Merge remote-tracking branch 'mdroth/qga-pull-3-11-2013' into staging

# By Laszlo Ersek (3) and others
# Via Michael Roth
* mdroth/qga-pull-3-11-2013:
  qga: implement qmp_guest_set_vcpus() for Linux with sysfs
  qga: implement qmp_guest_get_vcpus() for Linux with sysfs
  qga: introduce guest-get-vcpus / guest-set-vcpus with stubs
  qga: add guest-set-time command
  qga: add guest-get-time command
  qemu-ga: use key-value store to avoid recycling fd handles after restart
  qemu-ga: make guest-sync-delimited available during fsfreeze
  qemu-ga: fix confusing GAChannelMethod comparison
  qga: cast to int for DWORD type

qga/channel-win32.c

@@ -287,7 +287,7 @@ GIOStatus ga_channel_write_all(GAChannel *c, const char *buf, size_t size)
 static gboolean ga_channel_open(GAChannel *c, GAChannelMethod method,
                                 const gchar *path)
 {
-    if (!method == GA_CHANNEL_VIRTIO_SERIAL) {
+    if (method != GA_CHANNEL_VIRTIO_SERIAL) {
         g_critical("unsupported communication method");
         return false;
     }

qga/commands-posix.c

@@ -15,6 +15,10 @@
 #include <sys/types.h>
 #include <sys/ioctl.h>
 #include <sys/wait.h>
+#include <unistd.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <inttypes.h>
 #include "qga/guest-agent-core.h"
 #include "qga-qmp-commands.h"
 #include "qapi/qmp/qerror.h"
@@ -119,6 +123,77 @@ void qmp_guest_shutdown(bool has_mode, const char *mode, Error **err)
     /* succeded */
 }
 
+int64_t qmp_guest_get_time(Error **errp)
+{
+   int ret;
+   qemu_timeval tq;
+   int64_t time_ns;
+
+   ret = qemu_gettimeofday(&tq);
+   if (ret < 0) {
+       error_setg_errno(errp, errno, "Failed to get time");
+       return -1;
+   }
+
+   time_ns = tq.tv_sec * 1000000000LL + tq.tv_usec * 1000;
+   return time_ns;
+}
+
+void qmp_guest_set_time(int64_t time_ns, Error **errp)
+{
+    int ret;
+    int status;
+    pid_t pid;
+    Error *local_err = NULL;
+    struct timeval tv;
+
+    /* year-2038 will overflow in case time_t is 32bit */
+    if (time_ns / 1000000000 != (time_t)(time_ns / 1000000000)) {
+        error_setg(errp, "Time %" PRId64 " is too large", time_ns);
+        return;
+    }
+
+    tv.tv_sec = time_ns / 1000000000;
+    tv.tv_usec = (time_ns % 1000000000) / 1000;
+
+    ret = settimeofday(&tv, NULL);
+    if (ret < 0) {
+        error_setg_errno(errp, errno, "Failed to set time to guest");
+        return;
+    }
+
+    /* Set the Hardware Clock to the current System Time. */
+    pid = fork();
+    if (pid == 0) {
+        setsid();
+        reopen_fd_to_null(0);
+        reopen_fd_to_null(1);
+        reopen_fd_to_null(2);
+
+        execle("/sbin/hwclock", "hwclock", "-w", NULL, environ);
+        _exit(EXIT_FAILURE);
+    } else if (pid < 0) {
+        error_setg_errno(errp, errno, "failed to create child process");
+        return;
+    }
+
+    ga_wait_child(pid, &status, &local_err);
+    if (error_is_set(&local_err)) {
+        error_propagate(errp, local_err);
+        return;
+    }
+
+    if (!WIFEXITED(status)) {
+        error_setg(errp, "child process has terminated abnormally");
+        return;
+    }
+
+    if (WEXITSTATUS(status)) {
+        error_setg(errp, "hwclock failed to set hardware clock to system time");
+        return;
+    }
+}
+
 typedef struct GuestFileHandle {
     uint64_t id;
     FILE *fh;
@@ -129,14 +204,22 @@ static struct {
     QTAILQ_HEAD(, GuestFileHandle) filehandles;
 } guest_file_state;
 
