From mboxrd@z Thu Jan 1 00:00:00 1970 From: Peter Zijlstra Subject: Re: [PATCH v3 3/5] locking/qspinlock: Introduce CNA into the slow path of qspinlock Date: Wed, 17 Jul 2019 10:39:44 +0200 Message-ID: <20190717083944.GR3463@hirez.programming.kicks-ass.net> References: <20190715192536.104548-1-alex.kogan@oracle.com> <20190715192536.104548-4-alex.kogan@oracle.com> <20190716155022.GR3419@hirez.programming.kicks-ass.net> <193BBB31-F376-451F-BDE1-D4807140EB51@oracle.com> <20190716184724.GH3402@hirez.programming.kicks-ass.net> Mime-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: base64 Return-path: Content-Disposition: inline In-Reply-To: <20190716184724.GH3402@hirez.programming.kicks-ass.net> List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: "linux-arm-kernel" Errors-To: linux-arm-kernel-bounces+linux-arm-kernel=m.gmane.org@lists.infradead.org To: Alex Kogan Cc: linux-arch@vger.kernel.org, guohanjun@huawei.com, arnd@arndb.de, dave.dice@oracle.com, jglauber@marvell.com, x86@kernel.org, will.deacon@arm.com, linux@armlinux.org.uk, steven.sistare@oracle.com, linux-kernel@vger.kernel.org, rahul.x.yadav@oracle.com, mingo@redhat.com, bp@alien8.de, hpa@zytor.com, longman@redhat.com, tglx@linutronix.de, daniel.m.jordan@oracle.com, linux-arm-kernel@lists.infradead.org List-Id: linux-arch.vger.kernel.org T24gVHVlLCBKdWwgMTYsIDIwMTkgYXQgMDg6NDc6MjRQTSArMDIwMCwgUGV0ZXIgWmlqbHN0cmEg d3JvdGU6Cj4gT24gVHVlLCBKdWwgMTYsIDIwMTkgYXQgMDE6MTk6MTZQTSAtMDQwMCwgQWxleCBL b2dhbiB3cm90ZToKPiA+ID4gT24gSnVsIDE2LCAyMDE5LCBhdCAxMTo1MCBBTSwgUGV0ZXIgWmlq bHN0cmEgPHBldGVyekBpbmZyYWRlYWQub3JnPiB3cm90ZToKPiAKPiA+ID4gc3RhdGljIHZvaWQg Y25hX21vdmUoc3RydWN0IGNuYV9ub2RlICpjbiwgc3RydWN0IGNuYV9ub2RlICpjbmkpCj4gPiA+ IHsKPiA+ID4gCXN0cnVjdCBjbmFfbm9kZSAqaGVhZCwgKnRhaWw7Cj4gPiA+IAo+ID4gPiAJLyog cmVtb3ZlIEBjbmkgKi8KPiA+ID4gCVdSSVRFX09OQ0UoY24tPm1jcy5uZXh0LCBjbmktPm1jcy5u ZXh0KTsKPiA+ID4gCj4gPiA+IAkvKiBzdGljayBAY25pIG9uIHRoZSAnb3RoZXInIGxpc3QgdGFp bCAqLwo+ID4gPiAJY25pLT5tY3MubmV4dCA9IE5VTEw7Cj4gPiA+IAo+ID4gPiAJaWYgKGNuLT5t Y3MubG9ja2VkIDw9IDEpIHsKPiA+ID4gCQkvKiBoZWFkID0gdGFpbCA9IGNuaSAqLwo+ID4gPiAJ CWhlYWQgPSBjbmk7Cj4gPiA+IAkJaGVhZC0+dGFpbCA9IGNuaTsKPiA+ID4gCQljbi0+bWNzLmxv Y2tlZCA9IGhlYWQtPmVuY29kZWRfdGFpbDsKPiA+ID4gCX0gZWxzZSB7Cj4gPiA+IAkJLyogYWRk IHRvIHRhaWwgKi8KPiA+ID4gCQloZWFkID0gKHN0cnVjdCBjbmFfbm9kZSAqKWRlY29kZV90YWls