fuse: introduce the notion of FUSE_HANDLE_KILLPRIV_V2

We already have FUSE_HANDLE_KILLPRIV flag that says that file server will
remove suid/sgid/caps on truncate/chown/write. But that's little different
from what Linux VFS implements.

To be consistent with Linux VFS behavior what we want is.

- caps are always cleared on chown/write/truncate
- suid is always cleared on chown, while for truncate/write it is cleared
  only if caller does not have CAP_FSETID.
- sgid is always cleared on chown, while for truncate/write it is cleared
  only if caller does not have CAP_FSETID as well as file has group execute
  permission.

As previous flag did not provide above semantics. Implement a V2 of the
protocol with above said constraints.

Server does not know if caller has CAP_FSETID or not. So for the case
of write()/truncate(), client will send information in special flag to
indicate whether to kill priviliges or not. These changes are in subsequent
patches.

FUSE_HANDLE_KILLPRIV_V2 relies on WRITE being sent to server to clear
suid/sgid/security.capability. But with ->writeback_cache, WRITES are
cached in guest. So it is not recommended to use FUSE_HANDLE_KILLPRIV_V2
and writeback_cache together. Though it probably might be good enough
for lot of use cases.

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

diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index 8301c50..d414c78 100644 (file)
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -635,6 +635,14 @@ struct fuse_conn {
        /* show legacy mount options */
        unsigned int legacy_opts_show:1;
 
+       /*
+        * fs kills suid/sgid/cap on write/chown/trunc. suid is killed on
+        * write/trunc only if caller did not have CAP_FSETID.  sgid is killed
+        * on write/truncate only if caller did not have CAP_FSETID as well as
+        * file has group execute permission.
+        */
+       unsigned handle_killpriv_v2:1;
+
        /*
         * 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 e7e9005..5a6102c 100644 (file)
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -1038,6 +1038,8 @@ static void process_init_reply(struct fuse_mount *fm, struct fuse_args *args,
                            !fuse_dax_check_alignment(fc, arg->map_alignment)) {
                                ok = false;
                        }
+                       if (arg->flags & FUSE_HANDLE_KILLPRIV_V2)
+                               fc->handle_killpriv_v2 = 1;
                } else {
                        ra_pages = fc->max_read / PAGE_SIZE;
                        fc->no_lock = 1;
@@ -1080,7 +1082,8 @@ void fuse_send_init(struct fuse_mount *fm)
                FUSE_WRITEBACK_CACHE | FUSE_NO_OPEN_SUPPORT |
                FUSE_PARALLEL_DIROPS | FUSE_HANDLE_KILLPRIV | FUSE_POSIX_ACL |
                FUSE_ABORT_ERROR | FUSE_MAX_PAGES | FUSE_CACHE_SYMLINKS |
-               FUSE_NO_OPENDIR_SUPPORT | FUSE_EXPLICIT_INVAL_DATA;
+               FUSE_NO_OPENDIR_SUPPORT | FUSE_EXPLICIT_INVAL_DATA |
+               FUSE_HANDLE_KILLPRIV_V2;
 #ifdef CONFIG_FUSE_DAX
        if (fm->fc->dax)
                ia->in.flags |= FUSE_MAP_ALIGNMENT;

diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h
index 7233502..29bd2e0 100644 (file)
--- a/include/uapi/linux/fuse.h
+++ b/include/uapi/linux/fuse.h
@@ -175,6 +175,9 @@
  *
  *  7.32
  *  - add flags to fuse_attr, add FUSE_ATTR_SUBMOUNT, add FUSE_SUBMOUNTS
+ *
+ *  7.33
+ *  - add FUSE_HANDLE_KILLPRIV_V2
  */
 
 #ifndef _LINUX_FUSE_H
@@ -210,7 +213,7 @@
 #define FUSE_KERNEL_VERSION 7
 
 /** Minor version number of this interface */
-#define FUSE_KERNEL_MINOR_VERSION 32
+#define FUSE_KERNEL_MINOR_VERSION 33
 
 /** The node ID of the root inode */
 #define FUSE_ROOT_ID 1
@@ -320,6 +323,11 @@ struct fuse_file_lock {
  *                    foffset and moffset fields in struct
  *                    fuse_setupmapping_out and fuse_removemapping_one.
  * FUSE_SUBMOUNTS: kernel supports auto-mounting directory submounts
+ * FUSE_HANDLE_KILLPRIV_V2: fs kills suid/sgid/cap on write/chown/trunc.
+ *                     Upon write/truncate suid/sgid is only killed if caller
+ *                     does not have CAP_FSETID. Additionally upon
+ *                     write/truncate sgid is killed only if file has group
+ *                     execute permission. (Same as Linux VFS behavior).
  */
 #define FUSE_ASYNC_READ                (1 << 0)
 #define FUSE_POSIX_LOCKS       (1 << 1)
@@ -349,6 +357,7 @@ struct fuse_file_lock {
 #define FUSE_EXPLICIT_INVAL_DATA (1 << 25)
 #define FUSE_MAP_ALIGNMENT     (1 << 26)
 #define FUSE_SUBMOUNTS         (1 << 27)
+#define FUSE_HANDLE_KILLPRIV_V2        (1 << 28)
 
 /**
  * CUSE INIT request/reply flags