Message-ID: <9485dc39-ab09-b929-9f22-ebc6a5b01a43@intel.com>
Date:   Wed, 22 Feb 2023 15:59:24 -0800
MIME-Version: 1.0
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:102.0) Gecko/20100101
 Thunderbird/102.7.1
Subject: Re: [PATCH v2 4/7] platform/x86/intel/ifs: Implement Array BIST test
Content-Language: en-US
To:     "Joseph, Jithu" <jithu.joseph@intel.com>, hdegoede@redhat.com,
        markgross@kernel.org
Cc:     tglx@linutronix.de, mingo@redhat.com, bp@alien8.de,
        dave.hansen@linux.intel.com, x86@kernel.org, hpa@zytor.com,
        gregkh@linuxfoundation.org, rostedt@goodmis.org,
        ashok.raj@intel.com, tony.luck@intel.com,
        linux-kernel@vger.kernel.org, platform-driver-x86@vger.kernel.org,
        patches@lists.linux.dev, ravi.v.shankar@intel.com,
        thiago.macieira@intel.com, athenas.jimenez.gonzalez@intel.com,
        sohil.mehta@intel.com
References: <20230131234302.3997223-1-jithu.joseph@intel.com>
 <20230214234426.344960-1-jithu.joseph@intel.com>
 <20230214234426.344960-5-jithu.joseph@intel.com>
 <a24c65f8-978d-8968-7874-6b83e14b01ba@intel.com>
 <d9d18954-8434-4c85-88b8-8e1d99cd6a4b@intel.com>
 <dd501d6a-e7e9-be82-24fb-33b18fb6192b@intel.com>
 <b67d2125-4075-4eac-4cad-8e315b866144@intel.com>
 <5d57f42a-1bfc-5e6a-bb49-556ecb7402af@intel.com>
 <9c55a34b-c17e-2a62-9989-902ce940dde5@intel.com>
 <42ac85ea-0ffe-55fc-57c2-6f4555e8dc5b@intel.com>
 <8fb5ebbf-d468-169d-5603-b267e7b42516@intel.com>
 <82a6f9b2-bb17-babd-fbe0-c4a5bec1203b@intel.com>
From:   Dave Hansen <dave.hansen@intel.com>
In-Reply-To: <82a6f9b2-bb17-babd-fbe0-c4a5bec1203b@intel.com>
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 7bit
Precedence: bulk

On 2/22/23 15:32, Joseph, Jithu wrote:
> On 2/22/2023 2:28 PM, Dave Hansen wrote:
>> On 2/22/23 14:07, Joseph, Jithu wrote:
>>> Since the trace has to be explicitly enabled (I thought it is okay to
>>> add a more convenient custom one only to be enabled for detailed
>>> analysis when required).
>> 	man perf-script
>>
>> You should be able to write one to do exactly what you need in about 10
>> minutes.  No new tracepoints, no new kernel code to maintain.  Knock
> Thanks for the pointers. I gather that user level tools might be able to format the
> msr trace output in a more convenient way (perhaps as generated by the custom driver trace)
> 
> There is still the other convenience of not having to look-up the
> MSRs addresses corresponding to all the individual tests and setting the filter on them to
> analyze IFS test activity (rather than enabling it via echo 1 > /sys/kernel/debug/tracing/events/intel_ifs/enable)

Jithu, the perf-script tooling that I suggested wraps can abstract away
the sysfs interface.  I suspect you might also have discovered this in
the process of exploring my (and others') suggestions.

Please go invest some time there.  Feel free to come back to this thread
if you get stuck or have done your due diligence exhausted the
userspace-only path.