From mboxrd@z Thu Jan 1 00:00:00 1970 From: "Michael S. Tsirkin" Subject: __get_user slower than get_user (was Re: [RFC PATCH V3 0/5] Hi:) Date: Tue, 8 Jan 2019 23:31:14 -0500 Message-ID: <20190108232459-mutt-send-email-mst@kernel.org> References: <20190102154038-mutt-send-email-mst@kernel.org> <0efd115a-a7fb-54bf-5376-59d047a15fd3@redhat.com> <20190106221832-mutt-send-email-mst@kernel.org> <20190106230224-mutt-send-email-mst@kernel.org> <20190107084853-mutt-send-email-mst@kernel.org> <20190107172517-mutt-send-email-mst@kernel.org> Mime-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: base64 Cc: KVM list , Netdev , Linux Kernel Mailing List , virtualization@lists.linux-foundation.org, Linus Torvalds , David Miller To: Dan Williams Return-path: Content-Disposition: inline In-Reply-To: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: virtualization-bounces@lists.linux-foundation.org Errors-To: virtualization-bounces@lists.linux-foundation.org List-Id: netdev.vger.kernel.org T24gTW9uLCBKYW4gMDcsIDIwMTkgYXQgMDI6NDQ6MjRQTSAtMDgwMCwgRGFuIFdpbGxpYW1zIHdy b3RlOgo+IE9uIE1vbiwgSmFuIDcsIDIwMTkgYXQgMjoyNSBQTSBNaWNoYWVsIFMuIFRzaXJraW4g PG1zdEByZWRoYXQuY29tPiB3cm90ZToKPiA+Cj4gPiBPbiBNb24sIEphbiAwNywgMjAxOSBhdCAw MTozOToxNVBNIC0wODAwLCBEYW4gV2lsbGlhbXMgd3JvdGU6Cj4gPiA+IE9uIE1vbiwgSmFuIDcs IDIwMTkgYXQgNjoxMSBBTSBNaWNoYWVsIFMuIFRzaXJraW4gPG1zdEByZWRoYXQuY29tPiB3cm90 ZToKPiA+ID4gPgo+ID4gPiA+IE9uIFN1biwgSmFuIDA2LCAyMDE5IGF0IDExOjE1OjIwUE0gLTA4 MDAsIERhbiBXaWxsaWFtcyB3cm90ZToKPiA+ID4gPiA+IE9uIFN1biwgSmFuIDYsIDIwMTkgYXQg ODoxNyBQTSBNaWNoYWVsIFMuIFRzaXJraW4gPG1zdEByZWRoYXQuY29tPiB3cm90ZToKPiA+ID4g PiA+ID4KPiA+ID4gPiA+ID4gT24gTW9uLCBKYW4gMDcsIDIwMTkgYXQgMTE6NTM6NDFBTSArMDgw MCwgSmFzb24gV2FuZyB3cm90ZToKPiA+ID4gPiA+ID4gPgo+ID4gPiA+ID4gPiA+IE9uIDIwMTkv MS83IOS4iuWNiDExOjI4LCBNaWNoYWVsIFMuIFRzaXJraW4gd3JvdGU6Cj4gPiA+ID4gPiA+ID4g PiBPbiBNb24sIEphbiAwNywgMjAxOSBhdCAxMDoxOTowM0FNICswODAwLCBKYXNvbiBXYW5nIHdy b3RlOgo+ID4gPiA+ID4gPiA+ID4gPiBPbiAyMDE5LzEvMyDkuIrljYg0OjQ3LCBNaWNoYWVsIFMu IFRzaXJraW4gd3JvdGU6Cj4gPiA+ID4gPiA+ID4gPiA+ID4gT24gU2F0LCBEZWMgMjksIDIwMTgg YXQgMDg6NDY6NTFQTSArMDgwMCwgSmFzb24gV2FuZyB3cm90ZToKPiA+ID4gPiA+ID4gPiA+ID4g PiA+IFRoaXMgc2VyaWVzIHRyaWVzIHRvIGFjY2VzcyB2aXJ0cXVldWUgbWV0YWRhdGEgdGhyb3Vn aCBrZXJuZWwgdmlydHVhbAo+ID4gPiA+ID4gPiA+ID4gPiA+ID4gYWRkcmVzcyBpbnN0ZWFkIG9m IGNvcHlfdXNlcigpIGZyaWVuZHMgc2luY2UgdGhleSBoYWQgdG9vIG11Y2gKPiA+ID4gPiA+ID4g PiA+ID4gPiA+IG92ZXJoZWFkcyBsaWtlIGNoZWNrcywgc3BlYyBiYXJyaWVycyBvciBldmVuIGhh