overlayfs fixes for 5.11-rc7

-----BEGIN PGP SIGNATURE-----
 
 iHUEABYIAB0WIQSQHSd0lITzzeNWNm3h3BK/laaZPAUCYBuyTQAKCRDh3BK/laaZ
 PBBhAPwLy3ksQLhY7in4I8aKrSyWRpaCSAeLQUitxnX3eQiQnAD/S1EEIapwradV
 y4ou1PBRsGnhwNgArXODVCcTgqDJqw8=
 =GjU4
 -----END PGP SIGNATURE-----

Merge tag 'ovl-fixes-5.11-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/vfs

Pull overlayfs fixes from Miklos Szeredi:

 - Fix capability conversion and minor overlayfs bugs that are related
   to the unprivileged overlay mounts introduced in this cycle.

 - Fix two recent (v5.10) and one old (v4.10) bug.

 - Clean up security xattr copy-up (related to a SELinux regression).

* tag 'ovl-fixes-5.11-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/vfs:
  ovl: implement volatile-specific fsync error behaviour
  ovl: skip getxattr of security labels
  ovl: fix dentry leak in ovl_get_redirect
  ovl: avoid deadlock on directory ioctl
  cap: fix conversions on getxattr
  ovl: perform vfs_getxattr() with mounter creds
  ovl: add warning on user_ns mismatch

Documentation/filesystems/overlayfs.rst

@@ -586,6 +586,14 @@ without significant effort.
 The advantage of mounting with the "volatile" option is that all forms of
 sync calls to the upper filesystem are omitted.
 
+In order to avoid a giving a false sense of safety, the syncfs (and fsync)
+semantics of volatile mounts are slightly different than that of the rest of
+VFS.  If any writeback error occurs on the upperdir's filesystem after a
+volatile mount takes place, all sync functions will return an error.  Once this
+condition is reached, the filesystem will not recover, and every subsequent sync
+call will return an error, even if the upperdir has not experience a new error
+since the last sync call.
+
 When overlay is mounted with "volatile" option, the directory
 "$workdir/work/incompat/volatile" is created.  During next mount, overlay
 checks for this directory and refuses to mount if present. This is a strong

fs/overlayfs/copy_up.c

@@ -84,6 +84,14 @@ int ovl_copy_xattr(struct super_block *sb, struct dentry *old,
 
 		if (ovl_is_private_xattr(sb, name))
 			continue;
+
+		error = security_inode_copy_up_xattr(name);
+		if (error < 0 && error != -EOPNOTSUPP)
+			break;
+		if (error == 1) {
+			error = 0;
+			continue; /* Discard */
+		}
 retry:
 		size = vfs_getxattr(old, name, value, value_size);
 		if (size == -ERANGE)
@@ -107,13 +115,6 @@ int ovl_copy_xattr(struct super_block *sb, struct dentry *old,
 			goto retry;
 		}
 
-		error = security_inode_copy_up_xattr(name);
-		if (error < 0 && error != -EOPNOTSUPP)
-			break;
-		if (error == 1) {
-			error = 0;
-			continue; /* Discard */
-		}
 		error = vfs_setxattr(new, name, value, size, 0);
 		if (error) {
 			if (error != -EOPNOTSUPP || ovl_must_copy_xattr(name))

fs/overlayfs/dir.c

@@ -992,8 +992,8 @@ static char *ovl_get_redirect(struct dentry *dentry, bool abs_redirect)
 
 		buflen -= thislen;
 		memcpy(&buf[buflen], name, thislen);
-		tmp = dget_dlock(d->d_parent);
 		spin_unlock(&d->d_lock);
+		tmp = dget_parent(d);
 
 		dput(d);
 		d = tmp;

fs/overlayfs/file.c

@@ -398,8 +398,9 @@ static int ovl_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 	const struct cred *old_cred;
 	int ret;
 