KGNuLT5tY3MubG9ja2VkKTsKPiA+ID4gCQl0YWlsID0gdGFpbC0+dGFpbDsKPiA+ID4gCQl0YWls LT5uZXh0ID0gY25pOwo+ID4gPiAJfQo+ID4gPiB9Cj4gPiA+IAo+ID4gPiBzdGF0aWMgc3RydWN0 IGNuYV9ub2RlICpjbmFfZmluZF9uZXh0KHN0cnVjdCBtY3Nfc3BpbmxvY2sgKm5vZGUpCj4gPiA+ IHsKPiA+ID4gCXN0cnVjdCBjbmFfbm9kZSAqY25pLCAqY24gPSAoc3RydWN0IGNuYV9ub2RlICop bm9kZTsKPiA+ID4gCj4gPiA+IAl3aGlsZSAoKGNuaSA9IChzdHJ1Y3QgY25hX25vZGUgKilSRUFE X09OQ0UoY24tPm1jcy5uZXh0KSkpIHsKPiA+ID4gCQlpZiAobGlrZWx5KGNuaS0+bm9kZSA9PSBj bi0+bm9kZSkpCj4gPiA+IAkJCWJyZWFrOwo+ID4gPiAKPiA+ID4gCQljbmFfbW92ZShjbiwgY25p KTsKPiA+ID4gCX0KPiA+ID4gCj4gPiA+IAlyZXR1cm4gY25pOwo+ID4gPiB9Cj4gPiBCdXQgdGhl biB5b3UgbW92ZSBub2RlcyBmcm9tIHRoZSBtYWluIGxpc3QgdG8gdGhlIOKAmG90aGVy4oCZIGxp c3Qgb25lLWJ5LW9uZS4KPiA+IEnigJltIGFmcmFpZCB0aGlzIHdvdWxkIGJlIHVubmVjZXNzYXJ5 IGV4cGVuc2l2ZS4KPiA+IFBsdXMsIGFsbCB0aGlzIGV4dHJhIHdvcmsgaXMgd2FzdGVkIGlmIHlv dSBkbyBub3QgZmluZCBhIHRocmVhZCBvbiB0aGUgc2FtZSAKPiA+IE5VTUEgbm9kZSAoeW91IG1v dmUgZXZlcnlvbmUgdG8gdGhlIOKAmG90aGVy4oCZIGxpc3Qgb25seSB0byBtb3ZlIHRoZW0gYmFj ayBpbiAKPiA+IGNuYV9tY3NfcGFzc19sb2NrKCkpLgo+IAo+IE15IHByaW1hcnkgY29uY2VybiB3 YXMgcmVhZGFiaWxpdHk7IEkgZmluZCB0aGUgYWJvdmUgc3VnZ2VzdGlvbiBtdWNoCj4gbW9yZSBy ZWFkYWJsZS4gTWF5YmUgaXQgY2FuIGJlIHdyaXR0ZW4gZGlmZmVyZW50bHk7IHlvdSdsbCBoYXZl IHRvIHBsYXkKPiBhcm91bmQgYSBiaXQuCgpzdGF0aWMgdm9pZCBjbmFfc3BsaWNlX3RhaWwoc3Ry dWN0IGNuYV9ub2RlICpjbiwgc3RydWN0IGNuYV9ub2RlICpoZWFkLCBzdHJ1Y3QgY25hX25vZGUg KnRhaWwpCnsKCXN0cnVjdCBjbmFfbm9kZSAqbGlzdDsKCgkvKiByZW1vdmUgW2hlYWQsdGFpbF0g Ki8KCVdSSVRFX09OQ0UoY24tPm1jcy5uZXh0LCB0YWlsLT5tY3MubmV4dCk7Cgl0YWlsLT5tY3Mu bmV4dCA9IE5VTEw7CgoJLyogc3RpY2sgW2hlYWQsdGFpbF0gb24gdGhlIHNlY29uZGFyeSBsaXN0 IHRhaWwgKi8KCWlmIChjbi0+bWNzLmxvY2tlZCA8PSAxKSB7CgkJLyogY3JlYXRlIHNlY29uZGFy eSBsaXN0ICovCgkJaGVhZC0+dGFpbCA9IHRhaWw7CgkJY24tPm1jcy5sb2NrZWQgPSBoZWFkLT5l bmNvZGVkX3RhaWw7Cgl9IGVsc2UgewoJCS8qIGFkZCB0byB0YWlsICovCgkJbGlzdCA9IChzdHJ1 Y3QgY25hX25vZGUgKilkZWNvZGVfdGFpbChjbi0+bWNzLmxvY2tlZCk7CgkJbGlzdC0+dGFpbC0+ bmV4dCA9IGhlYWQ7CgkJbGlzdC0+dGFpbCA9IHRhaWw7Cgl9Cn0KCnN0YXRpYyBzdHJ1Y3QgY25h X25vZGUgKmNuYV9maW5kX25leHQoc3RydWN0IG1jc19zcGlubG9jayAqbm9kZSkKewoJc3RydWN0 IGNuYV9ub2RlICpjbmksICpjbiA9IChzdHJ1Y3QgY25hX25vZGUgKilub2RlOwoJc3RydWN0IGNu YV9ub2RlICpoZWFkLCAqdGFpbCA9IE5VTEw7CgoJLyogZmluZCBhbnkgbmV4dCBsb2NrIGZyb20g J291cicgbm9kZSAqLwoJZm9yIChoZWFkID0gY25pID0gKHN0cnVjdCBjbmFfbm9kZSAqKVJFQURf