[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <22155f49-2f57-73b8-6e89-ddd8a127967b@linux.intel.com>
Date: Mon, 1 Oct 2018 09:25:42 +0300
From: Alexey Budankov <alexey.budankov@...ux.intel.com>
To: Jann Horn <jannh@...gle.com>
Cc: Andi Kleen <ak@...ux.intel.com>,
Mark Rutland <mark.rutland@....com>,
Thomas Gleixner <tglx@...utronix.de>, tursulin@...ulin.net,
kernel list <linux-kernel@...r.kernel.org>,
tvrtko.ursulin@...ux.intel.com,
Peter Zijlstra <peterz@...radead.org>,
the arch/x86 maintainers <x86@...nel.org>,
"H . Peter Anvin" <hpa@...or.com>, acme@...nel.org,
alexander.shishkin@...ux.intel.com, jolsa@...hat.com,
namhyung@...nel.org, maddy@...ux.vnet.ibm.com,
Kees Cook <keescook@...omium.org>
Subject: Re: [RFC 0/5] perf: Per PMU access controls (paranoid setting)
Hello Jann,
> On Fri, Sep 28, 2018 at 11:22:37PM +0200, Jann Horn wrote:
<SNIP>
>>
>> <blasphemy>
>> Is that true? IIRC if you want to use the perf tools after a kernel
>> update, you have to install a new version of perf anyway, no?
There are usages in production where perf_event_open() syscall
accompanied with read(), mmap() etc. is embedded into application
on per-thread basis and is used for self monitoring and dynamic
execution tuning.
There are also other Perf tools around that, for example, are
statically linked and then used as on Linux as on Android.
Backward compatibility does matter in these cases.
Thanks,
Alexey
Powered by blists - more mailing lists