-	if (!ovl_should_sync(OVL_FS(file_inode(file)->i_sb)))
-		return 0;
+	ret = ovl_sync_status(OVL_FS(file_inode(file)->i_sb));
+	if (ret <= 0)
+		return ret;
 
 	ret = ovl_real_fdget_meta(file, &real, !datasync);
 	if (ret)

fs/overlayfs/inode.c

@@ -352,7 +352,9 @@ int ovl_xattr_set(struct dentry *dentry, struct inode *inode, const char *name,
 		goto out;
 
 	if (!value && !upperdentry) {
+		old_cred = ovl_override_creds(dentry->d_sb);
 		err = vfs_getxattr(realdentry, name, NULL, 0);
+		revert_creds(old_cred);
 		if (err < 0)
 			goto out_drop_write;
 	}

fs/overlayfs/overlayfs.h

@@ -324,6 +324,7 @@ int ovl_check_metacopy_xattr(struct ovl_fs *ofs, struct dentry *dentry);
 bool ovl_is_metacopy_dentry(struct dentry *dentry);
 char *ovl_get_redirect_xattr(struct ovl_fs *ofs, struct dentry *dentry,
 			     int padding);
+int ovl_sync_status(struct ovl_fs *ofs);
 
 static inline bool ovl_is_impuredir(struct super_block *sb,
 				    struct dentry *dentry)

fs/overlayfs/ovl_entry.h

@@ -81,6 +81,8 @@ struct ovl_fs {
 	atomic_long_t last_ino;
 	/* Whiteout dentry cache */
 	struct dentry *whiteout;
+	/* r/o snapshot of upperdir sb's only taken on volatile mounts */
+	errseq_t errseq;
 };
 
 static inline struct vfsmount *ovl_upper_mnt(struct ovl_fs *ofs)

fs/overlayfs/readdir.c

@@ -865,7 +865,7 @@ struct file *ovl_dir_real_file(const struct file *file, bool want_upper)
 
 	struct ovl_dir_file *od = file->private_data;
 	struct dentry *dentry = file->f_path.dentry;
-	struct file *realfile = od->realfile;
+	struct file *old, *realfile = od->realfile;
 
 	if (!OVL_TYPE_UPPER(ovl_path_type(dentry)))
 		return want_upper ? NULL : realfile;
@@ -874,29 +874,20 @@ struct file *ovl_dir_real_file(const struct file *file, bool want_upper)
 	 * Need to check if we started out being a lower dir, but got copied up
 	 */
 	if (!od->is_upper) {
-		struct inode *inode = file_inode(file);
-
 		realfile = READ_ONCE(od->upperfile);
 		if (!realfile) {
 			struct path upperpath;
 
 			ovl_path_upper(dentry, &upperpath);
 			realfile = ovl_dir_open_realfile(file, &upperpath);
+			if (IS_ERR(realfile))
+				return realfile;
 
-			inode_lock(inode);
-			if (!od->upperfile) {
-				if (IS_ERR(realfile)) {
-					inode_unlock(inode);
-					return realfile;
-				}
-				smp_store_release(&od->upperfile, realfile);
-			} else {
-				/* somebody has beaten us to it */
-				if (!IS_ERR(realfile))
-					fput(realfile);
-				realfile = od->upperfile;
+			old = cmpxchg_release(&od->upperfile, NULL, realfile);
+			if (old) {
+				fput(realfile);
+				realfile = old;
 			}
-			inode_unlock(inode);
 		}
 	}
 
@@ -909,8 +900,9 @@ static int ovl_dir_fsync(struct file *file, loff_t start, loff_t end,
 	struct file *realfile;
 	int err;
 
-	if (!ovl_should_sync(OVL_FS(file->f_path.dentry->d_sb)))
-		return 0;
+	err = ovl_sync_status(OVL_FS(file->f_path.dentry->d_sb));
+	if (err <= 0)
+		return err;
 
 	realfile = ovl_dir_real_file(file, true);
 	err = PTR_ERR_OR_ZERO(realfile);

fs/overlayfs/super.c

@@ -264,11 +264,20 @@ static int ovl_sync_fs(struct super_block *sb, int wait)
 	struct super_block *upper_sb;
 	int ret;
 