cmR3YXJlIGZlYXR1cmUKPiA+ID4gPiA+ID4gPiA+ID4gPiA+IHRvZ2dsaW5nLgo+ID4gPiA+ID4g PiA+ID4gPiA+IFdpbGwgcmV2aWV3LCB0aGFua3MhCj4gPiA+ID4gPiA+ID4gPiA+ID4gT25lIHF1 ZXN0aW9ucyB0aGF0IGNvbWVzIHRvIG1pbmQgaXMgd2hldGhlciBpdCdzIGFsbCBhYm91dCBieXBh c3NpbmcKPiA+ID4gPiA+ID4gPiA+ID4gPiBzdGFjL2NsYWMuICBDb3VsZCB5b3UgcGxlYXNlIGlu Y2x1ZGUgYSBwZXJmb3JtYW5jZSBjb21wYXJpc29uIHdpdGgKPiA+ID4gPiA+ID4gPiA+ID4gPiBu b3NtYXA/Cj4gPiA+ID4gPiA+ID4gPiA+ID4KPiA+ID4gPiA+ID4gPiA+ID4gT24gbWFjaGluZSB3 aXRob3V0IFNNQVAgKFNhbmR5IEJyaWRnZSk6Cj4gPiA+ID4gPiA+ID4gPiA+Cj4gPiA+ID4gPiA+ ID4gPiA+IEJlZm9yZTogNC44TXBwcwo+ID4gPiA+ID4gPiA+ID4gPgo+ID4gPiA+ID4gPiA+ID4g PiBBZnRlcjogNS4yTXBwcwo+ID4gPiA+ID4gPiA+ID4gT0sgc28gd291bGQgeW91IHNheSBpdCdz IHJlYWxseSB1bnNhZmUgdmVyc3VzIHNhZmUgYWNjZXNzZXM/Cj4gPiA+ID4gPiA+ID4gPiBPciB3 b3VsZCB5b3Ugc2F5IGl0J3MganVzdCBhIGJldHRlciB3cml0dGVuIGNvZGU/Cj4gPiA+ID4gPiA+ ID4KPiA+ID4gPiA+ID4gPgo+ID4gPiA+ID4gPiA+IEl0J3MgdGhlIGVmZmVjdCBvZiByZW1vdmlu ZyBzcGVjdWxhdGlvbiBiYXJyaWVyLgo+ID4gPiA+ID4gPgo+ID4gPiA+ID4gPgo+ID4gPiA+ID4g PiBZb3UgbWVhbiBfX3VhY2Nlc3NfYmVnaW5fbm9zcGVjIGludHJvZHVjZWQgYnkKPiA+ID4gPiA+ ID4gY29tbWl0IDMwNGVjMWIwNTAzMTA1NDhkYjMzMDYzZTU2NzEyM2ZhZThmZDAzMDEKPiA+ID4g PiA+ID4gPwo+ID4gPiA+ID4gPgo+ID4gPiA+ID4gPiBTbyBmdW5kYW1lbnRhbGx5IHdlIGRvIGFj Y2Vzc19vayBjaGVja3Mgd2hlbiBzdXBwbHlpbmcKPiA+ID4gPiA+ID4gdGhlIG1lbW9yeSB0YWJs ZSB0byB0aGUga2VybmVsIHRocmVhZCwgYW5kIHdlIHNob3VsZAo+ID4gPiA+ID4gPiBkbyB0aGUg c3BlYyBiYXJyaWVyIHRoZXJlLgo+ID4gPiA+ID4gPgo+ID4gPiA+ID4gPiBUaGVuIHdlIGNhbiBq dXN0IGNyZWF0ZSBhbmQgdXNlIGEgdmFyaWFudCBvZiB1YWNjZXNzIG1hY3JvcyB0aGF0IGRvZXMK PiA+ID4gPiA+ID4gbm90IGluY2x1ZGUgdGhlIGJhcnJpZXI/Cj4gPiA+ID4gPiA+Cj4gPiA+ID4g PiA+IE9yLCBob3cgYWJvdXQgbW92aW5nIHRoZSBiYXJyaWVyIGludG8gYWNjZXNzX29rPwo+ID4g PiA+ID4gPiBUaGlzIHdheSByZXBlYXRlZCBhY2Nlc3NlcyB3aXRoIGEgc2luZ2xlIGFjY2Vzc19v ayBnZXQgYSBiaXQgZmFzdGVyLgo+ID4gPiA+ID4gPiBDQyBEYW4gV2lsbGlhbXMgb24gdGhpcyBp ZGVhLgo+ID4gPiA+ID4KPiA+ID4gPiA+IEl0IHdvdWxkIGJlIGludGVyZXN0aW5nIHRvIHNlZSBo b3cgZXhwZW5zaXZlIHJlLWRvaW5nIHRoZSBhZGRyZXNzCj4gPiA+ID4gPiBsaW1pdCBjaGVjayBp cyBjb21wYXJlZCB0byB0aGUgc3BlY3VsYXRpb24gYmFycmllci4gSS5lLiBqdXN0IHN3aXRjaAo+ ID4gPiA+ID4gdmhvc3RfZ2V0X3VzZXIoKSB0byB1c2UgZ2V0X3VzZXIoKSByYXRoZXIgdGhhbiBf X2dldF91c2VyKCkuIFRoYXQgd2lsbAo+ID4gPiA+ID4gc2FuaXRpemUgdGhlIHBvaW50ZXIgaW4g dGhlIHNwZWN1bGF0aXZlIHBhdGggd2l0aG91dCBhIGJhcnJpZXIuCj4gPiA+ID4KPiA+ID4gPiBI bW0gaXQncyB3YXkgY2hlYXBlciBldmVuIHRob3VnaCBJSVJDIGl0J3MgbWVhc3VyZWFibGUuCj4g PiA+ID4gSmFzb24sIHdvdWxkIHlvdSBsaWtlIHRvIHRyeT8KPiA+ID4gPiBBbHRob3VnaCBmcmFu