@@ -145,6 +145,9 @@ obj-y += dump.o
obj-y += migration/ram.o migration/savevm.o
LIBS := $(libs_softmmu) $(LIBS)
+# qqq support
+obj-y += qqq.o
+
# xen support
obj-$(CONFIG_XEN) += xen-common.o
obj-$(CONFIG_XEN_I386) += xen-hvm.o xen-mapcache.o
@@ -1688,3 +1688,11 @@ void dump_drift_info(FILE *f, fprintf_function cpu_fprintf)
cpu_fprintf(f, "Max guest advance NA\n");
}
}
+
+void kick_all_vcpus(void)
+{
+ CPUState *cpu;
+ CPU_FOREACH(cpu) {
+ qemu_cpu_kick(cpu);
+ }
+}
new file mode 100644
@@ -0,0 +1,59 @@
+= Synchronizing the virtual clock with an external source =
+
+QEMU has a protocol for synchronizing its virtual clock
+with the clock of a simulator in which QEMU is embedded
+as a component. This options is enabled with the -qqq
+argument, and it should generally be accompanied by the
+following additional command line arguments:
+
+-icount 1,sleep=off -rtc clock=vm
+ or
+-enable-kvm -rtc clock=vm
+
+The -qqq argument is used to supply a file descriptor
+for a Unix socket, which is used for synchronization.
+The procedure for launching QEMU in is synchronization
+mode has three steps:
+
+(1) Create a socket pair with the Linux socketpair function.
+ The code segment that does this might look like
+
+ int socks[2];
+ socketpair(AF_UNIX,SOCK_STREAM,0,socks);
+
+(2) Fork QEMU with the appropriate command line arguments.
+ The -qqq part of the argument will look something like
+
+ -qqq sock=socks[1]
+
+(3) After forking QEMU, close sock[1] and retain the
+ sock[0] for communicating with QEMU.
+
+The synchronization protocol is very simple. To start, the
+external simulator writes an integer to its socket with
+the amount of time in microseconds that QEMU is allowed to
+advance. The code segment that does this might look like:
+
+ uint32_t ta = htonl(1000); // Advance by 1 millisecond
+ write(sock[0],&ta,sizeof(uint32_t));
+
+The external simulator can then advance its clock by this
+same amount. During this time, QEMU and the external simulator
+will be executing in parallel. When the external simulator
+completes its time advance, it waits for QEMU by reading from
+its socket. The value read will be the actual number of
+virtual microseconds by which QEMU has advanced its virtual clock.
+This will be greater than or equal to the requested advance.
+The code that does this might look like:
+
+ uint32_t ta;
+ read(fd,&ta,sizeof(uint32_t));
+ ta = ntohl(ta);
+
+These steps are repeated until either (1) the external simulator
+closes its socket thereby causing QEMU to terminate or (2) QEMU
+stops executing (e.g., if the emulated computer is shutdown) and
+causes a read or write error on the simulator's socket.
+
+You can find an example of a simulator using this protocol in
+the adevs simulation package at http://sourceforge.net/projects/adevs/
@@ -2,6 +2,7 @@
#define QEMU_CPUS_H
/* cpus.c */
+void kick_all_vcpus(void);
bool qemu_in_vcpu_thread(void);
void qemu_init_cpu_loop(void);
void resume_all_vcpus(void);
@@ -18,6 +18,7 @@
#include <linux/kvm.h>
+#include "qqq.h"
#include "qemu-common.h"
#include "qemu/atomic.h"
#include "qemu/option.h"
@@ -1926,6 +1927,15 @@ int kvm_cpu_exec(CPUState *cpu)
qemu_cpu_kick_self();
}
+ if (qqq_enabled()) {
+ /* Pause here while qqq is synchronizing with a simulation clock.
+ * We do not want to execute instructions past the synchronization
+ * deadline, but its ok to update the states of other equipment
+ * like timers, i/o devices, etc.
+ */
+ qqq_sync();
+ }
+
run_ret = kvm_vcpu_ioctl(cpu, KVM_RUN, 0);
attrs = kvm_arch_post_run(cpu, run);
@@ -3389,6 +3389,22 @@ many timer interrupts were not processed by the Windows guest and will
re-inject them.
