[PATCH v2 1/1] osdep: asynchronous teardown for shutdown on Linux

[Claudio Imbrenda]

This patch adds support for asynchronously tearing down a VM on Linux.

When qemu terminates, either naturally or because of a fatal signal,
the VM is torn down. If the VM is huge, it can take a considerable
amount of time for it to be cleaned up. In case of a protected VM, it
might take even longer than a non-protected VM (this is the case on
s390x, for example).

Some users might want to shut down a VM and restart it immediately,
without having to wait. This is especially true if management
infrastructure like libvirt is used.

This patch implements a simple trick on Linux to allow qemu to return
immediately, with the teardown of the VM being performed
asynchronously.

If the new commandline option -async-teardown is used, a new process is
spawned from qemu at startup, using the clone syscall, in such way that
it will share its address space with qemu.

The new process will then simpy wait until qemu terminates, and then it
will exit itself.

This allows qemu to terminate quickly, without having to wait for the
whole address space to be torn down. The teardown process will exit
after qemu, so it will be the last user of the address space, and
therefore it will take care of the actual teardown.

The teardown process will share the same cgroups as qemu, so both
memory usage and cpu time will be accounted properly.

This feature can already be used with libvirt by adding the following
to the XML domain definition:

  <commandline xmlns="http://libvirt.org/schemas/domain/qemu/1.0";>
  <arg value='-async-teardown'/>
  </commandline>

Signed-off-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
---
 include/qemu/osdep.h |  2 ++
 os-posix.c           |  5 ++++
 qemu-options.hx      | 17 ++++++++++++++
 util/osdep.c         | 55 ++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 79 insertions(+)

diff --git a/include/qemu/osdep.h b/include/qemu/osdep.h
index b1c161c035..3154759d79 100644
--- a/include/qemu/osdep.h
+++ b/include/qemu/osdep.h
@@ -549,6 +549,8 @@ ssize_t qemu_write_full(int fd, const void *buf, size_t 
count)
 
 void qemu_set_cloexec(int fd);
 
+void init_async_teardown(void);
+
 /* Return a dynamically allocated directory path that is appropriate for 
storing
  * local state.
  *
diff --git a/os-posix.c b/os-posix.c
index 321fc4bd13..dd3e42b4c4 100644
--- a/os-posix.c
+++ b/os-posix.c
@@ -150,6 +150,11 @@ int os_parse_cmd_args(int index, const char *optarg)
     case QEMU_OPTION_daemonize:
         daemonize = 1;
         break;
+#if defined(CONFIG_LINUX)
+    case QEMU_OPTION_asyncteardown:
+        init_async_teardown();
+        break;
+#endif
     default:
         return -1;
     }
diff --git a/qemu-options.hx b/qemu-options.hx
index 3f23a42fa8..d434353159 100644
--- a/qemu-options.hx
+++ b/qemu-options.hx
@@ -4743,6 +4743,23 @@ HXCOMM Internal use
 DEF("qtest", HAS_ARG, QEMU_OPTION_qtest, "", QEMU_ARCH_ALL)
 DEF("qtest-log", HAS_ARG, QEMU_OPTION_qtest_log, "", QEMU_ARCH_ALL)
 
+#ifdef __linux__
+DEF("async-teardown", 0, QEMU_OPTION_asyncteardown,
+    "-async-teardown enable asynchronous teardown\n",
+    QEMU_ARCH_ALL)
+#endif
+SRST
+``-async-teardown``
+    Enable asynchronous teardown. A new teardown process will be
+    created at startup, using clone. The teardown process will share
+    the address space of the main qemu process, and wait for the main
+    process to terminate. At that point, the teardown process will
+    also exit. This allows qemu to terminate quickly if the guest was
+    huge, leaving the teardown of the address space to the teardown
+    process. Since the teardown process shares the same cgroups as the
+    main qemu process, accounting is performed correctly.
+ERST
+
 DEF("msg", HAS_ARG, QEMU_OPTION_msg,
     "-msg [timestamp[=on|off]][,guest-name=[on|off]]\n"
     "                control error message format\n"
diff --git a/util/osdep.c b/util/osdep.c
index 60fcbbaebe..bb0baf97a0 100644
--- a/util/osdep.c
+++ b/util/osdep.c
@@ -23,6 +23,15 @@
  */
 #include "qemu/osdep.h"
 #include "qapi/error.h"
+
+#ifdef CONFIG_LINUX
+#include <sys/types.h>
+#include <sys/select.h>
+#include <sys/unistd.h>
+#include <sys/syscall.h>
+#include <signal.h>
+#endif
+
 #include "qemu/cutils.h"
 #include "qemu/sockets.h"
 #include "qemu/error-report.h"
@@ -512,6 +521,52 @@ const char *qemu_hw_version(void)
     return hw_version;
 }
 
+#ifdef __linux__
+static int async_teardown_fn(void *arg)
+{
+    sigset_t all_signals;
+    fd_set r, w, e;
+    int fd;
+
+    /* open a pidfd descriptor for the parent qemu process */
+    fd = syscall(__NR_pidfd_open, getppid(), 0);
+    /* if something went wrong, or if the file descriptor is too big */
+    if ((fd < 0) || (fd >= FD_SETSIZE)) {
+        _exit(1);
+    }
+    /* zero all fd sets */
+    FD_ZERO(&r);
+    FD_ZERO(&w);
+    FD_ZERO(&e);
+    /* set the fd for the pidfd in the "read" set */
+    FD_SET(fd, &r);
+    /* block all signals */
+    sigfillset(&all_signals);
+    sigprocmask(SIG_BLOCK, &all_signals, NULL);
+    /* wait for the pid to disappear -> fd will appear as ready for read */
+    (void) select(fd + 1, &r, &w, &e, NULL);
+
+    /*
+     * Close all file descriptors that might have been inherited from the
+     * main qemu process when doing clone. This is needed to make libvirt
+     * happy.
+     */
+    close_range(0, ~0U, 0);
+    _exit(0);
+}
+
+void init_async_teardown(void)
+{
+    const int size = 8192; /* should be more than enough */
+    char *stack = malloc(size);
+
+    /* start a new process sharing the address space with qemu */
+    clone(async_teardown_fn, stack + size, CLONE_VM, NULL, NULL, NULL, NULL);
+}
+#else /* __linux__ */
+void init_async_teardown(void) {}
+#endif
+
 #ifdef _WIN32
 static void socket_cleanup(void)
 {
-- 
2.37.1