mirrors/qemu
0
0
Fork 0
mirror of https://github.com/qemu/qemu.git synced 2024-11-25 03:43:37 +08:00
Code Issues Packages Projects Releases Wiki Activity
8092d2f031
qemu/qemu-timer.c
Peter Portante 158fd3ce98 qemu-timer.c: Remove 250us timeouts 
Basically, the main wait loop calls qemu_run_all_timers() unconditionally. The
first thing this routine used to do is to see if a timer had been serviced,
and then reset the loop timeout to the next deadline.

However, the new deadlines had not been calculated at that point, as
qemu_run_timers() had not been called yet for each of the clocks. So
qemu_rearm_alarm_timer() would end up with a negative or zero deadline, and
default to setting a 250us timeout for the loop.

As qemu_run_timers() is called for each clock, the real deadlines would be put
in place, but because a loop timeout was already set, the loop timeout would
not be changed.

Once that 250us timeout fired, the real deadline would be used for the
subsequent timeout.

For idle VMs, this effectively doubles the number of times through the loop,
doubling the number of select() system calls, timer calls, etc. putting added
scheduling pressure on the kernel. And under cgroups, this really causes a big
problem because the cgroup code does not scale well.

By simply running the timers before trying to rearm the timer, we always rearm
with a non-zero deadline, effectively halving the number of system calls.

Signed-off-by: Peter Portante <pportant@redhat.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
2012-04-16 12:56:48 -05:00

823 lines
20 KiB
C
Raw Blame History

/*
* QEMU System Emulator
*
* Copyright (c) 2003-2008 Fabrice Bellard
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to deal
* in the Software without restriction, including without limitation the rights
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
* copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
* THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
* THE SOFTWARE.
*/
#include "sysemu.h"
#include "net.h"
#include "monitor.h"
#include "console.h"
#include "hw/hw.h"
#include <unistd.h>
#include <fcntl.h>
#include <time.h>
#include <errno.h>
#include <sys/time.h>
#include <signal.h>
#ifdef __FreeBSD__
#include <sys/param.h>
#endif
#ifdef _WIN32
#include <windows.h>
#include <mmsystem.h>
#endif
#include "qemu-timer.h"
/***********************************************************/
/* timers */
#define QEMU_CLOCK_REALTIME 0
#define QEMU_CLOCK_VIRTUAL 1
#define QEMU_CLOCK_HOST 2
struct QEMUClock {
int type;
int enabled;
QEMUTimer *active_timers;
NotifierList reset_notifiers;
int64_t last;
};
struct QEMUTimer {
QEMUClock *clock;
int64_t expire_time; /* in nanoseconds */
int scale;
QEMUTimerCB *cb;
void *opaque;
struct QEMUTimer *next;
};
struct qemu_alarm_timer {
char const *name;
int (*start)(struct qemu_alarm_timer *t);
void (*stop)(struct qemu_alarm_timer *t);
void (*rearm)(struct qemu_alarm_timer *t, int64_t nearest_delta_ns);
#if defined(__linux__)
int fd;
timer_t timer;
#elif defined(_WIN32)
HANDLE timer;
#endif
char expired;
char pending;
};
static struct qemu_alarm_timer *alarm_timer;
static bool qemu_timer_expired_ns(QEMUTimer *timer_head, int64_t current_time)
{
return timer_head && (timer_head->expire_time <= current_time);
}
int qemu_alarm_pending(void)
{
return alarm_timer->pending;
}
static inline int alarm_has_dynticks(struct qemu_alarm_timer *t)
{
return !!t->rearm;
}
static int64_t qemu_next_alarm_deadline(void)
{
int64_t delta;
int64_t rtdelta;
if (!use_icount && vm_clock->active_timers) {
