From: Paolo Bonzini <pbonzini@redhat.com>
To: "Emilio G. Cota" <cota@braap.org>,
qemu-devel@nongnu.org, mttcg@greensocs.com
Cc: guillaume.delbergue@greensocs.com, alex.bennee@linaro.org,
mark.burton@greensocs.com, a.rigo@virtualopensystems.com,
Frederic Konrad <fred.konrad@greensocs.com>
Subject: Re: [Qemu-devel] [RFC 05/38] thread-posix: inline qemu_spin functions
Date: Sun, 23 Aug 2015 18:04:46 -0700 [thread overview]
Message-ID: <55DA6DAE.9070105@redhat.com> (raw)
In-Reply-To: <1440375847-17603-6-git-send-email-cota@braap.org>
On 23/08/2015 17:23, Emilio G. Cota wrote:
> On some parallel workloads this gives up to a 15% speed improvement.
>
> Signed-off-by: Emilio G. Cota <cota@braap.org>
> ---
> include/qemu/thread-posix.h | 47 ++++++++++++++++++++++++++++++++++++++++++
> include/qemu/thread.h | 6 ------
> util/qemu-thread-posix.c | 50 +++++----------------------------------------
> 3 files changed, 52 insertions(+), 51 deletions(-)
>
> diff --git a/include/qemu/thread-posix.h b/include/qemu/thread-posix.h
> index 8ce8f01..7d3a9f1 100644
> --- a/include/qemu/thread-posix.h
> +++ b/include/qemu/thread-posix.h
> @@ -37,4 +37,51 @@ struct QemuThread {
> pthread_t thread;
> };
>
> +void qemu_spin_error_exit(int err, const char *msg);
> +
> +static inline void qemu_spin_init(QemuSpin *spin)
> +{
> + int err;
> +
> + err = pthread_spin_init(&spin->lock, 0);
> + if (err) {
> + qemu_spin_error_exit(err, __func__);
> + }
> +}
> +
> +static inline void qemu_spin_destroy(QemuSpin *spin)
> +{
> + int err;
> +
> + err = pthread_spin_destroy(&spin->lock);
> + if (err) {
> + qemu_spin_error_exit(err, __func__);
> + }
> +}
> +
> +static inline void qemu_spin_lock(QemuSpin *spin)
> +{
> + int err;
> +
> + err = pthread_spin_lock(&spin->lock);
> + if (err) {
> + qemu_spin_error_exit(err, __func__);
> + }
> +}
> +
> +static inline int qemu_spin_trylock(QemuSpin *spin)
> +{
> + return pthread_spin_trylock(&spin->lock);
> +}
> +
> +static inline void qemu_spin_unlock(QemuSpin *spin)
> +{
> + int err;
> +
> + err = pthread_spin_unlock(&spin->lock);
> + if (err) {
> + qemu_spin_error_exit(err, __func__);
> + }
> +}
> +
> #endif
> diff --git a/include/qemu/thread.h b/include/qemu/thread.h
> index f5d1259..003daab 100644
> --- a/include/qemu/thread.h
> +++ b/include/qemu/thread.h
> @@ -26,12 +26,6 @@ void qemu_mutex_lock(QemuMutex *mutex);
> int qemu_mutex_trylock(QemuMutex *mutex);
> void qemu_mutex_unlock(QemuMutex *mutex);
>
> -void qemu_spin_init(QemuSpin *spin);
> -void qemu_spin_destroy(QemuSpin *spin);
> -void qemu_spin_lock(QemuSpin *spin);
> -int qemu_spin_trylock(QemuSpin *spin);
> -void qemu_spin_unlock(QemuSpin *spin);
> -
> void qemu_cond_init(QemuCond *cond);
> void qemu_cond_destroy(QemuCond *cond);
>
> diff --git a/util/qemu-thread-posix.c b/util/qemu-thread-posix.c
> index 224bacc..04dae0f 100644
> --- a/util/qemu-thread-posix.c
