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 Received: from kanga.kvack.org (kanga.kvack.org [205.233.56.17]) by smtp.lore.kernel.org (Postfix) with ESMTP id 54B33E77188 for ; Tue, 24 Dec 2024 18:08:48 +0000 (UTC) Received: by kanga.kvack.org (Postfix) id 6AC396B0082; Tue, 24 Dec 2024 13:08:47 -0500 (EST) Received: by kanga.kvack.org (Postfix, from userid 40) id 65B596B0083; Tue, 24 Dec 2024 13:08:47 -0500 (EST) X-Delivered-To: int-list-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix, from userid 63042) id 4D49F6B0085; Tue, 24 Dec 2024 13:08:47 -0500 (EST) X-Delivered-To: linux-mm@kvack.org Received: from relay.hostedemail.com (smtprelay0014.hostedemail.com [216.40.44.14]) by kanga.kvack.org (Postfix) with ESMTP id 322FA6B0082 for ; Tue, 24 Dec 2024 13:08:47 -0500 (EST) Received: from smtpin19.hostedemail.com (a10.router.float.18 [10.200.18.1]) by unirelay03.hostedemail.com (Postfix) with ESMTP id 9FABDA184E for ; Tue, 24 Dec 2024 18:08:46 +0000 (UTC) X-FDA: 82930636404.19.34B6A0B Received: from CY4PR05CU001.outbound.protection.outlook.com (mail-westcentralusazolkn19010009.outbound.protection.outlook.com [52.103.7.9]) by imf30.hostedemail.com (Postfix) with ESMTP id 2EA508000D for ; Tue, 24 Dec 2024 18:07:27 +0000 (UTC) Authentication-Results: imf30.hostedemail.com; dkim=pass header.d=outlook.com header.s=selector1 header.b=CnT3JN+H; spf=pass (imf30.hostedemail.com: domain of mhklinux@outlook.com designates 52.103.7.9 as permitted sender) smtp.mailfrom=mhklinux@outlook.com; dmarc=pass (policy=none) header.from=outlook.com; arc=pass ("microsoft.com:s=arcselector10001:i=1") ARC-Message-Signature: i=2; a=rsa-sha256; c=relaxed/relaxed; d=hostedemail.com; s=arc-20220608; t=1735063705; h=from:from:sender:reply-to:subject:subject:date:date: message-id:message-id:to:to:cc:cc:mime-version:mime-version: content-type:content-type: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references:dkim-signature; bh=qS5V/VDV6WH9828Kxq0J9E956mO2Kc5XPk9uYzlTqE0=; b=U3dqvhw1YBmed6wN+2kgINOqIFdtx/5RcXBulMIKiq2AV4VnXo0kk2X+grJz0sAObO3tcu k4dsKCxCTkwasVIJg/T/6BImtDDYT37GUOzpT+p5hamG9aUulQS+szpoquF17wvpXnLFTd 7TnYHbWsK87LqIU4zZdabpsHxb1khBo= ARC-Seal: i=2; s=arc-20220608; d=hostedemail.com; t=1735063705; a=rsa-sha256; cv=pass; b=JcBZdzKo3M6dSRsm56JV6F1rPpcr55Ieee+LGvuwxc9bYGmvhWXD1DXVMTQmlw0pueJE4T C6D9wK+hPzJZ1BD+BV9JV2xEPZWfoRe3a0UmwJ1T0UZXyqbrfyl1UYasxkLr/mHRB60GA7 c0o4qTMj0/B5bqd0lNitA3jH9ljVpL0= ARC-Authentication-Results: i=2; imf30.hostedemail.com; dkim=pass header.d=outlook.com header.s=selector1 header.b=CnT3JN+H; spf=pass (imf30.hostedemail.com: domain of mhklinux@outlook.com designates 52.103.7.9 as permitted sender) smtp.mailfrom=mhklinux@outlook.com; dmarc=pass (policy=none) header.from=outlook.com; arc=pass ("microsoft.com:s=arcselector10001:i=1") ARC-Seal: i=1; a=rsa-sha256; s=arcselector10001; d=microsoft.com; cv=none; b=iMjxbdXyBaJeqF7cGIxTz61SSWnrzREWDBTnz1bWwig/1g/FAwvfOLRAlGLyRzk9g79J7Va151J8e2lg+D4fIHFIaKQh+hUgY/oUMoua3xe7UN6b3Iok5hQHp4iNmBBsUJsSvnqvviwQWVPHOHfp5WZjCmuatIAwtVep80/1kyg7vOS2kFQwQUesBWxSDYRYetYg0OeqFvPDSGN8ncU5nZK+URYOsTwstMq+BlFNCHjQsXJI5JS2K0L64polCZvmKo3M6jNkutsIJBtDwgP7X/vh8UIZWwbz0s/3qD3KCZ3qa0wDxyT2HFTke5+hkJP+dtqnWJq2k9vbiUl1s9Ubxg== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=microsoft.com; s=arcselector10001; h=From:Date:Subject:Message-ID:Content-Type:MIME-Version:X-MS-Exchange-AntiSpam-MessageData-ChunkCount:X-MS-Exchange-AntiSpam-MessageData-0:X-MS-Exchange-AntiSpam-MessageData-1; bh=qS5V/VDV6WH9828Kxq0J9E956mO2Kc5XPk9uYzlTqE0=; b=lYvSrKCbrjpMJZSigKp3MRfdXevoOMYcvYRo9WhPDIl+FdKX5z/1xeXI+YrZ217Rw22QIT+cXDLVQ7/3GH70bZobHj0D3PbuwsiUL3eHvu7KyzwgFIIyUNViTE7gQ4OnXUgk3KeXzpH8KrozqCwbz6PY3UFuk1rNFLdiruV0I3b9P/Qw+14h5F+PxSlgUKdyVVhQfGR5Nl8IeqOzKO2KGArwcj2SnFIqP9GYe0OVRVw/1JlRbx88Acq9OHp+NTYyECy2XA9v0KGi7UQlBbHuh1UV3TueeGLTolj7iI/+qR+iSvXm/yEOThUCFozFQIepcIHBRs2jvjJN1Lt2JzyGgQ== ARC-Authentication-Results: i=1; mx.microsoft.com 1; spf=none; dmarc=none; dkim=none; arc=none DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=outlook.com; s=selector1; h=From:Date:Subject:Message-ID:Content-Type:MIME-Version:X-MS-Exchange-SenderADCheck; bh=qS5V/VDV6WH9828Kxq0J9E956mO2Kc5XPk9uYzlTqE0=; b=CnT3JN+H+6kvf8jJm1fvcJmLjEbVQRKzwzOnSYeyA5KowlC09bKuwhBGM81ekKDUnlPC1jtiT37jkC2AYID0QzE2Ljc+yDt73MchD4Arf7iH4XySMJpkMMdzCSeBMAobPsBtfzgyj6BrsJo7or4ySmO7DM+y+rIR6wME26ZfIv7iULYBkMaEUpheOMq/rD+6UknYxgNtzKNv81QP8nqaXFjjtCQcT50VMl6le/6YNCKcRbfqorkLiDpCVjyB461yPxZOyUMAL1EJ0aXTEyZIaR+aCMOAu3G+m+8jkVH3Xa5NSyIJBok7EwfwQn7c7/gjxP5G8l/i1HIG2M2Boe+M+w== Received: from SN6PR02MB4157.namprd02.prod.outlook.com (2603:10b6:805:33::23) by CH3PR02MB9235.namprd02.prod.outlook.com (2603:10b6:610:152::7) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id 15.20.8272.19; Tue, 24 Dec 2024 18:08:40 +0000 Received: from SN6PR02MB4157.namprd02.prod.outlook.com ([fe80::cedd:1e64:8f61:b9df]) by SN6PR02MB4157.namprd02.prod.outlook.com ([fe80::cedd:1e64:8f61:b9df%4]) with mapi id 15.20.8272.013; Tue, 24 Dec 2024 18:08:40 +0000 From: Michael Kelley To: "riel@surriel.com" , "x86@kernel.org" CC: "linux-kernel@vger.kernel.org" , "kernel-team@meta.com" , "dave.hansen@linux.intel.com" , "luto@kernel.org" , "peterz@infradead.org" , "tglx@linutronix.de" , "mingo@redhat.com" , "bp@alien8.de" , "hpa@zytor.com" , "akpm@linux-foundation.org" , "linux-mm@kvack.org" Subject: RE: [RFC PATCH v2 00/11] AMD broadcast TLB invalidation Thread-Topic: [RFC PATCH v2 00/11] AMD broadcast TLB invalidation Thread-Index: AQHbVOep6LW4wp7fuEeWOqBFB6CLaLL1r0tg Date: Tue, 24 Dec 2024 18:08:40 +0000 Message-ID: References: <20241223025751.3268975-1-riel@surriel.com> In-Reply-To: <20241223025751.3268975-1-riel@surriel.com> Accept-Language: en-US Content-Language: en-US X-MS-Has-Attach: X-MS-TNEF-Correlator: x-ms-publictraffictype: Email x-ms-traffictypediagnostic: SN6PR02MB4157:EE_|CH3PR02MB9235:EE_ x-ms-office365-filtering-correlation-id: 7369fa66-6818-4df1-2034-08dd2445ff1f x-microsoft-antispam: BCL:0;ARA:14566002|461199028|8060799006|19110799003|15080799006|8062599003|1602099012|10035399004|102099032|3412199025|4302099013|440099028; x-microsoft-antispam-message-info: =?us-ascii?Q?+FjEcr/MBPqBlSJNspseIoC2lsBzdIxi3tX7o9rVgH+6BhHO1tvcby7egXTV?= =?us-ascii?Q?ToB5zLiVOZNRUHn71qIMYNqyU0dFEnzJxZi5S5rgcUpImf+U08hjuZEI0CbX?= =?us-ascii?Q?FrgQSJxtG5nVtNuWFCJLIHkdUNYtdiDEnEcRfxEFz8u4vJatQI6vmfwX3uj1?= =?us-ascii?Q?Gm6OtXsD0kYbqSw/zHk8npTxC7AewJblR2dgrGbB4wdO+POVQtGjfA1fIv1n?= =?us-ascii?Q?lno/Fq7Cwt+2Me7M/Fg0jPnniH7ar1npqOvWjKgB0Z5gzdK3BtPNynDbB5YX?= =?us-ascii?Q?RKo2YeAbyJH8b7U7APcCRmR4tbVaBo5XcVpdao2FmEdMyr/+ShlHf0Zs/Ukm?= =?us-ascii?Q?M965ct4qSthafSBIiY3emG21okPB4Ni5veli3vUAgcwPEgnTr2VXDAguAONI?= =?us-ascii?Q?89Q0zT/yGjToPEvQVdVLXii8IjtV3tZKKDjF5kaXmT42auPqqzSkutP4FvF/?= =?us-ascii?Q?LwMR2hqKiD/kffQGDswxwfY+Utssvl1yvJuEG79S3JpbVRFAUbZlSEOCTi17?= =?us-ascii?Q?92/nUud3bWjckSlz1tEvnICoa8CrL1qdwDmxkbZFfWyTtYzghXj8ZmfoqY1u?= =?us-ascii?Q?DvrXBGARJFUpyW5c0yLW4ShzPEgVipeG44n/e5dFJdA+swEuu24lKdNV39+w?= =?us-ascii?Q?QVvCvIVwV8uTq+g9IByXglRHN3EAyi9WWau7a3D3GljUPC+6D+/tyNoFS6v1?= =?us-ascii?Q?24fWvxwNZ8fxRDW4RXPibC7zvWI0I5BZELxCuFgFyyn/5kId93J2FfC7UXAB?= =?us-ascii?Q?njXTBPChLjU7lS31N/JX9spUbYXQmjqV1hy/cB+IsVbjPMLjxDtqa6UOyi+3?= =?us-ascii?Q?kbH0ImDNI5AXH3vF9gPWjEXGMdSg2oPEgQoU8gdSnHwaak+VAn+zbL/51ppw?= =?us-ascii?Q?QSooO/iM37qqytX4JYWgUCCay9wusnPzWd2h2fiYUnOhctwbory1VUSz0S2y?= =?us-ascii?Q?c9IufKCXL7gV+pvsfDPd+ll9FIFHW9CU+30hKXtmpJ3AYrtdPgygdkrz7A9T?= =?us-ascii?Q?woncIxNGiUtbODhEz5WWDItULSa1EdSNswCSoMvDo5eZFJpn7RRCQyYNMzIE?= =?us-ascii?Q?AoX1xY7mUxWzPhVAShfMRKUzliaqcwpTKBDWYR+dosCiBemTZgeeFZrd75r5?= =?us-ascii?Q?KZPjK5P2vX8CgTE2gvxQer3Thp+2djr3DllYJ+W9IsJ4Uss/tGzRQQ0=3D?= x-ms-exchange-antispam-messagedata-chunkcount: 1 x-ms-exchange-antispam-messagedata-0: =?us-ascii?Q?EKjVLdqYBMjRkPO4aAmIjMtnxXLBRmqeMTGQV5jnzAAbHY7AgxlPtCSrWBXO?