X-Git-Url: https://git.proxmox.com/?a=blobdiff_plain;f=qemu-timer.c;h=30e8f1272e8c6ab4fca20931c38a979d52417133;hb=68e3508eafd111c050e0a6f4dc8588dbe75d0e1c;hp=50f1943afddafeb29c39259ab631c2dd5260ab71;hpb=56d7a964a5664d3778a0b7a369a5f350d0fe099f;p=qemu.git diff --git a/qemu-timer.c b/qemu-timer.c index 50f1943af..30e8f1272 100644 --- a/qemu-timer.c +++ b/qemu-timer.c @@ -39,15 +39,6 @@ #include #endif -#ifdef __linux__ -#include -#include -/* For the benefit of older linux systems which don't supply it, - we use a local copy of hpet.h. */ -/* #include */ -#include "hpet.h" -#endif - #ifdef _WIN32 #include #include @@ -110,9 +101,12 @@ static int64_t cpu_get_clock(void) } } +#ifndef CONFIG_IOTHREAD static int64_t qemu_icount_delta(void) { - if (use_icount == 1) { + if (!use_icount) { + return 5000 * (int64_t) 1000000; + } else if (use_icount == 1) { /* When not using an adaptive execution frequency we tend to get badly out of sync with real time, so just delay for a reasonable amount of time. */ @@ -121,6 +115,7 @@ static int64_t qemu_icount_delta(void) return cpu_get_icount() - cpu_get_clock(); } } +#endif /* enable cpu_get_ticks() */ void cpu_enable_ticks(void) @@ -153,6 +148,11 @@ void cpu_disable_ticks(void) struct QEMUClock { int type; int enabled; + + QEMUTimer *warp_timer; + + NotifierList reset_notifiers; + int64_t last; }; struct QEMUTimer { @@ -169,14 +169,23 @@ struct qemu_alarm_timer { int (*start)(struct qemu_alarm_timer *t); void (*stop)(struct qemu_alarm_timer *t); void (*rearm)(struct qemu_alarm_timer *t); - void *priv; - +#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; @@ -200,6 +209,10 @@ static void qemu_rearm_alarm_timer(struct qemu_alarm_timer *t) #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); + 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); @@ -208,6 +221,7 @@ static void win32_rearm_timer(struct qemu_alarm_timer *t); 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); #ifdef __linux__ @@ -215,12 +229,6 @@ 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); -static int hpet_start_timer(struct qemu_alarm_timer *t); -static void hpet_stop_timer(struct qemu_alarm_timer *t); - -static int rtc_start_timer(struct qemu_alarm_timer *t); -static void rtc_stop_timer(struct qemu_alarm_timer *t); - #endif /* __linux__ */ #endif /* _WIN32 */ @@ -284,18 +292,14 @@ static struct qemu_alarm_timer alarm_timers[] = { #ifndef _WIN32 #ifdef __linux__ {"dynticks", dynticks_start_timer, - dynticks_stop_timer, dynticks_rearm_timer, NULL}, - /* HPET - if available - is preferred */ - {"hpet", hpet_start_timer, hpet_stop_timer, NULL, NULL}, - /* ...otherwise try RTC */ - {"rtc", rtc_start_timer, rtc_stop_timer, NULL, NULL}, + dynticks_stop_timer, dynticks_rearm_timer}, #endif - {"unix", unix_start_timer, unix_stop_timer, NULL, NULL}, + {"unix", unix_start_timer, unix_stop_timer, unix_rearm_timer}, #else - {"dynticks", win32_start_timer, - win32_stop_timer, win32_rearm_timer, NULL}, - {"win32", win32_start_timer, - win32_stop_timer, NULL, NULL}, + {"mmtimer", mm_start_timer, mm_stop_timer, NULL}, + {"mmtimer2", mm_start_timer, mm_stop_timer, mm_rearm_timer}, + {"dynticks", win32_start_timer, win32_stop_timer, win32_rearm_timer}, + {"win32", win32_start_timer, win32_stop_timer, NULL}, #endif {NULL, } }; @@ -375,9 +379,15 @@ static QEMUTimer *active_timers[QEMU_NUM_CLOCKS]; static QEMUClock *qemu_new_clock(int type) { QEMUClock *clock; + clock = qemu_mallocz(sizeof(QEMUClock)); clock->type = type; clock->enabled = 1; + notifier_list_init(&clock->reset_notifiers); + /* required to detect & report backward jumps */ + if (type == QEMU_CLOCK_HOST) { + clock->last = get_clock_realtime(); + } return clock; } @@ -386,6 +396,90 @@ void qemu_clock_enable(QEMUClock *clock, int enabled) clock->enabled = enabled; } +static int64_t vm_clock_warp_start; + +static void icount_warp_rt(void *opaque) +{ + if (vm_clock_warp_start == -1) { + return; + } + + if (vm_running) { + int64_t clock = qemu_get_clock_ns(rt_clock); + int64_t warp_delta = clock - vm_clock_warp_start; + if (use_icount == 1) { + qemu_icount_bias += warp_delta; + } else { + /* + * In adaptive mode, do not let the vm_clock run too + * far ahead of real time. + */ + int64_t cur_time = cpu_get_clock(); + int64_t cur_icount = qemu_get_clock_ns(vm_clock); + int64_t delta = cur_time - cur_icount; + qemu_icount_bias += MIN(warp_delta, delta); + } + if (qemu_timer_expired(active_timers[QEMU_CLOCK_VIRTUAL], + qemu_get_clock_ns(vm_clock))) { + qemu_notify_event(); + } + } + vm_clock_warp_start = -1; +} + +void qemu_clock_warp(QEMUClock *clock) +{ + int64_t deadline; + + if (!clock->warp_timer) { + return; + } + + /* + * There are too many global variables to make the "warp" behavior + * applicable to other clocks. But a clock argument removes the + * need for if statements all over the place. + */ + assert(clock == vm_clock); + + /* + * If the CPUs have been sleeping, advance the vm_clock timer now. This + * ensures that the deadline for the timer is computed correctly below. + * This also makes sure that the insn counter is synchronized before the + * CPU starts running, in case the CPU is woken by an event other than + * the earliest vm_clock timer. + */ + icount_warp_rt(NULL); + if (!all_cpu_threads_idle() || !active_timers[clock->type]) { + qemu_del_timer(clock->warp_timer); + return; + } + + vm_clock_warp_start = qemu_get_clock_ns(rt_clock); + deadline = qemu_next_icount_deadline(); + if (deadline > 0) { + /* + * Ensure the vm_clock proceeds even when the virtual CPU goes to + * sleep. Otherwise, the CPU might be waiting for a future timer + * interrupt to wake it up, but the interrupt never comes because + * the vCPU isn't running any insns and thus doesn't advance the + * vm_clock. + * + * An extreme solution for this problem would be to never let VCPUs + * sleep in icount mode if there is a pending vm_clock timer; rather + * time could just advance to the next vm_clock event. Instead, we + * do stop VCPUs and only advance vm_clock after some "real" time, + * (related to the time left until the next event) has passed. This + * rt_clock timer will do this. This avoids that the warps are too + * visible externally---for example, you will not be sending network + * packets continously instead of every 100ms. + */ + qemu_mod_timer(clock->warp_timer, vm_clock_warp_start + deadline); + } else { + qemu_notify_event(); + } +} + QEMUTimer *qemu_new_timer(QEMUClock *clock, int scale, QEMUTimerCB *cb, void *opaque) { @@ -438,10 +532,9 @@ static void qemu_mod_timer_ns(QEMUTimer *ts, int64_t expire_time) pt = &active_timers[ts->clock->type]; for(;;) { t = *pt; - if (!t) - break; - if (t->expire_time > expire_time) + if (!qemu_timer_expired_ns(t, expire_time)) { break; + } pt = &t->next; } ts->expire_time = expire_time; @@ -454,8 +547,10 @@ static void qemu_mod_timer_ns(QEMUTimer *ts, int64_t expire_time) qemu_rearm_alarm_timer(alarm_timer); } /* Interrupt execution to force deadline recalculation. */ - if (use_icount) + qemu_clock_warp(ts->clock); + if (use_icount) { qemu_notify_event(); + } } } @@ -478,9 +573,7 @@ int qemu_timer_pending(QEMUTimer *ts) int qemu_timer_expired(QEMUTimer *timer_head, int64_t current_time) { - if (!timer_head) - return 0; - return (timer_head->expire_time <= current_time * timer_head->scale); + return qemu_timer_expired_ns(timer_head, current_time * timer_head->scale); } static void qemu_run_timers(QEMUClock *clock) @@ -495,8 +588,9 @@ static void qemu_run_timers(QEMUClock *clock) ptimer_head = &active_timers[clock->type]; for(;;) { ts = *ptimer_head; - if (!ts || ts->expire_time > current_time) + 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; @@ -508,6 +602,8 @@ static void qemu_run_timers(QEMUClock *clock) int64_t qemu_get_clock_ns(QEMUClock *clock) { + int64_t now, last; + switch(clock->type) { case QEMU_CLOCK_REALTIME: return get_clock(); @@ -519,10 +615,26 @@ int64_t qemu_get_clock_ns(QEMUClock *clock) return cpu_get_clock(); } case QEMU_CLOCK_HOST: - return get_clock_realtime(); + 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_list_remove(&clock->reset_notifiers, notifier); +} + void init_clocks(void) { rt_clock = qemu_new_clock(QEMU_CLOCK_REALTIME); @@ -576,6 +688,10 @@ void configure_icount(const char *option) if (!option) return; +#ifdef CONFIG_IOTHREAD + vm_clock->warp_timer = qemu_new_timer_ns(rt_clock, icount_warp_rt, NULL); +#endif + if (strcmp(option, "auto") != 0) { icount_time_shift = strtol(option, NULL, 0); use_icount = 1; @@ -669,21 +785,16 @@ static void host_alarm_handler(int host_signum) } } -int64_t qemu_next_deadline(void) +int64_t qemu_next_icount_deadline(void) { /* To avoid problems with overflow limit this to 2^32. */ int64_t delta = INT32_MAX; + assert(use_icount); if (active_timers[QEMU_CLOCK_VIRTUAL]) { delta = active_timers[QEMU_CLOCK_VIRTUAL]->expire_time - qemu_get_clock_ns(vm_clock); } - if (active_timers[QEMU_CLOCK_HOST]) { - int64_t hdelta = active_timers[QEMU_CLOCK_HOST]->expire_time - - qemu_get_clock_ns(host_clock); - if (hdelta < delta) - delta = hdelta; - } if (delta < 0) delta = 0; @@ -720,106 +831,7 @@ static int64_t qemu_next_alarm_deadline(void) #if defined(__linux__) -#define RTC_FREQ 1024 - -static void enable_sigio_timer(int fd) -{ - struct sigaction act; - - /* timer signal */ - sigfillset(&act.sa_mask); - act.sa_flags = 0; - act.sa_handler = host_alarm_handler; - - sigaction(SIGIO, &act, NULL); - fcntl_setfl(fd, O_ASYNC); - fcntl(fd, F_SETOWN, getpid()); -} - -static int hpet_start_timer(struct qemu_alarm_timer *t) -{ - struct hpet_info info; - int r, fd; - - fd = qemu_open("/dev/hpet", O_RDONLY); - if (fd < 0) - return -1; - - /* Set frequency */ - r = ioctl(fd, HPET_IRQFREQ, RTC_FREQ); - if (r < 0) { - fprintf(stderr, "Could not configure '/dev/hpet' to have a 1024Hz timer. This is not a fatal\n" - "error, but for better emulation accuracy type:\n" - "'echo 1024 > /proc/sys/dev/hpet/max-user-freq' as root.