public inbox for gcc-bugs@sourceware.org
help / color / mirror / Atom feed
From: "jefflexu at linux dot alibaba.com" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug tree-optimization/102714] A volatile-related problem cased by ipa inline pass
Date: Wed, 13 Oct 2021 02:11:02 +0000	[thread overview]
Message-ID: <bug-102714-4-I6LlbyTU6Q@http.gcc.gnu.org/bugzilla/> (raw)
In-Reply-To: <bug-102714-4@http.gcc.gnu.org/bugzilla/>

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=102714

--- Comment #1 from Jeffle Xu <jefflexu at linux dot alibaba.com> ---
Some more detailed information about the effect to the application:

Linux kernel relies 'volatile' to do synchronization. Let's say, there are two
processes accessing one memory, one of them will write the memory, while the
other will read the memory (through 'volatile') in a loop. That is, these two
processes will synchronize with each other with this shared memory.

With this bug, the process reading the memory may always read the old value
(cached in the register) rather than get the new value (from memory), and thus
will get stuck in the infinite loop and finally causes soft lockup.

  reply	other threads:[~2021-10-13  2:11 UTC|newest]

Thread overview: 15+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-10-12 17:17 [Bug tree-optimization/102714] New: " duan.db at linux dot alibaba.com
2021-10-13  2:11 ` jefflexu at linux dot alibaba.com [this message]
2021-10-13  7:09 ` [Bug tree-optimization/102714] [11/12 Regression] " rguenth at gcc dot gnu.org
2021-10-13  9:26 ` cvs-commit at gcc dot gnu.org
2021-10-13  9:30 ` [Bug tree-optimization/102714] [11 " rguenth at gcc dot gnu.org
2021-10-13 10:43 ` duan.db at linux dot alibaba.com
2021-10-29  2:12 ` duan.db at linux dot alibaba.com
2021-10-29  6:55 ` rguenth at gcc dot gnu.org
2021-10-29  7:03 ` [Bug tree-optimization/102714] [10/11 " rguenth at gcc dot gnu.org
2021-10-29  8:06 ` duan.db at linux dot alibaba.com
2021-11-03 13:09 ` cvs-commit at gcc dot gnu.org
2021-11-05  1:53 ` [Bug tree-optimization/102714] [10 " duan.db at linux dot alibaba.com
2021-11-05  7:08 ` rguenther at suse dot de
2021-11-09 13:06 ` cvs-commit at gcc dot gnu.org
2021-11-09 13:06 ` rguenth at gcc dot gnu.org

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=bug-102714-4-I6LlbyTU6Q@http.gcc.gnu.org/bugzilla/ \
    --to=gcc-bugzilla@gcc.gnu.org \
    --cc=gcc-bugs@gcc.gnu.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).