-static void guest_file_handle_add(FILE *fh)
+static int64_t guest_file_handle_add(FILE *fh, Error **errp)
 {
     GuestFileHandle *gfh;
+    int64_t handle;
+
+    handle = ga_get_fd_handle(ga_state, errp);
+    if (error_is_set(errp)) {
+        return 0;
+    }
 
     gfh = g_malloc0(sizeof(GuestFileHandle));
-    gfh->id = fileno(fh);
+    gfh->id = handle;
     gfh->fh = fh;
     QTAILQ_INSERT_TAIL(&guest_file_state.filehandles, gfh, next);
+
+    return handle;
 }
 
 static GuestFileHandle *guest_file_handle_find(int64_t id, Error **err)
@@ -158,7 +241,7 @@ int64_t qmp_guest_file_open(const char *path, bool has_mode, const char *mode, E
 {
     FILE *fh;
     int fd;
-    int64_t ret = -1;
+    int64_t ret = -1, handle;
 
     if (!has_mode) {
         mode = "r";
@@ -184,9 +267,14 @@ int64_t qmp_guest_file_open(const char *path, bool has_mode, const char *mode, E
         return -1;
     }
 
-    guest_file_handle_add(fh);
-    slog("guest-file-open, handle: %d", fd);
-    return fd;
+    handle = guest_file_handle_add(fh, err);
+    if (error_is_set(err)) {
+        fclose(fh);
+        return -1;
+    }
+
+    slog("guest-file-open, handle: %d", handle);
+    return handle;
 }
 
 void qmp_guest_file_close(int64_t handle, Error **err)
@@ -1027,6 +1115,162 @@ error:
     return NULL;
 }
 
+#define SYSCONF_EXACT(name, err) sysconf_exact((name), #name, (err))
+
+static long sysconf_exact(int name, const char *name_str, Error **err)
+{
+    long ret;
+
+    errno = 0;
+    ret = sysconf(name);
+    if (ret == -1) {
+        if (errno == 0) {
+            error_setg(err, "sysconf(%s): value indefinite", name_str);
+        } else {
+            error_setg_errno(err, errno, "sysconf(%s)", name_str);
+        }
+    }
+    return ret;
+}
+
+/* Transfer online/offline status between @vcpu and the guest system.
+ *
+ * On input either @errp or *@errp must be NULL.
+ *
+ * In system-to-@vcpu direction, the following @vcpu fields are accessed:
+ * - R: vcpu->logical_id
+ * - W: vcpu->online
+ * - W: vcpu->can_offline
+ *
+ * In @vcpu-to-system direction, the following @vcpu fields are accessed:
+ * - R: vcpu->logical_id
+ * - R: vcpu->online
+ *
+ * Written members remain unmodified on error.
+ */
+static void transfer_vcpu(GuestLogicalProcessor *vcpu, bool sys2vcpu,
+                          Error **errp)
+{
+    char *dirpath;
+    int dirfd;
+
+    dirpath = g_strdup_printf("/sys/devices/system/cpu/cpu%" PRId64 "/",
+                              vcpu->logical_id);
+    dirfd = open(dirpath, O_RDONLY | O_DIRECTORY);
+    if (dirfd == -1) {
+        error_setg_errno(errp, errno, "open(\"%s\")", dirpath);
+    } else {
+        static const char fn[] = "online";
+        int fd;
+        int res;
+
+        fd = openat(dirfd, fn, sys2vcpu ? O_RDONLY : O_RDWR);
+        if (fd == -1) {
+            if (errno != ENOENT) {
+                error_setg_errno(errp, errno, "open(\"%s/%s\")", dirpath, fn);
+            } else if (sys2vcpu) {
+                vcpu->online = true;
+                vcpu->can_offline = false;
+            } else if (!vcpu->online) {
+                error_setg(errp, "logical processor #%" PRId64 " can't be "
+                           "offlined", vcpu->logical_id);
+            } /* otherwise pretend successful re-onlining */
+        } else {
+            unsigned char status;
+
+            res = pread(fd, &status, 1, 0);
+            if (res == -1) {
+                error_setg_errno(errp, errno, "pread(\"%s/%s\")", dirpath, fn);
+            } else if (res == 0) {
+                error_setg(errp, "pread(\"%s/%s\"): unexpected EOF", dirpath,
+                           fn);
+            } else if (sys2vcpu) {
+                vcpu->online = (status != '0');
+                vcpu->can_offline = true;
+            } else if (vcpu->online != (status != '0')) {
+                status = '0' + vcpu->online;
+                if (pwrite(fd, &status, 1, 0) == -1) {
+                    error_setg_errno(errp, errno, "pwrite(\"%s/%s\")", dirpath,
+                                     fn);
+                }
+            } /* otherwise pretend successful re-(on|off)-lining */
+
+            res = close(fd);
+            g_assert(res == 0);
+        }
+
+        res = close(dirfd);
+        g_assert(res == 0);
+    }
+
+    g_free(dirpath);
+}
+
+GuestLogicalProcessorList *qmp_guest_get_vcpus(Error **errp)
+{
+    int64_t current;
+    GuestLogicalProcessorList *head, **link;
+    long sc_max;
+    Error *local_err = NULL;
+
+    current = 0;
+    head = NULL;
+    link = &head;
+    sc_max = SYSCONF_EXACT(_SC_NPROCESSORS_CONF, &local_err);
+
+    while (local_err == NULL && current < sc_max) {
+        GuestLogicalProcessor *vcpu;
+        GuestLogicalProcessorList *entry;
+
+        vcpu = g_malloc0(sizeof *vcpu);
+        vcpu->logical_id = current++;
+        vcpu->has_can_offline = true; /* lolspeak ftw */
+        transfer_vcpu(vcpu, true, &local_err);
+
+        entry = g_malloc0(sizeof *entry);
+        entry->value = vcpu;
+
+        *link = entry;
+        link = &entry->next;
+    }
+
+    if (local_err == NULL) {
+        /* there's no guest with zero VCPUs */
+        g_assert(head != NULL);
+        return head;
+    }
+
+    qapi_free_GuestLogicalProcessorList(head);
+    error_propagate(errp, local_err);
+    return NULL;
+}
+
+int64_t qmp_guest_set_vcpus(GuestLogicalProcessorList *vcpus, Error **errp)
+{
+    int64_t processed;
+    Error *local_err = NULL;
+
+    processed = 0;
+    while (vcpus != NULL) {
+        transfer_vcpu(vcpus->value, false, &local_err);
+        if (local_err != NULL) {
+            break;
+        }
+        ++processed;
+        vcpus = vcpus->next;
+    }
+
+    if (local_err != NULL) {
+        if (processed == 0) {
+            error_propagate(errp, local_err);
+        } else {
+            error_free(local_err);
+        }
+    }
+
+    return processed;
+}
+
 #else /* defined(__linux__) */
 
