From: Paolo Bonzini <pbonzini@redhat.com>
To: qemu-devel@nongnu.org
Cc: mttcg@greensocs.com, fred.konrad@greensocs.com
Subject: [Qemu-devel] [PATCH 02/10] cpus: remove tcg_halt_cond global variable.
Date: Wed, 12 Aug 2015 18:40:54 +0200 [thread overview]
Message-ID: <1439397664-70734-3-git-send-email-pbonzini@redhat.com> (raw)
In-Reply-To: <1439397664-70734-1-git-send-email-pbonzini@redhat.com>
From: KONRAD Frederic <fred.konrad@greensocs.com>
This removes tcg_halt_cond global variable.
We need one QemuCond per virtual cpu for multithread TCG.
Signed-off-by: KONRAD Frederic <fred.konrad@greensocs.com>
Message-Id: <1439220437-23957-9-git-send-email-fred.konrad@greensocs.com>
[Keep tcg_halt_cond for bisectability, while making it static. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
cpus.c | 12 +++++-------
1 file changed, 5 insertions(+), 7 deletions(-)
diff --git a/cpus.c b/cpus.c
index 9224488..8884278 100644
--- a/cpus.c
+++ b/cpus.c
@@ -813,7 +813,6 @@ static unsigned iothread_requesting_mutex;
static QemuThread io_thread;
static QemuThread *tcg_cpu_thread;
-static QemuCond *tcg_halt_cond;
/* cpu creation */
static QemuCond qemu_cpu_cond;
@@ -933,15 +932,13 @@ static void qemu_wait_io_event_common(CPUState *cpu)
cpu->thread_kicked = false;
}
-static void qemu_tcg_wait_io_event(void)
+static void qemu_tcg_wait_io_event(CPUState *cpu)
{
- CPUState *cpu;
-
while (all_cpu_threads_idle()) {
/* Start accounting real time to the virtual clock if the CPUs
are idle. */
qemu_clock_warp(QEMU_CLOCK_VIRTUAL);
- qemu_cond_wait(tcg_halt_cond, &qemu_global_mutex);
+ qemu_cond_wait(cpu->halt_cond, &qemu_global_mutex);
}
while (iothread_requesting_mutex) {
@@ -1067,7 +1064,7 @@ static void *qemu_tcg_cpu_thread_fn(void *arg)
/* wait for initial kick-off after machine start */
while (first_cpu->stopped) {
- qemu_cond_wait(tcg_halt_cond, &qemu_global_mutex);
+ qemu_cond_wait(first_cpu->halt_cond, &qemu_global_mutex);
/* process any pending work */
CPU_FOREACH(cpu) {
@@ -1088,7 +1085,7 @@ static void *qemu_tcg_cpu_thread_fn(void *arg)
qemu_clock_notify(QEMU_CLOCK_VIRTUAL);
}
}
- qemu_tcg_wait_io_event();
+ qemu_tcg_wait_io_event(QTAILQ_FIRST(&cpus));
}
return NULL;
@@ -1265,6 +1262,7 @@ void resume_all_vcpus(void)
static void qemu_tcg_init_vcpu(CPUState *cpu)
{
char thread_name[VCPU_THREAD_NAME_SIZE];
+ static QemuCond *tcg_halt_cond;
tcg_cpu_address_space_init(cpu, cpu->as);
--
1.8.3.1
next prev parent reply other threads:[~2015-08-12 16:41 UTC|newest]
Thread overview: 52+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-08-12 16:40 [Qemu-devel] [PATCH 00/10] translate-all.c thread-safety Paolo Bonzini
2015-08-12 16:40 ` [Qemu-devel] [PATCH 01/10] cpus: protect work list with work_mutex Paolo Bonzini
2015-08-28 14:33 ` Peter Maydell
2015-08-12 16:40 ` Paolo Bonzini [this message]