a2x5IF9fZ2V0X3VzZXIgYmVpbmcgc2xvd2VyIHRoYW4gZ2V0X3VzZXIgZmVlbHMgdmVyeSB3cm9u Zy4KPiA+ID4gPiBOb3QgeWV0IHN1cmUgd2hhdCB0byBkbyBleGFjdGx5IGJ1dCB3b3VsZCB5b3Ug YWdyZWU/Cj4gPiA+Cj4gPiA+IEFncmVlLiBfX2dldF91c2VyKCkgYmVpbmcgZmFzdGVyIHRoYW4g Z2V0X3VzZXIoKSBkZWZlYXRzIHRoZSB3aG9sZQo+ID4gPiBwb2ludCBvZiBjb252ZXJ0aW5nIGNv ZGUgcGF0aHMgdG8gdGhlIGFjY2Vzc19vaygpICsgX19nZXRfdXNlcigpCj4gPiA+IHBhdHRlcm4u Cj4gPgo+ID4gRGlkIHlvdSBtZWFuIHRoZSByZXZlcnNlPwo+IAo+IEhtbSwgbm8uLi4gSSdsbCBy ZXBocmFzZTogX19nZXRfdXNlcigpIHNob3VsZCBoYXZlIGxvd2VyIG92ZXJoZWFkIHRoYW4KPiBn ZXRfdXNlcigpLgoKUmlnaHQgLi4uCgpMaW51cywgZ2l2ZW4gdGhhdCB5b3UganVzdCBjaGFuZ2Vk IGFsbCB1c2VycyBvZiBhY2Nlc3Nfb2sgYW55d2F5LCBkbwp5b3Ugc3RpbGwgdGhpbmsgdGhhdCB0 aGUgYWNjZXNzX29rKCkgY29udmVyc2lvbiB0byByZXR1cm4gYSBzcGVjdWxhdGlvbgpzYW5pdGl6 ZWQgcG9pbnRlciBvciBOVUxMIGlzIHRvbyBiaWcgYSBjb252ZXJzaW9uPwoKSXQgd2FzIHByZXZp b3VzbHkgZGlzY2FyZGVkIGhlcmU6Cmh0dHBzOi8vbGttbC5vcmcvbGttbC8yMDE4LzEvMTcvOTI5 CmJ1dCBhdCB0aGF0IHBvaW50IHdlIGRpZG4ndCBoYXZlIG51bWJlcnMgYW5kIHRoZXJlIHdhcyBh biB1bmRlcnN0YW5kYWJsZQpydXNoIHRvIHNoaXAgc29tZXRoaW5nIHNhZmUuCgpBdCB0aGlzIHBv aW50IEkgdGhpbmsgdGhhdCB2aG9zdCBjYW4gc2hvdyB2ZXJ5IG1lYXN1cmVhYmxlIGdhaW5zIGZy b20KdGhpcyBjb252ZXJzaW9uLgoKVGhhbmtzLAoKLS0gCk1TVApfX19fX19fX19fX19fX19fX19f X19fX19fX19fX19fX19fX19fX19fX19fX19fXwpWaXJ0dWFsaXphdGlvbiBtYWlsaW5nIGxpc3QK VmlydHVhbGl6YXRpb25AbGlzdHMubGludXgtZm91bmRhdGlvbi5vcmcKaHR0cHM6Ly9saXN0cy5s aW51eGZvdW5kYXRpb24ub3JnL21haWxtYW4vbGlzdGluZm8vdmlydHVhbGl6YXRpb24= From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-1.0 required=3.0 tests=HEADER_FROM_DIFFERENT_DOMAINS, MAILING_LIST_MULTI,SPF_PASS,URIBL_BLOCKED autolearn=unavailable autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 06B7EC43612 for ; Wed, 9 Jan 2019 04:31:21 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.kernel.org (Postfix) with ESMTP id D234A2070B for ; Wed, 9 Jan 2019 04:31:20 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1728651AbfAIEbR (ORCPT ); Tue, 8 Jan 2019 23:31:17 -0500 Received: from mx1.redhat.com ([209.132.183.28]:58298 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1727828AbfAIEbR (ORCPT ); Tue, 8 Jan 2019 23:31:17 -0500 Received: from smtp.corp.redhat.com (int-mx04.intmail.prod.int.phx2.redhat.com [10.5.11.14]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mx1.redhat.com (Postfix) with ESMTPS id 540A4D4E56; Wed, 9 Jan 2019 04:31:16 +0000 (UTC) Received: from redhat.com (ovpn-120-220.rdu2.redhat.com [10.10.120.220]) by smtp.corp.redhat.com (Postfix) with ESMTP id 27DC35D9CA; Wed, 9 Jan 2019 04:31:15 +0000 (UTC) Date: Tue, 8 Jan 2019 23:31:14 -0500 From: "Michael S. Tsirkin" To: Dan Williams Cc: Jason Wang , KVM list , virtualization@lists.linux-foundation.org, Netdev , Linux Kernel Mailing List , David Miller , Linus Torvalds Subject: __get_user slower than get_user (was Re: [RFC PATCH V3 0/5] Hi:) Message-ID: <20190108232459-mutt-send-email-mst@kernel.org> References: <20190102154038-mutt-send-email-mst@kernel.org> <0efd115a-a7fb-54bf-5376-59d047a15fd3@redhat.com> <20190106221832-mutt-send-email-mst@kernel.org> <20190106230224-mutt-send-email-mst@kernel.org> <20190107084853-mutt-send-email-mst@kernel.org> <20190107172517-mutt-send-email-mst@kernel.org> MIME-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Disposition: inline Content-Transfer-Encoding: 8bit In-Reply-To: X-Scanned-By: MIMEDefang 2.79 on 10.5.11.14 X-Greylist: Sender IP whitelisted, not delayed by milter-greylist-4.5.16 (mx1.redhat.com [10.5.110.38]); Wed, 09 Jan 2019 04:31:16 +0000 (UTC) Sender: netdev-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org Message-ID: <20190109043114.eoDMh2s9z5CTCaCyxrH__6jI8Jit7UyulyXekebxrO4@z> On Mon, Jan 07, 2019 at 02:44:24PM -0800, Dan Williams wrote: > On Mon, Jan 7, 2019 at 2:25 PM Michael S. Tsirkin wrote: > > > > On Mon, Jan 07, 2019 at 01:39:15PM -0800, Dan Williams wrote: > > > On Mon, Jan 7, 2019 at 6:11 AM Michael S. Tsirkin wrote: > > > > > > > > On Sun, Jan 06, 2019 at 11:15:20PM -0800, Dan Williams wrote: > > > > > On Sun, Jan 6, 2019 at 8:17 PM Michael S. Tsirkin wrote: > > > > > > > > > > > > On Mon, Jan 07, 2019 at 11:53:41AM +0800, Jason Wang wrote: > > > > > > > > > > > > > > On 2019/1/7 上午11:28, Michael S. Tsirkin wrote: > > > > > > > > On Mon, Jan 07, 2019 at 10:19:03AM +0800, Jason Wang wrote: > > > > > > > > > On 2019/1/3 上午4:47, Michael S. Tsirkin wrote: > > > > > > > > > > On Sat, Dec 29, 2018 at 08:46:51PM +0800, Jason Wang wrote: > > > > > > > > > > > This series tries to access virtqueue metadata through kernel virtual > > > > > > > > > > > address instead of copy_user() friends since they had too much > > > > > > > > > > > overheads like checks, spec barriers or even hardware feature > > > > > > > > > > > toggling. > > > > > > > > > > Will review, thanks! > > > > > > > > > > One questions that comes to mind is whether it's all about bypassing > > > > > > > > > > stac/clac. Could you please include a performance