qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Frederic Konrad <fred.konrad@greensocs.com>
To: Paolo Bonzini <pbonzini@redhat.com>, qemu-devel@nongnu.org
Cc: jan.kiszka@siemens.com, Mark Burton <mark.burton@greensocs.com>,
	Guillaume Delbergue <guillaume.delbergue@greensocs.com>
Subject: Re: [Qemu-devel] [PATCH 1/9] main-loop: use qemu_mutex_lock_iothread consistently
Date: Tue, 23 Jun 2015 15:49:48 +0200	[thread overview]
Message-ID: <558963FC.6030308@greensocs.com> (raw)
In-Reply-To: <1434646046-27150-2-git-send-email-pbonzini@redhat.com>

On 18/06/2015 18:47, Paolo Bonzini wrote:
> The next patch will require the BQL to be always taken with
> qemu_mutex_lock_iothread(), while right now this isn't the case.
>
> Outside TCG mode this is not a problem.  In TCG mode, we need to be
> careful and avoid the "prod out of compiled code" step if already
> in a VCPU thread.  This is easily done with a check on current_cpu,
> i.e. qemu_in_vcpu_thread().
>
> Hopefully, multithreaded TCG will get rid of the whole logic to kick
> VCPUs whenever an I/O event occurs!
Hopefully :), this means dropping the iothread mutex as soon as possible and
removing the iothread_requesting_mutex I guess..

Fred

>
> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
> ---
>   cpus.c | 13 ++++++++-----
>   1 file changed, 8 insertions(+), 5 deletions(-)
>
> diff --git a/cpus.c b/cpus.c
> index de6469f..2e807f9 100644
> --- a/cpus.c
> +++ b/cpus.c
> @@ -924,7 +924,7 @@ static void *qemu_kvm_cpu_thread_fn(void *arg)
>       CPUState *cpu = arg;
>       int r;
>   
> -    qemu_mutex_lock(&qemu_global_mutex);
> +    qemu_mutex_lock_iothread();
>       qemu_thread_get_self(cpu->thread);
>       cpu->thread_id = qemu_get_thread_id();
>       cpu->can_do_io = 1;
> @@ -1004,10 +1004,10 @@ static void *qemu_tcg_cpu_thread_fn(void *arg)
>   {
>       CPUState *cpu = arg;
>   
> +    qemu_mutex_lock_iothread();
>       qemu_tcg_init_cpu_signals();
>       qemu_thread_get_self(cpu->thread);
>   
> -    qemu_mutex_lock(&qemu_global_mutex);
>       CPU_FOREACH(cpu) {
>           cpu->thread_id = qemu_get_thread_id();
>           cpu->created = true;
> @@ -1118,7 +1118,11 @@ bool qemu_in_vcpu_thread(void)
>   
>   void qemu_mutex_lock_iothread(void)
>   {
>       atomic_inc(&iothread_requesting_mutex);
> -    if (!tcg_enabled() || !first_cpu || !first_cpu->thread) {
> +    /* 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->thread) {
>           qemu_mutex_lock(&qemu_global_mutex);
>           atomic_dec(&iothread_requesting_mutex);
>       } else {

  reply	other threads:[~2015-06-23 13:50 UTC|newest]

Thread overview: 30+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-06-18 16:47 [Qemu-devel] [PATCH for-2.4 0/9] KVM: Do I/O outside BQL whenever possible Paolo Bonzini
2015-06-18 16:47 ` [Qemu-devel] [PATCH 1/9] main-loop: use qemu_mutex_lock_iothread consistently Paolo Bonzini
2015-06-23 13:49   ` Frederic Konrad [this message]
2015-06-23 13:56     ` Paolo Bonzini
2015-06-23 14:18       ` Frederic Konrad
2015-06-18 16:47 ` [Qemu-devel] [PATCH 2/9] main-loop: introduce qemu_mutex_iothread_locked Paolo Bonzini
2015-06-23  8:48   ` Fam Zheng
2015-06-18 16:47 ` [Qemu-devel] [PATCH 3/9] memory: Add global-locking property to memory regions Paolo Bonzini
2015-06-23  8:51   ` Fam Zheng
2015-06-18 16:47 ` [Qemu-devel] [PATCH 4/9] exec: pull qemu_flush_coalesced_mmio_buffer() into address_space_rw/ld*/st* Paolo Bonzini
2015-06-23  9:05   ` Fam Zheng
2015-06-23  9:12     ` Paolo Bonzini
2015-06-18 16:47 ` [Qemu-devel] [PATCH 5/9] memory: let address_space_rw/ld*/st* run outside the BQL Paolo Bonzini
2015-06-24 16:56   ` Alex Bennée
2015-06-24 17:21     ` Paolo Bonzini
2015-06-24 18:50       ` Alex Bennée
2015-06-25  8:13         ` Paolo Bonzini
2015-06-18 16:47 ` [Qemu-devel] [PATCH 6/9] kvm: First step to push iothread lock out of inner run loop Paolo Bonzini
2015-06-18 18:19   ` Christian Borntraeger
2015-06-23  9:26   ` Fam Zheng
2015-06-23  9:29     ` Paolo Bonzini
2015-06-23  9:45       ` Fam Zheng
2015-06-23  9:49         ` Paolo Bonzini
2015-06-18 16:47 ` [Qemu-devel] [PATCH 7/9] kvm: Switch to unlocked PIO Paolo Bonzini
2015-06-18 16:47 ` [Qemu-devel] [PATCH 8/9] acpi: mark PMTIMER as unlocked Paolo Bonzini
2015-06-18 16:47 ` [Qemu-devel] [PATCH 9/9] kvm: Switch to unlocked MMIO Paolo Bonzini
  -- strict thread matches above, loose matches on Subject: below --
2015-06-24 16:25 [Qemu-devel] [PATCH for-2.4 v2 0/9] KVM: Do I/O outside BQL whenever possible Paolo Bonzini
2015-06-24 16:25 ` [Qemu-devel] [PATCH 1/9] main-loop: use qemu_mutex_lock_iothread consistently Paolo Bonzini
2015-06-25  3:39   ` Fam Zheng
2015-06-25  8:20     ` Paolo Bonzini
2015-07-02  8:20 [Qemu-devel] [PATCH for-2.4 0/9 v3] KVM: Do I/O outside BQL whenever possible Paolo Bonzini
2015-07-02  8:20 ` [Qemu-devel] [PATCH 1/9] main-loop: use qemu_mutex_lock_iothread consistently Paolo Bonzini

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=558963FC.6030308@greensocs.com \
    --to=fred.konrad@greensocs.com \
    --cc=guillaume.delbergue@greensocs.com \
    --cc=jan.kiszka@siemens.com \
    --cc=mark.burton@greensocs.com \
    --cc=pbonzini@redhat.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).