From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1763786AbcALRuH (ORCPT ); Tue, 12 Jan 2016 12:50:07 -0500 Received: from mail-db3on0068.outbound.protection.outlook.com ([157.55.234.68]:60672 "EHLO emea01-db3-obe.outbound.protection.outlook.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1763763AbcALRuC (ORCPT ); Tue, 12 Jan 2016 12:50:02 -0500 Authentication-Results: spf=none (sender IP is ) smtp.mailfrom=cmetcalf@ezchip.com; Subject: Re: [PATCH v9 00/13] support "task_isolation" mode for nohz_full To: Will Deacon References: <1451936091-29247-1-git-send-email-cmetcalf@ezchip.com> <56941B86.9090009@ezchip.com> <20160112100708.GA15737@arm.com> CC: Gilad Ben Yossef , Steven Rostedt , Ingo Molnar , Peter Zijlstra , Andrew Morton , Rik van Riel , Tejun Heo , Frederic Weisbecker , Thomas Gleixner , "Paul E. McKenney" , Christoph Lameter , Viresh Kumar , Catalin Marinas , Andy Lutomirski , Daniel Lezcano , , , , Mark Rutland From: Chris Metcalf Message-ID: <56953CBA.9090208@ezchip.com> Date: Tue, 12 Jan 2016 12:49:46 -0500 User-Agent: Mozilla/5.0 (X11; Linux i686 on x86_64; rv:38.0) Gecko/20100101 Thunderbird/38.5.1 MIME-Version: 1.0 In-Reply-To: <20160112100708.GA15737@arm.com> Content-Type: text/plain; charset="windows-1252"; format=flowed Content-Transfer-Encoding: 7bit X-Originating-IP: [12.216.194.146] X-ClientProxiedBy: BLUPR07CA0098.namprd07.prod.outlook.com (2a01:111:e400:841::41) To AM3PR02MB113.eurprd02.prod.outlook.com (2a01:111:e400:8807::12) X-Microsoft-Exchange-Diagnostics: 1;AM3PR02MB113;2:GjPlNNP6chVZk0/E8/HKkElSkhkk7UXtxzburYPH35cnljtS5FqOuwy0BlQ67wasIjxfSfGB7vwNpT7oYue9lObvZirbnZCcGgt2wSY9iouYE5zWEwCW4qhN/VpZJU2Yj5f4Z46slUqgzJEUP+eLMg==;3:VJnQEo5Tf+2VK95aOymv8MUrFXRWPShPZQbeaqYWxRQ2Q3hQoIFANXwsaIKJ2b38yNCGGdQTNQ1G6F9ig2nz5IknYlSBcBjOsM5nFpwvNVcD9yv0760W/1Q0b8ClxI5U;25:rbEQR4e3DvmeLLH0mo94ey999WcJaP4C5vlRsN+7mxa5msT7K2eOCzBqaOlbJhuQ/V1vGhkEl9hjiChgTuk/HgyJA+AU7E/S1QIFYJlwb5ut68Qf86RaEdcpEilO5tyN5p0E1Yv7u8v4zy2xiCxtfeyrcXNZQ6gOFUyAAgdZMECm+OsTja7+iAXTyOwOr/qqEhgRmoXm4uztdWjssRDxkGzNpG3vL/V04lW6n/UJOM2mNk4N2wqQ/GsR/uoLuSmb;20:V4XN3nv5GrXYIraZlh/GhLcNMQvF8bEIl8/OVP6epArVL5U4Ekhs75GPgmk456YIQ1dzf6gaFo7OOXn1gFxcGZVjGszeQISjiih2UhhY7F5OoHt553UsN4nNBHAwYYePCQv7jDju+Bb1THcd4SNt0coQ75QzBBe1IfyODNxqj4E= X-Microsoft-Antispam: UriScan:;BCL:0;PCL:0;RULEID:;SRVR:AM3PR02MB113; X-MS-Office365-Filtering-Correlation-Id: 817778e6-4905-420c-df9b-08d31b78c9f3 X-Microsoft-Antispam-PRVS: X-Exchange-Antispam-Report-Test: UriScan:(121898900299872); X-Exchange-Antispam-Report-CFA-Test: BCL:0;PCL:0;RULEID:(601004)(2401047)(8121501046)(520078)(5005006)(10201501046)(3002001);SRVR:AM3PR02MB113;BCL:0;PCL:0;RULEID:;SRVR:AM3PR02MB113; X-Microsoft-Exchange-Diagnostics: 