fuse: handle killpriv in userspace fs

Only userspace filesystem can do the killing of suid/sgid without races.
So introduce an INIT flag and negotiate support for this.

Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>

4 files changed, 39 insertions, 19 deletions

diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index b7a690e..7cb68b1 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -1703,6 +1703,7 @@ error:
 static int fuse_setattr(struct dentry *entry, struct iattr *attr)
 {
 	struct inode *inode = d_inode(entry);
+	struct fuse_conn *fc = get_fuse_conn(inode);
 	struct file *file = (attr->ia_valid & ATTR_FILE) ? attr->ia_file : NULL;
 	int ret;
 
@@ -1710,27 +1711,36 @@ static int fuse_setattr(struct dentry *entry, struct iattr *attr)
 		return -EACCES;
 
 	if (attr->ia_valid & (ATTR_KILL_SUID | ATTR_KILL_SGID)) {
-		int kill;
-
 		attr->ia_valid &= ~(ATTR_KILL_SUID | ATTR_KILL_SGID |
 				    ATTR_MODE);
+
 		/*
-		 * ia_mode calculation may have used stale i_mode.  Refresh and
-		 * recalculate.
+		 * The only sane way to reliably kill suid/sgid is to do it in
+		 * the userspace filesystem
+		 *
+		 * This should be done on write(), truncate() and chown().
 		 */
-		ret = fuse_do_getattr(inode, NULL, file);
-		if (ret)
-			return ret;
-
-		attr->ia_mode = inode->i_mode;
-		kill = should_remove_suid(entry);
-		if (kill & ATTR_KILL_SUID) {
-			attr->ia_valid |= ATTR_MODE;
-			attr->ia_mode &= ~S_ISUID;
-		}
-		if (kill & ATTR_KILL_SGID) {
-			attr->ia_valid |= ATTR_MODE;
-			attr->ia_mode &= ~S_ISGID;
+		if (!fc->handle_killpriv) {
+			int kill;
+
+			/*
+			 * ia_mode calculation may have used stale i_mode.
+			 * Refresh and recalculate.
+			 */
+			ret = fuse_do_getattr(inode, NULL, file);
+			if (ret)
+				return ret;
+
+			attr->ia_mode = inode->i_mode;
+			kill = should_remove_suid(entry);
+			if (kill & ATTR_KILL_SUID) {
+				attr->ia_valid |= ATTR_MODE;
+				attr->ia_mode &= ~S_ISUID;
+			}
+			if (kill & ATTR_KILL_SGID) {
+				attr->ia_valid |= ATTR_MODE;
+				attr->ia_mode &= ~S_ISGID;
+			}
 		}
 	}
 	if (!attr->ia_valid)
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index 6db54d0..9940a64 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -547,6 +547,9 @@ struct fuse_conn {
 	/** allow parallel lookups and readdir (default is serialized) */
 	unsigned parallel_dirops:1;
 
+	/** handle fs handles killing suid/sgid/cap on write/chown/trunc */
+	unsigned handle_killpriv:1;
+
 	/*
 	 * The following bitfields are only for optimization purposes
 	 * and hence races in setting them will not cause malfunction
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 1e535f3..b965934 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -910,6 +910,8 @@ static void process_init_reply(struct fuse_conn *fc, struct fuse_req *req)
 				fc->writeback_cache = 1;
 			if (arg->flags & FUSE_PARALLEL_DIROPS)
 				fc->parallel_dirops = 1;
+			if (arg->flags & FUSE_HANDLE_KILLPRIV)
+				fc->handle_killpriv = 1;
 			if (arg->time_gran && arg->time_gran <= 1000000000)
 				fc->sb->s_time_gran = arg->time_gran;
 		} else {
@@ -941,7 +943,7 @@ static void fuse_send_init(struct fuse_conn *fc, struct fuse_req *req)
 		FUSE_FLOCK_LOCKS | FUSE_HAS_IOCTL_DIR | FUSE_AUTO_INVAL_DATA |
 		FUSE_DO_READDIRPLUS | FUSE_READDIRPLUS_AUTO | FUSE_ASYNC_DIO |
 		FUSE_WRITEBACK_CACHE | FUSE_NO_OPEN_SUPPORT |
-		FUSE_PARALLEL_DIROPS;
+		FUSE_PARALLEL_DIROPS | FUSE_HANDLE_KILLPRIV;
 	req->in.h.opcode = FUSE_INIT;
 	req->in.numargs = 1;
 	req->in.args[0].size = sizeof(*arg);
diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h
index 27e1736..14ca2f1 100644
--- a/include/uapi/linux/fuse.h
+++ b/include/uapi/linux/fuse.h
@@ -108,6 +108,9 @@
  *
  *  7.25
  *  - add FUSE_PARALLEL_DIROPS
+ *
+ *  7.26
+ *  - add FUSE_HANDLE_KILLPRIV
  */
 
 #ifndef _LINUX_FUSE_H
@@ -143,7 +146,7 @@
 #define FUSE_KERNEL_VERSION 7
 
 /** Minor version number of this interface */
-#define FUSE_KERNEL_MINOR_VERSION 25
+#define FUSE_KERNEL_MINOR_VERSION 26
 
 /** The node ID of the root inode */
 #define FUSE_ROOT_ID 1
@@ -238,6 +241,7 @@ struct fuse_file_lock {
  * FUSE_WRITEBACK_CACHE: use writeback cache for buffered writes
  * FUSE_NO_OPEN_SUPPORT: kernel supports zero-message opens
  * FUSE_PARALLEL_DIROPS: allow parallel lookups and readdir
+ * FUSE_HANDLE_KILLPRIV: fs handles killing suid/sgid/cap on write/chown/trunc
  */
 #define FUSE_ASYNC_READ		(1 << 0)
 #define FUSE_POSIX_LOCKS	(1 << 1)
@@ -258,6 +262,7 @@ struct fuse_file_lock {
 #define FUSE_WRITEBACK_CACHE	(1 << 16)
 #define FUSE_NO_OPEN_SUPPORT	(1 << 17)
 #define FUSE_PARALLEL_DIROPS    (1 << 18)
+#define FUSE_HANDLE_KILLPRIV	(1 << 19)
 
 /**
  * CUSE INIT request/reply flags