From mboxrd@z Thu Jan  1 00:00:00 1970
Received: from eggs.gnu.org ([2001:4830:134:3::10]:53287)
	by lists.gnu.org with esmtp (Exim 4.71)
	(envelope-from <pbonzini@redhat.com>) id 1YAdvV-0001n9-HA
	for qemu-devel@nongnu.org; Mon, 12 Jan 2015 07:16:58 -0500
Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71)
	(envelope-from <pbonzini@redhat.com>) id 1YAdvR-0005Bo-Gb
	for qemu-devel@nongnu.org; Mon, 12 Jan 2015 07:16:57 -0500
Received: from mx1.redhat.com ([209.132.183.28]:43504)
	by eggs.gnu.org with esmtp (Exim 4.71)
	(envelope-from <pbonzini@redhat.com>) id 1YAdvR-0005Be-AI
	for qemu-devel@nongnu.org; Mon, 12 Jan 2015 07:16:53 -0500
Message-ID: <54B3BB27.1040704@redhat.com>
Date: Mon, 12 Jan 2015 13:16:39 +0100
From: Paolo Bonzini <pbonzini@redhat.com>
MIME-Version: 1.0
References: <20150112115944.3504.66763.stgit@PASHA-ISP>
	<20150112120117.3504.54187.stgit@PASHA-ISP>
In-Reply-To: <20150112120117.3504.54187.stgit@PASHA-ISP>
Content-Type: text/plain; charset=utf-8
Content-Transfer-Encoding: 7bit
Subject: Re: [Qemu-devel] [RFC PATCH v7 16/21] replay: bottom halves
List-Id: <qemu-devel.nongnu.org>
List-Unsubscribe: <https://lists.nongnu.org/mailman/options/qemu-devel>,
	<mailto:qemu-devel-request@nongnu.org?subject=unsubscribe>
List-Archive: <http://lists.nongnu.org/archive/html/qemu-devel>
List-Post: <mailto:qemu-devel@nongnu.org>
List-Help: <mailto:qemu-devel-request@nongnu.org?subject=help>
List-Subscribe: <https://lists.nongnu.org/mailman/listinfo/qemu-devel>,
	<mailto:qemu-devel-request@nongnu.org?subject=subscribe>
To: Pavel Dovgalyuk <Pavel.Dovgaluk@ispras.ru>, qemu-devel@nongnu.org
Cc: peter.maydell@linaro.org, peter.crosthwaite@xilinx.com, alex.bennee@linaro.org, mark.burton@greensocs.com, real@ispras.ru, batuzovk@ispras.ru, maria.klimushenkova@ispras.ru, afaerber@suse.de, fred.konrad@greensocs.com



On 12/01/2015 13:01, Pavel Dovgalyuk wrote:
> -    bh->next = ctx->first_bh;
> -    /* Make sure that the members are ready before putting bh into list */
> -    smp_wmb();
> -    ctx->first_bh = bh;
> +    if (replay_mode != REPLAY_MODE_NONE) {
> +        /* Slower way, but this is a queue and not a stack.
> +           Replay will process the BH in the same order they
> +           came into the queue. */
> +        last = &ctx->first_bh;
> +        while (*last) {
> +            last = &(*last)->next;
> +        }
> +        smp_wmb();
> +        *last = bh;
> +    } else {
> +        bh->next = ctx->first_bh;
> +        /* Make sure that the members are ready before putting bh into list */
> +        smp_wmb();
> +        ctx->first_bh = bh;
> +    }

I am not sure I understand the reason for this, but feel free to change
the list to a QSIMPLEQ, and introduce QSIMPLEQ_INSERT_TAIL_RCU that has
the appropriate barriers.

Paolo