delta = vm_clock->active_timers->expire_time -
qemu_get_clock_ns(vm_clock);
} else {
delta = INT32_MAX;
}
if (host_clock->active_timers) {
int64_t hdelta = host_clock->active_timers->expire_time -
qemu_get_clock_ns(host_clock);
if (hdelta < delta) {
delta = hdelta;
}
}
if (rt_clock->active_timers) {
rtdelta = (rt_clock->active_timers->expire_time -
qemu_get_clock_ns(rt_clock));
if (rtdelta < delta) {
delta = rtdelta;
}
}
return delta;
}
static void qemu_rearm_alarm_timer(struct qemu_alarm_timer *t)
{
int64_t nearest_delta_ns;
assert(alarm_has_dynticks(t));
if (!rt_clock->active_timers &&
!vm_clock->active_timers &&
!host_clock->active_timers) {
return;
}
nearest_delta_ns = qemu_next_alarm_deadline();
t->rearm(t, nearest_delta_ns);
}
/* TODO: MIN_TIMER_REARM_NS should be optimized */
#define MIN_TIMER_REARM_NS 250000
#ifdef _WIN32
static int mm_start_timer(struct qemu_alarm_timer *t);
static void mm_stop_timer(struct qemu_alarm_timer *t);
static void mm_rearm_timer(struct qemu_alarm_timer *t, int64_t delta);
static int win32_start_timer(struct qemu_alarm_timer *t);
static void win32_stop_timer(struct qemu_alarm_timer *t);
static void win32_rearm_timer(struct qemu_alarm_timer *t, int64_t delta);
#else
static int unix_start_timer(struct qemu_alarm_timer *t);
static void unix_stop_timer(struct qemu_alarm_timer *t);
static void unix_rearm_timer(struct qemu_alarm_timer *t, int64_t delta);
#ifdef __linux__
static int dynticks_start_timer(struct qemu_alarm_timer *t);
static void dynticks_stop_timer(struct qemu_alarm_timer *t);
static void dynticks_rearm_timer(struct qemu_alarm_timer *t, int64_t delta);
#endif /* __linux__ */
#endif /* _WIN32 */
static struct qemu_alarm_timer alarm_timers[] = {
#ifndef _WIN32
#ifdef __linux__
{"dynticks", dynticks_start_timer,
dynticks_stop_timer, dynticks_rearm_timer},
#endif
{"unix", unix_start_timer, unix_stop_timer, unix_rearm_timer},
#else
{"mmtimer", mm_start_timer, mm_stop_timer, mm_rearm_timer},
{"dynticks", win32_start_timer, win32_stop_timer, win32_rearm_timer},
#endif
{NULL, }
};
static void show_available_alarms(void)
{
int i;
printf("Available alarm timers, in order of precedence:\n");
for (i = 0; alarm_timers[i].name; i++)
printf("%s\n", alarm_timers[i].name);
}
void configure_alarms(char const *opt)
{
int i;
int cur = 0;
int count = ARRAY_SIZE(alarm_timers) - 1;
char *arg;
char *name;
struct qemu_alarm_timer tmp;
if (!strcmp(opt, "?")) {
show_available_alarms();
exit(0);
}
arg = g_strdup(opt);
/* Reorder the array */
name = strtok(arg, ",");
while (name) {
for (i = 0; i < count && alarm_timers[i].name; i++) {
if (!strcmp(alarm_timers[i].name, name))
break;
}
if (i == count) {
fprintf(stderr, "Unknown clock %s\n", name);
goto next;
}
if (i < cur)
/* Ignore */
goto next;
/* Swap */
tmp = alarm_timers[i];
alarm_timers[i] = alarm_timers[cur];
alarm_timers[cur] = tmp;
cur++;
next:
name = strtok(NULL, ",");
}
g_free(arg);
if (cur) {
/* Disable remaining timers */
for (i = cur; i < count; i++)
alarm_timers[i].name = NULL;
} else {
show_available_alarms();
exit(1);
}
}
QEMUClock *rt_clock;
QEMUClock *vm_clock;
QEMUClock *host_clock;
static QEMUClock *qemu_new_clock(int type)
{
QEMUClock *clock;
clock = g_malloc0(sizeof(QEMUClock));
clock->type = type;
clock->enabled = 1;
clock->last = INT64_MIN;
notifier_list_init(&clock->reset_notifiers);
return clock;
}
void qemu_clock_enable(QEMUClock *clock, int enabled)
{
bool old = clock->enabled;
clock->enabled = enabled;
if (enabled && !old) {
qemu_rearm_alarm_timer(alarm_timer);
}