 void qmp_guest_suspend_disk(Error **err)
@@ -1050,6 +1294,18 @@ GuestNetworkInterfaceList *qmp_guest_network_get_interfaces(Error **errp)
     return NULL;
 }
 
+GuestLogicalProcessorList *qmp_guest_get_vcpus(Error **errp)
+{
+    error_set(errp, QERR_UNSUPPORTED);
+    return NULL;
+}
+
+int64_t qmp_guest_set_vcpus(GuestLogicalProcessorList *vcpus, Error **errp)
+{
+    error_set(errp, QERR_UNSUPPORTED);
+    return -1;
+}
+
 #endif
 
 #if !defined(CONFIG_FSFREEZE)

qga/commands-win32.c

@@ -278,6 +278,29 @@ GuestNetworkInterfaceList *qmp_guest_network_get_interfaces(Error **err)
     return NULL;
 }
 
+int64_t qmp_guest_get_time(Error **errp)
+{
+    error_set(errp, QERR_UNSUPPORTED);
+    return -1;
+}
+
+void qmp_guest_set_time(int64_t time_ns, Error **errp)
+{
+    error_set(errp, QERR_UNSUPPORTED);
+}
+
+GuestLogicalProcessorList *qmp_guest_get_vcpus(Error **errp)
+{
+    error_set(errp, QERR_UNSUPPORTED);
+    return NULL;
+}
+
+int64_t qmp_guest_set_vcpus(GuestLogicalProcessorList *vcpus, Error **errp)
+{
+    error_set(errp, QERR_UNSUPPORTED);
+    return -1;
+}
+
 /* register init/cleanup routines for stateful command groups */
 void ga_command_state_init(GAState *s, GACommandState *cs)
 {

qga/guest-agent-core.h

@@ -35,6 +35,7 @@ bool ga_is_frozen(GAState *s);
 void ga_set_frozen(GAState *s);
 void ga_unset_frozen(GAState *s);
 const char *ga_fsfreeze_hook(GAState *s);
+int64_t ga_get_fd_handle(GAState *s, Error **errp);
 
