tcg: drop global lock during TCG code execution

This finally allows TCG to benefit from the iothread introduction: Drop
the global mutex while running pure TCG CPU code. Reacquire the lock
when entering MMIO or PIO emulation, or when leaving the TCG loop.

We have to revert a few optimization for the current TCG threading
model, namely kicking the TCG thread in qemu_mutex_lock_iothread and not
kicking it in qemu_cpu_kick. We also need to disable RAM block
reordering until we have a more efficient locking mechanism at hand.

Still, a Linux x86 UP guest and my Musicpal ARM model boot fine here.
These numbers demonstrate where we gain something:

20338 jan       20   0  331m  75m 6904 R   99  0.9   0:50.95 qemu-system-arm
20337 jan       20   0  331m  75m 6904 S   20  0.9   0:26.50 qemu-system-arm

The guest CPU was fully loaded, but the iothread could still run mostly
independent on a second core. Without the patch we don't get beyond

32206 jan       20   0  330m  73m 7036 R   82  0.9   1:06.00 qemu-system-arm
32204 jan       20   0  330m  73m 7036 S   21  0.9   0:17.03 qemu-system-arm

We don't benefit significantly, though, when the guest is not fully
loading a host CPU.

Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Message-Id: <1439220437-23957-10-git-send-email-fred.konrad@greensocs.com>
[FK: Rebase, fix qemu_devices_reset deadlock, rm address_space_* mutex]
Signed-off-by: KONRAD Frederic <fred.konrad@greensocs.com>
[EGC: fixed iothread lock for cpu-exec IRQ handling]
Signed-off-by: Emilio G. Cota <cota@braap.org>
[AJB: -smp single-threaded fix, clean commit msg, BQL fixes]
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Reviewed-by: Richard Henderson <rth@twiddle.net>
Reviewed-by: Pranith Kumar <bobby.prani@gmail.com>
[PM: target-arm changes]
Acked-by: Peter Maydell <peter.maydell@linaro.org>
This commit is contained in:
Jan Kiszka 2017-02-23 18:29:11 +00:00 committed by Alex Bennée
parent 791158d93b
commit 8d04fb55de
18 changed files with 166 additions and 49 deletions

28
cpus.c
View file

@ -1027,8 +1027,6 @@ static void qemu_kvm_init_cpu_signals(CPUState *cpu)
#endif /* _WIN32 */
static QemuMutex qemu_global_mutex;
static QemuCond qemu_io_proceeded_cond;
static unsigned iothread_requesting_mutex;
static QemuThread io_thread;
@ -1042,7 +1040,6 @@ void qemu_init_cpu_loop(void)
qemu_init_sigbus();
qemu_cond_init(&qemu_cpu_cond);
qemu_cond_init(&qemu_pause_cond);
qemu_cond_init(&qemu_io_proceeded_cond);
qemu_mutex_init(&qemu_global_mutex);
qemu_thread_get_self(&io_thread);
@ -1085,10 +1082,6 @@ static void qemu_tcg_wait_io_event(CPUState *cpu)
start_tcg_kick_timer();
while (iothread_requesting_mutex) {
qemu_cond_wait(&qemu_io_proceeded_cond, &qemu_global_mutex);
}
CPU_FOREACH(cpu) {
qemu_wait_io_event_common(cpu);
}
@ -1249,9 +1242,11 @@ static int tcg_cpu_exec(CPUState *cpu)
cpu->icount_decr.u16.low = decr;
cpu->icount_extra = count;
}
qemu_mutex_unlock_iothread();
cpu_exec_start(cpu);
ret = cpu_exec(cpu);
cpu_exec_end(cpu);
qemu_mutex_lock_iothread();
#ifdef CONFIG_PROFILER
tcg_time += profile_getclock() - ti;
#endif
@ -1479,27 +1474,14 @@ bool qemu_mutex_iothread_locked(void)
void qemu_mutex_lock_iothread(void)
{
atomic_inc(&iothread_requesting_mutex);
/* In the simple case there is no need to bump the VCPU thread out of
* TCG code execution.
*/
if (!tcg_enabled() || qemu_in_vcpu_thread() ||
!first_cpu || !first_cpu->created) {
qemu_mutex_lock(&qemu_global_mutex);
atomic_dec(&iothread_requesting_mutex);
} else {
if (qemu_mutex_trylock(&qemu_global_mutex)) {
qemu_cpu_kick_rr_cpu();
qemu_mutex_lock(&qemu_global_mutex);
}
atomic_dec(&iothread_requesting_mutex);
qemu_cond_broadcast(&qemu_io_proceeded_cond);
}
g_assert(!qemu_mutex_iothread_locked());
qemu_mutex_lock(&qemu_global_mutex);
iothread_locked = true;
}
void qemu_mutex_unlock_iothread(void)
{
g_assert(qemu_mutex_iothread_locked());
iothread_locked = false;
qemu_mutex_unlock(&qemu_global_mutex);
}