linux-kernel - Re: [PATCH v8 1/3] perf: cavium: Support memory controller PMU counters

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <647e2941-d854-0341-3e6a-709a6c3db839@arm.com>
Date:   Mon, 7 Aug 2017 10:37:15 +0100
From:   Suzuki K Poulose <Suzuki.Poulose@....com>
To:     Jan Glauber <jan.glauber@...iumnetworks.com>,
        Borislav Petkov <bp@...en8.de>
Cc:     David Daney <ddaney.cavm@...il.com>,
        Greg KH <gregkh@...uxfoundation.org>,
        Mark Rutland <mark.rutland@....com>, linux-pci@...r.kernel.org,
        Will Deacon <will.deacon@....com>,
        "linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
        linux-arm-kernel@...ts.infradead.org
Subject: Re: [PATCH v8 1/3] perf: cavium: Support memory controller PMU
 counters

On 27/07/17 10:08, Jan Glauber wrote:
> On Thu, Jul 27, 2017 at 07:11:57AM +0200, Borislav Petkov wrote:
>> On Wed, Jul 26, 2017 at 02:02:42PM -0700, David Daney wrote:
>>> Also, if a given configuration disables CONFIG_EDAC there is some hackery
>>> needed to get the perf portion of the driver included.
>>
>> Yes, and we don't do performance counters in EDAC.
>>
>> So you could add a small memory controller driver which does the
>> arbitration or fix the firmware.
>
> OK. As fixing the firmware will take quite some time I'll go for the memory
> controller driver that starts EDAC / PMU depending on their CONFIG_.

Please could you also rename CAVIUM_PMU to something like CAVIUM_MMC_PMU or even
CAVIUM_UNCOR_PMU ? The symbol could easily be mistaken for a "cavium" CPU PMU.

Suzuki


>
> What would be the proper location for the multiplexer?
> drivers/soc/cavium or drivers/misc?
>
> --Jan
>