}
int64_t qemu_clock_has_timers(QEMUClock *clock)
{
return !!clock->active_timers;
}
int64_t qemu_clock_expired(QEMUClock *clock)
{
return (clock->active_timers &&
clock->active_timers->expire_time < qemu_get_clock_ns(clock));
}
int64_t qemu_clock_deadline(QEMUClock *clock)
{
/* To avoid problems with overflow limit this to 2^32. */
int64_t delta = INT32_MAX;
if (clock->active_timers) {
delta = clock->active_timers->expire_time - qemu_get_clock_ns(clock);
}
if (delta < 0) {
delta = 0;
}
return delta;
}
QEMUTimer *qemu_new_timer(QEMUClock *clock, int scale,
QEMUTimerCB *cb, void *opaque)
{
QEMUTimer *ts;
ts = g_malloc0(sizeof(QEMUTimer));
ts->clock = clock;
ts->cb = cb;
ts->opaque = opaque;
ts->scale = scale;
return ts;
}
void qemu_free_timer(QEMUTimer *ts)
{
g_free(ts);
}
/* stop a timer, but do not dealloc it */
void qemu_del_timer(QEMUTimer *ts)
{
QEMUTimer **pt, *t;
/* NOTE: this code must be signal safe because
qemu_timer_expired() can be called from a signal. */
pt = &ts->clock->active_timers;
for(;;) {
t = *pt;
if (!t)
break;
if (t == ts) {
*pt = t->next;
break;
}
pt = &t->next;
}
}
/* modify the current timer so that it will be fired when current_time
>= expire_time. The corresponding callback will be called. */
void qemu_mod_timer_ns(QEMUTimer *ts, int64_t expire_time)
{
QEMUTimer **pt, *t;
qemu_del_timer(ts);
/* add the timer in the sorted list */
/* NOTE: this code must be signal safe because
qemu_timer_expired() can be called from a signal. */
pt = &ts->clock->active_timers;
for(;;) {
t = *pt;
if (!qemu_timer_expired_ns(t, expire_time)) {
break;
}
pt = &t->next;
}
ts->expire_time = expire_time;
ts->next = *pt;
*pt = ts;
/* Rearm if necessary */
if (pt == &ts->clock->active_timers) {
if (!alarm_timer->pending) {
qemu_rearm_alarm_timer(alarm_timer);
}
/* Interrupt execution to force deadline recalculation. */
qemu_clock_warp(ts->clock);
if (use_icount) {
qemu_notify_event();
}
}
}
void qemu_mod_timer(QEMUTimer *ts, int64_t expire_time)
{
qemu_mod_timer_ns(ts, expire_time * ts->scale);
}
int qemu_timer_pending(QEMUTimer *ts)
{
QEMUTimer *t;
for (t = ts->clock->active_timers; t != NULL; t = t->next) {
if (t == ts)
return 1;
}
return 0;
}
int qemu_timer_expired(QEMUTimer *timer_head, int64_t current_time)
{
return qemu_timer_expired_ns(timer_head, current_time * timer_head->scale);
}
void qemu_run_timers(QEMUClock *clock)
{
QEMUTimer **ptimer_head, *ts;
int64_t current_time;
if (!clock->enabled)
return;
current_time = qemu_get_clock_ns(clock);
ptimer_head = &clock->active_timers;
for(;;) {
ts = *ptimer_head;
if (!qemu_timer_expired_ns(ts, current_time)) {
break;
}
/* remove timer from the list before calling the callback */
*ptimer_head = ts->next;
ts->next = NULL;
/* run the callback (the timer list can be modified) */
ts->cb(ts->opaque);
}
}
int64_t qemu_get_clock_ns(QEMUClock *clock)
{
int64_t now, last;
switch(clock->type) {
case QEMU_CLOCK_REALTIME:
return get_clock();
default:
case QEMU_CLOCK_VIRTUAL:
if (use_icount) {
return cpu_get_icount();
} else {
return cpu_get_clock();
}
case QEMU_CLOCK_HOST:
now = get_clock_realtime();
last = clock->last;
clock->last = now;
if (now < last) {
notifier_list_notify(&clock->reset_notifiers, &now);
}
return now;
}
}
void qemu_register_clock_reset_notifier(QEMUClock *clock, Notifier *notifier)
{
notifier_list_add(&clock->reset_notifiers, notifier);
}
void qemu_unregister_clock_reset_notifier(QEMUClock *clock, Notifier *notifier)
{
notifier_remove(notifier);
}
void init_clocks(void)
{
rt_clock = qemu_new_clock(QEMU_CLOCK_REALTIME);
