Migration and virtiofsd pull 2020-08-28

Migration:
    vsock support for migration
    minor fixes
 
 virtiofsd:
    Disable remote posix locks by default - because we
      never supported blocking variants and this breaks things
    Some prep work for un/less priviliged modes
 
 Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
 -----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCAAdFiEERfXHG0oMt/uXep+pBRYzHrxb/ecFAl9I++YACgkQBRYzHrxb
 /efI3A//bkUbMsQNu+AsK8xpRbj04/d7e0ImXr3Jn7eMR5PyZXoC1692f2hwr4w1
 iwdZ4an4dferCkK6wvjTjHUc6CFStkrdVNbBd1m44kyzbAdRarzr3Q108TnRgYzd
 xMwnF6T3tOWywUZ47ai+Vqn3TBPCAER1aAiAkQwSQkaJ/2kaflUv9eG8t63Yk5do
 ZRdsnCR3PWSKwO5FgA9QW+BfMpsSFYmN4d+RT6qaAytBeb0ID+HBd+ExDGEZiCbn
 nB8aY5nrb/61xjWpWGJ8DSXGveMv0nLYfiKV8ZBZ/YFm3O6IUceg4oPA8XVKLt+E
 JMh24MnoGymsyWAlfB9/UzuVY15Z0UCwtJuQNkuG+fDZAdXof+1Q9hG4bP0JlW8j
 mwvqChiheB6zEaAw6Qm+3YjbxeCZRF7WWfPrI5r5XHhdEOfOP8762PSnwhk9KGb9
 YcC9ElslsgkZGJW6MIP4R6XeINh7Xg6tTkhzKmzxjfkeMabuF4Yve5WiC3nIDFOA
 kcEBQ6CdieuY/YTkOOdw4D6Poy4z4j3DTfu4PKjoL5c2uPi0EAfvirhGN+237gDY
 B6Gc8EpOZz3qsSXSHyBJvdMpwwIAyGpU+kT5HiWrziHerPCsfI+QKPoh9v3EMg3g
 c/COVLfhoXBQYmoAy+NHmsoVXun1ykS8xpO3u+yR5dk6eVqCVcE=
 =Npro
 -----END PGP SIGNATURE-----

Merge remote-tracking branch 'remotes/dgilbert/tags/pull-migration-20200828a' into staging

Migration and virtiofsd pull 2020-08-28

Migration:
   vsock support for migration
   minor fixes

virtiofsd:
   Disable remote posix locks by default - because we
     never supported blocking variants and this breaks things
   Some prep work for un/less priviliged modes

Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>

# gpg: Signature made Fri 28 Aug 2020 13:43:18 BST
# gpg:                using RSA key 45F5C71B4A0CB7FB977A9FA90516331EBC5BFDE7
# gpg: Good signature from "Dr. David Alan Gilbert (RH2) <dgilbert@redhat.com>" [full]
# Primary key fingerprint: 45F5 C71B 4A0C B7FB 977A  9FA9 0516 331E BC5B FDE7

* remotes/dgilbert/tags/pull-migration-20200828a:
  virtiofsd: probe unshare(CLONE_FS) and print an error
  virtiofsd: drop CAP_DAC_READ_SEARCH
  virtiofsd: Remove "norace" from cmdline help and docs
  virtiofsd: Disable remote posix locks by default
  migration: tls: fix memory leak in migration_tls_get_creds
  migration: improve error reporting of block driver state name
  migration: add vsock as data channel support
  migration: unify the framework of socket-type channel

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

docs/tools/virtiofsd.rst

@@ -63,11 +63,8 @@ Options
     Print only log messages matching LEVEL or more severe.  LEVEL is one of
     ``err``, ``warn``, ``info``, or ``debug``.  The default is ``info``.
 
-  * norace -
-    Disable racy fallback.  The default is false.
-
   * posix_lock|no_posix_lock -
-    Enable/disable remote POSIX locks.  The default is ``posix_lock``.
+    Enable/disable remote POSIX locks.  The default is ``no_posix_lock``.
 