 #ifndef _WIN32
 void reopen_fd_to_null(int fd);

qga/main.c

@@ -15,6 +15,7 @@
 #include <stdbool.h>
 #include <glib.h>
 #include <getopt.h>
+#include <glib/gstdio.h>
 #ifndef _WIN32
 #include <syslog.h>
 #include <sys/wait.h>
@@ -30,6 +31,7 @@
 #include "qapi/qmp/qerror.h"
 #include "qapi/qmp/dispatch.h"
 #include "qga/channel.h"
+#include "qemu/bswap.h"
 #ifdef _WIN32
 #include "qga/service-win32.h"
 #include <windows.h>
@@ -53,6 +55,11 @@
 #endif
 #define QGA_SENTINEL_BYTE 0xFF
 
+typedef struct GAPersistentState {
+#define QGA_PSTATE_DEFAULT_FD_COUNTER 1000
+    int64_t fd_counter;
+} GAPersistentState;
+
 struct GAState {
     JSONMessageParser parser;
     GMainLoop *main_loop;
@@ -76,6 +83,8 @@ struct GAState {
 #ifdef CONFIG_FSFREEZE
     const char *fsfreeze_hook;
 #endif
+    const gchar *pstate_filepath;
+    GAPersistentState pstate;
 };
 
 struct GAState *ga_state;
@@ -85,6 +94,7 @@ static const char *ga_freeze_whitelist[] = {
     "guest-ping",
     "guest-info",
     "guest-sync",
+    "guest-sync-delimited",
     "guest-fsfreeze-status",
     "guest-fsfreeze-thaw",
     NULL
@@ -724,6 +734,171 @@ VOID WINAPI service_main(DWORD argc, TCHAR *argv[])
 }
 #endif
 