> +++ b/util/qemu-thread-posix.c
> @@ -48,6 +48,11 @@ static void error_exit(int err, const char *msg)
> abort();
> }
>
> +void qemu_spin_error_exit(int err, const char *msg)
> +{
> + error_exit(err, msg);
> +}
> +
> void qemu_mutex_init(QemuMutex *mutex)
> {
> int err;
> @@ -89,51 +94,6 @@ void qemu_mutex_unlock(QemuMutex *mutex)
> error_exit(err, __func__);
> }
>
> -void qemu_spin_init(QemuSpin *spin)
> -{
> - int err;
> -
> - err = pthread_spin_init(&spin->lock, 0);
> - if (err) {
> - error_exit(err, __func__);
> - }
> -}
> -
> -void qemu_spin_destroy(QemuSpin *spin)
> -{
> - int err;
> -
> - err = pthread_spin_destroy(&spin->lock);
> - if (err) {
> - error_exit(err, __func__);
> - }
> -}
> -
> -void qemu_spin_lock(QemuSpin *spin)
> -{
> - int err;
> -
> - err = pthread_spin_lock(&spin->lock);
> - if (err) {
> - error_exit(err, __func__);
> - }
> -}
> -
> -int qemu_spin_trylock(QemuSpin *spin)
> -{
> - return pthread_spin_trylock(&spin->lock);
> -}
> -
> -void qemu_spin_unlock(QemuSpin *spin)
> -{
> - int err;
> -
> - err = pthread_spin_unlock(&spin->lock);
> - if (err) {
> - error_exit(err, __func__);
> - }
> -}
> -
> void qemu_cond_init(QemuCond *cond)
> {
> int err;
>
Applied, but in the end the spinlock will probably simply use a simple
test-and-test-and-set lock, or an MCS lock. There is no need to use
pthreads for this.
Paolo
next prev parent reply other threads:[~2015-08-24 1:04 UTC|newest]
Thread overview: 110+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-08-24 0:23 [Qemu-devel] [RFC 00/38] MTTCG: i386, user+system mode Emilio G. Cota
2015-08-24 0:23 ` [Qemu-devel] [RFC 01/38] cpu-exec: add missing mmap_lock in tb_find_slow Emilio G. Cota
2015-09-07 15:33 ` Alex Bennée
2015-08-24 0:23 ` [Qemu-devel] [RFC 02/38] hw/i386/kvmvapic: add missing include of tcg.h Emilio G. Cota
2015-09-07 15:49 ` Alex Bennée
2015-09-07 16:11 ` Paolo Bonzini
2015-08-24 0:23 ` [Qemu-devel] [RFC 03/38] cpu-exec: set current_cpu at cpu_exec() Emilio G. Cota
2015-08-24 1:03 ` Paolo Bonzini
2015-08-25 0:41 ` [Qemu-devel] [PATCH 1/4] cpus: add qemu_cpu_thread_init_common() to avoid code duplication Emilio G. Cota
2015-08-25 0:41 ` [Qemu-devel] [PATCH 2/4] linux-user: add helper to set current_cpu before cpu_loop() Emilio G. Cota
2015-08-25 0:41 ` [Qemu-devel] [PATCH 3/4] linux-user: call rcu_(un)register_thread on thread creation/deletion Emilio G. Cota
2015-08-26 0:22 ` Paolo Bonzini
2015-08-25 0:41 ` [Qemu-devel] [PATCH 4/4] bsd-user: add helper to set current_cpu before cpu_loop() Emilio G. Cota
2015-08-25 18:07 ` Emilio G. Cota
2015-08-24 0:23 ` [Qemu-devel] [RFC 04/38] translate-all: remove volatile from have_tb_lock Emilio G. Cota
2015-09-07 15:50 ` Alex Bennée
2015-09-07 16:12 ` Paolo Bonzini
2015-08-24 0:23 ` [Qemu-devel] [RFC 05/38] thread-posix: inline qemu_spin functions Emilio G. Cota
2015-08-24 1:04 ` Paolo Bonzini [this message]