-	if (!ovl_upper_mnt(ofs))
-		return 0;
+	ret = ovl_sync_status(ofs);
+	/*
+	 * We have to always set the err, because the return value isn't
+	 * checked in syncfs, and instead indirectly return an error via
+	 * the sb's writeback errseq, which VFS inspects after this call.
+	 */
+	if (ret < 0) {
+		errseq_set(&sb->s_wb_err, -EIO);
+		return -EIO;
+	}
+
+	if (!ret)
+		return ret;
 
-	if (!ovl_should_sync(ofs))
-		return 0;
 	/*
 	 * Not called for sync(2) call or an emergency sync (SB_I_SKIP_SYNC).
 	 * All the super blocks will be iterated, including upper_sb.
@@ -1923,6 +1932,10 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 	unsigned int numlower;
 	int err;
 
+	err = -EIO;
+	if (WARN_ON(sb->s_user_ns != current_user_ns()))
+		goto out;
+
 	sb->s_d_op = &ovl_dentry_operations;
 
 	err = -ENOMEM;
@@ -1989,6 +2002,8 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 	sb->s_op = &ovl_super_operations;
 
 	if (ofs->config.upperdir) {
+		struct super_block *upper_sb;
+
 		if (!ofs->config.workdir) {
 			pr_err("missing 'workdir'\n");
 			goto out_err;
@@ -1998,6 +2013,16 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 		if (err)
 			goto out_err;
 
+		upper_sb = ovl_upper_mnt(ofs)->mnt_sb;
+		if (!ovl_should_sync(ofs)) {
+			ofs->errseq = errseq_sample(&upper_sb->s_wb_err);
+			if (errseq_check(&upper_sb->s_wb_err, ofs->errseq)) {
+				err = -EIO;
+				pr_err("Cannot mount volatile when upperdir has an unseen error. Sync upperdir fs to clear state.\n");
+				goto out_err;
+			}
+		}
+
 		err = ovl_get_workdir(sb, ofs, &upperpath);
 		if (err)
 			goto out_err;
@@ -2005,9 +2030,8 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 		if (!ofs->workdir)
 			sb->s_flags |= SB_RDONLY;
 
-		sb->s_stack_depth = ovl_upper_mnt(ofs)->mnt_sb->s_stack_depth;
-		sb->s_time_gran = ovl_upper_mnt(ofs)->mnt_sb->s_time_gran;
-
+		sb->s_stack_depth = upper_sb->s_stack_depth;
+		sb->s_time_gran = upper_sb->s_time_gran;
 	}
 	oe = ovl_get_lowerstack(sb, splitlower, numlower, ofs, layers);
 	err = PTR_ERR(oe);

fs/overlayfs/util.c

@@ -962,3 +962,30 @@ char *ovl_get_redirect_xattr(struct ovl_fs *ofs, struct dentry *dentry,
 	kfree(buf);
 	return ERR_PTR(res);
 }
+
+/*
+ * ovl_sync_status() - Check fs sync status for volatile mounts
+ *
+ * Returns 1 if this is not a volatile mount and a real sync is required.
+ *
+ * Returns 0 if syncing can be skipped because mount is volatile, and no errors
+ * have occurred on the upperdir since the mount.
+ *
+ * Returns -errno if it is a volatile mount, and the error that occurred since
+ * the last mount. If the error code changes, it'll return the latest error
+ * code.
+ */
+
+int ovl_sync_status(struct ovl_fs *ofs)
+{
+	struct vfsmount *mnt;
+
+	if (ovl_should_sync(ofs))
+		return 1;
+
+	mnt = ovl_upper_mnt(ofs);
+	if (!mnt)
+		return 0;
+
+	return errseq_check(&mnt->mnt_sb->s_wb_err, ofs->errseq);
+}

security/commoncap.c

@@ -371,10 +371,11 @@ int cap_inode_getsecurity(struct inode *inode, const char *name, void **buffer,
 {
 	int size, ret;
 	kuid_t kroot;
+	u32 nsmagic, magic;
 	uid_t root, mappedroot;
 	char *tmpbuf = NULL;
 	struct vfs_cap_data *cap;
-	struct vfs_ns_cap_data *nscap;
+	struct vfs_ns_cap_data *nscap = NULL;
 	struct dentry *dentry;
 	struct user_namespace *fs_ns;
 