   * readdirplus|no_readdirplus -
     Enable/disable readdirplus.  The default is ``readdirplus``.

migration/migration.c

@@ -378,21 +378,21 @@ void migrate_add_address(SocketAddress *address)
 
 void qemu_start_incoming_migration(const char *uri, Error **errp)
 {
-    const char *p;
+    const char *p = NULL;
 
     qapi_event_send_migration(MIGRATION_STATUS_SETUP);
     if (!strcmp(uri, "defer")) {
         deferred_incoming_migration(errp);
-    } else if (strstart(uri, "tcp:", &p)) {
+    } else if (strstart(uri, "tcp:", &p) ||
-        tcp_start_incoming_migration(p, errp);
+               strstart(uri, "unix:", NULL) ||
+               strstart(uri, "vsock:", NULL)) {
+        socket_start_incoming_migration(p ? p : uri, errp);
 #ifdef CONFIG_RDMA
     } else if (strstart(uri, "rdma:", &p)) {
         rdma_start_incoming_migration(p, errp);
 #endif
     } else if (strstart(uri, "exec:", &p)) {
         exec_start_incoming_migration(p, errp);
-    } else if (strstart(uri, "unix:", &p)) {
-        unix_start_incoming_migration(p, errp);
     } else if (strstart(uri, "fd:", &p)) {
         fd_start_incoming_migration(p, errp);
     } else {
@@ -2094,7 +2094,7 @@ void qmp_migrate(const char *uri, bool has_blk, bool blk,
 {
     Error *local_err = NULL;
     MigrationState *s = migrate_get_current();
-    const char *p;
+    const char *p = NULL;
 
     if (!migrate_prepare(s, has_blk && blk, has_inc && inc,
                          has_resume && resume, errp)) {
@@ -2102,16 +2102,16 @@ void qmp_migrate(const char *uri, bool has_blk, bool blk,
         return;
     }
 
-    if (strstart(uri, "tcp:", &p)) {
+    if (strstart(uri, "tcp:", &p) ||
-        tcp_start_outgoing_migration(s, p, &local_err);
+        strstart(uri, "unix:", NULL) ||
+        strstart(uri, "vsock:", NULL)) {
+        socket_start_outgoing_migration(s, p ? p : uri, &local_err);
 #ifdef CONFIG_RDMA
     } else if (strstart(uri, "rdma:", &p)) {
         rdma_start_outgoing_migration(s, p, &local_err);
 #endif
     } else if (strstart(uri, "exec:", &p)) {
         exec_start_outgoing_migration(s, p, &local_err);
-    } else if (strstart(uri, "unix:", &p)) {
-        unix_start_outgoing_migration(s, p, &local_err);
     } else if (strstart(uri, "fd:", &p)) {
         fd_start_outgoing_migration(s, p, &local_err);
     } else {

migration/savevm.c

@@ -2682,7 +2682,7 @@ int save_snapshot(const char *name, Error **errp)
 
     if (!bdrv_all_can_snapshot(&bs)) {
         error_setg(errp, "Device '%s' is writable but does not support "
-                   "snapshots", bdrv_get_device_name(bs));
+                   "snapshots", bdrv_get_device_or_node_name(bs));
         return ret;
     }
 
@@ -2691,7 +2691,7 @@ int save_snapshot(const char *name, Error **errp)
         ret = bdrv_all_delete_snapshot(name, &bs1, errp);
         if (ret < 0) {
             error_prepend(errp, "Error while deleting snapshot on device "
-                          "'%s': ", bdrv_get_device_name(bs1));
+                          "'%s': ", bdrv_get_device_or_node_name(bs1));
             return ret;
         }
     }
@@ -2766,7 +2766,7 @@ int save_snapshot(const char *name, Error **errp)
     ret = bdrv_all_create_snapshot(sn, bs, vm_state_size, &bs);
     if (ret < 0) {
         error_setg(errp, "Error while creating snapshot on '%s'",
-                   bdrv_get_device_name(bs));
+                   bdrv_get_device_or_node_name(bs));
         goto the_end;
     }
 
@@ -2884,14 +2884,14 @@ int load_snapshot(const char *name, Error **errp)
     if (!bdrv_all_can_snapshot(&bs)) {
         error_setg(errp,
                    "Device '%s' is writable but does not support snapshots",
-                   bdrv_get_device_name(bs));
+                   bdrv_get_device_or_node_name(bs));
         return -ENOTSUP;
     }
     ret = bdrv_all_find_snapshot(name, &bs);
     if (ret < 0) {
         error_setg(errp,
                    "Device '%s' does not have the requested snapshot '%s'",
-                   bdrv_get_device_name(bs), name);
+                   bdrv_get_device_or_node_name(bs), name);
         return ret;
     }
 