vm_clock = qemu_new_clock(QEMU_CLOCK_VIRTUAL);
host_clock = qemu_new_clock(QEMU_CLOCK_HOST);
}
uint64_t qemu_timer_expire_time_ns(QEMUTimer *ts)
{
return qemu_timer_pending(ts) ? ts->expire_time : -1;
}
void qemu_run_all_timers(void)
{
alarm_timer->pending = 0;
/* vm time timers */
qemu_run_timers(vm_clock);
qemu_run_timers(rt_clock);
qemu_run_timers(host_clock);
/* rearm timer, if not periodic */
if (alarm_timer->expired) {
alarm_timer->expired = 0;
qemu_rearm_alarm_timer(alarm_timer);
}
}
#ifdef _WIN32
static void CALLBACK host_alarm_handler(PVOID lpParam, BOOLEAN unused)
#else
static void host_alarm_handler(int host_signum)
#endif
{
struct qemu_alarm_timer *t = alarm_timer;
if (!t)
return;
if (alarm_has_dynticks(t) ||
qemu_next_alarm_deadline () <= 0) {
t->expired = alarm_has_dynticks(t);
t->pending = 1;
qemu_notify_event();
}
}
#if defined(__linux__)
#include "compatfd.h"
static int dynticks_start_timer(struct qemu_alarm_timer *t)
{
struct sigevent ev;
timer_t host_timer;
struct sigaction act;
sigfillset(&act.sa_mask);
act.sa_flags = 0;
act.sa_handler = host_alarm_handler;
sigaction(SIGALRM, &act, NULL);
/*
* Initialize ev struct to 0 to avoid valgrind complaining
* about uninitialized data in timer_create call
*/
memset(&ev, 0, sizeof(ev));
ev.sigev_value.sival_int = 0;
ev.sigev_notify = SIGEV_SIGNAL;
#ifdef SIGEV_THREAD_ID
if (qemu_signalfd_available()) {
ev.sigev_notify = SIGEV_THREAD_ID;
ev._sigev_un._tid = qemu_get_thread_id();
}
#endif /* SIGEV_THREAD_ID */
ev.sigev_signo = SIGALRM;
if (timer_create(CLOCK_REALTIME, &ev, &host_timer)) {
perror("timer_create");
/* disable dynticks */
fprintf(stderr, "Dynamic Ticks disabled\n");
return -1;
}
t->timer = host_timer;
return 0;
}
static void dynticks_stop_timer(struct qemu_alarm_timer *t)
{
timer_t host_timer = t->timer;
timer_delete(host_timer);
}
static void dynticks_rearm_timer(struct qemu_alarm_timer *t,
int64_t nearest_delta_ns)
{
timer_t host_timer = t->timer;
struct itimerspec timeout;
int64_t current_ns;
if (nearest_delta_ns < MIN_TIMER_REARM_NS)
nearest_delta_ns = MIN_TIMER_REARM_NS;
/* check whether a timer is already running */
if (timer_gettime(host_timer, &timeout)) {
perror("gettime");
fprintf(stderr, "Internal timer error: aborting\n");
exit(1);
}
current_ns = timeout.it_value.tv_sec * 1000000000LL + timeout.it_value.tv_nsec;
if (current_ns && current_ns <= nearest_delta_ns)
return;
timeout.it_interval.tv_sec = 0;
timeout.it_interval.tv_nsec = 0; /* 0 for one-shot timer */
timeout.it_value.tv_sec = nearest_delta_ns / 1000000000;
timeout.it_value.tv_nsec = nearest_delta_ns % 1000000000;
if (timer_settime(host_timer, 0 /* RELATIVE */, &timeout, NULL)) {
perror("settime");
fprintf(stderr, "Internal timer error: aborting\n");
exit(1);
}
}
#endif /* defined(__linux__) */
#if !defined(_WIN32)
static int unix_start_timer(struct qemu_alarm_timer *t)
{
struct sigaction act;
/* timer signal */
sigfillset(&act.sa_mask);
act.sa_flags = 0;
act.sa_handler = host_alarm_handler;
sigaction(SIGALRM, &act, NULL);
return 0;
}
static void unix_rearm_timer(struct qemu_alarm_timer *t,
int64_t nearest_delta_ns)
{
struct itimerval itv;
int err;
if (nearest_delta_ns < MIN_TIMER_REARM_NS)
nearest_delta_ns = MIN_TIMER_REARM_NS;
itv.it_interval.tv_sec = 0;
itv.it_interval.tv_usec = 0; /* 0 for one-shot timer */
itv.it_value.tv_sec = nearest_delta_ns / 1000000000;
itv.it_value.tv_usec = (nearest_delta_ns % 1000000000) / 1000;
err = setitimer(ITIMER_REAL, &itv, NULL);
if (err) {
perror("setitimer");
fprintf(stderr, "Internal timer error: aborting\n");
