From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:57035) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1agddq-00076Q-Bu for qemu-devel@nongnu.org; Thu, 17 Mar 2016 15:31:31 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1agddn-0002QB-1W for qemu-devel@nongnu.org; Thu, 17 Mar 2016 15:31:30 -0400 Received: from mail-wm0-x242.google.com ([2a00:1450:400c:c09::242]:34604) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1agddm-0002Q6-Qx for qemu-devel@nongnu.org; Thu, 17 Mar 2016 15:31:26 -0400 Received: by mail-wm0-x242.google.com with SMTP id p65so1541281wmp.1 for ; Thu, 17 Mar 2016 12:31:26 -0700 (PDT) Sender: Paolo Bonzini References: <1458222382-6498-1-git-send-email-sergey.fedorov@linaro.org> <1458222382-6498-4-git-send-email-sergey.fedorov@linaro.org> <56EAF001.2050303@twiddle.net> From: Paolo Bonzini Message-ID: <56EB060A.9080302@redhat.com> Date: Thu, 17 Mar 2016 20:31:22 +0100 MIME-Version: 1.0 In-Reply-To: <56EAF001.2050303@twiddle.net> Content-Type: text/plain; charset=windows-1252 Content-Transfer-Encoding: 8bit Subject: Re: [Qemu-devel] [PATCH 3/5] tcg: always keep jump target and tb->jmp_next consistent List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Richard Henderson , sergey.fedorov@linaro.org, qemu-devel@nongnu.org Cc: Sergey Fedorov , Peter Crosthwaite On 17/03/2016 18:57, Richard Henderson wrote: > > @@ -951,18 +959,10 @@ static inline void tb_jmp_remove(TranslationBlock *tb, int n) > > } > > /* now we can suppress tb(n) from the list */ > > *ptb = tb->jmp_next[n]; > > - > > - tb->jmp_next[n] = NULL; > > + tb_reset_jump(tb, n); > > What's the motivation here? This implies an extra cache flush. > Where were we resetting the jump previously? Or is this a bug > in that we *weren't* resetting the jump previously? Indeed I think this patch can be removed if it has a performance effect on machines that require icache invalidation. If it doesn't, it would be just a small code simplification. Paolo