All of lore.kernel.org
 help / color / mirror / Atom feed
From: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
To: libc-alpha <libc-alpha@sourceware.org>
Cc: Florian Weimer <fweimer@redhat.com>,
	"carlos@redhat.com" <carlos@redhat.com>,
	Mark Rutland <mark.rutland@arm.com>,
	Peter Zijlstra <peterz@infradead.org>,
	linux-kernel <linux-kernel@vger.kernel.org>,
	x86@kernel.org, paulmck <paulmck@kernel.org>,
	Michael Jeanson <mjeanson@efficios.com>
Subject: Prevent inconsistent CPU state after sequence of dlclose/dlopen
Date: Fri, 10 Jan 2025 10:55:36 -0500	[thread overview]
Message-ID: <c606fd39-e835-44a6-a9be-9c6fab3c48fd@efficios.com> (raw)

Hi,

I was discussing with Mark Rutland recently, and he pointed out that a
sequence of dlclose/dlopen mapping new code at the same addresses in
multithreaded environments is an issue on ARM, and possibly on Intel/AMD
with the newer TLB broadcast maintenance.

I maintain the membarrier(2) system call, which provides a
MEMBARRIER_CMD_PRIVATE_EXPEDITED_SYNC_CORE command for this
purpose. It's been there since Linux 4.16. It can be configured
out (CONFIG_MEMBARRIER=n), but it's enabled by default.

Calling this after dlclose() in glibc would prevent this issue.

Is it handled in some other way, or should we open a bugzilla
entry to track this ?

Thanks,

Mathieu

-- 
Mathieu Desnoyers
EfficiOS Inc.
https://www.efficios.com

             reply	other threads:[~2025-01-10 15:55 UTC|newest]

Thread overview: 18+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-01-10 15:55 Mathieu Desnoyers [this message]
2025-01-10 16:47 ` Prevent inconsistent CPU state after sequence of dlclose/dlopen Adhemerval Zanella Netto
2025-01-15 20:16   ` Mathieu Desnoyers
2025-01-10 16:54 ` Peter Zijlstra
2025-01-10 17:02   ` Mathieu Desnoyers
2025-01-10 17:10     ` Florian Weimer
2025-01-10 17:14       ` Adhemerval Zanella Netto
2025-01-10 17:15       ` Mathieu Desnoyers
2025-01-10 17:24         ` Adhemerval Zanella Netto
2025-01-10 17:35           ` Mathieu Desnoyers
2025-01-10 17:46         ` Florian Weimer
2025-01-10 19:16           ` Mathieu Desnoyers
2025-01-10 17:11     ` Peter Zijlstra
2025-01-10 18:41       ` Mark Rutland
2025-01-10 17:12     ` Adhemerval Zanella Netto
2025-01-10 17:04 ` Florian Weimer
2025-01-10 17:13   ` Mathieu Desnoyers
2025-01-10 18:33     ` Paul E. McKenney

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=c606fd39-e835-44a6-a9be-9c6fab3c48fd@efficios.com \
    --to=mathieu.desnoyers@efficios.com \
    --cc=carlos@redhat.com \
    --cc=fweimer@redhat.com \
    --cc=libc-alpha@sourceware.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mark.rutland@arm.com \
    --cc=mjeanson@efficios.com \
    --cc=paulmck@kernel.org \
    --cc=peterz@infradead.org \
    --cc=x86@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.