From: Peter Zijlstra <peterz@infradead.org>
To: Thomas Gleixner <tglx@linutronix.de>
Cc: Andy Lutomirski <luto@kernel.org>,
Josh Poimboeuf <jpoimboe@redhat.com>,
LKML <linux-kernel@vger.kernel.org>, X86 ML <x86@kernel.org>,
Will Deacon <will@kernel.org>,
Paolo Bonzini <pbonzini@redhat.com>,
kvm list <kvm@vger.kernel.org>,
linux-arch <linux-arch@vger.kernel.org>,
Mike Rapoport <rppt@linux.ibm.com>,
Miroslav Benes <mbenes@suse.cz>
Subject: Re: [patch V2 07/17] x86/entry/64: Remove redundant interrupt disable
Date: Thu, 24 Oct 2019 23:21:05 +0200 [thread overview]
Message-ID: <20191024212105.GY4114@hirez.programming.kicks-ass.net> (raw)
In-Reply-To: <alpine.DEB.2.21.1910242032080.1783@nanos.tec.linutronix.de>
On Thu, Oct 24, 2019 at 10:52:59PM +0200, Thomas Gleixner wrote:
> is just undefined behaviour and I personally consider it to be a plain bug.
I concur.
> Just for the record: This results in running a resulting or even completely
> unrelated signal handler with interrupts disabled as well.
>
> Whatever we decide it is, leaving it completely inconsistent is not a
> solution at all. The options are:
>
> 1) Always do conditional tracing depending on the user_regs->eflags.IF
> state.
>
> 2) #1 + warn once when syscalls and exceptions (except NMI/MCE) happen
> and user_regs->eflags.IF is cleared.
>
> 3a) #2 + enforce signal handling to run with interrupts enabled.
>
> 3b) #2 + set regs->eflags.IF. So the state is always correct from the
> kernel POV. Of course that changes existing behaviour, but its
> changing undefined and inconsistent behaviour.
>
> 4) Let iopl(level) return -EPERM if level == 3.
>
> Yeah, I know it's not possible due to regressions (DPKD uses iopl(3)),
> but TBH that'd be the sanest option of all.
>
> Of course the infinite wisdom of hardware designers tied IN, INS, OUT,
> OUTS and CLI/STI together on IOPL so we cannot even distangle them in
> any way.
>
> The only way out would be to actually use a full 8K sized I/O bitmap,
> but that's a massive pain as it has to be copied on every context
> switch.
>
> Really pretty options to chose from ...
If 4 is out (and I'm afraid it might be), then I'm on record for liking
3b.
next prev parent reply other threads:[~2019-10-24 21:21 UTC|newest]
Thread overview: 122+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-10-23 12:27 [patch V2 00/17] entry: Provide generic implementation for host and guest entry/exit work Thomas Gleixner
2019-10-23 12:27 ` Thomas Gleixner
2019-10-23 12:27 ` [patch V2 01/17] x86/entry/32: Remove unused resume_userspace label Thomas Gleixner
2019-10-23 12:27 ` Thomas Gleixner
2019-10-23 13:43 ` Sean Christopherson
2019-10-23 13:43 ` Sean Christopherson
2019-11-06 15:26 ` Alexandre Chartre
2019-11-06 15:26 ` Alexandre Chartre
2019-10-23 12:27 ` [patch V2 02/17] x86/entry/64: Remove pointless jump in paranoid_exit Thomas Gleixner
