From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:46950) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1bHyuk-00023P-MV for qemu-devel@nongnu.org; Tue, 28 Jun 2016 15:43:19 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1bHyue-00068Z-Oc for qemu-devel@nongnu.org; Tue, 28 Jun 2016 15:43:17 -0400 Received: from mail-lf0-x231.google.com ([2a00:1450:4010:c07::231]:32925) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1bHyue-00067x-F9 for qemu-devel@nongnu.org; Tue, 28 Jun 2016 15:43:12 -0400 Received: by mail-lf0-x231.google.com with SMTP id f6so18708430lfg.0 for ; Tue, 28 Jun 2016 12:43:12 -0700 (PDT) References: <1464986428-6739-1-git-send-email-alex.bennee@linaro.org> <1464986428-6739-17-git-send-email-alex.bennee@linaro.org> From: Sergey Fedorov Message-ID: <5772D34C.7050302@gmail.com> Date: Tue, 28 Jun 2016 22:43:08 +0300 MIME-Version: 1.0 In-Reply-To: <1464986428-6739-17-git-send-email-alex.bennee@linaro.org> Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: 8bit Subject: Re: [Qemu-devel] [RFC v3 16/19] tcg: move locking for tb_invalidate_phys_page_range up List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: =?UTF-8?Q?Alex_Benn=c3=a9e?= , mttcg@listserver.greensocs.com, qemu-devel@nongnu.org, fred.konrad@greensocs.com, a.rigo@virtualopensystems.com, cota@braap.org, bobby.prani@gmail.com Cc: mark.burton@greensocs.com, pbonzini@redhat.com, jan.kiszka@siemens.com, rth@twiddle.net, peter.maydell@linaro.org, claudio.fontana@huawei.com, Peter Crosthwaite On 03/06/16 23:40, Alex Bennée wrote: > While we previously assumed an existing memory lock protected the page > look up in the MTTCG SoftMMU case the memory lock is provided by the > tb_lock. As a result we push the taking of this lock up the call tree. > This requires a slightly different entry for the SoftMMU and user-mode > cases from tb_invalidate_phys_range. Sorry, I can't understand the description for the patch :( Some rewording might be helpful, if you don't mind. Thanks, Sergey > This also means user-mode breakpoint insertion needs to take two locks > but it hadn't taken any previously so this is an improvement. > > Signed-off-by: Alex Bennée > --- > exec.c | 16 ++++++++++++++++ > translate-all.c | 37 +++++++++++++++++++++++++++++-------- > 2 files changed, 45 insertions(+), 8 deletions(-) (snip)