From: Akihiko Odaki <akihiko.odaki@daynix.com>
To: Paolo Bonzini <pbonzini@redhat.com>, Stefan Weil <sw@weilnetz.de>,
Peter Xu <peterx@redhat.com>, Fabiano Rosas <farosas@suse.de>,
Hailiang Zhang <zhanghailiang@xfusion.com>
Cc: "Phil Dennis-Jordan" <phil@philjordan.eu>,
qemu-devel@nongnu.org, devel@daynix.com,
"Marc-André Lureau" <marcandre.lureau@redhat.com>,
"Daniel P. Berrangé" <berrange@redhat.com>,
"Philippe Mathieu-Daudé" <philmd@linaro.org>,
"Akihiko Odaki" <akihiko.odaki@daynix.com>
Subject: [PATCH v3 04/10] qemu-thread: Avoid futex abstraction for non-Linux
Date: Sun, 11 May 2025 15:08:21 +0900 [thread overview]
Message-ID: <20250511-event-v3-4-f7f69247d303@daynix.com> (raw)
In-Reply-To: <20250511-event-v3-0-f7f69247d303@daynix.com>
qemu-thread used to abstract pthread primitives into futex for the
QemuEvent implementation of POSIX systems other than Linux. However,
this abstraction has one key difference: unlike futex, pthread
primitives require an explicit destruction, and it must be ordered after
wait and wake operations.
It would be easier to perform destruction if a wait operation ensures
the corresponding wake operation finishes as POSIX semaphore does, but
that requires to protect state accesses in qemu_event_set() and
qemu_event_wait() with a mutex. On the other hand, real futex does not
need such a protection but needs complex barrier and atomic operations
to ensure ordering between the two functions.
Add special implementations of qemu_event_set() and qemu_event_wait()
using pthread primitives. qemu_event_wait() will ensure qemu_event_set()
finishes, and these functions will avoid complex barrier and atomic
operations to ensure ordering between them.
Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
Tested-by: Phil Dennis-Jordan <phil@philjordan.eu>
Reviewed-by: Phil Dennis-Jordan <phil@philjordan.eu>
---
util/qemu-thread-posix.c | 47 +++++++++++++++++++++--------------------------
1 file changed, 21 insertions(+), 26 deletions(-)
diff --git a/util/qemu-thread-posix.c b/util/qemu-thread-posix.c
index dfe26b8d020c..6dc6f2b25dce 100644
--- a/util/qemu-thread-posix.c
+++ b/util/qemu-thread-posix.c
@@ -319,28 +319,6 @@ void qemu_sem_wait(QemuSemaphore *sem)
#ifdef CONFIG_LINUX
#include "qemu/futex.h"
-#else
-static inline void qemu_futex_wake(QemuEvent *ev, int n)
-{
- assert(ev->initialized);
- pthread_mutex_lock(&ev->lock);
- if (n == 1) {
- pthread_cond_signal(&ev->cond);
- } else {
- pthread_cond_broadcast(&ev->cond);
- }
- pthread_mutex_unlock(&ev->lock);
-}
-
-static inline void qemu_futex_wait(QemuEvent *ev, unsigned val)
-{
- assert(ev->initialized);
- pthread_mutex_lock(&ev->lock);
- if (ev->value == val) {
- pthread_cond_wait(&ev->cond, &ev->lock);
- }
- pthread_mutex_unlock(&ev->lock);
-}
#endif
/* Valid transitions:
@@ -387,12 +365,17 @@ void qemu_event_set(QemuEvent *ev)
assert(ev->initialized);
/*
- * Pairs with both qemu_event_reset() and qemu_event_wait().
+ * Pairs with qemu_event_wait() (on Linux) and qemu_event_reset().
*
* qemu_event_set has release semantics, but because it *loads*
* ev->value we need a full memory barrier here.
+ *
+ * qemu_event_wait() do not have a paired barrier on non-Linux because
+ * ev->lock ensures ordering.
