[Top] [All Lists]

Re: [PATCH v5 04/12] MIPS: add support for hardware performance

To: David Daney <>
Subject: Re: [PATCH v5 04/12] MIPS: add support for hardware performance events (skeleton)
From: Deng-Cheng Zhu <>
Date: Sat, 29 May 2010 11:08:41 +0800
Dkim-signature: v=1; a=rsa-sha256; c=relaxed/relaxed;; s=gamma; h=domainkey-signature:mime-version:received:received:in-reply-to :references:date:message-id:subject:from:to:cc:content-type; bh=sh4cOLPVIToxBK+JO5MW4rJeqGcIRTInUaLsNwJ2PUw=; b=WclXvG23/mRd27hEy2hw+bIGy5Citku20QtU6bXsUvcOtCMHLtvSG2RJ557f45Ws0e ost/abZoIX1Vt/Gqr1VBxpn2Eoe8bgENIbR+y3hqX+QrrgxeFMft2SuSQaZsX7wEIJx5 JZ0UNNCQMdTsZHxbYgrWu2LzSbhNGgt1CST5E=
Domainkey-signature: a=rsa-sha1; c=nofws;; s=gamma; h=mime-version:in-reply-to:references:date:message-id:subject:from:to :cc:content-type; b=xexOGNQG7cRsFFS8NZJ+alIDj5+KdNF70d4wN3eMURGisM5vM43NAuE8wHAhd0sFuK U7Nl+GjO8R+z5o6c+lyh9PP0VYM6aE0+++WymBrsVcMenCZ+JJ8IO4X9vw19lqUfBJo0 BrJOxy9pv/8PYltM8YIulZUVD/+E9o9BremRE=
In-reply-to: <>
Original-recipient: rfc822;
References: <> <> <>
2010/5/28 David Daney <>:
> This depends on not consistent with the #if conditions in [01/12] for pmu.h.
>  They should be I think.
[DC]: It's a subset. If the code passes the test on other CPUs (such as
CPU_SB1), we can add them here.

> Probably removing the tests from pmu.h and encoding them here is better.
[DC]: According to my comments for [1/12], how about keeping them untouched
for now?

> IANAL, but who holds the copyright?  You or MTI ?
[DC]: OK. Will change like this:
Copyright (C) 2010 MIPS Technologies, Inc.
Author: Deng-Cheng Zhu

> This shadows the declaration in asm/time.h.  Declare it in exactly one place
> please.
[DC]: OK.

> Same thing about the copyright.
[DC]: OK.

> Not quite true.  They use the high bit, that can be either 31 or 63
> depending on the width of the counters.
[DC]: OK. Will change to consider 64-bit counters.

> Counters can be 64-bits wide, unsigned int is only 32-bits wide.
[DC]: OK.


<Prev in Thread] Current Thread [Next in Thread>