ETEXI
+DEF("qqq", HAS_ARG, QEMU_OPTION_qqq, \
+ "-qqq sock=fd\n" \
+ " enable synchronization of the virtual clock \n" \
+ " with an external simulation clock\n", QEMU_ARCH_ALL)
+STEXI
+@item -qqq sock=@var{fd0}
+@findex -qqq
+Qemu will use the supplied socket to synchronize its virtual clock with
+an external simulation clock. Qemu will wait until a time slice size in
+microseconds is supplied on the socket. Then it will execute for at
+least that number of virtual microseconds before writing the actual
+virtual time that has elapsed in microseconds to the socket. This
+cycle will repeat until a zero time advance is requested, which
+will cause qemu to exit.
+ETEXI
+
DEF("icount", HAS_ARG, QEMU_OPTION_icount, \
"-icount [shift=N|auto][,align=on|off][,sleep=on|off,rr=record|replay,rrfile=<filename>]\n" \
" enable virtual instruction counter with 2^N clock ticks per\n" \
new file mode 100644
@@ -0,0 +1,177 @@
+#include "qemu/osdep.h"
+#include "qemu/timer.h"
+#include "qemu/main-loop.h"
+#include "sysemu/cpus.h"
+#include "sysemu/kvm.h"
+#include "qqq.h"
+/* This is a Linux only feature */
+
+#ifndef _WIN32
+
+#include <arpa/inet.h>
+#include <stdint.h>
+#include <unistd.h>
+#include <assert.h>
+
+static bool enabled = false, syncing = true;
+static unsigned elapsed; /* initialized to zero */
+static int time_advance = -1;
+static int fd = -1;
+static int64_t t;
+static QEMUTimer *sync_timer;
+static QemuMutex qqq_mutex;
+static QemuCond qqq_cond;
+
+bool qqq_enabled(void)
+{
+ return enabled;
+}
+
+void qqq_sync(void)
+{
+ /* kvm-all.c will call this function before running
+ * instructions with kvm. Because syncing will be
+ * true while qqq is waiting for a new time advance
+ * from the simulation, no instructions will execute
+ * while the machine is supposed to be suspended in
+ * simulation time.
+ */
+ qemu_mutex_lock(&qqq_mutex);
+ while (syncing) {
+ qemu_cond_wait(&qqq_cond, &qqq_mutex);
+ }
+ qemu_mutex_unlock(&qqq_mutex);
+}
+
+static void cleanup_and_exit(void)
+{
+ /* Close the socket and quit */
+ close(fd);
+ exit(0);
+}
+
+static void start_emulator(void)
+{
+ if (kvm_enabled()) {
+ /* Setting syncing to false tells kvm-all that
+ * it can execute guest instructions.
+ */
+ qemu_mutex_lock(&qqq_mutex);
+ syncing = false;
+ qemu_mutex_unlock(&qqq_mutex);
+ qemu_cond_signal(&qqq_cond);
+ /* Restart the emulator clock */
+ cpu_enable_ticks();
+ }
+}
+
+static void stop_emulator(void)
+{
+ if (kvm_enabled()) {
+ /* Tell the emulator that it is not allowed to
+ * execute guest instructions.
+ */
+ qemu_mutex_lock(&qqq_mutex);
+ syncing = true;
+ qemu_mutex_unlock(&qqq_mutex);
+ /* Kick KVM off of the CPU and stop the emulator clock. */
+ cpu_disable_ticks();
+ kick_all_vcpus();
+ }
+}
+
+static void write_mem_value(unsigned val)
+{
+ uint32_t msg = htonl(val);
+ if (write(fd, &msg, sizeof(uint32_t)) != sizeof(uint32_t)) {
+ /* If the socket is no good, then assume this is an
+ * indication that we should exit.
+ */
+ cleanup_and_exit();
+ }
+}
+
+static unsigned read_mem_value(void)
+{
+ uint32_t msg;
+ if (read(fd, &msg, sizeof(uint32_t)) != sizeof(uint32_t)) {
+ /* If the socket is no good, then assume this is an
+ * indication that we should exit.
