summary refs log tree commit diff stats
path: root/util
diff options
context:
space:
mode:
Diffstat (limited to 'util')
-rw-r--r--util/aio-win32.c5
-rw-r--r--util/async-teardown.c150
-rw-r--r--util/log.c18
-rw-r--r--util/main-loop.c20
-rw-r--r--util/meson.build1
-rw-r--r--util/module.c191
6 files changed, 292 insertions, 93 deletions
diff --git a/util/aio-win32.c b/util/aio-win32.c
index 44003d645e..80cfe012ad 100644
--- a/util/aio-win32.c
+++ b/util/aio-win32.c
@@ -326,9 +326,9 @@ void aio_dispatch(AioContext *ctx)
 bool aio_poll(AioContext *ctx, bool blocking)
 {
     AioHandler *node;
-    HANDLE events[MAXIMUM_WAIT_OBJECTS + 1];
+    HANDLE events[MAXIMUM_WAIT_OBJECTS];
     bool progress, have_select_revents, first;
-    int count;
+    unsigned count;
     int timeout;
 
     /*
@@ -369,6 +369,7 @@ bool aio_poll(AioContext *ctx, bool blocking)
     QLIST_FOREACH_RCU(node, &ctx->aio_handlers, node) {
         if (!node->deleted && node->io_notify
             && aio_node_check(ctx, node->is_external)) {
+            assert(count < MAXIMUM_WAIT_OBJECTS);
             events[count++] = event_notifier_get_handle(node->e);
         }
     }
diff --git a/util/async-teardown.c b/util/async-teardown.c
new file mode 100644
index 0000000000..62bfce1b3c
--- /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/log.c b/util/log.c
index d6eb0378c3..c2198badf2 100644
--- a/util/log.c
+++ b/util/log.c
@@ -42,6 +42,7 @@ static QemuMutex global_mutex;
 static char *global_filename;
 static FILE *global_file;
 static __thread FILE *thread_file;
+static __thread Notifier qemu_log_thread_cleanup_notifier;
 
 int qemu_loglevel;
 static bool log_append;
@@ -77,6 +78,12 @@ static int log_thread_id(void)
 #endif
 }
 
+static void qemu_log_thread_cleanup(Notifier *n, void *unused)
+{
+    fclose(thread_file);
+    thread_file = NULL;
+}
+
 /* Lock/unlock output. */
 
 FILE *qemu_log_trylock(void)
@@ -93,6 +100,8 @@ FILE *qemu_log_trylock(void)
                 return NULL;
             }
             thread_file = logfile;
+            qemu_log_thread_cleanup_notifier.notify = qemu_log_thread_cleanup;
+            qemu_thread_atexit_add(&qemu_log_thread_cleanup_notifier);
         } else {
             rcu_read_lock();
             /*
@@ -197,6 +206,15 @@ static bool qemu_set_log_internal(const char *filename, bool changed_name,
     QEMU_LOCK_GUARD(&global_mutex);
     logfile = global_file;
 
+    /* The per-thread flag is immutable. */
+    if (log_per_thread) {
+        log_flags |= LOG_PER_THREAD;
+    } else {
+        if (global_filename) {
+            log_flags &= ~LOG_PER_THREAD;
+        }
+    }
+
     per_thread = log_flags & LOG_PER_THREAD;
 
     if (changed_name) {
diff --git a/util/main-loop.c b/util/main-loop.c
index f00a25451b..10fa74c6e3 100644
--- a/util/main-loop.c
+++ b/util/main-loop.c
@@ -363,20 +363,30 @@ void qemu_del_polling_cb(PollingFunc *func, void *opaque)
 /* Wait objects support */
 typedef struct WaitObjects {
     int num;
-    int revents[MAXIMUM_WAIT_OBJECTS + 1];
-    HANDLE events[MAXIMUM_WAIT_OBJECTS + 1];
-    WaitObjectFunc *func[MAXIMUM_WAIT_OBJECTS + 1];
-    void *opaque[MAXIMUM_WAIT_OBJECTS + 1];
+    int revents[MAXIMUM_WAIT_OBJECTS];
+    HANDLE events[MAXIMUM_WAIT_OBJECTS];
+    WaitObjectFunc *func[MAXIMUM_WAIT_OBJECTS];
+    void *opaque[MAXIMUM_WAIT_OBJECTS];
 } WaitObjects;
 