= =?us-ascii?Q?BsjLpMoEMmql7rEYlAkywgvud/wIGRFrvC2tGSOEX1+xTpQOwSKI2kQ7hqQV?= =?us-ascii?Q?4y5FggItsC7TU8cVZtlQXFRHRDVTBR243mJwcrBOLYhG5//J4ItwsvFjoCaY?= =?us-ascii?Q?mFIWLTP0lyNrnBFu/HYlSxg/RyzTA0ojcozo/OoLU9qxAE3DkjMX7PzTZnzG?= =?us-ascii?Q?pK5NScebvcqzpBTWRqQs7tp43rJd7lyk+p4jCo/l1pktqDpx7a0Iz7X8MOkd?= =?us-ascii?Q?T11F33phNK2B01dYWH7DqXk1pGduNZxyjr0z6tkwhnFi4c++UKx9KRpbJvsw?= =?us-ascii?Q?1jkcOM8IBR9UOyplo+JCDs7Pla03M4MYOaUXH0lZlI5nf7GITvp4jv7jckqG?= =?us-ascii?Q?gZJ4SA6p8/AhTYOC1SnidMIwa3BUu2/t1Up+RqoXgbp7OEvH/Y7+OxzHU2XO?= =?us-ascii?Q?ZHYxB5HNQMeYhWbBM21bf+FPXLzSP4867wUBbzb/oaZSv8F0Uz7uA7sb7e1X?= =?us-ascii?Q?p5i5lrkbTQSG6lQTdVuZwPuIK8dJ2V54nGTarb/Vz+jJE5IRHJiBpuggF3vL?= =?us-ascii?Q?O3fQP5Pnb9Z8UEvq4SKM/ZIMu1AaiBuMszc4TmwBe7pFI6JVE2VAM+mMcluN?= =?us-ascii?Q?jsWDeY+HopqvlGDdDh/0+8yitbgHfq1i27EmsAUdXS53OsfsmTMv+Qp97nm6?= =?us-ascii?Q?z7YfknVnkd7jSNgAJo76+9W31ZLB64Hwg68NyIFl18poD/RkH2ARxPgfFWZ0?= =?us-ascii?Q?9ssKskrN9YB2JGw5Hms2grajGDEI+0QewcRzv1oUihoqYq0w0v3UOHR3FDxE?= =?us-ascii?Q?qhcY6yPqbVOSsB3kFvdFcmQ4bhMDGG9a9swBDptRQ+R7d/7g0yS68yCllr83?= =?us-ascii?Q?gXX9dRPvaHNuj2emksTP2u2b5uoiJ9M2V//mCmzz0XTC9gtSrw+piyjKja/X?= =?us-ascii?Q?kYMnlulL0N8UBdC7dOYwRPm44B+LvR0Im+WR12Z/5WJAksNm+yjAhKqHOaYk?= =?us-ascii?Q?soXmMYfgVsyZqcL1nVh049nG2hsciZ1NjMQ+qYQpb/2Fh7J/NPOC6Aw0EGW1?= =?us-ascii?Q?EHyb6Tr70kfsdIkQLi0azJVFqFoJZ5XS9/+HjOUQpGSLxd0fF3Czkhj2VbYo?= =?us-ascii?Q?JA8BK+4aJ+u5re1Zu8S9XbLF2/4n7n/o7zvh8qaTyan1Ory3jeEIPmTplCbb?= =?us-ascii?Q?a1/r/OL9+t/8zIZ+vaZlCXHKHFocRaece0LXprnhmX/GRUxJjU8nhwNlyFI?= =?us-ascii?Q?=3D?= Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 X-OriginatorOrg: outlook.com X-MS-Exchange-CrossTenant-AuthAs: Internal X-MS-Exchange-CrossTenant-AuthSource: SN6PR02MB4157.namprd02.prod.outlook.com X-MS-Exchange-CrossTenant-RMS-PersistedConsumerOrg: 00000000-0000-0000-0000-000000000000 X-MS-Exchange-CrossTenant-Network-Message-Id: 7369fa66-6818-4df1-2034-08dd2445ff1f X-MS-Exchange-CrossTenant-rms-persistedconsumerorg: 00000000-0000-0000-0000-000000000000 X-MS-Exchange-CrossTenant-originalarrivaltime: 24 Dec 2024 18:08:40.7473 (UTC) X-MS-Exchange-CrossTenant-fromentityheader: Hosted X-MS-Exchange-CrossTenant-id: 84df9e7f-e9f6-40af-b435-aaaaaaaaaaaa X-MS-Exchange-Transport-CrossTenantHeadersStamped: CH3PR02MB9235 X-Rspamd-Server: rspam10 X-Rspamd-Queue-Id: 2EA508000D X-Stat-Signature: gcfoyumh6kj63nhnda73u1ruye841xs6 X-Rspam-User: X-HE-Tag: 1735063647-921109 X-HE-Meta: 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 gRDbKjzp 