linux-kernel - Re: 'branches' perf event mapping differs on ARC and ARM

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] [day] [month] [year] [list]

Message-ID: <C2D7FE5348E1B147BCA15975FBA2307501464172A6@US01WEMBX2.internal.synopsys.com>
Date:   Tue, 27 Nov 2018 17:06:10 +0000
From:   Vineet Gupta <vineet.gupta1@...opsys.com>
To:     Eugeniy Paltsev <eugeniy.paltsev@...opsys.com>,
        "linux-arm-kernel@...ts.infradead.org" 
        <linux-arm-kernel@...ts.infradead.org>,
        "linux-snps-arc@...ts.infradead.org" 
        <linux-snps-arc@...ts.infradead.org>
CC:     "linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
        "peterz@...radead.org" <peterz@...radead.org>,
        "jolsa@...hat.com" <jolsa@...hat.com>,
        "acme@...nel.org" <acme@...nel.org>,
        Alexey Brodkin <alexey.brodkin@...opsys.com>,
        "namhyung@...nel.org" <namhyung@...nel.org>,
        "mark.rutland@....com" <mark.rutland@....com>,
        "will.deacon@....com" <will.deacon@....com>,
        "mingo@...hat.com" <mingo@...hat.com>,
        "alexander.shishkin@...ux.intel.com" 
        <alexander.shishkin@...ux.intel.com>
Subject: Re: 'branches' perf event mapping differs on ARC and ARM

On 11/27/18 6:36 AM, Eugeniy Paltsev wrote:
> Hi,
>
> While playing with perf tool on ARMv7 and ARCv2 processors and profiling the
> same application I got interesting results. Even if we got pretty
> similar total
> execution time and instructions number the number of branches on ARC is about
> three times more then on ARM.
>
> I dug into architecture
> specific perf sources and found that we map different
> HW counters into generic 'branches' event on ARC and ARM.
> - We use "ijmp" event on ARC which
> counts all jump and branch instructions (regardless
> of real execution flow - even if no real jump happens)

That doesn't seem correct IMO. A NOT taken conditional branch doesn't change
control flow, so semantically doesn't qualify as a branch.
On ARC, the generic branches event should be mapped to "actually taken branches"
condition i.e.  ijmptak


> - We use "pc_write_retired" event on ARM
> which counts only taken branches (Instruction
> architecturally executed, condition check pass - software change of the PC)

That seems correct.

> I guess counting all jump and branch instructions is correct because we use
> 'branches' event value to calculate relative value of 'branch-misses' using
>
> following formula:
> ----------------------------8----------------------------
> branch-misses-ration = 'branch-misses' / 'branches' * 100.0
> ----------------
> ------------8----------------------------
> And using only taken branches here is incorrect IMHO.

Why ? branch-misses is a CPU specific micro-arch state where the a changed control
flow was NOT predicted. If an implementation mispredicts NOT taken branches, those
should actually get counted and be fed to hardware folks to improve the micro-arch.


>  So I guess we should
> map 'br_immed_retired' instead of
> "pc_write_retired" into generic 'branches'
> event on ARM.