\n"); - goto fail; - } - - /* Check capabilities */ - r = ioctl(fd, HPET_INFO, &info); - if (r < 0) - goto fail; - - /* Enable periodic mode */ - r = ioctl(fd, HPET_EPI, 0); - if (info.hi_flags && (r < 0)) - goto fail; - - /* Enable interrupt */ - r = ioctl(fd, HPET_IE_ON, 0); - if (r < 0) - goto fail; - - enable_sigio_timer(fd); - t->priv = (void *)(long)fd; - - return 0; -fail: - close(fd); - return -1; -} - -static void hpet_stop_timer(struct qemu_alarm_timer *t) -{ - int fd = (long)t->priv; - - close(fd); -} - -static int rtc_start_timer(struct qemu_alarm_timer *t) -{ - int rtc_fd; - unsigned long current_rtc_freq = 0; - - TFR(rtc_fd = qemu_open("/dev/rtc", O_RDONLY)); - if (rtc_fd < 0) - return -1; - ioctl(rtc_fd, RTC_IRQP_READ, ¤t_rtc_freq); - if (current_rtc_freq != RTC_FREQ && - ioctl(rtc_fd, RTC_IRQP_SET, RTC_FREQ) < 0) { - fprintf(stderr, "Could not configure '/dev/rtc' to have a 1024 Hz timer. This is not a fatal\n" - "error, but for better emulation accuracy either use a 2.6 host Linux kernel or\n" - "type 'echo 1024 > /proc/sys/dev/rtc/max-user-freq' as root.\n"); - goto fail; - } - if (ioctl(rtc_fd, RTC_PIE_ON, 0) < 0) { - fail: - close(rtc_fd); - return -1; - } - - enable_sigio_timer(rtc_fd); - - t->priv = (void *)(long)rtc_fd; - - return 0; -} - -static void rtc_stop_timer(struct qemu_alarm_timer *t) -{ - int rtc_fd = (long)t->priv; - - close(rtc_fd); -} +#include "compatfd.h" static int dynticks_start_timer(struct qemu_alarm_timer *t) { @@ -840,6 +852,12 @@ static int dynticks_start_timer(struct qemu_alarm_timer *t) 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)) { @@ -851,21 +869,21 @@ static int dynticks_start_timer(struct qemu_alarm_timer *t) return -1; } - t->priv = (void *)(long)host_timer; + t->timer = host_timer; return 0; } static void dynticks_stop_timer(struct qemu_alarm_timer *t) { - timer_t host_timer = (timer_t)(long)t->priv; + timer_t host_timer = t->timer; timer_delete(host_timer); } static void dynticks_rearm_timer(struct qemu_alarm_timer *t) { - timer_t host_timer = (timer_t)(long)t->priv; + timer_t host_timer = t->timer; struct itimerspec timeout; int64_t nearest_delta_ns = INT64_MAX; int64_t current_ns; @@ -908,8 +926,6 @@ static void dynticks_rearm_timer(struct qemu_alarm_timer *t) static int unix_start_timer(struct qemu_alarm_timer *t) { struct sigaction act; - struct itimerval itv; - int err; /* timer signal */ sigfillset(&act.sa_mask); @@ -917,18 +933,35 @@ static int unix_start_timer(struct qemu_alarm_timer *t) act.sa_handler = host_alarm_handler; sigaction(SIGALRM, &act, NULL); + return 0; +} - itv.it_interval.tv_sec = 0; - /* for i386 kernel 2.6 to get 1 ms */ - itv.it_interval.tv_usec = 999; - itv.it_value.tv_sec = 0; - itv.it_value.tv_usec = 10 * 1000; +static void unix_rearm_timer(struct qemu_alarm_timer *t) +{ + struct itimerval itv; + int64_t nearest_delta_ns = INT64_MAX; + int err; - err = setitimer(ITIMER_REAL, &itv, NULL); - if (err) - return -1; + assert(alarm_has_dynticks(t)); + if (!active_timers[QEMU_CLOCK_REALTIME] && + !active_timers[QEMU_CLOCK_VIRTUAL] && + !active_timers[QEMU_CLOCK_HOST]) + return; - return 0; + nearest_delta_ns = qemu_next_alarm_deadline(); + 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) @@ -944,6 +977,96 @@ static void unix_stop_timer(struct qemu_alarm_timer *t) #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) +{ + int nearest_delta_ms; + + assert(alarm_has_dynticks(t)); + if (!active_timers[QEMU_CLOCK_REALTIME] && + !active_timers[QEMU_CLOCK_VIRTUAL] && + !active_timers[QEMU_CLOCK_HOST]) { + return; + } + + timeKillEvent(mm_timer); + + nearest_delta_ms = (qemu_next_alarm_deadline() + 999999) / 1000000; + if (nearest_delta_ms < 1) { + nearest_delta_ms = 1; + } + 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; @@ -967,13 +1090,13 @@ static int win32_start_timer(struct qemu_alarm_timer *t) return -1; } - t->priv = (PVOID) hTimer; + t->timer = hTimer; return 0; } static void win32_stop_timer(struct qemu_alarm_timer *t) { - HANDLE hTimer = t->priv; + HANDLE hTimer = t->timer; if (hTimer) { DeleteTimerQueueTimer(NULL, hTimer, NULL); @@ -982,7 +1105,7 @@ static void win32_stop_timer(struct qemu_alarm_timer *t) static void win32_rearm_timer(struct qemu_alarm_timer *t) { - HANDLE hTimer = t->priv; + HANDLE hTimer = t->timer; int nearest_delta_ms; BOOLEAN success; @@ -1055,39 +1178,41 @@ void quit_timers(void) int qemu_calculate_timeout(void) { +#ifndef CONFIG_IOTHREAD int timeout; - int64_t add; - int64_t delta; - - /* When using icount, making forward progress with qemu_icount when the - guest CPU is idle is critical. We only use the static io-thread timeout - for non icount runs. */ - if (!use_icount || !vm_running) { - return 5000; - } - /* Advance virtual time to the next event. */ - delta = qemu_icount_delta(); - if (delta > 0) { - /* If virtual time is ahead of real time then just - wait for IO. */ - timeout = (delta + 999999) / 1000000; - } else { - /* Wait for either IO to occur or the next - timer event. */ - add = qemu_next_deadline(); - /* We advance the timer before checking for IO. - Limit the amount we advance so that early IO - activity won't get the guest too far ahead. */ - if (add > 10000000) - add = 10000000; - delta += add; - qemu_icount += qemu_icount_round (add); - timeout = delta / 1000000; - if (timeout < 0) - timeout = 0; + if (!vm_running) + timeout = 5000; + else { + /* XXX: use timeout computed from timers */ + int64_t add; + int64_t delta; + /* Advance virtual time to the next event. */ + delta = qemu_icount_delta(); + if (delta > 0) { + /* If virtual time is ahead of real time then just + wait for IO. */ + timeout = (delta + 999999) / 1000000; + } else { + /* Wait for either IO to occur or the next + timer event. */ + add = qemu_next_icount_deadline(); + /* We advance the timer before checking for IO. + Limit the amount we advance so that early IO + activity won't get the guest too far ahead. */ + if (add > 10000000) + add = 10000000; + delta += add; + qemu_icount += qemu_icount_round (add); + timeout = delta / 1000000; + if (timeout < 0) + timeout = 0; + } } return timeout; +#else /* CONFIG_IOTHREAD */ + return 1000; +#endif }