+ */
+ cleanup_and_exit();
+ }
+ return ntohl(msg);
+}
+
+static void schedule_next_event(void)
+{
+ /* If we got the time advance in fd_read, then don't do it
+ * again here. */
+ if (time_advance < 0) {
+ /* Otherwise read the value from the socket */
+ time_advance = read_mem_value();
+ }
+ assert(t == 0 ||
+ abs(t - qemu_clock_get_us(QEMU_CLOCK_VIRTUAL)) <= time_advance);
+ /* Schedule the next synchronization point */
+ timer_mod(sync_timer, t + time_advance);
+ /* Note that we need to read the time advance again on the next pass */
+ time_advance = -1;
+ /* Start advancing cpu ticks and the wall clock */
+ start_emulator();
+}
+
+static void sync_func(void *data)
+{
+ /* Stop advancing cpu ticks and the wall clock */
+ stop_emulator();
+ /* Report the actual elapsed time to the external simulator. */
+ int64_t tnow = qemu_clock_get_us(QEMU_CLOCK_VIRTUAL);
+ elapsed = tnow - t;
+ write_mem_value(elapsed);
+ /* Update our time of last event */
+ t = tnow;
+ /* Schedule the next event */
+ schedule_next_event();
+}
+
+static void fd_read(void *opaque)
+{
+ /* Read the time advance if its becomes available
+ * before our timer expires */
+ time_advance = read_mem_value();
+}
+
+void setup_qqq(QemuOpts *opts)
+{
+ /* The module has been enabled */
+ enabled = true;
+ if (kvm_enabled()) {
+ qemu_mutex_init(&qqq_mutex);
+ qemu_cond_init(&qqq_cond);
+ }
+ /* Stop the clock while the simulation is initialized */
+ stop_emulator();
+ /* Initialize the simulation clock */
+ t = 0;
+ /* Get the communication socket */
+ fd = qemu_opt_get_number(opts, "sock", 0);
+ /* Start the timer to ensure time warps advance the clock */
+ sync_timer = timer_new_us(QEMU_CLOCK_VIRTUAL, sync_func, NULL);
+ /* Get the time advance that is requested by the simulation */
+ schedule_next_event();
+ /* Register the file descriptor with qemu. This should ensure
+ * the emulator doesn't pause for lack of I/O and thereby
+ * cause the attached simulator to pause with it. */
+ qemu_set_fd_handler(fd, fd_read, NULL, NULL);
+}
+
+#else
+
+void setup_qqq(QemuOpts *opts)
+{
+ fprintf(stderr, "-qqq is not supported on Windows, exiting\n");
+ exit(0);
+}
+
+#endif
new file mode 100644
@@ -0,0 +1,37 @@
+/*
+ * This work is licensed under the terms of the GNU GPL
+ * version 2. Seethe COPYING file in the top-level directory.
+ *
+ * A module for pacing the rate of advance of the computer
+ * clock in reference to an external simulation clock. The
+ * basic approach used here is adapted from QBox from Green
+ * Socs. The mode of operation is as follows:
+ *
+ * The simulator uses pipes to exchange time advance data.
+ * The external simulator starts the exchange by forking a
+ * QEMU process and passing is descriptors for a read and
+ * write pipe. Then the external simulator writes an integer
+ * (native endian) to the pipe to indicate the number of
+ * microseconds that QEMU should advance. QEMU advances its
+ * virtual clock by this amount and writes to its write pipe
+ * the actual number of microseconds that have advanced.
+ * This process continues until a pipe on either side is
+ * closed, which will either cause QEMU to exit (if the
+ * external simulator closes a pipe) or raise SIGPIPE in the
+ * external simulator (if QEMU closes a pipe).