*/
smp_mb();
+
+#ifdef CONFIG_LINUX
if (qatomic_read(&ev->value) != EV_SET) {
int old = qatomic_xchg(&ev->value, EV_SET);
@@ -403,6 +386,12 @@ void qemu_event_set(QemuEvent *ev)
qemu_futex_wake_all(ev);
}
}
+#else
+ pthread_mutex_lock(&ev->lock);
+ qatomic_set(&ev->value, EV_SET);
+ pthread_cond_broadcast(&ev->cond);
+ pthread_mutex_unlock(&ev->lock);
+#endif
}
void qemu_event_reset(QemuEvent *ev)
@@ -424,10 +413,9 @@ void qemu_event_reset(QemuEvent *ev)
void qemu_event_wait(QemuEvent *ev)
{
- unsigned value;
-
assert(ev->initialized);
+#ifdef CONFIG_LINUX
while (true) {
/*
* qemu_event_wait must synchronize with qemu_event_set even if it does
@@ -438,7 +426,7 @@ void qemu_event_wait(QemuEvent *ev)
* might miss a qemu_event_set() here but ultimately the memory barrier
* in qemu_futex_wait() will ensure the check is done correctly.
*/
- value = qatomic_load_acquire(&ev->value);
+ unsigned value = qatomic_load_acquire(&ev->value);
if (value == EV_SET) {
break;
}
@@ -467,6 +455,13 @@ void qemu_event_wait(QemuEvent *ev)
*/
qemu_futex_wait(ev, EV_BUSY);
}
+#else
+ pthread_mutex_lock(&ev->lock);
+ while (qatomic_read(&ev->value) != EV_SET) {
+ pthread_cond_wait(&ev->cond, &ev->lock);
+ }
+ pthread_mutex_unlock(&ev->lock);
+#endif
}
static __thread NotifierList thread_exit;
--
2.49.0
next prev parent reply other threads:[~2025-05-11 6:11 UTC|newest]
Thread overview: 29+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-05-11 6:08 [PATCH v3 00/10] Improve futex usage Akihiko Odaki
2025-05-11 6:08 ` [PATCH v3 01/10] futex: Check value after qemu_futex_wait() Akihiko Odaki
2025-05-13 14:39 ` Peter Xu
2025-05-14 7:34 ` Akihiko Odaki
2025-05-14 17:06 ` Peter Xu
2025-05-16 5:34 ` Akihiko Odaki
2025-05-16 14:53 ` Peter Xu
2025-05-17 5:01 ` Akihiko Odaki
2025-05-11 6:08 ` [PATCH v3 02/10] futex: Support Windows Akihiko Odaki
2025-05-11 6:08 ` [PATCH v3 03/10] futex: Replace __linux__ with CONFIG_LINUX Akihiko Odaki
2025-05-11 6:08 ` Akihiko Odaki [this message]
2025-05-14 0:51 ` [PATCH v3 04/10] qemu-thread: Avoid futex abstraction for non-Linux Paolo Bonzini
2025-05-14 12:57 ` Akihiko Odaki
2025-05-16 11:09 ` Paolo Bonzini
2025-05-16 12:58 ` Akihiko Odaki
2025-05-16 14:25 ` Paolo Bonzini
2025-05-17 5:40 ` Akihiko Odaki
2025-05-17 10:24 ` Paolo Bonzini
2025-05-17 16:30 ` Akihiko Odaki
2025-05-11 6:08 ` [PATCH v3 05/10] qemu-thread: Use futex for QemuEvent on Windows Akihiko Odaki
2025-05-11 6:08 ` [PATCH v3 06/10] qemu-thread: Use futex if available for QemuLockCnt Akihiko Odaki
2025-05-11 6:08 ` [PATCH v3 07/10] migration: Replace QemuSemaphore with QemuEvent Akihiko Odaki
2025-05-13 19:13 ` Peter Xu
2025-05-14 12:36 ` Akihiko Odaki
2025-05-11 6:08 ` [PATCH v3 08/10] migration/colo: " Akihiko Odaki
2025-05-12 15:12 ` Fabiano Rosas
2025-05-11 6:08 ` [PATCH v3 09/10] migration/postcopy: " Akihiko Odaki
2025-05-12 15:12 ` Fabiano Rosas
2025-05-11 6:08 ` [PATCH v3 10/10] hw/display/apple-gfx: " Akihiko Odaki
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20250511-event-v3-4-f7f69247d303@daynix.com \
--to=akihiko.odaki@daynix.com \
--cc=berrange@redhat.com \
--cc=devel@daynix.com \
--cc=farosas@suse.de \
--cc=marcandre.lureau@redhat.com \
--cc=pbonzini@redhat.com \
--cc=peterx@redhat.com \
--cc=phil@philjordan.eu \
--cc=philmd@linaro.org \
--cc=qemu-devel@nongnu.org \
--cc=sw@weilnetz.de \
--cc=zhanghailiang@xfusion.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).