From: Thomas Gleixner <tglx@kernel.org>
To: Peter Zijlstra <peterz@infradead.org>
Cc: Binbin Wu <binbin.wu@linux.intel.com>,
"Verma, Vishal L" <vishal.l.verma@intel.com>,
"kvm@vger.kernel.org" <kvm@vger.kernel.org>,
"Edgecombe, Rick P" <rick.p.edgecombe@intel.com>,
"Wu, Binbin" <binbin.wu@intel.com>,
"x86@kernel.org" <x86@kernel.org>
Subject: Re: CPU Lockups in KVM with deferred hrtimer rearming
Date: Tue, 21 Apr 2026 18:30:43 +0200 [thread overview]
Message-ID: <87jyu0b7ik.ffs@tglx> (raw)
In-Reply-To: <20260421113212.GI3126523@noisy.programming.kicks-ass.net>
On Tue, Apr 21 2026 at 13:32, Peter Zijlstra wrote:
> On Tue, Apr 21, 2026 at 01:18:58PM +0200, Peter Zijlstra wrote:
>> > /*
>> > + * This is sadly required due to KVM, which invokes regular
>> > + * interrupt handlers with interrupt disabled state in @regs.
>> > + */
>> > + instrumentation_begin();
>> > + hrtimer_rearm_deferred();
>> > + instrumentation_end();
>> > +
>> > + /*
>> > * IRQ flags state is correct already. Just tell RCU if it
>> > * was not watching on entry.
>> > */
>
> Ohhh, wait. What happens if you take a page-fault from NMI context? Does
> this then not result in trying to program the timer from NMI context?
Uuuurgh, yes.
next prev parent reply other threads:[~2026-04-21 16:30 UTC|newest]
Thread overview: 48+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-04-16 20:50 CPU Lockups in KVM with deferred hrtimer rearming Verma, Vishal L
2026-04-20 15:00 ` Thomas Gleixner
2026-04-20 15:22 ` Thomas Gleixner
2026-04-20 20:57 ` Verma, Vishal L
2026-04-20 22:19 ` Thomas Gleixner
2026-04-20 22:24 ` Verma, Vishal L
2026-04-21 6:29 ` Thomas Gleixner
2026-04-21 4:51 ` Binbin Wu
2026-04-21 7:39 ` Thomas Gleixner
2026-04-21 11:18 ` Peter Zijlstra
2026-04-21 11:32 ` Peter Zijlstra
2026-04-21 11:34 ` Peter Zijlstra
2026-04-21 11:49 ` Peter Zijlstra
2026-04-21 12:05 ` Peter Zijlstra
2026-04-21 13:19 ` Peter Zijlstra
2026-04-21 13:29 ` Peter Zijlstra
2026-04-21 16:36 ` Thomas Gleixner
2026-04-21 18:11 ` Verma, Vishal L
2026-04-21 17:11 ` Thomas Gleixner
2026-04-21 17:20 ` Jim Mattson
2026-04-21 18:29 ` Thomas Gleixner
2026-04-21 18:55 ` Sean Christopherson
2026-04-21 20:06 ` Peter Zijlstra
2026-04-21 20:46 ` Peter Zijlstra
2026-04-21 20:57 ` Sean Christopherson
2026-04-21 21:02 ` Peter Zijlstra
2026-04-21 21:42 ` Sean Christopherson
2026-04-22 6:55 ` Peter Zijlstra
2026-04-22 7:46 ` Peter Zijlstra
2026-04-22 14:08 ` Peter Zijlstra
2026-04-22 15:26 ` Sean Christopherson
2026-04-22 19:13 ` Verma, Vishal L
2026-04-22 22:57 ` Thomas Gleixner
2026-04-23 15:23 ` Peter Zijlstra
2026-04-22 13:47 ` Sean Christopherson
2026-04-21 20:39 ` Paolo Bonzini
2026-04-21 21:02 ` Sean Christopherson
2026-04-21 22:48 ` Thomas Gleixner
2026-04-21 23:15 ` Paolo Bonzini
2026-04-21 23:34 ` Jim Mattson
2026-04-21 23:37 ` Paolo Bonzini
2026-04-22 2:10 ` Thomas Gleixner
2026-04-21 21:49 ` Thomas Gleixner
2026-04-21 22:07 ` Sean Christopherson
2026-04-21 22:24 ` Paolo Bonzini
2026-04-21 19:18 ` Verma, Vishal L
2026-04-21 16:30 ` Thomas Gleixner [this message]
2026-04-21 16:11 ` Verma, Vishal L
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=87jyu0b7ik.ffs@tglx \
--to=tglx@kernel.org \
--cc=binbin.wu@intel.com \
--cc=binbin.wu@linux.intel.com \
--cc=kvm@vger.kernel.org \
--cc=peterz@infradead.org \
--cc=rick.p.edgecombe@intel.com \
--cc=vishal.l.verma@intel.com \
--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.