Attachment 299586 Details for Bug 437970 – Upstream fix.

[patch] Upstream fix.

ppcdabr (text/plain), 3.89 KB, created by Jan Kratochvil on 2008-03-29 17:30:27 UTC

(hide)

Description:

Filename:

MIME Type:

Creator: Jan Kratochvil

Created: 2008-03-29 17:30:27 UTC

Size: 3.89 KB

patch

obsolete

>Return-Path: <michael@ozlabs.org>
>Received: from localhost
>	by host0.dyn.jankratochvil.net with IMAP (fetchmail-6.3.8)
>	for <jkratoch@localhost> (single-drop); Fri, 28 Mar 2008 09:12:12 +0100 (CET)
>Received: from pobox.devel.redhat.com ([unix socket])
>	 by pobox.devel.redhat.com (Cyrus v2.2.12-Invoca-RPM-2.2.12-8.1.RHEL4) with LMTPA;
>	 Fri, 28 Mar 2008 04:12:08 -0400
>X-Sieve: CMU Sieve 2.2
>Received: from int-mx1.corp.redhat.com (int-mx1.corp.redhat.com [172.16.52.254])
>	by pobox.devel.redhat.com (8.13.1/8.13.1) with ESMTP id m2S8C8Yd032302;
>	Fri, 28 Mar 2008 04:12:08 -0400
>Received: from mx3.redhat.com (mx3.redhat.com [172.16.48.32])
>	by int-mx1.corp.redhat.com (8.13.1/8.13.1) with ESMTP id m2S8C51O005453;
>	Fri, 28 Mar 2008 04:12:05 -0400
>Received: from ozlabs.org (ozlabs.org [203.10.76.45])
>	by mx3.redhat.com (8.13.8/8.13.8) with ESMTP id m2S8Bsxr020745;
>	Fri, 28 Mar 2008 04:11:55 -0400
>Received: by ozlabs.org (Postfix, from userid 1034)
>	id 7C499DDE9E; Fri, 28 Mar 2008 19:11:48 +1100 (EST)
>To: Paul Mackerras <paulus@samba.org>
>Cc: <jan.kratochvil@redhat.com>, <roland@redhat.com>,
>        Benjamin Herrenschmidt <benh@kernel.crashing.org>,
>        Anton Blanchard <anton@samba.org>
>Message-Id: <deeb6bcad042aec876919ef77d3b39b4b1c20784.1206691670.git.michael@ellerman.id.au>
>From: Michael Ellerman <michael@ellerman.id.au>
>Subject: [PATCH] Fix missed hardware breakpoints across multiple threads
>Date: Fri, 28 Mar 2008 19:11:48 +1100 (EST)
>X-RedHat-Spam-Score: -0.15 
>X-Scanned-By: MIMEDefang 2.58 on 172.16.52.254
>X-Scanned-By: MIMEDefang 2.63 on 172.16.48.32
>Status: RO
>Content-Length: 2356
>Lines: 70
>
>There is a bug in the powerpc DABR (data access breakpoint) handling,
>which can result in us missing breakpoints if several threads are trying
>to break on the same address.
>
>The circumstances are that do_page_fault() calls do_dabr(), this clears
>the DABR (sets it to 0) and sets up the signal which will report to
>userspace that the DABR was hit. The do_signal() code will restore the DABR
>value on the way out to userspace.
>
>If we reschedule before calling do_signal(), __switch_to() will check the
>cached DABR value and compare it to the new thread's value, if they match
>we don't set the DABR in hardware.
>
>So if two threads have the same DABR value, and we schedule from one to
>the other after taking the interrupt for the first thread hitting the DABR,
>the second thread will run without the DABR set in hardware.
>
>The cleanest fix is to move the cache update into set_dabr(), that way we
>can't forget to do it.
>
>Reported-by: Jan Kratochvil <jan.kratochvil@redhat.com>
>Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
>---
> arch/powerpc/kernel/process.c |   10 +++++-----
> 1 files changed, 5 insertions(+), 5 deletions(-)
>
>
>Paul, your call on if this is 25 or 26 material.
>
>
>diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
>index 59311ec..4ec6055 100644
>--- a/arch/powerpc/kernel/process.c
>+++ b/arch/powerpc/kernel/process.c
>@@ -241,8 +241,12 @@ void discard_lazy_cpu_state(void)
> }
> #endif /* CONFIG_SMP */
> 
>+static DEFINE_PER_CPU(unsigned long, current_dabr);
>+
> int set_dabr(unsigned long dabr)
> {
>+	__get_cpu_var(current_dabr) = dabr;
>+
> #ifdef CONFIG_PPC_MERGE		/* XXX for now */
> 	if (ppc_md.set_dabr)
> 		return ppc_md.set_dabr(dabr);
>@@ -259,8 +263,6 @@ int set_dabr(unsigned long dabr)
> DEFINE_PER_CPU(struct cpu_usage, cpu_usage_array);
> #endif
> 
>-static DEFINE_PER_CPU(unsigned long, current_dabr);
>-
> struct task_struct *__switch_to(struct task_struct *prev,
> 	struct task_struct *new)
> {
>@@ -325,10 +327,8 @@ struct task_struct *__switch_to(struct task_struct *prev,
> 
> #endif /* CONFIG_SMP */
> 
>-	if (unlikely(__get_cpu_var(current_dabr) != new->thread.dabr)) {
>+	if (unlikely(__get_cpu_var(current_dabr) != new->thread.dabr))
> 		set_dabr(new->thread.dabr);
>-		__get_cpu_var(current_dabr) = new->thread.dabr;
>-	}
> 
> 	new_thread = &new->thread;
> 	old_thread = &current->thread;
>-- 
>1.5.2.rc1.1884.g59b20
>

Actions: View | Diff

Attachments on bug 437970: 299586