Merge tag 'for-upstream' of https://gitlab.com/bonzini/qemu into staging

* only build util/async-teardown.c when system build is requested
* target/i386: fix BQL handling of the legacy FERR interrupts
* target/i386: fix memory operand size for CVTPS2PD
* target/i386: Add support for AMX-COMPLEX in CPUID enumeration
* compile plugins on Darwin
* configure and meson cleanups
* drop mkvenv support for Python 3.7 and Debian10
* add wrap file for libblkio
* tweak KVM stubs

# -----BEGIN PGP SIGNATURE-----
#
# iQFIBAABCAAyFiEE8TM4V0tmI4mGbHaCv/vSX3jHroMFAmT5t6UUHHBib256aW5p
# QHJlZGhhdC5jb20ACgkQv/vSX3jHroMmjwf+MpvVuq+nn+3PqGUXgnzJx5ccA5ne
# O9Xy8+1GdlQPzBw/tPovxXDSKn3HQtBfxObn2CCE1tu/4uHWpBA1Vksn++NHdUf2
# P0yoHxGskJu5iYYTtIcNw5cH2i+AizdiXuEjhfNjqD5Y234cFoHnUApt9e3zBvVO
# cwGD7WpPuSb4g38hHkV6nKcx72o7b4ejDToqUVZJ2N+RkddSqB03fSdrOru0hR7x
# V+lay0DYdFszNDFm05LJzfDbcrHuSryGA91wtty7Fzj6QhR/HBHQCUZJxMB5PI7F
# Zy4Zdpu60zxtSxUqeKgIi7UhNFgMcax2Hf9QEqdc/B4ARoBbboh4q4u8kQ==
# =dH7/
# -----END PGP SIGNATURE-----
# gpg: Signature made Thu 07 Sep 2023 07:44:37 EDT
# gpg:                using RSA key F13338574B662389866C7682BFFBD25F78C7AE83
# gpg:                issuer "pbonzini@redhat.com"
# gpg: Good signature from "Paolo Bonzini <bonzini@gnu.org>" [full]
# gpg:                 aka "Paolo Bonzini <pbonzini@redhat.com>" [full]
# Primary key fingerprint: 46F5 9FBD 57D6 12E7 BFD4  E2F7 7E15 100C CD36 69B1
#      Subkey fingerprint: F133 3857 4B66 2389 866C  7682 BFFB D25F 78C7 AE83

* tag 'for-upstream' of https://gitlab.com/bonzini/qemu: (51 commits)
  docs/system/replay: do not show removed command line option
  subprojects: add wrap file for libblkio
  sysemu/kvm: Restrict kvm_pc_setup_irq_routing() to x86 targets
  sysemu/kvm: Restrict kvm_has_pit_state2() to x86 targets
  sysemu/kvm: Restrict kvm_get_apic_state() to x86 targets
  sysemu/kvm: Restrict kvm_arch_get_supported_cpuid/msr() to x86 targets
  target/i386: Restrict declarations specific to CONFIG_KVM
  target/i386: Allow elision of kvm_hv_vpindex_settable()
  target/i386: Allow elision of kvm_enable_x2apic()
  target/i386: Remove unused KVM stubs
  target/i386/cpu-sysemu: Inline kvm_apic_in_kernel()
  target/i386/helper: Restrict KVM declarations to system emulation
  hw/i386/fw_cfg: Include missing 'cpu.h' header
  hw/i386/pc: Include missing 'cpu.h' header
  hw/i386/pc: Include missing 'sysemu/tcg.h' header
  Revert "mkvenv: work around broken pip installations on Debian 10"
  mkvenv: assume presence of importlib.metadata
  Python: Drop support for Python 3.7
  configure: remove dead code
  meson: list leftover CONFIG_* symbols
  ...

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

3 files changed, 230 insertions, 4 deletions

diff --git a/softmmu/async-teardown.c b/softmmu/async-teardown.c
new file mode 100644
index 0000000000..62cdeb0f20
--- /dev/null
+++ b/softmmu/async-teardown.c
@@ -0,0 +1,146 @@
+/*
+ * 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 "qemu/osdep.h"
+#include <dirent.h>
+#include <sys/prctl.h>
+#include <sched.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/softmmu/meson.build b/softmmu/meson.build
index ea5603f021..c18b7ad738 100644
--- a/softmmu/meson.build
+++ b/softmmu/meson.build
@@ -37,3 +37,4 @@ endif
 
