MIME-Version: 1.0
References: <20230126161559.1467374-1-guoren@kernel.org> <0abbbdd4-6b85-9659-03ee-97c56a5b77c1@huawei.com>
 <CAJF2gTS0s4X_uwLaEeSqKAyRmxCR2vxRuHhz7-SP2w4bBqzr+Q@mail.gmail.com>
 <87r0vc9h4g.fsf@all.your.base.are.belong.to.us> <CAJF2gTQZWO8Ubi60nHn-J-8czqBnsp1Kdyoim3uLNkjbYd-H8Q@mail.gmail.com>
 <87ilgntdef.fsf@all.your.base.are.belong.to.us> <CAJF2gTTaartwjVdmtmsm1FqmYVuAq5_nGYU5zc6nkdTtCm200A@mail.gmail.com>
 <Y9jz+zUDebQ4VLlF@andrea>
In-Reply-To: <Y9jz+zUDebQ4VLlF@andrea>
From:   Guo Ren <guoren@kernel.org>
Date:   Tue, 31 Jan 2023 21:23:59 +0800
Message-ID: <CAJF2gTQsRcUpMk8nvFkEsz_fpVV+v6tpUDcPzaNjqfj+i_VvXA@mail.gmail.com>
Subject: Re: [PATCH] riscv: kprobe: Optimize kprobe with accurate atomicity
To:     Andrea Parri <parri.andrea@gmail.com>
Cc:     =?UTF-8?B?QmrDtnJuIFTDtnBlbA==?= <bjorn@kernel.org>,
        "liaochang (A)" <liaochang1@huawei.com>, palmer@dabbelt.com,
        paul.walmsley@sifive.com, mhiramat@kernel.org,
        conor.dooley@microchip.com, penberg@kernel.org,
        mark.rutland@arm.com, linux-riscv@lists.infradead.org,
        linux-kernel@vger.kernel.org, Guo Ren <guoren@linux.alibaba.com>
Content-Type: text/plain; charset="UTF-8"
Precedence: bulk

On Tue, Jan 31, 2023 at 6:57 PM Andrea Parri <parri.andrea@gmail.com> wrote:
>
> > > It's the concurrent modification that I was referring to (removing
> > > stop_machine()). You're saying "it'll always work", I'm saying "I'm not
> > > so sure". :-) E.g., writing c.ebreak on an 32b insn. Can you say that
> > Software must ensure write c.ebreak on the head of an 32b insn.
> >
> > That means IFU only see:
> >  - c.ebreak + broken/illegal insn.
> > or
> >  - origin insn
> >
> > Even in the worst case, such as IFU fetches instructions one by one:
> > If the IFU gets the origin insn, it will skip the broken/illegal insn.
> > If the IFU gets the c.ebreak + broken/illegal insn, then an ebreak
> > exception is raised.
> >
> > Because c.ebreak would raise an exception, I don't see any problem.
>
> That's the problem, this discussion is:
>
> Reviewer: "I'm not sure, that's not written in our spec"
> Submitter: "I said it, it's called -accurate atomicity-"
I really don't see any hardware that could break the atomicity of this
c.ebreak scenario:
 - c.ebreak on the head of 32b insn
 - ebreak on an aligned 32b insn

If IFU fetches with cacheline, all is atomicity.
If IFU fetches with 16bit one by one, the first c.ebreak would raise
an exception and skip the next broke/illegal instruction.
Even if IFU fetches without any sequence, the IDU must decode one by
one, right? The first half c.ebreak would protect and prevent the next
broke/illegal instruction. Speculative execution on broke/illegal
instruction won't cause any exceptions.

It's a common issue, not a specific ISA issue.
32b instruction A -> 16b ebreak + 16b broken/illegal -> 32b
instruction A. It's safe to transform.

>
>   Andrea


-- 
Best Regards
 Guo Ren