 static WaitObjects wait_objects = {0};
 
 int qemu_add_wait_object(HANDLE handle, WaitObjectFunc *func, void *opaque)
 {
+    int i;
     WaitObjects *w = &wait_objects;
+
     if (w->num >= MAXIMUM_WAIT_OBJECTS) {
         return -1;
     }
+
+    for (i = 0; i < w->num; i++) {
+        /* check if the same handle is added twice */
+        if (w->events[i] == handle) {
+            return -1;
+        }
+    }
+
     w->events[w->num] = handle;
     w->func[w->num] = func;
     w->opaque[w->num] = opaque;
@@ -395,7 +405,7 @@ void qemu_del_wait_object(HANDLE handle, WaitObjectFunc *func, void *opaque)
         if (w->events[i] == handle) {
             found = 1;
         }
-        if (found) {
+        if (found && i < (MAXIMUM_WAIT_OBJECTS - 1)) {
             w->events[i] = w->events[i + 1];
             w->func[i] = w->func[i + 1];
             w->opaque[i] = w->opaque[i + 1];
diff --git a/util/meson.build b/util/meson.build
index c0a7bc54d4..59c1f467bb 100644
--- a/util/meson.build
+++ b/util/meson.build
@@ -3,6 +3,7 @@ util_ss.add(files('thread-context.c'), numa)
 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')
diff --git a/util/module.c b/util/module.c
index 8ddb0e18f5..32e263163c 100644
--- a/util/module.c
+++ b/util/module.c
@@ -21,6 +21,7 @@
 #include "qemu/module.h"
 #include "qemu/cutils.h"
 #include "qemu/config-file.h"
+#include "qapi/error.h"
 #ifdef CONFIG_MODULE_UPGRADES
 #include "qemu-version.h"
 #endif
@@ -144,25 +145,22 @@ static bool module_check_arch(const QemuModinfo *modinfo)
     return true;
 }
 
-static int module_load_file(const char *fname, bool mayfail, bool export_symbols)
+/*
+ * module_load_dso: attempt to load an existing dso file
+ *
+ * fname:          full pathname of the file to load
+ * export_symbols: if true, add the symbols to the global name space
+ * errp:           error to set.
+ *
+ * Return value:   true on success, false on error, and errp will be set.
+ */
+static bool module_load_dso(const char *fname, bool export_symbols,
+                            Error **errp)
 {
     GModule *g_module;
     void (*sym)(void);
-    const char *dsosuf = CONFIG_HOST_DSOSUF;
-    int len = strlen(fname);
-    int suf_len = strlen(dsosuf);
     ModuleEntry *e, *next;
-    int ret, flags;
-
-    if (len <= suf_len || strcmp(&fname[len - suf_len], dsosuf)) {
-        /* wrong suffix */
-        ret = -EINVAL;
-        goto out;
-    }
-    if (access(fname, F_OK)) {
-        ret = -ENOENT;
-        goto out;
-    }
+    int flags;
 
     assert(QTAILQ_EMPTY(&dso_init_list));
 
@@ -172,48 +170,38 @@ static int module_load_file(const char *fname, bool mayfail, bool export_symbols
     }
     g_module = g_module_open(fname, flags);
     if (!g_module) {
-        if (!mayfail) {
-            fprintf(stderr, "Failed to open module: %s\n",
-                    g_module_error());
-        }
-        ret = -EINVAL;
-        goto out;
+        error_setg(errp, "failed to open module: %s", g_module_error());
+        return false;
     }
     if (!g_module_symbol(g_module, DSO_STAMP_FUN_STR, (gpointer *)&sym)) {
-        fprintf(stderr, "Failed to initialize module: %s\n",
-                fname);
-        /* Print some info if this is a QEMU module (but from different build),
-         * this will make debugging user problems easier. */
+        error_setg(errp, "failed to initialize module: %s", fname);
+        /*
+         * Print some info if this is a QEMU module (but from different build),
+         * this will make debugging user problems easier.
+         */
         if (g_module_symbol(g_module, "qemu_module_dummy", (gpointer *)&sym)) {
-            fprintf(stderr,
-                    "Note: only modules from the same build can be loaded.\n");
+            error_append_hint(errp,
+                "Only modules from the same build can be loaded.\n");
         }
         g_module_close(g_module);
-        ret = -EINVAL;
-    } else {
-        QTAILQ_FOREACH(e, &dso_init_list, node) {
-            e->init();
-            register_module_init(e->init, e->type);
-        }
-        ret = 0;
+        return false;
     }
 