+ *
+ * Authors:
+ * James Nutaro <nutaro@gmail.com>
+ *
+ */
+#ifndef QQQ_H
+#define QQQ_H
+
+#include "qemu/osdep.h"
+#include "qemu-options.h"
+
+void qqq_sync(void);
+bool qqq_enabled(void);
+void setup_qqq(QemuOpts *opts);
+
+#endif
@@ -124,6 +124,8 @@ int main(int argc, char **argv)
#include "qapi/qmp/qerror.h"
#include "sysemu/iothread.h"
+#include "qqq.h"
+
#define MAX_VIRTIO_CONSOLES 1
#define MAX_SCLP_CONSOLES 1
@@ -234,6 +236,20 @@ static struct {
{ .driver = "virtio-vga", .flag = &default_vga },
};
+static QemuOptsList qemu_qqq_opts = {
+ .name = "qqq",
+ .implied_opt_name = "",
+ .merge_lists = true,
+ .head = QTAILQ_HEAD_INITIALIZER(qemu_qqq_opts.head),
+ .desc = {
+ {
+ .name = "sock",
+ .type = QEMU_OPT_NUMBER,
+ },
+ { /* end of list */ }
+ },
+};
+
static QemuOptsList qemu_rtc_opts = {
.name = "rtc",
.head = QTAILQ_HEAD_INITIALIZER(qemu_rtc_opts.head),
@@ -3001,6 +3017,7 @@ int main(int argc, char **argv, char **envp)
DisplayState *ds;
int cyls, heads, secs, translation;
QemuOpts *hda_opts = NULL, *opts, *machine_opts, *icount_opts = NULL;
+ QemuOpts *qqq_opts = NULL;
QemuOptsList *olist;
int optind;
const char *optarg;
@@ -3040,6 +3057,7 @@ int main(int argc, char **argv, char **envp)
module_call_init(MODULE_INIT_QOM);
module_call_init(MODULE_INIT_QAPI);
+ qemu_add_opts(&qemu_qqq_opts);
qemu_add_opts(&qemu_drive_opts);
qemu_add_drive_opts(&qemu_legacy_drive_opts);
qemu_add_drive_opts(&qemu_common_drive_opts);
@@ -3904,6 +3922,13 @@ int main(int argc, char **argv, char **envp)
exit(1);
}
break;
+ case QEMU_OPTION_qqq:
+ qqq_opts = qemu_opts_parse_noisily(qemu_find_opts("qqq"),
+ optarg, true);
+ if (!qqq_opts) {
+ exit(1);
+ }
+ break;
case QEMU_OPTION_incoming:
if (!incoming) {
runstate_set(RUN_STATE_INMIGRATE);
@@ -4412,6 +4437,17 @@ int main(int argc, char **argv, char **envp)
/* spice needs the timers to be initialized by this point */
qemu_spice_init();
+ if (qqq_opts) {
+ if (!(rtc_clock == QEMU_CLOCK_VIRTUAL && (
+ (icount_opts && !qemu_opt_get_bool(icount_opts, "sleep", true)) ||
+ kvm_enabled()))) {
+ error_report("-qqq requires options -rtc clock=vm and either "
+ "icount -1,sleep=off or -enable-kvm");
+ exit(1);
+ }
+ setup_qqq(qqq_opts);
+ }
+
cpu_ticks_init();
if (icount_opts) {
if (kvm_enabled() || xen_enabled()) {
This patch adds an interface for pacing the execution of QEMU to match an external simulation clock. Its aim is to permit QEMU to be used as a module within a larger simulation system. v6 -> v7 Added a check for command line arguments that are consistent with -qqq and print an error message if incompatible arguments are provide. [Paolo] Signed-off-by: James J. Nutaro <nutarojj@ornl.gov> --- Makefile.target | 3 + cpus.c | 8 +++ docs/simulation-sync.txt | 59 ++++++++++++++++ include/sysemu/cpus.h | 1 + kvm-all.c | 10 +++ qemu-options.hx | 16 +++++ qqq.c | 177 +++++++++++++++++++++++++++++++++++++++++++++++ qqq.h | 37 ++++++++++ vl.c | 36 ++++++++++ 9 files changed, 347 insertions(+) create mode 100644 docs/simulation-sync.txt create mode 100644 qqq.c create mode 100644 qqq.h