os-posix: asynchronous teardown for shutdown on Linux

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 have the
name "cleanup/<QEMU_PID>". It will wait until qemu terminates
completely, 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 cleanup 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 cleanup
process will share the same cgroups as qemu, so both memory usage and
cpu time will be accounted properly.

If possible, close_range will be used in the cleanup process to close
all open file descriptors. If it is not available or if it fails, /proc
will be used to determine which file descriptors to close.

If the cleanup process is forcefully killed with SIGKILL before the
main qemu process has terminated completely, the mechanism is defeated
and the teardown will not be asynchronous.

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

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

Signed-off-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
Reviewed-by: Murilo Opsfelder Araujo <muriloo@linux.ibm.com>
Tested-by: Murilo Opsfelder Araujo <muriloo@linux.ibm.com>
Message-Id: <20220812133453.82671-1-imbrenda@linux.ibm.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

2 files changed, 151 insertions, 0 deletions

diff --git a/util/async-teardown.c b/util/async-teardown.c
new file mode 100644
index 0000000..62bfce1
--- /dev/null
+++ b/util/async-teardown.c
@@ -0,0 +1,150 @@
+/*
+ * Asynchronous teardown
+ *
+ * Copyright IBM, Corp. 2022
+ *
+ * Authors:
+ *  Claudio Imbrenda <imbrenda@linux.ibm.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or (at your
+ * option) any later version.  See the COPYING file in the top-level directory.
+ *
+ */
+#include <stdlib.h>
+#include <stdio.h>
+#include <sys/types.h>
+#include <dirent.h>
+#include <sys/prctl.h>
+#include <signal.h>
+#include <sched.h>
+#include <unistd.h>
+
+#include "qemu/osdep.h"
+#include "qemu/async-teardown.h"
+
+#ifdef _SC_THREAD_STACK_MIN
+#define CLONE_STACK_SIZE sysconf(_SC_THREAD_STACK_MIN)
+#else
+#define CLONE_STACK_SIZE 16384
+#endif
+
+static pid_t the_ppid;
+
+/*
+ * Close all open file descriptors.
+ */
+static void close_all_open_fd(void)
+{
+    struct dirent *de;
+    int fd, dfd;
+    DIR *dir;
+
+#ifdef CONFIG_CLOSE_RANGE
+    int r = close_range(0, ~0U, 0);
+    if (!r) {
+        /* Success, no need to try other ways. */
+        return;
+    }
+#endif
+
+    dir = opendir("/proc/self/fd");
+    if (!dir) {
+        /* If /proc is not mounted, there is nothing that can be done. */
+        return;
+    }
+    /* Avoid closing the directory. */
+    dfd = dirfd(dir);
+
+    for (de = readdir(dir); de; de = readdir(dir)) {
+        fd = atoi(de->d_name);
+        if (fd != dfd) {
+            close(fd);
+        }
+    }
+    closedir(dir);
+}
+
+static void hup_handler(int signal)
+{
+    /* Check every second if this process has been reparented. */
+    while (the_ppid == getppid()) {
+        /* sleep() is safe to use in a signal handler. */
+        sleep(1);
+    }
+
+    /* At this point the parent process has terminated completely. */
+    _exit(0);
+}
+
+static int async_teardown_fn(void *arg)
+{
+    struct sigaction sa = { .sa_handler = hup_handler };
+    sigset_t hup_signal;
+    char name[16];
+
+    /* Set a meaningful name for this process. */
+    snprintf(name, 16, "cleanup/%d", the_ppid);
+    prctl(PR_SET_NAME, (unsigned long)name);
+
+    /*
+     * Close all file descriptors that might have been inherited from the
+     * main qemu process when doing clone, needed to make libvirt happy.
+     * Not using close_range for increased compatibility with older kernels.
+     */
+    close_all_open_fd();
+
+    /* Set up a handler for SIGHUP and unblock SIGHUP. */
+    sigaction(SIGHUP, &sa, NULL);
+    sigemptyset(&hup_signal);
+    sigaddset(&hup_signal, SIGHUP);
+    sigprocmask(SIG_UNBLOCK, &hup_signal, NULL);
+
+    /* Ask to receive SIGHUP when the parent dies. */
+    prctl(PR_SET_PDEATHSIG, SIGHUP);
+
+    /*
+     * Sleep forever, unless the parent process has already terminated. The
+     * only interruption can come from the SIGHUP signal, which in normal
+     * operation is received when the parent process dies.
+     */
+    if (the_ppid == getppid()) {
+        pause();
+    }
+
+    /* At this point the parent process has terminated completely. */
+    _exit(0);
+}
+
+/*
+ * Allocate a new stack of a reasonable size, and return a pointer to its top.
+ */
+static void *new_stack_for_clone(void)
+{
+    size_t stack_size = CLONE_STACK_SIZE;
+    char *stack_ptr;
+
+    /* Allocate a new stack and get a pointer to its top. */
+    stack_ptr = qemu_alloc_stack(&stack_size);
+#if !defined(HOST_HPPA)
+    /* The top is at the end of the area, except on HPPA. */
+    stack_ptr += stack_size;
+#endif
+
+    return stack_ptr;
+}
+
+/*
+ * Block all signals, start (clone) a new process sharing the address space
+ * with qemu (CLONE_VM), then restore signals.
+ */
+void init_async_teardown(void)
+{
+    sigset_t all_signals, old_signals;
+
+    the_ppid = getpid();
+
+    sigfillset(&all_signals);
+    sigprocmask(SIG_BLOCK, &all_signals, &old_signals);
+    clone(async_teardown_fn, new_stack_for_clone(), CLONE_VM, NULL);
+    sigprocmask(SIG_SETMASK, &old_signals, NULL);
+}
diff --git a/util/meson.build b/util/meson.build
index 5e28213..63acd59 100644
--- a/util/meson.build
+++ b/util/meson.build
@@ -2,6 +2,7 @@ util_ss.add(files('osdep.c', 'cutils.c', 'unicode.c', 'qemu-timer-common.c'))
 if not config_host_data.get('CONFIG_ATOMIC64')
   util_ss.add(files('atomic64.c'))
 endif
+util_ss.add(when: 'CONFIG_LINUX', if_true: files('async-teardown.c'))
 util_ss.add(when: 'CONFIG_POSIX', if_true: files('aio-posix.c'))
 util_ss.add(when: 'CONFIG_POSIX', if_true: files('fdmon-poll.c'))
 if config_host_data.get('CONFIG_EPOLL_CREATE1')