+    QTAILQ_FOREACH(e, &dso_init_list, node) {
+        e->init();
+        register_module_init(e->init, e->type);
+    }
     trace_module_load_module(fname);
     QTAILQ_FOREACH_SAFE(e, &dso_init_list, node, next) {
         QTAILQ_REMOVE(&dso_init_list, e, node);
         g_free(e);
     }
-out:
-    return ret;
+    return true;
 }
-#endif
 
-bool module_load_one(const char *prefix, const char *lib_name, bool mayfail)
+int module_load(const char *prefix, const char *name, Error **errp)
 {
-    bool success = false;
-
-#ifdef CONFIG_MODULES
-    char *fname = NULL;
+    int rv = -1;
 #ifdef CONFIG_MODULE_UPGRADES
     char *version_dir;
 #endif
@@ -221,34 +209,52 @@ bool module_load_one(const char *prefix, const char *lib_name, bool mayfail)
     char *dirs[5];
     char *module_name;
     int i = 0, n_dirs = 0;
-    int ret;
     bool export_symbols = false;
     static GHashTable *loaded_modules;
     const QemuModinfo *modinfo;
     const char **sl;
 
     if (!g_module_supported()) {
-        fprintf(stderr, "Module is not supported by system.\n");
-        return false;
+        error_setg(errp, "%s", "this platform does not support GLib modules");
+        return -1;
     }
 
     if (!loaded_modules) {
         loaded_modules = g_hash_table_new(g_str_hash, g_str_equal);
     }
 
-    module_name = g_strdup_printf("%s%s", prefix, lib_name);
+    /* allocate all resources managed by the out: label here */
+    module_name = g_strdup_printf("%s%s", prefix, name);
 
     if (g_hash_table_contains(loaded_modules, module_name)) {
         g_free(module_name);
-        return true;
+        return 2; /* module already loaded */
     }
     g_hash_table_add(loaded_modules, module_name);
 
+    search_dir = getenv("QEMU_MODULE_DIR");
+    if (search_dir != NULL) {
+        dirs[n_dirs++] = g_strdup_printf("%s", search_dir);
+    }
+    dirs[n_dirs++] = get_relocated_path(CONFIG_QEMU_MODDIR);
+
+#ifdef CONFIG_MODULE_UPGRADES
+    version_dir = g_strcanon(g_strdup(QEMU_PKGVERSION),
+                             G_CSET_A_2_Z G_CSET_a_2_z G_CSET_DIGITS "+-.~",
+                             '_');
+    dirs[n_dirs++] = g_strdup_printf("/var/run/qemu/%s", version_dir);
+#endif
+    assert(n_dirs <= ARRAY_SIZE(dirs));
+
+    /* end of resources managed by the out: label */
+
     for (modinfo = module_info; modinfo->name != NULL; modinfo++) {
         if (modinfo->arch) {
             if (strcmp(modinfo->name, module_name) == 0) {
                 if (!module_check_arch(modinfo)) {
-                    return false;
+                    error_setg(errp, "module arch does not match: "
+                        "expected '%s', got '%s'", module_arch, modinfo->arch);
+                    goto out;
                 }
             }
         }
@@ -256,7 +262,11 @@ bool module_load_one(const char *prefix, const char *lib_name, bool mayfail)
             if (strcmp(modinfo->name, module_name) == 0) {
                 /* we depend on other module(s) */
                 for (sl = modinfo->deps; *sl != NULL; sl++) {
-                    module_load_one("", *sl, false);
+                    int subrv = module_load("", *sl, errp);
+                    if (subrv <= 0) {
+                        rv = subrv;
+                        goto out;
+                    }
                 }
             } else {
                 for (sl = modinfo->deps; *sl != NULL; sl++) {
@@ -269,58 +279,52 @@ bool module_load_one(const char *prefix, const char *lib_name, bool mayfail)
         }
     }
 
-    search_dir = getenv("QEMU_MODULE_DIR");
-    if (search_dir != NULL) {
-        dirs[n_dirs++] = g_strdup_printf("%s", search_dir);
-    }
-    dirs[n_dirs++] = get_relocated_path(CONFIG_QEMU_MODDIR);
-
-#ifdef CONFIG_MODULE_UPGRADES
-    version_dir = g_strcanon(g_strdup(QEMU_PKGVERSION),
-                             G_CSET_A_2_Z G_CSET_a_2_z G_CSET_DIGITS "+-.~",
-                             '_');
-    dirs[n_dirs++] = g_strdup_printf("/var/run/qemu/%s", version_dir);
-#endif
-
-    assert(n_dirs <= ARRAY_SIZE(dirs));
-
     for (i = 0; i < n_dirs; i++) {
-        fname = g_strdup_printf("%s/%s%s",
-                dirs[i], module_name, CONFIG_HOST_DSOSUF);
-        ret = module_load_file(fname, mayfail, export_symbols);
-        g_free(fname);
-        fname = NULL;
-        /* Try loading until loaded a module file */
-        if (!ret) {
-            success = true;
-            break;
+        char *fname = g_strdup_printf("%s/%s%s",
+                                      dirs[i], module_name, CONFIG_HOST_DSOSUF);
+        int ret = access(fname, F_OK);
+        if (ret != 0 && (errno == ENOENT || errno == ENOTDIR)) {
+            /*
+             * if we don't find the module in this dir, try the next one.
+             * If we don't find it in any dir, that can be fine too: user
+             * did not install the module. We will return 0 in this case
+             * with no error set.
+             */
+            g_free(fname);
+            continue;
+        } else if (ret != 0) {
+            /* most common is EACCES here */
+            error_setg_errno(errp, errno, "error trying to access %s", fname);
+        } else if (module_load_dso(fname, export_symbols, errp)) {
+            rv = 1; /* module successfully loaded */
         }
+        g_free(fname);
+        goto out;
     }
+    rv = 0; /* module not found */
 
-    if (!success) {
+out:
+    if (rv <= 0) {
         g_hash_table_remove(loaded_modules, module_name);
         g_free(module_name);
     }
-
     for (i = 0; i < n_dirs; i++) {
         g_free(dirs[i]);
     }
-
-#endif
-    return success;
+    return rv;
 }
 
-#ifdef CONFIG_MODULES
-
 static bool module_loaded_qom_all;
 
-void module_load_qom_one(const char *type)
+int module_load_qom(const char *type, Error **errp)
 {
     const QemuModinfo *modinfo;
     const char **sl;
+    int rv = 0;
 
     if (!type) {
-        return;
+        error_setg(errp, "%s", "type is NULL");
+        return -1;
     }
 
     trace_module_lookup_object_type(type);
@@ -333,15 +337,24 @@ void module_load_qom_one(const char *type)
         }
         for (sl = modinfo->objs; *sl != NULL; sl++) {
             if (strcmp(type, *sl) == 0) {
-                module_load_one("", modinfo->name, false);
+                if (rv > 0) {
+                    error_setg(errp, "multiple modules providing '%s'", type);
+                    return -1;
+                }
+                rv = module_load("", modinfo->name, errp);
+                if (rv < 0) {
+                    return rv;
+                }
             }
         }
     }
+    return rv;
 }
 
 void module_load_qom_all(void)
 {
     const QemuModinfo *modinfo;
+    Error *local_err = NULL;
 
     if (module_loaded_qom_all) {
         return;
@@ -354,7 +367,9 @@ void module_load_qom_all(void)
         if (!module_check_arch(modinfo)) {
             continue;
         }
-        module_load_one("", modinfo->name, false);
+        if (module_load("", modinfo->name, &local_err) < 0) {
+            error_report_err(local_err);
+        }
     }
     module_loaded_qom_all = true;
 }
@@ -370,7 +385,10 @@ void qemu_load_module_for_opts(const char *group)
         }
         for (sl = modinfo->opts; *sl != NULL; sl++) {
             if (strcmp(group, *sl) == 0) {
-                module_load_one("", modinfo->name, false);
+                Error *local_err = NULL;
+                if (module_load("", modinfo->name, &local_err) < 0) {
+                    error_report_err(local_err);
+                }
             }
         }
     }
@@ -380,7 +398,8 @@ void qemu_load_module_for_opts(const char *group)
 
 void module_allow_arch(const char *arch) {}
 void qemu_load_module_for_opts(const char *group) {}
-void module_load_qom_one(const char *type) {}
+int module_load(const char *prefix, const char *name, Error **errp) { return 2; }
+int module_load_qom(const char *type, Error **errp) { return 2; }
 void module_load_qom_all(void) {}
 
 #endif