[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [Qemu-devel] [PATCH v8 06/25] tcg: add kick timer for single-threade
From: |
Pranith Kumar |
Subject: |
Re: [Qemu-devel] [PATCH v8 06/25] tcg: add kick timer for single-threaded vCPU emulation |
Date: |
Sun, 29 Jan 2017 16:00:56 -0500 |
User-agent: |
mu4e 0.9.17; emacs 25.1.1 |
Alex Bennée writes:
> Currently we rely on the side effect of the main loop grabbing the
> iothread_mutex to give any long running basic block chains a kick to
> ensure the next vCPU is scheduled. As this code is being re-factored and
> rationalised we now do it explicitly here.
>
> Signed-off-by: Alex Bennée <address@hidden>
> Reviewed-by: Richard Henderson <address@hidden>
> ---
> v2
> - re-base fixes
> - get_ticks_per_sec() -> NANOSECONDS_PER_SEC
> v3
> - add define for TCG_KICK_FREQ
> - fix checkpatch warning
> v4
> - wrap next calc in inline qemu_tcg_next_kick() instead of macro
> v5
> - move all kick code into own section
> - use global for timer
> - add helper functions to start/stop timer
> - stop timer when all cores paused
> v7
> - checkpatch > 80 char fix
> ---
> cpus.c | 61 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
> 1 file changed, 61 insertions(+)
>
> diff --git a/cpus.c b/cpus.c
> index 76b6e04332..a98925105c 100644
> --- a/cpus.c
> +++ b/cpus.c
> @@ -767,6 +767,53 @@ void configure_icount(QemuOpts *opts, Error **errp)
> }
>
> /***********************************************************/
> +/* TCG vCPU kick timer
> + *
> + * The kick timer is responsible for moving single threaded vCPU
> + * emulation on to the next vCPU. If more than one vCPU is running a
> + * timer event with force a cpu->exit so the next vCPU can get
> + * scheduled.
s/with/will/
> + *
> + * The timer is removed if all vCPUs are idle and restarted again once
> + * idleness is complete.
> + */
> +
> +static QEMUTimer *tcg_kick_vcpu_timer;
> +
> +static void qemu_cpu_kick_no_halt(void);
> +
> +#define TCG_KICK_PERIOD (NANOSECONDS_PER_SECOND / 10)
> +
> +static inline int64_t qemu_tcg_next_kick(void)
> +{
> + return qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) + TCG_KICK_PERIOD;
> +}
> +
> +static void kick_tcg_thread(void *opaque)
> +{
> + timer_mod(tcg_kick_vcpu_timer, qemu_tcg_next_kick());
> + qemu_cpu_kick_no_halt();
> +}
> +
> +static void start_tcg_kick_timer(void)
> +{
> + if (!tcg_kick_vcpu_timer && CPU_NEXT(first_cpu)) {
> + tcg_kick_vcpu_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL,
> + kick_tcg_thread, NULL);
> + timer_mod(tcg_kick_vcpu_timer, qemu_tcg_next_kick());
> + }
> +}
> +
> +static void stop_tcg_kick_timer(void)
> +{
> + if (tcg_kick_vcpu_timer) {
> + timer_del(tcg_kick_vcpu_timer);
> + tcg_kick_vcpu_timer = NULL;
> + }
> +}
> +
> +
> +/***********************************************************/
> void hw_error(const char *fmt, ...)
> {
> va_list ap;
> @@ -1020,9 +1067,12 @@ static void qemu_wait_io_event_common(CPUState *cpu)
> static void qemu_tcg_wait_io_event(CPUState *cpu)
> {
> while (all_cpu_threads_idle()) {
> + stop_tcg_kick_timer();
> qemu_cond_wait(cpu->halt_cond, &qemu_global_mutex);
> }
>
> + start_tcg_kick_timer();
> +
> while (iothread_requesting_mutex) {
> qemu_cond_wait(&qemu_io_proceeded_cond, &qemu_global_mutex);
> }
> @@ -1222,6 +1272,15 @@ static void deal_with_unplugged_cpus(void)
> }
> }
>
> +/* Single-threaded TCG
> + *
> + * In the single-threaded case each vCPU is simulated in turn. If
> + * there is more than a single vCPU we create a simple timer to kick
> + * the vCPU and ensure we don't get stuck in a tight loop in one vCPU.
> + * This is done explicitly rather than relying on side-effects
> + * elsewhere.
> + */
> +
> static void *qemu_tcg_cpu_thread_fn(void *arg)
> {
> CPUState *cpu = arg;
> @@ -1248,6 +1307,8 @@ static void *qemu_tcg_cpu_thread_fn(void *arg)
> }
> }
>
> + start_tcg_kick_timer();
> +
> /* process any pending work */
> atomic_mb_set(&exit_request, 1);
Reviewed-by: Pranith Kumar <address@hidden>
Thanks,
--
Pranith
- [Qemu-devel] [PATCH v8 11/25] tcg: enable thread-per-vCPU, (continued)
- [Qemu-devel] [PATCH v8 14/25] cputlb: tweak qemu_ram_addr_from_host_nofail reporting, Alex Bennée, 2017/01/27
- [Qemu-devel] [PATCH v8 20/25] target-arm/powerctl: defer cpu reset work to CPU context, Alex Bennée, 2017/01/27
- [Qemu-devel] [PATCH v8 12/25] tcg: handle EXCP_ATOMIC exception for system emulation, Alex Bennée, 2017/01/27
- [Qemu-devel] [PATCH v8 06/25] tcg: add kick timer for single-threaded vCPU emulation, Alex Bennée, 2017/01/27
- Re: [Qemu-devel] [PATCH v8 06/25] tcg: add kick timer for single-threaded vCPU emulation,
Pranith Kumar <=
- [Qemu-devel] [PATCH v8 09/25] tcg: remove global exit_request, Alex Bennée, 2017/01/27
- [Qemu-devel] [PATCH v8 16/25] cputlb and arm/sparc targets: convert mmuidx flushes from varg to bitmap, Alex Bennée, 2017/01/27
- [Qemu-devel] [PATCH v8 22/25] target-arm/cpu.h: make ARM_CP defined consistent, Alex Bennée, 2017/01/27
- [Qemu-devel] [PATCH v8 18/25] cputlb: atomically update tlb fields used by tlb_reset_dirty, Alex Bennée, 2017/01/27
- [Qemu-devel] [PATCH v8 23/25] target-arm: introduce ARM_CP_EXIT_PC, Alex Bennée, 2017/01/27
- [Qemu-devel] [PATCH v8 24/25] target-arm: ensure all cross vCPUs TLB flushes complete, Alex Bennée, 2017/01/27
- [Qemu-devel] [PATCH v8 25/25] tcg: enable MTTCG by default for ARM on x86 hosts, Alex Bennée, 2017/01/27