Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::3:8 as permitted sender) client-ip=2620:137:e000::3:8;
Message-ID: <15bf097a-1863-ce32-cac7-d91df3c73215@amd.com>
Date:   Tue, 12 Dec 2023 09:48:50 +0530
User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:102.0) Gecko/20100101
 Thunderbird/102.10.0
Subject: Re: [PATCH 1/2] perf tool AMD: Use non-precise cycles as default
 event on certain Zen2 processors
Content-Language: en-US
To:     Namhyung Kim <namhyung@kernel.org>
Cc:     acme@kernel.org, kim.phillips@amd.com, peterz@infradead.org,
        mingo@redhat.com, mark.rutland@arm.com,
        alexander.shishkin@linux.intel.com, jolsa@kernel.org,
        irogers@google.com, adrian.hunter@intel.com,
        kan.liang@linux.intel.com, changbin.du@huawei.com,
        yangjihong1@huawei.com, zwisler@chromium.org,
        wangming01@loongson.cn, chenhuacai@kernel.org,
        kprateek.nayak@amd.com, linux-perf-users@vger.kernel.org,
        linux-kernel@vger.kernel.org, sandipan.das@amd.com,
        ananth.narayan@amd.com, santosh.shukla@amd.com,
        Ravi Bangoria <ravi.bangoria@amd.com>
References: <20231107083331.901-1-ravi.bangoria@amd.com>
 <CAM9d7cgs9Wk0OFoea4jOote-drHjvCimJyt7GWdO2Giw=d7Jog@mail.gmail.com>
 <f42bf6b7-75b8-124b-c79e-ad7a9b706990@amd.com>
 <CAM9d7cijrZzp=5m+BcQ77WFOSHT7e5vO-RCUTUp5Pevmz2wbtg@mail.gmail.com>
 <53374e41-d1e0-aa8f-d001-5e89783b962c@amd.com>
 <CAM9d7cgNsXVpFDsUt01TwxF3B=7G9TWZWoNU2dP_RGtQdQAJPQ@mail.gmail.com>
From:   Ravi Bangoria <ravi.bangoria@amd.com>
In-Reply-To: <CAM9d7cgNsXVpFDsUt01TwxF3B=7G9TWZWoNU2dP_RGtQdQAJPQ@mail.gmail.com>
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 7bit
MIME-Version: 1.0
X-MS-Exchange-AntiSpam-MessageData-ChunkCount: 1
X-MS-Exchange-AntiSpam-MessageData-0: =?utf-8?B?cGVuQTlXMngzbzhSQnd6QWdWdDhBZ2pSbXpXeFE0ZXdLRzFkM2hNdTJjS0hv?=
 =?utf-8?B?TmkxUkpLbytxTXVNR1BDbkFpT095c1RrRU9NSnZqVXcvallHdVpndEZ3dVh6?=
 =?utf-8?B?OTVTU3dIWVRWek1pVEMxb1E2VTJ6YVF5SDVQVXFVLzhzcGNmdUZwZjZTeHdO?=
 =?utf-8?B?bExLaW9BWmtiY0VMbER1VmtSb0VxcGg2Nkh1RWNwVmY2a1Q4NDA5M0xBS016?=
 =?utf-8?B?OG42d2dNNFBsaTczaVpSeUlEcGg3SlkxT1JFUVlVbFloNCtsbEptM2xBZElw?=
 =?utf-8?B?RmZLUU8yZ2l1eVAwMWpkMlpIMk9wTHBBYkZLd2lCRVVMWVVkeHNWTzVPb3Iv?=
 =?utf-8?B?b2ZrT1cxOWlJZm1OUzhJMVpCV0U4THlBOFEzRXJmV0lRbjJVZklQdVZSV3dw?=
 =?utf-8?B?UHdtaGJrMER6dnpxNFplQ09hUkxUMXJEbGsyT1RHNDNsTnFBRlY0QjA2andi?=
 =?utf-8?B?MGFaajVrMXZ5bFVDZXU2azUxdk5KeTVKTm1Lb3k3MGNISG5qcW4zeG0wV2ll?=
 =?utf-8?B?dmV6RTlYWW42d0xaa214aEwrUmhTL2kwY1ZoVVBFaU5XVDlXTlUvYXlNZE4z?=
 =?utf-8?B?ZUdBMm5GdWRGOVJkTVJBbXRvQzNsaHFVN3hUdVdQZGE3Yy91aitpbkhXUFRX?=
 =?utf-8?B?aVF4cTEvbXd4dExKUThOVUhhWXg3U29ZSnd1WXNFbmM4dHl2WTJEMzRwOWNQ?=
 =?utf-8?B?bCtnR2tXWkk3d3FIVXJoOCtSLzlMZ1ExRXRrY3B2T3libFU5RmFxblcxbWVL?=
 =?utf-8?B?NWlRbFVKQ3hyNU82RVhPZnZVaXRaNWdIc2JMSmJpS1JoMjZmeU9HaDBzbzJE?=