2015-08-25 2:30 ` Emilio G. Cota
2015-08-25 19:30 ` Emilio G. Cota
2015-08-25 22:53 ` Paolo Bonzini
2015-08-24 0:23 ` [Qemu-devel] [RFC 06/38] seqlock: add missing 'inline' to seqlock_read_retry Emilio G. Cota
2015-09-07 15:50 ` Alex Bennée
2015-08-24 0:23 ` [Qemu-devel] [RFC 07/38] seqlock: read sequence number atomically Emilio G. Cota
2015-09-07 15:53 ` Alex Bennée
2015-09-07 16:13 ` Paolo Bonzini
2015-08-24 0:23 ` [Qemu-devel] [RFC 08/38] rcu: init rcu_registry_lock after fork Emilio G. Cota
2015-09-08 17:34 ` Alex Bennée
2015-09-08 19:03 ` Emilio G. Cota
2015-09-09 9:35 ` Alex Bennée
2015-08-24 0:23 ` [Qemu-devel] [RFC 09/38] rcu: fix comment with s/rcu_gp_lock/rcu_registry_lock/ Emilio G. Cota
2015-09-10 11:18 ` Alex Bennée
2015-08-24 0:23 ` [Qemu-devel] [RFC 10/38] translate-all: remove obsolete comment about l1_map Emilio G. Cota
2015-09-10 11:59 ` Alex Bennée
2015-08-24 0:23 ` [Qemu-devel] [RFC 11/38] qemu-thread: handle spurious futex_wait wakeups Emilio G. Cota
2015-09-10 13:22 ` Alex Bennée
2015-09-10 17:46 ` Emilio G. Cota
2015-08-24 0:23 ` [Qemu-devel] [RFC 12/38] linux-user: call rcu_(un)register_thread on pthread_(exit|create) Emilio G. Cota
2015-08-25 0:45 ` Emilio G. Cota
2015-08-24 0:23 ` [Qemu-devel] [RFC 13/38] cputlb: add physical address to CPUTLBEntry Emilio G. Cota
2015-09-10 13:49 ` Alex Bennée
2015-09-10 17:50 ` Emilio G. Cota
2015-09-21 5:01 ` Paolo Bonzini
2015-08-24 0:23 ` [Qemu-devel] [RFC 14/38] softmmu: add helpers to get ld/st physical addresses Emilio G. Cota
2015-08-24 2:02 ` Paolo Bonzini
2015-08-25 2:47 ` Emilio G. Cota
2015-08-24 0:23 ` [Qemu-devel] [RFC 15/38] radix-tree: add generic lockless radix tree module Emilio G. Cota
2015-09-10 14:25 ` Alex Bennée
2015-09-10 18:00 ` Emilio G. Cota
2015-08-24 0:23 ` [Qemu-devel] [RFC 16/38] aie: add module for Atomic Instruction Emulation Emilio G. Cota
2015-08-24 0:23 ` [Qemu-devel] [RFC 17/38] aie: add target helpers Emilio G. Cota
2015-09-17 15:14 ` Alex Bennée
2015-09-21 5:18 ` Paolo Bonzini
2015-09-21 20:59 ` Alex Bennée
2015-08-24 0:23 ` [Qemu-devel] [RFC 18/38] tcg: add fences Emilio G. Cota
2015-09-10 15:28 ` Alex Bennée
2015-08-24 0:23 ` [Qemu-devel] [RFC 19/38] tcg: add tcg_gen_smp_rmb() Emilio G. Cota
2015-09-10 16:01 ` Alex Bennée
2015-09-10 18:05 ` Emilio G. Cota
2015-08-24 0:23 ` [Qemu-devel] [RFC 20/38] tcg/i386: implement fences Emilio G. Cota
2015-08-24 1:32 ` Paolo Bonzini
2015-08-25 3:02 ` Emilio G. Cota
2015-08-25 22:55 ` Paolo Bonzini
2015-08-24 0:23 ` [Qemu-devel] [RFC 21/38] target-i386: emulate atomic instructions + barriers using AIE Emilio G. Cota
2015-09-17 15:30 ` Alex Bennée
2015-08-24 0:23 ` [Qemu-devel] [RFC 22/38] cpu: update interrupt_request atomically Emilio G. Cota
2015-08-24 1:09 ` Paolo Bonzini
2015-08-25 20:36 ` Emilio G. Cota
2015-08-25 22:52 ` Paolo Bonzini