T05DRShjbi0+bWNzLm5leHQpOwoJICAgICBjbmkgJiYgY25pLT5ub2RlICE9IGNuLT5ub2RlOwoJ ICAgICB0YWlsID0gY25pLCBjbmkgPSAoc3RydWN0IGNuYV9ub2RlICopUkVBRF9PTkNFKGNuaS0+ bWNzLm5leHQpKQoJCTsKCgkvKiB3aGVuIGZvdW5kLCBzcGxpY2UgYW55IHNraXBwZWQgbG9ja3Mg b250byB0aGUgc2Vjb25kYXJ5IGxpc3QgKi8KCWlmIChjbmkgJiYgdGFpbCkKCQljbmFfc3BsaWNl X3RhaWwoY24sIGhlYWQsIHRhaWwpOwoKCXJldHVybiBjbmk7Cn0KCkhvdydzIHRoYXQ/CgpfX19f X19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fXwpsaW51eC1hcm0ta2Vy bmVsIG1haWxpbmcgbGlzdApsaW51eC1hcm0ta2VybmVsQGxpc3RzLmluZnJhZGVhZC5vcmcKaHR0 cDovL2xpc3RzLmluZnJhZGVhZC5vcmcvbWFpbG1hbi9saXN0aW5mby9saW51eC1hcm0ta2VybmVs Cg== From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from bombadil.infradead.org ([198.137.202.133]:45592 "EHLO bombadil.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1726336AbfGQIkB (ORCPT ); Wed, 17 Jul 2019 04:40:01 -0400 Date: Wed, 17 Jul 2019 10:39:44 +0200 From: Peter Zijlstra Subject: Re: [PATCH v3 3/5] locking/qspinlock: Introduce CNA into the slow path of qspinlock Message-ID: <20190717083944.GR3463@hirez.programming.kicks-ass.net> References: <20190715192536.104548-1-alex.kogan@oracle.com> <20190715192536.104548-4-alex.kogan@oracle.com> <20190716155022.GR3419@hirez.programming.kicks-ass.net> <193BBB31-F376-451F-BDE1-D4807140EB51@oracle.com> <20190716184724.GH3402@hirez.programming.kicks-ass.net> MIME-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Disposition: inline Content-Transfer-Encoding: 8bit In-Reply-To: <20190716184724.GH3402@hirez.programming.kicks-ass.net> Sender: linux-arch-owner@vger.kernel.org List-ID: To: Alex Kogan Cc: linux@armlinux.org.uk, mingo@redhat.com, will.deacon@arm.com, arnd@arndb.de, longman@redhat.com, linux-arch@vger.kernel.org, linux-arm-kernel@lists.infradead.org, linux-kernel@vger.kernel.org, tglx@linutronix.de, bp@alien8.de, hpa@zytor.com, x86@kernel.org, guohanjun@huawei.com, jglauber@marvell.com, steven.sistare@oracle.com, daniel.m.jordan@oracle.com, dave.dice@oracle.com, rahul.x.yadav@oracle.com Message-ID: <20190717083944.Wz5ay_-C0vdad2IXxcswMitjF1Jdvt4WUOg40swUuP4@z> On Tue, Jul 16, 2019 at 08:47:24PM +0200, Peter Zijlstra wrote: > On Tue, Jul 16, 2019 at 01:19:16PM -0400, Alex Kogan wrote: > > > On Jul 16, 2019, at 11:50 AM, Peter Zijlstra wrote: > > > > static void cna_move(struct cna_node *cn, struct cna_node *cni) > > > { > > > struct