1;AM3PR02MB113;4:o3/rr3BcqgZcX/Dnc0yKX1FWSbe0QXJXDiH9c1VUTSUjCIbxv9PlKVCmtmcSxrxoZ+r8wc/VR10aEKoXH30cBZr4UtKjgh9wp2lv32ESa+E6PMq+rlm8GizCIxVek5S2jjr0pPOS6aEy1ft+dbiUHoIdJV7Uv/78L/IQJhHrr89B5csBd4SKkKnIsA0lbbwimDMy1oPmAZ4f0+EneGohfPEGUurjYSj3+O5bOLKWq7cyHkMbZldRZzP5P3OdbmNFZXEWlvMjcAW+Cxcn2iw7+Lb2Z+CemRBvzZloJhmbmJBBZZ2/gNHHrnN2n/jY674Vj3YbUBGBU65pq7SGuS0IHrRsM4UDO2+w0H4yU5DAO/FD06gQ+4X3+ZclH4TzVQS4/vAGkhK5RnuvGUHCZFTmrlt+J3xxvdDAzjaMJHmP2ug/ufcpSgVLrCfGH/hQgyBg X-Forefront-PRVS: 081904387B X-Forefront-Antispam-Report: SFV:NSPM;SFS:(10009020)(6049001)(6009001)(24454002)(479174004)(199003)(377454003)(189002)(5004730100002)(586003)(80316001)(65816999)(101416001)(106356001)(110136002)(189998001)(86362001)(5001960100002)(97736004)(4326007)(105586002)(87266999)(33656002)(23746002)(76176999)(99136001)(81156007)(4001350100001)(66066001)(122386002)(50986999)(40100003)(230700001)(6116002)(87976001)(1096002)(42186005)(92566002)(65806001)(36756003)(15975445007)(83506001)(47776003)(2950100001)(59896002)(64126003)(19580395003)(3846002)(54356999)(77096005)(50466002)(2906002)(5008740100001)(65956001)(18886065003);DIR:OUT;SFP:1101;SCL:1;SRVR:AM3PR02MB113;H:[10.7.0.41];FPR:;SPF:None;PTR:InfoNoRecords;A:1;MX:1;LANG:en; X-Microsoft-Exchange-Diagnostics: =?Windows-1252?Q?1;AM3PR02MB113;23:uQHElJUk4Ha9h2fgzWAEKJh+P4Q10AXCPvx21D?= =?Windows-1252?Q?QrmFn4T6ujmESlf/DqTV7IhfPLGuMW8J7OV2KcNqUDpZzCem2dKozMSV?= =?Windows-1252?Q?sQs5+0cAkQUtQMz6ntltWSv+tRzxCOXm1WLeNsKEhUzPCjdiWJsJJYvg?= =?Windows-1252?Q?5hIv6k1Q43usl1KHAUi1EzTF5xSSP8xuqQ8ipocp99yHxtofmlMUivSn?= =?Windows-1252?Q?LVwHuEoZl6O0NmCJhZKSaFc8ci8adh2qBUU1NRnYe4oYkOt1K4pE7V+A?= =?Windows-1252?Q?tPXiMoMFljgmFxaxKmklci05w6jCj4YGingyyp/5jiDwDgHvKJoHBsfF?= =?Windows-1252?Q?2xWpUb5tKnIz4peuvDO2WStUozJ+55DI3PPQdGEibyq6WhTqP+EPFPSe?= =?Windows-1252?Q?HnWx7safRmjDpSRenW/PDRTfPtjkxtGktsTOY7bXc56f5zAday+QT6Rl?= =?Windows-1252?Q?T/WawGcu9LoUyx9VvlQJyVqVT3tuarm09UCh1jTcwwtDeG5Mv5BnaiZ8?= =?Windows-1252?Q?wd0UZ69sdm/I6EYptQC5c8+XUrHpUQNaHlfq6Wnz6xOggIhlKjm+mCbs?= =?Windows-1252?Q?e2NbF0GC60ssjyO+5mmL9qa3TeM5GrPih+IO9J+nbIlL76ltADAVs6YY?= =?Windows-1252?Q?knlULEwShFbh5V3trnFig/Lu6R/rGtbG1Lda4R2fyV5Izf2qQLSr1gqq?= =?Windows-1252?Q?pF5SOzMQ5nT4MzUwkAfZJEBIifsy0i5p8bNeCg7ubPcMJ9ZZqcfUhnU+?= =?Windows-1252?Q?m0ge65Pgk3/rAATxshIfaAs/OlbcFjY7Ivk7t1YXHBpp8ecIL9+jAtJC?= =?Windows-1252?Q?YVgNMSIOSxWjqwiLTidPoRhWOl1NxJEyVri1GSNu6/QiMEjenXefIiZ+?= =?Windows-1252?Q?gZRxcjCCC9LXKwfQIP3Ei+U7rAQPqTxA5TH/3RN7Lqgg5W/shtLegmDT?= =?Windows-1252?Q?jyEGFVb2ZlQphnzsGHJmgR+j7IbTs669NiT5OKELAULNtYI66fR4dW3u?= =?Windows-1252?Q?fmqZF2x3IB6iVUvofTOSmZ3asChuu9MH/jDPxKb4KVrovdjAAfftnQ/o?= =?Windows-1252?Q?bmss0wj18guCUsfmKsX+JyygW56iMw6q5kQm7nU1e3SLGV+bOLdHIFgq?