2015-08-24 0:23 ` [Qemu-devel] [RFC 23/38] cpu-exec: grab iothread lock during interrupt handling Emilio G. Cota
2015-09-09 10:13 ` Paolo Bonzini
2015-08-24 0:23 ` [Qemu-devel] [RFC 24/38] cpu-exec: reset mmap_lock after exiting the CPU loop Emilio G. Cota
2015-08-24 2:01 ` Paolo Bonzini
2015-08-25 21:16 ` Emilio G. Cota
2015-08-24 0:23 ` [Qemu-devel] [RFC 25/38] cpu: add barriers around cpu->tcg_exit_req Emilio G. Cota
2015-08-24 2:01 ` Paolo Bonzini
2015-08-24 0:23 ` [Qemu-devel] [RFC 26/38] cpu: protect tb_jmp_cache with seqlock Emilio G. Cota
2015-08-24 1:14 ` Paolo Bonzini
2015-08-25 21:46 ` Emilio G. Cota
2015-08-25 22:49 ` Paolo Bonzini
2015-09-04 8:50 ` Paolo Bonzini
2015-09-04 10:04 ` Paolo Bonzini
2015-08-24 0:23 ` [Qemu-devel] [RFC 27/38] cpu-exec: convert tb_invalidated_flag into a per-TB flag Emilio G. Cota
2015-08-24 0:23 ` [Qemu-devel] [RFC 28/38] cpu-exec: use RCU to perform lockless TB lookups Emilio G. Cota
2015-08-24 0:23 ` [Qemu-devel] [RFC 29/38] tcg: export have_tb_lock Emilio G. Cota
2015-08-24 0:23 ` [Qemu-devel] [RFC 30/38] translate-all: add tb_lock assertions Emilio G. Cota
2015-08-24 0:24 ` [Qemu-devel] [RFC 31/38] cpu: protect l1_map with tb_lock in full-system mode Emilio G. Cota
2015-08-24 1:07 ` Paolo Bonzini
2015-08-25 21:54 ` Emilio G. Cota
2015-08-24 0:24 ` [Qemu-devel] [RFC 32/38] cpu list: convert to RCU QLIST Emilio G. Cota
2015-08-24 0:24 ` [Qemu-devel] [RFC 33/38] cpu: introduce cpu_tcg_sched_work to run work while other CPUs sleep Emilio G. Cota
2015-08-24 1:24 ` Paolo Bonzini
2015-08-25 22:18 ` Emilio G. Cota
2015-08-24 0:24 ` [Qemu-devel] [RFC 34/38] translate-all: use tcg_sched_work for tb_flush Emilio G. Cota
2015-08-24 0:24 ` [Qemu-devel] [RFC 35/38] cputlb: use cpu_tcg_sched_work for tlb_flush_all Emilio G. Cota
2015-08-24 1:29 ` Paolo Bonzini
2015-08-25 22:31 ` Emilio G. Cota
2015-08-26 0:25 ` Paolo Bonzini
2015-09-01 16:10 ` Alex Bennée
2015-09-01 19:38 ` Emilio G. Cota
2015-09-01 20:18 ` Peter Maydell
2015-08-24 0:24 ` [Qemu-devel] [RFC 36/38] cputlb: use tcg_sched_work for tlb_flush_page_all Emilio G. Cota
2015-08-24 0:24 ` [Qemu-devel] [RFC 37/38] cpus: remove async_run_safe_work_on_cpu Emilio G. Cota
2015-08-24 0:24 ` [Qemu-devel] [RFC 38/38] Revert "target-i386: yield to another VCPU on PAUSE" Emilio G. Cota
2015-08-24 1:29 ` Paolo Bonzini
2015-08-24 2:01 ` [Qemu-devel] [RFC 00/38] MTTCG: i386, user+system mode Paolo Bonzini
2015-08-25 22:36 ` Emilio G. Cota
2015-08-24 16:08 ` Artyom Tarasenko
2015-08-24 20:16 ` Emilio G. Cota
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=55DA6DAE.9070105@redhat.com \
--to=pbonzini@redhat.com \
--cc=a.rigo@virtualopensystems.com \
--cc=alex.bennee@linaro.org \
--cc=cota@braap.org \
--cc=fred.konrad@greensocs.com \
--cc=guillaume.delbergue@greensocs.com \
--cc=mark.burton@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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.