cna_node *head, *tail; > > > > > > /* remove @cni */ > > > WRITE_ONCE(cn->mcs.next, cni->mcs.next); > > > > > > /* stick @cni on the 'other' list tail */ > > > cni->mcs.next = NULL; > > > > > > if (cn->mcs.locked <= 1) { > > > /* head = tail = cni */ > > > head = cni; > > > head->tail = cni; > > > cn->mcs.locked = head->encoded_tail; > > > } else { > > > /* add to tail */ > > > head = (struct cna_node *)decode_tail(cn->mcs.locked); > > > tail = tail->tail; > > > tail->next = cni; > > > } > > > } > > > > > > static struct cna_node *cna_find_next(struct mcs_spinlock *node) > > > { > > > struct cna_node *cni, *cn = (struct cna_node *)node; > > > > > > while ((cni = (struct cna_node *)READ_ONCE(cn->mcs.next))) { > > > if (likely(cni->node == cn->node)) > > > break; > > > > > > cna_move(cn, cni); > > > } > > > > > > return cni; > > > } > > But then you move nodes from the main list to the ‘other’ list one-by-one. > > I’m afraid this would be unnecessary expensive. > > Plus, all this extra work is wasted if you do not find a thread on the same > > NUMA node (you move everyone to the ‘other’ list only to move them back in > > cna_mcs_pass_lock()). > > My primary concern was readability; I find the above suggestion much > more readable. Maybe it can be written differently; you'll have to play > around a bit. static void cna_splice_tail(struct cna_node *cn, struct cna_node *head, struct cna_node *tail) { struct cna_node *list; /* remove [head,tail] */ WRITE_ONCE(cn->mcs.next, tail->mcs.next); tail->mcs.next = NULL; /* stick [head,tail] on the secondary list tail */ if (cn->mcs.locked <= 1) { /* create secondary list */ head->tail = tail; cn->mcs.locked = head->encoded_tail; } else { /* add to tail */ list = (struct cna_node *)decode_tail(cn->mcs.locked); list->tail->next = head; list->tail = tail; } } static struct cna_node *cna_find_next(struct mcs_spinlock *node) { struct cna_node *cni, *cn = (struct cna_node *)node; struct cna_node *head, *tail = NULL; /* find any next lock from 'our' node */ for (head = cni = (struct cna_node *)READ_ONCE(cn->mcs.next); cni && cni->node != cn->node; tail = cni, cni = (struct cna_node *)READ_ONCE(cni->mcs.next)) ; /* when found, splice any skipped locks onto the secondary list */ if (cni && tail) cna_splice_tail(cn, head, tail); return cni; } How's that?