 =?utf-8?B?bjhTbWh5M2hPeWgwMHFBdFRUZkg5K1BBbm1ZVUlpZVhEczAwUklPTDgzNUxu?=
 =?utf-8?B?T2pwei96eHVCYXRzMmhnZmlpcm1zdDB6ZE9qNVhhdzhhT3ZLcDdpK1pabkhD?=
 =?utf-8?B?Y01NRVdxYlNEMFZUY09uV0hpcFdCSUhmT0xucE11MFRET1BxT05wK0FDOGZB?=
 =?utf-8?B?STZMaThqczhXT0dxR3dyUWgvUDY2djBnTkdMeFlHdUtMYjUvbXBlVXZFcUV5?=
 =?utf-8?B?SWs4bFVJR0xMa2NhZ25iUCtlSDAxcXRybnJVNWNKa3VvdmQ4OXpMWGRod2Zq?=
 =?utf-8?B?QXlubE1QUlhGbGkwUjhVblZjdzQ1WFdObU51a09KN1YzSk81MzJ5MUsxRWg5?=
 =?utf-8?B?RkY3eHBlY1BjdEwzSHhReFhvZTRRdlJPREdzK1hvalppWjJCR0ptRGozSFoy?=
 =?utf-8?B?R21Qc0I3dkREME5pREt3YVhGeHFzVlFXUWVKK3lraWJtR09kQmtzWU9wSXht?=
 =?utf-8?B?WFZGdzZFL0hDNVp4YTRFQVI2eUdqUEtNSm1JUkhmTlVlRWF3QXprckVmcXRK?=
 =?utf-8?B?bkEwbXFHK3dWTGdSUjNOaHJTSkhyT2ZWZDU3aXVYejJxNFZHZVZ2Qk1jcksx?=
 =?utf-8?B?TUkrL1ZYU0s4UU9kNWE5TUhmS3ZieThGMURSSUFTQituaEd2UnZwdmdMZjI3?=
 =?utf-8?B?TWNYNWVHOXVnRmZsZUJGYmZqWGpmUU5HT3NNclR0SzI3Qm91TzVzZTkyeVk4?=
 =?utf-8?B?cDN3OXVpOXlmamVoTlZxYTB5RTJPK01hb3dCa1hkRm00dVJSUUhrTU5kbkw0?=
 =?utf-8?B?Q2NzN2cvRmswQU1zNE4rbXJsbEFaZ2VmdkUwcHA1NHVQY1JNTU5haVNjbnVw?=
 =?utf-8?B?QzNXWkVlZXo5MVg0SFFsVW9OQzJNeVFOclltaVlGNjYzbERyMkVMT1JUa2dn?=
 =?utf-8?B?YXZ3V0U5MURwQy8yZi9LWTRSamZGNjBOam9jbytQVXZGNExzNHJkT2Vmb1Vs?=
 =?utf-8?B?dzRGZFZOTTR3ZFNTbHBzRWtURUpEVndObjZiZUJBTlQ5SEl5TkJJUW1BLzl2?=
 =?utf-8?B?TlNpMlZiY0k2Rk9KRTNWMENvVWc3NkFlQTFsakZLUm5NUGdVVzRHdXZnUjhJ?=
 =?utf-8?B?dSt2end4VnFnZTVKYTE4U3NKeTN4UHM2SWROS0oyQXdWOU1mMDI4dXlSQklp?=
 =?utf-8?B?YzVPK3B6dUZIaGVJUDNFcGQzdjhBU0pxWWV0TUgyTUNoT1JoMStUVXgzWk9w?=
 =?utf-8?B?cVBVeVF3ak93clN4REhKMXY2ekgzUmRtalpVekluV2VGYXlvQ2xxcC9PRXNV?=
 =?utf-8?Q?sXYVoO4LLdDhAt05zr77w38QD?=
X-OriginatorOrg: amd.com
X-MS-Exchange-CrossTenant-Network-Message-Id: 6bf97bab-3b24-4cca-ce99-08dbfac977f0
X-MS-Exchange-CrossTenant-AuthSource: PH7PR12MB6588.namprd12.prod.outlook.com
X-MS-Exchange-CrossTenant-AuthAs: Internal
X-MS-Exchange-CrossTenant-OriginalArrivalTime: 12 Dec 2023 04:19:01.4075
 (UTC)
X-MS-Exchange-CrossTenant-FromEntityHeader: Hosted
X-MS-Exchange-CrossTenant-Id: 3dd8961f-e488-4e60-8e11-a82d994e183d
X-MS-Exchange-CrossTenant-MailboxType: HOSTED
X-MS-Exchange-CrossTenant-UserPrincipalName: CVT2rGy90xnjSQ9kodyQ5cnu9UMT+2yJRDtXR1XuiTE6WPbPAk/LN9Y1ys0XOWgJU5XVNuWIaWxTG4W7LjnW4w==
X-MS-Exchange-Transport-CrossTenantHeadersStamped: MW4PR12MB7438
X-Spam-Status: No, score=-3.4 required=5.0 tests=DKIMWL_WL_HIGH,DKIM_SIGNED,
	DKIM_VALID,DKIM_VALID_AU,HEADER_FROM_DIFFERENT_DOMAINS,
	MAILING_LIST_MULTI,NICE_REPLY_A,SPF_HELO_NONE,SPF_PASS,
	T_SCC_BODY_TEXT_LINE autolearn=unavailable autolearn_force=no
	version=3.4.6
X-Spam-Checker-Version: SpamAssassin 3.4.6 (2021-04-09) on fry.vger.email
Precedence: bulk
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org
X-Greylist: Sender passed SPF test, not delayed by milter-greylist-4.6.4 (fry.vger.email [0.0.0.0]); Mon, 11 Dec 2023 20:19:29 -0800 (PST)

>>>>>> By default, Perf uses precise cycles event when no explicit event is
>>>>>> specified by user. Precise cycles event is forwarded to ibs_op// pmu
>>>>>> on AMD. However, IBS has hw issue on certain Zen2 processors where
>>>>>> it might raise NMI without sample_valid bit set, which causes Unknown
>>>>>> NMI warnings. (Erratum #1215: IBS (Instruction Based Sampling) Counter
>>>>>> Valid Value May be Incorrect After Exit From Core C6 (CC6) State.) So,
>>>>>> use non-precise cycles as default event on affected processors.
>>>>>
>>>>> It seems like a kernel issue, do we have a kernel patch not to forward
>>>>> precise cycles or instructions events to IBS on the affected CPUs?
>>>>
>>>> I'm not sure how it's a kernel issue. User can use ibs_op// pmu directly
>>>> and might hit the hw bug.
>>>
>>> Sorry for the late reply.  I know it's the user's fault when using ibs_op//
>>> directly but I think the kernel should not forward cycles:pp to IBS.
>>
>> For all AMD zen uarchs, cycles:p is same as ibs_op// (man perf-list has
>> more detail). It's confusing if ibs_op// works but cycles:p fails on the
>> same machine.
> 
> Make sense.  Probably perf tools can provide a more detailed message
> about the situation.

+1

>> No strong opinion though. I can prepare a kernel patch, if you want.
> 
> I have a report that these unknown NMI messages caused some
> performance issues.  So maybe we need to be safe by not using
> IBS automatically.  I've also posted a patch to rate-limit the message
> itself.

Sure. Will prepare and post the patch.

Thanks,
Ravi