+static void set_persistent_state_defaults(GAPersistentState *pstate)
+{
+    g_assert(pstate);
+    pstate->fd_counter = QGA_PSTATE_DEFAULT_FD_COUNTER;
+}
+
+static void persistent_state_from_keyfile(GAPersistentState *pstate,
+                                          GKeyFile *keyfile)
+{
+    g_assert(pstate);
+    g_assert(keyfile);
+    /* if any fields are missing, either because the file was tampered with
+     * by agents of chaos, or because the field wasn't present at the time the
+     * file was created, the best we can ever do is start over with the default
+     * values. so load them now, and ignore any errors in accessing key-value
+     * pairs
+     */
+    set_persistent_state_defaults(pstate);
+
+    if (g_key_file_has_key(keyfile, "global", "fd_counter", NULL)) {
+        pstate->fd_counter =
+            g_key_file_get_int64(keyfile, "global", "fd_counter", NULL);
+    }
+}
+
+static void persistent_state_to_keyfile(const GAPersistentState *pstate,
+                                        GKeyFile *keyfile)
+{
+    g_assert(pstate);
+    g_assert(keyfile);
+
+    g_key_file_set_int64(keyfile, "global", "fd_counter", pstate->fd_counter);
+}
+
+static gboolean write_persistent_state(const GAPersistentState *pstate,
+                                       const gchar *path)
+{
+    GKeyFile *keyfile = g_key_file_new();
+    GError *gerr = NULL;
+    gboolean ret = true;
+    gchar *data = NULL;
+    gsize data_len;
+
+    g_assert(pstate);
+
+    persistent_state_to_keyfile(pstate, keyfile);
+    data = g_key_file_to_data(keyfile, &data_len, &gerr);
+    if (gerr) {
+        g_critical("failed to convert persistent state to string: %s",
+                   gerr->message);
+        ret = false;
+        goto out;
+    }
+
+    g_file_set_contents(path, data, data_len, &gerr);
+    if (gerr) {
+        g_critical("failed to write persistent state to %s: %s",
+                    path, gerr->message);
+        ret = false;
+        goto out;
+    }
+
+out:
+    if (gerr) {
+        g_error_free(gerr);
+    }
+    if (keyfile) {
+        g_key_file_free(keyfile);
+    }
+    g_free(data);
+    return ret;
+}
+
+static gboolean read_persistent_state(GAPersistentState *pstate,
+                                      const gchar *path, gboolean frozen)
+{
+    GKeyFile *keyfile = NULL;
+    GError *gerr = NULL;
+    struct stat st;
+    gboolean ret = true;
+
+    g_assert(pstate);
+
+    if (stat(path, &st) == -1) {
+        /* it's okay if state file doesn't exist, but any other error
+         * indicates a permissions issue or some other misconfiguration
+         * that we likely won't be able to recover from.
+         */
+        if (errno != ENOENT) {
+            g_critical("unable to access state file at path %s: %s",
+                       path, strerror(errno));
+            ret = false;
+            goto out;
+        }
+
+        /* file doesn't exist. initialize state to default values and
+         * attempt to save now. (we could wait till later when we have
+         * modified state we need to commit, but if there's a problem,
+         * such as a missing parent directory, we want to catch it now)
+         *
+         * there is a potential scenario where someone either managed to
+         * update the agent from a version that didn't use a key store
+         * while qemu-ga thought the filesystem was frozen, or
+         * deleted the key store prior to issuing a fsfreeze, prior
+         * to restarting the agent. in this case we go ahead and defer
+         * initial creation till we actually have modified state to
+         * write, otherwise fail to recover from freeze.
+         */
+        set_persistent_state_defaults(pstate);
+        if (!frozen) {
+            ret = write_persistent_state(pstate, path);
+            if (!ret) {
+                g_critical("unable to create state file at path %s", path);
+                ret = false;
+                goto out;
+            }
+        }
+        ret = true;
+        goto out;
+    }
+
+    keyfile = g_key_file_new();
+    g_key_file_load_from_file(keyfile, path, 0, &gerr);
+    if (gerr) {
+        g_critical("error loading persistent state from path: %s, %s",
+                   path, gerr->message);
+        ret = false;
+        goto out;
+    }
+
+    persistent_state_from_keyfile(pstate, keyfile);
+
+out:
+    if (keyfile) {
+        g_key_file_free(keyfile);
+    }
+    if (gerr) {
+        g_error_free(gerr);
+    }
+
+    return ret;
+}
+
+int64_t ga_get_fd_handle(GAState *s, Error **errp)
+{
+    int64_t handle;
+
+    g_assert(s->pstate_filepath);
+    /* we blacklist commands and avoid operations that potentially require
+     * writing to disk when we're in a frozen state. this includes opening
+     * new files, so we should never get here in that situation
+     */
+    g_assert(!ga_is_frozen(s));
+
+    handle = s->pstate.fd_counter++;
+    if (s->pstate.fd_counter < 0) {
+        s->pstate.fd_counter = 0;
+    }
+    if (!write_persistent_state(&s->pstate, s->pstate_filepath)) {
+        error_setg(errp, "failed to commit persistent state to disk");
+    }
+
+    return handle;
+}
+
 int main(int argc, char **argv)
 {
     const char *sopt = "hVvdm:p:l:f:F::b:s:t:";
@@ -853,7 +1028,9 @@ int main(int argc, char **argv)
     ga_enable_logging(s);
     s->state_filepath_isfrozen = g_strdup_printf("%s/qga.state.isfrozen",
                                                  state_dir);
+    s->pstate_filepath = g_strdup_printf("%s/qga.state", state_dir);
     s->frozen = false;
+
 #ifndef _WIN32
     /* check if a previous instance of qemu-ga exited with filesystems' state
      * marked as frozen. this could be a stale value (a non-qemu-ga process
@@ -910,6 +1087,14 @@ int main(int argc, char **argv)
         }
     }
 