@@ -396,46 +397,61 @@ int cap_inode_getsecurity(struct inode *inode, const char *name, void **buffer,
 	fs_ns = inode->i_sb->s_user_ns;
 	cap = (struct vfs_cap_data *) tmpbuf;
 	if (is_v2header((size_t) ret, cap)) {
-		/* If this is sizeof(vfs_cap_data) then we're ok with the
-		 * on-disk value, so return that.  */
-		if (alloc)
-			*buffer = tmpbuf;
-		else
-			kfree(tmpbuf);
-		return ret;
-	} else if (!is_v3header((size_t) ret, cap)) {
-		kfree(tmpbuf);
-		return -EINVAL;
+		root = 0;
+	} else if (is_v3header((size_t) ret, cap)) {
+		nscap = (struct vfs_ns_cap_data *) tmpbuf;
+		root = le32_to_cpu(nscap->rootid);
+	} else {
+		size = -EINVAL;
+		goto out_free;
 	}
 
-	nscap = (struct vfs_ns_cap_data *) tmpbuf;
-	root = le32_to_cpu(nscap->rootid);
 	kroot = make_kuid(fs_ns, root);
 
 	/* If the root kuid maps to a valid uid in current ns, then return
 	 * this as a nscap. */
 	mappedroot = from_kuid(current_user_ns(), kroot);
 	if (mappedroot != (uid_t)-1 && mappedroot != (uid_t)0) {
+		size = sizeof(struct vfs_ns_cap_data);
 		if (alloc) {
-			*buffer = tmpbuf;
+			if (!nscap) {
+				/* v2 -> v3 conversion */
+				nscap = kzalloc(size, GFP_ATOMIC);
+				if (!nscap) {
+					size = -ENOMEM;
+					goto out_free;
+				}
+				nsmagic = VFS_CAP_REVISION_3;
+				magic = le32_to_cpu(cap->magic_etc);
+				if (magic & VFS_CAP_FLAGS_EFFECTIVE)
+					nsmagic |= VFS_CAP_FLAGS_EFFECTIVE;
+				memcpy(&nscap->data, &cap->data, sizeof(__le32) * 2 * VFS_CAP_U32);
+				nscap->magic_etc = cpu_to_le32(nsmagic);
+			} else {
+				/* use allocated v3 buffer */
+				tmpbuf = NULL;
+			}
 			nscap->rootid = cpu_to_le32(mappedroot);
-		} else
-			kfree(tmpbuf);
-		return size;
+			*buffer = nscap;
+		}
+		goto out_free;
 	}
 
 	if (!rootid_owns_currentns(kroot)) {
-		kfree(tmpbuf);
-		return -EOPNOTSUPP;
+		size = -EOVERFLOW;
+		goto out_free;
 	}
 
 	/* This comes from a parent namespace.  Return as a v2 capability */
 	size = sizeof(struct vfs_cap_data);
 	if (alloc) {
-		*buffer = kmalloc(size, GFP_ATOMIC);
-		if (*buffer) {
-			struct vfs_cap_data *cap = *buffer;
-			__le32 nsmagic, magic;
+		if (nscap) {
+			/* v3 -> v2 conversion */
+			cap = kzalloc(size, GFP_ATOMIC);
+			if (!cap) {
+				size = -ENOMEM;
+				goto out_free;
+			}
 			magic = VFS_CAP_REVISION_2;
 			nsmagic = le32_to_cpu(nscap->magic_etc);
 			if (nsmagic & VFS_CAP_FLAGS_EFFECTIVE)
@@ -443,9 +459,12 @@ int cap_inode_getsecurity(struct inode *inode, const char *name, void **buffer,
 			memcpy(&cap->data, &nscap->data, sizeof(__le32) * 2 * VFS_CAP_U32);
 			cap->magic_etc = cpu_to_le32(magic);
 		} else {
-			size = -ENOMEM;
+			/* use unconverted v2 */
+			tmpbuf = NULL;
 		}
+		*buffer = cap;
 	}
+out_free:
 	kfree(tmpbuf);
 	return size;
 }