All of lore.kernel.org
 help / color / mirror / Atom feed
From: Andrea Parri <parri.andrea@gmail.com>
To: Guo Ren <guoren@kernel.org>
Cc: "Björn Töpel" <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>
Subject: Re: [PATCH] riscv: kprobe: Optimize kprobe with accurate atomicity
Date: Tue, 31 Jan 2023 11:56:59 +0100	[thread overview]
Message-ID: <Y9jz+zUDebQ4VLlF@andrea> (raw)
In-Reply-To: <CAJF2gTTaartwjVdmtmsm1FqmYVuAq5_nGYU5zc6nkdTtCm200A@mail.gmail.com>

> > 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-"

  Andrea

_______________________________________________
linux-riscv mailing list
linux-riscv@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-riscv

WARNING: multiple messages have this Message-ID (diff)
From: Andrea Parri <parri.andrea@gmail.com>
To: Guo Ren <guoren@kernel.org>
Cc: "Björn Töpel" <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>
Subject: Re: [PATCH] riscv: kprobe: Optimize kprobe with accurate atomicity
Date: Tue, 31 Jan 2023 11:56:59 +0100	[thread overview]
Message-ID: <Y9jz+zUDebQ4VLlF@andrea> (raw)
In-Reply-To: <CAJF2gTTaartwjVdmtmsm1FqmYVuAq5_nGYU5zc6nkdTtCm200A@mail.gmail.com>

> > 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-"

  Andrea

  reply	other threads:[~2023-01-31 10:57 UTC|newest]

Thread overview: 54+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-01-26 16:15 [PATCH] riscv: kprobe: Optimize kprobe with accurate atomicity guoren
2023-01-26 16:15 ` guoren
2023-01-28  3:52 ` liaochang (A)
2023-01-28  3:52   ` liaochang (A)
2023-01-28  4:45   ` Guo Ren
2023-01-28  4:45     ` Guo Ren
2023-01-30 15:28     ` Björn Töpel
2023-01-30 15:28       ` Björn Töpel
2023-01-30 15:49       ` Mark Rutland
2023-01-30 15:49         ` Mark Rutland
2023-01-30 16:56         ` Björn Töpel
2023-01-30 16:56           ` Björn Töpel
2023-01-31  1:48         ` Guo Ren
2023-01-31  1:48           ` Guo Ren
2023-01-31  7:12           ` Björn Töpel
2023-01-31  7:12             ` Björn Töpel
2023-01-31  8:30             ` Guo Ren
2023-01-31  8:30               ` Guo Ren
2023-01-31 10:33           ` Mark Rutland
2023-01-31 10:33             ` Mark Rutland
2023-02-16 15:23             ` Masami Hiramatsu
2023-02-16 15:23               ` Masami Hiramatsu
2023-02-20 10:35               ` Mark Rutland
2023-02-20 10:35                 ` Mark Rutland
2023-02-21  1:30               ` Guo Ren
2023-02-21  1:30                 ` Guo Ren
2023-01-31  1:01       ` Guo Ren
2023-01-31  1:01         ` Guo Ren
2023-01-31  1:09         ` Guo Ren
2023-01-31  1:09           ` Guo Ren
2023-01-31  7:03           ` Björn Töpel
2023-01-31  7:03             ` Björn Töpel
2023-01-31  8:27             ` Guo Ren
2023-01-31  8:27               ` Guo Ren
2023-01-31  6:40         ` Björn Töpel
2023-01-31  6:40           ` Björn Töpel
2023-01-31  8:15           ` Guo Ren
2023-01-31  8:15             ` Guo Ren
2023-01-31 10:56             ` Andrea Parri [this message]
2023-01-31 10:56               ` Andrea Parri
2023-01-31 13:23               ` Guo Ren
2023-01-31 13:23                 ` Guo Ren
2023-02-16  7:54                 ` Björn Töpel
2023-02-16  7:54                   ` Björn Töpel
2023-02-17  2:28                   ` Guo Ren
2023-02-17  2:28                     ` Guo Ren
2023-02-17  7:32                     ` Björn Töpel
2023-02-17  7:32                       ` Björn Töpel
2023-02-21  1:56                       ` Guo Ren
2023-02-21  1:56                         ` Guo Ren
2023-02-16 15:42 ` Masami Hiramatsu
2023-02-16 15:42   ` Masami Hiramatsu
2023-02-21  0:57   ` Guo Ren
2023-02-21  0:57     ` Guo Ren

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=Y9jz+zUDebQ4VLlF@andrea \
    --to=parri.andrea@gmail.com \
    --cc=bjorn@kernel.org \
    --cc=conor.dooley@microchip.com \
    --cc=guoren@kernel.org \
    --cc=guoren@linux.alibaba.com \
    --cc=liaochang1@huawei.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-riscv@lists.infradead.org \
    --cc=mark.rutland@arm.com \
    --cc=mhiramat@kernel.org \
    --cc=palmer@dabbelt.com \
    --cc=paul.walmsley@sifive.com \
    --cc=penberg@kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body. 
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.