exit(1);
}
}
static void unix_stop_timer(struct qemu_alarm_timer *t)
{
struct itimerval itv;
memset(&itv, 0, sizeof(itv));
setitimer(ITIMER_REAL, &itv, NULL);
}
#endif /* !defined(_WIN32) */
#ifdef _WIN32
static MMRESULT mm_timer;
static unsigned mm_period;
static void CALLBACK mm_alarm_handler(UINT uTimerID, UINT uMsg,
DWORD_PTR dwUser, DWORD_PTR dw1,
DWORD_PTR dw2)
{
struct qemu_alarm_timer *t = alarm_timer;
if (!t) {
return;
}
if (alarm_has_dynticks(t) || qemu_next_alarm_deadline() <= 0) {
t->expired = alarm_has_dynticks(t);
t->pending = 1;
qemu_notify_event();
}
}
static int mm_start_timer(struct qemu_alarm_timer *t)
{
TIMECAPS tc;
UINT flags;
memset(&tc, 0, sizeof(tc));
timeGetDevCaps(&tc, sizeof(tc));
mm_period = tc.wPeriodMin;
timeBeginPeriod(mm_period);
flags = TIME_CALLBACK_FUNCTION;
if (alarm_has_dynticks(t)) {
flags |= TIME_ONESHOT;
} else {
flags |= TIME_PERIODIC;
}
mm_timer = timeSetEvent(1, /* interval (ms) */
mm_period, /* resolution */
mm_alarm_handler, /* function */
(DWORD_PTR)t, /* parameter */
flags);
if (!mm_timer) {
fprintf(stderr, "Failed to initialize win32 alarm timer: %ld\n",
GetLastError());
timeEndPeriod(mm_period);
return -1;
}
return 0;
}
static void mm_stop_timer(struct qemu_alarm_timer *t)
{
timeKillEvent(mm_timer);
timeEndPeriod(mm_period);
}
static void mm_rearm_timer(struct qemu_alarm_timer *t, int64_t delta)
{
int nearest_delta_ms = (delta + 999999) / 1000000;
if (nearest_delta_ms < 1) {
nearest_delta_ms = 1;
}
timeKillEvent(mm_timer);
mm_timer = timeSetEvent(nearest_delta_ms,
mm_period,
mm_alarm_handler,
(DWORD_PTR)t,
TIME_ONESHOT | TIME_CALLBACK_FUNCTION);
if (!mm_timer) {
fprintf(stderr, "Failed to re-arm win32 alarm timer %ld\n",
GetLastError());
timeEndPeriod(mm_period);
exit(1);
}
}
static int win32_start_timer(struct qemu_alarm_timer *t)
{
HANDLE hTimer;
BOOLEAN success;
/* If you call ChangeTimerQueueTimer on a one-shot timer (its period
is zero) that has already expired, the timer is not updated. Since
creating a new timer is relatively expensive, set a bogus one-hour
interval in the dynticks case. */
success = CreateTimerQueueTimer(&hTimer,
NULL,
host_alarm_handler,
t,
1,
alarm_has_dynticks(t) ? 3600000 : 1,
WT_EXECUTEINTIMERTHREAD);
if (!success) {
fprintf(stderr, "Failed to initialize win32 alarm timer: %ld\n",
GetLastError());
return -1;
}
t->timer = hTimer;
return 0;
}
static void win32_stop_timer(struct qemu_alarm_timer *t)
{
HANDLE hTimer = t->timer;
if (hTimer) {
DeleteTimerQueueTimer(NULL, hTimer, NULL);
}
}
static void win32_rearm_timer(struct qemu_alarm_timer *t,
int64_t nearest_delta_ns)
{
HANDLE hTimer = t->timer;
int nearest_delta_ms;
BOOLEAN success;
nearest_delta_ms = (nearest_delta_ns + 999999) / 1000000;
if (nearest_delta_ms < 1) {
nearest_delta_ms = 1;
}
success = ChangeTimerQueueTimer(NULL,
hTimer,
nearest_delta_ms,
3600000);
if (!success) {
fprintf(stderr, "Failed to rearm win32 alarm timer: %ld\n",
GetLastError());
exit(-1);
}
}
#endif /* _WIN32 */
static void quit_timers(void)
{
struct qemu_alarm_timer *t = alarm_timer;
alarm_timer = NULL;
t->stop(t);
}
int init_timer_alarm(void)
{
struct qemu_alarm_timer *t = NULL;
int i, err = -1;
for (i = 0; alarm_timers[i].name; i++) {
t = &alarm_timers[i];
err = t->start(t);
if (!err)
break;
}
if (err) {
err = -ENOENT;
goto fail;
}
/* first event is at time 0 */
atexit(quit_timers);
t->pending = 1;
alarm_timer = t;
return 0;
fail:
return err;
}
int qemu_calculate_timeout(void)
{
return 1000;
}
Reference in New Issue View Git Blame Copy Permalink