From mboxrd@z Thu Jan 1 00:00:00 1970 From: "Burakov, Anatoly" Subject: Re: [PATCH] malloc: notify primary process about hotplug in secondary Date: Wed, 5 Dec 2018 10:36:37 +0000 Message-ID: References: <20181204170610.250124-1-seth.howell@intel.com> Mime-Version: 1.0 Content-Type: text/plain; charset=utf-8; format=flowed Content-Transfer-Encoding: 7bit Cc: dev@dpdk.org, Darek Stojaczyk To: Seth Howell Return-path: Received: from mga06.intel.com (mga06.intel.com [134.134.136.31]) by dpdk.org (Postfix) with ESMTP id 8A17F1B185 for ; Wed, 5 Dec 2018 11:36:40 +0100 (CET) In-Reply-To: <20181204170610.250124-1-seth.howell@intel.com> Content-Language: en-US List-Id: DPDK patches and discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dev-bounces@dpdk.org Sender: "dev" On 04-Dec-18 5:06 PM, Seth Howell wrote: > When secondary process hotplugs memory, it sends a request > to primary, which then performs the real mmap() and sends > sync requests to all secondary processes. Upon receiving > such sync request, each secondary process will notify the > upper layers of hotplugged memory (and will call all > locally registered event callbacks). > > In the end we'll end up with memory event callbacks fired > in all the processes except the primary, which is a bug. > > This gets critical if memory is hotplugged while a VFIO > device is attached, as the VFIO memory registration - > which is done from a memory event callback present in the > primary process only - is never called. > > After this patch, a primary process fires memory event > callbacks before secondary processes start their > synchronizations - both for hotplug and hotremove. > > Change-Id: I60de33913f58bc2454069c3844826c92cb043fff This is internal tag, please don't include it in the patch. Also, misses Fixes: tag, and Cc: stable@dpdk.org (since this bug goes back to 18.05). > Signed-off-by: Seth Howell > Signed-off-by: Darek Stojaczyk > --- Otherwise, Reviewed-by: Anatoly Burakov -- Thanks, Anatoly