2015-08-13 13:05 ` [Qemu-devel] [PATCH 02/10] cpus: remove tcg_halt_cond global variable Frederic Konrad
2015-08-13 13:08 ` Paolo Bonzini
2015-08-13 13:19 ` Frederic Konrad
2015-08-28 14:36 ` Peter Maydell
2015-08-29 6:52 ` Paolo Bonzini
2015-08-12 16:40 ` [Qemu-devel] [PATCH 03/10] replace spinlock by QemuMutex Paolo Bonzini
2015-08-13 12:17 ` Frederic Konrad
2015-08-13 13:12 ` Paolo Bonzini
2015-08-13 13:21 ` Frederic Konrad
2015-08-28 14:49 ` Peter Maydell
2015-08-28 14:53 ` Frederic Konrad
2015-08-29 6:51 ` Paolo Bonzini
2015-08-12 16:40 ` [Qemu-devel] [PATCH 04/10] exec-all: remove non-TCG stuff from exec-all.h header Paolo Bonzini
2015-08-28 14:53 ` Peter Maydell
2015-08-29 6:55 ` Paolo Bonzini
2015-08-12 16:40 ` [Qemu-devel] [PATCH 05/10] cpu-exec: elide more icount code if CONFIG_USER_ONLY Paolo Bonzini
2015-08-13 13:14 ` Frederic Konrad
2015-08-13 14:06 ` Paolo Bonzini
2015-08-28 14:56 ` Peter Maydell
2015-08-29 7:07 ` Paolo Bonzini
2015-08-12 16:40 ` [Qemu-devel] [PATCH 06/10] tcg: code_bitmap is not used by user-mode emulation Paolo Bonzini
2015-08-28 14:57 ` Peter Maydell
2015-08-29 7:13 ` Paolo Bonzini
2015-08-12 16:40 ` [Qemu-devel] [PATCH 07/10] tcg: comment on which functions have to be called with mmap_lock held Paolo Bonzini
2015-08-28 15:33 ` Peter Maydell
2015-08-29 6:57 ` Paolo Bonzini
2015-08-12 16:41 ` [Qemu-devel] [PATCH 08/10] tcg: add memory barriers in page_find_alloc accesses Paolo Bonzini
2015-08-12 20:37 ` Emilio G. Cota
2015-08-13 8:13 ` Paolo Bonzini
2015-08-13 19:50 ` Emilio G. Cota
2015-08-28 15:40 ` Peter Maydell
2015-08-29 6:58 ` Paolo Bonzini
2015-08-12 16:41 ` [Qemu-devel] [PATCH 09/10] exec: make mmap_lock/mmap_unlock globally available Paolo Bonzini
2015-08-28 15:42 ` Peter Maydell
2015-08-12 16:41 ` [Qemu-devel] [PATCH 10/10] cpu-exec: fix lock hierarchy for user-mode emulation Paolo Bonzini
2015-08-28 15:59 ` Peter Maydell
2015-08-12 16:41 ` [Qemu-devel] [PATCH 11/10] tcg: comment on which functions have to be called with tb_lock held Paolo Bonzini
2015-08-13 12:51 ` Frederic Konrad
2015-08-13 12:59 ` Paolo Bonzini
2015-08-13 13:32 ` Frederic Konrad
2015-08-13 14:39 ` Paolo Bonzini
2015-08-13 15:32 ` Peter Maydell
2015-08-13 16:20 ` Paolo Bonzini
2015-08-12 16:41 ` [Qemu-devel] [PATCH 12/10] tcg: protect TBContext with tb_lock Paolo Bonzini
2015-08-13 12:57 ` Frederic Konrad
2015-08-13 13:01 ` Paolo Bonzini
2015-08-13 13:04 ` Frederic Konrad
2015-08-14 9:26 ` [Qemu-devel] [PATCH 00/10] translate-all.c thread-safety Frederic Konrad
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=1439397664-70734-3-git-send-email-pbonzini@redhat.com \
--to=pbonzini@redhat.com \
--cc=fred.konrad@greensocs.com \
--cc=mttcg@greensocs.com \
--cc=qemu-devel@nongnu.org \
/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).