 system_ss.add(when: seccomp, if_true: files('qemu-seccomp.c'))
 system_ss.add(when: fdt, if_true: files('device_tree.c'))
+system_ss.add(when: 'CONFIG_LINUX', if_true: files('async-teardown.c'))
diff --git a/softmmu/vl.c b/softmmu/vl.c
index 5a10b3c309..3db4fd2680 100644
--- a/softmmu/vl.c
+++ b/softmmu/vl.c
@@ -49,6 +49,7 @@
 #include "qemu/error-report.h"
 #include "qemu/sockets.h"
 #include "qemu/accel.h"
+#include "qemu/async-teardown.h"
 #include "hw/usb.h"
 #include "hw/isa/isa.h"
 #include "hw/scsi/scsi.h"
@@ -89,7 +90,6 @@
 #include "qapi/qobject-input-visitor.h"
 #include "qemu/option.h"
 #include "qemu/config-file.h"
-#include "qemu/qemu-options.h"
 #include "qemu/main-loop.h"
 #ifdef CONFIG_VIRTFS
 #include "fsdev/qemu-fsdev.h"
@@ -747,6 +747,33 @@ static QemuOptsList qemu_smp_opts = {
     },
 };
 
+#if defined(CONFIG_POSIX)
+static QemuOptsList qemu_run_with_opts = {
+    .name = "run-with",
+    .head = QTAILQ_HEAD_INITIALIZER(qemu_run_with_opts.head),
+    .desc = {
+#if defined(CONFIG_LINUX)
+        {
+            .name = "async-teardown",
+            .type = QEMU_OPT_BOOL,
+        },
+#endif
+        {
+            .name = "chroot",
+            .type = QEMU_OPT_STRING,
+        },
+        { /* end of list */ }
+    },
+};
+
+#define qemu_add_run_with_opts() qemu_add_opts(&qemu_run_with_opts)
+
+#else
+
+#define qemu_add_run_with_opts()
+
+#endif /* CONFIG_POSIX */
+
 static void realtime_init(void)
 {
     if (enable_mlock) {
@@ -865,6 +892,16 @@ static void help(int exitcode)
     exit(exitcode);
 }
 
+enum {
+
+#define DEF(option, opt_arg, opt_enum, opt_help, arch_mask)     \
+    opt_enum,
+#define DEFHEADING(text)
+#define ARCHHEADING(text, arch_mask)
+
+#include "qemu-options.def"
+};
+
 #define HAS_ARG 0x0001
 
 typedef struct QEMUOption {
@@ -2698,6 +2735,7 @@ void qemu_init(int argc, char **argv)
     qemu_add_opts(&qemu_semihosting_config_opts);
     qemu_add_opts(&qemu_fw_cfg_opts);
     qemu_add_opts(&qemu_action_opts);
+    qemu_add_run_with_opts();
     module_call_init(MODULE_INIT_OPTS);
 
     error_init(argv[0]);
@@ -3516,11 +3554,52 @@ void qemu_init(int argc, char **argv)
             case QEMU_OPTION_nouserconfig:
                 /* Nothing to be parsed here. Especially, do not error out below. */
                 break;
-            default:
-                if (os_parse_cmd_args(popt->index, optarg)) {
-                    error_report("Option not supported in this build");
+#if defined(CONFIG_POSIX)
+            case QEMU_OPTION_runas:
+                if (!os_set_runas(optarg)) {
+                    error_report("User \"%s\" doesn't exist"
+                                 " (and is not <uid>:<gid>)",
+                                 optarg);
                     exit(1);
                 }
+                break;
+            case QEMU_OPTION_chroot:
+                warn_report("option is deprecated,"
+                            " use '-run-with chroot=...' instead");
+                os_set_chroot(optarg);
+                break;
+            case QEMU_OPTION_daemonize:
+                os_set_daemonize(true);
+                break;
+#if defined(CONFIG_LINUX)
+            /* deprecated */
+            case QEMU_OPTION_asyncteardown:
+                init_async_teardown();
+                break;
+#endif
+            case QEMU_OPTION_run_with: {
+                const char *str;
+                opts = qemu_opts_parse_noisily(qemu_find_opts("run-with"),
+                                                         optarg, false);
+                if (!opts) {
+                    exit(1);
+                }
+#if defined(CONFIG_LINUX)
+                if (qemu_opt_get_bool(opts, "async-teardown", false)) {
+                    init_async_teardown();
+                }
+#endif
+                str = qemu_opt_get(opts, "chroot");
+                if (str) {
+                    os_set_chroot(str);
+                }
+                break;
+            }
+#endif /* CONFIG_POSIX */
+
+            default:
+                error_report("Option not supported in this build");
+                exit(1);
             }
         }
     }