@@ -2920,7 +2920,7 @@ int load_snapshot(const char *name, Error **errp)
     ret = bdrv_all_goto_snapshot(name, &bs, errp);
     if (ret < 0) {
         error_prepend(errp, "Could not load snapshot '%s' on '%s': ",
-                      name, bdrv_get_device_name(bs));
+                      name, bdrv_get_device_or_node_name(bs));
         goto err_drain;
     }
 

migration/socket.c

@@ -50,34 +50,6 @@ int socket_send_channel_destroy(QIOChannel *send)
     return 0;
 }
 
-static SocketAddress *tcp_build_address(const char *host_port, Error **errp)
-{
-    SocketAddress *saddr;
-
-    saddr = g_new0(SocketAddress, 1);
-    saddr->type = SOCKET_ADDRESS_TYPE_INET;
-
-    if (inet_parse(&saddr->u.inet, host_port, errp)) {
-        qapi_free_SocketAddress(saddr);
-        return NULL;
-    }
-
-    return saddr;
-}
-
-
-static SocketAddress *unix_build_address(const char *path)
-{
-    SocketAddress *saddr;
-
-    saddr = g_new0(SocketAddress, 1);
-    saddr->type = SOCKET_ADDRESS_TYPE_UNIX;
-    saddr->u.q_unix.path = g_strdup(path);
-
-    return saddr;
-}
-
-
 struct SocketConnectData {
     MigrationState *s;
     char *hostname;
@@ -109,9 +81,10 @@ static void socket_outgoing_migration(QIOTask *task,
     object_unref(OBJECT(sioc));
 }
 
-static void socket_start_outgoing_migration(MigrationState *s,
+static void
-                                            SocketAddress *saddr,
+socket_start_outgoing_migration_internal(MigrationState *s,
-                                            Error **errp)
+                                         SocketAddress *saddr,
+                                         Error **errp)
 {
     QIOChannelSocket *sioc = qio_channel_socket_new();
     struct SocketConnectData *data = g_new0(struct SocketConnectData, 1);
@@ -135,27 +108,18 @@ static void socket_start_outgoing_migration(MigrationState *s,
                                      NULL);
 }
 
-void tcp_start_outgoing_migration(MigrationState *s,
+void socket_start_outgoing_migration(MigrationState *s,
-                                  const char *host_port,
+                                     const char *str,
-                                  Error **errp)
+                                     Error **errp)
 {
     Error *err = NULL;
-    SocketAddress *saddr = tcp_build_address(host_port, &err);
+    SocketAddress *saddr = socket_parse(str, &err);
     if (!err) {
-        socket_start_outgoing_migration(s, saddr, &err);
+        socket_start_outgoing_migration_internal(s, saddr, &err);
     }
     error_propagate(errp, err);
 }
 
-void unix_start_outgoing_migration(MigrationState *s,
-                                   const char *path,
-                                   Error **errp)
-{
-    SocketAddress *saddr = unix_build_address(path);
-    socket_start_outgoing_migration(s, saddr, errp);
-}
-
-
 static void socket_accept_incoming_migration(QIONetListener *listener,
                                              QIOChannelSocket *cioc,
                                              gpointer opaque)
@@ -173,8 +137,9 @@ static void socket_accept_incoming_migration(QIONetListener *listener,
 }
 
 
-static void socket_start_incoming_migration(SocketAddress *saddr,
+static void
-                                            Error **errp)
+socket_start_incoming_migration_internal(SocketAddress *saddr,
+                                         Error **errp)
 {
     QIONetListener *listener = qio_net_listener_new();
     size_t i;
@@ -207,20 +172,13 @@ static void socket_start_incoming_migration(SocketAddress *saddr,
     }
 }
 