comparison with > > > > > > > > > > nosmap? > > > > > > > > > > > > > > > > > > > On machine without SMAP (Sandy Bridge): > > > > > > > > > > > > > > > > > > Before: 4.8Mpps > > > > > > > > > > > > > > > > > > After: 5.2Mpps > > > > > > > > OK so would you say it's really unsafe versus safe accesses? > > > > > > > > Or would you say it's just a better written code? > > > > > > > > > > > > > > > > > > > > > It's the effect of removing speculation barrier. > > > > > > > > > > > > > > > > > > You mean __uaccess_begin_nospec introduced by > > > > > > commit 304ec1b050310548db33063e567123fae8fd0301 > > > > > > ? > > > > > > > > > > > > So fundamentally we do access_ok checks when supplying > > > > > > the memory table to the kernel thread, and we should > > > > > > do the spec barrier there. > > > > > > > > > > > > Then we can just create and use a variant of uaccess macros that does > > > > > > not include the barrier? > > > > > > > > > > > > Or, how about moving the barrier into access_ok? > > > > > > This way repeated accesses with a single access_ok get a bit faster. > > > > > > CC Dan Williams on this idea. > > > > > > > > > > It would be interesting to see how expensive re-doing the address > > > > > limit check is compared to the speculation barrier. I.e. just switch > > > > > vhost_get_user() to use get_user() rather than __get_user(). That will > > > > > sanitize the pointer in the speculative path without a barrier. > > > > > > > > Hmm it's way cheaper even though IIRC it's measureable. > > > > Jason, would you like to try? > > > > Although frankly __get_user being slower than get_user feels very wrong. > > > > Not yet sure what to do exactly but would you agree? > > > > > > Agree. __get_user() being faster than get_user() defeats the whole > > > point of converting code paths to the access_ok() + __get_user() > > > pattern. > > > > Did you mean the reverse? > > Hmm, no... I'll rephrase: __get_user() should have lower overhead than > get_user(). Right ... Linus, given that you just changed all users of access_ok anyway, do you still think that the access_ok() conversion to return a speculation sanitized pointer or NULL is too big a conversion? It was previously discarded here: https://lkml.org/lkml/2018/1/17/929 but at that point we didn't have numbers and there was an understandable rush to ship something safe. At this point I think that vhost can show very measureable gains from this conversion. Thanks, -- MST