= =?Windows-1252?Q?EShtrBwk44L29KoC7tL7sMkx9cpkjh0ufZZemp8cPpetZAIs9YUddk1T?= =?Windows-1252?Q?7aKUiCvweh02PVFGsN5c61dlxKPKKNsko86rs/39FVjymXsnyKh3TZe9?= =?Windows-1252?Q?0nDOAtcuEUJw/pONiJxqG4pdhQgq2r8cF0khvlBfTok1ZRG1R/T8sOLA?= =?Windows-1252?Q?bSBdDxG02yO6ISiXEkWeP/Jh/XzizHaX+dq6KZj7LmNQ7+5cEfZWmAF8?= =?Windows-1252?Q?FYzJpGxaZLxkFBeqzQ7pOHKkKHA0MD/JmlfmJjUbE9B3coh4cb9RvFZ5?= =?Windows-1252?Q?K3kfUHk9gjFkSYMbvSotok5rnckz7f1ntxksHK5klTaxKoTNV50n3mcr?= =?Windows-1252?Q?/RY9I=3D?= X-Microsoft-Exchange-Diagnostics: 1;AM3PR02MB113;5:pjY99TRELMp5MtHxhq6Y9B2bKadSdQM76+/PYllnSXOoWrbFlq5YVGQ+3VHCKEKy4GsoFyFEFsDcw7i98+h1u+YdcUVaJ/sNRxj12R/1v5kVlBzgF+rycGhujREzQjqiyhrIVsgyDDkDKfM3o9jj4w==;24:/zty7CPuclByJE5IbhcvZJfF5z/7b2C9gnqDQDrFM7btjmTp4p5388yQITrtv+xBltg2S7hqr2A5bETBIbtGSHrrfGa+wH5fW7Yl5tK4hzs= SpamDiagnosticOutput: 1:23 SpamDiagnosticMetadata: NSPM X-OriginatorOrg: ezchip.com X-MS-Exchange-CrossTenant-OriginalArrivalTime: 12 Jan 2016 17:49:56.5604 (UTC) X-MS-Exchange-CrossTenant-FromEntityHeader: Hosted X-MS-Exchange-Transport-CrossTenantHeadersStamped: AM3PR02MB113 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org (Adding Mark to cc's) On 01/12/2016 05:07 AM, Will Deacon wrote: > On Mon, Jan 11, 2016 at 04:15:50PM -0500, Chris Metcalf wrote: >> Ping! There has been no substantive feedback to this version of >> the patch in the week since I posted it, which optimistically suggests >> to me that people may be satisfied with it. If that's true, Frederic, >> I assume this would be pulled into your tree? >> >> I have slightly updated the v9 patch series since this posting: >> >> [...] >> >> - Incorporated Mark Rutland's changes to convert arm64 >> assembly to C code instead of using my own version. > Please avoid queuing these patches -- the first is already in the arm64 > queue for 4.5 and the second was found to introduce a substantial > performance regression on the syscall entry/exit path. I think Mark had > an updated version to address that, so it would be easier not to have > an old version sitting in some other queue! I am not formally queueing them anywhere (like linux-next), though now that you mention it, that's a pretty good idea - I'll talk to Steven about that, assuming this merge window closes without the task isolation stuff going in. In the arch/tile code, we load the thread_info_flags and test them against a bitmask before we call into C code, to avoid the various overheads involved in the C path. Perhaps that same strategy is all that's needed for the arm64 code? Hopefully you can get that code merged up during the 4.5 window so I can use it as the new baseline for the task isolation stuff. Thanks! -- Chris