-void tcp_start_incoming_migration(const char *host_port, Error **errp)
+void socket_start_incoming_migration(const char *str, Error **errp)
 {
     Error *err = NULL;
-    SocketAddress *saddr = tcp_build_address(host_port, &err);
+    SocketAddress *saddr = socket_parse(str, &err);
     if (!err) {
-        socket_start_incoming_migration(saddr, &err);
+        socket_start_incoming_migration_internal(saddr, &err);
     }
     qapi_free_SocketAddress(saddr);
     error_propagate(errp, err);
 }
-
-void unix_start_incoming_migration(const char *path, Error **errp)
-{
-    SocketAddress *saddr = unix_build_address(path);
-    socket_start_incoming_migration(saddr, errp);
-    qapi_free_SocketAddress(saddr);
-}

migration/socket.h

@@ -23,13 +23,8 @@
 void socket_send_channel_create(QIOTaskFunc f, void *data);
 int socket_send_channel_destroy(QIOChannel *send);
 
-void tcp_start_incoming_migration(const char *host_port, Error **errp);
+void socket_start_incoming_migration(const char *str, Error **errp);
 
-void tcp_start_outgoing_migration(MigrationState *s, const char *host_port,
+void socket_start_outgoing_migration(MigrationState *s, const char *str,
-                                  Error **errp);
+                                     Error **errp);
-
-void unix_start_incoming_migration(const char *path, Error **errp);
-
-void unix_start_outgoing_migration(MigrationState *s, const char *path,
-                                   Error **errp);
 #endif

migration/tls.c

@@ -58,7 +58,6 @@ migration_tls_get_creds(MigrationState *s,
         return NULL;
     }
 
-    object_ref(OBJECT(ret));
     return ret;
 }
 

tests/qemu-iotests/267.out

@@ -81,11 +81,11 @@ Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=134217728
 Testing: -blockdev driver=file,filename=TEST_DIR/t.IMGFMT,node-name=file
 QEMU X.Y.Z monitor - type 'help' for more information
 (qemu) savevm snap0
-Error: Device '' is writable but does not support snapshots
+Error: Device 'file' is writable but does not support snapshots
 (qemu) info snapshots
 No available block device supports snapshots
 (qemu) loadvm snap0
-Error: Device '' is writable but does not support snapshots
+Error: Device 'file' is writable but does not support snapshots
 (qemu) quit
 
 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=134217728

tools/virtiofsd/fuse_virtio.c

@@ -949,6 +949,22 @@ int virtio_session_mount(struct fuse_session *se)
 {
     int ret;
 
+    /*
+     * Test that unshare(CLONE_FS) works. fv_queue_worker() will need it. It's
+     * an unprivileged system call but some Docker/Moby versions are known to
+     * reject it via seccomp when CAP_SYS_ADMIN is not given.
+     *
+     * Note that the program is single-threaded here so this syscall has no
+     * visible effect and is safe to make.
+     */
+    ret = unshare(CLONE_FS);
+    if (ret == -1 && errno == EPERM) {
+        fuse_log(FUSE_LOG_ERR, "unshare(CLONE_FS) failed with EPERM. If "
+                "running in a container please check that the container "
+                "runtime seccomp policy allows unshare.\n");
+        return -1;
+    }
+
     ret = fv_create_listen_socket(se);
     if (ret < 0) {
         return ret;

tools/virtiofsd/helper.c

@@ -159,8 +159,6 @@ void fuse_cmdline_help(void)
            "    -o max_idle_threads        the maximum number of idle worker "
            "threads\n"
            "                               allowed (default: 10)\n"
-           "    -o norace                  disable racy fallback\n"
-           "                               default: false\n"
            "    -o posix_lock|no_posix_lock\n"
            "                               enable/disable remote posix lock\n"
            "                               default: posix_lock\n"

tools/virtiofsd/passthrough_ll.c

@@ -2596,7 +2596,6 @@ static void setup_capabilities(char *modcaps_in)
     if (capng_updatev(CAPNG_ADD, CAPNG_PERMITTED | CAPNG_EFFECTIVE,
             CAP_CHOWN,
             CAP_DAC_OVERRIDE,
-            CAP_DAC_READ_SEARCH,
             CAP_FOWNER,
             CAP_FSETID,
             CAP_SETGID,
@@ -2823,7 +2822,7 @@ int main(int argc, char *argv[])
     struct lo_data lo = {
         .debug = 0,
         .writeback = 0,
-        .posix_lock = 1,
+        .posix_lock = 0,
         .proc_self_fd = -1,
     };
     struct lo_map_elem *root_elem;