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 X-Bogosity: Ham, tests=bogofilter, spamicity=0.000000, version=1.2.4 Sender: owner-linux-mm@kvack.org Precedence: bulk X-Loop: owner-majordomo@kvack.org List-ID: List-Subscribe: List-Unsubscribe: From: riel@surriel.com Sent: Sunday, December 22, 2024 6= :55 PM >=20 > Add support for broadcast TLB invalidation using AMD's INVLPGB instructio= n. > This allows the kernel to invalidate TLB entries on remote CPUs without > needing to send IPIs, without having to wait for remote CPUs to handle > those interrupts, and with less interruption to what was running on > those CPUs. >=20 > Because x86 PCID space is limited, and there are some very large > systems out there, broadcast TLB invalidation is only used for > processes that are active on 3 or more CPUs, with the threshold > being gradually increased the more the PCID space gets exhausted. Rik -- What is this patch set's expectation about INVLPGB and TLBSYNC availability and usage in a VM? I see that INVLPGB and TLBYSNC behavior in a VM is spec'ed in the AMD Programmer's Manual, but I wonder about their impact in a multi-tenant host like in a public cloud environment. And given what this patch set does in assigning global ASIDs, should X86_FEATURE_INVLPGB be disabled if running in a VM where the hypervisor for whatever reason has enabled INVLPGB/TLBSYNC in its VMs? My knowledge of the details here is pretty limited, so my question may just reflect my ignorance. But it would be good for the code comments and/or commit messages to include explicit statements about what is expected in a VM. Michael >=20 > Combined with the removal of unnecessary lru_add_drain calls > (see https://lkml.org/lkml/2024/12/19/1388) this results in a > nice performance boost for the will-it-scale tlb_flush2_threads > test on an AMD Milan system with 36 cores: >=20 > - vanilla kernel: 527k loops/second > - lru_add_drain removal: 731k loops/second > - only INVLPGB: 527k loops/second > - lru_add_drain + INVLPGB: 1157k loops/second >=20 > Profiling with only the INVLPGB changes showed while > TLB invalidation went down from 40% of the total CPU > time to only around 4% of CPU time, the contention > simply moved to the LRU lock. >=20 > Fixing both at the same time about doubles the > number of iterations per second from this case. >=20 > v2: > - Apply suggestions by Peter and Borislav (thank you!) > - Fix bug in arch_tlbbatch_flush, where we need to do both > the TLBSYNC, and flush the CPUs that are in the cpumask. > - Some updates to comments and changelogs based on questions. >=20