2019-10-23 12:27 ` Thomas Gleixner
2019-10-23 13:45 ` Sean Christopherson
2019-10-23 13:45 ` Sean Christopherson
2019-11-06 15:29 ` Alexandre Chartre
2019-11-06 15:29 ` Alexandre Chartre
2019-10-23 12:27 ` [patch V2 03/17] x86/traps: Remove pointless irq enable from do_spurious_interrupt_bug() Thomas Gleixner
2019-10-23 12:27 ` Thomas Gleixner
2019-10-23 13:52 ` Sean Christopherson
2019-10-23 13:52 ` Sean Christopherson
2019-10-23 21:31 ` Josh Poimboeuf
2019-10-23 21:31 ` Josh Poimboeuf
2019-10-23 22:35 ` Thomas Gleixner
2019-10-23 22:35 ` Thomas Gleixner
2019-10-23 22:49 ` Josh Poimboeuf
2019-10-23 22:49 ` Josh Poimboeuf
2019-10-23 23:18 ` Thomas Gleixner
2019-10-23 23:18 ` Thomas Gleixner
2019-11-06 15:33 ` Alexandre Chartre
2019-11-06 15:33 ` Alexandre Chartre
2019-10-23 12:27 ` [patch V2 04/17] x86/entry: Make DEBUG_ENTRY_ASSERT_IRQS_OFF available for 32bit Thomas Gleixner
2019-10-23 12:27 ` Thomas Gleixner
2019-10-23 14:16 ` Sean Christopherson
2019-10-23 14:16 ` Sean Christopherson
2019-11-06 15:50 ` Alexandre Chartre
2019-11-06 15:50 ` Alexandre Chartre
2019-10-23 12:27 ` [patch V2 05/17] x86/traps: Make interrupt enable/disable symmetric in C code Thomas Gleixner
2019-10-23 12:27 ` Thomas Gleixner
2019-10-23 14:16 ` Sean Christopherson
2019-10-23 14:16 ` Sean Christopherson
2019-10-23 22:01 ` Josh Poimboeuf
2019-10-23 22:01 ` Josh Poimboeuf
2019-10-23 23:23 ` Thomas Gleixner
2019-10-23 23:23 ` Thomas Gleixner
2019-11-06 16:19 ` Alexandre Chartre
2019-11-06 16:19 ` Alexandre Chartre
2019-10-23 12:27 ` [patch V2 06/17] x86/entry/32: Remove redundant interrupt disable Thomas Gleixner
2019-10-23 12:27 ` Thomas Gleixner
2019-10-23 14:17 ` Sean Christopherson
2019-10-23 14:17 ` Sean Christopherson
2019-11-08 10:41 ` Alexandre Chartre
2019-11-08 10:41 ` Alexandre Chartre
2019-10-23 12:27 ` [patch V2 07/17] x86/entry/64: " Thomas Gleixner
2019-10-23 12:27 ` Thomas Gleixner
2019-10-23 14:20 ` Sean Christopherson
2019-10-23 14:20 ` Sean Christopherson
2019-10-23 22:06 ` Josh Poimboeuf
2019-10-23 22:06 ` Josh Poimboeuf
2019-10-23 23:52 ` Thomas Gleixner
2019-10-23 23:52 ` Thomas Gleixner
2019-10-24 16:18 ` Andy Lutomirski
2019-10-24 16:18 ` Andy Lutomirski
2019-10-24 20:52 ` Thomas Gleixner
2019-10-24 20:52 ` Thomas Gleixner
2019-10-24 20:59 ` Thomas Gleixner
2019-10-24 20:59 ` Thomas Gleixner
2019-10-24 21:21 ` Peter Zijlstra [this message]
2019-10-24 21:21 ` Peter Zijlstra
2019-10-24 21:24 ` Andy Lutomirski
2019-10-24 21:24 ` Andy Lutomirski
2019-10-24 22:33 ` Thomas Gleixner
2019-10-24 22:33 ` Thomas Gleixner
2019-11-08 11:07 ` Alexandre Chartre
2019-11-08 11:07 ` Alexandre Chartre
2019-10-23 12:27 ` [patch V2 08/17] x86/entry: Move syscall irq tracing to C code Thomas Gleixner
2019-10-23 12:27 ` Thomas Gleixner
2019-10-23 21:30 ` Andy Lutomirski
