    BIT(23)        /* Update inode I_version field */
@@ -1166,6 +1166,7 @@ extern int send_sigurg(struct fown_struct *fown);
 #define SB_I_PERSB_BDI 0x00000200      /* has a per-sb bdi */
 #define SB_I_TS_EXPIRY_WARNED 0x00000400 /* warned about timestamp range expiry */
 #define SB_I_RETIRED   0x00000800      /* superblock shouldn't be reused */
+#define SB_I_NOUMASK   0x00001000      /* VFS does not apply umask */
 
 /* Possible states of 'frozen' field */
 enum {

diff --git a/include/linux/namei.h b/include/linux/namei.h
index 1463cbda488867ba33a8a844570f616187a91d51..e3619920f9f0111696e4664873782c369fa91496 100644 (file)
--- a/include/linux/namei.h
+++ b/include/linux/namei.h
@@ -92,6 +92,30 @@ extern struct dentry *lock_rename(struct dentry *, struct dentry *);
 extern struct dentry *lock_rename_child(struct dentry *, struct dentry *);
 extern void unlock_rename(struct dentry *, struct dentry *);
 
+/**
+ * mode_strip_umask - handle vfs umask stripping
+ * @dir:       parent directory of the new inode
+ * @mode:      mode of the new inode to be created in @dir
+ *
+ * In most filesystems, umask stripping depends on whether or not the
+ * filesystem supports POSIX ACLs. If the filesystem doesn't support it umask
+ * stripping is done directly in here. If the filesystem does support POSIX
+ * ACLs umask stripping is deferred until the filesystem calls
+ * posix_acl_create().
+ *
+ * Some filesystems (like NFSv4) also want to avoid umask stripping by the
+ * VFS, but don't support POSIX ACLs. Those filesystems can set SB_I_NOUMASK
+ * to get this effect without declaring that they support POSIX ACLs.
+ *
+ * Returns: mode
+ */
+static inline umode_t __must_check mode_strip_umask(const struct inode *dir, umode_t mode)
+{
+       if (!IS_POSIXACL(dir) && !(dir->i_sb->s_iflags & SB_I_NOUMASK))
+               mode &= ~current_umask();
+       return mode;
+}
+
 extern int __must_check nd_jump_link(const struct path *path);
 
 static inline void nd_terminate_link(void *name, size_t len, size_t maxlen)