[Qemu-devel] [PATCH v2] Register Linux dyntick timer as per-thread signal

[Jan Kiszka]

Derived from kvm-tool patch
http://thread.gmane.org/gmane.comp.emulators.kvm.devel/74309

Ingo Molnar pointed out that sending the timer signal to the whole
process, just blocking it everywhere, is suboptimal with an increasing
number of threads. QEMU is also using this pattern so far.

Linux provides a (non-portable) way to restrict the signal to a single
thread: We can use SIGEV_THREAD_ID unless we are forced to emulate
signalfd via an additional thread. That case could theoretically be
optimized as well, but it doesn't look worth bothering.

Signed-off-by: Jan Kiszka <address@hidden>
---

Changes in v2:
 - refactored dynticks_start_timer changes as suggested by Richard
   Henderson
 - added reference to original kvm-tool patch

 compatfd.c   |   11 +++++++++++
 compatfd.h   |    1 +
 qemu-timer.c |    8 ++++++++
 3 files changed, 20 insertions(+), 0 deletions(-)

diff --git a/compatfd.c b/compatfd.c
index 41586ce..31654c6 100644
--- a/compatfd.c
+++ b/compatfd.c
@@ -115,3 +115,14 @@ int qemu_signalfd(const sigset_t *mask)
 
     return qemu_signalfd_compat(mask);
 }
+
+bool qemu_signalfd_available(void)
+{
+#ifdef CONFIG_SIGNALFD
+    errno = 0;
+    syscall(SYS_signalfd, -1, NULL, _NSIG / 8);
+    return errno != ENOSYS;
+#else
+    return false;
+#endif
+}
diff --git a/compatfd.h b/compatfd.h
index fc37915..6b04877 100644
--- a/compatfd.h
+++ b/compatfd.h
@@ -39,5 +39,6 @@ struct qemu_signalfd_siginfo {
 };
 
 int qemu_signalfd(const sigset_t *mask);
+bool qemu_signalfd_available(void);
 
 #endif
diff --git a/qemu-timer.c b/qemu-timer.c
index 72066c7..743cf96 100644
--- a/qemu-timer.c
+++ b/qemu-timer.c
@@ -803,6 +803,8 @@ static int64_t qemu_next_alarm_deadline(void)
 
 #if defined(__linux__)
 
+#include "compatfd.h"
+
 static int dynticks_start_timer(struct qemu_alarm_timer *t)
 {
     struct sigevent ev;
@@ -822,6 +824,12 @@ 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)) {
-- 
1.7.1