2019-10-23 21:30 ` Andy Lutomirski
2019-10-23 21:35 ` Andy Lutomirski
2019-10-23 21:35 ` Andy Lutomirski
2019-10-23 23:31 ` Thomas Gleixner
2019-10-23 23:31 ` Thomas Gleixner
2019-10-23 23:16 ` Thomas Gleixner
2019-10-23 23:16 ` Thomas Gleixner
2019-10-24 16:24 ` Andy Lutomirski
2019-10-24 16:24 ` Andy Lutomirski
2019-10-24 17:40 ` Peter Zijlstra
2019-10-24 17:40 ` Peter Zijlstra
2019-10-24 20:54 ` Thomas Gleixner
2019-10-24 20:54 ` Thomas Gleixner
2019-10-23 12:27 ` [patch V2 09/17] x86/entry: Remove _TIF_NOHZ from _TIF_WORK_SYSCALL_ENTRY Thomas Gleixner
2019-10-23 12:27 ` Thomas Gleixner
2020-01-06 4:11 ` Frederic Weisbecker
2020-01-06 4:11 ` Frederic Weisbecker
2019-10-23 12:27 ` [patch V2 10/17] entry: Provide generic syscall entry functionality Thomas Gleixner
2019-10-23 12:27 ` Thomas Gleixner
2019-10-23 12:27 ` [patch V2 11/17] x86/entry: Use generic syscall entry function Thomas Gleixner
2019-10-23 12:27 ` Thomas Gleixner
2019-10-23 12:27 ` [patch V2 12/17] entry: Provide generic syscall exit function Thomas Gleixner
2019-10-23 12:27 ` Thomas Gleixner
2019-10-23 12:27 ` [patch V2 13/17] x86/entry: Use generic syscall exit functionality Thomas Gleixner
2019-10-23 12:27 ` Thomas Gleixner
2019-10-23 12:27 ` [patch V2 14/17] entry: Provide generic exit to usermode functionality Thomas Gleixner
2019-10-23 12:27 ` Thomas Gleixner
2019-10-23 21:34 ` Andy Lutomirski
2019-10-23 21:34 ` Andy Lutomirski
2019-10-23 23:20 ` Thomas Gleixner
2019-10-23 23:20 ` Thomas Gleixner
2019-10-23 12:27 ` [patch V2 15/17] x86/entry: Use generic exit to usermode Thomas Gleixner
2019-10-23 12:27 ` Thomas Gleixner
2019-10-23 12:27 ` [patch V2 16/17] kvm/workpending: Provide infrastructure for work before entering a guest Thomas Gleixner
2019-10-23 12:27 ` Thomas Gleixner
2019-10-23 14:55 ` Sean Christopherson
2019-10-23 14:55 ` Sean Christopherson
2019-10-23 12:27 ` [patch V2 17/17] x86/kvm: Use generic exit to guest work function Thomas Gleixner
2019-10-23 12:27 ` Thomas Gleixner
2019-10-23 14:48 ` Sean Christopherson
2019-10-23 14:48 ` Sean Christopherson
2019-10-23 14:37 ` [patch V2 00/17] entry: Provide generic implementation for host and guest entry/exit work Peter Zijlstra
2019-10-23 14:37 ` Peter Zijlstra
2019-10-23 21:20 ` Josh Poimboeuf
2019-10-23 21:20 ` Josh Poimboeuf
2019-10-29 11:28 ` Will Deacon
2019-10-29 11:28 ` Will Deacon
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=20191024212105.GY4114@hirez.programming.kicks-ass.net \
--to=peterz@infradead.org \
--cc=jpoimboe@redhat.com \
--cc=kvm@vger.kernel.org \
--cc=linux-arch@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=luto@kernel.org \
--cc=mbenes@suse.cz \
--cc=pbonzini@redhat.com \
--cc=rppt@linux.ibm.com \
--cc=tglx@linutronix.de \
--cc=will@kernel.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox