linux-mips
[Top] [All Lists]

Re: ptrace question

To: Harald Krapfenbauer <krapfenbauer@ict.tuwien.ac.at>
Subject: Re: ptrace question
From: Ralf Baechle <ralf@linux-mips.org>
Date: Mon, 14 Jul 2008 12:43:42 +0100
Cc: "linux-mips@linux-mips.org" <linux-mips@linux-mips.org>
In-reply-to: <487B3242.60202@ict.tuwien.ac.at>
Original-recipient: rfc822;linux-mips@linux-mips.org
References: <487B3242.60202@ict.tuwien.ac.at>
Sender: linux-mips-bounce@linux-mips.org
User-agent: Mutt/1.5.18 (2008-05-17)
On Mon, Jul 14, 2008 at 01:02:26PM +0200, Harald Krapfenbauer wrote:

> Hello,
> 
> If I write memory (maybe with instructions) of a traced application with
> the ptrace() call, are the caches invalidated automatically, i.e. can I
> assume that the processor uses the newly written values after continuing?

ptrace semantics requires PTRACE_POKETEXT to ensure I-cache coherency and
consistency.

  Ralf

<Prev in Thread] Current Thread [Next in Thread>
  • ptrace question, Harald Krapfenbauer
    • Re: ptrace question, Ralf Baechle <=