Metcalf, EZChip Semiconductor http://www.ezchip.com From mboxrd@z Thu Jan 1 00:00:00 1970 From: Chris Metcalf Subject: Re: [PATCH v9 00/13] support "task_isolation" mode for nohz_full Date: Tue, 12 Jan 2016 12:49:46 -0500 Message-ID: <56953CBA.9090208@ezchip.com> References: <1451936091-29247-1-git-send-email-cmetcalf@ezchip.com> <56941B86.9090009@ezchip.com> <20160112100708.GA15737@arm.com> Mime-Version: 1.0 Content-Type: text/plain; charset="windows-1252"; format=flowed Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: <20160112100708.GA15737-5wv7dgnIgG8@public.gmane.org> Sender: linux-api-owner-u79uwXL29TY76Z2rM5mHXA@public.gmane.org To: Will Deacon Cc: Gilad Ben Yossef , Steven Rostedt , Ingo Molnar , Peter Zijlstra , Andrew Morton , Rik van Riel , Tejun Heo , Frederic Weisbecker , Thomas Gleixner , "Paul E. McKenney" , Christoph Lameter , Viresh Kumar , Catalin Marinas , Andy Lutomirski , Daniel Lezcano , linux-doc-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, linux-api-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, Mark Rutland List-Id: linux-api@vger.kernel.org (Adding Mark to cc's) On 01/12/2016 05:07 AM, Will Deacon wrote: > On Mon, Jan 11, 2016 at 04:15:50PM -0500, Chris Metcalf wrote: >> Ping! There has been no substantive feedback to this version of >> the patch in the week since I posted it, which optimistically suggests >> to me that people may be satisfied with it. If that's true, Frederic, >> I assume this would be pulled into your tree? >> >> I have slightly updated the v9 patch series since this posting: >> >> [...] >> >> - Incorporated Mark Rutland's changes to convert arm64 >> assembly to C code instead of using my own version. > Please avoid queuing these patches -- the first is already in the arm64 > queue for 4.5 and the second was found to introduce a substantial > performance regression on the syscall entry/exit path. I think Mark had > an updated version to address that, so it would be easier not to have > an old version sitting in some other queue! I am not formally queueing them anywhere (like linux-next), though now that you mention it, that's a pretty good idea - I'll talk to Steven about that, assuming this merge window closes without the task isolation stuff going in. In the arch/tile code, we load the thread_info_flags and test them against a bitmask before we call into C code, to avoid the various overheads involved in the C path. Perhaps that same strategy is all that's needed for the arm64 code? Hopefully you can get that code merged up during the 4.5 window so I can use it as the new baseline for the task isolation stuff. Thanks! -- Chris Metcalf, EZChip Semiconductor http://www.ezchip.com