From: peterz@infradead.org
To: Nicholas Piggin <npiggin@gmail.com>
Cc: Alexey Kardashevskiy <aik@ozlabs.ru>,
linux-arch@vger.kernel.org, linux-kernel@vger.kernel.org,
linuxppc-dev@lists.ozlabs.org, Ingo Molnar <mingo@redhat.com>,
Will Deacon <will@kernel.org>
Subject: Re: [PATCH 1/2] lockdep: improve current->(hard|soft)irqs_enabled synchronisation with actual irq state
Date: Sun, 26 Jul 2020 13:59:44 +0200 [thread overview]
Message-ID: <20200726115944.GB119549@hirez.programming.kicks-ass.net> (raw)
In-Reply-To: <1595735694.b784cvipam.astroid@bobo.none>
On Sun, Jul 26, 2020 at 02:14:34PM +1000, Nicholas Piggin wrote:
> > Now, x86, and at least arm64 call nmi_enter() before
> > trace_hardirqs_off(), but AFAICT Power never did that, and that's part
> > of the problem. nmi_enter() does lockdep_off() and that _used_ to also
> > kill IRQ tracking.
>
> Power does do nmi_enter -- __perf_event_interrupt()
>
> nmi = perf_intr_is_nmi(regs);
> if (nmi)
> nmi_enter();
> else
> irq_enter();
That's _waaaay_ too late, you've done the trace_hardirqs_{off,on} in
arch/powerpc/kernel/exceptions-64e.S, you need to _first_ do nmi_enter()
and _then_ trace_hardirqs_off(), or rather, that's still broken, but
then we get into the details of entry ordering.
WARNING: multiple messages have this Message-ID (diff)
From: peterz@infradead.org
To: Nicholas Piggin <npiggin@gmail.com>
Cc: linux-arch@vger.kernel.org, Alexey Kardashevskiy <aik@ozlabs.ru>,
Will Deacon <will@kernel.org>,
linux-kernel@vger.kernel.org, Ingo Molnar <mingo@redhat.com>,
linuxppc-dev@lists.ozlabs.org
Subject: Re: [PATCH 1/2] lockdep: improve current->(hard|soft)irqs_enabled synchronisation with actual irq state
Date: Sun, 26 Jul 2020 13:59:44 +0200 [thread overview]
Message-ID: <20200726115944.GB119549@hirez.programming.kicks-ass.net> (raw)
In-Reply-To: <1595735694.b784cvipam.astroid@bobo.none>
On Sun, Jul 26, 2020 at 02:14:34PM +1000, Nicholas Piggin wrote:
> > Now, x86, and at least arm64 call nmi_enter() before
> > trace_hardirqs_off(), but AFAICT Power never did that, and that's part
> > of the problem. nmi_enter() does lockdep_off() and that _used_ to also
> > kill IRQ tracking.
>
> Power does do nmi_enter -- __perf_event_interrupt()
>
> nmi = perf_intr_is_nmi(regs);
> if (nmi)
> nmi_enter();
> else
> irq_enter();
That's _waaaay_ too late, you've done the trace_hardirqs_{off,on} in
arch/powerpc/kernel/exceptions-64e.S, you need to _first_ do nmi_enter()
and _then_ trace_hardirqs_off(), or rather, that's still broken, but
then we get into the details of entry ordering.
next prev parent reply other threads:[~2020-07-26 11:59 UTC|newest]
Thread overview: 66+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-07-23 10:56 [PATCH 1/2] lockdep: improve current->(hard|soft)irqs_enabled synchronisation with actual irq state Nicholas Piggin
2020-07-23 10:56 ` Nicholas Piggin
2020-07-23 10:56 ` [PATCH 2/2] lockdep: warn on redundant or incorrect irq state changes Nicholas Piggin
2020-07-23 10:56 ` Nicholas Piggin
2020-07-24 2:57 ` kernel test robot
2020-07-24 2:57 ` kernel test robot
2020-07-24 2:57 ` kernel test robot
2020-07-24 2:57 ` kernel test robot
2020-07-24 2:57 ` kernel test robot
2020-08-04 10:00 ` Alexey Kardashevskiy
2020-08-04 10:00 ` Alexey Kardashevskiy
2020-07-23 11:40 ` [PATCH 1/2] lockdep: improve current->(hard|soft)irqs_enabled synchronisation with actual irq state Peter Zijlstra
2020-07-23 11:40 ` Peter Zijlstra
2020-07-23 13:11 ` Nicholas Piggin
2020-07-23 13:11 ` Nicholas Piggin
2020-07-23 14:59 ` Peter Zijlstra
2020-07-23 14:59 ` Peter Zijlstra
2020-07-23 16:20 ` Nicholas Piggin
2020-07-23 16:20 ` Nicholas Piggin
2020-07-24 4:16 ` Alexey Kardashevskiy
2020-07-24 4:16 ` Alexey Kardashevskiy
2020-07-24 5:59 ` Nicholas Piggin
2020-07-24 5:59 ` Nicholas Piggin
2020-07-26 7:40 ` Alexey Kardashevskiy
2020-07-26 7:40 ` Alexey Kardashevskiy
2020-07-24 6:16 ` Athira Rajeev
2020-07-24 6:16 ` Athira Rajeev
2020-07-24 2:19 ` kernel test robot
2020-07-24 2:19 ` kernel test robot
2020-07-24 2:19 ` kernel test robot
2020-07-24 2:19 ` kernel test robot
2020-07-24 2:19 ` kernel test robot
2020-07-24 3:15 ` kernel test robot
2020-07-24 3:15 ` kernel test robot
2020-07-24 3:15 ` kernel test robot
2020-07-24 3:15 ` kernel test robot
2020-07-24 3:15 ` kernel test robot
2020-07-25 20:26 ` Peter Zijlstra
2020-07-25 20:26 ` Peter Zijlstra
2020-07-26 4:14 ` Nicholas Piggin
2020-07-26 4:14 ` Nicholas Piggin
2020-07-26 11:59 ` peterz [this message]
2020-07-26 11:59 ` peterz
2020-07-26 12:11 ` peterz
2020-07-26 12:11 ` peterz
2020-07-28 11:22 ` Nicholas Piggin
2020-07-28 11:22 ` Nicholas Piggin
2020-08-07 11:11 ` peterz
2020-08-07 11:11 ` peterz
2020-08-12 8:18 ` Nicholas Piggin
2020-08-12 8:18 ` Nicholas Piggin
2020-08-12 10:35 ` peterz
2020-08-12 10:35 ` peterz
2020-08-18 7:22 ` Nicholas Piggin
2020-08-18 7:22 ` Nicholas Piggin
2020-08-18 15:41 ` peterz
2020-08-18 15:41 ` peterz
2020-08-18 23:54 ` Nicholas Piggin
2020-08-18 23:54 ` Nicholas Piggin
2020-08-19 10:39 ` Alexey Kardashevskiy
2020-08-19 10:39 ` Alexey Kardashevskiy
2020-08-19 15:32 ` peterz
2020-08-19 15:32 ` peterz
2020-08-19 15:39 ` peterz
2020-08-19 15:39 ` peterz
2020-08-27 7:54 ` [tip: locking/core] lockdep: Only trace IRQ edges tip-bot2 for Nicholas Piggin
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=20200726115944.GB119549@hirez.programming.kicks-ass.net \
--to=peterz@infradead.org \
--cc=aik@ozlabs.ru \
--cc=linux-arch@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linuxppc-dev@lists.ozlabs.org \
--cc=mingo@redhat.com \
--cc=npiggin@gmail.com \
--cc=will@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.