+    /* load persistent state from disk */
+    if (!read_persistent_state(&s->pstate,
+                               s->pstate_filepath,
+                               ga_is_frozen(s))) {
+        g_critical("failed to load persistent state");
+        goto out_bad;
+    }
+
     if (blacklist) {
         s->blacklist = blacklist;
         do {

qga/qapi-schema.json

@@ -82,6 +82,45 @@
 ##
 { 'command': 'guest-ping' }
 
+##
+# @guest-get-time:
+#
+# Get the information about guest time relative to the Epoch
+# of 1970-01-01 in UTC.
+#
+# Returns: Time in nanoseconds.
+#
+# Since 1.5
+##
+{ 'command': 'guest-get-time',
+  'returns': 'int' }
+
+##
+# @guest-set-time:
+#
+# Set guest time.
+#
+# When a guest is paused or migrated to a file then loaded
+# from that file, the guest OS has no idea that there
+# was a big gap in the time. Depending on how long the
+# gap was, NTP might not be able to resynchronize the
+# guest.
+#
+# This command tries to set guest time to the given value,
+# then sets the Hardware Clock to the current System Time.
+# This will make it easier for a guest to resynchronize
+# without waiting for NTP.
+#
+# @time: time of nanoseconds, relative to the Epoch of
+#        1970-01-01 in UTC.
+#
+# Returns: Nothing on success.
+#
+# Since: 1.5
+##
+{ 'command': 'guest-set-time',
+  'data': { 'time': 'int' } }
+
 ##
 # @GuestAgentCommandInfo:
 #
@@ -515,3 +554,75 @@
 ##
 { 'command': 'guest-network-get-interfaces',
   'returns': ['GuestNetworkInterface'] }
+
+##
+# @GuestLogicalProcessor:
+#
+# @logical-id: Arbitrary guest-specific unique identifier of the VCPU.
+#
+# @online: Whether the VCPU is enabled.
+#
+# @can-offline: Whether offlining the VCPU is possible. This member is always
+#               filled in by the guest agent when the structure is returned,
+#               and always ignored on input (hence it can be omitted then).
+#
+# Since: 1.5
+##
+{ 'type': 'GuestLogicalProcessor',
+  'data': {'logical-id': 'int',
+           'online': 'bool',
+           '*can-offline': 'bool'} }
+
+##
+# @guest-get-vcpus:
+#
+# Retrieve the list of the guest's logical processors.
+#
+# This is a read-only operation.
+#
+# Returns: The list of all VCPUs the guest knows about. Each VCPU is put on the
+# list exactly once, but their order is unspecified.
+#
+# Since: 1.5
+##
+{ 'command': 'guest-get-vcpus',
+  'returns': ['GuestLogicalProcessor'] }
+
+##
+# @guest-set-vcpus:
+#
+# Attempt to reconfigure (currently: enable/disable) logical processors inside
+# the guest.
+#
+# The input list is processed node by node in order. In each node @logical-id
+# is used to look up the guest VCPU, for which @online specifies the requested
+# state. The set of distinct @logical-id's is only required to be a subset of
+# the guest-supported identifiers. There's no restriction on list length or on
+# repeating the same @logical-id (with possibly different @online field).
+# Preferably the input list should describe a modified subset of
+# @guest-get-vcpus' return value.
+#
+# Returns: The length of the initial sublist that has been successfully
+#          processed. The guest agent maximizes this value. Possible cases:
+#
+#          0:                if the @vcpus list was empty on input. Guest state
+#                            has not been changed. Otherwise,
+#
+#          Error:            processing the first node of @vcpus failed for the
+#                            reason returned. Guest state has not been changed.
+#                            Otherwise,
+#
+#          < length(@vcpus): more than zero initial nodes have been processed,
+#                            but not the entire @vcpus list. Guest state has
+#                            changed accordingly. To retrieve the error
+#                            (assuming it persists), repeat the call with the
+#                            successfully processed initial sublist removed.
+#                            Otherwise,
+#
+#          length(@vcpus):   call successful.
+#
+# Since: 1.5
+##
+{ 'command': 'guest-set-vcpus',
+  'data':    {'vcpus': ['GuestLogicalProcessor'] },
+  'returns': 'int' }

qga/service-win32.c

@@ -29,7 +29,7 @@ static int printf_win_error(const char *text)
         MAKELANGID(LANG_NEUTRAL, SUBLANG_DEFAULT),
         (char *)&message, 0,
         NULL);
-    n = printf("%s. (Error: %d) %s", text, err, message);
+    n = printf("%s. (Error: %d) %s", text, (int)err, message);
     LocalFree(message);
 
     return n;